From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 21 Oct 2010 19:39:53 +0000 (-0700)
Subject: Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw
X-Git-Tag: v2.6.37-rc1~220
X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?p=pandora-kernel.git;a=commitdiff_plain;h=f6f0a6d6a7258eff41fd202fc70df18271a2de79;hp=33027af637da3f69bd17488cc3e68493c9052a7d

Merge git://git./linux/kernel/git/steve/gfs2-2.6-nmw

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw: (22 commits)
  GFS2: fixed typo
  GFS2: Fix type mapping for demote_rq interface
  GFS2 fatal: filesystem consistency error on rename
  GFS2: Improve journal allocation via sysfs
  GFS2: Add "norecovery" mount option as a synonym for "spectator"
  GFS2: Fix spectator umount issue
  GFS2: Fix compiler warning from previous patch
  GFS2: reserve more blocks for transactions
  GFS2: Fix journal check for spectator mounts
  GFS2: Remove upgrade mount option
  GFS2: Remove localcaching mount option
  GFS2: Remove ignore_local_fs mount argument
  GFS2: Make . and .. qstrs constant
  GFS2: Use new workqueue scheme
  GFS2: Update handling of DLM return codes to match reality
  GFS2: Don't enforce min hold time when two demotes occur in rapid succession
  GFS2: Fix whitespace in previous patch
  GFS2: fallocate support
  GFS2: Add a bug trap in allocation code
  GFS2: No longer experimental
  ...
---

diff --git a/CREDITS b/CREDITS
index 72b487869788..41d8e63d5165 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3554,12 +3554,12 @@ E: cvance@nai.com
 D: portions of the Linux Security Module (LSM) framework and security modules
 
 N: Petr Vandrovec
-E: vandrove@vc.cvut.cz
+E: petr@vandrovec.name
 D: Small contributions to ncpfs
 D: Matrox framebuffer driver
-S: Chudenicka 8
-S: 10200 Prague 10, Hostivar
-S: Czech Republic
+S: 21513 Conradia Ct
+S: Cupertino, CA 95014
+S: USA
 
 N: Thibaut Varene
 E: T-Bone@parisc-linux.org
diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt
index 2df71861e578..d9271e74e488 100644
--- a/Documentation/networking/e1000.txt
+++ b/Documentation/networking/e1000.txt
@@ -1,82 +1,35 @@
 Linux* Base Driver for the Intel(R) PRO/1000 Family of Adapters
 ===============================================================
 
-September 26, 2006
-
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
 
 Contents
 ========
 
-- In This Release
 - Identifying Your Adapter
-- Building and Installation
 - Command Line Parameters
 - Speed and Duplex Configuration
 - Additional Configurations
-- Known Issues
 - Support
 
-
-In This Release
-===============
-
-This file describes the Linux* Base Driver for the Intel(R) PRO/1000 Family
-of Adapters.  This driver includes support for Itanium(R)2-based systems.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel PRO/1000 adapter. All hardware requirements listed
-apply to use with Linux.
-
-The following features are now available in supported kernels:
- - Native VLANs
- - Channel Bonding (teaming)
- - SNMP
-
-Channel Bonding documentation can be found in the Linux kernel source:
-/Documentation/networking/bonding.txt
-
-The driver information previously displayed in the /proc filesystem is not
-supported in this release.  Alternatively, you can use ethtool (version 1.6
-or later), lspci, and ifconfig to obtain the same information.
-
-Instructions on updating ethtool can be found in the section "Additional
-Configurations" later in this document.
-
-NOTE: The Intel(R) 82562v 10/100 Network Connection only provides 10/100
-support.
-
-
 Identifying Your Adapter
 ========================
 
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
 
-    http://support.intel.com/support/network/adapter/pro100/21397.htm
+    http://support.intel.com/support/go/network/adapter/idguide.htm
 
 For the latest Intel network drivers for Linux, refer to the following
 website.  In the search field, enter your adapter name or type, or use the
 networking link on the left to search for your adapter:
 
-    http://downloadfinder.intel.com/scripts-df/support_intel.asp
-
+    http://support.intel.com/support/go/network/adapter/home.htm
 
 Command Line Parameters
 =======================
 
-If the driver is built as a module, the  following optional parameters
-are used by entering them on the command line with the modprobe command
-using this syntax:
-
-     modprobe e1000 [<option>=<VAL1>,<VAL2>,...]
-
-For example, with two PRO/1000 PCI adapters, entering:
-
-     modprobe e1000 TxDescriptors=80,128
-
-loads the e1000 driver with 80 TX descriptors for the first adapter and
-128 TX descriptors for the second adapter.
-
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
@@ -89,10 +42,6 @@ NOTES:  For more information about the AutoNeg, Duplex, and Speed
         parameters, see the application note at:
         http://www.intel.com/design/network/applnots/ap450.htm
 
-        A descriptor describes a data buffer and attributes related to
-        the data buffer.  This information is accessed by the hardware.
-
-
 AutoNeg
 -------
 (Supported only on adapters with copper connections)
@@ -106,7 +55,6 @@ Duplex parameters must not be specified.
 NOTE:  Refer to the Speed and Duplex section of this readme for more
        information on the AutoNeg parameter.
 
-
 Duplex
 ------
 (Supported only on adapters with copper connections)
@@ -119,7 +67,6 @@ set to auto-negotiate, the board auto-detects the correct duplex.  If the
 link partner is forced (either full or half), Duplex defaults to half-
 duplex.
 
-
 FlowControl
 -----------
 Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
@@ -128,16 +75,16 @@ Default Value: Reads flow control settings from the EEPROM
 This parameter controls the automatic generation(Tx) and response(Rx)
 to Ethernet PAUSE frames.
 
-
 InterruptThrottleRate
 ---------------------
 (not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-Valid Range:   0,1,3,100-100000 (0=off, 1=dynamic, 3=dynamic conservative)
+Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+                                   4=simplified balancing)
 Default Value: 3
 
 The driver can limit the amount of interrupts per second that the adapter
-will generate for incoming packets. It does this by writing a value to the 
-adapter that is based on the maximum amount of interrupts that the adapter 
+will generate for incoming packets. It does this by writing a value to the
+adapter that is based on the maximum amount of interrupts that the adapter
 will generate per second.
 
 Setting InterruptThrottleRate to a value greater or equal to 100
@@ -146,37 +93,43 @@ per second, even if more packets have come in. This reduces interrupt
 load on the system and can lower CPU utilization under heavy load,
 but will increase latency as packets are not processed as quickly.
 
-The default behaviour of the driver previously assumed a static 
-InterruptThrottleRate value of 8000, providing a good fallback value for 
-all traffic types,but lacking in small packet performance and latency. 
-The hardware can handle many more small packets per second however, and 
+The default behaviour of the driver previously assumed a static
+InterruptThrottleRate value of 8000, providing a good fallback value for
+all traffic types,but lacking in small packet performance and latency.
+The hardware can handle many more small packets per second however, and
 for this reason an adaptive interrupt moderation algorithm was implemented.
 
 Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which
-it dynamically adjusts the InterruptThrottleRate value based on the traffic 
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
 that it receives. After determining the type of incoming traffic in the last
-timeframe, it will adjust the InterruptThrottleRate to an appropriate value 
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
 for that traffic.
 
 The algorithm classifies the incoming traffic every interval into
-classes.  Once the class is determined, the InterruptThrottleRate value is 
-adjusted to suit that traffic type the best. There are three classes defined: 
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
 "Bulk traffic", for large amounts of packets of normal size; "Low latency",
 for small amounts of traffic and/or a significant percentage of small
-packets; and "Lowest latency", for almost completely small packets or 
+packets; and "Lowest latency", for almost completely small packets or
 minimal traffic.
 
-In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 
-for traffic that falls in class "Bulk traffic". If traffic falls in the "Low 
-latency" or "Lowest latency" class, the InterruptThrottleRate is increased 
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
 stepwise to 20000. This default mode is suitable for most applications.
 
 For situations where low latency is vital such as cluster or
 grid computing, the algorithm can reduce latency even more when
 InterruptThrottleRate is set to mode 1. In this mode, which operates
-the same as mode 3, the InterruptThrottleRate will be increased stepwise to 
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
 70000 for traffic in class "Lowest latency".
 
+In simplified mode the interrupt rate is based on the ratio of Tx and
+Rx traffic.  If the bytes per second rate is approximately equal, the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
 Setting InterruptThrottleRate to 0 turns off any interrupt moderation
 and may improve small packet latency, but is generally not suitable
 for bulk throughput traffic.
@@ -212,8 +165,6 @@ NOTE:  When e1000 is loaded with default settings and multiple adapters
        be platform-specific.  If CPU utilization is not a concern, use
        RX_POLLING (NAPI) and default driver settings.
 
-
-
 RxDescriptors
 -------------
 Valid Range:   80-256 for 82542 and 82543-based adapters
@@ -225,15 +176,14 @@ by the driver.  Increasing this value allows the driver to buffer more
 incoming packets, at the expense of increased system memory utilization.
 
 Each descriptor is 16 bytes.  A receive buffer is also allocated for each
-descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending 
+descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
 on the MTU setting. The maximum MTU size is 16110.
 
-NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo 
-       Frames.  Depending on the available system resources, the request 
-       for a higher number of receive descriptors may be denied.  In this 
+NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo
+       Frames.  Depending on the available system resources, the request
+       for a higher number of receive descriptors may be denied.  In this
        case, use a lower number.
 
-
 RxIntDelay
 ----------
 Valid Range:   0-65535 (0=off)
@@ -254,7 +204,6 @@ CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
           restoring the network connection.  To eliminate the potential
           for the hang ensure that RxIntDelay is set to 0.
 
-
 RxAbsIntDelay
 -------------
 (This parameter is supported only on 82540, 82545 and later adapters.)
@@ -268,7 +217,6 @@ packet is received within the set amount of time.  Proper tuning,
 along with RxIntDelay, may improve traffic throughput in specific network
 conditions.
 
-
 Speed
 -----
 (This parameter is supported only on adapters with copper connections.)
@@ -280,7 +228,6 @@ Speed forces the line speed to the specified value in megabits per second
 partner is set to auto-negotiate, the board will auto-detect the correct
 speed.  Duplex should also be set when Speed is set to either 10 or 100.
 
-
 TxDescriptors
 -------------
 Valid Range:   80-256 for 82542 and 82543-based adapters
@@ -295,6 +242,36 @@ NOTE:  Depending on the available system resources, the request for a
        higher number of transmit descriptors may be denied.  In this case,
        use a lower number.
 
+TxDescriptorStep
+----------------
+Valid Range:    1 (use every Tx Descriptor)
+		4 (use every 4th Tx Descriptor)
+
+Default Value:  1 (use every Tx Descriptor)
+
+On certain non-Intel architectures, it has been observed that intense TX
+traffic bursts of short packets may result in an improper descriptor
+writeback. If this occurs, the driver will report a "TX Timeout" and reset
+the adapter, after which the transmit flow will restart, though data may
+have stalled for as much as 10 seconds before it resumes.
+
+The improper writeback does not occur on the first descriptor in a system
+memory cache-line, which is typically 32 bytes, or 4 descriptors long.
+
+Setting TxDescriptorStep to a value of 4 will ensure that all TX descriptors
+are aligned to the start of a system memory cache line, and so this problem
+will not occur.
+
+NOTES: Setting TxDescriptorStep to 4 effectively reduces the number of
+       TxDescriptors available for transmits to 1/4 of the normal allocation.
+       This has a possible negative performance impact, which may be
+       compensated for by allocating more descriptors using the TxDescriptors
+       module parameter.
+
+       There are other conditions which may result in "TX Timeout", which will
+       not be resolved by the use of the TxDescriptorStep parameter. As the
+       issue addressed by this parameter has never been observed on Intel
+       Architecture platforms, it should not be used on Intel platforms.
 
 TxIntDelay
 ----------
@@ -307,7 +284,6 @@ efficiency if properly tuned for specific network traffic.  If the
 system is reporting dropped transmits, this value may be set too high
 causing the driver to run out of available transmit descriptors.
 
-
 TxAbsIntDelay
 -------------
 (This parameter is supported only on 82540, 82545 and later adapters.)
@@ -330,6 +306,35 @@ Default Value: 1
 A value of '1' indicates that the driver should enable IP checksum
 offload for received packets (both UDP and TCP) to the adapter hardware.
 
+Copybreak
+---------
+Valid Range:   0-xxxxxxx (0=off)
+Default Value: 256
+Usage: insmod e1000.ko copybreak=128
+
+Driver copies all packets below or equaling this size to a fresh Rx
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+Valid Range: 0-1
+Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can turn off
+this parameter in supported chipsets.
+
+KumeranLockLoss
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial
+silicon releases of ICH8 systems.
 
 Speed and Duplex Configuration
 ==============================
@@ -385,40 +390,9 @@ If the link partner is forced to a specific speed and duplex, then this
 parameter should not be used.  Instead, use the Speed and Duplex parameters
 previously mentioned to force the adapter to the same speed and duplex.
 
-
 Additional Configurations
 =========================
 
-  Configuring the Driver on Different Distributions
-  -------------------------------------------------
-  Configuring a network driver to load properly when the system is started
-  is distribution dependent.  Typically, the configuration process involves
-  adding an alias line to /etc/modules.conf or /etc/modprobe.conf as well
-  as editing other system startup scripts and/or configuration files.  Many
-  popular Linux distributions ship with tools to make these changes for you.
-  To learn the proper way to configure a network device for your system,
-  refer to your distribution documentation.  If during this process you are
-  asked for the driver or module name, the name for the Linux Base Driver
-  for the Intel(R) PRO/1000 Family of Adapters is e1000.
-
-  As an example, if you install the e1000 driver for two PRO/1000 adapters
-  (eth0 and eth1) and set the speed and duplex to 10full and 100half, add
-  the following to modules.conf or or modprobe.conf:
-
-       alias eth0 e1000
-       alias eth1 e1000
-       options e1000 Speed=10,100 Duplex=2,1
-
-  Viewing Link Messages
-  ---------------------
-  Link messages will not be displayed to the console if the distribution is
-  restricting system messages.  In order to see network driver link messages
-  on your console, set dmesg to eight by entering the following:
-
-       dmesg -n 8
-
-  NOTE: This setting is not saved across reboots.
-
   Jumbo Frames
   ------------
   Jumbo Frames support is enabled by changing the MTU to a value larger than
@@ -437,9 +411,11 @@ Additional Configurations
    setting in a different location.
 
   Notes:
-
-  - To enable Jumbo Frames, increase the MTU size on the interface beyond
-    1500.
+  Degradation in throughput performance may be observed in some Jumbo frames
+  environments. If this is observed, increasing the application's socket buffer
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
 
   - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
     with the maximum Jumbo Frames size of 16128.
@@ -447,40 +423,11 @@ Additional Configurations
   - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
     loss of link.
 
-  - Some Intel gigabit adapters that support Jumbo Frames have a frame size
-    limit of 9238 bytes, with a corresponding MTU size limit of 9216 bytes.
-    The adapters with this limitation are based on the Intel(R) 82571EB,
-    82572EI, 82573L and 80003ES2LAN controller.  These correspond to the
-    following product names:
-     Intel(R) PRO/1000 PT Server Adapter
-     Intel(R) PRO/1000 PT Desktop Adapter
-     Intel(R) PRO/1000 PT Network Connection
-     Intel(R) PRO/1000 PT Dual Port Server Adapter
-     Intel(R) PRO/1000 PT Dual Port Network Connection
-     Intel(R) PRO/1000 PF Server Adapter
-     Intel(R) PRO/1000 PF Network Connection
-     Intel(R) PRO/1000 PF Dual Port Server Adapter
-     Intel(R) PRO/1000 PB Server Connection
-     Intel(R) PRO/1000 PL Network Connection
-     Intel(R) PRO/1000 EB Network Connection with I/O Acceleration
-     Intel(R) PRO/1000 EB Backplane Connection with I/O Acceleration
-     Intel(R) PRO/1000 PT Quad Port Server Adapter
-
   - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
     support Jumbo Frames. These correspond to the following product names:
      Intel(R) PRO/1000 Gigabit Server Adapter
      Intel(R) PRO/1000 PM Network Connection
 
-  - The following adapters do not support Jumbo Frames:
-     Intel(R) 82562V 10/100 Network Connection
-     Intel(R) 82566DM Gigabit Network Connection
-     Intel(R) 82566DC Gigabit Network Connection
-     Intel(R) 82566MM Gigabit Network Connection
-     Intel(R) 82566MC Gigabit Network Connection
-     Intel(R) 82562GT 10/100 Network Connection
-     Intel(R) 82562G 10/100 Network Connection
-
-
   Ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
@@ -490,142 +437,14 @@ Additional Configurations
   The latest release of ethtool can be found from
   http://sourceforge.net/projects/gkernel.
 
-  NOTE: Ethtool 1.6 only supports a limited set of ethtool options.  Support
-  for a more complete ethtool feature set can be enabled by upgrading
-  ethtool to ethtool-1.8.1.
-
   Enabling Wake on LAN* (WoL)
   ---------------------------
-  WoL is configured through the Ethtool* utility.  Ethtool is included with
-  all versions of Red Hat after Red Hat 7.2.  For other Linux distributions,
-  download and install Ethtool from the following website:
-  http://sourceforge.net/projects/gkernel.
-
-  For instructions on enabling WoL with Ethtool, refer to the website listed
-  above.
+  WoL is configured through the Ethtool* utility.
 
   WoL will be enabled on the system during the next shut down or reboot.
   For this driver version, in order to enable WoL, the e1000 driver must be
   loaded when shutting down or rebooting the system.
 
-  Wake On LAN is only supported on port A for the following devices:
-  Intel(R) PRO/1000 PT Dual Port Network Connection
-  Intel(R) PRO/1000 PT Dual Port Server Connection
-  Intel(R) PRO/1000 PT Dual Port Server Adapter
-  Intel(R) PRO/1000 PF Dual Port Server Adapter
-  Intel(R) PRO/1000 PT Quad Port Server Adapter
-
-  NAPI
-  ----
-  NAPI (Rx polling mode) is enabled in the e1000 driver.
-
-  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
-
-
-Known Issues
-============
-
-Dropped Receive Packets on Half-duplex 10/100 Networks
-------------------------------------------------------
-If you have an Intel PCI Express adapter running at 10mbps or 100mbps, half-
-duplex, you may observe occasional dropped receive packets.  There are no
-workarounds for this problem in this network configuration.  The network must
-be updated to operate in full-duplex, and/or 1000mbps only.
-
-Jumbo Frames System Requirement
--------------------------------
-Memory allocation failures have been observed on Linux systems with 64 MB
-of RAM or less that are running Jumbo Frames.  If you are using Jumbo
-Frames, your system may require more than the advertised minimum
-requirement of 64 MB of system memory.
-
-Performance Degradation with Jumbo Frames
------------------------------------------
-Degradation in throughput performance may be observed in some Jumbo frames
-environments.  If this is observed, increasing the application's socket
-buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values
-may help.  See the specific application manual and
-/usr/src/linux*/Documentation/
-networking/ip-sysctl.txt for more details.
-
-Jumbo Frames on Foundry BigIron 8000 switch
--------------------------------------------
-There is a known issue using Jumbo frames when connected to a Foundry
-BigIron 8000 switch.  This is a 3rd party limitation.  If you experience
-loss of packets, lower the MTU size.
-
-Allocating Rx Buffers when Using Jumbo Frames 
----------------------------------------------
-Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if 
-the available memory is heavily fragmented. This issue may be seen with PCI-X 
-adapters or with packet split disabled. This can be reduced or eliminated 
-by changing the amount of available memory for receive buffer allocation, by
-increasing /proc/sys/vm/min_free_kbytes. 
-
-Multiple Interfaces on Same Ethernet Broadcast Network
-------------------------------------------------------
-Due to the default ARP behavior on Linux, it is not possible to have
-one system on two IP networks in the same Ethernet broadcast domain
-(non-partitioned switch) behave as expected.  All Ethernet interfaces
-will respond to IP traffic for any IP address assigned to the system.
-This results in unbalanced receive traffic.
-
-If you have multiple interfaces in a server, either turn on ARP
-filtering by entering:
-
-    echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-(this only works if your kernel's version is higher than 2.4.5),
-
-NOTE: This setting is not saved across reboots.  The configuration
-change can be made permanent by adding the line:
-    net.ipv4.conf.all.arp_filter = 1
-to the file /etc/sysctl.conf
-
-      or,
-
-install the interfaces in separate broadcast domains (either in
-different switches or in a switch partitioned to VLANs).
-
-82541/82547 can't link or are slow to link with some link partners
------------------------------------------------------------------
-There is a known compatibility issue with 82541/82547 and some
-low-end switches where the link will not be established, or will
-be slow to establish.  In particular, these switches are known to
-be incompatible with 82541/82547:
-
-    Planex FXG-08TE
-    I-O Data ETG-SH8
-
-To workaround this issue, the driver can be compiled with an override
-of the PHY's master/slave setting.  Forcing master or forcing slave
-mode will improve time-to-link.
-
-    # make CFLAGS_EXTRA=-DE1000_MASTER_SLAVE=<n>
-
-Where <n> is:
-
-    0 = Hardware default
-    1 = Master mode
-    2 = Slave mode
-    3 = Auto master/slave
-
-Disable rx flow control with ethtool
-------------------------------------
-In order to disable receive flow control using ethtool, you must turn
-off auto-negotiation on the same command line.
-
-For example:
-
-   ethtool -A eth? autoneg off rx off
-
-Unplugging network cable while ethtool -p is running
-----------------------------------------------------
-In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging
-the network cable while ethtool -p is running will cause the system to
-become unresponsive to keyboard commands, except for control-alt-delete.
-Restarting the system appears to be the only remedy.
-
-
 Support
 =======
 
diff --git a/Documentation/networking/e1000e.txt b/Documentation/networking/e1000e.txt
new file mode 100644
index 000000000000..6aa048badf32
--- /dev/null
+++ b/Documentation/networking/e1000e.txt
@@ -0,0 +1,302 @@
+Linux* Driver for Intel(R) Network Connection
+===============================================================
+
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Additional Configurations
+- Support
+
+Identifying Your Adapter
+========================
+
+The e1000e driver supports all PCI Express Intel(R) Gigabit Network
+Connections, except those that are 82575, 82576 and 82580-based*.
+
+* NOTE: The Intel(R) PRO/1000 P Dual Port Server Adapter is supported by
+  the e1000 driver, not the e1000e driver due to the 82546 part being used
+  behind a PCI Express bridge.
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/go/network/adapter/idguide.htm
+
+For the latest Intel network drivers for Linux, refer to the following
+website.  In the search field, enter your adapter name or type, or use the
+networking link on the left to search for your adapter:
+
+    http://support.intel.com/support/go/network/adapter/home.htm
+
+Command Line Parameters
+=======================
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+NOTES:  For more information about the InterruptThrottleRate,
+        RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay
+        parameters, see the application note at:
+        http://www.intel.com/design/network/applnots/ap450.htm
+
+InterruptThrottleRate
+---------------------
+Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+                                   4=simplified balancing)
+Default Value: 3
+
+The driver can limit the amount of interrupts per second that the adapter
+will generate for incoming packets. It does this by writing a value to the
+adapter that is based on the maximum amount of interrupts that the adapter
+will generate per second.
+
+Setting InterruptThrottleRate to a value greater or equal to 100
+will program the adapter to send out a maximum of that many interrupts
+per second, even if more packets have come in. This reduces interrupt
+load on the system and can lower CPU utilization under heavy load,
+but will increase latency as packets are not processed as quickly.
+
+The driver has two adaptive modes (setting 1 or 3) in which
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
+that it receives. After determining the type of incoming traffic in the last
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
+for that traffic.
+
+The algorithm classifies the incoming traffic every interval into
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
+"Bulk traffic", for large amounts of packets of normal size; "Low latency",
+for small amounts of traffic and/or a significant percentage of small
+packets; and "Lowest latency", for almost completely small packets or
+minimal traffic.
+
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
+stepwise to 20000. This default mode is suitable for most applications.
+
+For situations where low latency is vital such as cluster or
+grid computing, the algorithm can reduce latency even more when
+InterruptThrottleRate is set to mode 1. In this mode, which operates
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
+70000 for traffic in class "Lowest latency".
+
+In simplified mode the interrupt rate is based on the ratio of Tx and
+Rx traffic.  If the bytes per second rate is approximately equal the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
+Setting InterruptThrottleRate to 0 turns off any interrupt moderation
+and may improve small packet latency, but is generally not suitable
+for bulk throughput traffic.
+
+NOTE:  InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+       RxAbsIntDelay parameters.  In other words, minimizing the receive
+       and/or transmit absolute delays does not force the controller to
+       generate more interrupts than what the Interrupt Throttle Rate
+       allows.
+
+NOTE:  When e1000e is loaded with default settings and multiple adapters
+       are in use simultaneously, the CPU utilization may increase non-
+       linearly.  In order to limit the CPU utilization without impacting
+       the overall throughput, we recommend that you load the driver as
+       follows:
+
+           modprobe e1000e InterruptThrottleRate=3000,3000,3000
+
+       This sets the InterruptThrottleRate to 3000 interrupts/sec for
+       the first, second, and third instances of the driver.  The range
+       of 2000 to 3000 interrupts per second works on a majority of
+       systems and is a good starting point, but the optimal value will
+       be platform-specific.  If CPU utilization is not a concern, use
+       RX_POLLING (NAPI) and default driver settings.
+
+RxIntDelay
+----------
+Valid Range:   0-65535 (0=off)
+Default Value: 0
+
+This value delays the generation of receive interrupts in units of 1.024
+microseconds.  Receive interrupt reduction can improve CPU efficiency if
+properly tuned for specific network traffic.  Increasing this value adds
+extra latency to frame reception and can end up decreasing the throughput
+of TCP traffic.  If the system is reporting dropped receives, this value
+may be set too high, causing the driver to run out of available receive
+descriptors.
+
+CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
+          hang (stop transmitting) under certain network conditions.  If
+          this occurs a NETDEV WATCHDOG message is logged in the system
+          event log.  In addition, the controller is automatically reset,
+          restoring the network connection.  To eliminate the potential
+          for the hang ensure that RxIntDelay is set to 0.
+
+RxAbsIntDelay
+-------------
+Valid Range:   0-65535 (0=off)
+Default Value: 8
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is received within the set amount of time.  Proper tuning,
+along with RxIntDelay, may improve traffic throughput in specific network
+conditions.
+
+TxIntDelay
+----------
+Valid Range:   0-65535 (0=off)
+Default Value: 8
+
+This value delays the generation of transmit interrupts in units of
+1.024 microseconds.  Transmit interrupt reduction can improve CPU
+efficiency if properly tuned for specific network traffic.  If the
+system is reporting dropped transmits, this value may be set too high
+causing the driver to run out of available transmit descriptors.
+
+TxAbsIntDelay
+-------------
+Valid Range:   0-65535 (0=off)
+Default Value: 32
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is sent on the wire within the set amount of time.  Proper tuning,
+along with TxIntDelay, may improve traffic throughput in specific
+network conditions.
+
+Copybreak
+---------
+Valid Range:   0-xxxxxxx (0=off)
+Default Value: 256
+
+Driver copies all packets below or equaling this size to a fresh Rx
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000e/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+Valid Range: 0-1
+Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can set this parameter
+in supported chipsets.
+
+KumeranLockLoss
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial
+silicon releases of ICH8 systems.
+
+IntMode
+-------
+Valid Range: 0-2 (0=legacy, 1=MSI, 2=MSI-X)
+Default Value: 2
+
+Allows changing the interrupt mode at module load time, without requiring a
+recompile. If the driver load fails to enable a specific interrupt mode, the
+driver will try other interrupt modes, from least to most compatible.  The
+interrupt order is MSI-X, MSI, Legacy.  If specifying MSI (IntMode=1)
+interrupts, only MSI and Legacy will be attempted.
+
+CrcStripping
+------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+Strip the CRC from received packets before sending up the network stack.  If
+you have a machine with a BMC enabled but cannot receive IPMI traffic after
+loading or enabling the driver, try disabling this feature.
+
+WriteProtectNVM
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+Set the hardware to ignore all write/erase cycles to the GbE region in the
+ICHx NVM (non-volatile memory).  This feature can be disabled by the
+WriteProtectNVM module parameter (enabled by default) only after a hardware
+reset, but the machine must be power cycled before trying to enable writes.
+
+Note: the kernel boot option iomem=relaxed may need to be set if the kernel
+config option CONFIG_STRICT_DEVMEM=y, if the root user wants to write the
+NVM from user space via ethtool.
+
+Additional Configurations
+=========================
+
+  Jumbo Frames
+  ------------
+  Jumbo Frames support is enabled by changing the MTU to a value larger than
+  the default of 1500.  Use the ifconfig command to increase the MTU size.
+  For example:
+
+       ifconfig eth<x> mtu 9000 up
+
+  This setting is not saved across reboots.
+
+  Notes:
+
+  - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
+    with the maximum Jumbo Frames size of 9234 bytes.
+
+  - Using Jumbo Frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
+
+  - Some adapters limit Jumbo Frames sized packets to a maximum of
+    4096 bytes and some adapters do not support Jumbo Frames.
+
+
+  Ethtool
+  -------
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  We
+  strongly recommend downloading the latest version of Ethtool at:
+
+  http://sourceforge.net/projects/gkernel.
+
+  Speed and Duplex
+  ----------------
+  Speed and Duplex are configured through the Ethtool* utility. For
+  instructions,  refer to the Ethtool man page.
+
+  Enabling Wake on LAN* (WoL)
+  ---------------------------
+  WoL is configured through the Ethtool* utility. For instructions on
+  enabling WoL with Ethtool, refer to the Ethtool man page.
+
+  WoL will be enabled on the system during the next shut down or reboot.
+  For this driver version, in order to enable WoL, the e1000e driver must be
+  loaded when shutting down or rebooting the system.
+
+  In most cases Wake On LAN is only supported on port A for multiple port
+  adapters. To verify if a port supports Wake on LAN run ethtool eth<X>.
+
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
old mode 100755
new mode 100644
index 19015de6725f..21dd5d15b6b4
--- a/Documentation/networking/ixgbevf.txt
+++ b/Documentation/networking/ixgbevf.txt
@@ -1,19 +1,16 @@
 Linux* Base Driver for Intel(R) Network Connection
 ==================================================
 
-November 24, 2009
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
 
 Contents
 ========
 
-- In This Release
 - Identifying Your Adapter
 - Known Issues/Troubleshooting
 - Support
 
-In This Release
-===============
-
 This file describes the ixgbevf Linux* Base Driver for Intel Network
 Connection.
 
@@ -33,7 +30,7 @@ Identifying Your Adapter
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
 
-    http://support.intel.com/support/network/sb/CS-008441.htm
+    http://support.intel.com/support/go/network/adapter/idguide.htm
 
 Known Issues/Troubleshooting
 ============================
@@ -57,34 +54,3 @@ or the Intel Wired Networking project hosted by Sourceforge at:
 If an issue is identified with the released source code on the supported
 kernel with a supported adapter, email the specific information related
 to the issue to e1000-devel@lists.sf.net
-
-License
-=======
-
-Intel 10 Gigabit Linux driver.
-Copyright(c) 1999 - 2009 Intel Corporation.
-
-This program is free software; you can redistribute it and/or modify it
-under the terms and conditions of the GNU General Public License,
-version 2, as published by the Free Software Foundation.
-
-This program is distributed in the hope it will be useful, but WITHOUT
-ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-more details.
-
-You should have received a copy of the GNU General Public License along with
-this program; if not, write to the Free Software Foundation, Inc.,
-51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
-The full GNU General Public License is included in this distribution in
-the file called "COPYING".
-
-Trademarks
-==========
-
-Intel, Itanium, and Pentium are trademarks or registered trademarks of
-Intel Corporation or its subsidiaries in the United States and other
-countries.
-
-* Other names and brands may be claimed as the property of others.
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
index ccd951fa94ee..cc96ee2666f2 100644
--- a/Documentation/vm/page-types.c
+++ b/Documentation/vm/page-types.c
@@ -478,7 +478,7 @@ static void prepare_hwpoison_fd(void)
 	}
 
 	if (opt_unpoison && !hwpoison_forget_fd) {
-		sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs);
+		sprintf(buf, "%s/unpoison-pfn", hwpoison_debug_fs);
 		hwpoison_forget_fd = checked_open(buf, O_WRONLY);
 	}
 }
diff --git a/MAINTAINERS b/MAINTAINERS
index 411b0d04f69b..3d4179fbc526 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -962,6 +962,23 @@ W:	http://www.fluff.org/ben/linux/
 S:	Maintained
 F:	arch/arm/mach-s3c6410/
 
+ARM/S5P ARM ARCHITECTURES
+M:	Kukjin Kim <kgene.kim@samsung.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-s5p*/
+
+ARM/SAMSUNG S5P SERIES FIMC SUPPORT
+M:	Kyungmin Park <kyungmin.park@samsung.com>
+M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
+L:	linux-arm-kernel@lists.infradead.org
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	arch/arm/plat-s5p/dev-fimc*
+F:	arch/arm/plat-samsung/include/plat/*fimc*
+F:	drivers/media/video/s5p-fimc/
+
 ARM/SHMOBILE ARM ARCHITECTURE
 M:	Paul Mundt <lethal@linux-sh.org>
 M:	Magnus Damm <magnus.damm@gmail.com>
@@ -1220,7 +1237,7 @@ F:	drivers/auxdisplay/
 F:	include/linux/cfag12864b.h
 
 AVR32 ARCHITECTURE
-M:	Haavard Skinnemoen <hskinnemoen@atmel.com>
+M:	Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
 W:	http://www.atmel.com/products/AVR32/
 W:	http://avr32linux.org/
 W:	http://avrfreaks.net/
@@ -1228,7 +1245,7 @@ S:	Supported
 F:	arch/avr32/
 
 AVR32/AT32AP MACHINE SUPPORT
-M:	Haavard Skinnemoen <hskinnemoen@atmel.com>
+M:	Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
 S:	Supported
 F:	arch/avr32/mach-at32ap/
 
@@ -1510,6 +1527,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 S:	Supported
 F:	Documentation/filesystems/ceph.txt
 F:	fs/ceph
+F:	net/ceph
+F:	include/linux/ceph
 
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 M:	David Vrabel <david.vrabel@csr.com>
@@ -2199,6 +2218,12 @@ W:	http://acpi4asus.sf.net
 S:	Maintained
 F:	drivers/platform/x86/eeepc-laptop.c
 
+EFIFB FRAMEBUFFER DRIVER
+L:	linux-fbdev@vger.kernel.org
+M:	Peter Jones <pjones@redhat.com>
+S:	Maintained
+F:	drivers/video/efifb.c
+
 EFS FILESYSTEM
 W:	http://aeschi.ch.eu.org/efs/
 S:	Orphan
@@ -2522,7 +2547,7 @@ S:	Supported
 F:	drivers/scsi/gdt*
 
 GENERIC GPIO I2C DRIVER
-M:	Haavard Skinnemoen <hskinnemoen@atmel.com>
+M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
 S:	Supported
 F:	drivers/i2c/busses/i2c-gpio.c
 F:	include/linux/i2c-gpio.h
@@ -2662,6 +2687,8 @@ M:	Guenter Roeck <guenter.roeck@ericsson.com>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
 T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
+T:	quilt kernel.org/pub/linux/kernel/people/groeck/linux-staging/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
 F:	Documentation/hwmon/
 F:	drivers/hwmon/
@@ -3048,16 +3075,27 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ixp2000/
 
-INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe)
+INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf)
 M:	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
 M:	Jesse Brandeburg <jesse.brandeburg@intel.com>
 M:	Bruce Allan <bruce.w.allan@intel.com>
-M:	Alex Duyck <alexander.h.duyck@intel.com>
+M:	Carolyn Wyborny <carolyn.wyborny@intel.com>
+M:	Don Skidmore <donald.c.skidmore@intel.com>
+M:	Greg Rose <gregory.v.rose@intel.com>
 M:	PJ Waskiewicz <peter.p.waskiewicz.jr@intel.com>
+M:	Alex Duyck <alexander.h.duyck@intel.com>
 M:	John Ronciak <john.ronciak@intel.com>
 L:	e1000-devel@lists.sourceforge.net
 W:	http://e1000.sourceforge.net/
 S:	Supported
+F:	Documentation/networking/e100.txt
+F:	Documentation/networking/e1000.txt
+F:	Documentation/networking/e1000e.txt
+F:	Documentation/networking/igb.txt
+F:	Documentation/networking/igbvf.txt
+F:	Documentation/networking/ixgb.txt
+F:	Documentation/networking/ixgbe.txt
+F:	Documentation/networking/ixgbevf.txt
 F:	drivers/net/e100.c
 F:	drivers/net/e1000/
 F:	drivers/net/e1000e/
@@ -3065,6 +3103,7 @@ F:	drivers/net/igb/
 F:	drivers/net/igbvf/
 F:	drivers/net/ixgb/
 F:	drivers/net/ixgbe/
+F:	drivers/net/ixgbevf/
 
 INTEL PRO/WIRELESS 2100 NETWORK CONNECTION SUPPORT
 L:	linux-wireless@vger.kernel.org
@@ -3125,7 +3164,7 @@ F:	drivers/net/ioc3-eth.c
 
 IOC3 SERIAL DRIVER
 M:	Pat Gefre <pfg@sgi.com>
-L:	linux-mips@linux-mips.org
+L:	linux-serial@vger.kernel.org
 S:	Maintained
 F:	drivers/serial/ioc3_serial.c
 
@@ -3773,9 +3812,8 @@ W:	http://www.syskonnect.com
 S:	Supported
 
 MATROX FRAMEBUFFER DRIVER
-M:	Petr Vandrovec <vandrove@vc.cvut.cz>
 L:	linux-fbdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/video/matrox/matroxfb_*
 F:	include/linux/matroxfb.h
 
@@ -3899,10 +3937,8 @@ F:	Documentation/serial/moxa-smartio
 F:	drivers/char/mxser.*
 
 MSI LAPTOP SUPPORT
-M:	Lennart Poettering <mzxreary@0pointer.de>
+M:	Lee, Chun-Yi <jlee@novell.com>
 L:	platform-driver-x86@vger.kernel.org
-W:	https://tango.0pointer.de/mailman/listinfo/s270-linux
-W:	http://0pointer.de/lennart/tchibo.html
 S:	Maintained
 F:	drivers/platform/x86/msi-laptop.c
 
@@ -3919,8 +3955,10 @@ S:	Supported
 F:	drivers/mfd/
 
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
-S:	Orphan
+M:	Chris Ball <cjb@laptop.org>
 L:	linux-mmc@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git
+S:	Maintained
 F:	drivers/mmc/
 F:	include/linux/mmc/
 
@@ -3942,7 +3980,7 @@ F:	drivers/char/isicom.c
 F:	include/linux/isicom.h
 
 MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
-M:	Felipe Balbi <felipe.balbi@nokia.com>
+M:	Felipe Balbi <balbi@ti.com>
 L:	linux-usb@vger.kernel.org
 T:	git git://gitorious.org/usb/usb.git
 S:	Maintained
@@ -3962,8 +4000,8 @@ S:	Maintained
 F:	drivers/net/natsemi.c
 
 NCP FILESYSTEM
-M:	Petr Vandrovec <vandrove@vc.cvut.cz>
-S:	Maintained
+M:	Petr Vandrovec <petr@vandrovec.name>
+S:	Odd Fixes
 F:	fs/ncpfs/
 
 NCR DUAL 700 SCSI DRIVER (MICROCHANNEL)
@@ -4240,7 +4278,7 @@ S:	Maintained
 F:	drivers/char/hw_random/omap-rng.c
 
 OMAP USB SUPPORT
-M:	Felipe Balbi <felipe.balbi@nokia.com>
+M:	Felipe Balbi <balbi@ti.com>
 M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
@@ -4769,6 +4807,15 @@ F:	fs/qnx4/
 F:	include/linux/qnx4_fs.h
 F:	include/linux/qnxtypes.h
 
+RADOS BLOCK DEVICE (RBD)
+F:	include/linux/qnxtypes.h
+M:	Yehuda Sadeh <yehuda@hq.newdream.net>
+M:	Sage Weil <sage@newdream.net>
+M:	ceph-devel@vger.kernel.org
+S:	Supported
+F:	drivers/block/rbd.c
+F:	drivers/block/rbd_types.h
+
 RADEON FRAMEBUFFER DISPLAY DRIVER
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 L:	linux-fbdev@vger.kernel.org
@@ -4994,6 +5041,12 @@ F:	drivers/media/common/saa7146*
 F:	drivers/media/video/*7146*
 F:	include/media/*7146*
 
+SAMSUNG AUDIO (ASoC) DRIVERS
+M:	Jassi Brar <jassi.brar@samsung.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Supported
+F:	sound/soc/s3c24xx
+
 TLG2300 VIDEO4LINUX-2 DRIVER
 M:	Huang Shijie <shijie8@gmail.com>
 M:	Kang Yong <kangyong@telegent.com>
@@ -5091,8 +5144,10 @@ S:	Maintained
 F:	drivers/mmc/host/sdricoh_cs.c
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) DRIVER
-S:	Orphan
+M:	Chris Ball <cjb@laptop.org>
 L:	linux-mmc@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git
+S:	Maintained
 F:	drivers/mmc/host/sdhci.*
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF)
@@ -6434,8 +6489,10 @@ F:	include/linux/wm97xx.h
 WOLFSON MICROELECTRONICS DRIVERS
 M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
 M:	Ian Lartey <ian@opensource.wolfsonmicro.com>
+M:	Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
+T:	git git://opensource.wolfsonmicro.com/linux-2.6-asoc
 T:	git git://opensource.wolfsonmicro.com/linux-2.6-audioplus
-W:	http://opensource.wolfsonmicro.com/node/8
+W:	http://opensource.wolfsonmicro.com/content/linux-drivers-wolfson-devices
 S:	Supported
 F:	Documentation/hwmon/wm83??
 F:	drivers/leds/leds-wm83*.c
diff --git a/Makefile b/Makefile
index 92ab33f16cf0..860c26af52c3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 36
-EXTRAVERSION = -rc4
-NAME = Sheep on Meth
+EXTRAVERSION =
+NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
diff --git a/arch/Kconfig b/arch/Kconfig
index 4877a8c8ee16..fe48fc7a3eba 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -32,8 +32,9 @@ config HAVE_OPROFILE
 
 config KPROBES
 	bool "Kprobes"
-	depends on KALLSYMS && MODULES
+	depends on MODULES
 	depends on HAVE_KPROBES
+	select KALLSYMS
 	help
 	  Kprobes allows you to trap at almost any kernel address and
 	  execute a callback function.  register_kprobe() establishes
@@ -45,7 +46,6 @@ config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
-	select KALLSYMS_ALL
 
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index ab1ee0ab082b..6d159cee5f2f 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -73,8 +73,6 @@
 	ldq	$20, HAE_REG($19);	\
 	stq	$21, HAE_CACHE($19);	\
 	stq	$21, 0($20);		\
-	ldq	$0, 0($sp);		\
-	ldq	$1, 8($sp);		\
 99:;					\
 	ldq	$19, 72($sp);		\
 	ldq	$20, 80($sp);		\
@@ -316,7 +314,7 @@ ret_from_sys_call:
 	cmovne	$26, 0, $19		/* $19 = 0 => non-restartable */
 	ldq	$0, SP_OFF($sp)
 	and	$0, 8, $0
-	beq	$0, restore_all
+	beq	$0, ret_to_kernel
 ret_to_user:
 	/* Make sure need_resched and sigpending don't change between
 		sampling and the rti.  */
@@ -329,6 +327,11 @@ restore_all:
 	RESTORE_ALL
 	call_pal PAL_rti
 
+ret_to_kernel:
+	lda	$16, 7
+	call_pal PAL_swpipl
+	br restore_all
+
 	.align 3
 $syscall_error:
 	/*
@@ -657,7 +660,7 @@ kernel_thread:
 	/* We don't actually care for a3 success widgetry in the kernel.
 	   Not for positive errno values.  */
 	stq	$0, 0($sp)		/* $0 */
-	br	restore_all
+	br	ret_to_kernel
 .end kernel_thread
 
 /*
@@ -911,15 +914,6 @@ sys_execve:
 	jmp	$31, do_sys_execve
 .end sys_execve
 
-	.align	4
-	.globl	osf_sigprocmask
-	.ent	osf_sigprocmask
-osf_sigprocmask:
-	.prologue 0
-	mov	$sp, $18
-	jmp	$31, sys_osf_sigprocmask
-.end osf_sigprocmask
-
 	.align	4
 	.globl	alpha_ni_syscall
 	.ent	alpha_ni_syscall
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 842dba308eab..3ec35066f1dc 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -356,7 +356,7 @@ dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti)
 	dest[27] = pt->r27;
 	dest[28] = pt->r28;
 	dest[29] = pt->gp;
-	dest[30] = rdusp();
+	dest[30] = ti == current_thread_info() ? rdusp() : ti->pcb.usp;
 	dest[31] = pt->pc;
 
 	/* Once upon a time this was the PS value.  Which is stupid
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 0f6b51ae865a..6f7feb5db271 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *,
 /*
  * The OSF/1 sigprocmask calling sequence is different from the
  * C sigprocmask() sequence..
- *
- * how:
- * 1 - SIG_BLOCK
- * 2 - SIG_UNBLOCK
- * 3 - SIG_SETMASK
- *
- * We change the range to -1 .. 1 in order to let gcc easily
- * use the conditional move instructions.
- *
- * Note that we don't need to acquire the kernel lock for SMP
- * operation, as all of this is local to this thread.
  */
-SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask,
-		struct pt_regs *, regs)
+SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask)
 {
-	unsigned long oldmask = -EINVAL;
-
-	if ((unsigned long)how-1 <= 2) {
-		long sign = how-2;		/* -1 .. 1 */
-		unsigned long block, unblock;
-
-		newmask &= _BLOCKABLE;
-		spin_lock_irq(&current->sighand->siglock);
-		oldmask = current->blocked.sig[0];
-
-		unblock = oldmask & ~newmask;
-		block = oldmask | newmask;
-		if (!sign)
-			block = unblock;
-		if (sign <= 0)
-			newmask = block;
-		if (_NSIG_WORDS > 1 && sign > 0)
-			sigemptyset(&current->blocked);
-		current->blocked.sig[0] = newmask;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-
-		regs->r0 = 0;		/* special no error return */
+	sigset_t oldmask;
+	sigset_t mask;
+	unsigned long res;
+
+	siginitset(&mask, newmask & _BLOCKABLE);
+	res = sigprocmask(how, &mask, &oldmask);
+	if (!res) {
+		force_successful_syscall_return();
+		res = oldmask.sig[0];
 	}
-	return oldmask;
+	return res;
 }
 
 SYSCALL_DEFINE3(osf_sigaction, int, sig,
@@ -94,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
 		old_sigset_t mask;
 		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
 		    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-		    __get_user(new_ka.sa.sa_flags, &act->sa_flags))
+		    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+		    __get_user(mask, &act->sa_mask))
 			return -EFAULT;
-		__get_user(mask, &act->sa_mask);
 		siginitset(&new_ka.sa.sa_mask, mask);
 		new_ka.ka_restorer = NULL;
 	}
@@ -106,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
 	if (!ret && oact) {
 		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
 		    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags))
+		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+		    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
 			return -EFAULT;
-		__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
 	}
 
 	return ret;
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index ce594ef533cc..a6a1de9db16f 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -58,7 +58,7 @@ sys_call_table:
 	.quad sys_open				/* 45 */
 	.quad alpha_ni_syscall
 	.quad sys_getxgid
-	.quad osf_sigprocmask
+	.quad sys_osf_sigprocmask
 	.quad alpha_ni_syscall
 	.quad alpha_ni_syscall			/* 50 */
 	.quad sys_acct
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 553b7cf17bfb..9c26ba7244fb 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -271,7 +271,6 @@ config ARCH_AT91
 	bool "Atmel AT91"
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
-	select ARCH_USES_GETTIMEOFFSET
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -1051,6 +1050,32 @@ config ARM_ERRATA_460075
 	  ACTLR register. Note that setting specific bits in the ACTLR register
 	  may not be available in non-secure mode.
 
+config ARM_ERRATA_742230
+	bool "ARM errata: DMB operation may be faulty"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 742230 Cortex-A9
+	  (r1p0..r2p2) erratum. Under rare circumstances, a DMB instruction
+	  between two write operations may not ensure the correct visibility
+	  ordering of the two writes. This workaround sets a specific bit in
+	  the diagnostic register of the Cortex-A9 which causes the DMB
+	  instruction to behave as a DSB, ensuring the correct behaviour of
+	  the two writes.
+
+config ARM_ERRATA_742231
+	bool "ARM errata: Incorrect hazard handling in the SCU may lead to data corruption"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 742231 Cortex-A9
+	  (r2p0..r2p2) erratum. Under certain conditions, specific to the
+	  Cortex-A9 MPCore micro-architecture, two CPUs working in SMP mode,
+	  accessing some data located in the same cache line, may get corrupted
+	  data due to bad handling of the address hazard when the line gets
+	  replaced from one of the CPUs at the same time as another CPU is
+	  accessing it. This workaround sets specific bits in the diagnostic
+	  register of the Cortex-A9 which reduces the linefill issuing
+	  capabilities of the processor.
+
 config PL310_ERRATA_588369
 	bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
 	depends on CACHE_L2X0 && ARCH_OMAP4
@@ -1076,6 +1101,20 @@ config ARM_ERRATA_720789
 	  invalidated are not, resulting in an incoherency in the system page
 	  tables. The workaround changes the TLB flushing routines to invalidate
 	  entries regardless of the ASID.
+
+config ARM_ERRATA_743622
+	bool "ARM errata: Faulty hazard checking in the Store Buffer may lead to data corruption"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 743622 Cortex-A9
+	  (r2p0..r2p2) erratum. Under very rare conditions, a faulty
+	  optimisation in the Cortex-A9 Store Buffer may lead to data
+	  corruption. This workaround sets a specific bit in the diagnostic
+	  register of the Cortex-A9 which disables the Store Buffer
+	  optimisation, preventing the defect from occurring. This has no
+	  visible impact on the overall performance or power consumption of the
+	  processor.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index b23f6bc46cfa..65a7c1c588a9 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -116,5 +116,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
-$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile .config
+$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
 	@sed "$(SEDFLAGS)" < $< > $@
diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c
index 7974baacafce..1bec96e85196 100644
--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@@ -271,6 +271,14 @@ int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
 }
 
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (mask >= PHYS_OFFSET + SZ_64M - 1)
+		return 0;
+
+	return -EIO;
+}
+
 int __init it8152_pci_setup(int nr, struct pci_sys_data *sys)
 {
 	it8152_io.start = IT8152_IO_BASE + 0x12000;
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index ab68cf1ef80f..e90b167ea848 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -317,6 +317,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
 #else
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 1b560825e1cf..7885722bdf4e 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -48,6 +48,8 @@ work_pending:
 	beq	no_work_pending
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
+	tst	r1, #_TIF_SIGPENDING		@ delivering a signal?
+	movne	why, #0				@ prevent further restarts
 	bl	do_notify_resume
 	b	ret_slow_syscall		@ Check work again
 
diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c
index 8bccbfa693ff..2c1f0050c9c4 100644
--- a/arch/arm/kernel/kprobes-decode.c
+++ b/arch/arm/kernel/kprobes-decode.c
@@ -1162,11 +1162,12 @@ space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
 	/*
 	 * MSR   : cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx
-	 * Undef : cccc 0011 0x00 xxxx xxxx xxxx xxxx xxxx
+	 * Undef : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx
 	 * ALU op with S bit and Rd == 15 :
 	 *	   cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx
 	 */
-	if ((insn & 0x0f900000) == 0x03200000 ||	/* MSR & Undef */
+	if ((insn & 0x0fb00000) == 0x03200000 ||	/* MSR */
+	    (insn & 0x0ff00000) == 0x03400000 ||	/* Undef */
 	    (insn & 0x0e10f000) == 0x0210f000)		/* ALU s-bit, R15  */
 		return INSN_REJECTED;
 
@@ -1177,7 +1178,7 @@ space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	 * *S (bit 20) updates condition codes
 	 * ADC/SBC/RSC reads the C flag
 	 */
-	insn &= 0xfff00fff;	/* Rn = r0, Rd = r0 */
+	insn &= 0xffff0fff;	/* Rd = r0 */
 	asi->insn[0] = insn;
 	asi->insn_handler = (insn & (1 << 20)) ?  /* S-bit */
 			emulate_alu_imm_rwflags : emulate_alu_imm_rflags;
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 5e71ccd5e7d3..1276babf84d5 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -426,7 +426,7 @@ static struct i2c_gpio_platform_data pdata_i2c0 = {
 	.sda_is_open_drain	= 1,
 	.scl_pin		= AT91_PIN_PA21,
 	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
+	.udelay			= 5,		/* ~100 kHz */
 };
 
 static struct platform_device at91sam9g45_twi0_device = {
@@ -440,7 +440,7 @@ static struct i2c_gpio_platform_data pdata_i2c1 = {
 	.sda_is_open_drain	= 1,
 	.scl_pin		= AT91_PIN_PB11,
 	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
+	.udelay			= 5,		/* ~100 kHz */
 };
 
 static struct platform_device at91sam9g45_twi1_device = {
diff --git a/arch/arm/mach-at91/include/mach/system.h b/arch/arm/mach-at91/include/mach/system.h
index c80e090b3670..ee8db152592e 100644
--- a/arch/arm/mach-at91/include/mach/system.h
+++ b/arch/arm/mach-at91/include/mach/system.h
@@ -28,17 +28,16 @@
 
 static inline void arch_idle(void)
 {
-#ifndef CONFIG_DEBUG_KERNEL
 	/*
 	 * Disable the processor clock.  The processor will be automatically
 	 * re-enabled by an interrupt or by a reset.
 	 */
 	at91_sys_write(AT91_PMC_SCDR, AT91_PMC_PCK);
-#else
+#ifndef CONFIG_CPU_ARM920T
 	/*
 	 * Set the processor (CP15) into 'Wait for Interrupt' mode.
-	 * Unlike disabling the processor clock via the PMC (above)
-	 *  this allows the processor to be woken via JTAG.
+	 * Post-RM9200 processors need this in conjunction with the above
+	 * to save power when idle.
 	 */
 	cpu_do_idle();
 #endif
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 3d996b659ff4..9be261beae7d 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -769,8 +769,7 @@ static struct map_desc dm355_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 6b6f4c643709..7781e35daec3 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -969,8 +969,7 @@ static struct map_desc dm365_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 40fec315c99a..5e5b0a7831fb 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -653,8 +653,7 @@ static struct map_desc dm644x_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00008000),
 		.length		= SZ_16K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index e4a3df1872ac..26e8a9c7f50b 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -737,8 +737,7 @@ static struct map_desc dm646x_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h
index 3b3e4721ce2e..eb4936ff90ad 100644
--- a/arch/arm/mach-dove/include/mach/io.h
+++ b/arch/arm/mach-dove/include/mach/io.h
@@ -13,8 +13,8 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 
-#define __io(a)  ((void __iomem *)(((a) - DOVE_PCIE0_IO_PHYS_BASE) +\
-				   DOVE_PCIE0_IO_VIRT_BASE))
-#define __mem_pci(a)		(a)
+#define __io(a)  	((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \
+						 DOVE_PCIE0_IO_VIRT_BASE))
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ep93xx/dma-m2p.c b/arch/arm/mach-ep93xx/dma-m2p.c
index 8904ca4e2e24..a696d354b1f8 100644
--- a/arch/arm/mach-ep93xx/dma-m2p.c
+++ b/arch/arm/mach-ep93xx/dma-m2p.c
@@ -276,7 +276,7 @@ static void channel_disable(struct m2p_channel *ch)
 	v &= ~(M2P_CONTROL_STALL_IRQ_EN | M2P_CONTROL_NFB_IRQ_EN);
 	m2p_set_control(ch, v);
 
-	while (m2p_channel_state(ch) == STATE_ON)
+	while (m2p_channel_state(ch) >= STATE_ON)
 		cpu_relax();
 
 	m2p_set_control(ch, 0x0);
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index c5c0369bb481..2f7e2728970d 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -122,6 +122,7 @@ config MACH_CPUIMX27
 	select IMX_HAVE_PLATFORM_IMX_I2C
 	select IMX_HAVE_PLATFORM_IMX_UART
 	select IMX_HAVE_PLATFORM_MXC_NAND
+	select MXC_ULPI if USB_ULPI
 	help
 	  Include support for Eukrea CPUIMX27 platform. This includes
 	  specific configurations for the module and its peripherals.
diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c
index 339150ab0ea5..6830afd1d2ba 100644
--- a/arch/arm/mach-imx/mach-cpuimx27.c
+++ b/arch/arm/mach-imx/mach-cpuimx27.c
@@ -259,7 +259,7 @@ static void __init eukrea_cpuimx27_init(void)
 	i2c_register_board_info(0, eukrea_cpuimx27_i2c_devices,
 				ARRAY_SIZE(eukrea_cpuimx27_i2c_devices));
 
-	imx27_add_i2c_imx1(&cpuimx27_i2c1_data);
+	imx27_add_i2c_imx0(&cpuimx27_i2c1_data);
 
 	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
 
diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c
index 61cd4d64b985..24498a932ba6 100644
--- a/arch/arm/mach-ixp4xx/common-pci.c
+++ b/arch/arm/mach-ixp4xx/common-pci.c
@@ -503,6 +503,14 @@ struct pci_bus * __devinit ixp4xx_scan_bus(int nr, struct pci_sys_data *sys)
 	return pci_scan_bus(sys->busnr, &ixp4xx_ops, sys);
 }
 
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (mask >= SZ_64M - 1)
+		return 0;
+
+	return -EIO;
+}
+
 EXPORT_SYMBOL(ixp4xx_pci_read);
 EXPORT_SYMBOL(ixp4xx_pci_write);
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h
index f91ca6d4fbe8..8138371c406e 100644
--- a/arch/arm/mach-ixp4xx/include/mach/hardware.h
+++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h
@@ -26,6 +26,8 @@
 #define PCIBIOS_MAX_MEM		0x4BFFFFFF
 #endif
 
+#define ARCH_HAS_DMA_SET_COHERENT_MASK
+
 #define pcibios_assign_all_busses()	1
 
 /* Register locations and bits */
diff --git a/arch/arm/mach-kirkwood/include/mach/kirkwood.h b/arch/arm/mach-kirkwood/include/mach/kirkwood.h
index 93fc2ec95e76..6e924b398919 100644
--- a/arch/arm/mach-kirkwood/include/mach/kirkwood.h
+++ b/arch/arm/mach-kirkwood/include/mach/kirkwood.h
@@ -38,7 +38,7 @@
 
 #define KIRKWOOD_PCIE1_IO_PHYS_BASE	0xf3000000
 #define KIRKWOOD_PCIE1_IO_VIRT_BASE	0xfef00000
-#define KIRKWOOD_PCIE1_IO_BUS_BASE	0x00000000
+#define KIRKWOOD_PCIE1_IO_BUS_BASE	0x00100000
 #define KIRKWOOD_PCIE1_IO_SIZE		SZ_1M
 
 #define KIRKWOOD_PCIE_IO_PHYS_BASE	0xf2000000
diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c
index 55e7f00836b7..513ad3102d7c 100644
--- a/arch/arm/mach-kirkwood/pcie.c
+++ b/arch/arm/mach-kirkwood/pcie.c
@@ -117,7 +117,7 @@ static void __init pcie0_ioresources_init(struct pcie_port *pp)
 	 * IORESOURCE_IO
 	 */
 	pp->res[0].name = "PCIe 0 I/O Space";
-	pp->res[0].start = KIRKWOOD_PCIE_IO_PHYS_BASE;
+	pp->res[0].start = KIRKWOOD_PCIE_IO_BUS_BASE;
 	pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE_IO_SIZE - 1;
 	pp->res[0].flags = IORESOURCE_IO;
 
@@ -139,7 +139,7 @@ static void __init pcie1_ioresources_init(struct pcie_port *pp)
 	 * IORESOURCE_IO
 	 */
 	pp->res[0].name = "PCIe 1 I/O Space";
-	pp->res[0].start = KIRKWOOD_PCIE1_IO_PHYS_BASE;
+	pp->res[0].start = KIRKWOOD_PCIE1_IO_BUS_BASE;
 	pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE1_IO_SIZE - 1;
 	pp->res[0].flags = IORESOURCE_IO;
 
diff --git a/arch/arm/mach-mmp/include/mach/system.h b/arch/arm/mach-mmp/include/mach/system.h
index 4f5b0e0ce6cf..1a8a25edb1b4 100644
--- a/arch/arm/mach-mmp/include/mach/system.h
+++ b/arch/arm/mach-mmp/include/mach/system.h
@@ -9,6 +9,8 @@
 #ifndef __ASM_MACH_SYSTEM_H
 #define __ASM_MACH_SYSTEM_H
 
+#include <mach/cputype.h>
+
 static inline void arch_idle(void)
 {
 	cpu_do_idle();
@@ -16,6 +18,9 @@ static inline void arch_idle(void)
 
 static inline void arch_reset(char mode, const char *cmd)
 {
-	cpu_reset(0);
+	if (cpu_is_pxa168())
+		cpu_reset(0xffff0000);
+	else
+		cpu_reset(0);
 }
 #endif /* __ASM_MACH_SYSTEM_H */
diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
index 50d5939a78f1..58093d9e07be 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
@@ -312,8 +312,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	freqs.cpu = policy->cpu;
 
 	if (freq_debug)
-		pr_debug(KERN_INFO "Changing CPU frequency to %d Mhz, "
-			 "(SDRAM %d Mhz)\n",
+		pr_debug("Changing CPU frequency to %d Mhz, (SDRAM %d Mhz)\n",
 			 freqs.new / 1000, (pxa_freq_settings[idx].div2) ?
 			 (new_freq_mem / 2000) : (new_freq_mem / 1000));
 
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index 7f64d24cd564..814f1458a06a 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -264,23 +264,35 @@
  * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
  * == 0x3 for pxa300/pxa310/pxa320
  */
+#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x)
 #define __cpu_is_pxa2xx(id)				\
 	({						\
 		unsigned int _id = (id) >> 13 & 0x7;	\
 		_id <= 0x2;				\
 	 })
+#else
+#define __cpu_is_pxa2xx(id)	(0)
+#endif
 
+#ifdef CONFIG_PXA3xx
 #define __cpu_is_pxa3xx(id)				\
 	({						\
 		unsigned int _id = (id) >> 13 & 0x7;	\
 		_id == 0x3;				\
 	 })
+#else
+#define __cpu_is_pxa3xx(id)	(0)
+#endif
 
+#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935)
 #define __cpu_is_pxa93x(id)				\
 	({						\
 		unsigned int _id = (id) >> 4 & 0xfff;	\
 		_id == 0x683 || _id == 0x693;		\
 	 })
+#else
+#define __cpu_is_pxa93x(id)	(0)
+#endif
 
 #define cpu_is_pxa2xx()					\
 	({						\
@@ -309,7 +321,7 @@ extern unsigned long get_clock_tick_rate(void);
 #define PCIBIOS_MIN_IO		0
 #define PCIBIOS_MIN_MEM		0
 #define pcibios_assign_all_busses()	1
+#define ARCH_HAS_DMA_SET_COHERENT_MASK
 #endif
 
-
 #endif  /* _ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h
index 262691fb97d8..fdca3be47d9b 100644
--- a/arch/arm/mach-pxa/include/mach/io.h
+++ b/arch/arm/mach-pxa/include/mach/io.h
@@ -6,6 +6,8 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
+#include <mach/hardware.h>
+
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 77ad6d34ab5b..405b92a29793 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -469,9 +469,13 @@ static struct i2c_board_info __initdata palm27x_pi2c_board_info[] = {
 	},
 };
 
+static struct i2c_pxa_platform_data palm27x_i2c_power_info = {
+	.use_pio	= 1,
+};
+
 void __init palm27x_pmic_init(void)
 {
 	i2c_register_board_info(1, ARRAY_AND_SIZE(palm27x_pi2c_board_info));
-	pxa27x_set_i2c_power_info(NULL);
+	pxa27x_set_i2c_power_info(&palm27x_i2c_power_info);
 }
 #endif
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index c9b747cedea8..37d6173bbb66 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -240,6 +240,7 @@ static void __init vpac270_onenand_init(void) {}
 #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE)
 static struct pxamci_platform_data vpac270_mci_platform_data = {
 	.ocr_mask		= MMC_VDD_32_33 | MMC_VDD_33_34,
+	.gpio_power		= -1,
 	.gpio_card_detect	= GPIO53_VPAC270_SD_DETECT_N,
 	.gpio_card_ro		= GPIO52_VPAC270_SD_READONLY,
 	.detect_delay_ms	= 200,
diff --git a/arch/arm/mach-s5p6440/cpu.c b/arch/arm/mach-s5p6440/cpu.c
index 526f33adb31d..ec592e866054 100644
--- a/arch/arm/mach-s5p6440/cpu.c
+++ b/arch/arm/mach-s5p6440/cpu.c
@@ -19,6 +19,7 @@
 #include <linux/sysdev.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
+#include <linux/sched.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s5p6442/cpu.c b/arch/arm/mach-s5p6442/cpu.c
index a48fb553fd01..70ac681af72b 100644
--- a/arch/arm/mach-s5p6442/cpu.c
+++ b/arch/arm/mach-s5p6442/cpu.c
@@ -19,6 +19,7 @@
 #include <linux/sysdev.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
+#include <linux/sched.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s5pc100/cpu.c b/arch/arm/mach-s5pc100/cpu.c
index 251c92ac5b22..cd1afbce83e2 100644
--- a/arch/arm/mach-s5pc100/cpu.c
+++ b/arch/arm/mach-s5pc100/cpu.c
@@ -21,6 +21,7 @@
 #include <linux/sysdev.h>
 #include <linux/serial_core.h>
 #include <linux/platform_device.h>
+#include <linux/sched.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c
index cfecd70657cb..d562670e1b0b 100644
--- a/arch/arm/mach-s5pv210/clock.c
+++ b/arch/arm/mach-s5pv210/clock.c
@@ -173,11 +173,6 @@ static int s5pv210_clk_ip3_ctrl(struct clk *clk, int enable)
 	return s5p_gatectrl(S5P_CLKGATE_IP3, clk, enable);
 }
 
-static int s5pv210_clk_ip4_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLKGATE_IP4, clk, enable);
-}
-
 static int s5pv210_clk_mask0_ctrl(struct clk *clk, int enable)
 {
 	return s5p_gatectrl(S5P_CLK_SRC_MASK0, clk, enable);
diff --git a/arch/arm/mach-s5pv210/cpu.c b/arch/arm/mach-s5pv210/cpu.c
index 77f456c91ad3..245b82b53df4 100644
--- a/arch/arm/mach-s5pv210/cpu.c
+++ b/arch/arm/mach-s5pv210/cpu.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/sysdev.h>
 #include <linux/platform_device.h>
+#include <linux/sched.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-u300/include/mach/gpio.h b/arch/arm/mach-u300/include/mach/gpio.h
index 7b1fc984abb6..d5a71abcbaea 100644
--- a/arch/arm/mach-u300/include/mach/gpio.h
+++ b/arch/arm/mach-u300/include/mach/gpio.h
@@ -273,6 +273,9 @@ extern void gpio_pullup(unsigned gpio, int value);
 extern int gpio_get_value(unsigned gpio);
 extern void gpio_set_value(unsigned gpio, int value);
 
+#define gpio_get_value_cansleep gpio_get_value
+#define gpio_set_value_cansleep gpio_set_value
+
 /* wrappers to sleep-enable the previous two functions */
 static inline unsigned gpio_to_irq(unsigned gpio)
 {
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 577df6cccb08..71fb17349520 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -68,7 +68,7 @@ static void __init ct_ca9x4_init_irq(void)
 }
 
 #if 0
-static void ct_ca9x4_timer_init(void)
+static void __init ct_ca9x4_timer_init(void)
 {
 	writel(0, MMIO_P2V(CT_CA9X4_TIMER0) + TIMER_CTRL);
 	writel(0, MMIO_P2V(CT_CA9X4_TIMER1) + TIMER_CTRL);
@@ -222,12 +222,18 @@ static struct platform_device pmu_device = {
 	.resource	= pmu_resources,
 };
 
-static void ct_ca9x4_init(void)
+static void __init ct_ca9x4_init(void)
 {
 	int i;
 
 #ifdef CONFIG_CACHE_L2X0
-	l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00000000, 0xfe0fffff);
+	void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC);
+
+	/* set RAM latencies to 1 cycle for this core tile. */
+	writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
+	writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL);
+
+	l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
 #endif
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 817f0ad38a0b..7eaa232180a5 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -48,7 +48,7 @@ void __init v2m_map_io(struct map_desc *tile, size_t num)
 }
 
 
-static void v2m_timer_init(void)
+static void __init v2m_timer_init(void)
 {
 	writel(0, MMIO_P2V(V2M_TIMER0) + TIMER_CTRL);
 	writel(0, MMIO_P2V(V2M_TIMER1) + TIMER_CTRL);
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index d073b64ae87e..724ba3bce72c 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (ai_usermode & UM_SIGNAL)
 		force_sig(SIGBUS, current);
-	else
-		set_cr(cr_no_alignment);
+	else {
+		/*
+		 * We're about to disable the alignment trap and return to
+		 * user space.  But if an interrupt occurs before actually
+		 * reaching user space, then the IRQ vector entry code will
+		 * notice that we were still in kernel space and therefore
+		 * the alignment trap won't be re-enabled in that case as it
+		 * is presumed to be always on from kernel space.
+		 * Let's prevent that race by disabling interrupts here (they
+		 * are disabled on the way back to user space anyway in
+		 * entry-common.S) and disable the alignment trap only if
+		 * there is no work pending for this thread.
+		 */
+		raw_local_irq_disable();
+		if (!(current_thread_info()->flags & _TIF_WORK_MASK))
+			set_cr(cr_no_alignment);
+	}
 
 	return 0;
 }
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ab506272b2d3..17e7b0b57e49 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -204,8 +204,12 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
 	 */
-	if (WARN_ON(pfn_valid(pfn)))
-		return NULL;
+	if (pfn_valid(pfn)) {
+		printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory.  This leads\n"
+		       KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
+		       KERN_WARNING "will fail in the next kernel release.  Please fix your driver.\n");
+		WARN_ON(1);
+	}
 
 	type = get_mem_type(mtype);
 	if (!type)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6e1c4f6a2b3f..e8ed9dc461fe 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -246,6 +247,9 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_USER,
 	},
 	[MT_MEMORY] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_WRITE | L_PTE_EXEC,
+		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -254,6 +258,9 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_MEMORY_NONCACHED] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_WRITE | L_PTE_EXEC | L_PTE_MT_BUFFERABLE,
+		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -411,9 +418,12 @@ static void __init build_mem_type_table(void)
 	 * Enable CPU-specific coherency if supported.
 	 * (Only available on XSC3 at the moment.)
 	 */
-	if (arch_is_coherent() && cpu_is_xsc3())
+	if (arch_is_coherent() && cpu_is_xsc3()) {
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-
+		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+	}
 	/*
 	 * ARMv6 and above have extended page tables.
 	 */
@@ -438,7 +448,9 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
 		mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 #endif
 	}
 
@@ -475,6 +487,8 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
 	switch (cp->pmd) {
@@ -498,6 +512,19 @@ static void __init build_mem_type_table(void)
 	}
 }
 
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+			      unsigned long size, pgprot_t vma_prot)
+{
+	if (!pfn_valid(pfn))
+		return pgprot_noncached(vma_prot);
+	else if (file->f_flags & O_SYNC)
+		return pgprot_writecombine(vma_prot);
+	return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
+
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
 static void __init *early_alloc(unsigned long sz)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6a8506d99ee9..197f21bed5e9 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -186,13 +186,14 @@ cpu_v7_name:
  *	It is assumed that:
  *	- cache type register is implemented
  */
-__v7_setup:
+__v7_ca9mp_setup:
 #ifdef CONFIG_SMP
 	mrc	p15, 0, r0, c1, c0, 1
 	tst	r0, #(1 << 6)			@ SMP/nAMP mode enabled?
 	orreq	r0, r0, #(1 << 6) | (1 << 0)	@ Enable SMP/nAMP mode and
 	mcreq	p15, 0, r0, c1, c0, 1		@ TLB ops broadcasting
 #endif
+__v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
 	bl	v7_flush_dcache_all
@@ -201,11 +202,16 @@ __v7_setup:
 	mrc	p15, 0, r0, c0, c0, 0		@ read main ID register
 	and	r10, r0, #0xff000000		@ ARM?
 	teq	r10, #0x41000000
-	bne	2f
+	bne	3f
 	and	r5, r0, #0x00f00000		@ variant
 	and	r6, r0, #0x0000000f		@ revision
-	orr	r0, r6, r5, lsr #20-4		@ combine variant and revision
+	orr	r6, r6, r5, lsr #20-4		@ combine variant and revision
+	ubfx	r0, r0, #4, #12			@ primary part number
 
+	/* Cortex-A8 Errata */
+	ldr	r10, =0x00000c08		@ Cortex-A8 primary part number
+	teq	r0, r10
+	bne	2f
 #ifdef CONFIG_ARM_ERRATA_430973
 	teq	r5, #0x00100000			@ only present in r1p*
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
@@ -213,21 +219,50 @@ __v7_setup:
 	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-	teq	r0, #0x20			@ only present in r2p0
+	teq	r6, #0x20			@ only present in r2p0
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
 	orreq	r10, r10, #(1 << 5)		@ set L1NEON to 1
 	orreq	r10, r10, #(1 << 9)		@ set PLDNOP to 1
 	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-	teq	r0, #0x20			@ only present in r2p0
+	teq	r6, #0x20			@ only present in r2p0
 	mrceq	p15, 1, r10, c9, c0, 2		@ read L2 cache aux ctrl register
 	tsteq	r10, #1 << 22
 	orreq	r10, r10, #(1 << 22)		@ set the Write Allocate disable bit
 	mcreq	p15, 1, r10, c9, c0, 2		@ write the L2 cache aux ctrl register
 #endif
+	b	3f
 
-2:	mov	r10, #0
+	/* Cortex-A9 Errata */
+2:	ldr	r10, =0x00000c09		@ Cortex-A9 primary part number
+	teq	r0, r10
+	bne	3f
+#ifdef CONFIG_ARM_ERRATA_742230
+	cmp	r6, #0x22			@ only present up to r2p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 4		@ set bit #4
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+	teq	r6, #0x20			@ present in r2p0
+	teqne	r6, #0x21			@ present in r2p1
+	teqne	r6, #0x22			@ present in r2p2
+	mrceq	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orreq	r10, r10, #1 << 12		@ set bit #12
+	orreq	r10, r10, #1 << 22		@ set bit #22
+	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_743622
+	teq	r6, #0x20			@ present in r2p0
+	teqne	r6, #0x21			@ present in r2p1
+	teqne	r6, #0x22			@ present in r2p2
+	mrceq	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orreq	r10, r10, #1 << 6		@ set bit #6
+	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+
+3:	mov	r10, #0
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 #endif
@@ -323,6 +358,29 @@ cpu_elf_name:
 
 	.section ".proc.info.init", #alloc, #execinstr
 
+	.type   __v7_ca9mp_proc_info, #object
+__v7_ca9mp_proc_info:
+	.long	0x410fc090		@ Required ID value
+	.long	0xff0ffff0		@ Mask for ID
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_XN | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	b	__v7_ca9mp_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
+	.long	cpu_v7_name
+	.long	v7_processor_functions
+	.long	v7wbi_tlb_fns
+	.long	v6_user_fns
+	.long	v7_cache_fns
+	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
 	/*
 	 * Match any ARMv7 processor core.
 	 */
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 0691176899ff..72e09eb642dd 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -102,6 +102,7 @@ static int op_create_counter(int cpu, int event)
 	if (IS_ERR(pevent)) {
 		ret = PTR_ERR(pevent);
 	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		perf_event_release_kernel(pevent);
 		pr_warning("oprofile: failed to enable event %d "
 				"on CPU %d\n", event, cpu);
 		ret = -EBUSY;
@@ -365,6 +366,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	ret = init_driverfs();
 	if (ret) {
 		kfree(counter_config);
+		counter_config = NULL;
 		return ret;
 	}
 
@@ -402,7 +404,6 @@ void oprofile_arch_exit(void)
 	struct perf_event *event;
 
 	if (*perf_events) {
-		exit_driverfs();
 		for_each_possible_cpu(cpu) {
 			for (id = 0; id < perf_num_counters; ++id) {
 				event = perf_events[cpu][id];
@@ -413,8 +414,10 @@ void oprofile_arch_exit(void)
 		}
 	}
 
-	if (counter_config)
+	if (counter_config) {
 		kfree(counter_config);
+		exit_driverfs();
+	}
 }
 #else
 int __init oprofile_arch_init(struct oprofile_operations *ops)
diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c
index ea3ca86c5283..aedf9c1d645e 100644
--- a/arch/arm/plat-nomadik/timer.c
+++ b/arch/arm/plat-nomadik/timer.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/mach-nomadik/timer.c
+ *  linux/arch/arm/plat-nomadik/timer.c
  *
  * Copyright (C) 2008 STMicroelectronics
  * Copyright (C) 2010 Alessandro Rubini
@@ -75,7 +75,7 @@ static void nmdk_clkevt_mode(enum clock_event_mode mode,
 		cr = readl(mtu_base + MTU_CR(1));
 		writel(0, mtu_base + MTU_LR(1));
 		writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(1));
-		writel(0x2, mtu_base + MTU_IMSC);
+		writel(1 << 1, mtu_base + MTU_IMSC);
 		break;
 	case CLOCK_EVT_MODE_SHUTDOWN:
 	case CLOCK_EVT_MODE_UNUSED:
@@ -131,25 +131,23 @@ void __init nmdk_timer_init(void)
 {
 	unsigned long rate;
 	struct clk *clk0;
-	struct clk *clk1;
-	u32 cr;
+	u32 cr = MTU_CRn_32BITS;
 
 	clk0 = clk_get_sys("mtu0", NULL);
 	BUG_ON(IS_ERR(clk0));
 
-	clk1 = clk_get_sys("mtu1", NULL);
-	BUG_ON(IS_ERR(clk1));
-
 	clk_enable(clk0);
-	clk_enable(clk1);
 
 	/*
-	 * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500:
-	 * use a divide-by-16 counter if it's more than 16MHz
+	 * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz
+	 * for ux500.
+	 * Use a divide-by-16 counter if the tick rate is more than 32MHz.
+	 * At 32 MHz, the timer (with 32 bit counter) can be programmed
+	 * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer
+	 * with 16 gives too low timer resolution.
 	 */
-	cr = MTU_CRn_32BITS;;
 	rate = clk_get_rate(clk0);
-	if (rate > 16 << 20) {
+	if (rate > 32000000) {
 		rate /= 16;
 		cr |= MTU_CRn_PRESCALE_16;
 	} else {
@@ -170,15 +168,8 @@ void __init nmdk_timer_init(void)
 		pr_err("timer: failed to initialize clock source %s\n",
 		       nmdk_clksrc.name);
 
-	/* Timer 1 is used for events, fix according to rate */
-	cr = MTU_CRn_32BITS;
-	rate = clk_get_rate(clk1);
-	if (rate > 16 << 20) {
-		rate /= 16;
-		cr |= MTU_CRn_PRESCALE_16;
-	} else {
-		cr |= MTU_CRn_PRESCALE_1;
-	}
+	/* Timer 1 is used for events */
+
 	clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE);
 
 	writel(cr | MTU_CRn_ONESHOT, mtu_base + MTU_CR(1)); /* off, currently */
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index e39a417a368d..a92cb499313f 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -33,7 +33,7 @@ config OMAP_DEBUG_DEVICES
 config OMAP_DEBUG_LEDS
 	bool
 	depends on OMAP_DEBUG_DEVICES
-	default y if LEDS
+	default y if LEDS_CLASS
 
 config OMAP_RESET_CLOCKS
 	bool "Reset unused clocks during boot"
diff --git a/arch/arm/plat-omap/iommu.c b/arch/arm/plat-omap/iommu.c
index a202a2ce6e3d..6cd151b31bc5 100644
--- a/arch/arm/plat-omap/iommu.c
+++ b/arch/arm/plat-omap/iommu.c
@@ -320,6 +320,7 @@ void flush_iotlb_page(struct iommu *obj, u32 da)
 		if ((start <= da) && (da < start + bytes)) {
 			dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n",
 				__func__, start, da, bytes);
+			iotlb_load_cr(obj, &cr);
 			iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
 		}
 	}
diff --git a/arch/arm/plat-omap/mcbsp.c b/arch/arm/plat-omap/mcbsp.c
index e31496e35b0f..0c8612fd8312 100644
--- a/arch/arm/plat-omap/mcbsp.c
+++ b/arch/arm/plat-omap/mcbsp.c
@@ -156,7 +156,7 @@ static irqreturn_t omap_mcbsp_rx_irq_handler(int irq, void *dev_id)
 		/* Writing zero to RSYNC_ERR clears the IRQ */
 		MCBSP_WRITE(mcbsp_rx, SPCR1, MCBSP_READ_CACHE(mcbsp_rx, SPCR1));
 	} else {
-		complete(&mcbsp_rx->tx_irq_completion);
+		complete(&mcbsp_rx->rx_irq_completion);
 	}
 
 	return IRQ_HANDLED;
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 226b2e858d6c..10b3b4c63372 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -220,20 +220,7 @@ void __init omap_map_sram(void)
 	if (omap_sram_size == 0)
 		return;
 
-	if (cpu_is_omap24xx()) {
-		omap_sram_io_desc[0].virtual = OMAP2_SRAM_VA;
-
-		base = OMAP2_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-	}
-
 	if (cpu_is_omap34xx()) {
-		omap_sram_io_desc[0].virtual = OMAP3_SRAM_VA;
-		base = OMAP3_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-
 		/*
 		 * SRAM must be marked as non-cached on OMAP3 since the
 		 * CORE DPLL M2 divider change code (in SRAM) runs with the
@@ -244,13 +231,11 @@ void __init omap_map_sram(void)
 		omap_sram_io_desc[0].type = MT_MEMORY_NONCACHED;
 	}
 
-	if (cpu_is_omap44xx()) {
-		omap_sram_io_desc[0].virtual = OMAP4_SRAM_VA;
-		base = OMAP4_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-	}
-	omap_sram_io_desc[0].length = 1024 * 1024;	/* Use section desc */
+	omap_sram_io_desc[0].virtual = omap_sram_base;
+	base = omap_sram_start;
+	base = ROUND_DOWN(base, PAGE_SIZE);
+	omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
+	omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE);
 	iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc));
 
 	printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n",
diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c
index 04d9521ddc9f..e8f2be2d67f2 100644
--- a/arch/arm/plat-samsung/adc.c
+++ b/arch/arm/plat-samsung/adc.c
@@ -435,7 +435,6 @@ static int s3c_adc_suspend(struct platform_device *pdev, pm_message_t state)
 static int s3c_adc_resume(struct platform_device *pdev)
 {
 	struct adc_device *adc = platform_get_drvdata(pdev);
-	unsigned long flags;
 
 	clk_enable(adc->clk);
 	enable_irq(adc->irq);
diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c
index 90a20512d68d..e8d20b0bc50e 100644
--- a/arch/arm/plat-samsung/clock.c
+++ b/arch/arm/plat-samsung/clock.c
@@ -48,6 +48,9 @@
 #include <plat/clock.h>
 #include <plat/cpu.h>
 
+#include <linux/serial_core.h>
+#include <plat/regs-serial.h> /* for s3c24xx_uart_devs */
+
 /* clock information */
 
 static LIST_HEAD(clocks);
@@ -65,6 +68,28 @@ static int clk_null_enable(struct clk *clk, int enable)
 	return 0;
 }
 
+static int dev_is_s3c_uart(struct device *dev)
+{
+	struct platform_device **pdev = s3c24xx_uart_devs;
+	int i;
+	for (i = 0; i < ARRAY_SIZE(s3c24xx_uart_devs); i++, pdev++)
+		if (*pdev && dev == &(*pdev)->dev)
+			return 1;
+	return 0;
+}
+
+/*
+ * Serial drivers call get_clock() very early, before platform bus
+ * has been set up, this requires a special check to let them get
+ * a proper clock
+ */
+
+static int dev_is_platform_device(struct device *dev)
+{
+	return dev->bus == &platform_bus_type ||
+	       (dev->bus == NULL && dev_is_s3c_uart(dev));
+}
+
 /* Clock API calls */
 
 struct clk *clk_get(struct device *dev, const char *id)
@@ -73,7 +98,7 @@ struct clk *clk_get(struct device *dev, const char *id)
 	struct clk *clk = ERR_PTR(-ENOENT);
 	int idno;
 
-	if (dev == NULL || dev->bus != &platform_bus_type)
+	if (dev == NULL || !dev_is_platform_device(dev))
 		idno = -1;
 	else
 		idno = to_platform_device(dev)->id;
diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c
index 98f94d041d9c..a727f54d64d6 100644
--- a/arch/avr32/kernel/module.c
+++ b/arch/avr32/kernel/module.c
@@ -314,10 +314,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
 	vfree(module->arch.syminfo);
 	module->arch.syminfo = NULL;
 
-	return module_bug_finalize(hdr, sechdrs, module);
+	return 0;
 }
 
 void module_arch_cleanup(struct module *module)
 {
-	module_bug_cleanup(module);
 }
diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c
index 0974c0ecc594..bab01298b58e 100644
--- a/arch/frv/kernel/signal.c
+++ b/arch/frv/kernel/signal.c
@@ -121,6 +121,9 @@ static int restore_sigcontext(struct sigcontext __user *sc, int *_gr8)
 	struct user_context *user = current->thread.user;
 	unsigned long tbr, psr;
 
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
 	tbr = user->i.tbr;
 	psr = user->i.psr;
 	if (copy_from_user(user, &sc->sc_context, sizeof(sc->sc_context)))
@@ -250,6 +253,8 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set)
 	struct sigframe __user *frame;
 	int rsig;
 
+	set_fs(USER_DS);
+
 	frame = get_sigframe(ka, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
@@ -293,22 +298,23 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set)
 				   (unsigned long) (frame->retcode + 2));
 	}
 
-	/* set up registers for signal handler */
-	__frame->sp   = (unsigned long) frame;
-	__frame->lr   = (unsigned long) &frame->retcode;
-	__frame->gr8  = sig;
-
+	/* Set up registers for the signal handler */
 	if (current->personality & FDPIC_FUNCPTRS) {
 		struct fdpic_func_descriptor __user *funcptr =
 			(struct fdpic_func_descriptor __user *) ka->sa.sa_handler;
-		__get_user(__frame->pc, &funcptr->text);
-		__get_user(__frame->gr15, &funcptr->GOT);
+		struct fdpic_func_descriptor desc;
+		if (copy_from_user(&desc, funcptr, sizeof(desc)))
+			goto give_sigsegv;
+		__frame->pc = desc.text;
+		__frame->gr15 = desc.GOT;
 	} else {
 		__frame->pc   = (unsigned long) ka->sa.sa_handler;
 		__frame->gr15 = 0;
 	}
 
-	set_fs(USER_DS);
+	__frame->sp   = (unsigned long) frame;
+	__frame->lr   = (unsigned long) &frame->retcode;
+	__frame->gr8  = sig;
 
 	/* the tracer may want to single-step inside the handler */
 	if (test_thread_flag(TIF_SINGLESTEP))
@@ -323,7 +329,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set)
 	return 0;
 
 give_sigsegv:
-	force_sig(SIGSEGV, current);
+	force_sigsegv(sig, current);
 	return -EFAULT;
 
 } /* end setup_frame() */
@@ -338,6 +344,8 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	struct rt_sigframe __user *frame;
 	int rsig;
 
+	set_fs(USER_DS);
+
 	frame = get_sigframe(ka, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
@@ -392,22 +400,23 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	}
 
 	/* Set up registers for signal handler */
-	__frame->sp  = (unsigned long) frame;
-	__frame->lr   = (unsigned long) &frame->retcode;
-	__frame->gr8 = sig;
-	__frame->gr9 = (unsigned long) &frame->info;
-
 	if (current->personality & FDPIC_FUNCPTRS) {
 		struct fdpic_func_descriptor __user *funcptr =
 			(struct fdpic_func_descriptor __user *) ka->sa.sa_handler;
-		__get_user(__frame->pc, &funcptr->text);
-		__get_user(__frame->gr15, &funcptr->GOT);
+		struct fdpic_func_descriptor desc;
+		if (copy_from_user(&desc, funcptr, sizeof(desc)))
+			goto give_sigsegv;
+		__frame->pc = desc.text;
+		__frame->gr15 = desc.GOT;
 	} else {
 		__frame->pc   = (unsigned long) ka->sa.sa_handler;
 		__frame->gr15 = 0;
 	}
 
-	set_fs(USER_DS);
+	__frame->sp  = (unsigned long) frame;
+	__frame->lr  = (unsigned long) &frame->retcode;
+	__frame->gr8 = sig;
+	__frame->gr9 = (unsigned long) &frame->info;
 
 	/* the tracer may want to single-step inside the handler */
 	if (test_thread_flag(TIF_SINGLESTEP))
@@ -422,7 +431,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	return 0;
 
 give_sigsegv:
-	force_sig(SIGSEGV, current);
+	force_sigsegv(sig, current);
 	return -EFAULT;
 
 } /* end setup_rt_frame() */
@@ -437,7 +446,7 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 	int ret;
 
 	/* Are we from a system call? */
-	if (in_syscall(__frame)) {
+	if (__frame->syscallno != -1) {
 		/* If so, check system call restarting.. */
 		switch (__frame->gr8) {
 		case -ERESTART_RESTARTBLOCK:
@@ -456,6 +465,7 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 			__frame->gr8 = __frame->orig_gr8;
 			__frame->pc -= 4;
 		}
+		__frame->syscallno = -1;
 	}
 
 	/* Set up the stack frame */
@@ -538,10 +548,11 @@ no_signal:
 			break;
 
 		case -ERESTART_RESTARTBLOCK:
-			__frame->gr8 = __NR_restart_syscall;
+			__frame->gr7 = __NR_restart_syscall;
 			__frame->pc -= 4;
 			break;
 		}
+		__frame->syscallno = -1;
 	}
 
 	/* if there's no signal to deliver, we just put the saved sigmask
diff --git a/arch/h8300/kernel/module.c b/arch/h8300/kernel/module.c
index 0865e291c20d..db4953dc4e1b 100644
--- a/arch/h8300/kernel/module.c
+++ b/arch/h8300/kernel/module.c
@@ -112,10 +112,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	return module_bug_finalize(hdr, sechdrs, me);
+	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
-	module_bug_cleanup(mod);
 }
diff --git a/arch/m32r/include/asm/elf.h b/arch/m32r/include/asm/elf.h
index 2f85412ef730..b8da7d0574d2 100644
--- a/arch/m32r/include/asm/elf.h
+++ b/arch/m32r/include/asm/elf.h
@@ -82,9 +82,9 @@ typedef elf_fpreg_t elf_fpregset_t;
  * These are used to set parameters in the core dumps.
  */
 #define ELF_CLASS	ELFCLASS32
-#if defined(__LITTLE_ENDIAN)
+#if defined(__LITTLE_ENDIAN__)
 #define ELF_DATA	ELFDATA2LSB
-#elif defined(__BIG_ENDIAN)
+#elif defined(__BIG_ENDIAN__)
 #define ELF_DATA	ELFDATA2MSB
 #else
 #error no endian defined
diff --git a/arch/m32r/include/asm/signal.h b/arch/m32r/include/asm/signal.h
index 9c1acb2b1a92..b2eeb0de1c8d 100644
--- a/arch/m32r/include/asm/signal.h
+++ b/arch/m32r/include/asm/signal.h
@@ -157,7 +157,6 @@ typedef struct sigaltstack {
 #undef __HAVE_ARCH_SIG_BITOPS
 
 struct pt_regs;
-extern int do_signal(struct pt_regs *regs, sigset_t *oldset);
 
 #define ptrace_signal_deliver(regs, cookie)	do { } while (0)
 
diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h
index 76125777483c..c70545689da8 100644
--- a/arch/m32r/include/asm/unistd.h
+++ b/arch/m32r/include/asm/unistd.h
@@ -351,6 +351,7 @@
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT /*will be unused*/
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
 
 #define __IGNORE_lchown
 #define __IGNORE_setuid
diff --git a/arch/m32r/kernel/.gitignore b/arch/m32r/kernel/.gitignore
new file mode 100644
index 000000000000..c5f676c3c224
--- /dev/null
+++ b/arch/m32r/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/m32r/kernel/entry.S b/arch/m32r/kernel/entry.S
index 403869833b98..225412bc227e 100644
--- a/arch/m32r/kernel/entry.S
+++ b/arch/m32r/kernel/entry.S
@@ -235,10 +235,9 @@ work_resched:
 work_notifysig:				; deal with pending signals and
 					; notify-resume requests
 	mv	r0, sp			; arg1 : struct pt_regs *regs
-	ldi	r1, #0			; arg2 : sigset_t *oldset
-	mv	r2, r9			; arg3 : __u32 thread_info_flags
+	mv	r1, r9			; arg2 : __u32 thread_info_flags
 	bl	do_notify_resume
-	bra	restore_all
+	bra	resume_userspace
 
 	; perform syscall exit tracing
 	ALIGN
diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c
index e555091eb97c..0021ade4cba8 100644
--- a/arch/m32r/kernel/ptrace.c
+++ b/arch/m32r/kernel/ptrace.c
@@ -592,16 +592,17 @@ void user_enable_single_step(struct task_struct *child)
 
 	if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0)
 	    != sizeof(insn))
-		break;
+		return -EIO;
 
 	compute_next_pc(insn, pc, &next_pc, child);
 	if (next_pc & 0x80000000)
-		break;
+		return -EIO;
 
 	if (embed_debug_trap(child, next_pc))
-		break;
+		return -EIO;
 
 	invalidate_cache();
+	return 0;
 }
 
 void user_disable_single_step(struct task_struct *child)
diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c
index 144b0f124fc7..a08697f0886d 100644
--- a/arch/m32r/kernel/signal.c
+++ b/arch/m32r/kernel/signal.c
@@ -30,35 +30,6 @@
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-int do_signal(struct pt_regs *, sigset_t *);
-
-asmlinkage int
-sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize,
-		  unsigned long r2, unsigned long r3, unsigned long r4,
-		  unsigned long r5, unsigned long r6, struct pt_regs *regs)
-{
-	sigset_t newset;
-
-	/* XXX: Don't preclude handling different sized sigset_t's.  */
-	if (sigsetsize != sizeof(sigset_t))
-		return -EINVAL;
-
-	if (copy_from_user(&newset, unewset, sizeof(newset)))
-		return -EFAULT;
-	sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP));
-
-	spin_lock_irq(&current->sighand->siglock);
-	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	current->state = TASK_INTERRUPTIBLE;
-	schedule();
-	set_thread_flag(TIF_RESTORE_SIGMASK);
-	return -ERESTARTNOHAND;
-}
-
 asmlinkage int
 sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 		unsigned long r2, unsigned long r3, unsigned long r4,
@@ -218,7 +189,7 @@ get_sigframe(struct k_sigaction *ka, unsigned long sp, size_t frame_size)
 	return (void __user *)((sp - frame_size) & -8ul);
 }
 
-static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 			   sigset_t *set, struct pt_regs *regs)
 {
 	struct rt_sigframe __user *frame;
@@ -275,22 +246,34 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		current->comm, current->pid, frame, regs->pc);
 #endif
 
-	return;
+	return 0;
 
 give_sigsegv:
 	force_sigsegv(sig, current);
+	return -EFAULT;
+}
+
+static int prev_insn(struct pt_regs *regs)
+{
+	u16 inst;
+	if (get_user(inst, (u16 __user *)(regs->bpc - 2)))
+		return -EFAULT;
+	if ((inst & 0xfff0) == 0x10f0)	/* trap ? */
+		regs->bpc -= 2;
+	else
+		regs->bpc -= 4;
+	regs->syscall_nr = -1;
+	return 0;
 }
 
 /*
  * OK, we're invoking a handler
  */
 
-static void
+static int
 handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
 	      sigset_t *oldset, struct pt_regs *regs)
 {
-	unsigned short inst;
-
 	/* Are we from a system call? */
 	if (regs->syscall_nr >= 0) {
 		/* If so, check system call restarting.. */
@@ -308,16 +291,14 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
 			/* fallthrough */
 			case -ERESTARTNOINTR:
 				regs->r0 = regs->orig_r0;
-				inst = *(unsigned short *)(regs->bpc - 2);
-				if ((inst & 0xfff0) == 0x10f0)	/* trap ? */
-					regs->bpc -= 2;
-				else
-					regs->bpc -= 4;
+				if (prev_insn(regs) < 0)
+					return -EFAULT;
 		}
 	}
 
 	/* Set up the stack frame */
-	setup_rt_frame(sig, ka, info, oldset, regs);
+	if (setup_rt_frame(sig, ka, info, oldset, regs))
+		return -EFAULT;
 
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
@@ -325,6 +306,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
 		sigaddset(&current->blocked,sig);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
+	return 0;
 }
 
 /*
@@ -332,12 +314,12 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info,
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-int do_signal(struct pt_regs *regs, sigset_t *oldset)
+static void do_signal(struct pt_regs *regs)
 {
 	siginfo_t info;
 	int signr;
 	struct k_sigaction ka;
-	unsigned short inst;
+	sigset_t *oldset;
 
 	/*
 	 * We want the common case to go fast, which
@@ -346,12 +328,14 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 	 * if so.
 	 */
 	if (!user_mode(regs))
-		return 1;
+		return;
 
 	if (try_to_freeze()) 
 		goto no_signal;
 
-	if (!oldset)
+	if (test_thread_flag(TIF_RESTORE_SIGMASK))
+		oldset = &current->saved_sigmask;
+	else
 		oldset = &current->blocked;
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
@@ -363,8 +347,10 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 		 */
 
 		/* Whee!  Actually deliver the signal.  */
-		handle_signal(signr, &ka, &info, oldset, regs);
-		return 1;
+		if (handle_signal(signr, &ka, &info, oldset, regs) == 0)
+			clear_thread_flag(TIF_RESTORE_SIGMASK);
+
+		return;
 	}
 
  no_signal:
@@ -375,31 +361,24 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 		    regs->r0 == -ERESTARTSYS ||
 		    regs->r0 == -ERESTARTNOINTR) {
 			regs->r0 = regs->orig_r0;
-			inst = *(unsigned short *)(regs->bpc - 2);
-			if ((inst & 0xfff0) == 0x10f0)	/* trap ? */
-				regs->bpc -= 2;
-			else
-				regs->bpc -= 4;
-		}
-		if (regs->r0 == -ERESTART_RESTARTBLOCK){
+			prev_insn(regs);
+		} else if (regs->r0 == -ERESTART_RESTARTBLOCK){
 			regs->r0 = regs->orig_r0;
 			regs->r7 = __NR_restart_syscall;
-			inst = *(unsigned short *)(regs->bpc - 2);
-			if ((inst & 0xfff0) == 0x10f0)	/* trap ? */
-				regs->bpc -= 2;
-			else
-				regs->bpc -= 4;
+			prev_insn(regs);
 		}
 	}
-	return 0;
+	if (test_thread_flag(TIF_RESTORE_SIGMASK)) {
+		clear_thread_flag(TIF_RESTORE_SIGMASK);
+		sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
+	}
 }
 
 /*
  * notification of userspace execution resumption
  * - triggered by current->work.notify_resume
  */
-void do_notify_resume(struct pt_regs *regs, sigset_t *oldset,
-		      __u32 thread_info_flags)
+void do_notify_resume(struct pt_regs *regs, __u32 thread_info_flags)
 {
 	/* Pending single-step? */
 	if (thread_info_flags & _TIF_SINGLESTEP)
@@ -407,7 +386,7 @@ void do_notify_resume(struct pt_regs *regs, sigset_t *oldset,
 
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
-		do_signal(regs,oldset);
+		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
 		clear_thread_flag(TIF_NOTIFY_RESUME);
diff --git a/arch/m68k/mac/macboing.c b/arch/m68k/mac/macboing.c
index 8f0640847ad2..05285d08e547 100644
--- a/arch/m68k/mac/macboing.c
+++ b/arch/m68k/mac/macboing.c
@@ -162,7 +162,7 @@ static void mac_init_asc( void )
 void mac_mksound( unsigned int freq, unsigned int length )
 {
 	__u32 cfreq = ( freq << 5 ) / 468;
-	__u32 flags;
+	unsigned long flags;
 	int i;
 
 	if ( mac_special_bell == NULL )
@@ -224,7 +224,7 @@ static void mac_nosound( unsigned long ignored )
  */
 static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsigned int volume )
 {
-	__u32 flags;
+	unsigned long flags;
 
 	/* if the bell is already ringing, ring longer */
 	if ( mac_bell_duration > 0 )
@@ -271,7 +271,7 @@ static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsig
 static void mac_quadra_ring_bell( unsigned long ignored )
 {
 	int	i, count = mac_asc_samplespersec / HZ;
-	__u32 flags;
+	unsigned long flags;
 
 	/*
 	 * we neither want a sound buffer overflow nor underflow, so we need to match
diff --git a/arch/mips/Kbuild b/arch/mips/Kbuild
index e322d65f33a4..7dd65cfae837 100644
--- a/arch/mips/Kbuild
+++ b/arch/mips/Kbuild
@@ -7,6 +7,10 @@ subdir-ccflags-y := -Werror
 include arch/mips/Kbuild.platforms
 obj-y := $(platform-y)
 
+# make clean traverses $(obj-) without having included .config, so
+# everything ends up here
+obj- := $(platform-)
+
 # mips object files
 # The object files are linked as core-y files would be linked
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 3ad59dde4852..4c9f402295dd 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -13,6 +13,7 @@ config MIPS
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select RTC_LIB if !MACH_LOONGSON
+	select GENERIC_ATOMIC64 if !64BIT
 
 mainmenu "Linux/MIPS Kernel Configuration"
 
@@ -880,11 +881,15 @@ config NO_IOPORT
 config GENERIC_ISA_DMA
 	bool
 	select ZONE_DMA if GENERIC_ISA_DMA_SUPPORT_BROKEN=n
+	select ISA_DMA_API
 
 config GENERIC_ISA_DMA_SUPPORT_BROKEN
 	bool
 	select GENERIC_ISA_DMA
 
+config ISA_DMA_API
+	bool
+
 config GENERIC_GPIO
 	bool
 
@@ -1646,8 +1651,16 @@ config MIPS_MT_SMP
 	select SYS_SUPPORTS_SMP
 	select SMP_UP
 	help
-	  This is a kernel model which is also known a VSMP or lately
-	  has been marketesed into SMVP.
+	  This is a kernel model which is known a VSMP but lately has been
+	  marketesed into SMVP.
+	  Virtual SMP uses the processor's VPEs  to implement virtual
+	  processors. In currently available configuration of the 34K processor
+	  this allows for a dual processor. Both processors will share the same
+	  primary caches; each will obtain the half of the TLB for it's own
+	  exclusive use. For a layman this model can be described as similar to
+	  what Intel calls Hyperthreading.
+
+	  For further information see http://www.linux-mips.org/wiki/34K#VSMP
 
 config MIPS_MT_SMTC
 	bool "SMTC: Use all TCs on all VPEs for SMP"
@@ -1664,6 +1677,14 @@ config MIPS_MT_SMTC
 	help
 	  This is a kernel model which is known a SMTC or lately has been
 	  marketesed into SMVP.
+	  is presenting the available TC's of the core as processors to Linux.
+	  On currently available 34K processors this means a Linux system will
+	  see up to 5 processors. The implementation of the SMTC kernel differs
+	  significantly from VSMP and cannot efficiently coexist in the same
+	  kernel binary so the choice between VSMP and SMTC is a compile time
+	  decision.
+
+	  For further information see http://www.linux-mips.org/wiki/34K#SMTC
 
 endchoice
 
diff --git a/arch/mips/alchemy/common/prom.c b/arch/mips/alchemy/common/prom.c
index c29511b11d44..534021059629 100644
--- a/arch/mips/alchemy/common/prom.c
+++ b/arch/mips/alchemy/common/prom.c
@@ -43,7 +43,7 @@ int prom_argc;
 char **prom_argv;
 char **prom_envp;
 
-void prom_init_cmdline(void)
+void __init prom_init_cmdline(void)
 {
 	int i;
 
@@ -104,7 +104,7 @@ static inline void str2eaddr(unsigned char *ea, unsigned char *str)
 	}
 }
 
-int prom_get_ethernet_addr(char *ethernet_addr)
+int __init prom_get_ethernet_addr(char *ethernet_addr)
 {
 	char *ethaddr_str;
 
@@ -123,7 +123,6 @@ int prom_get_ethernet_addr(char *ethernet_addr)
 
 	return 0;
 }
-EXPORT_SYMBOL(prom_get_ethernet_addr);
 
 void __init prom_free_prom_memory(void)
 {
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index ed9bb709c9a3..5042d51b0512 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -59,7 +59,7 @@ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE
 hostprogs-y := calc_vmlinuz_load_addr
 
 VMLINUZ_LOAD_ADDRESS = $(shell $(obj)/calc_vmlinuz_load_addr \
-		$(objtree)/$(KBUILD_IMAGE) $(VMLINUX_LOAD_ADDRESS))
+		$(obj)/vmlinux.bin $(VMLINUX_LOAD_ADDRESS))
 
 vmlinuzobjs-y += $(obj)/piggy.o
 
@@ -105,4 +105,4 @@ OBJCOPYFLAGS_vmlinuz.srec := $(OBJCOPYFLAGS) -S -O srec
 vmlinuz.srec: vmlinuz
 	$(call cmd,objcopy)
 
-clean-files := $(objtree)/vmlinuz.*
+clean-files := $(objtree)/vmlinuz $(objtree)/vmlinuz.{32,ecoff,bin,srec}
diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index 094c17e38e16..47323ca452dc 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -83,3 +83,7 @@ config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	select SPARSEMEM_STATIC
 	depends on CPU_CAVIUM_OCTEON
+
+config CAVIUM_OCTEON_HELPER
+	def_bool y
+	depends on OCTEON_ETHERNET || PCI
diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c
index c664c8cc2b42..a5b427909b5c 100644
--- a/arch/mips/cavium-octeon/cpu.c
+++ b/arch/mips/cavium-octeon/cpu.c
@@ -41,7 +41,7 @@ static int cnmips_cu2_call(struct notifier_block *nfb, unsigned long action,
 	return NOTIFY_OK;		/* Let default notifier send signals */
 }
 
-static int cnmips_cu2_setup(void)
+static int __init cnmips_cu2_setup(void)
 {
 	return cu2_notifier(cnmips_cu2_call, 0);
 }
diff --git a/arch/mips/cavium-octeon/executive/Makefile b/arch/mips/cavium-octeon/executive/Makefile
index 2fd66db6939e..7f41c5be2190 100644
--- a/arch/mips/cavium-octeon/executive/Makefile
+++ b/arch/mips/cavium-octeon/executive/Makefile
@@ -11,4 +11,4 @@
 
 obj-y += cvmx-bootmem.o cvmx-l2c.o cvmx-sysinfo.o octeon-model.o
 
-obj-$(CONFIG_PCI) += cvmx-helper-errata.o cvmx-helper-jtag.o
+obj-$(CONFIG_CAVIUM_OCTEON_HELPER) += cvmx-helper-errata.o cvmx-helper-jtag.o
diff --git a/arch/mips/dec/Platform b/arch/mips/dec/Platform
index 3adbcbd95db1..cf55a6f4e720 100644
--- a/arch/mips/dec/Platform
+++ b/arch/mips/dec/Platform
@@ -1,7 +1,7 @@
 #
 # DECstation family
 #
-platform-$(CONFIG_MACH_DECSTATION)	= dec/
+platform-$(CONFIG_MACH_DECSTATION)	+= dec/
 cflags-$(CONFIG_MACH_DECSTATION)	+= \
 			-I$(srctree)/arch/mips/include/asm/mach-dec
 libs-$(CONFIG_MACH_DECSTATION)		+= arch/mips/dec/prom/
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index c63c56bfd184..47d87da379f9 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -782,6 +782,10 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
  */
 #define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
 
+#else /* !CONFIG_64BIT */
+
+#include <asm-generic/atomic64.h>
+
 #endif /* CONFIG_64BIT */
 
 /*
diff --git a/arch/mips/include/asm/cop2.h b/arch/mips/include/asm/cop2.h
index 2cb2f0c2c4f8..3532e2c5f098 100644
--- a/arch/mips/include/asm/cop2.h
+++ b/arch/mips/include/asm/cop2.h
@@ -24,7 +24,7 @@ extern int cu2_notifier_call_chain(unsigned long val, void *v);
 
 #define cu2_notifier(fn, pri)						\
 ({									\
-	static struct notifier_block fn##_nb __cpuinitdata = {		\
+	static struct notifier_block fn##_nb = {			\
 		.notifier_call = fn,					\
 		.priority = pri						\
 	};								\
diff --git a/arch/mips/include/asm/fcntl.h b/arch/mips/include/asm/fcntl.h
index e482fe90fe88..75eddedcfc3e 100644
--- a/arch/mips/include/asm/fcntl.h
+++ b/arch/mips/include/asm/fcntl.h
@@ -56,6 +56,7 @@
  */
 
 #ifdef CONFIG_32BIT
+#include <linux/types.h>
 
 struct flock {
 	short	l_type;
diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h
index 9b9436a4d816..86548da650e7 100644
--- a/arch/mips/include/asm/gic.h
+++ b/arch/mips/include/asm/gic.h
@@ -321,6 +321,7 @@ struct gic_intrmask_regs {
  */
 struct gic_intr_map {
 	unsigned int cpunum;	/* Directed to this CPU */
+#define GIC_UNUSED		0xdead			/* Dummy data */
 	unsigned int pin;	/* Directed to this Pin */
 	unsigned int polarity;	/* Polarity : +/-	*/
 	unsigned int trigtype;	/* Trigger  : Edge/Levl */
diff --git a/arch/mips/include/asm/mach-tx49xx/kmalloc.h b/arch/mips/include/asm/mach-tx49xx/kmalloc.h
index b74caf65482b..ff9a8b86cb93 100644
--- a/arch/mips/include/asm/mach-tx49xx/kmalloc.h
+++ b/arch/mips/include/asm/mach-tx49xx/kmalloc.h
@@ -1,6 +1,6 @@
 #ifndef __ASM_MACH_TX49XX_KMALLOC_H
 #define __ASM_MACH_TX49XX_KMALLOC_H
 
-#define ARCH_KMALLOC_MINALIGN	L1_CACHE_BYTES
+#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
 
 #endif /* __ASM_MACH_TX49XX_KMALLOC_H */
diff --git a/arch/mips/include/asm/mips-boards/maltaint.h b/arch/mips/include/asm/mips-boards/maltaint.h
index cea872fc6f5c..d11aa02a956a 100644
--- a/arch/mips/include/asm/mips-boards/maltaint.h
+++ b/arch/mips/include/asm/mips-boards/maltaint.h
@@ -88,9 +88,6 @@
 
 #define GIC_EXT_INTR(x)		x
 
-/* Dummy data */
-#define X			0xdead
-
 /* External Interrupts used for IPI */
 #define GIC_IPI_EXT_INTR_RESCHED_VPE0	16
 #define GIC_IPI_EXT_INTR_CALLFNC_VPE0	17
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index a16beafcea91..e59cd1ac09c2 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -150,6 +150,20 @@ typedef struct { unsigned long pgprot; } pgprot_t;
     ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET)
 #endif
 #define __va(x)		((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET))
+
+/*
+ * RELOC_HIDE was originally added by 6007b903dfe5f1d13e0c711ac2894bdd4a61b1ad
+ * (lmo) rsp. 8431fd094d625b94d364fe393076ccef88e6ce18 (kernel.org).  The
+ * discussion can be found in lkml posting
+ * <a2ebde260608230500o3407b108hc03debb9da6e62c@mail.gmail.com> which is
+ * archived at http://lists.linuxcoding.com/kernel/2006-q3/msg17360.html
+ *
+ * It is unclear if the misscompilations mentioned in
+ * http://lkml.org/lkml/2010/8/8/138 also affect MIPS so we keep this one
+ * until GCC 3.x has been retired before we can apply
+ * https://patchwork.linux-mips.org/patch/1541/
+ */
+
 #define __pa_symbol(x)	__pa(RELOC_HIDE((unsigned long)(x), 0))
 
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
diff --git a/arch/mips/include/asm/siginfo.h b/arch/mips/include/asm/siginfo.h
index 96e28f18dad1..1ca64b4d33d9 100644
--- a/arch/mips/include/asm/siginfo.h
+++ b/arch/mips/include/asm/siginfo.h
@@ -88,6 +88,7 @@ typedef struct siginfo {
 #ifdef __ARCH_SI_TRAPNO
 			int _trapno;	/* TRAP # which caused the signal */
 #endif
+			short _addr_lsb;
 		} _sigfault;
 
 		/* SIGPOLL, SIGXFSZ (To do ...)  */
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 2376f2e06e47..70df9c0d3c5b 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -146,7 +146,8 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define _TIF_LOAD_WATCH		(1<<TIF_LOAD_WATCH)
 
 /* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK		(0x0000ffef & ~_TIF_SECCOMP)
+#define _TIF_WORK_MASK		(0x0000ffef &				\
+					~(_TIF_SECCOMP | _TIF_SYSCALL_AUDIT))
 /* work to do on any return to u-space */
 #define _TIF_ALLWORK_MASK	(0x8000ffff & ~_TIF_SECCOMP)
 
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index baa318a59c97..550725b881d5 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -356,16 +356,19 @@
 #define __NR_perf_event_open		(__NR_Linux + 333)
 #define __NR_accept4			(__NR_Linux + 334)
 #define __NR_recvmmsg			(__NR_Linux + 335)
+#define __NR_fanotify_init		(__NR_Linux + 336)
+#define __NR_fanotify_mark		(__NR_Linux + 337)
+#define __NR_prlimit64			(__NR_Linux + 338)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		335
+#define __NR_Linux_syscalls		338
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		335
+#define __NR_O32_Linux_syscalls		338
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -668,16 +671,19 @@
 #define __NR_perf_event_open		(__NR_Linux + 292)
 #define __NR_accept4			(__NR_Linux + 293)
 #define __NR_recvmmsg			(__NR_Linux + 294)
+#define __NR_fanotify_init		(__NR_Linux + 295)
+#define __NR_fanotify_mark		(__NR_Linux + 296)
+#define __NR_prlimit64			(__NR_Linux + 297)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		294
+#define __NR_Linux_syscalls		297
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		294
+#define __NR_64_Linux_syscalls		297
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -985,16 +991,19 @@
 #define __NR_accept4			(__NR_Linux + 297)
 #define __NR_recvmmsg			(__NR_Linux + 298)
 #define __NR_getdents64			(__NR_Linux + 299)
+#define __NR_fanotify_init		(__NR_Linux + 300)
+#define __NR_fanotify_mark		(__NR_Linux + 301)
+#define __NR_prlimit64			(__NR_Linux + 302)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		299
+#define __NR_Linux_syscalls		302
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		299
+#define __NR_N32_Linux_syscalls		302
 
 #ifdef __KERNEL__
 
diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform
index 6a97230e3d05..ba91be9c21ef 100644
--- a/arch/mips/jz4740/Platform
+++ b/arch/mips/jz4740/Platform
@@ -1,3 +1,3 @@
-core-$(CONFIG_MACH_JZ4740)	+= arch/mips/jz4740/
+platform-$(CONFIG_MACH_JZ4740)	+= jz4740/
 cflags-$(CONFIG_MACH_JZ4740)	+= -I$(srctree)/arch/mips/include/asm/mach-jz4740
 load-$(CONFIG_MACH_JZ4740)	+= 0xffffffff80010000
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 0176ed015c89..32103cc2a257 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -40,7 +40,6 @@ int __compute_return_epc(struct pt_regs *regs)
 		return -EFAULT;
 	}
 
-	regs->regs[0] = 0;
 	switch (insn.i_format.opcode) {
 	/*
 	 * jr and jalr are in r_format format.
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index b181f2f0ea8e..82ba9f62f49e 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -7,7 +7,6 @@
 #include <asm/io.h>
 #include <asm/gic.h>
 #include <asm/gcmpregs.h>
-#include <asm/mips-boards/maltaint.h>
 #include <asm/irq.h>
 #include <linux/hardirq.h>
 #include <asm-generic/bitops/find.h>
@@ -131,7 +130,7 @@ static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	int		i;
 
 	irq -= _irqbase;
-	pr_debug(KERN_DEBUG "%s(%d) called\n", __func__, irq);
+	pr_debug("%s(%d) called\n", __func__, irq);
 	cpumask_and(&tmp, cpumask, cpu_online_mask);
 	if (cpus_empty(tmp))
 		return -1;
@@ -222,7 +221,7 @@ static void __init gic_basic_init(int numintrs, int numvpes,
 	/* Setup specifics */
 	for (i = 0; i < mapsize; i++) {
 		cpu = intrmap[i].cpunum;
-		if (cpu == X)
+		if (cpu == GIC_UNUSED)
 			continue;
 		if (cpu == 0 && i != 0 && intrmap[i].flags == 0)
 			continue;
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index 1f4e2fa64140..f4546e97c60d 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -283,7 +283,7 @@ static int kgdb_mips_notify(struct notifier_block *self, unsigned long cmd,
 	struct pt_regs *regs = args->regs;
 	int trap = (regs->cp0_cause & 0x7c) >> 2;
 
-	/* Userpace events, ignore. */
+	/* Userspace events, ignore. */
 	if (user_mode(regs))
 		return NOTIFY_DONE;
 
diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c
index 80e2ba694bab..29811f043399 100644
--- a/arch/mips/kernel/kspd.c
+++ b/arch/mips/kernel/kspd.c
@@ -251,7 +251,7 @@ void sp_work_handle_request(void)
  		memset(&tz, 0, sizeof(tz));
  		if ((ret.retval = sp_syscall(__NR_gettimeofday, (int)&tv,
 					     (int)&tz, 0, 0)) == 0)
-		ret.retval = tv.tv_sec;
+			ret.retval = tv.tv_sec;
 		break;
 
  	case MTSP_SYSCALL_EXIT:
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index c2dab140dc98..6343b4a5b835 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -341,3 +341,10 @@ asmlinkage long sys32_lookup_dcookie(u32 a0, u32 a1, char __user *buf,
 {
 	return sys_lookup_dcookie(merge_64(a0, a1), buf, len);
 }
+
+SYSCALL_DEFINE6(32_fanotify_mark, int, fanotify_fd, unsigned int, flags,
+		u64, a3, u64, a4, int, dfd, const char  __user *, pathname)
+{
+	return sys_fanotify_mark(fanotify_fd, flags, merge_64(a3, a4),
+				 dfd, pathname);
+}
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index c51b95ff8644..c8777333e198 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -536,7 +536,7 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
 {
 	/* do the secure computing check first */
 	if (!entryexit)
-		secure_computing(regs->regs[0]);
+		secure_computing(regs->regs[2]);
 
 	if (unlikely(current->audit_context) && entryexit)
 		audit_syscall_exit(AUDITSC_RESULT(regs->regs[2]),
@@ -565,7 +565,7 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
 
 out:
 	if (unlikely(current->audit_context) && !entryexit)
-		audit_syscall_entry(audit_arch(), regs->regs[0],
+		audit_syscall_entry(audit_arch(), regs->regs[2],
 				    regs->regs[4], regs->regs[5],
 				    regs->regs[6], regs->regs[7]);
 }
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 17202bbe843f..fbaabad0e6e2 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -63,9 +63,9 @@ stack_done:
 	sw	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	lw	t1, PT_R2(sp)		# syscall number
 	negu	v0			# error
-	sw	v0, PT_R0(sp)		# set flag for syscall
-					# restarting
+	sw	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sw	v0, PT_R2(sp)		# result
 
 o32_syscall_exit:
@@ -104,9 +104,9 @@ syscall_trace_entry:
 	sw	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	lw	t1, PT_R2(sp)		# syscall number
 	negu	v0			# error
-	sw	v0, PT_R0(sp)		# set flag for syscall
-					# restarting
+	sw	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sw	v0, PT_R2(sp)		# result
 
 	j	syscall_exit
@@ -169,8 +169,7 @@ stackargs:
 	 * We probably should handle this case a bit more drastic.
 	 */
 bad_stack:
-	negu	v0				# error
-	sw	v0, PT_R0(sp)
+	li	v0, EFAULT
 	sw	v0, PT_R2(sp)
 	li	t0, 1				# set error flag
 	sw	t0, PT_R7(sp)
@@ -583,7 +582,10 @@ einval:	li	v0, -ENOSYS
 	sys	sys_rt_tgsigqueueinfo	4
 	sys	sys_perf_event_open	5
 	sys	sys_accept4		4
-	sys     sys_recvmmsg            5
+	sys	sys_recvmmsg		5	/* 4335 */
+	sys	sys_fanotify_init	2
+	sys	sys_fanotify_mark	6
+	sys	sys_prlimit64		4
 	.endm
 
 	/* We pre-compute the number of _instruction_ bytes needed to
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index a8a6c596eb04..3f4179283207 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -66,9 +66,9 @@ NESTED(handle_sys64, PT_SIZE, sp)
 	sd	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	ld	t1, PT_R2(sp)		# syscall number
 	dnegu	v0			# error
-	sd	v0, PT_R0(sp)		# set flag for syscall
-					# restarting
+	sd	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sd	v0, PT_R2(sp)		# result
 
 n64_syscall_exit:
@@ -109,8 +109,9 @@ syscall_trace_entry:
 	sd	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	ld	t1, PT_R2(sp)		# syscall number
 	dnegu	v0			# error
-	sd	v0, PT_R0(sp)		# set flag for syscall restarting
+	sd	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sd	v0, PT_R2(sp)		# result
 
 	j	syscall_exit
@@ -416,9 +417,12 @@ sys_call_table:
 	PTR	sys_pipe2
 	PTR	sys_inotify_init1
 	PTR	sys_preadv
-	PTR	sys_pwritev			/* 5390 */
+	PTR	sys_pwritev			/* 5290 */
 	PTR	sys_rt_tgsigqueueinfo
 	PTR	sys_perf_event_open
 	PTR	sys_accept4
-	PTR     sys_recvmmsg
+	PTR	sys_recvmmsg
+	PTR	sys_fanotify_init		/* 5295 */
+	PTR	sys_fanotify_mark
+	PTR	sys_prlimit64
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index a3d66137731a..f08ece6d8acc 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -65,8 +65,9 @@ NESTED(handle_sysn32, PT_SIZE, sp)
 	sd	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	ld	t1, PT_R2(sp)		# syscall number
 	dnegu	v0			# error
-	sd	v0, PT_R0(sp)		# set flag for syscall restarting
+	sd	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sd	v0, PT_R2(sp)		# result
 
 	local_irq_disable		# make sure need_resched and
@@ -106,8 +107,9 @@ n32_syscall_trace_entry:
 	sd	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	ld	t1, PT_R2(sp)		# syscall number
 	dnegu	v0			# error
-	sd	v0, PT_R0(sp)		# set flag for syscall restarting
+	sd	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sd	v0, PT_R2(sp)		# result
 
 	j	syscall_exit
@@ -320,10 +322,10 @@ EXPORT(sysn32_call_table)
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
 	PTR	sys_sysmips
-	PTR	sys_io_setup			/* 6200 */
+	PTR	compat_sys_io_setup			/* 6200 */
 	PTR	sys_io_destroy
-	PTR	sys_io_getevents
-	PTR	sys_io_submit
+	PTR	compat_sys_io_getevents
+	PTR	compat_sys_io_submit
 	PTR	sys_io_cancel
 	PTR	sys_exit_group			/* 6205 */
 	PTR	sys_lookup_dcookie
@@ -419,5 +421,8 @@ EXPORT(sysn32_call_table)
 	PTR	sys_perf_event_open
 	PTR	sys_accept4
 	PTR     compat_sys_recvmmsg
-	PTR     sys_getdents
+	PTR     sys_getdents64
+	PTR	sys_fanotify_init		/* 6300 */
+	PTR	sys_fanotify_mark
+	PTR	sys_prlimit64
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 813689ef2384..78d768a3e19d 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -93,8 +93,9 @@ NESTED(handle_sys, PT_SIZE, sp)
 	sd	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	ld	t1, PT_R2(sp)		# syscall number
 	dnegu	v0			# error
-	sd	v0, PT_R0(sp)		# flag for syscall restarting
+	sd	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sd	v0, PT_R2(sp)		# result
 
 o32_syscall_exit:
@@ -142,8 +143,9 @@ trace_a_syscall:
 	sd	t0, PT_R7(sp)		# set error flag
 	beqz	t0, 1f
 
+	ld	t1, PT_R2(sp)		# syscall number
 	dnegu	v0			# error
-	sd	v0, PT_R0(sp)		# set flag for syscall restarting
+	sd	t1, PT_R0(sp)		# save it for syscall restarting
 1:	sd	v0, PT_R2(sp)		# result
 
 	j	syscall_exit
@@ -154,8 +156,7 @@ trace_a_syscall:
 	 * The stackpointer for a call with more than 4 arguments is bad.
 	 */
 bad_stack:
-	dnegu	v0			# error
-	sd	v0, PT_R0(sp)
+	li	v0, EFAULT
 	sd	v0, PT_R2(sp)
 	li	t0, 1			# set error flag
 	sd	t0, PT_R7(sp)
@@ -444,10 +445,10 @@ sys_call_table:
 	PTR	compat_sys_futex
 	PTR	compat_sys_sched_setaffinity
 	PTR	compat_sys_sched_getaffinity	/* 4240 */
-	PTR	sys_io_setup
+	PTR	compat_sys_io_setup
 	PTR	sys_io_destroy
-	PTR	sys_io_getevents
-	PTR	sys_io_submit
+	PTR	compat_sys_io_getevents
+	PTR	compat_sys_io_submit
 	PTR	sys_io_cancel			/* 4245 */
 	PTR	sys_exit_group
 	PTR	sys32_lookup_dcookie
@@ -538,5 +539,8 @@ sys_call_table:
 	PTR	compat_sys_rt_tgsigqueueinfo
 	PTR	sys_perf_event_open
 	PTR	sys_accept4
-	PTR     compat_sys_recvmmsg
+	PTR	compat_sys_recvmmsg		/* 4335 */
+	PTR	sys_fanotify_init
+	PTR	sys_32_fanotify_mark
+	PTR	sys_prlimit64
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 2099d5a4c4b7..5922342bca39 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -390,7 +390,6 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 {
 	struct rt_sigframe __user *frame;
 	sigset_t set;
-	stack_t st;
 	int sig;
 
 	frame = (struct rt_sigframe __user *) regs.regs[29];
@@ -411,11 +410,9 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	else if (sig)
 		force_sig(sig, current);
 
-	if (__copy_from_user(&st, &frame->rs_uc.uc_stack, sizeof(st)))
-		goto badframe;
 	/* It is more difficult to avoid calling this function than to
 	   call it and ignore errors.  */
-	do_sigaltstack((stack_t __user *)&st, NULL, regs.regs[29]);
+	do_sigaltstack(&frame->rs_uc.uc_stack, NULL, regs.regs[29]);
 
 	/*
 	 * Don't let your children do this ...
@@ -550,23 +547,26 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 	struct mips_abi *abi = current->thread.abi;
 	void *vdso = current->mm->context.vdso;
 
-	switch(regs->regs[0]) {
-	case ERESTART_RESTARTBLOCK:
-	case ERESTARTNOHAND:
-		regs->regs[2] = EINTR;
-		break;
-	case ERESTARTSYS:
-		if (!(ka->sa.sa_flags & SA_RESTART)) {
+	if (regs->regs[0]) {
+		switch(regs->regs[2]) {
+		case ERESTART_RESTARTBLOCK:
+		case ERESTARTNOHAND:
 			regs->regs[2] = EINTR;
 			break;
+		case ERESTARTSYS:
+			if (!(ka->sa.sa_flags & SA_RESTART)) {
+				regs->regs[2] = EINTR;
+				break;
+			}
+		/* fallthrough */
+		case ERESTARTNOINTR:
+			regs->regs[7] = regs->regs[26];
+			regs->regs[2] = regs->regs[0];
+			regs->cp0_epc -= 4;
 		}
-	/* fallthrough */
-	case ERESTARTNOINTR:		/* Userland will reload $v0.  */
-		regs->regs[7] = regs->regs[26];
-		regs->cp0_epc -= 8;
-	}
 
-	regs->regs[0] = 0;		/* Don't deal with this again.  */
+		regs->regs[0] = 0;		/* Don't deal with this again.  */
+	}
 
 	if (sig_uses_siginfo(ka))
 		ret = abi->setup_rt_frame(vdso + abi->rt_signal_return_offset,
@@ -575,6 +575,9 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 		ret = abi->setup_frame(vdso + abi->signal_return_offset,
 				       ka, regs, sig, oldset);
 
+	if (ret)
+		return ret;
+
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
 	if (!(ka->sa.sa_flags & SA_NODEFER))
@@ -622,17 +625,13 @@ static void do_signal(struct pt_regs *regs)
 		return;
 	}
 
-	/*
-	 * Who's code doesn't conform to the restartable syscall convention
-	 * dies here!!!  The li instruction, a single machine instruction,
-	 * must directly be followed by the syscall instruction.
-	 */
 	if (regs->regs[0]) {
 		if (regs->regs[2] == ERESTARTNOHAND ||
 		    regs->regs[2] == ERESTARTSYS ||
 		    regs->regs[2] == ERESTARTNOINTR) {
+			regs->regs[2] = regs->regs[0];
 			regs->regs[7] = regs->regs[26];
-			regs->cp0_epc -= 8;
+			regs->cp0_epc -= 4;
 		}
 		if (regs->regs[2] == ERESTART_RESTARTBLOCK) {
 			regs->regs[2] = current->thread.abi->restart;
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index 2c5df818c65a..ee24d814d5b9 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -109,6 +109,7 @@ asmlinkage int sysn32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)
 asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 {
 	struct rt_sigframe_n32 __user *frame;
+	mm_segment_t old_fs;
 	sigset_t set;
 	stack_t st;
 	s32 sp;
@@ -143,7 +144,11 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	/* It is more difficult to avoid calling this function than to
 	   call it and ignore errors.  */
+	old_fs = get_fs();
+	set_fs(KERNEL_DS);
 	do_sigaltstack((stack_t __user *)&st, NULL, regs.regs[29]);
+	set_fs(old_fs);
+
 
 	/*
 	 * Don't let your children do this ...
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 69b039ca8d83..33d5a5ce4a29 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -109,8 +109,6 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	unsigned long value;
 	unsigned int res;
 
-	regs->regs[0] = 0;
-
 	/*
 	 * This load never faults.
 	 */
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 7ba890860d98..469d4019f795 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -44,27 +44,39 @@ static inline int cpu_is_noncoherent_r10000(struct device *dev)
 
 static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
 {
+	gfp_t dma_flag;
+
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-#ifdef CONFIG_ZONE_DMA
+#ifdef CONFIG_ISA
 	if (dev == NULL)
-		gfp |= __GFP_DMA;
-	else if (dev->coherent_dma_mask < DMA_BIT_MASK(24))
-		gfp |= __GFP_DMA;
+		dma_flag = __GFP_DMA;
 	else
 #endif
-#ifdef CONFIG_ZONE_DMA32
+#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
 	     if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
-		gfp |= __GFP_DMA32;
+			dma_flag = __GFP_DMA;
+	else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
+			dma_flag = __GFP_DMA32;
+	else
+#endif
+#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
+	     if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
+		dma_flag = __GFP_DMA32;
+	else
+#endif
+#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
+	     if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
+		dma_flag = __GFP_DMA;
 	else
 #endif
-		;
+		dma_flag = 0;
 
 	/* Don't invoke OOM killer */
 	gfp |= __GFP_NORETRY;
 
-	return gfp;
+	return gfp | dma_flag;
 }
 
 void *dma_alloc_noncoherent(struct device *dev, size_t size,
diff --git a/arch/mips/mm/sc-rm7k.c b/arch/mips/mm/sc-rm7k.c
index 1ef75cd80a0d..274af3be1442 100644
--- a/arch/mips/mm/sc-rm7k.c
+++ b/arch/mips/mm/sc-rm7k.c
@@ -30,7 +30,7 @@
 #define tc_lsize	32
 
 extern unsigned long icache_way_size, dcache_way_size;
-unsigned long tcache_size;
+static unsigned long tcache_size;
 
 #include <asm/r4kcache.h>
 
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index 15949b0be811..b79b24afe3a2 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -385,6 +385,8 @@ static int __initdata msc_nr_eicirqs = ARRAY_SIZE(msc_eicirqmap);
  */
 
 #define GIC_CPU_NMI GIC_MAP_TO_NMI_MSK
+#define X GIC_UNUSED
+
 static struct gic_intr_map gic_intr_map[GIC_NUM_INTRS] = {
 	{ X, X,		   X,		X,		0 },
 	{ X, X,		   X,	 	X,		0 },
@@ -404,6 +406,7 @@ static struct gic_intr_map gic_intr_map[GIC_NUM_INTRS] = {
 	{ X, X,		   X,		X,	        0 },
 	/* The remainder of this table is initialised by fill_ipi_map */
 };
+#undef X
 
 /*
  * GCMP needs to be detected before any SMP initialisation
diff --git a/arch/mips/pci/pci-rc32434.c b/arch/mips/pci/pci-rc32434.c
index 71f7d27b0d4c..f31218e17d3c 100644
--- a/arch/mips/pci/pci-rc32434.c
+++ b/arch/mips/pci/pci-rc32434.c
@@ -118,7 +118,7 @@ static int __init rc32434_pcibridge_init(void)
 	if (!((pcicvalue == PCIM_H_EA) ||
 	      (pcicvalue == PCIM_H_IA_FIX) ||
 	      (pcicvalue == PCIM_H_IA_RR))) {
-		pr_err(KERN_ERR "PCI init error!!!\n");
+		pr_err("PCI init error!!!\n");
 		/* Not in Host Mode, return ERROR */
 		return -1;
 	}
diff --git a/arch/mips/pnx8550/common/reset.c b/arch/mips/pnx8550/common/reset.c
index fadd8744a6bc..e7a12ff304b9 100644
--- a/arch/mips/pnx8550/common/reset.c
+++ b/arch/mips/pnx8550/common/reset.c
@@ -22,29 +22,19 @@
  */
 #include <linux/kernel.h>
 
+#include <asm/processor.h>
 #include <asm/reboot.h>
 #include <glb.h>
 
 void pnx8550_machine_restart(char *command)
 {
-	char head[] = "************* Machine restart *************";
-	char foot[] = "*******************************************";
-
-	printk("\n\n");
-	printk("%s\n", head);
-	if (command != NULL)
-		printk("* %s\n", command);
-	printk("%s\n", foot);
-
 	PNX8550_RST_CTL = PNX8550_RST_DO_SW_RST;
 }
 
 void pnx8550_machine_halt(void)
 {
-	printk("*** Machine halt. (Not implemented) ***\n");
-}
-
-void pnx8550_machine_power_off(void)
-{
-	printk("*** Machine power off.  (Not implemented) ***\n");
+	while (1) {
+		if (cpu_wait)
+			cpu_wait();
+	}
 }
diff --git a/arch/mips/pnx8550/common/setup.c b/arch/mips/pnx8550/common/setup.c
index 64246c9c875c..43cb3945fdbf 100644
--- a/arch/mips/pnx8550/common/setup.c
+++ b/arch/mips/pnx8550/common/setup.c
@@ -44,7 +44,6 @@
 extern void __init board_setup(void);
 extern void pnx8550_machine_restart(char *);
 extern void pnx8550_machine_halt(void);
-extern void pnx8550_machine_power_off(void);
 extern struct resource ioport_resource;
 extern struct resource iomem_resource;
 extern char *prom_getcmdline(void);
@@ -100,7 +99,7 @@ void __init plat_mem_setup(void)
 
         _machine_restart = pnx8550_machine_restart;
         _machine_halt = pnx8550_machine_halt;
-        pm_power_off = pnx8550_machine_power_off;
+        pm_power_off = pnx8550_machine_halt;
 
 	/* Clear the Global 2 Register, PCI Inta Output Enable Registers
 	   Bit 1:Enable DAC Powerdown
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 444b9f918fdf..7c2a2f7f8dc1 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -8,7 +8,6 @@ mainmenu "Linux Kernel Configuration"
 config MN10300
 	def_bool y
 	select HAVE_OPROFILE
-	select HAVE_ARCH_TRACEHOOK
 
 config AM33
 	def_bool y
diff --git a/arch/mn10300/Kconfig.debug b/arch/mn10300/Kconfig.debug
index ff80e86b9bd2..ce83c74b3fd7 100644
--- a/arch/mn10300/Kconfig.debug
+++ b/arch/mn10300/Kconfig.debug
@@ -101,7 +101,7 @@ config GDBSTUB_DEBUG_BREAKPOINT
 
 choice
 	prompt "GDB stub port"
-	default GDBSTUB_TTYSM0
+	default GDBSTUB_ON_TTYSM0
 	depends on GDBSTUB
 	help
 	  Select the serial port used for GDB-stub.
diff --git a/arch/mn10300/include/asm/bitops.h b/arch/mn10300/include/asm/bitops.h
index f49ac49e09ad..3f50e9661076 100644
--- a/arch/mn10300/include/asm/bitops.h
+++ b/arch/mn10300/include/asm/bitops.h
@@ -229,9 +229,9 @@ int ffs(int x)
 #include <asm-generic/bitops/hweight.h>
 
 #define ext2_set_bit_atomic(lock, nr, addr) \
-	test_and_set_bit((nr) ^ 0x18, (addr))
+	test_and_set_bit((nr), (addr))
 #define ext2_clear_bit_atomic(lock, nr, addr) \
-	test_and_clear_bit((nr) ^ 0x18, (addr))
+	test_and_clear_bit((nr), (addr))
 
 #include <asm-generic/bitops/ext2-non-atomic.h>
 #include <asm-generic/bitops/minix-le.h>
diff --git a/arch/mn10300/include/asm/signal.h b/arch/mn10300/include/asm/signal.h
index 7e891fce2370..1865d72a86ff 100644
--- a/arch/mn10300/include/asm/signal.h
+++ b/arch/mn10300/include/asm/signal.h
@@ -78,7 +78,7 @@ typedef unsigned long sigset_t;
 
 /* These should not be considered constants from userland.  */
 #define SIGRTMIN	32
-#define SIGRTMAX	(_NSIG-1)
+#define SIGRTMAX	_NSIG
 
 /*
  * SA_FLAGS values:
diff --git a/arch/mn10300/kernel/module.c b/arch/mn10300/kernel/module.c
index 6aea7fd76993..196a111e2e29 100644
--- a/arch/mn10300/kernel/module.c
+++ b/arch/mn10300/kernel/module.c
@@ -206,7 +206,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	return module_bug_finalize(hdr, sechdrs, me);
+	return 0;
 }
 
 /*
@@ -214,5 +214,4 @@ int module_finalize(const Elf_Ehdr *hdr,
  */
 void module_arch_cleanup(struct module *mod)
 {
-	module_bug_cleanup(mod);
 }
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index 717db14c2cc3..d4de05ab7864 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -65,10 +65,10 @@ asmlinkage long sys_sigaction(int sig,
 		old_sigset_t mask;
 		if (verify_area(VERIFY_READ, act, sizeof(*act)) ||
 		    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-		    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+		    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) ||
+		    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+		    __get_user(mask, &act->sa_mask))
 			return -EFAULT;
-		__get_user(new_ka.sa.sa_flags, &act->sa_flags);
-		__get_user(mask, &act->sa_mask);
 		siginitset(&new_ka.sa.sa_mask, mask);
 	}
 
@@ -77,10 +77,10 @@ asmlinkage long sys_sigaction(int sig,
 	if (!ret && oact) {
 		if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) ||
 		    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-		    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+		    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) ||
+		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+		    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
 			return -EFAULT;
-		__put_user(old_ka.sa.sa_flags, &oact->sa_flags);
-		__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
 	}
 
 	return ret;
@@ -102,6 +102,9 @@ static int restore_sigcontext(struct pt_regs *regs,
 {
 	unsigned int err = 0;
 
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
 	if (is_using_fpu(current))
 		fpu_kill_state(current);
 
@@ -330,8 +333,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
 	regs->d0 = sig;
 	regs->d1 = (unsigned long) &frame->sc;
 
-	set_fs(USER_DS);
-
 	/* the tracer may want to single-step inside the handler */
 	if (test_thread_flag(TIF_SINGLESTEP))
 		ptrace_notify(SIGTRAP);
@@ -345,7 +346,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
 	return 0;
 
 give_sigsegv:
-	force_sig(SIGSEGV, current);
+	force_sigsegv(sig, current);
 	return -EFAULT;
 }
 
@@ -413,8 +414,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->d0 = sig;
 	regs->d1 = (long) &frame->info;
 
-	set_fs(USER_DS);
-
 	/* the tracer may want to single-step inside the handler */
 	if (test_thread_flag(TIF_SINGLESTEP))
 		ptrace_notify(SIGTRAP);
@@ -428,10 +427,16 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	return 0;
 
 give_sigsegv:
-	force_sig(SIGSEGV, current);
+	force_sigsegv(sig, current);
 	return -EFAULT;
 }
 
+static inline void stepback(struct pt_regs *regs)
+{
+	regs->pc -= 2;
+	regs->orig_d0 = -1;
+}
+
 /*
  * handle the actual delivery of a signal to userspace
  */
@@ -459,7 +464,7 @@ static int handle_signal(int sig,
 			/* fallthrough */
 		case -ERESTARTNOINTR:
 			regs->d0 = regs->orig_d0;
-			regs->pc -= 2;
+			stepback(regs);
 		}
 	}
 
@@ -527,12 +532,12 @@ static void do_signal(struct pt_regs *regs)
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
 			regs->d0 = regs->orig_d0;
-			regs->pc -= 2;
+			stepback(regs);
 			break;
 
 		case -ERESTART_RESTARTBLOCK:
 			regs->d0 = __NR_restart_syscall;
-			regs->pc -= 2;
+			stepback(regs);
 			break;
 		}
 	}
diff --git a/arch/mn10300/mm/Makefile b/arch/mn10300/mm/Makefile
index 28b9d983db0c..1557277fbc5c 100644
--- a/arch/mn10300/mm/Makefile
+++ b/arch/mn10300/mm/Makefile
@@ -2,13 +2,11 @@
 # Makefile for the MN10300-specific memory management code
 #
 
+cacheflush-y	:= cache.o cache-mn10300.o
+cacheflush-$(CONFIG_MN10300_CACHE_WBACK) += cache-flush-mn10300.o
+
+cacheflush-$(CONFIG_MN10300_CACHE_DISABLED) := cache-disabled.o
+
 obj-y := \
 	init.o fault.o pgtable.o extable.o tlb-mn10300.o mmu-context.o \
-	misalignment.o dma-alloc.o
-
-ifneq ($(CONFIG_MN10300_CACHE_DISABLED),y)
-obj-y	+= cache.o cache-mn10300.o
-ifeq ($(CONFIG_MN10300_CACHE_WBACK),y)
-obj-y	+= cache-flush-mn10300.o
-endif
-endif
+	misalignment.o dma-alloc.o $(cacheflush-y)
diff --git a/arch/mn10300/mm/cache-disabled.c b/arch/mn10300/mm/cache-disabled.c
new file mode 100644
index 000000000000..f669ea42aba6
--- /dev/null
+++ b/arch/mn10300/mm/cache-disabled.c
@@ -0,0 +1,21 @@
+/* Handle the cache being disabled
+ *
+ * Copyright (C) 2010 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/mm.h>
+
+/*
+ * allow userspace to flush the instruction cache
+ */
+asmlinkage long sys_cacheflush(unsigned long start, unsigned long end)
+{
+	if (end < start)
+		return -EINVAL;
+	return 0;
+}
diff --git a/arch/mn10300/mm/cache.c b/arch/mn10300/mm/cache.c
index 1b76719ec1c3..9261217e8d2c 100644
--- a/arch/mn10300/mm/cache.c
+++ b/arch/mn10300/mm/cache.c
@@ -54,13 +54,30 @@ EXPORT_SYMBOL(flush_icache_page);
 void flush_icache_range(unsigned long start, unsigned long end)
 {
 #ifdef CONFIG_MN10300_CACHE_WBACK
-	unsigned long addr, size, off;
+	unsigned long addr, size, base, off;
 	struct page *page;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ppte, pte;
 
+	if (end > 0x80000000UL) {
+		/* addresses above 0xa0000000 do not go through the cache */
+		if (end > 0xa0000000UL) {
+			end = 0xa0000000UL;
+			if (start >= end)
+				return;
+		}
+
+		/* kernel addresses between 0x80000000 and 0x9fffffff do not
+		 * require page tables, so we just map such addresses directly */
+		base = (start >= 0x80000000UL) ? start : 0x80000000UL;
+		mn10300_dcache_flush_range(base, end);
+		if (base == start)
+			goto invalidate;
+		end = base;
+	}
+
 	for (; start < end; start += size) {
 		/* work out how much of the page to flush */
 		off = start & (PAGE_SIZE - 1);
@@ -104,6 +121,7 @@ void flush_icache_range(unsigned long start, unsigned long end)
 	}
 #endif
 
+invalidate:
 	mn10300_icache_inv();
 }
 EXPORT_SYMBOL(flush_icache_range);
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index 159a2b81e90c..6e81bb596e5b 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -941,11 +941,10 @@ int module_finalize(const Elf_Ehdr *hdr,
 	nsyms = newptr - (Elf_Sym *)symhdr->sh_addr;
 	DEBUGP("NEW num_symtab %lu\n", nsyms);
 	symhdr->sh_size = nsyms * sizeof(Elf_Sym);
-	return module_bug_finalize(hdr, sechdrs, me);
+	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
 	deregister_unwind_table(mod);
-	module_bug_cleanup(mod);
 }
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 477c663e0140..49cee9df225b 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -63,11 +63,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 		const Elf_Shdr *sechdrs, struct module *me)
 {
 	const Elf_Shdr *sect;
-	int err;
-
-	err = module_bug_finalize(hdr, sechdrs, me);
-	if (err)
-		return err;
 
 	/* Apply feature fixups */
 	sect = find_section(hdr, sechdrs, "__ftr_fixup");
@@ -101,5 +96,4 @@ int module_finalize(const Elf_Ehdr *hdr,
 
 void module_arch_cleanup(struct module *mod)
 {
-	module_bug_cleanup(mod);
 }
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 7109f5b1baa8..2300426e531a 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -138,6 +138,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 			ti->local_flags &= ~_TLF_RESTORE_SIGMASK;
 			sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
 		}
+		regs->trap = 0;
 		return 0;               /* no signals delivered */
 	}
 
@@ -164,6 +165,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 		ret = handle_rt_signal64(signr, &ka, &info, oldset, regs);
 	}
 
+	regs->trap = 0;
 	if (ret) {
 		spin_lock_irq(&current->sighand->siglock);
 		sigorsets(&current->blocked, &current->blocked,
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 266610119f66..b96a3a010c26 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -511,6 +511,7 @@ static long restore_user_regs(struct pt_regs *regs,
 	if (!sig)
 		save_r2 = (unsigned int)regs->gpr[2];
 	err = restore_general_regs(regs, sr);
+	regs->trap = 0;
 	err |= __get_user(msr, &sr->mc_gregs[PT_MSR]);
 	if (!sig)
 		regs->gpr[2] = (unsigned long) save_r2;
@@ -884,7 +885,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 	regs->nip = (unsigned long) ka->sa.sa_handler;
 	/* enter the signal handler in big-endian mode */
 	regs->msr &= ~MSR_LE;
-	regs->trap = 0;
 	return 1;
 
 badframe:
@@ -1228,7 +1228,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	regs->nip = (unsigned long) ka->sa.sa_handler;
 	/* enter the signal handler in big-endian mode */
 	regs->msr &= ~MSR_LE;
-	regs->trap = 0;
 
 	return 1;
 
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 2fe6fc64b614..27c4a4584f80 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -178,7 +178,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 	err |= __get_user(regs->xer, &sc->gp_regs[PT_XER]);
 	err |= __get_user(regs->ccr, &sc->gp_regs[PT_CCR]);
 	/* skip SOFTE */
-	err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]);
+	regs->trap = 0;
 	err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
 	err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
 	err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c
index 5b243bd3eb3b..3dc2a8d262b8 100644
--- a/arch/powerpc/platforms/512x/clock.c
+++ b/arch/powerpc/platforms/512x/clock.c
@@ -57,7 +57,7 @@ static struct clk *mpc5121_clk_get(struct device *dev, const char *id)
 	int id_match = 0;
 
 	if (dev == NULL || id == NULL)
-		return NULL;
+		return clk;
 
 	mutex_lock(&clocks_mutex);
 	list_for_each_entry(p, &clocks, node) {
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 45c0cb9b67e6..18c104820198 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -99,7 +99,7 @@ static void __init efika_pcisetup(void)
 	if (bus_range == NULL || len < 2 * sizeof(int)) {
 		printk(KERN_WARNING EFIKA_PLATFORM_NAME
 		       ": Can't get bus-range for %s\n", pcictrl->full_name);
-		return;
+		goto out_put;
 	}
 
 	if (bus_range[1] == bus_range[0])
@@ -111,12 +111,12 @@ static void __init efika_pcisetup(void)
 	printk(" controlled by %s\n", pcictrl->full_name);
 	printk("\n");
 
-	hose = pcibios_alloc_controller(of_node_get(pcictrl));
+	hose = pcibios_alloc_controller(pcictrl);
 	if (!hose) {
 		printk(KERN_WARNING EFIKA_PLATFORM_NAME
 		       ": Can't allocate PCI controller structure for %s\n",
 		       pcictrl->full_name);
-		return;
+		goto out_put;
 	}
 
 	hose->first_busno = bus_range[0];
@@ -124,6 +124,9 @@ static void __init efika_pcisetup(void)
 	hose->ops = &rtas_pci_ops;
 
 	pci_process_bridge_OF_ranges(hose, pcictrl, 0);
+	return;
+out_put:
+	of_node_put(pcictrl);
 }
 
 #else
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index 6e905314ad5d..41f3a7eda1de 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -325,12 +325,16 @@ int mpc5200_psc_ac97_gpio_reset(int psc_number)
 	clrbits32(&simple_gpio->simple_dvo, sync | out);
 	clrbits8(&wkup_gpio->wkup_dvo, reset);
 
-	/* wait at lease 1 us */
-	udelay(2);
+	/* wait for 1 us */
+	udelay(1);
 
 	/* Deassert reset */
 	setbits8(&wkup_gpio->wkup_dvo, reset);
 
+	/* wait at least 200ns */
+	/* 7 ~= (200ns * timebase) / ns2sec */
+	__delay(7);
+
 	/* Restore pin-muxing */
 	out_be32(&simple_gpio->port_config, mux);
 
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 22cfd634c355..f7167ee4604c 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -407,10 +407,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 {
 	vfree(me->arch.syminfo);
 	me->arch.syminfo = NULL;
-	return module_bug_finalize(hdr, sechdrs, me);
+	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
-	module_bug_cleanup(mod);
 }
diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c
index 43adddfe4c04..ae0be697a89e 100644
--- a/arch/sh/kernel/module.c
+++ b/arch/sh/kernel/module.c
@@ -149,13 +149,11 @@ int module_finalize(const Elf_Ehdr *hdr,
 	int ret = 0;
 
 	ret |= module_dwarf_finalize(hdr, sechdrs, me);
-	ret |= module_bug_finalize(hdr, sechdrs, me);
 
 	return ret;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
-	module_bug_cleanup(mod);
 	module_dwarf_cleanup(mod);
 }
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 357ced3c33ff..6318e622cfb0 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1038,6 +1038,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
+	pmap = NULL;
 	if (attr->type == PERF_TYPE_HARDWARE) {
 		if (attr->config >= sparc_pmu->max_events)
 			return -EINVAL;
@@ -1046,9 +1047,18 @@ static int __hw_perf_event_init(struct perf_event *event)
 		pmap = sparc_map_cache_event(attr->config);
 		if (IS_ERR(pmap))
 			return PTR_ERR(pmap);
-	} else
+	} else if (attr->type != PERF_TYPE_RAW)
 		return -EOPNOTSUPP;
 
+	if (pmap) {
+		hwc->event_base = perf_event_encode(pmap);
+	} else {
+		/* User gives us "(encoding << 16) | pic_mask" for
+		 * PERF_TYPE_RAW events.
+		 */
+		hwc->event_base = attr->config;
+	}
+
 	/* We save the enable bits in the config_base.  */
 	hwc->config_base = sparc_pmu->irq_bit;
 	if (!attr->exclude_user)
@@ -1058,8 +1068,6 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if (!attr->exclude_hv)
 		hwc->config_base |= sparc_pmu->hv_bit;
 
-	hwc->event_base = perf_event_encode(pmap);
-
 	n = 0;
 	if (event->group_leader != event) {
 		n = collect_events(event->group_leader,
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index ea22cd373c64..75fad425e249 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -453,8 +453,66 @@ static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	return err;
 }
 
-static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
-			  int signo, sigset_t *oldset)
+/* The I-cache flush instruction only works in the primary ASI, which
+ * right now is the nucleus, aka. kernel space.
+ *
+ * Therefore we have to kick the instructions out using the kernel
+ * side linear mapping of the physical address backing the user
+ * instructions.
+ */
+static void flush_signal_insns(unsigned long address)
+{
+	unsigned long pstate, paddr;
+	pte_t *ptep, pte;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+
+	/* Commit all stores of the instructions we are about to flush.  */
+	wmb();
+
+	/* Disable cross-call reception.  In this way even a very wide
+	 * munmap() on another cpu can't tear down the page table
+	 * hierarchy from underneath us, since that can't complete
+	 * until the IPI tlb flush returns.
+	 */
+
+	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
+	__asm__ __volatile__("wrpr %0, %1, %%pstate"
+				: : "r" (pstate), "i" (PSTATE_IE));
+
+	pgdp = pgd_offset(current->mm, address);
+	if (pgd_none(*pgdp))
+		goto out_irqs_on;
+	pudp = pud_offset(pgdp, address);
+	if (pud_none(*pudp))
+		goto out_irqs_on;
+	pmdp = pmd_offset(pudp, address);
+	if (pmd_none(*pmdp))
+		goto out_irqs_on;
+
+	ptep = pte_offset_map(pmdp, address);
+	pte = *ptep;
+	if (!pte_present(pte))
+		goto out_unmap;
+
+	paddr = (unsigned long) page_address(pte_page(pte));
+
+	__asm__ __volatile__("flush	%0 + %1"
+			     : /* no outputs */
+			     : "r" (paddr),
+			       "r" (address & (PAGE_SIZE - 1))
+			     : "memory");
+
+out_unmap:
+	pte_unmap(ptep);
+out_irqs_on:
+	__asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
+
+}
+
+static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
+			 int signo, sigset_t *oldset)
 {
 	struct signal_frame32 __user *sf;
 	int sigframe_size;
@@ -547,13 +605,7 @@ static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	if (ka->ka_restorer) {
 		regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer;
 	} else {
-		/* Flush instruction space. */
 		unsigned long address = ((unsigned long)&(sf->insns[0]));
-		pgd_t *pgdp = pgd_offset(current->mm, address);
-		pud_t *pudp = pud_offset(pgdp, address);
-		pmd_t *pmdp = pmd_offset(pudp, address);
-		pte_t *ptep;
-		pte_t pte;
 
 		regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2);
 	
@@ -562,34 +614,22 @@ static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 		if (err)
 			goto sigsegv;
 
-		preempt_disable();
-		ptep = pte_offset_map(pmdp, address);
-		pte = *ptep;
-		if (pte_present(pte)) {
-			unsigned long page = (unsigned long)
-				page_address(pte_page(pte));
-
-			wmb();
-			__asm__ __volatile__("flush	%0 + %1"
-					     : /* no outputs */
-					     : "r" (page),
-					       "r" (address & (PAGE_SIZE - 1))
-					     : "memory");
-		}
-		pte_unmap(ptep);
-		preempt_enable();
+		flush_signal_insns(address);
 	}
-	return;
+	return 0;
 
 sigill:
 	do_exit(SIGILL);
+	return -EINVAL;
+
 sigsegv:
 	force_sigsegv(signo, current);
+	return -EFAULT;
 }
 
-static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
-			     unsigned long signr, sigset_t *oldset,
-			     siginfo_t *info)
+static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
+			    unsigned long signr, sigset_t *oldset,
+			    siginfo_t *info)
 {
 	struct rt_signal_frame32 __user *sf;
 	int sigframe_size;
@@ -687,12 +727,7 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	if (ka->ka_restorer)
 		regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer;
 	else {
-		/* Flush instruction space. */
 		unsigned long address = ((unsigned long)&(sf->insns[0]));
-		pgd_t *pgdp = pgd_offset(current->mm, address);
-		pud_t *pudp = pud_offset(pgdp, address);
-		pmd_t *pmdp = pmd_offset(pudp, address);
-		pte_t *ptep;
 
 		regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2);
 	
@@ -704,38 +739,32 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 		if (err)
 			goto sigsegv;
 
-		preempt_disable();
-		ptep = pte_offset_map(pmdp, address);
-		if (pte_present(*ptep)) {
-			unsigned long page = (unsigned long)
-				page_address(pte_page(*ptep));
-
-			wmb();
-			__asm__ __volatile__("flush	%0 + %1"
-					     : /* no outputs */
-					     : "r" (page),
-					       "r" (address & (PAGE_SIZE - 1))
-					     : "memory");
-		}
-		pte_unmap(ptep);
-		preempt_enable();
+		flush_signal_insns(address);
 	}
-	return;
+	return 0;
 
 sigill:
 	do_exit(SIGILL);
+	return -EINVAL;
+
 sigsegv:
 	force_sigsegv(signr, current);
+	return -EFAULT;
 }
 
-static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka,
-				   siginfo_t *info,
-				   sigset_t *oldset, struct pt_regs *regs)
+static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka,
+				  siginfo_t *info,
+				  sigset_t *oldset, struct pt_regs *regs)
 {
+	int err;
+
 	if (ka->sa.sa_flags & SA_SIGINFO)
-		setup_rt_frame32(ka, regs, signr, oldset, info);
+		err = setup_rt_frame32(ka, regs, signr, oldset, info);
 	else
-		setup_frame32(ka, regs, signr, oldset);
+		err = setup_frame32(ka, regs, signr, oldset);
+
+	if (err)
+		return err;
 
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
@@ -743,6 +772,10 @@ static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka,
 		sigaddset(&current->blocked,signr);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
+
+	tracehook_signal_handler(signr, info, ka, regs, 0);
+
+	return 0;
 }
 
 static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs,
@@ -789,16 +822,14 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs,
 	if (signr > 0) {
 		if (restart_syscall)
 			syscall_restart32(orig_i0, regs, &ka.sa);
-		handle_signal32(signr, &ka, &info, oldset, regs);
-
-		/* A signal was successfully delivered; the saved
-		 * sigmask will have been stored in the signal frame,
-		 * and will be restored by sigreturn, so we can simply
-		 * clear the TS_RESTORE_SIGMASK flag.
-		 */
-		current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-
-		tracehook_signal_handler(signr, &info, &ka, regs, 0);
+		if (handle_signal32(signr, &ka, &info, oldset, regs) == 0) {
+			/* A signal was successfully delivered; the saved
+			 * sigmask will have been stored in the signal frame,
+			 * and will be restored by sigreturn, so we can simply
+			 * clear the TS_RESTORE_SIGMASK flag.
+			 */
+			current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
+		}
 		return;
 	}
 	if (restart_syscall &&
@@ -809,12 +840,14 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs,
 		regs->u_regs[UREG_I0] = orig_i0;
 		regs->tpc -= 4;
 		regs->tnpc -= 4;
+		pt_regs_clear_syscall(regs);
 	}
 	if (restart_syscall &&
 	    regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) {
 		regs->u_regs[UREG_G1] = __NR_restart_syscall;
 		regs->tpc -= 4;
 		regs->tnpc -= 4;
+		pt_regs_clear_syscall(regs);
 	}
 
 	/* If there's no signal to deliver, we just put the saved sigmask
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 9882df92ba0a..5e5c5fd03783 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -315,8 +315,8 @@ save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	return err;
 }
 
-static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
-			int signo, sigset_t *oldset)
+static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
+		       int signo, sigset_t *oldset)
 {
 	struct signal_frame __user *sf;
 	int sigframe_size, err;
@@ -384,16 +384,19 @@ static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 		/* Flush instruction space. */
 		flush_sig_insns(current->mm, (unsigned long) &(sf->insns[0]));
 	}
-	return;
+	return 0;
 
 sigill_and_return:
 	do_exit(SIGILL);
+	return -EINVAL;
+
 sigsegv:
 	force_sigsegv(signo, current);
+	return -EFAULT;
 }
 
-static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
-			   int signo, sigset_t *oldset, siginfo_t *info)
+static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
+			  int signo, sigset_t *oldset, siginfo_t *info)
 {
 	struct rt_signal_frame __user *sf;
 	int sigframe_size;
@@ -466,22 +469,30 @@ static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 		/* Flush instruction space. */
 		flush_sig_insns(current->mm, (unsigned long) &(sf->insns[0]));
 	}
-	return;
+	return 0;
 
 sigill:
 	do_exit(SIGILL);
+	return -EINVAL;
+
 sigsegv:
 	force_sigsegv(signo, current);
+	return -EFAULT;
 }
 
-static inline void
+static inline int
 handle_signal(unsigned long signr, struct k_sigaction *ka,
 	      siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
 {
+	int err;
+
 	if (ka->sa.sa_flags & SA_SIGINFO)
-		setup_rt_frame(ka, regs, signr, oldset, info);
+		err = setup_rt_frame(ka, regs, signr, oldset, info);
 	else
-		setup_frame(ka, regs, signr, oldset);
+		err = setup_frame(ka, regs, signr, oldset);
+
+	if (err)
+		return err;
 
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
@@ -489,6 +500,10 @@ handle_signal(unsigned long signr, struct k_sigaction *ka,
 		sigaddset(&current->blocked, signr);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
+
+	tracehook_signal_handler(signr, info, ka, regs, 0);
+
+	return 0;
 }
 
 static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs,
@@ -546,17 +561,15 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	if (signr > 0) {
 		if (restart_syscall)
 			syscall_restart(orig_i0, regs, &ka.sa);
-		handle_signal(signr, &ka, &info, oldset, regs);
-
-		/* a signal was successfully delivered; the saved
-		 * sigmask will have been stored in the signal frame,
-		 * and will be restored by sigreturn, so we can simply
-		 * clear the TIF_RESTORE_SIGMASK flag.
-		 */
-		if (test_thread_flag(TIF_RESTORE_SIGMASK))
-			clear_thread_flag(TIF_RESTORE_SIGMASK);
-
-		tracehook_signal_handler(signr, &info, &ka, regs, 0);
+		if (handle_signal(signr, &ka, &info, oldset, regs) == 0) {
+			/* a signal was successfully delivered; the saved
+			 * sigmask will have been stored in the signal frame,
+			 * and will be restored by sigreturn, so we can simply
+			 * clear the TIF_RESTORE_SIGMASK flag.
+			 */
+			if (test_thread_flag(TIF_RESTORE_SIGMASK))
+				clear_thread_flag(TIF_RESTORE_SIGMASK);
+		}
 		return;
 	}
 	if (restart_syscall &&
@@ -567,12 +580,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 		regs->u_regs[UREG_I0] = orig_i0;
 		regs->pc -= 4;
 		regs->npc -= 4;
+		pt_regs_clear_syscall(regs);
 	}
 	if (restart_syscall &&
 	    regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) {
 		regs->u_regs[UREG_G1] = __NR_restart_syscall;
 		regs->pc -= 4;
 		regs->npc -= 4;
+		pt_regs_clear_syscall(regs);
 	}
 
 	/* if there's no signal to deliver, we just put the saved sigmask
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 9fa48c30037e..006fe4515886 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -409,7 +409,7 @@ static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *
 	return (void __user *) sp;
 }
 
-static inline void
+static inline int
 setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	       int signo, sigset_t *oldset, siginfo_t *info)
 {
@@ -483,26 +483,37 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	}
 	/* 4. return to kernel instructions */
 	regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer;
-	return;
+	return 0;
 
 sigill:
 	do_exit(SIGILL);
+	return -EINVAL;
+
 sigsegv:
 	force_sigsegv(signo, current);
+	return -EFAULT;
 }
 
-static inline void handle_signal(unsigned long signr, struct k_sigaction *ka,
-				 siginfo_t *info,
-				 sigset_t *oldset, struct pt_regs *regs)
+static inline int handle_signal(unsigned long signr, struct k_sigaction *ka,
+				siginfo_t *info,
+				sigset_t *oldset, struct pt_regs *regs)
 {
-	setup_rt_frame(ka, regs, signr, oldset,
-		       (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL);
+	int err;
+
+	err = setup_rt_frame(ka, regs, signr, oldset,
+			     (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL);
+	if (err)
+		return err;
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
 	if (!(ka->sa.sa_flags & SA_NOMASK))
 		sigaddset(&current->blocked,signr);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
+
+	tracehook_signal_handler(signr, info, ka, regs, 0);
+
+	return 0;
 }
 
 static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs,
@@ -571,16 +582,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	if (signr > 0) {
 		if (restart_syscall)
 			syscall_restart(orig_i0, regs, &ka.sa);
-		handle_signal(signr, &ka, &info, oldset, regs);
-
-		/* A signal was successfully delivered; the saved
-		 * sigmask will have been stored in the signal frame,
-		 * and will be restored by sigreturn, so we can simply
-		 * clear the TS_RESTORE_SIGMASK flag.
-		 */
-		current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-
-		tracehook_signal_handler(signr, &info, &ka, regs, 0);
+		if (handle_signal(signr, &ka, &info, oldset, regs) == 0) {
+			/* A signal was successfully delivered; the saved
+			 * sigmask will have been stored in the signal frame,
+			 * and will be restored by sigreturn, so we can simply
+			 * clear the TS_RESTORE_SIGMASK flag.
+			 */
+			current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
+		}
 		return;
 	}
 	if (restart_syscall &&
@@ -591,12 +600,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 		regs->u_regs[UREG_I0] = orig_i0;
 		regs->tpc -= 4;
 		regs->tnpc -= 4;
+		pt_regs_clear_syscall(regs);
 	}
 	if (restart_syscall &&
 	    regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) {
 		regs->u_regs[UREG_G1] = __NR_restart_syscall;
 		regs->tpc -= 4;
 		regs->tnpc -= 4;
+		pt_regs_clear_syscall(regs);
 	}
 
 	/* If there's no signal to deliver, we just put the saved sigmask
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index 84f296ca9e63..8f58bdff20d7 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -1506,13 +1506,6 @@ handle_ill:
 	}
 	STD_ENDPROC(handle_ill)
 
-	.pushsection .rodata, "a"
-	.align  8
-bpt_code:
-	bpt
-	ENDPROC(bpt_code)
-	.popsection
-
 /* Various stub interrupt handlers and syscall handlers */
 
 STD_ENTRY_LOCAL(_kernel_double_fault)
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index 0c46e398cd8f..63c740a85b4c 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -40,6 +40,11 @@ static char *mixer = HOSTAUDIO_DEV_MIXER;
 "    This is used to specify the host mixer device to the hostaudio driver.\n"\
 "    The default is \"" HOSTAUDIO_DEV_MIXER "\".\n\n"
 
+module_param(dsp, charp, 0644);
+MODULE_PARM_DESC(dsp, DSP_HELP);
+module_param(mixer, charp, 0644);
+MODULE_PARM_DESC(mixer, MIXER_HELP);
+
 #ifndef MODULE
 static int set_dsp(char *name, int *add)
 {
@@ -56,15 +61,6 @@ static int set_mixer(char *name, int *add)
 }
 
 __uml_setup("mixer=", set_mixer, "mixer=<mixer device>\n" MIXER_HELP);
-
-#else /*MODULE*/
-
-module_param(dsp, charp, 0644);
-MODULE_PARM_DESC(dsp, DSP_HELP);
-
-module_param(mixer, charp, 0644);
-MODULE_PARM_DESC(mixer, MIXER_HELP);
-
 #endif
 
 /* /dev/dsp file operations */
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 2ab233ba32c1..47d0c37897d5 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -255,18 +255,6 @@ static void uml_net_tx_timeout(struct net_device *dev)
 	netif_wake_queue(dev);
 }
 
-static int uml_net_set_mac(struct net_device *dev, void *addr)
-{
-	struct uml_net_private *lp = netdev_priv(dev);
-	struct sockaddr *hwaddr = addr;
-
-	spin_lock_irq(&lp->lock);
-	eth_mac_addr(dev, hwaddr->sa_data);
-	spin_unlock_irq(&lp->lock);
-
-	return 0;
-}
-
 static int uml_net_change_mtu(struct net_device *dev, int new_mtu)
 {
 	dev->mtu = new_mtu;
@@ -373,7 +361,7 @@ static const struct net_device_ops uml_netdev_ops = {
 	.ndo_start_xmit 	= uml_net_start_xmit,
 	.ndo_set_multicast_list = uml_net_set_multicast_list,
 	.ndo_tx_timeout 	= uml_net_tx_timeout,
-	.ndo_set_mac_address	= uml_net_set_mac,
+	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_change_mtu 	= uml_net_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -472,7 +460,8 @@ static void eth_configure(int n, void *init, char *mac,
 	    ((*transport->user->init)(&lp->user, dev) != 0))
 		goto out_unregister;
 
-	eth_mac_addr(dev, device->mac);
+	/* don't use eth_mac_addr, it will not work here */
+	memcpy(dev->dev_addr, device->mac, ETH_ALEN);
 	dev->mtu = transport->user->mtu;
 	dev->netdev_ops = &uml_netdev_ops;
 	dev->ethtool_ops = &uml_net_ethtool_ops;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 1bcd208c459f..9734994cba1e 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -163,6 +163,7 @@ struct ubd {
 	struct scatterlist sg[MAX_SG];
 	struct request *request;
 	int start_sg, end_sg;
+	sector_t rq_pos;
 };
 
 #define DEFAULT_COW { \
@@ -187,6 +188,7 @@ struct ubd {
 	.request =		NULL, \
 	.start_sg =		0, \
 	.end_sg =		0, \
+	.rq_pos =		0, \
 }
 
 /* Protected by ubd_lock */
@@ -1228,7 +1230,6 @@ static void do_ubd_request(struct request_queue *q)
 {
 	struct io_thread_req *io_req;
 	struct request *req;
-	sector_t sector;
 	int n;
 
 	while(1){
@@ -1239,12 +1240,12 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 
 			dev->request = req;
+			dev->rq_pos = blk_rq_pos(req);
 			dev->start_sg = 0;
 			dev->end_sg = blk_rq_map_sg(q, req, dev->sg);
 		}
 
 		req = dev->request;
-		sector = blk_rq_pos(req);
 		while(dev->start_sg < dev->end_sg){
 			struct scatterlist *sg = &dev->sg[dev->start_sg];
 
@@ -1256,10 +1257,9 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 			prepare_request(req, io_req,
-					(unsigned long long)sector << 9,
+					(unsigned long long)dev->rq_pos << 9,
 					sg->offset, sg->length, sg_page(sg));
 
-			sector += sg->length >> 9;
 			n = os_write_file(thread_fd, &io_req,
 					  sizeof(struct io_thread_req *));
 			if(n != sizeof(struct io_thread_req *)){
@@ -1272,6 +1272,7 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 
+			dev->rq_pos += sg->length >> 9;
 			dev->start_sg++;
 		}
 		dev->end_sg = 0;
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index cd145eda3579..49b5e1eb3262 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -62,7 +62,7 @@ static long execve1(const char *file,
 	return error;
 }
 
-long um_execve(const char *file, char __user *__user *argv, char __user *__user *env)
+long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env)
 {
 	long err;
 
@@ -72,8 +72,8 @@ long um_execve(const char *file, char __user *__user *argv, char __user *__user
 	return err;
 }
 
-long sys_execve(const char __user *file, char __user *__user *argv,
-		char __user *__user *env)
+long sys_execve(const char __user *file, const char __user *const __user *argv,
+		const char __user *const __user *env)
 {
 	long error;
 	char *filename;
diff --git a/arch/um/kernel/internal.h b/arch/um/kernel/internal.h
index 1303a105fe91..5bf97db24a04 100644
--- a/arch/um/kernel/internal.h
+++ b/arch/um/kernel/internal.h
@@ -1 +1 @@
-extern long um_execve(const char *file, char __user *__user *argv, char __user *__user *env);
+extern long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env);
diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c
index 5ddb246626db..f958cb876ee3 100644
--- a/arch/um/kernel/syscall.c
+++ b/arch/um/kernel/syscall.c
@@ -60,8 +60,8 @@ int kernel_execve(const char *filename,
 
 	fs = get_fs();
 	set_fs(KERNEL_DS);
-	ret = um_execve(filename, (char __user *__user *)argv,
-			(char __user *__user *) envp);
+	ret = um_execve(filename, (const char __user *const __user *)argv,
+			(const char __user *const __user *) envp);
 	set_fs(fs);
 
 	return ret;
diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c
index 030f4b93e255..5df2869c874b 100644
--- a/arch/x86/boot/early_serial_console.c
+++ b/arch/x86/boot/early_serial_console.c
@@ -58,7 +58,19 @@ static void parse_earlyprintk(void)
 		if (arg[pos] == ',')
 			pos++;
 
-		if (!strncmp(arg, "ttyS", 4)) {
+		/*
+		 * make sure we have
+		 *	"serial,0x3f8,115200"
+		 *	"serial,ttyS0,115200"
+		 *	"ttyS0,115200"
+		 */
+		if (pos == 7 && !strncmp(arg + pos, "0x", 2)) {
+			port = simple_strtoull(arg + pos, &e, 16);
+			if (port == 0 || arg + pos == e)
+				port = DEFAULT_SERIAL_PORT;
+			else
+				pos = e - arg;
+		} else if (!strncmp(arg + pos, "ttyS", 4)) {
 			static const int bases[] = { 0x3f8, 0x2f8 };
 			int idx = 0;
 
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 0350311906ae..2d93bdbc9ac0 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -34,7 +34,7 @@
 #include <asm/ia32.h>
 
 #undef WARN_OLD
-#undef CORE_DUMP /* probably broken */
+#undef CORE_DUMP /* definitely broken */
 
 static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs);
 static int load_aout_library(struct file *);
@@ -131,21 +131,15 @@ static void set_brk(unsigned long start, unsigned long end)
  * macros to write out all the necessary info.
  */
 
-static int dump_write(struct file *file, const void *addr, int nr)
-{
-	return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
-}
+#include <linux/coredump.h>
 
 #define DUMP_WRITE(addr, nr)			     \
 	if (!dump_write(file, (void *)(addr), (nr))) \
 		goto end_coredump;
 
-#define DUMP_SEEK(offset)						\
-	if (file->f_op->llseek) {					\
-		if (file->f_op->llseek(file, (offset), 0) != (offset))	\
-			goto end_coredump;				\
-	} else								\
-		file->f_pos = (offset)
+#define DUMP_SEEK(offset)		\
+	if (!dump_seek(file, offset))	\
+		goto end_coredump;
 
 #define START_DATA()	(u.u_tsize << PAGE_SHIFT)
 #define START_STACK(u)	(u.start_stack)
@@ -217,12 +211,6 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 		dump_size = dump.u_ssize << PAGE_SHIFT;
 		DUMP_WRITE(dump_start, dump_size);
 	}
-	/*
-	 * Finally dump the task struct.  Not be used by gdb, but
-	 * could be useful
-	 */
-	set_fs(KERNEL_DS);
-	DUMP_WRITE(current, sizeof(*current));
 end_coredump:
 	set_fs(fs);
 	return has_dumped;
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index d2544f1d705d..cb030374b90a 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -38,4 +38,10 @@ static inline void amd_iommu_stats_init(void) { }
 
 #endif /* !CONFIG_AMD_IOMMU_STATS */
 
+static inline bool is_rd890_iommu(struct pci_dev *pdev)
+{
+	return (pdev->vendor == PCI_VENDOR_ID_ATI) &&
+	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
+}
+
 #endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 7014e88bc779..08616180deaf 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -368,6 +368,9 @@ struct amd_iommu {
 	/* capabilities of that IOMMU read from ACPI */
 	u32 cap;
 
+	/* flags read from acpi table */
+	u8 acpi_flags;
+
 	/*
 	 * Capability pointer. There could be more than one IOMMU per PCI
 	 * device function if there are more than one AMD IOMMU capability
@@ -411,6 +414,15 @@ struct amd_iommu {
 
 	/* default dma_ops domain for that IOMMU */
 	struct dma_ops_domain *default_dom;
+
+	/*
+	 * This array is required to work around a potential BIOS bug.
+	 * The BIOS may miss to restore parts of the PCI configuration
+	 * space when the system resumes from S3. The result is that the
+	 * IOMMU does not execute commands anymore which leads to system
+	 * failure.
+	 */
+	u32 cache_cfg[4];
 };
 
 /*
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 545776efeb16..bafd80defa43 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -309,7 +309,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+		(addr[nr / BITS_PER_LONG])) != 0;
 }
 
 static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index c6fbb7b430d1..3f76523589af 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,6 +168,7 @@
 #define X86_FEATURE_XSAVEOPT	(7*32+ 4) /* Optimized Xsave */
 #define X86_FEATURE_PLN		(7*32+ 5) /* Intel Power Limit Notification */
 #define X86_FEATURE_PTS		(7*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_DTS		(7*32+ 7) /* Digital Thermal Sensor */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 528a11e8d3e3..824ca07860d0 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -20,7 +20,7 @@ struct arch_hw_breakpoint {
 #include <linux/list.h>
 
 /* Available HW breakpoint length encodings */
-#define X86_BREAKPOINT_LEN_X		0x00
+#define X86_BREAKPOINT_LEN_X		0x40
 #define X86_BREAKPOINT_LEN_1		0x40
 #define X86_BREAKPOINT_LEN_2		0x44
 #define X86_BREAKPOINT_LEN_4		0x4c
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 502e53f999cf..c52e2eb40a1e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -652,20 +652,6 @@ static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
 	return (struct kvm_mmu_page *)page_private(page);
 }
 
-static inline u16 kvm_read_fs(void)
-{
-	u16 seg;
-	asm("mov %%fs, %0" : "=g"(seg));
-	return seg;
-}
-
-static inline u16 kvm_read_gs(void)
-{
-	u16 seg;
-	asm("mov %%gs, %0" : "=g"(seg));
-	return seg;
-}
-
 static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
@@ -673,16 +659,6 @@ static inline u16 kvm_read_ldt(void)
 	return ldt;
 }
 
-static inline void kvm_load_fs(u16 sel)
-{
-	asm("mov %0, %%fs" : : "rm"(sel));
-}
-
-static inline void kvm_load_gs(u16 sel)
-{
-	asm("mov %0, %%gs" : : "rm"(sel));
-}
-
 static inline void kvm_load_ldt(u16 sel)
 {
 	asm("lldt %0" : : "rm"(sel));
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0925676266bd..fedf32a8c3ec 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -11,6 +11,8 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
+CFLAGS_REMOVE_pvclock.o = -pg
+CFLAGS_REMOVE_kvmclock.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index fb7a5f052e2b..fb16f17e59be 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -61,7 +61,7 @@ struct cstate_entry {
 		unsigned int ecx;
 	} states[ACPI_PROCESSOR_MAX_POWER];
 };
-static struct cstate_entry *cpu_cstate_entry;	/* per CPU ptr */
+static struct cstate_entry __percpu *cpu_cstate_entry;	/* per CPU ptr */
 
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index fa044e1e30a2..679b6450382b 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1953,6 +1953,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 			   size_t size,
 			   int dir)
 {
+	dma_addr_t flush_addr;
 	dma_addr_t i, start;
 	unsigned int pages;
 
@@ -1960,6 +1961,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 	    (dma_addr + size > dma_dom->aperture_size))
 		return;
 
+	flush_addr = dma_addr;
 	pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	dma_addr &= PAGE_MASK;
 	start = dma_addr;
@@ -1974,7 +1976,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 	dma_ops_free_addresses(dma_dom, dma_addr, pages);
 
 	if (amd_iommu_unmap_flush || dma_dom->need_flush) {
-		iommu_flush_pages(&dma_dom->domain, dma_addr, size);
+		iommu_flush_pages(&dma_dom->domain, flush_addr, size);
 		dma_dom->need_flush = false;
 	}
 }
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3cc63e2b8dd4..5a170cbbbed8 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -632,6 +632,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 	iommu->last_device = calc_devid(MMIO_GET_BUS(range),
 					MMIO_GET_LD(range));
 	iommu->evt_msi_num = MMIO_MSI_NUM(misc);
+
+	if (is_rd890_iommu(iommu->dev)) {
+		pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]);
+		pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]);
+		pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]);
+		pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]);
+	}
 }
 
 /*
@@ -649,29 +656,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	struct ivhd_entry *e;
 
 	/*
-	 * First set the recommended feature enable bits from ACPI
-	 * into the IOMMU control registers
+	 * First save the recommended feature enable bits from ACPI
 	 */
-	h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
-		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
-
-	h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
-		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
-
-	h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
-		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
-
-	h->flags & IVHD_FLAG_ISOC_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
-		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
-
-	/*
-	 * make IOMMU memory accesses cache coherent
-	 */
-	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+	iommu->acpi_flags = h->flags;
 
 	/*
 	 * Done. Now parse the device entries
@@ -1116,6 +1103,40 @@ static void init_device_table(void)
 	}
 }
 
+static void iommu_init_flags(struct amd_iommu *iommu)
+{
+	iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
+		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
+		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
+
+	/*
+	 * make IOMMU memory accesses cache coherent
+	 */
+	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+}
+
+static void iommu_apply_quirks(struct amd_iommu *iommu)
+{
+	if (is_rd890_iommu(iommu->dev)) {
+		pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]);
+		pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]);
+		pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]);
+		pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]);
+	}
+}
+
 /*
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
@@ -1126,6 +1147,8 @@ static void enable_iommus(void)
 
 	for_each_iommu(iommu) {
 		iommu_disable(iommu);
+		iommu_apply_quirks(iommu);
+		iommu_init_flags(iommu);
 		iommu_set_device_table(iommu);
 		iommu_enable_command_buffer(iommu);
 		iommu_enable_event_buffer(iommu);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f1efebaf5510..5c5b8f3dddb5 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -306,14 +306,19 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc,
 
 	old_cfg = old_desc->chip_data;
 
-	memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
+	cfg->vector = old_cfg->vector;
+	cfg->move_in_progress = old_cfg->move_in_progress;
+	cpumask_copy(cfg->domain, old_cfg->domain);
+	cpumask_copy(cfg->old_domain, old_cfg->old_domain);
 
 	init_copy_irq_2_pin(old_cfg, cfg, node);
 }
 
-static void free_irq_cfg(struct irq_cfg *old_cfg)
+static void free_irq_cfg(struct irq_cfg *cfg)
 {
-	kfree(old_cfg);
+	free_cpumask_var(cfg->domain);
+	free_cpumask_var(cfg->old_domain);
+	kfree(cfg);
 }
 
 void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 490dac63c2d2..f2f9ac7da25c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -545,7 +545,7 @@ void __cpuinit cpu_detect(struct cpuinfo_x86 *c)
 	}
 }
 
-static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
+void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 tfms, xlvl;
 	u32 ebx;
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 3624e8a0f71b..f668bb1f7d43 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -33,5 +33,6 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+extern void get_cpu_cap(struct cpuinfo_x86 *c);
 
 #endif
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
index 994230d4dc4e..4f6f679f2799 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -368,16 +368,22 @@ static int __init pcc_cpufreq_do_osc(acpi_handle *handle)
 		return -ENODEV;
 
 	out_obj = output.pointer;
-	if (out_obj->type != ACPI_TYPE_BUFFER)
-		return -ENODEV;
+	if (out_obj->type != ACPI_TYPE_BUFFER) {
+		ret = -ENODEV;
+		goto out_free;
+	}
 
 	errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
-	if (errors)
-		return -ENODEV;
+	if (errors) {
+		ret = -ENODEV;
+		goto out_free;
+	}
 
 	supported = *((u32 *)(out_obj->buffer.pointer + 4));
-	if (!(supported & 0x1))
-		return -ENODEV;
+	if (!(supported & 0x1)) {
+		ret = -ENODEV;
+		goto out_free;
+	}
 
 out_free:
 	kfree(output.pointer);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 85f69cdeae10..b4389441efbb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -39,6 +39,7 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 			misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
 			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 			c->cpuid_level = cpuid_eax(0);
+			get_cpu_cap(c);
 		}
 	}
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 5e975298fa81..39aaee5c1ab2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -141,6 +141,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 				address = (low & MASK_BLKPTR_LO) >> 21;
 				if (!address)
 					break;
+
 				address += MCG_XBLK_ADDR;
 			} else
 				++address;
@@ -148,12 +149,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			if (rdmsr_safe(address, &low, &high))
 				break;
 
-			if (!(high & MASK_VALID_HI)) {
-				if (block)
-					continue;
-				else
-					break;
-			}
+			if (!(high & MASK_VALID_HI))
+				continue;
 
 			if (!(high & MASK_CNTP_HI)  ||
 			     (high & MASK_LOCKED_HI))
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d9368eeda309..169d8804a9f8 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -216,7 +216,7 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
 		err = sysfs_add_file_to_group(&sys_dev->kobj,
 					      &attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
-	if (cpu_has(c, X86_FEATURE_PTS))
+	if (cpu_has(c, X86_FEATURE_PTS)) {
 		err = sysfs_add_file_to_group(&sys_dev->kobj,
 					      &attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
@@ -224,6 +224,7 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
 			err = sysfs_add_file_to_group(&sys_dev->kobj,
 					&attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
+	}
 
 	return err;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3efdf2870a35..03a5b0385ad6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -102,6 +102,7 @@ struct cpu_hw_events {
 	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
 	int			n_events;
@@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event)
 	x86_perf_event_set_period(event);
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
+	__set_bit(idx, cpuc->running);
 	x86_pmu.enable(event);
 	perf_event_update_userpage(event);
 
@@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!test_bit(idx, cpuc->active_mask)) {
+			/*
+			 * Though we deactivated the counter some cpus
+			 * might still deliver spurious interrupts still
+			 * in flight. Catch them:
+			 */
+			if (__test_and_clear_bit(idx, cpuc->running))
+				handled++;
 			continue;
+		}
 
 		event = cpuc->events[idx];
 		hwc = &event->hw;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index b560db3305be..249015173992 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -660,8 +660,12 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		int overflow;
 
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!test_bit(idx, cpuc->active_mask)) {
+			/* catch in-flight IRQs */
+			if (__test_and_clear_bit(idx, cpuc->running))
+				handled++;
 			continue;
+		}
 
 		event = cpuc->events[idx];
 		hwc = &event->hw;
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 34b4dad6f0b8..d49079515122 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	const struct cpuid_bit *cb;
 
 	static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
+		{ X86_FEATURE_DTS,		CR_EAX, 0, 0x00000006, 0 },
 		{ X86_FEATURE_IDA,		CR_EAX, 1, 0x00000006, 0 },
 		{ X86_FEATURE_ARAT,		CR_EAX, 2, 0x00000006, 0 },
 		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 410fdb3f1939..7494999141b3 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -506,7 +506,7 @@ static int hpet_assign_irq(struct hpet_dev *dev)
 {
 	unsigned int irq;
 
-	irq = create_irq();
+	irq = create_irq_nr(0, -1);
 	if (!irq)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index a474ec37c32f..ff15c9dcc25d 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -206,11 +206,27 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
-	/* Len */
-	switch (x86_len) {
-	case X86_BREAKPOINT_LEN_X:
+	/* Type */
+	switch (x86_type) {
+	case X86_BREAKPOINT_EXECUTE:
+		if (x86_len != X86_BREAKPOINT_LEN_X)
+			return -EINVAL;
+
+		*gen_type = HW_BREAKPOINT_X;
 		*gen_len = sizeof(long);
+		return 0;
+	case X86_BREAKPOINT_WRITE:
+		*gen_type = HW_BREAKPOINT_W;
 		break;
+	case X86_BREAKPOINT_RW:
+		*gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Len */
+	switch (x86_len) {
 	case X86_BREAKPOINT_LEN_1:
 		*gen_len = HW_BREAKPOINT_LEN_1;
 		break;
@@ -229,21 +245,6 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 		return -EINVAL;
 	}
 
-	/* Type */
-	switch (x86_type) {
-	case X86_BREAKPOINT_EXECUTE:
-		*gen_type = HW_BREAKPOINT_X;
-		break;
-	case X86_BREAKPOINT_WRITE:
-		*gen_type = HW_BREAKPOINT_W;
-		break;
-	case X86_BREAKPOINT_RW:
-		*gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	return 0;
 }
 
@@ -316,9 +317,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	ret = -EINVAL;
 
 	switch (info->len) {
-	case X86_BREAKPOINT_LEN_X:
-		align = sizeof(long) -1;
-		break;
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
 		break;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index e0bc186d7501..1c355c550960 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -239,11 +239,10 @@ int module_finalize(const Elf_Ehdr *hdr,
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
 
-	return module_bug_finalize(hdr, sechdrs, me);
+	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
 	alternatives_smp_module_del(mod);
-	module_bug_cleanup(mod);
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index bc5b9b8d4a33..8a3f9f64f86f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -766,7 +766,6 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 	control->iopm_base_pa = iopm_base;
 	control->msrpm_base_pa = __pa(svm->msrpm);
-	control->tsc_offset = 0;
 	control->int_ctl = V_INTR_MASKING_MASK;
 
 	init_seg(&save->es);
@@ -902,6 +901,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	svm->asid_generation = 0;
 	init_vmcb(svm);
+	svm->vmcb->control.tsc_offset = 0-native_read_tsc();
 
 	err = fx_init(&svm->vcpu);
 	if (err)
@@ -3163,8 +3163,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	sync_lapic_to_cr8(vcpu);
 
 	save_host_msrs(vcpu);
-	fs_selector = kvm_read_fs();
-	gs_selector = kvm_read_gs();
+	savesegment(fs, fs_selector);
+	savesegment(gs, gs_selector);
 	ldt_selector = kvm_read_ldt();
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 	/* required for live migration with NPT */
@@ -3251,10 +3251,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
-	kvm_load_fs(fs_selector);
-	kvm_load_gs(gs_selector);
-	kvm_load_ldt(ldt_selector);
 	load_host_msrs(vcpu);
+	loadsegment(fs, fs_selector);
+#ifdef CONFIG_X86_64
+	load_gs_index(gs_selector);
+	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
+#else
+	loadsegment(gs, gs_selector);
+#endif
+	kvm_load_ldt(ldt_selector);
 
 	reload_tss(vcpu);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 49b25eee25ac..7bddfab12013 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -803,7 +803,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	 */
 	vmx->host_state.ldt_sel = kvm_read_ldt();
 	vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
-	vmx->host_state.fs_sel = kvm_read_fs();
+	savesegment(fs, vmx->host_state.fs_sel);
 	if (!(vmx->host_state.fs_sel & 7)) {
 		vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
 		vmx->host_state.fs_reload_needed = 0;
@@ -811,7 +811,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 		vmcs_write16(HOST_FS_SELECTOR, 0);
 		vmx->host_state.fs_reload_needed = 1;
 	}
-	vmx->host_state.gs_sel = kvm_read_gs();
+	savesegment(gs, vmx->host_state.gs_sel);
 	if (!(vmx->host_state.gs_sel & 7))
 		vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel);
 	else {
@@ -841,27 +841,21 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 
 static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 {
-	unsigned long flags;
-
 	if (!vmx->host_state.loaded)
 		return;
 
 	++vmx->vcpu.stat.host_state_reload;
 	vmx->host_state.loaded = 0;
 	if (vmx->host_state.fs_reload_needed)
-		kvm_load_fs(vmx->host_state.fs_sel);
+		loadsegment(fs, vmx->host_state.fs_sel);
 	if (vmx->host_state.gs_ldt_reload_needed) {
 		kvm_load_ldt(vmx->host_state.ldt_sel);
-		/*
-		 * If we have to reload gs, we must take care to
-		 * preserve our gs base.
-		 */
-		local_irq_save(flags);
-		kvm_load_gs(vmx->host_state.gs_sel);
 #ifdef CONFIG_X86_64
-		wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE));
+		load_gs_index(vmx->host_state.gs_sel);
+		wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
+#else
+		loadsegment(gs, vmx->host_state.gs_sel);
 #endif
-		local_irq_restore(flags);
 	}
 	reload_tss();
 #ifdef CONFIG_X86_64
@@ -2589,8 +2583,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
 	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
-	vmcs_write16(HOST_FS_SELECTOR, kvm_read_fs());    /* 22.2.4 */
-	vmcs_write16(HOST_GS_SELECTOR, kvm_read_gs());    /* 22.2.4 */
+	vmcs_write16(HOST_FS_SELECTOR, 0);            /* 22.2.4 */
+	vmcs_write16(HOST_GS_SELECTOR, 0);            /* 22.2.4 */
 	vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
 	rdmsrl(MSR_FS_BASE, a);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 9257510b4836..9d5f55848455 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -324,9 +324,8 @@ static void lguest_load_gdt(const struct desc_ptr *desc)
 }
 
 /*
- * For a single GDT entry which changes, we do the lazy thing: alter our GDT,
- * then tell the Host to reload the entire thing.  This operation is so rare
- * that this naive implementation is reasonable.
+ * For a single GDT entry which changes, we simply change our copy and
+ * then tell the host about it.
  */
 static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum,
 				   const void *desc, int type)
@@ -338,9 +337,13 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum,
 }
 
 /*
- * OK, I lied.  There are three "thread local storage" GDT entries which change
+ * There are three "thread local storage" GDT entries which change
  * on every context switch (these three entries are how glibc implements
- * __thread variables).  So we have a hypercall specifically for this case.
+ * __thread variables).  As an optimization, we have a hypercall
+ * specifically for this case.
+ *
+ * Wouldn't it be nicer to have a general LOAD_GDT_ENTRIES hypercall
+ * which took a range of entries?
  */
 static void lguest_load_tls(struct thread_struct *t, unsigned int cpu)
 {
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index f9897f7a9ef1..9c0d0d399c30 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -420,9 +420,11 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 	}
 
-	for_each_node_mask(i, nodes_parsed)
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
-						nodes[i].end >> PAGE_SHIFT);
+	for (i = 0; i < num_node_memblks; i++)
+		e820_register_active_regions(memblk_nodeid[i],
+				node_memblk_range[i].start >> PAGE_SHIFT,
+				node_memblk_range[i].end >> PAGE_SHIFT);
+
 	/* for out of order entries in SRAT */
 	sort_node_map();
 	if (!nodes_cover_memory(nodes)) {
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cfe4faabb0f6..f1575c9a2572 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -671,7 +671,10 @@ static int __init ppro_init(char **cpu_type)
 	case 14:
 		*cpu_type = "i386/core";
 		break;
-	case 15: case 23:
+	case 0x0f:
+	case 0x16:
+	case 0x17:
+	case 0x1d:
 		*cpu_type = "i386/core_2";
 		break;
 	case 0x1a:
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 1a5353a753fc..b2bb5aa3b054 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -489,8 +489,9 @@ static void xen_hvm_setup_cpu_clockevents(void)
 __init void xen_hvm_init_time_ops(void)
 {
 	/* vector callback is needed otherwise we cannot receive interrupts
-	 * on cpu > 0 */
-	if (!xen_have_vector_callback && num_present_cpus() > 1)
+	 * on cpu > 0 and at this point we don't know how many cpus are
+	 * available */
+	if (!xen_have_vector_callback)
 		return;
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
 		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
diff --git a/block/blk-map.c b/block/blk-map.c
index c65d7593f7f1..ade0a08c9099 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -307,7 +307,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		return PTR_ERR(bio);
 
 	if (rq_data_dir(rq) == WRITE)
-		bio->bi_rw |= (1 << REQ_WRITE);
+		bio->bi_rw |= REQ_WRITE;
 
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3b0cd4249671..eafc94f68d79 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -361,6 +361,18 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return 0;
 
+	/*
+	 * Don't merge file system requests and discard requests
+	 */
+	if ((req->cmd_flags & REQ_DISCARD) != (next->cmd_flags & REQ_DISCARD))
+		return 0;
+
+	/*
+	 * Don't merge discard requests and secure discard requests
+	 */
+	if ((req->cmd_flags & REQ_SECURE) != (next->cmd_flags & REQ_SECURE))
+		return 0;
+
 	/*
 	 * not contiguous
 	 */
diff --git a/block/bsg.c b/block/bsg.c
index 82d58829ba59..0c00870553a3 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -426,7 +426,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	/*
 	 * fill in all the output members
 	 */
-	hdr->device_status = status_byte(rq->errors);
+	hdr->device_status = rq->errors & 0xff;
 	hdr->transport_status = host_byte(rq->errors);
 	hdr->driver_status = driver_byte(rq->errors);
 	hdr->info = 0;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index f65c6f01c475..9eba291eb6fd 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1019,10 +1019,20 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	 */
 	atomic_set(&cfqg->ref, 1);
 
-	/* Add group onto cgroup list */
-	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-	cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+	/*
+	 * Add group onto cgroup list. It might happen that bdi->dev is
+	 * not initiliazed yet. Initialize this new group without major
+	 * and minor info and this info will be filled in once a new thread
+	 * comes for IO. See code above.
+	 */
+	if (bdi->dev) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
 					MKDEV(major, minor));
+	} else
+		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+					0);
+
 	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
 
 	/* Add group on cfqd list */
diff --git a/block/elevator.c b/block/elevator.c
index 205b09a5bd9e..4e11559aa2b0 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -938,6 +938,7 @@ int elv_register_queue(struct request_queue *q)
 			}
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
+		e->registered = 1;
 	}
 	return error;
 }
@@ -947,6 +948,7 @@ static void __elv_unregister_queue(struct elevator_queue *e)
 {
 	kobject_uevent(&e->kobj, KOBJ_REMOVE);
 	kobject_del(&e->kobj);
+	e->registered = 0;
 }
 
 void elv_unregister_queue(struct request_queue *q)
@@ -1042,11 +1044,13 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
 	spin_unlock_irq(q->queue_lock);
 
-	__elv_unregister_queue(old_elevator);
+	if (old_elevator->registered) {
+		__elv_unregister_queue(old_elevator);
 
-	err = elv_register_queue(q);
-	if (err)
-		goto fail_register;
+		err = elv_register_queue(q);
+		if (err)
+			goto fail_register;
+	}
 
 	/*
 	 * finally exit old elevator and turn off BYPASS.
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index b811f2173f6f..88681aca88c5 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -105,7 +105,7 @@ config ACPI_EC_DEBUGFS
 
 	  Be aware that using this interface can confuse your Embedded
 	  Controller in a way that a normal reboot is not enough. You then
-	  have to power of your system, and remove the laptop battery for
+	  have to power off your system, and remove the laptop battery for
 	  some seconds.
 	  An Embedded Controller typically is available on laptops and reads
 	  sensor values like battery state and temperature.
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index b76848c80be3..6b115f6c4313 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -382,31 +382,32 @@ static void acpi_pad_remove_sysfs(struct acpi_device *device)
 	device_remove_file(&device->dev, &dev_attr_rrtime);
 }
 
-/* Query firmware how many CPUs should be idle */
-static int acpi_pad_pur(acpi_handle handle, int *num_cpus)
+/*
+ * Query firmware how many CPUs should be idle
+ * return -1 on failure
+ */
+static int acpi_pad_pur(acpi_handle handle)
 {
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	union acpi_object *package;
-	int rev, num, ret = -EINVAL;
+	int num = -1;
 
 	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_PUR", NULL, &buffer)))
-		return -EINVAL;
+		return num;
 
 	if (!buffer.length || !buffer.pointer)
-		return -EINVAL;
+		return num;
 
 	package = buffer.pointer;
-	if (package->type != ACPI_TYPE_PACKAGE || package->package.count != 2)
-		goto out;
-	rev = package->package.elements[0].integer.value;
-	num = package->package.elements[1].integer.value;
-	if (rev != 1 || num < 0)
-		goto out;
-	*num_cpus = num;
-	ret = 0;
-out:
+
+	if (package->type == ACPI_TYPE_PACKAGE &&
+		package->package.count == 2 &&
+		package->package.elements[0].integer.value == 1) /* rev 1 */
+
+		num = package->package.elements[1].integer.value;
+
 	kfree(buffer.pointer);
-	return ret;
+	return num;
 }
 
 /* Notify firmware how many CPUs are idle */
@@ -433,7 +434,8 @@ static void acpi_pad_handle_notify(acpi_handle handle)
 	uint32_t idle_cpus;
 
 	mutex_lock(&isolated_cpus_lock);
-	if (acpi_pad_pur(handle, &num_cpus)) {
+	num_cpus = acpi_pad_pur(handle);
+	if (num_cpus < 0) {
 		mutex_unlock(&isolated_cpus_lock);
 		return;
 	}
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index df85b53a674f..7dad9160f209 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -854,6 +854,7 @@ struct acpi_bit_register_info {
 	ACPI_BITMASK_POWER_BUTTON_STATUS   | \
 	ACPI_BITMASK_SLEEP_BUTTON_STATUS   | \
 	ACPI_BITMASK_RT_CLOCK_STATUS       | \
+	ACPI_BITMASK_PCIEXP_WAKE_DISABLE   | \
 	ACPI_BITMASK_WAKE_STATUS)
 
 #define ACPI_BITMASK_TIMER_ENABLE               0x0001
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index 74c24d517f81..4093522eed45 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -109,7 +109,7 @@ void acpi_ex_enter_interpreter(void)
  *
  * DESCRIPTION: Reacquire the interpreter execution region from within the
  *              interpreter code. Failure to enter the interpreter region is a
- *              fatal system error. Used in  conjuction with
+ *              fatal system error. Used in  conjunction with
  *              relinquish_interpreter
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/rsutils.c b/drivers/acpi/acpica/rsutils.c
index 22cfcfbd9fff..491191e6cf69 100644
--- a/drivers/acpi/acpica/rsutils.c
+++ b/drivers/acpi/acpica/rsutils.c
@@ -149,7 +149,7 @@ acpi_rs_move_data(void *destination, void *source, u16 item_count, u8 move_type)
 
 			/*
 			 * 16-, 32-, and 64-bit cases must use the move macros that perform
-			 * endian conversion and/or accomodate hardware that cannot perform
+			 * endian conversion and/or accommodate hardware that cannot perform
 			 * misaligned memory transfers
 			 */
 		case ACPI_RSC_MOVE16:
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 907e350f1c7d..fca34ccfd294 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -34,6 +34,6 @@ config ACPI_APEI_ERST_DEBUG
 	depends on ACPI_APEI
 	help
 	  ERST is a way provided by APEI to save and retrieve hardware
-	  error infomation to and from a persistent store. Enable this
+	  error information to and from a persistent store. Enable this
 	  if you want to debugging and testing the ERST kernel support
 	  and firmware implementation.
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 73fd0c7487c1..4a904a4bf05f 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -445,11 +445,15 @@ EXPORT_SYMBOL_GPL(apei_resources_sub);
 int apei_resources_request(struct apei_resources *resources,
 			   const char *desc)
 {
-	struct apei_res *res, *res_bak;
+	struct apei_res *res, *res_bak = NULL;
 	struct resource *r;
+	int rc;
 
-	apei_resources_sub(resources, &apei_resources_all);
+	rc = apei_resources_sub(resources, &apei_resources_all);
+	if (rc)
+		return rc;
 
+	rc = -EINVAL;
 	list_for_each_entry(res, &resources->iomem, list) {
 		r = request_mem_region(res->start, res->end - res->start,
 				       desc);
@@ -475,7 +479,11 @@ int apei_resources_request(struct apei_resources *resources,
 		}
 	}
 
-	apei_resources_merge(&apei_resources_all, resources);
+	rc = apei_resources_merge(&apei_resources_all, resources);
+	if (rc) {
+		pr_err(APEI_PFX "Fail to merge resources!\n");
+		goto err_unmap_ioport;
+	}
 
 	return 0;
 err_unmap_ioport:
@@ -491,12 +499,13 @@ err_unmap_iomem:
 			break;
 		release_mem_region(res->start, res->end - res->start);
 	}
-	return -EINVAL;
+	return rc;
 }
 EXPORT_SYMBOL_GPL(apei_resources_request);
 
 void apei_resources_release(struct apei_resources *resources)
 {
+	int rc;
 	struct apei_res *res;
 
 	list_for_each_entry(res, &resources->iomem, list)
@@ -504,7 +513,9 @@ void apei_resources_release(struct apei_resources *resources)
 	list_for_each_entry(res, &resources->ioport, list)
 		release_region(res->start, res->end - res->start);
 
-	apei_resources_sub(&apei_resources_all, resources);
+	rc = apei_resources_sub(&apei_resources_all, resources);
+	if (rc)
+		pr_err(APEI_PFX "Fail to sub resources!\n");
 }
 EXPORT_SYMBOL_GPL(apei_resources_release);
 
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 465c885938ee..cf29df69380b 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -426,7 +426,9 @@ DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL,
 
 static int einj_check_table(struct acpi_table_einj *einj_tab)
 {
-	if (einj_tab->header_length != sizeof(struct acpi_table_einj))
+	if ((einj_tab->header_length !=
+	     (sizeof(struct acpi_table_einj) - sizeof(einj_tab->header)))
+	    && (einj_tab->header_length != sizeof(struct acpi_table_einj)))
 		return -EINVAL;
 	if (einj_tab->header.length < sizeof(struct acpi_table_einj))
 		return -EINVAL;
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index 5281ddda2777..da1228a9a544 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -2,7 +2,7 @@
  * APEI Error Record Serialization Table debug support
  *
  * ERST is a way provided by APEI to save and retrieve hardware error
- * infomation to and from a persistent store. This file provide the
+ * information to and from a persistent store. This file provide the
  * debugging/testing support for ERST kernel support and firmware
  * implementation.
  *
@@ -111,11 +111,13 @@ retry:
 		goto out;
 	}
 	if (len > erst_dbg_buf_len) {
-		kfree(erst_dbg_buf);
+		void *p;
 		rc = -ENOMEM;
-		erst_dbg_buf = kmalloc(len, GFP_KERNEL);
-		if (!erst_dbg_buf)
+		p = kmalloc(len, GFP_KERNEL);
+		if (!p)
 			goto out;
+		kfree(erst_dbg_buf);
+		erst_dbg_buf = p;
 		erst_dbg_buf_len = len;
 		goto retry;
 	}
@@ -150,11 +152,13 @@ static ssize_t erst_dbg_write(struct file *filp, const char __user *ubuf,
 	if (mutex_lock_interruptible(&erst_dbg_mutex))
 		return -EINTR;
 	if (usize > erst_dbg_buf_len) {
-		kfree(erst_dbg_buf);
+		void *p;
 		rc = -ENOMEM;
-		erst_dbg_buf = kmalloc(usize, GFP_KERNEL);
-		if (!erst_dbg_buf)
+		p = kmalloc(usize, GFP_KERNEL);
+		if (!p)
 			goto out;
+		kfree(erst_dbg_buf);
+		erst_dbg_buf = p;
 		erst_dbg_buf_len = usize;
 	}
 	rc = copy_from_user(erst_dbg_buf, ubuf, usize);
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 18645f4e83cd..1211c03149e8 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -2,7 +2,7 @@
  * APEI Error Record Serialization Table support
  *
  * ERST is a way provided by APEI to save and retrieve hardware error
- * infomation to and from a persistent store.
+ * information to and from a persistent store.
  *
  * For more information about ERST, please refer to ACPI Specification
  * version 4.0, section 17.4.
@@ -266,13 +266,30 @@ static int erst_exec_move_data(struct apei_exec_context *ctx,
 {
 	int rc;
 	u64 offset;
+	void *src, *dst;
+
+	/* ioremap does not work in interrupt context */
+	if (in_interrupt()) {
+		pr_warning(ERST_PFX
+			   "MOVE_DATA can not be used in interrupt context");
+		return -EBUSY;
+	}
 
 	rc = __apei_exec_read_register(entry, &offset);
 	if (rc)
 		return rc;
-	memmove((void *)ctx->dst_base + offset,
-		(void *)ctx->src_base + offset,
-		ctx->var2);
+
+	src = ioremap(ctx->src_base + offset, ctx->var2);
+	if (!src)
+		return -ENOMEM;
+	dst = ioremap(ctx->dst_base + offset, ctx->var2);
+	if (!dst)
+		return -ENOMEM;
+
+	memmove(dst, src, ctx->var2);
+
+	iounmap(src);
+	iounmap(dst);
 
 	return 0;
 }
@@ -750,7 +767,9 @@ __setup("erst_disable", setup_erst_disable);
 
 static int erst_check_table(struct acpi_table_erst *erst_tab)
 {
-	if (erst_tab->header_length != sizeof(struct acpi_table_erst))
+	if ((erst_tab->header_length !=
+	     (sizeof(struct acpi_table_erst) - sizeof(erst_tab->header)))
+	    && (erst_tab->header_length != sizeof(struct acpi_table_einj)))
 		return -EINVAL;
 	if (erst_tab->header.length < sizeof(struct acpi_table_erst))
 		return -EINVAL;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 385a6059714a..0d505e59214d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -302,7 +302,7 @@ static int __devinit ghes_probe(struct platform_device *ghes_dev)
 	struct ghes *ghes = NULL;
 	int rc = -EINVAL;
 
-	generic = ghes_dev->dev.platform_data;
+	generic = *(struct acpi_hest_generic **)ghes_dev->dev.platform_data;
 	if (!generic->enabled)
 		return -ENODEV;
 
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 343168d18266..1a3508a7fe03 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -137,20 +137,23 @@ static int hest_parse_ghes_count(struct acpi_hest_header *hest_hdr, void *data)
 
 static int hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data)
 {
-	struct acpi_hest_generic *generic;
 	struct platform_device *ghes_dev;
 	struct ghes_arr *ghes_arr = data;
 	int rc;
 
 	if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR)
 		return 0;
-	generic = (struct acpi_hest_generic *)hest_hdr;
-	if (!generic->enabled)
+
+	if (!((struct acpi_hest_generic *)hest_hdr)->enabled)
 		return 0;
 	ghes_dev = platform_device_alloc("GHES", hest_hdr->source_id);
 	if (!ghes_dev)
 		return -ENOMEM;
-	ghes_dev->dev.platform_data = generic;
+
+	rc = platform_device_add_data(ghes_dev, &hest_hdr, sizeof(void *));
+	if (rc)
+		goto err;
+
 	rc = platform_device_add(ghes_dev);
 	if (rc)
 		goto err;
diff --git a/drivers/acpi/atomicio.c b/drivers/acpi/atomicio.c
index 8f8bd736d4ff..542e53903891 100644
--- a/drivers/acpi/atomicio.c
+++ b/drivers/acpi/atomicio.c
@@ -142,7 +142,7 @@ static void __iomem *acpi_pre_map(phys_addr_t paddr,
 	list_add_tail_rcu(&map->list, &acpi_iomaps);
 	spin_unlock_irqrestore(&acpi_iomaps_lock, flags);
 
-	return vaddr + (paddr - pg_off);
+	return map->vaddr + (paddr - map->paddr);
 err_unmap:
 	iounmap(vaddr);
 	return NULL;
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index dc58402b0a17..98417201e9ce 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -273,7 +273,6 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_CYCLE_COUNT,
 	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
-	POWER_SUPPLY_PROP_CURRENT_NOW,
 	POWER_SUPPLY_PROP_POWER_NOW,
 	POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN,
 	POWER_SUPPLY_PROP_ENERGY_FULL,
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 2bb28b9d91c4..af308d03f492 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -183,6 +183,8 @@ static int __init dmi_disable_osi_vista(const struct dmi_system_id *d)
 {
 	printk(KERN_NOTICE PREFIX "DMI detected: %s\n", d->ident);
 	acpi_osi_setup("!Windows 2006");
+	acpi_osi_setup("!Windows 2006 SP1");
+	acpi_osi_setup("!Windows 2006 SP2");
 	return 0;
 }
 static int __init dmi_disable_osi_win7(const struct dmi_system_id *d)
@@ -202,6 +204,23 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		},
 	},
 	{
+	/*
+	 * There have a NVIF method in MSI GX723 DSDT need call by Nvidia
+	 * driver (e.g. nouveau) when user press brightness hotkey.
+	 * Currently, nouveau driver didn't do the job and it causes there
+	 * have a infinite while loop in DSDT when user press hotkey.
+	 * We add MSI GX723's dmi information to this table for workaround
+	 * this issue.
+	 * Will remove MSI GX723 from the table after nouveau grows support.
+	 */
+	.callback = dmi_disable_osi_vista,
+	.ident = "MSI GX723",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star International"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "GX723"),
+		},
+	},
+	{
 	.callback = dmi_disable_osi_vista,
 	.ident = "Sony VGN-NS10J_S",
 	.matches = {
@@ -226,6 +245,14 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		},
 	},
 	{
+	.callback = dmi_disable_osi_vista,
+	.ident = "Toshiba Satellite L355",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+		     DMI_MATCH(DMI_PRODUCT_VERSION, "Satellite L355"),
+		},
+	},
+	{
 	.callback = dmi_disable_osi_win7,
 	.ident = "ASUS K50IJ",
 	.matches = {
@@ -233,6 +260,14 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_NAME, "K50IJ"),
 		},
 	},
+	{
+	.callback = dmi_disable_osi_vista,
+	.ident = "Toshiba P305D",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P305D"),
+		},
+	},
 
 	/*
 	 * BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 5c221ab535d5..310e3b9749cb 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -55,7 +55,7 @@ EXPORT_SYMBOL(acpi_root_dir);
 static int set_power_nocheck(const struct dmi_system_id *id)
 {
 	printk(KERN_NOTICE PREFIX "%s detected - "
-		"disable power check in power transistion\n", id->ident);
+		"disable power check in power transition\n", id->ident);
 	acpi_power_nocheck = 1;
 	return 0;
 }
@@ -80,23 +80,15 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 
 static struct dmi_system_id dsdt_dmi_table[] __initdata = {
 	/*
-	 * Insyde BIOS on some TOSHIBA machines corrupt the DSDT.
+	 * Invoke DSDT corruption work-around on all Toshiba Satellite.
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=14679
 	 */
 	{
 	 .callback = set_copy_dsdt,
-	 .ident = "TOSHIBA Satellite A505",
+	 .ident = "TOSHIBA Satellite",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Satellite A505"),
-		},
-	},
-	{
-	 .callback = set_copy_dsdt,
-	 .ident = "TOSHIBA Satellite L505D",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Satellite L505D"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Satellite"),
 		},
 	},
 	{}
@@ -1027,7 +1019,7 @@ static int __init acpi_init(void)
 
 	/*
 	 * If the laptop falls into the DMI check table, the power state check
-	 * will be disabled in the course of device power transistion.
+	 * will be disabled in the course of device power transition.
 	 */
 	dmi_check_system(power_nocheck_dmi_table);
 
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 8a3b840c0bb2..d94d2953c974 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -369,7 +369,9 @@ static void __exit acpi_fan_exit(void)
 
 	acpi_bus_unregister_driver(&acpi_fan_driver);
 
+#ifdef CONFIG_ACPI_PROCFS
 	remove_proc_entry(ACPI_FAN_CLASS, acpi_root_dir);
+#endif
 
 	return;
 }
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index e9699aaed109..bec561c14beb 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -28,12 +28,6 @@ static int set_no_mwait(const struct dmi_system_id *id)
 }
 
 static struct dmi_system_id __cpuinitdata processor_idle_dmi_table[] = {
-	{
-	set_no_mwait, "IFL91 board", {
-	DMI_MATCH(DMI_BIOS_VENDOR, "COMPAL"),
-	DMI_MATCH(DMI_SYS_VENDOR, "ZEPTO"),
-	DMI_MATCH(DMI_PRODUCT_VERSION, "3215W"),
-	DMI_MATCH(DMI_BOARD_NAME, "IFL91") }, NULL},
 	{
 	set_no_mwait, "Extensa 5220", {
 	DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
@@ -352,4 +346,5 @@ void __init acpi_early_processor_set_pdc(void)
 	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
 			    ACPI_UINT32_MAX,
 			    early_init_pdc, NULL, NULL, NULL);
+	acpi_get_devices("ACPI0007", early_init_pdc, NULL, NULL);
 }
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 156021892389..347eb21b2353 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -850,7 +850,7 @@ static int __init acpi_processor_init(void)
 		printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n",
 			acpi_idle_driver.name);
 	} else {
-		printk(KERN_DEBUG "ACPI: acpi_idle yielding to %s",
+		printk(KERN_DEBUG "ACPI: acpi_idle yielding to %s\n",
 			cpuidle_get_driver()->name);
 	}
 
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index ba1bd263d903..3a73a93596e8 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -447,8 +447,8 @@ int acpi_processor_notify_smm(struct module *calling_module)
 	if (!try_module_get(calling_module))
 		return -EINVAL;
 
-	/* is_done is set to negative if an error occured,
-	 * and to postitive if _no_ error occured, but SMM
+	/* is_done is set to negative if an error occurred,
+	 * and to postitive if _no_ error occurred, but SMM
 	 * was already notified. This avoids double notification
 	 * which might lead to unexpected results...
 	 */
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index cf82989ae756..4754ff6e70e6 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -363,6 +363,12 @@ static int __init init_old_suspend_ordering(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init init_nvs_nosave(const struct dmi_system_id *d)
+{
+	acpi_nvs_nosave();
+	return 0;
+}
+
 static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
 	{
 	.callback = init_old_suspend_ordering,
@@ -397,6 +403,22 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
 		DMI_MATCH(DMI_BOARD_NAME, "CF51-2L"),
 		},
 	},
+	{
+	.callback = init_nvs_nosave,
+	.ident = "Sony Vaio VGN-SR11M",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "VGN-SR11M"),
+		},
+	},
+	{
+	.callback = init_nvs_nosave,
+	.ident = "Everex StepNote Series",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Everex Systems, Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Everex StepNote Series"),
+		},
+	},
 	{},
 };
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 68e2e4582fa2..f8588f81048a 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -100,7 +100,7 @@ static const struct acpi_dlevel acpi_debug_levels[] = {
 	ACPI_DEBUG_INIT(ACPI_LV_EVENTS),
 };
 
-static int param_get_debug_layer(char *buffer, struct kernel_param *kp)
+static int param_get_debug_layer(char *buffer, const struct kernel_param *kp)
 {
 	int result = 0;
 	int i;
@@ -128,7 +128,7 @@ static int param_get_debug_layer(char *buffer, struct kernel_param *kp)
 	return result;
 }
 
-static int param_get_debug_level(char *buffer, struct kernel_param *kp)
+static int param_get_debug_level(char *buffer, const struct kernel_param *kp)
 {
 	int result = 0;
 	int i;
@@ -149,10 +149,18 @@ static int param_get_debug_level(char *buffer, struct kernel_param *kp)
 	return result;
 }
 
-module_param_call(debug_layer, param_set_uint, param_get_debug_layer,
-		  &acpi_dbg_layer, 0644);
-module_param_call(debug_level, param_set_uint, param_get_debug_level,
-		  &acpi_dbg_level, 0644);
+static struct kernel_param_ops param_ops_debug_layer = {
+	.set = param_set_uint,
+	.get = param_get_debug_layer,
+};
+
+static struct kernel_param_ops param_ops_debug_level = {
+	.set = param_set_uint,
+	.get = param_get_debug_level,
+};
+
+module_param_cb(debug_layer, &param_ops_debug_layer, &acpi_dbg_layer, 0644);
+module_param_cb(debug_level, &param_ops_debug_level, &acpi_dbg_level, 0644);
 
 static char trace_method_name[6];
 module_param_string(trace_method_name, trace_method_name, 6, 0644);
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index c5fef01b3c95..b83676126598 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -59,8 +59,8 @@ acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context,
 				  "support\n"));
 		*cap |= ACPI_VIDEO_BACKLIGHT;
 		if (ACPI_FAILURE(acpi_get_handle(handle, "_BQC", &h_dummy)))
-			printk(KERN_WARNING FW_BUG PREFIX "ACPI brightness "
-					"control misses _BQC function\n");
+			printk(KERN_WARNING FW_BUG PREFIX "No _BQC method, "
+				"cannot determine initial brightness\n");
 		/* We have backlight support, no need to scan further */
 		return AE_CTRL_TERMINATE;
 	}
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index ff1c945fba98..99d0e5a51148 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -90,6 +90,10 @@ static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg);
 static int ahci_pci_device_resume(struct pci_dev *pdev);
 #endif
 
+static struct scsi_host_template ahci_sht = {
+	AHCI_SHT("ahci"),
+};
+
 static struct ata_port_operations ahci_vt8251_ops = {
 	.inherits		= &ahci_ops,
 	.hardreset		= ahci_vt8251_hardreset,
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 474427b6f99f..e5fdeebf9ef0 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -298,7 +298,17 @@ struct ahci_host_priv {
 
 extern int ahci_ignore_sss;
 
-extern struct scsi_host_template ahci_sht;
+extern struct device_attribute *ahci_shost_attrs[];
+extern struct device_attribute *ahci_sdev_attrs[];
+
+#define AHCI_SHT(drv_name)						\
+	ATA_NCQ_SHT(drv_name),						\
+	.can_queue		= AHCI_MAX_CMDS - 1,			\
+	.sg_tablesize		= AHCI_MAX_SG,				\
+	.dma_boundary		= AHCI_DMA_BOUNDARY,			\
+	.shost_attrs		= ahci_shost_attrs,			\
+	.sdev_attrs		= ahci_sdev_attrs
+
 extern struct ata_port_operations ahci_ops;
 
 void ahci_save_initial_config(struct device *dev,
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 4e97f33cca44..84b643270e7a 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -23,6 +23,10 @@
 #include <linux/ahci_platform.h>
 #include "ahci.h"
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT("ahci_platform"),
+};
+
 static int __init ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -145,7 +149,7 @@ static int __init ahci_probe(struct platform_device *pdev)
 	ahci_print_info(host, "platform");
 
 	rc = ata_host_activate(host, irq, ahci_interrupt, IRQF_SHARED,
-			       &ahci_sht);
+			       &ahci_platform_sht);
 	if (rc)
 		goto err0;
 
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 68dc6785472f..8eea309ea212 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -121,7 +121,7 @@ static DEVICE_ATTR(ahci_port_cmd, S_IRUGO, ahci_show_port_cmd, NULL);
 static DEVICE_ATTR(em_buffer, S_IWUSR | S_IRUGO,
 		   ahci_read_em_buffer, ahci_store_em_buffer);
 
-static struct device_attribute *ahci_shost_attrs[] = {
+struct device_attribute *ahci_shost_attrs[] = {
 	&dev_attr_link_power_management_policy,
 	&dev_attr_em_message_type,
 	&dev_attr_em_message,
@@ -132,22 +132,14 @@ static struct device_attribute *ahci_shost_attrs[] = {
 	&dev_attr_em_buffer,
 	NULL
 };
+EXPORT_SYMBOL_GPL(ahci_shost_attrs);
 
-static struct device_attribute *ahci_sdev_attrs[] = {
+struct device_attribute *ahci_sdev_attrs[] = {
 	&dev_attr_sw_activity,
 	&dev_attr_unload_heads,
 	NULL
 };
-
-struct scsi_host_template ahci_sht = {
-	ATA_NCQ_SHT("ahci"),
-	.can_queue		= AHCI_MAX_CMDS - 1,
-	.sg_tablesize		= AHCI_MAX_SG,
-	.dma_boundary		= AHCI_DMA_BOUNDARY,
-	.shost_attrs		= ahci_shost_attrs,
-	.sdev_attrs		= ahci_sdev_attrs,
-};
-EXPORT_SYMBOL_GPL(ahci_sht);
+EXPORT_SYMBOL_GPL(ahci_sdev_attrs);
 
 struct ata_port_operations ahci_ops = {
 	.inherits		= &sata_pmp_port_ops,
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index ee9ddeb53417..8cb0347dec28 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -3156,7 +3156,6 @@ static int __devinit ia_init_one(struct pci_dev *pdev,
 {  
 	struct atm_dev *dev;  
 	IADEV *iadev;  
-        unsigned long flags;
 	int ret;
 
 	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
@@ -3188,19 +3187,14 @@ static int __devinit ia_init_one(struct pci_dev *pdev,
 	ia_dev[iadev_count] = iadev;
 	_ia_dev[iadev_count] = dev;
 	iadev_count++;
-	spin_lock_init(&iadev->misc_lock);
-	/* First fixes first. I don't want to think about this now. */
-	spin_lock_irqsave(&iadev->misc_lock, flags); 
 	if (ia_init(dev) || ia_start(dev)) {  
 		IF_INIT(printk("IA register failed!\n");)
 		iadev_count--;
 		ia_dev[iadev_count] = NULL;
 		_ia_dev[iadev_count] = NULL;
-		spin_unlock_irqrestore(&iadev->misc_lock, flags); 
 		ret = -EINVAL;
 		goto err_out_deregister_dev;
 	}
-	spin_unlock_irqrestore(&iadev->misc_lock, flags); 
 	IF_EVENT(printk("iadev_count = %d\n", iadev_count);)
 
 	iadev->next_board = ia_boards;  
diff --git a/drivers/atm/iphase.h b/drivers/atm/iphase.h
index b2cd20f549cb..077735e0e04b 100644
--- a/drivers/atm/iphase.h
+++ b/drivers/atm/iphase.h
@@ -1022,7 +1022,7 @@ typedef struct iadev_t {
 	struct dle_q rx_dle_q;  
 	struct free_desc_q *rx_free_desc_qhead;  
 	struct sk_buff_head rx_dma_q;  
-        spinlock_t rx_lock, misc_lock;
+	spinlock_t rx_lock;
 	struct atm_vcc **rx_open;	/* list of all open VCs */  
         u16 num_rx_desc, rx_buf_sz, rxing;
         u32 rx_pkt_ram, rx_tmp_cnt;
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index f916ddf63938..f46138ab38b6 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -444,6 +444,7 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr,
 	struct atm_dev *atmdev = container_of(dev, struct atm_dev, class_dev);
 	struct solos_card *card = atmdev->dev_data;
 	struct sk_buff *skb;
+	unsigned int len;
 
 	spin_lock(&card->cli_queue_lock);
 	skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]);
@@ -451,11 +452,12 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr,
 	if(skb == NULL)
 		return sprintf(buf, "No data.\n");
 
-	memcpy(buf, skb->data, skb->len);
-	dev_dbg(&card->dev->dev, "len: %d\n", skb->len);
+	len = skb->len;
+	memcpy(buf, skb->data, len);
+	dev_dbg(&card->dev->dev, "len: %d\n", len);
 
 	kfree_skb(skb);
-	return skb->len;
+	return len;
 }
 
 static int send_command(struct solos_card *card, int dev, const char *buf, size_t size)
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index de277689da61..4b9359a6f6ca 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -488,4 +488,21 @@ config BLK_DEV_HD
 
 	  If unsure, say N.
 
+config BLK_DEV_RBD
+	tristate "Rados block device (RBD)"
+	depends on INET && EXPERIMENTAL && BLOCK
+	select CEPH_LIB
+	select LIBCRC32C
+	select CRYPTO_AES
+	select CRYPTO
+	default n
+	help
+	  Say Y here if you want include the Rados block device, which stripes
+	  a block device over objects stored in the Ceph distributed object
+	  store.
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+
 endif # BLK_DEV
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index aff5ac925c34..d7f463d6312d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -37,5 +37,6 @@ obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
 obj-$(CONFIG_BLK_DEV_DRBD)     += drbd/
+obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 
 swim_mod-objs	:= swim.o swim_asm.o
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 6124c2fd2d33..5e4fadcdece9 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -4792,7 +4792,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 clean4:
 	kfree(h->cmd_pool_bits);
 	/* Free up sg elements */
-	for (k = 0; k < h->nr_cmds; k++)
+	for (k-- ; k >= 0; k--)
 		kfree(h->scatter_list[k]);
 	kfree(h->scatter_list);
 	cciss_free_sg_chain_blocks(h->cmd_sg_list, h->nr_cmds);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index b1cbeb59bb76..37a2bb595076 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2369,7 +2369,7 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
 	pkt_shrink_pktlist(pd);
 }
 
-static struct pktcdvd_device *pkt_find_dev_from_minor(int dev_minor)
+static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
 {
 	if (dev_minor >= MAX_WRITERS)
 		return NULL;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index e9da874d0419..03688c2da319 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -113,7 +113,7 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
 			memcpy(buf, dev->bounce_buf+offset, size);
 		offset += size;
 		flush_kernel_dcache_page(bvec->bv_page);
-		bvec_kunmap_irq(bvec, &flags);
+		bvec_kunmap_irq(buf, &flags);
 		i++;
 	}
 }
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
new file mode 100644
index 000000000000..6ec9d53806c5
--- /dev/null
+++ b/drivers/block/rbd.c
@@ -0,0 +1,1841 @@
+/*
+   rbd.c -- Export ceph rados objects as a Linux block device
+
+
+   based on drivers/block/osdblk.c:
+
+   Copyright 2009 Red Hat, Inc.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+
+   Instructions for use
+   --------------------
+
+   1) Map a Linux block device to an existing rbd image.
+
+      Usage: <mon ip addr> <options> <pool name> <rbd image name> [snap name]
+
+      $ echo "192.168.0.1 name=admin rbd foo" > /sys/class/rbd/add
+
+      The snapshot name can be "-" or omitted to map the image read/write.
+
+   2) List all active blkdev<->object mappings.
+
+      In this example, we have performed step #1 twice, creating two blkdevs,
+      mapped to two separate rados objects in the rados rbd pool
+
+      $ cat /sys/class/rbd/list
+      #id     major   client_name     pool    name    snap    KB
+      0       254     client4143      rbd     foo     -      1024000
+
+      The columns, in order, are:
+      - blkdev unique id
+      - blkdev assigned major
+      - rados client id
+      - rados pool name
+      - rados block device name
+      - mapped snapshot ("-" if none)
+      - device size in KB
+
+
+   3) Create a snapshot.
+
+      Usage: <blkdev id> <snapname>
+
+      $ echo "0 mysnap" > /sys/class/rbd/snap_create
+
+
+   4) Listing a snapshot.
+
+      $ cat /sys/class/rbd/snaps_list
+      #id     snap    KB
+      0       -       1024000 (*)
+      0       foo     1024000
+
+      The columns, in order, are:
+      - blkdev unique id
+      - snapshot name, '-' means none (active read/write version)
+      - size of device at time of snapshot
+      - the (*) indicates this is the active version
+
+   5) Rollback to snapshot.
+
+      Usage: <blkdev id> <snapname>
+
+      $ echo "0 mysnap" > /sys/class/rbd/snap_rollback
+
+
+   6) Mapping an image using snapshot.
+
+      A snapshot mapping is read-only. This is being done by passing
+      snap=<snapname> to the options when adding a device.
+
+      $ echo "192.168.0.1 name=admin,snap=mysnap rbd foo" > /sys/class/rbd/add
+
+
+   7) Remove an active blkdev<->rbd image mapping.
+
+      In this example, we remove the mapping with blkdev unique id 1.
+
+      $ echo 1 > /sys/class/rbd/remove
+
+
+   NOTE:  The actual creation and deletion of rados objects is outside the scope
+   of this driver.
+
+ */
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+
+#include "rbd_types.h"
+
+#define DRV_NAME "rbd"
+#define DRV_NAME_LONG "rbd (rados block device)"
+
+#define RBD_MINORS_PER_MAJOR	256		/* max minors per blkdev */
+
+#define RBD_MAX_MD_NAME_LEN	(96 + sizeof(RBD_SUFFIX))
+#define RBD_MAX_POOL_NAME_LEN	64
+#define RBD_MAX_SNAP_NAME_LEN	32
+#define RBD_MAX_OPT_LEN		1024
+
+#define RBD_SNAP_HEAD_NAME	"-"
+
+#define DEV_NAME_LEN		32
+
+/*
+ * block device image metadata (in-memory version)
+ */
+struct rbd_image_header {
+	u64 image_size;
+	char block_name[32];
+	__u8 obj_order;
+	__u8 crypt_type;
+	__u8 comp_type;
+	struct rw_semaphore snap_rwsem;
+	struct ceph_snap_context *snapc;
+	size_t snap_names_len;
+	u64 snap_seq;
+	u32 total_snaps;
+
+	char *snap_names;
+	u64 *snap_sizes;
+};
+
+/*
+ * an instance of the client.  multiple devices may share a client.
+ */
+struct rbd_client {
+	struct ceph_client	*client;
+	struct kref		kref;
+	struct list_head	node;
+};
+
+/*
+ * a single io request
+ */
+struct rbd_request {
+	struct request		*rq;		/* blk layer request */
+	struct bio		*bio;		/* cloned bio */
+	struct page		**pages;	/* list of used pages */
+	u64			len;
+};
+
+/*
+ * a single device
+ */
+struct rbd_device {
+	int			id;		/* blkdev unique id */
+
+	int			major;		/* blkdev assigned major */
+	struct gendisk		*disk;		/* blkdev's gendisk and rq */
+	struct request_queue	*q;
+
+	struct ceph_client	*client;
+	struct rbd_client	*rbd_client;
+
+	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
+
+	spinlock_t		lock;		/* queue lock */
+
+	struct rbd_image_header	header;
+	char			obj[RBD_MAX_OBJ_NAME_LEN]; /* rbd image name */
+	int			obj_len;
+	char			obj_md_name[RBD_MAX_MD_NAME_LEN]; /* hdr nm. */
+	char			pool_name[RBD_MAX_POOL_NAME_LEN];
+	int			poolid;
+
+	char                    snap_name[RBD_MAX_SNAP_NAME_LEN];
+	u32 cur_snap;	/* index+1 of current snapshot within snap context
+			   0 - for the head */
+	int read_only;
+
+	struct list_head	node;
+};
+
+static spinlock_t node_lock;      /* protects client get/put */
+
+static struct class *class_rbd;	  /* /sys/class/rbd */
+static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
+static LIST_HEAD(rbd_dev_list);    /* devices */
+static LIST_HEAD(rbd_client_list);      /* clients */
+
+
+static int rbd_open(struct block_device *bdev, fmode_t mode)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct rbd_device *rbd_dev = disk->private_data;
+
+	set_device_ro(bdev, rbd_dev->read_only);
+
+	if ((mode & FMODE_WRITE) && rbd_dev->read_only)
+		return -EROFS;
+
+	return 0;
+}
+
+static const struct block_device_operations rbd_bd_ops = {
+	.owner			= THIS_MODULE,
+	.open			= rbd_open,
+};
+
+/*
+ * Initialize an rbd client instance.
+ * We own *opt.
+ */
+static struct rbd_client *rbd_client_create(struct ceph_options *opt)
+{
+	struct rbd_client *rbdc;
+	int ret = -ENOMEM;
+
+	dout("rbd_client_create\n");
+	rbdc = kmalloc(sizeof(struct rbd_client), GFP_KERNEL);
+	if (!rbdc)
+		goto out_opt;
+
+	kref_init(&rbdc->kref);
+	INIT_LIST_HEAD(&rbdc->node);
+
+	rbdc->client = ceph_create_client(opt, rbdc);
+	if (IS_ERR(rbdc->client))
+		goto out_rbdc;
+	opt = NULL; /* Now rbdc->client is responsible for opt */
+
+	ret = ceph_open_session(rbdc->client);
+	if (ret < 0)
+		goto out_err;
+
+	spin_lock(&node_lock);
+	list_add_tail(&rbdc->node, &rbd_client_list);
+	spin_unlock(&node_lock);
+
+	dout("rbd_client_create created %p\n", rbdc);
+	return rbdc;
+
+out_err:
+	ceph_destroy_client(rbdc->client);
+out_rbdc:
+	kfree(rbdc);
+out_opt:
+	if (opt)
+		ceph_destroy_options(opt);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Find a ceph client with specific addr and configuration.
+ */
+static struct rbd_client *__rbd_client_find(struct ceph_options *opt)
+{
+	struct rbd_client *client_node;
+
+	if (opt->flags & CEPH_OPT_NOSHARE)
+		return NULL;
+
+	list_for_each_entry(client_node, &rbd_client_list, node)
+		if (ceph_compare_options(opt, client_node->client) == 0)
+			return client_node;
+	return NULL;
+}
+
+/*
+ * Get a ceph client with specific addr and configuration, if one does
+ * not exist create it.
+ */
+static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr,
+			  char *options)
+{
+	struct rbd_client *rbdc;
+	struct ceph_options *opt;
+	int ret;
+
+	ret = ceph_parse_options(&opt, options, mon_addr,
+				 mon_addr + strlen(mon_addr), NULL, NULL);
+	if (ret < 0)
+		return ret;
+
+	spin_lock(&node_lock);
+	rbdc = __rbd_client_find(opt);
+	if (rbdc) {
+		ceph_destroy_options(opt);
+
+		/* using an existing client */
+		kref_get(&rbdc->kref);
+		rbd_dev->rbd_client = rbdc;
+		rbd_dev->client = rbdc->client;
+		spin_unlock(&node_lock);
+		return 0;
+	}
+	spin_unlock(&node_lock);
+
+	rbdc = rbd_client_create(opt);
+	if (IS_ERR(rbdc))
+		return PTR_ERR(rbdc);
+
+	rbd_dev->rbd_client = rbdc;
+	rbd_dev->client = rbdc->client;
+	return 0;
+}
+
+/*
+ * Destroy ceph client
+ */
+static void rbd_client_release(struct kref *kref)
+{
+	struct rbd_client *rbdc = container_of(kref, struct rbd_client, kref);
+
+	dout("rbd_release_client %p\n", rbdc);
+	spin_lock(&node_lock);
+	list_del(&rbdc->node);
+	spin_unlock(&node_lock);
+
+	ceph_destroy_client(rbdc->client);
+	kfree(rbdc);
+}
+
+/*
+ * Drop reference to ceph client node. If it's not referenced anymore, release
+ * it.
+ */
+static void rbd_put_client(struct rbd_device *rbd_dev)
+{
+	kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
+	rbd_dev->rbd_client = NULL;
+	rbd_dev->client = NULL;
+}
+
+
+/*
+ * Create a new header structure, translate header format from the on-disk
+ * header.
+ */
+static int rbd_header_from_disk(struct rbd_image_header *header,
+				 struct rbd_image_header_ondisk *ondisk,
+				 int allocated_snaps,
+				 gfp_t gfp_flags)
+{
+	int i;
+	u32 snap_count = le32_to_cpu(ondisk->snap_count);
+	int ret = -ENOMEM;
+
+	init_rwsem(&header->snap_rwsem);
+
+	header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
+	header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
+				snap_count *
+				 sizeof(struct rbd_image_snap_ondisk),
+				gfp_flags);
+	if (!header->snapc)
+		return -ENOMEM;
+	if (snap_count) {
+		header->snap_names = kmalloc(header->snap_names_len,
+					     GFP_KERNEL);
+		if (!header->snap_names)
+			goto err_snapc;
+		header->snap_sizes = kmalloc(snap_count * sizeof(u64),
+					     GFP_KERNEL);
+		if (!header->snap_sizes)
+			goto err_names;
+	} else {
+		header->snap_names = NULL;
+		header->snap_sizes = NULL;
+	}
+	memcpy(header->block_name, ondisk->block_name,
+	       sizeof(ondisk->block_name));
+
+	header->image_size = le64_to_cpu(ondisk->image_size);
+	header->obj_order = ondisk->options.order;
+	header->crypt_type = ondisk->options.crypt_type;
+	header->comp_type = ondisk->options.comp_type;
+
+	atomic_set(&header->snapc->nref, 1);
+	header->snap_seq = le64_to_cpu(ondisk->snap_seq);
+	header->snapc->num_snaps = snap_count;
+	header->total_snaps = snap_count;
+
+	if (snap_count &&
+	    allocated_snaps == snap_count) {
+		for (i = 0; i < snap_count; i++) {
+			header->snapc->snaps[i] =
+				le64_to_cpu(ondisk->snaps[i].id);
+			header->snap_sizes[i] =
+				le64_to_cpu(ondisk->snaps[i].image_size);
+		}
+
+		/* copy snapshot names */
+		memcpy(header->snap_names, &ondisk->snaps[i],
+			header->snap_names_len);
+	}
+
+	return 0;
+
+err_names:
+	kfree(header->snap_names);
+err_snapc:
+	kfree(header->snapc);
+	return ret;
+}
+
+static int snap_index(struct rbd_image_header *header, int snap_num)
+{
+	return header->total_snaps - snap_num;
+}
+
+static u64 cur_snap_id(struct rbd_device *rbd_dev)
+{
+	struct rbd_image_header *header = &rbd_dev->header;
+
+	if (!rbd_dev->cur_snap)
+		return 0;
+
+	return header->snapc->snaps[snap_index(header, rbd_dev->cur_snap)];
+}
+
+static int snap_by_name(struct rbd_image_header *header, const char *snap_name,
+			u64 *seq, u64 *size)
+{
+	int i;
+	char *p = header->snap_names;
+
+	for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
+		if (strcmp(snap_name, p) == 0)
+			break;
+	}
+	if (i == header->total_snaps)
+		return -ENOENT;
+	if (seq)
+		*seq = header->snapc->snaps[i];
+
+	if (size)
+		*size = header->snap_sizes[i];
+
+	return i;
+}
+
+static int rbd_header_set_snap(struct rbd_device *dev,
+			       const char *snap_name,
+			       u64 *size)
+{
+	struct rbd_image_header *header = &dev->header;
+	struct ceph_snap_context *snapc = header->snapc;
+	int ret = -ENOENT;
+
+	down_write(&header->snap_rwsem);
+
+	if (!snap_name ||
+	    !*snap_name ||
+	    strcmp(snap_name, "-") == 0 ||
+	    strcmp(snap_name, RBD_SNAP_HEAD_NAME) == 0) {
+		if (header->total_snaps)
+			snapc->seq = header->snap_seq;
+		else
+			snapc->seq = 0;
+		dev->cur_snap = 0;
+		dev->read_only = 0;
+		if (size)
+			*size = header->image_size;
+	} else {
+		ret = snap_by_name(header, snap_name, &snapc->seq, size);
+		if (ret < 0)
+			goto done;
+
+		dev->cur_snap = header->total_snaps - ret;
+		dev->read_only = 1;
+	}
+
+	ret = 0;
+done:
+	up_write(&header->snap_rwsem);
+	return ret;
+}
+
+static void rbd_header_free(struct rbd_image_header *header)
+{
+	kfree(header->snapc);
+	kfree(header->snap_names);
+	kfree(header->snap_sizes);
+}
+
+/*
+ * get the actual striped segment name, offset and length
+ */
+static u64 rbd_get_segment(struct rbd_image_header *header,
+			   const char *block_name,
+			   u64 ofs, u64 len,
+			   char *seg_name, u64 *segofs)
+{
+	u64 seg = ofs >> header->obj_order;
+
+	if (seg_name)
+		snprintf(seg_name, RBD_MAX_SEG_NAME_LEN,
+			 "%s.%012llx", block_name, seg);
+
+	ofs = ofs & ((1 << header->obj_order) - 1);
+	len = min_t(u64, len, (1 << header->obj_order) - ofs);
+
+	if (segofs)
+		*segofs = ofs;
+
+	return len;
+}
+
+/*
+ * bio helpers
+ */
+
+static void bio_chain_put(struct bio *chain)
+{
+	struct bio *tmp;
+
+	while (chain) {
+		tmp = chain;
+		chain = chain->bi_next;
+		bio_put(tmp);
+	}
+}
+
+/*
+ * zeros a bio chain, starting at specific offset
+ */
+static void zero_bio_chain(struct bio *chain, int start_ofs)
+{
+	struct bio_vec *bv;
+	unsigned long flags;
+	void *buf;
+	int i;
+	int pos = 0;
+
+	while (chain) {
+		bio_for_each_segment(bv, chain, i) {
+			if (pos + bv->bv_len > start_ofs) {
+				int remainder = max(start_ofs - pos, 0);
+				buf = bvec_kmap_irq(bv, &flags);
+				memset(buf + remainder, 0,
+				       bv->bv_len - remainder);
+				bvec_kunmap_irq(buf, &flags);
+			}
+			pos += bv->bv_len;
+		}
+
+		chain = chain->bi_next;
+	}
+}
+
+/*
+ * bio_chain_clone - clone a chain of bios up to a certain length.
+ * might return a bio_pair that will need to be released.
+ */
+static struct bio *bio_chain_clone(struct bio **old, struct bio **next,
+				   struct bio_pair **bp,
+				   int len, gfp_t gfpmask)
+{
+	struct bio *tmp, *old_chain = *old, *new_chain = NULL, *tail = NULL;
+	int total = 0;
+
+	if (*bp) {
+		bio_pair_release(*bp);
+		*bp = NULL;
+	}
+
+	while (old_chain && (total < len)) {
+		tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs);
+		if (!tmp)
+			goto err_out;
+
+		if (total + old_chain->bi_size > len) {
+			struct bio_pair *bp;
+
+			/*
+			 * this split can only happen with a single paged bio,
+			 * split_bio will BUG_ON if this is not the case
+			 */
+			dout("bio_chain_clone split! total=%d remaining=%d"
+			     "bi_size=%d\n",
+			     (int)total, (int)len-total,
+			     (int)old_chain->bi_size);
+
+			/* split the bio. We'll release it either in the next
+			   call, or it will have to be released outside */
+			bp = bio_split(old_chain, (len - total) / 512ULL);
+			if (!bp)
+				goto err_out;
+
+			__bio_clone(tmp, &bp->bio1);
+
+			*next = &bp->bio2;
+		} else {
+			__bio_clone(tmp, old_chain);
+			*next = old_chain->bi_next;
+		}
+
+		tmp->bi_bdev = NULL;
+		gfpmask &= ~__GFP_WAIT;
+		tmp->bi_next = NULL;
+
+		if (!new_chain) {
+			new_chain = tail = tmp;
+		} else {
+			tail->bi_next = tmp;
+			tail = tmp;
+		}
+		old_chain = old_chain->bi_next;
+
+		total += tmp->bi_size;
+	}
+
+	BUG_ON(total < len);
+
+	if (tail)
+		tail->bi_next = NULL;
+
+	*old = old_chain;
+
+	return new_chain;
+
+err_out:
+	dout("bio_chain_clone with err\n");
+	bio_chain_put(new_chain);
+	return NULL;
+}
+
+/*
+ * helpers for osd request op vectors.
+ */
+static int rbd_create_rw_ops(struct ceph_osd_req_op **ops,
+			    int num_ops,
+			    int opcode,
+			    u32 payload_len)
+{
+	*ops = kzalloc(sizeof(struct ceph_osd_req_op) * (num_ops + 1),
+		       GFP_NOIO);
+	if (!*ops)
+		return -ENOMEM;
+	(*ops)[0].op = opcode;
+	/*
+	 * op extent offset and length will be set later on
+	 * in calc_raw_layout()
+	 */
+	(*ops)[0].payload_len = payload_len;
+	return 0;
+}
+
+static void rbd_destroy_ops(struct ceph_osd_req_op *ops)
+{
+	kfree(ops);
+}
+
+/*
+ * Send ceph osd request
+ */
+static int rbd_do_request(struct request *rq,
+			  struct rbd_device *dev,
+			  struct ceph_snap_context *snapc,
+			  u64 snapid,
+			  const char *obj, u64 ofs, u64 len,
+			  struct bio *bio,
+			  struct page **pages,
+			  int num_pages,
+			  int flags,
+			  struct ceph_osd_req_op *ops,
+			  int num_reply,
+			  void (*rbd_cb)(struct ceph_osd_request *req,
+					 struct ceph_msg *msg))
+{
+	struct ceph_osd_request *req;
+	struct ceph_file_layout *layout;
+	int ret;
+	u64 bno;
+	struct timespec mtime = CURRENT_TIME;
+	struct rbd_request *req_data;
+	struct ceph_osd_request_head *reqhead;
+	struct rbd_image_header *header = &dev->header;
+
+	ret = -ENOMEM;
+	req_data = kzalloc(sizeof(*req_data), GFP_NOIO);
+	if (!req_data)
+		goto done;
+
+	dout("rbd_do_request len=%lld ofs=%lld\n", len, ofs);
+
+	down_read(&header->snap_rwsem);
+
+	req = ceph_osdc_alloc_request(&dev->client->osdc, flags,
+				      snapc,
+				      ops,
+				      false,
+				      GFP_NOIO, pages, bio);
+	if (IS_ERR(req)) {
+		up_read(&header->snap_rwsem);
+		ret = PTR_ERR(req);
+		goto done_pages;
+	}
+
+	req->r_callback = rbd_cb;
+
+	req_data->rq = rq;
+	req_data->bio = bio;
+	req_data->pages = pages;
+	req_data->len = len;
+
+	req->r_priv = req_data;
+
+	reqhead = req->r_request->front.iov_base;
+	reqhead->snapid = cpu_to_le64(CEPH_NOSNAP);
+
+	strncpy(req->r_oid, obj, sizeof(req->r_oid));
+	req->r_oid_len = strlen(req->r_oid);
+
+	layout = &req->r_file_layout;
+	memset(layout, 0, sizeof(*layout));
+	layout->fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
+	layout->fl_stripe_count = cpu_to_le32(1);
+	layout->fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
+	layout->fl_pg_preferred = cpu_to_le32(-1);
+	layout->fl_pg_pool = cpu_to_le32(dev->poolid);
+	ceph_calc_raw_layout(&dev->client->osdc, layout, snapid,
+			     ofs, &len, &bno, req, ops);
+
+	ceph_osdc_build_request(req, ofs, &len,
+				ops,
+				snapc,
+				&mtime,
+				req->r_oid, req->r_oid_len);
+	up_read(&header->snap_rwsem);
+
+	ret = ceph_osdc_start_request(&dev->client->osdc, req, false);
+	if (ret < 0)
+		goto done_err;
+
+	if (!rbd_cb) {
+		ret = ceph_osdc_wait_request(&dev->client->osdc, req);
+		ceph_osdc_put_request(req);
+	}
+	return ret;
+
+done_err:
+	bio_chain_put(req_data->bio);
+	ceph_osdc_put_request(req);
+done_pages:
+	kfree(req_data);
+done:
+	if (rq)
+		blk_end_request(rq, ret, len);
+	return ret;
+}
+
+/*
+ * Ceph osd op callback
+ */
+static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg)
+{
+	struct rbd_request *req_data = req->r_priv;
+	struct ceph_osd_reply_head *replyhead;
+	struct ceph_osd_op *op;
+	__s32 rc;
+	u64 bytes;
+	int read_op;
+
+	/* parse reply */
+	replyhead = msg->front.iov_base;
+	WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
+	op = (void *)(replyhead + 1);
+	rc = le32_to_cpu(replyhead->result);
+	bytes = le64_to_cpu(op->extent.length);
+	read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ);
+
+	dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc);
+
+	if (rc == -ENOENT && read_op) {
+		zero_bio_chain(req_data->bio, 0);
+		rc = 0;
+	} else if (rc == 0 && read_op && bytes < req_data->len) {
+		zero_bio_chain(req_data->bio, bytes);
+		bytes = req_data->len;
+	}
+
+	blk_end_request(req_data->rq, rc, bytes);
+
+	if (req_data->bio)
+		bio_chain_put(req_data->bio);
+
+	ceph_osdc_put_request(req);
+	kfree(req_data);
+}
+
+/*
+ * Do a synchronous ceph osd operation
+ */
+static int rbd_req_sync_op(struct rbd_device *dev,
+			   struct ceph_snap_context *snapc,
+			   u64 snapid,
+			   int opcode,
+			   int flags,
+			   struct ceph_osd_req_op *orig_ops,
+			   int num_reply,
+			   const char *obj,
+			   u64 ofs, u64 len,
+			   char *buf)
+{
+	int ret;
+	struct page **pages;
+	int num_pages;
+	struct ceph_osd_req_op *ops = orig_ops;
+	u32 payload_len;
+
+	num_pages = calc_pages_for(ofs , len);
+	pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	if (!orig_ops) {
+		payload_len = (flags & CEPH_OSD_FLAG_WRITE ? len : 0);
+		ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
+		if (ret < 0)
+			goto done;
+
+		if ((flags & CEPH_OSD_FLAG_WRITE) && buf) {
+			ret = ceph_copy_to_page_vector(pages, buf, ofs, len);
+			if (ret < 0)
+				goto done_ops;
+		}
+	}
+
+	ret = rbd_do_request(NULL, dev, snapc, snapid,
+			  obj, ofs, len, NULL,
+			  pages, num_pages,
+			  flags,
+			  ops,
+			  2,
+			  NULL);
+	if (ret < 0)
+		goto done_ops;
+
+	if ((flags & CEPH_OSD_FLAG_READ) && buf)
+		ret = ceph_copy_from_page_vector(pages, buf, ofs, ret);
+
+done_ops:
+	if (!orig_ops)
+		rbd_destroy_ops(ops);
+done:
+	ceph_release_page_vector(pages, num_pages);
+	return ret;
+}
+
+/*
+ * Do an asynchronous ceph osd operation
+ */
+static int rbd_do_op(struct request *rq,
+		     struct rbd_device *rbd_dev ,
+		     struct ceph_snap_context *snapc,
+		     u64 snapid,
+		     int opcode, int flags, int num_reply,
+		     u64 ofs, u64 len,
+		     struct bio *bio)
+{
+	char *seg_name;
+	u64 seg_ofs;
+	u64 seg_len;
+	int ret;
+	struct ceph_osd_req_op *ops;
+	u32 payload_len;
+
+	seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
+	if (!seg_name)
+		return -ENOMEM;
+
+	seg_len = rbd_get_segment(&rbd_dev->header,
+				  rbd_dev->header.block_name,
+				  ofs, len,
+				  seg_name, &seg_ofs);
+
+	payload_len = (flags & CEPH_OSD_FLAG_WRITE ? seg_len : 0);
+
+	ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
+	if (ret < 0)
+		goto done;
+
+	/* we've taken care of segment sizes earlier when we
+	   cloned the bios. We should never have a segment
+	   truncated at this point */
+	BUG_ON(seg_len < len);
+
+	ret = rbd_do_request(rq, rbd_dev, snapc, snapid,
+			     seg_name, seg_ofs, seg_len,
+			     bio,
+			     NULL, 0,
+			     flags,
+			     ops,
+			     num_reply,
+			     rbd_req_cb);
+done:
+	kfree(seg_name);
+	return ret;
+}
+
+/*
+ * Request async osd write
+ */
+static int rbd_req_write(struct request *rq,
+			 struct rbd_device *rbd_dev,
+			 struct ceph_snap_context *snapc,
+			 u64 ofs, u64 len,
+			 struct bio *bio)
+{
+	return rbd_do_op(rq, rbd_dev, snapc, CEPH_NOSNAP,
+			 CEPH_OSD_OP_WRITE,
+			 CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+			 2,
+			 ofs, len, bio);
+}
+
+/*
+ * Request async osd read
+ */
+static int rbd_req_read(struct request *rq,
+			 struct rbd_device *rbd_dev,
+			 u64 snapid,
+			 u64 ofs, u64 len,
+			 struct bio *bio)
+{
+	return rbd_do_op(rq, rbd_dev, NULL,
+			 (snapid ? snapid : CEPH_NOSNAP),
+			 CEPH_OSD_OP_READ,
+			 CEPH_OSD_FLAG_READ,
+			 2,
+			 ofs, len, bio);
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_read(struct rbd_device *dev,
+			  struct ceph_snap_context *snapc,
+			  u64 snapid,
+			  const char *obj,
+			  u64 ofs, u64 len,
+			  char *buf)
+{
+	return rbd_req_sync_op(dev, NULL,
+			       (snapid ? snapid : CEPH_NOSNAP),
+			       CEPH_OSD_OP_READ,
+			       CEPH_OSD_FLAG_READ,
+			       NULL,
+			       1, obj, ofs, len, buf);
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_rollback_obj(struct rbd_device *dev,
+				     u64 snapid,
+				     const char *obj)
+{
+	struct ceph_osd_req_op *ops;
+	int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_ROLLBACK, 0);
+	if (ret < 0)
+		return ret;
+
+	ops[0].snap.snapid = snapid;
+
+	ret = rbd_req_sync_op(dev, NULL,
+			       CEPH_NOSNAP,
+			       0,
+			       CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+			       ops,
+			       1, obj, 0, 0, NULL);
+
+	rbd_destroy_ops(ops);
+
+	if (ret < 0)
+		return ret;
+
+	return ret;
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_exec(struct rbd_device *dev,
+			     const char *obj,
+			     const char *cls,
+			     const char *method,
+			     const char *data,
+			     int len)
+{
+	struct ceph_osd_req_op *ops;
+	int cls_len = strlen(cls);
+	int method_len = strlen(method);
+	int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_CALL,
+				    cls_len + method_len + len);
+	if (ret < 0)
+		return ret;
+
+	ops[0].cls.class_name = cls;
+	ops[0].cls.class_len = (__u8)cls_len;
+	ops[0].cls.method_name = method;
+	ops[0].cls.method_len = (__u8)method_len;
+	ops[0].cls.argc = 0;
+	ops[0].cls.indata = data;
+	ops[0].cls.indata_len = len;
+
+	ret = rbd_req_sync_op(dev, NULL,
+			       CEPH_NOSNAP,
+			       0,
+			       CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+			       ops,
+			       1, obj, 0, 0, NULL);
+
+	rbd_destroy_ops(ops);
+
+	dout("cls_exec returned %d\n", ret);
+	return ret;
+}
+
+/*
+ * block device queue callback
+ */
+static void rbd_rq_fn(struct request_queue *q)
+{
+	struct rbd_device *rbd_dev = q->queuedata;
+	struct request *rq;
+	struct bio_pair *bp = NULL;
+
+	rq = blk_fetch_request(q);
+
+	while (1) {
+		struct bio *bio;
+		struct bio *rq_bio, *next_bio = NULL;
+		bool do_write;
+		int size, op_size = 0;
+		u64 ofs;
+
+		/* peek at request from block layer */
+		if (!rq)
+			break;
+
+		dout("fetched request\n");
+
+		/* filter out block requests we don't understand */
+		if ((rq->cmd_type != REQ_TYPE_FS)) {
+			__blk_end_request_all(rq, 0);
+			goto next;
+		}
+
+		/* deduce our operation (read, write) */
+		do_write = (rq_data_dir(rq) == WRITE);
+
+		size = blk_rq_bytes(rq);
+		ofs = blk_rq_pos(rq) * 512ULL;
+		rq_bio = rq->bio;
+		if (do_write && rbd_dev->read_only) {
+			__blk_end_request_all(rq, -EROFS);
+			goto next;
+		}
+
+		spin_unlock_irq(q->queue_lock);
+
+		dout("%s 0x%x bytes at 0x%llx\n",
+		     do_write ? "write" : "read",
+		     size, blk_rq_pos(rq) * 512ULL);
+
+		do {
+			/* a bio clone to be passed down to OSD req */
+			dout("rq->bio->bi_vcnt=%d\n", rq->bio->bi_vcnt);
+			op_size = rbd_get_segment(&rbd_dev->header,
+						  rbd_dev->header.block_name,
+						  ofs, size,
+						  NULL, NULL);
+			bio = bio_chain_clone(&rq_bio, &next_bio, &bp,
+					      op_size, GFP_ATOMIC);
+			if (!bio) {
+				spin_lock_irq(q->queue_lock);
+				__blk_end_request_all(rq, -ENOMEM);
+				goto next;
+			}
+
+			/* init OSD command: write or read */
+			if (do_write)
+				rbd_req_write(rq, rbd_dev,
+					      rbd_dev->header.snapc,
+					      ofs,
+					      op_size, bio);
+			else
+				rbd_req_read(rq, rbd_dev,
+					     cur_snap_id(rbd_dev),
+					     ofs,
+					     op_size, bio);
+
+			size -= op_size;
+			ofs += op_size;
+
+			rq_bio = next_bio;
+		} while (size > 0);
+
+		if (bp)
+			bio_pair_release(bp);
+
+		spin_lock_irq(q->queue_lock);
+next:
+		rq = blk_fetch_request(q);
+	}
+}
+
+/*
+ * a queue callback. Makes sure that we don't create a bio that spans across
+ * multiple osd objects. One exception would be with a single page bios,
+ * which we handle later at bio_chain_clone
+ */
+static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
+			  struct bio_vec *bvec)
+{
+	struct rbd_device *rbd_dev = q->queuedata;
+	unsigned int chunk_sectors = 1 << (rbd_dev->header.obj_order - 9);
+	sector_t sector = bmd->bi_sector + get_start_sect(bmd->bi_bdev);
+	unsigned int bio_sectors = bmd->bi_size >> 9;
+	int max;
+
+	max =  (chunk_sectors - ((sector & (chunk_sectors - 1))
+				 + bio_sectors)) << 9;
+	if (max < 0)
+		max = 0; /* bio_add cannot handle a negative return */
+	if (max <= bvec->bv_len && bio_sectors == 0)
+		return bvec->bv_len;
+	return max;
+}
+
+static void rbd_free_disk(struct rbd_device *rbd_dev)
+{
+	struct gendisk *disk = rbd_dev->disk;
+
+	if (!disk)
+		return;
+
+	rbd_header_free(&rbd_dev->header);
+
+	if (disk->flags & GENHD_FL_UP)
+		del_gendisk(disk);
+	if (disk->queue)
+		blk_cleanup_queue(disk->queue);
+	put_disk(disk);
+}
+
+/*
+ * reload the ondisk the header 
+ */
+static int rbd_read_header(struct rbd_device *rbd_dev,
+			   struct rbd_image_header *header)
+{
+	ssize_t rc;
+	struct rbd_image_header_ondisk *dh;
+	int snap_count = 0;
+	u64 snap_names_len = 0;
+
+	while (1) {
+		int len = sizeof(*dh) +
+			  snap_count * sizeof(struct rbd_image_snap_ondisk) +
+			  snap_names_len;
+
+		rc = -ENOMEM;
+		dh = kmalloc(len, GFP_KERNEL);
+		if (!dh)
+			return -ENOMEM;
+
+		rc = rbd_req_sync_read(rbd_dev,
+				       NULL, CEPH_NOSNAP,
+				       rbd_dev->obj_md_name,
+				       0, len,
+				       (char *)dh);
+		if (rc < 0)
+			goto out_dh;
+
+		rc = rbd_header_from_disk(header, dh, snap_count, GFP_KERNEL);
+		if (rc < 0)
+			goto out_dh;
+
+		if (snap_count != header->total_snaps) {
+			snap_count = header->total_snaps;
+			snap_names_len = header->snap_names_len;
+			rbd_header_free(header);
+			kfree(dh);
+			continue;
+		}
+		break;
+	}
+
+out_dh:
+	kfree(dh);
+	return rc;
+}
+
+/*
+ * create a snapshot
+ */
+static int rbd_header_add_snap(struct rbd_device *dev,
+			       const char *snap_name,
+			       gfp_t gfp_flags)
+{
+	int name_len = strlen(snap_name);
+	u64 new_snapid;
+	int ret;
+	void *data, *data_start, *data_end;
+
+	/* we should create a snapshot only if we're pointing at the head */
+	if (dev->cur_snap)
+		return -EINVAL;
+
+	ret = ceph_monc_create_snapid(&dev->client->monc, dev->poolid,
+				      &new_snapid);
+	dout("created snapid=%lld\n", new_snapid);
+	if (ret < 0)
+		return ret;
+
+	data = kmalloc(name_len + 16, gfp_flags);
+	if (!data)
+		return -ENOMEM;
+
+	data_start = data;
+	data_end = data + name_len + 16;
+
+	ceph_encode_string_safe(&data, data_end, snap_name, name_len, bad);
+	ceph_encode_64_safe(&data, data_end, new_snapid, bad);
+
+	ret = rbd_req_sync_exec(dev, dev->obj_md_name, "rbd", "snap_add",
+				data_start, data - data_start);
+
+	kfree(data_start);
+
+	if (ret < 0)
+		return ret;
+
+	dev->header.snapc->seq =  new_snapid;
+
+	return 0;
+bad:
+	return -ERANGE;
+}
+
+/*
+ * only read the first part of the ondisk header, without the snaps info
+ */
+static int rbd_update_snaps(struct rbd_device *rbd_dev)
+{
+	int ret;
+	struct rbd_image_header h;
+	u64 snap_seq;
+
+	ret = rbd_read_header(rbd_dev, &h);
+	if (ret < 0)
+		return ret;
+
+	down_write(&rbd_dev->header.snap_rwsem);
+
+	snap_seq = rbd_dev->header.snapc->seq;
+
+	kfree(rbd_dev->header.snapc);
+	kfree(rbd_dev->header.snap_names);
+	kfree(rbd_dev->header.snap_sizes);
+
+	rbd_dev->header.total_snaps = h.total_snaps;
+	rbd_dev->header.snapc = h.snapc;
+	rbd_dev->header.snap_names = h.snap_names;
+	rbd_dev->header.snap_sizes = h.snap_sizes;
+	rbd_dev->header.snapc->seq = snap_seq;
+
+	up_write(&rbd_dev->header.snap_rwsem);
+
+	return 0;
+}
+
+static int rbd_init_disk(struct rbd_device *rbd_dev)
+{
+	struct gendisk *disk;
+	struct request_queue *q;
+	int rc;
+	u64 total_size = 0;
+
+	/* contact OSD, request size info about the object being mapped */
+	rc = rbd_read_header(rbd_dev, &rbd_dev->header);
+	if (rc)
+		return rc;
+
+	rc = rbd_header_set_snap(rbd_dev, rbd_dev->snap_name, &total_size);
+	if (rc)
+		return rc;
+
+	/* create gendisk info */
+	rc = -ENOMEM;
+	disk = alloc_disk(RBD_MINORS_PER_MAJOR);
+	if (!disk)
+		goto out;
+
+	sprintf(disk->disk_name, DRV_NAME "%d", rbd_dev->id);
+	disk->major = rbd_dev->major;
+	disk->first_minor = 0;
+	disk->fops = &rbd_bd_ops;
+	disk->private_data = rbd_dev;
+
+	/* init rq */
+	rc = -ENOMEM;
+	q = blk_init_queue(rbd_rq_fn, &rbd_dev->lock);
+	if (!q)
+		goto out_disk;
+	blk_queue_merge_bvec(q, rbd_merge_bvec);
+	disk->queue = q;
+
+	q->queuedata = rbd_dev;
+
+	rbd_dev->disk = disk;
+	rbd_dev->q = q;
+
+	/* finally, announce the disk to the world */
+	set_capacity(disk, total_size / 512ULL);
+	add_disk(disk);
+
+	pr_info("%s: added with size 0x%llx\n",
+		disk->disk_name, (unsigned long long)total_size);
+	return 0;
+
+out_disk:
+	put_disk(disk);
+out:
+	return rc;
+}
+
+/********************************************************************
+ * /sys/class/rbd/
+ *                   add	map rados objects to blkdev
+ *                   remove	unmap rados objects
+ *                   list	show mappings
+ *******************************************************************/
+
+static void class_rbd_release(struct class *cls)
+{
+	kfree(cls);
+}
+
+static ssize_t class_rbd_list(struct class *c,
+			      struct class_attribute *attr,
+			      char *data)
+{
+	int n = 0;
+	struct list_head *tmp;
+	int max = PAGE_SIZE;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	n += snprintf(data, max,
+		      "#id\tmajor\tclient_name\tpool\tname\tsnap\tKB\n");
+
+	list_for_each(tmp, &rbd_dev_list) {
+		struct rbd_device *rbd_dev;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		n += snprintf(data+n, max-n,
+			      "%d\t%d\tclient%lld\t%s\t%s\t%s\t%lld\n",
+			      rbd_dev->id,
+			      rbd_dev->major,
+			      ceph_client_id(rbd_dev->client),
+			      rbd_dev->pool_name,
+			      rbd_dev->obj, rbd_dev->snap_name,
+			      rbd_dev->header.image_size >> 10);
+		if (n == max)
+			break;
+	}
+
+	mutex_unlock(&ctl_mutex);
+	return n;
+}
+
+static ssize_t class_rbd_add(struct class *c,
+			     struct class_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct ceph_osd_client *osdc;
+	struct rbd_device *rbd_dev;
+	ssize_t rc = -ENOMEM;
+	int irc, new_id = 0;
+	struct list_head *tmp;
+	char *mon_dev_name;
+	char *options;
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	mon_dev_name = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
+	if (!mon_dev_name)
+		goto err_out_mod;
+
+	options = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
+	if (!options)
+		goto err_mon_dev;
+
+	/* new rbd_device object */
+	rbd_dev = kzalloc(sizeof(*rbd_dev), GFP_KERNEL);
+	if (!rbd_dev)
+		goto err_out_opt;
+
+	/* static rbd_device initialization */
+	spin_lock_init(&rbd_dev->lock);
+	INIT_LIST_HEAD(&rbd_dev->node);
+
+	/* generate unique id: find highest unique id, add one */
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	list_for_each(tmp, &rbd_dev_list) {
+		struct rbd_device *rbd_dev;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		if (rbd_dev->id >= new_id)
+			new_id = rbd_dev->id + 1;
+	}
+
+	rbd_dev->id = new_id;
+
+	/* add to global list */
+	list_add_tail(&rbd_dev->node, &rbd_dev_list);
+
+	/* parse add command */
+	if (sscanf(buf, "%" __stringify(RBD_MAX_OPT_LEN) "s "
+		   "%" __stringify(RBD_MAX_OPT_LEN) "s "
+		   "%" __stringify(RBD_MAX_POOL_NAME_LEN) "s "
+		   "%" __stringify(RBD_MAX_OBJ_NAME_LEN) "s"
+		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+		   mon_dev_name, options, rbd_dev->pool_name,
+		   rbd_dev->obj, rbd_dev->snap_name) < 4) {
+		rc = -EINVAL;
+		goto err_out_slot;
+	}
+
+	if (rbd_dev->snap_name[0] == 0)
+		rbd_dev->snap_name[0] = '-';
+
+	rbd_dev->obj_len = strlen(rbd_dev->obj);
+	snprintf(rbd_dev->obj_md_name, sizeof(rbd_dev->obj_md_name), "%s%s",
+		 rbd_dev->obj, RBD_SUFFIX);
+
+	/* initialize rest of new object */
+	snprintf(rbd_dev->name, DEV_NAME_LEN, DRV_NAME "%d", rbd_dev->id);
+	rc = rbd_get_client(rbd_dev, mon_dev_name, options);
+	if (rc < 0)
+		goto err_out_slot;
+
+	mutex_unlock(&ctl_mutex);
+
+	/* pick the pool */
+	osdc = &rbd_dev->client->osdc;
+	rc = ceph_pg_poolid_by_name(osdc->osdmap, rbd_dev->pool_name);
+	if (rc < 0)
+		goto err_out_client;
+	rbd_dev->poolid = rc;
+
+	/* register our block device */
+	irc = register_blkdev(0, rbd_dev->name);
+	if (irc < 0) {
+		rc = irc;
+		goto err_out_client;
+	}
+	rbd_dev->major = irc;
+
+	/* set up and announce blkdev mapping */
+	rc = rbd_init_disk(rbd_dev);
+	if (rc)
+		goto err_out_blkdev;
+
+	return count;
+
+err_out_blkdev:
+	unregister_blkdev(rbd_dev->major, rbd_dev->name);
+err_out_client:
+	rbd_put_client(rbd_dev);
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+err_out_slot:
+	list_del_init(&rbd_dev->node);
+	mutex_unlock(&ctl_mutex);
+
+	kfree(rbd_dev);
+err_out_opt:
+	kfree(options);
+err_mon_dev:
+	kfree(mon_dev_name);
+err_out_mod:
+	dout("Error adding device %s\n", buf);
+	module_put(THIS_MODULE);
+	return rc;
+}
+
+static struct rbd_device *__rbd_get_dev(unsigned long id)
+{
+	struct list_head *tmp;
+	struct rbd_device *rbd_dev;
+
+	list_for_each(tmp, &rbd_dev_list) {
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		if (rbd_dev->id == id)
+			return rbd_dev;
+	}
+	return NULL;
+}
+
+static ssize_t class_rbd_remove(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, rc;
+	unsigned long ul;
+
+	rc = strict_strtoul(buf, 10, &ul);
+	if (rc)
+		return rc;
+
+	/* convert to int; abort if we lost anything in the conversion */
+	target_id = (int) ul;
+	if (target_id != ul)
+		return -EINVAL;
+
+	/* remove object from list immediately */
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (rbd_dev)
+		list_del_init(&rbd_dev->node);
+
+	mutex_unlock(&ctl_mutex);
+
+	if (!rbd_dev)
+		return -ENOENT;
+
+	rbd_put_client(rbd_dev);
+
+	/* clean up and free blkdev */
+	rbd_free_disk(rbd_dev);
+	unregister_blkdev(rbd_dev->major, rbd_dev->name);
+	kfree(rbd_dev);
+
+	/* release module ref */
+	module_put(THIS_MODULE);
+
+	return count;
+}
+
+static ssize_t class_rbd_snaps_list(struct class *c,
+			      struct class_attribute *attr,
+			      char *data)
+{
+	struct rbd_device *rbd_dev = NULL;
+	struct list_head *tmp;
+	struct rbd_image_header *header;
+	int i, n = 0, max = PAGE_SIZE;
+	int ret;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	n += snprintf(data, max, "#id\tsnap\tKB\n");
+
+	list_for_each(tmp, &rbd_dev_list) {
+		char *names, *p;
+		struct ceph_snap_context *snapc;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		header = &rbd_dev->header;
+
+		down_read(&header->snap_rwsem);
+
+		names = header->snap_names;
+		snapc = header->snapc;
+
+		n += snprintf(data + n, max - n, "%d\t%s\t%lld%s\n",
+			      rbd_dev->id, RBD_SNAP_HEAD_NAME,
+			      header->image_size >> 10,
+			      (!rbd_dev->cur_snap ? " (*)" : ""));
+		if (n == max)
+			break;
+
+		p = names;
+		for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
+			n += snprintf(data + n, max - n, "%d\t%s\t%lld%s\n",
+			      rbd_dev->id, p, header->snap_sizes[i] >> 10,
+			      (rbd_dev->cur_snap &&
+			       (snap_index(header, i) == rbd_dev->cur_snap) ?
+			       " (*)" : ""));
+			if (n == max)
+				break;
+		}
+
+		up_read(&header->snap_rwsem);
+	}
+
+
+	ret = n;
+	mutex_unlock(&ctl_mutex);
+	return ret;
+}
+
+static ssize_t class_rbd_snaps_refresh(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, rc;
+	unsigned long ul;
+	int ret = count;
+
+	rc = strict_strtoul(buf, 10, &ul);
+	if (rc)
+		return rc;
+
+	/* convert to int; abort if we lost anything in the conversion */
+	target_id = (int) ul;
+	if (target_id != ul)
+		return -EINVAL;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (!rbd_dev) {
+		ret = -ENOENT;
+		goto done;
+	}
+
+	rc = rbd_update_snaps(rbd_dev);
+	if (rc < 0)
+		ret = rc;
+
+done:
+	mutex_unlock(&ctl_mutex);
+	return ret;
+}
+
+static ssize_t class_rbd_snap_create(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, ret;
+	char *name;
+
+	name = kmalloc(RBD_MAX_SNAP_NAME_LEN + 1, GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+
+	/* parse snaps add command */
+	if (sscanf(buf, "%d "
+		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+		   &target_id,
+		   name) != 2) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (!rbd_dev) {
+		ret = -ENOENT;
+		goto done_unlock;
+	}
+
+	ret = rbd_header_add_snap(rbd_dev,
+				  name, GFP_KERNEL);
+	if (ret < 0)
+		goto done_unlock;
+
+	ret = rbd_update_snaps(rbd_dev);
+	if (ret < 0)
+		goto done_unlock;
+
+	ret = count;
+done_unlock:
+	mutex_unlock(&ctl_mutex);
+done:
+	kfree(name);
+	return ret;
+}
+
+static ssize_t class_rbd_rollback(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, ret;
+	u64 snapid;
+	char snap_name[RBD_MAX_SNAP_NAME_LEN];
+	u64 cur_ofs;
+	char *seg_name;
+
+	/* parse snaps add command */
+	if (sscanf(buf, "%d "
+		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+		   &target_id,
+		   snap_name) != 2) {
+		return -EINVAL;
+	}
+
+	ret = -ENOMEM;
+	seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
+	if (!seg_name)
+		return ret;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (!rbd_dev) {
+		ret = -ENOENT;
+		goto done_unlock;
+	}
+
+	ret = snap_by_name(&rbd_dev->header, snap_name, &snapid, NULL);
+	if (ret < 0)
+		goto done_unlock;
+
+	dout("snapid=%lld\n", snapid);
+
+	cur_ofs = 0;
+	while (cur_ofs < rbd_dev->header.image_size) {
+		cur_ofs += rbd_get_segment(&rbd_dev->header,
+					   rbd_dev->obj,
+					   cur_ofs, (u64)-1,
+					   seg_name, NULL);
+		dout("seg_name=%s\n", seg_name);
+
+		ret = rbd_req_sync_rollback_obj(rbd_dev, snapid, seg_name);
+		if (ret < 0)
+			pr_warning("could not roll back obj %s err=%d\n",
+				   seg_name, ret);
+	}
+
+	ret = rbd_update_snaps(rbd_dev);
+	if (ret < 0)
+		goto done_unlock;
+
+	ret = count;
+
+done_unlock:
+	mutex_unlock(&ctl_mutex);
+	kfree(seg_name);
+
+	return ret;
+}
+
+static struct class_attribute class_rbd_attrs[] = {
+	__ATTR(add,		0200, NULL, class_rbd_add),
+	__ATTR(remove,		0200, NULL, class_rbd_remove),
+	__ATTR(list,		0444, class_rbd_list, NULL),
+	__ATTR(snaps_refresh,	0200, NULL, class_rbd_snaps_refresh),
+	__ATTR(snap_create,	0200, NULL, class_rbd_snap_create),
+	__ATTR(snaps_list,	0444, class_rbd_snaps_list, NULL),
+	__ATTR(snap_rollback,	0200, NULL, class_rbd_rollback),
+	__ATTR_NULL
+};
+
+/*
+ * create control files in sysfs
+ * /sys/class/rbd/...
+ */
+static int rbd_sysfs_init(void)
+{
+	int ret = -ENOMEM;
+
+	class_rbd = kzalloc(sizeof(*class_rbd), GFP_KERNEL);
+	if (!class_rbd)
+		goto out;
+
+	class_rbd->name = DRV_NAME;
+	class_rbd->owner = THIS_MODULE;
+	class_rbd->class_release = class_rbd_release;
+	class_rbd->class_attrs = class_rbd_attrs;
+
+	ret = class_register(class_rbd);
+	if (ret)
+		goto out_class;
+	return 0;
+
+out_class:
+	kfree(class_rbd);
+	class_rbd = NULL;
+	pr_err(DRV_NAME ": failed to create class rbd\n");
+out:
+	return ret;
+}
+
+static void rbd_sysfs_cleanup(void)
+{
+	if (class_rbd)
+		class_destroy(class_rbd);
+	class_rbd = NULL;
+}
+
+int __init rbd_init(void)
+{
+	int rc;
+
+	rc = rbd_sysfs_init();
+	if (rc)
+		return rc;
+	spin_lock_init(&node_lock);
+	pr_info("loaded " DRV_NAME_LONG "\n");
+	return 0;
+}
+
+void __exit rbd_exit(void)
+{
+	rbd_sysfs_cleanup();
+}
+
+module_init(rbd_init);
+module_exit(rbd_exit);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_DESCRIPTION("rados block device");
+
+/* following authorship retained from original osdblk.c */
+MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/block/rbd_types.h b/drivers/block/rbd_types.h
new file mode 100644
index 000000000000..fc6c678aa2cb
--- /dev/null
+++ b/drivers/block/rbd_types.h
@@ -0,0 +1,73 @@
+/*
+ * Ceph - scalable distributed file system
+ *
+ * Copyright (C) 2004-2010 Sage Weil <sage@newdream.net>
+ *
+ * This is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software
+ * Foundation.  See file COPYING.
+ *
+ */
+
+#ifndef CEPH_RBD_TYPES_H
+#define CEPH_RBD_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * rbd image 'foo' consists of objects
+ *   foo.rbd      - image metadata
+ *   foo.00000000
+ *   foo.00000001
+ *   ...          - data
+ */
+
+#define RBD_SUFFIX		".rbd"
+#define RBD_DIRECTORY           "rbd_directory"
+#define RBD_INFO                "rbd_info"
+
+#define RBD_DEFAULT_OBJ_ORDER	22   /* 4MB */
+#define RBD_MIN_OBJ_ORDER       16
+#define RBD_MAX_OBJ_ORDER       30
+
+#define RBD_MAX_OBJ_NAME_LEN	96
+#define RBD_MAX_SEG_NAME_LEN	128
+
+#define RBD_COMP_NONE		0
+#define RBD_CRYPT_NONE		0
+
+#define RBD_HEADER_TEXT		"<<< Rados Block Device Image >>>\n"
+#define RBD_HEADER_SIGNATURE	"RBD"
+#define RBD_HEADER_VERSION	"001.005"
+
+struct rbd_info {
+	__le64 max_id;
+} __attribute__ ((packed));
+
+struct rbd_image_snap_ondisk {
+	__le64 id;
+	__le64 image_size;
+} __attribute__((packed));
+
+struct rbd_image_header_ondisk {
+	char text[40];
+	char block_name[24];
+	char signature[4];
+	char version[8];
+	struct {
+		__u8 order;
+		__u8 crypt_type;
+		__u8 comp_type;
+		__u8 unused;
+	} __attribute__((packed)) options;
+	__le64 image_size;
+	__le64 snap_seq;
+	__le32 snap_count;
+	__le32 reserved;
+	__le64 snap_names_len;
+	struct rbd_image_snap_ondisk snaps[0];
+} __attribute__((packed));
+
+
+#endif
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2aafafca2b13..1101e251a629 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -202,6 +202,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	struct virtio_blk *vblk = disk->private_data;
 	struct request *req;
 	struct bio *bio;
+	int err;
 
 	bio = bio_map_kern(vblk->disk->queue, id_str, VIRTIO_BLK_ID_BYTES,
 			   GFP_KERNEL);
@@ -215,7 +216,10 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	}
 
 	req->cmd_type = REQ_TYPE_SPECIAL;
-	return blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+	blk_put_request(req);
+
+	return err;
 }
 
 static int virtblk_locked_ioctl(struct block_device *bdev, fmode_t mode,
diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c
index eab58db5f91c..cd18493c9527 100644
--- a/drivers/char/agp/intel-agp.c
+++ b/drivers/char/agp/intel-agp.c
@@ -806,6 +806,8 @@ static const struct intel_driver_description {
 	    "G45/G43", NULL, &intel_i965_driver },
 	{ PCI_DEVICE_ID_INTEL_B43_HB, PCI_DEVICE_ID_INTEL_B43_IG,
 	    "B43", NULL, &intel_i965_driver },
+	{ PCI_DEVICE_ID_INTEL_B43_1_HB, PCI_DEVICE_ID_INTEL_B43_1_IG,
+	    "B43", NULL, &intel_i965_driver },
 	{ PCI_DEVICE_ID_INTEL_G41_HB, PCI_DEVICE_ID_INTEL_G41_IG,
 	    "G41", NULL, &intel_i965_driver },
 	{ PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB, PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG,
diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index ee189c74d345..d09b1ab7e8ab 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -186,6 +186,8 @@
 #define PCI_DEVICE_ID_INTEL_Q33_IG          0x29D2
 #define PCI_DEVICE_ID_INTEL_B43_HB          0x2E40
 #define PCI_DEVICE_ID_INTEL_B43_IG          0x2E42
+#define PCI_DEVICE_ID_INTEL_B43_1_HB        0x2E90
+#define PCI_DEVICE_ID_INTEL_B43_1_IG        0x2E92
 #define PCI_DEVICE_ID_INTEL_GM45_HB         0x2A40
 #define PCI_DEVICE_ID_INTEL_GM45_IG         0x2A42
 #define PCI_DEVICE_ID_INTEL_EAGLELAKE_HB        0x2E00
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 3822b4f49c84..7bd7c45b53ef 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -305,6 +305,9 @@ static int num_force_kipmid;
 #ifdef CONFIG_PCI
 static int pci_registered;
 #endif
+#ifdef CONFIG_ACPI
+static int pnp_registered;
+#endif
 #ifdef CONFIG_PPC_OF
 static int of_registered;
 #endif
@@ -2126,7 +2129,7 @@ static int __devinit ipmi_pnp_probe(struct pnp_dev *dev,
 {
 	struct acpi_device *acpi_dev;
 	struct smi_info *info;
-	struct resource *res;
+	struct resource *res, *res_second;
 	acpi_handle handle;
 	acpi_status status;
 	unsigned long long tmp;
@@ -2182,13 +2185,13 @@ static int __devinit ipmi_pnp_probe(struct pnp_dev *dev,
 	info->io.addr_data = res->start;
 
 	info->io.regspacing = DEFAULT_REGSPACING;
-	res = pnp_get_resource(dev,
+	res_second = pnp_get_resource(dev,
 			       (info->io.addr_type == IPMI_IO_ADDR_SPACE) ?
 					IORESOURCE_IO : IORESOURCE_MEM,
 			       1);
-	if (res) {
-		if (res->start > info->io.addr_data)
-			info->io.regspacing = res->start - info->io.addr_data;
+	if (res_second) {
+		if (res_second->start > info->io.addr_data)
+			info->io.regspacing = res_second->start - info->io.addr_data;
 	}
 	info->io.regsize = DEFAULT_REGSPACING;
 	info->io.regshift = 0;
@@ -3359,6 +3362,7 @@ static __devinit int init_ipmi_si(void)
 
 #ifdef CONFIG_ACPI
 	pnp_register_driver(&ipmi_pnp_driver);
+	pnp_registered = 1;
 #endif
 
 #ifdef CONFIG_DMI
@@ -3526,7 +3530,8 @@ static __exit void cleanup_ipmi_si(void)
 		pci_unregister_driver(&ipmi_pci_driver);
 #endif
 #ifdef CONFIG_ACPI
-	pnp_unregister_driver(&ipmi_pnp_driver);
+	if (pnp_registered)
+		pnp_unregister_driver(&ipmi_pnp_driver);
 #endif
 
 #ifdef CONFIG_PPC_OF
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index a398ecdbd758..1f528fad3516 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -788,10 +788,11 @@ static const struct file_operations zero_fops = {
 /*
  * capabilities for /dev/zero
  * - permits private mappings, "copies" are taken of the source of zeros
+ * - no writeback happens
  */
 static struct backing_dev_info zero_bdi = {
 	.name		= "char/mem",
-	.capabilities	= BDI_CAP_MAP_COPY,
+	.capabilities	= BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
 static const struct file_operations full_fops = {
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 942a9826bd23..0f69c5ec0ecd 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -459,9 +459,12 @@ static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count,
 
 	/*
 	 * Wait till the host acknowledges it pushed out the data we
-	 * sent.  This is done for ports in blocking mode or for data
-	 * from the hvc_console; the tty operations are performed with
-	 * spinlocks held so we can't sleep here.
+	 * sent.  This is done for data from the hvc_console; the tty
+	 * operations are performed with spinlocks held so we can't
+	 * sleep here.  An alternative would be to copy the data to a
+	 * buffer and relax the spinning requirement.  The downside is
+	 * we need to kmalloc a GFP_ATOMIC buffer each time the
+	 * console driver writes something out.
 	 */
 	while (!virtqueue_get_buf(out_vq, &len))
 		cpu_relax();
@@ -596,6 +599,10 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 	ssize_t ret;
 	bool nonblock;
 
+	/* Userspace could be out to fool us */
+	if (!count)
+		return 0;
+
 	port = filp->private_data;
 
 	nonblock = filp->f_flags & O_NONBLOCK;
@@ -622,6 +629,14 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 		goto free_buf;
 	}
 
+	/*
+	 * We now ask send_buf() to not spin for generic ports -- we
+	 * can re-use the same code path that non-blocking file
+	 * descriptors take for blocking file descriptors since the
+	 * wait is already done and we're certain the write will go
+	 * through to the host.
+	 */
+	nonblock = true;
 	ret = send_buf(port, buf, count, nonblock);
 
 	if (nonblock && ret > 0)
@@ -642,7 +657,7 @@ static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
 	poll_wait(filp, &port->waitqueue, wait);
 
 	ret = 0;
-	if (port->inbuf)
+	if (!will_read_block(port))
 		ret |= POLLIN | POLLRDNORM;
 	if (!will_write_block(port))
 		ret |= POLLOUT;
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index c2408bbe9c2e..f508690eb958 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -80,7 +80,7 @@
  * Limiting Performance Impact
  * ---------------------------
  * C states, especially those with large exit latencies, can have a real
- * noticable impact on workloads, which is not acceptable for most sysadmins,
+ * noticeable impact on workloads, which is not acceptable for most sysadmins,
  * and in addition, less performance has a power price of its own.
  *
  * As a general rule of thumb, menu assumes that the following heuristic
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 216f9d383b5b..effd140fc042 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -879,7 +879,7 @@ int __devinit ioat2_dma_probe(struct ioatdma_device *device, int dca)
 	dma->device_issue_pending = ioat2_issue_pending;
 	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
 	dma->device_free_chan_resources = ioat2_free_chan_resources;
-	dma->device_tx_status = ioat_tx_status;
+	dma->device_tx_status = ioat_dma_tx_status;
 
 	err = ioat_probe(device);
 	if (err)
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 86c5ae9fde34..411d5bf50fc4 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -162,7 +162,7 @@ static int mv_is_err_intr(u32 intr_cause)
 
 static void mv_xor_device_clear_eoc_cause(struct mv_xor_chan *chan)
 {
-	u32 val = (1 << (1 + (chan->idx * 16)));
+	u32 val = ~(1 << (chan->idx * 16));
 	dev_dbg(chan->device->common.dev, "%s, val 0x%08x\n", __func__, val);
 	__raw_writel(val, XOR_INTR_CAUSE(chan));
 }
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index fb64cf36ba61..eb6b54dbb806 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -580,7 +580,6 @@ static struct dma_async_tx_descriptor *sh_dmae_prep_slave_sg(
 
 	sh_chan = to_sh_chan(chan);
 	param = chan->private;
-	slave_addr = param->config->addr;
 
 	/* Someone calling slave DMA on a public channel? */
 	if (!param || !sg_len) {
@@ -589,6 +588,8 @@ static struct dma_async_tx_descriptor *sh_dmae_prep_slave_sg(
 		return NULL;
 	}
 
+	slave_addr = param->config->addr;
+
 	/*
 	 * if (param != NULL), this is a successfully requested slave channel,
 	 * therefore param->config != NULL too.
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 3630308e7b81..6b21e25f7a84 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -339,6 +339,9 @@ static void edac_mc_workq_teardown(struct mem_ctl_info *mci)
 {
 	int status;
 
+	if (mci->op_state != OP_RUNNING_POLL)
+		return;
+
 	status = cancel_delayed_work(&mci->work);
 	if (status == 0) {
 		debugf0("%s() not canceled, flush the queue\n",
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index e0187d16dd7c..0fd5b85a0f75 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1140,6 +1140,7 @@ static struct mcidev_sysfs_attribute i7core_udimm_counters_attrs[] = {
 	ATTR_COUNTER(0),
 	ATTR_COUNTER(1),
 	ATTR_COUNTER(2),
+	{ .attr = { .name = NULL } }
 };
 
 static struct mcidev_sysfs_group i7core_udimm_counters = {
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 1b05896648bc..9dcb17d51aee 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2840,7 +2840,7 @@ static int __devinit pci_probe(struct pci_dev *dev,
 			       const struct pci_device_id *ent)
 {
 	struct fw_ohci *ohci;
-	u32 bus_options, max_receive, link_speed, version, link_enh;
+	u32 bus_options, max_receive, link_speed, version;
 	u64 guid;
 	int i, err, n_ir, n_it;
 	size_t size;
@@ -2894,23 +2894,6 @@ static int __devinit pci_probe(struct pci_dev *dev,
 	if (param_quirks)
 		ohci->quirks = param_quirks;
 
-	/* TI OHCI-Lynx and compatible: set recommended configuration bits. */
-	if (dev->vendor == PCI_VENDOR_ID_TI) {
-		pci_read_config_dword(dev, PCI_CFG_TI_LinkEnh, &link_enh);
-
-		/* adjust latency of ATx FIFO: use 1.7 KB threshold */
-		link_enh &= ~TI_LinkEnh_atx_thresh_mask;
-		link_enh |= TI_LinkEnh_atx_thresh_1_7K;
-
-		/* use priority arbitration for asynchronous responses */
-		link_enh |= TI_LinkEnh_enab_unfair;
-
-		/* required for aPhyEnhanceEnable to work */
-		link_enh |= TI_LinkEnh_enab_accel;
-
-		pci_write_config_dword(dev, PCI_CFG_TI_LinkEnh, link_enh);
-	}
-
 	ar_context_init(&ohci->ar_request_ctx, ohci,
 			OHCI1394_AsReqRcvContextControlSet);
 
diff --git a/drivers/firewire/ohci.h b/drivers/firewire/ohci.h
index 0e6c5a466908..ef5e7336da68 100644
--- a/drivers/firewire/ohci.h
+++ b/drivers/firewire/ohci.h
@@ -155,12 +155,4 @@
 
 #define OHCI1394_phy_tcode		0xe
 
-/* TI extensions */
-
-#define PCI_CFG_TI_LinkEnh		0xf4
-#define  TI_LinkEnh_enab_accel		0x00000002
-#define  TI_LinkEnh_enab_unfair		0x00000080
-#define  TI_LinkEnh_atx_thresh_mask	0x00003000
-#define  TI_LinkEnh_atx_thresh_1_7K	0x00001000
-
 #endif /* _FIREWIRE_OHCI_H */
diff --git a/drivers/gpu/drm/drm_buffer.c b/drivers/gpu/drm/drm_buffer.c
index 55d03ed05000..529a0dbe9fc6 100644
--- a/drivers/gpu/drm/drm_buffer.c
+++ b/drivers/gpu/drm/drm_buffer.c
@@ -98,8 +98,8 @@ EXPORT_SYMBOL(drm_buffer_alloc);
  *   user_data: A pointer the data that is copied to the buffer.
  *   size: The Number of bytes to copy.
  */
-extern int drm_buffer_copy_from_user(struct drm_buffer *buf,
-		void __user *user_data, int size)
+int drm_buffer_copy_from_user(struct drm_buffer *buf,
+			      void __user *user_data, int size)
 {
 	int nr_pages = size / PAGE_SIZE + 1;
 	int idx;
@@ -163,7 +163,7 @@ void *drm_buffer_read_object(struct drm_buffer *buf,
 {
 	int idx = drm_buffer_index(buf);
 	int page = drm_buffer_page(buf);
-	void *obj = 0;
+	void *obj = NULL;
 
 	if (idx + objsize <= PAGE_SIZE) {
 		obj = &buf->data[page][idx];
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index bf92d07510df..5663d2719063 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -148,7 +148,7 @@ int drm_gem_object_init(struct drm_device *dev,
 		return -ENOMEM;
 
 	kref_init(&obj->refcount);
-	kref_init(&obj->handlecount);
+	atomic_set(&obj->handle_count, 0);
 	obj->size = size;
 
 	atomic_inc(&dev->object_count);
@@ -462,28 +462,6 @@ drm_gem_object_free(struct kref *kref)
 }
 EXPORT_SYMBOL(drm_gem_object_free);
 
-/**
- * Called after the last reference to the object has been lost.
- * Must be called without holding struct_mutex
- *
- * Frees the object
- */
-void
-drm_gem_object_free_unlocked(struct kref *kref)
-{
-	struct drm_gem_object *obj = (struct drm_gem_object *) kref;
-	struct drm_device *dev = obj->dev;
-
-	if (dev->driver->gem_free_object_unlocked != NULL)
-		dev->driver->gem_free_object_unlocked(obj);
-	else if (dev->driver->gem_free_object != NULL) {
-		mutex_lock(&dev->struct_mutex);
-		dev->driver->gem_free_object(obj);
-		mutex_unlock(&dev->struct_mutex);
-	}
-}
-EXPORT_SYMBOL(drm_gem_object_free_unlocked);
-
 static void drm_gem_object_ref_bug(struct kref *list_kref)
 {
 	BUG();
@@ -496,12 +474,8 @@ static void drm_gem_object_ref_bug(struct kref *list_kref)
  * called before drm_gem_object_free or we'll be touching
  * freed memory
  */
-void
-drm_gem_object_handle_free(struct kref *kref)
+void drm_gem_object_handle_free(struct drm_gem_object *obj)
 {
-	struct drm_gem_object *obj = container_of(kref,
-						  struct drm_gem_object,
-						  handlecount);
 	struct drm_device *dev = obj->dev;
 
 	/* Remove any name for this object */
@@ -528,6 +502,10 @@ void drm_gem_vm_open(struct vm_area_struct *vma)
 	struct drm_gem_object *obj = vma->vm_private_data;
 
 	drm_gem_object_reference(obj);
+
+	mutex_lock(&obj->dev->struct_mutex);
+	drm_vm_open_locked(vma);
+	mutex_unlock(&obj->dev->struct_mutex);
 }
 EXPORT_SYMBOL(drm_gem_vm_open);
 
@@ -535,7 +513,10 @@ void drm_gem_vm_close(struct vm_area_struct *vma)
 {
 	struct drm_gem_object *obj = vma->vm_private_data;
 
-	drm_gem_object_unreference_unlocked(obj);
+	mutex_lock(&obj->dev->struct_mutex);
+	drm_vm_close_locked(vma);
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&obj->dev->struct_mutex);
 }
 EXPORT_SYMBOL(drm_gem_vm_close);
 
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 2ef2c7827243..974e970ce3f8 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -255,7 +255,7 @@ int drm_gem_one_name_info(int id, void *ptr, void *data)
 
 	seq_printf(m, "%6d %8zd %7d %8d\n",
 		   obj->name, obj->size,
-		   atomic_read(&obj->handlecount.refcount),
+		   atomic_read(&obj->handle_count),
 		   atomic_read(&obj->refcount.refcount));
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index fda67468e603..5df450683aab 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -433,15 +433,7 @@ static void drm_vm_open(struct vm_area_struct *vma)
 	mutex_unlock(&dev->struct_mutex);
 }
 
-/**
- * \c close method for all virtual memory types.
- *
- * \param vma virtual memory area.
- *
- * Search the \p vma private data entry in drm_device::vmalist, unlink it, and
- * free it.
- */
-static void drm_vm_close(struct vm_area_struct *vma)
+void drm_vm_close_locked(struct vm_area_struct *vma)
 {
 	struct drm_file *priv = vma->vm_file->private_data;
 	struct drm_device *dev = priv->minor->dev;
@@ -451,7 +443,6 @@ static void drm_vm_close(struct vm_area_struct *vma)
 		  vma->vm_start, vma->vm_end - vma->vm_start);
 	atomic_dec(&dev->vma_count);
 
-	mutex_lock(&dev->struct_mutex);
 	list_for_each_entry_safe(pt, temp, &dev->vmalist, head) {
 		if (pt->vma == vma) {
 			list_del(&pt->head);
@@ -459,6 +450,23 @@ static void drm_vm_close(struct vm_area_struct *vma)
 			break;
 		}
 	}
+}
+
+/**
+ * \c close method for all virtual memory types.
+ *
+ * \param vma virtual memory area.
+ *
+ * Search the \p vma private data entry in drm_device::vmalist, unlink it, and
+ * free it.
+ */
+static void drm_vm_close(struct vm_area_struct *vma)
+{
+	struct drm_file *priv = vma->vm_file->private_data;
+	struct drm_device *dev = priv->minor->dev;
+
+	mutex_lock(&dev->struct_mutex);
+	drm_vm_close_locked(vma);
 	mutex_unlock(&dev->struct_mutex);
 }
 
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index 61b4caf220fa..fb07e73581e8 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -116,7 +116,7 @@ static int i810_mmap_buffers(struct file *filp, struct vm_area_struct *vma)
 static const struct file_operations i810_buffer_fops = {
 	.open = drm_open,
 	.release = drm_release,
-	.unlocked_ioctl = drm_ioctl,
+	.unlocked_ioctl = i810_ioctl,
 	.mmap = i810_mmap_buffers,
 	.fasync = drm_fasync,
 };
diff --git a/drivers/gpu/drm/i830/i830_dma.c b/drivers/gpu/drm/i830/i830_dma.c
index 671aa18415ac..cc92c7e6236f 100644
--- a/drivers/gpu/drm/i830/i830_dma.c
+++ b/drivers/gpu/drm/i830/i830_dma.c
@@ -118,7 +118,7 @@ static int i830_mmap_buffers(struct file *filp, struct vm_area_struct *vma)
 static const struct file_operations i830_buffer_fops = {
 	.open = drm_open,
 	.release = drm_release,
-	.unlocked_ioctl = drm_ioctl,
+	.unlocked_ioctl = i830_ioctl,
 	.mmap = i830_mmap_buffers,
 	.fasync = drm_fasync,
 };
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9d67b4853030..2dd2c93ebfa3 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1787,9 +1787,9 @@ unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 		}
 	}
 
-	div_u64(diff, diff1);
+	diff = div_u64(diff, diff1);
 	ret = ((m * diff) + c);
-	div_u64(ret, 10);
+	ret = div_u64(ret, 10);
 
 	dev_priv->last_count1 = total_count;
 	dev_priv->last_time1 = now;
@@ -1858,7 +1858,7 @@ void i915_update_gfx_val(struct drm_i915_private *dev_priv)
 
 	/* More magic constants... */
 	diff = diff * 1181;
-	div_u64(diff, diffms * 10);
+	diff = div_u64(diff, diffms * 10);
 	dev_priv->gfx_power = diff;
 }
 
@@ -2231,6 +2231,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	dev_priv->mchdev_lock = &mchdev_lock;
 	spin_unlock(&mchdev_lock);
 
+	/* XXX Prevent module unload due to memory corruption bugs. */
+	__module_get(THIS_MODULE);
+
 	return 0;
 
 out_workqueue_free:
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 216deb579785..6dbe14cc4f74 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -170,6 +170,7 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x2e22, &intel_g45_info),		/* G45_G */
 	INTEL_VGA_DEVICE(0x2e32, &intel_g45_info),		/* G41_G */
 	INTEL_VGA_DEVICE(0x2e42, &intel_g45_info),		/* B43_G */
+	INTEL_VGA_DEVICE(0x2e92, &intel_g45_info),		/* B43_G.1 */
 	INTEL_VGA_DEVICE(0xa001, &intel_pineview_info),
 	INTEL_VGA_DEVICE(0xa011, &intel_pineview_info),
 	INTEL_VGA_DEVICE(0x0042, &intel_ironlake_d_info),
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 16fca1d1799a..90b1d6753b9d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -136,14 +136,12 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data,
 		return -ENOMEM;
 
 	ret = drm_gem_handle_create(file_priv, obj, &handle);
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(obj);
 	if (ret) {
-		drm_gem_object_unreference_unlocked(obj);
 		return ret;
 	}
 
-	/* Sink the floating reference from kref_init(handlecount) */
-	drm_gem_object_handle_unreference_unlocked(obj);
-
 	args->handle = handle;
 	return 0;
 }
@@ -471,14 +469,17 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 		return -ENOENT;
 	obj_priv = to_intel_bo(obj);
 
-	/* Bounds check source.
-	 *
-	 * XXX: This could use review for overflow issues...
-	 */
-	if (args->offset > obj->size || args->size > obj->size ||
-	    args->offset + args->size > obj->size) {
-		drm_gem_object_unreference_unlocked(obj);
-		return -EINVAL;
+	/* Bounds check source.  */
+	if (args->offset > obj->size || args->size > obj->size - args->offset) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (!access_ok(VERIFY_WRITE,
+		       (char __user *)(uintptr_t)args->data_ptr,
+		       args->size)) {
+		ret = -EFAULT;
+		goto err;
 	}
 
 	if (i915_gem_object_needs_bit17_swizzle(obj)) {
@@ -490,8 +491,8 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 							file_priv);
 	}
 
+err:
 	drm_gem_object_unreference_unlocked(obj);
-
 	return ret;
 }
 
@@ -580,8 +581,6 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, struct drm_gem_object *obj,
 
 	user_data = (char __user *) (uintptr_t) args->data_ptr;
 	remain = args->size;
-	if (!access_ok(VERIFY_READ, user_data, remain))
-		return -EFAULT;
 
 
 	mutex_lock(&dev->struct_mutex);
@@ -934,14 +933,17 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		return -ENOENT;
 	obj_priv = to_intel_bo(obj);
 
-	/* Bounds check destination.
-	 *
-	 * XXX: This could use review for overflow issues...
-	 */
-	if (args->offset > obj->size || args->size > obj->size ||
-	    args->offset + args->size > obj->size) {
-		drm_gem_object_unreference_unlocked(obj);
-		return -EINVAL;
+	/* Bounds check destination. */
+	if (args->offset > obj->size || args->size > obj->size - args->offset) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (!access_ok(VERIFY_READ,
+		       (char __user *)(uintptr_t)args->data_ptr,
+		       args->size)) {
+		ret = -EFAULT;
+		goto err;
 	}
 
 	/* We can only do the GTT pwrite on untiled buffers, as otherwise
@@ -975,8 +977,8 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		DRM_INFO("pwrite failed %d\n", ret);
 #endif
 
+err:
 	drm_gem_object_unreference_unlocked(obj);
-
 	return ret;
 }
 
@@ -2351,14 +2353,21 @@ i915_gem_object_get_fence_reg(struct drm_gem_object *obj)
 
 	reg->obj = obj;
 
-	if (IS_GEN6(dev))
+	switch (INTEL_INFO(dev)->gen) {
+	case 6:
 		sandybridge_write_fence_reg(reg);
-	else if (IS_I965G(dev))
+		break;
+	case 5:
+	case 4:
 		i965_write_fence_reg(reg);
-	else if (IS_I9XX(dev))
+		break;
+	case 3:
 		i915_write_fence_reg(reg);
-	else
+		break;
+	case 2:
 		i830_write_fence_reg(reg);
+		break;
+	}
 
 	trace_i915_gem_object_get_fence(obj, obj_priv->fence_reg,
 			obj_priv->tiling_mode);
@@ -2381,22 +2390,26 @@ i915_gem_clear_fence_reg(struct drm_gem_object *obj)
 	struct drm_i915_gem_object *obj_priv = to_intel_bo(obj);
 	struct drm_i915_fence_reg *reg =
 		&dev_priv->fence_regs[obj_priv->fence_reg];
+	uint32_t fence_reg;
 
-	if (IS_GEN6(dev)) {
+	switch (INTEL_INFO(dev)->gen) {
+	case 6:
 		I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 +
 			     (obj_priv->fence_reg * 8), 0);
-	} else if (IS_I965G(dev)) {
+		break;
+	case 5:
+	case 4:
 		I915_WRITE64(FENCE_REG_965_0 + (obj_priv->fence_reg * 8), 0);
-	} else {
-		uint32_t fence_reg;
-
-		if (obj_priv->fence_reg < 8)
-			fence_reg = FENCE_REG_830_0 + obj_priv->fence_reg * 4;
+		break;
+	case 3:
+		if (obj_priv->fence_reg >= 8)
+			fence_reg = FENCE_REG_945_8 + (obj_priv->fence_reg - 8) * 4;
 		else
-			fence_reg = FENCE_REG_945_8 + (obj_priv->fence_reg -
-						       8) * 4;
+	case 2:
+			fence_reg = FENCE_REG_830_0 + obj_priv->fence_reg * 4;
 
 		I915_WRITE(fence_reg, 0);
+		break;
 	}
 
 	reg->obj = NULL;
@@ -3247,6 +3260,8 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
 				  (int) reloc->offset,
 				  reloc->read_domains,
 				  reloc->write_domain);
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
 			return -EINVAL;
 		}
 		if (reloc->write_domain & I915_GEM_DOMAIN_CPU ||
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 72cae3cccad8..5c428fa3e0b3 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -79,6 +79,7 @@ mark_free(struct drm_i915_gem_object *obj_priv,
 	   struct list_head *unwind)
 {
 	list_add(&obj_priv->evict_list, unwind);
+	drm_gem_object_reference(&obj_priv->base);
 	return drm_mm_scan_add_block(obj_priv->gtt_space);
 }
 
@@ -92,7 +93,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, unsigned alignmen
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct list_head eviction_list, unwind_list;
-	struct drm_i915_gem_object *obj_priv, *tmp_obj_priv;
+	struct drm_i915_gem_object *obj_priv;
 	struct list_head *render_iter, *bsd_iter;
 	int ret = 0;
 
@@ -165,6 +166,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, unsigned alignmen
 	list_for_each_entry(obj_priv, &unwind_list, evict_list) {
 		ret = drm_mm_scan_remove_block(obj_priv->gtt_space);
 		BUG_ON(ret);
+		drm_gem_object_unreference(&obj_priv->base);
 	}
 
 	/* We expect the caller to unpin, evict all and try again, or give up.
@@ -173,36 +175,34 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, unsigned alignmen
 	return -ENOSPC;
 
 found:
+	/* drm_mm doesn't allow any other other operations while
+	 * scanning, therefore store to be evicted objects on a
+	 * temporary list. */
 	INIT_LIST_HEAD(&eviction_list);
-	list_for_each_entry_safe(obj_priv, tmp_obj_priv,
-				 &unwind_list, evict_list) {
+	while (!list_empty(&unwind_list)) {
+		obj_priv = list_first_entry(&unwind_list,
+					    struct drm_i915_gem_object,
+					    evict_list);
 		if (drm_mm_scan_remove_block(obj_priv->gtt_space)) {
-			/* drm_mm doesn't allow any other other operations while
-			 * scanning, therefore store to be evicted objects on a
-			 * temporary list. */
 			list_move(&obj_priv->evict_list, &eviction_list);
+			continue;
 		}
+		list_del(&obj_priv->evict_list);
+		drm_gem_object_unreference(&obj_priv->base);
 	}
 
 	/* Unbinding will emit any required flushes */
-	list_for_each_entry_safe(obj_priv, tmp_obj_priv,
-				 &eviction_list, evict_list) {
-#if WATCH_LRU
-		DRM_INFO("%s: evicting %p\n", __func__, obj);
-#endif
-		ret = i915_gem_object_unbind(&obj_priv->base);
-		if (ret)
-			return ret;
+	while (!list_empty(&eviction_list)) {
+		obj_priv = list_first_entry(&eviction_list,
+					    struct drm_i915_gem_object,
+					    evict_list);
+		if (ret == 0)
+			ret = i915_gem_object_unbind(&obj_priv->base);
+		list_del(&obj_priv->evict_list);
+		drm_gem_object_unreference(&obj_priv->base);
 	}
 
-	/* The just created free hole should be on the top of the free stack
-	 * maintained by drm_mm, so this BUG_ON actually executes in O(1).
-	 * Furthermore all accessed data has just recently been used, so it
-	 * should be really fast, too. */
-	BUG_ON(!drm_mm_search_free(&dev_priv->mm.gtt_space, min_size,
-				   alignment, 0));
-
-	return 0;
+	return ret;
 }
 
 int
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 2c6b98f2440e..31f08581e93a 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -789,16 +789,25 @@ int i915_save_state(struct drm_device *dev)
 		dev_priv->saveSWF2[i] = I915_READ(SWF30 + (i << 2));
 
 	/* Fences */
-	if (IS_I965G(dev)) {
+	switch (INTEL_INFO(dev)->gen) {
+	case 6:
+		for (i = 0; i < 16; i++)
+			dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
+		break;
+	case 5:
+	case 4:
 		for (i = 0; i < 16; i++)
 			dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_965_0 + (i * 8));
-	} else {
-		for (i = 0; i < 8; i++)
-			dev_priv->saveFENCE[i] = I915_READ(FENCE_REG_830_0 + (i * 4));
-
+		break;
+	case 3:
 		if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
 			for (i = 0; i < 8; i++)
 				dev_priv->saveFENCE[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4));
+	case 2:
+		for (i = 0; i < 8; i++)
+			dev_priv->saveFENCE[i] = I915_READ(FENCE_REG_830_0 + (i * 4));
+		break;
+
 	}
 
 	return 0;
@@ -815,15 +824,24 @@ int i915_restore_state(struct drm_device *dev)
 	I915_WRITE(HWS_PGA, dev_priv->saveHWS);
 
 	/* Fences */
-	if (IS_I965G(dev)) {
+	switch (INTEL_INFO(dev)->gen) {
+	case 6:
+		for (i = 0; i < 16; i++)
+			I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->saveFENCE[i]);
+		break;
+	case 5:
+	case 4:
 		for (i = 0; i < 16; i++)
 			I915_WRITE64(FENCE_REG_965_0 + (i * 8), dev_priv->saveFENCE[i]);
-	} else {
-		for (i = 0; i < 8; i++)
-			I915_WRITE(FENCE_REG_830_0 + (i * 4), dev_priv->saveFENCE[i]);
+		break;
+	case 3:
+	case 2:
 		if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
 			for (i = 0; i < 8; i++)
 				I915_WRITE(FENCE_REG_945_8 + (i * 4), dev_priv->saveFENCE[i+8]);
+		for (i = 0; i < 8; i++)
+			I915_WRITE(FENCE_REG_830_0 + (i * 4), dev_priv->saveFENCE[i]);
+		break;
 	}
 
 	i915_restore_display(dev);
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index a02a8df73727..197d4f32585a 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -188,7 +188,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 
 	if (wait_for((I915_READ(PCH_ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0,
 		     1000, 1))
-		DRM_ERROR("timed out waiting for FORCE_TRIGGER");
+		DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER");
 
 	if (turn_off_dac) {
 		I915_WRITE(PCH_ADPA, temp);
@@ -245,7 +245,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 		if (wait_for((I915_READ(PORT_HOTPLUG_EN) &
 			      CRT_HOTPLUG_FORCE_DETECT) == 0,
 			     1000, 1))
-			DRM_ERROR("timed out waiting for FORCE_DETECT to go off");
+			DRM_DEBUG_KMS("timed out waiting for FORCE_DETECT to go off");
 	}
 
 	stat = I915_READ(PORT_HOTPLUG_STAT);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 19daead5b525..979228594599 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1013,8 +1013,8 @@ void intel_wait_for_vblank(struct drm_device *dev, int pipe)
 		DRM_DEBUG_KMS("vblank wait timed out\n");
 }
 
-/**
- * intel_wait_for_vblank_off - wait for vblank after disabling a pipe
+/*
+ * intel_wait_for_pipe_off - wait for pipe to turn off
  * @dev: drm device
  * @pipe: pipe to wait for
  *
@@ -1022,25 +1022,39 @@ void intel_wait_for_vblank(struct drm_device *dev, int pipe)
  * spinning on the vblank interrupt status bit, since we won't actually
  * see an interrupt when the pipe is disabled.
  *
- * So this function waits for the display line value to settle (it
- * usually ends up stopping at the start of the next frame).
+ * On Gen4 and above:
+ *   wait for the pipe register state bit to turn off
+ *
+ * Otherwise:
+ *   wait for the display line value to settle (it usually
+ *   ends up stopping at the start of the next frame).
+ *  
  */
-void intel_wait_for_vblank_off(struct drm_device *dev, int pipe)
+static void intel_wait_for_pipe_off(struct drm_device *dev, int pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipedsl_reg = (pipe == 0 ? PIPEADSL : PIPEBDSL);
-	unsigned long timeout = jiffies + msecs_to_jiffies(100);
-	u32 last_line;
-
-	/* Wait for the display line to settle */
-	do {
-		last_line = I915_READ(pipedsl_reg) & DSL_LINEMASK;
-		mdelay(5);
-	} while (((I915_READ(pipedsl_reg) & DSL_LINEMASK) != last_line) &&
-		 time_after(timeout, jiffies));
-
-	if (time_after(jiffies, timeout))
-		DRM_DEBUG_KMS("vblank wait timed out\n");
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		int pipeconf_reg = (pipe == 0 ? PIPEACONF : PIPEBCONF);
+
+		/* Wait for the Pipe State to go off */
+		if (wait_for((I915_READ(pipeconf_reg) & I965_PIPECONF_ACTIVE) == 0,
+			     100, 0))
+			DRM_DEBUG_KMS("pipe_off wait timed out\n");
+	} else {
+		u32 last_line;
+		int pipedsl_reg = (pipe == 0 ? PIPEADSL : PIPEBDSL);
+		unsigned long timeout = jiffies + msecs_to_jiffies(100);
+
+		/* Wait for the display line to settle */
+		do {
+			last_line = I915_READ(pipedsl_reg) & DSL_LINEMASK;
+			mdelay(5);
+		} while (((I915_READ(pipedsl_reg) & DSL_LINEMASK) != last_line) &&
+			 time_after(timeout, jiffies));
+		if (time_after(jiffies, timeout))
+			DRM_DEBUG_KMS("pipe_off wait timed out\n");
+	}
 }
 
 /* Parameters have changed, update FBC info */
@@ -2328,13 +2342,13 @@ static void i9xx_crtc_dpms(struct drm_crtc *crtc, int mode)
 			I915_READ(dspbase_reg);
 		}
 
-		/* Wait for vblank for the disable to take effect */
-		intel_wait_for_vblank_off(dev, pipe);
-
 		/* Don't disable pipe A or pipe A PLLs if needed */
 		if (pipeconf_reg == PIPEACONF &&
-		    (dev_priv->quirks & QUIRK_PIPEA_FORCE))
+		    (dev_priv->quirks & QUIRK_PIPEA_FORCE)) {
+			/* Wait for vblank for the disable to take effect */
+			intel_wait_for_vblank(dev, pipe);
 			goto skip_pipe_off;
+		}
 
 		/* Next, disable display pipes */
 		temp = I915_READ(pipeconf_reg);
@@ -2343,8 +2357,8 @@ static void i9xx_crtc_dpms(struct drm_crtc *crtc, int mode)
 			I915_READ(pipeconf_reg);
 		}
 
-		/* Wait for vblank for the disable to take effect. */
-		intel_wait_for_vblank_off(dev, pipe);
+		/* Wait for the pipe to turn off */
+		intel_wait_for_pipe_off(dev, pipe);
 
 		temp = I915_READ(dpll_reg);
 		if ((temp & DPLL_VCO_ENABLE) != 0) {
@@ -2463,11 +2477,19 @@ static bool intel_crtc_mode_fixup(struct drm_crtc *crtc,
 				  struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = crtc->dev;
+
 	if (HAS_PCH_SPLIT(dev)) {
 		/* FDI link clock is fixed at 2.7G */
 		if (mode->clock * 3 > IRONLAKE_FDI_FREQ * 4)
 			return false;
 	}
+
+	/* XXX some encoders set the crtcinfo, others don't.
+	 * Obviously we need some form of conflict resolution here...
+	 */
+	if (adjusted_mode->crtc_htotal == 0)
+		drm_mode_set_crtcinfo(adjusted_mode, 0);
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 1a51ee07de3e..9ab8708ac6ba 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1138,18 +1138,14 @@ static bool
 intel_dp_set_link_train(struct intel_dp *intel_dp,
 			uint32_t dp_reg_value,
 			uint8_t dp_train_pat,
-			uint8_t train_set[4],
-			bool first)
+			uint8_t train_set[4])
 {
 	struct drm_device *dev = intel_dp->base.enc.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(intel_dp->base.enc.crtc);
 	int ret;
 
 	I915_WRITE(intel_dp->output_reg, dp_reg_value);
 	POSTING_READ(intel_dp->output_reg);
-	if (first)
-		intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	intel_dp_aux_native_write_1(intel_dp,
 				    DP_TRAINING_PATTERN_SET,
@@ -1174,10 +1170,15 @@ intel_dp_link_train(struct intel_dp *intel_dp)
 	uint8_t voltage;
 	bool clock_recovery = false;
 	bool channel_eq = false;
-	bool first = true;
 	int tries;
 	u32 reg;
 	uint32_t DP = intel_dp->DP;
+	struct intel_crtc *intel_crtc = to_intel_crtc(intel_dp->base.enc.crtc);
+
+	/* Enable output, wait for it to become active */
+	I915_WRITE(intel_dp->output_reg, intel_dp->DP);
+	POSTING_READ(intel_dp->output_reg);
+	intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	/* Write the link configuration data */
 	intel_dp_aux_native_write(intel_dp, DP_LINK_BW_SET,
@@ -1210,9 +1211,8 @@ intel_dp_link_train(struct intel_dp *intel_dp)
 			reg = DP | DP_LINK_TRAIN_PAT_1;
 
 		if (!intel_dp_set_link_train(intel_dp, reg,
-					     DP_TRAINING_PATTERN_1, train_set, first))
+					     DP_TRAINING_PATTERN_1, train_set))
 			break;
-		first = false;
 		/* Set training pattern 1 */
 
 		udelay(100);
@@ -1266,8 +1266,7 @@ intel_dp_link_train(struct intel_dp *intel_dp)
 
 		/* channel eq pattern */
 		if (!intel_dp_set_link_train(intel_dp, reg,
-					     DP_TRAINING_PATTERN_2, train_set,
-					     false))
+					     DP_TRAINING_PATTERN_2, train_set))
 			break;
 
 		udelay(400);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ad312ca6b3e5..8828b3ac6414 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -229,7 +229,6 @@ extern struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 						    struct drm_crtc *crtc);
 int intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
-extern void intel_wait_for_vblank_off(struct drm_device *dev, int pipe);
 extern void intel_wait_for_vblank(struct drm_device *dev, int pipe);
 extern struct drm_crtc *intel_get_crtc_from_pipe(struct drm_device *dev, int pipe);
 extern struct drm_crtc *intel_get_load_detect_pipe(struct intel_encoder *intel_encoder,
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index 7bdc96256bf5..b61966c126d3 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -237,8 +237,10 @@ int intel_fbdev_destroy(struct drm_device *dev,
 	drm_fb_helper_fini(&ifbdev->helper);
 
 	drm_framebuffer_cleanup(&ifb->base);
-	if (ifb->obj)
+	if (ifb->obj) {
 		drm_gem_object_unreference(ifb->obj);
+		ifb->obj = NULL;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index e8e902d614ed..ee73e428a84a 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2170,8 +2170,7 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type)
         return true;
 
 err:
-	intel_sdvo_destroy_enhance_property(connector);
-	kfree(intel_sdvo_connector);
+	intel_sdvo_destroy(connector);
 	return false;
 }
 
@@ -2243,8 +2242,7 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
 	return true;
 
 err:
-	intel_sdvo_destroy_enhance_property(connector);
-	kfree(intel_sdvo_connector);
+	intel_sdvo_destroy(connector);
 	return false;
 }
 
@@ -2522,11 +2520,10 @@ static bool intel_sdvo_create_enhance_property(struct intel_sdvo *intel_sdvo,
 		uint16_t response;
 	} enhancements;
 
-	if (!intel_sdvo_get_value(intel_sdvo,
-				  SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS,
-				  &enhancements, sizeof(enhancements)))
-		return false;
-
+	enhancements.response = 0;
+	intel_sdvo_get_value(intel_sdvo,
+			     SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS,
+			     &enhancements, sizeof(enhancements));
 	if (enhancements.response == 0) {
 		DRM_DEBUG_KMS("No enhancement is supported\n");
 		return true;
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 87186a4bbf03..fc737037f751 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -558,8 +558,10 @@ nouveau_connector_get_modes(struct drm_connector *connector)
 	if (nv_encoder->dcb->type == OUTPUT_LVDS &&
 	    (nv_encoder->dcb->lvdsconf.use_straps_for_mode ||
 	     dev_priv->vbios.fp_no_ddc) && nouveau_bios_fp_mode(dev, NULL)) {
-		nv_connector->native_mode = drm_mode_create(dev);
-		nouveau_bios_fp_mode(dev, nv_connector->native_mode);
+		struct drm_display_mode mode;
+
+		nouveau_bios_fp_mode(dev, &mode);
+		nv_connector->native_mode = drm_mode_duplicate(dev, &mode);
 	}
 
 	/* Find the native mode if this is a digital panel, if we didn't
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index ead7b8fc53fc..19620a6709f5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -167,11 +167,9 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data,
 		goto out;
 
 	ret = drm_gem_handle_create(file_priv, nvbo->gem, &req->info.handle);
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(nvbo->gem);
 out:
-	drm_gem_object_handle_unreference_unlocked(nvbo->gem);
-
-	if (ret)
-		drm_gem_object_unreference_unlocked(nvbo->gem);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 1bc72c3190a9..fe359a239df3 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -4999,7 +4999,7 @@ typedef struct _SW_I2C_IO_DATA_PARAMETERS
 #define SW_I2C_CNTL_WRITE1BIT 6
 
 //==============================VESA definition Portion===============================
-#define VESA_OEM_PRODUCT_REV			            '01.00'
+#define VESA_OEM_PRODUCT_REV			            "01.00"
 #define VESA_MODE_ATTRIBUTE_MODE_SUPPORT	     0xBB	//refer to VBE spec p.32, no TTY support
 #define VESA_MODE_WIN_ATTRIBUTE						     7
 #define VESA_WIN_SIZE											     64
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 79082d4398ae..2f93d46ae69a 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1137,7 +1137,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 
 		WREG32(RCU_IND_INDEX, 0x203);
 		efuse_straps_3 = RREG32(RCU_IND_DATA);
-		efuse_box_bit_127_124 = (u8)(efuse_straps_3 & 0xF0000000) >> 28;
+		efuse_box_bit_127_124 = (u8)((efuse_straps_3 & 0xF0000000) >> 28);
 
 		switch(efuse_box_bit_127_124) {
 		case 0x0:
@@ -1407,6 +1407,7 @@ int evergreen_mc_init(struct radeon_device *rdev)
 	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
 	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	r600_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
 
@@ -1520,7 +1521,7 @@ void evergreen_disable_interrupt_state(struct radeon_device *rdev)
 {
 	u32 tmp;
 
-	WREG32(CP_INT_CNTL, 0);
+	WREG32(CP_INT_CNTL, CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
 	WREG32(GRBM_INT_CNTL, 0);
 	WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
 	WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index e151f16a8f86..e59422320bb6 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1030,6 +1030,7 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 		return r;
 	}
 	rdev->cp.ready = true;
+	rdev->mc.active_vram_size = rdev->mc.real_vram_size;
 	return 0;
 }
 
@@ -1047,6 +1048,7 @@ void r100_cp_fini(struct radeon_device *rdev)
 void r100_cp_disable(struct radeon_device *rdev)
 {
 	/* Disable ring */
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	rdev->cp.ready = false;
 	WREG32(RADEON_CP_CSQ_MODE, 0);
 	WREG32(RADEON_CP_CSQ_CNTL, 0);
@@ -2295,6 +2297,7 @@ void r100_vram_init_sizes(struct radeon_device *rdev)
 	/* FIXME we don't use the second aperture yet when we could use it */
 	if (rdev->mc.visible_vram_size > rdev->mc.aper_size)
 		rdev->mc.visible_vram_size = rdev->mc.aper_size;
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	config_aper_size = RREG32(RADEON_CONFIG_APER_SIZE);
 	if (rdev->flags & RADEON_IS_IGP) {
 		uint32_t tom;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index afc18d87fdca..7b65e4efe8af 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1248,6 +1248,7 @@ int r600_mc_init(struct radeon_device *rdev)
 	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	r600_vram_gtt_location(rdev, &rdev->mc);
 
 	if (rdev->flags & RADEON_IS_IGP) {
@@ -1917,6 +1918,7 @@ void r600_pciep_wreg(struct radeon_device *rdev, u32 reg, u32 v)
  */
 void r600_cp_stop(struct radeon_device *rdev)
 {
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1));
 }
 
@@ -2729,7 +2731,7 @@ int r600_ib_test(struct radeon_device *rdev)
 	if (i < rdev->usec_timeout) {
 		DRM_INFO("ib test succeeded in %u usecs\n", i);
 	} else {
-		DRM_ERROR("radeon: ib test failed (sracth(0x%04X)=0x%08X)\n",
+		DRM_ERROR("radeon: ib test failed (scratch(0x%04X)=0x%08X)\n",
 			  scratch, tmp);
 		r = -EINVAL;
 	}
@@ -2910,7 +2912,7 @@ static void r600_disable_interrupt_state(struct radeon_device *rdev)
 {
 	u32 tmp;
 
-	WREG32(CP_INT_CNTL, 0);
+	WREG32(CP_INT_CNTL, CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
 	WREG32(GRBM_INT_CNTL, 0);
 	WREG32(DxMODE_INT_MASK, 0);
 	if (ASIC_IS_DCE3(rdev)) {
@@ -3528,7 +3530,8 @@ void r600_ioctl_wait_idle(struct radeon_device *rdev, struct radeon_bo *bo)
 	/* r7xx hw bug.  write to HDP_DEBUG1 followed by fb read
 	 * rather than write to HDP_REG_COHERENCY_FLUSH_CNTL
 	 */
-	if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_RV740)) {
+	if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_RV740) &&
+	    rdev->vram_scratch.ptr) {
 		void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
 		u32 tmp;
 
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index 9ceb2a1ce799..3473c00781ff 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -532,6 +532,7 @@ int r600_blit_init(struct radeon_device *rdev)
 	memcpy(ptr + rdev->r600_blit.ps_offset, r6xx_ps, r6xx_ps_size * 4);
 	radeon_bo_kunmap(rdev->r600_blit.shader_obj);
 	radeon_bo_unreserve(rdev->r600_blit.shader_obj);
+	rdev->mc.active_vram_size = rdev->mc.real_vram_size;
 	return 0;
 }
 
@@ -539,6 +540,7 @@ void r600_blit_fini(struct radeon_device *rdev)
 {
 	int r;
 
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	if (rdev->r600_blit.shader_obj == NULL)
 		return;
 	/* If we can't reserve the bo, unref should be enough to destroy
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a168d644bf9e..9ff38c99a6ea 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -344,6 +344,7 @@ struct radeon_mc {
 	 * about vram size near mc fb location */
 	u64			mc_vram_size;
 	u64			visible_vram_size;
+	u64			active_vram_size;
 	u64			gtt_size;
 	u64			gtt_start;
 	u64			gtt_end;
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index ebae14c4b768..8e43ddae70cc 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -317,6 +317,15 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
 			*connector_type = DRM_MODE_CONNECTOR_DVID;
 	}
 
+	/* MSI K9A2GM V2/V3 board has no HDMI or DVI */
+	if ((dev->pdev->device == 0x796e) &&
+	    (dev->pdev->subsystem_vendor == 0x1462) &&
+	    (dev->pdev->subsystem_device == 0x7302)) {
+		if ((supported_device == ATOM_DEVICE_DFP2_SUPPORT) ||
+		    (supported_device == ATOM_DEVICE_DFP3_SUPPORT))
+			return false;
+	}
+
 	/* a-bit f-i90hd - ciaranm on #radeonhd - this board has no DVI */
 	if ((dev->pdev->device == 0x7941) &&
 	    (dev->pdev->subsystem_vendor == 0x147b) &&
@@ -1549,39 +1558,39 @@ radeon_atombios_get_tv_info(struct radeon_device *rdev)
 		switch (tv_info->ucTV_BootUpDefaultStandard) {
 		case ATOM_TV_NTSC:
 			tv_std = TV_STD_NTSC;
-			DRM_INFO("Default TV standard: NTSC\n");
+			DRM_DEBUG_KMS("Default TV standard: NTSC\n");
 			break;
 		case ATOM_TV_NTSCJ:
 			tv_std = TV_STD_NTSC_J;
-			DRM_INFO("Default TV standard: NTSC-J\n");
+			DRM_DEBUG_KMS("Default TV standard: NTSC-J\n");
 			break;
 		case ATOM_TV_PAL:
 			tv_std = TV_STD_PAL;
-			DRM_INFO("Default TV standard: PAL\n");
+			DRM_DEBUG_KMS("Default TV standard: PAL\n");
 			break;
 		case ATOM_TV_PALM:
 			tv_std = TV_STD_PAL_M;
-			DRM_INFO("Default TV standard: PAL-M\n");
+			DRM_DEBUG_KMS("Default TV standard: PAL-M\n");
 			break;
 		case ATOM_TV_PALN:
 			tv_std = TV_STD_PAL_N;
-			DRM_INFO("Default TV standard: PAL-N\n");
+			DRM_DEBUG_KMS("Default TV standard: PAL-N\n");
 			break;
 		case ATOM_TV_PALCN:
 			tv_std = TV_STD_PAL_CN;
-			DRM_INFO("Default TV standard: PAL-CN\n");
+			DRM_DEBUG_KMS("Default TV standard: PAL-CN\n");
 			break;
 		case ATOM_TV_PAL60:
 			tv_std = TV_STD_PAL_60;
-			DRM_INFO("Default TV standard: PAL-60\n");
+			DRM_DEBUG_KMS("Default TV standard: PAL-60\n");
 			break;
 		case ATOM_TV_SECAM:
 			tv_std = TV_STD_SECAM;
-			DRM_INFO("Default TV standard: SECAM\n");
+			DRM_DEBUG_KMS("Default TV standard: SECAM\n");
 			break;
 		default:
 			tv_std = TV_STD_NTSC;
-			DRM_INFO("Unknown TV standard; defaulting to NTSC\n");
+			DRM_DEBUG_KMS("Unknown TV standard; defaulting to NTSC\n");
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index a04b7a6ad95f..7b7ea269549c 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -913,47 +913,47 @@ radeon_combios_get_tv_info(struct radeon_device *rdev)
 			switch (RBIOS8(tv_info + 7) & 0xf) {
 			case 1:
 				tv_std = TV_STD_NTSC;
-				DRM_INFO("Default TV standard: NTSC\n");
+				DRM_DEBUG_KMS("Default TV standard: NTSC\n");
 				break;
 			case 2:
 				tv_std = TV_STD_PAL;
-				DRM_INFO("Default TV standard: PAL\n");
+				DRM_DEBUG_KMS("Default TV standard: PAL\n");
 				break;
 			case 3:
 				tv_std = TV_STD_PAL_M;
-				DRM_INFO("Default TV standard: PAL-M\n");
+				DRM_DEBUG_KMS("Default TV standard: PAL-M\n");
 				break;
 			case 4:
 				tv_std = TV_STD_PAL_60;
-				DRM_INFO("Default TV standard: PAL-60\n");
+				DRM_DEBUG_KMS("Default TV standard: PAL-60\n");
 				break;
 			case 5:
 				tv_std = TV_STD_NTSC_J;
-				DRM_INFO("Default TV standard: NTSC-J\n");
+				DRM_DEBUG_KMS("Default TV standard: NTSC-J\n");
 				break;
 			case 6:
 				tv_std = TV_STD_SCART_PAL;
-				DRM_INFO("Default TV standard: SCART-PAL\n");
+				DRM_DEBUG_KMS("Default TV standard: SCART-PAL\n");
 				break;
 			default:
 				tv_std = TV_STD_NTSC;
-				DRM_INFO
+				DRM_DEBUG_KMS
 				    ("Unknown TV standard; defaulting to NTSC\n");
 				break;
 			}
 
 			switch ((RBIOS8(tv_info + 9) >> 2) & 0x3) {
 			case 0:
-				DRM_INFO("29.498928713 MHz TV ref clk\n");
+				DRM_DEBUG_KMS("29.498928713 MHz TV ref clk\n");
 				break;
 			case 1:
-				DRM_INFO("28.636360000 MHz TV ref clk\n");
+				DRM_DEBUG_KMS("28.636360000 MHz TV ref clk\n");
 				break;
 			case 2:
-				DRM_INFO("14.318180000 MHz TV ref clk\n");
+				DRM_DEBUG_KMS("14.318180000 MHz TV ref clk\n");
 				break;
 			case 3:
-				DRM_INFO("27.000000000 MHz TV ref clk\n");
+				DRM_DEBUG_KMS("27.000000000 MHz TV ref clk\n");
 				break;
 			default:
 				break;
@@ -1324,7 +1324,7 @@ bool radeon_legacy_get_tmds_info_from_combios(struct radeon_encoder *encoder,
 
 	if (tmds_info) {
 		ver = RBIOS8(tmds_info);
-		DRM_INFO("DFP table revision: %d\n", ver);
+		DRM_DEBUG_KMS("DFP table revision: %d\n", ver);
 		if (ver == 3) {
 			n = RBIOS8(tmds_info + 5) + 1;
 			if (n > 4)
@@ -1408,7 +1408,7 @@ bool radeon_legacy_get_ext_tmds_info_from_combios(struct radeon_encoder *encoder
 		offset = combios_get_table_offset(dev, COMBIOS_EXT_TMDS_INFO_TABLE);
 		if (offset) {
 			ver = RBIOS8(offset);
-			DRM_INFO("External TMDS Table revision: %d\n", ver);
+			DRM_DEBUG_KMS("External TMDS Table revision: %d\n", ver);
 			tmds->slave_addr = RBIOS8(offset + 4 + 2);
 			tmds->slave_addr >>= 1; /* 7 bit addressing */
 			gpio = RBIOS8(offset + 4 + 3);
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 5731fc9b1ae3..3eef567b0421 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -203,6 +203,7 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct radeon_device *rdev = crtc->dev->dev_private;
 	int xorigin = 0, yorigin = 0;
+	int w = radeon_crtc->cursor_width;
 
 	if (x < 0)
 		xorigin = -x + 1;
@@ -213,22 +214,7 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 	if (yorigin >= CURSOR_HEIGHT)
 		yorigin = CURSOR_HEIGHT - 1;
 
-	radeon_lock_cursor(crtc, true);
-	if (ASIC_IS_DCE4(rdev)) {
-		/* cursors are offset into the total surface */
-		x += crtc->x;
-		y += crtc->y;
-		DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
-
-		/* XXX: check if evergreen has the same issues as avivo chips */
-		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset,
-		       ((xorigin ? 0 : x) << 16) |
-		       (yorigin ? 0 : y));
-		WREG32(EVERGREEN_CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
-		WREG32(EVERGREEN_CUR_SIZE + radeon_crtc->crtc_offset,
-		       ((radeon_crtc->cursor_width - 1) << 16) | (radeon_crtc->cursor_height - 1));
-	} else if (ASIC_IS_AVIVO(rdev)) {
-		int w = radeon_crtc->cursor_width;
+	if (ASIC_IS_AVIVO(rdev)) {
 		int i = 0;
 		struct drm_crtc *crtc_p;
 
@@ -260,7 +246,17 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 			if (w <= 0)
 				w = 1;
 		}
+	}
 
+	radeon_lock_cursor(crtc, true);
+	if (ASIC_IS_DCE4(rdev)) {
+		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset,
+		       ((xorigin ? 0 : x) << 16) |
+		       (yorigin ? 0 : y));
+		WREG32(EVERGREEN_CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
+		WREG32(EVERGREEN_CUR_SIZE + radeon_crtc->crtc_offset,
+		       ((w - 1) << 16) | (radeon_crtc->cursor_height - 1));
+	} else if (ASIC_IS_AVIVO(rdev)) {
 		WREG32(AVIVO_D1CUR_POSITION + radeon_crtc->crtc_offset,
 			     ((xorigin ? 0 : x) << 16) |
 			     (yorigin ? 0 : y));
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 127a395f70fb..b92d2f2fcbed 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -349,6 +349,8 @@ static void radeon_print_display_setup(struct drm_device *dev)
 					DRM_INFO("    DFP4: %s\n", encoder_names[radeon_encoder->encoder_id]);
 				if (devices & ATOM_DEVICE_DFP5_SUPPORT)
 					DRM_INFO("    DFP5: %s\n", encoder_names[radeon_encoder->encoder_id]);
+				if (devices & ATOM_DEVICE_DFP6_SUPPORT)
+					DRM_INFO("    DFP6: %s\n", encoder_names[radeon_encoder->encoder_id]);
 				if (devices & ATOM_DEVICE_TV1_SUPPORT)
 					DRM_INFO("    TV1: %s\n", encoder_names[radeon_encoder->encoder_id]);
 				if (devices & ATOM_DEVICE_CV_SUPPORT)
@@ -841,8 +843,9 @@ static void radeon_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct radeon_framebuffer *radeon_fb = to_radeon_framebuffer(fb);
 
-	if (radeon_fb->obj)
+	if (radeon_fb->obj) {
 		drm_gem_object_unreference_unlocked(radeon_fb->obj);
+	}
 	drm_framebuffer_cleanup(fb);
 	kfree(radeon_fb);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index c74a8b20d941..40b0c087b592 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -94,6 +94,7 @@ static void radeonfb_destroy_pinned_object(struct drm_gem_object *gobj)
 	ret = radeon_bo_reserve(rbo, false);
 	if (likely(ret == 0)) {
 		radeon_bo_kunmap(rbo);
+		radeon_bo_unpin(rbo);
 		radeon_bo_unreserve(rbo);
 	}
 	drm_gem_object_unreference_unlocked(gobj);
@@ -325,8 +326,6 @@ static int radeon_fbdev_destroy(struct drm_device *dev, struct radeon_fbdev *rfb
 {
 	struct fb_info *info;
 	struct radeon_framebuffer *rfb = &rfbdev->rfb;
-	struct radeon_bo *rbo;
-	int r;
 
 	if (rfbdev->helper.fbdev) {
 		info = rfbdev->helper.fbdev;
@@ -338,14 +337,8 @@ static int radeon_fbdev_destroy(struct drm_device *dev, struct radeon_fbdev *rfb
 	}
 
 	if (rfb->obj) {
-		rbo = rfb->obj->driver_private;
-		r = radeon_bo_reserve(rbo, false);
-		if (likely(r == 0)) {
-			radeon_bo_kunmap(rbo);
-			radeon_bo_unpin(rbo);
-			radeon_bo_unreserve(rbo);
-		}
-		drm_gem_object_unreference_unlocked(rfb->obj);
+		radeonfb_destroy_pinned_object(rfb->obj);
+		rfb->obj = NULL;
 	}
 	drm_fb_helper_fini(&rfbdev->helper);
 	drm_framebuffer_cleanup(&rfb->base);
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index c578f265b24c..d1e595d91723 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -201,11 +201,11 @@ int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
 		return r;
 	}
 	r = drm_gem_handle_create(filp, gobj, &handle);
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(gobj);
 	if (r) {
-		drm_gem_object_unreference_unlocked(gobj);
 		return r;
 	}
-	drm_gem_object_handle_unreference_unlocked(gobj);
 	args->handle = handle;
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 5eee3c41d124..8fbbe1c6ebbd 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -203,6 +203,10 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  */
 int radeon_driver_firstopen_kms(struct drm_device *dev)
 {
+	struct radeon_device *rdev = dev->dev_private;
+
+	if (rdev->powered_down)
+		return -EINVAL;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 0afd1e62347d..b3b5306bb578 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -69,7 +69,7 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	u32 c = 0;
 
 	rbo->placement.fpfn = 0;
-	rbo->placement.lpfn = 0;
+	rbo->placement.lpfn = rbo->rdev->mc.active_vram_size >> PAGE_SHIFT;
 	rbo->placement.placement = rbo->placements;
 	rbo->placement.busy_placement = rbo->placements;
 	if (domain & RADEON_GEM_DOMAIN_VRAM)
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 353998dc2c03..3481bc7f6f58 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -124,11 +124,8 @@ static inline int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type,
 	int r;
 
 	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, 0);
-	if (unlikely(r != 0)) {
-		if (r != -ERESTARTSYS)
-			dev_err(bo->rdev->dev, "%p reserve failed for wait\n", bo);
+	if (unlikely(r != 0))
 		return r;
-	}
 	spin_lock(&bo->tbo.lock);
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index cc05b230d7ef..51d5f7b5ab21 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -693,6 +693,7 @@ void rs600_mc_init(struct radeon_device *rdev)
 	rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE);
 	rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
 	base = RREG32_MC(R_000004_MC_FB_LOCATION);
 	base = G_000004_MC_FB_START(base) << 16;
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3e3f75718be3..4dc2a87ea680 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -157,6 +157,7 @@ void rs690_mc_init(struct radeon_device *rdev)
 	rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
 	rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
 	base = G_000100_MC_FB_START(base) << 16;
 	rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index bfa59db374d2..9490da700749 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -267,6 +267,7 @@ static void rv770_mc_program(struct radeon_device *rdev)
  */
 void r700_cp_stop(struct radeon_device *rdev)
 {
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	WREG32(CP_ME_CNTL, (CP_ME_HALT | CP_PFP_HALT));
 }
 
@@ -992,6 +993,7 @@ int rv770_mc_init(struct radeon_device *rdev)
 	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE);
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
+	rdev->mc.active_vram_size = rdev->mc.visible_vram_size;
 	r600_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index cb4cf7ef4d1e..db809e034cc4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -441,6 +441,43 @@ out_err:
 	return ret;
 }
 
+/**
+ * Call bo::reserved and with the lru lock held.
+ * Will release GPU memory type usage on destruction.
+ * This is the place to put in driver specific hooks.
+ * Will release the bo::reserved lock and the
+ * lru lock on exit.
+ */
+
+static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
+{
+	struct ttm_bo_global *glob = bo->glob;
+
+	if (bo->ttm) {
+
+		/**
+		 * Release the lru_lock, since we don't want to have
+		 * an atomic requirement on ttm_tt[unbind|destroy].
+		 */
+
+		spin_unlock(&glob->lru_lock);
+		ttm_tt_unbind(bo->ttm);
+		ttm_tt_destroy(bo->ttm);
+		bo->ttm = NULL;
+		spin_lock(&glob->lru_lock);
+	}
+
+	if (bo->mem.mm_node) {
+		drm_mm_put_block(bo->mem.mm_node);
+		bo->mem.mm_node = NULL;
+	}
+
+	atomic_set(&bo->reserved, 0);
+	wake_up_all(&bo->event_queue);
+	spin_unlock(&glob->lru_lock);
+}
+
+
 /**
  * If bo idle, remove from delayed- and lru lists, and unref.
  * If not idle, and already on delayed list, do nothing.
@@ -456,6 +493,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, bool remove_all)
 	int ret;
 
 	spin_lock(&bo->lock);
+retry:
 	(void) ttm_bo_wait(bo, false, false, !remove_all);
 
 	if (!bo->sync_obj) {
@@ -464,31 +502,52 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, bool remove_all)
 		spin_unlock(&bo->lock);
 
 		spin_lock(&glob->lru_lock);
-		put_count = ttm_bo_del_from_lru(bo);
+		ret = ttm_bo_reserve_locked(bo, false, !remove_all, false, 0);
+
+		/**
+		 * Someone else has the object reserved. Bail and retry.
+		 */
 
-		ret = ttm_bo_reserve_locked(bo, false, false, false, 0);
-		BUG_ON(ret);
-		if (bo->ttm)
-			ttm_tt_unbind(bo->ttm);
+		if (unlikely(ret == -EBUSY)) {
+			spin_unlock(&glob->lru_lock);
+			spin_lock(&bo->lock);
+			goto requeue;
+		}
+
+		/**
+		 * We can re-check for sync object without taking
+		 * the bo::lock since setting the sync object requires
+		 * also bo::reserved. A busy object at this point may
+		 * be caused by another thread starting an accelerated
+		 * eviction.
+		 */
+
+		if (unlikely(bo->sync_obj)) {
+			atomic_set(&bo->reserved, 0);
+			wake_up_all(&bo->event_queue);
+			spin_unlock(&glob->lru_lock);
+			spin_lock(&bo->lock);
+			if (remove_all)
+				goto retry;
+			else
+				goto requeue;
+		}
+
+		put_count = ttm_bo_del_from_lru(bo);
 
 		if (!list_empty(&bo->ddestroy)) {
 			list_del_init(&bo->ddestroy);
 			++put_count;
 		}
-		if (bo->mem.mm_node) {
-			drm_mm_put_block(bo->mem.mm_node);
-			bo->mem.mm_node = NULL;
-		}
-		spin_unlock(&glob->lru_lock);
 
-		atomic_set(&bo->reserved, 0);
+		ttm_bo_cleanup_memtype_use(bo);
 
 		while (put_count--)
 			kref_put(&bo->list_kref, ttm_bo_ref_bug);
 
 		return 0;
 	}
-
+requeue:
 	spin_lock(&glob->lru_lock);
 	if (list_empty(&bo->ddestroy)) {
 		void *sync_obj = bo->sync_obj;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 7cffb3e04232..3451a82adba7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -351,6 +351,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->lru);
 	INIT_LIST_HEAD(&fbo->swap);
 	fbo->vm_node = NULL;
+	atomic_set(&fbo->cpu_writers, 0);
 
 	fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
 	kref_init(&fbo->list_kref);
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index ca904799f018..b1e02fffd3cc 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -69,7 +69,7 @@ struct ttm_page_pool {
 	spinlock_t		lock;
 	bool			fill_lock;
 	struct list_head	list;
-	int			gfp_flags;
+	gfp_t			gfp_flags;
 	unsigned		npages;
 	char			*name;
 	unsigned long		nfrees;
@@ -475,7 +475,7 @@ static void ttm_handle_caching_state_failure(struct list_head *pages,
  * This function is reentrant if caller updates count depending on number of
  * pages returned in pages array.
  */
-static int ttm_alloc_new_pages(struct list_head *pages, int gfp_flags,
+static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags,
 		int ttm_flags, enum ttm_caching_state cstate, unsigned count)
 {
 	struct page **caching_array;
@@ -666,7 +666,7 @@ int ttm_get_pages(struct list_head *pages, int flags,
 {
 	struct ttm_page_pool *pool = ttm_get_pool(flags, cstate);
 	struct page *p = NULL;
-	int gfp_flags = GFP_USER;
+	gfp_t gfp_flags = GFP_USER;
 	int r;
 
 	/* set zero flag for page allocation if required */
@@ -818,7 +818,7 @@ int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
 	return 0;
 }
 
-void ttm_page_alloc_fini()
+void ttm_page_alloc_fini(void)
 {
 	int i;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 72ec2e2b6e97..a96ed6d9d010 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -148,13 +148,16 @@ static struct pci_device_id vmw_pci_id_list[] = {
 	{0, 0, 0}
 };
 
-static char *vmw_devname = "vmwgfx";
+static int enable_fbdev;
 
 static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
 static void vmw_master_init(struct vmw_master *);
 static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
 			      void *ptr);
 
+MODULE_PARM_DESC(enable_fbdev, "Enable vmwgfx fbdev");
+module_param_named(enable_fbdev, enable_fbdev, int, 0600);
+
 static void vmw_print_capabilities(uint32_t capabilities)
 {
 	DRM_INFO("Capabilities:\n");
@@ -192,8 +195,6 @@ static int vmw_request_device(struct vmw_private *dev_priv)
 {
 	int ret;
 
-	vmw_kms_save_vga(dev_priv);
-
 	ret = vmw_fifo_init(dev_priv, &dev_priv->fifo);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Unable to initialize FIFO.\n");
@@ -206,9 +207,35 @@ static int vmw_request_device(struct vmw_private *dev_priv)
 static void vmw_release_device(struct vmw_private *dev_priv)
 {
 	vmw_fifo_release(dev_priv, &dev_priv->fifo);
-	vmw_kms_restore_vga(dev_priv);
 }
 
+int vmw_3d_resource_inc(struct vmw_private *dev_priv)
+{
+	int ret = 0;
+
+	mutex_lock(&dev_priv->release_mutex);
+	if (unlikely(dev_priv->num_3d_resources++ == 0)) {
+		ret = vmw_request_device(dev_priv);
+		if (unlikely(ret != 0))
+			--dev_priv->num_3d_resources;
+	}
+	mutex_unlock(&dev_priv->release_mutex);
+	return ret;
+}
+
+
+void vmw_3d_resource_dec(struct vmw_private *dev_priv)
+{
+	int32_t n3d;
+
+	mutex_lock(&dev_priv->release_mutex);
+	if (unlikely(--dev_priv->num_3d_resources == 0))
+		vmw_release_device(dev_priv);
+	n3d = (int32_t) dev_priv->num_3d_resources;
+	mutex_unlock(&dev_priv->release_mutex);
+
+	BUG_ON(n3d < 0);
+}
 
 static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 {
@@ -228,6 +255,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	dev_priv->last_read_sequence = (uint32_t) -100;
 	mutex_init(&dev_priv->hw_mutex);
 	mutex_init(&dev_priv->cmdbuf_mutex);
+	mutex_init(&dev_priv->release_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	idr_init(&dev_priv->context_idr);
 	idr_init(&dev_priv->surface_idr);
@@ -244,6 +272,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	dev_priv->vram_start = pci_resource_start(dev->pdev, 1);
 	dev_priv->mmio_start = pci_resource_start(dev->pdev, 2);
 
+	dev_priv->enable_fb = enable_fbdev;
+
 	mutex_lock(&dev_priv->hw_mutex);
 
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
@@ -343,17 +373,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	dev->dev_private = dev_priv;
 
-	if (!dev->devname)
-		dev->devname = vmw_devname;
-
-	if (dev_priv->capabilities & SVGA_CAP_IRQMASK) {
-		ret = drm_irq_install(dev);
-		if (unlikely(ret != 0)) {
-			DRM_ERROR("Failed installing irq: %d\n", ret);
-			goto out_no_irq;
-		}
-	}
-
 	ret = pci_request_regions(dev->pdev, "vmwgfx probe");
 	dev_priv->stealth = (ret != 0);
 	if (dev_priv->stealth) {
@@ -369,26 +388,52 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 			goto out_no_device;
 		}
 	}
-	ret = vmw_request_device(dev_priv);
+	ret = vmw_kms_init(dev_priv);
 	if (unlikely(ret != 0))
-		goto out_no_device;
-	vmw_kms_init(dev_priv);
+		goto out_no_kms;
 	vmw_overlay_init(dev_priv);
-	vmw_fb_init(dev_priv);
+	if (dev_priv->enable_fb) {
+		ret = vmw_3d_resource_inc(dev_priv);
+		if (unlikely(ret != 0))
+			goto out_no_fifo;
+		vmw_kms_save_vga(dev_priv);
+		vmw_fb_init(dev_priv);
+		DRM_INFO("%s", vmw_fifo_have_3d(dev_priv) ?
+			 "Detected device 3D availability.\n" :
+			 "Detected no device 3D availability.\n");
+	} else {
+		DRM_INFO("Delayed 3D detection since we're not "
+			 "running the device in SVGA mode yet.\n");
+	}
+
+	if (dev_priv->capabilities & SVGA_CAP_IRQMASK) {
+		ret = drm_irq_install(dev);
+		if (unlikely(ret != 0)) {
+			DRM_ERROR("Failed installing irq: %d\n", ret);
+			goto out_no_irq;
+		}
+	}
 
 	dev_priv->pm_nb.notifier_call = vmwgfx_pm_notifier;
 	register_pm_notifier(&dev_priv->pm_nb);
 
-	DRM_INFO("%s", vmw_fifo_have_3d(dev_priv) ? "Have 3D\n" : "No 3D\n");
-
 	return 0;
 
-out_no_device:
-	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
-		drm_irq_uninstall(dev_priv->dev);
-	if (dev->devname == vmw_devname)
-		dev->devname = NULL;
 out_no_irq:
+	if (dev_priv->enable_fb) {
+		vmw_fb_close(dev_priv);
+		vmw_kms_restore_vga(dev_priv);
+		vmw_3d_resource_dec(dev_priv);
+	}
+out_no_fifo:
+	vmw_overlay_close(dev_priv);
+	vmw_kms_close(dev_priv);
+out_no_kms:
+	if (dev_priv->stealth)
+		pci_release_region(dev->pdev, 2);
+	else
+		pci_release_regions(dev->pdev);
+out_no_device:
 	ttm_object_device_release(&dev_priv->tdev);
 out_err4:
 	iounmap(dev_priv->mmio_virt);
@@ -415,19 +460,20 @@ static int vmw_driver_unload(struct drm_device *dev)
 
 	unregister_pm_notifier(&dev_priv->pm_nb);
 
-	vmw_fb_close(dev_priv);
+	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
+		drm_irq_uninstall(dev_priv->dev);
+	if (dev_priv->enable_fb) {
+		vmw_fb_close(dev_priv);
+		vmw_kms_restore_vga(dev_priv);
+		vmw_3d_resource_dec(dev_priv);
+	}
 	vmw_kms_close(dev_priv);
 	vmw_overlay_close(dev_priv);
-	vmw_release_device(dev_priv);
 	if (dev_priv->stealth)
 		pci_release_region(dev->pdev, 2);
 	else
 		pci_release_regions(dev->pdev);
 
-	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
-		drm_irq_uninstall(dev_priv->dev);
-	if (dev->devname == vmw_devname)
-		dev->devname = NULL;
 	ttm_object_device_release(&dev_priv->tdev);
 	iounmap(dev_priv->mmio_virt);
 	drm_mtrr_del(dev_priv->mmio_mtrr, dev_priv->mmio_start,
@@ -500,7 +546,7 @@ static long vmw_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		struct drm_ioctl_desc *ioctl =
 		    &vmw_ioctls[nr - DRM_COMMAND_BASE];
 
-		if (unlikely(ioctl->cmd != cmd)) {
+		if (unlikely(ioctl->cmd_drv != cmd)) {
 			DRM_ERROR("Invalid command format, ioctl %d\n",
 				  nr - DRM_COMMAND_BASE);
 			return -EINVAL;
@@ -589,6 +635,16 @@ static int vmw_master_set(struct drm_device *dev,
 	struct vmw_master *vmaster = vmw_master(file_priv->master);
 	int ret = 0;
 
+	if (!dev_priv->enable_fb) {
+		ret = vmw_3d_resource_inc(dev_priv);
+		if (unlikely(ret != 0))
+			return ret;
+		vmw_kms_save_vga(dev_priv);
+		mutex_lock(&dev_priv->hw_mutex);
+		vmw_write(dev_priv, SVGA_REG_TRACES, 0);
+		mutex_unlock(&dev_priv->hw_mutex);
+	}
+
 	if (active) {
 		BUG_ON(active != &dev_priv->fbdev_master);
 		ret = ttm_vt_lock(&active->lock, false, vmw_fp->tfile);
@@ -617,7 +673,13 @@ static int vmw_master_set(struct drm_device *dev,
 	return 0;
 
 out_no_active_lock:
-	vmw_release_device(dev_priv);
+	if (!dev_priv->enable_fb) {
+		mutex_lock(&dev_priv->hw_mutex);
+		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
+		mutex_unlock(&dev_priv->hw_mutex);
+		vmw_kms_restore_vga(dev_priv);
+		vmw_3d_resource_dec(dev_priv);
+	}
 	return ret;
 }
 
@@ -645,11 +707,23 @@ static void vmw_master_drop(struct drm_device *dev,
 
 	ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
 
+	if (!dev_priv->enable_fb) {
+		ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM);
+		if (unlikely(ret != 0))
+			DRM_ERROR("Unable to clean VRAM on master drop.\n");
+		mutex_lock(&dev_priv->hw_mutex);
+		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
+		mutex_unlock(&dev_priv->hw_mutex);
+		vmw_kms_restore_vga(dev_priv);
+		vmw_3d_resource_dec(dev_priv);
+	}
+
 	dev_priv->active_master = &dev_priv->fbdev_master;
 	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
 	ttm_vt_unlock(&dev_priv->fbdev_master.lock);
 
-	vmw_fb_on(dev_priv);
+	if (dev_priv->enable_fb)
+		vmw_fb_on(dev_priv);
 }
 
 
@@ -722,6 +796,7 @@ static struct drm_driver driver = {
 	.irq_postinstall = vmw_irq_postinstall,
 	.irq_uninstall = vmw_irq_uninstall,
 	.irq_handler = vmw_irq_handler,
+	.get_vblank_counter = vmw_get_vblank_counter,
 	.reclaim_buffers_locked = NULL,
 	.get_map_ofs = drm_core_get_map_ofs,
 	.get_reg_ofs = drm_core_get_reg_ofs,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 429f917b60bf..58de6393f611 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -277,6 +277,7 @@ struct vmw_private {
 
 	bool stealth;
 	bool is_opened;
+	bool enable_fb;
 
 	/**
 	 * Master management.
@@ -285,6 +286,9 @@ struct vmw_private {
 	struct vmw_master *active_master;
 	struct vmw_master fbdev_master;
 	struct notifier_block pm_nb;
+
+	struct mutex release_mutex;
+	uint32_t num_3d_resources;
 };
 
 static inline struct vmw_private *vmw_priv(struct drm_device *dev)
@@ -319,6 +323,9 @@ static inline uint32_t vmw_read(struct vmw_private *dev_priv,
 	return val;
 }
 
+int vmw_3d_resource_inc(struct vmw_private *dev_priv);
+void vmw_3d_resource_dec(struct vmw_private *dev_priv);
+
 /**
  * GMR utilities - vmwgfx_gmr.c
  */
@@ -511,6 +518,7 @@ void vmw_kms_write_svga(struct vmw_private *vmw_priv,
 			unsigned bbp, unsigned depth);
 int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
+u32 vmw_get_vblank_counter(struct drm_device *dev, int crtc);
 
 /**
  * Overlay control - vmwgfx_overlay.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 870967a97c15..409e172f4abf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -615,6 +615,11 @@ int vmw_dmabuf_to_start_of_vram(struct vmw_private *vmw_priv,
 	if (unlikely(ret != 0))
 		goto err_unlock;
 
+	if (bo->mem.mem_type == TTM_PL_VRAM &&
+	    bo->mem.mm_node->start < bo->num_pages)
+		(void) ttm_bo_validate(bo, &vmw_sys_placement, false,
+				       false, false);
+
 	ret = ttm_bo_validate(bo, &ne_placement, false, false, false);
 
 	/* Could probably bug on */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index e6a1eb7ea954..0fe31766e4cf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -106,6 +106,7 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 	mutex_lock(&dev_priv->hw_mutex);
 	dev_priv->enable_state = vmw_read(dev_priv, SVGA_REG_ENABLE);
 	dev_priv->config_done_state = vmw_read(dev_priv, SVGA_REG_CONFIG_DONE);
+	dev_priv->traces_state = vmw_read(dev_priv, SVGA_REG_TRACES);
 	vmw_write(dev_priv, SVGA_REG_ENABLE, 1);
 
 	min = 4;
@@ -175,6 +176,8 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 		  dev_priv->config_done_state);
 	vmw_write(dev_priv, SVGA_REG_ENABLE,
 		  dev_priv->enable_state);
+	vmw_write(dev_priv, SVGA_REG_TRACES,
+		  dev_priv->traces_state);
 
 	mutex_unlock(&dev_priv->hw_mutex);
 	vmw_fence_queue_takedown(&fifo->fence_queue);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 64d7f47df868..e882ba099f0c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -898,7 +898,19 @@ int vmw_kms_save_vga(struct vmw_private *vmw_priv)
 		save->width = vmw_read(vmw_priv, SVGA_REG_DISPLAY_WIDTH);
 		save->height = vmw_read(vmw_priv, SVGA_REG_DISPLAY_HEIGHT);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_ID, SVGA_ID_INVALID);
+		if (i == 0 && vmw_priv->num_displays == 1 &&
+		    save->width == 0 && save->height == 0) {
+
+			/*
+			 * It should be fairly safe to assume that these
+			 * values are uninitialized.
+			 */
+
+			save->width = vmw_priv->vga_width - save->pos_x;
+			save->height = vmw_priv->vga_height - save->pos_y;
+		}
 	}
+
 	return 0;
 }
 
@@ -984,3 +996,8 @@ out_unlock:
 	ttm_read_unlock(&vmaster->lock);
 	return ret;
 }
+
+u32 vmw_get_vblank_counter(struct drm_device *dev, int crtc)
+{
+	return 0;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 7083b1a24df3..11cb39e3accb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -27,6 +27,8 @@
 
 #include "vmwgfx_kms.h"
 
+#define VMWGFX_LDU_NUM_DU 8
+
 #define vmw_crtc_to_ldu(x) \
 	container_of(x, struct vmw_legacy_display_unit, base.crtc)
 #define vmw_encoder_to_ldu(x) \
@@ -536,6 +538,10 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 
 int vmw_kms_init_legacy_display_system(struct vmw_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
+	int i;
+	int ret;
+
 	if (dev_priv->ldu_priv) {
 		DRM_INFO("ldu system already on\n");
 		return -EINVAL;
@@ -553,23 +559,24 @@ int vmw_kms_init_legacy_display_system(struct vmw_private *dev_priv)
 
 	drm_mode_create_dirty_info_property(dev_priv->dev);
 
-	vmw_ldu_init(dev_priv, 0);
-	/* for old hardware without multimon only enable one display */
 	if (dev_priv->capabilities & SVGA_CAP_MULTIMON) {
-		vmw_ldu_init(dev_priv, 1);
-		vmw_ldu_init(dev_priv, 2);
-		vmw_ldu_init(dev_priv, 3);
-		vmw_ldu_init(dev_priv, 4);
-		vmw_ldu_init(dev_priv, 5);
-		vmw_ldu_init(dev_priv, 6);
-		vmw_ldu_init(dev_priv, 7);
+		for (i = 0; i < VMWGFX_LDU_NUM_DU; ++i)
+			vmw_ldu_init(dev_priv, i);
+		ret = drm_vblank_init(dev, VMWGFX_LDU_NUM_DU);
+	} else {
+		/* for old hardware without multimon only enable one display */
+		vmw_ldu_init(dev_priv, 0);
+		ret = drm_vblank_init(dev, 1);
 	}
 
-	return 0;
+	return ret;
 }
 
 int vmw_kms_close_legacy_display_system(struct vmw_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
+
+	drm_vblank_cleanup(dev);
 	if (!dev_priv->ldu_priv)
 		return -ENOSYS;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 5f2d5df01e5c..c8c40e9979db 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -211,6 +211,7 @@ static void vmw_hw_context_destroy(struct vmw_resource *res)
 	cmd->body.cid = cpu_to_le32(res->id);
 
 	vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	vmw_3d_resource_dec(dev_priv);
 }
 
 static int vmw_context_init(struct vmw_private *dev_priv,
@@ -247,6 +248,7 @@ static int vmw_context_init(struct vmw_private *dev_priv,
 	cmd->body.cid = cpu_to_le32(res->id);
 
 	vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	(void) vmw_3d_resource_inc(dev_priv);
 	vmw_resource_activate(res, vmw_hw_context_destroy);
 	return 0;
 }
@@ -406,6 +408,7 @@ static void vmw_hw_surface_destroy(struct vmw_resource *res)
 	cmd->body.sid = cpu_to_le32(res->id);
 
 	vmw_fifo_commit(dev_priv, sizeof(*cmd));
+	vmw_3d_resource_dec(dev_priv);
 }
 
 void vmw_surface_res_free(struct vmw_resource *res)
@@ -473,6 +476,7 @@ int vmw_surface_init(struct vmw_private *dev_priv,
 	}
 
 	vmw_fifo_commit(dev_priv, submit_size);
+	(void) vmw_3d_resource_inc(dev_priv);
 	vmw_resource_activate(res, vmw_hw_surface_destroy);
 	return 0;
 }
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index b87569e96b16..f366f968155a 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -598,7 +598,7 @@ static inline void vga_update_device_decodes(struct vga_device *vgadev,
 	pr_debug("vgaarb: decoding count now is: %d\n", vga_decode_count);
 }
 
-void __vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes, bool userspace)
+static void __vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes, bool userspace)
 {
 	struct vga_device *vgadev;
 	unsigned long flags;
diff --git a/drivers/hid/hid-cando.c b/drivers/hid/hid-cando.c
index 4267a6fdc277..5925bdcd417d 100644
--- a/drivers/hid/hid-cando.c
+++ b/drivers/hid/hid-cando.c
@@ -237,6 +237,8 @@ static const struct hid_device_id cando_devices[] = {
 			USB_DEVICE_ID_CANDO_MULTI_TOUCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CANDO,
 			USB_DEVICE_ID_CANDO_MULTI_TOUCH_11_6) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CANDO,
+		USB_DEVICE_ID_CANDO_MULTI_TOUCH_15_6) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, cando_devices);
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3f7292486024..a0dea3d1296e 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1292,6 +1292,7 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BTC, USB_DEVICE_ID_BTC_EMPREX_REMOTE_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CANDO, USB_DEVICE_ID_CANDO_MULTI_TOUCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CANDO, USB_DEVICE_ID_CANDO_MULTI_TOUCH_11_6) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CANDO, USB_DEVICE_ID_CANDO_MULTI_TOUCH_15_6) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_TACTICAL_PAD) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 765a4f53eb5c..c5ae5f1545bd 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -134,6 +134,7 @@
 #define USB_VENDOR_ID_CANDO		0x2087
 #define USB_DEVICE_ID_CANDO_MULTI_TOUCH	0x0a01
 #define USB_DEVICE_ID_CANDO_MULTI_TOUCH_11_6 0x0b03
+#define USB_DEVICE_ID_CANDO_MULTI_TOUCH_15_6 0x0f01
 
 #define USB_VENDOR_ID_CH		0x068e
 #define USB_DEVICE_ID_CH_PRO_PEDALS	0x00f2
@@ -503,6 +504,7 @@
 
 #define USB_VENDOR_ID_TURBOX		0x062a
 #define USB_DEVICE_ID_TURBOX_KEYBOARD	0x0201
+#define USB_DEVICE_ID_TURBOX_TOUCHSCREEN_MOSART	0x7100
 
 #define USB_VENDOR_ID_TWINHAN		0x6253
 #define USB_DEVICE_ID_TWINHAN_IR_REMOTE	0x0100
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 47d70c523d93..a3866b5c0c43 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -109,6 +109,12 @@ static ssize_t hidraw_write(struct file *file, const char __user *buffer, size_t
 	int ret = 0;
 
 	mutex_lock(&minors_lock);
+
+	if (!hidraw_table[minor]) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	dev = hidraw_table[minor]->hid;
 
 	if (!dev->hid_output_raw_report) {
@@ -244,6 +250,10 @@ static long hidraw_ioctl(struct file *file, unsigned int cmd,
 
 	mutex_lock(&minors_lock);
 	dev = hidraw_table[minor];
+	if (!dev) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	switch (cmd) {
 		case HIDIOCGRDESCSIZE:
@@ -317,6 +327,7 @@ static long hidraw_ioctl(struct file *file, unsigned int cmd,
 
 		ret = -ENOTTY;
 	}
+out:
 	mutex_unlock(&minors_lock);
 	return ret;
 }
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 70da3181c8a0..f0260c699adb 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -36,6 +36,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_DWAV, USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER, HID_QUIRK_MULTI_INPUT | HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_MOJO, USB_DEVICE_ID_RETRO_ADAPTER, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_TURBOX, USB_DEVICE_ID_TURBOX_TOUCHSCREEN_MOSART, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_DRIVING, HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING, HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING, HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 4d4d09bdec0a..97499d00615a 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -409,7 +409,7 @@ config SENSORS_CORETEMP
 
 config SENSORS_PKGTEMP
 	tristate "Intel processor package temperature sensor"
-	depends on X86 && PCI && EXPERIMENTAL
+	depends on X86 && EXPERIMENTAL
 	help
 	  If you say yes here you get support for the package level temperature
 	  sensor inside your CPU. Check documentation/driver for details.
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index de8111114f46..a23b17a78ace 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -36,6 +36,7 @@
 #include <linux/pci.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
+#include <asm/smp.h>
 
 #define DRVNAME	"coretemp"
 
@@ -423,9 +424,18 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)
 	int err;
 	struct platform_device *pdev;
 	struct pdev_entry *pdev_entry;
-#ifdef CONFIG_SMP
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
-#endif
+
+	/*
+	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
+	 * sensors. We check this bit only, all the early CPUs
+	 * without thermal sensors will be filtered out.
+	 */
+	if (!cpu_has(c, X86_FEATURE_DTS)) {
+		printk(KERN_INFO DRVNAME ": CPU (model=0x%x)"
+		       " has no thermal sensor.\n", c->x86_model);
+		return 0;
+	}
 
 	mutex_lock(&pdev_list_mutex);
 
@@ -482,14 +492,22 @@ exit:
 
 static void coretemp_device_remove(unsigned int cpu)
 {
-	struct pdev_entry *p, *n;
+	struct pdev_entry *p;
+	unsigned int i;
+
 	mutex_lock(&pdev_list_mutex);
-	list_for_each_entry_safe(p, n, &pdev_list, list) {
-		if (p->cpu == cpu) {
-			platform_device_unregister(p->pdev);
-			list_del(&p->list);
-			kfree(p);
-		}
+	list_for_each_entry(p, &pdev_list, list) {
+		if (p->cpu != cpu)
+			continue;
+
+		platform_device_unregister(p->pdev);
+		list_del(&p->list);
+		mutex_unlock(&pdev_list_mutex);
+		kfree(p);
+		for_each_cpu(i, cpu_sibling_mask(cpu))
+			if (i != cpu && !coretemp_device_add(i))
+				break;
+		return;
 	}
 	mutex_unlock(&pdev_list_mutex);
 }
@@ -527,30 +545,21 @@ static int __init coretemp_init(void)
 	if (err)
 		goto exit;
 
-	for_each_online_cpu(i) {
-		struct cpuinfo_x86 *c = &cpu_data(i);
-		/*
-		 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
-		 * sensors. We check this bit only, all the early CPUs
-		 * without thermal sensors will be filtered out.
-		 */
-		if (c->cpuid_level >= 6 && (cpuid_eax(0x06) & 0x01))
-			coretemp_device_add(i);
-		else {
-			printk(KERN_INFO DRVNAME ": CPU (model=0x%x)"
-				" has no thermal sensor.\n", c->x86_model);
-		}
-	}
+	for_each_online_cpu(i)
+		coretemp_device_add(i);
+
+#ifndef CONFIG_HOTPLUG_CPU
 	if (list_empty(&pdev_list)) {
 		err = -ENODEV;
 		goto exit_driver_unreg;
 	}
+#endif
 
 	register_hotcpu_notifier(&coretemp_cpu_notifier);
 	return 0;
 
-exit_driver_unreg:
 #ifndef CONFIG_HOTPLUG_CPU
+exit_driver_unreg:
 	platform_driver_unregister(&coretemp_driver);
 #endif
 exit:
diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c
index 537841ef44b9..75afb3b0e076 100644
--- a/drivers/hwmon/f71882fg.c
+++ b/drivers/hwmon/f71882fg.c
@@ -111,7 +111,7 @@ static struct platform_device *f71882fg_pdev;
 /* Super-I/O Function prototypes */
 static inline int superio_inb(int base, int reg);
 static inline int superio_inw(int base, int reg);
-static inline void superio_enter(int base);
+static inline int superio_enter(int base);
 static inline void superio_select(int base, int ld);
 static inline void superio_exit(int base);
 
@@ -861,11 +861,20 @@ static int superio_inw(int base, int reg)
 	return val;
 }
 
-static inline void superio_enter(int base)
+static inline int superio_enter(int base)
 {
+	/* Don't step on other drivers' I/O space by accident */
+	if (!request_muxed_region(base, 2, DRVNAME)) {
+		printk(KERN_ERR DRVNAME ": I/O address 0x%04x already in use\n",
+				base);
+		return -EBUSY;
+	}
+
 	/* according to the datasheet the key must be send twice! */
 	outb(SIO_UNLOCK_KEY, base);
 	outb(SIO_UNLOCK_KEY, base);
+
+	return 0;
 }
 
 static inline void superio_select(int base, int ld)
@@ -877,6 +886,7 @@ static inline void superio_select(int base, int ld)
 static inline void superio_exit(int base)
 {
 	outb(SIO_LOCK_KEY, base);
+	release_region(base, 2);
 }
 
 static inline int fan_from_reg(u16 reg)
@@ -2175,21 +2185,15 @@ static int f71882fg_remove(struct platform_device *pdev)
 static int __init f71882fg_find(int sioaddr, unsigned short *address,
 	struct f71882fg_sio_data *sio_data)
 {
-	int err = -ENODEV;
 	u16 devid;
-
-	/* Don't step on other drivers' I/O space by accident */
-	if (!request_region(sioaddr, 2, DRVNAME)) {
-		printk(KERN_ERR DRVNAME ": I/O address 0x%04x already in use\n",
-				(int)sioaddr);
-		return -EBUSY;
-	}
-
-	superio_enter(sioaddr);
+	int err = superio_enter(sioaddr);
+	if (err)
+		return err;
 
 	devid = superio_inw(sioaddr, SIO_REG_MANID);
 	if (devid != SIO_FINTEK_ID) {
 		pr_debug(DRVNAME ": Not a Fintek device\n");
+		err = -ENODEV;
 		goto exit;
 	}
 
@@ -2213,6 +2217,7 @@ static int __init f71882fg_find(int sioaddr, unsigned short *address,
 	default:
 		printk(KERN_INFO DRVNAME ": Unsupported Fintek device: %04x\n",
 		       (unsigned int)devid);
+		err = -ENODEV;
 		goto exit;
 	}
 
@@ -2223,12 +2228,14 @@ static int __init f71882fg_find(int sioaddr, unsigned short *address,
 
 	if (!(superio_inb(sioaddr, SIO_REG_ENABLE) & 0x01)) {
 		printk(KERN_WARNING DRVNAME ": Device not activated\n");
+		err = -ENODEV;
 		goto exit;
 	}
 
 	*address = superio_inw(sioaddr, SIO_REG_ADDR);
 	if (*address == 0) {
 		printk(KERN_WARNING DRVNAME ": Base address not set\n");
+		err = -ENODEV;
 		goto exit;
 	}
 	*address &= ~(REGION_LENGTH - 1);	/* Ignore 3 LSB */
@@ -2239,7 +2246,6 @@ static int __init f71882fg_find(int sioaddr, unsigned short *address,
 		(int)superio_inb(sioaddr, SIO_REG_DEVREV));
 exit:
 	superio_exit(sioaddr);
-	release_region(sioaddr, 2);
 	return err;
 }
 
diff --git a/drivers/hwmon/lis3lv02d.c b/drivers/hwmon/lis3lv02d.c
index 6138f036b159..fc591ae53107 100644
--- a/drivers/hwmon/lis3lv02d.c
+++ b/drivers/hwmon/lis3lv02d.c
@@ -277,7 +277,7 @@ static irqreturn_t lis302dl_interrupt(int irq, void *dummy)
 	wake_up_interruptible(&lis3_dev.misc_wait);
 	kill_fasync(&lis3_dev.async_queue, SIGIO, POLL_IN);
 out:
-	if (lis3_dev.whoami == WAI_8B && lis3_dev.idev &&
+	if (lis3_dev.pdata && lis3_dev.whoami == WAI_8B && lis3_dev.idev &&
 	    lis3_dev.idev->input->users)
 		return IRQ_WAKE_THREAD;
 	return IRQ_HANDLED;
@@ -718,7 +718,7 @@ int lis3lv02d_init_device(struct lis3lv02d *dev)
 	 * io-apic is not configurable (and generates a warning) but I keep it
 	 * in case of support for other hardware.
 	 */
-	if (dev->whoami == WAI_8B)
+	if (dev->pdata && dev->whoami == WAI_8B)
 		thread_fn = lis302dl_interrupt_thread1_8b;
 	else
 		thread_fn = NULL;
diff --git a/drivers/hwmon/pkgtemp.c b/drivers/hwmon/pkgtemp.c
index 74157fcda6ed..f11903936c8b 100644
--- a/drivers/hwmon/pkgtemp.c
+++ b/drivers/hwmon/pkgtemp.c
@@ -33,7 +33,6 @@
 #include <linux/list.h>
 #include <linux/platform_device.h>
 #include <linux/cpu.h>
-#include <linux/pci.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
 
@@ -224,7 +223,7 @@ static int __devinit pkgtemp_probe(struct platform_device *pdev)
 
 	err = sysfs_create_group(&pdev->dev.kobj, &pkgtemp_group);
 	if (err)
-		goto exit_free;
+		goto exit_dev;
 
 	data->hwmon_dev = hwmon_device_register(&pdev->dev);
 	if (IS_ERR(data->hwmon_dev)) {
@@ -238,6 +237,8 @@ static int __devinit pkgtemp_probe(struct platform_device *pdev)
 
 exit_class:
 	sysfs_remove_group(&pdev->dev.kobj, &pkgtemp_group);
+exit_dev:
+	device_remove_file(&pdev->dev, &sensor_dev_attr_temp1_max.dev_attr);
 exit_free:
 	kfree(data);
 exit:
@@ -250,6 +251,7 @@ static int __devexit pkgtemp_remove(struct platform_device *pdev)
 
 	hwmon_device_unregister(data->hwmon_dev);
 	sysfs_remove_group(&pdev->dev.kobj, &pkgtemp_group);
+	device_remove_file(&pdev->dev, &sensor_dev_attr_temp1_max.dev_attr);
 	platform_set_drvdata(pdev, NULL);
 	kfree(data);
 	return 0;
@@ -281,9 +283,10 @@ static int __cpuinit pkgtemp_device_add(unsigned int cpu)
 	int err;
 	struct platform_device *pdev;
 	struct pdev_entry *pdev_entry;
-#ifdef CONFIG_SMP
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
-#endif
+
+	if (!cpu_has(c, X86_FEATURE_PTS))
+		return 0;
 
 	mutex_lock(&pdev_list_mutex);
 
@@ -339,17 +342,18 @@ exit:
 #ifdef CONFIG_HOTPLUG_CPU
 static void pkgtemp_device_remove(unsigned int cpu)
 {
-	struct pdev_entry *p, *n;
+	struct pdev_entry *p;
 	unsigned int i;
 	int err;
 
 	mutex_lock(&pdev_list_mutex);
-	list_for_each_entry_safe(p, n, &pdev_list, list) {
+	list_for_each_entry(p, &pdev_list, list) {
 		if (p->cpu != cpu)
 			continue;
 
 		platform_device_unregister(p->pdev);
 		list_del(&p->list);
+		mutex_unlock(&pdev_list_mutex);
 		kfree(p);
 		for_each_cpu(i, cpu_core_mask(cpu)) {
 			if (i != cpu) {
@@ -358,7 +362,7 @@ static void pkgtemp_device_remove(unsigned int cpu)
 					break;
 			}
 		}
-		break;
+		return;
 	}
 	mutex_unlock(&pdev_list_mutex);
 }
@@ -399,11 +403,6 @@ static int __init pkgtemp_init(void)
 		goto exit;
 
 	for_each_online_cpu(i) {
-		struct cpuinfo_x86 *c = &cpu_data(i);
-
-		if (!cpu_has(c, X86_FEATURE_PTS))
-			continue;
-
 		err = pkgtemp_device_add(i);
 		if (err)
 			goto exit_devices_unreg;
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index f7bd2613cecc..f2de3be35df3 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -677,6 +677,11 @@ static int __devinit cpm_i2c_probe(struct platform_device *ofdev,
 	dev_dbg(&ofdev->dev, "hw routines for %s registered.\n",
 		cpm->adap.name);
 
+	/*
+	 * register OF I2C devices
+	 */
+	of_i2c_register_devices(&cpm->adap);
+
 	return 0;
 out_shut:
 	cpm_i2c_shutdown(cpm);
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index 2222c87876b9..5795c8398c7c 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -331,21 +331,16 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop)
 	INIT_COMPLETION(dev->cmd_complete);
 	dev->cmd_err = 0;
 
-	/* Take I2C out of reset, configure it as master and set the
-	 * start bit */
-	flag = DAVINCI_I2C_MDR_IRS | DAVINCI_I2C_MDR_MST | DAVINCI_I2C_MDR_STT;
+	/* Take I2C out of reset and configure it as master */
+	flag = DAVINCI_I2C_MDR_IRS | DAVINCI_I2C_MDR_MST;
 
 	/* if the slave address is ten bit address, enable XA bit */
 	if (msg->flags & I2C_M_TEN)
 		flag |= DAVINCI_I2C_MDR_XA;
 	if (!(msg->flags & I2C_M_RD))
 		flag |= DAVINCI_I2C_MDR_TRX;
-	if (stop)
-		flag |= DAVINCI_I2C_MDR_STP;
-	if (msg->len == 0) {
+	if (msg->len == 0)
 		flag |= DAVINCI_I2C_MDR_RM;
-		flag &= ~DAVINCI_I2C_MDR_STP;
-	}
 
 	/* Enable receive or transmit interrupts */
 	w = davinci_i2c_read_reg(dev, DAVINCI_I2C_IMR_REG);
@@ -357,7 +352,11 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop)
 
 	dev->terminate = 0;
 
-	/* write the data into mode register */
+	/*
+	 * Write mode register first as needed for correct behaviour
+	 * on OMAP-L138, but don't set STT yet to avoid a race with XRDY
+	 * occuring before we have loaded DXR
+	 */
 	davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, flag);
 
 	/*
@@ -365,12 +364,19 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop)
 	 * because transmit-data-ready interrupt can come before
 	 * NACK-interrupt during sending of previous message and
 	 * ICDXR may have wrong data
+	 * It also saves us one interrupt, slightly faster
 	 */
 	if ((!(msg->flags & I2C_M_RD)) && dev->buf_len) {
 		davinci_i2c_write_reg(dev, DAVINCI_I2C_DXR_REG, *dev->buf++);
 		dev->buf_len--;
 	}
 
+	/* Set STT to begin transmit now DXR is loaded */
+	flag |= DAVINCI_I2C_MDR_STT;
+	if (stop && msg->len != 0)
+		flag |= DAVINCI_I2C_MDR_STP;
+	davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, flag);
+
 	r = wait_for_completion_interruptible_timeout(&dev->cmd_complete,
 						      dev->adapter.timeout);
 	if (r == 0) {
diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c
index 43ca32fddde2..89eedf45d30e 100644
--- a/drivers/i2c/busses/i2c-ibm_iic.c
+++ b/drivers/i2c/busses/i2c-ibm_iic.c
@@ -761,6 +761,9 @@ static int __devinit iic_probe(struct platform_device *ofdev,
 	dev_info(&ofdev->dev, "using %s mode\n",
 		 dev->fast_mode ? "fast (400 kHz)" : "standard (100 kHz)");
 
+	/* Now register all the child nodes */
+	of_i2c_register_devices(adap);
+
 	return 0;
 
 error_cleanup:
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index d1ff9408dc1f..4c2a62b75b5c 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -159,15 +159,9 @@ static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy)
 
 static int i2c_imx_trx_complete(struct imx_i2c_struct *i2c_imx)
 {
-	int result;
-
-	result = wait_event_interruptible_timeout(i2c_imx->queue,
-		i2c_imx->i2csr & I2SR_IIF, HZ / 10);
+	wait_event_timeout(i2c_imx->queue, i2c_imx->i2csr & I2SR_IIF, HZ / 10);
 
-	if (unlikely(result < 0)) {
-		dev_dbg(&i2c_imx->adapter.dev, "<%s> result < 0\n", __func__);
-		return result;
-	} else if (unlikely(!(i2c_imx->i2csr & I2SR_IIF))) {
+	if (unlikely(!(i2c_imx->i2csr & I2SR_IIF))) {
 		dev_dbg(&i2c_imx->adapter.dev, "<%s> Timeout\n", __func__);
 		return -ETIMEDOUT;
 	}
@@ -295,7 +289,7 @@ static irqreturn_t i2c_imx_isr(int irq, void *dev_id)
 		i2c_imx->i2csr = temp;
 		temp &= ~I2SR_IIF;
 		writeb(temp, i2c_imx->base + IMX_I2C_I2SR);
-		wake_up_interruptible(&i2c_imx->queue);
+		wake_up(&i2c_imx->queue);
 		return IRQ_HANDLED;
 	}
 
diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c
index a1c419a716af..b74e6dc6886c 100644
--- a/drivers/i2c/busses/i2c-mpc.c
+++ b/drivers/i2c/busses/i2c-mpc.c
@@ -632,6 +632,7 @@ static int __devinit fsl_i2c_probe(struct platform_device *op,
 		dev_err(i2c->dev, "failed to add adapter\n");
 		goto fail_add;
 	}
+	of_i2c_register_devices(&i2c->adap);
 
 	return result;
 
diff --git a/drivers/i2c/busses/i2c-octeon.c b/drivers/i2c/busses/i2c-octeon.c
index 0e9f85d0a835..56dbe54e8811 100644
--- a/drivers/i2c/busses/i2c-octeon.c
+++ b/drivers/i2c/busses/i2c-octeon.c
@@ -218,7 +218,7 @@ static int octeon_i2c_wait(struct octeon_i2c *i2c)
 		return result;
 	} else if (result == 0) {
 		dev_dbg(i2c->dev, "%s: timeout\n", __func__);
-		result = -ETIMEDOUT;
+		return -ETIMEDOUT;
 	}
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 7674efb55378..b33c78586bfc 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -680,6 +680,8 @@ omap_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 
 	if (r == 0)
 		r = num;
+
+	omap_i2c_wait_for_bb(dev);
 out:
 	omap_i2c_idle(dev);
 	return r;
diff --git a/drivers/i2c/busses/i2c-pca-isa.c b/drivers/i2c/busses/i2c-pca-isa.c
index bbd77603a417..29933f87d8fa 100644
--- a/drivers/i2c/busses/i2c-pca-isa.c
+++ b/drivers/i2c/busses/i2c-pca-isa.c
@@ -71,8 +71,8 @@ static int pca_isa_readbyte(void *pd, int reg)
 
 static int pca_isa_waitforcompletion(void *pd)
 {
-	long ret = ~0;
 	unsigned long timeout;
+	long ret;
 
 	if (irq > -1) {
 		ret = wait_event_timeout(pca_wait,
@@ -81,11 +81,15 @@ static int pca_isa_waitforcompletion(void *pd)
 	} else {
 		/* Do polling */
 		timeout = jiffies + pca_isa_ops.timeout;
-		while (((pca_isa_readbyte(pd, I2C_PCA_CON)
-				& I2C_PCA_CON_SI) == 0)
-				&& (ret = time_before(jiffies, timeout)))
+		do {
+			ret = time_before(jiffies, timeout);
+			if (pca_isa_readbyte(pd, I2C_PCA_CON)
+					& I2C_PCA_CON_SI)
+				break;
 			udelay(100);
+		} while (ret);
 	}
+
 	return ret > 0;
 }
 
diff --git a/drivers/i2c/busses/i2c-pca-platform.c b/drivers/i2c/busses/i2c-pca-platform.c
index ef5c78487eb7..5f6d7f89e225 100644
--- a/drivers/i2c/busses/i2c-pca-platform.c
+++ b/drivers/i2c/busses/i2c-pca-platform.c
@@ -80,8 +80,8 @@ static void i2c_pca_pf_writebyte32(void *pd, int reg, int val)
 static int i2c_pca_pf_waitforcompletion(void *pd)
 {
 	struct i2c_pca_pf_data *i2c = pd;
-	long ret = ~0;
 	unsigned long timeout;
+	long ret;
 
 	if (i2c->irq) {
 		ret = wait_event_timeout(i2c->wait,
@@ -90,10 +90,13 @@ static int i2c_pca_pf_waitforcompletion(void *pd)
 	} else {
 		/* Do polling */
 		timeout = jiffies + i2c->adap.timeout;
-		while (((i2c->algo_data.read_byte(i2c, I2C_PCA_CON)
-				& I2C_PCA_CON_SI) == 0)
-				&& (ret = time_before(jiffies, timeout)))
+		do {
+			ret = time_before(jiffies, timeout);
+			if (i2c->algo_data.read_byte(i2c, I2C_PCA_CON)
+					& I2C_PCA_CON_SI)
+				break;
 			udelay(100);
+		} while (ret);
 	}
 
 	return ret > 0;
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 72902e0bbfa7..bf831bf81587 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -662,8 +662,8 @@ static int s3c24xx_i2c_clockrate(struct s3c24xx_i2c *i2c, unsigned int *got)
 		unsigned long sda_delay;
 
 		if (pdata->sda_delay) {
-			sda_delay = (freq / 1000) * pdata->sda_delay;
-			sda_delay /= 1000000;
+			sda_delay = clkin * pdata->sda_delay;
+			sda_delay = DIV_ROUND_UP(sda_delay, 1000000);
 			sda_delay = DIV_ROUND_UP(sda_delay, 5);
 			if (sda_delay > 3)
 				sda_delay = 3;
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 6649176de940..bea4c5021d26 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -32,7 +32,6 @@
 #include <linux/init.h>
 #include <linux/idr.h>
 #include <linux/mutex.h>
-#include <linux/of_i2c.h>
 #include <linux/of_device.h>
 #include <linux/completion.h>
 #include <linux/hardirq.h>
@@ -197,11 +196,12 @@ static int i2c_device_pm_suspend(struct device *dev)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	if (pm)
-		return pm->suspend ? pm->suspend(dev) : 0;
+	if (pm) {
+		if (pm_runtime_suspended(dev))
+			return 0;
+		else
+			return pm->suspend ? pm->suspend(dev) : 0;
+	}
 
 	return i2c_legacy_suspend(dev, PMSG_SUSPEND);
 }
@@ -216,12 +216,6 @@ static int i2c_device_pm_resume(struct device *dev)
 	else
 		ret = i2c_legacy_resume(dev);
 
-	if (!ret) {
-		pm_runtime_disable(dev);
-		pm_runtime_set_active(dev);
-		pm_runtime_enable(dev);
-	}
-
 	return ret;
 }
 
@@ -229,11 +223,12 @@ static int i2c_device_pm_freeze(struct device *dev)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	if (pm)
-		return pm->freeze ? pm->freeze(dev) : 0;
+	if (pm) {
+		if (pm_runtime_suspended(dev))
+			return 0;
+		else
+			return pm->freeze ? pm->freeze(dev) : 0;
+	}
 
 	return i2c_legacy_suspend(dev, PMSG_FREEZE);
 }
@@ -242,11 +237,12 @@ static int i2c_device_pm_thaw(struct device *dev)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	if (pm)
-		return pm->thaw ? pm->thaw(dev) : 0;
+	if (pm) {
+		if (pm_runtime_suspended(dev))
+			return 0;
+		else
+			return pm->thaw ? pm->thaw(dev) : 0;
+	}
 
 	return i2c_legacy_resume(dev);
 }
@@ -255,11 +251,12 @@ static int i2c_device_pm_poweroff(struct device *dev)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	if (pm)
-		return pm->poweroff ? pm->poweroff(dev) : 0;
+	if (pm) {
+		if (pm_runtime_suspended(dev))
+			return 0;
+		else
+			return pm->poweroff ? pm->poweroff(dev) : 0;
+	}
 
 	return i2c_legacy_suspend(dev, PMSG_HIBERNATE);
 }
@@ -876,9 +873,6 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 	if (adap->nr < __i2c_first_dynamic_bus_num)
 		i2c_scan_static_board_info(adap);
 
-	/* Register devices from the device tree */
-	of_i2c_register_devices(adap);
-
 	/* Notify drivers */
 	mutex_lock(&core_lock);
 	bus_for_each_drv(&i2c_bus_type, NULL, adap, __process_new_adapter);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
old mode 100755
new mode 100644
index a10152bb1427..c37ef64d1465
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -83,7 +83,7 @@ static unsigned int mwait_substates;
 /* Reliable LAPIC Timer States, bit 1 for C1 etc.  */
 static unsigned int lapic_timer_reliable_states;
 
-static struct cpuidle_device *intel_idle_cpuidle_devices;
+static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state);
 
 static struct cpuidle_state *cpuidle_state_table;
@@ -108,7 +108,7 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.name = "NHM-C3",
 		.desc = "MWAIT 0x10",
 		.driver_data = (void *) 0x10,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 20,
 		.power_usage = 500,
 		.target_residency = 80,
@@ -117,7 +117,7 @@ static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.name = "NHM-C6",
 		.desc = "MWAIT 0x20",
 		.driver_data = (void *) 0x20,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 200,
 		.power_usage = 350,
 		.target_residency = 800,
@@ -149,7 +149,7 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
 		.name = "ATM-C4",
 		.desc = "MWAIT 0x30",
 		.driver_data = (void *) 0x30,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
+		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 100,
 		.power_usage = 250,
 		.target_residency = 400,
@@ -157,13 +157,13 @@ static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
 	{ /* MWAIT C5 */ },
 	{ /* MWAIT C6 */
 		.name = "ATM-C6",
-		.desc = "MWAIT 0x40",
-		.driver_data = (void *) 0x40,
-		.flags = CPUIDLE_FLAG_TIME_VALID,
-		.exit_latency = 200,
+		.desc = "MWAIT 0x52",
+		.driver_data = (void *) 0x52,
+		.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
 		.power_usage = 150,
-		.target_residency = 800,
-		.enter = NULL },	/* disabled */
+		.target_residency = 560,
+		.enter = &intel_idle },
 };
 
 /**
@@ -185,6 +185,16 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state)
 
 	local_irq_disable();
 
+	/*
+	 * If the state flag indicates that the TLB will be flushed or if this
+	 * is the deepest c-state supported, do a voluntary leave mm to avoid
+	 * costly and mostly unnecessary wakeups for flushing the user TLB's
+	 * associated with the active mm.
+	 */
+	if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED ||
+	    (&dev->states[dev->state_count - 1] == state))
+		leave_mm(cpu);
+
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index d88077a21994..13c88871dc3b 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -463,7 +463,8 @@ static int send_connect(struct iwch_ep *ep)
 	    V_MSS_IDX(mtu_idx) |
 	    V_L2T_IDX(ep->l2t->idx) | V_TX_CHANNEL(ep->l2t->smt_idx);
 	opt0l = V_TOS((ep->tos >> 2) & M_TOS) | V_RCV_BUFSIZ(rcv_win>>10);
-	opt2 = V_FLAVORS_VALID(1) | V_CONG_CONTROL_FLAVOR(cong_flavor);
+	opt2 = F_RX_COALESCE_VALID | V_RX_COALESCE(0) | V_FLAVORS_VALID(1) |
+	       V_CONG_CONTROL_FLAVOR(cong_flavor);
 	skb->priority = CPL_PRIORITY_SETUP;
 	set_arp_failure_handler(skb, act_open_req_arp_failure);
 
@@ -1280,7 +1281,8 @@ static void accept_cr(struct iwch_ep *ep, __be32 peer_ip, struct sk_buff *skb)
 	    V_MSS_IDX(mtu_idx) |
 	    V_L2T_IDX(ep->l2t->idx) | V_TX_CHANNEL(ep->l2t->smt_idx);
 	opt0l = V_TOS((ep->tos >> 2) & M_TOS) | V_RCV_BUFSIZ(rcv_win>>10);
-	opt2 = V_FLAVORS_VALID(1) | V_CONG_CONTROL_FLAVOR(cong_flavor);
+	opt2 = F_RX_COALESCE_VALID | V_RX_COALESCE(0) | V_FLAVORS_VALID(1) |
+	       V_CONG_CONTROL_FLAVOR(cong_flavor);
 
 	rpl = cplhdr(skb);
 	rpl->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index c908c5f83645..9ddafc30f432 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -669,6 +669,9 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 
 		if ((_IOC_NR(cmd) & ~ABS_MAX) == _IOC_NR(EVIOCGABS(0))) {
 
+			if (!dev->absinfo)
+				return -EINVAL;
+
 			t = _IOC_NR(cmd) & ABS_MAX;
 			abs = dev->absinfo[t];
 
@@ -680,10 +683,13 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 		}
 	}
 
-	if (_IOC_DIR(cmd) == _IOC_READ) {
+	if (_IOC_DIR(cmd) == _IOC_WRITE) {
 
 		if ((_IOC_NR(cmd) & ~ABS_MAX) == _IOC_NR(EVIOCSABS(0))) {
 
+			if (!dev->absinfo)
+				return -EINVAL;
+
 			t = _IOC_NR(cmd) & ABS_MAX;
 
 			if (copy_from_user(&abs, p, min_t(size_t,
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index d85bd8a7967d..22239e988498 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -483,6 +483,9 @@ static int joydev_handle_JSIOCSAXMAP(struct joydev *joydev,
 
 	memcpy(joydev->abspam, abspam, len);
 
+	for (i = 0; i < joydev->nabs; i++)
+		joydev->absmap[joydev->abspam[i]] = i;
+
  out:
 	kfree(abspam);
 	return retval;
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 0d4266a533a5..360698553eb5 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -404,6 +404,13 @@ static int uinput_setup_device(struct uinput_device *udev, const char __user *bu
 		retval = uinput_validate_absbits(dev);
 		if (retval < 0)
 			goto exit;
+		if (test_bit(ABS_MT_SLOT, dev->absbit)) {
+			int nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
+			input_mt_create_slots(dev, nslot);
+			input_set_events_per_packet(dev, 6 * nslot);
+		} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
+			input_set_events_per_packet(dev, 60);
+		}
 	}
 
 	udev->state = UIST_SETUP_COMPLETE;
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index 42ba3691d908..b35876ee6908 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -103,27 +103,26 @@ static void wacom_sys_irq(struct urb *urb)
 static int wacom_open(struct input_dev *dev)
 {
 	struct wacom *wacom = input_get_drvdata(dev);
+	int retval = 0;
 
-	mutex_lock(&wacom->lock);
-
-	wacom->irq->dev = wacom->usbdev;
-
-	if (usb_autopm_get_interface(wacom->intf) < 0) {
-		mutex_unlock(&wacom->lock);
+	if (usb_autopm_get_interface(wacom->intf) < 0)
 		return -EIO;
-	}
+
+	mutex_lock(&wacom->lock);
 
 	if (usb_submit_urb(wacom->irq, GFP_KERNEL)) {
-		usb_autopm_put_interface(wacom->intf);
-		mutex_unlock(&wacom->lock);
-		return -EIO;
+		retval = -EIO;
+		goto out;
 	}
 
 	wacom->open = true;
 	wacom->intf->needs_remote_wakeup = 1;
 
+out:
 	mutex_unlock(&wacom->lock);
-	return 0;
+	if (retval)
+		usb_autopm_put_interface(wacom->intf);
+	return retval;
 }
 
 static void wacom_close(struct input_dev *dev)
@@ -135,6 +134,8 @@ static void wacom_close(struct input_dev *dev)
 	wacom->open = false;
 	wacom->intf->needs_remote_wakeup = 0;
 	mutex_unlock(&wacom->lock);
+
+	usb_autopm_put_interface(wacom->intf);
 }
 
 static int wacom_parse_hid(struct usb_interface *intf, struct hid_descriptor *hid_desc,
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index 6e29badb969e..47fd7a041c52 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -442,8 +442,10 @@ static void wacom_intuos_general(struct wacom_wac *wacom)
 	/* general pen packet */
 	if ((data[1] & 0xb8) == 0xa0) {
 		t = (data[6] << 2) | ((data[7] >> 6) & 3);
-		if (features->type >= INTUOS4S && features->type <= INTUOS4L)
+		if ((features->type >= INTUOS4S && features->type <= INTUOS4L) ||
+		    features->type == WACOM_21UX2) {
 			t = (t << 1) | (data[1] & 1);
+		}
 		input_report_abs(input, ABS_PRESSURE, t);
 		input_report_abs(input, ABS_TILT_X,
 				((data[7] << 1) & 0x7e) | (data[8] >> 7));
diff --git a/drivers/isdn/sc/interrupt.c b/drivers/isdn/sc/interrupt.c
index 485be8b1e1b3..f0225bc0f267 100644
--- a/drivers/isdn/sc/interrupt.c
+++ b/drivers/isdn/sc/interrupt.c
@@ -112,11 +112,19 @@ irqreturn_t interrupt_handler(int dummy, void *card_inst)
 			}
 			else if(callid>=0x0000 && callid<=0x7FFF)
 			{
+				int len;
+
 				pr_debug("%s: Got Incoming Call\n",
 						sc_adapter[card]->devicename);
-				strcpy(setup.phone,&(rcvmsg.msg_data.byte_array[4]));
-				strcpy(setup.eazmsn,
-					sc_adapter[card]->channel[rcvmsg.phy_link_no-1].dn);
+				len = strlcpy(setup.phone, &(rcvmsg.msg_data.byte_array[4]),
+						sizeof(setup.phone));
+				if (len >= sizeof(setup.phone))
+					continue;
+				len = strlcpy(setup.eazmsn,
+						sc_adapter[card]->channel[rcvmsg.phy_link_no - 1].dn,
+						sizeof(setup.eazmsn));
+				if (len >= sizeof(setup.eazmsn))
+					continue;
 				setup.si1 = 7;
 				setup.si2 = 0;
 				setup.plan = 0;
@@ -176,7 +184,9 @@ irqreturn_t interrupt_handler(int dummy, void *card_inst)
 		 * Handle a GetMyNumber Rsp
 		 */
 		if (IS_CE_MESSAGE(rcvmsg,Call,0,GetMyNumber)){
-			strcpy(sc_adapter[card]->channel[rcvmsg.phy_link_no-1].dn,rcvmsg.msg_data.byte_array);
+			strlcpy(sc_adapter[card]->channel[rcvmsg.phy_link_no - 1].dn,
+				rcvmsg.msg_data.byte_array,
+				sizeof(rcvmsg.msg_data.byte_array));
 			continue;
 		}
 			
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index 74dce4ba0262..350eb34f049c 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -81,7 +81,7 @@ static int ns2_led_get_mode(struct ns2_led_data *led_dat,
 	int cmd_level;
 	int slow_level;
 
-	read_lock(&led_dat->rw_lock);
+	read_lock_irq(&led_dat->rw_lock);
 
 	cmd_level = gpio_get_value(led_dat->cmd);
 	slow_level = gpio_get_value(led_dat->slow);
@@ -95,7 +95,7 @@ static int ns2_led_get_mode(struct ns2_led_data *led_dat,
 		}
 	}
 
-	read_unlock(&led_dat->rw_lock);
+	read_unlock_irq(&led_dat->rw_lock);
 
 	return ret;
 }
@@ -104,8 +104,9 @@ static void ns2_led_set_mode(struct ns2_led_data *led_dat,
 			     enum ns2_led_modes mode)
 {
 	int i;
+	unsigned long flags;
 
-	write_lock(&led_dat->rw_lock);
+	write_lock_irqsave(&led_dat->rw_lock, flags);
 
 	for (i = 0; i < ARRAY_SIZE(ns2_led_modval); i++) {
 		if (mode == ns2_led_modval[i].mode) {
@@ -116,7 +117,7 @@ static void ns2_led_set_mode(struct ns2_led_data *led_dat,
 		}
 	}
 
-	write_unlock(&led_dat->rw_lock);
+	write_unlock_irqrestore(&led_dat->rw_lock, flags);
 }
 
 static void ns2_led_set(struct led_classdev *led_cdev,
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index ed4900ade93a..e4fb58db5454 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1000,10 +1000,11 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 				page = bitmap->sb_page;
 				offset = sizeof(bitmap_super_t);
 				if (!file)
-					read_sb_page(bitmap->mddev,
-						     bitmap->mddev->bitmap_info.offset,
-						     page,
-						     index, count);
+					page = read_sb_page(
+						bitmap->mddev,
+						bitmap->mddev->bitmap_info.offset,
+						page,
+						index, count);
 			} else if (file) {
 				page = read_page(file, index, bitmap, count);
 				offset = 0;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index ad83a4dcadc3..0b830bbe1d8b 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1839,7 +1839,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 
 		/* take from bio_init */
 		bio->bi_next = NULL;
+		bio->bi_flags &= ~(BIO_POOL_MASK-1);
 		bio->bi_flags |= 1 << BIO_UPTODATE;
+		bio->bi_comp_cpu = -1;
 		bio->bi_rw = READ;
 		bio->bi_vcnt = 0;
 		bio->bi_idx = 0;
@@ -1912,7 +1914,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
 			BUG_ON(sync_blocks < (PAGE_SIZE>>9));
-			if (len > (sync_blocks<<9))
+			if ((len >> 9) > sync_blocks)
 				len = sync_blocks<<9;
 		}
 
diff --git a/drivers/media/IR/ir-keytable.c b/drivers/media/IR/ir-keytable.c
index 7e82a9df726b..7961d59f5cac 100644
--- a/drivers/media/IR/ir-keytable.c
+++ b/drivers/media/IR/ir-keytable.c
@@ -319,7 +319,7 @@ static void ir_timer_keyup(unsigned long cookie)
 	 * a keyup event might follow immediately after the keydown.
 	 */
 	spin_lock_irqsave(&ir->keylock, flags);
-	if (time_is_after_eq_jiffies(ir->keyup_jiffies))
+	if (time_is_before_eq_jiffies(ir->keyup_jiffies))
 		ir_keyup(ir);
 	spin_unlock_irqrestore(&ir->keylock, flags);
 }
@@ -510,6 +510,13 @@ int __ir_input_register(struct input_dev *input_dev,
 		   (ir_dev->props && ir_dev->props->driver_type == RC_DRIVER_IR_RAW) ?
 			" in raw mode" : "");
 
+	/*
+	 * Default delay of 250ms is too short for some protocols, expecially
+	 * since the timeout is currently set to 250ms. Increase it to 500ms,
+	 * to avoid wrong repetition of the keycodes.
+	 */
+	input_dev->rep[REP_DELAY] = 500;
+
 	return 0;
 
 out_event:
diff --git a/drivers/media/IR/ir-lirc-codec.c b/drivers/media/IR/ir-lirc-codec.c
index 77b5946413c0..e63f757d5d72 100644
--- a/drivers/media/IR/ir-lirc-codec.c
+++ b/drivers/media/IR/ir-lirc-codec.c
@@ -267,7 +267,7 @@ static int ir_lirc_register(struct input_dev *input_dev)
 			features |= LIRC_CAN_SET_SEND_CARRIER;
 
 		if (ir_dev->props->s_tx_duty_cycle)
-			features |= LIRC_CAN_SET_REC_DUTY_CYCLE;
+			features |= LIRC_CAN_SET_SEND_DUTY_CYCLE;
 	}
 
 	if (ir_dev->props->s_rx_carrier_range)
diff --git a/drivers/media/IR/ir-raw-event.c b/drivers/media/IR/ir-raw-event.c
index 43094e7eccfa..8e0e1b1f8c87 100644
--- a/drivers/media/IR/ir-raw-event.c
+++ b/drivers/media/IR/ir-raw-event.c
@@ -279,9 +279,11 @@ int ir_raw_event_register(struct input_dev *input_dev)
 			"rc%u",  (unsigned int)ir->devno);
 
 	if (IS_ERR(ir->raw->thread)) {
+		int ret = PTR_ERR(ir->raw->thread);
+
 		kfree(ir->raw);
 		ir->raw = NULL;
-		return PTR_ERR(ir->raw->thread);
+		return ret;
 	}
 
 	mutex_lock(&ir_raw_handler_lock);
diff --git a/drivers/media/IR/ir-sysfs.c b/drivers/media/IR/ir-sysfs.c
index 96dafc425c8e..46d42467f9b4 100644
--- a/drivers/media/IR/ir-sysfs.c
+++ b/drivers/media/IR/ir-sysfs.c
@@ -67,13 +67,14 @@ static ssize_t show_protocols(struct device *d,
 	char *tmp = buf;
 	int i;
 
-	if (ir_dev->props->driver_type == RC_DRIVER_SCANCODE) {
+	if (ir_dev->props && ir_dev->props->driver_type == RC_DRIVER_SCANCODE) {
 		enabled = ir_dev->rc_tab.ir_type;
 		allowed = ir_dev->props->allowed_protos;
-	} else {
+	} else if (ir_dev->raw) {
 		enabled = ir_dev->raw->enabled_protocols;
 		allowed = ir_raw_get_allowed_protocols();
-	}
+	} else
+		return sprintf(tmp, "[builtin]\n");
 
 	IR_dprintk(1, "allowed - 0x%llx, enabled - 0x%llx\n",
 		   (long long)allowed,
@@ -121,10 +122,14 @@ static ssize_t store_protocols(struct device *d,
 	int rc, i, count = 0;
 	unsigned long flags;
 
-	if (ir_dev->props->driver_type == RC_DRIVER_SCANCODE)
+	if (ir_dev->props && ir_dev->props->driver_type == RC_DRIVER_SCANCODE)
 		type = ir_dev->rc_tab.ir_type;
-	else
+	else if (ir_dev->raw)
 		type = ir_dev->raw->enabled_protocols;
+	else {
+		IR_dprintk(1, "Protocol switching not supported\n");
+		return -EINVAL;
+	}
 
 	while ((tmp = strsep((char **) &data, " \n")) != NULL) {
 		if (!*tmp)
@@ -185,7 +190,7 @@ static ssize_t store_protocols(struct device *d,
 		}
 	}
 
-	if (ir_dev->props->driver_type == RC_DRIVER_SCANCODE) {
+	if (ir_dev->props && ir_dev->props->driver_type == RC_DRIVER_SCANCODE) {
 		spin_lock_irqsave(&ir_dev->rc_tab.lock, flags);
 		ir_dev->rc_tab.ir_type = type;
 		spin_unlock_irqrestore(&ir_dev->rc_tab.lock, flags);
diff --git a/drivers/media/IR/keymaps/rc-rc6-mce.c b/drivers/media/IR/keymaps/rc-rc6-mce.c
index 64264f7f838f..39557ad401b6 100644
--- a/drivers/media/IR/keymaps/rc-rc6-mce.c
+++ b/drivers/media/IR/keymaps/rc-rc6-mce.c
@@ -19,6 +19,7 @@ static struct ir_scancode rc6_mce[] = {
 
 	{ 0x800f0416, KEY_PLAY },
 	{ 0x800f0418, KEY_PAUSE },
+	{ 0x800f046e, KEY_PLAYPAUSE },
 	{ 0x800f0419, KEY_STOP },
 	{ 0x800f0417, KEY_RECORD },
 
@@ -37,6 +38,8 @@ static struct ir_scancode rc6_mce[] = {
 	{ 0x800f0411, KEY_VOLUMEDOWN },
 	{ 0x800f0412, KEY_CHANNELUP },
 	{ 0x800f0413, KEY_CHANNELDOWN },
+	{ 0x800f043a, KEY_BRIGHTNESSUP },
+	{ 0x800f0480, KEY_BRIGHTNESSDOWN },
 
 	{ 0x800f0401, KEY_NUMERIC_1 },
 	{ 0x800f0402, KEY_NUMERIC_2 },
diff --git a/drivers/media/IR/mceusb.c b/drivers/media/IR/mceusb.c
index ac6bb2c01a48..bc620e10ef77 100644
--- a/drivers/media/IR/mceusb.c
+++ b/drivers/media/IR/mceusb.c
@@ -120,6 +120,10 @@ static struct usb_device_id mceusb_dev_table[] = {
 	{ USB_DEVICE(VENDOR_PHILIPS, 0x0613) },
 	/* Philips eHome Infrared Transceiver */
 	{ USB_DEVICE(VENDOR_PHILIPS, 0x0815) },
+	/* Philips/Spinel plus IR transceiver for ASUS */
+	{ USB_DEVICE(VENDOR_PHILIPS, 0x206c) },
+	/* Philips/Spinel plus IR transceiver for ASUS */
+	{ USB_DEVICE(VENDOR_PHILIPS, 0x2088) },
 	/* Realtek MCE IR Receiver */
 	{ USB_DEVICE(VENDOR_REALTEK, 0x0161) },
 	/* SMK/Toshiba G83C0004D410 */
diff --git a/drivers/media/dvb/dvb-usb/dib0700_core.c b/drivers/media/dvb/dvb-usb/dib0700_core.c
index fe818348b8a3..48397f103d32 100644
--- a/drivers/media/dvb/dvb-usb/dib0700_core.c
+++ b/drivers/media/dvb/dvb-usb/dib0700_core.c
@@ -673,9 +673,6 @@ static int dib0700_probe(struct usb_interface *intf,
 			else
 				dev->props.rc.core.bulk_mode = false;
 
-			/* Need a higher delay, to avoid wrong repeat */
-			dev->rc_input_dev->rep[REP_DELAY] = 500;
-
 			dib0700_rc_setup(dev);
 
 			return 0;
diff --git a/drivers/media/dvb/dvb-usb/dib0700_devices.c b/drivers/media/dvb/dvb-usb/dib0700_devices.c
index f634d2e784b2..e06acd1fecb6 100644
--- a/drivers/media/dvb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/dvb/dvb-usb/dib0700_devices.c
@@ -940,6 +940,58 @@ static int stk7070p_frontend_attach(struct dvb_usb_adapter *adap)
 	return adap->fe == NULL ? -ENODEV : 0;
 }
 
+/* STK7770P */
+static struct dib7000p_config dib7770p_dib7000p_config = {
+	.output_mpeg2_in_188_bytes = 1,
+
+	.agc_config_count = 1,
+	.agc = &dib7070_agc_config,
+	.bw  = &dib7070_bw_config_12_mhz,
+	.tuner_is_baseband = 1,
+	.spur_protect = 1,
+
+	.gpio_dir = DIB7000P_GPIO_DEFAULT_DIRECTIONS,
+	.gpio_val = DIB7000P_GPIO_DEFAULT_VALUES,
+	.gpio_pwm_pos = DIB7000P_GPIO_DEFAULT_PWM_POS,
+
+	.hostbus_diversity = 1,
+	.enable_current_mirror = 1,
+	.disable_sample_and_hold = 0,
+};
+
+static int stk7770p_frontend_attach(struct dvb_usb_adapter *adap)
+{
+	struct usb_device_descriptor *p = &adap->dev->udev->descriptor;
+	if (p->idVendor  == cpu_to_le16(USB_VID_PINNACLE) &&
+	    p->idProduct == cpu_to_le16(USB_PID_PINNACLE_PCTV72E))
+		dib0700_set_gpio(adap->dev, GPIO6, GPIO_OUT, 0);
+	else
+		dib0700_set_gpio(adap->dev, GPIO6, GPIO_OUT, 1);
+	msleep(10);
+	dib0700_set_gpio(adap->dev, GPIO9, GPIO_OUT, 1);
+	dib0700_set_gpio(adap->dev, GPIO4, GPIO_OUT, 1);
+	dib0700_set_gpio(adap->dev, GPIO7, GPIO_OUT, 1);
+	dib0700_set_gpio(adap->dev, GPIO10, GPIO_OUT, 0);
+
+	dib0700_ctrl_clock(adap->dev, 72, 1);
+
+	msleep(10);
+	dib0700_set_gpio(adap->dev, GPIO10, GPIO_OUT, 1);
+	msleep(10);
+	dib0700_set_gpio(adap->dev, GPIO0, GPIO_OUT, 1);
+
+	if (dib7000p_i2c_enumeration(&adap->dev->i2c_adap, 1, 18,
+				     &dib7770p_dib7000p_config) != 0) {
+		err("%s: dib7000p_i2c_enumeration failed.  Cannot continue\n",
+		    __func__);
+		return -ENODEV;
+	}
+
+	adap->fe = dvb_attach(dib7000p_attach, &adap->dev->i2c_adap, 0x80,
+		&dib7770p_dib7000p_config);
+	return adap->fe == NULL ? -ENODEV : 0;
+}
+
 /* DIB807x generic */
 static struct dibx000_agc_config dib807x_agc_config[2] = {
 	{
@@ -1781,7 +1833,7 @@ struct usb_device_id dib0700_usb_id_table[] = {
 /* 60 */{ USB_DEVICE(USB_VID_TERRATEC,	USB_PID_TERRATEC_CINERGY_T_XXS_2) },
 	{ USB_DEVICE(USB_VID_DIBCOM,    USB_PID_DIBCOM_STK807XPVR) },
 	{ USB_DEVICE(USB_VID_DIBCOM,    USB_PID_DIBCOM_STK807XP) },
-	{ USB_DEVICE(USB_VID_PIXELVIEW, USB_PID_PIXELVIEW_SBTVD) },
+	{ USB_DEVICE_VER(USB_VID_PIXELVIEW, USB_PID_PIXELVIEW_SBTVD, 0x000, 0x3f00) },
 	{ USB_DEVICE(USB_VID_EVOLUTEPC, USB_PID_TVWAY_PLUS) },
 /* 65 */{ USB_DEVICE(USB_VID_PINNACLE,	USB_PID_PINNACLE_PCTV73ESE) },
 	{ USB_DEVICE(USB_VID_PINNACLE,	USB_PID_PINNACLE_PCTV282E) },
@@ -2406,7 +2458,7 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 				.pid_filter_count = 32,
 				.pid_filter       = stk70x0p_pid_filter,
 				.pid_filter_ctrl  = stk70x0p_pid_filter_ctrl,
-				.frontend_attach  = stk7070p_frontend_attach,
+				.frontend_attach  = stk7770p_frontend_attach,
 				.tuner_attach     = dib7770p_tuner_attach,
 
 				DIB0700_DEFAULT_STREAMING_CONFIG(0x02),
diff --git a/drivers/media/dvb/dvb-usb/opera1.c b/drivers/media/dvb/dvb-usb/opera1.c
index 6b22ec64ab0c..f896337b4535 100644
--- a/drivers/media/dvb/dvb-usb/opera1.c
+++ b/drivers/media/dvb/dvb-usb/opera1.c
@@ -483,9 +483,7 @@ static int opera1_xilinx_load_firmware(struct usb_device *dev,
 		}
 	}
 	kfree(p);
-	if (fw) {
-		release_firmware(fw);
-	}
+	release_firmware(fw);
 	return ret;
 }
 
diff --git a/drivers/media/dvb/frontends/dib7000p.c b/drivers/media/dvb/frontends/dib7000p.c
index 2e28b973dfd3..3aed0d433921 100644
--- a/drivers/media/dvb/frontends/dib7000p.c
+++ b/drivers/media/dvb/frontends/dib7000p.c
@@ -260,6 +260,9 @@ static void dib7000p_set_adc_state(struct dib7000p_state *state, enum dibx000_ad
 
 //	dprintk( "908: %x, 909: %x\n", reg_908, reg_909);
 
+	reg_909 |= (state->cfg.disable_sample_and_hold & 1) << 4;
+	reg_908 |= (state->cfg.enable_current_mirror & 1) << 7;
+
 	dib7000p_write_word(state, 908, reg_908);
 	dib7000p_write_word(state, 909, reg_909);
 }
@@ -778,7 +781,10 @@ static void dib7000p_set_channel(struct dib7000p_state *state, struct dvb_fronte
 		default:
 		case GUARD_INTERVAL_1_32: value *= 1; break;
 	}
-	state->div_sync_wait = (value * 3) / 2 + 32; // add 50% SFN margin + compensate for one DVSY-fifo TODO
+	if (state->cfg.diversity_delay == 0)
+		state->div_sync_wait = (value * 3) / 2 + 48; // add 50% SFN margin + compensate for one DVSY-fifo
+	else
+		state->div_sync_wait = (value * 3) / 2 + state->cfg.diversity_delay; // add 50% SFN margin + compensate for one DVSY-fifo
 
 	/* deactive the possibility of diversity reception if extended interleaver */
 	state->div_force_off = !1 && ch->u.ofdm.transmission_mode != TRANSMISSION_MODE_8K;
diff --git a/drivers/media/dvb/frontends/dib7000p.h b/drivers/media/dvb/frontends/dib7000p.h
index 805dd13a97ee..da17345bf5bd 100644
--- a/drivers/media/dvb/frontends/dib7000p.h
+++ b/drivers/media/dvb/frontends/dib7000p.h
@@ -33,6 +33,11 @@ struct dib7000p_config {
 	int (*agc_control) (struct dvb_frontend *, u8 before);
 
 	u8 output_mode;
+	u8 disable_sample_and_hold : 1;
+
+	u8 enable_current_mirror : 1;
+	u8 diversity_delay;
+
 };
 
 #define DEFAULT_DIB7000P_I2C_ADDRESS 18
diff --git a/drivers/media/dvb/siano/smscoreapi.c b/drivers/media/dvb/siano/smscoreapi.c
index d93468cd3a85..ff3b0fa901b3 100644
--- a/drivers/media/dvb/siano/smscoreapi.c
+++ b/drivers/media/dvb/siano/smscoreapi.c
@@ -1098,33 +1098,26 @@ EXPORT_SYMBOL_GPL(smscore_onresponse);
  *
  * @return pointer to descriptor on success, NULL on error.
  */
-struct smscore_buffer_t *smscore_getbuffer(struct smscore_device_t *coredev)
+
+struct smscore_buffer_t *get_entry(struct smscore_device_t *coredev)
 {
 	struct smscore_buffer_t *cb = NULL;
 	unsigned long flags;
 
-	DEFINE_WAIT(wait);
-
 	spin_lock_irqsave(&coredev->bufferslock, flags);
-
-	/* This function must return a valid buffer, since the buffer list is
-	 * finite, we check that there is an available buffer, if not, we wait
-	 * until such buffer become available.
-	 */
-
-	prepare_to_wait(&coredev->buffer_mng_waitq, &wait, TASK_INTERRUPTIBLE);
-	if (list_empty(&coredev->buffers)) {
-		spin_unlock_irqrestore(&coredev->bufferslock, flags);
-		schedule();
-		spin_lock_irqsave(&coredev->bufferslock, flags);
+	if (!list_empty(&coredev->buffers)) {
+		cb = (struct smscore_buffer_t *) coredev->buffers.next;
+		list_del(&cb->entry);
 	}
+	spin_unlock_irqrestore(&coredev->bufferslock, flags);
+	return cb;
+}
 
-	finish_wait(&coredev->buffer_mng_waitq, &wait);
-
-	cb = (struct smscore_buffer_t *) coredev->buffers.next;
-	list_del(&cb->entry);
+struct smscore_buffer_t *smscore_getbuffer(struct smscore_device_t *coredev)
+{
+	struct smscore_buffer_t *cb = NULL;
 
-	spin_unlock_irqrestore(&coredev->bufferslock, flags);
+	wait_event(coredev->buffer_mng_waitq, (cb = get_entry(coredev)));
 
 	return cb;
 }
diff --git a/drivers/media/radio/si470x/radio-si470x-i2c.c b/drivers/media/radio/si470x/radio-si470x-i2c.c
index 67a4ec8768a6..4ce541a5eb47 100644
--- a/drivers/media/radio/si470x/radio-si470x-i2c.c
+++ b/drivers/media/radio/si470x/radio-si470x-i2c.c
@@ -395,7 +395,7 @@ static int __devinit si470x_i2c_probe(struct i2c_client *client,
 	radio->registers[POWERCFG] = POWERCFG_ENABLE;
 	if (si470x_set_register(radio, POWERCFG) < 0) {
 		retval = -EIO;
-		goto err_all;
+		goto err_video;
 	}
 	msleep(110);
 
diff --git a/drivers/media/video/cx231xx/Makefile b/drivers/media/video/cx231xx/Makefile
index 755dd0ce65ff..6f2b57384488 100644
--- a/drivers/media/video/cx231xx/Makefile
+++ b/drivers/media/video/cx231xx/Makefile
@@ -11,4 +11,5 @@ EXTRA_CFLAGS += -Idrivers/media/video
 EXTRA_CFLAGS += -Idrivers/media/common/tuners
 EXTRA_CFLAGS += -Idrivers/media/dvb/dvb-core
 EXTRA_CFLAGS += -Idrivers/media/dvb/frontends
+EXTRA_CFLAGS += -Idrivers/media/dvb/dvb-usb
 
diff --git a/drivers/media/video/cx231xx/cx231xx-cards.c b/drivers/media/video/cx231xx/cx231xx-cards.c
index 6bdc0ef18119..f2a4900014bc 100644
--- a/drivers/media/video/cx231xx/cx231xx-cards.c
+++ b/drivers/media/video/cx231xx/cx231xx-cards.c
@@ -32,6 +32,7 @@
 #include <media/v4l2-chip-ident.h>
 
 #include <media/cx25840.h>
+#include "dvb-usb-ids.h"
 #include "xc5000.h"
 
 #include "cx231xx.h"
@@ -175,6 +176,8 @@ struct usb_device_id cx231xx_id_table[] = {
 	 .driver_info = CX231XX_BOARD_CNXT_RDE_250},
 	{USB_DEVICE(0x0572, 0x58A1),
 	 .driver_info = CX231XX_BOARD_CNXT_RDU_250},
+	{USB_DEVICE_VER(USB_VID_PIXELVIEW, USB_PID_PIXELVIEW_SBTVD, 0x4000,0x4fff),
+	 .driver_info = CX231XX_BOARD_UNKNOWN},
 	{},
 };
 
@@ -226,14 +229,16 @@ void cx231xx_pre_card_setup(struct cx231xx *dev)
 		     dev->board.name, dev->model);
 
 	/* set the direction for GPIO pins */
-	cx231xx_set_gpio_direction(dev, dev->board.tuner_gpio->bit, 1);
-	cx231xx_set_gpio_value(dev, dev->board.tuner_gpio->bit, 1);
-	cx231xx_set_gpio_direction(dev, dev->board.tuner_sif_gpio, 1);
+	if (dev->board.tuner_gpio) {
+		cx231xx_set_gpio_direction(dev, dev->board.tuner_gpio->bit, 1);
+		cx231xx_set_gpio_value(dev, dev->board.tuner_gpio->bit, 1);
+		cx231xx_set_gpio_direction(dev, dev->board.tuner_sif_gpio, 1);
 
-	/* request some modules if any required */
+		/* request some modules if any required */
 
-	/* reset the Tuner */
-	cx231xx_gpio_set(dev, dev->board.tuner_gpio);
+		/* reset the Tuner */
+		cx231xx_gpio_set(dev, dev->board.tuner_gpio);
+	}
 
 	/* set the mode to Analog mode initially */
 	cx231xx_set_mode(dev, CX231XX_ANALOG_MODE);
diff --git a/drivers/media/video/cx25840/cx25840-core.c b/drivers/media/video/cx25840/cx25840-core.c
index 86ca8c2359dd..f5a3e74c3c7c 100644
--- a/drivers/media/video/cx25840/cx25840-core.c
+++ b/drivers/media/video/cx25840/cx25840-core.c
@@ -1996,7 +1996,7 @@ static int cx25840_probe(struct i2c_client *client,
 
 		state->volume = v4l2_ctrl_new_std(&state->hdl,
 			&cx25840_audio_ctrl_ops, V4L2_CID_AUDIO_VOLUME,
-			0, 65335, 65535 / 100, default_volume);
+			0, 65535, 65535 / 100, default_volume);
 		state->mute = v4l2_ctrl_new_std(&state->hdl,
 			&cx25840_audio_ctrl_ops, V4L2_CID_AUDIO_MUTE,
 			0, 1, 1, 0);
diff --git a/drivers/media/video/cx88/Kconfig b/drivers/media/video/cx88/Kconfig
index 99dbae117591..0fa85cbefbb1 100644
--- a/drivers/media/video/cx88/Kconfig
+++ b/drivers/media/video/cx88/Kconfig
@@ -17,7 +17,7 @@ config VIDEO_CX88
 
 config VIDEO_CX88_ALSA
 	tristate "Conexant 2388x DMA audio support"
-	depends on VIDEO_CX88 && SND && EXPERIMENTAL
+	depends on VIDEO_CX88 && SND
 	select SND_PCM
 	---help---
 	  This is a video4linux driver for direct (DMA) audio on
diff --git a/drivers/media/video/gspca/gspca.c b/drivers/media/video/gspca/gspca.c
index b9846106913e..78abc1c1f9d5 100644
--- a/drivers/media/video/gspca/gspca.c
+++ b/drivers/media/video/gspca/gspca.c
@@ -223,6 +223,7 @@ static int alloc_and_submit_int_urb(struct gspca_dev *gspca_dev,
 		usb_rcvintpipe(dev, ep->bEndpointAddress),
 		buffer, buffer_len,
 		int_irq, (void *)gspca_dev, interval);
+	urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 	gspca_dev->int_urb = urb;
 	ret = usb_submit_urb(urb, GFP_KERNEL);
 	if (ret < 0) {
diff --git a/drivers/media/video/gspca/sn9c20x.c b/drivers/media/video/gspca/sn9c20x.c
index 83a718f0f3f9..9052d5702556 100644
--- a/drivers/media/video/gspca/sn9c20x.c
+++ b/drivers/media/video/gspca/sn9c20x.c
@@ -2357,8 +2357,7 @@ static void sd_pkt_scan(struct gspca_dev *gspca_dev,
 			    (data[33] << 10);
 		avg_lum >>= 9;
 		atomic_set(&sd->avg_lum, avg_lum);
-		gspca_frame_add(gspca_dev, LAST_PACKET,
-				data, len);
+		gspca_frame_add(gspca_dev, LAST_PACKET, NULL, 0);
 		return;
 	}
 	if (gspca_dev->last_packet_type == LAST_PACKET) {
diff --git a/drivers/media/video/ivtv/ivtvfb.c b/drivers/media/video/ivtv/ivtvfb.c
index be03a712731c..f0316d02f09f 100644
--- a/drivers/media/video/ivtv/ivtvfb.c
+++ b/drivers/media/video/ivtv/ivtvfb.c
@@ -466,6 +466,8 @@ static int ivtvfb_ioctl(struct fb_info *info, unsigned int cmd, unsigned long ar
 			struct fb_vblank vblank;
 			u32 trace;
 
+			memset(&vblank, 0, sizeof(struct fb_vblank));
+
 			vblank.flags = FB_VBLANK_HAVE_COUNT |FB_VBLANK_HAVE_VCOUNT |
 					FB_VBLANK_HAVE_VSYNC;
 			trace = read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16;
diff --git a/drivers/media/video/mem2mem_testdev.c b/drivers/media/video/mem2mem_testdev.c
index 4525335f9bd4..a7210d981388 100644
--- a/drivers/media/video/mem2mem_testdev.c
+++ b/drivers/media/video/mem2mem_testdev.c
@@ -239,7 +239,7 @@ static int device_process(struct m2mtest_ctx *ctx,
 		return -EFAULT;
 	}
 
-	if (in_buf->vb.size < out_buf->vb.size) {
+	if (in_buf->vb.size > out_buf->vb.size) {
 		v4l2_err(&dev->v4l2_dev, "Output buffer is too small\n");
 		return -EINVAL;
 	}
@@ -1014,6 +1014,7 @@ static int m2mtest_remove(struct platform_device *pdev)
 	v4l2_m2m_release(dev->m2m_dev);
 	del_timer_sync(&dev->timer);
 	video_unregister_device(dev->vfd);
+	video_device_release(dev->vfd);
 	v4l2_device_unregister(&dev->v4l2_dev);
 	kfree(dev);
 
diff --git a/drivers/media/video/mt9m111.c b/drivers/media/video/mt9m111.c
index 758a4db27d65..c71af4e0e517 100644
--- a/drivers/media/video/mt9m111.c
+++ b/drivers/media/video/mt9m111.c
@@ -447,6 +447,9 @@ static int mt9m111_s_crop(struct v4l2_subdev *sd, struct v4l2_crop *a)
 	dev_dbg(&client->dev, "%s left=%d, top=%d, width=%d, height=%d\n",
 		__func__, rect.left, rect.top, rect.width, rect.height);
 
+	if (a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
 	ret = mt9m111_make_rect(client, &rect);
 	if (!ret)
 		mt9m111->rect = rect;
@@ -466,12 +469,14 @@ static int mt9m111_g_crop(struct v4l2_subdev *sd, struct v4l2_crop *a)
 
 static int mt9m111_cropcap(struct v4l2_subdev *sd, struct v4l2_cropcap *a)
 {
+	if (a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
 	a->bounds.left			= MT9M111_MIN_DARK_COLS;
 	a->bounds.top			= MT9M111_MIN_DARK_ROWS;
 	a->bounds.width			= MT9M111_MAX_WIDTH;
 	a->bounds.height		= MT9M111_MAX_HEIGHT;
 	a->defrect			= a->bounds;
-	a->type				= V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	a->pixelaspect.numerator	= 1;
 	a->pixelaspect.denominator	= 1;
 
@@ -487,6 +492,7 @@ static int mt9m111_g_fmt(struct v4l2_subdev *sd,
 	mf->width	= mt9m111->rect.width;
 	mf->height	= mt9m111->rect.height;
 	mf->code	= mt9m111->fmt->code;
+	mf->colorspace	= mt9m111->fmt->colorspace;
 	mf->field	= V4L2_FIELD_NONE;
 
 	return 0;
diff --git a/drivers/media/video/mt9v022.c b/drivers/media/video/mt9v022.c
index e7cd23cd6394..b48473c7896b 100644
--- a/drivers/media/video/mt9v022.c
+++ b/drivers/media/video/mt9v022.c
@@ -402,9 +402,6 @@ static int mt9v022_s_fmt(struct v4l2_subdev *sd,
 		if (mt9v022->model != V4L2_IDENT_MT9V022IX7ATC)
 			return -EINVAL;
 		break;
-	case 0:
-		/* No format change, only geometry */
-		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/media/video/mx2_camera.c b/drivers/media/video/mx2_camera.c
index 66ff174151b5..b6ea67221d1d 100644
--- a/drivers/media/video/mx2_camera.c
+++ b/drivers/media/video/mx2_camera.c
@@ -378,6 +378,9 @@ static void mx25_camera_frame_done(struct mx2_camera_dev *pcdev, int fb,
 
 	spin_lock_irqsave(&pcdev->lock, flags);
 
+	if (*fb_active == NULL)
+		goto out;
+
 	vb = &(*fb_active)->vb;
 	dev_dbg(pcdev->dev, "%s (vb=0x%p) 0x%08lx %d\n", __func__,
 		vb, vb->baddr, vb->bsize);
@@ -402,6 +405,7 @@ static void mx25_camera_frame_done(struct mx2_camera_dev *pcdev, int fb,
 
 	*fb_active = buf;
 
+out:
 	spin_unlock_irqrestore(&pcdev->lock, flags);
 }
 
diff --git a/drivers/media/video/pvrusb2/pvrusb2-ctrl.c b/drivers/media/video/pvrusb2/pvrusb2-ctrl.c
index 1b992b847198..55ea914c7fcd 100644
--- a/drivers/media/video/pvrusb2/pvrusb2-ctrl.c
+++ b/drivers/media/video/pvrusb2/pvrusb2-ctrl.c
@@ -513,7 +513,7 @@ int pvr2_ctrl_sym_to_value(struct pvr2_ctrl *cptr,
 			if (ret >= 0) {
 				ret = pvr2_ctrl_range_check(cptr,*valptr);
 			}
-			if (maskptr) *maskptr = ~0;
+			*maskptr = ~0;
 		} else if (cptr->info->type == pvr2_ctl_bool) {
 			ret = parse_token(ptr,len,valptr,boolNames,
 					  ARRAY_SIZE(boolNames));
@@ -522,7 +522,7 @@ int pvr2_ctrl_sym_to_value(struct pvr2_ctrl *cptr,
 			} else if (ret == 0) {
 				*valptr = (*valptr & 1) ? !0 : 0;
 			}
-			if (maskptr) *maskptr = 1;
+			*maskptr = 1;
 		} else if (cptr->info->type == pvr2_ctl_enum) {
 			ret = parse_token(
 				ptr,len,valptr,
@@ -531,7 +531,7 @@ int pvr2_ctrl_sym_to_value(struct pvr2_ctrl *cptr,
 			if (ret >= 0) {
 				ret = pvr2_ctrl_range_check(cptr,*valptr);
 			}
-			if (maskptr) *maskptr = ~0;
+			*maskptr = ~0;
 		} else if (cptr->info->type == pvr2_ctl_bitmask) {
 			ret = parse_tlist(
 				ptr,len,maskptr,valptr,
diff --git a/drivers/media/video/s5p-fimc/fimc-core.c b/drivers/media/video/s5p-fimc/fimc-core.c
index b151c7be8a50..6961c55baf9b 100644
--- a/drivers/media/video/s5p-fimc/fimc-core.c
+++ b/drivers/media/video/s5p-fimc/fimc-core.c
@@ -393,6 +393,37 @@ static void fimc_set_yuv_order(struct fimc_ctx *ctx)
 	dbg("ctx->out_order_1p= %d", ctx->out_order_1p);
 }
 
+static void fimc_prepare_dma_offset(struct fimc_ctx *ctx, struct fimc_frame *f)
+{
+	struct samsung_fimc_variant *variant = ctx->fimc_dev->variant;
+
+	f->dma_offset.y_h = f->offs_h;
+	if (!variant->pix_hoff)
+		f->dma_offset.y_h *= (f->fmt->depth >> 3);
+
+	f->dma_offset.y_v = f->offs_v;
+
+	f->dma_offset.cb_h = f->offs_h;
+	f->dma_offset.cb_v = f->offs_v;
+
+	f->dma_offset.cr_h = f->offs_h;
+	f->dma_offset.cr_v = f->offs_v;
+
+	if (!variant->pix_hoff) {
+		if (f->fmt->planes_cnt == 3) {
+			f->dma_offset.cb_h >>= 1;
+			f->dma_offset.cr_h >>= 1;
+		}
+		if (f->fmt->color == S5P_FIMC_YCBCR420) {
+			f->dma_offset.cb_v >>= 1;
+			f->dma_offset.cr_v >>= 1;
+		}
+	}
+
+	dbg("in_offset: color= %d, y_h= %d, y_v= %d",
+	    f->fmt->color, f->dma_offset.y_h, f->dma_offset.y_v);
+}
+
 /**
  * fimc_prepare_config - check dimensions, operation and color mode
  *			 and pre-calculate offset and the scaling coefficients.
@@ -406,7 +437,6 @@ static int fimc_prepare_config(struct fimc_ctx *ctx, u32 flags)
 {
 	struct fimc_frame *s_frame, *d_frame;
 	struct fimc_vid_buffer *buf = NULL;
-	struct samsung_fimc_variant *variant = ctx->fimc_dev->variant;
 	int ret = 0;
 
 	s_frame = &ctx->s_frame;
@@ -419,61 +449,16 @@ static int fimc_prepare_config(struct fimc_ctx *ctx, u32 flags)
 			swap(d_frame->width, d_frame->height);
 		}
 
-		/* Prepare the output offset ratios for scaler. */
-		d_frame->dma_offset.y_h = d_frame->offs_h;
-		if (!variant->pix_hoff)
-			d_frame->dma_offset.y_h *= (d_frame->fmt->depth >> 3);
-
-		d_frame->dma_offset.y_v = d_frame->offs_v;
-
-		d_frame->dma_offset.cb_h = d_frame->offs_h;
-		d_frame->dma_offset.cb_v = d_frame->offs_v;
-
-		d_frame->dma_offset.cr_h = d_frame->offs_h;
-		d_frame->dma_offset.cr_v = d_frame->offs_v;
+		/* Prepare the DMA offset ratios for scaler. */
+		fimc_prepare_dma_offset(ctx, &ctx->s_frame);
+		fimc_prepare_dma_offset(ctx, &ctx->d_frame);
 
-		if (!variant->pix_hoff && d_frame->fmt->planes_cnt == 3) {
-			d_frame->dma_offset.cb_h >>= 1;
-			d_frame->dma_offset.cb_v >>= 1;
-			d_frame->dma_offset.cr_h >>= 1;
-			d_frame->dma_offset.cr_v >>= 1;
-		}
-
-		dbg("out offset: color= %d, y_h= %d, y_v= %d",
-			d_frame->fmt->color,
-			d_frame->dma_offset.y_h, d_frame->dma_offset.y_v);
-
-		/* Prepare the input offset ratios for scaler. */
-		s_frame->dma_offset.y_h = s_frame->offs_h;
-		if (!variant->pix_hoff)
-			s_frame->dma_offset.y_h *= (s_frame->fmt->depth >> 3);
-		s_frame->dma_offset.y_v = s_frame->offs_v;
-
-		s_frame->dma_offset.cb_h = s_frame->offs_h;
-		s_frame->dma_offset.cb_v = s_frame->offs_v;
-
-		s_frame->dma_offset.cr_h = s_frame->offs_h;
-		s_frame->dma_offset.cr_v = s_frame->offs_v;
-
-		if (!variant->pix_hoff && s_frame->fmt->planes_cnt == 3) {
-			s_frame->dma_offset.cb_h >>= 1;
-			s_frame->dma_offset.cb_v >>= 1;
-			s_frame->dma_offset.cr_h >>= 1;
-			s_frame->dma_offset.cr_v >>= 1;
-		}
-
-		dbg("in offset: color= %d, y_h= %d, y_v= %d",
-			s_frame->fmt->color, s_frame->dma_offset.y_h,
-			s_frame->dma_offset.y_v);
-
-		fimc_set_yuv_order(ctx);
-
-		/* Check against the scaler ratio. */
 		if (s_frame->height > (SCALER_MAX_VRATIO * d_frame->height) ||
 		    s_frame->width > (SCALER_MAX_HRATIO * d_frame->width)) {
 			err("out of scaler range");
 			return -EINVAL;
 		}
+		fimc_set_yuv_order(ctx);
 	}
 
 	/* Input DMA mode is not allowed when the scaler is disabled. */
@@ -822,7 +807,8 @@ static int fimc_m2m_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 	} else {
 		v4l2_err(&ctx->fimc_dev->m2m.v4l2_dev,
 			 "Wrong buffer/video queue type (%d)\n", f->type);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto s_fmt_out;
 	}
 
 	pix = &f->fmt.pix;
@@ -1414,8 +1400,10 @@ static int fimc_probe(struct platform_device *pdev)
 	}
 
 	fimc->work_queue = create_workqueue(dev_name(&fimc->pdev->dev));
-	if (!fimc->work_queue)
+	if (!fimc->work_queue) {
+		ret = -ENOMEM;
 		goto err_irq;
+	}
 
 	ret = fimc_register_m2m_device(fimc);
 	if (ret)
@@ -1492,6 +1480,7 @@ static struct samsung_fimc_variant fimc2_variant_s5p = {
 };
 
 static struct samsung_fimc_variant fimc01_variant_s5pv210 = {
+	.pix_hoff	= 1,
 	.has_inp_rot	= 1,
 	.has_out_rot	= 1,
 	.min_inp_pixsize = 16,
@@ -1506,6 +1495,7 @@ static struct samsung_fimc_variant fimc01_variant_s5pv210 = {
 };
 
 static struct samsung_fimc_variant fimc2_variant_s5pv210 = {
+	.pix_hoff	 = 1,
 	.min_inp_pixsize = 16,
 	.min_out_pixsize = 32,
 
diff --git a/drivers/media/video/saa7134/saa7134-cards.c b/drivers/media/video/saa7134/saa7134-cards.c
index ec697fcd406e..bb8d83d8ddaf 100644
--- a/drivers/media/video/saa7134/saa7134-cards.c
+++ b/drivers/media/video/saa7134/saa7134-cards.c
@@ -4323,13 +4323,13 @@ struct saa7134_board saa7134_boards[] = {
 	},
 	[SAA7134_BOARD_BEHOLD_COLUMBUS_TVFM] = {
 		/*       Beholder Intl. Ltd. 2008      */
-		/*Dmitry Belimov <d.belimov@gmail.com> */
-		.name           = "Beholder BeholdTV Columbus TVFM",
+		/* Dmitry Belimov <d.belimov@gmail.com> */
+		.name           = "Beholder BeholdTV Columbus TV/FM",
 		.audio_clock    = 0x00187de7,
 		.tuner_type     = TUNER_ALPS_TSBE5_PAL,
-		.radio_type     = UNSET,
-		.tuner_addr     = ADDR_UNSET,
-		.radio_addr     = ADDR_UNSET,
+		.radio_type     = TUNER_TEA5767,
+		.tuner_addr     = 0xc2 >> 1,
+		.radio_addr     = 0xc0 >> 1,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x000A8004,
 		.inputs         = {{
diff --git a/drivers/media/video/saa7164/saa7164-buffer.c b/drivers/media/video/saa7164/saa7164-buffer.c
index 5713f3a4b76c..ddd25d32723d 100644
--- a/drivers/media/video/saa7164/saa7164-buffer.c
+++ b/drivers/media/video/saa7164/saa7164-buffer.c
@@ -136,10 +136,11 @@ ret:
 int saa7164_buffer_dealloc(struct saa7164_tsport *port,
 	struct saa7164_buffer *buf)
 {
-	struct saa7164_dev *dev = port->dev;
+	struct saa7164_dev *dev;
 
-	if ((buf == 0) || (port == 0))
+	if (!buf || !port)
 		return SAA_ERR_BAD_PARAMETER;
+	dev = port->dev;
 
 	dprintk(DBGLVL_BUF, "%s() deallocating buffer @ 0x%p\n", __func__, buf);
 
diff --git a/drivers/media/video/uvc/uvc_driver.c b/drivers/media/video/uvc/uvc_driver.c
index 8bdd940f32e6..2ac85d8984f0 100644
--- a/drivers/media/video/uvc/uvc_driver.c
+++ b/drivers/media/video/uvc/uvc_driver.c
@@ -486,6 +486,12 @@ static int uvc_parse_format(struct uvc_device *dev,
 			    max(frame->dwFrameInterval[0],
 				frame->dwDefaultFrameInterval));
 
+		if (dev->quirks & UVC_QUIRK_RESTRICT_FRAME_RATE) {
+			frame->bFrameIntervalType = 1;
+			frame->dwFrameInterval[0] =
+				frame->dwDefaultFrameInterval;
+		}
+
 		uvc_trace(UVC_TRACE_DESCR, "- %ux%u (%u.%u fps)\n",
 			frame->wWidth, frame->wHeight,
 			10000000/frame->dwDefaultFrameInterval,
@@ -2026,6 +2032,15 @@ static struct usb_device_id uvc_ids[] = {
 	  .bInterfaceClass	= USB_CLASS_VENDOR_SPEC,
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0 },
+	/* Chicony CNF7129 (Asus EEE 100HE) */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x04f2,
+	  .idProduct		= 0xb071,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_QUIRK_RESTRICT_FRAME_RATE },
 	/* Alcor Micro AU3820 (Future Boy PC USB Webcam) */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
@@ -2091,6 +2106,15 @@ static struct usb_device_id uvc_ids[] = {
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= UVC_QUIRK_PROBE_MINMAX
 				| UVC_QUIRK_PROBE_DEF },
+	/* IMC Networks (Medion Akoya) */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x13d3,
+	  .idProduct		= 0x5103,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_QUIRK_STREAM_NO_FID },
 	/* Syntek (HP Spartan) */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
diff --git a/drivers/media/video/uvc/uvcvideo.h b/drivers/media/video/uvc/uvcvideo.h
index bdacf3beabf5..892e0e51916c 100644
--- a/drivers/media/video/uvc/uvcvideo.h
+++ b/drivers/media/video/uvc/uvcvideo.h
@@ -182,6 +182,7 @@ struct uvc_xu_control {
 #define UVC_QUIRK_IGNORE_SELECTOR_UNIT	0x00000020
 #define UVC_QUIRK_FIX_BANDWIDTH		0x00000080
 #define UVC_QUIRK_PROBE_DEF		0x00000100
+#define UVC_QUIRK_RESTRICT_FRAME_RATE	0x00000200
 
 /* Format flags */
 #define UVC_FMT_FLAG_COMPRESSED		0x00000001
diff --git a/drivers/media/video/v4l2-compat-ioctl32.c b/drivers/media/video/v4l2-compat-ioctl32.c
index 073f01390cdd..86294ed35c9b 100644
--- a/drivers/media/video/v4l2-compat-ioctl32.c
+++ b/drivers/media/video/v4l2-compat-ioctl32.c
@@ -193,17 +193,24 @@ static int put_video_window32(struct video_window *kp, struct video_window32 __u
 struct video_code32 {
 	char		loadwhat[16];	/* name or tag of file being passed */
 	compat_int_t	datasize;
-	unsigned char	*data;
+	compat_uptr_t	data;
 };
 
-static int get_microcode32(struct video_code *kp, struct video_code32 __user *up)
+static struct video_code __user *get_microcode32(struct video_code32 *kp)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct video_code32)) ||
-		copy_from_user(kp->loadwhat, up->loadwhat, sizeof(up->loadwhat)) ||
-		get_user(kp->datasize, &up->datasize) ||
-		copy_from_user(kp->data, up->data, up->datasize))
-			return -EFAULT;
-	return 0;
+	struct video_code __user *up;
+
+	up = compat_alloc_user_space(sizeof(*up));
+
+	/*
+	 * NOTE! We don't actually care if these fail. If the
+	 * user address is invalid, the native ioctl will do
+	 * the error handling for us
+	 */
+	(void) copy_to_user(up->loadwhat, kp->loadwhat, sizeof(up->loadwhat));
+	(void) put_user(kp->datasize, &up->datasize);
+	(void) put_user(compat_ptr(kp->data), &up->data);
+	return up;
 }
 
 #define VIDIOCGTUNER32		_IOWR('v', 4, struct video_tuner32)
@@ -739,7 +746,7 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		struct video_tuner vt;
 		struct video_buffer vb;
 		struct video_window vw;
-		struct video_code vc;
+		struct video_code32 vc;
 		struct video_audio va;
 #endif
 		struct v4l2_format v2f;
@@ -818,8 +825,11 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		break;
 
 	case VIDIOCSMICROCODE:
-		err = get_microcode32(&karg.vc, up);
-		compatible_arg = 0;
+		/* Copy the 32-bit "video_code32" to kernel space */
+		if (copy_from_user(&karg.vc, up, sizeof(karg.vc)))
+			return -EFAULT;
+		/* Convert the 32-bit version to a 64-bit version in user space */
+		up = get_microcode32(&karg.vc);
 		break;
 
 	case VIDIOCSFREQ:
diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c
index 372b87efcd05..6ff9e4bac3ea 100644
--- a/drivers/media/video/videobuf-dma-contig.c
+++ b/drivers/media/video/videobuf-dma-contig.c
@@ -393,8 +393,10 @@ void videobuf_dma_contig_free(struct videobuf_queue *q,
 	}
 
 	/* read() method */
-	dma_free_coherent(q->dev, mem->size, mem->vaddr, mem->dma_handle);
-	mem->vaddr = NULL;
+	if (mem->vaddr) {
+		dma_free_coherent(q->dev, mem->size, mem->vaddr, mem->dma_handle);
+		mem->vaddr = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(videobuf_dma_contig_free);
 
diff --git a/drivers/media/video/videobuf-dma-sg.c b/drivers/media/video/videobuf-dma-sg.c
index 06f9a9c2a39a..2ad0bc252b0e 100644
--- a/drivers/media/video/videobuf-dma-sg.c
+++ b/drivers/media/video/videobuf-dma-sg.c
@@ -94,7 +94,7 @@ err:
  * must free the memory.
  */
 static struct scatterlist *videobuf_pages_to_sg(struct page **pages,
-						int nr_pages, int offset)
+					int nr_pages, int offset, size_t size)
 {
 	struct scatterlist *sglist;
 	int i;
@@ -110,12 +110,14 @@ static struct scatterlist *videobuf_pages_to_sg(struct page **pages,
 		/* DMA to highmem pages might not work */
 		goto highmem;
 	sg_set_page(&sglist[0], pages[0], PAGE_SIZE - offset, offset);
+	size -= PAGE_SIZE - offset;
 	for (i = 1; i < nr_pages; i++) {
 		if (NULL == pages[i])
 			goto nopage;
 		if (PageHighMem(pages[i]))
 			goto highmem;
-		sg_set_page(&sglist[i], pages[i], PAGE_SIZE, 0);
+		sg_set_page(&sglist[i], pages[i], min(PAGE_SIZE, size), 0);
+		size -= min(PAGE_SIZE, size);
 	}
 	return sglist;
 
@@ -170,7 +172,8 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 
 	first = (data          & PAGE_MASK) >> PAGE_SHIFT;
 	last  = ((data+size-1) & PAGE_MASK) >> PAGE_SHIFT;
-	dma->offset   = data & ~PAGE_MASK;
+	dma->offset = data & ~PAGE_MASK;
+	dma->size = size;
 	dma->nr_pages = last-first+1;
 	dma->pages = kmalloc(dma->nr_pages * sizeof(struct page *), GFP_KERNEL);
 	if (NULL == dma->pages)
@@ -252,7 +255,7 @@ int videobuf_dma_map(struct device *dev, struct videobuf_dmabuf *dma)
 
 	if (dma->pages) {
 		dma->sglist = videobuf_pages_to_sg(dma->pages, dma->nr_pages,
-						   dma->offset);
+						   dma->offset, dma->size);
 	}
 	if (dma->vaddr) {
 		dma->sglist = videobuf_vmalloc_to_sg(dma->vaddr,
diff --git a/drivers/mfd/max8925-core.c b/drivers/mfd/max8925-core.c
index 04028a9ee082..428377a5a6f5 100644
--- a/drivers/mfd/max8925-core.c
+++ b/drivers/mfd/max8925-core.c
@@ -429,24 +429,25 @@ static void max8925_irq_sync_unlock(unsigned int irq)
 	irq_tsc = cache_tsc;
 	for (i = 0; i < ARRAY_SIZE(max8925_irqs); i++) {
 		irq_data = &max8925_irqs[i];
+		/* 1 -- disable, 0 -- enable */
 		switch (irq_data->mask_reg) {
 		case MAX8925_CHG_IRQ1_MASK:
-			irq_chg[0] &= irq_data->enable;
+			irq_chg[0] &= ~irq_data->enable;
 			break;
 		case MAX8925_CHG_IRQ2_MASK:
-			irq_chg[1] &= irq_data->enable;
+			irq_chg[1] &= ~irq_data->enable;
 			break;
 		case MAX8925_ON_OFF_IRQ1_MASK:
-			irq_on[0] &= irq_data->enable;
+			irq_on[0] &= ~irq_data->enable;
 			break;
 		case MAX8925_ON_OFF_IRQ2_MASK:
-			irq_on[1] &= irq_data->enable;
+			irq_on[1] &= ~irq_data->enable;
 			break;
 		case MAX8925_RTC_IRQ_MASK:
-			irq_rtc &= irq_data->enable;
+			irq_rtc &= ~irq_data->enable;
 			break;
 		case MAX8925_TSC_IRQ_MASK:
-			irq_tsc &= irq_data->enable;
+			irq_tsc &= ~irq_data->enable;
 			break;
 		default:
 			dev_err(chip->dev, "wrong IRQ\n");
diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c
index 7dabe4dbd373..294183b6260b 100644
--- a/drivers/mfd/wm831x-irq.c
+++ b/drivers/mfd/wm831x-irq.c
@@ -394,8 +394,13 @@ static int wm831x_irq_set_type(unsigned int irq, unsigned int type)
 
 	irq = irq - wm831x->irq_base;
 
-	if (irq < WM831X_IRQ_GPIO_1 || irq > WM831X_IRQ_GPIO_11)
-		return -EINVAL;
+	if (irq < WM831X_IRQ_GPIO_1 || irq > WM831X_IRQ_GPIO_11) {
+		/* Ignore internal-only IRQs */
+		if (irq >= 0 && irq < WM831X_NUM_IRQS)
+			return 0;
+		else
+			return -EINVAL;
+	}
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_BOTH:
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 0b591b658243..b74331260744 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -368,7 +368,7 @@ config VMWARE_BALLOON
 	  If unsure, say N.
 
 	  To compile this driver as a module, choose M here: the
-	  module will be called vmware_balloon.
+	  module will be called vmw_balloon.
 
 config ARM_CHARLCD
 	bool "ARM Ltd. Character LCD Driver"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 255a80dc9d73..42eab95cde2a 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -33,5 +33,5 @@ obj-$(CONFIG_IWMC3200TOP)      += iwmc3200top/
 obj-$(CONFIG_HMC6352)		+= hmc6352.o
 obj-y				+= eeprom/
 obj-y				+= cb710/
-obj-$(CONFIG_VMWARE_BALLOON)	+= vmware_balloon.o
+obj-$(CONFIG_VMWARE_BALLOON)	+= vmw_balloon.o
 obj-$(CONFIG_ARM_CHARLCD)	+= arm-charlcd.o
diff --git a/drivers/misc/bh1780gli.c b/drivers/misc/bh1780gli.c
index 714c6b487313..d5f3a3fd2319 100644
--- a/drivers/misc/bh1780gli.c
+++ b/drivers/misc/bh1780gli.c
@@ -190,7 +190,6 @@ static int __devexit bh1780_remove(struct i2c_client *client)
 
 	ddata = i2c_get_clientdata(client);
 	sysfs_remove_group(&client->dev.kobj, &bh1780_attr_group);
-	i2c_set_clientdata(client, NULL);
 	kfree(ddata);
 
 	return 0;
diff --git a/drivers/misc/vmware_balloon.c b/drivers/misc/vmw_balloon.c
similarity index 100%
rename from drivers/misc/vmware_balloon.c
rename to drivers/misc/vmw_balloon.c
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 5db49b124ffa..09eee6df0653 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1631,6 +1631,19 @@ int mmc_suspend_host(struct mmc_host *host)
 	if (host->bus_ops && !host->bus_dead) {
 		if (host->bus_ops->suspend)
 			err = host->bus_ops->suspend(host);
+		if (err == -ENOSYS || !host->bus_ops->resume) {
+			/*
+			 * We simply "remove" the card in this case.
+			 * It will be redetected on resume.
+			 */
+			if (host->bus_ops->remove)
+				host->bus_ops->remove(host);
+			mmc_claim_host(host);
+			mmc_detach_bus(host);
+			mmc_release_host(host);
+			host->pm_flags = 0;
+			err = 0;
+		}
 	}
 	mmc_bus_put(host);
 
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 71ad4163b95e..aacb862ecc8a 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -241,8 +241,10 @@ static struct sdhci_ops sdhci_s3c_ops = {
 static void sdhci_s3c_notify_change(struct platform_device *dev, int state)
 {
 	struct sdhci_host *host = platform_get_drvdata(dev);
+	unsigned long flags;
+
 	if (host) {
-		spin_lock(&host->lock);
+		spin_lock_irqsave(&host->lock, flags);
 		if (state) {
 			dev_dbg(&dev->dev, "card inserted.\n");
 			host->flags &= ~SDHCI_DEVICE_DEAD;
@@ -253,7 +255,7 @@ static void sdhci_s3c_notify_change(struct platform_device *dev, int state)
 			host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 		}
 		tasklet_schedule(&host->card_tasklet);
-		spin_unlock(&host->lock);
+		spin_unlock_irqrestore(&host->lock, flags);
 	}
 }
 
@@ -481,8 +483,10 @@ static int __devexit sdhci_s3c_remove(struct platform_device *pdev)
 	sdhci_remove_host(host, 1);
 
 	for (ptr = 0; ptr < 3; ptr++) {
-		clk_disable(sc->clk_bus[ptr]);
-		clk_put(sc->clk_bus[ptr]);
+		if (sc->clk_bus[ptr]) {
+			clk_disable(sc->clk_bus[ptr]);
+			clk_put(sc->clk_bus[ptr]);
+		}
 	}
 	clk_disable(sc->clk_io);
 	clk_put(sc->clk_io);
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index b2828e84d243..214b03afdd48 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -30,6 +30,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/completion.h>
 
 #include <asm/mach/flash.h>
 #include <mach/mxc_nand.h>
@@ -151,7 +153,7 @@ struct mxc_nand_host {
 	int			irq;
 	int			eccsize;
 
-	wait_queue_head_t	irq_waitq;
+	struct completion	op_completion;
 
 	uint8_t			*data_buf;
 	unsigned int		buf_start;
@@ -164,6 +166,7 @@ struct mxc_nand_host {
 	void			(*send_read_id)(struct mxc_nand_host *);
 	uint16_t		(*get_dev_status)(struct mxc_nand_host *);
 	int			(*check_int)(struct mxc_nand_host *);
+	void			(*irq_control)(struct mxc_nand_host *, int);
 };
 
 /* OOB placement block for use with hardware ecc generation */
@@ -216,9 +219,12 @@ static irqreturn_t mxc_nfc_irq(int irq, void *dev_id)
 {
 	struct mxc_nand_host *host = dev_id;
 
-	disable_irq_nosync(irq);
+	if (!host->check_int(host))
+		return IRQ_NONE;
 
-	wake_up(&host->irq_waitq);
+	host->irq_control(host, 0);
+
+	complete(&host->op_completion);
 
 	return IRQ_HANDLED;
 }
@@ -245,11 +251,54 @@ static int check_int_v1_v2(struct mxc_nand_host *host)
 	if (!(tmp & NFC_V1_V2_CONFIG2_INT))
 		return 0;
 
-	writew(tmp & ~NFC_V1_V2_CONFIG2_INT, NFC_V1_V2_CONFIG2);
+	if (!cpu_is_mx21())
+		writew(tmp & ~NFC_V1_V2_CONFIG2_INT, NFC_V1_V2_CONFIG2);
 
 	return 1;
 }
 
+/*
+ * It has been observed that the i.MX21 cannot read the CONFIG2:INT bit
+ * if interrupts are masked (CONFIG1:INT_MSK is set). To handle this, the
+ * driver can enable/disable the irq line rather than simply masking the
+ * interrupts.
+ */
+static void irq_control_mx21(struct mxc_nand_host *host, int activate)
+{
+	if (activate)
+		enable_irq(host->irq);
+	else
+		disable_irq_nosync(host->irq);
+}
+
+static void irq_control_v1_v2(struct mxc_nand_host *host, int activate)
+{
+	uint16_t tmp;
+
+	tmp = readw(NFC_V1_V2_CONFIG1);
+
+	if (activate)
+		tmp &= ~NFC_V1_V2_CONFIG1_INT_MSK;
+	else
+		tmp |= NFC_V1_V2_CONFIG1_INT_MSK;
+
+	writew(tmp, NFC_V1_V2_CONFIG1);
+}
+
+static void irq_control_v3(struct mxc_nand_host *host, int activate)
+{
+	uint32_t tmp;
+
+	tmp = readl(NFC_V3_CONFIG2);
+
+	if (activate)
+		tmp &= ~NFC_V3_CONFIG2_INT_MSK;
+	else
+		tmp |= NFC_V3_CONFIG2_INT_MSK;
+
+	writel(tmp, NFC_V3_CONFIG2);
+}
+
 /* This function polls the NANDFC to wait for the basic operation to
  * complete by checking the INT bit of config2 register.
  */
@@ -259,10 +308,9 @@ static void wait_op_done(struct mxc_nand_host *host, int useirq)
 
 	if (useirq) {
 		if (!host->check_int(host)) {
-
-			enable_irq(host->irq);
-
-			wait_event(host->irq_waitq, host->check_int(host));
+			INIT_COMPLETION(host->op_completion);
+			host->irq_control(host, 1);
+			wait_for_completion(&host->op_completion);
 		}
 	} else {
 		while (max_retries-- > 0) {
@@ -799,6 +847,7 @@ static void preset_v3(struct mtd_info *mtd)
 		NFC_V3_CONFIG2_2CMD_PHASES |
 		NFC_V3_CONFIG2_SPAS(mtd->oobsize >> 1) |
 		NFC_V3_CONFIG2_ST_CMD(0x70) |
+		NFC_V3_CONFIG2_INT_MSK |
 		NFC_V3_CONFIG2_NUM_ADDR_PHASE0;
 
 	if (chip->ecc.mode == NAND_ECC_HW)
@@ -1024,6 +1073,10 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 		host->send_read_id = send_read_id_v1_v2;
 		host->get_dev_status = get_dev_status_v1_v2;
 		host->check_int = check_int_v1_v2;
+		if (cpu_is_mx21())
+			host->irq_control = irq_control_mx21;
+		else
+			host->irq_control = irq_control_v1_v2;
 	}
 
 	if (nfc_is_v21()) {
@@ -1062,6 +1115,7 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 		host->send_read_id = send_read_id_v3;
 		host->check_int = check_int_v3;
 		host->get_dev_status = get_dev_status_v3;
+		host->irq_control = irq_control_v3;
 		oob_smallpage = &nandv2_hw_eccoob_smallpage;
 		oob_largepage = &nandv2_hw_eccoob_largepage;
 	} else
@@ -1093,14 +1147,34 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 		this->options |= NAND_USE_FLASH_BBT;
 	}
 
-	init_waitqueue_head(&host->irq_waitq);
+	init_completion(&host->op_completion);
 
 	host->irq = platform_get_irq(pdev, 0);
 
+	/*
+	 * mask the interrupt. For i.MX21 explicitely call
+	 * irq_control_v1_v2 to use the mask bit. We can't call
+	 * disable_irq_nosync() for an interrupt we do not own yet.
+	 */
+	if (cpu_is_mx21())
+		irq_control_v1_v2(host, 0);
+	else
+		host->irq_control(host, 0);
+
 	err = request_irq(host->irq, mxc_nfc_irq, IRQF_DISABLED, DRIVER_NAME, host);
 	if (err)
 		goto eirq;
 
+	host->irq_control(host, 0);
+
+	/*
+	 * Now that the interrupt is disabled make sure the interrupt
+	 * mask bit is cleared on i.MX21. Otherwise we can't read
+	 * the interrupt status bit on this machine.
+	 */
+	if (cpu_is_mx21())
+		irq_control_v1_v2(host, 1);
+
 	/* first scan to find the device and get the page size */
 	if (nand_scan_ident(mtd, 1, NULL)) {
 		err = -ENXIO;
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 133d51528f8d..513e0a76a4a7 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -413,7 +413,7 @@ static inline int omap_nand_dma_transfer(struct mtd_info *mtd, void *addr,
 		prefetch_status = gpmc_read_status(GPMC_PREFETCH_COUNT);
 	} while (prefetch_status);
 	/* disable and stop the PFPW engine */
-	gpmc_prefetch_reset();
+	gpmc_prefetch_reset(info->gpmc_cs);
 
 	dma_unmap_single(&info->pdev->dev, dma_addr, len, dir);
 	return 0;
diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
index fa42103b2874..179871d9e71f 100644
--- a/drivers/net/3c59x.c
+++ b/drivers/net/3c59x.c
@@ -2942,6 +2942,9 @@ static void vortex_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct vortex_private *vp = netdev_priv(dev);
 
+	if (!VORTEX_PCI(vp))
+		return;
+
 	wol->supported = WAKE_MAGIC;
 
 	wol->wolopts = 0;
@@ -2952,6 +2955,10 @@ static void vortex_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 static int vortex_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct vortex_private *vp = netdev_priv(dev);
+
+	if (!VORTEX_PCI(vp))
+		return -EOPNOTSUPP;
+
 	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EINVAL;
 
@@ -3201,6 +3208,9 @@ static void acpi_set_WOL(struct net_device *dev)
 			return;
 		}
 
+		if (VORTEX_PCI(vp)->current_state < PCI_D3hot)
+			return;
+
 		/* Change the power state to D3; RxEnable doesn't take effect. */
 		pci_set_power_state(VORTEX_PCI(vp), PCI_D3hot);
 	}
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 2cc81a54cbf3..5db667c0b371 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2428,7 +2428,7 @@ config UGETH_TX_ON_DEMAND
 
 config MV643XX_ETH
 	tristate "Marvell Discovery (643XX) and Orion ethernet support"
-	depends on MV64X60 || PPC32 || PLAT_ORION
+	depends on (MV64X60 || PPC32 || PLAT_ORION) && INET
 	select INET_LRO
 	select PHYLIB
 	help
@@ -2803,7 +2803,7 @@ config NIU
 
 config PASEMI_MAC
 	tristate "PA Semi 1/10Gbit MAC"
-	depends on PPC_PASEMI && PCI
+	depends on PPC_PASEMI && PCI && INET
 	select PHYLIB
 	select INET_LRO
 	help
diff --git a/drivers/net/atlx/atl1.c b/drivers/net/atlx/atl1.c
index 63b9ba0cc67e..c73be2848319 100644
--- a/drivers/net/atlx/atl1.c
+++ b/drivers/net/atlx/atl1.c
@@ -1251,6 +1251,12 @@ static void atl1_free_ring_resources(struct atl1_adapter *adapter)
 
 	rrd_ring->desc = NULL;
 	rrd_ring->dma = 0;
+
+	adapter->cmb.dma = 0;
+	adapter->cmb.cmb = NULL;
+
+	adapter->smb.dma = 0;
+	adapter->smb.smb = NULL;
 }
 
 static void atl1_setup_mac_ctrl(struct atl1_adapter *adapter)
@@ -2847,10 +2853,11 @@ static int atl1_resume(struct pci_dev *pdev)
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
 	atl1_reset_hw(&adapter->hw);
-	adapter->cmb.cmb->int_stats = 0;
 
-	if (netif_running(netdev))
+	if (netif_running(netdev)) {
+		adapter->cmb.cmb->int_stats = 0;
 		atl1_up(adapter);
+	}
 	netif_device_attach(netdev);
 
 	return 0;
diff --git a/drivers/net/b44.c b/drivers/net/b44.c
index 1e620e287ae0..efeffdf9e5fa 100644
--- a/drivers/net/b44.c
+++ b/drivers/net/b44.c
@@ -2170,8 +2170,6 @@ static int __devinit b44_init_one(struct ssb_device *sdev,
 	dev->irq = sdev->irq;
 	SET_ETHTOOL_OPS(dev, &b44_ethtool_ops);
 
-	netif_carrier_off(dev);
-
 	err = ssb_bus_powerup(sdev->bus, 0);
 	if (err) {
 		dev_err(sdev->dev,
@@ -2213,6 +2211,8 @@ static int __devinit b44_init_one(struct ssb_device *sdev,
 		goto err_out_powerdown;
 	}
 
+	netif_carrier_off(dev);
+
 	ssb_set_drvdata(sdev, dev);
 
 	/* Chip reset provides power to the b44 MAC & PCI cores, which
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3b16f62d5606..e953c6ad6e6d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5164,6 +5164,15 @@ int bond_create(struct net *net, const char *name)
 		res = dev_alloc_name(bond_dev, "bond%d");
 		if (res < 0)
 			goto out;
+	} else {
+		/*
+		 * If we're given a name to register
+		 * we need to ensure that its not already
+		 * registered
+		 */
+		res = -EEXIST;
+		if (__dev_get_by_name(net, name) != NULL)
+			goto out;
 	}
 
 	res = register_netdevice(bond_dev);
diff --git a/drivers/net/e1000e/hw.h b/drivers/net/e1000e/hw.h
index 66ed08f726fb..ba302a5c2c30 100644
--- a/drivers/net/e1000e/hw.h
+++ b/drivers/net/e1000e/hw.h
@@ -57,6 +57,7 @@ enum e1e_registers {
 	E1000_SCTL     = 0x00024, /* SerDes Control - RW */
 	E1000_FCAL     = 0x00028, /* Flow Control Address Low - RW */
 	E1000_FCAH     = 0x0002C, /* Flow Control Address High -RW */
+	E1000_FEXTNVM4 = 0x00024, /* Future Extended NVM 4 - RW */
 	E1000_FEXTNVM  = 0x00028, /* Future Extended NVM - RW */
 	E1000_FCT      = 0x00030, /* Flow Control Type - RW */
 	E1000_VET      = 0x00038, /* VLAN Ether Type - RW */
diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c
index 63930d12711c..57b5435599ab 100644
--- a/drivers/net/e1000e/ich8lan.c
+++ b/drivers/net/e1000e/ich8lan.c
@@ -105,6 +105,10 @@
 #define E1000_FEXTNVM_SW_CONFIG		1
 #define E1000_FEXTNVM_SW_CONFIG_ICH8M (1 << 27) /* Bit redefined for ICH8M :/ */
 
+#define E1000_FEXTNVM4_BEACON_DURATION_MASK    0x7
+#define E1000_FEXTNVM4_BEACON_DURATION_8USEC   0x7
+#define E1000_FEXTNVM4_BEACON_DURATION_16USEC  0x3
+
 #define PCIE_ICH8_SNOOP_ALL		PCIE_NO_SNOOP_ALL
 
 #define E1000_ICH_RAR_ENTRIES		7
@@ -125,6 +129,7 @@
 
 /* SMBus Address Phy Register */
 #define HV_SMB_ADDR            PHY_REG(768, 26)
+#define HV_SMB_ADDR_MASK       0x007F
 #define HV_SMB_ADDR_PEC_EN     0x0200
 #define HV_SMB_ADDR_VALID      0x0080
 
@@ -237,6 +242,8 @@ static s32  e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link);
 static s32 e1000_set_mdio_slow_mode_hv(struct e1000_hw *hw);
 static bool e1000_check_mng_mode_ich8lan(struct e1000_hw *hw);
 static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw);
+static s32 e1000_k1_workaround_lv(struct e1000_hw *hw);
+static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate);
 
 static inline u16 __er16flash(struct e1000_hw *hw, unsigned long reg)
 {
@@ -272,7 +279,7 @@ static inline void __ew32flash(struct e1000_hw *hw, unsigned long reg, u32 val)
 static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 {
 	struct e1000_phy_info *phy = &hw->phy;
-	u32 ctrl;
+	u32 ctrl, fwsm;
 	s32 ret_val = 0;
 
 	phy->addr                     = 1;
@@ -294,7 +301,8 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 	 * disabled, then toggle the LANPHYPC Value bit to force
 	 * the interconnect to PCIe mode.
 	 */
-	if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
+	fwsm = er32(FWSM);
+	if (!(fwsm & E1000_ICH_FWSM_FW_VALID)) {
 		ctrl = er32(CTRL);
 		ctrl |=  E1000_CTRL_LANPHYPC_OVERRIDE;
 		ctrl &= ~E1000_CTRL_LANPHYPC_VALUE;
@@ -303,6 +311,13 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 		ctrl &= ~E1000_CTRL_LANPHYPC_OVERRIDE;
 		ew32(CTRL, ctrl);
 		msleep(50);
+
+		/*
+		 * Gate automatic PHY configuration by hardware on
+		 * non-managed 82579
+		 */
+		if (hw->mac.type == e1000_pch2lan)
+			e1000_gate_hw_phy_config_ich8lan(hw, true);
 	}
 
 	/*
@@ -315,6 +330,13 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 	if (ret_val)
 		goto out;
 
+	/* Ungate automatic PHY configuration on non-managed 82579 */
+	if ((hw->mac.type == e1000_pch2lan)  &&
+	    !(fwsm & E1000_ICH_FWSM_FW_VALID)) {
+		msleep(10);
+		e1000_gate_hw_phy_config_ich8lan(hw, false);
+	}
+
 	phy->id = e1000_phy_unknown;
 	ret_val = e1000e_get_phy_id(hw);
 	if (ret_val)
@@ -561,13 +583,10 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_adapter *adapter)
 	if (mac->type == e1000_ich8lan)
 		e1000e_set_kmrn_lock_loss_workaround_ich8lan(hw, true);
 
-	/* Disable PHY configuration by hardware, config by software */
-	if (mac->type == e1000_pch2lan) {
-		u32 extcnf_ctrl = er32(EXTCNF_CTRL);
-
-		extcnf_ctrl |= E1000_EXTCNF_CTRL_GATE_PHY_CFG;
-		ew32(EXTCNF_CTRL, extcnf_ctrl);
-	}
+	/* Gate automatic PHY configuration by hardware on managed 82579 */
+	if ((mac->type == e1000_pch2lan) &&
+	    (er32(FWSM) & E1000_ICH_FWSM_FW_VALID))
+		e1000_gate_hw_phy_config_ich8lan(hw, true);
 
 	return 0;
 }
@@ -652,6 +671,12 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 			goto out;
 	}
 
+	if (hw->mac.type == e1000_pch2lan) {
+		ret_val = e1000_k1_workaround_lv(hw);
+		if (ret_val)
+			goto out;
+	}
+
 	/*
 	 * Check if there was DownShift, must be checked
 	 * immediately after link-up
@@ -894,6 +919,34 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw)
 	return (fwsm & E1000_ICH_FWSM_RSPCIPHY) ? 0 : E1000_BLK_PHY_RESET;
 }
 
+/**
+ *  e1000_write_smbus_addr - Write SMBus address to PHY needed during Sx states
+ *  @hw: pointer to the HW structure
+ *
+ *  Assumes semaphore already acquired.
+ *
+ **/
+static s32 e1000_write_smbus_addr(struct e1000_hw *hw)
+{
+	u16 phy_data;
+	u32 strap = er32(STRAP);
+	s32 ret_val = 0;
+
+	strap &= E1000_STRAP_SMBUS_ADDRESS_MASK;
+
+	ret_val = e1000_read_phy_reg_hv_locked(hw, HV_SMB_ADDR, &phy_data);
+	if (ret_val)
+		goto out;
+
+	phy_data &= ~HV_SMB_ADDR_MASK;
+	phy_data |= (strap >> E1000_STRAP_SMBUS_ADDRESS_SHIFT);
+	phy_data |= HV_SMB_ADDR_PEC_EN | HV_SMB_ADDR_VALID;
+	ret_val = e1000_write_phy_reg_hv_locked(hw, HV_SMB_ADDR, phy_data);
+
+out:
+	return ret_val;
+}
+
 /**
  *  e1000_sw_lcd_config_ich8lan - SW-based LCD Configuration
  *  @hw:   pointer to the HW structure
@@ -903,7 +956,6 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw)
  **/
 static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 {
-	struct e1000_adapter *adapter = hw->adapter;
 	struct e1000_phy_info *phy = &hw->phy;
 	u32 i, data, cnf_size, cnf_base_addr, sw_cfg_mask;
 	s32 ret_val = 0;
@@ -921,7 +973,8 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 		if (phy->type != e1000_phy_igp_3)
 			return ret_val;
 
-		if (adapter->pdev->device == E1000_DEV_ID_ICH8_IGP_AMT) {
+		if ((hw->adapter->pdev->device == E1000_DEV_ID_ICH8_IGP_AMT) ||
+		    (hw->adapter->pdev->device == E1000_DEV_ID_ICH8_IGP_C)) {
 			sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG;
 			break;
 		}
@@ -961,21 +1014,16 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 	cnf_base_addr = data & E1000_EXTCNF_CTRL_EXT_CNF_POINTER_MASK;
 	cnf_base_addr >>= E1000_EXTCNF_CTRL_EXT_CNF_POINTER_SHIFT;
 
-	if (!(data & E1000_EXTCNF_CTRL_OEM_WRITE_ENABLE) &&
-	    ((hw->mac.type == e1000_pchlan) ||
-	     (hw->mac.type == e1000_pch2lan))) {
+	if ((!(data & E1000_EXTCNF_CTRL_OEM_WRITE_ENABLE) &&
+	    (hw->mac.type == e1000_pchlan)) ||
+	     (hw->mac.type == e1000_pch2lan)) {
 		/*
 		 * HW configures the SMBus address and LEDs when the
 		 * OEM and LCD Write Enable bits are set in the NVM.
 		 * When both NVM bits are cleared, SW will configure
 		 * them instead.
 		 */
-		data = er32(STRAP);
-		data &= E1000_STRAP_SMBUS_ADDRESS_MASK;
-		reg_data = data >> E1000_STRAP_SMBUS_ADDRESS_SHIFT;
-		reg_data |= HV_SMB_ADDR_PEC_EN | HV_SMB_ADDR_VALID;
-		ret_val = e1000_write_phy_reg_hv_locked(hw, HV_SMB_ADDR,
-							reg_data);
+		ret_val = e1000_write_smbus_addr(hw);
 		if (ret_val)
 			goto out;
 
@@ -1440,10 +1488,6 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable)
 			goto out;
 
 		/* Enable jumbo frame workaround in the PHY */
-		e1e_rphy(hw, PHY_REG(769, 20), &data);
-		ret_val = e1e_wphy(hw, PHY_REG(769, 20), data & ~(1 << 14));
-		if (ret_val)
-			goto out;
 		e1e_rphy(hw, PHY_REG(769, 23), &data);
 		data &= ~(0x7F << 5);
 		data |= (0x37 << 5);
@@ -1452,7 +1496,6 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable)
 			goto out;
 		e1e_rphy(hw, PHY_REG(769, 16), &data);
 		data &= ~(1 << 13);
-		data |= (1 << 12);
 		ret_val = e1e_wphy(hw, PHY_REG(769, 16), data);
 		if (ret_val)
 			goto out;
@@ -1477,7 +1520,7 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable)
 
 		mac_reg = er32(RCTL);
 		mac_reg &= ~E1000_RCTL_SECRC;
-		ew32(FFLT_DBG, mac_reg);
+		ew32(RCTL, mac_reg);
 
 		ret_val = e1000e_read_kmrn_reg(hw,
 						E1000_KMRNCTRLSTA_CTRL_OFFSET,
@@ -1503,17 +1546,12 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable)
 			goto out;
 
 		/* Write PHY register values back to h/w defaults */
-		e1e_rphy(hw, PHY_REG(769, 20), &data);
-		ret_val = e1e_wphy(hw, PHY_REG(769, 20), data & ~(1 << 14));
-		if (ret_val)
-			goto out;
 		e1e_rphy(hw, PHY_REG(769, 23), &data);
 		data &= ~(0x7F << 5);
 		ret_val = e1e_wphy(hw, PHY_REG(769, 23), data);
 		if (ret_val)
 			goto out;
 		e1e_rphy(hw, PHY_REG(769, 16), &data);
-		data &= ~(1 << 12);
 		data |= (1 << 13);
 		ret_val = e1e_wphy(hw, PHY_REG(769, 16), data);
 		if (ret_val)
@@ -1558,6 +1596,69 @@ out:
 	return ret_val;
 }
 
+/**
+ *  e1000_k1_gig_workaround_lv - K1 Si workaround
+ *  @hw:   pointer to the HW structure
+ *
+ *  Workaround to set the K1 beacon duration for 82579 parts
+ **/
+static s32 e1000_k1_workaround_lv(struct e1000_hw *hw)
+{
+	s32 ret_val = 0;
+	u16 status_reg = 0;
+	u32 mac_reg;
+
+	if (hw->mac.type != e1000_pch2lan)
+		goto out;
+
+	/* Set K1 beacon duration based on 1Gbps speed or otherwise */
+	ret_val = e1e_rphy(hw, HV_M_STATUS, &status_reg);
+	if (ret_val)
+		goto out;
+
+	if ((status_reg & (HV_M_STATUS_LINK_UP | HV_M_STATUS_AUTONEG_COMPLETE))
+	    == (HV_M_STATUS_LINK_UP | HV_M_STATUS_AUTONEG_COMPLETE)) {
+		mac_reg = er32(FEXTNVM4);
+		mac_reg &= ~E1000_FEXTNVM4_BEACON_DURATION_MASK;
+
+		if (status_reg & HV_M_STATUS_SPEED_1000)
+			mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_8USEC;
+		else
+			mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_16USEC;
+
+		ew32(FEXTNVM4, mac_reg);
+	}
+
+out:
+	return ret_val;
+}
+
+/**
+ *  e1000_gate_hw_phy_config_ich8lan - disable PHY config via hardware
+ *  @hw:   pointer to the HW structure
+ *  @gate: boolean set to true to gate, false to ungate
+ *
+ *  Gate/ungate the automatic PHY configuration via hardware; perform
+ *  the configuration via software instead.
+ **/
+static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate)
+{
+	u32 extcnf_ctrl;
+
+	if (hw->mac.type != e1000_pch2lan)
+		return;
+
+	extcnf_ctrl = er32(EXTCNF_CTRL);
+
+	if (gate)
+		extcnf_ctrl |= E1000_EXTCNF_CTRL_GATE_PHY_CFG;
+	else
+		extcnf_ctrl &= ~E1000_EXTCNF_CTRL_GATE_PHY_CFG;
+
+	ew32(EXTCNF_CTRL, extcnf_ctrl);
+	return;
+}
+
 /**
  *  e1000_lan_init_done_ich8lan - Check for PHY config completion
  *  @hw: pointer to the HW structure
@@ -1602,6 +1703,9 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw)
 	if (e1000_check_reset_block(hw))
 		goto out;
 
+	/* Allow time for h/w to get to quiescent state after reset */
+	msleep(10);
+
 	/* Perform any necessary post-reset workarounds */
 	switch (hw->mac.type) {
 	case e1000_pchlan:
@@ -1630,6 +1734,13 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw)
 	/* Configure the LCD with the OEM bits in NVM */
 	ret_val = e1000_oem_bits_config_ich8lan(hw, true);
 
+	/* Ungate automatic PHY configuration on non-managed 82579 */
+	if ((hw->mac.type == e1000_pch2lan) &&
+	    !(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
+		msleep(10);
+		e1000_gate_hw_phy_config_ich8lan(hw, false);
+	}
+
 out:
 	return ret_val;
 }
@@ -1646,6 +1757,11 @@ static s32 e1000_phy_hw_reset_ich8lan(struct e1000_hw *hw)
 {
 	s32 ret_val = 0;
 
+	/* Gate automatic PHY configuration by hardware on non-managed 82579 */
+	if ((hw->mac.type == e1000_pch2lan) &&
+	    !(er32(FWSM) & E1000_ICH_FWSM_FW_VALID))
+		e1000_gate_hw_phy_config_ich8lan(hw, true);
+
 	ret_val = e1000e_phy_hw_reset_generic(hw);
 	if (ret_val)
 		goto out;
@@ -2910,6 +3026,14 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
 		 * external PHY is reset.
 		 */
 		ctrl |= E1000_CTRL_PHY_RST;
+
+		/*
+		 * Gate automatic PHY configuration by hardware on
+		 * non-managed 82579
+		 */
+		if ((hw->mac.type == e1000_pch2lan) &&
+		    !(er32(FWSM) & E1000_ICH_FWSM_FW_VALID))
+			e1000_gate_hw_phy_config_ich8lan(hw, true);
 	}
 	ret_val = e1000_acquire_swflag_ich8lan(hw);
 	e_dbg("Issuing a global reset to ich8lan\n");
@@ -3460,13 +3584,20 @@ void e1000e_gig_downshift_workaround_ich8lan(struct e1000_hw *hw)
 void e1000e_disable_gig_wol_ich8lan(struct e1000_hw *hw)
 {
 	u32 phy_ctrl;
+	s32 ret_val;
 
 	phy_ctrl = er32(PHY_CTRL);
 	phy_ctrl |= E1000_PHY_CTRL_D0A_LPLU | E1000_PHY_CTRL_GBE_DISABLE;
 	ew32(PHY_CTRL, phy_ctrl);
 
-	if (hw->mac.type >= e1000_pchlan)
-		e1000_phy_hw_reset_ich8lan(hw);
+	if (hw->mac.type >= e1000_pchlan) {
+		e1000_oem_bits_config_ich8lan(hw, true);
+		ret_val = hw->phy.ops.acquire(hw);
+		if (ret_val)
+			return;
+		e1000_write_smbus_addr(hw);
+		hw->phy.ops.release(hw);
+	}
 }
 
 /**
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 2b8ef44bd2b1..e561d15c3eb1 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -2704,6 +2704,16 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
 	u32 psrctl = 0;
 	u32 pages = 0;
 
+	/* Workaround Si errata on 82579 - configure jumbo frame flow */
+	if (hw->mac.type == e1000_pch2lan) {
+		s32 ret_val;
+
+		if (adapter->netdev->mtu > ETH_DATA_LEN)
+			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true);
+		else
+			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false);
+	}
+
 	/* Program MC offset vector base */
 	rctl = er32(RCTL);
 	rctl &= ~(3 << E1000_RCTL_MO_SHIFT);
@@ -2744,16 +2754,6 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
 		e1e_wphy(hw, 22, phy_data);
 	}
 
-	/* Workaround Si errata on 82579 - configure jumbo frame flow */
-	if (hw->mac.type == e1000_pch2lan) {
-		s32 ret_val;
-
-		if (rctl & E1000_RCTL_LPE)
-			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true);
-		else
-			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false);
-	}
-
 	/* Setup buffer sizes */
 	rctl &= ~E1000_RCTL_SZ_4096;
 	rctl |= E1000_RCTL_BSEX;
@@ -4833,6 +4833,15 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EINVAL;
 	}
 
+	/* Jumbo frame workaround on 82579 requires CRC be stripped */
+	if ((adapter->hw.mac.type == e1000_pch2lan) &&
+	    !(adapter->flags2 & FLAG2_CRC_STRIPPING) &&
+	    (new_mtu > ETH_DATA_LEN)) {
+		e_err("Jumbo Frames not supported on 82579 when CRC "
+		      "stripping is disabled.\n");
+		return -EINVAL;
+	}
+
 	/* 82573 Errata 17 */
 	if (((adapter->hw.mac.type == e1000_82573) ||
 	     (adapter->hw.mac.type == e1000_82574)) &&
diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c
index a333b42111b8..6372610ed240 100644
--- a/drivers/net/ehea/ehea_main.c
+++ b/drivers/net/ehea/ehea_main.c
@@ -533,8 +533,15 @@ static inline void ehea_fill_skb(struct net_device *dev,
 	int length = cqe->num_bytes_transfered - 4;	/*remove CRC */
 
 	skb_put(skb, length);
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	skb->protocol = eth_type_trans(skb, dev);
+
+	/* The packet was not an IPV4 packet so a complemented checksum was
+	   calculated. The value is found in the Internet Checksum field. */
+	if (cqe->status & EHEA_CQE_BLIND_CKSUM) {
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = csum_unfold(~cqe->inet_checksum_value);
+	} else
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 }
 
 static inline struct sk_buff *get_skb_by_index(struct sk_buff **skb_array,
diff --git a/drivers/net/ehea/ehea_qmr.h b/drivers/net/ehea/ehea_qmr.h
index f608a6c54af5..38104734a3be 100644
--- a/drivers/net/ehea/ehea_qmr.h
+++ b/drivers/net/ehea/ehea_qmr.h
@@ -150,6 +150,7 @@ struct ehea_rwqe {
 #define EHEA_CQE_TYPE_RQ           0x60
 #define EHEA_CQE_STAT_ERR_MASK     0x700F
 #define EHEA_CQE_STAT_FAT_ERR_MASK 0xF
+#define EHEA_CQE_BLIND_CKSUM       0x8000
 #define EHEA_CQE_STAT_ERR_TCP      0x4000
 #define EHEA_CQE_STAT_ERR_IP       0x2000
 #define EHEA_CQE_STAT_ERR_CRC      0x1000
diff --git a/drivers/net/fec.c b/drivers/net/fec.c
index 768b840aeb6b..cce32d43175f 100644
--- a/drivers/net/fec.c
+++ b/drivers/net/fec.c
@@ -678,24 +678,37 @@ static int fec_enet_mii_probe(struct net_device *dev)
 {
 	struct fec_enet_private *fep = netdev_priv(dev);
 	struct phy_device *phy_dev = NULL;
-	int ret;
+	char mdio_bus_id[MII_BUS_ID_SIZE];
+	char phy_name[MII_BUS_ID_SIZE + 3];
+	int phy_id;
 
 	fep->phy_dev = NULL;
 
-	/* find the first phy */
-	phy_dev = phy_find_first(fep->mii_bus);
-	if (!phy_dev) {
-		printk(KERN_ERR "%s: no PHY found\n", dev->name);
-		return -ENODEV;
+	/* check for attached phy */
+	for (phy_id = 0; (phy_id < PHY_MAX_ADDR); phy_id++) {
+		if ((fep->mii_bus->phy_mask & (1 << phy_id)))
+			continue;
+		if (fep->mii_bus->phy_map[phy_id] == NULL)
+			continue;
+		if (fep->mii_bus->phy_map[phy_id]->phy_id == 0)
+			continue;
+		strncpy(mdio_bus_id, fep->mii_bus->id, MII_BUS_ID_SIZE);
+		break;
 	}
 
-	/* attach the mac to the phy */
-	ret = phy_connect_direct(dev, phy_dev,
-			     &fec_enet_adjust_link, 0,
-			     PHY_INTERFACE_MODE_MII);
-	if (ret) {
-		printk(KERN_ERR "%s: Could not attach to PHY\n", dev->name);
-		return ret;
+	if (phy_id >= PHY_MAX_ADDR) {
+		printk(KERN_INFO "%s: no PHY, assuming direct connection "
+			"to switch\n", dev->name);
+		strncpy(mdio_bus_id, "0", MII_BUS_ID_SIZE);
+		phy_id = 0;
+	}
+
+	snprintf(phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT, mdio_bus_id, phy_id);
+	phy_dev = phy_connect(dev, phy_name, &fec_enet_adjust_link, 0,
+		PHY_INTERFACE_MODE_MII);
+	if (IS_ERR(phy_dev)) {
+		printk(KERN_ERR "%s: could not attach to PHY\n", dev->name);
+		return PTR_ERR(phy_dev);
 	}
 
 	/* mask with MAC supported features */
@@ -738,7 +751,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	fep->mii_bus->read = fec_enet_mdio_read;
 	fep->mii_bus->write = fec_enet_mdio_write;
 	fep->mii_bus->reset = fec_enet_mdio_reset;
-	snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id);
+	snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id + 1);
 	fep->mii_bus->priv = fep;
 	fep->mii_bus->parent = &pdev->dev;
 
@@ -1311,6 +1324,9 @@ fec_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_mii_init;
 
+	/* Carrier starts down, phylib will bring it up */
+	netif_carrier_off(ndev);
+
 	ret = register_netdev(ndev);
 	if (ret)
 		goto failed_register;
diff --git a/drivers/net/ibm_newemac/core.c b/drivers/net/ibm_newemac/core.c
index 3506fd6ad726..519e19e23955 100644
--- a/drivers/net/ibm_newemac/core.c
+++ b/drivers/net/ibm_newemac/core.c
@@ -2928,7 +2928,7 @@ static int __devinit emac_probe(struct platform_device *ofdev,
 	if (dev->emac_irq != NO_IRQ)
 		irq_dispose_mapping(dev->emac_irq);
  err_free:
-	kfree(ndev);
+	free_netdev(ndev);
  err_gone:
 	/* if we were on the bootlist, remove us as we won't show up and
 	 * wake up all waiters to notify them in case they were waiting
@@ -2971,7 +2971,7 @@ static int __devexit emac_remove(struct platform_device *ofdev)
 	if (dev->emac_irq != NO_IRQ)
 		irq_dispose_mapping(dev->emac_irq);
 
-	kfree(dev->ndev);
+	free_netdev(dev->ndev);
 
 	return 0;
 }
diff --git a/drivers/net/netxen/netxen_nic_init.c b/drivers/net/netxen/netxen_nic_init.c
index cabae7bb1fc6..b075a35b85d4 100644
--- a/drivers/net/netxen/netxen_nic_init.c
+++ b/drivers/net/netxen/netxen_nic_init.c
@@ -1540,7 +1540,6 @@ netxen_process_rcv(struct netxen_adapter *adapter,
 	if (pkt_offset)
 		skb_pull(skb, pkt_offset);
 
-	skb->truesize = skb->len + sizeof(struct sk_buff);
 	skb->protocol = eth_type_trans(skb, netdev);
 
 	napi_gro_receive(&sds_ring->napi, skb);
@@ -1602,8 +1601,6 @@ netxen_process_lro(struct netxen_adapter *adapter,
 
 	skb_put(skb, lro_length + data_offset);
 
-	skb->truesize = skb->len + sizeof(struct sk_buff) + skb_headroom(skb);
-
 	skb_pull(skb, l2_hdr_offset);
 	skb->protocol = eth_type_trans(skb, netdev);
 
diff --git a/drivers/net/qlcnic/qlcnic_init.c b/drivers/net/qlcnic/qlcnic_init.c
index 75ba744b173c..2c7cf0b64811 100644
--- a/drivers/net/qlcnic/qlcnic_init.c
+++ b/drivers/net/qlcnic/qlcnic_init.c
@@ -1316,7 +1316,7 @@ qlcnic_alloc_rx_skb(struct qlcnic_adapter *adapter,
 		return -ENOMEM;
 	}
 
-	skb_reserve(skb, 2);
+	skb_reserve(skb, NET_IP_ALIGN);
 
 	dma = pci_map_single(pdev, skb->data,
 			rds_ring->dma_size, PCI_DMA_FROMDEVICE);
@@ -1404,7 +1404,6 @@ qlcnic_process_rcv(struct qlcnic_adapter *adapter,
 	if (pkt_offset)
 		skb_pull(skb, pkt_offset);
 
-	skb->truesize = skb->len + sizeof(struct sk_buff);
 	skb->protocol = eth_type_trans(skb, netdev);
 
 	napi_gro_receive(&sds_ring->napi, skb);
@@ -1466,8 +1465,6 @@ qlcnic_process_lro(struct qlcnic_adapter *adapter,
 
 	skb_put(skb, lro_length + data_offset);
 
-	skb->truesize = skb->len + sizeof(struct sk_buff) + skb_headroom(skb);
-
 	skb_pull(skb, l2_hdr_offset);
 	skb->protocol = eth_type_trans(skb, netdev);
 
@@ -1700,8 +1697,6 @@ qlcnic_process_rcv_diag(struct qlcnic_adapter *adapter,
 	if (pkt_offset)
 		skb_pull(skb, pkt_offset);
 
-	skb->truesize = skb->len + sizeof(struct sk_buff);
-
 	if (!qlcnic_check_loopback_buff(skb->data))
 		adapter->diag_cnt++;
 
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index a0da4a17b025..992db2fa136e 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -1212,7 +1212,8 @@ static void rtl8169_update_counters(struct net_device *dev)
 	if ((RTL_R8(ChipCmd) & CmdRxEnb) == 0)
 		return;
 
-	counters = pci_alloc_consistent(tp->pci_dev, sizeof(*counters), &paddr);
+	counters = dma_alloc_coherent(&tp->pci_dev->dev, sizeof(*counters),
+				      &paddr, GFP_KERNEL);
 	if (!counters)
 		return;
 
@@ -1233,7 +1234,8 @@ static void rtl8169_update_counters(struct net_device *dev)
 	RTL_W32(CounterAddrLow, 0);
 	RTL_W32(CounterAddrHigh, 0);
 
-	pci_free_consistent(tp->pci_dev, sizeof(*counters), counters, paddr);
+	dma_free_coherent(&tp->pci_dev->dev, sizeof(*counters), counters,
+			  paddr);
 }
 
 static void rtl8169_get_ethtool_stats(struct net_device *dev,
@@ -3292,15 +3294,15 @@ static int rtl8169_open(struct net_device *dev)
 
 	/*
 	 * Rx and Tx desscriptors needs 256 bytes alignment.
-	 * pci_alloc_consistent provides more.
+	 * dma_alloc_coherent provides more.
 	 */
-	tp->TxDescArray = pci_alloc_consistent(pdev, R8169_TX_RING_BYTES,
-					       &tp->TxPhyAddr);
+	tp->TxDescArray = dma_alloc_coherent(&pdev->dev, R8169_TX_RING_BYTES,
+					     &tp->TxPhyAddr, GFP_KERNEL);
 	if (!tp->TxDescArray)
 		goto err_pm_runtime_put;
 
-	tp->RxDescArray = pci_alloc_consistent(pdev, R8169_RX_RING_BYTES,
-					       &tp->RxPhyAddr);
+	tp->RxDescArray = dma_alloc_coherent(&pdev->dev, R8169_RX_RING_BYTES,
+					     &tp->RxPhyAddr, GFP_KERNEL);
 	if (!tp->RxDescArray)
 		goto err_free_tx_0;
 
@@ -3334,12 +3336,12 @@ out:
 err_release_ring_2:
 	rtl8169_rx_clear(tp);
 err_free_rx_1:
-	pci_free_consistent(pdev, R8169_RX_RING_BYTES, tp->RxDescArray,
-			    tp->RxPhyAddr);
+	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
+			  tp->RxPhyAddr);
 	tp->RxDescArray = NULL;
 err_free_tx_0:
-	pci_free_consistent(pdev, R8169_TX_RING_BYTES, tp->TxDescArray,
-			    tp->TxPhyAddr);
+	dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray,
+			  tp->TxPhyAddr);
 	tp->TxDescArray = NULL;
 err_pm_runtime_put:
 	pm_runtime_put_noidle(&pdev->dev);
@@ -3975,7 +3977,7 @@ static void rtl8169_free_rx_skb(struct rtl8169_private *tp,
 {
 	struct pci_dev *pdev = tp->pci_dev;
 
-	pci_unmap_single(pdev, le64_to_cpu(desc->addr), tp->rx_buf_sz,
+	dma_unmap_single(&pdev->dev, le64_to_cpu(desc->addr), tp->rx_buf_sz,
 			 PCI_DMA_FROMDEVICE);
 	dev_kfree_skb(*sk_buff);
 	*sk_buff = NULL;
@@ -4000,7 +4002,7 @@ static inline void rtl8169_map_to_asic(struct RxDesc *desc, dma_addr_t mapping,
 static struct sk_buff *rtl8169_alloc_rx_skb(struct pci_dev *pdev,
 					    struct net_device *dev,
 					    struct RxDesc *desc, int rx_buf_sz,
-					    unsigned int align)
+					    unsigned int align, gfp_t gfp)
 {
 	struct sk_buff *skb;
 	dma_addr_t mapping;
@@ -4008,13 +4010,13 @@ static struct sk_buff *rtl8169_alloc_rx_skb(struct pci_dev *pdev,
 
 	pad = align ? align : NET_IP_ALIGN;
 
-	skb = netdev_alloc_skb(dev, rx_buf_sz + pad);
+	skb = __netdev_alloc_skb(dev, rx_buf_sz + pad, gfp);
 	if (!skb)
 		goto err_out;
 
 	skb_reserve(skb, align ? ((pad - 1) & (unsigned long)skb->data) : pad);
 
-	mapping = pci_map_single(pdev, skb->data, rx_buf_sz,
+	mapping = dma_map_single(&pdev->dev, skb->data, rx_buf_sz,
 				 PCI_DMA_FROMDEVICE);
 
 	rtl8169_map_to_asic(desc, mapping, rx_buf_sz);
@@ -4039,7 +4041,7 @@ static void rtl8169_rx_clear(struct rtl8169_private *tp)
 }
 
 static u32 rtl8169_rx_fill(struct rtl8169_private *tp, struct net_device *dev,
-			   u32 start, u32 end)
+			   u32 start, u32 end, gfp_t gfp)
 {
 	u32 cur;
 
@@ -4054,7 +4056,7 @@ static u32 rtl8169_rx_fill(struct rtl8169_private *tp, struct net_device *dev,
 
 		skb = rtl8169_alloc_rx_skb(tp->pci_dev, dev,
 					   tp->RxDescArray + i,
-					   tp->rx_buf_sz, tp->align);
+					   tp->rx_buf_sz, tp->align, gfp);
 		if (!skb)
 			break;
 
@@ -4082,7 +4084,7 @@ static int rtl8169_init_ring(struct net_device *dev)
 	memset(tp->tx_skb, 0x0, NUM_TX_DESC * sizeof(struct ring_info));
 	memset(tp->Rx_skbuff, 0x0, NUM_RX_DESC * sizeof(struct sk_buff *));
 
-	if (rtl8169_rx_fill(tp, dev, 0, NUM_RX_DESC) != NUM_RX_DESC)
+	if (rtl8169_rx_fill(tp, dev, 0, NUM_RX_DESC, GFP_KERNEL) != NUM_RX_DESC)
 		goto err_out;
 
 	rtl8169_mark_as_last_descriptor(tp->RxDescArray + NUM_RX_DESC - 1);
@@ -4099,7 +4101,8 @@ static void rtl8169_unmap_tx_skb(struct pci_dev *pdev, struct ring_info *tx_skb,
 {
 	unsigned int len = tx_skb->len;
 
-	pci_unmap_single(pdev, le64_to_cpu(desc->addr), len, PCI_DMA_TODEVICE);
+	dma_unmap_single(&pdev->dev, le64_to_cpu(desc->addr), len,
+			 PCI_DMA_TODEVICE);
 	desc->opts1 = 0x00;
 	desc->opts2 = 0x00;
 	desc->addr = 0x00;
@@ -4243,7 +4246,8 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 		txd = tp->TxDescArray + entry;
 		len = frag->size;
 		addr = ((void *) page_address(frag->page)) + frag->page_offset;
-		mapping = pci_map_single(tp->pci_dev, addr, len, PCI_DMA_TODEVICE);
+		mapping = dma_map_single(&tp->pci_dev->dev, addr, len,
+					 PCI_DMA_TODEVICE);
 
 		/* anti gcc 2.95.3 bugware (sic) */
 		status = opts1 | len | (RingEnd * !((entry + 1) % NUM_TX_DESC));
@@ -4313,7 +4317,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 		tp->tx_skb[entry].skb = skb;
 	}
 
-	mapping = pci_map_single(tp->pci_dev, skb->data, len, PCI_DMA_TODEVICE);
+	mapping = dma_map_single(&tp->pci_dev->dev, skb->data, len,
+				 PCI_DMA_TODEVICE);
 
 	tp->tx_skb[entry].len = len;
 	txd->addr = cpu_to_le64(mapping);
@@ -4477,8 +4482,8 @@ static inline bool rtl8169_try_rx_copy(struct sk_buff **sk_buff,
 	if (!skb)
 		goto out;
 
-	pci_dma_sync_single_for_cpu(tp->pci_dev, addr, pkt_size,
-				    PCI_DMA_FROMDEVICE);
+	dma_sync_single_for_cpu(&tp->pci_dev->dev, addr, pkt_size,
+				PCI_DMA_FROMDEVICE);
 	skb_copy_from_linear_data(*sk_buff, skb->data, pkt_size);
 	*sk_buff = skb;
 	done = true;
@@ -4549,11 +4554,11 @@ static int rtl8169_rx_interrupt(struct net_device *dev,
 			rtl8169_rx_csum(skb, desc);
 
 			if (rtl8169_try_rx_copy(&skb, tp, pkt_size, addr)) {
-				pci_dma_sync_single_for_device(pdev, addr,
+				dma_sync_single_for_device(&pdev->dev, addr,
 					pkt_size, PCI_DMA_FROMDEVICE);
 				rtl8169_mark_to_asic(desc, tp->rx_buf_sz);
 			} else {
-				pci_unmap_single(pdev, addr, tp->rx_buf_sz,
+				dma_unmap_single(&pdev->dev, addr, tp->rx_buf_sz,
 						 PCI_DMA_FROMDEVICE);
 				tp->Rx_skbuff[entry] = NULL;
 			}
@@ -4583,7 +4588,7 @@ static int rtl8169_rx_interrupt(struct net_device *dev,
 	count = cur_rx - tp->cur_rx;
 	tp->cur_rx = cur_rx;
 
-	delta = rtl8169_rx_fill(tp, dev, tp->dirty_rx, tp->cur_rx);
+	delta = rtl8169_rx_fill(tp, dev, tp->dirty_rx, tp->cur_rx, GFP_ATOMIC);
 	if (!delta && count)
 		netif_info(tp, intr, dev, "no Rx buffer allocated\n");
 	tp->dirty_rx += delta;
@@ -4769,10 +4774,10 @@ static int rtl8169_close(struct net_device *dev)
 
 	free_irq(dev->irq, dev);
 
-	pci_free_consistent(pdev, R8169_RX_RING_BYTES, tp->RxDescArray,
-			    tp->RxPhyAddr);
-	pci_free_consistent(pdev, R8169_TX_RING_BYTES, tp->TxDescArray,
-			    tp->TxPhyAddr);
+	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
+			  tp->RxPhyAddr);
+	dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray,
+			  tp->TxPhyAddr);
 	tp->TxDescArray = NULL;
 	tp->RxDescArray = NULL;
 
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 07eb884ff982..44150f2f7bfd 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -384,7 +384,7 @@ static void rionet_remove(struct rio_dev *rdev)
 	free_pages((unsigned long)rionet_active, rdev->net->hport->sys_size ?
 					__ilog2(sizeof(void *)) + 4 : 0);
 	unregister_netdev(ndev);
-	kfree(ndev);
+	free_netdev(ndev);
 
 	list_for_each_entry_safe(peer, tmp, &rionet_peers, node) {
 		list_del(&peer->node);
diff --git a/drivers/net/sgiseeq.c b/drivers/net/sgiseeq.c
index cc4bd8c65f8b..9265315baa0b 100644
--- a/drivers/net/sgiseeq.c
+++ b/drivers/net/sgiseeq.c
@@ -804,7 +804,7 @@ static int __devinit sgiseeq_probe(struct platform_device *pdev)
 err_out_free_page:
 	free_page((unsigned long) sp->srings);
 err_out_free_dev:
-	kfree(dev);
+	free_netdev(dev);
 
 err_out:
 	return err;
diff --git a/drivers/net/skge.c b/drivers/net/skge.c
index 40e5c46e7571..465ae7e84507 100644
--- a/drivers/net/skge.c
+++ b/drivers/net/skge.c
@@ -43,6 +43,7 @@
 #include <linux/seq_file.h>
 #include <linux/mii.h>
 #include <linux/slab.h>
+#include <linux/dmi.h>
 #include <asm/irq.h>
 
 #include "skge.h"
@@ -3868,6 +3869,8 @@ static void __devinit skge_show_addr(struct net_device *dev)
 	netif_info(skge, probe, skge->netdev, "addr %pM\n", dev->dev_addr);
 }
 
+static int only_32bit_dma;
+
 static int __devinit skge_probe(struct pci_dev *pdev,
 				const struct pci_device_id *ent)
 {
@@ -3889,7 +3892,7 @@ static int __devinit skge_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	if (!only_32bit_dma && !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	} else if (!(err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
@@ -4147,8 +4150,21 @@ static struct pci_driver skge_driver = {
 	.shutdown =	skge_shutdown,
 };
 
+static struct dmi_system_id skge_32bit_dma_boards[] = {
+	{
+		.ident = "Gigabyte nForce boards",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co"),
+			DMI_MATCH(DMI_BOARD_NAME, "nForce"),
+		},
+	},
+	{}
+};
+
 static int __init skge_init_module(void)
 {
+	if (dmi_check_system(skge_32bit_dma_boards))
+		only_32bit_dma = 1;
 	skge_debug_init();
 	return pci_register_driver(&skge_driver);
 }
diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c
index 0909ae934ad0..8150ba154116 100644
--- a/drivers/net/smsc911x.c
+++ b/drivers/net/smsc911x.c
@@ -58,6 +58,7 @@
 
 MODULE_LICENSE("GPL");
 MODULE_VERSION(SMSC_DRV_VERSION);
+MODULE_ALIAS("platform:smsc911x");
 
 #if USE_DEBUG > 0
 static int debug = 16;
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index bc3af78a869f..1ec4b9e0239a 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -4666,7 +4666,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				       desc_idx, *post_ptr);
 		drop_it_no_recycle:
 			/* Other statistics kept track of by card. */
-			tp->net_stats.rx_dropped++;
+			tp->rx_dropped++;
 			goto next_pkt;
 		}
 
@@ -4726,7 +4726,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 		if (len > (tp->dev->mtu + ETH_HLEN) &&
 		    skb->protocol != htons(ETH_P_8021Q)) {
 			dev_kfree_skb(skb);
-			goto next_pkt;
+			goto drop_it_no_recycle;
 		}
 
 		if (desc->type_flags & RXD_FLAG_VLAN &&
@@ -9240,6 +9240,8 @@ static struct rtnl_link_stats64 *tg3_get_stats64(struct net_device *dev,
 	stats->rx_missed_errors = old_stats->rx_missed_errors +
 		get_stat64(&hw_stats->rx_discards);
 
+	stats->rx_dropped = tp->rx_dropped;
+
 	return stats;
 }
 
diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h
index 4937bd190964..be7ff138a7f9 100644
--- a/drivers/net/tg3.h
+++ b/drivers/net/tg3.h
@@ -2759,7 +2759,7 @@ struct tg3 {
 
 
 	/* begin "everything else" cacheline(s) section */
-	struct rtnl_link_stats64	net_stats;
+	unsigned long			rx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
 	struct tg3_ethtool_stats	estats;
 	struct tg3_ethtool_stats	estats_prev;
diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c
index 5efa57757a2c..6888e3d41462 100644
--- a/drivers/net/tulip/de2104x.c
+++ b/drivers/net/tulip/de2104x.c
@@ -243,6 +243,7 @@ enum {
 	NWayState		= (1 << 14) | (1 << 13) | (1 << 12),
 	NWayRestart		= (1 << 12),
 	NonselPortActive	= (1 << 9),
+	SelPortActive		= (1 << 8),
 	LinkFailStatus		= (1 << 2),
 	NetCxnErr		= (1 << 1),
 };
@@ -363,7 +364,9 @@ static u16 t21040_csr15[] = { 0, 0, 0x0006, 0x0000, 0x0000, };
 
 /* 21041 transceiver register settings: TP AUTO, BNC, AUI, TP, TP FD*/
 static u16 t21041_csr13[] = { 0xEF01, 0xEF09, 0xEF09, 0xEF01, 0xEF09, };
-static u16 t21041_csr14[] = { 0xFFFF, 0xF7FD, 0xF7FD, 0x6F3F, 0x6F3D, };
+static u16 t21041_csr14[] = { 0xFFFF, 0xF7FD, 0xF7FD, 0x7F3F, 0x7F3D, };
+/* If on-chip autonegotiation is broken, use half-duplex (FF3F) instead */
+static u16 t21041_csr14_brk[] = { 0xFF3F, 0xF7FD, 0xF7FD, 0x7F3F, 0x7F3D, };
 static u16 t21041_csr15[] = { 0x0008, 0x0006, 0x000E, 0x0008, 0x0008, };
 
 
@@ -1064,6 +1067,9 @@ static void de21041_media_timer (unsigned long data)
 	unsigned int carrier;
 	unsigned long flags;
 
+	/* clear port active bits */
+	dw32(SIAStatus, NonselPortActive | SelPortActive);
+
 	carrier = (status & NetCxnErr) ? 0 : 1;
 
 	if (carrier) {
@@ -1158,14 +1164,29 @@ no_link_yet:
 static void de_media_interrupt (struct de_private *de, u32 status)
 {
 	if (status & LinkPass) {
+		/* Ignore if current media is AUI or BNC and we can't use TP */
+		if ((de->media_type == DE_MEDIA_AUI ||
+		     de->media_type == DE_MEDIA_BNC) &&
+		    (de->media_lock ||
+		     !de_ok_to_advertise(de, DE_MEDIA_TP_AUTO)))
+			return;
+		/* If current media is not TP, change it to TP */
+		if ((de->media_type == DE_MEDIA_AUI ||
+		     de->media_type == DE_MEDIA_BNC)) {
+			de->media_type = DE_MEDIA_TP_AUTO;
+			de_stop_rxtx(de);
+			de_set_media(de);
+			de_start_rxtx(de);
+		}
 		de_link_up(de);
 		mod_timer(&de->media_timer, jiffies + DE_TIMER_LINK);
 		return;
 	}
 
 	BUG_ON(!(status & LinkFail));
-
-	if (netif_carrier_ok(de->dev)) {
+	/* Mark the link as down only if current media is TP */
+	if (netif_carrier_ok(de->dev) && de->media_type != DE_MEDIA_AUI &&
+	    de->media_type != DE_MEDIA_BNC) {
 		de_link_down(de);
 		mod_timer(&de->media_timer, jiffies + DE_TIMER_NO_LINK);
 	}
@@ -1229,6 +1250,7 @@ static void de_adapter_sleep (struct de_private *de)
 	if (de->de21040)
 		return;
 
+	dw32(CSR13, 0); /* Reset phy */
 	pci_read_config_dword(de->pdev, PCIPM, &pmctl);
 	pmctl |= PM_Sleep;
 	pci_write_config_dword(de->pdev, PCIPM, pmctl);
@@ -1574,12 +1596,15 @@ static int __de_set_settings(struct de_private *de, struct ethtool_cmd *ecmd)
 		return 0; /* nothing to change */
 
 	de_link_down(de);
+	mod_timer(&de->media_timer, jiffies + DE_TIMER_NO_LINK);
 	de_stop_rxtx(de);
 
 	de->media_type = new_media;
 	de->media_lock = media_lock;
 	de->media_advertise = ecmd->advertising;
 	de_set_media(de);
+	if (netif_running(de->dev))
+		de_start_rxtx(de);
 
 	return 0;
 }
@@ -1911,8 +1936,14 @@ fill_defaults:
 	for (i = 0; i < DE_MAX_MEDIA; i++) {
 		if (de->media[i].csr13 == 0xffff)
 			de->media[i].csr13 = t21041_csr13[i];
-		if (de->media[i].csr14 == 0xffff)
-			de->media[i].csr14 = t21041_csr14[i];
+		if (de->media[i].csr14 == 0xffff) {
+			/* autonegotiation is broken at least on some chip
+			   revisions - rev. 0x21 works, 0x11 does not */
+			if (de->pdev->revision < 0x20)
+				de->media[i].csr14 = t21041_csr14_brk[i];
+			else
+				de->media[i].csr14 = t21041_csr14[i];
+		}
 		if (de->media[i].csr15 == 0xffff)
 			de->media[i].csr15 = t21041_csr15[i];
 	}
@@ -2158,6 +2189,8 @@ static int de_resume (struct pci_dev *pdev)
 		dev_err(&dev->dev, "pci_enable_device failed in resume\n");
 		goto out;
 	}
+	pci_set_master(pdev);
+	de_init_rings(de);
 	de_init_hw(de);
 out_attach:
 	netif_device_attach(dev);
diff --git a/drivers/net/wimax/i2400m/rx.c b/drivers/net/wimax/i2400m/rx.c
index 8cc9e319f435..1737d1488b35 100644
--- a/drivers/net/wimax/i2400m/rx.c
+++ b/drivers/net/wimax/i2400m/rx.c
@@ -1244,16 +1244,16 @@ int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
 	int i, result;
 	struct device *dev = i2400m_dev(i2400m);
 	const struct i2400m_msg_hdr *msg_hdr;
-	size_t pl_itr, pl_size, skb_len;
+	size_t pl_itr, pl_size;
 	unsigned long flags;
-	unsigned num_pls, single_last;
+	unsigned num_pls, single_last, skb_len;
 
 	skb_len = skb->len;
-	d_fnstart(4, dev, "(i2400m %p skb %p [size %zu])\n",
+	d_fnstart(4, dev, "(i2400m %p skb %p [size %u])\n",
 		  i2400m, skb, skb_len);
 	result = -EIO;
 	msg_hdr = (void *) skb->data;
-	result = i2400m_rx_msg_hdr_check(i2400m, msg_hdr, skb->len);
+	result = i2400m_rx_msg_hdr_check(i2400m, msg_hdr, skb_len);
 	if (result < 0)
 		goto error_msg_hdr_check;
 	result = -EIO;
@@ -1261,10 +1261,10 @@ int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
 	pl_itr = sizeof(*msg_hdr) +	/* Check payload descriptor(s) */
 		num_pls * sizeof(msg_hdr->pld[0]);
 	pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN);
-	if (pl_itr > skb->len) {	/* got all the payload descriptors? */
+	if (pl_itr > skb_len) {	/* got all the payload descriptors? */
 		dev_err(dev, "RX: HW BUG? message too short (%u bytes) for "
 			"%u payload descriptors (%zu each, total %zu)\n",
-			skb->len, num_pls, sizeof(msg_hdr->pld[0]), pl_itr);
+			skb_len, num_pls, sizeof(msg_hdr->pld[0]), pl_itr);
 		goto error_pl_descr_short;
 	}
 	/* Walk each payload payload--check we really got it */
@@ -1272,7 +1272,7 @@ int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
 		/* work around old gcc warnings */
 		pl_size = i2400m_pld_size(&msg_hdr->pld[i]);
 		result = i2400m_rx_pl_descr_check(i2400m, &msg_hdr->pld[i],
-						  pl_itr, skb->len);
+						  pl_itr, skb_len);
 		if (result < 0)
 			goto error_pl_descr_check;
 		single_last = num_pls == 1 || i == num_pls - 1;
@@ -1290,16 +1290,16 @@ int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
 	if (i < i2400m->rx_pl_min)
 		i2400m->rx_pl_min = i;
 	i2400m->rx_num++;
-	i2400m->rx_size_acc += skb->len;
-	if (skb->len < i2400m->rx_size_min)
-		i2400m->rx_size_min = skb->len;
-	if (skb->len > i2400m->rx_size_max)
-		i2400m->rx_size_max = skb->len;
+	i2400m->rx_size_acc += skb_len;
+	if (skb_len < i2400m->rx_size_min)
+		i2400m->rx_size_min = skb_len;
+	if (skb_len > i2400m->rx_size_max)
+		i2400m->rx_size_max = skb_len;
 	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
 error_pl_descr_check:
 error_pl_descr_short:
 error_msg_hdr_check:
-	d_fnend(4, dev, "(i2400m %p skb %p [size %zu]) = %d\n",
+	d_fnend(4, dev, "(i2400m %p skb %p [size %u]) = %d\n",
 		i2400m, skb, skb_len, result);
 	return result;
 }
diff --git a/drivers/net/wireless/ath/ath9k/ani.c b/drivers/net/wireless/ath/ath9k/ani.c
index cc648b6ae31c..a3d95cca8f0c 100644
--- a/drivers/net/wireless/ath/ath9k/ani.c
+++ b/drivers/net/wireless/ath/ath9k/ani.c
@@ -543,7 +543,7 @@ static u8 ath9k_hw_chan_2_clockrate_mhz(struct ath_hw *ah)
 	if (conf_is_ht40(conf))
 		return clockrate * 2;
 
-	return clockrate * 2;
+	return clockrate;
 }
 
 static int32_t ath9k_hw_ani_get_listen_time(struct ath_hw *ah)
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
index 9dd9e64c2b0b..8fd00a6e5120 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
@@ -1411,7 +1411,7 @@ void iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
 	clear_bit(STATUS_SCAN_HW, &priv->status);
 	clear_bit(STATUS_SCANNING, &priv->status);
 	/* inform mac80211 scan aborted */
-	queue_work(priv->workqueue, &priv->scan_completed);
+	queue_work(priv->workqueue, &priv->abort_scan);
 }
 
 int iwlagn_manage_ibss_station(struct iwl_priv *priv,
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c
index 07dbc2796448..e23c4060a0f0 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.c
+++ b/drivers/net/wireless/iwlwifi/iwl-core.c
@@ -2613,6 +2613,11 @@ int iwl_force_reset(struct iwl_priv *priv, int mode, bool external)
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status))
 		return -EINVAL;
 
+	if (test_bit(STATUS_SCANNING, &priv->status)) {
+		IWL_DEBUG_INFO(priv, "scan in progress.\n");
+		return -EINVAL;
+	}
+
 	if (mode >= IWL_MAX_FORCE_RESET) {
 		IWL_DEBUG_INFO(priv, "invalid reset request.\n");
 		return -EINVAL;
diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c
index 59a308b02f95..d31661c1ce77 100644
--- a/drivers/net/wireless/iwlwifi/iwl3945-base.c
+++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c
@@ -3018,7 +3018,7 @@ void iwl3945_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
 	clear_bit(STATUS_SCANNING, &priv->status);
 
 	/* inform mac80211 scan aborted */
-	queue_work(priv->workqueue, &priv->scan_completed);
+	queue_work(priv->workqueue, &priv->abort_scan);
 }
 
 static void iwl3945_bg_restart(struct work_struct *data)
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index c3ceebb5be84..4789f8e8bf7a 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -71,6 +71,49 @@
 #define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 #define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
 
+/* page table handling */
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return 30 + agaw * LEVEL_STRIDE;
+}
+
+static inline int width_to_agaw(int width)
+{
+	return (width - 30) / LEVEL_STRIDE;
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(unsigned long pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline unsigned long level_mask(int level)
+{
+	return -1UL << level_to_offset_bits(level);
+}
+
+static inline unsigned long level_size(int level)
+{
+	return 1UL << level_to_offset_bits(level);
+}
+
+static inline unsigned long align_to_level(unsigned long pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
@@ -434,8 +477,6 @@ void free_iova_mem(struct iova *iova)
 }
 
 
-static inline int width_to_agaw(int width);
-
 static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
 {
 	unsigned long sagaw;
@@ -646,51 +687,6 @@ out:
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-/* page table handling */
-#define LEVEL_STRIDE		(9)
-#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
-
-static inline int agaw_to_level(int agaw)
-{
-	return agaw + 2;
-}
-
-static inline int agaw_to_width(int agaw)
-{
-	return 30 + agaw * LEVEL_STRIDE;
-
-}
-
-static inline int width_to_agaw(int width)
-{
-	return (width - 30) / LEVEL_STRIDE;
-}
-
-static inline unsigned int level_to_offset_bits(int level)
-{
-	return (level - 1) * LEVEL_STRIDE;
-}
-
-static inline int pfn_level_offset(unsigned long pfn, int level)
-{
-	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
-}
-
-static inline unsigned long level_mask(int level)
-{
-	return -1UL << level_to_offset_bits(level);
-}
-
-static inline unsigned long level_size(int level)
-{
-	return 1UL << level_to_offset_bits(level);
-}
-
-static inline unsigned long align_to_level(unsigned long pfn, int level)
-{
-	return (pfn + level_size(level) - 1) & level_mask(level);
-}
-
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 				      unsigned long pfn)
 {
@@ -3761,6 +3757,33 @@ static void __devinit quirk_iommu_rwbf(struct pci_dev *dev)
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);
 
+#define GGC 0x52
+#define GGC_MEMORY_SIZE_MASK	(0xf << 8)
+#define GGC_MEMORY_SIZE_NONE	(0x0 << 8)
+#define GGC_MEMORY_SIZE_1M	(0x1 << 8)
+#define GGC_MEMORY_SIZE_2M	(0x3 << 8)
+#define GGC_MEMORY_VT_ENABLED	(0x8 << 8)
+#define GGC_MEMORY_SIZE_2M_VT	(0x9 << 8)
+#define GGC_MEMORY_SIZE_3M_VT	(0xa << 8)
+#define GGC_MEMORY_SIZE_4M_VT	(0xb << 8)
+
+static void __devinit quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
+{
+	unsigned short ggc;
+
+	if (pci_read_config_word(dev, GGC, &ggc))
+		return;
+
+	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
+		printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
+		dmar_map_gfx = 0;
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
+
 /* On Tylersburg chipsets, some BIOSes have been known to enable the
    ISOCH DMAR unit for the Azalia sound device, but not give it any
    TLB entries, which causes it to deadlock. Check for that.  We do
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index ce6a3666b3d9..553d8ee55c1c 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -608,7 +608,7 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno,
  * the VF BAR size multiplied by the number of VFs.  The alignment
  * is just the VF BAR size.
  */
-int pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
+resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
 {
 	struct resource tmp;
 	enum pci_bar_type type;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 7754a678ab15..6beb11b617a9 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -264,7 +264,8 @@ extern int pci_iov_init(struct pci_dev *dev);
 extern void pci_iov_release(struct pci_dev *dev);
 extern int pci_iov_resource_bar(struct pci_dev *dev, int resno,
 				enum pci_bar_type *type);
-extern int pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
+extern resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev,
+						    int resno);
 extern void pci_restore_iov_state(struct pci_dev *dev);
 extern int pci_iov_bus_range(struct pci_bus *bus);
 
@@ -320,7 +321,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev)
 }
 #endif /* CONFIG_PCI_IOV */
 
-static inline int pci_resource_alignment(struct pci_dev *dev,
+static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 					 struct resource *res)
 {
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 89ed181cd90c..857ae01734a6 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -162,6 +162,26 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_1,	quirk_isa_d
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_2,	quirk_isa_dma_hangs);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_3,	quirk_isa_dma_hangs);
 
+/*
+ * Intel NM10 "TigerPoint" LPC PM1a_STS.BM_STS must be clear
+ * for some HT machines to use C4 w/o hanging.
+ */
+static void __devinit quirk_tigerpoint_bm_sts(struct pci_dev *dev)
+{
+	u32 pmbase;
+	u16 pm1a;
+
+	pci_read_config_dword(dev, 0x40, &pmbase);
+	pmbase = pmbase & 0xff80;
+	pm1a = inw(pmbase);
+
+	if (pm1a & 0x10) {
+		dev_info(&dev->dev, FW_BUG "TigerPoint LPC.BM_STS cleared\n");
+		outw(0x10, pmbase);
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGP_LPC, quirk_tigerpoint_bm_sts);
+
 /*
  *	Chipsets where PCI->PCI transfers vanish or hang
  */
diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c
index a5c176598d95..9ba4dade69a4 100644
--- a/drivers/pcmcia/pcmcia_resource.c
+++ b/drivers/pcmcia/pcmcia_resource.c
@@ -595,7 +595,13 @@ int pcmcia_request_io(struct pcmcia_device *p_dev)
 	if (c->io[1].end) {
 		ret = alloc_io_space(s, &c->io[1], p_dev->io_lines);
 		if (ret) {
+			struct resource tmp = c->io[0];
+			/* release the previously allocated resource */
 			release_io_space(s, &c->io[0]);
+			/* but preserve the settings, for they worked... */
+			c->io[0].end = resource_size(&tmp);
+			c->io[0].start = tmp.start;
+			c->io[0].flags = tmp.flags;
 			goto out;
 		}
 	} else
diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c
index b8a869af0f44..deef6656ab7b 100644
--- a/drivers/pcmcia/pd6729.c
+++ b/drivers/pcmcia/pd6729.c
@@ -646,7 +646,7 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev,
 	if (!pci_resource_start(dev, 0)) {
 		dev_warn(&dev->dev, "refusing to load the driver as the "
 			"io_base is NULL.\n");
-		goto err_out_free_mem;
+		goto err_out_disable;
 	}
 
 	dev_info(&dev->dev, "Cirrus PD6729 PCI to PCMCIA Bridge at 0x%llx "
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 9024480a8228..c44a5e8b8b82 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -51,7 +51,6 @@
  * TODO:
  *   - handle CPU hotplug
  *   - provide turbo enable/disable api
- *   - make sure we can write turbo enable/disable reg based on MISC_EN
  *
  * Related documents:
  *   - CDI 403777, 403778 - Auburndale EDS vol 1 & 2
@@ -230,7 +229,7 @@
 #define THM_TC2		0xac
 #define THM_DTV		0xb0
 #define THM_ITV		0xd8
-#define   ITV_ME_SEQNO_MASK 0x000f0000 /* ME should update every ~200ms */
+#define   ITV_ME_SEQNO_MASK 0x00ff0000 /* ME should update every ~200ms */
 #define   ITV_ME_SEQNO_SHIFT (16)
 #define   ITV_MCH_TEMP_MASK 0x0000ff00
 #define   ITV_MCH_TEMP_SHIFT (8)
@@ -325,6 +324,7 @@ struct ips_driver {
 	bool gpu_preferred;
 	bool poll_turbo_status;
 	bool second_cpu;
+	bool turbo_toggle_allowed;
 	struct ips_mcp_limits *limits;
 
 	/* Optional MCH interfaces for if i915 is in use */
@@ -415,7 +415,7 @@ static void ips_cpu_lower(struct ips_driver *ips)
 	new_limit = cur_limit - 8; /* 1W decrease */
 
 	/* Clamp to SKU TDP limit */
-	if (((new_limit * 10) / 8) < (ips->orig_turbo_limit & TURBO_TDP_MASK))
+	if (new_limit  < (ips->orig_turbo_limit & TURBO_TDP_MASK))
 		new_limit = ips->orig_turbo_limit & TURBO_TDP_MASK;
 
 	thm_writew(THM_MPCPC, (new_limit * 10) / 8);
@@ -461,7 +461,8 @@ static void ips_enable_cpu_turbo(struct ips_driver *ips)
 	if (ips->__cpu_turbo_on)
 		return;
 
-	on_each_cpu(do_enable_cpu_turbo, ips, 1);
+	if (ips->turbo_toggle_allowed)
+		on_each_cpu(do_enable_cpu_turbo, ips, 1);
 
 	ips->__cpu_turbo_on = true;
 }
@@ -498,7 +499,8 @@ static void ips_disable_cpu_turbo(struct ips_driver *ips)
 	if (!ips->__cpu_turbo_on)
 		return;
 
-	on_each_cpu(do_disable_cpu_turbo, ips, 1);
+	if (ips->turbo_toggle_allowed)
+		on_each_cpu(do_disable_cpu_turbo, ips, 1);
 
 	ips->__cpu_turbo_on = false;
 }
@@ -598,17 +600,29 @@ static bool mcp_exceeded(struct ips_driver *ips)
 {
 	unsigned long flags;
 	bool ret = false;
+	u32 temp_limit;
+	u32 avg_power;
+	const char *msg = "MCP limit exceeded: ";
 
 	spin_lock_irqsave(&ips->turbo_status_lock, flags);
-	if (ips->mcp_avg_temp > (ips->mcp_temp_limit * 100))
-		ret = true;
-	if (ips->cpu_avg_power + ips->mch_avg_power > ips->mcp_power_limit)
+
+	temp_limit = ips->mcp_temp_limit * 100;
+	if (ips->mcp_avg_temp > temp_limit) {
+		dev_info(&ips->dev->dev,
+			"%sAvg temp %u, limit %u\n", msg, ips->mcp_avg_temp,
+			temp_limit);
 		ret = true;
-	spin_unlock_irqrestore(&ips->turbo_status_lock, flags);
+	}
 
-	if (ret)
+	avg_power = ips->cpu_avg_power + ips->mch_avg_power;
+	if (avg_power > ips->mcp_power_limit) {
 		dev_info(&ips->dev->dev,
-			 "MCP power or thermal limit exceeded\n");
+			"%sAvg power %u, limit %u\n", msg, avg_power,
+			ips->mcp_power_limit);
+		ret = true;
+	}
+
+	spin_unlock_irqrestore(&ips->turbo_status_lock, flags);
 
 	return ret;
 }
@@ -662,6 +676,27 @@ static bool mch_exceeded(struct ips_driver *ips)
 	return ret;
 }
 
+/**
+ * verify_limits - verify BIOS provided limits
+ * @ips: IPS structure
+ *
+ * BIOS can optionally provide non-default limits for power and temp.  Check
+ * them here and use the defaults if the BIOS values are not provided or
+ * are otherwise unusable.
+ */
+static void verify_limits(struct ips_driver *ips)
+{
+	if (ips->mcp_power_limit < ips->limits->mcp_power_limit ||
+	    ips->mcp_power_limit > 35000)
+		ips->mcp_power_limit = ips->limits->mcp_power_limit;
+
+	if (ips->mcp_temp_limit < ips->limits->core_temp_limit ||
+	    ips->mcp_temp_limit < ips->limits->mch_temp_limit ||
+	    ips->mcp_temp_limit > 150)
+		ips->mcp_temp_limit = min(ips->limits->core_temp_limit,
+					  ips->limits->mch_temp_limit);
+}
+
 /**
  * update_turbo_limits - get various limits & settings from regs
  * @ips: IPS driver struct
@@ -680,12 +715,21 @@ static void update_turbo_limits(struct ips_driver *ips)
 	u32 hts = thm_readl(THM_HTS);
 
 	ips->cpu_turbo_enabled = !(hts & HTS_PCTD_DIS);
-	ips->gpu_turbo_enabled = !(hts & HTS_GTD_DIS);
+	/* 
+	 * Disable turbo for now, until we can figure out why the power figures
+	 * are wrong
+	 */
+	ips->cpu_turbo_enabled = false;
+
+	if (ips->gpu_busy)
+		ips->gpu_turbo_enabled = !(hts & HTS_GTD_DIS);
+
 	ips->core_power_limit = thm_readw(THM_MPCPC);
 	ips->mch_power_limit = thm_readw(THM_MMGPC);
 	ips->mcp_temp_limit = thm_readw(THM_PTL);
 	ips->mcp_power_limit = thm_readw(THM_MPPC);
 
+	verify_limits(ips);
 	/* Ignore BIOS CPU vs GPU pref */
 }
 
@@ -858,7 +902,7 @@ static u32 get_cpu_power(struct ips_driver *ips, u32 *last, int period)
 	ret = (ret * 1000) / 65535;
 	*last = val;
 
-	return ret;
+	return 0;
 }
 
 static const u16 temp_decay_factor = 2;
@@ -940,7 +984,6 @@ static int ips_monitor(void *data)
 		kfree(mch_samples);
 		kfree(cpu_samples);
 		kfree(mchp_samples);
-		kthread_stop(ips->adjust);
 		return -ENOMEM;
 	}
 
@@ -948,7 +991,7 @@ static int ips_monitor(void *data)
 		ITV_ME_SEQNO_SHIFT;
 	seqno_timestamp = get_jiffies_64();
 
-	old_cpu_power = thm_readl(THM_CEC) / 65535;
+	old_cpu_power = thm_readl(THM_CEC);
 	schedule_timeout_interruptible(msecs_to_jiffies(IPS_SAMPLE_PERIOD));
 
 	/* Collect an initial average */
@@ -1150,11 +1193,18 @@ static irqreturn_t ips_irq_handler(int irq, void *arg)
 				STS_GPL_SHIFT;
 			/* ignore EC CPU vs GPU pref */
 			ips->cpu_turbo_enabled = !(sts & STS_PCTD_DIS);
-			ips->gpu_turbo_enabled = !(sts & STS_GTD_DIS);
+			/* 
+			 * Disable turbo for now, until we can figure
+			 * out why the power figures are wrong
+			 */
+			ips->cpu_turbo_enabled = false;
+			if (ips->gpu_busy)
+				ips->gpu_turbo_enabled = !(sts & STS_GTD_DIS);
 			ips->mcp_temp_limit = (sts & STS_PTL_MASK) >>
 				STS_PTL_SHIFT;
 			ips->mcp_power_limit = (tc1 & STS_PPL_MASK) >>
 				STS_PPL_SHIFT;
+			verify_limits(ips);
 			spin_unlock(&ips->turbo_status_lock);
 
 			thm_writeb(THM_SEC, SEC_ACK);
@@ -1333,8 +1383,10 @@ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
 	 * turbo manually or we'll get an illegal MSR access, even though
 	 * turbo will still be available.
 	 */
-	if (!(misc_en & IA32_MISC_TURBO_EN))
-		; /* add turbo MSR write allowed flag if necessary */
+	if (misc_en & IA32_MISC_TURBO_EN)
+		ips->turbo_toggle_allowed = true;
+	else
+		ips->turbo_toggle_allowed = false;
 
 	if (strstr(boot_cpu_data.x86_model_id, "CPU       M"))
 		limits = &ips_sv_limits;
@@ -1351,9 +1403,10 @@ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
 	tdp = turbo_power & TURBO_TDP_MASK;
 
 	/* Sanity check TDP against CPU */
-	if (limits->mcp_power_limit != (tdp / 8) * 1000) {
-		dev_warn(&ips->dev->dev, "Warning: CPU TDP doesn't match expected value (found %d, expected %d)\n",
-			 tdp / 8, limits->mcp_power_limit / 1000);
+	if (limits->core_power_limit != (tdp / 8) * 1000) {
+		dev_info(&ips->dev->dev, "CPU TDP doesn't match expected value (found %d, expected %d)\n",
+			 tdp / 8, limits->core_power_limit / 1000);
+		limits->core_power_limit = (tdp / 8) * 1000;
 	}
 
 out:
@@ -1390,7 +1443,7 @@ static bool ips_get_i915_syms(struct ips_driver *ips)
 	return true;
 
 out_put_busy:
-	symbol_put(i915_gpu_turbo_disable);
+	symbol_put(i915_gpu_busy);
 out_put_lower:
 	symbol_put(i915_gpu_lower);
 out_put_raise:
@@ -1532,22 +1585,27 @@ static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* Save turbo limits & ratios */
 	rdmsrl(TURBO_POWER_CURRENT_LIMIT, ips->orig_turbo_limit);
 
-	ips_enable_cpu_turbo(ips);
-	ips->cpu_turbo_enabled = true;
+	ips_disable_cpu_turbo(ips);
+	ips->cpu_turbo_enabled = false;
 
-	/* Set up the work queue and monitor/adjust threads */
-	ips->monitor = kthread_run(ips_monitor, ips, "ips-monitor");
-	if (IS_ERR(ips->monitor)) {
+	/* Create thermal adjust thread */
+	ips->adjust = kthread_create(ips_adjust, ips, "ips-adjust");
+	if (IS_ERR(ips->adjust)) {
 		dev_err(&dev->dev,
-			"failed to create thermal monitor thread, aborting\n");
+			"failed to create thermal adjust thread, aborting\n");
 		ret = -ENOMEM;
 		goto error_free_irq;
+
 	}
 
-	ips->adjust = kthread_create(ips_adjust, ips, "ips-adjust");
-	if (IS_ERR(ips->adjust)) {
+	/*
+	 * Set up the work queue and monitor thread. The monitor thread
+	 * will wake up ips_adjust thread.
+	 */
+	ips->monitor = kthread_run(ips_monitor, ips, "ips-monitor");
+	if (IS_ERR(ips->monitor)) {
 		dev_err(&dev->dev,
-			"failed to create thermal adjust thread, aborting\n");
+			"failed to create thermal monitor thread, aborting\n");
 		ret = -ENOMEM;
 		goto error_thread_cleanup;
 	}
@@ -1566,7 +1624,7 @@ static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return ret;
 
 error_thread_cleanup:
-	kthread_stop(ips->monitor);
+	kthread_stop(ips->adjust);
 error_free_irq:
 	free_irq(ips->dev->irq, ips);
 error_unmap:
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index e35ed128bdef..2d61186ad5a2 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -3093,7 +3093,8 @@ static const struct tpacpi_quirk tpacpi_hotkey_qtable[] __initconst = {
 	TPACPI_Q_IBM('1', 'D', TPACPI_HK_Q_INIMASK), /* X22, X23, X24 */
 };
 
-typedef u16 tpacpi_keymap_t[TPACPI_HOTKEY_MAP_LEN];
+typedef u16 tpacpi_keymap_entry_t;
+typedef tpacpi_keymap_entry_t tpacpi_keymap_t[TPACPI_HOTKEY_MAP_LEN];
 
 static int __init hotkey_init(struct ibm_init_struct *iibm)
 {
@@ -3230,7 +3231,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 	};
 
 #define TPACPI_HOTKEY_MAP_SIZE		sizeof(tpacpi_keymap_t)
-#define TPACPI_HOTKEY_MAP_TYPESIZE	sizeof(tpacpi_keymap_t[0])
+#define TPACPI_HOTKEY_MAP_TYPESIZE	sizeof(tpacpi_keymap_entry_t)
 
 	int res, i;
 	int status;
diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c
index df1fb53c09d2..a4be41614eeb 100644
--- a/drivers/regulator/ad5398.c
+++ b/drivers/regulator/ad5398.c
@@ -256,7 +256,6 @@ static int __devexit ad5398_remove(struct i2c_client *client)
 
 	regulator_unregister(chip->rdev);
 	kfree(chip);
-	i2c_set_clientdata(client, NULL);
 
 	return 0;
 }
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 422a709d271d..cc8b337b9119 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -700,7 +700,7 @@ static void print_constraints(struct regulator_dev *rdev)
 	    constraints->min_uA != constraints->max_uA) {
 		ret = _regulator_get_current_limit(rdev);
 		if (ret > 0)
-			count += sprintf(buf + count, "at %d uA ", ret / 1000);
+			count += sprintf(buf + count, "at %d mA ", ret / 1000);
 	}
 
 	if (constraints->valid_modes_mask & REGULATOR_MODE_FAST)
@@ -2302,8 +2302,10 @@ struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
 	dev_set_name(&rdev->dev, "regulator.%d",
 		     atomic_inc_return(&regulator_no) - 1);
 	ret = device_register(&rdev->dev);
-	if (ret != 0)
+	if (ret != 0) {
+		put_device(&rdev->dev);
 		goto clean;
+	}
 
 	dev_set_drvdata(&rdev->dev, rdev);
 
diff --git a/drivers/regulator/isl6271a-regulator.c b/drivers/regulator/isl6271a-regulator.c
index d61ecb885a8c..b8cc6389a541 100644
--- a/drivers/regulator/isl6271a-regulator.c
+++ b/drivers/regulator/isl6271a-regulator.c
@@ -191,8 +191,6 @@ static int __devexit isl6271a_remove(struct i2c_client *i2c)
 	struct isl_pmic *pmic = i2c_get_clientdata(i2c);
 	int i;
 
-	i2c_set_clientdata(i2c, NULL);
-
 	for (i = 0; i < 3; i++)
 		regulator_unregister(pmic->rdev[i]);
 
diff --git a/drivers/regulator/max8649.c b/drivers/regulator/max8649.c
index 4520ace3f7e7..6b60a9c0366b 100644
--- a/drivers/regulator/max8649.c
+++ b/drivers/regulator/max8649.c
@@ -330,7 +330,7 @@ static int __devinit max8649_regulator_probe(struct i2c_client *client,
 		/* set external clock frequency */
 		info->extclk_freq = pdata->extclk_freq;
 		max8649_set_bits(info->i2c, MAX8649_SYNC, MAX8649_EXT_MASK,
-				 info->extclk_freq);
+				 info->extclk_freq << 6);
 	}
 
 	if (pdata->ramp_timing) {
diff --git a/drivers/rtc/rtc-ab3100.c b/drivers/rtc/rtc-ab3100.c
index d26780ea254b..261a07e0fb24 100644
--- a/drivers/rtc/rtc-ab3100.c
+++ b/drivers/rtc/rtc-ab3100.c
@@ -235,6 +235,7 @@ static int __init ab3100_rtc_probe(struct platform_device *pdev)
 		err = PTR_ERR(rtc);
 		return err;
 	}
+	platform_set_drvdata(pdev, rtc);
 
 	return 0;
 }
@@ -244,6 +245,7 @@ static int __exit ab3100_rtc_remove(struct platform_device *pdev)
 	struct rtc_device *rtc = platform_get_drvdata(pdev);
 
 	rtc_device_unregister(rtc);
+	platform_set_drvdata(pdev, NULL);
 	return 0;
 }
 
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 9daed8db83d3..9de8516e3531 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -268,7 +268,6 @@ out_irq:
 		free_irq(client->irq, client);
 
 out_free:
-	i2c_set_clientdata(client, NULL);
 	kfree(ds3232);
 	return ret;
 }
@@ -287,7 +286,6 @@ static int __devexit ds3232_remove(struct i2c_client *client)
 	}
 
 	rtc_device_unregister(ds3232->rtc);
-	i2c_set_clientdata(client, NULL);
 	kfree(ds3232);
 	return 0;
 }
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index a0d3ec89d412..f57a87f4ae96 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -310,11 +310,6 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	s3c_rtc_setaie(alrm->enabled);
 
-	if (alrm->enabled)
-		enable_irq_wake(s3c_rtc_alarmno);
-	else
-		disable_irq_wake(s3c_rtc_alarmno);
-
 	return 0;
 }
 
@@ -587,6 +582,10 @@ static int s3c_rtc_suspend(struct platform_device *pdev, pm_message_t state)
 		ticnt_en_save &= S3C64XX_RTCCON_TICEN;
 	}
 	s3c_rtc_enable(pdev, 0);
+
+	if (device_may_wakeup(&pdev->dev))
+		enable_irq_wake(s3c_rtc_alarmno);
+
 	return 0;
 }
 
@@ -600,6 +599,10 @@ static int s3c_rtc_resume(struct platform_device *pdev)
 		tmp = readb(s3c_rtc_base + S3C2410_RTCCON);
 		writeb(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON);
 	}
+
+	if (device_may_wakeup(&pdev->dev))
+		disable_irq_wake(s3c_rtc_alarmno);
+
 	return 0;
 }
 #else
diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c
index 6edf20b62de5..2c7d2d9be4d0 100644
--- a/drivers/s390/net/ctcm_main.c
+++ b/drivers/s390/net/ctcm_main.c
@@ -1154,7 +1154,7 @@ static struct net_device *ctcm_init_netdevice(struct ctcm_priv *priv)
 				dev_fsm, dev_fsm_len, GFP_KERNEL);
 	if (priv->fsm == NULL) {
 		CTCMY_DBF_DEV(SETUP, dev, "init_fsm error");
-		kfree(dev);
+		free_netdev(dev);
 		return NULL;
 	}
 	fsm_newstate(priv->fsm, DEV_STATE_STOPPED);
@@ -1165,7 +1165,7 @@ static struct net_device *ctcm_init_netdevice(struct ctcm_priv *priv)
 		grp = ctcmpc_init_mpc_group(priv);
 		if (grp == NULL) {
 			MPC_DBF_DEV(SETUP, dev, "init_mpc_group error");
-			kfree(dev);
+			free_netdev(dev);
 			return NULL;
 		}
 		tasklet_init(&grp->mpc_tasklet2,
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index ad0ed212db4a..348fba0a8976 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -1046,13 +1046,13 @@ int scsi_get_vpd_page(struct scsi_device *sdev, u8 page, unsigned char *buf,
 
 	/* If the user actually wanted this page, we can skip the rest */
 	if (page == 0)
-		return -EINVAL;
+		return 0;
 
 	for (i = 0; i < min((int)buf[3], buf_len - 4); i++)
 		if (buf[i + 4] == page)
 			goto found;
 
-	if (i < buf[3] && i > buf_len)
+	if (i < buf[3] && i >= buf_len - 4)
 		/* ran off the end of the buffer, give us benefit of doubt */
 		goto found;
 	/* The device claims it doesn't support the requested page */
diff --git a/drivers/serial/amba-pl010.c b/drivers/serial/amba-pl010.c
index 50441ffe8e38..2904aa044126 100644
--- a/drivers/serial/amba-pl010.c
+++ b/drivers/serial/amba-pl010.c
@@ -472,14 +472,9 @@ pl010_set_termios(struct uart_port *port, struct ktermios *termios,
 	spin_unlock_irqrestore(&uap->port.lock, flags);
 }
 
-static void pl010_set_ldisc(struct uart_port *port)
+static void pl010_set_ldisc(struct uart_port *port, int new)
 {
-	int line = port->line;
-
-	if (line >= port->state->port.tty->driver->num)
-		return;
-
-	if (port->state->port.tty->ldisc->ops->num == N_PPS) {
+	if (new == N_PPS) {
 		port->flags |= UPF_HARDPPS_CD;
 		pl010_enable_ms(port);
 	} else
diff --git a/drivers/serial/ioc3_serial.c b/drivers/serial/ioc3_serial.c
index 93de907b1208..800c54602339 100644
--- a/drivers/serial/ioc3_serial.c
+++ b/drivers/serial/ioc3_serial.c
@@ -2044,6 +2044,7 @@ ioc3uart_probe(struct ioc3_submodule *is, struct ioc3_driver_data *idd)
 		if (!port) {
 			printk(KERN_WARNING
 			       "IOC3 serial memory not available for port\n");
+			ret = -ENOMEM;
 			goto out4;
 		}
 		spin_lock_init(&port->ip_lock);
diff --git a/drivers/serial/mfd.c b/drivers/serial/mfd.c
index bc9af503907f..5dff45c76d32 100644
--- a/drivers/serial/mfd.c
+++ b/drivers/serial/mfd.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/sysrq.h>
+#include <linux/slab.h>
 #include <linux/serial_reg.h>
 #include <linux/circ_buf.h>
 #include <linux/delay.h>
@@ -1423,7 +1424,6 @@ static void hsu_global_init(void)
 	}
 
 	phsu = hsu;
-
 	hsu_debugfs_init(hsu);
 	return;
 
@@ -1435,18 +1435,20 @@ err_free_region:
 
 static void serial_hsu_remove(struct pci_dev *pdev)
 {
-	struct hsu_port *hsu;
-	int i;
+	void *priv = pci_get_drvdata(pdev);
+	struct uart_hsu_port *up;
 
-	hsu = pci_get_drvdata(pdev);
-	if (!hsu)
+	if (!priv)
 		return;
 
-	for (i = 0; i < 3; i++)
-		uart_remove_one_port(&serial_hsu_reg, &hsu->port[i].port);
+	/* For port 0/1/2, priv is the address of uart_hsu_port */
+	if (pdev->device != 0x081E) {
+		up = priv;
+		uart_remove_one_port(&serial_hsu_reg, &up->port);
+	}
 
 	pci_set_drvdata(pdev, NULL);
-	free_irq(hsu->irq, hsu);
+	free_irq(pdev->irq, priv);
 	pci_disable_device(pdev);
 }
 
diff --git a/drivers/serial/mrst_max3110.c b/drivers/serial/mrst_max3110.c
index f6ad1ecbff79..51c15f58e01e 100644
--- a/drivers/serial/mrst_max3110.c
+++ b/drivers/serial/mrst_max3110.c
@@ -29,6 +29,7 @@
 
 #include <linux/module.h>
 #include <linux/ioport.h>
+#include <linux/irq.h>
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/sysrq.h>
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 0bcf4c1601a2..b5a78a1f4421 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -23,6 +23,7 @@
 #include <linux/init.h>
 #include <linux/cache.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/mod_devicetable.h>
 #include <linux/spi/spi.h>
@@ -86,6 +87,10 @@ static int spi_match_device(struct device *dev, struct device_driver *drv)
 	const struct spi_device	*spi = to_spi_device(dev);
 	const struct spi_driver	*sdrv = to_spi_driver(drv);
 
+	/* Attempt an OF style match */
+	if (of_driver_match_device(dev, drv))
+		return 1;
+
 	if (sdrv->id_table)
 		return !!spi_match_id(sdrv->id_table, spi);
 
diff --git a/drivers/spi/spi_gpio.c b/drivers/spi/spi_gpio.c
index e24a63498acb..63e51b011d50 100644
--- a/drivers/spi/spi_gpio.c
+++ b/drivers/spi/spi_gpio.c
@@ -350,7 +350,7 @@ static int __init spi_gpio_probe(struct platform_device *pdev)
 	spi_gpio->bitbang.master = spi_master_get(master);
 	spi_gpio->bitbang.chipselect = spi_gpio_chipselect;
 
-	if ((master_flags & (SPI_MASTER_NO_RX | SPI_MASTER_NO_RX)) == 0) {
+	if ((master_flags & (SPI_MASTER_NO_TX | SPI_MASTER_NO_RX)) == 0) {
 		spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0;
 		spi_gpio->bitbang.txrx_word[SPI_MODE_1] = spi_gpio_txrx_word_mode1;
 		spi_gpio->bitbang.txrx_word[SPI_MODE_2] = spi_gpio_txrx_word_mode2;
diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index d31b57f7baaf..1dd86b835cd8 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -408,11 +408,17 @@ static void mpc8xxx_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi)
 
 	xfer_ofs = mspi->xfer_in_progress->len - mspi->count;
 
-	out_be32(&rx_bd->cbd_bufaddr, mspi->rx_dma + xfer_ofs);
+	if (mspi->rx_dma == mspi->dma_dummy_rx)
+		out_be32(&rx_bd->cbd_bufaddr, mspi->rx_dma);
+	else
+		out_be32(&rx_bd->cbd_bufaddr, mspi->rx_dma + xfer_ofs);
 	out_be16(&rx_bd->cbd_datlen, 0);
 	out_be16(&rx_bd->cbd_sc, BD_SC_EMPTY | BD_SC_INTRPT | BD_SC_WRAP);
 
-	out_be32(&tx_bd->cbd_bufaddr, mspi->tx_dma + xfer_ofs);
+	if (mspi->tx_dma == mspi->dma_dummy_tx)
+		out_be32(&tx_bd->cbd_bufaddr, mspi->tx_dma);
+	else
+		out_be32(&tx_bd->cbd_bufaddr, mspi->tx_dma + xfer_ofs);
 	out_be16(&tx_bd->cbd_datlen, xfer_len);
 	out_be16(&tx_bd->cbd_sc, BD_SC_READY | BD_SC_INTRPT | BD_SC_WRAP |
 				 BD_SC_LAST);
diff --git a/drivers/staging/batman-adv/hard-interface.c b/drivers/staging/batman-adv/hard-interface.c
index baa8b05b9e8d..6e973a79aa25 100644
--- a/drivers/staging/batman-adv/hard-interface.c
+++ b/drivers/staging/batman-adv/hard-interface.c
@@ -30,7 +30,6 @@
 #include "hash.h"
 
 #include <linux/if_arp.h>
-#include <linux/netfilter_bridge.h>
 
 #define MIN(x, y) ((x) < (y) ? (x) : (y))
 
@@ -431,11 +430,6 @@ out:
 	return NOTIFY_DONE;
 }
 
-static int batman_skb_recv_finish(struct sk_buff *skb)
-{
-	return NF_ACCEPT;
-}
-
 /* receive a packet with the batman ethertype coming on a hard
  * interface */
 int batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
@@ -456,13 +450,6 @@ int batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
 	if (atomic_read(&module_state) != MODULE_ACTIVE)
 		goto err_free;
 
-	/* if netfilter/ebtables wants to block incoming batman
-	 * packets then give them a chance to do so here */
-	ret = NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, dev, NULL,
-		      batman_skb_recv_finish);
-	if (ret != 1)
-		goto err_out;
-
 	/* packet should hold at least type and version */
 	if (unlikely(skb_headlen(skb) < 2))
 		goto err_free;
diff --git a/drivers/staging/batman-adv/send.c b/drivers/staging/batman-adv/send.c
index 055edee7b4e4..da3c82e47bbd 100644
--- a/drivers/staging/batman-adv/send.c
+++ b/drivers/staging/batman-adv/send.c
@@ -29,7 +29,6 @@
 #include "vis.h"
 #include "aggregation.h"
 
-#include <linux/netfilter_bridge.h>
 
 static void send_outstanding_bcast_packet(struct work_struct *work);
 
@@ -92,12 +91,9 @@ int send_skb_packet(struct sk_buff *skb,
 
 	/* dev_queue_xmit() returns a negative result on error.	 However on
 	 * congestion and traffic shaping, it drops and returns NET_XMIT_DROP
-	 * (which is > 0). This will not be treated as an error.
-	 * Also, if netfilter/ebtables wants to block outgoing batman
-	 * packets then giving them a chance to do so here */
+	 * (which is > 0). This will not be treated as an error. */
 
-	return NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
-		       dev_queue_xmit);
+	return dev_queue_xmit(skb);
 send_skb_err:
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
diff --git a/drivers/staging/ti-st/st.h b/drivers/staging/ti-st/st.h
index 9952579425b9..1b3060eb2921 100644
--- a/drivers/staging/ti-st/st.h
+++ b/drivers/staging/ti-st/st.h
@@ -80,5 +80,4 @@ struct st_proto_s {
 extern long st_register(struct st_proto_s *);
 extern long st_unregister(enum proto_type);
 
-extern struct platform_device *st_get_plat_device(void);
 #endif /* ST_H */
diff --git a/drivers/staging/ti-st/st_core.c b/drivers/staging/ti-st/st_core.c
index 063c9b1db1ab..b85d8bfdf600 100644
--- a/drivers/staging/ti-st/st_core.c
+++ b/drivers/staging/ti-st/st_core.c
@@ -38,7 +38,6 @@
 #include "st_ll.h"
 #include "st.h"
 
-#define VERBOSE
 /* strings to be used for rfkill entries and by
  * ST Core to be used for sysfs debug entry
  */
@@ -581,7 +580,7 @@ long st_register(struct st_proto_s *new_proto)
 	long err = 0;
 	unsigned long flags = 0;
 
-	st_kim_ref(&st_gdata);
+	st_kim_ref(&st_gdata, 0);
 	pr_info("%s(%d) ", __func__, new_proto->type);
 	if (st_gdata == NULL || new_proto == NULL || new_proto->recv == NULL
 	    || new_proto->reg_complete_cb == NULL) {
@@ -713,7 +712,7 @@ long st_unregister(enum proto_type type)
 
 	pr_debug("%s: %d ", __func__, type);
 
-	st_kim_ref(&st_gdata);
+	st_kim_ref(&st_gdata, 0);
 	if (type < ST_BT || type >= ST_MAX) {
 		pr_err(" protocol %d not supported", type);
 		return -EPROTONOSUPPORT;
@@ -767,7 +766,7 @@ long st_write(struct sk_buff *skb)
 #endif
 	long len;
 
-	st_kim_ref(&st_gdata);
+	st_kim_ref(&st_gdata, 0);
 	if (unlikely(skb == NULL || st_gdata == NULL
 		|| st_gdata->tty == NULL)) {
 		pr_err("data/tty unavailable to perform write");
@@ -818,7 +817,7 @@ static int st_tty_open(struct tty_struct *tty)
 	struct st_data_s *st_gdata;
 	pr_info("%s ", __func__);
 
-	st_kim_ref(&st_gdata);
+	st_kim_ref(&st_gdata, 0);
 	st_gdata->tty = tty;
 	tty->disc_data = st_gdata;
 
diff --git a/drivers/staging/ti-st/st_core.h b/drivers/staging/ti-st/st_core.h
index e0c32d149f5f..8601320a679e 100644
--- a/drivers/staging/ti-st/st_core.h
+++ b/drivers/staging/ti-st/st_core.h
@@ -117,7 +117,7 @@ int st_core_init(struct st_data_s **);
 void st_core_exit(struct st_data_s *);
 
 /* ask for reference from KIM */
-void st_kim_ref(struct st_data_s **);
+void st_kim_ref(struct st_data_s **, int);
 
 #define GPS_STUB_TEST
 #ifdef GPS_STUB_TEST
diff --git a/drivers/staging/ti-st/st_kim.c b/drivers/staging/ti-st/st_kim.c
index b4a6c7fdc4e6..9e99463f76e8 100644
--- a/drivers/staging/ti-st/st_kim.c
+++ b/drivers/staging/ti-st/st_kim.c
@@ -72,10 +72,25 @@ const unsigned char *protocol_names[] = {
 	PROTO_ENTRY(ST_GPS, "GPS"),
 };
 
+#define MAX_ST_DEVICES	3	/* Imagine 1 on each UART for now */
+struct platform_device *st_kim_devices[MAX_ST_DEVICES];
 
 /**********************************************************************/
 /* internal functions */
 
+/**
+ * st_get_plat_device -
+ *	function which returns the reference to the platform device
+ *	requested by id. As of now only 1 such device exists (id=0)
+ *	the context requesting for reference can get the id to be
+ *	requested by a. The protocol driver which is registering or
+ *	b. the tty device which is opened.
+ */
+static struct platform_device *st_get_plat_device(int id)
+{
+	return st_kim_devices[id];
+}
+
 /**
  * validate_firmware_response -
  *	function to return whether the firmware response was proper
@@ -353,7 +368,7 @@ void st_kim_chip_toggle(enum proto_type type, enum kim_gpio_state state)
 	struct kim_data_s	*kim_gdata;
 	pr_info(" %s ", __func__);
 
-	kim_pdev = st_get_plat_device();
+	kim_pdev = st_get_plat_device(0);
 	kim_gdata = dev_get_drvdata(&kim_pdev->dev);
 
 	if (kim_gdata->gpios[type] == -1) {
@@ -574,12 +589,12 @@ static int kim_toggle_radio(void *data, bool blocked)
  *	This would enable multiple such platform devices to exist
  *	on a given platform
  */
-void st_kim_ref(struct st_data_s **core_data)
+void st_kim_ref(struct st_data_s **core_data, int id)
 {
 	struct platform_device	*pdev;
 	struct kim_data_s	*kim_gdata;
 	/* get kim_gdata reference from platform device */
-	pdev = st_get_plat_device();
+	pdev = st_get_plat_device(id);
 	kim_gdata = dev_get_drvdata(&pdev->dev);
 	*core_data = kim_gdata->core_data;
 }
@@ -623,6 +638,7 @@ static int kim_probe(struct platform_device *pdev)
 	long *gpios = pdev->dev.platform_data;
 	struct kim_data_s	*kim_gdata;
 
+	st_kim_devices[pdev->id] = pdev;
 	kim_gdata = kzalloc(sizeof(struct kim_data_s), GFP_ATOMIC);
 	if (!kim_gdata) {
 		pr_err("no mem to allocate");
diff --git a/drivers/staging/tm6000/Kconfig b/drivers/staging/tm6000/Kconfig
index c725356cc346..de7ebb99d8f6 100644
--- a/drivers/staging/tm6000/Kconfig
+++ b/drivers/staging/tm6000/Kconfig
@@ -1,6 +1,6 @@
 config VIDEO_TM6000
 	tristate "TV Master TM5600/6000/6010 driver"
-	depends on VIDEO_DEV && I2C && INPUT && USB && EXPERIMENTAL
+	depends on VIDEO_DEV && I2C && INPUT && IR_CORE && USB && EXPERIMENTAL
 	select VIDEO_TUNER
 	select MEDIA_TUNER_XC2028
 	select MEDIA_TUNER_XC5000
diff --git a/drivers/staging/tm6000/tm6000-input.c b/drivers/staging/tm6000/tm6000-input.c
index 32f7a0af6938..54f7667cc706 100644
--- a/drivers/staging/tm6000/tm6000-input.c
+++ b/drivers/staging/tm6000/tm6000-input.c
@@ -46,7 +46,7 @@ MODULE_PARM_DESC(enable_ir, "enable ir (default is enable");
 	}
 
 struct tm6000_ir_poll_result {
-	u8 rc_data[4];
+	u16 rc_data;
 };
 
 struct tm6000_IR {
@@ -60,9 +60,9 @@ struct tm6000_IR {
 	int			polling;
 	struct delayed_work	work;
 	u8			wait:1;
+	u8			key:1;
 	struct urb		*int_urb;
 	u8			*urb_data;
-	u8			key:1;
 
 	int (*get_key) (struct tm6000_IR *, struct tm6000_ir_poll_result *);
 
@@ -122,13 +122,14 @@ static void tm6000_ir_urb_received(struct urb *urb)
 
 	if (urb->status != 0)
 		printk(KERN_INFO "not ready\n");
-	else if (urb->actual_length > 0)
+	else if (urb->actual_length > 0) {
 		memcpy(ir->urb_data, urb->transfer_buffer, urb->actual_length);
 
-	dprintk("data %02x %02x %02x %02x\n", ir->urb_data[0],
-	ir->urb_data[1], ir->urb_data[2], ir->urb_data[3]);
+		dprintk("data %02x %02x %02x %02x\n", ir->urb_data[0],
+			ir->urb_data[1], ir->urb_data[2], ir->urb_data[3]);
 
-	ir->key = 1;
+		ir->key = 1;
+	}
 
 	rc = usb_submit_urb(urb, GFP_ATOMIC);
 }
@@ -140,30 +141,47 @@ static int default_polling_getkey(struct tm6000_IR *ir,
 	int rc;
 	u8 buf[2];
 
-	if (ir->wait && !&dev->int_in) {
-		poll_result->rc_data[0] = 0xff;
+	if (ir->wait && !&dev->int_in)
 		return 0;
-	}
 
 	if (&dev->int_in) {
-		poll_result->rc_data[0] = ir->urb_data[0];
-		poll_result->rc_data[1] = ir->urb_data[1];
+		if (ir->ir.ir_type == IR_TYPE_RC5)
+			poll_result->rc_data = ir->urb_data[0];
+		else
+			poll_result->rc_data = ir->urb_data[0] | ir->urb_data[1] << 8;
 	} else {
 		tm6000_set_reg(dev, REQ_04_EN_DISABLE_MCU_INT, 2, 0);
 		msleep(10);
 		tm6000_set_reg(dev, REQ_04_EN_DISABLE_MCU_INT, 2, 1);
 		msleep(10);
 
-		rc = tm6000_read_write_usb(dev, USB_DIR_IN | USB_TYPE_VENDOR |
-		 USB_RECIP_DEVICE, REQ_02_GET_IR_CODE, 0, 0, buf, 1);
+		if (ir->ir.ir_type == IR_TYPE_RC5) {
+			rc = tm6000_read_write_usb(dev, USB_DIR_IN |
+				USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+				REQ_02_GET_IR_CODE, 0, 0, buf, 1);
 
-		msleep(10);
+			msleep(10);
 
-		dprintk("read data=%02x\n", buf[0]);
-		if (rc < 0)
-			return rc;
+			dprintk("read data=%02x\n", buf[0]);
+			if (rc < 0)
+				return rc;
 
-		poll_result->rc_data[0] = buf[0];
+			poll_result->rc_data = buf[0];
+		} else {
+			rc = tm6000_read_write_usb(dev, USB_DIR_IN |
+				USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+				REQ_02_GET_IR_CODE, 0, 0, buf, 2);
+
+			msleep(10);
+
+			dprintk("read data=%04x\n", buf[0] | buf[1] << 8);
+			if (rc < 0)
+				return rc;
+
+			poll_result->rc_data = buf[0] | buf[1] << 8;
+		}
+		if ((poll_result->rc_data & 0x00ff) != 0xff)
+			ir->key = 1;
 	}
 	return 0;
 }
@@ -180,12 +198,11 @@ static void tm6000_ir_handle_key(struct tm6000_IR *ir)
 		return;
 	}
 
-	dprintk("ir->get_key result data=%02x %02x\n",
-		poll_result.rc_data[0], poll_result.rc_data[1]);
+	dprintk("ir->get_key result data=%04x\n", poll_result.rc_data);
 
-	if (poll_result.rc_data[0] != 0xff && ir->key == 1) {
+	if (ir->key) {
 		ir_input_keydown(ir->input->input_dev, &ir->ir,
-			poll_result.rc_data[0] | poll_result.rc_data[1] << 8);
+				(u32)poll_result.rc_data);
 
 		ir_input_nokey(ir->input->input_dev, &ir->ir);
 		ir->key = 0;
diff --git a/drivers/staging/vt6655/wpactl.c b/drivers/staging/vt6655/wpactl.c
index 0142338bcafe..4bdb8362de82 100644
--- a/drivers/staging/vt6655/wpactl.c
+++ b/drivers/staging/vt6655/wpactl.c
@@ -766,9 +766,14 @@ static int wpa_set_associate(PSDevice pDevice,
     DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "wpa_ie_len = %d\n", param->u.wpa_associate.wpa_ie_len);
 
 
-	if (param->u.wpa_associate.wpa_ie &&
-	    copy_from_user(&abyWPAIE[0], param->u.wpa_associate.wpa_ie, param->u.wpa_associate.wpa_ie_len))
-	    return -EINVAL;
+	if (param->u.wpa_associate.wpa_ie_len) {
+		if (!param->u.wpa_associate.wpa_ie)
+			return -EINVAL;
+		if (param->u.wpa_associate.wpa_ie_len > sizeof(abyWPAIE))
+			return -EINVAL;
+		if (copy_from_user(&abyWPAIE[0], param->u.wpa_associate.wpa_ie, param->u.wpa_associate.wpa_ie_len))
+			return -EFAULT;
+	}
 
 	if (param->u.wpa_associate.mode == 1)
 	    pMgmt->eConfigMode = WMAC_CONFIG_IBSS_STA;
diff --git a/drivers/usb/core/Kconfig b/drivers/usb/core/Kconfig
index 7e594449600e..9eed5b52d9de 100644
--- a/drivers/usb/core/Kconfig
+++ b/drivers/usb/core/Kconfig
@@ -91,12 +91,12 @@ config USB_DYNAMIC_MINORS
 	  If you are unsure about this, say N here.
 
 config USB_SUSPEND
-	bool "USB runtime power management (suspend/resume and wakeup)"
+	bool "USB runtime power management (autosuspend) and wakeup"
 	depends on USB && PM_RUNTIME
 	help
 	  If you say Y here, you can use driver calls or the sysfs
-	  "power/level" file to suspend or resume individual USB
-	  peripherals and to enable or disable autosuspend (see
+	  "power/control" file to enable or disable autosuspend for
+	  individual USB peripherals (see
 	  Documentation/usb/power-management.txt for more details).
 
 	  Also, USB "remote wakeup" signaling is supported, whereby some
diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c
index f06f5dbc8cdc..1e6ccef2cf0c 100644
--- a/drivers/usb/core/file.c
+++ b/drivers/usb/core/file.c
@@ -159,9 +159,9 @@ void usb_major_cleanup(void)
 int usb_register_dev(struct usb_interface *intf,
 		     struct usb_class_driver *class_driver)
 {
-	int retval = -EINVAL;
+	int retval;
 	int minor_base = class_driver->minor_base;
-	int minor = 0;
+	int minor;
 	char name[20];
 	char *temp;
 
@@ -173,12 +173,17 @@ int usb_register_dev(struct usb_interface *intf,
 	 */
 	minor_base = 0;
 #endif
-	intf->minor = -1;
-
-	dbg ("looking for a minor, starting at %d", minor_base);
 
 	if (class_driver->fops == NULL)
-		goto exit;
+		return -EINVAL;
+	if (intf->minor >= 0)
+		return -EADDRINUSE;
+
+	retval = init_usb_class();
+	if (retval)
+		return retval;
+
+	dev_dbg(&intf->dev, "looking for a minor, starting at %d", minor_base);
 
 	down_write(&minor_rwsem);
 	for (minor = minor_base; minor < MAX_USB_MINORS; ++minor) {
@@ -186,20 +191,12 @@ int usb_register_dev(struct usb_interface *intf,
 			continue;
 
 		usb_minors[minor] = class_driver->fops;
-
-		retval = 0;
+		intf->minor = minor;
 		break;
 	}
 	up_write(&minor_rwsem);
-
-	if (retval)
-		goto exit;
-
-	retval = init_usb_class();
-	if (retval)
-		goto exit;
-
-	intf->minor = minor;
+	if (intf->minor < 0)
+		return -EXFULL;
 
 	/* create a usb class device for this usb interface */
 	snprintf(name, sizeof(name), class_driver->name, minor - minor_base);
@@ -213,11 +210,11 @@ int usb_register_dev(struct usb_interface *intf,
 				      "%s", temp);
 	if (IS_ERR(intf->usb_dev)) {
 		down_write(&minor_rwsem);
-		usb_minors[intf->minor] = NULL;
+		usb_minors[minor] = NULL;
+		intf->minor = -1;
 		up_write(&minor_rwsem);
 		retval = PTR_ERR(intf->usb_dev);
 	}
-exit:
 	return retval;
 }
 EXPORT_SYMBOL_GPL(usb_register_dev);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 844683e50383..9f0ce7de0e36 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1802,6 +1802,7 @@ free_interfaces:
 		intf->dev.groups = usb_interface_groups;
 		intf->dev.dma_mask = dev->dev.dma_mask;
 		INIT_WORK(&intf->reset_ws, __usb_queue_reset_device);
+		intf->minor = -1;
 		device_initialize(&intf->dev);
 		dev_set_name(&intf->dev, "%d-%s:%d.%d",
 			dev->bus->busnum, dev->devpath,
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 58b72d741d93..a1e8d273103f 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -119,6 +119,11 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
 			ehci->broken_periodic = 1;
 			ehci_info(ehci, "using broken periodic workaround\n");
 		}
+		if (pdev->device == 0x0806 || pdev->device == 0x0811
+				|| pdev->device == 0x0829) {
+			ehci_info(ehci, "disable lpm for langwell/penwell\n");
+			ehci->has_lpm = 0;
+		}
 		break;
 	case PCI_VENDOR_ID_TDI:
 		if (pdev->device == PCI_DEVICE_ID_TDI_EHCI) {
diff --git a/drivers/usb/musb/cppi_dma.c b/drivers/usb/musb/cppi_dma.c
index 59dc3d351b60..5ab5bb89bae3 100644
--- a/drivers/usb/musb/cppi_dma.c
+++ b/drivers/usb/musb/cppi_dma.c
@@ -322,6 +322,7 @@ cppi_channel_allocate(struct dma_controller *c,
 				index, transmit ? 'T' : 'R', cppi_ch);
 	cppi_ch->hw_ep = ep;
 	cppi_ch->channel.status = MUSB_DMA_STATUS_FREE;
+	cppi_ch->channel.max_len = 0x7fffffff;
 
 	DBG(4, "Allocate CPPI%d %cX\n", index, transmit ? 'T' : 'R');
 	return &cppi_ch->channel;
diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c
index c79a5e30d437..9e8639d4e862 100644
--- a/drivers/usb/musb/musb_debugfs.c
+++ b/drivers/usb/musb/musb_debugfs.c
@@ -195,15 +195,14 @@ static const struct file_operations musb_regdump_fops = {
 
 static int musb_test_mode_open(struct inode *inode, struct file *file)
 {
-	file->private_data = inode->i_private;
-
 	return single_open(file, musb_test_mode_show, inode->i_private);
 }
 
 static ssize_t musb_test_mode_write(struct file *file,
 		const char __user *ubuf, size_t count, loff_t *ppos)
 {
-	struct musb		*musb = file->private_data;
+	struct seq_file		*s = file->private_data;
+	struct musb		*musb = s->private;
 	u8			test = 0;
 	char			buf[18];
 
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index 6fca870e957e..d065e23f123e 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -300,6 +300,11 @@ static void txstate(struct musb *musb, struct musb_request *req)
 #ifndef	CONFIG_MUSB_PIO_ONLY
 	if (is_dma_capable() && musb_ep->dma) {
 		struct dma_controller	*c = musb->dma_controller;
+		size_t request_size;
+
+		/* setup DMA, then program endpoint CSR */
+		request_size = min_t(size_t, request->length - request->actual,
+					musb_ep->dma->max_len);
 
 		use_dma = (request->dma != DMA_ADDR_INVALID);
 
@@ -307,11 +312,6 @@ static void txstate(struct musb *musb, struct musb_request *req)
 
 #ifdef CONFIG_USB_INVENTRA_DMA
 		{
-			size_t request_size;
-
-			/* setup DMA, then program endpoint CSR */
-			request_size = min_t(size_t, request->length,
-						musb_ep->dma->max_len);
 			if (request_size < musb_ep->packet_sz)
 				musb_ep->dma->desired_mode = 0;
 			else
@@ -373,8 +373,8 @@ static void txstate(struct musb *musb, struct musb_request *req)
 		use_dma = use_dma && c->channel_program(
 				musb_ep->dma, musb_ep->packet_sz,
 				0,
-				request->dma,
-				request->length);
+				request->dma + request->actual,
+				request_size);
 		if (!use_dma) {
 			c->channel_release(musb_ep->dma);
 			musb_ep->dma = NULL;
@@ -386,8 +386,8 @@ static void txstate(struct musb *musb, struct musb_request *req)
 		use_dma = use_dma && c->channel_program(
 				musb_ep->dma, musb_ep->packet_sz,
 				request->zero,
-				request->dma,
-				request->length);
+				request->dma + request->actual,
+				request_size);
 #endif
 	}
 #endif
@@ -501,26 +501,14 @@ void musb_g_tx(struct musb *musb, u8 epnum)
 				request->zero = 0;
 			}
 
-			/* ... or if not, then complete it. */
-			musb_g_giveback(musb_ep, request, 0);
-
-			/*
-			 * Kickstart next transfer if appropriate;
-			 * the packet that just completed might not
-			 * be transmitted for hours or days.
-			 * REVISIT for double buffering...
-			 * FIXME revisit for stalls too...
-			 */
-			musb_ep_select(mbase, epnum);
-			csr = musb_readw(epio, MUSB_TXCSR);
-			if (csr & MUSB_TXCSR_FIFONOTEMPTY)
-				return;
-
-			request = musb_ep->desc ? next_request(musb_ep) : NULL;
-			if (!request) {
-				DBG(4, "%s idle now\n",
-					musb_ep->end_point.name);
-				return;
+			if (request->actual == request->length) {
+				musb_g_giveback(musb_ep, request, 0);
+				request = musb_ep->desc ? next_request(musb_ep) : NULL;
+				if (!request) {
+					DBG(4, "%s idle now\n",
+						musb_ep->end_point.name);
+					return;
+				}
 			}
 		}
 
@@ -568,11 +556,19 @@ static void rxstate(struct musb *musb, struct musb_request *req)
 {
 	const u8		epnum = req->epnum;
 	struct usb_request	*request = &req->request;
-	struct musb_ep		*musb_ep = &musb->endpoints[epnum].ep_out;
+	struct musb_ep		*musb_ep;
 	void __iomem		*epio = musb->endpoints[epnum].regs;
 	unsigned		fifo_count = 0;
-	u16			len = musb_ep->packet_sz;
+	u16			len;
 	u16			csr = musb_readw(epio, MUSB_RXCSR);
+	struct musb_hw_ep	*hw_ep = &musb->endpoints[epnum];
+
+	if (hw_ep->is_shared_fifo)
+		musb_ep = &hw_ep->ep_in;
+	else
+		musb_ep = &hw_ep->ep_out;
+
+	len = musb_ep->packet_sz;
 
 	/* We shouldn't get here while DMA is active, but we do... */
 	if (dma_channel_status(musb_ep->dma) == MUSB_DMA_STATUS_BUSY) {
@@ -647,8 +643,8 @@ static void rxstate(struct musb *musb, struct musb_request *req)
 	 */
 
 				csr |= MUSB_RXCSR_DMAENAB;
-#ifdef USE_MODE1
 				csr |= MUSB_RXCSR_AUTOCLEAR;
+#ifdef USE_MODE1
 				/* csr |= MUSB_RXCSR_DMAMODE; */
 
 				/* this special sequence (enabling and then
@@ -663,10 +659,11 @@ static void rxstate(struct musb *musb, struct musb_request *req)
 				if (request->actual < request->length) {
 					int transfer_size = 0;
 #ifdef USE_MODE1
-					transfer_size = min(request->length,
+					transfer_size = min(request->length - request->actual,
 							channel->max_len);
 #else
-					transfer_size = len;
+					transfer_size = min(request->length - request->actual,
+							(unsigned)len);
 #endif
 					if (transfer_size <= musb_ep->packet_sz)
 						musb_ep->dma->desired_mode = 0;
@@ -740,9 +737,15 @@ void musb_g_rx(struct musb *musb, u8 epnum)
 	u16			csr;
 	struct usb_request	*request;
 	void __iomem		*mbase = musb->mregs;
-	struct musb_ep		*musb_ep = &musb->endpoints[epnum].ep_out;
+	struct musb_ep		*musb_ep;
 	void __iomem		*epio = musb->endpoints[epnum].regs;
 	struct dma_channel	*dma;
+	struct musb_hw_ep	*hw_ep = &musb->endpoints[epnum];
+
+	if (hw_ep->is_shared_fifo)
+		musb_ep = &hw_ep->ep_in;
+	else
+		musb_ep = &hw_ep->ep_out;
 
 	musb_ep_select(mbase, epnum);
 
@@ -1081,7 +1084,7 @@ struct free_record {
 /*
  * Context: controller locked, IRQs blocked.
  */
-static void musb_ep_restart(struct musb *musb, struct musb_request *req)
+void musb_ep_restart(struct musb *musb, struct musb_request *req)
 {
 	DBG(3, "<== %s request %p len %u on hw_ep%d\n",
 		req->tx ? "TX/IN" : "RX/OUT",
diff --git a/drivers/usb/musb/musb_gadget.h b/drivers/usb/musb/musb_gadget.h
index c8b140325d82..572b1da7f2dc 100644
--- a/drivers/usb/musb/musb_gadget.h
+++ b/drivers/usb/musb/musb_gadget.h
@@ -105,4 +105,6 @@ extern void musb_gadget_cleanup(struct musb *);
 
 extern void musb_g_giveback(struct musb_ep *, struct usb_request *, int);
 
+extern void musb_ep_restart(struct musb *, struct musb_request *);
+
 #endif		/* __MUSB_GADGET_H */
diff --git a/drivers/usb/musb/musb_gadget_ep0.c b/drivers/usb/musb/musb_gadget_ep0.c
index 59bef8f3a358..6dd03f4c5f49 100644
--- a/drivers/usb/musb/musb_gadget_ep0.c
+++ b/drivers/usb/musb/musb_gadget_ep0.c
@@ -261,6 +261,7 @@ __acquires(musb->lock)
 					ctrlrequest->wIndex & 0x0f;
 				struct musb_ep		*musb_ep;
 				struct musb_hw_ep	*ep;
+				struct musb_request	*request;
 				void __iomem		*regs;
 				int			is_in;
 				u16			csr;
@@ -302,6 +303,14 @@ __acquires(musb->lock)
 					musb_writew(regs, MUSB_RXCSR, csr);
 				}
 
+				/* Maybe start the first request in the queue */
+				request = to_musb_request(
+						next_request(musb_ep));
+				if (!musb_ep->busy && request) {
+					DBG(3, "restarting the request\n");
+					musb_ep_restart(musb, request);
+				}
+
 				/* select ep0 again */
 				musb_ep_select(mbase, 0);
 				} break;
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 877d20b1dff9..9e65c47cc98b 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -660,6 +660,12 @@ static bool musb_tx_dma_program(struct dma_controller *dma,
 
 	qh->segsize = length;
 
+	/*
+	 * Ensure the data reaches to main memory before starting
+	 * DMA transfer
+	 */
+	wmb();
+
 	if (!dma->channel_program(channel, pkt_size, mode,
 			urb->transfer_dma + offset, length)) {
 		dma->channel_release(channel);
diff --git a/drivers/usb/otg/twl4030-usb.c b/drivers/usb/otg/twl4030-usb.c
index 05aaac1c3861..0bc97698af15 100644
--- a/drivers/usb/otg/twl4030-usb.c
+++ b/drivers/usb/otg/twl4030-usb.c
@@ -347,11 +347,20 @@ static void twl4030_i2c_access(struct twl4030_usb *twl, int on)
 	}
 }
 
-static void twl4030_phy_power(struct twl4030_usb *twl, int on)
+static void __twl4030_phy_power(struct twl4030_usb *twl, int on)
 {
-	u8 pwr;
+	u8 pwr = twl4030_usb_read(twl, PHY_PWR_CTRL);
+
+	if (on)
+		pwr &= ~PHY_PWR_PHYPWD;
+	else
+		pwr |= PHY_PWR_PHYPWD;
 
-	pwr = twl4030_usb_read(twl, PHY_PWR_CTRL);
+	WARN_ON(twl4030_usb_write_verify(twl, PHY_PWR_CTRL, pwr) < 0);
+}
+
+static void twl4030_phy_power(struct twl4030_usb *twl, int on)
+{
 	if (on) {
 		regulator_enable(twl->usb3v1);
 		regulator_enable(twl->usb1v8);
@@ -365,15 +374,13 @@ static void twl4030_phy_power(struct twl4030_usb *twl, int on)
 		twl_i2c_write_u8(TWL4030_MODULE_PM_RECEIVER, 0,
 							VUSB_DEDICATED2);
 		regulator_enable(twl->usb1v5);
-		pwr &= ~PHY_PWR_PHYPWD;
-		WARN_ON(twl4030_usb_write_verify(twl, PHY_PWR_CTRL, pwr) < 0);
+		__twl4030_phy_power(twl, 1);
 		twl4030_usb_write(twl, PHY_CLK_CTRL,
 				  twl4030_usb_read(twl, PHY_CLK_CTRL) |
 					(PHY_CLK_CTRL_CLOCKGATING_EN |
 						PHY_CLK_CTRL_CLK32K_EN));
-	} else  {
-		pwr |= PHY_PWR_PHYPWD;
-		WARN_ON(twl4030_usb_write_verify(twl, PHY_PWR_CTRL, pwr) < 0);
+	} else {
+		__twl4030_phy_power(twl, 0);
 		regulator_disable(twl->usb1v5);
 		regulator_disable(twl->usb1v8);
 		regulator_disable(twl->usb3v1);
@@ -387,19 +394,25 @@ static void twl4030_phy_suspend(struct twl4030_usb *twl, int controller_off)
 
 	twl4030_phy_power(twl, 0);
 	twl->asleep = 1;
+	dev_dbg(twl->dev, "%s\n", __func__);
 }
 
-static void twl4030_phy_resume(struct twl4030_usb *twl)
+static void __twl4030_phy_resume(struct twl4030_usb *twl)
 {
-	if (!twl->asleep)
-		return;
-
 	twl4030_phy_power(twl, 1);
 	twl4030_i2c_access(twl, 1);
 	twl4030_usb_set_mode(twl, twl->usb_mode);
 	if (twl->usb_mode == T2_USB_MODE_ULPI)
 		twl4030_i2c_access(twl, 0);
+}
+
+static void twl4030_phy_resume(struct twl4030_usb *twl)
+{
+	if (!twl->asleep)
+		return;
+	__twl4030_phy_resume(twl);
 	twl->asleep = 0;
+	dev_dbg(twl->dev, "%s\n", __func__);
 }
 
 static int twl4030_usb_ldo_init(struct twl4030_usb *twl)
@@ -408,8 +421,8 @@ static int twl4030_usb_ldo_init(struct twl4030_usb *twl)
 	twl_i2c_write_u8(TWL4030_MODULE_PM_MASTER, 0xC0, PROTECT_KEY);
 	twl_i2c_write_u8(TWL4030_MODULE_PM_MASTER, 0x0C, PROTECT_KEY);
 
-	/* put VUSB3V1 LDO in active state */
-	twl_i2c_write_u8(TWL4030_MODULE_PM_RECEIVER, 0, VUSB_DEDICATED2);
+	/* Keep VUSB3V1 LDO in sleep state until VBUS/ID change detected*/
+	/*twl_i2c_write_u8(TWL4030_MODULE_PM_RECEIVER, 0, VUSB_DEDICATED2);*/
 
 	/* input to VUSB3V1 LDO is from VBAT, not VBUS */
 	twl_i2c_write_u8(TWL4030_MODULE_PM_RECEIVER, 0x14, VUSB_DEDICATED1);
@@ -502,6 +515,26 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
 	return IRQ_HANDLED;
 }
 
+static void twl4030_usb_phy_init(struct twl4030_usb *twl)
+{
+	int status;
+
+	status = twl4030_usb_linkstat(twl);
+	if (status >= 0) {
+		if (status == USB_EVENT_NONE) {
+			__twl4030_phy_power(twl, 0);
+			twl->asleep = 1;
+		} else {
+			__twl4030_phy_resume(twl);
+			twl->asleep = 0;
+		}
+
+		blocking_notifier_call_chain(&twl->otg.notifier, status,
+				twl->otg.gadget);
+	}
+	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
+}
+
 static int twl4030_set_suspend(struct otg_transceiver *x, int suspend)
 {
 	struct twl4030_usb *twl = xceiv_to_twl(x);
@@ -550,7 +583,6 @@ static int __devinit twl4030_usb_probe(struct platform_device *pdev)
 	struct twl4030_usb_data *pdata = pdev->dev.platform_data;
 	struct twl4030_usb	*twl;
 	int			status, err;
-	u8			pwr;
 
 	if (!pdata) {
 		dev_dbg(&pdev->dev, "platform_data not available\n");
@@ -569,10 +601,7 @@ static int __devinit twl4030_usb_probe(struct platform_device *pdev)
 	twl->otg.set_peripheral	= twl4030_set_peripheral;
 	twl->otg.set_suspend	= twl4030_set_suspend;
 	twl->usb_mode		= pdata->usb_mode;
-
-	pwr = twl4030_usb_read(twl, PHY_PWR_CTRL);
-
-	twl->asleep		= (pwr & PHY_PWR_PHYPWD);
+	twl->asleep = 1;
 
 	/* init spinlock for workqueue */
 	spin_lock_init(&twl->lock);
@@ -610,15 +639,10 @@ static int __devinit twl4030_usb_probe(struct platform_device *pdev)
 		return status;
 	}
 
-	/* The IRQ handler just handles changes from the previous states
-	 * of the ID and VBUS pins ... in probe() we must initialize that
-	 * previous state.  The easy way:  fake an IRQ.
-	 *
-	 * REVISIT:  a real IRQ might have happened already, if PREEMPT is
-	 * enabled.  Else the IRQ may not yet be configured or enabled,
-	 * because of scheduling delays.
+	/* Power down phy or make it work according to
+	 * current link state.
 	 */
-	twl4030_usb_irq(twl->irq, twl);
+	twl4030_usb_phy_init(twl);
 
 	dev_info(&pdev->dev, "Initialized TWL4030 USB module\n");
 	return 0;
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 30922a7e3347..aa665817a272 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -2024,6 +2024,9 @@ static int mos7720_ioctl(struct tty_struct *tty, struct file *file,
 
 	case TIOCGICOUNT:
 		cnow = mos7720_port->icount;
+
+		memset(&icount, 0, sizeof(struct serial_icounter_struct));
+
 		icount.cts = cnow.cts;
 		icount.dsr = cnow.dsr;
 		icount.rng = cnow.rng;
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 1c9b6e9b2386..1a42bc213799 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -2285,6 +2285,9 @@ static int mos7840_ioctl(struct tty_struct *tty, struct file *file,
 	case TIOCGICOUNT:
 		cnow = mos7840_port->icount;
 		smp_rmb();
+
+		memset(&icount, 0, sizeof(struct serial_icounter_struct));
+
 		icount.cts = cnow.cts;
 		icount.dsr = cnow.dsr;
 		icount.rng = cnow.rng;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 29e850a7a2f9..7c8008225ee3 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -243,7 +243,7 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	int r, nlogs = 0;
 
 	while (datalen > 0) {
-		if (unlikely(headcount >= VHOST_NET_MAX_SG)) {
+		if (unlikely(seg >= VHOST_NET_MAX_SG)) {
 			r = -ENOBUFS;
 			goto err;
 		}
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c579dcc9200c..dd3d6f7406f8 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -858,11 +858,12 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		if (r < 0)
 			return r;
 		len -= l;
-		if (!len)
+		if (!len) {
+			if (vq->log_ctx)
+				eventfd_signal(vq->log_ctx, 1);
 			return 0;
+		}
 	}
-	if (vq->log_ctx)
-		eventfd_signal(vq->log_ctx, 1);
 	/* Length written exceeds what we have stored. This is a bug. */
 	BUG();
 	return 0;
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 84f842331dfa..7ccc967831f0 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -3508,7 +3508,7 @@ static void fbcon_exit(void)
 	softback_buf = 0UL;
 
 	for (i = 0; i < FB_MAX; i++) {
-		int pending;
+		int pending = 0;
 
 		mapped = 0;
 		info = registered_fb[i];
@@ -3516,7 +3516,8 @@ static void fbcon_exit(void)
 		if (info == NULL)
 			continue;
 
-		pending = cancel_work_sync(&info->queue);
+		if (info->queue.func)
+			pending = cancel_work_sync(&info->queue);
 		DPRINTK("fbcon: %s pending work\n", (pending ? "canceled" :
 			"no"));
 
diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 815f84b07933..70477c2e4b61 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -13,7 +13,7 @@
 #include <linux/platform_device.h>
 #include <linux/screen_info.h>
 #include <linux/dmi.h>
-
+#include <linux/pci.h>
 #include <video/vga.h>
 
 static struct fb_var_screeninfo efifb_defined __devinitdata = {
@@ -39,17 +39,31 @@ enum {
 	M_I20,		/* 20-Inch iMac */
 	M_I20_SR,	/* 20-Inch iMac (Santa Rosa) */
 	M_I24,		/* 24-Inch iMac */
+	M_I24_8_1,	/* 24-Inch iMac, 8,1th gen */
+	M_I24_10_1,	/* 24-Inch iMac, 10,1th gen */
+	M_I27_11_1,	/* 27-Inch iMac, 11,1th gen */
 	M_MINI,		/* Mac Mini */
+	M_MINI_3_1,	/* Mac Mini, 3,1th gen */
+	M_MINI_4_1,	/* Mac Mini, 4,1th gen */
 	M_MB,		/* MacBook */
 	M_MB_2,		/* MacBook, 2nd rev. */
 	M_MB_3,		/* MacBook, 3rd rev. */
+	M_MB_5_1,	/* MacBook, 5th rev. */
+	M_MB_6_1,	/* MacBook, 6th rev. */
+	M_MB_7_1,	/* MacBook, 7th rev. */
 	M_MB_SR,	/* MacBook, 2nd gen, (Santa Rosa) */
 	M_MBA,		/* MacBook Air */
 	M_MBP,		/* MacBook Pro */
 	M_MBP_2,	/* MacBook Pro 2nd gen */
+	M_MBP_2_2,	/* MacBook Pro 2,2nd gen */
 	M_MBP_SR,	/* MacBook Pro (Santa Rosa) */
 	M_MBP_4,	/* MacBook Pro, 4th gen */
 	M_MBP_5_1,    /* MacBook Pro, 5,1th gen */
+	M_MBP_5_2,	/* MacBook Pro, 5,2th gen */
+	M_MBP_5_3,	/* MacBook Pro, 5,3rd gen */
+	M_MBP_6_1,	/* MacBook Pro, 6,1th gen */
+	M_MBP_6_2,	/* MacBook Pro, 6,2th gen */
+	M_MBP_7_1,	/* MacBook Pro, 7,1th gen */
 	M_UNKNOWN	/* placeholder */
 };
 
@@ -64,14 +78,28 @@ static struct efifb_dmi_info {
 	[M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050 }, /* guess */
 	[M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050 },
 	[M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200 }, /* guess */
+	[M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200 },
+	[M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080 },
+	[M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440 },
 	[M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768 },
+	[M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768 },
+	[M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200 },
 	[M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800 },
+	[M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800 },
+	[M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800 },
+	[M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800 },
 	[M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800 },
 	[M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900 },
 	[M_MBP_2] = { "mbp2", 0, 0, 0, 0 }, /* placeholder */
+	[M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900 },
 	[M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900 },
 	[M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200 },
 	[M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900 },
+	[M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200 },
+	[M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900 },
+	[M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200 },
+	[M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050 },
+	[M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800 },
 	[M_UNKNOWN] = { NULL, 0, 0, 0, 0 }
 };
 
@@ -92,7 +120,12 @@ static const struct dmi_system_id dmi_system_table[] __initconst = {
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1),
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1),
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB),
 	/* At least one of these two will be right; maybe both? */
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB),
@@ -101,14 +134,23 @@ static const struct dmi_system_id dmi_system_table[] __initconst = {
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA),
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP),
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2),
 	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4),
 	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1),
 	{},
 };
 
@@ -116,7 +158,7 @@ static int set_system(const struct dmi_system_id *id)
 {
 	struct efifb_dmi_info *info = id->driver_data;
 	if (info->base == 0)
-		return -ENODEV;
+		return 0;
 
 	printk(KERN_INFO "efifb: dmi detected %s - framebuffer at %p "
 			 "(%dx%d, stride %d)\n", id->ident,
@@ -124,18 +166,55 @@ static int set_system(const struct dmi_system_id *id)
 			 info->stride);
 
 	/* Trust the bootloader over the DMI tables */
-	if (screen_info.lfb_base == 0)
+	if (screen_info.lfb_base == 0) {
+#if defined(CONFIG_PCI)
+		struct pci_dev *dev = NULL;
+		int found_bar = 0;
+#endif
 		screen_info.lfb_base = info->base;
-	if (screen_info.lfb_linelength == 0)
-		screen_info.lfb_linelength = info->stride;
-	if (screen_info.lfb_width == 0)
-		screen_info.lfb_width = info->width;
-	if (screen_info.lfb_height == 0)
-		screen_info.lfb_height = info->height;
-	if (screen_info.orig_video_isVGA == 0)
-		screen_info.orig_video_isVGA = VIDEO_TYPE_EFI;
 
-	return 0;
+#if defined(CONFIG_PCI)
+		/* make sure that the address in the table is actually on a
+		 * VGA device's PCI BAR */
+
+		for_each_pci_dev(dev) {
+			int i;
+			if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
+				continue;
+			for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+				resource_size_t start, end;
+
+				start = pci_resource_start(dev, i);
+				if (start == 0)
+					break;
+				end = pci_resource_end(dev, i);
+				if (screen_info.lfb_base >= start &&
+						screen_info.lfb_base < end) {
+					found_bar = 1;
+				}
+			}
+		}
+		if (!found_bar)
+			screen_info.lfb_base = 0;
+#endif
+	}
+	if (screen_info.lfb_base) {
+		if (screen_info.lfb_linelength == 0)
+			screen_info.lfb_linelength = info->stride;
+		if (screen_info.lfb_width == 0)
+			screen_info.lfb_width = info->width;
+		if (screen_info.lfb_height == 0)
+			screen_info.lfb_height = info->height;
+		if (screen_info.orig_video_isVGA == 0)
+			screen_info.orig_video_isVGA = VIDEO_TYPE_EFI;
+	} else {
+		screen_info.lfb_linelength = 0;
+		screen_info.lfb_width = 0;
+		screen_info.lfb_height = 0;
+		screen_info.orig_video_isVGA = 0;
+		return 0;
+	}
+	return 1;
 }
 
 static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green,
diff --git a/drivers/video/pxa168fb.c b/drivers/video/pxa168fb.c
index 5d786bd3e304..a31a77ff6f3d 100644
--- a/drivers/video/pxa168fb.c
+++ b/drivers/video/pxa168fb.c
@@ -298,8 +298,8 @@ static void set_dma_control0(struct pxa168fb_info *fbi)
 	 * Set bit to enable graphics DMA.
 	 */
 	x = readl(fbi->reg_base + LCD_SPU_DMA_CTRL0);
-	x |= fbi->active ? 0x00000100 : 0;
-	fbi->active = 0;
+	x &= ~CFG_GRA_ENA_MASK;
+	x |= fbi->active ? CFG_GRA_ENA(1) : CFG_GRA_ENA(0);
 
 	/*
 	 * If we are in a pseudo-color mode, we need to enable
diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c
index 559bf1727a2b..b52f8e4ef1fd 100644
--- a/drivers/video/sis/sis_main.c
+++ b/drivers/video/sis/sis_main.c
@@ -1701,6 +1701,9 @@ static int	sisfb_ioctl(struct fb_info *info, unsigned int cmd,
 		break;
 
 	   case FBIOGET_VBLANK:
+
+		memset(&sisvbblank, 0, sizeof(struct fb_vblank));
+
 		sisvbblank.count = 0;
 		sisvbblank.flags = sisfb_setupvbblankflags(ivideo, &sisvbblank.vcount, &sisvbblank.hcount);
 
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 29bac5118877..d409495876f1 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -755,7 +755,10 @@ int register_xenstore_notifier(struct notifier_block *nb)
 {
 	int ret = 0;
 
-	blocking_notifier_chain_register(&xenstore_chain, nb);
+	if (xenstored_ready > 0)
+		ret = nb->notifier_call(nb, 0, NULL);
+	else
+		blocking_notifier_chain_register(&xenstore_chain, nb);
 
 	return ret;
 }
@@ -769,7 +772,7 @@ EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
 
 void xenbus_probe(struct work_struct *unused)
 {
-	BUG_ON((xenstored_ready <= 0));
+	xenstored_ready = 1;
 
 	/* Enumerate devices in xenstore and watch for changes. */
 	xenbus_probe_devices(&xenbus_frontend);
@@ -835,8 +838,8 @@ static int __init xenbus_init(void)
 			xen_store_evtchn = xen_start_info->store_evtchn;
 			xen_store_mfn = xen_start_info->store_mfn;
 			xen_store_interface = mfn_to_virt(xen_store_mfn);
+			xenstored_ready = 1;
 		}
-		xenstored_ready = 1;
 	}
 
 	/* Initialize the interface to xenstore. */
diff --git a/fs/aio.c b/fs/aio.c
index 1320b2a05fb2..250b0a73c8a8 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -712,8 +712,16 @@ static ssize_t aio_run_iocb(struct kiocb *iocb)
 	 */
 	ret = retry(iocb);
 
-	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED)
+	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) {
+		/*
+		 * There's no easy way to restart the syscall since other AIO's
+		 * may be already running. Just fail this IO with EINTR.
+		 */
+		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
+			     ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK))
+			ret = -EINTR;
 		aio_complete(iocb, ret, 0);
+	}
 out:
 	spin_lock_irq(&ctx->ctx_lock);
 
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index f96eff04e11a..a6395bdb26ae 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -134,10 +134,6 @@ static int aout_core_dump(struct coredump_params *cprm)
 		if (!dump_write(file, dump_start, dump_size))
 			goto end_coredump;
 	}
-/* Finally dump the task struct.  Not be used by gdb, but could be useful */
-	set_fs(KERNEL_DS);
-	if (!dump_write(file, current, sizeof(*current)))
-		goto end_coredump;
 end_coredump:
 	set_fs(fs);
 	return has_dumped;
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index bc87b9c1d27e..9eb134ea6eb2 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -1,8 +1,11 @@
 config CEPH_FS
         tristate "Ceph distributed file system (EXPERIMENTAL)"
 	depends on INET && EXPERIMENTAL
+	select CEPH_LIB
 	select LIBCRC32C
 	select CRYPTO_AES
+	select CRYPTO
+	default n
 	help
 	  Choose Y or M here to include support for mounting the
 	  experimental Ceph distributed file system.  Ceph is an extremely
@@ -13,15 +16,3 @@ config CEPH_FS
 
 	  If unsure, say N.
 
-config CEPH_FS_PRETTYDEBUG
-	bool "Include file:line in ceph debug output"
-	depends on CEPH_FS
-	default n
-	help
-	  If you say Y here, debug output will include a filename and
-	  line to aid debugging.  This icnreases kernel size and slows
-	  execution slightly when debug call sites are enabled (e.g.,
-	  via CONFIG_DYNAMIC_DEBUG).
-
-	  If unsure, say N.
-
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index 278e1172600d..9e6c4f2e8ff1 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -8,15 +8,8 @@ obj-$(CONFIG_CEPH_FS) += ceph.o
 
 ceph-objs := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 	export.o caps.o snap.o xattr.o \
-	messenger.o msgpool.o buffer.o pagelist.o \
-	mds_client.o mdsmap.o \
-	mon_client.o \
-	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
-	debugfs.o \
-	auth.o auth_none.o \
-	crypto.o armor.o \
-	auth_x.o \
-	ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o
+	mds_client.o mdsmap.o strings.o ceph_frag.o \
+	debugfs.o
 
 else
 #Otherwise we were called directly from the command
diff --git a/fs/ceph/README b/fs/ceph/README
deleted file mode 100644
index 18352fab37c0..000000000000
--- a/fs/ceph/README
+++ /dev/null
@@ -1,20 +0,0 @@
-#
-# The following files are shared by (and manually synchronized
-# between) the Ceph userland and kernel client.
-#
-# userland                  kernel
-src/include/ceph_fs.h	    fs/ceph/ceph_fs.h
-src/include/ceph_fs.cc	    fs/ceph/ceph_fs.c
-src/include/msgr.h	    fs/ceph/msgr.h
-src/include/rados.h	    fs/ceph/rados.h
-src/include/ceph_strings.cc fs/ceph/ceph_strings.c
-src/include/ceph_frag.h	    fs/ceph/ceph_frag.h
-src/include/ceph_frag.cc    fs/ceph/ceph_frag.c
-src/include/ceph_hash.h	    fs/ceph/ceph_hash.h
-src/include/ceph_hash.cc    fs/ceph/ceph_hash.c
-src/crush/crush.c	    fs/ceph/crush/crush.c
-src/crush/crush.h	    fs/ceph/crush/crush.h
-src/crush/mapper.c	    fs/ceph/crush/mapper.c
-src/crush/mapper.h	    fs/ceph/crush/mapper.h
-src/crush/hash.h	    fs/ceph/crush/hash.h
-src/crush/hash.c	    fs/ceph/crush/hash.c
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4cfce1ee31fa..51bcc5ce3230 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
@@ -10,7 +10,8 @@
 #include <linux/task_io_accounting_ops.h>
 
 #include "super.h"
-#include "osd_client.h"
+#include "mds_client.h"
+#include <linux/ceph/osd_client.h>
 
 /*
  * Ceph address space ops.
@@ -193,7 +194,8 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 {
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+	struct ceph_osd_client *osdc = 
+		&ceph_inode_to_client(inode)->client->osdc;
 	int err = 0;
 	u64 len = PAGE_CACHE_SIZE;
 
@@ -265,7 +267,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+	struct ceph_osd_client *osdc =
+		&ceph_inode_to_client(inode)->client->osdc;
 	int rc = 0;
 	struct page **pages;
 	loff_t offset;
@@ -365,7 +368,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 {
 	struct inode *inode;
 	struct ceph_inode_info *ci;
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc;
 	struct ceph_osd_client *osdc;
 	loff_t page_off = page->index << PAGE_CACHE_SHIFT;
 	int len = PAGE_CACHE_SIZE;
@@ -383,8 +386,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	}
 	inode = page->mapping->host;
 	ci = ceph_inode(inode);
-	client = ceph_inode_to_client(inode);
-	osdc = &client->osdc;
+	fsc = ceph_inode_to_client(inode);
+	osdc = &fsc->client->osdc;
 
 	/* verify this is a writeable snap context */
 	snapc = (void *)page->private;
@@ -411,13 +414,13 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	if (i_size < page_off + len)
 		len = i_size - page_off;
 
-	dout("writepage %p page %p index %lu on %llu~%u\n",
-	     inode, page, page->index, page_off, len);
+	dout("writepage %p page %p index %lu on %llu~%u snapc %p\n",
+	     inode, page, page->index, page_off, len, snapc);
 
-	writeback_stat = atomic_long_inc_return(&client->writeback_count);
+	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
 	if (writeback_stat >
-	    CONGESTION_ON_THRESH(client->mount_args->congestion_kb))
-		set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);
+	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
+		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
 
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -496,7 +499,7 @@ static void writepages_finish(struct ceph_osd_request *req,
 	struct address_space *mapping = inode->i_mapping;
 	__s32 rc = -EIO;
 	u64 bytes = 0;
-	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	long writeback_stat;
 	unsigned issued = ceph_caps_issued(ci);
 
@@ -529,10 +532,10 @@ static void writepages_finish(struct ceph_osd_request *req,
 		WARN_ON(!PageUptodate(page));
 
 		writeback_stat =
-			atomic_long_dec_return(&client->writeback_count);
+			atomic_long_dec_return(&fsc->writeback_count);
 		if (writeback_stat <
-		    CONGESTION_OFF_THRESH(client->mount_args->congestion_kb))
-			clear_bdi_congested(&client->backing_dev_info,
+		    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+			clear_bdi_congested(&fsc->backing_dev_info,
 					    BLK_RW_ASYNC);
 
 		ceph_put_snap_context((void *)page->private);
@@ -569,13 +572,13 @@ static void writepages_finish(struct ceph_osd_request *req,
  * mempool.  we avoid the mempool if we can because req->r_num_pages
  * may be less than the maximum write size.
  */
-static void alloc_page_vec(struct ceph_client *client,
+static void alloc_page_vec(struct ceph_fs_client *fsc,
 			   struct ceph_osd_request *req)
 {
 	req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages,
 			       GFP_NOFS);
 	if (!req->r_pages) {
-		req->r_pages = mempool_alloc(client->wb_pagevec_pool, GFP_NOFS);
+		req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS);
 		req->r_pages_from_pool = 1;
 		WARN_ON(!req->r_pages);
 	}
@@ -590,7 +593,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc;
 	pgoff_t index, start, end;
 	int range_whole = 0;
 	int should_loop = 1;
@@ -617,13 +620,13 @@ static int ceph_writepages_start(struct address_space *mapping,
 	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
 	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
-	client = ceph_inode_to_client(inode);
-	if (client->mount_state == CEPH_MOUNT_SHUTDOWN) {
+	fsc = ceph_inode_to_client(inode);
+	if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
 		pr_warning("writepage_start %p on forced umount\n", inode);
 		return -EIO; /* we're in a forced umount, don't write! */
 	}
-	if (client->mount_args->wsize && client->mount_args->wsize < wsize)
-		wsize = client->mount_args->wsize;
+	if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
+		wsize = fsc->mount_options->wsize;
 	if (wsize < PAGE_CACHE_SIZE)
 		wsize = PAGE_CACHE_SIZE;
 	max_pages_ever = wsize >> PAGE_CACHE_SHIFT;
@@ -766,9 +769,10 @@ get_more_pages:
 			/* ok */
 			if (locked_pages == 0) {
 				/* prepare async write request */
-				offset = page->index << PAGE_CACHE_SHIFT;
+				offset = (unsigned long long)page->index
+					<< PAGE_CACHE_SHIFT;
 				len = wsize;
-				req = ceph_osdc_new_request(&client->osdc,
+				req = ceph_osdc_new_request(&fsc->client->osdc,
 					    &ci->i_layout,
 					    ceph_vino(inode),
 					    offset, &len,
@@ -781,7 +785,7 @@ get_more_pages:
 					    &inode->i_mtime, true, 1);
 				max_pages = req->r_num_pages;
 
-				alloc_page_vec(client, req);
+				alloc_page_vec(fsc, req);
 				req->r_callback = writepages_finish;
 				req->r_inode = inode;
 			}
@@ -793,10 +797,10 @@ get_more_pages:
 			     inode, page, page->index);
 
 			writeback_stat =
-			       atomic_long_inc_return(&client->writeback_count);
+			       atomic_long_inc_return(&fsc->writeback_count);
 			if (writeback_stat > CONGESTION_ON_THRESH(
-				    client->mount_args->congestion_kb)) {
-				set_bdi_congested(&client->backing_dev_info,
+				    fsc->mount_options->congestion_kb)) {
+				set_bdi_congested(&fsc->backing_dev_info,
 						  BLK_RW_ASYNC);
 			}
 
@@ -845,7 +849,7 @@ get_more_pages:
 		op->payload_len = cpu_to_le32(len);
 		req->r_request->hdr.data_len = cpu_to_le32(len);
 
-		ceph_osdc_start_request(&client->osdc, req, true);
+		ceph_osdc_start_request(&fsc->client->osdc, req, true);
 		req = NULL;
 
 		/* continue? */
@@ -914,7 +918,7 @@ static int ceph_update_writeable_page(struct file *file,
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	loff_t page_off = pos & PAGE_CACHE_MASK;
 	int pos_in_page = pos & ~PAGE_CACHE_MASK;
 	int end_in_page = pos_in_page + len;
@@ -1052,8 +1056,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  struct page *page, void *fsdata)
 {
 	struct inode *inode = file->f_dentry->d_inode;
-	struct ceph_client *client = ceph_inode_to_client(inode);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
 	int check_cap = 0;
 
@@ -1122,7 +1126,7 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct inode *inode = vma->vm_file->f_dentry->d_inode;
 	struct page *page = vmf->page;
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	loff_t off = page->index << PAGE_CACHE_SHIFT;
 	loff_t size, len;
 	int ret;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a2069b6680ae..98ab13e2b71d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -9,8 +9,9 @@
 #include <linux/writeback.h>
 
 #include "super.h"
-#include "decode.h"
-#include "messenger.h"
+#include "mds_client.h"
+#include <linux/ceph/decode.h>
+#include <linux/ceph/messenger.h>
 
 /*
  * Capability management
@@ -287,11 +288,11 @@ void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap)
 	spin_unlock(&mdsc->caps_list_lock);
 }
 
-void ceph_reservation_status(struct ceph_client *client,
+void ceph_reservation_status(struct ceph_fs_client *fsc,
 			     int *total, int *avail, int *used, int *reserved,
 			     int *min)
 {
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 
 	if (total)
 		*total = mdsc->caps_total_count;
@@ -399,7 +400,7 @@ static void __insert_cap_node(struct ceph_inode_info *ci,
 static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
 			       struct ceph_inode_info *ci)
 {
-	struct ceph_mount_args *ma = mdsc->client->mount_args;
+	struct ceph_mount_options *ma = mdsc->fsc->mount_options;
 
 	ci->i_hold_caps_min = round_jiffies(jiffies +
 					    ma->caps_wanted_delay_min * HZ);
@@ -515,7 +516,7 @@ int ceph_add_cap(struct inode *inode,
 		 unsigned seq, unsigned mseq, u64 realmino, int flags,
 		 struct ceph_cap_reservation *caps_reservation)
 {
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap *new_cap = NULL;
 	struct ceph_cap *cap;
@@ -814,7 +815,7 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
 		used |= CEPH_CAP_PIN;
 	if (ci->i_rd_ref)
 		used |= CEPH_CAP_FILE_RD;
-	if (ci->i_rdcache_ref || ci->i_rdcache_gen)
+	if (ci->i_rdcache_ref || ci->vfs_inode.i_data.nrpages)
 		used |= CEPH_CAP_FILE_CACHE;
 	if (ci->i_wr_ref)
 		used |= CEPH_CAP_FILE_WR;
@@ -873,7 +874,7 @@ void __ceph_remove_cap(struct ceph_cap *cap)
 	struct ceph_mds_session *session = cap->session;
 	struct ceph_inode_info *ci = cap->ci;
 	struct ceph_mds_client *mdsc =
-		&ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
 	int removed = 0;
 
 	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
@@ -1195,10 +1196,14 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
  * asynchronously back to the MDS once sync writes complete and dirty
  * data is written out.
  *
+ * Unless @again is true, skip cap_snaps that were already sent to
+ * the MDS (i.e., during this session).
+ *
  * Called under i_lock.  Takes s_mutex as needed.
  */
 void __ceph_flush_snaps(struct ceph_inode_info *ci,
-			struct ceph_mds_session **psession)
+			struct ceph_mds_session **psession,
+			int again)
 		__releases(ci->vfs_inode->i_lock)
 		__acquires(ci->vfs_inode->i_lock)
 {
@@ -1206,7 +1211,7 @@ void __ceph_flush_snaps(struct ceph_inode_info *ci,
 	int mds;
 	struct ceph_cap_snap *capsnap;
 	u32 mseq;
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_session *session = NULL; /* if session != NULL, we hold
 						    session->s_mutex */
 	u64 next_follows = 0;  /* keep track of how far we've gotten through the
@@ -1227,7 +1232,7 @@ retry:
 		 * pages to be written out.
 		 */
 		if (capsnap->dirty_pages || capsnap->writing)
-			continue;
+			break;
 
 		/*
 		 * if cap writeback already occurred, we should have dropped
@@ -1240,6 +1245,13 @@ retry:
 			dout("no auth cap (migrating?), doing nothing\n");
 			goto out;
 		}
+
+		/* only flush each capsnap once */
+		if (!again && !list_empty(&capsnap->flushing_item)) {
+			dout("already flushed %p, skipping\n", capsnap);
+			continue;
+		}
+
 		mds = ci->i_auth_cap->session->s_mds;
 		mseq = ci->i_auth_cap->mseq;
 
@@ -1276,8 +1288,8 @@ retry:
 			      &session->s_cap_snaps_flushing);
 		spin_unlock(&inode->i_lock);
 
-		dout("flush_snaps %p cap_snap %p follows %lld size %llu\n",
-		     inode, capsnap, next_follows, capsnap->size);
+		dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
+		     inode, capsnap, capsnap->follows, capsnap->flush_tid);
 		send_cap_msg(session, ceph_vino(inode).ino, 0,
 			     CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0,
 			     capsnap->dirty, 0, capsnap->flush_tid, 0, mseq,
@@ -1314,7 +1326,7 @@ static void ceph_flush_snaps(struct ceph_inode_info *ci)
 	struct inode *inode = &ci->vfs_inode;
 
 	spin_lock(&inode->i_lock);
-	__ceph_flush_snaps(ci, NULL);
+	__ceph_flush_snaps(ci, NULL, 0);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -1325,7 +1337,7 @@ static void ceph_flush_snaps(struct ceph_inode_info *ci)
 void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
 {
 	struct ceph_mds_client *mdsc =
-		&ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
 	struct inode *inode = &ci->vfs_inode;
 	int was = ci->i_dirty_caps;
 	int dirty = 0;
@@ -1367,7 +1379,7 @@ void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
 static int __mark_caps_flushing(struct inode *inode,
 				 struct ceph_mds_session *session)
 {
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int flushing;
 
@@ -1405,17 +1417,6 @@ static int __mark_caps_flushing(struct inode *inode,
 /*
  * try to invalidate mapping pages without blocking.
  */
-static int mapping_is_empty(struct address_space *mapping)
-{
-	struct page *page = find_get_page(mapping, 0);
-
-	if (!page)
-		return 1;
-
-	put_page(page);
-	return 0;
-}
-
 static int try_nonblocking_invalidate(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1425,7 +1426,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	invalidate_mapping_pages(&inode->i_data, 0, -1);
 	spin_lock(&inode->i_lock);
 
-	if (mapping_is_empty(&inode->i_data) &&
+	if (inode->i_data.nrpages == 0 &&
 	    invalidating_gen == ci->i_rdcache_gen) {
 		/* success. */
 		dout("try_nonblocking_invalidate %p success\n", inode);
@@ -1451,8 +1452,8 @@ static int try_nonblocking_invalidate(struct inode *inode)
 void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 		     struct ceph_mds_session *session)
 {
-	struct ceph_client *client = ceph_inode_to_client(&ci->vfs_inode);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
 	int file_wanted, used;
@@ -1477,7 +1478,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 
 	/* flush snaps first time around only */
 	if (!list_empty(&ci->i_cap_snaps))
-		__ceph_flush_snaps(ci, &session);
+		__ceph_flush_snaps(ci, &session, 0);
 	goto retry_locked;
 retry:
 	spin_lock(&inode->i_lock);
@@ -1522,7 +1523,7 @@ retry_locked:
 	 */
 	if ((!is_delayed || mdsc->stopping) &&
 	    ci->i_wrbuffer_ref == 0 &&               /* no dirty pages... */
-	    ci->i_rdcache_gen &&                     /* may have cached pages */
+	    inode->i_data.nrpages &&                 /* have cached pages */
 	    (file_wanted == 0 ||                     /* no open files */
 	     (revoking & (CEPH_CAP_FILE_CACHE|
 			  CEPH_CAP_FILE_LAZYIO))) && /*  or revoking cache */
@@ -1695,7 +1696,7 @@ ack:
 static int try_flush_caps(struct inode *inode, struct ceph_mds_session *session,
 			  unsigned *flush_tid)
 {
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int unlock_session = session ? 0 : 1;
 	int flushing = 0;
@@ -1861,7 +1862,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 				       caps_are_flushed(inode, flush_tid));
 	} else {
 		struct ceph_mds_client *mdsc =
-			&ceph_sb_to_client(inode->i_sb)->mdsc;
+			ceph_sb_to_client(inode->i_sb)->mdsc;
 
 		spin_lock(&inode->i_lock);
 		if (__ceph_caps_dirty(ci))
@@ -1894,7 +1895,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc,
 		if (cap && cap->session == session) {
 			dout("kick_flushing_caps %p cap %p capsnap %p\n", inode,
 			     cap, capsnap);
-			__ceph_flush_snaps(ci, &session);
+			__ceph_flush_snaps(ci, &session, 1);
 		} else {
 			pr_err("%p auth cap %p not mds%d ???\n", inode,
 			       cap, session->s_mds);
@@ -2272,7 +2273,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int mds = session->s_mds;
-	int seq = le32_to_cpu(grant->seq);
+	unsigned seq = le32_to_cpu(grant->seq);
+	unsigned issue_seq = le32_to_cpu(grant->issue_seq);
 	int newcaps = le32_to_cpu(grant->caps);
 	int issued, implemented, used, wanted, dirty;
 	u64 size = le64_to_cpu(grant->size);
@@ -2284,8 +2286,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 	int revoked_rdcache = 0;
 	int queue_invalidate = 0;
 
-	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
-	     inode, cap, mds, seq, ceph_cap_string(newcaps));
+	dout("handle_cap_grant inode %p cap %p mds%d seq %u/%u %s\n",
+	     inode, cap, mds, seq, issue_seq, ceph_cap_string(newcaps));
 	dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
 		inode->i_size);
 
@@ -2381,6 +2383,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 	}
 
 	cap->seq = seq;
+	cap->issue_seq = issue_seq;
 
 	/* file layout may have changed */
 	ci->i_layout = grant->layout;
@@ -2452,7 +2455,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 	__releases(inode->i_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	unsigned seq = le32_to_cpu(m->seq);
 	int dirty = le32_to_cpu(m->dirty);
 	int cleaned = 0;
@@ -2700,7 +2703,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		      struct ceph_msg *msg)
 {
 	struct ceph_mds_client *mdsc = session->s_mdsc;
-	struct super_block *sb = mdsc->client->sb;
+	struct super_block *sb = mdsc->fsc->sb;
 	struct inode *inode;
 	struct ceph_cap *cap;
 	struct ceph_mds_caps *h;
@@ -2763,15 +2766,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		if (op == CEPH_CAP_OP_IMPORT)
 			__queue_cap_release(session, vino.ino, cap_id,
 					    mseq, seq);
-
-		/*
-		 * send any full release message to try to move things
-		 * along for the mds (who clearly thinks we still have this
-		 * cap).
-		 */
-		ceph_add_cap_releases(mdsc, session);
-		ceph_send_cap_releases(mdsc, session);
-		goto done;
+		goto flush_cap_releases;
 	}
 
 	/* these will work even if we don't have a cap yet */
@@ -2799,7 +2794,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		dout(" no cap on %p ino %llx.%llx from mds%d\n",
 		     inode, ceph_ino(inode), ceph_snap(inode), mds);
 		spin_unlock(&inode->i_lock);
-		goto done;
+		goto flush_cap_releases;
 	}
 
 	/* note that each of these drops i_lock for us */
@@ -2823,6 +2818,17 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		       ceph_cap_op_name(op));
 	}
 
+	goto done;
+
+flush_cap_releases:
+	/*
+	 * send any full release message to try to move things
+	 * along for the mds (who clearly thinks we still have this
+	 * cap).
+	 */
+	ceph_add_cap_releases(mdsc, session);
+	ceph_send_cap_releases(mdsc, session);
+
 done:
 	mutex_unlock(&session->s_mutex);
 done_unlocked:
diff --git a/fs/ceph/ceph_frag.c b/fs/ceph/ceph_frag.c
index ab6cf35c4091..bdce8b1fbd06 100644
--- a/fs/ceph/ceph_frag.c
+++ b/fs/ceph/ceph_frag.c
@@ -1,7 +1,8 @@
 /*
  * Ceph 'frag' type
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
 int ceph_frag_compare(__u32 a, __u32 b)
 {
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6fd8b20a8611..7ae1b3d55b58 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/device.h>
 #include <linux/slab.h>
@@ -7,143 +7,49 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
 #include "super.h"
-#include "mds_client.h"
-#include "mon_client.h"
-#include "auth.h"
 
 #ifdef CONFIG_DEBUG_FS
 
-/*
- * Implement /sys/kernel/debug/ceph fun
- *
- * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
- *      .../osdmap      - current osdmap
- *      .../mdsmap      - current mdsmap
- *      .../monmap      - current monmap
- *      .../osdc        - active osd requests
- *      .../mdsc        - active mds requests
- *      .../monc        - mon client state
- *      .../dentry_lru  - dump contents of dentry lru
- *      .../caps        - expose cap (reservation) stats
- *      .../bdi         - symlink to ../../bdi/something
- */
-
-static struct dentry *ceph_debugfs_dir;
-
-static int monmap_show(struct seq_file *s, void *p)
-{
-	int i;
-	struct ceph_client *client = s->private;
-
-	if (client->monc.monmap == NULL)
-		return 0;
-
-	seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
-	for (i = 0; i < client->monc.monmap->num_mon; i++) {
-		struct ceph_entity_inst *inst =
-			&client->monc.monmap->mon_inst[i];
-
-		seq_printf(s, "\t%s%lld\t%s\n",
-			   ENTITY_NAME(inst->name),
-			   pr_addr(&inst->addr.in_addr));
-	}
-	return 0;
-}
+#include "mds_client.h"
 
 static int mdsmap_show(struct seq_file *s, void *p)
 {
 	int i;
-	struct ceph_client *client = s->private;
+	struct ceph_fs_client *fsc = s->private;
 
-	if (client->mdsc.mdsmap == NULL)
+	if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
 		return 0;
-	seq_printf(s, "epoch %d\n", client->mdsc.mdsmap->m_epoch);
-	seq_printf(s, "root %d\n", client->mdsc.mdsmap->m_root);
+	seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
 	seq_printf(s, "session_timeout %d\n",
-		       client->mdsc.mdsmap->m_session_timeout);
+		       fsc->mdsc->mdsmap->m_session_timeout);
 	seq_printf(s, "session_autoclose %d\n",
-		       client->mdsc.mdsmap->m_session_autoclose);
-	for (i = 0; i < client->mdsc.mdsmap->m_max_mds; i++) {
+		       fsc->mdsc->mdsmap->m_session_autoclose);
+	for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
 		struct ceph_entity_addr *addr =
-			&client->mdsc.mdsmap->m_info[i].addr;
-		int state = client->mdsc.mdsmap->m_info[i].state;
+			&fsc->mdsc->mdsmap->m_info[i].addr;
+		int state = fsc->mdsc->mdsmap->m_info[i].state;
 
-		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, pr_addr(&addr->in_addr),
+		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
+			       ceph_pr_addr(&addr->in_addr),
 			       ceph_mds_state_name(state));
 	}
 	return 0;
 }
 
-static int osdmap_show(struct seq_file *s, void *p)
-{
-	int i;
-	struct ceph_client *client = s->private;
-	struct rb_node *n;
-
-	if (client->osdc.osdmap == NULL)
-		return 0;
-	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
-	seq_printf(s, "flags%s%s\n",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
-		   " NEARFULL" : "",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
-		   " FULL" : "");
-	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
-		struct ceph_pg_pool_info *pool =
-			rb_entry(n, struct ceph_pg_pool_info, node);
-		seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
-			   pool->id, pool->v.pg_num, pool->pg_num_mask,
-			   pool->v.lpg_num, pool->lpg_num_mask);
-	}
-	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
-		struct ceph_entity_addr *addr =
-			&client->osdc.osdmap->osd_addr[i];
-		int state = client->osdc.osdmap->osd_state[i];
-		char sb[64];
-
-		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
-			   i, pr_addr(&addr->in_addr),
-			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
-			   ceph_osdmap_state_str(sb, sizeof(sb), state));
-	}
-	return 0;
-}
-
-static int monc_show(struct seq_file *s, void *p)
-{
-	struct ceph_client *client = s->private;
-	struct ceph_mon_generic_request *req;
-	struct ceph_mon_client *monc = &client->monc;
-	struct rb_node *rp;
-
-	mutex_lock(&monc->mutex);
-
-	if (monc->have_mdsmap)
-		seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
-	if (monc->have_osdmap)
-		seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
-	if (monc->want_next_osdmap)
-		seq_printf(s, "want next osdmap\n");
-
-	for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
-		__u16 op;
-		req = rb_entry(rp, struct ceph_mon_generic_request, node);
-		op = le16_to_cpu(req->request->hdr.type);
-		if (op == CEPH_MSG_STATFS)
-			seq_printf(s, "%lld statfs\n", req->tid);
-		else
-			seq_printf(s, "%lld unknown\n", req->tid);
-	}
-
-	mutex_unlock(&monc->mutex);
-	return 0;
-}
-
+/*
+ * mdsc debugfs
+ */
 static int mdsc_show(struct seq_file *s, void *p)
 {
-	struct ceph_client *client = s->private;
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct rb_node *rp;
 	int pathlen;
@@ -214,61 +120,12 @@ static int mdsc_show(struct seq_file *s, void *p)
 	return 0;
 }
 
-static int osdc_show(struct seq_file *s, void *pp)
-{
-	struct ceph_client *client = s->private;
-	struct ceph_osd_client *osdc = &client->osdc;
-	struct rb_node *p;
-
-	mutex_lock(&osdc->request_mutex);
-	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
-		struct ceph_osd_request *req;
-		struct ceph_osd_request_head *head;
-		struct ceph_osd_op *op;
-		int num_ops;
-		int opcode, olen;
-		int i;
-
-		req = rb_entry(p, struct ceph_osd_request, r_node);
-
-		seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
-			   req->r_osd ? req->r_osd->o_osd : -1,
-			   le32_to_cpu(req->r_pgid.pool),
-			   le16_to_cpu(req->r_pgid.ps));
-
-		head = req->r_request->front.iov_base;
-		op = (void *)(head + 1);
-
-		num_ops = le16_to_cpu(head->num_ops);
-		olen = le32_to_cpu(head->object_len);
-		seq_printf(s, "%.*s", olen,
-			   (const char *)(head->ops + num_ops));
-
-		if (req->r_reassert_version.epoch)
-			seq_printf(s, "\t%u'%llu",
-			   (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
-			   le64_to_cpu(req->r_reassert_version.version));
-		else
-			seq_printf(s, "\t");
-
-		for (i = 0; i < num_ops; i++) {
-			opcode = le16_to_cpu(op->op);
-			seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
-			op++;
-		}
-
-		seq_printf(s, "\n");
-	}
-	mutex_unlock(&osdc->request_mutex);
-	return 0;
-}
-
 static int caps_show(struct seq_file *s, void *p)
 {
-	struct ceph_client *client = s->private;
+	struct ceph_fs_client *fsc = s->private;
 	int total, avail, used, reserved, min;
 
-	ceph_reservation_status(client, &total, &avail, &used, &reserved, &min);
+	ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min);
 	seq_printf(s, "total\t\t%d\n"
 		   "avail\t\t%d\n"
 		   "used\t\t%d\n"
@@ -280,8 +137,8 @@ static int caps_show(struct seq_file *s, void *p)
 
 static int dentry_lru_show(struct seq_file *s, void *ptr)
 {
-	struct ceph_client *client = s->private;
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_dentry_info *di;
 
 	spin_lock(&mdsc->dentry_lru_lock);
@@ -295,199 +152,124 @@ static int dentry_lru_show(struct seq_file *s, void *ptr)
 	return 0;
 }
 
-#define DEFINE_SHOW_FUNC(name)						\
-static int name##_open(struct inode *inode, struct file *file)		\
-{									\
-	struct seq_file *sf;						\
-	int ret;							\
-									\
-	ret = single_open(file, name, NULL);				\
-	sf = file->private_data;					\
-	sf->private = inode->i_private;					\
-	return ret;							\
-}									\
-									\
-static const struct file_operations name##_fops = {			\
-	.open		= name##_open,					\
-	.read		= seq_read,					\
-	.llseek		= seq_lseek,					\
-	.release	= single_release,				\
-};
-
-DEFINE_SHOW_FUNC(monmap_show)
-DEFINE_SHOW_FUNC(mdsmap_show)
-DEFINE_SHOW_FUNC(osdmap_show)
-DEFINE_SHOW_FUNC(monc_show)
-DEFINE_SHOW_FUNC(mdsc_show)
-DEFINE_SHOW_FUNC(osdc_show)
-DEFINE_SHOW_FUNC(dentry_lru_show)
-DEFINE_SHOW_FUNC(caps_show)
+CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
+CEPH_DEFINE_SHOW_FUNC(mdsc_show)
+CEPH_DEFINE_SHOW_FUNC(caps_show)
+CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
+
 
+/*
+ * debugfs
+ */
 static int congestion_kb_set(void *data, u64 val)
 {
-	struct ceph_client *client = (struct ceph_client *)data;
-
-	if (client)
-		client->mount_args->congestion_kb = (int)val;
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
 
+	fsc->mount_options->congestion_kb = (int)val;
 	return 0;
 }
 
 static int congestion_kb_get(void *data, u64 *val)
 {
-	struct ceph_client *client = (struct ceph_client *)data;
-
-	if (client)
-		*val = (u64)client->mount_args->congestion_kb;
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
 
+	*val = (u64)fsc->mount_options->congestion_kb;
 	return 0;
 }
 
-
 DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
 			congestion_kb_set, "%llu\n");
 
-int __init ceph_debugfs_init(void)
-{
-	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
-	if (!ceph_debugfs_dir)
-		return -ENOMEM;
-	return 0;
-}
 
-void ceph_debugfs_cleanup(void)
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
-	debugfs_remove(ceph_debugfs_dir);
+	dout("ceph_fs_debugfs_cleanup\n");
+	debugfs_remove(fsc->debugfs_bdi);
+	debugfs_remove(fsc->debugfs_congestion_kb);
+	debugfs_remove(fsc->debugfs_mdsmap);
+	debugfs_remove(fsc->debugfs_caps);
+	debugfs_remove(fsc->debugfs_mdsc);
+	debugfs_remove(fsc->debugfs_dentry_lru);
 }
 
-int ceph_debugfs_client_init(struct ceph_client *client)
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
-	int ret = 0;
-	char name[80];
-
-	snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
-		 client->monc.auth->global_id);
+	char name[100];
+	int err = -ENOMEM;
 
-	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
-	if (!client->debugfs_dir)
-		goto out;
-
-	client->monc.debugfs_file = debugfs_create_file("monc",
-						      0600,
-						      client->debugfs_dir,
-						      client,
-						      &monc_show_fops);
-	if (!client->monc.debugfs_file)
+	dout("ceph_fs_debugfs_init\n");
+	fsc->debugfs_congestion_kb =
+		debugfs_create_file("writeback_congestion_kb",
+				    0600,
+				    fsc->client->debugfs_dir,
+				    fsc,
+				    &congestion_kb_fops);
+	if (!fsc->debugfs_congestion_kb)
 		goto out;
 
-	client->mdsc.debugfs_file = debugfs_create_file("mdsc",
-						      0600,
-						      client->debugfs_dir,
-						      client,
-						      &mdsc_show_fops);
-	if (!client->mdsc.debugfs_file)
-		goto out;
+	dout("a\n");
 
-	client->osdc.debugfs_file = debugfs_create_file("osdc",
-						      0600,
-						      client->debugfs_dir,
-						      client,
-						      &osdc_show_fops);
-	if (!client->osdc.debugfs_file)
+	snprintf(name, sizeof(name), "../../bdi/%s",
+		 dev_name(fsc->backing_dev_info.dev));
+	fsc->debugfs_bdi =
+		debugfs_create_symlink("bdi",
+				       fsc->client->debugfs_dir,
+				       name);
+	if (!fsc->debugfs_bdi)
 		goto out;
 
-	client->debugfs_monmap = debugfs_create_file("monmap",
+	dout("b\n");
+	fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
 					0600,
-					client->debugfs_dir,
-					client,
-					&monmap_show_fops);
-	if (!client->debugfs_monmap)
-		goto out;
-
-	client->debugfs_mdsmap = debugfs_create_file("mdsmap",
-					0600,
-					client->debugfs_dir,
-					client,
+					fsc->client->debugfs_dir,
+					fsc,
 					&mdsmap_show_fops);
-	if (!client->debugfs_mdsmap)
-		goto out;
-
-	client->debugfs_osdmap = debugfs_create_file("osdmap",
-					0600,
-					client->debugfs_dir,
-					client,
-					&osdmap_show_fops);
-	if (!client->debugfs_osdmap)
+	if (!fsc->debugfs_mdsmap)
 		goto out;
 
-	client->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
-					0600,
-					client->debugfs_dir,
-					client,
-					&dentry_lru_show_fops);
-	if (!client->debugfs_dentry_lru)
+	dout("ca\n");
+	fsc->debugfs_mdsc = debugfs_create_file("mdsc",
+						0600,
+						fsc->client->debugfs_dir,
+						fsc,
+						&mdsc_show_fops);
+	if (!fsc->debugfs_mdsc)
 		goto out;
 
-	client->debugfs_caps = debugfs_create_file("caps",
+	dout("da\n");
+	fsc->debugfs_caps = debugfs_create_file("caps",
 						   0400,
-						   client->debugfs_dir,
-						   client,
+						   fsc->client->debugfs_dir,
+						   fsc,
 						   &caps_show_fops);
-	if (!client->debugfs_caps)
+	if (!fsc->debugfs_caps)
 		goto out;
 
-	client->debugfs_congestion_kb =
-		debugfs_create_file("writeback_congestion_kb",
-				    0600,
-				    client->debugfs_dir,
-				    client,
-				    &congestion_kb_fops);
-	if (!client->debugfs_congestion_kb)
+	dout("ea\n");
+	fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&dentry_lru_show_fops);
+	if (!fsc->debugfs_dentry_lru)
 		goto out;
 
-	sprintf(name, "../../bdi/%s", dev_name(client->sb->s_bdi->dev));
-	client->debugfs_bdi = debugfs_create_symlink("bdi", client->debugfs_dir,
-						     name);
-
 	return 0;
 
 out:
-	ceph_debugfs_client_cleanup(client);
-	return ret;
+	ceph_fs_debugfs_cleanup(fsc);
+	return err;
 }
 
-void ceph_debugfs_client_cleanup(struct ceph_client *client)
-{
-	debugfs_remove(client->debugfs_bdi);
-	debugfs_remove(client->debugfs_caps);
-	debugfs_remove(client->debugfs_dentry_lru);
-	debugfs_remove(client->debugfs_osdmap);
-	debugfs_remove(client->debugfs_mdsmap);
-	debugfs_remove(client->debugfs_monmap);
-	debugfs_remove(client->osdc.debugfs_file);
-	debugfs_remove(client->mdsc.debugfs_file);
-	debugfs_remove(client->monc.debugfs_file);
-	debugfs_remove(client->debugfs_congestion_kb);
-	debugfs_remove(client->debugfs_dir);
-}
 
 #else  /* CONFIG_DEBUG_FS */
 
-int __init ceph_debugfs_init(void)
-{
-	return 0;
-}
-
-void ceph_debugfs_cleanup(void)
-{
-}
-
-int ceph_debugfs_client_init(struct ceph_client *client)
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
 	return 0;
 }
 
-void ceph_debugfs_client_cleanup(struct ceph_client *client)
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
 }
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6e4f43ff23ec..e0a2dc6fcafc 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/spinlock.h>
 #include <linux/fs_struct.h>
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 /*
  * Directory operations: readdir, lookup, create, link, unlink,
@@ -94,10 +95,7 @@ static unsigned fpos_off(loff_t p)
  */
 static int __dcache_readdir(struct file *filp,
 			    void *dirent, filldir_t filldir)
-		__releases(inode->i_lock)
-		__acquires(inode->i_lock)
 {
-	struct inode *inode = filp->f_dentry->d_inode;
 	struct ceph_file_info *fi = filp->private_data;
 	struct dentry *parent = filp->f_dentry;
 	struct inode *dir = parent->d_inode;
@@ -153,7 +151,6 @@ more:
 
 	atomic_inc(&dentry->d_count);
 	spin_unlock(&dcache_lock);
-	spin_unlock(&inode->i_lock);
 
 	dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
 	     dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
@@ -171,35 +168,30 @@ more:
 		} else {
 			dput(last);
 		}
-		last = NULL;
 	}
-
-	spin_lock(&inode->i_lock);
-	spin_lock(&dcache_lock);
-
 	last = dentry;
 
 	if (err < 0)
-		goto out_unlock;
+		goto out;
 
-	p = p->prev;
 	filp->f_pos++;
 
 	/* make sure a dentry wasn't dropped while we didn't have dcache_lock */
-	if ((ceph_inode(dir)->i_ceph_flags & CEPH_I_COMPLETE))
-		goto more;
-	dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
-	err = -EAGAIN;
+	if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
+		dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
+		err = -EAGAIN;
+		goto out;
+	}
+
+	spin_lock(&dcache_lock);
+	p = p->prev;	/* advance to next dentry */
+	goto more;
 
 out_unlock:
 	spin_unlock(&dcache_lock);
-
-	if (last) {
-		spin_unlock(&inode->i_lock);
+out:
+	if (last)
 		dput(last);
-		spin_lock(&inode->i_lock);
-	}
-
 	return err;
 }
 
@@ -227,15 +219,15 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	struct ceph_file_info *fi = filp->private_data;
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client = ceph_inode_to_client(inode);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	unsigned frag = fpos_frag(filp->f_pos);
 	int off = fpos_off(filp->f_pos);
 	int err;
 	u32 ftype;
 	struct ceph_mds_reply_info_parsed *rinfo;
-	const int max_entries = client->mount_args->max_readdir;
-	const int max_bytes = client->mount_args->max_readdir_bytes;
+	const int max_entries = fsc->mount_options->max_readdir;
+	const int max_bytes = fsc->mount_options->max_readdir_bytes;
 
 	dout("readdir %p filp %p frag %u off %u\n", inode, filp, frag, off);
 	if (fi->at_end)
@@ -267,17 +259,17 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	/* can we use the dcache? */
 	spin_lock(&inode->i_lock);
 	if ((filp->f_pos == 2 || fi->dentry) &&
-	    !ceph_test_opt(client, NOASYNCREADDIR) &&
+	    !ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
 	    ceph_snap(inode) != CEPH_SNAPDIR &&
 	    (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
 	    __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
+		spin_unlock(&inode->i_lock);
 		err = __dcache_readdir(filp, dirent, filldir);
-		if (err != -EAGAIN) {
-			spin_unlock(&inode->i_lock);
+		if (err != -EAGAIN)
 			return err;
-		}
+	} else {
+		spin_unlock(&inode->i_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	if (fi->dentry) {
 		err = note_last_dentry(fi, fi->dentry->d_name.name,
 				       fi->dentry->d_name.len);
@@ -487,14 +479,13 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin)
 struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
 				  struct dentry *dentry, int err)
 {
-	struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 	struct inode *parent = dentry->d_parent->d_inode;
 
 	/* .snap dir? */
 	if (err == -ENOENT &&
-	    ceph_vino(parent).ino != CEPH_INO_ROOT && /* no .snap in root dir */
 	    strcmp(dentry->d_name.name,
-		   client->mount_args->snapdir_name) == 0) {
+		   fsc->mount_options->snapdir_name) == 0) {
 		struct inode *inode = ceph_get_snapdir(parent);
 		dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
 		     dentry, dentry->d_name.len, dentry->d_name.name, inode);
@@ -539,8 +530,8 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
 static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 				  struct nameidata *nd)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int op;
 	int err;
@@ -572,7 +563,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		spin_lock(&dir->i_lock);
 		dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
 		if (strncmp(dentry->d_name.name,
-			    client->mount_args->snapdir_name,
+			    fsc->mount_options->snapdir_name,
 			    dentry->d_name.len) &&
 		    !is_root_ceph_dentry(dir, dentry) &&
 		    (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
@@ -629,8 +620,8 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
 static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 		      int mode, dev_t rdev)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -685,8 +676,8 @@ static int ceph_create(struct inode *dir, struct dentry *dentry, int mode,
 static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 			    const char *dest)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -716,8 +707,8 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 
 static int ceph_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err = -EROFS;
 	int op;
@@ -758,8 +749,8 @@ out:
 static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 		     struct dentry *dentry)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -813,8 +804,8 @@ static int drop_caps_for_unlink(struct inode *inode)
  */
 static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = dentry->d_inode;
 	struct ceph_mds_request *req;
 	int err = -EROFS;
@@ -854,8 +845,8 @@ out:
 static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 		       struct inode *new_dir, struct dentry *new_dentry)
 {
-	struct ceph_client *client = ceph_sb_to_client(old_dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -1021,11 +1012,15 @@ out_touch:
 static void ceph_dentry_release(struct dentry *dentry)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
-	struct inode *parent_inode = dentry->d_parent->d_inode;
-	u64 snapid = ceph_snap(parent_inode);
+	struct inode *parent_inode = NULL;
+	u64 snapid = CEPH_NOSNAP;
 
+	if (!IS_ROOT(dentry)) {
+		parent_inode = dentry->d_parent->d_inode;
+		if (parent_inode)
+			snapid = ceph_snap(parent_inode);
+	}
 	dout("dentry_release %p parent %p\n", dentry, parent_inode);
-
 	if (parent_inode && snapid != CEPH_SNAPDIR) {
 		struct ceph_inode_info *ci = ceph_inode(parent_inode);
 
@@ -1072,7 +1067,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int left;
 
-	if (!ceph_test_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
+	if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
 		return -EISDIR;
 
 	if (!cf->dir_info) {
@@ -1173,7 +1168,7 @@ void ceph_dentry_lru_add(struct dentry *dn)
 	dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
 	     dn->d_name.len, dn->d_name.name);
 	if (di) {
-		mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 		spin_lock(&mdsc->dentry_lru_lock);
 		list_add_tail(&di->lru, &mdsc->dentry_lru);
 		mdsc->num_dentry++;
@@ -1189,7 +1184,7 @@ void ceph_dentry_lru_touch(struct dentry *dn)
 	dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn,
 	     dn->d_name.len, dn->d_name.name, di->offset);
 	if (di) {
-		mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 		spin_lock(&mdsc->dentry_lru_lock);
 		list_move_tail(&di->lru, &mdsc->dentry_lru);
 		spin_unlock(&mdsc->dentry_lru_lock);
@@ -1204,7 +1199,7 @@ void ceph_dentry_lru_del(struct dentry *dn)
 	dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
 	     dn->d_name.len, dn->d_name.name);
 	if (di) {
-		mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 		spin_lock(&mdsc->dentry_lru_lock);
 		list_del_init(&di->lru);
 		mdsc->num_dentry--;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 4480cb1c63e7..2297d9426992 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -1,10 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/exportfs.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 /*
  * NFS export support
@@ -42,32 +43,37 @@ struct ceph_nfs_confh {
 static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
 			  int connectable)
 {
+	int type;
 	struct ceph_nfs_fh *fh = (void *)rawfh;
 	struct ceph_nfs_confh *cfh = (void *)rawfh;
 	struct dentry *parent = dentry->d_parent;
 	struct inode *inode = dentry->d_inode;
-	int type;
+	int connected_handle_length = sizeof(*cfh)/4;
+	int handle_length = sizeof(*fh)/4;
 
 	/* don't re-export snaps */
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EINVAL;
 
-	if (*max_len >= sizeof(*cfh)) {
+	if (*max_len >= connected_handle_length) {
 		dout("encode_fh %p connectable\n", dentry);
 		cfh->ino = ceph_ino(dentry->d_inode);
 		cfh->parent_ino = ceph_ino(parent->d_inode);
 		cfh->parent_name_hash = parent->d_name.hash;
-		*max_len = sizeof(*cfh);
+		*max_len = connected_handle_length;
 		type = 2;
-	} else if (*max_len > sizeof(*fh)) {
-		if (connectable)
-			return -ENOSPC;
+	} else if (*max_len >= handle_length) {
+		if (connectable) {
+			*max_len = connected_handle_length;
+			return 255;
+		}
 		dout("encode_fh %p\n", dentry);
 		fh->ino = ceph_ino(dentry->d_inode);
-		*max_len = sizeof(*fh);
+		*max_len = handle_length;
 		type = 1;
 	} else {
-		return -ENOSPC;
+		*max_len = handle_length;
+		return 255;
 	}
 	return type;
 }
@@ -115,7 +121,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 static struct dentry *__cfh_to_dentry(struct super_block *sb,
 				      struct ceph_nfs_confh *cfh)
 {
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
 	struct dentry *dentry;
 	struct ceph_vino vino;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8c044a4f0457..e77c28cf3690 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1,5 +1,6 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -38,8 +39,8 @@
 static struct ceph_mds_request *
 prepare_open_request(struct super_block *sb, int flags, int create_mode)
 {
-	struct ceph_client *client = ceph_sb_to_client(sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int want_auth = USE_ANY_MDS;
 	int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
@@ -117,8 +118,8 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 int ceph_open(struct inode *inode, struct file *file)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client = ceph_sb_to_client(inode->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_file_info *cf = file->private_data;
 	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
@@ -216,8 +217,8 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
 				struct nameidata *nd, int mode,
 				int locked_dir)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct file *file = nd->intent.open.file;
 	struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry);
 	struct ceph_mds_request *req;
@@ -269,163 +270,6 @@ int ceph_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-/*
- * build a vector of user pages
- */
-static struct page **get_direct_page_vector(const char __user *data,
-					    int num_pages,
-					    loff_t off, size_t len)
-{
-	struct page **pages;
-	int rc;
-
-	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
-
-	down_read(&current->mm->mmap_sem);
-	rc = get_user_pages(current, current->mm, (unsigned long)data,
-			    num_pages, 0, 0, pages, NULL);
-	up_read(&current->mm->mmap_sem);
-	if (rc < 0)
-		goto fail;
-	return pages;
-
-fail:
-	kfree(pages);
-	return ERR_PTR(rc);
-}
-
-static void put_page_vector(struct page **pages, int num_pages)
-{
-	int i;
-
-	for (i = 0; i < num_pages; i++)
-		put_page(pages[i]);
-	kfree(pages);
-}
-
-void ceph_release_page_vector(struct page **pages, int num_pages)
-{
-	int i;
-
-	for (i = 0; i < num_pages; i++)
-		__free_pages(pages[i], 0);
-	kfree(pages);
-}
-
-/*
- * allocate a vector new pages
- */
-static struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
-{
-	struct page **pages;
-	int i;
-
-	pages = kmalloc(sizeof(*pages) * num_pages, flags);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
-	for (i = 0; i < num_pages; i++) {
-		pages[i] = __page_cache_alloc(flags);
-		if (pages[i] == NULL) {
-			ceph_release_page_vector(pages, i);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-	return pages;
-}
-
-/*
- * copy user data into a page vector
- */
-static int copy_user_to_page_vector(struct page **pages,
-				    const char __user *data,
-				    loff_t off, size_t len)
-{
-	int i = 0;
-	int po = off & ~PAGE_CACHE_MASK;
-	int left = len;
-	int l, bad;
-
-	while (left > 0) {
-		l = min_t(int, PAGE_CACHE_SIZE-po, left);
-		bad = copy_from_user(page_address(pages[i]) + po, data, l);
-		if (bad == l)
-			return -EFAULT;
-		data += l - bad;
-		left -= l - bad;
-		po += l - bad;
-		if (po == PAGE_CACHE_SIZE) {
-			po = 0;
-			i++;
-		}
-	}
-	return len;
-}
-
-/*
- * copy user data from a page vector into a user pointer
- */
-static int copy_page_vector_to_user(struct page **pages, char __user *data,
-				    loff_t off, size_t len)
-{
-	int i = 0;
-	int po = off & ~PAGE_CACHE_MASK;
-	int left = len;
-	int l, bad;
-
-	while (left > 0) {
-		l = min_t(int, left, PAGE_CACHE_SIZE-po);
-		bad = copy_to_user(data, page_address(pages[i]) + po, l);
-		if (bad == l)
-			return -EFAULT;
-		data += l - bad;
-		left -= l - bad;
-		if (po) {
-			po += l - bad;
-			if (po == PAGE_CACHE_SIZE)
-				po = 0;
-		}
-		i++;
-	}
-	return len;
-}
-
-/*
- * Zero an extent within a page vector.  Offset is relative to the
- * start of the first page.
- */
-static void zero_page_vector_range(int off, int len, struct page **pages)
-{
-	int i = off >> PAGE_CACHE_SHIFT;
-
-	off &= ~PAGE_CACHE_MASK;
-
-	dout("zero_page_vector_page %u~%u\n", off, len);
-
-	/* leading partial page? */
-	if (off) {
-		int end = min((int)PAGE_CACHE_SIZE, off + len);
-		dout("zeroing %d %p head from %d\n", i, pages[i],
-		     (int)off);
-		zero_user_segment(pages[i], off, end);
-		len -= (end - off);
-		i++;
-	}
-	while (len >= PAGE_CACHE_SIZE) {
-		dout("zeroing %d %p len=%d\n", i, pages[i], len);
-		zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
-		len -= PAGE_CACHE_SIZE;
-		i++;
-	}
-	/* trailing partial page? */
-	if (len) {
-		dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
-		zero_user_segment(pages[i], 0, len);
-	}
-}
-
-
 /*
  * Read a range of bytes striped over one or more objects.  Iterate over
  * objects we stripe over.  (That's not atomic, but good enough for now.)
@@ -438,7 +282,7 @@ static int striped_read(struct inode *inode,
 			struct page **pages, int num_pages,
 			int *checkeof)
 {
-	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 pos, this_len;
 	int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
@@ -459,7 +303,7 @@ static int striped_read(struct inode *inode,
 
 more:
 	this_len = left;
-	ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode),
+	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
 				  &ci->i_layout, pos, &this_len,
 				  ci->i_truncate_seq,
 				  ci->i_truncate_size,
@@ -477,8 +321,8 @@ more:
 
 		if (read < pos - off) {
 			dout(" zero gap %llu to %llu\n", off + read, pos);
-			zero_page_vector_range(page_off + read,
-					       pos - off - read, pages);
+			ceph_zero_page_vector_range(page_off + read,
+						    pos - off - read, pages);
 		}
 		pos += ret;
 		read = pos - off;
@@ -495,8 +339,8 @@ more:
 		/* was original extent fully inside i_size? */
 		if (pos + left <= inode->i_size) {
 			dout("zero tail\n");
-			zero_page_vector_range(page_off + read, len - read,
-					       pages);
+			ceph_zero_page_vector_range(page_off + read, len - read,
+						    pages);
 			read = len;
 			goto out;
 		}
@@ -531,7 +375,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
 	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
 	if (file->f_flags & O_DIRECT) {
-		pages = get_direct_page_vector(data, num_pages, off, len);
+		pages = ceph_get_direct_page_vector(data, num_pages, off, len);
 
 		/*
 		 * flush any page cache pages in this range.  this
@@ -552,13 +396,13 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
 	ret = striped_read(inode, off, len, pages, num_pages, checkeof);
 
 	if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
-		ret = copy_page_vector_to_user(pages, data, off, ret);
+		ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
 	if (ret >= 0)
 		*poff = off + ret;
 
 done:
 	if (file->f_flags & O_DIRECT)
-		put_page_vector(pages, num_pages);
+		ceph_put_page_vector(pages, num_pages);
 	else
 		ceph_release_page_vector(pages, num_pages);
 	dout("sync_read result %d\n", ret);
@@ -594,7 +438,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_request *req;
 	struct page **pages;
 	int num_pages;
@@ -642,7 +486,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 	 */
 more:
 	len = left;
-	req = ceph_osdc_new_request(&client->osdc, &ci->i_layout,
+	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), pos, &len,
 				    CEPH_OSD_OP_WRITE, flags,
 				    ci->i_snap_realm->cached_context,
@@ -655,7 +499,7 @@ more:
 	num_pages = calc_pages_for(pos, len);
 
 	if (file->f_flags & O_DIRECT) {
-		pages = get_direct_page_vector(data, num_pages, pos, len);
+		pages = ceph_get_direct_page_vector(data, num_pages, pos, len);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
 			goto out;
@@ -673,7 +517,7 @@ more:
 			ret = PTR_ERR(pages);
 			goto out;
 		}
-		ret = copy_user_to_page_vector(pages, data, pos, len);
+		ret = ceph_copy_user_to_page_vector(pages, data, pos, len);
 		if (ret < 0) {
 			ceph_release_page_vector(pages, num_pages);
 			goto out;
@@ -689,7 +533,7 @@ more:
 	req->r_num_pages = num_pages;
 	req->r_inode = inode;
 
-	ret = ceph_osdc_start_request(&client->osdc, req, false);
+	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
 	if (!ret) {
 		if (req->r_safe_callback) {
 			/*
@@ -697,15 +541,15 @@ more:
 			 * start_request so that a tid has been assigned.
 			 */
 			spin_lock(&ci->i_unsafe_lock);
-			list_add(&ci->i_unsafe_writes, &req->r_unsafe_item);
+			list_add(&req->r_unsafe_item, &ci->i_unsafe_writes);
 			spin_unlock(&ci->i_unsafe_lock);
 			ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
 		}
-		ret = ceph_osdc_wait_request(&client->osdc, req);
+		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 	}
 
 	if (file->f_flags & O_DIRECT)
-		put_page_vector(pages, num_pages);
+		ceph_put_page_vector(pages, num_pages);
 	else if (file->f_flags & O_SYNC)
 		ceph_release_page_vector(pages, num_pages);
 
@@ -814,7 +658,8 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	struct ceph_file_info *fi = file->private_data;
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_client(inode->i_sb)->client->osdc;
 	loff_t endoff = pos + iov->iov_len;
 	int want, got = 0;
 	int ret, err;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e7cca414da03..1d6a45b5a04c 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
@@ -13,7 +13,8 @@
 #include <linux/pagevec.h>
 
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+#include <linux/ceph/decode.h>
 
 /*
  * Ceph inode operations
@@ -384,7 +385,7 @@ void ceph_destroy_inode(struct inode *inode)
 	 */
 	if (ci->i_snap_realm) {
 		struct ceph_mds_client *mdsc =
-			&ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+			ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
 		struct ceph_snap_realm *realm = ci->i_snap_realm;
 
 		dout(" dropping residual ref to snap realm %p\n", realm);
@@ -685,7 +686,7 @@ static int fill_inode(struct inode *inode,
 		}
 
 		/* it may be better to set st_size in getattr instead? */
-		if (ceph_test_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
+		if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
 			inode->i_size = ci->i_rbytes;
 		break;
 	default:
@@ -845,7 +846,7 @@ static void ceph_set_dentry_offset(struct dentry *dn)
  * the caller) if we fail.
  */
 static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
-				    bool *prehash)
+				    bool *prehash, bool set_offset)
 {
 	struct dentry *realdn;
 
@@ -877,7 +878,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	}
 	if ((!prehash || *prehash) && d_unhashed(dn))
 		d_rehash(dn);
-	ceph_set_dentry_offset(dn);
+	if (set_offset)
+		ceph_set_dentry_offset(dn);
 out:
 	return dn;
 }
@@ -900,7 +902,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	struct inode *in = NULL;
 	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
-	struct ceph_client *client = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 	int i = 0;
 	int err = 0;
 
@@ -964,7 +966,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	 */
 	if (rinfo->head->is_dentry && !req->r_aborted &&
 	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
-					       client->mount_args->snapdir_name,
+					       fsc->mount_options->snapdir_name,
 					       req->r_dentry->d_name.len))) {
 		/*
 		 * lookup link rename   : null -> possibly existing inode
@@ -1062,7 +1064,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 				d_delete(dn);
 				goto done;
 			}
-			dn = splice_dentry(dn, in, &have_lease);
+			dn = splice_dentry(dn, in, &have_lease, true);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
@@ -1105,7 +1107,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			goto done;
 		}
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
-		dn = splice_dentry(dn, in, NULL);
+		dn = splice_dentry(dn, in, NULL, true);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
@@ -1237,7 +1239,7 @@ retry_lookup:
 				err = PTR_ERR(in);
 				goto out;
 			}
-			dn = splice_dentry(dn, in, NULL);
+			dn = splice_dentry(dn, in, NULL, false);
 			if (IS_ERR(dn))
 				dn = NULL;
 		}
@@ -1532,7 +1534,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	struct inode *parent_inode = dentry->d_parent->d_inode;
 	const unsigned int ia_valid = attr->ia_valid;
 	struct ceph_mds_request *req;
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(dentry->d_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
 	int issued;
 	int release = 0, dirtied = 0;
 	int mask = 0;
@@ -1727,8 +1729,8 @@ out:
  */
 int ceph_do_getattr(struct inode *inode, int mask)
 {
-	struct ceph_client *client = ceph_sb_to_client(inode->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 76e307d2aba1..8888c9ba68db 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -1,8 +1,10 @@
 #include <linux/in.h>
 
-#include "ioctl.h"
 #include "super.h"
-#include "ceph_debug.h"
+#include "mds_client.h"
+#include <linux/ceph/ceph_debug.h>
+
+#include "ioctl.h"
 
 
 /*
@@ -37,7 +39,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_ioctl_layout l;
 	int err, i;
@@ -89,6 +91,68 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 	return err;
 }
 
+/*
+ * Set a layout policy on a directory inode. All items in the tree
+ * rooted at this inode will inherit this layout on creation,
+ * (It doesn't apply retroactively )
+ * unless a subdirectory has its own layout policy.
+ */
+static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	int err, i;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+
+	/* copy and validate */
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	if ((l.object_size & ~PAGE_MASK) ||
+	    (l.stripe_unit & ~PAGE_MASK) ||
+	    !l.stripe_unit ||
+	    (l.object_size &&
+	        (unsigned)l.object_size % (unsigned)l.stripe_unit))
+		return -EINVAL;
+
+	/* make sure it's a valid data pool */
+	if (l.data_pool > 0) {
+		mutex_lock(&mdsc->mutex);
+		err = -EINVAL;
+		for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+			if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
+				err = 0;
+				break;
+			}
+		mutex_unlock(&mdsc->mutex);
+		if (err)
+			return err;
+	}
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
+				       USE_AUTH_MDS);
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = igrab(inode);
+
+	req->r_args.setlayout.layout.fl_stripe_unit =
+			cpu_to_le32(l.stripe_unit);
+	req->r_args.setlayout.layout.fl_stripe_count =
+			cpu_to_le32(l.stripe_count);
+	req->r_args.setlayout.layout.fl_object_size =
+			cpu_to_le32(l.object_size);
+	req->r_args.setlayout.layout.fl_pg_pool =
+			cpu_to_le32(l.data_pool);
+	req->r_args.setlayout.layout.fl_pg_preferred =
+			cpu_to_le32(l.preferred_osd);
+
+	err = ceph_mdsc_do_request(mdsc, inode, req);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
 /*
  * Return object name, size/offset information, and location (OSD
  * number, network address) for a given file offset.
@@ -98,7 +162,8 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 	struct ceph_ioctl_dataloc dl;
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_client(inode->i_sb)->client->osdc;
 	u64 len = 1, olen;
 	u64 tmp;
 	struct ceph_object_layout ol;
@@ -174,11 +239,15 @@ long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case CEPH_IOC_SET_LAYOUT:
 		return ceph_ioctl_set_layout(file, (void __user *)arg);
 
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return ceph_ioctl_set_layout_policy(file, (void __user *)arg);
+
 	case CEPH_IOC_GET_DATALOC:
 		return ceph_ioctl_get_dataloc(file, (void __user *)arg);
 
 	case CEPH_IOC_LAZYIO:
 		return ceph_ioctl_lazyio(file);
 	}
+
 	return -ENOTTY;
 }
diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
index 88451a3b6857..a6ce54e94eb5 100644
--- a/fs/ceph/ioctl.h
+++ b/fs/ceph/ioctl.h
@@ -4,7 +4,7 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
-#define CEPH_IOCTL_MAGIC 0x97
+#define CEPH_IOCTL_MAGIC 0x98
 
 /* just use u64 to align sanely on all archs */
 struct ceph_ioctl_layout {
@@ -17,6 +17,8 @@ struct ceph_ioctl_layout {
 				   struct ceph_ioctl_layout)
 #define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2,		\
 				   struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT_POLICY _IOW(CEPH_IOCTL_MAGIC, 5,	\
+				   struct ceph_ioctl_layout)
 
 /*
  * Extract identity, address of the OSD and object storing a given
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ff4e753aae92..40abde93c345 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -1,11 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/file.h>
 #include <linux/namei.h>
 
 #include "super.h"
 #include "mds_client.h"
-#include "pagelist.h"
+#include <linux/ceph/pagelist.h>
 
 /**
  * Implement fcntl and flock locking functions.
@@ -16,7 +16,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_mds_client *mdsc =
-		&ceph_sb_to_client(inode->i_sb)->mdsc;
+		ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -181,8 +181,9 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
  * Encode the flock and fcntl locks for the given inode into the pagelist.
  * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
  * sequential flock locks.
- * Must be called with BLK already held, and the lock numbers should have
- * been gathered under the same lock holding window.
+ * Must be called with lock_flocks() already held.
+ * If we encounter more of a specific lock type than expected,
+ * we return the value 1.
  */
 int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 		      int num_fcntl_locks, int num_flock_locks)
@@ -190,6 +191,8 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 	struct file_lock *lock;
 	struct ceph_filelock cephlock;
 	int err = 0;
+	int seen_fcntl = 0;
+	int seen_flock = 0;
 
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
@@ -198,6 +201,11 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 		goto fail;
 	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
 		if (lock->fl_flags & FL_POSIX) {
+			++seen_fcntl;
+			if (seen_fcntl > num_fcntl_locks) {
+				err = -ENOSPC;
+				goto fail;
+			}
 			err = lock_to_ceph_filelock(lock, &cephlock);
 			if (err)
 				goto fail;
@@ -213,6 +221,11 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 		goto fail;
 	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
 		if (lock->fl_flags & FL_FLOCK) {
+			++seen_flock;
+			if (seen_flock > num_flock_locks) {
+				err = -ENOSPC;
+				goto fail;
+			}
 			err = lock_to_ceph_filelock(lock, &cephlock);
 			if (err)
 				goto fail;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f091b1351786..3142b15940c2 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1,17 +1,21 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/fs.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/smp_lock.h>
 
-#include "mds_client.h"
-#include "mon_client.h"
 #include "super.h"
-#include "messenger.h"
-#include "decode.h"
-#include "auth.h"
-#include "pagelist.h"
+#include "mds_client.h"
+
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
 
 /*
  * A cluster of MDS (metadata server) daemons is responsible for
@@ -286,8 +290,9 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
 	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
 	if (atomic_dec_and_test(&s->s_ref)) {
 		if (s->s_authorizer)
-			s->s_mdsc->client->monc.auth->ops->destroy_authorizer(
-				s->s_mdsc->client->monc.auth, s->s_authorizer);
+		     s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
+			     s->s_mdsc->fsc->client->monc.auth,
+			     s->s_authorizer);
 		kfree(s);
 	}
 }
@@ -344,7 +349,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_seq = 0;
 	mutex_init(&s->s_mutex);
 
-	ceph_con_init(mdsc->client->msgr, &s->s_con);
+	ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
 	s->s_con.private = s;
 	s->s_con.ops = &mds_con_ops;
 	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
@@ -599,7 +604,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 	} else if (req->r_dentry) {
 		struct inode *dir = req->r_dentry->d_parent->d_inode;
 
-		if (dir->i_sb != mdsc->client->sb) {
+		if (dir->i_sb != mdsc->fsc->sb) {
 			/* not this fs! */
 			inode = req->r_dentry->d_inode;
 		} else if (ceph_snap(dir) != CEPH_NOSNAP) {
@@ -884,7 +889,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	__ceph_remove_cap(cap);
 	if (!__ceph_is_any_real_caps(ci)) {
 		struct ceph_mds_client *mdsc =
-			&ceph_sb_to_client(inode->i_sb)->mdsc;
+			ceph_sb_to_client(inode->i_sb)->mdsc;
 
 		spin_lock(&mdsc->cap_dirty_lock);
 		if (!list_empty(&ci->i_dirty_item)) {
@@ -1146,7 +1151,7 @@ int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
 	struct ceph_msg *msg, *partial = NULL;
 	struct ceph_mds_cap_release *head;
 	int err = -ENOMEM;
-	int extra = mdsc->client->mount_args->cap_release_safety;
+	int extra = mdsc->fsc->mount_options->cap_release_safety;
 	int num;
 
 	dout("add_cap_releases %p mds%d extra %d\n", session, session->s_mds,
@@ -2085,7 +2090,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
-	err = ceph_fill_trace(mdsc->client->sb, req, req->r_session);
+	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
 	if (err == 0) {
 		if (result == 0 && rinfo->dir_nr)
 			ceph_readdir_prepopulate(req, req->r_session);
@@ -2361,19 +2366,37 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 
 	if (recon_state->flock) {
 		int num_fcntl_locks, num_flock_locks;
-
-		lock_kernel();
-		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
-		rec.v2.flock_len = (2*sizeof(u32) +
-				    (num_fcntl_locks+num_flock_locks) *
-				    sizeof(struct ceph_filelock));
-
+		struct ceph_pagelist_cursor trunc_point;
+
+		ceph_pagelist_set_cursor(pagelist, &trunc_point);
+		do {
+			lock_flocks();
+			ceph_count_locks(inode, &num_fcntl_locks,
+					 &num_flock_locks);
+			rec.v2.flock_len = (2*sizeof(u32) +
+					    (num_fcntl_locks+num_flock_locks) *
+					    sizeof(struct ceph_filelock));
+			unlock_flocks();
+
+			/* pre-alloc pagelist */
+			ceph_pagelist_truncate(pagelist, &trunc_point);
+			err = ceph_pagelist_append(pagelist, &rec, reclen);
+			if (!err)
+				err = ceph_pagelist_reserve(pagelist,
+							    rec.v2.flock_len);
+
+			/* encode locks */
+			if (!err) {
+				lock_flocks();
+				err = ceph_encode_locks(inode,
+							pagelist,
+							num_fcntl_locks,
+							num_flock_locks);
+				unlock_flocks();
+			}
+		} while (err == -ENOSPC);
+	} else {
 		err = ceph_pagelist_append(pagelist, &rec, reclen);
-		if (!err)
-			err = ceph_encode_locks(inode, pagelist,
-						num_fcntl_locks,
-						num_flock_locks);
-		unlock_kernel();
 	}
 
 out_free:
@@ -2611,7 +2634,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 			 struct ceph_mds_session *session,
 			 struct ceph_msg *msg)
 {
-	struct super_block *sb = mdsc->client->sb;
+	struct super_block *sb = mdsc->fsc->sb;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	struct dentry *parent, *dentry;
@@ -2889,10 +2912,16 @@ static void delayed_work(struct work_struct *work)
 	schedule_delayed(mdsc);
 }
 
+int ceph_mdsc_init(struct ceph_fs_client *fsc)
 
-int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
 {
-	mdsc->client = client;
+	struct ceph_mds_client *mdsc;
+
+	mdsc = kzalloc(sizeof(struct ceph_mds_client), GFP_NOFS);
+	if (!mdsc)
+		return -ENOMEM;
+	mdsc->fsc = fsc;
+	fsc->mdsc = mdsc;
 	mutex_init(&mdsc->mutex);
 	mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
 	if (mdsc->mdsmap == NULL)
@@ -2925,7 +2954,7 @@ int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
 	INIT_LIST_HEAD(&mdsc->dentry_lru);
 
 	ceph_caps_init(mdsc);
-	ceph_adjust_min_caps(mdsc, client->min_caps);
+	ceph_adjust_min_caps(mdsc, fsc->min_caps);
 
 	return 0;
 }
@@ -2937,7 +2966,7 @@ int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
 static void wait_requests(struct ceph_mds_client *mdsc)
 {
 	struct ceph_mds_request *req;
-	struct ceph_client *client = mdsc->client;
+	struct ceph_fs_client *fsc = mdsc->fsc;
 
 	mutex_lock(&mdsc->mutex);
 	if (__get_oldest_req(mdsc)) {
@@ -2945,7 +2974,7 @@ static void wait_requests(struct ceph_mds_client *mdsc)
 
 		dout("wait_requests waiting for requests\n");
 		wait_for_completion_timeout(&mdsc->safe_umount_waiters,
-				    client->mount_args->mount_timeout * HZ);
+				    fsc->client->options->mount_timeout * HZ);
 
 		/* tear down remaining requests */
 		mutex_lock(&mdsc->mutex);
@@ -3028,7 +3057,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
 	u64 want_tid, want_flush;
 
-	if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN)
+	if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
 		return;
 
 	dout("sync\n");
@@ -3051,7 +3080,7 @@ bool done_closing_sessions(struct ceph_mds_client *mdsc)
 {
 	int i, n = 0;
 
-	if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN)
+	if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
 		return true;
 
 	mutex_lock(&mdsc->mutex);
@@ -3069,8 +3098,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 {
 	struct ceph_mds_session *session;
 	int i;
-	struct ceph_client *client = mdsc->client;
-	unsigned long timeout = client->mount_args->mount_timeout * HZ;
+	struct ceph_fs_client *fsc = mdsc->fsc;
+	unsigned long timeout = fsc->client->options->mount_timeout * HZ;
 
 	dout("close_sessions\n");
 
@@ -3117,7 +3146,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	dout("stopped\n");
 }
 
-void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
+static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
 	dout("stop\n");
 	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
@@ -3127,6 +3156,15 @@ void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 	ceph_caps_finalize(mdsc);
 }
 
+void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
+{
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+
+	ceph_mdsc_stop(mdsc);
+	fsc->mdsc = NULL;
+	kfree(mdsc);
+}
+
 
 /*
  * handle mds map update.
@@ -3143,14 +3181,14 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 
 	ceph_decode_need(&p, end, sizeof(fsid)+2*sizeof(u32), bad);
 	ceph_decode_copy(&p, &fsid, sizeof(fsid));
-	if (ceph_check_fsid(mdsc->client, &fsid) < 0)
+	if (ceph_check_fsid(mdsc->fsc->client, &fsid) < 0)
 		return;
 	epoch = ceph_decode_32(&p);
 	maplen = ceph_decode_32(&p);
 	dout("handle_map epoch %u len %d\n", epoch, (int)maplen);
 
 	/* do we need it? */
-	ceph_monc_got_mdsmap(&mdsc->client->monc, epoch);
+	ceph_monc_got_mdsmap(&mdsc->fsc->client->monc, epoch);
 	mutex_lock(&mdsc->mutex);
 	if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) {
 		dout("handle_map epoch %u <= our %u\n",
@@ -3174,7 +3212,7 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	} else {
 		mdsc->mdsmap = newmap;  /* first mds map */
 	}
-	mdsc->client->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
+	mdsc->fsc->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
 
 	__wake_requests(mdsc, &mdsc->waiting_for_map);
 
@@ -3275,7 +3313,7 @@ static int get_authorizer(struct ceph_connection *con,
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
-	struct ceph_auth_client *ac = mdsc->client->monc.auth;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 	int ret = 0;
 
 	if (force_new && s->s_authorizer) {
@@ -3309,7 +3347,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
-	struct ceph_auth_client *ac = mdsc->client->monc.auth;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
 	return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len);
 }
@@ -3318,12 +3356,12 @@ static int invalidate_authorizer(struct ceph_connection *con)
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
-	struct ceph_auth_client *ac = mdsc->client->monc.auth;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
 	if (ac->ops->invalidate_authorizer)
 		ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
 
-	return ceph_monc_validate_auth(&mdsc->client->monc);
+	return ceph_monc_validate_auth(&mdsc->fsc->client->monc);
 }
 
 static const struct ceph_connection_operations mds_con_ops = {
@@ -3336,7 +3374,4 @@ static const struct ceph_connection_operations mds_con_ops = {
 	.peer_reset = peer_reset,
 };
 
-
-
-
 /* eof */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index c98267ce6d2a..d66d63c72355 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -8,9 +8,9 @@
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
 
-#include "types.h"
-#include "messenger.h"
-#include "mdsmap.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/mdsmap.h>
 
 /*
  * Some lock dependencies:
@@ -26,7 +26,7 @@
  *
  */
 
-struct ceph_client;
+struct ceph_fs_client;
 struct ceph_cap;
 
 /*
@@ -230,7 +230,7 @@ struct ceph_mds_request {
  * mds client state
  */
 struct ceph_mds_client {
-	struct ceph_client      *client;
+	struct ceph_fs_client  *fsc;
 	struct mutex            mutex;         /* all nested structures */
 
 	struct ceph_mdsmap      *mdsmap;
@@ -289,11 +289,6 @@ struct ceph_mds_client {
 	int		caps_avail_count;    /* unused, unreserved */
 	int		caps_min_count;      /* keep at least this many
 						(unreserved) */
-
-#ifdef CONFIG_DEBUG_FS
-	struct dentry 	  *debugfs_file;
-#endif
-
 	spinlock_t	  dentry_lru_lock;
 	struct list_head  dentry_lru;
 	int		  num_dentry;
@@ -316,10 +311,9 @@ extern void ceph_put_mds_session(struct ceph_mds_session *s);
 extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
 			     struct ceph_msg *msg, int mds);
 
-extern int ceph_mdsc_init(struct ceph_mds_client *mdsc,
-			   struct ceph_client *client);
+extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
 extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
-extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
 
 extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
 
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 040be6d1150b..73b7d44e8a35 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/bug.h>
 #include <linux/err.h>
@@ -6,9 +6,9 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include "mdsmap.h"
-#include "messenger.h"
-#include "decode.h"
+#include <linux/ceph/mdsmap.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
 
 #include "super.h"
 
@@ -117,7 +117,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		}
 
 		dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n",
-		     i+1, n, global_id, mds, inc, pr_addr(&addr.in_addr),
+		     i+1, n, global_id, mds, inc,
+		     ceph_pr_addr(&addr.in_addr),
 		     ceph_mds_state_name(state));
 		if (mds >= 0 && mds < m->m_max_mds && state > 0) {
 			m->m_info[mds].global_id = global_id;
diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
deleted file mode 100644
index b6859f47d364..000000000000
--- a/fs/ceph/pagelist.c
+++ /dev/null
@@ -1,55 +0,0 @@
-
-#include <linux/gfp.h>
-#include <linux/pagemap.h>
-#include <linux/highmem.h>
-
-#include "pagelist.h"
-
-int ceph_pagelist_release(struct ceph_pagelist *pl)
-{
-	if (pl->mapped_tail)
-		kunmap(pl->mapped_tail);
-	while (!list_empty(&pl->head)) {
-		struct page *page = list_first_entry(&pl->head, struct page,
-						     lru);
-		list_del(&page->lru);
-		__free_page(page);
-	}
-	return 0;
-}
-
-static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
-{
-	struct page *page = __page_cache_alloc(GFP_NOFS);
-	if (!page)
-		return -ENOMEM;
-	pl->room += PAGE_SIZE;
-	list_add_tail(&page->lru, &pl->head);
-	if (pl->mapped_tail)
-		kunmap(pl->mapped_tail);
-	pl->mapped_tail = kmap(page);
-	return 0;
-}
-
-int ceph_pagelist_append(struct ceph_pagelist *pl, void *buf, size_t len)
-{
-	while (pl->room < len) {
-		size_t bit = pl->room;
-		int ret;
-
-		memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
-		       buf, bit);
-		pl->length += bit;
-		pl->room -= bit;
-		buf += bit;
-		len -= bit;
-		ret = ceph_pagelist_addpage(pl);
-		if (ret)
-			return ret;
-	}
-
-	memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
-	pl->length += len;
-	pl->room -= len;
-	return 0;
-}
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4868b9dcac5a..39c243acd062 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1,10 +1,12 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/sort.h>
 #include <linux/slab.h>
 
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
 
 /*
  * Snapshots in ceph are driven in large part by cooperation from the
@@ -119,6 +121,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 	INIT_LIST_HEAD(&realm->children);
 	INIT_LIST_HEAD(&realm->child_item);
 	INIT_LIST_HEAD(&realm->empty_item);
+	INIT_LIST_HEAD(&realm->dirty_item);
 	INIT_LIST_HEAD(&realm->inodes_with_caps);
 	spin_lock_init(&realm->inodes_with_caps_lock);
 	__insert_snap_realm(&mdsc->snap_realms, realm);
@@ -467,7 +470,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 		INIT_LIST_HEAD(&capsnap->ci_item);
 		INIT_LIST_HEAD(&capsnap->flushing_item);
 
-		capsnap->follows = snapc->seq - 1;
+		capsnap->follows = snapc->seq;
 		capsnap->issued = __ceph_caps_issued(ci, NULL);
 		capsnap->dirty = dirty;
 
@@ -525,7 +528,7 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 			    struct ceph_cap_snap *capsnap)
 {
 	struct inode *inode = &ci->vfs_inode;
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 
 	BUG_ON(capsnap->writing);
 	capsnap->size = inode->i_size;
@@ -604,6 +607,7 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
 	struct ceph_snap_realm *realm;
 	int invalidate = 0;
 	int err = -ENOMEM;
+	LIST_HEAD(dirty_realms);
 
 	dout("update_snap_trace deletion=%d\n", deletion);
 more:
@@ -626,24 +630,6 @@ more:
 		}
 	}
 
-	if (le64_to_cpu(ri->seq) > realm->seq) {
-		dout("update_snap_trace updating %llx %p %lld -> %lld\n",
-		     realm->ino, realm, realm->seq, le64_to_cpu(ri->seq));
-		/*
-		 * if the realm seq has changed, queue a cap_snap for every
-		 * inode with open caps.  we do this _before_ we update
-		 * the realm info so that we prepare for writeback under the
-		 * _previous_ snap context.
-		 *
-		 * ...unless it's a snap deletion!
-		 */
-		if (!deletion)
-			queue_realm_cap_snaps(realm);
-	} else {
-		dout("update_snap_trace %llx %p seq %lld unchanged\n",
-		     realm->ino, realm, realm->seq);
-	}
-
 	/* ensure the parent is correct */
 	err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent));
 	if (err < 0)
@@ -651,6 +637,8 @@ more:
 	invalidate += err;
 
 	if (le64_to_cpu(ri->seq) > realm->seq) {
+		dout("update_snap_trace updating %llx %p %lld -> %lld\n",
+		     realm->ino, realm, realm->seq, le64_to_cpu(ri->seq));
 		/* update realm parameters, snap lists */
 		realm->seq = le64_to_cpu(ri->seq);
 		realm->created = le64_to_cpu(ri->created);
@@ -668,9 +656,17 @@ more:
 		if (err < 0)
 			goto fail;
 
+		/* queue realm for cap_snap creation */
+		list_add(&realm->dirty_item, &dirty_realms);
+
 		invalidate = 1;
 	} else if (!realm->cached_context) {
+		dout("update_snap_trace %llx %p seq %lld new\n",
+		     realm->ino, realm, realm->seq);
 		invalidate = 1;
+	} else {
+		dout("update_snap_trace %llx %p seq %lld unchanged\n",
+		     realm->ino, realm, realm->seq);
 	}
 
 	dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino,
@@ -683,6 +679,14 @@ more:
 	if (invalidate)
 		rebuild_snap_realms(realm);
 
+	/*
+	 * queue cap snaps _after_ we've built the new snap contexts,
+	 * so that i_head_snapc can be set appropriately.
+	 */
+	list_for_each_entry(realm, &dirty_realms, dirty_item) {
+		queue_realm_cap_snaps(realm);
+	}
+
 	__cleanup_empty_realms(mdsc);
 	return 0;
 
@@ -715,7 +719,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
 		igrab(inode);
 		spin_unlock(&mdsc->snap_flush_lock);
 		spin_lock(&inode->i_lock);
-		__ceph_flush_snaps(ci, &session);
+		__ceph_flush_snaps(ci, &session, 0);
 		spin_unlock(&inode->i_lock);
 		iput(inode);
 		spin_lock(&mdsc->snap_flush_lock);
@@ -745,7 +749,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 		      struct ceph_mds_session *session,
 		      struct ceph_msg *msg)
 {
-	struct super_block *sb = mdsc->client->sb;
+	struct super_block *sb = mdsc->fsc->sb;
 	int mds = session->s_mds;
 	u64 split;
 	int op;
@@ -816,6 +820,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			};
 			struct inode *inode = ceph_find_inode(sb, vino);
 			struct ceph_inode_info *ci;
+			struct ceph_snap_realm *oldrealm;
 
 			if (!inode)
 				continue;
@@ -841,18 +846,19 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			dout(" will move %p to split realm %llx %p\n",
 			     inode, realm->ino, realm);
 			/*
-			 * Remove the inode from the realm's inode
-			 * list, but don't add it to the new realm
-			 * yet.  We don't want the cap_snap to be
-			 * queued (again) by ceph_update_snap_trace()
-			 * below.  Queue it _now_, under the old context.
+			 * Move the inode to the new realm
 			 */
 			spin_lock(&realm->inodes_with_caps_lock);
 			list_del_init(&ci->i_snap_realm_item);
+			list_add(&ci->i_snap_realm_item,
+				 &realm->inodes_with_caps);
+			oldrealm = ci->i_snap_realm;
+			ci->i_snap_realm = realm;
 			spin_unlock(&realm->inodes_with_caps_lock);
 			spin_unlock(&inode->i_lock);
 
-			ceph_queue_cap_snap(ci);
+			ceph_get_snap_realm(mdsc, realm);
+			ceph_put_snap_realm(mdsc, oldrealm);
 
 			iput(inode);
 			continue;
@@ -880,43 +886,9 @@ skip_inode:
 	ceph_update_snap_trace(mdsc, p, e,
 			       op == CEPH_SNAP_OP_DESTROY);
 
-	if (op == CEPH_SNAP_OP_SPLIT) {
-		/*
-		 * ok, _now_ add the inodes into the new realm.
-		 */
-		for (i = 0; i < num_split_inos; i++) {
-			struct ceph_vino vino = {
-				.ino = le64_to_cpu(split_inos[i]),
-				.snap = CEPH_NOSNAP,
-			};
-			struct inode *inode = ceph_find_inode(sb, vino);
-			struct ceph_inode_info *ci;
-
-			if (!inode)
-				continue;
-			ci = ceph_inode(inode);
-			spin_lock(&inode->i_lock);
-			if (list_empty(&ci->i_snap_realm_item)) {
-				struct ceph_snap_realm *oldrealm =
-					ci->i_snap_realm;
-
-				dout(" moving %p to split realm %llx %p\n",
-				     inode, realm->ino, realm);
-				spin_lock(&realm->inodes_with_caps_lock);
-				list_add(&ci->i_snap_realm_item,
-					 &realm->inodes_with_caps);
-				ci->i_snap_realm = realm;
-				spin_unlock(&realm->inodes_with_caps_lock);
-				ceph_get_snap_realm(mdsc, realm);
-				ceph_put_snap_realm(mdsc, oldrealm);
-			}
-			spin_unlock(&inode->i_lock);
-			iput(inode);
-		}
-
+	if (op == CEPH_SNAP_OP_SPLIT)
 		/* we took a reference when we created the realm, above */
 		ceph_put_snap_realm(mdsc, realm);
-	}
 
 	__cleanup_empty_realms(mdsc);
 
diff --git a/fs/ceph/ceph_strings.c b/fs/ceph/strings.c
similarity index 59%
rename from fs/ceph/ceph_strings.c
rename to fs/ceph/strings.c
index c6179d3a26a2..cd5097d7c804 100644
--- a/fs/ceph/ceph_strings.c
+++ b/fs/ceph/strings.c
@@ -1,71 +1,9 @@
 /*
- * Ceph string constants
+ * Ceph fs string constants
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
-const char *ceph_entity_type_name(int type)
-{
-	switch (type) {
-	case CEPH_ENTITY_TYPE_MDS: return "mds";
-	case CEPH_ENTITY_TYPE_OSD: return "osd";
-	case CEPH_ENTITY_TYPE_MON: return "mon";
-	case CEPH_ENTITY_TYPE_CLIENT: return "client";
-	case CEPH_ENTITY_TYPE_AUTH: return "auth";
-	default: return "unknown";
-	}
-}
-
-const char *ceph_osd_op_name(int op)
-{
-	switch (op) {
-	case CEPH_OSD_OP_READ: return "read";
-	case CEPH_OSD_OP_STAT: return "stat";
-
-	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
-
-	case CEPH_OSD_OP_WRITE: return "write";
-	case CEPH_OSD_OP_DELETE: return "delete";
-	case CEPH_OSD_OP_TRUNCATE: return "truncate";
-	case CEPH_OSD_OP_ZERO: return "zero";
-	case CEPH_OSD_OP_WRITEFULL: return "writefull";
-	case CEPH_OSD_OP_ROLLBACK: return "rollback";
-
-	case CEPH_OSD_OP_APPEND: return "append";
-	case CEPH_OSD_OP_STARTSYNC: return "startsync";
-	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
-	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
-
-	case CEPH_OSD_OP_TMAPUP: return "tmapup";
-	case CEPH_OSD_OP_TMAPGET: return "tmapget";
-	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
-
-	case CEPH_OSD_OP_GETXATTR: return "getxattr";
-	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
-	case CEPH_OSD_OP_SETXATTR: return "setxattr";
-	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
-	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
-	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
-	case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
-
-	case CEPH_OSD_OP_PULL: return "pull";
-	case CEPH_OSD_OP_PUSH: return "push";
-	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
-	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
-	case CEPH_OSD_OP_SCRUB: return "scrub";
-
-	case CEPH_OSD_OP_WRLOCK: return "wrlock";
-	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
-	case CEPH_OSD_OP_RDLOCK: return "rdlock";
-	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
-	case CEPH_OSD_OP_UPLOCK: return "uplock";
-	case CEPH_OSD_OP_DNLOCK: return "dnlock";
-
-	case CEPH_OSD_OP_CALL: return "call";
-
-	case CEPH_OSD_OP_PGLS: return "pgls";
-	}
-	return "???";
-}
 
 const char *ceph_mds_state_name(int s)
 {
@@ -177,17 +115,3 @@ const char *ceph_snap_op_name(int o)
 	}
 	return "???";
 }
-
-const char *ceph_pool_op_name(int op)
-{
-	switch (op) {
-	case POOL_OP_CREATE: return "create";
-	case POOL_OP_DELETE: return "delete";
-	case POOL_OP_AUID_CHANGE: return "auid change";
-	case POOL_OP_CREATE_SNAP: return "create snap";
-	case POOL_OP_DELETE_SNAP: return "delete snap";
-	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
-	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
-	}
-	return "???";
-}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 9922628532b2..d6e0e0421891 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1,5 +1,5 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/backing-dev.h>
 #include <linux/ctype.h>
@@ -15,10 +15,13 @@
 #include <linux/statfs.h>
 #include <linux/string.h>
 
-#include "decode.h"
 #include "super.h"
-#include "mon_client.h"
-#include "auth.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
 
 /*
  * Ceph superblock operations
@@ -26,36 +29,22 @@
  * Handle the basics of mounting, unmounting.
  */
 
-
-/*
- * find filename portion of a path (/foo/bar/baz -> baz)
- */
-const char *ceph_file_part(const char *s, int len)
-{
-	const char *e = s + len;
-
-	while (e != s && *(e-1) != '/')
-		e--;
-	return e;
-}
-
-
 /*
  * super ops
  */
 static void ceph_put_super(struct super_block *s)
 {
-	struct ceph_client *client = ceph_sb_to_client(s);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
 
 	dout("put_super\n");
-	ceph_mdsc_close_sessions(&client->mdsc);
+	ceph_mdsc_close_sessions(fsc->mdsc);
 
 	/*
 	 * ensure we release the bdi before put_anon_super releases
 	 * the device name.
 	 */
-	if (s->s_bdi == &client->backing_dev_info) {
-		bdi_unregister(&client->backing_dev_info);
+	if (s->s_bdi == &fsc->backing_dev_info) {
+		bdi_unregister(&fsc->backing_dev_info);
 		s->s_bdi = NULL;
 	}
 
@@ -64,14 +53,14 @@ static void ceph_put_super(struct super_block *s)
 
 static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct ceph_client *client = ceph_inode_to_client(dentry->d_inode);
-	struct ceph_monmap *monmap = client->monc.monmap;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(dentry->d_inode);
+	struct ceph_monmap *monmap = fsc->client->monc.monmap;
 	struct ceph_statfs st;
 	u64 fsid;
 	int err;
 
 	dout("statfs\n");
-	err = ceph_monc_do_statfs(&client->monc, &st);
+	err = ceph_monc_do_statfs(&fsc->client->monc, &st);
 	if (err < 0)
 		return err;
 
@@ -104,238 +93,28 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static int ceph_sync_fs(struct super_block *sb, int wait)
 {
-	struct ceph_client *client = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 
 	if (!wait) {
 		dout("sync_fs (non-blocking)\n");
-		ceph_flush_dirty_caps(&client->mdsc);
+		ceph_flush_dirty_caps(fsc->mdsc);
 		dout("sync_fs (non-blocking) done\n");
 		return 0;
 	}
 
 	dout("sync_fs (blocking)\n");
-	ceph_osdc_sync(&ceph_sb_to_client(sb)->osdc);
-	ceph_mdsc_sync(&ceph_sb_to_client(sb)->mdsc);
+	ceph_osdc_sync(&fsc->client->osdc);
+	ceph_mdsc_sync(fsc->mdsc);
 	dout("sync_fs (blocking) done\n");
 	return 0;
 }
 
-static int default_congestion_kb(void)
-{
-	int congestion_kb;
-
-	/*
-	 * Copied from NFS
-	 *
-	 * congestion size, scale with available memory.
-	 *
-	 *  64MB:    8192k
-	 * 128MB:   11585k
-	 * 256MB:   16384k
-	 * 512MB:   23170k
-	 *   1GB:   32768k
-	 *   2GB:   46340k
-	 *   4GB:   65536k
-	 *   8GB:   92681k
-	 *  16GB:  131072k
-	 *
-	 * This allows larger machines to have larger/more transfers.
-	 * Limit the default to 256M
-	 */
-	congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
-	if (congestion_kb > 256*1024)
-		congestion_kb = 256*1024;
-
-	return congestion_kb;
-}
-
-/**
- * ceph_show_options - Show mount options in /proc/mounts
- * @m: seq_file to write to
- * @mnt: mount descriptor
- */
-static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
-{
-	struct ceph_client *client = ceph_sb_to_client(mnt->mnt_sb);
-	struct ceph_mount_args *args = client->mount_args;
-
-	if (args->flags & CEPH_OPT_FSID)
-		seq_printf(m, ",fsid=%pU", &args->fsid);
-	if (args->flags & CEPH_OPT_NOSHARE)
-		seq_puts(m, ",noshare");
-	if (args->flags & CEPH_OPT_DIRSTAT)
-		seq_puts(m, ",dirstat");
-	if ((args->flags & CEPH_OPT_RBYTES) == 0)
-		seq_puts(m, ",norbytes");
-	if (args->flags & CEPH_OPT_NOCRC)
-		seq_puts(m, ",nocrc");
-	if (args->flags & CEPH_OPT_NOASYNCREADDIR)
-		seq_puts(m, ",noasyncreaddir");
-
-	if (args->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
-		seq_printf(m, ",mount_timeout=%d", args->mount_timeout);
-	if (args->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
-		seq_printf(m, ",osd_idle_ttl=%d", args->osd_idle_ttl);
-	if (args->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
-		seq_printf(m, ",osdtimeout=%d", args->osd_timeout);
-	if (args->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
-		seq_printf(m, ",osdkeepalivetimeout=%d",
-			 args->osd_keepalive_timeout);
-	if (args->wsize)
-		seq_printf(m, ",wsize=%d", args->wsize);
-	if (args->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
-		seq_printf(m, ",rsize=%d", args->rsize);
-	if (args->congestion_kb != default_congestion_kb())
-		seq_printf(m, ",write_congestion_kb=%d", args->congestion_kb);
-	if (args->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
-		seq_printf(m, ",caps_wanted_delay_min=%d",
-			 args->caps_wanted_delay_min);
-	if (args->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT)
-		seq_printf(m, ",caps_wanted_delay_max=%d",
-			   args->caps_wanted_delay_max);
-	if (args->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT)
-		seq_printf(m, ",cap_release_safety=%d",
-			   args->cap_release_safety);
-	if (args->max_readdir != CEPH_MAX_READDIR_DEFAULT)
-		seq_printf(m, ",readdir_max_entries=%d", args->max_readdir);
-	if (args->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT)
-		seq_printf(m, ",readdir_max_bytes=%d", args->max_readdir_bytes);
-	if (strcmp(args->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
-		seq_printf(m, ",snapdirname=%s", args->snapdir_name);
-	if (args->name)
-		seq_printf(m, ",name=%s", args->name);
-	if (args->secret)
-		seq_puts(m, ",secret=<hidden>");
-	return 0;
-}
-
-/*
- * caches
- */
-struct kmem_cache *ceph_inode_cachep;
-struct kmem_cache *ceph_cap_cachep;
-struct kmem_cache *ceph_dentry_cachep;
-struct kmem_cache *ceph_file_cachep;
-
-static void ceph_inode_init_once(void *foo)
-{
-	struct ceph_inode_info *ci = foo;
-	inode_init_once(&ci->vfs_inode);
-}
-
-static int __init init_caches(void)
-{
-	ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
-				      sizeof(struct ceph_inode_info),
-				      __alignof__(struct ceph_inode_info),
-				      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
-				      ceph_inode_init_once);
-	if (ceph_inode_cachep == NULL)
-		return -ENOMEM;
-
-	ceph_cap_cachep = KMEM_CACHE(ceph_cap,
-				     SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
-	if (ceph_cap_cachep == NULL)
-		goto bad_cap;
-
-	ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info,
-					SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
-	if (ceph_dentry_cachep == NULL)
-		goto bad_dentry;
-
-	ceph_file_cachep = KMEM_CACHE(ceph_file_info,
-				      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
-	if (ceph_file_cachep == NULL)
-		goto bad_file;
-
-	return 0;
-
-bad_file:
-	kmem_cache_destroy(ceph_dentry_cachep);
-bad_dentry:
-	kmem_cache_destroy(ceph_cap_cachep);
-bad_cap:
-	kmem_cache_destroy(ceph_inode_cachep);
-	return -ENOMEM;
-}
-
-static void destroy_caches(void)
-{
-	kmem_cache_destroy(ceph_inode_cachep);
-	kmem_cache_destroy(ceph_cap_cachep);
-	kmem_cache_destroy(ceph_dentry_cachep);
-	kmem_cache_destroy(ceph_file_cachep);
-}
-
-
-/*
- * ceph_umount_begin - initiate forced umount.  Tear down down the
- * mount, skipping steps that may hang while waiting for server(s).
- */
-static void ceph_umount_begin(struct super_block *sb)
-{
-	struct ceph_client *client = ceph_sb_to_client(sb);
-
-	dout("ceph_umount_begin - starting forced umount\n");
-	if (!client)
-		return;
-	client->mount_state = CEPH_MOUNT_SHUTDOWN;
-	return;
-}
-
-static const struct super_operations ceph_super_ops = {
-	.alloc_inode	= ceph_alloc_inode,
-	.destroy_inode	= ceph_destroy_inode,
-	.write_inode    = ceph_write_inode,
-	.sync_fs        = ceph_sync_fs,
-	.put_super	= ceph_put_super,
-	.show_options   = ceph_show_options,
-	.statfs		= ceph_statfs,
-	.umount_begin   = ceph_umount_begin,
-};
-
-
-const char *ceph_msg_type_name(int type)
-{
-	switch (type) {
-	case CEPH_MSG_SHUTDOWN: return "shutdown";
-	case CEPH_MSG_PING: return "ping";
-	case CEPH_MSG_AUTH: return "auth";
-	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
-	case CEPH_MSG_MON_MAP: return "mon_map";
-	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
-	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
-	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
-	case CEPH_MSG_STATFS: return "statfs";
-	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
-	case CEPH_MSG_MDS_MAP: return "mds_map";
-	case CEPH_MSG_CLIENT_SESSION: return "client_session";
-	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
-	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
-	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
-	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
-	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
-	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
-	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
-	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
-	case CEPH_MSG_OSD_MAP: return "osd_map";
-	case CEPH_MSG_OSD_OP: return "osd_op";
-	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
-	default: return "unknown";
-	}
-}
-
-
 /*
  * mount options
  */
 enum {
 	Opt_wsize,
 	Opt_rsize,
-	Opt_osdtimeout,
-	Opt_osdkeepalivetimeout,
-	Opt_mount_timeout,
-	Opt_osd_idle_ttl,
 	Opt_caps_wanted_delay_min,
 	Opt_caps_wanted_delay_max,
 	Opt_cap_release_safety,
@@ -344,29 +123,19 @@ enum {
 	Opt_congestion_kb,
 	Opt_last_int,
 	/* int args above */
-	Opt_fsid,
 	Opt_snapdirname,
-	Opt_name,
-	Opt_secret,
 	Opt_last_string,
 	/* string args above */
-	Opt_ip,
-	Opt_noshare,
 	Opt_dirstat,
 	Opt_nodirstat,
 	Opt_rbytes,
 	Opt_norbytes,
-	Opt_nocrc,
 	Opt_noasyncreaddir,
 };
 
-static match_table_t arg_tokens = {
+static match_table_t fsopt_tokens = {
 	{Opt_wsize, "wsize=%d"},
 	{Opt_rsize, "rsize=%d"},
-	{Opt_osdtimeout, "osdtimeout=%d"},
-	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
-	{Opt_mount_timeout, "mount_timeout=%d"},
-	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
 	{Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
 	{Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
 	{Opt_cap_release_safety, "cap_release_safety=%d"},
@@ -374,403 +143,459 @@ static match_table_t arg_tokens = {
 	{Opt_readdir_max_bytes, "readdir_max_bytes=%d"},
 	{Opt_congestion_kb, "write_congestion_kb=%d"},
 	/* int args above */
-	{Opt_fsid, "fsid=%s"},
 	{Opt_snapdirname, "snapdirname=%s"},
-	{Opt_name, "name=%s"},
-	{Opt_secret, "secret=%s"},
 	/* string args above */
-	{Opt_ip, "ip=%s"},
-	{Opt_noshare, "noshare"},
 	{Opt_dirstat, "dirstat"},
 	{Opt_nodirstat, "nodirstat"},
 	{Opt_rbytes, "rbytes"},
 	{Opt_norbytes, "norbytes"},
-	{Opt_nocrc, "nocrc"},
 	{Opt_noasyncreaddir, "noasyncreaddir"},
 	{-1, NULL}
 };
 
-static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+static int parse_fsopt_token(char *c, void *private)
 {
-	int i = 0;
-	char tmp[3];
-	int err = -EINVAL;
-	int d;
-
-	dout("parse_fsid '%s'\n", str);
-	tmp[2] = 0;
-	while (*str && i < 16) {
-		if (ispunct(*str)) {
-			str++;
-			continue;
+	struct ceph_mount_options *fsopt = private;
+	substring_t argstr[MAX_OPT_ARGS];
+	int token, intval, ret;
+
+	token = match_token((char *)c, fsopt_tokens, argstr);
+	if (token < 0)
+		return -EINVAL;
+
+	if (token < Opt_last_int) {
+		ret = match_int(&argstr[0], &intval);
+		if (ret < 0) {
+			pr_err("bad mount option arg (not int) "
+			       "at '%s'\n", c);
+			return ret;
 		}
-		if (!isxdigit(str[0]) || !isxdigit(str[1]))
-			break;
-		tmp[0] = str[0];
-		tmp[1] = str[1];
-		if (sscanf(tmp, "%x", &d) < 1)
-			break;
-		fsid->fsid[i] = d & 0xff;
-		i++;
-		str += 2;
+		dout("got int token %d val %d\n", token, intval);
+	} else if (token > Opt_last_int && token < Opt_last_string) {
+		dout("got string token %d val %s\n", token,
+		     argstr[0].from);
+	} else {
+		dout("got token %d\n", token);
 	}
 
-	if (i == 16)
-		err = 0;
-	dout("parse_fsid ret %d got fsid %pU", err, fsid);
-	return err;
+	switch (token) {
+	case Opt_snapdirname:
+		kfree(fsopt->snapdir_name);
+		fsopt->snapdir_name = kstrndup(argstr[0].from,
+					       argstr[0].to-argstr[0].from,
+					       GFP_KERNEL);
+		if (!fsopt->snapdir_name)
+			return -ENOMEM;
+		break;
+
+		/* misc */
+	case Opt_wsize:
+		fsopt->wsize = intval;
+		break;
+	case Opt_rsize:
+		fsopt->rsize = intval;
+		break;
+	case Opt_caps_wanted_delay_min:
+		fsopt->caps_wanted_delay_min = intval;
+		break;
+	case Opt_caps_wanted_delay_max:
+		fsopt->caps_wanted_delay_max = intval;
+		break;
+	case Opt_readdir_max_entries:
+		fsopt->max_readdir = intval;
+		break;
+	case Opt_readdir_max_bytes:
+		fsopt->max_readdir_bytes = intval;
+		break;
+	case Opt_congestion_kb:
+		fsopt->congestion_kb = intval;
+		break;
+	case Opt_dirstat:
+		fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT;
+		break;
+	case Opt_nodirstat:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT;
+		break;
+	case Opt_rbytes:
+		fsopt->flags |= CEPH_MOUNT_OPT_RBYTES;
+		break;
+	case Opt_norbytes:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
+		break;
+	case Opt_noasyncreaddir:
+		fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
+		break;
+	default:
+		BUG_ON(token);
+	}
+	return 0;
 }
 
-static struct ceph_mount_args *parse_mount_args(int flags, char *options,
-						const char *dev_name,
-						const char **path)
+static void destroy_mount_options(struct ceph_mount_options *args)
 {
-	struct ceph_mount_args *args;
-	const char *c;
-	int err = -ENOMEM;
-	substring_t argstr[MAX_OPT_ARGS];
+	dout("destroy_mount_options %p\n", args);
+	kfree(args->snapdir_name);
+	kfree(args);
+}
 
-	args = kzalloc(sizeof(*args), GFP_KERNEL);
-	if (!args)
-		return ERR_PTR(-ENOMEM);
-	args->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*args->mon_addr),
-				 GFP_KERNEL);
-	if (!args->mon_addr)
-		goto out;
+static int strcmp_null(const char *s1, const char *s2)
+{
+	if (!s1 && !s2)
+		return 0;
+	if (s1 && !s2)
+		return -1;
+	if (!s1 && s2)
+		return 1;
+	return strcmp(s1, s2);
+}
 
-	dout("parse_mount_args %p, dev_name '%s'\n", args, dev_name);
-
-	/* start with defaults */
-	args->sb_flags = flags;
-	args->flags = CEPH_OPT_DEFAULT;
-	args->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
-	args->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
-	args->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
-	args->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
-	args->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
-	args->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
-	args->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
-	args->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
-	args->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
-	args->max_readdir = CEPH_MAX_READDIR_DEFAULT;
-	args->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
-	args->congestion_kb = default_congestion_kb();
-
-	/* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
-	err = -EINVAL;
-	if (!dev_name)
-		goto out;
-	*path = strstr(dev_name, ":/");
-	if (*path == NULL) {
-		pr_err("device name is missing path (no :/ in %s)\n",
-		       dev_name);
-		goto out;
-	}
+static int compare_mount_options(struct ceph_mount_options *new_fsopt,
+				 struct ceph_options *new_opt,
+				 struct ceph_fs_client *fsc)
+{
+	struct ceph_mount_options *fsopt1 = new_fsopt;
+	struct ceph_mount_options *fsopt2 = fsc->mount_options;
+	int ofs = offsetof(struct ceph_mount_options, snapdir_name);
+	int ret;
 
-	/* get mon ip(s) */
-	err = ceph_parse_ips(dev_name, *path, args->mon_addr,
-			     CEPH_MAX_MON, &args->num_mon);
-	if (err < 0)
-		goto out;
+	ret = memcmp(fsopt1, fsopt2, ofs);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name);
+	if (ret)
+		return ret;
+
+	return ceph_compare_options(new_opt, fsc->client);
+}
+
+static int parse_mount_options(struct ceph_mount_options **pfsopt,
+			       struct ceph_options **popt,
+			       int flags, char *options,
+			       const char *dev_name,
+			       const char **path)
+{
+	struct ceph_mount_options *fsopt;
+	const char *dev_name_end;
+	int err = -ENOMEM;
+
+	fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL);
+	if (!fsopt)
+		return -ENOMEM;
+
+	dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name);
+
+        fsopt->sb_flags = flags;
+        fsopt->flags = CEPH_MOUNT_OPT_DEFAULT;
+
+        fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
+        fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+        fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
+        fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
+        fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
+        fsopt->congestion_kb = default_congestion_kb();
+	
+        /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
+        err = -EINVAL;
+        if (!dev_name)
+                goto out;
+        *path = strstr(dev_name, ":/");
+        if (*path == NULL) {
+                pr_err("device name is missing path (no :/ in %s)\n",
+                       dev_name);
+                goto out;
+        }
+	dev_name_end = *path;
+	dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
 
 	/* path on server */
 	*path += 2;
 	dout("server path '%s'\n", *path);
 
-	/* parse mount options */
-	while ((c = strsep(&options, ",")) != NULL) {
-		int token, intval, ret;
-		if (!*c)
-			continue;
-		err = -EINVAL;
-		token = match_token((char *)c, arg_tokens, argstr);
-		if (token < 0) {
-			pr_err("bad mount option at '%s'\n", c);
-			goto out;
-		}
-		if (token < Opt_last_int) {
-			ret = match_int(&argstr[0], &intval);
-			if (ret < 0) {
-				pr_err("bad mount option arg (not int) "
-				       "at '%s'\n", c);
-				continue;
-			}
-			dout("got int token %d val %d\n", token, intval);
-		} else if (token > Opt_last_int && token < Opt_last_string) {
-			dout("got string token %d val %s\n", token,
-			     argstr[0].from);
-		} else {
-			dout("got token %d\n", token);
-		}
-		switch (token) {
-		case Opt_ip:
-			err = ceph_parse_ips(argstr[0].from,
-					     argstr[0].to,
-					     &args->my_addr,
-					     1, NULL);
-			if (err < 0)
-				goto out;
-			args->flags |= CEPH_OPT_MYIP;
-			break;
-
-		case Opt_fsid:
-			err = parse_fsid(argstr[0].from, &args->fsid);
-			if (err == 0)
-				args->flags |= CEPH_OPT_FSID;
-			break;
-		case Opt_snapdirname:
-			kfree(args->snapdir_name);
-			args->snapdir_name = kstrndup(argstr[0].from,
-					      argstr[0].to-argstr[0].from,
-					      GFP_KERNEL);
-			break;
-		case Opt_name:
-			args->name = kstrndup(argstr[0].from,
-					      argstr[0].to-argstr[0].from,
-					      GFP_KERNEL);
-			break;
-		case Opt_secret:
-			args->secret = kstrndup(argstr[0].from,
-						argstr[0].to-argstr[0].from,
-						GFP_KERNEL);
-			break;
-
-			/* misc */
-		case Opt_wsize:
-			args->wsize = intval;
-			break;
-		case Opt_rsize:
-			args->rsize = intval;
-			break;
-		case Opt_osdtimeout:
-			args->osd_timeout = intval;
-			break;
-		case Opt_osdkeepalivetimeout:
-			args->osd_keepalive_timeout = intval;
-			break;
-		case Opt_osd_idle_ttl:
-			args->osd_idle_ttl = intval;
-			break;
-		case Opt_mount_timeout:
-			args->mount_timeout = intval;
-			break;
-		case Opt_caps_wanted_delay_min:
-			args->caps_wanted_delay_min = intval;
-			break;
-		case Opt_caps_wanted_delay_max:
-			args->caps_wanted_delay_max = intval;
-			break;
-		case Opt_readdir_max_entries:
-			args->max_readdir = intval;
-			break;
-		case Opt_readdir_max_bytes:
-			args->max_readdir_bytes = intval;
-			break;
-		case Opt_congestion_kb:
-			args->congestion_kb = intval;
-			break;
-
-		case Opt_noshare:
-			args->flags |= CEPH_OPT_NOSHARE;
-			break;
-
-		case Opt_dirstat:
-			args->flags |= CEPH_OPT_DIRSTAT;
-			break;
-		case Opt_nodirstat:
-			args->flags &= ~CEPH_OPT_DIRSTAT;
-			break;
-		case Opt_rbytes:
-			args->flags |= CEPH_OPT_RBYTES;
-			break;
-		case Opt_norbytes:
-			args->flags &= ~CEPH_OPT_RBYTES;
-			break;
-		case Opt_nocrc:
-			args->flags |= CEPH_OPT_NOCRC;
-			break;
-		case Opt_noasyncreaddir:
-			args->flags |= CEPH_OPT_NOASYNCREADDIR;
-			break;
-
-		default:
-			BUG_ON(token);
-		}
-	}
-	return args;
+	err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+				 parse_fsopt_token, (void *)fsopt);
+	if (err)
+		goto out;
+
+	/* success */
+	*pfsopt = fsopt;
+	return 0;
 
 out:
-	kfree(args->mon_addr);
-	kfree(args);
-	return ERR_PTR(err);
+	destroy_mount_options(fsopt);
+	return err;
 }
 
-static void destroy_mount_args(struct ceph_mount_args *args)
+/**
+ * ceph_show_options - Show mount options in /proc/mounts
+ * @m: seq_file to write to
+ * @mnt: mount descriptor
+ */
+static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
 {
-	dout("destroy_mount_args %p\n", args);
-	kfree(args->snapdir_name);
-	args->snapdir_name = NULL;
-	kfree(args->name);
-	args->name = NULL;
-	kfree(args->secret);
-	args->secret = NULL;
-	kfree(args);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(mnt->mnt_sb);
+	struct ceph_mount_options *fsopt = fsc->mount_options;
+	struct ceph_options *opt = fsc->client->options;
+
+	if (opt->flags & CEPH_OPT_FSID)
+		seq_printf(m, ",fsid=%pU", &opt->fsid);
+	if (opt->flags & CEPH_OPT_NOSHARE)
+		seq_puts(m, ",noshare");
+	if (opt->flags & CEPH_OPT_NOCRC)
+		seq_puts(m, ",nocrc");
+
+	if (opt->name)
+		seq_printf(m, ",name=%s", opt->name);
+	if (opt->secret)
+		seq_puts(m, ",secret=<hidden>");
+
+	if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
+		seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
+	if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
+		seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
+	if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
+		seq_printf(m, ",osdtimeout=%d", opt->osd_timeout);
+	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
+		seq_printf(m, ",osdkeepalivetimeout=%d",
+			   opt->osd_keepalive_timeout);
+
+	if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT)
+		seq_puts(m, ",dirstat");
+	if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES) == 0)
+		seq_puts(m, ",norbytes");
+	if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
+		seq_puts(m, ",noasyncreaddir");
+
+	if (fsopt->wsize)
+		seq_printf(m, ",wsize=%d", fsopt->wsize);
+	if (fsopt->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
+		seq_printf(m, ",rsize=%d", fsopt->rsize);
+	if (fsopt->congestion_kb != default_congestion_kb())
+		seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
+	if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
+		seq_printf(m, ",caps_wanted_delay_min=%d",
+			 fsopt->caps_wanted_delay_min);
+	if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT)
+		seq_printf(m, ",caps_wanted_delay_max=%d",
+			   fsopt->caps_wanted_delay_max);
+	if (fsopt->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT)
+		seq_printf(m, ",cap_release_safety=%d",
+			   fsopt->cap_release_safety);
+	if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT)
+		seq_printf(m, ",readdir_max_entries=%d", fsopt->max_readdir);
+	if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT)
+		seq_printf(m, ",readdir_max_bytes=%d", fsopt->max_readdir_bytes);
+	if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
+		seq_printf(m, ",snapdirname=%s", fsopt->snapdir_name);
+	return 0;
 }
 
 /*
- * create a fresh client instance
+ * handle any mon messages the standard library doesn't understand.
+ * return error if we don't either.
  */
-static struct ceph_client *ceph_create_client(struct ceph_mount_args *args)
+static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg)
 {
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc = client->private;
+	int type = le16_to_cpu(msg->hdr.type);
+
+	switch (type) {
+	case CEPH_MSG_MDS_MAP:
+		ceph_mdsc_handle_map(fsc->mdsc, msg);
+		return 0;
+
+	default:
+		return -1;
+	}
+}
+
+/*
+ * create a new fs client
+ */
+struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
+					struct ceph_options *opt)
+{
+	struct ceph_fs_client *fsc;
 	int err = -ENOMEM;
 
-	client = kzalloc(sizeof(*client), GFP_KERNEL);
-	if (client == NULL)
+	fsc = kzalloc(sizeof(*fsc), GFP_KERNEL);
+	if (!fsc)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_init(&client->mount_mutex);
-
-	init_waitqueue_head(&client->auth_wq);
+	fsc->client = ceph_create_client(opt, fsc);
+	if (IS_ERR(fsc->client)) {
+		err = PTR_ERR(fsc->client);
+		goto fail;
+	}
+	fsc->client->extra_mon_dispatch = extra_mon_dispatch;
+	fsc->client->supported_features |= CEPH_FEATURE_FLOCK;
+	fsc->client->monc.want_mdsmap = 1;
 
-	client->sb = NULL;
-	client->mount_state = CEPH_MOUNT_MOUNTING;
-	client->mount_args = args;
+	fsc->mount_options = fsopt;
 
-	client->msgr = NULL;
+	fsc->sb = NULL;
+	fsc->mount_state = CEPH_MOUNT_MOUNTING;
 
-	client->auth_err = 0;
-	atomic_long_set(&client->writeback_count, 0);
+	atomic_long_set(&fsc->writeback_count, 0);
 
-	err = bdi_init(&client->backing_dev_info);
+	err = bdi_init(&fsc->backing_dev_info);
 	if (err < 0)
-		goto fail;
+		goto fail_client;
 
 	err = -ENOMEM;
-	client->wb_wq = create_workqueue("ceph-writeback");
-	if (client->wb_wq == NULL)
+	fsc->wb_wq = create_workqueue("ceph-writeback");
+	if (fsc->wb_wq == NULL)
 		goto fail_bdi;
-	client->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
-	if (client->pg_inv_wq == NULL)
+	fsc->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
+	if (fsc->pg_inv_wq == NULL)
 		goto fail_wb_wq;
-	client->trunc_wq = create_singlethread_workqueue("ceph-trunc");
-	if (client->trunc_wq == NULL)
+	fsc->trunc_wq = create_singlethread_workqueue("ceph-trunc");
+	if (fsc->trunc_wq == NULL)
 		goto fail_pg_inv_wq;
 
 	/* set up mempools */
 	err = -ENOMEM;
-	client->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
-			      client->mount_args->wsize >> PAGE_CACHE_SHIFT);
-	if (!client->wb_pagevec_pool)
+	fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
+			      fsc->mount_options->wsize >> PAGE_CACHE_SHIFT);
+	if (!fsc->wb_pagevec_pool)
 		goto fail_trunc_wq;
 
 	/* caps */
-	client->min_caps = args->max_readdir;
+	fsc->min_caps = fsopt->max_readdir;
+
+	return fsc;
 
-	/* subsystems */
-	err = ceph_monc_init(&client->monc, client);
-	if (err < 0)
-		goto fail_mempool;
-	err = ceph_osdc_init(&client->osdc, client);
-	if (err < 0)
-		goto fail_monc;
-	err = ceph_mdsc_init(&client->mdsc, client);
-	if (err < 0)
-		goto fail_osdc;
-	return client;
-
-fail_osdc:
-	ceph_osdc_stop(&client->osdc);
-fail_monc:
-	ceph_monc_stop(&client->monc);
-fail_mempool:
-	mempool_destroy(client->wb_pagevec_pool);
 fail_trunc_wq:
-	destroy_workqueue(client->trunc_wq);
+	destroy_workqueue(fsc->trunc_wq);
 fail_pg_inv_wq:
-	destroy_workqueue(client->pg_inv_wq);
+	destroy_workqueue(fsc->pg_inv_wq);
 fail_wb_wq:
-	destroy_workqueue(client->wb_wq);
+	destroy_workqueue(fsc->wb_wq);
 fail_bdi:
-	bdi_destroy(&client->backing_dev_info);
+	bdi_destroy(&fsc->backing_dev_info);
+fail_client:
+	ceph_destroy_client(fsc->client);
 fail:
-	kfree(client);
+	kfree(fsc);
 	return ERR_PTR(err);
 }
 
-static void ceph_destroy_client(struct ceph_client *client)
+void destroy_fs_client(struct ceph_fs_client *fsc)
 {
-	dout("destroy_client %p\n", client);
+	dout("destroy_fs_client %p\n", fsc);
 
-	/* unmount */
-	ceph_mdsc_stop(&client->mdsc);
-	ceph_osdc_stop(&client->osdc);
+	destroy_workqueue(fsc->wb_wq);
+	destroy_workqueue(fsc->pg_inv_wq);
+	destroy_workqueue(fsc->trunc_wq);
 
-	/*
-	 * make sure mds and osd connections close out before destroying
-	 * the auth module, which is needed to free those connections'
-	 * ceph_authorizers.
-	 */
-	ceph_msgr_flush();
-
-	ceph_monc_stop(&client->monc);
+	bdi_destroy(&fsc->backing_dev_info);
 
-	ceph_debugfs_client_cleanup(client);
-	destroy_workqueue(client->wb_wq);
-	destroy_workqueue(client->pg_inv_wq);
-	destroy_workqueue(client->trunc_wq);
+	mempool_destroy(fsc->wb_pagevec_pool);
 
-	bdi_destroy(&client->backing_dev_info);
+	destroy_mount_options(fsc->mount_options);
 
-	if (client->msgr)
-		ceph_messenger_destroy(client->msgr);
-	mempool_destroy(client->wb_pagevec_pool);
+	ceph_fs_debugfs_cleanup(fsc);
 
-	destroy_mount_args(client->mount_args);
+	ceph_destroy_client(fsc->client);
 
-	kfree(client);
-	dout("destroy_client %p done\n", client);
+	kfree(fsc);
+	dout("destroy_fs_client %p done\n", fsc);
 }
 
 /*
- * Initially learn our fsid, or verify an fsid matches.
+ * caches
  */
-int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
+struct kmem_cache *ceph_inode_cachep;
+struct kmem_cache *ceph_cap_cachep;
+struct kmem_cache *ceph_dentry_cachep;
+struct kmem_cache *ceph_file_cachep;
+
+static void ceph_inode_init_once(void *foo)
 {
-	if (client->have_fsid) {
-		if (ceph_fsid_compare(&client->fsid, fsid)) {
-			pr_err("bad fsid, had %pU got %pU",
-			       &client->fsid, fsid);
-			return -1;
-		}
-	} else {
-		pr_info("client%lld fsid %pU\n", client->monc.auth->global_id,
-			fsid);
-		memcpy(&client->fsid, fsid, sizeof(*fsid));
-		ceph_debugfs_client_init(client);
-		client->have_fsid = true;
-	}
+	struct ceph_inode_info *ci = foo;
+	inode_init_once(&ci->vfs_inode);
+}
+
+static int __init init_caches(void)
+{
+	ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
+				      sizeof(struct ceph_inode_info),
+				      __alignof__(struct ceph_inode_info),
+				      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
+				      ceph_inode_init_once);
+	if (ceph_inode_cachep == NULL)
+		return -ENOMEM;
+
+	ceph_cap_cachep = KMEM_CACHE(ceph_cap,
+				     SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+	if (ceph_cap_cachep == NULL)
+		goto bad_cap;
+
+	ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info,
+					SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+	if (ceph_dentry_cachep == NULL)
+		goto bad_dentry;
+
+	ceph_file_cachep = KMEM_CACHE(ceph_file_info,
+				      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+	if (ceph_file_cachep == NULL)
+		goto bad_file;
+
 	return 0;
+
+bad_file:
+	kmem_cache_destroy(ceph_dentry_cachep);
+bad_dentry:
+	kmem_cache_destroy(ceph_cap_cachep);
+bad_cap:
+	kmem_cache_destroy(ceph_inode_cachep);
+	return -ENOMEM;
 }
 
+static void destroy_caches(void)
+{
+	kmem_cache_destroy(ceph_inode_cachep);
+	kmem_cache_destroy(ceph_cap_cachep);
+	kmem_cache_destroy(ceph_dentry_cachep);
+	kmem_cache_destroy(ceph_file_cachep);
+}
+
+
 /*
- * true if we have the mon map (and have thus joined the cluster)
+ * ceph_umount_begin - initiate forced umount.  Tear down down the
+ * mount, skipping steps that may hang while waiting for server(s).
  */
-static int have_mon_and_osd_map(struct ceph_client *client)
+static void ceph_umount_begin(struct super_block *sb)
 {
-	return client->monc.monmap && client->monc.monmap->epoch &&
-	       client->osdc.osdmap && client->osdc.osdmap->epoch;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+
+	dout("ceph_umount_begin - starting forced umount\n");
+	if (!fsc)
+		return;
+	fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
+	return;
 }
 
+static const struct super_operations ceph_super_ops = {
+	.alloc_inode	= ceph_alloc_inode,
+	.destroy_inode	= ceph_destroy_inode,
+	.write_inode    = ceph_write_inode,
+	.sync_fs        = ceph_sync_fs,
+	.put_super	= ceph_put_super,
+	.show_options   = ceph_show_options,
+	.statfs		= ceph_statfs,
+	.umount_begin   = ceph_umount_begin,
+};
+
 /*
  * Bootstrap mount by opening the root directory.  Note the mount
  * @started time from caller, and time out if this takes too long.
  */
-static struct dentry *open_root_dentry(struct ceph_client *client,
+static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
 				       const char *path,
 				       unsigned long started)
 {
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req = NULL;
 	int err;
 	struct dentry *root;
@@ -784,14 +609,14 @@ static struct dentry *open_root_dentry(struct ceph_client *client,
 	req->r_ino1.ino = CEPH_INO_ROOT;
 	req->r_ino1.snap = CEPH_NOSNAP;
 	req->r_started = started;
-	req->r_timeout = client->mount_args->mount_timeout * HZ;
+	req->r_timeout = fsc->client->options->mount_timeout * HZ;
 	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	if (err == 0) {
 		dout("open_root_inode success\n");
 		if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT &&
-		    client->sb->s_root == NULL)
+		    fsc->sb->s_root == NULL)
 			root = d_alloc_root(req->r_target_inode);
 		else
 			root = d_obtain_alias(req->r_target_inode);
@@ -804,105 +629,86 @@ static struct dentry *open_root_dentry(struct ceph_client *client,
 	return root;
 }
 
+
+
+
 /*
  * mount: join the ceph cluster, and open root directory.
  */
-static int ceph_mount(struct ceph_client *client, struct vfsmount *mnt,
+static int ceph_mount(struct ceph_fs_client *fsc, struct vfsmount *mnt,
 		      const char *path)
 {
-	struct ceph_entity_addr *myaddr = NULL;
 	int err;
-	unsigned long timeout = client->mount_args->mount_timeout * HZ;
 	unsigned long started = jiffies;  /* note the start time */
 	struct dentry *root;
+	int first = 0;   /* first vfsmount for this super_block */
 
 	dout("mount start\n");
-	mutex_lock(&client->mount_mutex);
-
-	/* initialize the messenger */
-	if (client->msgr == NULL) {
-		if (ceph_test_opt(client, MYIP))
-			myaddr = &client->mount_args->my_addr;
-		client->msgr = ceph_messenger_create(myaddr);
-		if (IS_ERR(client->msgr)) {
-			err = PTR_ERR(client->msgr);
-			client->msgr = NULL;
-			goto out;
-		}
-		client->msgr->nocrc = ceph_test_opt(client, NOCRC);
-	}
+	mutex_lock(&fsc->client->mount_mutex);
 
-	/* open session, and wait for mon, mds, and osd maps */
-	err = ceph_monc_open_session(&client->monc);
+	err = __ceph_open_session(fsc->client, started);
 	if (err < 0)
 		goto out;
 
-	while (!have_mon_and_osd_map(client)) {
-		err = -EIO;
-		if (timeout && time_after_eq(jiffies, started + timeout))
-			goto out;
-
-		/* wait */
-		dout("mount waiting for mon_map\n");
-		err = wait_event_interruptible_timeout(client->auth_wq,
-		       have_mon_and_osd_map(client) || (client->auth_err < 0),
-		       timeout);
-		if (err == -EINTR || err == -ERESTARTSYS)
-			goto out;
-		if (client->auth_err < 0) {
-			err = client->auth_err;
-			goto out;
-		}
-	}
-
 	dout("mount opening root\n");
-	root = open_root_dentry(client, "", started);
+	root = open_root_dentry(fsc, "", started);
 	if (IS_ERR(root)) {
 		err = PTR_ERR(root);
 		goto out;
 	}
-	if (client->sb->s_root)
+	if (fsc->sb->s_root) {
 		dput(root);
-	else
-		client->sb->s_root = root;
+	} else {
+		fsc->sb->s_root = root;
+		first = 1;
+
+		err = ceph_fs_debugfs_init(fsc);
+		if (err < 0)
+			goto fail;
+	}
 
 	if (path[0] == 0) {
 		dget(root);
 	} else {
 		dout("mount opening base mountpoint\n");
-		root = open_root_dentry(client, path, started);
+		root = open_root_dentry(fsc, path, started);
 		if (IS_ERR(root)) {
 			err = PTR_ERR(root);
-			dput(client->sb->s_root);
-			client->sb->s_root = NULL;
-			goto out;
+			goto fail;
 		}
 	}
 
 	mnt->mnt_root = root;
-	mnt->mnt_sb = client->sb;
+	mnt->mnt_sb = fsc->sb;
 
-	client->mount_state = CEPH_MOUNT_MOUNTED;
+	fsc->mount_state = CEPH_MOUNT_MOUNTED;
 	dout("mount success\n");
 	err = 0;
 
 out:
-	mutex_unlock(&client->mount_mutex);
+	mutex_unlock(&fsc->client->mount_mutex);
 	return err;
+
+fail:
+	if (first) {
+		dput(fsc->sb->s_root);
+		fsc->sb->s_root = NULL;
+	}
+	goto out;
 }
 
 static int ceph_set_super(struct super_block *s, void *data)
 {
-	struct ceph_client *client = data;
+	struct ceph_fs_client *fsc = data;
 	int ret;
 
 	dout("set_super %p data %p\n", s, data);
 
-	s->s_flags = client->mount_args->sb_flags;
+	s->s_flags = fsc->mount_options->sb_flags;
 	s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */
 
-	s->s_fs_info = client;
-	client->sb = s;
+	s->s_fs_info = fsc;
+	fsc->sb = s;
 
 	s->s_op = &ceph_super_ops;
 	s->s_export_op = &ceph_export_ops;
@@ -917,7 +723,7 @@ static int ceph_set_super(struct super_block *s, void *data)
 
 fail:
 	s->s_fs_info = NULL;
-	client->sb = NULL;
+	fsc->sb = NULL;
 	return ret;
 }
 
@@ -926,30 +732,23 @@ fail:
  */
 static int ceph_compare_super(struct super_block *sb, void *data)
 {
-	struct ceph_client *new = data;
-	struct ceph_mount_args *args = new->mount_args;
-	struct ceph_client *other = ceph_sb_to_client(sb);
-	int i;
+	struct ceph_fs_client *new = data;
+	struct ceph_mount_options *fsopt = new->mount_options;
+	struct ceph_options *opt = new->client->options;
+	struct ceph_fs_client *other = ceph_sb_to_client(sb);
 
 	dout("ceph_compare_super %p\n", sb);
-	if (args->flags & CEPH_OPT_FSID) {
-		if (ceph_fsid_compare(&args->fsid, &other->fsid)) {
-			dout("fsid doesn't match\n");
-			return 0;
-		}
-	} else {
-		/* do we share (a) monitor? */
-		for (i = 0; i < new->monc.monmap->num_mon; i++)
-			if (ceph_monmap_contains(other->monc.monmap,
-					 &new->monc.monmap->mon_inst[i].addr))
-				break;
-		if (i == new->monc.monmap->num_mon) {
-			dout("mon ip not part of monmap\n");
-			return 0;
-		}
-		dout("mon ip matches existing sb %p\n", sb);
+
+	if (compare_mount_options(fsopt, opt, other)) {
+		dout("monitor(s)/mount options don't match\n");
+		return 0;
 	}
-	if (args->sb_flags != other->mount_args->sb_flags) {
+	if ((opt->flags & CEPH_OPT_FSID) &&
+	    ceph_fsid_compare(&opt->fsid, &other->client->fsid)) {
+		dout("fsid doesn't match\n");
+		return 0;
+	}
+	if (fsopt->sb_flags != other->mount_options->sb_flags) {
 		dout("flags differ\n");
 		return 0;
 	}
@@ -961,19 +760,20 @@ static int ceph_compare_super(struct super_block *sb, void *data)
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb, struct ceph_client *client)
+static int ceph_register_bdi(struct super_block *sb,
+			     struct ceph_fs_client *fsc)
 {
 	int err;
 
 	/* set ra_pages based on rsize mount option? */
-	if (client->mount_args->rsize >= PAGE_CACHE_SIZE)
-		client->backing_dev_info.ra_pages =
-			(client->mount_args->rsize + PAGE_CACHE_SIZE - 1)
+	if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
+		fsc->backing_dev_info.ra_pages =
+			(fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
 			>> PAGE_SHIFT;
-	err = bdi_register(&client->backing_dev_info, NULL, "ceph-%d",
+	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d",
 			   atomic_long_inc_return(&bdi_seq));
 	if (!err)
-		sb->s_bdi = &client->backing_dev_info;
+		sb->s_bdi = &fsc->backing_dev_info;
 	return err;
 }
 
@@ -982,46 +782,52 @@ static int ceph_get_sb(struct file_system_type *fs_type,
 		       struct vfsmount *mnt)
 {
 	struct super_block *sb;
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc;
 	int err;
 	int (*compare_super)(struct super_block *, void *) = ceph_compare_super;
 	const char *path = NULL;
-	struct ceph_mount_args *args;
+	struct ceph_mount_options *fsopt = NULL;
+	struct ceph_options *opt = NULL;
 
 	dout("ceph_get_sb\n");
-	args = parse_mount_args(flags, data, dev_name, &path);
-	if (IS_ERR(args)) {
-		err = PTR_ERR(args);
+	err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
+	if (err < 0)
 		goto out_final;
-	}
 
 	/* create client (which we may/may not use) */
-	client = ceph_create_client(args);
-	if (IS_ERR(client)) {
-		err = PTR_ERR(client);
+	fsc = create_fs_client(fsopt, opt);
+	if (IS_ERR(fsc)) {
+		err = PTR_ERR(fsc);
+		kfree(fsopt);
+		kfree(opt);
 		goto out_final;
 	}
 
-	if (client->mount_args->flags & CEPH_OPT_NOSHARE)
+	err = ceph_mdsc_init(fsc);
+	if (err < 0)
+		goto out;
+
+	if (ceph_test_opt(fsc->client, NOSHARE))
 		compare_super = NULL;
-	sb = sget(fs_type, compare_super, ceph_set_super, client);
+	sb = sget(fs_type, compare_super, ceph_set_super, fsc);
 	if (IS_ERR(sb)) {
 		err = PTR_ERR(sb);
 		goto out;
 	}
 
-	if (ceph_sb_to_client(sb) != client) {
-		ceph_destroy_client(client);
-		client = ceph_sb_to_client(sb);
-		dout("get_sb got existing client %p\n", client);
+	if (ceph_sb_to_client(sb) != fsc) {
+		ceph_mdsc_destroy(fsc);
+		destroy_fs_client(fsc);
+		fsc = ceph_sb_to_client(sb);
+		dout("get_sb got existing client %p\n", fsc);
 	} else {
-		dout("get_sb using new client %p\n", client);
-		err = ceph_register_bdi(sb, client);
+		dout("get_sb using new client %p\n", fsc);
+		err = ceph_register_bdi(sb, fsc);
 		if (err < 0)
 			goto out_splat;
 	}
 
-	err = ceph_mount(client, mnt, path);
+	err = ceph_mount(fsc, mnt, path);
 	if (err < 0)
 		goto out_splat;
 	dout("root %p inode %p ino %llx.%llx\n", mnt->mnt_root,
@@ -1029,12 +835,13 @@ static int ceph_get_sb(struct file_system_type *fs_type,
 	return 0;
 
 out_splat:
-	ceph_mdsc_close_sessions(&client->mdsc);
+	ceph_mdsc_close_sessions(fsc->mdsc);
 	deactivate_locked_super(sb);
 	goto out_final;
 
 out:
-	ceph_destroy_client(client);
+	ceph_mdsc_destroy(fsc);
+	destroy_fs_client(fsc);
 out_final:
 	dout("ceph_get_sb fail %d\n", err);
 	return err;
@@ -1042,11 +849,12 @@ out_final:
 
 static void ceph_kill_sb(struct super_block *s)
 {
-	struct ceph_client *client = ceph_sb_to_client(s);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
 	dout("kill_sb %p\n", s);
-	ceph_mdsc_pre_umount(&client->mdsc);
+	ceph_mdsc_pre_umount(fsc->mdsc);
 	kill_anon_super(s);    /* will call put_super after sb is r/o */
-	ceph_destroy_client(client);
+	ceph_mdsc_destroy(fsc);
+	destroy_fs_client(fsc);
 }
 
 static struct file_system_type ceph_fs_type = {
@@ -1062,36 +870,20 @@ static struct file_system_type ceph_fs_type = {
 
 static int __init init_ceph(void)
 {
-	int ret = 0;
-
-	ret = ceph_debugfs_init();
-	if (ret < 0)
-		goto out;
-
-	ret = ceph_msgr_init();
-	if (ret < 0)
-		goto out_debugfs;
-
-	ret = init_caches();
+	int ret = init_caches();
 	if (ret)
-		goto out_msgr;
+		goto out;
 
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
 		goto out_icache;
 
-	pr_info("loaded (mon/mds/osd proto %d/%d/%d, osdmap %d/%d %d/%d)\n",
-		CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL,
-		CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
-		CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+	pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
+
 	return 0;
 
 out_icache:
 	destroy_caches();
-out_msgr:
-	ceph_msgr_exit();
-out_debugfs:
-	ceph_debugfs_cleanup();
 out:
 	return ret;
 }
@@ -1101,8 +893,6 @@ static void __exit exit_ceph(void)
 	dout("exit_ceph\n");
 	unregister_filesystem(&ceph_fs_type);
 	destroy_caches();
-	ceph_msgr_exit();
-	ceph_debugfs_cleanup();
 }
 
 module_init(init_ceph);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index c33897ae5725..1886294e12f7 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1,7 +1,7 @@
 #ifndef _FS_CEPH_SUPER_H
 #define _FS_CEPH_SUPER_H
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <asm/unaligned.h>
 #include <linux/backing-dev.h>
@@ -14,13 +14,7 @@
 #include <linux/writeback.h>
 #include <linux/slab.h>
 
-#include "types.h"
-#include "messenger.h"
-#include "msgpool.h"
-#include "mon_client.h"
-#include "mds_client.h"
-#include "osd_client.h"
-#include "ceph_fs.h"
+#include <linux/ceph/libceph.h>
 
 /* f_type in struct statfs */
 #define CEPH_SUPER_MAGIC 0x00c36400
@@ -30,42 +24,25 @@
 #define CEPH_BLOCK_SHIFT   20  /* 1 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
-/*
- * Supported features
- */
-#define CEPH_FEATURE_SUPPORTED CEPH_FEATURE_NOSRCADDR | CEPH_FEATURE_FLOCK
-#define CEPH_FEATURE_REQUIRED  CEPH_FEATURE_NOSRCADDR
+#define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
+#define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
+#define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
 
-/*
- * mount options
- */
-#define CEPH_OPT_FSID             (1<<0)
-#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
-#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
-#define CEPH_OPT_DIRSTAT          (1<<4) /* funky `cat dirname` for stats */
-#define CEPH_OPT_RBYTES           (1<<5) /* dir st_bytes = rbytes */
-#define CEPH_OPT_NOCRC            (1<<6) /* no data crc on writes */
-#define CEPH_OPT_NOASYNCREADDIR   (1<<7) /* no dcache readdir */
+#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES)
 
-#define CEPH_OPT_DEFAULT   (CEPH_OPT_RBYTES)
+#define ceph_set_mount_opt(fsc, opt) \
+	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
+#define ceph_test_mount_opt(fsc, opt) \
+	(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
 
-#define ceph_set_opt(client, opt) \
-	(client)->mount_args->flags |= CEPH_OPT_##opt;
-#define ceph_test_opt(client, opt) \
-	(!!((client)->mount_args->flags & CEPH_OPT_##opt))
+#define CEPH_MAX_READDIR_DEFAULT        1024
+#define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
+#define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
 
-
-struct ceph_mount_args {
-	int sb_flags;
+struct ceph_mount_options {
 	int flags;
-	struct ceph_fsid fsid;
-	struct ceph_entity_addr my_addr;
-	int num_mon;
-	struct ceph_entity_addr *mon_addr;
-	int mount_timeout;
-	int osd_idle_ttl;
-	int osd_timeout;
-	int osd_keepalive_timeout;
+	int sb_flags;
+
 	int wsize;
 	int rsize;            /* max readahead */
 	int congestion_kb;    /* max writeback in flight */
@@ -73,82 +50,25 @@ struct ceph_mount_args {
 	int cap_release_safety;
 	int max_readdir;       /* max readdir result (entires) */
 	int max_readdir_bytes; /* max readdir result (bytes) */
-	char *snapdir_name;   /* default ".snap" */
-	char *name;
-	char *secret;
-};
 
-/*
- * defaults
- */
-#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
-#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
-#define CEPH_OSD_KEEPALIVE_DEFAULT  5
-#define CEPH_OSD_IDLE_TTL_DEFAULT    60
-#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
-#define CEPH_MAX_READDIR_DEFAULT    1024
-#define CEPH_MAX_READDIR_BYTES_DEFAULT    (512*1024)
-
-#define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
-#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
-
-#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
-#define CEPH_AUTH_NAME_DEFAULT   "guest"
-/*
- * Delay telling the MDS we no longer want caps, in case we reopen
- * the file.  Delay a minimum amount of time, even if we send a cap
- * message for some other reason.  Otherwise, take the oppotunity to
- * update the mds to avoid sending another message later.
- */
-#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
-#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
-
-#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)
-
-/* mount state */
-enum {
-	CEPH_MOUNT_MOUNTING,
-	CEPH_MOUNT_MOUNTED,
-	CEPH_MOUNT_UNMOUNTING,
-	CEPH_MOUNT_UNMOUNTED,
-	CEPH_MOUNT_SHUTDOWN,
-};
-
-/*
- * subtract jiffies
- */
-static inline unsigned long time_sub(unsigned long a, unsigned long b)
-{
-	BUG_ON(time_after(b, a));
-	return (long)a - (long)b;
-}
-
-/*
- * per-filesystem client state
- *
- * possibly shared by multiple mount points, if they are
- * mounting the same ceph filesystem/cluster.
- */
-struct ceph_client {
-	struct ceph_fsid fsid;
-	bool have_fsid;
+	/*
+	 * everything above this point can be memcmp'd; everything below
+	 * is handled in compare_mount_options()
+	 */
 
-	struct mutex mount_mutex;       /* serialize mount attempts */
-	struct ceph_mount_args *mount_args;
+	char *snapdir_name;   /* default ".snap" */
+};
 
+struct ceph_fs_client {
 	struct super_block *sb;
 
-	unsigned long mount_state;
-	wait_queue_head_t auth_wq;
-
-	int auth_err;
+	struct ceph_mount_options *mount_options;
+	struct ceph_client *client;
 
+	unsigned long mount_state;
 	int min_caps;                  /* min caps i added */
 
-	struct ceph_messenger *msgr;   /* messenger instance */
-	struct ceph_mon_client monc;
-	struct ceph_mds_client mdsc;
-	struct ceph_osd_client osdc;
+	struct ceph_mds_client *mdsc;
 
 	/* writeback */
 	mempool_t *wb_pagevec_pool;
@@ -160,14 +80,14 @@ struct ceph_client {
 	struct backing_dev_info backing_dev_info;
 
 #ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_monmap;
-	struct dentry *debugfs_mdsmap, *debugfs_osdmap;
-	struct dentry *debugfs_dir, *debugfs_dentry_lru, *debugfs_caps;
+	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
 	struct dentry *debugfs_bdi;
+	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
 #endif
 };
 
+
 /*
  * File i/o capability.  This tracks shared state with the metadata
  * server that allows us to cache or writeback attributes or to read
@@ -275,6 +195,20 @@ struct ceph_inode_xattr {
 	int should_free_val;
 };
 
+/*
+ * Ceph dentry state
+ */
+struct ceph_dentry_info {
+	struct ceph_mds_session *lease_session;
+	u32 lease_gen, lease_shared_gen;
+	u32 lease_seq;
+	unsigned long lease_renew_after, lease_renew_from;
+	struct list_head lru;
+	struct dentry *dentry;
+	u64 time;
+	u64 offset;
+};
+
 struct ceph_inode_xattrs_info {
 	/*
 	 * (still encoded) xattr blob. we avoid the overhead of parsing
@@ -296,11 +230,6 @@ struct ceph_inode_xattrs_info {
 /*
  * Ceph inode.
  */
-#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
-#define CEPH_I_NODELAY   4  /* do not delay cap release */
-#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
-#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
-
 struct ceph_inode_info {
 	struct ceph_vino i_vino;   /* ceph ino + snap */
 
@@ -391,6 +320,63 @@ static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
 	return container_of(inode, struct ceph_inode_info, vfs_inode);
 }
 
+static inline struct ceph_vino ceph_vino(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino;
+}
+
+/*
+ * ino_t is <64 bits on many architectures, blech.
+ *
+ * don't include snap in ino hash, at least for now.
+ */
+static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
+{
+	ino_t ino = (ino_t)vino.ino;  /* ^ (vino.snap << 20); */
+#if BITS_PER_LONG == 32
+	ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
+	if (!ino)
+		ino = 1;
+#endif
+	return ino;
+}
+
+/* for printf-style formatting */
+#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
+
+static inline u64 ceph_ino(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino.ino;
+}
+static inline u64 ceph_snap(struct inode *inode)
+{
+	return ceph_inode(inode)->i_vino.snap;
+}
+
+static inline int ceph_ino_compare(struct inode *inode, void *data)
+{
+	struct ceph_vino *pvino = (struct ceph_vino *)data;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	return ci->i_vino.ino == pvino->ino &&
+		ci->i_vino.snap == pvino->snap;
+}
+
+static inline struct inode *ceph_find_inode(struct super_block *sb,
+					    struct ceph_vino vino)
+{
+	ino_t t = ceph_vino_to_ino(vino);
+	return ilookup5(sb, t, ceph_ino_compare, &vino);
+}
+
+
+/*
+ * Ceph inode.
+ */
+#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
+#define CEPH_I_NODELAY   4  /* do not delay cap release */
+#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
+#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
+
 static inline void ceph_i_clear(struct inode *inode, unsigned mask)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -414,8 +400,9 @@ static inline bool ceph_i_test(struct inode *inode, unsigned mask)
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	bool r;
 
-	smp_mb();
+	spin_lock(&inode->i_lock);
 	r = (ci->i_ceph_flags & mask) == mask;
+	spin_unlock(&inode->i_lock);
 	return r;
 }
 
@@ -432,20 +419,6 @@ extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
 			    struct ceph_inode_frag *pfrag,
 			    int *found);
 
-/*
- * Ceph dentry state
- */
-struct ceph_dentry_info {
-	struct ceph_mds_session *lease_session;
-	u32 lease_gen, lease_shared_gen;
-	u32 lease_seq;
-	unsigned long lease_renew_after, lease_renew_from;
-	struct list_head lru;
-	struct dentry *dentry;
-	u64 time;
-	u64 offset;
-};
-
 static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry)
 {
 	return (struct ceph_dentry_info *)dentry->d_fsdata;
@@ -456,22 +429,6 @@ static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
 	return ((loff_t)frag << 32) | (loff_t)off;
 }
 
-/*
- * ino_t is <64 bits on many architectures, blech.
- *
- * don't include snap in ino hash, at least for now.
- */
-static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
-{
-	ino_t ino = (ino_t)vino.ino;  /* ^ (vino.snap << 20); */
-#if BITS_PER_LONG == 32
-	ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
-	if (!ino)
-		ino = 1;
-#endif
-	return ino;
-}
-
 static inline int ceph_set_ino_cb(struct inode *inode, void *data)
 {
 	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
@@ -479,39 +436,6 @@ static inline int ceph_set_ino_cb(struct inode *inode, void *data)
 	return 0;
 }
 
-static inline struct ceph_vino ceph_vino(struct inode *inode)
-{
-	return ceph_inode(inode)->i_vino;
-}
-
-/* for printf-style formatting */
-#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
-
-static inline u64 ceph_ino(struct inode *inode)
-{
-	return ceph_inode(inode)->i_vino.ino;
-}
-static inline u64 ceph_snap(struct inode *inode)
-{
-	return ceph_inode(inode)->i_vino.snap;
-}
-
-static inline int ceph_ino_compare(struct inode *inode, void *data)
-{
-	struct ceph_vino *pvino = (struct ceph_vino *)data;
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	return ci->i_vino.ino == pvino->ino &&
-		ci->i_vino.snap == pvino->snap;
-}
-
-static inline struct inode *ceph_find_inode(struct super_block *sb,
-					    struct ceph_vino vino)
-{
-	ino_t t = ceph_vino_to_ino(vino);
-	return ilookup5(sb, t, ceph_ino_compare, &vino);
-}
-
-
 /*
  * caps helpers
  */
@@ -576,18 +500,18 @@ extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
 			     struct ceph_cap_reservation *ctx, int need);
 extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
 			       struct ceph_cap_reservation *ctx);
-extern void ceph_reservation_status(struct ceph_client *client,
+extern void ceph_reservation_status(struct ceph_fs_client *client,
 				    int *total, int *avail, int *used,
 				    int *reserved, int *min);
 
-static inline struct ceph_client *ceph_inode_to_client(struct inode *inode)
+static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
 {
-	return (struct ceph_client *)inode->i_sb->s_fs_info;
+	return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
 }
 
-static inline struct ceph_client *ceph_sb_to_client(struct super_block *sb)
+static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
 {
-	return (struct ceph_client *)sb->s_fs_info;
+	return (struct ceph_fs_client *)sb->s_fs_info;
 }
 
 
@@ -616,51 +540,6 @@ struct ceph_file_info {
 
 
 
-/*
- * snapshots
- */
-
-/*
- * A "snap context" is the set of existing snapshots when we
- * write data.  It is used by the OSD to guide its COW behavior.
- *
- * The ceph_snap_context is refcounted, and attached to each dirty
- * page, indicating which context the dirty data belonged when it was
- * dirtied.
- */
-struct ceph_snap_context {
-	atomic_t nref;
-	u64 seq;
-	int num_snaps;
-	u64 snaps[];
-};
-
-static inline struct ceph_snap_context *
-ceph_get_snap_context(struct ceph_snap_context *sc)
-{
-	/*
-	printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
-	       atomic_read(&sc->nref)+1);
-	*/
-	if (sc)
-		atomic_inc(&sc->nref);
-	return sc;
-}
-
-static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
-{
-	if (!sc)
-		return;
-	/*
-	printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
-	       atomic_read(&sc->nref)-1);
-	*/
-	if (atomic_dec_and_test(&sc->nref)) {
-		/*printk(" deleting snap_context %p\n", sc);*/
-		kfree(sc);
-	}
-}
-
 /*
  * A "snap realm" describes a subset of the file hierarchy sharing
  * the same set of snapshots that apply to it.  The realms themselves
@@ -690,6 +569,8 @@ struct ceph_snap_realm {
 
 	struct list_head empty_item;     /* if i have ref==0 */
 
+	struct list_head dirty_item;     /* if realm needs new context */
+
 	/* the current set of snaps for this realm */
 	struct ceph_snap_context *cached_context;
 
@@ -697,16 +578,33 @@ struct ceph_snap_realm {
 	spinlock_t inodes_with_caps_lock;
 };
 
-
-
-/*
- * calculate the number of pages a given length and offset map onto,
- * if we align the data.
- */
-static inline int calc_pages_for(u64 off, u64 len)
+static inline int default_congestion_kb(void)
 {
-	return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
-		(off >> PAGE_CACHE_SHIFT);
+	int congestion_kb;
+
+	/*
+	 * Copied from NFS
+	 *
+	 * congestion size, scale with available memory.
+	 *
+	 *  64MB:    8192k
+	 * 128MB:   11585k
+	 * 256MB:   16384k
+	 * 512MB:   23170k
+	 *   1GB:   32768k
+	 *   2GB:   46340k
+	 *   4GB:   65536k
+	 *   8GB:   92681k
+	 *  16GB:  131072k
+	 *
+	 * This allows larger machines to have larger/more transfers.
+	 * Limit the default to 256M
+	 */
+	congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
+	if (congestion_kb > 256*1024)
+		congestion_kb = 256*1024;
+
+	return congestion_kb;
 }
 
 
@@ -739,16 +637,6 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
 			   ci_item)->writing;
 }
 
-
-/* super.c */
-extern struct kmem_cache *ceph_inode_cachep;
-extern struct kmem_cache *ceph_cap_cachep;
-extern struct kmem_cache *ceph_dentry_cachep;
-extern struct kmem_cache *ceph_file_cachep;
-
-extern const char *ceph_msg_type_name(int type);
-extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
-
 /* inode.c */
 extern const struct inode_operations ceph_file_iops;
 
@@ -826,7 +714,8 @@ extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
 extern void __ceph_flush_snaps(struct ceph_inode_info *ci,
-			       struct ceph_mds_session **psession);
+			       struct ceph_mds_session **psession,
+			       int again);
 extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 			    struct ceph_mds_session *session);
 extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
@@ -854,12 +743,18 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
 /* file.c */
 extern const struct file_operations ceph_file_fops;
 extern const struct address_space_operations ceph_aops;
+extern int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
 				       struct nameidata *nd, int mode,
 				       int locked_dir);
 extern int ceph_release(struct inode *inode, struct file *filp);
-extern void ceph_release_page_vector(struct page **pages, int num_pages);
 
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
@@ -889,12 +784,6 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 /* export.c */
 extern const struct export_operations ceph_export_ops;
 
-/* debugfs.c */
-extern int ceph_debugfs_init(void);
-extern void ceph_debugfs_cleanup(void);
-extern int ceph_debugfs_client_init(struct ceph_client *client);
-extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
-
 /* locks.c */
 extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
 extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
@@ -911,4 +800,8 @@ static inline struct inode *get_dentry_parent_inode(struct dentry *dentry)
 	return NULL;
 }
 
+/* debugfs.c */
+extern int ceph_fs_debugfs_init(struct ceph_fs_client *client);
+extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);
+
 #endif /* _FS_CEPH_SUPER_H */
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 9578af610b73..6e12a6ba5f79 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1,6 +1,9 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
+
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
 
 #include <linux/xattr.h>
 #include <linux/slab.h>
@@ -620,12 +623,12 @@ out:
 static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 			      const char *value, size_t size, int flags)
 {
-	struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct inode *parent_inode = dentry->d_parent->d_inode;
 	struct ceph_mds_request *req;
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int err;
 	int i, nr_pages;
 	struct page **pages = NULL;
@@ -713,10 +716,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
 
 	/* preallocate memory for xattr name, value, index node */
 	err = -ENOMEM;
-	newname = kmalloc(name_len + 1, GFP_NOFS);
+	newname = kmemdup(name, name_len + 1, GFP_NOFS);
 	if (!newname)
 		goto out;
-	memcpy(newname, name, name_len + 1);
 
 	if (val_len) {
 		newval = kmalloc(val_len + 1, GFP_NOFS);
@@ -777,8 +779,8 @@ out:
 
 static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 {
-	struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = dentry->d_inode;
 	struct inode *parent_inode = dentry->d_parent->d_inode;
 	struct ceph_mds_request *req;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index f80a4f25123c..143d393881cb 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -40,7 +40,9 @@ struct backing_dev_info directly_mappable_cdev_bdi = {
 #endif
 		/* permit direct mmap, for read, write or exec */
 		BDI_CAP_MAP_DIRECT |
-		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP),
+		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP |
+		/* no writeback happens */
+		BDI_CAP_NO_ACCT_AND_WRITEBACK),
 };
 
 static struct kobj_map *cdev_map;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index c65c3419dd37..7e83b356cc9e 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -232,7 +232,7 @@ static int
 small_smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 		void **request_buf)
 {
-	int rc = 0;
+	int rc;
 
 	rc = cifs_reconnect_tcon(tcon, smb_command);
 	if (rc)
@@ -250,7 +250,7 @@ small_smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 	if (tcon != NULL)
 		cifs_stats_inc(&tcon->num_smbs_sent);
 
-	return rc;
+	return 0;
 }
 
 int
@@ -281,16 +281,9 @@ small_smb_init_no_tc(const int smb_command, const int wct,
 
 /* If the return code is zero, this function must fill in request_buf pointer */
 static int
-smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
-	 void **request_buf /* returned */ ,
-	 void **response_buf /* returned */ )
+__smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
+			void **request_buf, void **response_buf)
 {
-	int rc = 0;
-
-	rc = cifs_reconnect_tcon(tcon, smb_command);
-	if (rc)
-		return rc;
-
 	*request_buf = cifs_buf_get();
 	if (*request_buf == NULL) {
 		/* BB should we add a retry in here if not a writepage? */
@@ -309,7 +302,31 @@ smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 	if (tcon != NULL)
 		cifs_stats_inc(&tcon->num_smbs_sent);
 
-	return rc;
+	return 0;
+}
+
+/* If the return code is zero, this function must fill in request_buf pointer */
+static int
+smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
+	 void **request_buf, void **response_buf)
+{
+	int rc;
+
+	rc = cifs_reconnect_tcon(tcon, smb_command);
+	if (rc)
+		return rc;
+
+	return __smb_init(smb_command, wct, tcon, request_buf, response_buf);
+}
+
+static int
+smb_init_no_reconnect(int smb_command, int wct, struct cifsTconInfo *tcon,
+			void **request_buf, void **response_buf)
+{
+	if (tcon->ses->need_reconnect || tcon->need_reconnect)
+		return -EHOSTDOWN;
+
+	return __smb_init(smb_command, wct, tcon, request_buf, response_buf);
 }
 
 static int validate_t2(struct smb_t2_rsp *pSMB)
@@ -4534,8 +4551,8 @@ CIFSSMBQFSUnixInfo(const int xid, struct cifsTconInfo *tcon)
 
 	cFYI(1, "In QFSUnixInfo");
 QFSUnixRetry:
-	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
-		      (void **) &pSMBr);
+	rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, tcon,
+				   (void **) &pSMB, (void **) &pSMBr);
 	if (rc)
 		return rc;
 
@@ -4604,8 +4621,8 @@ CIFSSMBSetFSUnixInfo(const int xid, struct cifsTconInfo *tcon, __u64 cap)
 	cFYI(1, "In SETFSUnixInfo");
 SETFSUnixRetry:
 	/* BB switch to small buf init to save memory */
-	rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB,
-		      (void **) &pSMBr);
+	rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, tcon,
+					(void **) &pSMB, (void **) &pSMBr);
 	if (rc)
 		return rc;
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 93f77d438d3c..53cce8cc2224 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -801,6 +801,8 @@ retry_iget5_locked:
 			inode->i_flags |= S_NOATIME | S_NOCMTIME;
 		if (inode->i_state & I_NEW) {
 			inode->i_ino = hash;
+			if (S_ISREG(inode->i_mode))
+				inode->i_data.backing_dev_info = sb->s_bdi;
 #ifdef CONFIG_CIFS_FSCACHE
 			/* initialize per-inode cache cookie pointer */
 			CIFS_I(inode)->fscache = NULL;
diff --git a/fs/compat.c b/fs/compat.c
index 718c7062aec1..0644a154672b 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1153,7 +1153,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 {
 	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov;
+	struct iovec *iov = iovstack;
 	ssize_t ret;
 	io_fn_t fn;
 	iov_fn_t fnv;
diff --git a/fs/exec.c b/fs/exec.c
index 828dd2461d6b..6d2b6f936858 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2014,3 +2014,43 @@ fail_creds:
 fail:
 	return;
 }
+
+/*
+ * Core dumping helper functions.  These are the only things you should
+ * do on a core-file: use only these functions to write out all the
+ * necessary info.
+ */
+int dump_write(struct file *file, const void *addr, int nr)
+{
+	return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr;
+}
+EXPORT_SYMBOL(dump_write);
+
+int dump_seek(struct file *file, loff_t off)
+{
+	int ret = 1;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
+			return 0;
+	} else {
+		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
+
+		if (!buf)
+			return 0;
+		while (off > 0) {
+			unsigned long n = off;
+
+			if (n > PAGE_SIZE)
+				n = PAGE_SIZE;
+			if (!dump_write(file, buf, n)) {
+				ret = 0;
+				break;
+			}
+			off -= n;
+		}
+		free_page((unsigned long)buf);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(dump_seek);
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index eb7368ebd8cd..3eadd97324b1 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -54,6 +54,9 @@ struct page_collect {
 	unsigned nr_pages;
 	unsigned long length;
 	loff_t pg_first; /* keep 64bit also in 32-arches */
+	bool read_4_write; /* This means two things: that the read is sync
+			    * And the pages should not be unlocked.
+			    */
 };
 
 static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
@@ -71,6 +74,7 @@ static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
 	pcol->nr_pages = 0;
 	pcol->length = 0;
 	pcol->pg_first = -1;
+	pcol->read_4_write = false;
 }
 
 static void _pcol_reset(struct page_collect *pcol)
@@ -347,7 +351,8 @@ static int readpage_strip(void *data, struct page *page)
 		if (PageError(page))
 			ClearPageError(page);
 
-		unlock_page(page);
+		if (!pcol->read_4_write)
+			unlock_page(page);
 		EXOFS_DBGMSG("readpage_strip(0x%lx, 0x%lx) empty page,"
 			     " splitting\n", inode->i_ino, page->index);
 
@@ -428,6 +433,7 @@ static int _readpage(struct page *page, bool is_sync)
 	/* readpage_strip might call read_exec(,is_sync==false) at several
 	 * places but not if we have a single page.
 	 */
+	pcol.read_4_write = is_sync;
 	ret = readpage_strip(&pcol, page);
 	if (ret) {
 		EXOFS_ERR("_readpage => %d\n", ret);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 81e086d8aa57..ab38fef1c9a1 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -52,8 +52,6 @@ struct wb_writeback_work {
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
-#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
-
 /*
  * We don't actually have pdflush, but this one is exported though /proc...
  */
@@ -71,6 +69,16 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 	return test_bit(BDI_writeback_running, &bdi->state);
 }
 
+static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (strcmp(sb->s_type->name, "bdev") == 0)
+		return inode->i_mapping->backing_dev_info;
+
+	return sb->s_bdi;
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index d367af1514ef..cde755cca564 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1354,7 +1354,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 	loff_t file_size;
 	unsigned int num;
 	unsigned int offset;
-	size_t total_len;
+	size_t total_len = 0;
 
 	req = fuse_get_req(fc);
 	if (IS_ERR(req))
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index 5007a41f1be9..d182438c7ae4 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -23,7 +23,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
 	fd->search_key = ptr;
 	fd->key = ptr + tree->max_key_len + 2;
 	dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0));
-	down(&tree->tree_lock);
+	mutex_lock(&tree->tree_lock);
 	return 0;
 }
 
@@ -32,7 +32,7 @@ void hfs_find_exit(struct hfs_find_data *fd)
 	hfs_bnode_put(fd->bnode);
 	kfree(fd->search_key);
 	dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0));
-	up(&fd->tree->tree_lock);
+	mutex_unlock(&fd->tree->tree_lock);
 	fd->tree = NULL;
 }
 
@@ -52,6 +52,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
 		rec = (e + b) / 2;
 		len = hfs_brec_lenoff(bnode, rec, &off);
 		keylen = hfs_brec_keylen(bnode, rec);
+		if (keylen == 0) {
+			res = -EINVAL;
+			goto fail;
+		}
 		hfs_bnode_read(bnode, fd->key, off, keylen);
 		cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
 		if (!cmpval) {
@@ -67,6 +71,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
 	if (rec != e && e >= 0) {
 		len = hfs_brec_lenoff(bnode, e, &off);
 		keylen = hfs_brec_keylen(bnode, e);
+		if (keylen == 0) {
+			res = -EINVAL;
+			goto fail;
+		}
 		hfs_bnode_read(bnode, fd->key, off, keylen);
 	}
 done:
@@ -75,6 +83,7 @@ done:
 	fd->keylength = keylen;
 	fd->entryoffset = off + keylen;
 	fd->entrylength = len - keylen;
+fail:
 	return res;
 }
 
@@ -198,6 +207,10 @@ int hfs_brec_goto(struct hfs_find_data *fd, int cnt)
 
 	len = hfs_brec_lenoff(bnode, fd->record, &off);
 	keylen = hfs_brec_keylen(bnode, fd->record);
+	if (keylen == 0) {
+		res = -EINVAL;
+		goto out;
+	}
 	fd->keyoffset = off;
 	fd->keylength = keylen;
 	fd->entryoffset = off + keylen;
diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c
index ea30afc2a03c..ad57f5991eb1 100644
--- a/fs/hfsplus/bitmap.c
+++ b/fs/hfsplus/bitmap.c
@@ -17,6 +17,7 @@
 
 int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *max)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct page *page;
 	struct address_space *mapping;
 	__be32 *pptr, *curr, *end;
@@ -29,8 +30,8 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *ma
 		return size;
 
 	dprint(DBG_BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len);
-	mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
-	mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
+	mutex_lock(&sbi->alloc_mutex);
+	mapping = sbi->alloc_file->i_mapping;
 	page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL);
 	if (IS_ERR(page)) {
 		start = size;
@@ -150,16 +151,17 @@ done:
 	set_page_dirty(page);
 	kunmap(page);
 	*max = offset + (curr - pptr) * 32 + i - start;
-	HFSPLUS_SB(sb).free_blocks -= *max;
+	sbi->free_blocks -= *max;
 	sb->s_dirt = 1;
 	dprint(DBG_BITMAP, "-> %u,%u\n", start, *max);
 out:
-	mutex_unlock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
+	mutex_unlock(&sbi->alloc_mutex);
 	return start;
 }
 
 int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct page *page;
 	struct address_space *mapping;
 	__be32 *pptr, *curr, *end;
@@ -172,11 +174,11 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 
 	dprint(DBG_BITMAP, "block_free: %u,%u\n", offset, count);
 	/* are all of the bits in range? */
-	if ((offset + count) > HFSPLUS_SB(sb).total_blocks)
+	if ((offset + count) > sbi->total_blocks)
 		return -2;
 
-	mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
-	mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
+	mutex_lock(&sbi->alloc_mutex);
+	mapping = sbi->alloc_file->i_mapping;
 	pnr = offset / PAGE_CACHE_BITS;
 	page = read_mapping_page(mapping, pnr, NULL);
 	pptr = kmap(page);
@@ -224,9 +226,9 @@ done:
 out:
 	set_page_dirty(page);
 	kunmap(page);
-	HFSPLUS_SB(sb).free_blocks += len;
+	sbi->free_blocks += len;
 	sb->s_dirt = 1;
-	mutex_unlock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
+	mutex_unlock(&sbi->alloc_mutex);
 
 	return 0;
 }
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index c88e5d72a402..2f39d05443e1 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -42,10 +42,13 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec)
 		recoff = hfs_bnode_read_u16(node, node->tree->node_size - (rec + 1) * 2);
 		if (!recoff)
 			return 0;
-		if (node->tree->attributes & HFS_TREE_BIGKEYS)
-			retval = hfs_bnode_read_u16(node, recoff) + 2;
-		else
-			retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1;
+
+		retval = hfs_bnode_read_u16(node, recoff) + 2;
+		if (retval > node->tree->max_key_len + 2) {
+			printk(KERN_ERR "hfs: keylen %d too large\n",
+				retval);
+			retval = 0;
+		}
 	}
 	return retval;
 }
@@ -216,7 +219,7 @@ skip:
 static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
 {
 	struct hfs_btree *tree;
-	struct hfs_bnode *node, *new_node;
+	struct hfs_bnode *node, *new_node, *next_node;
 	struct hfs_bnode_desc node_desc;
 	int num_recs, new_rec_off, new_off, old_rec_off;
 	int data_start, data_end, size;
@@ -235,6 +238,17 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
 	new_node->type = node->type;
 	new_node->height = node->height;
 
+	if (node->next)
+		next_node = hfs_bnode_find(tree, node->next);
+	else
+		next_node = NULL;
+
+	if (IS_ERR(next_node)) {
+		hfs_bnode_put(node);
+		hfs_bnode_put(new_node);
+		return next_node;
+	}
+
 	size = tree->node_size / 2 - node->num_recs * 2 - 14;
 	old_rec_off = tree->node_size - 4;
 	num_recs = 1;
@@ -248,6 +262,8 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
 		/* panic? */
 		hfs_bnode_put(node);
 		hfs_bnode_put(new_node);
+		if (next_node)
+			hfs_bnode_put(next_node);
 		return ERR_PTR(-ENOSPC);
 	}
 
@@ -302,8 +318,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
 	hfs_bnode_write(node, &node_desc, 0, sizeof(node_desc));
 
 	/* update next bnode header */
-	if (new_node->next) {
-		struct hfs_bnode *next_node = hfs_bnode_find(tree, new_node->next);
+	if (next_node) {
 		next_node->prev = new_node->this;
 		hfs_bnode_read(next_node, &node_desc, 0, sizeof(node_desc));
 		node_desc.prev = cpu_to_be32(next_node->prev);
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index e49fcee1e293..22e4d4e32999 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -30,7 +30,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
 	if (!tree)
 		return NULL;
 
-	init_MUTEX(&tree->tree_lock);
+	mutex_init(&tree->tree_lock);
 	spin_lock_init(&tree->hash_lock);
 	tree->sb = sb;
 	tree->cnid = id;
@@ -39,10 +39,16 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
 		goto free_tree;
 	tree->inode = inode;
 
+	if (!HFSPLUS_I(tree->inode)->first_blocks) {
+		printk(KERN_ERR
+		       "hfs: invalid btree extent records (0 size).\n");
+		goto free_inode;
+	}
+
 	mapping = tree->inode->i_mapping;
 	page = read_mapping_page(mapping, 0, NULL);
 	if (IS_ERR(page))
-		goto free_tree;
+		goto free_inode;
 
 	/* Load the header */
 	head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc));
@@ -57,27 +63,56 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
 	tree->max_key_len = be16_to_cpu(head->max_key_len);
 	tree->depth = be16_to_cpu(head->depth);
 
-	/* Set the correct compare function */
-	if (id == HFSPLUS_EXT_CNID) {
+	/* Verify the tree and set the correct compare function */
+	switch (id) {
+	case HFSPLUS_EXT_CNID:
+		if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) {
+			printk(KERN_ERR "hfs: invalid extent max_key_len %d\n",
+				tree->max_key_len);
+			goto fail_page;
+		}
+		if (tree->attributes & HFS_TREE_VARIDXKEYS) {
+			printk(KERN_ERR "hfs: invalid extent btree flag\n");
+			goto fail_page;
+		}
+
 		tree->keycmp = hfsplus_ext_cmp_key;
-	} else if (id == HFSPLUS_CAT_CNID) {
-		if ((HFSPLUS_SB(sb).flags & HFSPLUS_SB_HFSX) &&
+		break;
+	case HFSPLUS_CAT_CNID:
+		if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) {
+			printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n",
+				tree->max_key_len);
+			goto fail_page;
+		}
+		if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) {
+			printk(KERN_ERR "hfs: invalid catalog btree flag\n");
+			goto fail_page;
+		}
+
+		if (test_bit(HFSPLUS_SB_HFSX, &HFSPLUS_SB(sb)->flags) &&
 		    (head->key_type == HFSPLUS_KEY_BINARY))
 			tree->keycmp = hfsplus_cat_bin_cmp_key;
 		else {
 			tree->keycmp = hfsplus_cat_case_cmp_key;
-			HFSPLUS_SB(sb).flags |= HFSPLUS_SB_CASEFOLD;
+			set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
 		}
-	} else {
+		break;
+	default:
 		printk(KERN_ERR "hfs: unknown B*Tree requested\n");
 		goto fail_page;
 	}
 
+	if (!(tree->attributes & HFS_TREE_BIGKEYS)) {
+		printk(KERN_ERR "hfs: invalid btree flag\n");
+		goto fail_page;
+	}
+
 	size = tree->node_size;
 	if (!is_power_of_2(size))
 		goto fail_page;
 	if (!tree->node_count)
 		goto fail_page;
+
 	tree->node_size_shift = ffs(size) - 1;
 
 	tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
@@ -87,10 +122,11 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
 	return tree;
 
  fail_page:
-	tree->inode->i_mapping->a_ops = &hfsplus_aops;
 	page_cache_release(page);
- free_tree:
+ free_inode:
+	tree->inode->i_mapping->a_ops = &hfsplus_aops;
 	iput(tree->inode);
+ free_tree:
 	kfree(tree);
 	return NULL;
 }
@@ -192,17 +228,18 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 
 	while (!tree->free_nodes) {
 		struct inode *inode = tree->inode;
+		struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 		u32 count;
 		int res;
 
 		res = hfsplus_file_extend(inode);
 		if (res)
 			return ERR_PTR(res);
-		HFSPLUS_I(inode).phys_size = inode->i_size =
-				(loff_t)HFSPLUS_I(inode).alloc_blocks <<
-				HFSPLUS_SB(tree->sb).alloc_blksz_shift;
-		HFSPLUS_I(inode).fs_blocks = HFSPLUS_I(inode).alloc_blocks <<
-					     HFSPLUS_SB(tree->sb).fs_shift;
+		hip->phys_size = inode->i_size =
+			(loff_t)hip->alloc_blocks <<
+				HFSPLUS_SB(tree->sb)->alloc_blksz_shift;
+		hip->fs_blocks =
+			hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift;
 		inode_set_bytes(inode, inode->i_size);
 		count = inode->i_size >> tree->node_size_shift;
 		tree->free_nodes = count - tree->node_count;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index f6874acb2cf2..8af45fc5b051 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -67,7 +67,7 @@ static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent,
 	key->key_len = cpu_to_be16(6 + ustrlen);
 }
 
-static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
+void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms)
 {
 	if (inode->i_flags & S_IMMUTABLE)
 		perms->rootflags |= HFSPLUS_FLG_IMMUTABLE;
@@ -77,15 +77,24 @@ static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
 		perms->rootflags |= HFSPLUS_FLG_APPEND;
 	else
 		perms->rootflags &= ~HFSPLUS_FLG_APPEND;
-	HFSPLUS_I(inode).rootflags = perms->rootflags;
-	HFSPLUS_I(inode).userflags = perms->userflags;
+
+	perms->userflags = HFSPLUS_I(inode)->userflags;
 	perms->mode = cpu_to_be16(inode->i_mode);
 	perms->owner = cpu_to_be32(inode->i_uid);
 	perms->group = cpu_to_be32(inode->i_gid);
+
+	if (S_ISREG(inode->i_mode))
+		perms->dev = cpu_to_be32(inode->i_nlink);
+	else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode))
+		perms->dev = cpu_to_be32(inode->i_rdev);
+	else
+		perms->dev = 0;
 }
 
 static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct inode *inode)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+
 	if (S_ISDIR(inode->i_mode)) {
 		struct hfsplus_cat_folder *folder;
 
@@ -93,13 +102,13 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
 		memset(folder, 0, sizeof(*folder));
 		folder->type = cpu_to_be16(HFSPLUS_FOLDER);
 		folder->id = cpu_to_be32(inode->i_ino);
-		HFSPLUS_I(inode).create_date =
+		HFSPLUS_I(inode)->create_date =
 			folder->create_date =
 			folder->content_mod_date =
 			folder->attribute_mod_date =
 			folder->access_date = hfsp_now2mt();
-		hfsplus_set_perms(inode, &folder->permissions);
-		if (inode == HFSPLUS_SB(inode->i_sb).hidden_dir)
+		hfsplus_cat_set_perms(inode, &folder->permissions);
+		if (inode == sbi->hidden_dir)
 			/* invisible and namelocked */
 			folder->user_info.frFlags = cpu_to_be16(0x5000);
 		return sizeof(*folder);
@@ -111,19 +120,19 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
 		file->type = cpu_to_be16(HFSPLUS_FILE);
 		file->flags = cpu_to_be16(HFSPLUS_FILE_THREAD_EXISTS);
 		file->id = cpu_to_be32(cnid);
-		HFSPLUS_I(inode).create_date =
+		HFSPLUS_I(inode)->create_date =
 			file->create_date =
 			file->content_mod_date =
 			file->attribute_mod_date =
 			file->access_date = hfsp_now2mt();
 		if (cnid == inode->i_ino) {
-			hfsplus_set_perms(inode, &file->permissions);
+			hfsplus_cat_set_perms(inode, &file->permissions);
 			if (S_ISLNK(inode->i_mode)) {
 				file->user_info.fdType = cpu_to_be32(HFSP_SYMLINK_TYPE);
 				file->user_info.fdCreator = cpu_to_be32(HFSP_SYMLINK_CREATOR);
 			} else {
-				file->user_info.fdType = cpu_to_be32(HFSPLUS_SB(inode->i_sb).type);
-				file->user_info.fdCreator = cpu_to_be32(HFSPLUS_SB(inode->i_sb).creator);
+				file->user_info.fdType = cpu_to_be32(sbi->type);
+				file->user_info.fdCreator = cpu_to_be32(sbi->creator);
 			}
 			if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
 				file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
@@ -131,8 +140,8 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
 			file->user_info.fdType = cpu_to_be32(HFSP_HARDLINK_TYPE);
 			file->user_info.fdCreator = cpu_to_be32(HFSP_HFSPLUS_CREATOR);
 			file->user_info.fdFlags = cpu_to_be16(0x100);
-			file->create_date = HFSPLUS_I(HFSPLUS_SB(inode->i_sb).hidden_dir).create_date;
-			file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode).dev);
+			file->create_date = HFSPLUS_I(sbi->hidden_dir)->create_date;
+			file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode)->linkid);
 		}
 		return sizeof(*file);
 	}
@@ -180,15 +189,14 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 
 int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct inode *inode)
 {
+	struct super_block *sb = dir->i_sb;
 	struct hfs_find_data fd;
-	struct super_block *sb;
 	hfsplus_cat_entry entry;
 	int entry_size;
 	int err;
 
 	dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink);
-	sb = dir->i_sb;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
 	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ?
@@ -234,7 +242,7 @@ err2:
 
 int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 {
-	struct super_block *sb;
+	struct super_block *sb = dir->i_sb;
 	struct hfs_find_data fd;
 	struct hfsplus_fork_raw fork;
 	struct list_head *pos;
@@ -242,8 +250,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	u16 type;
 
 	dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid);
-	sb = dir->i_sb;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
 	if (!str) {
 		int len;
@@ -279,7 +286,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 		hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC);
 	}
 
-	list_for_each(pos, &HFSPLUS_I(dir).open_dir_list) {
+	list_for_each(pos, &HFSPLUS_I(dir)->open_dir_list) {
 		struct hfsplus_readdir_data *rd =
 			list_entry(pos, struct hfsplus_readdir_data, list);
 		if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
@@ -312,7 +319,7 @@ int hfsplus_rename_cat(u32 cnid,
 		       struct inode *src_dir, struct qstr *src_name,
 		       struct inode *dst_dir, struct qstr *dst_name)
 {
-	struct super_block *sb;
+	struct super_block *sb = src_dir->i_sb;
 	struct hfs_find_data src_fd, dst_fd;
 	hfsplus_cat_entry entry;
 	int entry_size, type;
@@ -320,8 +327,7 @@ int hfsplus_rename_cat(u32 cnid,
 
 	dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name,
 		dst_dir->i_ino, dst_name->name);
-	sb = src_dir->i_sb;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &src_fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd);
 	dst_fd = src_fd;
 
 	/* find the old dir entry and read the data */
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 764fd1bdca88..d236d85ec9d7 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -39,7 +39,7 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 
 	dentry->d_op = &hfsplus_dentry_operations;
 	dentry->d_fsdata = NULL;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
 again:
 	err = hfs_brec_read(&fd, &entry, sizeof(entry));
@@ -68,9 +68,9 @@ again:
 		cnid = be32_to_cpu(entry.file.id);
 		if (entry.file.user_info.fdType == cpu_to_be32(HFSP_HARDLINK_TYPE) &&
 		    entry.file.user_info.fdCreator == cpu_to_be32(HFSP_HFSPLUS_CREATOR) &&
-		    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb).hidden_dir).create_date ||
-		     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode).create_date) &&
-		    HFSPLUS_SB(sb).hidden_dir) {
+		    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb)->hidden_dir)->create_date ||
+		     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode)->create_date) &&
+		    HFSPLUS_SB(sb)->hidden_dir) {
 			struct qstr str;
 			char name[32];
 
@@ -86,7 +86,8 @@ again:
 				linkid = be32_to_cpu(entry.file.permissions.dev);
 				str.len = sprintf(name, "iNode%d", linkid);
 				str.name = name;
-				hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_SB(sb).hidden_dir->i_ino, &str);
+				hfsplus_cat_build_key(sb, fd.search_key,
+					HFSPLUS_SB(sb)->hidden_dir->i_ino, &str);
 				goto again;
 			}
 		} else if (!dentry->d_fsdata)
@@ -101,7 +102,7 @@ again:
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 	if (S_ISREG(inode->i_mode))
-		HFSPLUS_I(inode).dev = linkid;
+		HFSPLUS_I(inode)->linkid = linkid;
 out:
 	d_add(dentry, inode);
 	return NULL;
@@ -124,7 +125,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	if (filp->f_pos >= inode->i_size)
 		return 0;
 
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
 	err = hfs_brec_find(&fd);
 	if (err)
@@ -180,8 +181,9 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
 				err = -EIO;
 				goto out;
 			}
-			if (HFSPLUS_SB(sb).hidden_dir &&
-			    HFSPLUS_SB(sb).hidden_dir->i_ino == be32_to_cpu(entry.folder.id))
+			if (HFSPLUS_SB(sb)->hidden_dir &&
+			    HFSPLUS_SB(sb)->hidden_dir->i_ino ==
+					be32_to_cpu(entry.folder.id))
 				goto next;
 			if (filldir(dirent, strbuf, len, filp->f_pos,
 				    be32_to_cpu(entry.folder.id), DT_DIR))
@@ -217,7 +219,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		}
 		filp->private_data = rd;
 		rd->file = filp;
-		list_add(&rd->list, &HFSPLUS_I(inode).open_dir_list);
+		list_add(&rd->list, &HFSPLUS_I(inode)->open_dir_list);
 	}
 	memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key));
 out:
@@ -229,38 +231,18 @@ static int hfsplus_dir_release(struct inode *inode, struct file *file)
 {
 	struct hfsplus_readdir_data *rd = file->private_data;
 	if (rd) {
+		mutex_lock(&inode->i_mutex);
 		list_del(&rd->list);
+		mutex_unlock(&inode->i_mutex);
 		kfree(rd);
 	}
 	return 0;
 }
 
-static int hfsplus_create(struct inode *dir, struct dentry *dentry, int mode,
-			  struct nameidata *nd)
-{
-	struct inode *inode;
-	int res;
-
-	inode = hfsplus_new_inode(dir->i_sb, mode);
-	if (!inode)
-		return -ENOSPC;
-
-	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
-	if (res) {
-		inode->i_nlink = 0;
-		hfsplus_delete_inode(inode);
-		iput(inode);
-		return res;
-	}
-	hfsplus_instantiate(dentry, inode, inode->i_ino);
-	mark_inode_dirty(inode);
-	return 0;
-}
-
 static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 			struct dentry *dst_dentry)
 {
-	struct super_block *sb = dst_dir->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dst_dir->i_sb);
 	struct inode *inode = src_dentry->d_inode;
 	struct inode *src_dir = src_dentry->d_parent->d_inode;
 	struct qstr str;
@@ -270,7 +252,10 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 
 	if (HFSPLUS_IS_RSRC(inode))
 		return -EPERM;
+	if (!S_ISREG(inode->i_mode))
+		return -EPERM;
 
+	mutex_lock(&sbi->vh_mutex);
 	if (inode->i_ino == (u32)(unsigned long)src_dentry->d_fsdata) {
 		for (;;) {
 			get_random_bytes(&id, sizeof(cnid));
@@ -279,40 +264,41 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 			str.len = sprintf(name, "iNode%d", id);
 			res = hfsplus_rename_cat(inode->i_ino,
 						 src_dir, &src_dentry->d_name,
-						 HFSPLUS_SB(sb).hidden_dir, &str);
+						 sbi->hidden_dir, &str);
 			if (!res)
 				break;
 			if (res != -EEXIST)
-				return res;
+				goto out;
 		}
-		HFSPLUS_I(inode).dev = id;
-		cnid = HFSPLUS_SB(sb).next_cnid++;
+		HFSPLUS_I(inode)->linkid = id;
+		cnid = sbi->next_cnid++;
 		src_dentry->d_fsdata = (void *)(unsigned long)cnid;
 		res = hfsplus_create_cat(cnid, src_dir, &src_dentry->d_name, inode);
 		if (res)
 			/* panic? */
-			return res;
-		HFSPLUS_SB(sb).file_count++;
+			goto out;
+		sbi->file_count++;
 	}
-	cnid = HFSPLUS_SB(sb).next_cnid++;
+	cnid = sbi->next_cnid++;
 	res = hfsplus_create_cat(cnid, dst_dir, &dst_dentry->d_name, inode);
 	if (res)
-		return res;
+		goto out;
 
 	inc_nlink(inode);
 	hfsplus_instantiate(dst_dentry, inode, cnid);
 	atomic_inc(&inode->i_count);
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-	HFSPLUS_SB(sb).file_count++;
-	sb->s_dirt = 1;
-
-	return 0;
+	sbi->file_count++;
+	dst_dir->i_sb->s_dirt = 1;
+out:
+	mutex_unlock(&sbi->vh_mutex);
+	return res;
 }
 
 static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct super_block *sb = dir->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
 	struct inode *inode = dentry->d_inode;
 	struct qstr str;
 	char name[32];
@@ -322,21 +308,22 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
 	if (HFSPLUS_IS_RSRC(inode))
 		return -EPERM;
 
+	mutex_lock(&sbi->vh_mutex);
 	cnid = (u32)(unsigned long)dentry->d_fsdata;
 	if (inode->i_ino == cnid &&
-	    atomic_read(&HFSPLUS_I(inode).opencnt)) {
+	    atomic_read(&HFSPLUS_I(inode)->opencnt)) {
 		str.name = name;
 		str.len = sprintf(name, "temp%lu", inode->i_ino);
 		res = hfsplus_rename_cat(inode->i_ino,
 					 dir, &dentry->d_name,
-					 HFSPLUS_SB(sb).hidden_dir, &str);
+					 sbi->hidden_dir, &str);
 		if (!res)
 			inode->i_flags |= S_DEAD;
-		return res;
+		goto out;
 	}
 	res = hfsplus_delete_cat(cnid, dir, &dentry->d_name);
 	if (res)
-		return res;
+		goto out;
 
 	if (inode->i_nlink > 0)
 		drop_nlink(inode);
@@ -344,10 +331,10 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
 		clear_nlink(inode);
 	if (!inode->i_nlink) {
 		if (inode->i_ino != cnid) {
-			HFSPLUS_SB(sb).file_count--;
-			if (!atomic_read(&HFSPLUS_I(inode).opencnt)) {
+			sbi->file_count--;
+			if (!atomic_read(&HFSPLUS_I(inode)->opencnt)) {
 				res = hfsplus_delete_cat(inode->i_ino,
-							 HFSPLUS_SB(sb).hidden_dir,
+							 sbi->hidden_dir,
 							 NULL);
 				if (!res)
 					hfsplus_delete_inode(inode);
@@ -356,107 +343,108 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
 		} else
 			hfsplus_delete_inode(inode);
 	} else
-		HFSPLUS_SB(sb).file_count--;
+		sbi->file_count--;
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-
+out:
+	mutex_unlock(&sbi->vh_mutex);
 	return res;
 }
 
-static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, int mode)
-{
-	struct inode *inode;
-	int res;
-
-	inode = hfsplus_new_inode(dir->i_sb, S_IFDIR | mode);
-	if (!inode)
-		return -ENOSPC;
-
-	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
-	if (res) {
-		inode->i_nlink = 0;
-		hfsplus_delete_inode(inode);
-		iput(inode);
-		return res;
-	}
-	hfsplus_instantiate(dentry, inode, inode->i_ino);
-	mark_inode_dirty(inode);
-	return 0;
-}
-
 static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	struct inode *inode;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+	struct inode *inode = dentry->d_inode;
 	int res;
 
-	inode = dentry->d_inode;
 	if (inode->i_size != 2)
 		return -ENOTEMPTY;
+
+	mutex_lock(&sbi->vh_mutex);
 	res = hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
 	if (res)
-		return res;
+		goto out;
 	clear_nlink(inode);
 	inode->i_ctime = CURRENT_TIME_SEC;
 	hfsplus_delete_inode(inode);
 	mark_inode_dirty(inode);
-	return 0;
+out:
+	mutex_unlock(&sbi->vh_mutex);
+	return res;
 }
 
 static int hfsplus_symlink(struct inode *dir, struct dentry *dentry,
 			   const char *symname)
 {
-	struct super_block *sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
 	struct inode *inode;
-	int res;
+	int res = -ENOSPC;
 
-	sb = dir->i_sb;
-	inode = hfsplus_new_inode(sb, S_IFLNK | S_IRWXUGO);
+	mutex_lock(&sbi->vh_mutex);
+	inode = hfsplus_new_inode(dir->i_sb, S_IFLNK | S_IRWXUGO);
 	if (!inode)
-		return -ENOSPC;
+		goto out;
 
 	res = page_symlink(inode, symname, strlen(symname) + 1);
-	if (res) {
-		inode->i_nlink = 0;
-		hfsplus_delete_inode(inode);
-		iput(inode);
-		return res;
-	}
+	if (res)
+		goto out_err;
 
-	mark_inode_dirty(inode);
 	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
+	if (res)
+		goto out_err;
 
-	if (!res) {
-		hfsplus_instantiate(dentry, inode, inode->i_ino);
-		mark_inode_dirty(inode);
-	}
+	hfsplus_instantiate(dentry, inode, inode->i_ino);
+	mark_inode_dirty(inode);
+	goto out;
 
+out_err:
+	inode->i_nlink = 0;
+	hfsplus_delete_inode(inode);
+	iput(inode);
+out:
+	mutex_unlock(&sbi->vh_mutex);
 	return res;
 }
 
 static int hfsplus_mknod(struct inode *dir, struct dentry *dentry,
 			 int mode, dev_t rdev)
 {
-	struct super_block *sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
 	struct inode *inode;
-	int res;
+	int res = -ENOSPC;
 
-	sb = dir->i_sb;
-	inode = hfsplus_new_inode(sb, mode);
+	mutex_lock(&sbi->vh_mutex);
+	inode = hfsplus_new_inode(dir->i_sb, mode);
 	if (!inode)
-		return -ENOSPC;
+		goto out;
+
+	if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode))
+		init_special_inode(inode, mode, rdev);
 
 	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
 	if (res) {
 		inode->i_nlink = 0;
 		hfsplus_delete_inode(inode);
 		iput(inode);
-		return res;
+		goto out;
 	}
-	init_special_inode(inode, mode, rdev);
+
 	hfsplus_instantiate(dentry, inode, inode->i_ino);
 	mark_inode_dirty(inode);
+out:
+	mutex_unlock(&sbi->vh_mutex);
+	return res;
+}
 
-	return 0;
+static int hfsplus_create(struct inode *dir, struct dentry *dentry, int mode,
+			  struct nameidata *nd)
+{
+	return hfsplus_mknod(dir, dentry, mode, 0);
+}
+
+static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+	return hfsplus_mknod(dir, dentry, mode | S_IFDIR, 0);
 }
 
 static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -466,7 +454,10 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
-		res = hfsplus_unlink(new_dir, new_dentry);
+		if (S_ISDIR(new_dentry->d_inode->i_mode))
+			res = hfsplus_rmdir(new_dir, new_dentry);
+		else
+			res = hfsplus_unlink(new_dir, new_dentry);
 		if (res)
 			return res;
 	}
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 0022eec63cda..0c9cb1820a52 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -85,35 +85,49 @@ static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext)
 
 static void __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd)
 {
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	int res;
 
-	hfsplus_ext_build_key(fd->search_key, inode->i_ino, HFSPLUS_I(inode).cached_start,
-			      HFSPLUS_IS_RSRC(inode) ?  HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+	WARN_ON(!mutex_is_locked(&hip->extents_lock));
+
+	hfsplus_ext_build_key(fd->search_key, inode->i_ino, hip->cached_start,
+			      HFSPLUS_IS_RSRC(inode) ?
+				HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+
 	res = hfs_brec_find(fd);
-	if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_NEW) {
+	if (hip->flags & HFSPLUS_FLG_EXT_NEW) {
 		if (res != -ENOENT)
 			return;
-		hfs_brec_insert(fd, HFSPLUS_I(inode).cached_extents, sizeof(hfsplus_extent_rec));
-		HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+		hfs_brec_insert(fd, hip->cached_extents,
+				sizeof(hfsplus_extent_rec));
+		hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
 	} else {
 		if (res)
 			return;
-		hfs_bnode_write(fd->bnode, HFSPLUS_I(inode).cached_extents, fd->entryoffset, fd->entrylength);
-		HFSPLUS_I(inode).flags &= ~HFSPLUS_FLG_EXT_DIRTY;
+		hfs_bnode_write(fd->bnode, hip->cached_extents,
+				fd->entryoffset, fd->entrylength);
+		hip->flags &= ~HFSPLUS_FLG_EXT_DIRTY;
 	}
 }
 
-void hfsplus_ext_write_extent(struct inode *inode)
+static void hfsplus_ext_write_extent_locked(struct inode *inode)
 {
-	if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_DIRTY) {
+	if (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_EXT_DIRTY) {
 		struct hfs_find_data fd;
 
-		hfs_find_init(HFSPLUS_SB(inode->i_sb).ext_tree, &fd);
+		hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
 		__hfsplus_ext_write_extent(inode, &fd);
 		hfs_find_exit(&fd);
 	}
 }
 
+void hfsplus_ext_write_extent(struct inode *inode)
+{
+	mutex_lock(&HFSPLUS_I(inode)->extents_lock);
+	hfsplus_ext_write_extent_locked(inode);
+	mutex_unlock(&HFSPLUS_I(inode)->extents_lock);
+}
+
 static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
 					    struct hfsplus_extent *extent,
 					    u32 cnid, u32 block, u8 type)
@@ -136,33 +150,39 @@ static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
 
 static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct inode *inode, u32 block)
 {
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	int res;
 
-	if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_DIRTY)
+	WARN_ON(!mutex_is_locked(&hip->extents_lock));
+
+	if (hip->flags & HFSPLUS_FLG_EXT_DIRTY)
 		__hfsplus_ext_write_extent(inode, fd);
 
-	res = __hfsplus_ext_read_extent(fd, HFSPLUS_I(inode).cached_extents, inode->i_ino,
-					block, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+	res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino,
+					block, HFSPLUS_IS_RSRC(inode) ?
+						HFSPLUS_TYPE_RSRC :
+						HFSPLUS_TYPE_DATA);
 	if (!res) {
-		HFSPLUS_I(inode).cached_start = be32_to_cpu(fd->key->ext.start_block);
-		HFSPLUS_I(inode).cached_blocks = hfsplus_ext_block_count(HFSPLUS_I(inode).cached_extents);
+		hip->cached_start = be32_to_cpu(fd->key->ext.start_block);
+		hip->cached_blocks = hfsplus_ext_block_count(hip->cached_extents);
 	} else {
-		HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).cached_blocks = 0;
-		HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+		hip->cached_start = hip->cached_blocks = 0;
+		hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
 	}
 	return res;
 }
 
 static int hfsplus_ext_read_extent(struct inode *inode, u32 block)
 {
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	struct hfs_find_data fd;
 	int res;
 
-	if (block >= HFSPLUS_I(inode).cached_start &&
-	    block < HFSPLUS_I(inode).cached_start + HFSPLUS_I(inode).cached_blocks)
+	if (block >= hip->cached_start &&
+	    block < hip->cached_start + hip->cached_blocks)
 		return 0;
 
-	hfs_find_init(HFSPLUS_SB(inode->i_sb).ext_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
 	res = __hfsplus_ext_cache_extent(&fd, inode, block);
 	hfs_find_exit(&fd);
 	return res;
@@ -172,21 +192,21 @@ static int hfsplus_ext_read_extent(struct inode *inode, u32 block)
 int hfsplus_get_block(struct inode *inode, sector_t iblock,
 		      struct buffer_head *bh_result, int create)
 {
-	struct super_block *sb;
+	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	int res = -EIO;
 	u32 ablock, dblock, mask;
 	int shift;
 
-	sb = inode->i_sb;
-
 	/* Convert inode block to disk allocation block */
-	shift = HFSPLUS_SB(sb).alloc_blksz_shift - sb->s_blocksize_bits;
-	ablock = iblock >> HFSPLUS_SB(sb).fs_shift;
+	shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
+	ablock = iblock >> sbi->fs_shift;
 
-	if (iblock >= HFSPLUS_I(inode).fs_blocks) {
-		if (iblock > HFSPLUS_I(inode).fs_blocks || !create)
+	if (iblock >= hip->fs_blocks) {
+		if (iblock > hip->fs_blocks || !create)
 			return -EIO;
-		if (ablock >= HFSPLUS_I(inode).alloc_blocks) {
+		if (ablock >= hip->alloc_blocks) {
 			res = hfsplus_file_extend(inode);
 			if (res)
 				return res;
@@ -194,33 +214,33 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
 	} else
 		create = 0;
 
-	if (ablock < HFSPLUS_I(inode).first_blocks) {
-		dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).first_extents, ablock);
+	if (ablock < hip->first_blocks) {
+		dblock = hfsplus_ext_find_block(hip->first_extents, ablock);
 		goto done;
 	}
 
 	if (inode->i_ino == HFSPLUS_EXT_CNID)
 		return -EIO;
 
-	mutex_lock(&HFSPLUS_I(inode).extents_lock);
+	mutex_lock(&hip->extents_lock);
 	res = hfsplus_ext_read_extent(inode, ablock);
 	if (!res) {
-		dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).cached_extents, ablock -
-					     HFSPLUS_I(inode).cached_start);
+		dblock = hfsplus_ext_find_block(hip->cached_extents,
+						ablock - hip->cached_start);
 	} else {
-		mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+		mutex_unlock(&hip->extents_lock);
 		return -EIO;
 	}
-	mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+	mutex_unlock(&hip->extents_lock);
 
 done:
 	dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock);
-	mask = (1 << HFSPLUS_SB(sb).fs_shift) - 1;
-	map_bh(bh_result, sb, (dblock << HFSPLUS_SB(sb).fs_shift) + HFSPLUS_SB(sb).blockoffset + (iblock & mask));
+	mask = (1 << sbi->fs_shift) - 1;
+	map_bh(bh_result, sb, (dblock << sbi->fs_shift) + sbi->blockoffset + (iblock & mask));
 	if (create) {
 		set_buffer_new(bh_result);
-		HFSPLUS_I(inode).phys_size += sb->s_blocksize;
-		HFSPLUS_I(inode).fs_blocks++;
+		hip->phys_size += sb->s_blocksize;
+		hip->fs_blocks++;
 		inode_add_bytes(inode, sb->s_blocksize);
 		mark_inode_dirty(inode);
 	}
@@ -327,7 +347,7 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw
 	if (total_blocks == blocks)
 		return 0;
 
-	hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
 	do {
 		res = __hfsplus_ext_read_extent(&fd, ext_entry, cnid,
 						total_blocks, type);
@@ -348,29 +368,33 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw
 int hfsplus_file_extend(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	u32 start, len, goal;
 	int res;
 
-	if (HFSPLUS_SB(sb).alloc_file->i_size * 8 < HFSPLUS_SB(sb).total_blocks - HFSPLUS_SB(sb).free_blocks + 8) {
+	if (sbi->alloc_file->i_size * 8 <
+	    sbi->total_blocks - sbi->free_blocks + 8) {
 		// extend alloc file
-		printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n", HFSPLUS_SB(sb).alloc_file->i_size * 8,
-			HFSPLUS_SB(sb).total_blocks, HFSPLUS_SB(sb).free_blocks);
+		printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n",
+				sbi->alloc_file->i_size * 8,
+				sbi->total_blocks, sbi->free_blocks);
 		return -ENOSPC;
 	}
 
-	mutex_lock(&HFSPLUS_I(inode).extents_lock);
-	if (HFSPLUS_I(inode).alloc_blocks == HFSPLUS_I(inode).first_blocks)
-		goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).first_extents);
+	mutex_lock(&hip->extents_lock);
+	if (hip->alloc_blocks == hip->first_blocks)
+		goal = hfsplus_ext_lastblock(hip->first_extents);
 	else {
-		res = hfsplus_ext_read_extent(inode, HFSPLUS_I(inode).alloc_blocks);
+		res = hfsplus_ext_read_extent(inode, hip->alloc_blocks);
 		if (res)
 			goto out;
-		goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).cached_extents);
+		goal = hfsplus_ext_lastblock(hip->cached_extents);
 	}
 
-	len = HFSPLUS_I(inode).clump_blocks;
-	start = hfsplus_block_allocate(sb, HFSPLUS_SB(sb).total_blocks, goal, &len);
-	if (start >= HFSPLUS_SB(sb).total_blocks) {
+	len = hip->clump_blocks;
+	start = hfsplus_block_allocate(sb, sbi->total_blocks, goal, &len);
+	if (start >= sbi->total_blocks) {
 		start = hfsplus_block_allocate(sb, goal, 0, &len);
 		if (start >= goal) {
 			res = -ENOSPC;
@@ -379,56 +403,56 @@ int hfsplus_file_extend(struct inode *inode)
 	}
 
 	dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len);
-	if (HFSPLUS_I(inode).alloc_blocks <= HFSPLUS_I(inode).first_blocks) {
-		if (!HFSPLUS_I(inode).first_blocks) {
+
+	if (hip->alloc_blocks <= hip->first_blocks) {
+		if (!hip->first_blocks) {
 			dprint(DBG_EXTENT, "first extents\n");
 			/* no extents yet */
-			HFSPLUS_I(inode).first_extents[0].start_block = cpu_to_be32(start);
-			HFSPLUS_I(inode).first_extents[0].block_count = cpu_to_be32(len);
+			hip->first_extents[0].start_block = cpu_to_be32(start);
+			hip->first_extents[0].block_count = cpu_to_be32(len);
 			res = 0;
 		} else {
 			/* try to append to extents in inode */
-			res = hfsplus_add_extent(HFSPLUS_I(inode).first_extents,
-						 HFSPLUS_I(inode).alloc_blocks,
+			res = hfsplus_add_extent(hip->first_extents,
+						 hip->alloc_blocks,
 						 start, len);
 			if (res == -ENOSPC)
 				goto insert_extent;
 		}
 		if (!res) {
-			hfsplus_dump_extent(HFSPLUS_I(inode).first_extents);
-			HFSPLUS_I(inode).first_blocks += len;
+			hfsplus_dump_extent(hip->first_extents);
+			hip->first_blocks += len;
 		}
 	} else {
-		res = hfsplus_add_extent(HFSPLUS_I(inode).cached_extents,
-					 HFSPLUS_I(inode).alloc_blocks -
-					 HFSPLUS_I(inode).cached_start,
+		res = hfsplus_add_extent(hip->cached_extents,
+					 hip->alloc_blocks - hip->cached_start,
 					 start, len);
 		if (!res) {
-			hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
-			HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY;
-			HFSPLUS_I(inode).cached_blocks += len;
+			hfsplus_dump_extent(hip->cached_extents);
+			hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
+			hip->cached_blocks += len;
 		} else if (res == -ENOSPC)
 			goto insert_extent;
 	}
 out:
-	mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+	mutex_unlock(&hip->extents_lock);
 	if (!res) {
-		HFSPLUS_I(inode).alloc_blocks += len;
+		hip->alloc_blocks += len;
 		mark_inode_dirty(inode);
 	}
 	return res;
 
 insert_extent:
 	dprint(DBG_EXTENT, "insert new extent\n");
-	hfsplus_ext_write_extent(inode);
+	hfsplus_ext_write_extent_locked(inode);
 
-	memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-	HFSPLUS_I(inode).cached_extents[0].start_block = cpu_to_be32(start);
-	HFSPLUS_I(inode).cached_extents[0].block_count = cpu_to_be32(len);
-	hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
-	HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
-	HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).alloc_blocks;
-	HFSPLUS_I(inode).cached_blocks = len;
+	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+	hip->cached_extents[0].start_block = cpu_to_be32(start);
+	hip->cached_extents[0].block_count = cpu_to_be32(len);
+	hfsplus_dump_extent(hip->cached_extents);
+	hip->flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
+	hip->cached_start = hip->alloc_blocks;
+	hip->cached_blocks = len;
 
 	res = 0;
 	goto out;
@@ -437,13 +461,15 @@ insert_extent:
 void hfsplus_file_truncate(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	struct hfs_find_data fd;
 	u32 alloc_cnt, blk_cnt, start;
 	int res;
 
-	dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n", inode->i_ino,
-	       (long long)HFSPLUS_I(inode).phys_size, inode->i_size);
-	if (inode->i_size > HFSPLUS_I(inode).phys_size) {
+	dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n",
+		inode->i_ino, (long long)hip->phys_size, inode->i_size);
+
+	if (inode->i_size > hip->phys_size) {
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
@@ -460,47 +486,48 @@ void hfsplus_file_truncate(struct inode *inode)
 			return;
 		mark_inode_dirty(inode);
 		return;
-	} else if (inode->i_size == HFSPLUS_I(inode).phys_size)
+	} else if (inode->i_size == hip->phys_size)
 		return;
 
-	blk_cnt = (inode->i_size + HFSPLUS_SB(sb).alloc_blksz - 1) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	alloc_cnt = HFSPLUS_I(inode).alloc_blocks;
+	blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >>
+			HFSPLUS_SB(sb)->alloc_blksz_shift;
+	alloc_cnt = hip->alloc_blocks;
 	if (blk_cnt == alloc_cnt)
 		goto out;
 
-	mutex_lock(&HFSPLUS_I(inode).extents_lock);
-	hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
+	mutex_lock(&hip->extents_lock);
+	hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
 	while (1) {
-		if (alloc_cnt == HFSPLUS_I(inode).first_blocks) {
-			hfsplus_free_extents(sb, HFSPLUS_I(inode).first_extents,
+		if (alloc_cnt == hip->first_blocks) {
+			hfsplus_free_extents(sb, hip->first_extents,
 					     alloc_cnt, alloc_cnt - blk_cnt);
-			hfsplus_dump_extent(HFSPLUS_I(inode).first_extents);
-			HFSPLUS_I(inode).first_blocks = blk_cnt;
+			hfsplus_dump_extent(hip->first_extents);
+			hip->first_blocks = blk_cnt;
 			break;
 		}
 		res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt);
 		if (res)
 			break;
-		start = HFSPLUS_I(inode).cached_start;
-		hfsplus_free_extents(sb, HFSPLUS_I(inode).cached_extents,
+		start = hip->cached_start;
+		hfsplus_free_extents(sb, hip->cached_extents,
 				     alloc_cnt - start, alloc_cnt - blk_cnt);
-		hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
+		hfsplus_dump_extent(hip->cached_extents);
 		if (blk_cnt > start) {
-			HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY;
+			hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
 			break;
 		}
 		alloc_cnt = start;
-		HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).cached_blocks = 0;
-		HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+		hip->cached_start = hip->cached_blocks = 0;
+		hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
 		hfs_brec_remove(&fd);
 	}
 	hfs_find_exit(&fd);
-	mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+	mutex_unlock(&hip->extents_lock);
 
-	HFSPLUS_I(inode).alloc_blocks = blk_cnt;
+	hip->alloc_blocks = blk_cnt;
 out:
-	HFSPLUS_I(inode).phys_size = inode->i_size;
-	HFSPLUS_I(inode).fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-	inode_set_bytes(inode, HFSPLUS_I(inode).fs_blocks << sb->s_blocksize_bits);
+	hip->phys_size = inode->i_size;
+	hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
 	mark_inode_dirty(inode);
 }
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index dc856be3c2b0..cb3653efb57a 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -62,7 +62,7 @@ struct hfs_btree {
 	unsigned int depth;
 
 	//unsigned int map1_size, map_size;
-	struct semaphore tree_lock;
+	struct mutex tree_lock;
 
 	unsigned int pages_per_bnode;
 	spinlock_t hash_lock;
@@ -121,16 +121,21 @@ struct hfsplus_sb_info {
 	u32 sect_count;
 	int fs_shift;
 
-	/* Stuff in host order from Vol Header */
+	/* immutable data from the volume header */
 	u32 alloc_blksz;
 	int alloc_blksz_shift;
 	u32 total_blocks;
+	u32 data_clump_blocks, rsrc_clump_blocks;
+
+	/* mutable data from the volume header, protected by alloc_mutex */
 	u32 free_blocks;
-	u32 next_alloc;
+	struct mutex alloc_mutex;
+
+	/* mutable data from the volume header, protected by vh_mutex */
 	u32 next_cnid;
 	u32 file_count;
 	u32 folder_count;
-	u32 data_clump_blocks, rsrc_clump_blocks;
+	struct mutex vh_mutex;
 
 	/* Config options */
 	u32 creator;
@@ -143,40 +148,50 @@ struct hfsplus_sb_info {
 	int part, session;
 
 	unsigned long flags;
-
-	struct hlist_head rsrc_inodes;
 };
 
-#define HFSPLUS_SB_WRITEBACKUP	0x0001
-#define HFSPLUS_SB_NODECOMPOSE	0x0002
-#define HFSPLUS_SB_FORCE	0x0004
-#define HFSPLUS_SB_HFSX		0x0008
-#define HFSPLUS_SB_CASEFOLD	0x0010
+#define HFSPLUS_SB_WRITEBACKUP	0
+#define HFSPLUS_SB_NODECOMPOSE	1
+#define HFSPLUS_SB_FORCE	2
+#define HFSPLUS_SB_HFSX		3
+#define HFSPLUS_SB_CASEFOLD	4
 
 
 struct hfsplus_inode_info {
-	struct mutex extents_lock;
-	u32 clump_blocks, alloc_blocks;
-	sector_t fs_blocks;
-	/* Allocation extents from catalog record or volume header */
-	hfsplus_extent_rec first_extents;
-	u32 first_blocks;
-	hfsplus_extent_rec cached_extents;
-	u32 cached_start, cached_blocks;
 	atomic_t opencnt;
 
-	struct inode *rsrc_inode;
+	/*
+	 * Extent allocation information, protected by extents_lock.
+	 */
+	u32 first_blocks;
+	u32 clump_blocks;
+	u32 alloc_blocks;
+	u32 cached_start;
+	u32 cached_blocks;
+	hfsplus_extent_rec first_extents;
+	hfsplus_extent_rec cached_extents;
 	unsigned long flags;
+	struct mutex extents_lock;
 
+	/*
+	 * Immutable data.
+	 */
+	struct inode *rsrc_inode;
 	__be32 create_date;
-	/* Device number in hfsplus_permissions in catalog */
-	u32 dev;
-	/* BSD system and user file flags */
-	u8 rootflags;
-	u8 userflags;
 
+	/*
+	 * Protected by sbi->vh_mutex.
+	 */
+	u32 linkid;
+
+	/*
+	 * Protected by i_mutex.
+	 */
+	sector_t fs_blocks;
+	u8 userflags;		/* BSD user file flags */
 	struct list_head open_dir_list;
 	loff_t phys_size;
+
 	struct inode vfs_inode;
 };
 
@@ -184,8 +199,8 @@ struct hfsplus_inode_info {
 #define HFSPLUS_FLG_EXT_DIRTY	0x0002
 #define HFSPLUS_FLG_EXT_NEW	0x0004
 
-#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode).flags & HFSPLUS_FLG_RSRC))
-#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode).flags & HFSPLUS_FLG_RSRC)
+#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC))
+#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC)
 
 struct hfs_find_data {
 	/* filled by caller */
@@ -311,6 +326,7 @@ int hfsplus_create_cat(u32, struct inode *, struct qstr *, struct inode *);
 int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
 int hfsplus_rename_cat(u32, struct inode *, struct qstr *,
 		       struct inode *, struct qstr *);
+void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 
 /* dir.c */
 extern const struct inode_operations hfsplus_dir_inode_operations;
@@ -372,26 +388,15 @@ int hfsplus_read_wrapper(struct super_block *);
 int hfs_part_find(struct super_block *, sector_t *, sector_t *);
 
 /* access macros */
-/*
 static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
 }
+
 static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 {
 	return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
 }
-*/
-#define HFSPLUS_SB(super)	(*(struct hfsplus_sb_info *)(super)->s_fs_info)
-#define HFSPLUS_I(inode)	(*list_entry(inode, struct hfsplus_inode_info, vfs_inode))
-
-#if 1
-#define hfsplus_kmap(p)		({ struct page *__p = (p); kmap(__p); })
-#define hfsplus_kunmap(p)	({ struct page *__p = (p); kunmap(__p); __p; })
-#else
-#define hfsplus_kmap(p)		kmap(p)
-#define hfsplus_kunmap(p)	kunmap(p)
-#endif
 
 #define sb_bread512(sb, sec, data) ({			\
 	struct buffer_head *__bh;			\
@@ -419,6 +424,4 @@ static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 #define hfsp_ut2mt(t)		__hfsp_ut2mt((t).tv_sec)
 #define hfsp_now2mt()		__hfsp_ut2mt(get_seconds())
 
-#define kdev_t_to_nr(x)		(x)
-
 #endif
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index fe99fe8db61a..6892899fd6fb 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -200,6 +200,7 @@ struct hfsplus_cat_key {
 	struct hfsplus_unistr name;
 } __packed;
 
+#define HFSPLUS_CAT_KEYLEN	(sizeof(struct hfsplus_cat_key))
 
 /* Structs from hfs.h */
 struct hfsp_point {
@@ -323,7 +324,7 @@ struct hfsplus_ext_key {
 	__be32 start_block;
 } __packed;
 
-#define HFSPLUS_EXT_KEYLEN 12
+#define HFSPLUS_EXT_KEYLEN	sizeof(struct hfsplus_ext_key)
 
 /* HFS+ generic BTree key */
 typedef union {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index c5a979d62c65..78449280dae0 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -36,7 +36,7 @@ static int hfsplus_write_begin(struct file *file, struct address_space *mapping,
 	*pagep = NULL;
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				hfsplus_get_block,
-				&HFSPLUS_I(mapping->host).phys_size);
+				&HFSPLUS_I(mapping->host)->phys_size);
 	if (unlikely(ret)) {
 		loff_t isize = mapping->host->i_size;
 		if (pos + len > isize)
@@ -62,13 +62,13 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
 
 	switch (inode->i_ino) {
 	case HFSPLUS_EXT_CNID:
-		tree = HFSPLUS_SB(sb).ext_tree;
+		tree = HFSPLUS_SB(sb)->ext_tree;
 		break;
 	case HFSPLUS_CAT_CNID:
-		tree = HFSPLUS_SB(sb).cat_tree;
+		tree = HFSPLUS_SB(sb)->cat_tree;
 		break;
 	case HFSPLUS_ATTR_CNID:
-		tree = HFSPLUS_SB(sb).attr_tree;
+		tree = HFSPLUS_SB(sb)->attr_tree;
 		break;
 	default:
 		BUG();
@@ -172,12 +172,13 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
 	struct hfs_find_data fd;
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;
+	struct hfsplus_inode_info *hip;
 	int err;
 
 	if (HFSPLUS_IS_RSRC(dir) || strcmp(dentry->d_name.name, "rsrc"))
 		goto out;
 
-	inode = HFSPLUS_I(dir).rsrc_inode;
+	inode = HFSPLUS_I(dir)->rsrc_inode;
 	if (inode)
 		goto out;
 
@@ -185,12 +186,13 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
+	hip = HFSPLUS_I(inode);
 	inode->i_ino = dir->i_ino;
-	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-	mutex_init(&HFSPLUS_I(inode).extents_lock);
-	HFSPLUS_I(inode).flags = HFSPLUS_FLG_RSRC;
+	INIT_LIST_HEAD(&hip->open_dir_list);
+	mutex_init(&hip->extents_lock);
+	hip->flags = HFSPLUS_FLG_RSRC;
 
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	err = hfsplus_find_cat(sb, dir->i_ino, &fd);
 	if (!err)
 		err = hfsplus_cat_read_inode(inode, &fd);
@@ -199,10 +201,18 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
 		iput(inode);
 		return ERR_PTR(err);
 	}
-	HFSPLUS_I(inode).rsrc_inode = dir;
-	HFSPLUS_I(dir).rsrc_inode = inode;
+	hip->rsrc_inode = dir;
+	HFSPLUS_I(dir)->rsrc_inode = inode;
 	igrab(dir);
-	hlist_add_head(&inode->i_hash, &HFSPLUS_SB(sb).rsrc_inodes);
+
+	/*
+	 * __mark_inode_dirty expects inodes to be hashed.  Since we don't
+	 * want resource fork inodes in the regular inode space, we make them
+	 * appear hashed, but do not put on any lists.  hlist_del()
+	 * will work fine and require no locking.
+	 */
+	inode->i_hash.pprev = &inode->i_hash.next;
+
 	mark_inode_dirty(inode);
 out:
 	d_add(dentry, inode);
@@ -211,30 +221,27 @@ out:
 
 static void hfsplus_get_perms(struct inode *inode, struct hfsplus_perm *perms, int dir)
 {
-	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
 	u16 mode;
 
 	mode = be16_to_cpu(perms->mode);
 
 	inode->i_uid = be32_to_cpu(perms->owner);
 	if (!inode->i_uid && !mode)
-		inode->i_uid = HFSPLUS_SB(sb).uid;
+		inode->i_uid = sbi->uid;
 
 	inode->i_gid = be32_to_cpu(perms->group);
 	if (!inode->i_gid && !mode)
-		inode->i_gid = HFSPLUS_SB(sb).gid;
+		inode->i_gid = sbi->gid;
 
 	if (dir) {
-		mode = mode ? (mode & S_IALLUGO) :
-			(S_IRWXUGO & ~(HFSPLUS_SB(sb).umask));
+		mode = mode ? (mode & S_IALLUGO) : (S_IRWXUGO & ~(sbi->umask));
 		mode |= S_IFDIR;
 	} else if (!mode)
-		mode = S_IFREG | ((S_IRUGO|S_IWUGO) &
-			~(HFSPLUS_SB(sb).umask));
+		mode = S_IFREG | ((S_IRUGO|S_IWUGO) & ~(sbi->umask));
 	inode->i_mode = mode;
 
-	HFSPLUS_I(inode).rootflags = perms->rootflags;
-	HFSPLUS_I(inode).userflags = perms->userflags;
+	HFSPLUS_I(inode)->userflags = perms->userflags;
 	if (perms->rootflags & HFSPLUS_FLG_IMMUTABLE)
 		inode->i_flags |= S_IMMUTABLE;
 	else
@@ -245,30 +252,13 @@ static void hfsplus_get_perms(struct inode *inode, struct hfsplus_perm *perms, i
 		inode->i_flags &= ~S_APPEND;
 }
 
-static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
-{
-	if (inode->i_flags & S_IMMUTABLE)
-		perms->rootflags |= HFSPLUS_FLG_IMMUTABLE;
-	else
-		perms->rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
-	if (inode->i_flags & S_APPEND)
-		perms->rootflags |= HFSPLUS_FLG_APPEND;
-	else
-		perms->rootflags &= ~HFSPLUS_FLG_APPEND;
-	perms->userflags = HFSPLUS_I(inode).userflags;
-	perms->mode = cpu_to_be16(inode->i_mode);
-	perms->owner = cpu_to_be32(inode->i_uid);
-	perms->group = cpu_to_be32(inode->i_gid);
-	perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev);
-}
-
 static int hfsplus_file_open(struct inode *inode, struct file *file)
 {
 	if (HFSPLUS_IS_RSRC(inode))
-		inode = HFSPLUS_I(inode).rsrc_inode;
+		inode = HFSPLUS_I(inode)->rsrc_inode;
 	if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
 		return -EOVERFLOW;
-	atomic_inc(&HFSPLUS_I(inode).opencnt);
+	atomic_inc(&HFSPLUS_I(inode)->opencnt);
 	return 0;
 }
 
@@ -277,12 +267,13 @@ static int hfsplus_file_release(struct inode *inode, struct file *file)
 	struct super_block *sb = inode->i_sb;
 
 	if (HFSPLUS_IS_RSRC(inode))
-		inode = HFSPLUS_I(inode).rsrc_inode;
-	if (atomic_dec_and_test(&HFSPLUS_I(inode).opencnt)) {
+		inode = HFSPLUS_I(inode)->rsrc_inode;
+	if (atomic_dec_and_test(&HFSPLUS_I(inode)->opencnt)) {
 		mutex_lock(&inode->i_mutex);
 		hfsplus_file_truncate(inode);
 		if (inode->i_flags & S_DEAD) {
-			hfsplus_delete_cat(inode->i_ino, HFSPLUS_SB(sb).hidden_dir, NULL);
+			hfsplus_delete_cat(inode->i_ino,
+					   HFSPLUS_SB(sb)->hidden_dir, NULL);
 			hfsplus_delete_inode(inode);
 		}
 		mutex_unlock(&inode->i_mutex);
@@ -361,47 +352,52 @@ static const struct file_operations hfsplus_file_operations = {
 
 struct inode *hfsplus_new_inode(struct super_block *sb, int mode)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct inode *inode = new_inode(sb);
+	struct hfsplus_inode_info *hip;
+
 	if (!inode)
 		return NULL;
 
-	inode->i_ino = HFSPLUS_SB(sb).next_cnid++;
+	inode->i_ino = sbi->next_cnid++;
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
 	inode->i_nlink = 1;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
-	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-	mutex_init(&HFSPLUS_I(inode).extents_lock);
-	atomic_set(&HFSPLUS_I(inode).opencnt, 0);
-	HFSPLUS_I(inode).flags = 0;
-	memset(HFSPLUS_I(inode).first_extents, 0, sizeof(hfsplus_extent_rec));
-	memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-	HFSPLUS_I(inode).alloc_blocks = 0;
-	HFSPLUS_I(inode).first_blocks = 0;
-	HFSPLUS_I(inode).cached_start = 0;
-	HFSPLUS_I(inode).cached_blocks = 0;
-	HFSPLUS_I(inode).phys_size = 0;
-	HFSPLUS_I(inode).fs_blocks = 0;
-	HFSPLUS_I(inode).rsrc_inode = NULL;
+
+	hip = HFSPLUS_I(inode);
+	INIT_LIST_HEAD(&hip->open_dir_list);
+	mutex_init(&hip->extents_lock);
+	atomic_set(&hip->opencnt, 0);
+	hip->flags = 0;
+	memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
+	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+	hip->alloc_blocks = 0;
+	hip->first_blocks = 0;
+	hip->cached_start = 0;
+	hip->cached_blocks = 0;
+	hip->phys_size = 0;
+	hip->fs_blocks = 0;
+	hip->rsrc_inode = NULL;
 	if (S_ISDIR(inode->i_mode)) {
 		inode->i_size = 2;
-		HFSPLUS_SB(sb).folder_count++;
+		sbi->folder_count++;
 		inode->i_op = &hfsplus_dir_inode_operations;
 		inode->i_fop = &hfsplus_dir_operations;
 	} else if (S_ISREG(inode->i_mode)) {
-		HFSPLUS_SB(sb).file_count++;
+		sbi->file_count++;
 		inode->i_op = &hfsplus_file_inode_operations;
 		inode->i_fop = &hfsplus_file_operations;
 		inode->i_mapping->a_ops = &hfsplus_aops;
-		HFSPLUS_I(inode).clump_blocks = HFSPLUS_SB(sb).data_clump_blocks;
+		hip->clump_blocks = sbi->data_clump_blocks;
 	} else if (S_ISLNK(inode->i_mode)) {
-		HFSPLUS_SB(sb).file_count++;
+		sbi->file_count++;
 		inode->i_op = &page_symlink_inode_operations;
 		inode->i_mapping->a_ops = &hfsplus_aops;
-		HFSPLUS_I(inode).clump_blocks = 1;
+		hip->clump_blocks = 1;
 	} else
-		HFSPLUS_SB(sb).file_count++;
+		sbi->file_count++;
 	insert_inode_hash(inode);
 	mark_inode_dirty(inode);
 	sb->s_dirt = 1;
@@ -414,11 +410,11 @@ void hfsplus_delete_inode(struct inode *inode)
 	struct super_block *sb = inode->i_sb;
 
 	if (S_ISDIR(inode->i_mode)) {
-		HFSPLUS_SB(sb).folder_count--;
+		HFSPLUS_SB(sb)->folder_count--;
 		sb->s_dirt = 1;
 		return;
 	}
-	HFSPLUS_SB(sb).file_count--;
+	HFSPLUS_SB(sb)->file_count--;
 	if (S_ISREG(inode->i_mode)) {
 		if (!inode->i_nlink) {
 			inode->i_size = 0;
@@ -434,34 +430,39 @@ void hfsplus_delete_inode(struct inode *inode)
 void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
 {
 	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	u32 count;
 	int i;
 
-	memcpy(&HFSPLUS_I(inode).first_extents, &fork->extents,
-	       sizeof(hfsplus_extent_rec));
+	memcpy(&hip->first_extents, &fork->extents, sizeof(hfsplus_extent_rec));
 	for (count = 0, i = 0; i < 8; i++)
 		count += be32_to_cpu(fork->extents[i].block_count);
-	HFSPLUS_I(inode).first_blocks = count;
-	memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-	HFSPLUS_I(inode).cached_start = 0;
-	HFSPLUS_I(inode).cached_blocks = 0;
-
-	HFSPLUS_I(inode).alloc_blocks = be32_to_cpu(fork->total_blocks);
-	inode->i_size = HFSPLUS_I(inode).phys_size = be64_to_cpu(fork->total_size);
-	HFSPLUS_I(inode).fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-	inode_set_bytes(inode, HFSPLUS_I(inode).fs_blocks << sb->s_blocksize_bits);
-	HFSPLUS_I(inode).clump_blocks = be32_to_cpu(fork->clump_size) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	if (!HFSPLUS_I(inode).clump_blocks)
-		HFSPLUS_I(inode).clump_blocks = HFSPLUS_IS_RSRC(inode) ? HFSPLUS_SB(sb).rsrc_clump_blocks :
-				HFSPLUS_SB(sb).data_clump_blocks;
+	hip->first_blocks = count;
+	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+	hip->cached_start = 0;
+	hip->cached_blocks = 0;
+
+	hip->alloc_blocks = be32_to_cpu(fork->total_blocks);
+	hip->phys_size = inode->i_size = be64_to_cpu(fork->total_size);
+	hip->fs_blocks =
+		(inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
+	hip->clump_blocks =
+		be32_to_cpu(fork->clump_size) >> sbi->alloc_blksz_shift;
+	if (!hip->clump_blocks) {
+		hip->clump_blocks = HFSPLUS_IS_RSRC(inode) ?
+			sbi->rsrc_clump_blocks :
+			sbi->data_clump_blocks;
+	}
 }
 
 void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
 {
-	memcpy(&fork->extents, &HFSPLUS_I(inode).first_extents,
+	memcpy(&fork->extents, &HFSPLUS_I(inode)->first_extents,
 	       sizeof(hfsplus_extent_rec));
 	fork->total_size = cpu_to_be64(inode->i_size);
-	fork->total_blocks = cpu_to_be32(HFSPLUS_I(inode).alloc_blocks);
+	fork->total_blocks = cpu_to_be32(HFSPLUS_I(inode)->alloc_blocks);
 }
 
 int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
@@ -472,7 +473,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 
 	type = hfs_bnode_read_u16(fd->bnode, fd->entryoffset);
 
-	HFSPLUS_I(inode).dev = 0;
+	HFSPLUS_I(inode)->linkid = 0;
 	if (type == HFSPLUS_FOLDER) {
 		struct hfsplus_cat_folder *folder = &entry.folder;
 
@@ -486,8 +487,8 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 		inode->i_atime = hfsp_mt2ut(folder->access_date);
 		inode->i_mtime = hfsp_mt2ut(folder->content_mod_date);
 		inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
-		HFSPLUS_I(inode).create_date = folder->create_date;
-		HFSPLUS_I(inode).fs_blocks = 0;
+		HFSPLUS_I(inode)->create_date = folder->create_date;
+		HFSPLUS_I(inode)->fs_blocks = 0;
 		inode->i_op = &hfsplus_dir_inode_operations;
 		inode->i_fop = &hfsplus_dir_operations;
 	} else if (type == HFSPLUS_FILE) {
@@ -518,7 +519,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 		inode->i_atime = hfsp_mt2ut(file->access_date);
 		inode->i_mtime = hfsp_mt2ut(file->content_mod_date);
 		inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date);
-		HFSPLUS_I(inode).create_date = file->create_date;
+		HFSPLUS_I(inode)->create_date = file->create_date;
 	} else {
 		printk(KERN_ERR "hfs: bad catalog entry used to create inode\n");
 		res = -EIO;
@@ -533,12 +534,12 @@ int hfsplus_cat_write_inode(struct inode *inode)
 	hfsplus_cat_entry entry;
 
 	if (HFSPLUS_IS_RSRC(inode))
-		main_inode = HFSPLUS_I(inode).rsrc_inode;
+		main_inode = HFSPLUS_I(inode)->rsrc_inode;
 
 	if (!main_inode->i_nlink)
 		return 0;
 
-	if (hfs_find_init(HFSPLUS_SB(main_inode->i_sb).cat_tree, &fd))
+	if (hfs_find_init(HFSPLUS_SB(main_inode->i_sb)->cat_tree, &fd))
 		/* panic? */
 		return -EIO;
 
@@ -554,7 +555,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
 					sizeof(struct hfsplus_cat_folder));
 		/* simple node checks? */
-		hfsplus_set_perms(inode, &folder->permissions);
+		hfsplus_cat_set_perms(inode, &folder->permissions);
 		folder->access_date = hfsp_ut2mt(inode->i_atime);
 		folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
 		folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
@@ -576,11 +577,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
 					sizeof(struct hfsplus_cat_file));
 		hfsplus_inode_write_fork(inode, &file->data_fork);
-		if (S_ISREG(inode->i_mode))
-			HFSPLUS_I(inode).dev = inode->i_nlink;
-		if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
-			HFSPLUS_I(inode).dev = kdev_t_to_nr(inode->i_rdev);
-		hfsplus_set_perms(inode, &file->permissions);
+		hfsplus_cat_set_perms(inode, &file->permissions);
 		if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
 			file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
 		else
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index ac405f099026..5b4667e08ef7 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -17,83 +17,98 @@
 #include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/xattr.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include "hfsplus_fs.h"
 
-long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
 {
-	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+	unsigned int flags = 0;
+
+	if (inode->i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+	if (inode->i_flags |= S_APPEND)
+		flags |= FS_APPEND_FL;
+	if (hip->userflags & HFSPLUS_FLG_NODUMP)
+		flags |= FS_NODUMP_FL;
+
+	return put_user(flags, user_flags);
+}
+
+static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	unsigned int flags;
+	int err = 0;
 
-	lock_kernel();
-	switch (cmd) {
-	case HFSPLUS_IOC_EXT2_GETFLAGS:
-		flags = 0;
-		if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_IMMUTABLE)
-			flags |= FS_IMMUTABLE_FL; /* EXT2_IMMUTABLE_FL */
-		if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_APPEND)
-			flags |= FS_APPEND_FL; /* EXT2_APPEND_FL */
-		if (HFSPLUS_I(inode).userflags & HFSPLUS_FLG_NODUMP)
-			flags |= FS_NODUMP_FL; /* EXT2_NODUMP_FL */
-		return put_user(flags, (int __user *)arg);
-	case HFSPLUS_IOC_EXT2_SETFLAGS: {
-		int err = 0;
-		err = mnt_want_write(filp->f_path.mnt);
-		if (err) {
-			unlock_kernel();
-			return err;
-		}
+	err = mnt_want_write(file->f_path.mnt);
+	if (err)
+		goto out;
 
-		if (!is_owner_or_cap(inode)) {
-			err = -EACCES;
-			goto setflags_out;
-		}
-		if (get_user(flags, (int __user *)arg)) {
-			err = -EFAULT;
-			goto setflags_out;
-		}
-		if (flags & (FS_IMMUTABLE_FL|FS_APPEND_FL) ||
-		    HFSPLUS_I(inode).rootflags & (HFSPLUS_FLG_IMMUTABLE|HFSPLUS_FLG_APPEND)) {
-			if (!capable(CAP_LINUX_IMMUTABLE)) {
-				err = -EPERM;
-				goto setflags_out;
-			}
-		}
+	if (!is_owner_or_cap(inode)) {
+		err = -EACCES;
+		goto out_drop_write;
+	}
 
-		/* don't silently ignore unsupported ext2 flags */
-		if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
-			err = -EOPNOTSUPP;
-			goto setflags_out;
-		}
-		if (flags & FS_IMMUTABLE_FL) { /* EXT2_IMMUTABLE_FL */
-			inode->i_flags |= S_IMMUTABLE;
-			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_IMMUTABLE;
-		} else {
-			inode->i_flags &= ~S_IMMUTABLE;
-			HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
-		}
-		if (flags & FS_APPEND_FL) { /* EXT2_APPEND_FL */
-			inode->i_flags |= S_APPEND;
-			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_APPEND;
-		} else {
-			inode->i_flags &= ~S_APPEND;
-			HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_APPEND;
+	if (get_user(flags, user_flags)) {
+		err = -EFAULT;
+		goto out_drop_write;
+	}
+
+	mutex_lock(&inode->i_mutex);
+
+	if ((flags & (FS_IMMUTABLE_FL|FS_APPEND_FL)) ||
+	    inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
+		if (!capable(CAP_LINUX_IMMUTABLE)) {
+			err = -EPERM;
+			goto out_unlock_inode;
 		}
-		if (flags & FS_NODUMP_FL) /* EXT2_NODUMP_FL */
-			HFSPLUS_I(inode).userflags |= HFSPLUS_FLG_NODUMP;
-		else
-			HFSPLUS_I(inode).userflags &= ~HFSPLUS_FLG_NODUMP;
-
-		inode->i_ctime = CURRENT_TIME_SEC;
-		mark_inode_dirty(inode);
-setflags_out:
-		mnt_drop_write(filp->f_path.mnt);
-		unlock_kernel();
-		return err;
 	}
+
+	/* don't silently ignore unsupported ext2 flags */
+	if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
+		err = -EOPNOTSUPP;
+		goto out_unlock_inode;
+	}
+
+	if (flags & FS_IMMUTABLE_FL)
+		inode->i_flags |= S_IMMUTABLE;
+	else
+		inode->i_flags &= ~S_IMMUTABLE;
+
+	if (flags & FS_APPEND_FL)
+		inode->i_flags |= S_APPEND;
+	else
+		inode->i_flags &= ~S_APPEND;
+
+	if (flags & FS_NODUMP_FL)
+		hip->userflags |= HFSPLUS_FLG_NODUMP;
+	else
+		hip->userflags &= ~HFSPLUS_FLG_NODUMP;
+
+	inode->i_ctime = CURRENT_TIME_SEC;
+	mark_inode_dirty(inode);
+
+out_unlock_inode:
+	mutex_lock(&inode->i_mutex);
+out_drop_write:
+	mnt_drop_write(file->f_path.mnt);
+out:
+	return err;
+}
+
+long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+	case HFSPLUS_IOC_EXT2_GETFLAGS:
+		return hfsplus_ioctl_getflags(file, argp);
+	case HFSPLUS_IOC_EXT2_SETFLAGS:
+		return hfsplus_ioctl_setflags(file, argp);
 	default:
-		unlock_kernel();
 		return -ENOTTY;
 	}
 }
@@ -110,7 +125,7 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name,
 	if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
 		return -EOPNOTSUPP;
 
-	res = hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
+	res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
 	if (res)
 		return res;
 	res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
@@ -153,7 +168,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
 		return -EOPNOTSUPP;
 
 	if (size) {
-		res = hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
+		res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
 		if (res)
 			return res;
 		res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
@@ -177,7 +192,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
 		} else
 			res = size ? -ERANGE : 4;
 	} else
-		res = -ENODATA;
+		res = -EOPNOTSUPP;
 out:
 	if (size)
 		hfs_find_exit(&fd);
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 572628b4b07d..f9ab276a4d8d 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -143,13 +143,13 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
 			kfree(p);
 			break;
 		case opt_decompose:
-			sbi->flags &= ~HFSPLUS_SB_NODECOMPOSE;
+			clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
 			break;
 		case opt_nodecompose:
-			sbi->flags |= HFSPLUS_SB_NODECOMPOSE;
+			set_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
 			break;
 		case opt_force:
-			sbi->flags |= HFSPLUS_SB_FORCE;
+			set_bit(HFSPLUS_SB_FORCE, &sbi->flags);
 			break;
 		default:
 			return 0;
@@ -171,7 +171,7 @@ done:
 
 int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
 {
-	struct hfsplus_sb_info *sbi = &HFSPLUS_SB(mnt->mnt_sb);
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(mnt->mnt_sb);
 
 	if (sbi->creator != HFSPLUS_DEF_CR_TYPE)
 		seq_printf(seq, ",creator=%.4s", (char *)&sbi->creator);
@@ -184,7 +184,7 @@ int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
 		seq_printf(seq, ",session=%u", sbi->session);
 	if (sbi->nls)
 		seq_printf(seq, ",nls=%s", sbi->nls->charset);
-	if (sbi->flags & HFSPLUS_SB_NODECOMPOSE)
+	if (test_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags))
 		seq_printf(seq, ",nodecompose");
 	return 0;
 }
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index 1528a6fd0299..208b16c645cc 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -74,6 +74,7 @@ struct old_pmap {
 int hfs_part_find(struct super_block *sb,
 		  sector_t *part_start, sector_t *part_size)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct buffer_head *bh;
 	__be16 *data;
 	int i, size, res;
@@ -95,7 +96,7 @@ int hfs_part_find(struct super_block *sb,
 		for (i = 0; i < size; p++, i++) {
 			if (p->pdStart && p->pdSize &&
 			    p->pdFSID == cpu_to_be32(0x54465331)/*"TFS1"*/ &&
-			    (HFSPLUS_SB(sb).part < 0 || HFSPLUS_SB(sb).part == i)) {
+			    (sbi->part < 0 || sbi->part == i)) {
 				*part_start += be32_to_cpu(p->pdStart);
 				*part_size = be32_to_cpu(p->pdSize);
 				res = 0;
@@ -111,7 +112,7 @@ int hfs_part_find(struct super_block *sb,
 		size = be32_to_cpu(pm->pmMapBlkCnt);
 		for (i = 0; i < size;) {
 			if (!memcmp(pm->pmPartType,"Apple_HFS", 9) &&
-			    (HFSPLUS_SB(sb).part < 0 || HFSPLUS_SB(sb).part == i)) {
+			    (sbi->part < 0 || sbi->part == i)) {
 				*part_start += be32_to_cpu(pm->pmPyPartStart);
 				*part_size = be32_to_cpu(pm->pmPartBlkCnt);
 				res = 0;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 3b55c050c742..9a88d7536103 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -12,7 +12,6 @@
 #include <linux/pagemap.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/nls.h>
 
@@ -21,40 +20,11 @@ static void hfsplus_destroy_inode(struct inode *inode);
 
 #include "hfsplus_fs.h"
 
-struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
+static int hfsplus_system_read_inode(struct inode *inode)
 {
-	struct hfs_find_data fd;
-	struct hfsplus_vh *vhdr;
-	struct inode *inode;
-	long err = -EIO;
-
-	inode = iget_locked(sb, ino);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW))
-		return inode;
+	struct hfsplus_vh *vhdr = HFSPLUS_SB(inode->i_sb)->s_vhdr;
 
-	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-	mutex_init(&HFSPLUS_I(inode).extents_lock);
-	HFSPLUS_I(inode).flags = 0;
-	HFSPLUS_I(inode).rsrc_inode = NULL;
-	atomic_set(&HFSPLUS_I(inode).opencnt, 0);
-
-	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID) {
-	read_inode:
-		hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
-		err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
-		if (!err)
-			err = hfsplus_cat_read_inode(inode, &fd);
-		hfs_find_exit(&fd);
-		if (err)
-			goto bad_inode;
-		goto done;
-	}
-	vhdr = HFSPLUS_SB(inode->i_sb).s_vhdr;
-	switch(inode->i_ino) {
-	case HFSPLUS_ROOT_CNID:
-		goto read_inode;
+	switch (inode->i_ino) {
 	case HFSPLUS_EXT_CNID:
 		hfsplus_inode_read_fork(inode, &vhdr->ext_file);
 		inode->i_mapping->a_ops = &hfsplus_btree_aops;
@@ -75,74 +45,101 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
 		inode->i_mapping->a_ops = &hfsplus_btree_aops;
 		break;
 	default:
-		goto bad_inode;
+		return -EIO;
+	}
+
+	return 0;
+}
+
+struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
+{
+	struct hfs_find_data fd;
+	struct inode *inode;
+	int err;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
+	mutex_init(&HFSPLUS_I(inode)->extents_lock);
+	HFSPLUS_I(inode)->flags = 0;
+	HFSPLUS_I(inode)->rsrc_inode = NULL;
+	atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
+
+	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
+	    inode->i_ino == HFSPLUS_ROOT_CNID) {
+		hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+		err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+		if (!err)
+			err = hfsplus_cat_read_inode(inode, &fd);
+		hfs_find_exit(&fd);
+	} else {
+		err = hfsplus_system_read_inode(inode);
+	}
+
+	if (err) {
+		iget_failed(inode);
+		return ERR_PTR(err);
 	}
 
-done:
 	unlock_new_inode(inode);
 	return inode;
-
-bad_inode:
-	iget_failed(inode);
-	return ERR_PTR(err);
 }
 
-static int hfsplus_write_inode(struct inode *inode,
-		struct writeback_control *wbc)
+static int hfsplus_system_write_inode(struct inode *inode)
 {
-	struct hfsplus_vh *vhdr;
-	int ret = 0;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+	struct hfsplus_vh *vhdr = sbi->s_vhdr;
+	struct hfsplus_fork_raw *fork;
+	struct hfs_btree *tree = NULL;
 
-	dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino);
-	hfsplus_ext_write_extent(inode);
-	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID) {
-		return hfsplus_cat_write_inode(inode);
-	}
-	vhdr = HFSPLUS_SB(inode->i_sb).s_vhdr;
 	switch (inode->i_ino) {
-	case HFSPLUS_ROOT_CNID:
-		ret = hfsplus_cat_write_inode(inode);
-		break;
 	case HFSPLUS_EXT_CNID:
-		if (vhdr->ext_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->ext_file);
-		hfs_btree_write(HFSPLUS_SB(inode->i_sb).ext_tree);
+		fork = &vhdr->ext_file;
+		tree = sbi->ext_tree;
 		break;
 	case HFSPLUS_CAT_CNID:
-		if (vhdr->cat_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->cat_file);
-		hfs_btree_write(HFSPLUS_SB(inode->i_sb).cat_tree);
+		fork = &vhdr->cat_file;
+		tree = sbi->cat_tree;
 		break;
 	case HFSPLUS_ALLOC_CNID:
-		if (vhdr->alloc_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->alloc_file);
+		fork = &vhdr->alloc_file;
 		break;
 	case HFSPLUS_START_CNID:
-		if (vhdr->start_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->start_file);
+		fork = &vhdr->start_file;
 		break;
 	case HFSPLUS_ATTR_CNID:
-		if (vhdr->attr_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->attr_file);
-		hfs_btree_write(HFSPLUS_SB(inode->i_sb).attr_tree);
-		break;
+		fork = &vhdr->attr_file;
+		tree = sbi->attr_tree;
+	default:
+		return -EIO;
+	}
+
+	if (fork->total_size != cpu_to_be64(inode->i_size)) {
+		set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags);
+		inode->i_sb->s_dirt = 1;
 	}
-	return ret;
+	hfsplus_inode_write_fork(inode, fork);
+	if (tree)
+		hfs_btree_write(tree);
+	return 0;
+}
+
+static int hfsplus_write_inode(struct inode *inode,
+		struct writeback_control *wbc)
+{
+	dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino);
+
+	hfsplus_ext_write_extent(inode);
+
+	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
+	    inode->i_ino == HFSPLUS_ROOT_CNID)
+		return hfsplus_cat_write_inode(inode);
+	else
+		return hfsplus_system_write_inode(inode);
 }
 
 static void hfsplus_evict_inode(struct inode *inode)
@@ -151,51 +148,53 @@ static void hfsplus_evict_inode(struct inode *inode)
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
 	if (HFSPLUS_IS_RSRC(inode)) {
-		HFSPLUS_I(HFSPLUS_I(inode).rsrc_inode).rsrc_inode = NULL;
-		iput(HFSPLUS_I(inode).rsrc_inode);
+		HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
+		iput(HFSPLUS_I(inode)->rsrc_inode);
 	}
 }
 
 int hfsplus_sync_fs(struct super_block *sb, int wait)
 {
-	struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
 	dprint(DBG_SUPER, "hfsplus_write_super\n");
 
-	lock_super(sb);
+	mutex_lock(&sbi->vh_mutex);
+	mutex_lock(&sbi->alloc_mutex);
 	sb->s_dirt = 0;
 
-	vhdr->free_blocks = cpu_to_be32(HFSPLUS_SB(sb).free_blocks);
-	vhdr->next_alloc = cpu_to_be32(HFSPLUS_SB(sb).next_alloc);
-	vhdr->next_cnid = cpu_to_be32(HFSPLUS_SB(sb).next_cnid);
-	vhdr->folder_count = cpu_to_be32(HFSPLUS_SB(sb).folder_count);
-	vhdr->file_count = cpu_to_be32(HFSPLUS_SB(sb).file_count);
+	vhdr->free_blocks = cpu_to_be32(sbi->free_blocks);
+	vhdr->next_cnid = cpu_to_be32(sbi->next_cnid);
+	vhdr->folder_count = cpu_to_be32(sbi->folder_count);
+	vhdr->file_count = cpu_to_be32(sbi->file_count);
 
-	mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-	if (HFSPLUS_SB(sb).flags & HFSPLUS_SB_WRITEBACKUP) {
-		if (HFSPLUS_SB(sb).sect_count) {
+	mark_buffer_dirty(sbi->s_vhbh);
+	if (test_and_clear_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags)) {
+		if (sbi->sect_count) {
 			struct buffer_head *bh;
 			u32 block, offset;
 
-			block = HFSPLUS_SB(sb).blockoffset;
-			block += (HFSPLUS_SB(sb).sect_count - 2) >> (sb->s_blocksize_bits - 9);
-			offset = ((HFSPLUS_SB(sb).sect_count - 2) << 9) & (sb->s_blocksize - 1);
-			printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n", HFSPLUS_SB(sb).blockoffset,
-				HFSPLUS_SB(sb).sect_count, block, offset);
+			block = sbi->blockoffset;
+			block += (sbi->sect_count - 2) >> (sb->s_blocksize_bits - 9);
+			offset = ((sbi->sect_count - 2) << 9) & (sb->s_blocksize - 1);
+			printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n",
+					  sbi->blockoffset, sbi->sect_count,
+					  block, offset);
 			bh = sb_bread(sb, block);
 			if (bh) {
 				vhdr = (struct hfsplus_vh *)(bh->b_data + offset);
 				if (be16_to_cpu(vhdr->signature) == HFSPLUS_VOLHEAD_SIG) {
-					memcpy(vhdr, HFSPLUS_SB(sb).s_vhdr, sizeof(*vhdr));
+					memcpy(vhdr, sbi->s_vhdr, sizeof(*vhdr));
 					mark_buffer_dirty(bh);
 					brelse(bh);
 				} else
 					printk(KERN_WARNING "hfs: backup not found!\n");
 			}
 		}
-		HFSPLUS_SB(sb).flags &= ~HFSPLUS_SB_WRITEBACKUP;
 	}
-	unlock_super(sb);
+	mutex_unlock(&sbi->alloc_mutex);
+	mutex_unlock(&sbi->vh_mutex);
 	return 0;
 }
 
@@ -209,48 +208,48 @@ static void hfsplus_write_super(struct super_block *sb)
 
 static void hfsplus_put_super(struct super_block *sb)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+
 	dprint(DBG_SUPER, "hfsplus_put_super\n");
+
 	if (!sb->s_fs_info)
 		return;
 
-	lock_kernel();
-
 	if (sb->s_dirt)
 		hfsplus_write_super(sb);
-	if (!(sb->s_flags & MS_RDONLY) && HFSPLUS_SB(sb).s_vhdr) {
-		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+	if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) {
+		struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
 		vhdr->modify_date = hfsp_now2mt();
 		vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT);
 		vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT);
-		mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-		sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh);
+		mark_buffer_dirty(sbi->s_vhbh);
+		sync_dirty_buffer(sbi->s_vhbh);
 	}
 
-	hfs_btree_close(HFSPLUS_SB(sb).cat_tree);
-	hfs_btree_close(HFSPLUS_SB(sb).ext_tree);
-	iput(HFSPLUS_SB(sb).alloc_file);
-	iput(HFSPLUS_SB(sb).hidden_dir);
-	brelse(HFSPLUS_SB(sb).s_vhbh);
-	unload_nls(HFSPLUS_SB(sb).nls);
+	hfs_btree_close(sbi->cat_tree);
+	hfs_btree_close(sbi->ext_tree);
+	iput(sbi->alloc_file);
+	iput(sbi->hidden_dir);
+	brelse(sbi->s_vhbh);
+	unload_nls(sbi->nls);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
-
-	unlock_kernel();
 }
 
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = HFSPLUS_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_blocks = HFSPLUS_SB(sb).total_blocks << HFSPLUS_SB(sb).fs_shift;
-	buf->f_bfree = HFSPLUS_SB(sb).free_blocks << HFSPLUS_SB(sb).fs_shift;
+	buf->f_blocks = sbi->total_blocks << sbi->fs_shift;
+	buf->f_bfree = sbi->free_blocks << sbi->fs_shift;
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0xFFFFFFFF;
-	buf->f_ffree = 0xFFFFFFFF - HFSPLUS_SB(sb).next_cnid;
+	buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = HFSPLUS_MAX_STRLEN;
@@ -263,11 +262,11 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
 	if (!(*flags & MS_RDONLY)) {
-		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
 		struct hfsplus_sb_info sbi;
 
 		memset(&sbi, 0, sizeof(struct hfsplus_sb_info));
-		sbi.nls = HFSPLUS_SB(sb).nls;
+		sbi.nls = HFSPLUS_SB(sb)->nls;
 		if (!hfsplus_parse_options(data, &sbi))
 			return -EINVAL;
 
@@ -276,7 +275,7 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
 			       "running fsck.hfsplus is recommended.  leaving read-only.\n");
 			sb->s_flags |= MS_RDONLY;
 			*flags |= MS_RDONLY;
-		} else if (sbi.flags & HFSPLUS_SB_FORCE) {
+		} else if (test_bit(HFSPLUS_SB_FORCE, &sbi.flags)) {
 			/* nothing */
 		} else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
 			printk(KERN_WARNING "hfs: filesystem is marked locked, leaving read-only.\n");
@@ -320,7 +319,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 
 	sb->s_fs_info = sbi;
-	INIT_HLIST_HEAD(&sbi->rsrc_inodes);
+	mutex_init(&sbi->alloc_mutex);
+	mutex_init(&sbi->vh_mutex);
 	hfsplus_fill_defaults(sbi);
 	if (!hfsplus_parse_options(data, sbi)) {
 		printk(KERN_ERR "hfs: unable to parse mount options\n");
@@ -344,7 +344,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 		err = -EINVAL;
 		goto cleanup;
 	}
-	vhdr = HFSPLUS_SB(sb).s_vhdr;
+	vhdr = sbi->s_vhdr;
 
 	/* Copy parts of the volume header into the superblock */
 	sb->s_magic = HFSPLUS_VOLHEAD_SIG;
@@ -353,18 +353,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 		printk(KERN_ERR "hfs: wrong filesystem version\n");
 		goto cleanup;
 	}
-	HFSPLUS_SB(sb).total_blocks = be32_to_cpu(vhdr->total_blocks);
-	HFSPLUS_SB(sb).free_blocks = be32_to_cpu(vhdr->free_blocks);
-	HFSPLUS_SB(sb).next_alloc = be32_to_cpu(vhdr->next_alloc);
-	HFSPLUS_SB(sb).next_cnid = be32_to_cpu(vhdr->next_cnid);
-	HFSPLUS_SB(sb).file_count = be32_to_cpu(vhdr->file_count);
-	HFSPLUS_SB(sb).folder_count = be32_to_cpu(vhdr->folder_count);
-	HFSPLUS_SB(sb).data_clump_blocks = be32_to_cpu(vhdr->data_clump_sz) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	if (!HFSPLUS_SB(sb).data_clump_blocks)
-		HFSPLUS_SB(sb).data_clump_blocks = 1;
-	HFSPLUS_SB(sb).rsrc_clump_blocks = be32_to_cpu(vhdr->rsrc_clump_sz) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	if (!HFSPLUS_SB(sb).rsrc_clump_blocks)
-		HFSPLUS_SB(sb).rsrc_clump_blocks = 1;
+	sbi->total_blocks = be32_to_cpu(vhdr->total_blocks);
+	sbi->free_blocks = be32_to_cpu(vhdr->free_blocks);
+	sbi->next_cnid = be32_to_cpu(vhdr->next_cnid);
+	sbi->file_count = be32_to_cpu(vhdr->file_count);
+	sbi->folder_count = be32_to_cpu(vhdr->folder_count);
+	sbi->data_clump_blocks =
+		be32_to_cpu(vhdr->data_clump_sz) >> sbi->alloc_blksz_shift;
+	if (!sbi->data_clump_blocks)
+		sbi->data_clump_blocks = 1;
+	sbi->rsrc_clump_blocks =
+		be32_to_cpu(vhdr->rsrc_clump_sz) >> sbi->alloc_blksz_shift;
+	if (!sbi->rsrc_clump_blocks)
+		sbi->rsrc_clump_blocks = 1;
 
 	/* Set up operations so we can load metadata */
 	sb->s_op = &hfsplus_sops;
@@ -374,7 +375,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 		printk(KERN_WARNING "hfs: Filesystem was not cleanly unmounted, "
 		       "running fsck.hfsplus is recommended.  mounting read-only.\n");
 		sb->s_flags |= MS_RDONLY;
-	} else if (sbi->flags & HFSPLUS_SB_FORCE) {
+	} else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
 		/* nothing */
 	} else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
 		printk(KERN_WARNING "hfs: Filesystem is marked locked, mounting read-only.\n");
@@ -384,16 +385,15 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 		       "use the force option at your own risk, mounting read-only.\n");
 		sb->s_flags |= MS_RDONLY;
 	}
-	sbi->flags &= ~HFSPLUS_SB_FORCE;
 
 	/* Load metadata objects (B*Trees) */
-	HFSPLUS_SB(sb).ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
-	if (!HFSPLUS_SB(sb).ext_tree) {
+	sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
+	if (!sbi->ext_tree) {
 		printk(KERN_ERR "hfs: failed to load extents file\n");
 		goto cleanup;
 	}
-	HFSPLUS_SB(sb).cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
-	if (!HFSPLUS_SB(sb).cat_tree) {
+	sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
+	if (!sbi->cat_tree) {
 		printk(KERN_ERR "hfs: failed to load catalog file\n");
 		goto cleanup;
 	}
@@ -404,7 +404,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 		err = PTR_ERR(inode);
 		goto cleanup;
 	}
-	HFSPLUS_SB(sb).alloc_file = inode;
+	sbi->alloc_file = inode;
 
 	/* Load the root directory */
 	root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID);
@@ -423,7 +423,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 
 	str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
 	str.name = HFSP_HIDDENDIR_NAME;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(sbi->cat_tree, &fd);
 	hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
@@ -434,7 +434,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 			err = PTR_ERR(inode);
 			goto cleanup;
 		}
-		HFSPLUS_SB(sb).hidden_dir = inode;
+		sbi->hidden_dir = inode;
 	} else
 		hfs_find_exit(&fd);
 
@@ -449,15 +449,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	be32_add_cpu(&vhdr->write_count, 1);
 	vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
 	vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
-	mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-	sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh);
+	mark_buffer_dirty(sbi->s_vhbh);
+	sync_dirty_buffer(sbi->s_vhbh);
 
-	if (!HFSPLUS_SB(sb).hidden_dir) {
+	if (!sbi->hidden_dir) {
 		printk(KERN_DEBUG "hfs: create hidden dir...\n");
-		HFSPLUS_SB(sb).hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
-		hfsplus_create_cat(HFSPLUS_SB(sb).hidden_dir->i_ino, sb->s_root->d_inode,
-				   &str, HFSPLUS_SB(sb).hidden_dir);
-		mark_inode_dirty(HFSPLUS_SB(sb).hidden_dir);
+
+		mutex_lock(&sbi->vh_mutex);
+		sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
+		hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode,
+				   &str, sbi->hidden_dir);
+		mutex_unlock(&sbi->vh_mutex);
+
+		mark_inode_dirty(sbi->hidden_dir);
 	}
 out:
 	unload_nls(sbi->nls);
@@ -486,7 +490,7 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb)
 
 static void hfsplus_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(hfsplus_inode_cachep, &HFSPLUS_I(inode));
+	kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode));
 }
 
 #define HFSPLUS_INODE_SIZE	sizeof(struct hfsplus_inode_info)
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index 628ccf6fa402..b66d67de882c 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -121,7 +121,7 @@ static u16 *hfsplus_compose_lookup(u16 *p, u16 cc)
 int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, char *astr, int *len_p)
 {
 	const hfsplus_unichr *ip;
-	struct nls_table *nls = HFSPLUS_SB(sb).nls;
+	struct nls_table *nls = HFSPLUS_SB(sb)->nls;
 	u8 *op;
 	u16 cc, c0, c1;
 	u16 *ce1, *ce2;
@@ -132,7 +132,7 @@ int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, c
 	ustrlen = be16_to_cpu(ustr->length);
 	len = *len_p;
 	ce1 = NULL;
-	compose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 
 	while (ustrlen > 0) {
 		c0 = be16_to_cpu(*ip++);
@@ -246,7 +246,7 @@ out:
 static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
 			      wchar_t *uc)
 {
-	int size = HFSPLUS_SB(sb).nls->char2uni(astr, len, uc);
+	int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc);
 	if (size <= 0) {
 		*uc = '?';
 		size = 1;
@@ -293,7 +293,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
 	u16 *dstr, outlen = 0;
 	wchar_t c;
 
-	decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
 		size = asc2unichar(sb, astr, len, &c);
 
@@ -330,8 +330,8 @@ int hfsplus_hash_dentry(struct dentry *dentry, struct qstr *str)
 	wchar_t c;
 	u16 c2;
 
-	casefold = (HFSPLUS_SB(sb).flags & HFSPLUS_SB_CASEFOLD);
-	decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
+	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	hash = init_name_hash();
 	astr = str->name;
 	len = str->len;
@@ -373,8 +373,8 @@ int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *
 	u16 c1, c2;
 	wchar_t c;
 
-	casefold = (HFSPLUS_SB(sb).flags & HFSPLUS_SB_CASEFOLD);
-	decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
+	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	astr1 = s1->name;
 	len1 = s1->len;
 	astr2 = s2->name;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index bed78ac8f6d1..8972c20b3216 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -65,8 +65,8 @@ static int hfsplus_get_last_session(struct super_block *sb,
 	*start = 0;
 	*size = sb->s_bdev->bd_inode->i_size >> 9;
 
-	if (HFSPLUS_SB(sb).session >= 0) {
-		te.cdte_track = HFSPLUS_SB(sb).session;
+	if (HFSPLUS_SB(sb)->session >= 0) {
+		te.cdte_track = HFSPLUS_SB(sb)->session;
 		te.cdte_format = CDROM_LBA;
 		res = ioctl_by_bdev(sb->s_bdev, CDROMREADTOCENTRY, (unsigned long)&te);
 		if (!res && (te.cdte_ctrl & CDROM_DATA_TRACK) == 4) {
@@ -87,6 +87,7 @@ static int hfsplus_get_last_session(struct super_block *sb,
 /* Takes in super block, returns true if good data read */
 int hfsplus_read_wrapper(struct super_block *sb)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct buffer_head *bh;
 	struct hfsplus_vh *vhdr;
 	struct hfsplus_wd wd;
@@ -122,7 +123,7 @@ int hfsplus_read_wrapper(struct super_block *sb)
 		if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
 			break;
 		if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIGX)) {
-			HFSPLUS_SB(sb).flags |= HFSPLUS_SB_HFSX;
+			set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
 			break;
 		}
 		brelse(bh);
@@ -143,11 +144,11 @@ int hfsplus_read_wrapper(struct super_block *sb)
 	if (blocksize < HFSPLUS_SECTOR_SIZE ||
 	    ((blocksize - 1) & blocksize))
 		return -EINVAL;
-	HFSPLUS_SB(sb).alloc_blksz = blocksize;
-	HFSPLUS_SB(sb).alloc_blksz_shift = 0;
+	sbi->alloc_blksz = blocksize;
+	sbi->alloc_blksz_shift = 0;
 	while ((blocksize >>= 1) != 0)
-		HFSPLUS_SB(sb).alloc_blksz_shift++;
-	blocksize = min(HFSPLUS_SB(sb).alloc_blksz, (u32)PAGE_SIZE);
+		sbi->alloc_blksz_shift++;
+	blocksize = min(sbi->alloc_blksz, (u32)PAGE_SIZE);
 
 	/* align block size to block offset */
 	while (part_start & ((blocksize >> HFSPLUS_SECTOR_SHIFT) - 1))
@@ -158,23 +159,26 @@ int hfsplus_read_wrapper(struct super_block *sb)
 		return -EINVAL;
 	}
 
-	HFSPLUS_SB(sb).blockoffset = part_start >>
-			(sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
-	HFSPLUS_SB(sb).sect_count = part_size;
-	HFSPLUS_SB(sb).fs_shift = HFSPLUS_SB(sb).alloc_blksz_shift -
-			sb->s_blocksize_bits;
+	sbi->blockoffset =
+		part_start >> (sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
+	sbi->sect_count = part_size;
+	sbi->fs_shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
 
 	bh = sb_bread512(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, vhdr);
 	if (!bh)
 		return -EIO;
 
 	/* should still be the same... */
-	if (vhdr->signature != (HFSPLUS_SB(sb).flags & HFSPLUS_SB_HFSX ?
-				cpu_to_be16(HFSPLUS_VOLHEAD_SIGX) :
-				cpu_to_be16(HFSPLUS_VOLHEAD_SIG)))
-		goto error;
-	HFSPLUS_SB(sb).s_vhbh = bh;
-	HFSPLUS_SB(sb).s_vhdr = vhdr;
+	if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+		if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIGX))
+			goto error;
+	} else {
+		if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
+			goto error;
+	}
+
+	sbi->s_vhbh = bh;
+	sbi->s_vhdr = vhdr;
 
 	return 0;
  error:
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index cdfb8c6a4206..c16f8d8331b5 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -196,8 +196,6 @@ fh_lock(struct svc_fh *fhp)
 static inline void
 fh_unlock(struct svc_fh *fhp)
 {
-	BUG_ON(!fhp->fh_dentry);
-
 	if (fhp->fh_locked) {
 		fill_post_wcc(fhp);
 		mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex);
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
index 22c629eedd82..b388443c3a09 100644
--- a/fs/notify/Kconfig
+++ b/fs/notify/Kconfig
@@ -3,4 +3,4 @@ config FSNOTIFY
 
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"
-source "fs/notify/fanotify/Kconfig"
+#source "fs/notify/fanotify/Kconfig"
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index a76e0aa5cd3f..391915093fe1 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -209,7 +209,10 @@ static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
 	}
 
 	inode->i_mode = new_mode;
+	inode->i_ctime = CURRENT_TIME;
 	di->i_mode = cpu_to_le16(inode->i_mode);
+	di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
+	di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
 
 	ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 1361997cf205..cbe2f057cc28 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -977,7 +977,7 @@ static int o2net_tx_can_proceed(struct o2net_node *nn,
 int o2net_send_message_vec(u32 msg_type, u32 key, struct kvec *caller_vec,
 			   size_t caller_veclen, u8 target_node, int *status)
 {
-	int ret;
+	int ret = 0;
 	struct o2net_msg *msg = NULL;
 	size_t veclen, caller_bytes = 0;
 	struct kvec *vec = NULL;
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index f04ebcfffc4a..c49f6de0e7ab 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -3931,6 +3931,15 @@ static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir,
 		goto out_commit;
 	}
 
+	cpos = split_hash;
+	ret = ocfs2_dx_dir_new_cluster(dir, &et, cpos, handle,
+				       data_ac, meta_ac, new_dx_leaves,
+				       num_dx_leaves);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
 	for (i = 0; i < num_dx_leaves; i++) {
 		ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir),
 					      orig_dx_leaves[i],
@@ -3939,15 +3948,14 @@ static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir,
 			mlog_errno(ret);
 			goto out_commit;
 		}
-	}
 
-	cpos = split_hash;
-	ret = ocfs2_dx_dir_new_cluster(dir, &et, cpos, handle,
-				       data_ac, meta_ac, new_dx_leaves,
-				       num_dx_leaves);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_commit;
+		ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir),
+					      new_dx_leaves[i],
+					      OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
 	}
 
 	ocfs2_dx_dir_transfer_leaf(dir, split_hash, handle, tmp_dx_leaf,
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 4b6ae2c13b47..765298908f1d 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -1030,6 +1030,7 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm,
 			 struct dlm_lock_resource *res);
 void dlm_clean_master_list(struct dlm_ctxt *dlm,
 			   u8 dead_node);
+void dlm_force_free_mles(struct dlm_ctxt *dlm);
 int dlm_lock_basts_flushed(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 int __dlm_lockres_has_locks(struct dlm_lock_resource *res);
 int __dlm_lockres_unused(struct dlm_lock_resource *res);
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 5efdd37dfe48..901ca52bf86b 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -636,8 +636,14 @@ static void *lockres_seq_start(struct seq_file *m, loff_t *pos)
 	spin_lock(&dlm->track_lock);
 	if (oldres)
 		track_list = &oldres->tracking;
-	else
+	else {
 		track_list = &dlm->tracking_list;
+		if (list_empty(track_list)) {
+			dl = NULL;
+			spin_unlock(&dlm->track_lock);
+			goto bail;
+		}
+	}
 
 	list_for_each_entry(res, track_list, tracking) {
 		if (&res->tracking == &dlm->tracking_list)
@@ -660,6 +666,7 @@ static void *lockres_seq_start(struct seq_file *m, loff_t *pos)
 	} else
 		dl = NULL;
 
+bail:
 	/* passed to seq_show */
 	return dl;
 }
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 153abb5abef0..11a5c87fd7f7 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -693,6 +693,7 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm)
 
 		dlm_mark_domain_leaving(dlm);
 		dlm_leave_domain(dlm);
+		dlm_force_free_mles(dlm);
 		dlm_complete_dlm_shutdown(dlm);
 	}
 	dlm_put(dlm);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index ffb4c68dafa4..f564b0e5f80d 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -3433,3 +3433,43 @@ void dlm_lockres_release_ast(struct dlm_ctxt *dlm,
 	wake_up(&res->wq);
 	wake_up(&dlm->migration_wq);
 }
+
+void dlm_force_free_mles(struct dlm_ctxt *dlm)
+{
+	int i;
+	struct hlist_head *bucket;
+	struct dlm_master_list_entry *mle;
+	struct hlist_node *tmp, *list;
+
+	/*
+	 * We notified all other nodes that we are exiting the domain and
+	 * marked the dlm state to DLM_CTXT_LEAVING. If any mles are still
+	 * around we force free them and wake any processes that are waiting
+	 * on the mles
+	 */
+	spin_lock(&dlm->spinlock);
+	spin_lock(&dlm->master_lock);
+
+	BUG_ON(dlm->dlm_state != DLM_CTXT_LEAVING);
+	BUG_ON((find_next_bit(dlm->domain_map, O2NM_MAX_NODES, 0) < O2NM_MAX_NODES));
+
+	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
+		bucket = dlm_master_hash(dlm, i);
+		hlist_for_each_safe(list, tmp, bucket) {
+			mle = hlist_entry(list, struct dlm_master_list_entry,
+					  master_hash_node);
+			if (mle->type != DLM_MLE_BLOCK) {
+				mlog(ML_ERROR, "bad mle: %p\n", mle);
+				dlm_print_one_mle(mle);
+			}
+			atomic_set(&mle->woken, 1);
+			wake_up(&mle->wq);
+
+			__dlm_unlink_mle(dlm, mle);
+			__dlm_mle_detach_hb_events(dlm, mle);
+			__dlm_put_mle(mle);
+		}
+	}
+	spin_unlock(&dlm->master_lock);
+	spin_unlock(&dlm->spinlock);
+}
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index d1ce48e1b3d6..1d596d8c4a4a 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -84,6 +84,7 @@ enum {
 	OI_LS_PARENT,
 	OI_LS_RENAME1,
 	OI_LS_RENAME2,
+	OI_LS_REFLINK_TARGET,
 };
 
 int ocfs2_dlm_init(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 33f1c9a8258d..fa31d05e41b7 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -235,18 +235,31 @@
 #define OCFS2_HAS_REFCOUNT_FL   (0x0010)
 
 /* Inode attributes, keep in sync with EXT2 */
-#define OCFS2_SECRM_FL		(0x00000001)	/* Secure deletion */
-#define OCFS2_UNRM_FL		(0x00000002)	/* Undelete */
-#define OCFS2_COMPR_FL		(0x00000004)	/* Compress file */
-#define OCFS2_SYNC_FL		(0x00000008)	/* Synchronous updates */
-#define OCFS2_IMMUTABLE_FL	(0x00000010)	/* Immutable file */
-#define OCFS2_APPEND_FL		(0x00000020)	/* writes to file may only append */
-#define OCFS2_NODUMP_FL		(0x00000040)	/* do not dump file */
-#define OCFS2_NOATIME_FL	(0x00000080)	/* do not update atime */
-#define OCFS2_DIRSYNC_FL	(0x00010000)	/* dirsync behaviour (directories only) */
-
-#define OCFS2_FL_VISIBLE	(0x000100FF)	/* User visible flags */
-#define OCFS2_FL_MODIFIABLE	(0x000100FF)	/* User modifiable flags */
+#define OCFS2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define OCFS2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define OCFS2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define OCFS2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define OCFS2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define OCFS2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define OCFS2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define OCFS2_NOATIME_FL		FS_NOATIME_FL	/* do not update atime */
+/* Reserved for compression usage... */
+#define OCFS2_DIRTY_FL			FS_DIRTY_FL
+#define OCFS2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define OCFS2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define OCFS2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
+/* End compression flags --- maybe not all used */
+#define OCFS2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define OCFS2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define OCFS2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define OCFS2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define OCFS2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define OCFS2_DIRSYNC_FL		FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define OCFS2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define OCFS2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define OCFS2_FL_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define OCFS2_FL_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
 
 /*
  * Extent record flags (e_node.leaf.flags)
diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h
index 2d3420af1a83..5d241505690b 100644
--- a/fs/ocfs2/ocfs2_ioctl.h
+++ b/fs/ocfs2/ocfs2_ioctl.h
@@ -23,10 +23,10 @@
 /*
  * ioctl commands
  */
-#define OCFS2_IOC_GETFLAGS	_IOR('f', 1, long)
-#define OCFS2_IOC_SETFLAGS	_IOW('f', 2, long)
-#define OCFS2_IOC32_GETFLAGS	_IOR('f', 1, int)
-#define OCFS2_IOC32_SETFLAGS	_IOW('f', 2, int)
+#define OCFS2_IOC_GETFLAGS	FS_IOC_GETFLAGS
+#define OCFS2_IOC_SETFLAGS	FS_IOC_SETFLAGS
+#define OCFS2_IOC32_GETFLAGS	FS_IOC32_GETFLAGS
+#define OCFS2_IOC32_SETFLAGS	FS_IOC32_SETFLAGS
 
 /*
  * Space reservation / allocation / free ioctls and argument structure
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 0afeda83120f..efdd75607406 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4201,8 +4201,9 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 		goto out;
 	}
 
-	mutex_lock(&new_inode->i_mutex);
-	ret = ocfs2_inode_lock(new_inode, &new_bh, 1);
+	mutex_lock_nested(&new_inode->i_mutex, I_MUTEX_CHILD);
+	ret = ocfs2_inode_lock_nested(new_inode, &new_bh, 1,
+				      OI_LS_REFLINK_TARGET);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_unlock;
diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c
index d8b6e4259b80..3e78db361bc7 100644
--- a/fs/ocfs2/reservations.c
+++ b/fs/ocfs2/reservations.c
@@ -732,25 +732,23 @@ int ocfs2_resmap_resv_bits(struct ocfs2_reservation_map *resmap,
 			   struct ocfs2_alloc_reservation *resv,
 			   int *cstart, int *clen)
 {
-	unsigned int wanted = *clen;
-
 	if (resv == NULL || ocfs2_resmap_disabled(resmap))
 		return -ENOSPC;
 
 	spin_lock(&resv_lock);
 
-	/*
-	 * We don't want to over-allocate for temporary
-	 * windows. Otherwise, we run the risk of fragmenting the
-	 * allocation space.
-	 */
-	wanted = ocfs2_resv_window_bits(resmap, resv);
-	if ((resv->r_flags & OCFS2_RESV_FLAG_TMP) || wanted < *clen)
-		wanted = *clen;
-
 	if (ocfs2_resv_empty(resv)) {
-		mlog(0, "empty reservation, find new window\n");
+		/*
+		 * We don't want to over-allocate for temporary
+		 * windows. Otherwise, we run the risk of fragmenting the
+		 * allocation space.
+		 */
+		unsigned int wanted = ocfs2_resv_window_bits(resmap, resv);
 
+		if ((resv->r_flags & OCFS2_RESV_FLAG_TMP) || wanted < *clen)
+			wanted = *clen;
+
+		mlog(0, "empty reservation, find new window\n");
 		/*
 		 * Try to get a window here. If it works, we must fall
 		 * through and test the bitmap . This avoids some
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 8a286f54dca1..849c2f0e0a0e 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -357,7 +357,7 @@ out:
 static void ocfs2_bg_discontig_add_extent(struct ocfs2_super *osb,
 					  struct ocfs2_group_desc *bg,
 					  struct ocfs2_chain_list *cl,
-					  u64 p_blkno, u32 clusters)
+					  u64 p_blkno, unsigned int clusters)
 {
 	struct ocfs2_extent_list *el = &bg->bg_list;
 	struct ocfs2_extent_rec *rec;
@@ -369,7 +369,7 @@ static void ocfs2_bg_discontig_add_extent(struct ocfs2_super *osb,
 	rec->e_blkno = cpu_to_le64(p_blkno);
 	rec->e_cpos = cpu_to_le32(le16_to_cpu(bg->bg_bits) /
 				  le16_to_cpu(cl->cl_bpc));
-	rec->e_leaf_clusters = cpu_to_le32(clusters);
+	rec->e_leaf_clusters = cpu_to_le16(clusters);
 	le16_add_cpu(&bg->bg_bits, clusters * le16_to_cpu(cl->cl_bpc));
 	le16_add_cpu(&bg->bg_free_bits_count,
 		     clusters * le16_to_cpu(cl->cl_bpc));
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index 32499d213fc4..9975457c981f 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -128,7 +128,7 @@ static void *ocfs2_fast_follow_link(struct dentry *dentry,
 	}
 
 	/* Fast symlinks can't be large */
-	len = strlen(target);
+	len = strnlen(target, ocfs2_fast_symlink_chars(inode->i_sb));
 	link = kzalloc(len + 1, GFP_NOFS);
 	if (!link) {
 		status = -ENOMEM;
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index d03469f61801..06fa5e77c40e 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1286,13 +1286,11 @@ int ocfs2_xattr_get_nolock(struct inode *inode,
 	xis.inode_bh = xbs.inode_bh = di_bh;
 	di = (struct ocfs2_dinode *)di_bh->b_data;
 
-	down_read(&oi->ip_xattr_sem);
 	ret = ocfs2_xattr_ibody_get(inode, name_index, name, buffer,
 				    buffer_size, &xis);
 	if (ret == -ENODATA && di->i_xattr_loc)
 		ret = ocfs2_xattr_block_get(inode, name_index, name, buffer,
 					    buffer_size, &xbs);
-	up_read(&oi->ip_xattr_sem);
 
 	return ret;
 }
@@ -1316,8 +1314,10 @@ static int ocfs2_xattr_get(struct inode *inode,
 		mlog_errno(ret);
 		return ret;
 	}
+	down_read(&OCFS2_I(inode)->ip_xattr_sem);
 	ret = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
 				     name, buffer, buffer_size);
+	up_read(&OCFS2_I(inode)->ip_xattr_sem);
 
 	ocfs2_inode_unlock(inode, 0);
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a1c43e7c8a7b..8e4addaa5424 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2675,7 +2675,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("auxv",       S_IRUSR, proc_pid_auxv),
 	ONE("status",     S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
-	INF("limits",	  S_IRUSR, proc_pid_limits),
+	INF("limits",	  S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
@@ -3011,7 +3011,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	INF("auxv",      S_IRUSR, proc_pid_auxv),
 	ONE("status",    S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
-	INF("limits",	 S_IRUSR, proc_pid_limits),
+	INF("limits",	 S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 271afc48b9a5..1dbca4e8cc16 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -363,13 +363,13 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			mss->referenced += PAGE_SIZE;
 		mapcount = page_mapcount(page);
 		if (mapcount >= 2) {
-			if (pte_dirty(ptent))
+			if (pte_dirty(ptent) || PageDirty(page))
 				mss->shared_dirty += PAGE_SIZE;
 			else
 				mss->shared_clean += PAGE_SIZE;
 			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
 		} else {
-			if (pte_dirty(ptent))
+			if (pte_dirty(ptent) || PageDirty(page))
 				mss->private_dirty += PAGE_SIZE;
 			else
 				mss->private_clean += PAGE_SIZE;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 91c817ff02c3..2367fb3f70bc 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -163,7 +163,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 
 static const struct file_operations proc_vmcore_operations = {
 	.read		= read_vmcore,
-	.llseek		= generic_file_llseek,
+	.llseek		= default_llseek,
 };
 
 static struct vmcore* __init get_new_element(void)
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index f53505de0712..5cbb81e134ac 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -170,6 +170,7 @@ int reiserfs_prepare_write(struct file *f, struct page *page,
 int reiserfs_unpack(struct inode *inode, struct file *filp)
 {
 	int retval = 0;
+	int depth;
 	int index;
 	struct page *page;
 	struct address_space *mapping;
@@ -188,8 +189,8 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 	/* we need to make sure nobody is changing the file size beneath
 	 ** us
 	 */
-	mutex_lock(&inode->i_mutex);
-	reiserfs_write_lock(inode->i_sb);
+	reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb);
+	depth = reiserfs_write_lock_once(inode->i_sb);
 
 	write_from = inode->i_size & (blocksize - 1);
 	/* if we are on a block boundary, we are already unpacked.  */
@@ -224,6 +225,6 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 
       out:
 	mutex_unlock(&inode->i_mutex);
-	reiserfs_write_unlock(inode->i_sb);
+	reiserfs_write_unlock_once(inode->i_sb, depth);
 	return retval;
 }
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index d59c4a65d492..81976ffed7d6 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -668,14 +668,11 @@ xfs_inode_set_reclaim_tag(
 	xfs_perag_put(pag);
 }
 
-void
-__xfs_inode_clear_reclaim_tag(
-	xfs_mount_t	*mp,
+STATIC void
+__xfs_inode_clear_reclaim(
 	xfs_perag_t	*pag,
 	xfs_inode_t	*ip)
 {
-	radix_tree_tag_clear(&pag->pag_ici_root,
-			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
 	pag->pag_ici_reclaimable--;
 	if (!pag->pag_ici_reclaimable) {
 		/* clear the reclaim tag from the perag radix tree */
@@ -689,6 +686,17 @@ __xfs_inode_clear_reclaim_tag(
 	}
 }
 
+void
+__xfs_inode_clear_reclaim_tag(
+	xfs_mount_t	*mp,
+	xfs_perag_t	*pag,
+	xfs_inode_t	*ip)
+{
+	radix_tree_tag_clear(&pag->pag_ici_root,
+			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+	__xfs_inode_clear_reclaim(pag, ip);
+}
+
 /*
  * Inodes in different states need to be treated differently, and the return
  * value of xfs_iflush is not sufficient to get this right. The following table
@@ -838,6 +846,7 @@ reclaim:
 	if (!radix_tree_delete(&pag->pag_ici_root,
 				XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
 		ASSERT(0);
+	__xfs_inode_clear_reclaim(pag, ip);
 	write_unlock(&pag->pag_ici_lock);
 
 	/*
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ed575fb4b495..7e206fc1fa36 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -405,9 +405,15 @@ xlog_cil_push(
 	new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS);
 	new_ctx->ticket = xlog_cil_ticket_alloc(log);
 
-	/* lock out transaction commit, but don't block on background push */
+	/*
+	 * Lock out transaction commit, but don't block for background pushes
+	 * unless we are well over the CIL space limit. See the definition of
+	 * XLOG_CIL_HARD_SPACE_LIMIT() for the full explanation of the logic
+	 * used here.
+	 */
 	if (!down_write_trylock(&cil->xc_ctx_lock)) {
-		if (!push_seq)
+		if (!push_seq &&
+		    cil->xc_ctx->space_used < XLOG_CIL_HARD_SPACE_LIMIT(log))
 			goto out_free_ticket;
 		down_write(&cil->xc_ctx_lock);
 	}
@@ -422,7 +428,7 @@ xlog_cil_push(
 		goto out_skip;
 
 	/* check for a previously pushed seqeunce */
-	if (push_seq < cil->xc_ctx->sequence)
+	if (push_seq && push_seq < cil->xc_ctx->sequence)
 		goto out_skip;
 
 	/*
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ced52b98b322..edcdfe01617f 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -426,13 +426,13 @@ struct xfs_cil {
 };
 
 /*
- * The amount of log space we should the CIL to aggregate is difficult to size.
- * Whatever we chose we have to make we can get a reservation for the log space
- * effectively, that it is large enough to capture sufficient relogging to
- * reduce log buffer IO significantly, but it is not too large for the log or
- * induces too much latency when writing out through the iclogs. We track both
- * space consumed and the number of vectors in the checkpoint context, so we
- * need to decide which to use for limiting.
+ * The amount of log space we allow the CIL to aggregate is difficult to size.
+ * Whatever we choose, we have to make sure we can get a reservation for the
+ * log space effectively, that it is large enough to capture sufficient
+ * relogging to reduce log buffer IO significantly, but it is not too large for
+ * the log or induces too much latency when writing out through the iclogs. We
+ * track both space consumed and the number of vectors in the checkpoint
+ * context, so we need to decide which to use for limiting.
  *
  * Every log buffer we write out during a push needs a header reserved, which
  * is at least one sector and more for v2 logs. Hence we need a reservation of
@@ -459,16 +459,21 @@ struct xfs_cil {
  * checkpoint transaction ticket is specific to the checkpoint context, rather
  * than the CIL itself.
  *
- * With dynamic reservations, we can basically make up arbitrary limits for the
- * checkpoint size so long as they don't violate any other size rules.  Hence
- * the initial maximum size for the checkpoint transaction will be set to a
- * quarter of the log or 8MB, which ever is smaller. 8MB is an arbitrary limit
- * right now based on the latency of writing out a large amount of data through
- * the circular iclog buffers.
+ * With dynamic reservations, we can effectively make up arbitrary limits for
+ * the checkpoint size so long as they don't violate any other size rules.
+ * Recovery imposes a rule that no transaction exceed half the log, so we are
+ * limited by that.  Furthermore, the log transaction reservation subsystem
+ * tries to keep 25% of the log free, so we need to keep below that limit or we
+ * risk running out of free log space to start any new transactions.
+ *
+ * In order to keep background CIL push efficient, we will set a lower
+ * threshold at which background pushing is attempted without blocking current
+ * transaction commits.  A separate, higher bound defines when CIL pushes are
+ * enforced to ensure we stay within our maximum checkpoint size bounds.
+ * threshold, yet give us plenty of space for aggregation on large logs.
  */
-
-#define XLOG_CIL_SPACE_LIMIT(log)	\
-	(min((log->l_logsize >> 2), (8 * 1024 * 1024)))
+#define XLOG_CIL_SPACE_LIMIT(log)	(log->l_logsize >> 3)
+#define XLOG_CIL_HARD_SPACE_LIMIT(log)	(3 * (log->l_logsize >> 4))
 
 /*
  * The reservation head lsn is not made up of a cycle number and block number.
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index c0786d446a00..984cdc62e30b 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -55,7 +55,7 @@
 extern u8 acpi_gbl_permanent_mmap;
 
 /*
- * Globals that are publically available, allowing for
+ * Globals that are publicly available, allowing for
  * run time configuration
  */
 extern u32 acpi_dbg_level;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 7809d230adee..4c9461a4f9e6 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -612,7 +612,7 @@ struct drm_gem_object {
 	struct kref refcount;
 
 	/** Handle count of this object. Each handle also holds a reference */
-	struct kref handlecount;
+	atomic_t handle_count; /* number of handles on this object */
 
 	/** Related drm device */
 	struct drm_device *dev;
@@ -808,7 +808,6 @@ struct drm_driver {
 	 */
 	int (*gem_init_object) (struct drm_gem_object *obj);
 	void (*gem_free_object) (struct drm_gem_object *obj);
-	void (*gem_free_object_unlocked) (struct drm_gem_object *obj);
 
 	/* vga arb irq handler */
 	void (*vgaarb_irq)(struct drm_device *dev, bool state);
@@ -1175,6 +1174,7 @@ extern int drm_release(struct inode *inode, struct file *filp);
 extern int drm_mmap(struct file *filp, struct vm_area_struct *vma);
 extern int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma);
 extern void drm_vm_open_locked(struct vm_area_struct *vma);
+extern void drm_vm_close_locked(struct vm_area_struct *vma);
 extern resource_size_t drm_core_get_map_ofs(struct drm_local_map * map);
 extern resource_size_t drm_core_get_reg_ofs(struct drm_device *dev);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
@@ -1455,12 +1455,11 @@ int drm_gem_init(struct drm_device *dev);
 void drm_gem_destroy(struct drm_device *dev);
 void drm_gem_object_release(struct drm_gem_object *obj);
 void drm_gem_object_free(struct kref *kref);
-void drm_gem_object_free_unlocked(struct kref *kref);
 struct drm_gem_object *drm_gem_object_alloc(struct drm_device *dev,
 					    size_t size);
 int drm_gem_object_init(struct drm_device *dev,
 			struct drm_gem_object *obj, size_t size);
-void drm_gem_object_handle_free(struct kref *kref);
+void drm_gem_object_handle_free(struct drm_gem_object *obj);
 void drm_gem_vm_open(struct vm_area_struct *vma);
 void drm_gem_vm_close(struct vm_area_struct *vma);
 int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
@@ -1483,8 +1482,12 @@ drm_gem_object_unreference(struct drm_gem_object *obj)
 static inline void
 drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
 {
-	if (obj != NULL)
-		kref_put(&obj->refcount, drm_gem_object_free_unlocked);
+	if (obj != NULL) {
+		struct drm_device *dev = obj->dev;
+		mutex_lock(&dev->struct_mutex);
+		kref_put(&obj->refcount, drm_gem_object_free);
+		mutex_unlock(&dev->struct_mutex);
+	}
 }
 
 int drm_gem_handle_create(struct drm_file *file_priv,
@@ -1495,7 +1498,7 @@ static inline void
 drm_gem_object_handle_reference(struct drm_gem_object *obj)
 {
 	drm_gem_object_reference(obj);
-	kref_get(&obj->handlecount);
+	atomic_inc(&obj->handle_count);
 }
 
 static inline void
@@ -1504,12 +1507,15 @@ drm_gem_object_handle_unreference(struct drm_gem_object *obj)
 	if (obj == NULL)
 		return;
 
+	if (atomic_read(&obj->handle_count) == 0)
+		return;
 	/*
 	 * Must bump handle count first as this may be the last
 	 * ref, in which case the object would disappear before we
 	 * checked for a name
 	 */
-	kref_put(&obj->handlecount, drm_gem_object_handle_free);
+	if (atomic_dec_and_test(&obj->handle_count))
+		drm_gem_object_handle_free(obj);
 	drm_gem_object_unreference(obj);
 }
 
@@ -1519,12 +1525,17 @@ drm_gem_object_handle_unreference_unlocked(struct drm_gem_object *obj)
 	if (obj == NULL)
 		return;
 
+	if (atomic_read(&obj->handle_count) == 0)
+		return;
+
 	/*
 	* Must bump handle count first as this may be the last
 	* ref, in which case the object would disappear before we
 	* checked for a name
 	*/
-	kref_put(&obj->handlecount, drm_gem_object_handle_free);
+
+	if (atomic_dec_and_test(&obj->handle_count))
+		drm_gem_object_handle_free(obj);
 	drm_gem_object_unreference_unlocked(obj);
 }
 
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 3a9940ef728b..883c1d439899 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -85,7 +85,6 @@
 	{0x1002, 0x5460, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x5462, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x5464, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
-	{0x1002, 0x5657, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5548, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5549, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x554A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
@@ -103,6 +102,7 @@
 	{0x1002, 0x564F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5652, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5653, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5657, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5834, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP}, \
 	{0x1002, 0x5835, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x5954, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 267a86c74e2e..2040e6c4f172 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -246,9 +246,11 @@ struct ttm_buffer_object {
 
 	atomic_t reserved;
 
-
 	/**
 	 * Members protected by the bo::lock
+	 * In addition, setting sync_obj to anything else
+	 * than NULL requires bo::reserved to be held. This allows for
+	 * checking NULL while reserved but not holding bo::lock.
 	 */
 
 	void *sync_obj_arg;
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 626b629429ff..4e8ea8c8ec1e 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -118,7 +118,6 @@ header-y += eventpoll.h
 header-y += ext2_fs.h
 header-y += fadvise.h
 header-y += falloc.h
-header-y += fanotify.h
 header-y += fb.h
 header-y += fcntl.h
 header-y += fd.h
diff --git a/fs/ceph/auth.h b/include/linux/ceph/auth.h
similarity index 97%
rename from fs/ceph/auth.h
rename to include/linux/ceph/auth.h
index d38a2fb4a137..7fff521d7eb5 100644
--- a/fs/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -1,8 +1,8 @@
 #ifndef _FS_CEPH_AUTH_H
 #define _FS_CEPH_AUTH_H
 
-#include "types.h"
-#include "buffer.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
 
 /*
  * Abstract interface for communicating with the authenticate module.
diff --git a/fs/ceph/buffer.h b/include/linux/ceph/buffer.h
similarity index 100%
rename from fs/ceph/buffer.h
rename to include/linux/ceph/buffer.h
diff --git a/fs/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
similarity index 86%
rename from fs/ceph/ceph_debug.h
rename to include/linux/ceph/ceph_debug.h
index 1818c2305610..aa2e19182d99 100644
--- a/fs/ceph/ceph_debug.h
+++ b/include/linux/ceph/ceph_debug.h
@@ -3,7 +3,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_CEPH_FS_PRETTYDEBUG
+#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG
 
 /*
  * wrap pr_debug to include a filename:lineno prefix on each line.
@@ -14,7 +14,8 @@
 # if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 extern const char *ceph_file_part(const char *s, int len);
 #  define dout(fmt, ...)						\
-	pr_debug(" %12.12s:%-4d : " fmt,				\
+	pr_debug("%.*s %12.12s:%-4d : " fmt,				\
+		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
 		 ceph_file_part(__FILE__, sizeof(__FILE__)),		\
 		 __LINE__, ##__VA_ARGS__)
 # else
diff --git a/fs/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
similarity index 100%
rename from fs/ceph/ceph_frag.h
rename to include/linux/ceph/ceph_frag.h
diff --git a/fs/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
similarity index 99%
rename from fs/ceph/ceph_fs.h
rename to include/linux/ceph/ceph_fs.h
index d5619ac86711..c3c74aef289d 100644
--- a/fs/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -299,6 +299,7 @@ enum {
 	CEPH_MDS_OP_SETATTR    = 0x01108,
 	CEPH_MDS_OP_SETFILELOCK= 0x01109,
 	CEPH_MDS_OP_GETFILELOCK= 0x00110,
+	CEPH_MDS_OP_SETDIRLAYOUT=0x0110a,
 
 	CEPH_MDS_OP_MKNOD      = 0x01201,
 	CEPH_MDS_OP_LINK       = 0x01202,
diff --git a/fs/ceph/ceph_hash.h b/include/linux/ceph/ceph_hash.h
similarity index 100%
rename from fs/ceph/ceph_hash.h
rename to include/linux/ceph/ceph_hash.h
diff --git a/include/linux/ceph/debugfs.h b/include/linux/ceph/debugfs.h
new file mode 100644
index 000000000000..2a79702e092b
--- /dev/null
+++ b/include/linux/ceph/debugfs.h
@@ -0,0 +1,33 @@
+#ifndef _FS_CEPH_DEBUGFS_H
+#define _FS_CEPH_DEBUGFS_H
+
+#include "ceph_debug.h"
+#include "types.h"
+
+#define CEPH_DEFINE_SHOW_FUNC(name)					\
+static int name##_open(struct inode *inode, struct file *file)		\
+{									\
+	struct seq_file *sf;						\
+	int ret;							\
+									\
+	ret = single_open(file, name, NULL);				\
+	sf = file->private_data;					\
+	sf->private = inode->i_private;					\
+	return ret;							\
+}									\
+									\
+static const struct file_operations name##_fops = {			\
+	.open		= name##_open,					\
+	.read		= seq_read,					\
+	.llseek		= seq_lseek,					\
+	.release	= single_release,				\
+};
+
+/* debugfs.c */
+extern int ceph_debugfs_init(void);
+extern void ceph_debugfs_cleanup(void);
+extern int ceph_debugfs_client_init(struct ceph_client *client);
+extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
+
+#endif
+
diff --git a/fs/ceph/decode.h b/include/linux/ceph/decode.h
similarity index 96%
rename from fs/ceph/decode.h
rename to include/linux/ceph/decode.h
index 3d25415afe63..c5b6939fb32a 100644
--- a/fs/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -191,6 +191,11 @@ static inline void ceph_encode_string(void **p, void *end,
 		ceph_encode_need(p, end, n, bad);		\
 		ceph_encode_copy(p, pv, n);			\
 	} while (0)
+#define ceph_encode_string_safe(p, end, s, n, bad)		\
+	do {							\
+		ceph_encode_need(p, end, n, bad);		\
+		ceph_encode_string(p, end, s, n);		\
+	} while (0)
 
 
 #endif
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
new file mode 100644
index 000000000000..f22b2e941686
--- /dev/null
+++ b/include/linux/ceph/libceph.h
@@ -0,0 +1,249 @@
+#ifndef _FS_CEPH_LIBCEPH_H
+#define _FS_CEPH_LIBCEPH_H
+
+#include "ceph_debug.h"
+
+#include <asm/unaligned.h>
+#include <linux/backing-dev.h>
+#include <linux/completion.h>
+#include <linux/exportfs.h>
+#include <linux/fs.h>
+#include <linux/mempool.h>
+#include <linux/pagemap.h>
+#include <linux/wait.h>
+#include <linux/writeback.h>
+#include <linux/slab.h>
+
+#include "types.h"
+#include "messenger.h"
+#include "msgpool.h"
+#include "mon_client.h"
+#include "osd_client.h"
+#include "ceph_fs.h"
+
+/*
+ * Supported features
+ */
+#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR
+#define CEPH_FEATURE_REQUIRED_DEFAULT  CEPH_FEATURE_NOSRCADDR
+
+/*
+ * mount options
+ */
+#define CEPH_OPT_FSID             (1<<0)
+#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
+#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
+#define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
+
+#define CEPH_OPT_DEFAULT   (0);
+
+#define ceph_set_opt(client, opt) \
+	(client)->options->flags |= CEPH_OPT_##opt;
+#define ceph_test_opt(client, opt) \
+	(!!((client)->options->flags & CEPH_OPT_##opt))
+
+struct ceph_options {
+	int flags;
+	struct ceph_fsid fsid;
+	struct ceph_entity_addr my_addr;
+	int mount_timeout;
+	int osd_idle_ttl;
+	int osd_timeout;
+	int osd_keepalive_timeout;
+
+	/*
+	 * any type that can't be simply compared or doesn't need need
+	 * to be compared should go beyond this point,
+	 * ceph_compare_options() should be updated accordingly
+	 */
+
+	struct ceph_entity_addr *mon_addr; /* should be the first
+					      pointer type of args */
+	int num_mon;
+	char *name;
+	char *secret;
+};
+
+/*
+ * defaults
+ */
+#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
+#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
+#define CEPH_OSD_KEEPALIVE_DEFAULT  5
+#define CEPH_OSD_IDLE_TTL_DEFAULT    60
+#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
+
+#define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
+#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
+
+#define CEPH_AUTH_NAME_DEFAULT   "guest"
+
+/*
+ * Delay telling the MDS we no longer want caps, in case we reopen
+ * the file.  Delay a minimum amount of time, even if we send a cap
+ * message for some other reason.  Otherwise, take the oppotunity to
+ * update the mds to avoid sending another message later.
+ */
+#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
+#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
+
+#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)
+
+/* mount state */
+enum {
+	CEPH_MOUNT_MOUNTING,
+	CEPH_MOUNT_MOUNTED,
+	CEPH_MOUNT_UNMOUNTING,
+	CEPH_MOUNT_UNMOUNTED,
+	CEPH_MOUNT_SHUTDOWN,
+};
+
+/*
+ * subtract jiffies
+ */
+static inline unsigned long time_sub(unsigned long a, unsigned long b)
+{
+	BUG_ON(time_after(b, a));
+	return (long)a - (long)b;
+}
+
+struct ceph_mds_client;
+
+/*
+ * per client state
+ *
+ * possibly shared by multiple mount points, if they are
+ * mounting the same ceph filesystem/cluster.
+ */
+struct ceph_client {
+	struct ceph_fsid fsid;
+	bool have_fsid;
+
+	void *private;
+
+	struct ceph_options *options;
+
+	struct mutex mount_mutex;      /* serialize mount attempts */
+	wait_queue_head_t auth_wq;
+	int auth_err;
+
+	int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *);
+
+	u32 supported_features;
+	u32 required_features;
+
+	struct ceph_messenger *msgr;   /* messenger instance */
+	struct ceph_mon_client monc;
+	struct ceph_osd_client osdc;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs_dir;
+	struct dentry *debugfs_monmap;
+	struct dentry *debugfs_osdmap;
+#endif
+};
+
+
+
+/*
+ * snapshots
+ */
+
+/*
+ * A "snap context" is the set of existing snapshots when we
+ * write data.  It is used by the OSD to guide its COW behavior.
+ *
+ * The ceph_snap_context is refcounted, and attached to each dirty
+ * page, indicating which context the dirty data belonged when it was
+ * dirtied.
+ */
+struct ceph_snap_context {
+	atomic_t nref;
+	u64 seq;
+	int num_snaps;
+	u64 snaps[];
+};
+
+static inline struct ceph_snap_context *
+ceph_get_snap_context(struct ceph_snap_context *sc)
+{
+	/*
+	printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+	       atomic_read(&sc->nref)+1);
+	*/
+	if (sc)
+		atomic_inc(&sc->nref);
+	return sc;
+}
+
+static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
+{
+	if (!sc)
+		return;
+	/*
+	printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+	       atomic_read(&sc->nref)-1);
+	*/
+	if (atomic_dec_and_test(&sc->nref)) {
+		/*printk(" deleting snap_context %p\n", sc);*/
+		kfree(sc);
+	}
+}
+
+/*
+ * calculate the number of pages a given length and offset map onto,
+ * if we align the data.
+ */
+static inline int calc_pages_for(u64 off, u64 len)
+{
+	return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
+		(off >> PAGE_CACHE_SHIFT);
+}
+
+/* ceph_common.c */
+extern const char *ceph_msg_type_name(int type);
+extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
+extern struct kmem_cache *ceph_inode_cachep;
+extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_dentry_cachep;
+extern struct kmem_cache *ceph_file_cachep;
+
+extern int ceph_parse_options(struct ceph_options **popt, char *options,
+			      const char *dev_name, const char *dev_name_end,
+			      int (*parse_extra_token)(char *c, void *private),
+			      void *private);
+extern void ceph_destroy_options(struct ceph_options *opt);
+extern int ceph_compare_options(struct ceph_options *new_opt,
+				struct ceph_client *client);
+extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
+					      void *private);
+extern u64 ceph_client_id(struct ceph_client *client);
+extern void ceph_destroy_client(struct ceph_client *client);
+extern int __ceph_open_session(struct ceph_client *client,
+			       unsigned long started);
+extern int ceph_open_session(struct ceph_client *client);
+
+/* pagevec.c */
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+
+extern struct page **ceph_get_direct_page_vector(const char __user *data,
+					    int num_pages,
+					    loff_t off, size_t len);
+extern void ceph_put_page_vector(struct page **pages, int num_pages);
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+extern int ceph_copy_user_to_page_vector(struct page **pages,
+					 const char __user *data,
+					 loff_t off, size_t len);
+extern int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len);
+extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data,
+				    loff_t off, size_t len);
+extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
+
+
+#endif /* _FS_CEPH_SUPER_H */
diff --git a/fs/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
similarity index 100%
rename from fs/ceph/mdsmap.h
rename to include/linux/ceph/mdsmap.h
diff --git a/fs/ceph/messenger.h b/include/linux/ceph/messenger.h
similarity index 95%
rename from fs/ceph/messenger.h
rename to include/linux/ceph/messenger.h
index 76fbc957bc13..5956d62c3057 100644
--- a/fs/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -65,6 +65,9 @@ struct ceph_messenger {
 	 */
 	u32 global_seq;
 	spinlock_t global_seq_lock;
+
+	u32 supported_features;
+	u32 required_features;
 };
 
 /*
@@ -82,6 +85,10 @@ struct ceph_msg {
 	struct ceph_pagelist *pagelist; /* instead of pages */
 	struct list_head list_head;
 	struct kref kref;
+	struct bio  *bio;		/* instead of pages/pagelist */
+	struct bio  *bio_iter;		/* bio iterator */
+	int bio_seg;			/* current bio segment */
+	struct ceph_pagelist *trail;	/* the trailing part of the data */
 	bool front_is_vmalloc;
 	bool more_to_follow;
 	bool needs_out_seq;
@@ -205,7 +212,7 @@ struct ceph_connection {
 };
 
 
-extern const char *pr_addr(const struct sockaddr_storage *ss);
+extern const char *ceph_pr_addr(const struct sockaddr_storage *ss);
 extern int ceph_parse_ips(const char *c, const char *end,
 			  struct ceph_entity_addr *addr,
 			  int max_count, int *count);
@@ -216,7 +223,8 @@ extern void ceph_msgr_exit(void);
 extern void ceph_msgr_flush(void);
 
 extern struct ceph_messenger *ceph_messenger_create(
-	struct ceph_entity_addr *myaddr);
+	struct ceph_entity_addr *myaddr,
+	u32 features, u32 required);
 extern void ceph_messenger_destroy(struct ceph_messenger *);
 
 extern void ceph_con_init(struct ceph_messenger *msgr,
diff --git a/fs/ceph/mon_client.h b/include/linux/ceph/mon_client.h
similarity index 99%
rename from fs/ceph/mon_client.h
rename to include/linux/ceph/mon_client.h
index 8e396f2c0963..545f85917780 100644
--- a/fs/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -79,6 +79,7 @@ struct ceph_mon_client {
 	u64 last_tid;
 
 	/* mds/osd map */
+	int want_mdsmap;
 	int want_next_osdmap; /* 1 = want, 2 = want+asked */
 	u32 have_osdmap, have_mdsmap;
 
diff --git a/fs/ceph/msgpool.h b/include/linux/ceph/msgpool.h
similarity index 100%
rename from fs/ceph/msgpool.h
rename to include/linux/ceph/msgpool.h
diff --git a/fs/ceph/msgr.h b/include/linux/ceph/msgr.h
similarity index 100%
rename from fs/ceph/msgr.h
rename to include/linux/ceph/msgr.h
diff --git a/fs/ceph/osd_client.h b/include/linux/ceph/osd_client.h
similarity index 76%
rename from fs/ceph/osd_client.h
rename to include/linux/ceph/osd_client.h
index ce776989ef6a..6c91fb032c39 100644
--- a/fs/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -15,6 +15,7 @@ struct ceph_snap_context;
 struct ceph_osd_request;
 struct ceph_osd_client;
 struct ceph_authorizer;
+struct ceph_pagelist;
 
 /*
  * completion callback for async writepages
@@ -68,6 +69,7 @@ struct ceph_osd_request {
 	struct list_head  r_unsafe_item;
 
 	struct inode *r_inode;         	      /* for use by callbacks */
+	void *r_priv;			      /* ditto */
 
 	char              r_oid[40];          /* object name */
 	int               r_oid_len;
@@ -80,6 +82,11 @@ struct ceph_osd_request {
 	struct page     **r_pages;            /* pages for data payload */
 	int               r_pages_from_pool;
 	int               r_own_pages;        /* if true, i own page list */
+#ifdef CONFIG_BLOCK
+	struct bio       *r_bio;	      /* instead of pages */
+#endif
+
+	struct ceph_pagelist *r_trail;	      /* trailing part of the data */
 };
 
 struct ceph_osd_client {
@@ -110,6 +117,42 @@ struct ceph_osd_client {
 	struct ceph_msgpool	msgpool_op_reply;
 };
 
+struct ceph_osd_req_op {
+	u16 op;           /* CEPH_OSD_OP_* */
+	u32 flags;        /* CEPH_OSD_FLAG_* */
+	union {
+		struct {
+			u64 offset, length;
+			u64 truncate_size;
+			u32 truncate_seq;
+		} extent;
+		struct {
+			const char *name;
+			u32 name_len;
+			const char  *val;
+			u32 value_len;
+			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
+			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
+		} xattr;
+		struct {
+			const char *class_name;
+			__u8 class_len;
+			const char *method_name;
+			__u8 method_len;
+			__u8 argc;
+			const char *indata;
+			u32 indata_len;
+		} cls;
+		struct {
+			u64 cookie, count;
+		} pgls;
+	        struct {
+		        u64 snapid;
+	        } snap;
+	};
+	u32 payload_len;
+};
+
 extern int ceph_osdc_init(struct ceph_osd_client *osdc,
 			  struct ceph_client *client);
 extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
@@ -119,6 +162,30 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 				 struct ceph_msg *msg);
 
+extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+			struct ceph_file_layout *layout,
+			u64 snapid,
+			u64 off, u64 *plen, u64 *bno,
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op);
+
+extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+					       int flags,
+					       struct ceph_snap_context *snapc,
+					       struct ceph_osd_req_op *ops,
+					       bool use_mempool,
+					       gfp_t gfp_flags,
+					       struct page **pages,
+					       struct bio *bio);
+
+extern void ceph_osdc_build_request(struct ceph_osd_request *req,
+				    u64 off, u64 *plen,
+				    struct ceph_osd_req_op *src_ops,
+				    struct ceph_snap_context *snapc,
+				    struct timespec *mtime,
+				    const char *oid,
+				    int oid_len);
+
 extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      struct ceph_file_layout *layout,
 				      struct ceph_vino vino,
diff --git a/fs/ceph/osdmap.h b/include/linux/ceph/osdmap.h
similarity index 97%
rename from fs/ceph/osdmap.h
rename to include/linux/ceph/osdmap.h
index 970b547e510d..ba4c205cbb01 100644
--- a/fs/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -4,7 +4,7 @@
 #include <linux/rbtree.h>
 #include "types.h"
 #include "ceph_fs.h"
-#include "crush/crush.h"
+#include <linux/crush/crush.h>
 
 /*
  * The osd map describes the current membership of the osd cluster and
@@ -125,4 +125,6 @@ extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 
+extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
+
 #endif
diff --git a/fs/ceph/pagelist.h b/include/linux/ceph/pagelist.h
similarity index 62%
rename from fs/ceph/pagelist.h
rename to include/linux/ceph/pagelist.h
index e8a4187e1087..9660d6b0a35d 100644
--- a/fs/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -8,6 +8,14 @@ struct ceph_pagelist {
 	void *mapped_tail;
 	size_t length;
 	size_t room;
+	struct list_head free_list;
+	size_t num_pages_free;
+};
+
+struct ceph_pagelist_cursor {
+	struct ceph_pagelist *pl;   /* pagelist, for error checking */
+	struct list_head *page_lru; /* page in list */
+	size_t room;		    /* room remaining to reset to */
 };
 
 static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
@@ -16,10 +24,23 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
 	pl->mapped_tail = NULL;
 	pl->length = 0;
 	pl->room = 0;
+	INIT_LIST_HEAD(&pl->free_list);
+	pl->num_pages_free = 0;
 }
+
 extern int ceph_pagelist_release(struct ceph_pagelist *pl);
 
-extern int ceph_pagelist_append(struct ceph_pagelist *pl, void *d, size_t l);
+extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
+
+extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space);
+
+extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl);
+
+extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+				     struct ceph_pagelist_cursor *c);
+
+extern int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+				  struct ceph_pagelist_cursor *c);
 
 static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
 {
diff --git a/fs/ceph/rados.h b/include/linux/ceph/rados.h
similarity index 100%
rename from fs/ceph/rados.h
rename to include/linux/ceph/rados.h
diff --git a/fs/ceph/types.h b/include/linux/ceph/types.h
similarity index 100%
rename from fs/ceph/types.h
rename to include/linux/ceph/types.h
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 8ba66a9d9022..ba4b85a6d9b8 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -9,37 +9,7 @@
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.
  */
-static inline int dump_write(struct file *file, const void *addr, int nr)
-{
-	return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
-}
-
-static inline int dump_seek(struct file *file, loff_t off)
-{
-	int ret = 1;
-
-	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
-		if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
-			return 0;
-	} else {
-		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
-
-		if (!buf)
-			return 0;
-		while (off > 0) {
-			unsigned long n = off;
-
-			if (n > PAGE_SIZE)
-				n = PAGE_SIZE;
-			if (!dump_write(file, buf, n)) {
-				ret = 0;
-				break;
-			}
-			off -= n;
-		}
-		free_page((unsigned long)buf);
-	}
-	return ret;
-}
+extern int dump_write(struct file *file, const void *addr, int nr);
+extern int dump_seek(struct file *file, loff_t off);
 
 #endif /* _LINUX_COREDUMP_H */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 36ca9721a0c2..1be416bbbb82 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -53,6 +53,7 @@ struct cpuidle_state {
 #define CPUIDLE_FLAG_BALANCED	(0x40) /* medium latency, moderate savings */
 #define CPUIDLE_FLAG_DEEP	(0x80) /* high latency, large savings */
 #define CPUIDLE_FLAG_IGNORE	(0x100) /* ignore during this idle period */
+#define CPUIDLE_FLAG_TLB_FLUSHED (0x200) /* tlb will be flushed */
 
 #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000)
 
diff --git a/fs/ceph/crush/crush.h b/include/linux/crush/crush.h
similarity index 100%
rename from fs/ceph/crush/crush.h
rename to include/linux/crush/crush.h
diff --git a/fs/ceph/crush/hash.h b/include/linux/crush/hash.h
similarity index 100%
rename from fs/ceph/crush/hash.h
rename to include/linux/crush/hash.h
diff --git a/fs/ceph/crush/mapper.h b/include/linux/crush/mapper.h
similarity index 100%
rename from fs/ceph/crush/mapper.h
rename to include/linux/crush/mapper.h
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index ce29b8151198..ba8319ae5fcc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -102,6 +102,9 @@ static inline u64 dma_get_mask(struct device *dev)
 	return DMA_BIT_MASK(32);
 }
 
+#ifdef ARCH_HAS_DMA_SET_COHERENT_MASK
+int dma_set_coherent_mask(struct device *dev, u64 mask);
+#else
 static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
 	if (!dma_supported(dev, mask))
@@ -109,6 +112,7 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
 	dev->coherent_dma_mask = mask;
 	return 0;
 }
+#endif
 
 extern u64 dma_get_required_mask(struct device *dev);
 
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index c61d4ca27bcc..e2106495cc11 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -548,7 +548,7 @@ static inline bool dma_dev_has_pq_continue(struct dma_device *dma)
 	return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE;
 }
 
-static unsigned short dma_dev_to_maxpq(struct dma_device *dma)
+static inline unsigned short dma_dev_to_maxpq(struct dma_device *dma)
 {
 	return dma->max_pq & ~DMA_HAS_PQ_CONTINUE;
 }
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 926b50322a46..4fd978e7eb83 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -93,6 +93,7 @@ struct elevator_queue
 	struct elevator_type *elevator_type;
 	struct mutex sysfs_lock;
 	struct hlist_head *hash;
+	unsigned int registered:1;
 };
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 76041b614758..63d069bd80b7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1093,6 +1093,10 @@ struct file_lock {
 
 #include <linux/fcntl.h>
 
+/* temporary stubs for BKL removal */
+#define lock_flocks() lock_kernel()
+#define unlock_flocks() unlock_kernel()
+
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 #ifdef CONFIG_FILE_LOCKING
diff --git a/include/linux/module.h b/include/linux/module.h
index 8a6b9fdc7ffa..aace066bad8f 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -686,17 +686,16 @@ extern int module_sysfs_initialized;
 
 
 #ifdef CONFIG_GENERIC_BUG
-int  module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *,
+void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *,
 			 struct module *);
 void module_bug_cleanup(struct module *);
 
 #else	/* !CONFIG_GENERIC_BUG */
 
-static inline int  module_bug_finalize(const Elf_Ehdr *hdr,
+static inline void module_bug_finalize(const Elf_Ehdr *hdr,
 					const Elf_Shdr *sechdrs,
 					struct module *mod)
 {
-	return 0;
 }
 static inline void module_bug_cleanup(struct module *mod) {}
 #endif	/* CONFIG_GENERIC_BUG */
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 59d066936ab9..123566912d73 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -27,8 +27,6 @@
 
 #define MAX_LINKS 32		
 
-struct net;
-
 struct sockaddr_nl {
 	sa_family_t	nl_family;	/* AF_NETLINK	*/
 	unsigned short	nl_pad;		/* zero		*/
@@ -151,6 +149,8 @@ struct nlattr {
 #include <linux/capability.h>
 #include <linux/skbuff.h>
 
+struct net;
+
 static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
 {
 	return (struct nlmsghdr *)skb->data;
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 10d33309e9a6..570fddeb0388 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -393,6 +393,9 @@
 #define PCI_DEVICE_ID_VLSI_82C147	0x0105
 #define PCI_DEVICE_ID_VLSI_VAS96011	0x0702
 
+/* AMD RD890 Chipset */
+#define PCI_DEVICE_ID_RD890_IOMMU	0x5a23
+
 #define PCI_VENDOR_ID_ADL		0x1005
 #define PCI_DEVICE_ID_ADL_2301		0x2301
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 9fbc54a2585d..83af1f8d8b74 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -454,7 +454,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * Makes rcu_dereference_check() do the dirty work.
  */
 #define rcu_dereference_bh(p) \
-		rcu_dereference_check(p, rcu_read_lock_bh_held())
+		rcu_dereference_check(p, rcu_read_lock_bh_held() || irqs_disabled())
 
 /**
  * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
diff --git a/include/linux/socket.h b/include/linux/socket.h
index a2fada9becb6..a8f56e1ec760 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -322,7 +322,7 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata,
 					  int offset, 
 					  unsigned int len, __wsum *csump);
 
-extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode);
+extern long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode);
 extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len);
 extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
 			     int offset, int len);
diff --git a/include/linux/types.h b/include/linux/types.h
index 01a082f56ef4..357dbc19606f 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -121,7 +121,15 @@ typedef		__u64		u_int64_t;
 typedef		__s64		int64_t;
 #endif
 
-/* this is a special 64bit data type that is 8-byte aligned */
+/*
+ * aligned_u64 should be used in defining kernel<->userspace ABIs to avoid
+ * common 32/64-bit compat problems.
+ * 64-bit values align to 4-byte boundaries on x86_32 (and possibly other
+ * architectures) and to 8-byte boundaries on 64-bit architetures.  The new
+ * aligned_64 type enforces 8-byte alignment so that structs containing
+ * aligned_64 values have the same alignment on 32-bit and 64-bit architectures.
+ * No conversions are necessary between 32-bit user-space and a 64-bit kernel.
+ */
 #define aligned_u64 __u64 __attribute__((aligned(8)))
 #define aligned_be64 __be64 __attribute__((aligned(8)))
 #define aligned_le64 __le64 __attribute__((aligned(8)))
@@ -178,6 +186,11 @@ typedef __u64 __bitwise __be64;
 typedef __u16 __bitwise __sum16;
 typedef __u32 __bitwise __wsum;
 
+/* this is a special 64bit data type that is 8-byte aligned */
+#define __aligned_u64 __u64 __attribute__((aligned(8)))
+#define __aligned_be64 __be64 __attribute__((aligned(8)))
+#define __aligned_le64 __le64 __attribute__((aligned(8)))
+
 #ifdef __KERNEL__
 typedef unsigned __bitwise__ gfp_t;
 typedef unsigned __bitwise__ fmode_t;
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 0836ccc57121..3efc9f3f43a0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -614,6 +614,7 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 		(wait)->private = current;				\
 		(wait)->func = autoremove_wake_function;		\
 		INIT_LIST_HEAD(&(wait)->task_list);			\
+		(wait)->flags = 0;					\
 	} while (0)
 
 /**
diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h
index 97e07f46a0fa..aa4ebb42a565 100644
--- a/include/media/videobuf-dma-sg.h
+++ b/include/media/videobuf-dma-sg.h
@@ -48,6 +48,7 @@ struct videobuf_dmabuf {
 
 	/* for userland buffer */
 	int                 offset;
+	size_t		    size;
 	struct page         **pages;
 
 	/* for kernel buffers */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 45375b41a2a0..4d40c4d0230b 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -121,6 +121,7 @@ static inline int addrconf_finite_timeout(unsigned long timeout)
  *	IPv6 Address Label subsystem (addrlabel.c)
  */
 extern int			ipv6_addr_label_init(void);
+extern void			ipv6_addr_label_cleanup(void);
 extern void			ipv6_addr_label_rtnl_register(void);
 extern u32			ipv6_addr_label(struct net *net,
 						const struct in6_addr *addr,
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 27a902d9b3a9..30fce0128dd7 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -161,12 +161,30 @@ static inline struct sk_buff *bt_skb_send_alloc(struct sock *sk, unsigned long l
 {
 	struct sk_buff *skb;
 
+	release_sock(sk);
 	if ((skb = sock_alloc_send_skb(sk, len + BT_SKB_RESERVE, nb, err))) {
 		skb_reserve(skb, BT_SKB_RESERVE);
 		bt_cb(skb)->incoming  = 0;
 	}
+	lock_sock(sk);
+
+	if (!skb && *err)
+		return NULL;
+
+	*err = sock_error(sk);
+	if (*err)
+		goto out;
+
+	if (sk->sk_shutdown) {
+		*err = -ECONNRESET;
+		goto out;
+	}
 
 	return skb;
+
+out:
+	kfree_skb(skb);
+	return NULL;
 }
 
 int bt_err(__u16 code);
diff --git a/include/net/dst.h b/include/net/dst.h
index 81d1413a8701..02386505033d 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -242,6 +242,7 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += skb->len;
 	skb->rxhash = 0;
+	skb_set_queue_mapping(skb, 0);
 	skb_dst_drop(skb);
 	nf_reset(skb);
 }
diff --git a/include/net/route.h b/include/net/route.h
index bd732d62e1c3..7e5e73bfa4de 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -199,6 +199,8 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol,
 		fl.fl_ip_sport = sport;
 		fl.fl_ip_dport = dport;
 		fl.proto = protocol;
+		if (inet_sk(sk)->transparent)
+			fl.flags |= FLOWI_FLAG_ANYSRC;
 		ip_rt_put(*rp);
 		*rp = NULL;
 		security_sk_classify_flow(sk, &fl);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index fc8f36dd0f5c..4f53532d4c2f 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -298,8 +298,8 @@ struct xfrm_state_afinfo {
 	const struct xfrm_type	*type_map[IPPROTO_MAX];
 	struct xfrm_mode	*mode_map[XFRM_MODE_MAX];
 	int			(*init_flags)(struct xfrm_state *x);
-	void			(*init_tempsel)(struct xfrm_state *x, struct flowi *fl,
-						struct xfrm_tmpl *tmpl,
+	void			(*init_tempsel)(struct xfrm_selector *sel, struct flowi *fl);
+	void			(*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
 						xfrm_address_t *daddr, xfrm_address_t *saddr);
 	int			(*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
 	int			(*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n);
diff --git a/ipc/sem.c b/ipc/sem.c
index 40a8f462a822..0e0d49bbb867 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -743,6 +743,8 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in,
 	    {
 		struct semid_ds out;
 
+		memset(&out, 0, sizeof(out));
+
 		ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm);
 
 		out.sem_otime	= in->sem_otime;
diff --git a/kernel/fork.c b/kernel/fork.c
index b7e9d60a675d..c445f8cc408d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -356,10 +356,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (IS_ERR(pol))
 			goto fail_nomem_policy;
 		vma_set_policy(tmp, pol);
+		tmp->vm_mm = mm;
 		if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
-		tmp->vm_mm = mm;
 		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 1decafbb6b1a..72206cf5c6cf 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -931,6 +931,7 @@ static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
 	if (hrtimer_is_queued(timer)) {
+		unsigned long state;
 		int reprogram;
 
 		/*
@@ -944,8 +945,13 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
-		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
-				 reprogram);
+		/*
+		 * We must preserve the CALLBACK state flag here,
+		 * otherwise we could move the timer base in
+		 * switch_hrtimer_base.
+		 */
+		state = timer->state & HRTIMER_STATE_CALLBACK;
+		__remove_hrtimer(timer, base, state, reprogram);
 		return 1;
 	}
 	return 0;
@@ -1231,6 +1237,9 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
 		enqueue_hrtimer(timer, base);
 	}
+
+	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+
 	timer->state &= ~HRTIMER_STATE_CALLBACK;
 }
 
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index d71a987fd2bf..c7c2aed9e2dc 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -433,7 +433,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
+						triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 6b5580c57644..01a0700e873f 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -365,8 +365,6 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl,
 	n = setup_sgl_buf(sgl, fifo->data + off, nents, l);
 	n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l);
 
-	if (n)
-		sg_mark_end(sgl + n - 1);
 	return n;
 }
 
diff --git a/kernel/module.c b/kernel/module.c
index d0b5f8db11b4..ccd641991842 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1537,6 +1537,7 @@ static int __unlink_module(void *_mod)
 {
 	struct module *mod = _mod;
 	list_del(&mod->list);
+	module_bug_cleanup(mod);
 	return 0;
 }
 
@@ -2625,6 +2626,7 @@ static struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto ddebug;
 
+	module_bug_finalize(info.hdr, info.sechdrs, mod);
 	list_add_rcu(&mod->list, &modules);
 	mutex_unlock(&module_mutex);
 
@@ -2650,6 +2652,8 @@ static struct module *load_module(void __user *umod,
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
+	module_bug_cleanup(mod);
+
  ddebug:
 	if (!mod->taints)
 		dynamic_debug_remove(info.debug);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index db5b56064687..b98bed3d8182 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2202,15 +2202,13 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	unsigned long size;
 	int ret = 0;
 	u64 value;
 
 	if (!event->attr.sample_period)
 		return -EINVAL;
 
-	size = copy_from_user(&value, arg, sizeof(value));
-	if (size != sizeof(value))
+	if (copy_from_user(&value, arg, sizeof(value)))
 		return -EFAULT;
 
 	if (!value)
diff --git a/kernel/sched.c b/kernel/sched.c
index ed09d4f2a69c..dc85ceb90832 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3513,9 +3513,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
 
 	if (total) {
-		u64 temp;
+		u64 temp = rtime;
 
-		temp = (u64)(rtime * utime);
+		temp *= utime;
 		do_div(temp, total);
 		utime = (cputime_t)temp;
 	} else
@@ -3546,9 +3546,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
 
 	if (total) {
-		u64 temp;
+		u64 temp = rtime;
 
-		temp = (u64)(rtime * cputime.utime);
+		temp *= cputime.utime;
 		do_div(temp, total);
 		utime = (cputime_t)temp;
 	} else
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a171138a9402..db3f674ca49d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3630,7 +3630,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
-	if (!rq->nr_running)
+	if (rq->idle_at_tick)
 		return 0;
 
 	first_pick_cpu = atomic_read(&nohz.first_pick_cpu);
diff --git a/kernel/signal.c b/kernel/signal.c
index bded65187780..919562c3d6b7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2214,6 +2214,14 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
 		err |= __put_user(from->si_addr, &to->si_addr);
 #ifdef __ARCH_SI_TRAPNO
 		err |= __put_user(from->si_trapno, &to->si_trapno);
+#endif
+#ifdef BUS_MCEERR_AO
+		/* 
+		 * Other callers might not initialize the si_lsb field,
+	 	 * so check explicitely for the right codes here.
+		 */
+		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
 	case __SI_CHLD:
diff --git a/kernel/smp.c b/kernel/smp.c
index 75c970c715d3..ed6aacfcb7ef 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -365,9 +365,10 @@ call:
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
 /**
- * __smp_call_function_single(): Run a function on another CPU
+ * __smp_call_function_single(): Run a function on a specific CPU
  * @cpu: The CPU to run on.
  * @data: Pre-allocated and setup data structure
+ * @wait: If true, wait until function has completed on specified CPU.
  *
  * Like smp_call_function_single(), but allow caller to pass in a
  * pre-allocated data structure. Useful for embedding @data inside
@@ -376,8 +377,10 @@ EXPORT_SYMBOL_GPL(smp_call_function_any);
 void __smp_call_function_single(int cpu, struct call_single_data *data,
 				int wait)
 {
-	csd_lock(data);
+	unsigned int this_cpu;
+	unsigned long flags;
 
+	this_cpu = get_cpu();
 	/*
 	 * Can deadlock when called with interrupts disabled.
 	 * We allow cpu's that are not yet online though, as no one else can
@@ -387,7 +390,15 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
 	WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
 		     && !oops_in_progress);
 
-	generic_exec_single(cpu, data, wait);
+	if (cpu == this_cpu) {
+		local_irq_save(flags);
+		data->func(data->info);
+		local_irq_restore(flags);
+	} else {
+		csd_lock(data);
+		generic_exec_single(cpu, data, wait);
+	}
+	put_cpu();
 }
 
 /**
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f88552c6d227..3a45c224770f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2485,7 +2485,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 		kbuf[left] = 0;
 	}
 
-	for (; left && vleft--; i++, min++, max++, first=0) {
+	for (; left && vleft--; i++, first = 0) {
 		unsigned long val;
 
 		if (write) {
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index 04cdcf72c827..10b90d8a03c4 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -143,15 +143,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
 				if (!table->maxlen)
 					set_fail(&fail, table, "No maxlen");
 			}
-			if ((table->proc_handler == proc_doulongvec_minmax) ||
-			    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
-				if (table->maxlen > sizeof (unsigned long)) {
-					if (!table->extra1)
-						set_fail(&fail, table, "No min");
-					if (!table->extra2)
-						set_fail(&fail, table, "No max");
-				}
-			}
 #ifdef CONFIG_PROC_SYSCTL
 			if (table->procname && !table->proc_handler)
 				set_fail(&fail, table, "No proc_handler");
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 492197e2f86c..bca96377fd4e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -405,7 +405,7 @@ static inline int test_time_stamp(u64 delta)
 #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
 
 /* Max number of timestamps that can fit on a page */
-#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_EXTEND)
 
 int ring_buffer_print_page_header(struct trace_seq *s)
 {
diff --git a/lib/bug.c b/lib/bug.c
index 7cdfad88128f..19552096d16b 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -72,8 +72,8 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr)
 	return NULL;
 }
 
-int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
-			struct module *mod)
+void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+			 struct module *mod)
 {
 	char *secstrings;
 	unsigned int i;
@@ -97,8 +97,6 @@ int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
 	 * could potentially lead to deadlock and thus be counter-productive.
 	 */
 	list_add(&mod->bug_list, &module_bug_list);
-
-	return 0;
 }
 
 void module_bug_cleanup(struct module *mod)
diff --git a/lib/list_sort.c b/lib/list_sort.c
index 4b5cb794c38b..a7616fa3162e 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -70,7 +70,7 @@ static void merge_and_restore_back_links(void *priv,
 		 * element comparison is needed, so the client's cmp()
 		 * routine can invoke cond_resched() periodically.
 		 */
-		(*cmp)(priv, tail, tail);
+		(*cmp)(priv, tail->next, tail->next);
 
 		tail->next->prev = tail;
 		tail = tail->next;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c2bf86f470ed..65d420499a61 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -30,6 +30,7 @@ EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
@@ -243,6 +244,7 @@ static int __init default_bdi_init(void)
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
+	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
 }
diff --git a/mm/fremap.c b/mm/fremap.c
index 46f5dacf90a2..ec520c7b28df 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -125,7 +125,6 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 {
 	struct mm_struct *mm = current->mm;
 	struct address_space *mapping;
-	unsigned long end = start + size;
 	struct vm_area_struct *vma;
 	int err = -EINVAL;
 	int has_write_lock = 0;
@@ -142,6 +141,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (start + size <= start)
 		return err;
 
+	/* Does pgoff wrap? */
+	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+		return err;
+
 	/* Can we represent this offset inside this architecture's pte's? */
 #if PTE_FILE_MAX_BITS < BITS_PER_LONG
 	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
@@ -168,7 +171,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (!(vma->vm_flags & VM_CAN_NONLINEAR))
 		goto out;
 
-	if (end <= start || start < vma->vm_start || end > vma->vm_end)
+	if (start < vma->vm_start || start + size > vma->vm_end)
 		goto out;
 
 	/* Must set VM_NONLINEAR before any pages are populated. */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cc5be788a39f..c03273807182 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2324,11 +2324,8 @@ retry_avoidcopy:
 	 * and just make the page writable */
 	avoidcopy = (page_mapcount(old_page) == 1);
 	if (avoidcopy) {
-		if (!trylock_page(old_page)) {
-			if (PageAnon(old_page))
-				page_move_anon_rmap(old_page, vma, address);
-		} else
-			unlock_page(old_page);
+		if (PageAnon(old_page))
+			page_move_anon_rmap(old_page, vma, address);
 		set_huge_ptep_writable(vma, address, ptep);
 		return 0;
 	}
@@ -2404,7 +2401,7 @@ retry_avoidcopy:
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
 		page_remove_rmap(old_page);
-		hugepage_add_anon_rmap(new_page, vma, address);
+		hugepage_add_new_anon_rmap(new_page, vma, address);
 		/* Make the old page be freed below */
 		new_page = old_page;
 		mmu_notifier_invalidate_range_end(mm,
@@ -2631,10 +2628,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 								vma, address);
 	}
 
-	if (!pagecache_page) {
-		page = pte_page(entry);
+	/*
+	 * hugetlb_cow() requires page locks of pte_page(entry) and
+	 * pagecache_page, so here we need take the former one
+	 * when page != pagecache_page or !pagecache_page.
+	 * Note that locking order is always pagecache_page -> page,
+	 * so no worry about deadlock.
+	 */
+	page = pte_page(entry);
+	if (page != pagecache_page)
 		lock_page(page);
-	}
 
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
@@ -2661,9 +2664,8 @@ out_page_table_lock:
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
 		put_page(pagecache_page);
-	} else {
-		unlock_page(page);
 	}
+	unlock_page(page);
 
 out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
diff --git a/mm/ksm.c b/mm/ksm.c
index b1873cf03ed9..65ab5c7067d9 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -712,7 +712,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	if (!ptep)
 		goto out;
 
-	if (pte_write(*ptep)) {
+	if (pte_write(*ptep) || pte_dirty(*ptep)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
@@ -735,7 +735,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			set_pte_at(mm, addr, ptep, entry);
 			goto out_unlock;
 		}
-		entry = pte_wrprotect(entry);
+		if (pte_dirty(entry))
+			set_page_dirty(page);
+		entry = pte_mkclean(pte_wrprotect(entry));
 		set_pte_at_notify(mm, addr, ptep, entry);
 	}
 	*orig_pte = *ptep;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3eed583895a6..9be3cf8a5da4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3587,9 +3587,13 @@ unlock:
 
 static void mem_cgroup_threshold(struct mem_cgroup *memcg)
 {
-	__mem_cgroup_threshold(memcg, false);
-	if (do_swap_account)
-		__mem_cgroup_threshold(memcg, true);
+	while (memcg) {
+		__mem_cgroup_threshold(memcg, false);
+		if (do_swap_account)
+			__mem_cgroup_threshold(memcg, true);
+
+		memcg = parent_mem_cgroup(memcg);
+	}
 }
 
 static int compare_thresholds(const void *a, const void *b)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9c26eeca1342..757f6b0accfe 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -183,7 +183,7 @@ EXPORT_SYMBOL_GPL(hwpoison_filter);
  * signal.
  */
 static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
-			unsigned long pfn)
+			unsigned long pfn, struct page *page)
 {
 	struct siginfo si;
 	int ret;
@@ -198,7 +198,7 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
 #ifdef __ARCH_SI_TRAPNO
 	si.si_trapno = trapno;
 #endif
-	si.si_addr_lsb = PAGE_SHIFT;
+	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
 	/*
 	 * Don't use force here, it's convenient if the signal
 	 * can be temporarily blocked.
@@ -235,7 +235,7 @@ void shake_page(struct page *p, int access)
 		int nr;
 		do {
 			nr = shrink_slab(1000, GFP_KERNEL, 1000);
-			if (page_count(p) == 0)
+			if (page_count(p) == 1)
 				break;
 		} while (nr > 10);
 	}
@@ -327,7 +327,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
  * wrong earlier.
  */
 static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
-			  int fail, unsigned long pfn)
+			  int fail, struct page *page, unsigned long pfn)
 {
 	struct to_kill *tk, *next;
 
@@ -352,7 +352,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
 			 * process anyways.
 			 */
 			else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
-					      pfn) < 0)
+					      pfn, page) < 0)
 				printk(KERN_ERR
 		"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
 					pfn, tk->tsk->comm, tk->tsk->pid);
@@ -928,7 +928,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * any accesses to the poisoned memory.
 	 */
 	kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
-		      ret != SWAP_SUCCESS, pfn);
+		      ret != SWAP_SUCCESS, p, pfn);
 
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 71b161b73bb5..0e18b4d649ec 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2680,10 +2680,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
 	/*
-	 * Make sure try_to_free_swap didn't release the swapcache
-	 * from under us. The page pin isn't enough to prevent that.
+	 * Make sure try_to_free_swap or reuse_swap_page or swapoff did not
+	 * release the swapcache from under us.  The page pin, and pte_same
+	 * test below, are not enough to exclude that.  Even if it is still
+	 * swapcache, we need to check that the page's swap has not changed.
 	 */
-	if (unlikely(!PageSwapCache(page)))
+	if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
 		goto out_page;
 
 	if (ksm_might_need_to_copy(page, vma, address)) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 6128dc8e5ede..00161a48a451 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2009,6 +2009,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 			removed_exe_file_vma(mm);
 		fput(new->vm_file);
 	}
+	unlink_anon_vmas(new);
  out_free_mpol:
 	mpol_put(pol);
  out_free_vma:
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index fc81cb22869e..4029583a1024 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -121,8 +121,8 @@ struct task_struct *find_lock_task_mm(struct task_struct *p)
 }
 
 /* return true if the task is not adequate as candidate victim task. */
-static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *mem,
-			   const nodemask_t *nodemask)
+static bool oom_unkillable_task(struct task_struct *p,
+		const struct mem_cgroup *mem, const nodemask_t *nodemask)
 {
 	if (is_global_init(p))
 		return true;
@@ -208,8 +208,13 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	 */
 	points += p->signal->oom_score_adj;
 
-	if (points < 0)
-		return 0;
+	/*
+	 * Never return 0 for an eligible task that may be killed since it's
+	 * possible that no single user task uses more than 0.1% of memory and
+	 * no single admin tasks uses more than 3.0%.
+	 */
+	if (points <= 0)
+		return 1;
 	return (points < 1000) ? points : 1000;
 }
 
@@ -339,26 +344,24 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 /**
  * dump_tasks - dump current memory state of all system tasks
  * @mem: current's memory controller, if constrained
+ * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
- * Dumps the current memory state of all system tasks, excluding kernel threads.
+ * Dumps the current memory state of all eligible tasks.  Tasks not in the same
+ * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
+ * are not shown.
  * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
  * value, oom_score_adj value, and name.
  *
- * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are
- * shown.
- *
  * Call with tasklist_lock read-locked.
  */
-static void dump_tasks(const struct mem_cgroup *mem)
+static void dump_tasks(const struct mem_cgroup *mem, const nodemask_t *nodemask)
 {
 	struct task_struct *p;
 	struct task_struct *task;
 
 	pr_info("[ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name\n");
 	for_each_process(p) {
-		if (p->flags & PF_KTHREAD)
-			continue;
-		if (mem && !task_in_mem_cgroup(p, mem))
+		if (oom_unkillable_task(p, mem, nodemask))
 			continue;
 
 		task = find_lock_task_mm(p);
@@ -381,7 +384,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
 }
 
 static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
-							struct mem_cgroup *mem)
+			struct mem_cgroup *mem, const nodemask_t *nodemask)
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
@@ -394,7 +397,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 	mem_cgroup_print_oom_info(mem, p);
 	show_mem();
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(mem);
+		dump_tasks(mem, nodemask);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
@@ -436,7 +439,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	unsigned int victim_points = 0;
 
 	if (printk_ratelimit())
-		dump_header(p, gfp_mask, order, mem);
+		dump_header(p, gfp_mask, order, mem, nodemask);
 
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
@@ -482,7 +485,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
 static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-				int order)
+				int order, const nodemask_t *nodemask)
 {
 	if (likely(!sysctl_panic_on_oom))
 		return;
@@ -496,7 +499,7 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 			return;
 	}
 	read_lock(&tasklist_lock);
-	dump_header(NULL, gfp_mask, order, NULL);
+	dump_header(NULL, gfp_mask, order, NULL, nodemask);
 	read_unlock(&tasklist_lock);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
@@ -509,7 +512,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
 	unsigned int points = 0;
 	struct task_struct *p;
 
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0);
+	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL);
 	limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT;
 	read_lock(&tasklist_lock);
 retry:
@@ -641,6 +644,7 @@ static void clear_system_oom(void)
 void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *nodemask)
 {
+	const nodemask_t *mpol_mask;
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
@@ -670,7 +674,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	 */
 	constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
 						&totalpages);
-	check_panic_on_oom(constraint, gfp_mask, order);
+	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
+	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
 
 	read_lock(&tasklist_lock);
 	if (sysctl_oom_kill_allocating_task &&
@@ -688,15 +693,13 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	}
 
 retry:
-	p = select_bad_process(&points, totalpages, NULL,
-			constraint == CONSTRAINT_MEMORY_POLICY ? nodemask :
-								 NULL);
+	p = select_bad_process(&points, totalpages, NULL, mpol_mask);
 	if (PTR_ERR(p) == -1UL)
 		goto out;
 
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
-		dump_header(NULL, gfp_mask, order, NULL);
+		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
 		read_unlock(&tasklist_lock);
 		panic("Out of memory and no killable processes...\n");
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a8cfa9cc6e86..f12ad1836abe 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5182,9 +5182,9 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (!table)
 		panic("Failed to allocate %s hash table\n", tablename);
 
-	printk(KERN_INFO "%s hash table entries: %d (order: %d, %lu bytes)\n",
+	printk(KERN_INFO "%s hash table entries: %ld (order: %d, %lu bytes)\n",
 	       tablename,
-	       (1U << log2qty),
+	       (1UL << log2qty),
 	       ilog2(size) - PAGE_SHIFT,
 	       size);
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 58c572b18b07..c76ef3891e0d 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1401,9 +1401,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 			if (pcpu_first_unit_cpu == NR_CPUS)
 				pcpu_first_unit_cpu = cpu;
+			pcpu_last_unit_cpu = cpu;
 		}
 	}
-	pcpu_last_unit_cpu = cpu;
 	pcpu_nr_units = unit;
 
 	for_each_possible_cpu(cpu)
diff --git a/mm/rmap.c b/mm/rmap.c
index f6f0d2dda2ea..92e6757f196e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -381,7 +381,13 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
 	if (PageAnon(page)) {
-		if (vma->anon_vma->root != page_anon_vma(page)->root)
+		struct anon_vma *page__anon_vma = page_anon_vma(page);
+		/*
+		 * Note: swapoff's unuse_vma() is more efficient with this
+		 * check, and needs it to match anon_vma when KSM is active.
+		 */
+		if (!vma->anon_vma || !page__anon_vma ||
+		    vma->anon_vma->root != page__anon_vma->root)
 			return -EFAULT;
 	} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
 		if (!vma->vm_file ||
@@ -1564,13 +1570,14 @@ static void __hugepage_set_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
+
 	BUG_ON(!anon_vma);
-	if (!exclusive) {
-		struct anon_vma_chain *avc;
-		avc = list_entry(vma->anon_vma_chain.prev,
-				 struct anon_vma_chain, same_vma);
-		anon_vma = avc->anon_vma;
-	}
+
+	if (PageAnon(page))
+		return;
+	if (!exclusive)
+		anon_vma = anon_vma->root;
+
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	page->mapping = (struct address_space *) anon_vma;
 	page->index = linear_page_index(vma, address);
@@ -1581,6 +1588,8 @@ void hugepage_add_anon_rmap(struct page *page,
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	int first;
+
+	BUG_ON(!PageLocked(page));
 	BUG_ON(!anon_vma);
 	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	first = atomic_inc_and_test(&page->_mapcount);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c391c320dbaf..c5dfabf25f11 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1804,12 +1804,11 @@ static void shrink_zone(int priority, struct zone *zone,
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static bool shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
-	bool all_unreclaimable = true;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -1827,8 +1826,38 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 		}
 
 		shrink_zone(priority, zone, sc);
-		all_unreclaimable = false;
 	}
+}
+
+static bool zone_reclaimable(struct zone *zone)
+{
+	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+}
+
+/*
+ * As hibernation is going on, kswapd is freezed so that it can't mark
+ * the zone into all_unreclaimable. It can't handle OOM during hibernation.
+ * So let's check zone's unreclaimable in direct reclaim as well as kswapd.
+ */
+static bool all_unreclaimable(struct zonelist *zonelist,
+		struct scan_control *sc)
+{
+	struct zoneref *z;
+	struct zone *zone;
+	bool all_unreclaimable = true;
+
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+			gfp_zone(sc->gfp_mask), sc->nodemask) {
+		if (!populated_zone(zone))
+			continue;
+		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+			continue;
+		if (zone_reclaimable(zone)) {
+			all_unreclaimable = false;
+			break;
+		}
+	}
+
 	return all_unreclaimable;
 }
 
@@ -1852,7 +1881,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	int priority;
-	bool all_unreclaimable;
 	unsigned long total_scanned = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct zoneref *z;
@@ -1869,7 +1897,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		all_unreclaimable = shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -1931,7 +1959,7 @@ out:
 		return sc->nr_reclaimed;
 
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (scanning_global_lru(sc) && !all_unreclaimable)
+	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
 
 	return 0;
@@ -2197,8 +2225,7 @@ loop_again:
 			total_scanned += sc.nr_scanned;
 			if (zone->all_unreclaimable)
 				continue;
-			if (nr_slab == 0 &&
-			    zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+			if (nr_slab == 0 && !zone_reclaimable(zone))
 				zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 01ddb0472f86..0eb96f7e44be 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -24,8 +24,11 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
 
 	if (vlan_dev)
 		skb->dev = vlan_dev;
-	else if (vlan_id)
-		goto drop;
+	else if (vlan_id) {
+		if (!(skb->dev->flags & IFF_PROMISC))
+			goto drop;
+		skb->pkt_type = PACKET_OTHERHOST;
+	}
 
 	return (polling ? netif_receive_skb(skb) : netif_rx(skb));
 
@@ -102,8 +105,11 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
 
 	if (vlan_dev)
 		skb->dev = vlan_dev;
-	else if (vlan_id)
-		goto drop;
+	else if (vlan_id) {
+		if (!(skb->dev->flags & IFF_PROMISC))
+			goto drop;
+		skb->pkt_type = PACKET_OTHERHOST;
+	}
 
 	for (p = napi->gro_list; p; p = p->next) {
 		NAPI_GRO_CB(p)->same_flow =
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 0ea20c30466c..17c5ba7551a5 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -426,8 +426,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 
 	/* Allocate an fcall for the reply */
 	rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL);
-	if (!rpl_context)
+	if (!rpl_context) {
+		err = -ENOMEM;
 		goto err_close;
+	}
 
 	/*
 	 * If the request has a buffer, steal it, otherwise
@@ -445,8 +447,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	}
 	rpl_context->rc = req->rc;
 	if (!rpl_context->rc) {
-		kfree(rpl_context);
-		goto err_close;
+		err = -ENOMEM;
+		goto err_free2;
 	}
 
 	/*
@@ -458,11 +460,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	 */
 	if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) {
 		err = post_recv(client, rpl_context);
-		if (err) {
-			kfree(rpl_context->rc);
-			kfree(rpl_context);
-			goto err_close;
-		}
+		if (err)
+			goto err_free1;
 	} else
 		atomic_dec(&rdma->rq_count);
 
@@ -471,8 +470,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 
 	/* Post the request */
 	c = kmalloc(sizeof *c, GFP_KERNEL);
-	if (!c)
-		goto err_close;
+	if (!c) {
+		err = -ENOMEM;
+		goto err_free1;
+	}
 	c->req = req;
 
 	c->busa = ib_dma_map_single(rdma->cm_id->device,
@@ -499,9 +500,15 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	return ib_post_send(rdma->qp, &wr, &bad_wr);
 
  error:
+	kfree(c);
+	kfree(rpl_context->rc);
+	kfree(rpl_context);
 	P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n");
 	return -EIO;
-
+ err_free1:
+	kfree(rpl_context->rc);
+ err_free2:
+	kfree(rpl_context);
  err_close:
 	spin_lock_irqsave(&rdma->req_lock, flags);
 	if (rdma->state < P9_RDMA_CLOSING) {
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index dcfbe99ff81c..b88515936e4b 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -329,7 +329,8 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args)
 
 	mutex_lock(&virtio_9p_lock);
 	list_for_each_entry(chan, &virtio_chan_list, chan_list) {
-		if (!strncmp(devname, chan->tag, chan->tag_len)) {
+		if (!strncmp(devname, chan->tag, chan->tag_len) &&
+		    strlen(devname) == chan->tag_len) {
 			if (!chan->inuse) {
 				chan->inuse = true;
 				found = 1;
diff --git a/net/Kconfig b/net/Kconfig
index e926884c1675..55fd82e9ffd9 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -293,6 +293,7 @@ source "net/wimax/Kconfig"
 source "net/rfkill/Kconfig"
 source "net/9p/Kconfig"
 source "net/caif/Kconfig"
+source "net/ceph/Kconfig"
 
 
 endif   # if NET
diff --git a/net/Makefile b/net/Makefile
index ea60fbce9b1b..6b7bfd7f1416 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -68,3 +68,4 @@ obj-$(CONFIG_SYSCTL)		+= sysctl_net.o
 endif
 obj-$(CONFIG_WIMAX)		+= wimax/
 obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
+obj-$(CONFIG_CEPH_LIB)		+= ceph/
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index 651babdfab38..ad2b232a2055 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -399,12 +399,6 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb)
 			unregister_netdev(net_dev);
 			free_netdev(net_dev);
 		}
-		read_lock_irq(&devs_lock);
-		if (list_empty(&br2684_devs)) {
-			/* last br2684 device */
-			unregister_atmdevice_notifier(&atm_dev_notifier);
-		}
-		read_unlock_irq(&devs_lock);
 		return;
 	}
 
@@ -675,7 +669,6 @@ static int br2684_create(void __user *arg)
 
 	if (list_empty(&br2684_devs)) {
 		/* 1st br2684 device */
-		register_atmdevice_notifier(&atm_dev_notifier);
 		brdev->number = 1;
 	} else
 		brdev->number = BRPRIV(list_entry_brdev(br2684_devs.prev))->number + 1;
@@ -815,6 +808,7 @@ static int __init br2684_init(void)
 		return -ENOMEM;
 #endif
 	register_atm_ioctl(&br2684_ioctl_ops);
+	register_atmdevice_notifier(&atm_dev_notifier);
 	return 0;
 }
 
@@ -830,9 +824,7 @@ static void __exit br2684_exit(void)
 #endif
 
 
-	/* if not already empty */
-	if (!list_empty(&br2684_devs))
-		unregister_atmdevice_notifier(&atm_dev_notifier);
+	unregister_atmdevice_notifier(&atm_dev_notifier);
 
 	while (!list_empty(&br2684_devs)) {
 		net_dev = list_entry_brdev(br2684_devs.next);
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 622b471e14e0..74bcc662c3dd 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -778,7 +778,7 @@ static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb)
 	eg->packets_rcvd++;
 	mpc->eg_ops->put(eg);
 
-	memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data));
+	memset(ATM_SKB(new_skb), 0, sizeof(struct atm_skb_data));
 	netif_rx(new_skb);
 }
 
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index fadf26b4ed7c..0b54b7dd8401 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -1441,33 +1441,23 @@ static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb)
 
 static void l2cap_streaming_send(struct sock *sk)
 {
-	struct sk_buff *skb, *tx_skb;
+	struct sk_buff *skb;
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
 	u16 control, fcs;
 
-	while ((skb = sk->sk_send_head)) {
-		tx_skb = skb_clone(skb, GFP_ATOMIC);
-
-		control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE);
+	while ((skb = skb_dequeue(TX_QUEUE(sk)))) {
+		control = get_unaligned_le16(skb->data + L2CAP_HDR_SIZE);
 		control |= pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT;
-		put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE);
+		put_unaligned_le16(control, skb->data + L2CAP_HDR_SIZE);
 
 		if (pi->fcs == L2CAP_FCS_CRC16) {
-			fcs = crc16(0, (u8 *)tx_skb->data, tx_skb->len - 2);
-			put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2);
+			fcs = crc16(0, (u8 *)skb->data, skb->len - 2);
+			put_unaligned_le16(fcs, skb->data + skb->len - 2);
 		}
 
-		l2cap_do_send(sk, tx_skb);
+		l2cap_do_send(sk, skb);
 
 		pi->next_tx_seq = (pi->next_tx_seq + 1) % 64;
-
-		if (skb_queue_is_last(TX_QUEUE(sk), skb))
-			sk->sk_send_head = NULL;
-		else
-			sk->sk_send_head = skb_queue_next(TX_QUEUE(sk), skb);
-
-		skb = skb_dequeue(TX_QUEUE(sk));
-		kfree_skb(skb);
 	}
 }
 
@@ -1960,6 +1950,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us
 
 	switch (optname) {
 	case L2CAP_OPTIONS:
+		if (sk->sk_state == BT_CONNECTED) {
+			err = -EINVAL;
+			break;
+		}
+
 		opts.imtu     = l2cap_pi(sk)->imtu;
 		opts.omtu     = l2cap_pi(sk)->omtu;
 		opts.flush_to = l2cap_pi(sk)->flush_to;
@@ -2771,10 +2766,10 @@ static int l2cap_parse_conf_rsp(struct sock *sk, void *rsp, int len, void *data,
 		case L2CAP_CONF_MTU:
 			if (val < L2CAP_DEFAULT_MIN_MTU) {
 				*result = L2CAP_CONF_UNACCEPT;
-				pi->omtu = L2CAP_DEFAULT_MIN_MTU;
+				pi->imtu = L2CAP_DEFAULT_MIN_MTU;
 			} else
-				pi->omtu = val;
-			l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu);
+				pi->imtu = val;
+			l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->imtu);
 			break;
 
 		case L2CAP_CONF_FLUSH_TO:
@@ -3071,6 +3066,17 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd
 	return 0;
 }
 
+static inline void set_default_fcs(struct l2cap_pinfo *pi)
+{
+	/* FCS is enabled only in ERTM or streaming mode, if one or both
+	 * sides request it.
+	 */
+	if (pi->mode != L2CAP_MODE_ERTM && pi->mode != L2CAP_MODE_STREAMING)
+		pi->fcs = L2CAP_FCS_NONE;
+	else if (!(pi->conf_state & L2CAP_CONF_NO_FCS_RECV))
+		pi->fcs = L2CAP_FCS_CRC16;
+}
+
 static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data)
 {
 	struct l2cap_conf_req *req = (struct l2cap_conf_req *) data;
@@ -3088,14 +3094,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr
 	if (!sk)
 		return -ENOENT;
 
-	if (sk->sk_state != BT_CONFIG) {
-		struct l2cap_cmd_rej rej;
-
-		rej.reason = cpu_to_le16(0x0002);
-		l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
-				sizeof(rej), &rej);
+	if (sk->sk_state == BT_DISCONN)
 		goto unlock;
-	}
 
 	/* Reject if config buffer is too small. */
 	len = cmd_len - sizeof(*req);
@@ -3135,9 +3135,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr
 		goto unlock;
 
 	if (l2cap_pi(sk)->conf_state & L2CAP_CONF_INPUT_DONE) {
-		if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) ||
-		    l2cap_pi(sk)->fcs != L2CAP_FCS_NONE)
-			l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16;
+		set_default_fcs(l2cap_pi(sk));
 
 		sk->sk_state = BT_CONNECTED;
 
@@ -3225,9 +3223,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr
 	l2cap_pi(sk)->conf_state |= L2CAP_CONF_INPUT_DONE;
 
 	if (l2cap_pi(sk)->conf_state & L2CAP_CONF_OUTPUT_DONE) {
-		if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) ||
-		    l2cap_pi(sk)->fcs != L2CAP_FCS_NONE)
-			l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16;
+		set_default_fcs(l2cap_pi(sk));
 
 		sk->sk_state = BT_CONNECTED;
 		l2cap_pi(sk)->next_tx_seq = 0;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 44a623275951..194b3a04cfd3 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -82,11 +82,14 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb)
 static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
 {
 	struct sock *sk = d->owner, *parent;
+	unsigned long flags;
+
 	if (!sk)
 		return;
 
 	BT_DBG("dlc %p state %ld err %d", d, d->state, err);
 
+	local_irq_save(flags);
 	bh_lock_sock(sk);
 
 	if (err)
@@ -108,6 +111,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
 	}
 
 	bh_unlock_sock(sk);
+	local_irq_restore(flags);
 
 	if (parent && sock_flag(sk, SOCK_ZAPPED)) {
 		/* We have to drop DLC lock here, otherwise
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 8ce904786116..4bf28f25f368 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -827,6 +827,7 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr,
 	long timeo;
 	int err;
 	int ifindex, headroom, tailroom;
+	unsigned int mtu;
 	struct net_device *dev;
 
 	lock_sock(sk);
@@ -896,15 +897,23 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr,
 		cf_sk->sk.sk_state = CAIF_DISCONNECTED;
 		goto out;
 	}
-	dev = dev_get_by_index(sock_net(sk), ifindex);
+
+	err = -ENODEV;
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+	if (!dev) {
+		rcu_read_unlock();
+		goto out;
+	}
 	cf_sk->headroom = LL_RESERVED_SPACE_EXTRA(dev, headroom);
+	mtu = dev->mtu;
+	rcu_read_unlock();
+
 	cf_sk->tailroom = tailroom;
-	cf_sk->maxframe = dev->mtu - (headroom + tailroom);
-	dev_put(dev);
+	cf_sk->maxframe = mtu - (headroom + tailroom);
 	if (cf_sk->maxframe < 1) {
-		pr_warning("CAIF: %s(): CAIF Interface MTU too small (%d)\n",
-			__func__, dev->mtu);
-		err = -ENODEV;
+		pr_warning("CAIF: %s(): CAIF Interface MTU too small (%u)\n",
+			   __func__, mtu);
 		goto out;
 	}
 
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
new file mode 100644
index 000000000000..ad424049b0cf
--- /dev/null
+++ b/net/ceph/Kconfig
@@ -0,0 +1,28 @@
+config CEPH_LIB
+        tristate "Ceph core library (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+	select LIBCRC32C
+	select CRYPTO_AES
+	select CRYPTO
+	default n
+	help
+	  Choose Y or M here to include cephlib, which provides the
+	  common functionality to both the Ceph filesystem and
+	  to the rados block device (rbd).
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+
+config CEPH_LIB_PRETTYDEBUG
+	bool "Include file:line in ceph debug output"
+	depends on CEPH_LIB
+	default n
+	help
+	  If you say Y here, debug output will include a filename and
+	  line to aid debugging.  This increases kernel size and slows
+	  execution slightly when debug call sites are enabled (e.g.,
+	  via CONFIG_DYNAMIC_DEBUG).
+
+	  If unsure, say N.
+
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
new file mode 100644
index 000000000000..aab1cabb8035
--- /dev/null
+++ b/net/ceph/Makefile
@@ -0,0 +1,37 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+ifneq ($(KERNELRELEASE),)
+
+obj-$(CONFIG_CEPH_LIB) += libceph.o
+
+libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
+	mon_client.o \
+	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
+	debugfs.o \
+	auth.o auth_none.o \
+	crypto.o armor.o \
+	auth_x.o \
+	ceph_fs.o ceph_strings.o ceph_hash.o \
+	pagevec.o
+
+else
+#Otherwise we were called directly from the command
+# line; invoke the kernel build system.
+
+KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+
+default: all
+
+all:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules
+
+modules_install:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install
+
+clean:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+
+endif
diff --git a/fs/ceph/armor.c b/net/ceph/armor.c
similarity index 100%
rename from fs/ceph/armor.c
rename to net/ceph/armor.c
diff --git a/fs/ceph/auth.c b/net/ceph/auth.c
similarity index 97%
rename from fs/ceph/auth.c
rename to net/ceph/auth.c
index 6d2e30600627..549c1f43e1d5 100644
--- a/fs/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -1,16 +1,16 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include "types.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
 #include "auth_none.h"
 #include "auth_x.h"
-#include "decode.h"
-#include "super.h"
 
-#include "messenger.h"
 
 /*
  * get protocol handler
diff --git a/fs/ceph/auth_none.c b/net/ceph/auth_none.c
similarity index 96%
rename from fs/ceph/auth_none.c
rename to net/ceph/auth_none.c
index ad1dc21286c7..214c2bb43d62 100644
--- a/fs/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -1,14 +1,15 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
 #include "auth_none.h"
-#include "auth.h"
-#include "decode.h"
 
 static void reset(struct ceph_auth_client *ac)
 {
diff --git a/fs/ceph/auth_none.h b/net/ceph/auth_none.h
similarity index 94%
rename from fs/ceph/auth_none.h
rename to net/ceph/auth_none.h
index 8164df1a08be..ed7d088b1bc9 100644
--- a/fs/ceph/auth_none.h
+++ b/net/ceph/auth_none.h
@@ -2,8 +2,7 @@
 #define _FS_CEPH_AUTH_NONE_H
 
 #include <linux/slab.h>
-
-#include "auth.h"
+#include <linux/ceph/auth.h>
 
 /*
  * null security mode.
diff --git a/fs/ceph/auth_x.c b/net/ceph/auth_x.c
similarity index 99%
rename from fs/ceph/auth_x.c
rename to net/ceph/auth_x.c
index a2d002cbdec2..7fd5dfcf6e18 100644
--- a/fs/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -1,16 +1,17 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
+#include "crypto.h"
 #include "auth_x.h"
 #include "auth_x_protocol.h"
-#include "crypto.h"
-#include "auth.h"
-#include "decode.h"
 
 #define TEMP_TICKET_BUF_LEN	256
 
diff --git a/fs/ceph/auth_x.h b/net/ceph/auth_x.h
similarity index 96%
rename from fs/ceph/auth_x.h
rename to net/ceph/auth_x.h
index ff6f8180e681..e02da7a5c5a1 100644
--- a/fs/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -3,8 +3,9 @@
 
 #include <linux/rbtree.h>
 
+#include <linux/ceph/auth.h>
+
 #include "crypto.h"
-#include "auth.h"
 #include "auth_x_protocol.h"
 
 /*
diff --git a/fs/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
similarity index 100%
rename from fs/ceph/auth_x_protocol.h
rename to net/ceph/auth_x_protocol.h
diff --git a/fs/ceph/buffer.c b/net/ceph/buffer.c
similarity index 86%
rename from fs/ceph/buffer.c
rename to net/ceph/buffer.c
index cd39f17021de..53d8abfa25d5 100644
--- a/fs/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -1,10 +1,11 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/slab.h>
 
-#include "buffer.h"
-#include "decode.h"
+#include <linux/ceph/buffer.h>
+#include <linux/ceph/decode.h>
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -32,6 +33,7 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 	dout("buffer_new %p\n", b);
 	return b;
 }
+EXPORT_SYMBOL(ceph_buffer_new);
 
 void ceph_buffer_release(struct kref *kref)
 {
@@ -46,6 +48,7 @@ void ceph_buffer_release(struct kref *kref)
 	}
 	kfree(b);
 }
+EXPORT_SYMBOL(ceph_buffer_release);
 
 int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end)
 {
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
new file mode 100644
index 000000000000..f3e4a13fea0c
--- /dev/null
+++ b/net/ceph/ceph_common.c
@@ -0,0 +1,529 @@
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/backing-dev.h>
+#include <linux/ctype.h>
+#include <linux/fs.h>
+#include <linux/inet.h>
+#include <linux/in6.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/parser.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/string.h>
+
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/debugfs.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+
+
+
+/*
+ * find filename portion of a path (/foo/bar/baz -> baz)
+ */
+const char *ceph_file_part(const char *s, int len)
+{
+	const char *e = s + len;
+
+	while (e != s && *(e-1) != '/')
+		e--;
+	return e;
+}
+EXPORT_SYMBOL(ceph_file_part);
+
+const char *ceph_msg_type_name(int type)
+{
+	switch (type) {
+	case CEPH_MSG_SHUTDOWN: return "shutdown";
+	case CEPH_MSG_PING: return "ping";
+	case CEPH_MSG_AUTH: return "auth";
+	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
+	case CEPH_MSG_MON_MAP: return "mon_map";
+	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
+	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
+	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
+	case CEPH_MSG_STATFS: return "statfs";
+	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MDS_MAP: return "mds_map";
+	case CEPH_MSG_CLIENT_SESSION: return "client_session";
+	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
+	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
+	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
+	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
+	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
+	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
+	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
+	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
+	case CEPH_MSG_OSD_MAP: return "osd_map";
+	case CEPH_MSG_OSD_OP: return "osd_op";
+	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
+	default: return "unknown";
+	}
+}
+EXPORT_SYMBOL(ceph_msg_type_name);
+
+/*
+ * Initially learn our fsid, or verify an fsid matches.
+ */
+int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
+{
+	if (client->have_fsid) {
+		if (ceph_fsid_compare(&client->fsid, fsid)) {
+			pr_err("bad fsid, had %pU got %pU",
+			       &client->fsid, fsid);
+			return -1;
+		}
+	} else {
+		pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid);
+		memcpy(&client->fsid, fsid, sizeof(*fsid));
+		ceph_debugfs_client_init(client);
+		client->have_fsid = true;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_check_fsid);
+
+static int strcmp_null(const char *s1, const char *s2)
+{
+	if (!s1 && !s2)
+		return 0;
+	if (s1 && !s2)
+		return -1;
+	if (!s1 && s2)
+		return 1;
+	return strcmp(s1, s2);
+}
+
+int ceph_compare_options(struct ceph_options *new_opt,
+			 struct ceph_client *client)
+{
+	struct ceph_options *opt1 = new_opt;
+	struct ceph_options *opt2 = client->options;
+	int ofs = offsetof(struct ceph_options, mon_addr);
+	int i;
+	int ret;
+
+	ret = memcmp(opt1, opt2, ofs);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(opt1->name, opt2->name);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(opt1->secret, opt2->secret);
+	if (ret)
+		return ret;
+
+	/* any matching mon ip implies a match */
+	for (i = 0; i < opt1->num_mon; i++) {
+		if (ceph_monmap_contains(client->monc.monmap,
+				 &opt1->mon_addr[i]))
+			return 0;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(ceph_compare_options);
+
+
+static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+{
+	int i = 0;
+	char tmp[3];
+	int err = -EINVAL;
+	int d;
+
+	dout("parse_fsid '%s'\n", str);
+	tmp[2] = 0;
+	while (*str && i < 16) {
+		if (ispunct(*str)) {
+			str++;
+			continue;
+		}
+		if (!isxdigit(str[0]) || !isxdigit(str[1]))
+			break;
+		tmp[0] = str[0];
+		tmp[1] = str[1];
+		if (sscanf(tmp, "%x", &d) < 1)
+			break;
+		fsid->fsid[i] = d & 0xff;
+		i++;
+		str += 2;
+	}
+
+	if (i == 16)
+		err = 0;
+	dout("parse_fsid ret %d got fsid %pU", err, fsid);
+	return err;
+}
+
+/*
+ * ceph options
+ */
+enum {
+	Opt_osdtimeout,
+	Opt_osdkeepalivetimeout,
+	Opt_mount_timeout,
+	Opt_osd_idle_ttl,
+	Opt_last_int,
+	/* int args above */
+	Opt_fsid,
+	Opt_name,
+	Opt_secret,
+	Opt_ip,
+	Opt_last_string,
+	/* string args above */
+	Opt_noshare,
+	Opt_nocrc,
+};
+
+static match_table_t opt_tokens = {
+	{Opt_osdtimeout, "osdtimeout=%d"},
+	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
+	{Opt_mount_timeout, "mount_timeout=%d"},
+	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+	/* int args above */
+	{Opt_fsid, "fsid=%s"},
+	{Opt_name, "name=%s"},
+	{Opt_secret, "secret=%s"},
+	{Opt_ip, "ip=%s"},
+	/* string args above */
+	{Opt_noshare, "noshare"},
+	{Opt_nocrc, "nocrc"},
+	{-1, NULL}
+};
+
+void ceph_destroy_options(struct ceph_options *opt)
+{
+	dout("destroy_options %p\n", opt);
+	kfree(opt->name);
+	kfree(opt->secret);
+	kfree(opt);
+}
+EXPORT_SYMBOL(ceph_destroy_options);
+
+int ceph_parse_options(struct ceph_options **popt, char *options,
+		       const char *dev_name, const char *dev_name_end,
+		       int (*parse_extra_token)(char *c, void *private),
+		       void *private)
+{
+	struct ceph_options *opt;
+	const char *c;
+	int err = -ENOMEM;
+	substring_t argstr[MAX_OPT_ARGS];
+
+	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
+	if (!opt)
+		return err;
+	opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
+				GFP_KERNEL);
+	if (!opt->mon_addr)
+		goto out;
+
+	dout("parse_options %p options '%s' dev_name '%s'\n", opt, options,
+	     dev_name);
+
+	/* start with defaults */
+	opt->flags = CEPH_OPT_DEFAULT;
+	opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
+	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
+	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
+	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
+
+	/* get mon ip(s) */
+	/* ip1[:port1][,ip2[:port2]...] */
+	err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr,
+			     CEPH_MAX_MON, &opt->num_mon);
+	if (err < 0)
+		goto out;
+
+	/* parse mount options */
+	while ((c = strsep(&options, ",")) != NULL) {
+		int token, intval, ret;
+		if (!*c)
+			continue;
+		err = -EINVAL;
+		token = match_token((char *)c, opt_tokens, argstr);
+		if (token < 0 && parse_extra_token) {
+			/* extra? */
+			err = parse_extra_token((char *)c, private);
+			if (err < 0) {
+				pr_err("bad option at '%s'\n", c);
+				goto out;
+			}
+			continue;
+		}
+		if (token < Opt_last_int) {
+			ret = match_int(&argstr[0], &intval);
+			if (ret < 0) {
+				pr_err("bad mount option arg (not int) "
+				       "at '%s'\n", c);
+				continue;
+			}
+			dout("got int token %d val %d\n", token, intval);
+		} else if (token > Opt_last_int && token < Opt_last_string) {
+			dout("got string token %d val %s\n", token,
+			     argstr[0].from);
+		} else {
+			dout("got token %d\n", token);
+		}
+		switch (token) {
+		case Opt_ip:
+			err = ceph_parse_ips(argstr[0].from,
+					     argstr[0].to,
+					     &opt->my_addr,
+					     1, NULL);
+			if (err < 0)
+				goto out;
+			opt->flags |= CEPH_OPT_MYIP;
+			break;
+
+		case Opt_fsid:
+			err = parse_fsid(argstr[0].from, &opt->fsid);
+			if (err == 0)
+				opt->flags |= CEPH_OPT_FSID;
+			break;
+		case Opt_name:
+			opt->name = kstrndup(argstr[0].from,
+					      argstr[0].to-argstr[0].from,
+					      GFP_KERNEL);
+			break;
+		case Opt_secret:
+			opt->secret = kstrndup(argstr[0].from,
+						argstr[0].to-argstr[0].from,
+						GFP_KERNEL);
+			break;
+
+			/* misc */
+		case Opt_osdtimeout:
+			opt->osd_timeout = intval;
+			break;
+		case Opt_osdkeepalivetimeout:
+			opt->osd_keepalive_timeout = intval;
+			break;
+		case Opt_osd_idle_ttl:
+			opt->osd_idle_ttl = intval;
+			break;
+		case Opt_mount_timeout:
+			opt->mount_timeout = intval;
+			break;
+
+		case Opt_noshare:
+			opt->flags |= CEPH_OPT_NOSHARE;
+			break;
+
+		case Opt_nocrc:
+			opt->flags |= CEPH_OPT_NOCRC;
+			break;
+
+		default:
+			BUG_ON(token);
+		}
+	}
+
+	/* success */
+	*popt = opt;
+	return 0;
+
+out:
+	ceph_destroy_options(opt);
+	return err;
+}
+EXPORT_SYMBOL(ceph_parse_options);
+
+u64 ceph_client_id(struct ceph_client *client)
+{
+	return client->monc.auth->global_id;
+}
+EXPORT_SYMBOL(ceph_client_id);
+
+/*
+ * create a fresh client instance
+ */
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
+{
+	struct ceph_client *client;
+	int err = -ENOMEM;
+
+	client = kzalloc(sizeof(*client), GFP_KERNEL);
+	if (client == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	client->private = private;
+	client->options = opt;
+
+	mutex_init(&client->mount_mutex);
+	init_waitqueue_head(&client->auth_wq);
+	client->auth_err = 0;
+
+	client->extra_mon_dispatch = NULL;
+	client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT;
+	client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT;
+
+	client->msgr = NULL;
+
+	/* subsystems */
+	err = ceph_monc_init(&client->monc, client);
+	if (err < 0)
+		goto fail;
+	err = ceph_osdc_init(&client->osdc, client);
+	if (err < 0)
+		goto fail_monc;
+
+	return client;
+
+fail_monc:
+	ceph_monc_stop(&client->monc);
+fail:
+	kfree(client);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(ceph_create_client);
+
+void ceph_destroy_client(struct ceph_client *client)
+{
+	dout("destroy_client %p\n", client);
+
+	/* unmount */
+	ceph_osdc_stop(&client->osdc);
+
+	/*
+	 * make sure mds and osd connections close out before destroying
+	 * the auth module, which is needed to free those connections'
+	 * ceph_authorizers.
+	 */
+	ceph_msgr_flush();
+
+	ceph_monc_stop(&client->monc);
+
+	ceph_debugfs_client_cleanup(client);
+
+	if (client->msgr)
+		ceph_messenger_destroy(client->msgr);
+
+	ceph_destroy_options(client->options);
+
+	kfree(client);
+	dout("destroy_client %p done\n", client);
+}
+EXPORT_SYMBOL(ceph_destroy_client);
+
+/*
+ * true if we have the mon map (and have thus joined the cluster)
+ */
+static int have_mon_and_osd_map(struct ceph_client *client)
+{
+	return client->monc.monmap && client->monc.monmap->epoch &&
+	       client->osdc.osdmap && client->osdc.osdmap->epoch;
+}
+
+/*
+ * mount: join the ceph cluster, and open root directory.
+ */
+int __ceph_open_session(struct ceph_client *client, unsigned long started)
+{
+	struct ceph_entity_addr *myaddr = NULL;
+	int err;
+	unsigned long timeout = client->options->mount_timeout * HZ;
+
+	/* initialize the messenger */
+	if (client->msgr == NULL) {
+		if (ceph_test_opt(client, MYIP))
+			myaddr = &client->options->my_addr;
+		client->msgr = ceph_messenger_create(myaddr,
+					client->supported_features,
+					client->required_features);
+		if (IS_ERR(client->msgr)) {
+			client->msgr = NULL;
+			return PTR_ERR(client->msgr);
+		}
+		client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+	}
+
+	/* open session, and wait for mon and osd maps */
+	err = ceph_monc_open_session(&client->monc);
+	if (err < 0)
+		return err;
+
+	while (!have_mon_and_osd_map(client)) {
+		err = -EIO;
+		if (timeout && time_after_eq(jiffies, started + timeout))
+			return err;
+
+		/* wait */
+		dout("mount waiting for mon_map\n");
+		err = wait_event_interruptible_timeout(client->auth_wq,
+			have_mon_and_osd_map(client) || (client->auth_err < 0),
+			timeout);
+		if (err == -EINTR || err == -ERESTARTSYS)
+			return err;
+		if (client->auth_err < 0)
+			return client->auth_err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__ceph_open_session);
+
+
+int ceph_open_session(struct ceph_client *client)
+{
+	int ret;
+	unsigned long started = jiffies;  /* note the start time */
+
+	dout("open_session start\n");
+	mutex_lock(&client->mount_mutex);
+
+	ret = __ceph_open_session(client, started);
+
+	mutex_unlock(&client->mount_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_open_session);
+
+
+static int __init init_ceph_lib(void)
+{
+	int ret = 0;
+
+	ret = ceph_debugfs_init();
+	if (ret < 0)
+		goto out;
+
+	ret = ceph_msgr_init();
+	if (ret < 0)
+		goto out_debugfs;
+
+	pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n",
+		CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL,
+		CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
+		CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+
+	return 0;
+
+out_debugfs:
+	ceph_debugfs_cleanup();
+out:
+	return ret;
+}
+
+static void __exit exit_ceph_lib(void)
+{
+	dout("exit_ceph_lib\n");
+	ceph_msgr_exit();
+	ceph_debugfs_cleanup();
+}
+
+module_init(init_ceph_lib);
+module_exit(exit_ceph_lib);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
+MODULE_DESCRIPTION("Ceph filesystem for Linux");
+MODULE_LICENSE("GPL");
diff --git a/fs/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
similarity index 92%
rename from fs/ceph/ceph_fs.c
rename to net/ceph/ceph_fs.c
index 3ac6cc7c1156..a3a3a31d3c37 100644
--- a/fs/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -1,7 +1,8 @@
 /*
  * Some non-inline ceph helpers
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
 /*
  * return true if @layout appears to be valid
@@ -52,6 +53,7 @@ int ceph_flags_to_mode(int flags)
 
 	return mode;
 }
+EXPORT_SYMBOL(ceph_flags_to_mode);
 
 int ceph_caps_for_mode(int mode)
 {
@@ -70,3 +72,4 @@ int ceph_caps_for_mode(int mode)
 
 	return caps;
 }
+EXPORT_SYMBOL(ceph_caps_for_mode);
diff --git a/fs/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
similarity index 98%
rename from fs/ceph/ceph_hash.c
rename to net/ceph/ceph_hash.c
index bd570015d147..815ef8826796 100644
--- a/fs/ceph/ceph_hash.c
+++ b/net/ceph/ceph_hash.c
@@ -1,5 +1,5 @@
 
-#include "types.h"
+#include <linux/ceph/types.h>
 
 /*
  * Robert Jenkin's hash function.
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
new file mode 100644
index 000000000000..3fbda04de29c
--- /dev/null
+++ b/net/ceph/ceph_strings.c
@@ -0,0 +1,84 @@
+/*
+ * Ceph string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+const char *ceph_entity_type_name(int type)
+{
+	switch (type) {
+	case CEPH_ENTITY_TYPE_MDS: return "mds";
+	case CEPH_ENTITY_TYPE_OSD: return "osd";
+	case CEPH_ENTITY_TYPE_MON: return "mon";
+	case CEPH_ENTITY_TYPE_CLIENT: return "client";
+	case CEPH_ENTITY_TYPE_AUTH: return "auth";
+	default: return "unknown";
+	}
+}
+
+const char *ceph_osd_op_name(int op)
+{
+	switch (op) {
+	case CEPH_OSD_OP_READ: return "read";
+	case CEPH_OSD_OP_STAT: return "stat";
+
+	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
+
+	case CEPH_OSD_OP_WRITE: return "write";
+	case CEPH_OSD_OP_DELETE: return "delete";
+	case CEPH_OSD_OP_TRUNCATE: return "truncate";
+	case CEPH_OSD_OP_ZERO: return "zero";
+	case CEPH_OSD_OP_WRITEFULL: return "writefull";
+	case CEPH_OSD_OP_ROLLBACK: return "rollback";
+
+	case CEPH_OSD_OP_APPEND: return "append";
+	case CEPH_OSD_OP_STARTSYNC: return "startsync";
+	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
+	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
+
+	case CEPH_OSD_OP_TMAPUP: return "tmapup";
+	case CEPH_OSD_OP_TMAPGET: return "tmapget";
+	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
+
+	case CEPH_OSD_OP_GETXATTR: return "getxattr";
+	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
+	case CEPH_OSD_OP_SETXATTR: return "setxattr";
+	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
+	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
+	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
+	case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
+
+	case CEPH_OSD_OP_PULL: return "pull";
+	case CEPH_OSD_OP_PUSH: return "push";
+	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
+	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
+	case CEPH_OSD_OP_SCRUB: return "scrub";
+
+	case CEPH_OSD_OP_WRLOCK: return "wrlock";
+	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
+	case CEPH_OSD_OP_RDLOCK: return "rdlock";
+	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
+	case CEPH_OSD_OP_UPLOCK: return "uplock";
+	case CEPH_OSD_OP_DNLOCK: return "dnlock";
+
+	case CEPH_OSD_OP_CALL: return "call";
+
+	case CEPH_OSD_OP_PGLS: return "pgls";
+	}
+	return "???";
+}
+
+
+const char *ceph_pool_op_name(int op)
+{
+	switch (op) {
+	case POOL_OP_CREATE: return "create";
+	case POOL_OP_DELETE: return "delete";
+	case POOL_OP_AUID_CHANGE: return "auid change";
+	case POOL_OP_CREATE_SNAP: return "create snap";
+	case POOL_OP_DELETE_SNAP: return "delete snap";
+	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
+	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
+	}
+	return "???";
+}
diff --git a/fs/ceph/crush/crush.c b/net/ceph/crush/crush.c
similarity index 99%
rename from fs/ceph/crush/crush.c
rename to net/ceph/crush/crush.c
index fabd302e5779..d6ebb13a18a4 100644
--- a/fs/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -8,7 +8,7 @@
 # define BUG_ON(x) assert(!(x))
 #endif
 
-#include "crush.h"
+#include <linux/crush/crush.h>
 
 const char *crush_bucket_alg_name(int alg)
 {
diff --git a/fs/ceph/crush/hash.c b/net/ceph/crush/hash.c
similarity index 99%
rename from fs/ceph/crush/hash.c
rename to net/ceph/crush/hash.c
index 5873aed694bf..5bb63e37a8a1 100644
--- a/fs/ceph/crush/hash.c
+++ b/net/ceph/crush/hash.c
@@ -1,6 +1,6 @@
 
 #include <linux/types.h>
-#include "hash.h"
+#include <linux/crush/hash.h>
 
 /*
  * Robert Jenkins' function for mixing 32-bit values
diff --git a/fs/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
similarity index 99%
rename from fs/ceph/crush/mapper.c
rename to net/ceph/crush/mapper.c
index a4eec133258e..42599e31dcad 100644
--- a/fs/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -18,8 +18,8 @@
 # define kfree(x) free(x)
 #endif
 
-#include "crush.h"
-#include "hash.h"
+#include <linux/crush/crush.h>
+#include <linux/crush/hash.h>
 
 /*
  * Implement the core CRUSH mapping algorithm.
diff --git a/fs/ceph/crypto.c b/net/ceph/crypto.c
similarity index 99%
rename from fs/ceph/crypto.c
rename to net/ceph/crypto.c
index a3e627f63293..7b505b0c983f 100644
--- a/fs/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -1,13 +1,13 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <crypto/hash.h>
 
+#include <linux/ceph/decode.h>
 #include "crypto.h"
-#include "decode.h"
 
 int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end)
 {
diff --git a/fs/ceph/crypto.h b/net/ceph/crypto.h
similarity index 95%
rename from fs/ceph/crypto.h
rename to net/ceph/crypto.h
index bdf38607323c..f9eccace592b 100644
--- a/fs/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -1,8 +1,8 @@
 #ifndef _FS_CEPH_CRYPTO_H
 #define _FS_CEPH_CRYPTO_H
 
-#include "types.h"
-#include "buffer.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
 
 /*
  * cryptographic secret
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
new file mode 100644
index 000000000000..27d4ea315d12
--- /dev/null
+++ b/net/ceph/debugfs.c
@@ -0,0 +1,267 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
+#ifdef CONFIG_DEBUG_FS
+
+/*
+ * Implement /sys/kernel/debug/ceph fun
+ *
+ * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
+ *      .../osdmap      - current osdmap
+ *      .../monmap      - current monmap
+ *      .../osdc        - active osd requests
+ *      .../monc        - mon client state
+ *      .../dentry_lru  - dump contents of dentry lru
+ *      .../caps        - expose cap (reservation) stats
+ *      .../bdi         - symlink to ../../bdi/something
+ */
+
+static struct dentry *ceph_debugfs_dir;
+
+static int monmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+
+	if (client->monc.monmap == NULL)
+		return 0;
+
+	seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
+	for (i = 0; i < client->monc.monmap->num_mon; i++) {
+		struct ceph_entity_inst *inst =
+			&client->monc.monmap->mon_inst[i];
+
+		seq_printf(s, "\t%s%lld\t%s\n",
+			   ENTITY_NAME(inst->name),
+			   ceph_pr_addr(&inst->addr.in_addr));
+	}
+	return 0;
+}
+
+static int osdmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+	struct rb_node *n;
+
+	if (client->osdc.osdmap == NULL)
+		return 0;
+	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
+	seq_printf(s, "flags%s%s\n",
+		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
+		   " NEARFULL" : "",
+		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
+		   " FULL" : "");
+	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
+		struct ceph_pg_pool_info *pool =
+			rb_entry(n, struct ceph_pg_pool_info, node);
+		seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
+			   pool->id, pool->v.pg_num, pool->pg_num_mask,
+			   pool->v.lpg_num, pool->lpg_num_mask);
+	}
+	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
+		struct ceph_entity_addr *addr =
+			&client->osdc.osdmap->osd_addr[i];
+		int state = client->osdc.osdmap->osd_state[i];
+		char sb[64];
+
+		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
+			   i, ceph_pr_addr(&addr->in_addr),
+			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
+			   ceph_osdmap_state_str(sb, sizeof(sb), state));
+	}
+	return 0;
+}
+
+static int monc_show(struct seq_file *s, void *p)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_mon_generic_request *req;
+	struct ceph_mon_client *monc = &client->monc;
+	struct rb_node *rp;
+
+	mutex_lock(&monc->mutex);
+
+	if (monc->have_mdsmap)
+		seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
+	if (monc->have_osdmap)
+		seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
+	if (monc->want_next_osdmap)
+		seq_printf(s, "want next osdmap\n");
+
+	for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
+		__u16 op;
+		req = rb_entry(rp, struct ceph_mon_generic_request, node);
+		op = le16_to_cpu(req->request->hdr.type);
+		if (op == CEPH_MSG_STATFS)
+			seq_printf(s, "%lld statfs\n", req->tid);
+		else
+			seq_printf(s, "%lld unknown\n", req->tid);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+static int osdc_show(struct seq_file *s, void *pp)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_osd_client *osdc = &client->osdc;
+	struct rb_node *p;
+
+	mutex_lock(&osdc->request_mutex);
+	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+		struct ceph_osd_request *req;
+		struct ceph_osd_request_head *head;
+		struct ceph_osd_op *op;
+		int num_ops;
+		int opcode, olen;
+		int i;
+
+		req = rb_entry(p, struct ceph_osd_request, r_node);
+
+		seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
+			   req->r_osd ? req->r_osd->o_osd : -1,
+			   le32_to_cpu(req->r_pgid.pool),
+			   le16_to_cpu(req->r_pgid.ps));
+
+		head = req->r_request->front.iov_base;
+		op = (void *)(head + 1);
+
+		num_ops = le16_to_cpu(head->num_ops);
+		olen = le32_to_cpu(head->object_len);
+		seq_printf(s, "%.*s", olen,
+			   (const char *)(head->ops + num_ops));
+
+		if (req->r_reassert_version.epoch)
+			seq_printf(s, "\t%u'%llu",
+			   (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
+			   le64_to_cpu(req->r_reassert_version.version));
+		else
+			seq_printf(s, "\t");
+
+		for (i = 0; i < num_ops; i++) {
+			opcode = le16_to_cpu(op->op);
+			seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
+			op++;
+		}
+
+		seq_printf(s, "\n");
+	}
+	mutex_unlock(&osdc->request_mutex);
+	return 0;
+}
+
+CEPH_DEFINE_SHOW_FUNC(monmap_show)
+CEPH_DEFINE_SHOW_FUNC(osdmap_show)
+CEPH_DEFINE_SHOW_FUNC(monc_show)
+CEPH_DEFINE_SHOW_FUNC(osdc_show)
+
+int ceph_debugfs_init(void)
+{
+	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
+	if (!ceph_debugfs_dir)
+		return -ENOMEM;
+	return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+	debugfs_remove(ceph_debugfs_dir);
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+	int ret = -ENOMEM;
+	char name[80];
+
+	snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
+		 client->monc.auth->global_id);
+
+	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
+	if (!client->debugfs_dir)
+		goto out;
+
+	client->monc.debugfs_file = debugfs_create_file("monc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &monc_show_fops);
+	if (!client->monc.debugfs_file)
+		goto out;
+
+	client->osdc.debugfs_file = debugfs_create_file("osdc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &osdc_show_fops);
+	if (!client->osdc.debugfs_file)
+		goto out;
+
+	client->debugfs_monmap = debugfs_create_file("monmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&monmap_show_fops);
+	if (!client->debugfs_monmap)
+		goto out;
+
+	client->debugfs_osdmap = debugfs_create_file("osdmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&osdmap_show_fops);
+	if (!client->debugfs_osdmap)
+		goto out;
+
+	return 0;
+
+out:
+	ceph_debugfs_client_cleanup(client);
+	return ret;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+	debugfs_remove(client->debugfs_osdmap);
+	debugfs_remove(client->debugfs_monmap);
+	debugfs_remove(client->osdc.debugfs_file);
+	debugfs_remove(client->monc.debugfs_file);
+	debugfs_remove(client->debugfs_dir);
+}
+
+#else  /* CONFIG_DEBUG_FS */
+
+int ceph_debugfs_init(void)
+{
+	return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+	return 0;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+}
+
+#endif  /* CONFIG_DEBUG_FS */
+
+EXPORT_SYMBOL(ceph_debugfs_init);
+EXPORT_SYMBOL(ceph_debugfs_cleanup);
diff --git a/fs/ceph/messenger.c b/net/ceph/messenger.c
similarity index 89%
rename from fs/ceph/messenger.c
rename to net/ceph/messenger.c
index 2502d76fcec1..0e8157ee5d43 100644
--- a/fs/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/crc32c.h>
 #include <linux/ctype.h>
@@ -9,12 +9,14 @@
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
 #include <net/tcp.h>
 
-#include "super.h"
-#include "messenger.h"
-#include "decode.h"
-#include "pagelist.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
 
 /*
  * Ceph uses the messenger to exchange ceph_msg messages with other
@@ -48,7 +50,7 @@ static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN];
 static DEFINE_SPINLOCK(addr_str_lock);
 static int last_addr_str;
 
-const char *pr_addr(const struct sockaddr_storage *ss)
+const char *ceph_pr_addr(const struct sockaddr_storage *ss)
 {
 	int i;
 	char *s;
@@ -79,6 +81,7 @@ const char *pr_addr(const struct sockaddr_storage *ss)
 
 	return s;
 }
+EXPORT_SYMBOL(ceph_pr_addr);
 
 static void encode_my_addr(struct ceph_messenger *msgr)
 {
@@ -91,7 +94,7 @@ static void encode_my_addr(struct ceph_messenger *msgr)
  */
 struct workqueue_struct *ceph_msgr_wq;
 
-int __init ceph_msgr_init(void)
+int ceph_msgr_init(void)
 {
 	ceph_msgr_wq = create_workqueue("ceph-msgr");
 	if (IS_ERR(ceph_msgr_wq)) {
@@ -102,16 +105,19 @@ int __init ceph_msgr_init(void)
 	}
 	return 0;
 }
+EXPORT_SYMBOL(ceph_msgr_init);
 
 void ceph_msgr_exit(void)
 {
 	destroy_workqueue(ceph_msgr_wq);
 }
+EXPORT_SYMBOL(ceph_msgr_exit);
 
 void ceph_msgr_flush(void)
 {
 	flush_workqueue(ceph_msgr_wq);
 }
+EXPORT_SYMBOL(ceph_msgr_flush);
 
 
 /*
@@ -221,19 +227,19 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
 
 	set_sock_callbacks(sock, con);
 
-	dout("connect %s\n", pr_addr(&con->peer_addr.in_addr));
+	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
 
 	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
 				 O_NONBLOCK);
 	if (ret == -EINPROGRESS) {
 		dout("connect %s EINPROGRESS sk_state = %u\n",
-		     pr_addr(&con->peer_addr.in_addr),
+		     ceph_pr_addr(&con->peer_addr.in_addr),
 		     sock->sk->sk_state);
 		ret = 0;
 	}
 	if (ret < 0) {
 		pr_err("connect %s error %d\n",
-		       pr_addr(&con->peer_addr.in_addr), ret);
+		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
 		sock_release(sock);
 		con->sock = NULL;
 		con->error_msg = "connect error";
@@ -334,7 +340,8 @@ static void reset_connection(struct ceph_connection *con)
  */
 void ceph_con_close(struct ceph_connection *con)
 {
-	dout("con_close %p peer %s\n", con, pr_addr(&con->peer_addr.in_addr));
+	dout("con_close %p peer %s\n", con,
+	     ceph_pr_addr(&con->peer_addr.in_addr));
 	set_bit(CLOSED, &con->state);  /* in case there's queued work */
 	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
 	clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
@@ -347,19 +354,21 @@ void ceph_con_close(struct ceph_connection *con)
 	mutex_unlock(&con->mutex);
 	queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_close);
 
 /*
  * Reopen a closed connection, with a new peer address.
  */
 void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
 {
-	dout("con_open %p %s\n", con, pr_addr(&addr->in_addr));
+	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
 	set_bit(OPENING, &con->state);
 	clear_bit(CLOSED, &con->state);
 	memcpy(&con->peer_addr, addr, sizeof(*addr));
 	con->delay = 0;      /* reset backoff memory */
 	queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_open);
 
 /*
  * return true if this connection ever successfully opened
@@ -406,6 +415,7 @@ void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
 	INIT_LIST_HEAD(&con->out_sent);
 	INIT_DELAYED_WORK(&con->work, con_work);
 }
+EXPORT_SYMBOL(ceph_con_init);
 
 
 /*
@@ -529,8 +539,11 @@ static void prepare_write_message(struct ceph_connection *con)
 	if (le32_to_cpu(m->hdr.data_len) > 0) {
 		/* initialize page iterator */
 		con->out_msg_pos.page = 0;
-		con->out_msg_pos.page_pos =
-			le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+		if (m->pages)
+			con->out_msg_pos.page_pos =
+				le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+		else
+			con->out_msg_pos.page_pos = 0;
 		con->out_msg_pos.data_pos = 0;
 		con->out_msg_pos.did_page_crc = 0;
 		con->out_more = 1;  /* data + footer will follow */
@@ -647,7 +660,7 @@ static void prepare_write_connect(struct ceph_messenger *msgr,
 	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
 	     con->connect_seq, global_seq, proto);
 
-	con->out_connect.features = cpu_to_le64(CEPH_FEATURE_SUPPORTED);
+	con->out_connect.features = cpu_to_le64(msgr->supported_features);
 	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
 	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
 	con->out_connect.global_seq = cpu_to_le32(global_seq);
@@ -712,6 +725,31 @@ out:
 	return ret;  /* done! */
 }
 
+#ifdef CONFIG_BLOCK
+static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+{
+	if (!bio) {
+		*iter = NULL;
+		*seg = 0;
+		return;
+	}
+	*iter = bio;
+	*seg = bio->bi_idx;
+}
+
+static void iter_bio_next(struct bio **bio_iter, int *seg)
+{
+	if (*bio_iter == NULL)
+		return;
+
+	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+
+	(*seg)++;
+	if (*seg == (*bio_iter)->bi_vcnt)
+		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
+}
+#endif
+
 /*
  * Write as much message data payload as we can.  If we finish, queue
  * up the footer.
@@ -726,21 +764,46 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 	size_t len;
 	int crc = con->msgr->nocrc;
 	int ret;
+	int total_max_write;
+	int in_trail = 0;
+	size_t trail_len = (msg->trail ? msg->trail->length : 0);
 
 	dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
 	     con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
 	     con->out_msg_pos.page_pos);
 
-	while (con->out_msg_pos.page < con->out_msg->nr_pages) {
+#ifdef CONFIG_BLOCK
+	if (msg->bio && !msg->bio_iter)
+		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
+#endif
+
+	while (data_len > con->out_msg_pos.data_pos) {
 		struct page *page = NULL;
 		void *kaddr = NULL;
+		int max_write = PAGE_SIZE;
+		int page_shift = 0;
+
+		total_max_write = data_len - trail_len -
+			con->out_msg_pos.data_pos;
 
 		/*
 		 * if we are calculating the data crc (the default), we need
 		 * to map the page.  if our pages[] has been revoked, use the
 		 * zero page.
 		 */
-		if (msg->pages) {
+
+		/* have we reached the trail part of the data? */
+		if (con->out_msg_pos.data_pos >= data_len - trail_len) {
+			in_trail = 1;
+
+			total_max_write = data_len - con->out_msg_pos.data_pos;
+
+			page = list_first_entry(&msg->trail->head,
+						struct page, lru);
+			if (crc)
+				kaddr = kmap(page);
+			max_write = PAGE_SIZE;
+		} else if (msg->pages) {
 			page = msg->pages[con->out_msg_pos.page];
 			if (crc)
 				kaddr = kmap(page);
@@ -749,13 +812,25 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 						struct page, lru);
 			if (crc)
 				kaddr = kmap(page);
+#ifdef CONFIG_BLOCK
+		} else if (msg->bio) {
+			struct bio_vec *bv;
+
+			bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
+			page = bv->bv_page;
+			page_shift = bv->bv_offset;
+			if (crc)
+				kaddr = kmap(page) + page_shift;
+			max_write = bv->bv_len;
+#endif
 		} else {
 			page = con->msgr->zero_page;
 			if (crc)
 				kaddr = page_address(con->msgr->zero_page);
 		}
-		len = min((int)(PAGE_SIZE - con->out_msg_pos.page_pos),
-			  (int)(data_len - con->out_msg_pos.data_pos));
+		len = min_t(int, max_write - con->out_msg_pos.page_pos,
+			    total_max_write);
+
 		if (crc && !con->out_msg_pos.did_page_crc) {
 			void *base = kaddr + con->out_msg_pos.page_pos;
 			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
@@ -765,13 +840,14 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 				cpu_to_le32(crc32c(tmpcrc, base, len));
 			con->out_msg_pos.did_page_crc = 1;
 		}
-
 		ret = kernel_sendpage(con->sock, page,
-				      con->out_msg_pos.page_pos, len,
+				      con->out_msg_pos.page_pos + page_shift,
+				      len,
 				      MSG_DONTWAIT | MSG_NOSIGNAL |
 				      MSG_MORE);
 
-		if (crc && (msg->pages || msg->pagelist))
+		if (crc &&
+		    (msg->pages || msg->pagelist || msg->bio || in_trail))
 			kunmap(page);
 
 		if (ret <= 0)
@@ -783,9 +859,16 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 			con->out_msg_pos.page_pos = 0;
 			con->out_msg_pos.page++;
 			con->out_msg_pos.did_page_crc = 0;
-			if (msg->pagelist)
+			if (in_trail)
+				list_move_tail(&page->lru,
+					       &msg->trail->head);
+			else if (msg->pagelist)
 				list_move_tail(&page->lru,
 					       &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+			else if (msg->bio)
+				iter_bio_next(&msg->bio_iter, &msg->bio_seg);
+#endif
 		}
 	}
 
@@ -938,7 +1021,7 @@ static int verify_hello(struct ceph_connection *con)
 {
 	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
 		pr_err("connect to %s got bad banner\n",
-		       pr_addr(&con->peer_addr.in_addr));
+		       ceph_pr_addr(&con->peer_addr.in_addr));
 		con->error_msg = "protocol error, bad banner";
 		return -1;
 	}
@@ -1041,7 +1124,7 @@ int ceph_parse_ips(const char *c, const char *end,
 
 		addr_set_port(ss, port);
 
-		dout("parse_ips got %s\n", pr_addr(ss));
+		dout("parse_ips got %s\n", ceph_pr_addr(ss));
 
 		if (p == end)
 			break;
@@ -1061,6 +1144,7 @@ bad:
 	pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c);
 	return -EINVAL;
 }
+EXPORT_SYMBOL(ceph_parse_ips);
 
 static int process_banner(struct ceph_connection *con)
 {
@@ -1082,9 +1166,9 @@ static int process_banner(struct ceph_connection *con)
 	    !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
 	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
 		pr_warning("wrong peer, want %s/%d, got %s/%d\n",
-			   pr_addr(&con->peer_addr.in_addr),
+			   ceph_pr_addr(&con->peer_addr.in_addr),
 			   (int)le32_to_cpu(con->peer_addr.nonce),
-			   pr_addr(&con->actual_peer_addr.in_addr),
+			   ceph_pr_addr(&con->actual_peer_addr.in_addr),
 			   (int)le32_to_cpu(con->actual_peer_addr.nonce));
 		con->error_msg = "wrong peer at address";
 		return -1;
@@ -1102,7 +1186,7 @@ static int process_banner(struct ceph_connection *con)
 		addr_set_port(&con->msgr->inst.addr.in_addr, port);
 		encode_my_addr(con->msgr);
 		dout("process_banner learned my addr is %s\n",
-		     pr_addr(&con->msgr->inst.addr.in_addr));
+		     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
 	}
 
 	set_bit(NEGOTIATING, &con->state);
@@ -1123,8 +1207,8 @@ static void fail_protocol(struct ceph_connection *con)
 
 static int process_connect(struct ceph_connection *con)
 {
-	u64 sup_feat = CEPH_FEATURE_SUPPORTED;
-	u64 req_feat = CEPH_FEATURE_REQUIRED;
+	u64 sup_feat = con->msgr->supported_features;
+	u64 req_feat = con->msgr->required_features;
 	u64 server_feat = le64_to_cpu(con->in_reply.features);
 
 	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
@@ -1134,7 +1218,7 @@ static int process_connect(struct ceph_connection *con)
 		pr_err("%s%lld %s feature set mismatch,"
 		       " my %llx < server's %llx, missing %llx\n",
 		       ENTITY_NAME(con->peer_name),
-		       pr_addr(&con->peer_addr.in_addr),
+		       ceph_pr_addr(&con->peer_addr.in_addr),
 		       sup_feat, server_feat, server_feat & ~sup_feat);
 		con->error_msg = "missing required protocol features";
 		fail_protocol(con);
@@ -1144,7 +1228,7 @@ static int process_connect(struct ceph_connection *con)
 		pr_err("%s%lld %s protocol version mismatch,"
 		       " my %d != server's %d\n",
 		       ENTITY_NAME(con->peer_name),
-		       pr_addr(&con->peer_addr.in_addr),
+		       ceph_pr_addr(&con->peer_addr.in_addr),
 		       le32_to_cpu(con->out_connect.protocol_version),
 		       le32_to_cpu(con->in_reply.protocol_version));
 		con->error_msg = "protocol version mismatch";
@@ -1178,7 +1262,7 @@ static int process_connect(struct ceph_connection *con)
 		     le32_to_cpu(con->in_connect.connect_seq));
 		pr_err("%s%lld %s connection reset\n",
 		       ENTITY_NAME(con->peer_name),
-		       pr_addr(&con->peer_addr.in_addr));
+		       ceph_pr_addr(&con->peer_addr.in_addr));
 		reset_connection(con);
 		prepare_write_connect(con->msgr, con, 0);
 		prepare_read_connect(con);
@@ -1223,7 +1307,7 @@ static int process_connect(struct ceph_connection *con)
 			pr_err("%s%lld %s protocol feature mismatch,"
 			       " my required %llx > server's %llx, need %llx\n",
 			       ENTITY_NAME(con->peer_name),
-			       pr_addr(&con->peer_addr.in_addr),
+			       ceph_pr_addr(&con->peer_addr.in_addr),
 			       req_feat, server_feat, req_feat & ~server_feat);
 			con->error_msg = "missing required protocol features";
 			fail_protocol(con);
@@ -1305,8 +1389,7 @@ static int read_partial_message_section(struct ceph_connection *con,
 					struct kvec *section,
 					unsigned int sec_len, u32 *crc)
 {
-	int left;
-	int ret;
+	int ret, left;
 
 	BUG_ON(!section);
 
@@ -1329,13 +1412,83 @@ static int read_partial_message_section(struct ceph_connection *con,
 static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
 				struct ceph_msg_header *hdr,
 				int *skip);
+
+
+static int read_partial_message_pages(struct ceph_connection *con,
+				      struct page **pages,
+				      unsigned data_len, int datacrc)
+{
+	void *p;
+	int ret;
+	int left;
+
+	left = min((int)(data_len - con->in_msg_pos.data_pos),
+		   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
+	/* (page) data */
+	BUG_ON(pages == NULL);
+	p = kmap(pages[con->in_msg_pos.page]);
+	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+			       left);
+	if (ret > 0 && datacrc)
+		con->in_data_crc =
+			crc32c(con->in_data_crc,
+				  p + con->in_msg_pos.page_pos, ret);
+	kunmap(pages[con->in_msg_pos.page]);
+	if (ret <= 0)
+		return ret;
+	con->in_msg_pos.data_pos += ret;
+	con->in_msg_pos.page_pos += ret;
+	if (con->in_msg_pos.page_pos == PAGE_SIZE) {
+		con->in_msg_pos.page_pos = 0;
+		con->in_msg_pos.page++;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_BLOCK
+static int read_partial_message_bio(struct ceph_connection *con,
+				    struct bio **bio_iter, int *bio_seg,
+				    unsigned data_len, int datacrc)
+{
+	struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
+	void *p;
+	int ret, left;
+
+	if (IS_ERR(bv))
+		return PTR_ERR(bv);
+
+	left = min((int)(data_len - con->in_msg_pos.data_pos),
+		   (int)(bv->bv_len - con->in_msg_pos.page_pos));
+
+	p = kmap(bv->bv_page) + bv->bv_offset;
+
+	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+			       left);
+	if (ret > 0 && datacrc)
+		con->in_data_crc =
+			crc32c(con->in_data_crc,
+				  p + con->in_msg_pos.page_pos, ret);
+	kunmap(bv->bv_page);
+	if (ret <= 0)
+		return ret;
+	con->in_msg_pos.data_pos += ret;
+	con->in_msg_pos.page_pos += ret;
+	if (con->in_msg_pos.page_pos == bv->bv_len) {
+		con->in_msg_pos.page_pos = 0;
+		iter_bio_next(bio_iter, bio_seg);
+	}
+
+	return ret;
+}
+#endif
+
 /*
  * read (part of) a message.
  */
 static int read_partial_message(struct ceph_connection *con)
 {
 	struct ceph_msg *m = con->in_msg;
-	void *p;
 	int ret;
 	int to, left;
 	unsigned front_len, middle_len, data_len, data_off;
@@ -1381,7 +1534,7 @@ static int read_partial_message(struct ceph_connection *con)
 	if ((s64)seq - (s64)con->in_seq < 1) {
 		pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
 			ENTITY_NAME(con->peer_name),
-			pr_addr(&con->peer_addr.in_addr),
+			ceph_pr_addr(&con->peer_addr.in_addr),
 			seq, con->in_seq + 1);
 		con->in_base_pos = -front_len - middle_len - data_len -
 			sizeof(m->footer);
@@ -1422,7 +1575,10 @@ static int read_partial_message(struct ceph_connection *con)
 			m->middle->vec.iov_len = 0;
 
 		con->in_msg_pos.page = 0;
-		con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+		if (m->pages)
+			con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+		else
+			con->in_msg_pos.page_pos = 0;
 		con->in_msg_pos.data_pos = 0;
 	}
 
@@ -1440,27 +1596,29 @@ static int read_partial_message(struct ceph_connection *con)
 		if (ret <= 0)
 			return ret;
 	}
+#ifdef CONFIG_BLOCK
+	if (m->bio && !m->bio_iter)
+		init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
+#endif
 
 	/* (page) data */
 	while (con->in_msg_pos.data_pos < data_len) {
-		left = min((int)(data_len - con->in_msg_pos.data_pos),
-			   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
-		BUG_ON(m->pages == NULL);
-		p = kmap(m->pages[con->in_msg_pos.page]);
-		ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
-				       left);
-		if (ret > 0 && datacrc)
-			con->in_data_crc =
-				crc32c(con->in_data_crc,
-					  p + con->in_msg_pos.page_pos, ret);
-		kunmap(m->pages[con->in_msg_pos.page]);
-		if (ret <= 0)
-			return ret;
-		con->in_msg_pos.data_pos += ret;
-		con->in_msg_pos.page_pos += ret;
-		if (con->in_msg_pos.page_pos == PAGE_SIZE) {
-			con->in_msg_pos.page_pos = 0;
-			con->in_msg_pos.page++;
+		if (m->pages) {
+			ret = read_partial_message_pages(con, m->pages,
+						 data_len, datacrc);
+			if (ret <= 0)
+				return ret;
+#ifdef CONFIG_BLOCK
+		} else if (m->bio) {
+
+			ret = read_partial_message_bio(con,
+						 &m->bio_iter, &m->bio_seg,
+						 data_len, datacrc);
+			if (ret <= 0)
+				return ret;
+#endif
+		} else {
+			BUG_ON(1);
 		}
 	}
 
@@ -1874,9 +2032,9 @@ out:
 static void ceph_fault(struct ceph_connection *con)
 {
 	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
-	       pr_addr(&con->peer_addr.in_addr), con->error_msg);
+	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	dout("fault %p state %lu to peer %s\n",
-	     con, con->state, pr_addr(&con->peer_addr.in_addr));
+	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
 	if (test_bit(LOSSYTX, &con->state)) {
 		dout("fault on LOSSYTX channel\n");
@@ -1936,7 +2094,9 @@ out:
 /*
  * create a new messenger instance
  */
-struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
+struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
+					     u32 supported_features,
+					     u32 required_features)
 {
 	struct ceph_messenger *msgr;
 
@@ -1944,6 +2104,9 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
 	if (msgr == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	msgr->supported_features = supported_features;
+	msgr->required_features = required_features;
+
 	spin_lock_init(&msgr->global_seq_lock);
 
 	/* the zero page is needed if a request is "canceled" while the message
@@ -1966,6 +2129,7 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
 	dout("messenger_create %p\n", msgr);
 	return msgr;
 }
+EXPORT_SYMBOL(ceph_messenger_create);
 
 void ceph_messenger_destroy(struct ceph_messenger *msgr)
 {
@@ -1975,6 +2139,7 @@ void ceph_messenger_destroy(struct ceph_messenger *msgr)
 	kfree(msgr);
 	dout("destroyed messenger %p\n", msgr);
 }
+EXPORT_SYMBOL(ceph_messenger_destroy);
 
 /*
  * Queue up an outgoing message on the given connection.
@@ -2011,6 +2176,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
 		queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_send);
 
 /*
  * Revoke a message that was previously queued for send
@@ -2076,6 +2242,7 @@ void ceph_con_keepalive(struct ceph_connection *con)
 	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
 		queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_keepalive);
 
 
 /*
@@ -2136,6 +2303,10 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
 	m->nr_pages = 0;
 	m->pages = NULL;
 	m->pagelist = NULL;
+	m->bio = NULL;
+	m->bio_iter = NULL;
+	m->bio_seg = 0;
+	m->trail = NULL;
 
 	dout("ceph_msg_new %p front %d\n", m, front_len);
 	return m;
@@ -2146,6 +2317,7 @@ out:
 	pr_err("msg_new can't create type %d front %d\n", type, front_len);
 	return NULL;
 }
+EXPORT_SYMBOL(ceph_msg_new);
 
 /*
  * Allocate "middle" portion of a message, if it is needed and wasn't
@@ -2250,11 +2422,14 @@ void ceph_msg_last_put(struct kref *kref)
 		m->pagelist = NULL;
 	}
 
+	m->trail = NULL;
+
 	if (m->pool)
 		ceph_msgpool_put(m->pool, m);
 	else
 		ceph_msg_kfree(m);
 }
+EXPORT_SYMBOL(ceph_msg_last_put);
 
 void ceph_msg_dump(struct ceph_msg *msg)
 {
@@ -2275,3 +2450,4 @@ void ceph_msg_dump(struct ceph_msg *msg)
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       &msg->footer, sizeof(msg->footer), true);
 }
+EXPORT_SYMBOL(ceph_msg_dump);
diff --git a/fs/ceph/mon_client.c b/net/ceph/mon_client.c
similarity index 94%
rename from fs/ceph/mon_client.c
rename to net/ceph/mon_client.c
index b2a5a3e4a671..8a079399174a 100644
--- a/fs/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1,14 +1,16 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/sched.h>
 
-#include "mon_client.h"
-#include "super.h"
-#include "auth.h"
-#include "decode.h"
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/ceph/auth.h>
 
 /*
  * Interact with Ceph monitor cluster.  Handle requests for new map
@@ -74,7 +76,7 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
 	     m->num_mon);
 	for (i = 0; i < m->num_mon; i++)
 		dout("monmap_decode  mon%d is %s\n", i,
-		     pr_addr(&m->mon_inst[i].addr.in_addr));
+		     ceph_pr_addr(&m->mon_inst[i].addr.in_addr));
 	return m;
 
 bad:
@@ -191,30 +193,33 @@ static void __send_subscribe(struct ceph_mon_client *monc)
 		struct ceph_msg *msg = monc->m_subscribe;
 		struct ceph_mon_subscribe_item *i;
 		void *p, *end;
+		int num;
 
 		p = msg->front.iov_base;
 		end = p + msg->front_max;
 
-		dout("__send_subscribe to 'mdsmap' %u+\n",
-		     (unsigned)monc->have_mdsmap);
+		num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
+		ceph_encode_32(&p, num);
+
 		if (monc->want_next_osdmap) {
 			dout("__send_subscribe to 'osdmap' %u\n",
 			     (unsigned)monc->have_osdmap);
-			ceph_encode_32(&p, 3);
 			ceph_encode_string(&p, end, "osdmap", 6);
 			i = p;
 			i->have = cpu_to_le64(monc->have_osdmap);
 			i->onetime = 1;
 			p += sizeof(*i);
 			monc->want_next_osdmap = 2;  /* requested */
-		} else {
-			ceph_encode_32(&p, 2);
 		}
-		ceph_encode_string(&p, end, "mdsmap", 6);
-		i = p;
-		i->have = cpu_to_le64(monc->have_mdsmap);
-		i->onetime = 0;
-		p += sizeof(*i);
+		if (monc->want_mdsmap) {
+			dout("__send_subscribe to 'mdsmap' %u+\n",
+			     (unsigned)monc->have_mdsmap);
+			ceph_encode_string(&p, end, "mdsmap", 6);
+			i = p;
+			i->have = cpu_to_le64(monc->have_mdsmap);
+			i->onetime = 0;
+			p += sizeof(*i);
+		}
 		ceph_encode_string(&p, end, "monmap", 6);
 		i = p;
 		i->have = 0;
@@ -243,7 +248,8 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc,
 	mutex_lock(&monc->mutex);
 	if (monc->hunting) {
 		pr_info("mon%d %s session established\n",
-			monc->cur_mon, pr_addr(&monc->con->peer_addr.in_addr));
+			monc->cur_mon,
+			ceph_pr_addr(&monc->con->peer_addr.in_addr));
 		monc->hunting = false;
 	}
 	dout("handle_subscribe_ack after %d seconds\n", seconds);
@@ -266,6 +272,7 @@ int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got)
 	mutex_unlock(&monc->mutex);
 	return 0;
 }
+EXPORT_SYMBOL(ceph_monc_got_mdsmap);
 
 int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got)
 {
@@ -310,6 +317,7 @@ int ceph_monc_open_session(struct ceph_mon_client *monc)
 	mutex_unlock(&monc->mutex);
 	return 0;
 }
+EXPORT_SYMBOL(ceph_monc_open_session);
 
 /*
  * The monitor responds with mount ack indicate mount success.  The
@@ -540,6 +548,7 @@ out:
 	kref_put(&req->kref, release_generic_request);
 	return err;
 }
+EXPORT_SYMBOL(ceph_monc_do_statfs);
 
 /*
  * pool ops
@@ -651,6 +660,7 @@ int ceph_monc_create_snapid(struct ceph_mon_client *monc,
 				   pool, 0, (char *)snapid, sizeof(*snapid));
 
 }
+EXPORT_SYMBOL(ceph_monc_create_snapid);
 
 int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
 			    u32 pool, u64 snapid)
@@ -708,9 +718,9 @@ static void delayed_work(struct work_struct *work)
  */
 static int build_initial_monmap(struct ceph_mon_client *monc)
 {
-	struct ceph_mount_args *args = monc->client->mount_args;
-	struct ceph_entity_addr *mon_addr = args->mon_addr;
-	int num_mon = args->num_mon;
+	struct ceph_options *opt = monc->client->options;
+	struct ceph_entity_addr *mon_addr = opt->mon_addr;
+	int num_mon = opt->num_mon;
 	int i;
 
 	/* build initial monmap */
@@ -728,11 +738,6 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
 	}
 	monc->monmap->num_mon = num_mon;
 	monc->have_fsid = false;
-
-	/* release addr memory */
-	kfree(args->mon_addr);
-	args->mon_addr = NULL;
-	args->num_mon = 0;
 	return 0;
 }
 
@@ -753,8 +758,8 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 	monc->con = NULL;
 
 	/* authentication */
-	monc->auth = ceph_auth_init(cl->mount_args->name,
-				    cl->mount_args->secret);
+	monc->auth = ceph_auth_init(cl->options->name,
+				    cl->options->secret);
 	if (IS_ERR(monc->auth))
 		return PTR_ERR(monc->auth);
 	monc->auth->want_keys =
@@ -808,6 +813,7 @@ out_monmap:
 out:
 	return err;
 }
+EXPORT_SYMBOL(ceph_monc_init);
 
 void ceph_monc_stop(struct ceph_mon_client *monc)
 {
@@ -832,6 +838,7 @@ void ceph_monc_stop(struct ceph_mon_client *monc)
 
 	kfree(monc->monmap);
 }
+EXPORT_SYMBOL(ceph_monc_stop);
 
 static void handle_auth_reply(struct ceph_mon_client *monc,
 			      struct ceph_msg *msg)
@@ -889,6 +896,7 @@ int ceph_monc_validate_auth(struct ceph_mon_client *monc)
 	mutex_unlock(&monc->mutex);
 	return ret;
 }
+EXPORT_SYMBOL(ceph_monc_validate_auth);
 
 /*
  * handle incoming message
@@ -922,15 +930,16 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		ceph_monc_handle_map(monc, msg);
 		break;
 
-	case CEPH_MSG_MDS_MAP:
-		ceph_mdsc_handle_map(&monc->client->mdsc, msg);
-		break;
-
 	case CEPH_MSG_OSD_MAP:
 		ceph_osdc_handle_map(&monc->client->osdc, msg);
 		break;
 
 	default:
+		/* can the chained handler handle it? */
+		if (monc->client->extra_mon_dispatch &&
+		    monc->client->extra_mon_dispatch(monc->client, msg) == 0)
+			break;
+			
 		pr_err("received unknown message type %d %s\n", type,
 		       ceph_msg_type_name(type));
 	}
@@ -994,7 +1003,7 @@ static void mon_fault(struct ceph_connection *con)
 	if (monc->con && !monc->hunting)
 		pr_info("mon%d %s session lost, "
 			"hunting for new mon\n", monc->cur_mon,
-			pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con->peer_addr.in_addr));
 
 	__close_session(monc);
 	if (!monc->hunting) {
diff --git a/fs/ceph/msgpool.c b/net/ceph/msgpool.c
similarity index 95%
rename from fs/ceph/msgpool.c
rename to net/ceph/msgpool.c
index dd65a6438131..d5f2d97ac05c 100644
--- a/fs/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -1,11 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
-#include "msgpool.h"
+#include <linux/ceph/msgpool.h>
 
 static void *alloc_fn(gfp_t gfp_mask, void *arg)
 {
diff --git a/fs/ceph/osd_client.c b/net/ceph/osd_client.c
similarity index 84%
rename from fs/ceph/osd_client.c
rename to net/ceph/osd_client.c
index dfced1dacbcd..79391994b3ed 100644
--- a/fs/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1,17 +1,22 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#ifdef CONFIG_BLOCK
+#include <linux/bio.h>
+#endif
 
-#include "super.h"
-#include "osd_client.h"
-#include "messenger.h"
-#include "decode.h"
-#include "auth.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/pagelist.h>
 
 #define OSD_OP_FRONT_LEN	4096
 #define OSD_OPREPLY_FRONT_LEN	512
@@ -22,6 +27,59 @@ static int __kick_requests(struct ceph_osd_client *osdc,
 
 static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd);
 
+static int op_needs_trail(int op)
+{
+	switch (op) {
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+	case CEPH_OSD_OP_CALL:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static int op_has_extent(int op)
+{
+	return (op == CEPH_OSD_OP_READ ||
+		op == CEPH_OSD_OP_WRITE);
+}
+
+void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+			struct ceph_file_layout *layout,
+			u64 snapid,
+			u64 off, u64 *plen, u64 *bno,
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op)
+{
+	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
+	u64 orig_len = *plen;
+	u64 objoff, objlen;    /* extent in object */
+
+	reqhead->snapid = cpu_to_le64(snapid);
+
+	/* object extent? */
+	ceph_calc_file_object_mapping(layout, off, plen, bno,
+				      &objoff, &objlen);
+	if (*plen < orig_len)
+		dout(" skipping last %llu, final file extent %llu~%llu\n",
+		     orig_len - *plen, off, *plen);
+
+	if (op_has_extent(op->op)) {
+		op->extent.offset = objoff;
+		op->extent.length = objlen;
+	}
+	req->r_num_pages = calc_pages_for(off, *plen);
+	if (op->op == CEPH_OSD_OP_WRITE)
+		op->payload_len = *plen;
+
+	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
+	     *bno, objoff, objlen, req->r_num_pages);
+
+}
+EXPORT_SYMBOL(ceph_calc_raw_layout);
+
 /*
  * Implement client access to distributed object storage cluster.
  *
@@ -48,34 +106,19 @@ static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd);
  * fill osd op in request message.
  */
 static void calc_layout(struct ceph_osd_client *osdc,
-			struct ceph_vino vino, struct ceph_file_layout *layout,
+			struct ceph_vino vino,
+			struct ceph_file_layout *layout,
 			u64 off, u64 *plen,
-			struct ceph_osd_request *req)
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op)
 {
-	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
-	struct ceph_osd_op *op = (void *)(reqhead + 1);
-	u64 orig_len = *plen;
-	u64 objoff, objlen;    /* extent in object */
 	u64 bno;
 
-	reqhead->snapid = cpu_to_le64(vino.snap);
-
-	/* object extent? */
-	ceph_calc_file_object_mapping(layout, off, plen, &bno,
-				      &objoff, &objlen);
-	if (*plen < orig_len)
-		dout(" skipping last %llu, final file extent %llu~%llu\n",
-		     orig_len - *plen, off, *plen);
+	ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+			     plen, &bno, req, op);
 
 	sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno);
 	req->r_oid_len = strlen(req->r_oid);
-
-	op->extent.offset = cpu_to_le64(objoff);
-	op->extent.length = cpu_to_le64(objlen);
-	req->r_num_pages = calc_pages_for(off, *plen);
-
-	dout("calc_layout %s (%d) %llu~%llu (%d pages)\n",
-	     req->r_oid, req->r_oid_len, objoff, objlen, req->r_num_pages);
 }
 
 /*
@@ -101,56 +144,66 @@ void ceph_osdc_release_request(struct kref *kref)
 	if (req->r_own_pages)
 		ceph_release_page_vector(req->r_pages,
 					 req->r_num_pages);
+#ifdef CONFIG_BLOCK
+	if (req->r_bio)
+		bio_put(req->r_bio);
+#endif
 	ceph_put_snap_context(req->r_snapc);
+	if (req->r_trail) {
+		ceph_pagelist_release(req->r_trail);
+		kfree(req->r_trail);
+	}
 	if (req->r_mempool)
 		mempool_free(req, req->r_osdc->req_mempool);
 	else
 		kfree(req);
 }
+EXPORT_SYMBOL(ceph_osdc_release_request);
 
-/*
- * build new request AND message, calculate layout, and adjust file
- * extent as needed.
- *
- * if the file was recently truncated, we include information about its
- * old and new size so that the object can be updated appropriately.  (we
- * avoid synchronously deleting truncated objects because it's slow.)
- *
- * if @do_sync, include a 'startsync' command so that the osd will flush
- * data quickly.
- */
-struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
-					       struct ceph_file_layout *layout,
-					       struct ceph_vino vino,
-					       u64 off, u64 *plen,
-					       int opcode, int flags,
+static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail)
+{
+	int i = 0;
+
+	if (needs_trail)
+		*needs_trail = 0;
+	while (ops[i].op) {
+		if (needs_trail && op_needs_trail(ops[i].op))
+			*needs_trail = 1;
+		i++;
+	}
+
+	return i;
+}
+
+struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+					       int flags,
 					       struct ceph_snap_context *snapc,
-					       int do_sync,
-					       u32 truncate_seq,
-					       u64 truncate_size,
-					       struct timespec *mtime,
-					       bool use_mempool, int num_reply)
+					       struct ceph_osd_req_op *ops,
+					       bool use_mempool,
+					       gfp_t gfp_flags,
+					       struct page **pages,
+					       struct bio *bio)
 {
 	struct ceph_osd_request *req;
 	struct ceph_msg *msg;
-	struct ceph_osd_request_head *head;
-	struct ceph_osd_op *op;
-	void *p;
-	int num_op = 1 + do_sync;
-	size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
-	int i;
+	int needs_trail;
+	int num_op = get_num_ops(ops, &needs_trail);
+	size_t msg_size = sizeof(struct ceph_osd_request_head);
+
+	msg_size += num_op*sizeof(struct ceph_osd_op);
 
 	if (use_mempool) {
-		req = mempool_alloc(osdc->req_mempool, GFP_NOFS);
+		req = mempool_alloc(osdc->req_mempool, gfp_flags);
 		memset(req, 0, sizeof(*req));
 	} else {
-		req = kzalloc(sizeof(*req), GFP_NOFS);
+		req = kzalloc(sizeof(*req), gfp_flags);
 	}
 	if (req == NULL)
 		return NULL;
 
 	req->r_osdc = osdc;
 	req->r_mempool = use_mempool;
+
 	kref_init(&req->r_kref);
 	init_completion(&req->r_completion);
 	init_completion(&req->r_safe_completion);
@@ -164,13 +217,22 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
 	else
 		msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
-				   OSD_OPREPLY_FRONT_LEN, GFP_NOFS);
+				   OSD_OPREPLY_FRONT_LEN, gfp_flags);
 	if (!msg) {
 		ceph_osdc_put_request(req);
 		return NULL;
 	}
 	req->r_reply = msg;
 
+	/* allocate space for the trailing data */
+	if (needs_trail) {
+		req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags);
+		if (!req->r_trail) {
+			ceph_osdc_put_request(req);
+			return NULL;
+		}
+		ceph_pagelist_init(req->r_trail);
+	}
 	/* create request message; allow space for oid */
 	msg_size += 40;
 	if (snapc)
@@ -178,18 +240,115 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (use_mempool)
 		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
 	else
-		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, GFP_NOFS);
+		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags);
 	if (!msg) {
 		ceph_osdc_put_request(req);
 		return NULL;
 	}
+
 	msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
 	memset(msg->front.iov_base, 0, msg->front.iov_len);
+
+	req->r_request = msg;
+	req->r_pages = pages;
+#ifdef CONFIG_BLOCK
+	if (bio) {
+		req->r_bio = bio;
+		bio_get(req->r_bio);
+	}
+#endif
+
+	return req;
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_request);
+
+static void osd_req_encode_op(struct ceph_osd_request *req,
+			      struct ceph_osd_op *dst,
+			      struct ceph_osd_req_op *src)
+{
+	dst->op = cpu_to_le16(src->op);
+
+	switch (dst->op) {
+	case CEPH_OSD_OP_READ:
+	case CEPH_OSD_OP_WRITE:
+		dst->extent.offset =
+			cpu_to_le64(src->extent.offset);
+		dst->extent.length =
+			cpu_to_le64(src->extent.length);
+		dst->extent.truncate_size =
+			cpu_to_le64(src->extent.truncate_size);
+		dst->extent.truncate_seq =
+			cpu_to_le32(src->extent.truncate_seq);
+		break;
+
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		BUG_ON(!req->r_trail);
+
+		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+		dst->xattr.cmp_op = src->xattr.cmp_op;
+		dst->xattr.cmp_mode = src->xattr.cmp_mode;
+		ceph_pagelist_append(req->r_trail, src->xattr.name,
+				     src->xattr.name_len);
+		ceph_pagelist_append(req->r_trail, src->xattr.val,
+				     src->xattr.value_len);
+		break;
+	case CEPH_OSD_OP_CALL:
+		BUG_ON(!req->r_trail);
+
+		dst->cls.class_len = src->cls.class_len;
+		dst->cls.method_len = src->cls.method_len;
+		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
+
+		ceph_pagelist_append(req->r_trail, src->cls.class_name,
+				     src->cls.class_len);
+		ceph_pagelist_append(req->r_trail, src->cls.method_name,
+				     src->cls.method_len);
+		ceph_pagelist_append(req->r_trail, src->cls.indata,
+				     src->cls.indata_len);
+		break;
+	case CEPH_OSD_OP_ROLLBACK:
+		dst->snap.snapid = cpu_to_le64(src->snap.snapid);
+		break;
+	case CEPH_OSD_OP_STARTSYNC:
+		break;
+	default:
+		pr_err("unrecognized osd opcode %d\n", dst->op);
+		WARN_ON(1);
+		break;
+	}
+	dst->payload_len = cpu_to_le32(src->payload_len);
+}
+
+/*
+ * build new request AND message
+ *
+ */
+void ceph_osdc_build_request(struct ceph_osd_request *req,
+			     u64 off, u64 *plen,
+			     struct ceph_osd_req_op *src_ops,
+			     struct ceph_snap_context *snapc,
+			     struct timespec *mtime,
+			     const char *oid,
+			     int oid_len)
+{
+	struct ceph_msg *msg = req->r_request;
+	struct ceph_osd_request_head *head;
+	struct ceph_osd_req_op *src_op;
+	struct ceph_osd_op *op;
+	void *p;
+	int num_op = get_num_ops(src_ops, NULL);
+	size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
+	int flags = req->r_flags;
+	u64 data_len = 0;
+	int i;
+
 	head = msg->front.iov_base;
 	op = (void *)(head + 1);
 	p = (void *)(op + num_op);
 
-	req->r_request = msg;
 	req->r_snapc = ceph_get_snap_context(snapc);
 
 	head->client_inc = cpu_to_le32(1); /* always, for now. */
@@ -197,29 +356,23 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (flags & CEPH_OSD_FLAG_WRITE)
 		ceph_encode_timespec(&head->mtime, mtime);
 	head->num_ops = cpu_to_le16(num_op);
-	op->op = cpu_to_le16(opcode);
 
-	/* calculate max write size */
-	calc_layout(osdc, vino, layout, off, plen, req);
-	req->r_file_layout = *layout;  /* keep a copy */
-
-	if (flags & CEPH_OSD_FLAG_WRITE) {
-		req->r_request->hdr.data_off = cpu_to_le16(off);
-		req->r_request->hdr.data_len = cpu_to_le32(*plen);
-		op->payload_len = cpu_to_le32(*plen);
-	}
-	op->extent.truncate_size = cpu_to_le64(truncate_size);
-	op->extent.truncate_seq = cpu_to_le32(truncate_seq);
 
 	/* fill in oid */
-	head->object_len = cpu_to_le32(req->r_oid_len);
-	memcpy(p, req->r_oid, req->r_oid_len);
-	p += req->r_oid_len;
-
-	if (do_sync) {
+	head->object_len = cpu_to_le32(oid_len);
+	memcpy(p, oid, oid_len);
+	p += oid_len;
+
+	src_op = src_ops;
+	while (src_op->op) {
+		osd_req_encode_op(req, op, src_op);
+		src_op++;
 		op++;
-		op->op = cpu_to_le16(CEPH_OSD_OP_STARTSYNC);
 	}
+
+	if (req->r_trail)
+		data_len += req->r_trail->length;
+
 	if (snapc) {
 		head->snap_seq = cpu_to_le64(snapc->seq);
 		head->num_snaps = cpu_to_le32(snapc->num_snaps);
@@ -229,12 +382,79 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 		}
 	}
 
+	if (flags & CEPH_OSD_FLAG_WRITE) {
+		req->r_request->hdr.data_off = cpu_to_le16(off);
+		req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len);
+	} else if (data_len) {
+		req->r_request->hdr.data_off = 0;
+		req->r_request->hdr.data_len = cpu_to_le32(data_len);
+	}
+
 	BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
 	msg_size = p - msg->front.iov_base;
 	msg->front.iov_len = msg_size;
 	msg->hdr.front_len = cpu_to_le32(msg_size);
+	return;
+}
+EXPORT_SYMBOL(ceph_osdc_build_request);
+
+/*
+ * build new request AND message, calculate layout, and adjust file
+ * extent as needed.
+ *
+ * if the file was recently truncated, we include information about its
+ * old and new size so that the object can be updated appropriately.  (we
+ * avoid synchronously deleting truncated objects because it's slow.)
+ *
+ * if @do_sync, include a 'startsync' command so that the osd will flush
+ * data quickly.
+ */
+struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
+					       struct ceph_file_layout *layout,
+					       struct ceph_vino vino,
+					       u64 off, u64 *plen,
+					       int opcode, int flags,
+					       struct ceph_snap_context *snapc,
+					       int do_sync,
+					       u32 truncate_seq,
+					       u64 truncate_size,
+					       struct timespec *mtime,
+					       bool use_mempool, int num_reply)
+{
+	struct ceph_osd_req_op ops[3];
+	struct ceph_osd_request *req;
+
+	ops[0].op = opcode;
+	ops[0].extent.truncate_seq = truncate_seq;
+	ops[0].extent.truncate_size = truncate_size;
+	ops[0].payload_len = 0;
+
+	if (do_sync) {
+		ops[1].op = CEPH_OSD_OP_STARTSYNC;
+		ops[1].payload_len = 0;
+		ops[2].op = 0;
+	} else
+		ops[1].op = 0;
+
+	req = ceph_osdc_alloc_request(osdc, flags,
+					 snapc, ops,
+					 use_mempool,
+					 GFP_NOFS, NULL, NULL);
+	if (IS_ERR(req))
+		return req;
+
+	/* calculate max write size */
+	calc_layout(osdc, vino, layout, off, plen, req, ops);
+	req->r_file_layout = *layout;  /* keep a copy */
+
+	ceph_osdc_build_request(req, off, plen, ops,
+				snapc,
+				mtime,
+				req->r_oid, req->r_oid_len);
+
 	return req;
 }
+EXPORT_SYMBOL(ceph_osdc_new_request);
 
 /*
  * We keep osd requests in an rbtree, sorted by ->r_tid.
@@ -389,7 +609,7 @@ static void __move_osd_to_lru(struct ceph_osd_client *osdc,
 	dout("__move_osd_to_lru %p\n", osd);
 	BUG_ON(!list_empty(&osd->o_osd_lru));
 	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
-	osd->lru_ttl = jiffies + osdc->client->mount_args->osd_idle_ttl * HZ;
+	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl * HZ;
 }
 
 static void __remove_osd_from_lru(struct ceph_osd *osd)
@@ -483,7 +703,7 @@ static struct ceph_osd *__lookup_osd(struct ceph_osd_client *osdc, int o)
 static void __schedule_osd_timeout(struct ceph_osd_client *osdc)
 {
 	schedule_delayed_work(&osdc->timeout_work,
-			osdc->client->mount_args->osd_keepalive_timeout * HZ);
+			osdc->client->options->osd_keepalive_timeout * HZ);
 }
 
 static void __cancel_osd_timeout(struct ceph_osd_client *osdc)
@@ -549,7 +769,7 @@ static void __unregister_request(struct ceph_osd_client *osdc,
  */
 static void __cancel_request(struct ceph_osd_request *req)
 {
-	if (req->r_sent) {
+	if (req->r_sent && req->r_osd) {
 		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
 		req->r_sent = 0;
 	}
@@ -684,9 +904,9 @@ static void handle_timeout(struct work_struct *work)
 		container_of(work, struct ceph_osd_client, timeout_work.work);
 	struct ceph_osd_request *req, *last_req = NULL;
 	struct ceph_osd *osd;
-	unsigned long timeout = osdc->client->mount_args->osd_timeout * HZ;
+	unsigned long timeout = osdc->client->options->osd_timeout * HZ;
 	unsigned long keepalive =
-		osdc->client->mount_args->osd_keepalive_timeout * HZ;
+		osdc->client->options->osd_keepalive_timeout * HZ;
 	unsigned long last_stamp = 0;
 	struct rb_node *p;
 	struct list_head slow_osds;
@@ -773,7 +993,7 @@ static void handle_osds_timeout(struct work_struct *work)
 		container_of(work, struct ceph_osd_client,
 			     osds_timeout_work.work);
 	unsigned long delay =
-		osdc->client->mount_args->osd_idle_ttl * HZ >> 2;
+		osdc->client->options->osd_idle_ttl * HZ >> 2;
 
 	dout("osds timeout\n");
 	down_read(&osdc->map_sem);
@@ -1104,6 +1324,10 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 
 	req->r_request->pages = req->r_pages;
 	req->r_request->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+	req->r_request->bio = req->r_bio;
+#endif
+	req->r_request->trail = req->r_trail;
 
 	register_request(osdc, req);
 
@@ -1131,6 +1355,7 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 	up_read(&osdc->map_sem);
 	return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_start_request);
 
 /*
  * wait for a request to complete
@@ -1153,6 +1378,7 @@ int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
 	dout("wait_request tid %llu result %d\n", req->r_tid, req->r_result);
 	return req->r_result;
 }
+EXPORT_SYMBOL(ceph_osdc_wait_request);
 
 /*
  * sync - wait for all in-flight requests to flush.  avoid starvation.
@@ -1186,6 +1412,7 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc)
 	mutex_unlock(&osdc->request_mutex);
 	dout("sync done (thru tid %llu)\n", last_tid);
 }
+EXPORT_SYMBOL(ceph_osdc_sync);
 
 /*
  * init, shutdown
@@ -1211,7 +1438,7 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
 	INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);
 
 	schedule_delayed_work(&osdc->osds_timeout_work,
-	   round_jiffies_relative(osdc->client->mount_args->osd_idle_ttl * HZ));
+	   round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ));
 
 	err = -ENOMEM;
 	osdc->req_mempool = mempool_create_kmalloc_pool(10,
@@ -1237,6 +1464,7 @@ out_mempool:
 out:
 	return err;
 }
+EXPORT_SYMBOL(ceph_osdc_init);
 
 void ceph_osdc_stop(struct ceph_osd_client *osdc)
 {
@@ -1251,6 +1479,7 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc)
 	ceph_msgpool_destroy(&osdc->msgpool_op);
 	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 }
+EXPORT_SYMBOL(ceph_osdc_stop);
 
 /*
  * Read some contiguous pages.  If we cross a stripe boundary, shorten
@@ -1288,6 +1517,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 	dout("readpages result %d\n", rc);
 	return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_readpages);
 
 /*
  * do a synchronous write on N pages
@@ -1330,6 +1560,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 	dout("writepages result %d\n", rc);
 	return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_writepages);
 
 /*
  * handle incoming message
@@ -1420,6 +1651,9 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 		}
 		m->pages = req->r_pages;
 		m->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+		m->bio = req->r_bio;
+#endif
 	}
 	*skip = 0;
 	req->r_con_filling_msg = ceph_con_get(con);
diff --git a/fs/ceph/osdmap.c b/net/ceph/osdmap.c
similarity index 97%
rename from fs/ceph/osdmap.c
rename to net/ceph/osdmap.c
index e31f118f1392..d73f3f6efa36 100644
--- a/fs/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1,14 +1,15 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/div64.h>
 
-#include "super.h"
-#include "osdmap.h"
-#include "crush/hash.h"
-#include "crush/mapper.h"
-#include "decode.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osdmap.h>
+#include <linux/ceph/decode.h>
+#include <linux/crush/hash.h>
+#include <linux/crush/mapper.h>
 
 char *ceph_osdmap_state_str(char *str, int len, int state)
 {
@@ -417,6 +418,20 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
 	return NULL;
 }
 
+int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
+{
+	struct rb_node *rbp;
+
+	for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rbp, struct ceph_pg_pool_info, node);
+		if (pi->name && strcmp(pi->name, name) == 0)
+			return pi->id;
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL(ceph_pg_poolid_by_name);
+
 static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
 {
 	rb_erase(&pi->node, root);
@@ -966,6 +981,7 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 
 	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
 }
+EXPORT_SYMBOL(ceph_calc_file_object_mapping);
 
 /*
  * calculate an object layout (i.e. pgid) from an oid,
@@ -1011,6 +1027,7 @@ int ceph_calc_object_layout(struct ceph_object_layout *ol,
 	ol->ol_stripe_unit = fl->fl_object_stripe_unit;
 	return 0;
 }
+EXPORT_SYMBOL(ceph_calc_object_layout);
 
 /*
  * Calculate raw osd vector for the given pgid.  Return pointer to osd
@@ -1108,3 +1125,4 @@ int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
 			return osds[i];
 	return -1;
 }
+EXPORT_SYMBOL(ceph_calc_pg_primary);
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
new file mode 100644
index 000000000000..13cb409a7bba
--- /dev/null
+++ b/net/ceph/pagelist.c
@@ -0,0 +1,154 @@
+
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/ceph/pagelist.h>
+
+static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
+{
+	if (pl->mapped_tail) {
+		struct page *page = list_entry(pl->head.prev, struct page, lru);
+		kunmap(page);
+		pl->mapped_tail = NULL;
+	}
+}
+
+int ceph_pagelist_release(struct ceph_pagelist *pl)
+{
+	ceph_pagelist_unmap_tail(pl);
+	while (!list_empty(&pl->head)) {
+		struct page *page = list_first_entry(&pl->head, struct page,
+						     lru);
+		list_del(&page->lru);
+		__free_page(page);
+	}
+	ceph_pagelist_free_reserve(pl);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_release);
+
+static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
+{
+	struct page *page;
+
+	if (!pl->num_pages_free) {
+		page = __page_cache_alloc(GFP_NOFS);
+	} else {
+		page = list_first_entry(&pl->free_list, struct page, lru);
+		list_del(&page->lru);
+		--pl->num_pages_free;
+	}
+	if (!page)
+		return -ENOMEM;
+	pl->room += PAGE_SIZE;
+	ceph_pagelist_unmap_tail(pl);
+	list_add_tail(&page->lru, &pl->head);
+	pl->mapped_tail = kmap(page);
+	return 0;
+}
+
+int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len)
+{
+	while (pl->room < len) {
+		size_t bit = pl->room;
+		int ret;
+
+		memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
+		       buf, bit);
+		pl->length += bit;
+		pl->room -= bit;
+		buf += bit;
+		len -= bit;
+		ret = ceph_pagelist_addpage(pl);
+		if (ret)
+			return ret;
+	}
+
+	memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
+	pl->length += len;
+	pl->room -= len;
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_append);
+
+/**
+ * Allocate enough pages for a pagelist to append the given amount
+ * of data without without allocating.
+ * Returns: 0 on success, -ENOMEM on error.
+ */
+int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space)
+{
+	if (space <= pl->room)
+		return 0;
+	space -= pl->room;
+	space = (space + PAGE_SIZE - 1) >> PAGE_SHIFT;   /* conv to num pages */
+
+	while (space > pl->num_pages_free) {
+		struct page *page = __page_cache_alloc(GFP_NOFS);
+		if (!page)
+			return -ENOMEM;
+		list_add_tail(&page->lru, &pl->free_list);
+		++pl->num_pages_free;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_reserve);
+
+/**
+ * Free any pages that have been preallocated.
+ */
+int ceph_pagelist_free_reserve(struct ceph_pagelist *pl)
+{
+	while (!list_empty(&pl->free_list)) {
+		struct page *page = list_first_entry(&pl->free_list,
+						     struct page, lru);
+		list_del(&page->lru);
+		__free_page(page);
+		--pl->num_pages_free;
+	}
+	BUG_ON(pl->num_pages_free);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_free_reserve);
+
+/**
+ * Create a truncation point.
+ */
+void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+			      struct ceph_pagelist_cursor *c)
+{
+	c->pl = pl;
+	c->page_lru = pl->head.prev;
+	c->room = pl->room;
+}
+EXPORT_SYMBOL(ceph_pagelist_set_cursor);
+
+/**
+ * Truncate a pagelist to the given point. Move extra pages to reserve.
+ * This won't sleep.
+ * Returns: 0 on success,
+ *          -EINVAL if the pagelist doesn't match the trunc point pagelist
+ */
+int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+			   struct ceph_pagelist_cursor *c)
+{
+	struct page *page;
+
+	if (pl != c->pl)
+		return -EINVAL;
+	ceph_pagelist_unmap_tail(pl);
+	while (pl->head.prev != c->page_lru) {
+		page = list_entry(pl->head.prev, struct page, lru);
+		list_del(&page->lru);                /* remove from pagelist */
+		list_add_tail(&page->lru, &pl->free_list); /* add to reserve */
+		++pl->num_pages_free;
+	}
+	pl->room = c->room;
+	if (!list_empty(&pl->head)) {
+		page = list_entry(pl->head.prev, struct page, lru);
+		pl->mapped_tail = kmap(page);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_truncate);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
new file mode 100644
index 000000000000..54caf0687155
--- /dev/null
+++ b/net/ceph/pagevec.c
@@ -0,0 +1,223 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/writeback.h>
+
+#include <linux/ceph/libceph.h>
+
+/*
+ * build a vector of user pages
+ */
+struct page **ceph_get_direct_page_vector(const char __user *data,
+						 int num_pages,
+						 loff_t off, size_t len)
+{
+	struct page **pages;
+	int rc;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	down_read(&current->mm->mmap_sem);
+	rc = get_user_pages(current, current->mm, (unsigned long)data,
+			    num_pages, 0, 0, pages, NULL);
+	up_read(&current->mm->mmap_sem);
+	if (rc < 0)
+		goto fail;
+	return pages;
+
+fail:
+	kfree(pages);
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL(ceph_get_direct_page_vector);
+
+void ceph_put_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+	kfree(pages);
+}
+EXPORT_SYMBOL(ceph_put_page_vector);
+
+void ceph_release_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		__free_pages(pages[i], 0);
+	kfree(pages);
+}
+EXPORT_SYMBOL(ceph_release_page_vector);
+
+/*
+ * allocate a vector new pages
+ */
+struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
+{
+	struct page **pages;
+	int i;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, flags);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = __page_cache_alloc(flags);
+		if (pages[i] == NULL) {
+			ceph_release_page_vector(pages, i);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+	return pages;
+}
+EXPORT_SYMBOL(ceph_alloc_page_vector);
+
+/*
+ * copy user data into a page vector
+ */
+int ceph_copy_user_to_page_vector(struct page **pages,
+					 const char __user *data,
+					 loff_t off, size_t len)
+{
+	int i = 0;
+	int po = off & ~PAGE_CACHE_MASK;
+	int left = len;
+	int l, bad;
+
+	while (left > 0) {
+		l = min_t(int, PAGE_CACHE_SIZE-po, left);
+		bad = copy_from_user(page_address(pages[i]) + po, data, l);
+		if (bad == l)
+			return -EFAULT;
+		data += l - bad;
+		left -= l - bad;
+		po += l - bad;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_user_to_page_vector);
+
+int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	size_t po = off & ~PAGE_CACHE_MASK;
+	size_t left = len;
+	size_t l;
+
+	while (left > 0) {
+		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		memcpy(page_address(pages[i]) + po, data, l);
+		data += l;
+		left -= l;
+		po += l;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_to_page_vector);
+
+int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	size_t po = off & ~PAGE_CACHE_MASK;
+	size_t left = len;
+	size_t l;
+
+	while (left > 0) {
+		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		memcpy(data, page_address(pages[i]) + po, l);
+		data += l;
+		left -= l;
+		po += l;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_from_page_vector);
+
+/*
+ * copy user data from a page vector into a user pointer
+ */
+int ceph_copy_page_vector_to_user(struct page **pages,
+					 char __user *data,
+					 loff_t off, size_t len)
+{
+	int i = 0;
+	int po = off & ~PAGE_CACHE_MASK;
+	int left = len;
+	int l, bad;
+
+	while (left > 0) {
+		l = min_t(int, left, PAGE_CACHE_SIZE-po);
+		bad = copy_to_user(data, page_address(pages[i]) + po, l);
+		if (bad == l)
+			return -EFAULT;
+		data += l - bad;
+		left -= l - bad;
+		if (po) {
+			po += l - bad;
+			if (po == PAGE_CACHE_SIZE)
+				po = 0;
+		}
+		i++;
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_page_vector_to_user);
+
+/*
+ * Zero an extent within a page vector.  Offset is relative to the
+ * start of the first page.
+ */
+void ceph_zero_page_vector_range(int off, int len, struct page **pages)
+{
+	int i = off >> PAGE_CACHE_SHIFT;
+
+	off &= ~PAGE_CACHE_MASK;
+
+	dout("zero_page_vector_page %u~%u\n", off, len);
+
+	/* leading partial page? */
+	if (off) {
+		int end = min((int)PAGE_CACHE_SIZE, off + len);
+		dout("zeroing %d %p head from %d\n", i, pages[i],
+		     (int)off);
+		zero_user_segment(pages[i], off, end);
+		len -= (end - off);
+		i++;
+	}
+	while (len >= PAGE_CACHE_SIZE) {
+		dout("zeroing %d %p len=%d\n", i, pages[i], len);
+		zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
+		len -= PAGE_CACHE_SIZE;
+		i++;
+	}
+	/* trailing partial page? */
+	if (len) {
+		dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
+		zero_user_segment(pages[i], 0, len);
+	}
+}
+EXPORT_SYMBOL(ceph_zero_page_vector_range);
+
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 7a85367b3c2f..8451ab481095 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -348,7 +348,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 	if (info.cmd == ETHTOOL_GRXCLSRLALL) {
 		if (info.rule_cnt > 0) {
 			if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32))
-				rule_buf = kmalloc(info.rule_cnt * sizeof(u32),
+				rule_buf = kzalloc(info.rule_cnt * sizeof(u32),
 						   GFP_USER);
 			if (!rule_buf)
 				return -ENOMEM;
@@ -397,7 +397,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	    (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index))
 		return -ENOMEM;
 	full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size;
-	indir = kmalloc(full_size, GFP_USER);
+	indir = kzalloc(full_size, GFP_USER);
 	if (!indir)
 		return -ENOMEM;
 
@@ -538,7 +538,7 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr)
 
 	gstrings.len = ret;
 
-	data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+	data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
 	if (!data)
 		return -ENOMEM;
 
@@ -775,7 +775,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 	if (regs.len > reglen)
 		regs.len = reglen;
 
-	regbuf = kmalloc(reglen, GFP_USER);
+	regbuf = kzalloc(reglen, GFP_USER);
 	if (!regbuf)
 		return -ENOMEM;
 
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 1cd98df412df..e6b133b77ccb 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -35,9 +35,10 @@
  *	in any case.
  */
 
-int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode)
+long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode)
 {
-	int size, err, ct;
+	int size, ct;
+	long err;
 
 	if (m->msg_namelen) {
 		if (mode == VERIFY_READ) {
diff --git a/net/core/sock.c b/net/core/sock.c
index b05b9b6ddb87..ef30e9d286e7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk)
 {
 	int uid;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 	return uid;
 }
 EXPORT_SYMBOL(sock_i_uid);
@@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk)
 {
 	unsigned long ino;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 	return ino;
 }
 EXPORT_SYMBOL(sock_i_ino);
diff --git a/net/core/stream.c b/net/core/stream.c
index d959e0f41528..f5df85dcd20b 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -141,10 +141,10 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk->sk_write_pending++;
-		sk_wait_event(sk, &current_timeo, !sk->sk_err &&
-						  !(sk->sk_shutdown & SEND_SHUTDOWN) &&
-						  sk_stream_memory_free(sk) &&
-						  vm_wait);
+		sk_wait_event(sk, &current_timeo, sk->sk_err ||
+						  (sk->sk_shutdown & SEND_SHUTDOWN) ||
+						  (sk_stream_memory_free(sk) &&
+						  !vm_wait));
 		sk->sk_write_pending--;
 
 		if (vm_wait) {
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 571f8950ed06..7cd7760144f7 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -217,6 +217,7 @@ config NET_IPIP
 
 config NET_IPGRE
 	tristate "IP: GRE tunnels over IP"
+	depends on IPV6 || IPV6=n
 	help
 	  Tunneling means encapsulating data of one protocol type within
 	  another protocol and sending it over a channel that understands the
@@ -412,7 +413,7 @@ config INET_XFRM_MODE_BEET
 	  If unsure, say Y.
 
 config INET_LRO
-	bool "Large Receive Offload (ipv4/tcp)"
+	tristate "Large Receive Offload (ipv4/tcp)"
 	default y
 	---help---
 	  Support for Large Receive Offload (ipv4/tcp).
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1fdcacd36ce7..2a4bb76f2132 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -834,7 +834,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 	int			mark = 0;
 
 
-	if (len == 8 || IGMP_V2_SEEN(in_dev)) {
+	if (len == 8) {
 		if (ih->code == 0) {
 			/* Alas, old v1 router presents here. */
 
@@ -856,6 +856,18 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		igmpv3_clear_delrec(in_dev);
 	} else if (len < 12) {
 		return;	/* ignore bogus packet; freed by caller */
+	} else if (IGMP_V1_SEEN(in_dev)) {
+		/* This is a v3 query with v1 queriers present */
+		max_delay = IGMP_Query_Response_Interval;
+		group = 0;
+	} else if (IGMP_V2_SEEN(in_dev)) {
+		/* this is a v3 query with v2 queriers present;
+		 * Interpretation of the max_delay code is problematic here.
+		 * A real v2 host would use ih_code directly, while v3 has a
+		 * different encoding. We use the v3 encoding as more likely
+		 * to be intended in a v3 query.
+		 */
+		max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE);
 	} else { /* v3 */
 		if (!pskb_may_pull(skb, sizeof(struct igmpv3_query)))
 			return;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 945b20a5ad50..35c93e8b6a46 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -45,7 +45,7 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
@@ -699,7 +699,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			if ((dst = rt->rt_gateway) == 0)
 				goto tx_error_icmp;
 		}
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
 			struct in6_addr *addr6;
 			int addr_type;
@@ -774,7 +774,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			goto tx_error;
 		}
 	}
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	else if (skb->protocol == htons(ETH_P_IPV6)) {
 		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
 
@@ -850,7 +850,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 	if ((iph->ttl = tiph->ttl) == 0) {
 		if (skb->protocol == htons(ETH_P_IP))
 			iph->ttl = old_iph->ttl;
-#ifdef CONFIG_IPV6
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6))
 			iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
 #endif
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 04b69896df5f..7649d7750075 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 * we can switch to copy when see the first bad fragment.
 	 */
 	if (skb_has_frags(skb)) {
-		struct sk_buff *frag;
+		struct sk_buff *frag, *frag2;
 		int first_len = skb_pagelen(skb);
-		int truesizes = 0;
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
@@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
 			    skb_headroom(frag) < hlen)
-			    goto slow_path;
+				goto slow_path_clean;
 
 			/* Partially cloned skb? */
 			if (skb_shared(frag))
-				goto slow_path;
+				goto slow_path_clean;
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
 			}
-			truesizes += frag->truesize;
+			skb->truesize -= frag->truesize;
 		}
 
 		/* Everything is OK. Generate! */
@@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		frag = skb_shinfo(skb)->frag_list;
 		skb_frag_list_init(skb);
 		skb->data_len = first_len - skb_headlen(skb);
-		skb->truesize -= truesizes;
 		skb->len = first_len;
 		iph->tot_len = htons(first_len);
 		iph->frag_off = htons(IP_MF);
@@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		}
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		return err;
+
+slow_path_clean:
+		skb_walk_frags(skb, frag2) {
+			if (frag2 == frag)
+				break;
+			frag2->sk = NULL;
+			frag2->destructor = NULL;
+			skb->truesize += frag2->truesize;
+		}
 	}
 
 slow_path:
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index b254dafaf429..43eec80c0e7c 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 	/* ip_route_me_harder expects skb->dst to be set */
 	skb_dst_set_noref(nskb, skb_dst(oldskb));
 
+	nskb->protocol = htons(ETH_P_IP);
 	if (ip_route_me_harder(nskb, addr_type))
 		goto free_nskb;
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index eab8de32f200..f3a9b42b16c6 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
 					  const struct net_device *out,
 					  int (*okfn)(struct sk_buff *))
 {
+	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(skb->sk);
 
-	if (inet && inet->nodefrag)
+	if (sk && (sk->sk_family == PF_INET) &&
+	    inet->nodefrag)
 		return NF_ACCEPT;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 1679e2c0963d..ee5f419d0a56 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum,
 	unsigned char s[4];
 
 	if (offset & 1) {
-		s[0] = s[2] = 0;
+		s[0] = ~0;
 		s[1] = ~*optr;
+		s[2] = 0;
 		s[3] = *nptr;
 	} else {
-		s[1] = s[3] = 0;
 		s[0] = ~*optr;
+		s[1] = ~0;
 		s[2] = *nptr;
+		s[3] = 0;
 	}
 
 	*csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum)));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6298f75d5e93..ac6559cb54f9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1231,7 +1231,7 @@ restart:
 			}
 
 			if (net_ratelimit())
-				printk(KERN_WARNING "Neighbour table overflow.\n");
+				printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
 			rt_drop(rt);
 			return -ENOBUFS;
 		}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3fb1428e526e..f115ea68a4ef 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	 */
 
 	mask = 0;
-	if (sk->sk_err)
-		mask = POLLERR;
 
 	/*
 	 * POLLHUP is certainly not done right. But poll() doesn't
@@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
 	}
+	/* This barrier is coupled with smp_wmb() in tcp_reset() */
+	smp_rmb();
+	if (sk->sk_err)
+		mask |= POLLERR;
+
 	return mask;
 }
 EXPORT_SYMBOL(tcp_poll);
@@ -940,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	sg = sk->sk_route_caps & NETIF_F_SG;
 
 	while (--iovlen >= 0) {
-		int seglen = iov->iov_len;
+		size_t seglen = iov->iov_len;
 		unsigned char __user *from = iov->iov_base;
 
 		iov++;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e663b78a2ef6..b55f60f6fcbe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2545,7 +2545,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets)
 			cnt += tcp_skb_pcount(skb);
 
 		if (cnt > packets) {
-			if (tcp_is_sack(tp) || (oldcnt >= packets))
+			if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+			    (oldcnt >= packets))
 				break;
 
 			mss = skb_shinfo(skb)->gso_size;
@@ -4048,6 +4049,8 @@ static void tcp_reset(struct sock *sk)
 	default:
 		sk->sk_err = ECONNRESET;
 	}
+	/* This barrier is coupled with smp_rmb() in tcp_poll() */
+	smp_wmb();
 
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_error_report(sk);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c35b469e851c..74c54b30600f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 
 /* This function calculates a "timeout" which is equivalent to the timeout of a
  * TCP connection after "boundary" unsuccessful, exponentially backed-off
- * retransmissions with an initial RTO of TCP_RTO_MIN.
+ * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
+ * syn_set flag is set.
  */
 static bool retransmits_timed_out(struct sock *sk,
-				  unsigned int boundary)
+				  unsigned int boundary,
+				  bool syn_set)
 {
 	unsigned int timeout, linear_backoff_thresh;
 	unsigned int start_ts;
+	unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
 
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
@@ -151,12 +154,12 @@ static bool retransmits_timed_out(struct sock *sk,
 	else
 		start_ts = tcp_sk(sk)->retrans_stamp;
 
-	linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+	linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
 
 	if (boundary <= linear_backoff_thresh)
-		timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+		timeout = ((2 << boundary) - 1) * rto_base;
 	else
-		timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+		timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
 			  (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 
 	return (tcp_time_stamp - start_ts) >= timeout;
@@ -167,14 +170,15 @@ static int tcp_write_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int retry_until;
-	bool do_reset;
+	bool do_reset, syn_set = 0;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
 			dst_negative_advice(sk);
 		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+		syn_set = 1;
 	} else {
-		if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
+		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) {
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
@@ -187,14 +191,14 @@ static int tcp_write_timeout(struct sock *sk)
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
-				   !retransmits_timed_out(sk, retry_until);
+				   !retransmits_timed_out(sk, retry_until, 0);
 
 			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
 	}
 
-	if (retransmits_timed_out(sk, retry_until)) {
+	if (retransmits_timed_out(sk, retry_until, syn_set)) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);
 		return 1;
@@ -436,7 +440,7 @@ out_reset_timer:
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
-	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
+	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0))
 		__sk_dst_reset(sk);
 
 out:;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 869078d4eeb9..a580349f0b8a 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net,
 
 static int xfrm4_get_tos(struct flowi *fl)
 {
-	return fl->fl4_tos;
+	return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */
 }
 
 static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 1ef1366a0a03..47947624eccc 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x)
 }
 
 static void
-__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl,
-		     struct xfrm_tmpl *tmpl,
-		     xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
+{
+	sel->daddr.a4 = fl->fl4_dst;
+	sel->saddr.a4 = fl->fl4_src;
+	sel->dport = xfrm_flowi_dport(fl);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET;
+	sel->prefixlen_d = 32;
+	sel->prefixlen_s = 32;
+	sel->proto = fl->proto;
+	sel->ifindex = fl->oif;
+}
+
+static void
+xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+		   xfrm_address_t *daddr, xfrm_address_t *saddr)
 {
-	x->sel.daddr.a4 = fl->fl4_dst;
-	x->sel.saddr.a4 = fl->fl4_src;
-	x->sel.dport = xfrm_flowi_dport(fl);
-	x->sel.dport_mask = htons(0xffff);
-	x->sel.sport = xfrm_flowi_sport(fl);
-	x->sel.sport_mask = htons(0xffff);
-	x->sel.family = AF_INET;
-	x->sel.prefixlen_d = 32;
-	x->sel.prefixlen_s = 32;
-	x->sel.proto = fl->proto;
-	x->sel.ifindex = fl->oif;
 	x->id = tmpl->id;
 	if (x->id.daddr.a4 == 0)
 		x->id.daddr.a4 = daddr->a4;
@@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = {
 	.owner			= THIS_MODULE,
 	.init_flags		= xfrm4_init_flags,
 	.init_tempsel		= __xfrm4_init_tempsel,
+	.init_temprop		= xfrm4_init_temprop,
 	.output			= xfrm4_output,
 	.extract_input		= xfrm4_extract_input,
 	.extract_output		= xfrm4_extract_output,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ab70a3fbcafa..324fac3b6c16 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4637,10 +4637,12 @@ int __init addrconf_init(void)
 	if (err < 0) {
 		printk(KERN_CRIT "IPv6 Addrconf:"
 		       " cannot initialize default policy table: %d.\n", err);
-		return err;
+		goto out;
 	}
 
-	register_pernet_subsys(&addrconf_ops);
+	err = register_pernet_subsys(&addrconf_ops);
+	if (err < 0)
+		goto out_addrlabel;
 
 	/* The addrconf netdev notifier requires that loopback_dev
 	 * has it's ipv6 private information allocated and setup
@@ -4692,7 +4694,9 @@ errout:
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:
 	unregister_pernet_subsys(&addrconf_ops);
-
+out_addrlabel:
+	ipv6_addr_label_cleanup();
+out:
 	return err;
 }
 
@@ -4703,6 +4707,7 @@ void addrconf_cleanup(void)
 
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 	unregister_pernet_subsys(&addrconf_ops);
+	ipv6_addr_label_cleanup();
 
 	rtnl_lock();
 
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index f0e774cea386..8175f802651b 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void)
 	return register_pernet_subsys(&ipv6_addr_label_ops);
 }
 
+void ipv6_addr_label_cleanup(void)
+{
+	unregister_pernet_subsys(&ipv6_addr_label_ops);
+}
+
 static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
 	[IFAL_ADDRESS]		= { .len = sizeof(struct in6_addr), },
 	[IFAL_LABEL]		= { .len = sizeof(u32), },
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d40b330c0ee6..980912ed7a38 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	if (skb_has_frags(skb)) {
 		int first_len = skb_pagelen(skb);
-		int truesizes = 0;
+		struct sk_buff *frag2;
 
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
@@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
 			    skb_headroom(frag) < hlen)
-			    goto slow_path;
+				goto slow_path_clean;
 
 			/* Partially cloned skb? */
 			if (skb_shared(frag))
-				goto slow_path;
+				goto slow_path_clean;
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
-				truesizes += frag->truesize;
 			}
+			skb->truesize -= frag->truesize;
 		}
 
 		err = 0;
@@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 		first_len = skb_pagelen(skb);
 		skb->data_len = first_len - skb_headlen(skb);
-		skb->truesize -= truesizes;
 		skb->len = first_len;
 		ipv6_hdr(skb)->payload_len = htons(first_len -
 						   sizeof(struct ipv6hdr));
@@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			      IPSTATS_MIB_FRAGFAILS);
 		dst_release(&rt->dst);
 		return err;
+
+slow_path_clean:
+		skb_walk_frags(skb, frag2) {
+			if (frag2 == frag)
+				break;
+			frag2->sk = NULL;
+			frag2->destructor = NULL;
+			skb->truesize += frag2->truesize;
+		}
 	}
 
 slow_path:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d126365ac046..a275c6e1e25c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -670,7 +670,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
 
 			if (net_ratelimit())
 				printk(KERN_WARNING
-				       "Neighbour table overflow.\n");
+				       "ipv6: Neighbour table overflow.\n");
 			dst_free(&rt->dst);
 			return NULL;
 		}
@@ -1556,14 +1556,13 @@ out:
  *	i.e. Path MTU discovery
  */
 
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
-			struct net_device *dev, u32 pmtu)
+static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+			     struct net *net, u32 pmtu, int ifindex)
 {
 	struct rt6_info *rt, *nrt;
-	struct net *net = dev_net(dev);
 	int allfrag = 0;
 
-	rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
+	rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
 	if (rt == NULL)
 		return;
 
@@ -1631,6 +1630,27 @@ out:
 	dst_release(&rt->dst);
 }
 
+void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
+			struct net_device *dev, u32 pmtu)
+{
+	struct net *net = dev_net(dev);
+
+	/*
+	 * RFC 1981 states that a node "MUST reduce the size of the packets it
+	 * is sending along the path" that caused the Packet Too Big message.
+	 * Since it's not possible in the general case to determine which
+	 * interface was used to send the original packet, we update the MTU
+	 * on the interface that will be used to send future packets. We also
+	 * update the MTU on the interface that received the Packet Too Big in
+	 * case the original packet was forced out that interface with
+	 * SO_BINDTODEVICE or similar. This is the next best thing to the
+	 * correct behaviour, which would be to update the MTU on all
+	 * interfaces.
+	 */
+	rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
+	rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
+}
+
 /*
  *	Misc support functions
  */
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index f417b77fa0e1..a67575d472a3 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -20,23 +20,27 @@
 #include <net/addrconf.h>
 
 static void
-__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl,
-		     struct xfrm_tmpl *tmpl,
-		     xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
 {
 	/* Initialize temporary selector matching only
 	 * to current session. */
-	ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst);
-	ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src);
-	x->sel.dport = xfrm_flowi_dport(fl);
-	x->sel.dport_mask = htons(0xffff);
-	x->sel.sport = xfrm_flowi_sport(fl);
-	x->sel.sport_mask = htons(0xffff);
-	x->sel.family = AF_INET6;
-	x->sel.prefixlen_d = 128;
-	x->sel.prefixlen_s = 128;
-	x->sel.proto = fl->proto;
-	x->sel.ifindex = fl->oif;
+	ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
+	ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
+	sel->dport = xfrm_flowi_dport(fl);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET6;
+	sel->prefixlen_d = 128;
+	sel->prefixlen_s = 128;
+	sel->proto = fl->proto;
+	sel->ifindex = fl->oif;
+}
+
+static void
+xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+		   xfrm_address_t *daddr, xfrm_address_t *saddr)
+{
 	x->id = tmpl->id;
 	if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
 		memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
@@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
 	.eth_proto		= htons(ETH_P_IPV6),
 	.owner			= THIS_MODULE,
 	.init_tempsel		= __xfrm6_init_tempsel,
+	.init_temprop		= xfrm6_init_temprop,
 	.tmpl_sort		= __xfrm6_tmpl_sort,
 	.state_sort		= __xfrm6_state_sort,
 	.output			= xfrm6_output,
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index c893f236acea..8f23401832b7 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -175,6 +175,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 
 	set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state);
 
+	del_timer_sync(&tid_tx->addba_resp_timer);
+
 	/*
 	 * After this packets are no longer handed right through
 	 * to the driver but are put onto tid_tx->pending instead,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index fa0f37e4afe4..28624282c5f3 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2199,9 +2199,6 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
 	struct net_device *prev_dev = NULL;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 
-	if (status->flag & RX_FLAG_INTERNAL_CMTR)
-		goto out_free_skb;
-
 	if (skb_headroom(skb) < sizeof(*rthdr) &&
 	    pskb_expand_head(skb, sizeof(*rthdr), 0, GFP_ATOMIC))
 		goto out_free_skb;
@@ -2260,7 +2257,6 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
 	} else
 		goto out_free_skb;
 
-	status->flag |= RX_FLAG_INTERNAL_CMTR;
 	return;
 
  out_free_skb:
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 10caec5ea8fa..34da67995d94 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -377,7 +377,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 				skb2 = skb_clone(skb, GFP_ATOMIC);
 				if (skb2) {
 					skb2->dev = prev_dev;
-					netif_receive_skb(skb2);
+					netif_rx(skb2);
 				}
 			}
 
@@ -386,7 +386,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	}
 	if (prev_dev) {
 		skb->dev = prev_dev;
-		netif_receive_skb(skb);
+		netif_rx(skb);
 		skb = NULL;
 	}
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 7dcf7a404190..8d9e4c949b96 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -48,15 +48,17 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp)
 {
 	unsigned int off, len;
 	struct nf_ct_ext_type *t;
+	size_t alloc_size;
 
 	rcu_read_lock();
 	t = rcu_dereference(nf_ct_ext_types[id]);
 	BUG_ON(t == NULL);
 	off = ALIGN(sizeof(struct nf_ct_ext), t->align);
 	len = off + t->len;
+	alloc_size = t->alloc_size;
 	rcu_read_unlock();
 
-	*ext = kzalloc(t->alloc_size, gfp);
+	*ext = kzalloc(alloc_size, gfp);
 	if (!*ext)
 		return NULL;
 
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 53d892210a04..f64de9544866 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1376,7 +1376,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
 	unsigned int msglen, origlen;
 	const char *dptr, *end;
 	s16 diff, tdiff = 0;
-	int ret;
+	int ret = NF_ACCEPT;
 	typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust;
 
 	if (ctinfo != IP_CT_ESTABLISHED &&
diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c
index 5490fc37c92d..daab8c4a903c 100644
--- a/net/netfilter/nf_tproxy_core.c
+++ b/net/netfilter/nf_tproxy_core.c
@@ -70,7 +70,11 @@ nf_tproxy_destructor(struct sk_buff *skb)
 int
 nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
 {
-	if (inet_sk(sk)->transparent) {
+	bool transparent = (sk->sk_state == TCP_TIME_WAIT) ?
+				inet_twsk(sk)->tw_transparent :
+				inet_sk(sk)->transparent;
+
+	if (transparent) {
 		skb_orphan(skb);
 		skb->sk = sk;
 		skb->destructor = nf_tproxy_destructor;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index b2a3ae6cad78..15003021f4f0 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -225,12 +225,13 @@ static void pipe_grant_credits(struct sock *sk)
 static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 {
 	struct pep_sock *pn = pep_sk(sk);
-	struct pnpipehdr *hdr = pnp_hdr(skb);
+	struct pnpipehdr *hdr;
 	int wake = 0;
 
 	if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
 		return -EINVAL;
 
+	hdr = pnp_hdr(skb);
 	if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
 		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n",
 				(unsigned)hdr->data[0]);
diff --git a/net/rds/page.c b/net/rds/page.c
index 595a952d4b17..1dfbfea12e9b 100644
--- a/net/rds/page.c
+++ b/net/rds/page.c
@@ -57,30 +57,17 @@ int rds_page_copy_user(struct page *page, unsigned long offset,
 	unsigned long ret;
 	void *addr;
 
-	if (to_user)
+	addr = kmap(page);
+	if (to_user) {
 		rds_stats_add(s_copy_to_user, bytes);
-	else
+		ret = copy_to_user(ptr, addr + offset, bytes);
+	} else {
 		rds_stats_add(s_copy_from_user, bytes);
-
-	addr = kmap_atomic(page, KM_USER0);
-	if (to_user)
-		ret = __copy_to_user_inatomic(ptr, addr + offset, bytes);
-	else
-		ret = __copy_from_user_inatomic(addr + offset, ptr, bytes);
-	kunmap_atomic(addr, KM_USER0);
-
-	if (ret) {
-		addr = kmap(page);
-		if (to_user)
-			ret = copy_to_user(ptr, addr + offset, bytes);
-		else
-			ret = copy_from_user(addr + offset, ptr, bytes);
-		kunmap(page);
-		if (ret)
-			return -EFAULT;
+		ret = copy_from_user(addr + offset, ptr, bytes);
 	}
+	kunmap(page);
 
-	return 0;
+	return ret ? -EFAULT : 0;
 }
 EXPORT_SYMBOL_GPL(rds_page_copy_user);
 
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index c397524c039c..c519939e8da9 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk)
 	struct rds_connection *conn;
 	struct rds_tcp_connection *tc;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	conn = sk->sk_user_data;
 	if (conn == NULL) {
 		state_change = sk->sk_state_change;
@@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk)
 			break;
 	}
 out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 	state_change(sk);
 }
 
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 975183fe6950..27844f231d10 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
 
 	rdsdebug("listen data ready sk %p\n", sk);
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	ready = sk->sk_user_data;
 	if (ready == NULL) { /* check for teardown race */
 		ready = sk->sk_data_ready;
@@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
 		queue_work(rds_wq, &rds_tcp_listen_work);
 
 out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 	ready(sk, bytes);
 }
 
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 1aba6878fa5d..e43797404102 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -324,7 +324,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
 
 	rdsdebug("data ready sk %p bytes %d\n", sk, bytes);
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	conn = sk->sk_user_data;
 	if (conn == NULL) { /* check for teardown race */
 		ready = sk->sk_data_ready;
@@ -338,7 +338,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
 	if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM)
 		queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
 out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 	ready(sk, bytes);
 }
 
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index a28b895ff0d1..2f012a07d94d 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -224,7 +224,7 @@ void rds_tcp_write_space(struct sock *sk)
 	struct rds_connection *conn;
 	struct rds_tcp_connection *tc;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	conn = sk->sk_user_data;
 	if (conn == NULL) {
 		write_space = sk->sk_write_space;
@@ -244,7 +244,7 @@ void rds_tcp_write_space(struct sock *sk)
 		queue_delayed_work(rds_wq, &conn->c_send_w, 0);
 
 out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 
 	/*
 	 * write_space is only called when data leaves tcp's send queue if
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 8e45e76a95f5..d952e7eac188 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -679,7 +679,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1)
 		return -EINVAL;
 
-	if (addr->srose_ndigis > ROSE_MAX_DIGIS)
+	if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS)
 		return -EINVAL;
 
 	if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) {
@@ -739,7 +739,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 	if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1)
 		return -EINVAL;
 
-	if (addr->srose_ndigis > ROSE_MAX_DIGIS)
+	if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS)
 		return -EINVAL;
 
 	/* Source + Destination digis should not exceed ROSE_MAX_DIGIS */
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 7416a5c73b2a..b0c2a82178af 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -137,7 +137,7 @@ next_knode:
 			int toff = off + key->off + (off2 & key->offmask);
 			__be32 *data, _data;
 
-			if (skb_headroom(skb) + toff < 0)
+			if (skb_headroom(skb) + toff > INT_MAX)
 				goto out;
 
 			data = skb_header_pointer(skb, toff, 4, &_data);
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 86366390038a..ddbbf7c81fa1 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -543,16 +543,20 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc)
 		id = ntohs(hmacs->hmac_ids[i]);
 
 		/* Check the id is in the supported range */
-		if (id > SCTP_AUTH_HMAC_ID_MAX)
+		if (id > SCTP_AUTH_HMAC_ID_MAX) {
+			id = 0;
 			continue;
+		}
 
 		/* See is we support the id.  Supported IDs have name and
 		 * length fields set, so that we can allocated and use
 		 * them.  We can safely just check for name, for without the
 		 * name, we can't allocate the TFM.
 		 */
-		if (!sctp_hmac_list[id].hmac_name)
+		if (!sctp_hmac_list[id].hmac_name) {
+			id = 0;
 			continue;
+		}
 
 		break;
 	}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ca44917872d2..fbb70770ad05 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -916,6 +916,11 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk,
 	/* Walk through the addrs buffer and count the number of addresses. */
 	addr_buf = kaddrs;
 	while (walk_size < addrs_size) {
+		if (walk_size + sizeof(sa_family_t) > addrs_size) {
+			kfree(kaddrs);
+			return -EINVAL;
+		}
+
 		sa_addr = (struct sockaddr *)addr_buf;
 		af = sctp_get_af_specific(sa_addr->sa_family);
 
@@ -1002,9 +1007,13 @@ static int __sctp_connect(struct sock* sk,
 	/* Walk through the addrs buffer and count the number of addresses. */
 	addr_buf = kaddrs;
 	while (walk_size < addrs_size) {
+		if (walk_size + sizeof(sa_family_t) > addrs_size) {
+			err = -EINVAL;
+			goto out_free;
+		}
+
 		sa_addr = (union sctp_addr *)addr_buf;
 		af = sctp_get_af_specific(sa_addr->sa.sa_family);
-		port = ntohs(sa_addr->v4.sin_port);
 
 		/* If the address family is not supported or if this address
 		 * causes the address buffer to overflow return EINVAL.
@@ -1014,6 +1023,8 @@ static int __sctp_connect(struct sock* sk,
 			goto out_free;
 		}
 
+		port = ntohs(sa_addr->v4.sin_port);
+
 		/* Save current address so we can work with it */
 		memcpy(&to, sa_addr, af->sockaddr_len);
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index b6309db56226..fe9306bf10cc 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len)
 	u32 _xid;
 	__be32 *xp;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	dprintk("RPC:       xs_udp_data_ready...\n");
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
@@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len)
  dropit:
 	skb_free_datagram(sk, skb);
  out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
@@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
 
 	dprintk("RPC:       xs_tcp_data_ready...\n");
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 	if (xprt->shutdown)
@@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
 		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
 	} while (read > 0);
 out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 /*
@@ -1301,7 +1301,7 @@ static void xs_tcp_state_change(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 	dprintk("RPC:       xs_tcp_state_change client %p...\n", xprt);
@@ -1313,7 +1313,7 @@ static void xs_tcp_state_change(struct sock *sk)
 
 	switch (sk->sk_state) {
 	case TCP_ESTABLISHED:
-		spin_lock_bh(&xprt->transport_lock);
+		spin_lock(&xprt->transport_lock);
 		if (!xprt_test_and_set_connected(xprt)) {
 			struct sock_xprt *transport = container_of(xprt,
 					struct sock_xprt, xprt);
@@ -1327,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk)
 
 			xprt_wake_pending_tasks(xprt, -EAGAIN);
 		}
-		spin_unlock_bh(&xprt->transport_lock);
+		spin_unlock(&xprt->transport_lock);
 		break;
 	case TCP_FIN_WAIT1:
 		/* The client initiated a shutdown of the socket */
@@ -1365,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk)
 		xs_sock_mark_closed(xprt);
 	}
  out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 /**
@@ -1376,7 +1376,7 @@ static void xs_error_report(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 	dprintk("RPC:       %s client %p...\n"
@@ -1384,7 +1384,7 @@ static void xs_error_report(struct sock *sk)
 			__func__, xprt, sk->sk_err);
 	xprt_wake_pending_tasks(xprt, -EAGAIN);
 out:
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void xs_write_space(struct sock *sk)
@@ -1416,13 +1416,13 @@ static void xs_write_space(struct sock *sk)
  */
 static void xs_udp_write_space(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 
 	/* from net/core/sock.c:sock_def_write_space */
 	if (sock_writeable(sk))
 		xs_write_space(sk);
 
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 /**
@@ -1437,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk)
  */
 static void xs_tcp_write_space(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 
 	/* from net/core/stream.c:sk_stream_write_space */
 	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
 		xs_write_space(sk);
 
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c
index 3feb28e41c53..674d426a9d24 100644
--- a/net/wireless/wext-priv.c
+++ b/net/wireless/wext-priv.c
@@ -152,7 +152,7 @@ static int ioctl_private_iw_point(struct iw_point *iwp, unsigned int cmd,
 	} else if (!iwp->pointer)
 		return -EFAULT;
 
-	extra = kmalloc(extra_size, GFP_KERNEL);
+	extra = kzalloc(extra_size, GFP_KERNEL);
 	if (!extra)
 		return -ENOMEM;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 2b3ed7ad4933..cbab6e1a8c9c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1175,9 +1175,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl,
 		    tmpl->mode == XFRM_MODE_BEET) {
 			remote = &tmpl->id.daddr;
 			local = &tmpl->saddr;
-			family = tmpl->encap_family;
-			if (xfrm_addr_any(local, family)) {
-				error = xfrm_get_saddr(net, &tmp, remote, family);
+			if (xfrm_addr_any(local, tmpl->encap_family)) {
+				error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family);
 				if (error)
 					goto fail;
 				local = &tmp;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 5208b12fbfb4..eb96ce52f178 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -656,15 +656,23 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 EXPORT_SYMBOL(xfrm_sad_getinfo);
 
 static int
-xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl,
-		  struct xfrm_tmpl *tmpl,
-		  xfrm_address_t *daddr, xfrm_address_t *saddr,
-		  unsigned short family)
+xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl,
+		    struct xfrm_tmpl *tmpl,
+		    xfrm_address_t *daddr, xfrm_address_t *saddr,
+		    unsigned short family)
 {
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
 	if (!afinfo)
 		return -1;
-	afinfo->init_tempsel(x, fl, tmpl, daddr, saddr);
+	afinfo->init_tempsel(&x->sel, fl);
+
+	if (family != tmpl->encap_family) {
+		xfrm_state_put_afinfo(afinfo);
+		afinfo = xfrm_state_get_afinfo(tmpl->encap_family);
+		if (!afinfo)
+			return -1;
+	}
+	afinfo->init_temprop(x, tmpl, daddr, saddr);
 	xfrm_state_put_afinfo(afinfo);
 	return 0;
 }
@@ -790,37 +798,38 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
 	int error = 0;
 	struct xfrm_state *best = NULL;
 	u32 mark = pol->mark.v & pol->mark.m;
+	unsigned short encap_family = tmpl->encap_family;
 
 	to_put = NULL;
 
 	spin_lock_bh(&xfrm_state_lock);
-	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, family);
+	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
 	hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
-		if (x->props.family == family &&
+		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
 		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
-		    xfrm_state_addr_check(x, daddr, saddr, family) &&
+		    xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
 		    tmpl->mode == x->props.mode &&
 		    tmpl->id.proto == x->id.proto &&
 		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
-			xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+			xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr,
 					   &best, &acquire_in_progress, &error);
 	}
 	if (best)
 		goto found;
 
-	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family);
+	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
 	hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) {
-		if (x->props.family == family &&
+		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
 		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
-		    xfrm_state_addr_check(x, daddr, saddr, family) &&
+		    xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
 		    tmpl->mode == x->props.mode &&
 		    tmpl->id.proto == x->id.proto &&
 		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
-			xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+			xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr,
 					   &best, &acquire_in_progress, &error);
 	}
 
@@ -829,7 +838,7 @@ found:
 	if (!x && !error && !acquire_in_progress) {
 		if (tmpl->id.spi &&
 		    (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi,
-					      tmpl->id.proto, family)) != NULL) {
+					      tmpl->id.proto, encap_family)) != NULL) {
 			to_put = x0;
 			error = -EEXIST;
 			goto out;
@@ -839,9 +848,9 @@ found:
 			error = -ENOMEM;
 			goto out;
 		}
-		/* Initialize temporary selector matching only
+		/* Initialize temporary state matching only
 		 * to current session. */
-		xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family);
+		xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
 		memcpy(&x->mark, &pol->mark, sizeof(x->mark));
 
 		error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid);
@@ -856,10 +865,10 @@ found:
 			x->km.state = XFRM_STATE_ACQ;
 			list_add(&x->km.all, &net->xfrm.state_all);
 			hlist_add_head(&x->bydst, net->xfrm.state_bydst+h);
-			h = xfrm_src_hash(net, daddr, saddr, family);
+			h = xfrm_src_hash(net, daddr, saddr, encap_family);
 			hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
 			if (x->id.spi) {
-				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, family);
+				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
 				hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c
index ee03a4f0b64f..06473791c08a 100644
--- a/samples/kfifo/dma-example.c
+++ b/samples/kfifo/dma-example.c
@@ -24,6 +24,7 @@ static int __init example_init(void)
 {
 	int			i;
 	unsigned int		ret;
+	unsigned int		nents;
 	struct scatterlist	sg[10];
 
 	printk(KERN_INFO "DMA fifo test start\n");
@@ -61,9 +62,9 @@ static int __init example_init(void)
 	 * byte at the beginning, after the kfifo_skip().
 	 */
 	sg_init_table(sg, ARRAY_SIZE(sg));
-	ret = kfifo_dma_in_prepare(&fifo, sg, ARRAY_SIZE(sg), FIFO_SIZE);
-	printk(KERN_INFO "DMA sgl entries: %d\n", ret);
-	if (!ret) {
+	nents = kfifo_dma_in_prepare(&fifo, sg, ARRAY_SIZE(sg), FIFO_SIZE);
+	printk(KERN_INFO "DMA sgl entries: %d\n", nents);
+	if (!nents) {
 		/* fifo is full and no sgl was created */
 		printk(KERN_WARNING "error kfifo_dma_in_prepare\n");
 		return -EIO;
@@ -71,7 +72,7 @@ static int __init example_init(void)
 
 	/* receive data */
 	printk(KERN_INFO "scatterlist for receive:\n");
-	for (i = 0; i < ARRAY_SIZE(sg); i++) {
+	for (i = 0; i < nents; i++) {
 		printk(KERN_INFO
 		"sg[%d] -> "
 		"page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n",
@@ -91,16 +92,16 @@ static int __init example_init(void)
 	kfifo_dma_in_finish(&fifo, ret);
 
 	/* Prepare to transmit data, example: 8 bytes */
-	ret = kfifo_dma_out_prepare(&fifo, sg, ARRAY_SIZE(sg), 8);
-	printk(KERN_INFO "DMA sgl entries: %d\n", ret);
-	if (!ret) {
+	nents = kfifo_dma_out_prepare(&fifo, sg, ARRAY_SIZE(sg), 8);
+	printk(KERN_INFO "DMA sgl entries: %d\n", nents);
+	if (!nents) {
 		/* no data was available and no sgl was created */
 		printk(KERN_WARNING "error kfifo_dma_out_prepare\n");
 		return -EIO;
 	}
 
 	printk(KERN_INFO "scatterlist for transmit:\n");
-	for (i = 0; i < ARRAY_SIZE(sg); i++) {
+	for (i = 0; i < nents; i++) {
 		printk(KERN_INFO
 		"sg[%d] -> "
 		"page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n",
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 5b7c86ea43a1..7ef429cd5cb3 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -427,7 +427,7 @@ static void check_conf(struct menu *menu)
 				if (sym->name && !sym_is_choice_value(sym)) {
 					printf("CONFIG_%s\n", sym->name);
 				}
-			} else {
+			} else if (input_mode != oldnoconfig) {
 				if (!conf_cnt++)
 					printf(_("*\n* Restart config...\n*\n"));
 				rootEntry = menu_get_parent_menu(menu);
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index 6ee2e4fb1481..170459c224a1 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -165,7 +165,6 @@ struct menu {
 	struct symbol *sym;
 	struct property *prompt;
 	struct expr *dep;
-	struct expr *dir_dep;
 	unsigned int flags;
 	char *help;
 	struct file *file;
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 4fb590247f33..edda8b49619d 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -107,7 +107,6 @@ static struct expr *menu_check_dep(struct expr *e)
 void menu_add_dep(struct expr *dep)
 {
 	current_entry->dep = expr_alloc_and(current_entry->dep, menu_check_dep(dep));
-	current_entry->dir_dep = current_entry->dep;
 }
 
 void menu_set_type(int type)
@@ -291,10 +290,6 @@ void menu_finalize(struct menu *parent)
 		for (menu = parent->list; menu; menu = menu->next)
 			menu_finalize(menu);
 	} else if (sym) {
-		/* ignore inherited dependencies for dir_dep */
-		sym->dir_dep.expr = expr_transform(expr_copy(parent->dir_dep));
-		sym->dir_dep.expr = expr_eliminate_dups(sym->dir_dep.expr);
-
 		basedep = parent->prompt ? parent->prompt->visible.expr : NULL;
 		basedep = expr_trans_compare(basedep, E_UNEQUAL, &symbol_no);
 		basedep = expr_eliminate_dups(expr_transform(basedep));
@@ -325,6 +320,8 @@ void menu_finalize(struct menu *parent)
 			parent->next = last_menu->next;
 			last_menu->next = NULL;
 		}
+
+		sym->dir_dep.expr = parent->dep;
 	}
 	for (menu = parent->list; menu; menu = menu->next) {
 		if (sym && sym_is_choice(sym) &&
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 943712ca6c0a..1f8b305449db 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -350,6 +350,7 @@ void sym_calc_value(struct symbol *sym)
 				}
 			}
 		calc_newval:
+#if 0
 			if (sym->dir_dep.tri == no && sym->rev_dep.tri != no) {
 				fprintf(stderr, "warning: (");
 				expr_fprint(sym->rev_dep.expr, stderr);
@@ -358,6 +359,7 @@ void sym_calc_value(struct symbol *sym)
 				expr_fprint(sym->dir_dep.expr, stderr);
 				fprintf(stderr, ")\n");
 			}
+#endif
 			newval.tri = EXPR_OR(newval.tri, sym->rev_dep.tri);
 		}
 		if (newval.tri == mod && sym_get_type(sym) == S_BOOLEAN)
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index ef43995119a4..c668b447c725 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -1416,15 +1416,19 @@ static char *tomoyo_print_header(struct tomoyo_request_info *r)
 	const pid_t gpid = task_pid_nr(current);
 	static const int tomoyo_buffer_len = 4096;
 	char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS);
+	pid_t ppid;
 	if (!buffer)
 		return NULL;
 	do_gettimeofday(&tv);
+	rcu_read_lock();
+	ppid = task_tgid_vnr(current->real_parent);
+	rcu_read_unlock();
 	snprintf(buffer, tomoyo_buffer_len - 1,
 		 "#timestamp=%lu profile=%u mode=%s (global-pid=%u)"
 		 " task={ pid=%u ppid=%u uid=%u gid=%u euid=%u"
 		 " egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }",
 		 tv.tv_sec, r->profile, tomoyo_mode[r->mode], gpid,
-		 (pid_t) sys_getpid(), (pid_t) sys_getppid(),
+		 task_tgid_vnr(current), ppid,
 		 current_uid(), current_gid(), current_euid(),
 		 current_egid(), current_suid(), current_sgid(),
 		 current_fsuid(), current_fsgid());
diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h
index 04454cb7b24a..7c66bd898782 100644
--- a/security/tomoyo/common.h
+++ b/security/tomoyo/common.h
@@ -689,9 +689,6 @@ struct tomoyo_profile {
 
 /********** Function prototypes. **********/
 
-extern asmlinkage long sys_getpid(void);
-extern asmlinkage long sys_getppid(void);
-
 /* Check whether the given string starts with the given keyword. */
 bool tomoyo_str_starts(char **src, const char *find);
 /* Get tomoyo_realpath() of current process. */
diff --git a/sound/core/control.c b/sound/core/control.c
index 070aab490191..45a818002d99 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -31,6 +31,7 @@
 
 /* max number of user-defined controls */
 #define MAX_USER_CONTROLS	32
+#define MAX_CONTROL_COUNT	1028
 
 struct snd_kctl_ioctl {
 	struct list_head list;		/* list of all ioctls */
@@ -195,6 +196,10 @@ static struct snd_kcontrol *snd_ctl_new(struct snd_kcontrol *control,
 	
 	if (snd_BUG_ON(!control || !control->count))
 		return NULL;
+
+	if (control->count > MAX_CONTROL_COUNT)
+		return NULL;
+
 	kctl = kzalloc(sizeof(*kctl) + sizeof(struct snd_kcontrol_volatile) * control->count, GFP_KERNEL);
 	if (kctl == NULL) {
 		snd_printk(KERN_ERR "Cannot allocate control instance\n");
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index a7868ad4d530..cbbed0db9e56 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -535,13 +535,15 @@ static int snd_rawmidi_release(struct inode *inode, struct file *file)
 {
 	struct snd_rawmidi_file *rfile;
 	struct snd_rawmidi *rmidi;
+	struct module *module;
 
 	rfile = file->private_data;
 	rmidi = rfile->rmidi;
 	rawmidi_release_priv(rfile);
 	kfree(rfile);
+	module = rmidi->card->module;
 	snd_card_file_remove(rmidi->card, file);
-	module_put(rmidi->card->module);
+	module_put(module);
 	return 0;
 }
 
diff --git a/sound/i2c/other/ak4xxx-adda.c b/sound/i2c/other/ak4xxx-adda.c
index 1adb8a3c2b62..42d7844ecd0b 100644
--- a/sound/i2c/other/ak4xxx-adda.c
+++ b/sound/i2c/other/ak4xxx-adda.c
@@ -900,7 +900,7 @@ static int proc_init(struct snd_akm4xxx *ak)
 	return 0;
 }
 #else /* !CONFIG_PROC_FS */
-static int proc_init(struct snd_akm4xxx *ak) {}
+static int proc_init(struct snd_akm4xxx *ak) { return 0; }
 #endif
 
 int snd_akm4xxx_build_controls(struct snd_akm4xxx *ak)
diff --git a/sound/oss/soundcard.c b/sound/oss/soundcard.c
index 92aa762ffb7e..07f803e6d203 100644
--- a/sound/oss/soundcard.c
+++ b/sound/oss/soundcard.c
@@ -391,11 +391,11 @@ static long sound_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case SND_DEV_DSP:
 	case SND_DEV_DSP16:
 	case SND_DEV_AUDIO:
-		return audio_ioctl(dev, file, cmd, p);
+		ret = audio_ioctl(dev, file, cmd, p);
 		break;
 
 	case SND_DEV_MIDIN:
-		return MIDIbuf_ioctl(dev, file, cmd, p);
+		ret = MIDIbuf_ioctl(dev, file, cmd, p);
 		break;
 
 	}
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index b697fd2a6f8b..10bbbaf6ebc3 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -3641,6 +3641,7 @@ static struct snd_pci_quirk ad1984_cfg_tbl[] = {
 	/* Lenovo Thinkpad T61/X61 */
 	SND_PCI_QUIRK_VENDOR(0x17aa, "Lenovo Thinkpad", AD1984_THINKPAD),
 	SND_PCI_QUIRK(0x1028, 0x0214, "Dell T3400", AD1984_DELL_DESKTOP),
+	SND_PCI_QUIRK(0x1028, 0x0233, "Dell Latitude E6400", AD1984_DELL_DESKTOP),
 	{}
 };
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a1312a6c8af2..a432e6efd19b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1594,12 +1594,22 @@ static void alc_auto_parse_digital(struct hda_codec *codec)
 	}
 
 	if (spec->autocfg.dig_in_pin) {
-		hda_nid_t dig_nid;
-		err = snd_hda_get_connections(codec,
-					      spec->autocfg.dig_in_pin,
-					      &dig_nid, 1);
-		if (err > 0)
-			spec->dig_in_nid = dig_nid;
+		dig_nid = codec->start_nid;
+		for (i = 0; i < codec->num_nodes; i++, dig_nid++) {
+			unsigned int wcaps = get_wcaps(codec, dig_nid);
+			if (get_wcaps_type(wcaps) != AC_WID_AUD_IN)
+				continue;
+			if (!(wcaps & AC_WCAP_DIGITAL))
+				continue;
+			if (!(wcaps & AC_WCAP_CONN_LIST))
+				continue;
+			err = get_connection_index(codec, dig_nid,
+						   spec->autocfg.dig_in_pin);
+			if (err >= 0) {
+				spec->dig_in_nid = dig_nid;
+				break;
+			}
+		}
 	}
 }
 
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 95148e58026c..c16c5ba0fda0 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -1747,6 +1747,8 @@ static struct snd_pci_quirk stac92hd71bxx_cfg_tbl[] = {
 		      "HP dv6", STAC_HP_DV5),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x3061,
 		      "HP dv6", STAC_HP_DV5), /* HP dv6-1110ax */
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x363e,
+		      "HP DV6", STAC_HP_DV5),
 	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xfff0, 0x7010,
 		      "HP", STAC_HP_DV5),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0233,
diff --git a/sound/pci/oxygen/oxygen.c b/sound/pci/oxygen/oxygen.c
index 289cb4dacfc7..6c0a11adb2a8 100644
--- a/sound/pci/oxygen/oxygen.c
+++ b/sound/pci/oxygen/oxygen.c
@@ -543,6 +543,10 @@ static int __devinit get_oxygen_model(struct oxygen *chip,
 		chip->model.suspend = claro_suspend;
 		chip->model.resume = claro_resume;
 		chip->model.set_adc_params = set_ak5385_params;
+		chip->model.device_config = PLAYBACK_0_TO_I2S |
+					    PLAYBACK_1_TO_SPDIF |
+					    CAPTURE_0_FROM_I2S_2 |
+					    CAPTURE_1_FROM_SPDIF;
 		break;
 	}
 	if (id->driver_data == MODEL_MERIDIAN ||
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index b92adef8e81e..d6fa7bfd9aa1 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -4609,6 +4609,7 @@ static int snd_hdsp_hwdep_ioctl(struct snd_hwdep *hw, struct file *file, unsigne
 		if (err < 0)
 			return err;
 
+		memset(&info, 0, sizeof(info));
 		spin_lock_irqsave(&hdsp->lock, flags);
 		info.pref_sync_ref = (unsigned char)hdsp_pref_sync_ref(hdsp);
 		info.wordclock_sync_check = (unsigned char)hdsp_wc_sync_check(hdsp);
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 547b713d7204..0c98ef9156d8 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -4127,6 +4127,7 @@ static int snd_hdspm_hwdep_ioctl(struct snd_hwdep * hw, struct file *file,
 
 	case SNDRV_HDSPM_IOCTL_GET_CONFIG_INFO:
 
+		memset(&info, 0, sizeof(info));
 		spin_lock_irq(&hdspm->lock);
 		info.pref_sync_ref = hdspm_pref_sync_ref(hdspm);
 		info.wordclock_sync_check = hdspm_wc_sync_check(hdspm);
diff --git a/sound/soc/sh/migor.c b/sound/soc/sh/migor.c
index b823a5c9b9bc..87e2b7fcbf17 100644
--- a/sound/soc/sh/migor.c
+++ b/sound/soc/sh/migor.c
@@ -12,6 +12,7 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 
+#include <asm/clkdev.h>
 #include <asm/clock.h>
 
 #include <cpu/sh7722.h>
@@ -40,12 +41,12 @@ static struct clk_ops siumckb_clk_ops = {
 };
 
 static struct clk siumckb_clk = {
-	.name		= "siumckb_clk",
-	.id		= -1,
 	.ops		= &siumckb_clk_ops,
 	.rate		= 0, /* initialised at run-time */
 };
 
+static struct clk_lookup *siumckb_lookup;
+
 static int migor_hw_params(struct snd_pcm_substream *substream,
 			   struct snd_pcm_hw_params *params)
 {
@@ -180,6 +181,13 @@ static int __init migor_init(void)
 	if (ret < 0)
 		return ret;
 
+	siumckb_lookup = clkdev_alloc(&siumckb_clk, "siumckb_clk", NULL);
+	if (!siumckb_lookup) {
+		ret = -ENOMEM;
+		goto eclkdevalloc;
+	}
+	clkdev_add(siumckb_lookup);
+
 	/* Port number used on this machine: port B */
 	migor_snd_device = platform_device_alloc("soc-audio", 1);
 	if (!migor_snd_device) {
@@ -200,12 +208,15 @@ static int __init migor_init(void)
 epdevadd:
 	platform_device_put(migor_snd_device);
 epdevalloc:
+	clkdev_drop(siumckb_lookup);
+eclkdevalloc:
 	clk_unregister(&siumckb_clk);
 	return ret;
 }
 
 static void __exit migor_exit(void)
 {
+	clkdev_drop(siumckb_lookup);
 	clk_unregister(&siumckb_clk);
 	platform_device_unregister(migor_snd_device);
 }
diff --git a/sound/soc/soc-cache.c b/sound/soc/soc-cache.c
index adbc68ce9050..f6b0d2829ea9 100644
--- a/sound/soc/soc-cache.c
+++ b/sound/soc/soc-cache.c
@@ -203,8 +203,9 @@ static int snd_soc_8_16_write(struct snd_soc_codec *codec, unsigned int reg,
 	data[1] = (value >> 8) & 0xff;
 	data[2] = value & 0xff;
 
-	if (!snd_soc_codec_volatile_register(codec, reg))
-		reg_cache[reg] = value;
+	if (!snd_soc_codec_volatile_register(codec, reg)
+		&& reg < codec->reg_cache_size)
+			reg_cache[reg] = value;
 
 	if (codec->cache_only) {
 		codec->cache_sync = 1;
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4f1fa77c1feb..1950e19af1cf 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1017,7 +1017,7 @@ builtin-revert.o wt-status.o: wt-status.h
 # we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
 # we depend the various files onto their directories.
 DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
-$(DIRECTORY_DEPS): $(sort $(dir $(DIRECTORY_DEPS)))
+$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
 # In the second step, we make a rule to actually create these directories
 $(sort $(dir $(DIRECTORY_DEPS))):
 	$(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index ef7aa0a0c526..95aaf565c704 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -73,6 +73,18 @@ void get_term_dimensions(struct winsize *ws);
 #define cpu_relax()	asm volatile("":::"memory")
 #endif
 
+#ifdef __mips__
+#include "../../arch/mips/include/asm/unistd.h"
+#define rmb()		asm volatile(					\
+				".set	mips2\n\t"			\
+				"sync\n\t"				\
+				".set	mips0"				\
+				: /* no output */			\
+				: /* no input */			\
+				: "memory")
+#define cpu_relax()	asm volatile("" ::: "memory")
+#endif
+
 #include <time.h>
 #include <unistd.h>
 #include <sys/types.h>
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 7ea983acfaea..f7af2fca965d 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -97,7 +97,7 @@ void setup_python_scripting(void)
 	register_python_scripting(&python_scripting_unsupported_ops);
 }
 #else
-struct scripting_ops python_scripting_ops;
+extern struct scripting_ops python_scripting_ops;
 
 void setup_python_scripting(void)
 {
@@ -158,7 +158,7 @@ void setup_perl_scripting(void)
 	register_perl_scripting(&perl_scripting_unsupported_ops);
 }
 #else
-struct scripting_ops perl_scripting_ops;
+extern struct scripting_ops perl_scripting_ops;
 
 void setup_perl_scripting(void)
 {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index dafdf6775d77..6866aa4c41e0 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -773,7 +773,7 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 
 			switch (key) {
 			case 'a':
-				if (browser->selection->map == NULL &&
+				if (browser->selection->map == NULL ||
 				    browser->selection->map->dso->annotate_warned)
 					continue;
 				goto do_annotate;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 66cf65b510b1..c1f1e3c62984 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -218,7 +218,6 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 	events = file->f_op->poll(file, &irqfd->pt);
 
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
-	spin_unlock_irq(&kvm->irqfds.lock);
 
 	/*
 	 * Check if there was an event already pending on the eventfd
@@ -227,6 +226,8 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 	if (events & POLLIN)
 		schedule_work(&irqfd->inject);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
 	/*
 	 * do not drop the file until the irqfd is fully initialized, otherwise
 	 * we might race against the POLLHUP
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d4853a54771a..5186e728c53e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1970,10 +1970,12 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 
 asmlinkage void kvm_handle_fault_on_reboot(void)
 {
-	if (kvm_rebooting)
+	if (kvm_rebooting) {
 		/* spin while reset goes on */
+		local_irq_enable();
 		while (true)
 			;
+	}
 	/* Fault while not rebooting.  We want the trace. */
 	BUG();
 }