640 files changed, 41157 insertions, 10167 deletions

diff --git a/.mailmap b/.mailmap
index 5a6dd592eedc..353ad5607156 100644
--- a/.mailmap
+++ b/.mailmap
@@ -32,6 +32,7 @@ Brian Avery <b.avery@hp.com>
 Brian King <brking@us.ibm.com>
 Christoph Hellwig <hch@lst.de>
 Corey Minyard <minyard@acm.org>
+Damian Hobson-Garcia <dhobsong@igel.co.jp>
 David Brownell <david-b@pacbell.net>
 David Woodhouse <dwmw2@shinybook.infradead.org>
 Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
diff --git a/CREDITS b/CREDITS
index 95c469c610bc..58d2a02add39 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2943,6 +2943,10 @@ S: Kasarmikatu 11 A4
 S: 70110 Kuopio
 S: Finland
 
+N: Tobias Ringström
+E: tori@unhappy.mine.nu
+D: Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver
+
 N: Luca Risolia
 E: luca.risolia@studio.unibo.it
 P: 1024D/FCE635A4 88E8 F32F 7244 68BA 3958  5D40 99DA 5D2A FCE6 35A4
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 4873c759d535..c1eb41cb9876 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -142,3 +142,67 @@ Description:
                 with the previous I/O request are enabled. When set to 2,
                 all merge tries are disabled. The default value is 0 -
                 which enables all types of merge tries.
+
+What:           /sys/block/<disk>/discard_alignment
+Date:           May 2011
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Devices that support discard functionality may
+                internally allocate space in units that are bigger than
+                the exported logical block size. The discard_alignment
+                parameter indicates how many bytes the beginning of the
+                device is offset from the internal allocation unit's
+                natural alignment.
+
+What:           /sys/block/<disk>/<partition>/discard_alignment
+Date:           May 2011
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Devices that support discard functionality may
+                internally allocate space in units that are bigger than
+                the exported logical block size. The discard_alignment
+                parameter indicates how many bytes the beginning of the
+                partition is offset from the internal allocation unit's
+                natural alignment.
+
+What:           /sys/block/<disk>/queue/discard_granularity
+Date:           May 2011
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Devices that support discard functionality may
+                internally allocate space using units that are bigger
+                than the logical block size. The discard_granularity
+                parameter indicates the size of the internal allocation
+                unit in bytes if reported by the device. Otherwise the
+                discard_granularity will be set to match the device's
+                physical block size. A discard_granularity of 0 means
+                that the device does not support discard functionality.
+
+What:           /sys/block/<disk>/queue/discard_max_bytes
+Date:           May 2011
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Devices that support discard functionality may have
+                internal limits on the number of bytes that can be
+                trimmed or unmapped in a single operation. Some storage
+                protocols also have inherent limits on the number of
+                blocks that can be described in a single command. The
+                discard_max_bytes parameter is set by the device driver
+                to the maximum number of bytes that can be discarded in
+                a single operation. Discard requests issued to the
+                device must not exceed this limit. A discard_max_bytes
+                value of 0 means that the device does not support
+                discard functionality.
+
+What:           /sys/block/<disk>/queue/discard_zeroes_data
+Date:           May 2011
+Contact:        Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+                Devices that support discard functionality may return
+                stale or random data when a previously discarded block
+                is read back. This can cause problems if the filesystem
+                expects discarded blocks to be explicitly cleared. If a
+                device reports that it deterministically returns zeroes
+                when a discarded area is read the discard_zeroes_data
+                parameter will be set to one. Otherwise it will be 0 and
+                the result of reading a discarded area is undefined.
diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp
new file mode 100644
index 000000000000..d40d2b550502
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-ptp
@@ -0,0 +1,98 @@
+What:           /sys/class/ptp/
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This directory contains files and directories
+                providing a standardized interface to the ancillary
+                features of PTP hardware clocks.
+
+What:           /sys/class/ptp/ptpN/
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This directory contains the attributes of the Nth PTP
+                hardware clock registered into the PTP class driver
+                subsystem.
+
+What:           /sys/class/ptp/ptpN/clock_name
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file contains the name of the PTP hardware clock
+                as a human readable string.
+
+What:           /sys/class/ptp/ptpN/max_adjustment
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file contains the PTP hardware clock's maximum
+                frequency adjustment value (a positive integer) in
+                parts per billion.
+
+What:           /sys/class/ptp/ptpN/n_alarms
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file contains the number of periodic or one shot
+                alarms offer by the PTP hardware clock.
+
+What:           /sys/class/ptp/ptpN/n_external_timestamps
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file contains the number of external timestamp
+                channels offered by the PTP hardware clock.
+
+What:           /sys/class/ptp/ptpN/n_periodic_outputs
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file contains the number of programmable periodic
+                output channels offered by the PTP hardware clock.
+
+What:           /sys/class/ptp/ptpN/pps_avaiable
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file indicates whether the PTP hardware clock
+                supports a Pulse Per Second to the host CPU. Reading
+                "1" means that the PPS is supported, while "0" means
+                not supported.
+
+What:           /sys/class/ptp/ptpN/extts_enable
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This write-only file enables or disables external
+                timestamps. To enable external timestamps, write the
+                channel index followed by a "1" into the file.
+                To disable external timestamps, write the channel
+                index followed by a "0" into the file.
+
+What:           /sys/class/ptp/ptpN/fifo
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This file provides timestamps on external events, in
+                the form of three integers: channel index, seconds,
+                and nanoseconds.
+
+What:           /sys/class/ptp/ptpN/period
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This write-only file enables or disables periodic
+                outputs. To enable a periodic output, write five
+                integers into the file: channel index, start time
+                seconds, start time nanoseconds, period seconds, and
+                period nanoseconds. To disable a periodic output, set
+                all the seconds and nanoseconds values to zero.
+
+What:           /sys/class/ptp/ptpN/pps_enable
+Date:           September 2010
+Contact:        Richard Cochran <richardcochran@gmail.com>
+Description:
+                This write-only file enables or disables delivery of
+                PPS events to the Linux PPS subsystem. To enable PPS
+                events, write a "1" into the file. To disable events,
+                write a "0" into the file.
diff --git a/Documentation/IRQ-affinity.txt b/Documentation/IRQ-affinity.txt
index b4a615b78403..7890fae18529 100644
--- a/Documentation/IRQ-affinity.txt
+++ b/Documentation/IRQ-affinity.txt
@@ -4,10 +4,11 @@ ChangeLog:
 
 SMP IRQ affinity
 
-/proc/irq/IRQ#/smp_affinity specifies which target CPUs are permitted
-for a given IRQ source. It's a bitmask of allowed CPUs. It's not allowed
-to turn off all CPUs, and if an IRQ controller does not support IRQ
-affinity then the value will not change from the default 0xffffffff.
+/proc/irq/IRQ#/smp_affinity and /proc/irq/IRQ#/smp_affinity_list specify
+which target CPUs are permitted for a given IRQ source.  It's a bitmask
+(smp_affinity) or cpu list (smp_affinity_list) of allowed CPUs.  It's not
+allowed to turn off all CPUs, and if an IRQ controller does not support
+IRQ affinity then the value will not change from the default of all cpus.
 
 /proc/irq/default_smp_affinity specifies default affinity mask that applies
 to all non-active IRQs. Once IRQ is allocated/activated its affinity bitmask
@@ -54,3 +55,11 @@ round-trip min/avg/max = 0.1/0.5/585.4 ms
 This time around IRQ44 was delivered only to the last four processors.
 i.e counters for the CPU0-3 did not change.
 
+Here is an example of limiting that same irq (44) to cpus 1024 to 1031:
+
+[root@moon 44]# echo 1024-1031 > smp_affinity
+[root@moon 44]# cat smp_affinity
+1024-1031
+
+Note that to do this with a bitmask would require 32 bitmasks of zero
+to follow the pertinent one.
diff --git a/Documentation/blockdev/cciss.txt b/Documentation/blockdev/cciss.txt
index 89698e8df7d4..c00c6a5ab21f 100644
--- a/Documentation/blockdev/cciss.txt
+++ b/Documentation/blockdev/cciss.txt
@@ -169,3 +169,18 @@ is issued which positions the tape to a known position.  Typically you
 must rewind the tape (by issuing "mt -f /dev/st0 rewind" for example)
 before i/o can proceed again to a tape drive which was reset.
 
+There is a cciss_tape_cmds module parameter which can be used to make cciss
+allocate more commands for use by tape drives.  Ordinarily only a few commands
+(6) are allocated for tape drives because tape drives are slow and
+infrequently used and the primary purpose of Smart Array controllers is to
+act as a RAID controller for disk drives, so the vast majority of commands
+are allocated for disk devices.  However, if you have more than a few tape
+drives attached to a smart array, the default number of commands may not be
+enought (for example, if you have 8 tape drives, you could only rewind 6
+at one time with the default number of commands.)  The cciss_tape_cmds module
+parameter allows more commands (up to 16 more) to be allocated for use by
+tape drives.  For example:
+
+        insmod cciss.ko cciss_tape_cmds=16
+
+Or, as a kernel boot parameter passed in via grub:  cciss.cciss_tape_cmds=8
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index 9164ae3b83bc..9b728dc17535 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -16,7 +16,7 @@ on all processors in the system.  Don't let this scare you into
 thinking SMP cache/tlb flushing must be so inefficient, this is in
 fact an area where many optimizations are possible.  For example,
 if it can be proven that a user address space has never executed
-on a cpu (see vma->cpu_vm_mask), one need not perform a flush
+on a cpu (see mm_cpumask()), one need not perform a flush
 for this address space on that cpu.
 
 First, the TLB flushing interfaces, since they are the simplest.  The
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index edb7ae19e868..2c6be0377f55 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -74,3 +74,57 @@ Example:
                 interrupt-parent = <&mpic>;
                 phy-handle = <&phy0>
         };
+
+* Gianfar PTP clock nodes
+
+General Properties:
+
+  - compatible   Should be "fsl,etsec-ptp"
+  - reg          Offset and length of the register set for the device
+  - interrupts   There should be at least two interrupts. Some devices
+                 have as many as four PTP related interrupts.
+
+Clock Properties:
+
+  - fsl,tclk-period  Timer reference clock period in nanoseconds.
+  - fsl,tmr-prsc     Prescaler, divides the output clock.
+  - fsl,tmr-add      Frequency compensation value.
+  - fsl,tmr-fiper1   Fixed interval period pulse generator.
+  - fsl,tmr-fiper2   Fixed interval period pulse generator.
+  - fsl,max-adj      Maximum frequency adjustment in parts per billion.
+
+  These properties set the operational parameters for the PTP
+  clock. You must choose these carefully for the clock to work right.
+  Here is how to figure good values:
+
+  TimerOsc     = system clock               MHz
+  tclk_period  = desired clock period       nanoseconds
+  NominalFreq  = 1000 / tclk_period         MHz
+  FreqDivRatio = TimerOsc / NominalFreq     (must be greater that 1.0)
+  tmr_add      = ceil(2^32 / FreqDivRatio)
+  OutputClock  = NominalFreq / tmr_prsc     MHz
+  PulseWidth   = 1 / OutputClock            microseconds
+  FiperFreq1   = desired frequency in Hz
+  FiperDiv1    = 1000000 * OutputClock / FiperFreq1
+  tmr_fiper1   = tmr_prsc * tclk_period * FiperDiv1 - tclk_period
+  max_adj      = 1000000000 * (FreqDivRatio - 1.0) - 1
+
+  The calculation for tmr_fiper2 is the same as for tmr_fiper1. The
+  driver expects that tmr_fiper1 will be correctly set to produce a 1
+  Pulse Per Second (PPS) signal, since this will be offered to the PPS
+  subsystem to synchronize the Linux clock.
+
+Example:
+
+        ptp_clock@24E00 {
+                compatible = "fsl,etsec-ptp";
+                reg = <0x24E00 0xB0>;
+                interrupts = <12 0x8 13 0x8>;
+                interrupt-parent = < &ipic >;
+                fsl,tclk-period = <10>;
+                fsl,tmr-prsc    = <100>;
+                fsl,tmr-add     = <0x999999A4>;
+                fsl,tmr-fiper1  = <0x3B9AC9F6>;
+                fsl,tmr-fiper2  = <0x00018696>;
+                fsl,max-adj     = <659999998>;
+        };
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index b22abba78fed..13de64c7f0ab 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -25,6 +25,8 @@ Other applications are described in the following papers:
                 http://xcpu.org/papers/cellfs-talk.pdf
         * PROSE I/O: Using 9p to enable Application Partitions
                 http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf
+        * VirtFS: A Virtualization Aware File System pass-through
+                http://goo.gl/3WPDg
 
 USAGE
 =====
@@ -130,31 +132,20 @@ OPTIONS
 RESOURCES
 =========
 
-Our current recommendation is to use Inferno (http://www.vitanuova.com/nferno/index.html)
-as the 9p server.  You can start a 9p server under Inferno by issuing the
-following command:
-   ; styxlisten -A tcp!*!564 export '#U*'
+Protocol specifications are maintained on github:
+http://ericvh.github.com/9p-rfc/
 
-The -A specifies an unauthenticated export.  The 564 is the port # (you may
-have to choose a higher port number if running as a normal user).  The '#U*'
-specifies exporting the root of the Linux name space.  You may specify a
-subset of the namespace by extending the path: '#U*'/tmp would just export
-/tmp.  For more information, see the Inferno manual pages covering styxlisten
-and export.
+9p client and server implementations are listed on
+http://9p.cat-v.org/implementations
 
-A Linux version of the 9p server is now maintained under the npfs project
-on sourceforge (http://sourceforge.net/projects/npfs).  The currently
-maintained version is the single-threaded version of the server (named spfs)
-available from the same SVN repository.
+A 9p2000.L server is being developed by LLNL and can be found
+at http://code.google.com/p/diod/
 
 There are user and developer mailing lists available through the v9fs project
 on sourceforge (http://sourceforge.net/projects/v9fs).
 
-A stand-alone version of the module (which should build for any 2.6 kernel)
-is available via (http://github.com/ericvh/9p-sac/tree/master)
-
-News and other information is maintained on SWiK (http://swik.net/v9fs)
-and the Wiki (http://sf.net/apps/mediawiki/v9fs/index.php).
+News and other information is maintained on a Wiki.
+(http://sf.net/apps/mediawiki/v9fs/index.php).
 
 Bug reports may be issued through the kernel.org bugzilla 
 (http://bugzilla.kernel.org)
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 60740e8ecb37..f48178024067 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -574,6 +574,12 @@ The contents of each smp_affinity file is the same by default:
   > cat /proc/irq/0/smp_affinity
   ffffffff
 
+There is an alternate interface, smp_affinity_list which allows specifying
+a cpu range instead of a bitmask:
+
+  > cat /proc/irq/0/smp_affinity_list
+  1024-1031
+
 The default_smp_affinity mask applies to all non-active IRQs, which are the
 IRQs which have not yet been allocated/activated, and hence which lack a
 /proc/irq/[0-9]* directory.
@@ -583,12 +589,13 @@ reports itself as being attached. This hardware locality information does not
 include information about any possible driver locality preference.
 
 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
-profiler. Default value is ffffffff (all cpus).
+profiler. Default value is ffffffff (all cpus if there are only 32 of them).
 
 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
 between all the CPUs which are allowed to handle it. As usual the kernel has
 more info than you and does a better job than you, so the defaults are the
-best choice for almost everyone.
+best choice for almost everyone.  [Note this applies only to those IO-APIC's
+that support "Round Robin" interrupt distribution.]
 
 There are  three  more  important subdirectories in /proc: net, scsi, and sys.
 The general  rule  is  that  the  contents,  or  even  the  existence of these
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7c6624e7a5cb..5438a2d7907f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1777,9 +1777,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
         nosoftlockup    [KNL] Disable the soft-lockup detector.
 
-        noswapaccount   [KNL] Disable accounting of swap in memory resource
-                        controller. (See Documentation/cgroups/memory.txt)
-
         nosync          [HW,M68K] Disables sync negotiation for all devices.
 
         notsc           [BUGS=X86-32] Disable Time Stamp Counter
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
index 65f4c795015d..9c0a80d17a23 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/lockstat.txt
@@ -136,7 +136,7 @@ View the top contending locks:
                              dcache_lock:          1037           1161           0.38          45.32         774.51           6611         243371           0.15         306.48       77387.24
                          &inode->i_mutex:           161            286 18446744073709       62882.54     1244614.55           3653          20598 18446744073709       62318.60     1693822.74
                          &zone->lru_lock:            94             94           0.53           7.33          92.10           4366          32690           0.29          59.81       16350.06
-              &inode->i_data.i_mmap_lock:            79             79           0.40           3.77          53.03          11779          87755           0.28         116.93       29898.44
+              &inode->i_data.i_mmap_mutex:            79             79           0.40           3.77          53.03          11779          87755           0.28         116.93       29898.44
                         &q->__queue_lock:            48             50           0.52          31.62          86.31            774          13131           0.17         113.08       12277.52
                         &rq->rq_lock_key:            43             47           0.74          68.50         170.63           3706          33929           0.22         107.99       17460.62
                       &rq->rq_lock_key#2:            39             46           0.75           6.68          49.03           2979          32292           0.17         125.17       17137.63
diff --git a/Documentation/ptp/ptp.txt b/Documentation/ptp/ptp.txt
new file mode 100644
index 000000000000..ae8fef86b832
--- /dev/null
+++ b/Documentation/ptp/ptp.txt
@@ -0,0 +1,89 @@
+
+* PTP hardware clock infrastructure for Linux
+
+  This patch set introduces support for IEEE 1588 PTP clocks in
+  Linux. Together with the SO_TIMESTAMPING socket options, this
+  presents a standardized method for developing PTP user space
+  programs, synchronizing Linux with external clocks, and using the
+  ancillary features of PTP hardware clocks.
+
+  A new class driver exports a kernel interface for specific clock
+  drivers and a user space interface. The infrastructure supports a
+  complete set of PTP hardware clock functionality.
+
+  + Basic clock operations
+    - Set time
+    - Get time
+    - Shift the clock by a given offset atomically
+    - Adjust clock frequency
+
+  + Ancillary clock features
+    - One short or periodic alarms, with signal delivery to user program
+    - Time stamp external events
+    - Period output signals configurable from user space
+    - Synchronization of the Linux system time via the PPS subsystem
+
+** PTP hardware clock kernel API
+
+   A PTP clock driver registers itself with the class driver. The
+   class driver handles all of the dealings with user space. The
+   author of a clock driver need only implement the details of
+   programming the clock hardware. The clock driver notifies the class
+   driver of asynchronous events (alarms and external time stamps) via
+   a simple message passing interface.
+
+   The class driver supports multiple PTP clock drivers. In normal use
+   cases, only one PTP clock is needed. However, for testing and
+   development, it can be useful to have more than one clock in a
+   single system, in order to allow performance comparisons.
+
+** PTP hardware clock user space API
+
+   The class driver also creates a character device for each
+   registered clock. User space can use an open file descriptor from
+   the character device as a POSIX clock id and may call
+   clock_gettime, clock_settime, and clock_adjtime.  These calls
+   implement the basic clock operations.
+
+   User space programs may control the clock using standardized
+   ioctls. A program may query, enable, configure, and disable the
+   ancillary clock features. User space can receive time stamped
+   events via blocking read() and poll(). One shot and periodic
+   signals may be configured via the POSIX timer_settime() system
+   call.
+
+** Writing clock drivers
+
+   Clock drivers include include/linux/ptp_clock_kernel.h and register
+   themselves by presenting a 'struct ptp_clock_info' to the
+   registration method. Clock drivers must implement all of the
+   functions in the interface. If a clock does not offer a particular
+   ancillary feature, then the driver should just return -EOPNOTSUPP
+   from those functions.
+
+   Drivers must ensure that all of the methods in interface are
+   reentrant. Since most hardware implementations treat the time value
+   as a 64 bit integer accessed as two 32 bit registers, drivers
+   should use spin_lock_irqsave/spin_unlock_irqrestore to protect
+   against concurrent access. This locking cannot be accomplished in
+   class driver, since the lock may also be needed by the clock
+   driver's interrupt service routine.
+
+** Supported hardware
+
+   + Freescale eTSEC gianfar
+     - 2 Time stamp external triggers, programmable polarity (opt. interrupt)
+     - 2 Alarm registers (optional interrupt)
+     - 3 Periodic signals (optional interrupt)
+
+   + National DP83640
+     - 6 GPIOs programmable as inputs or outputs
+     - 6 GPIOs with dedicated functions (LED/JTAG/clock) can also be
+       used as general inputs or outputs
+     - GPIO inputs can time stamp external triggers
+     - GPIO outputs can produce periodic signals
+     - 1 interrupt pin
+
+   + Intel IXP465
+     - Auxiliary Slave/Master Mode Snapshot (optional interrupt)
+     - Target Time (optional interrupt)
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
new file mode 100644
index 000000000000..f59ded066108
--- /dev/null
+++ b/Documentation/ptp/testptp.c
@@ -0,0 +1,381 @@
+/*
+ * PTP 1588 clock support - User space test program
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <math.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/timex.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/ptp_clock.h>
+
+#define DEVICE "/dev/ptp0"
+
+#ifndef ADJ_SETOFFSET
+#define ADJ_SETOFFSET 0x0100
+#endif
+
+#ifndef CLOCK_INVALID
+#define CLOCK_INVALID -1
+#endif
+
+/* When glibc offers the syscall, this will go away. */
+#include <sys/syscall.h>
+static int clock_adjtime(clockid_t id, struct timex *tx)
+{
+        return syscall(__NR_clock_adjtime, id, tx);
+}
+
+static clockid_t get_clockid(int fd)
+{
+#define CLOCKFD 3
+#define FD_TO_CLOCKID(fd)       ((~(clockid_t) (fd) << 3) | CLOCKFD)
+
+        return FD_TO_CLOCKID(fd);
+}
+
+static void handle_alarm(int s)
+{
+        printf("received signal %d\n", s);
+}
+
+static int install_handler(int signum, void (*handler)(int))
+{
+        struct sigaction action;
+        sigset_t mask;
+
+        /* Unblock the signal. */
+        sigemptyset(&mask);
+        sigaddset(&mask, signum);
+        sigprocmask(SIG_UNBLOCK, &mask, NULL);
+
+        /* Install the signal handler. */
+        action.sa_handler = handler;
+        action.sa_flags = 0;
+        sigemptyset(&action.sa_mask);
+        sigaction(signum, &action, NULL);
+
+        return 0;
+}
+
+static long ppb_to_scaled_ppm(int ppb)
+{
+        /*
+         * The 'freq' field in the 'struct timex' is in parts per
+         * million, but with a 16 bit binary fractional field.
+         * Instead of calculating either one of
+         *
+         *    scaled_ppm = (ppb / 1000) << 16  [1]
+         *    scaled_ppm = (ppb << 16) / 1000  [2]
+         *
+         * we simply use double precision math, in order to avoid the
+         * truncation in [1] and the possible overflow in [2].
+         */
+        return (long) (ppb * 65.536);
+}
+
+static void usage(char *progname)
+{
+        fprintf(stderr,
+                "usage: %s [options]\n"
+                " -a val     request a one-shot alarm after 'val' seconds\n"
+                " -A val     request a periodic alarm every 'val' seconds\n"
+                " -c         query the ptp clock's capabilities\n"
+                " -d name    device to open\n"
+                " -e val     read 'val' external time stamp events\n"
+                " -f val     adjust the ptp clock frequency by 'val' ppb\n"
+                " -g         get the ptp clock time\n"
+                " -h         prints this message\n"
+                " -p val     enable output with a period of 'val' nanoseconds\n"
+                " -P val     enable or disable (val=1|0) the system clock PPS\n"
+                " -s         set the ptp clock time from the system time\n"
+                " -S         set the system time from the ptp clock time\n"
+                " -t val     shift the ptp clock time by 'val' seconds\n",
+                progname);
+}
+
+int main(int argc, char *argv[])
+{
+        struct ptp_clock_caps caps;
+        struct ptp_extts_event event;
+        struct ptp_extts_request extts_request;
+        struct ptp_perout_request perout_request;
+        struct timespec ts;
+        struct timex tx;
+
+        static timer_t timerid;
+        struct itimerspec timeout;
+        struct sigevent sigevent;
+
+        char *progname;
+        int c, cnt, fd;
+
+        char *device = DEVICE;
+        clockid_t clkid;
+        int adjfreq = 0x7fffffff;
+        int adjtime = 0;
+        int capabilities = 0;
+        int extts = 0;
+        int gettime = 0;
+        int oneshot = 0;
+        int periodic = 0;
+        int perout = -1;
+        int pps = -1;
+        int settime = 0;
+
+        progname = strrchr(argv[0], '/');
+        progname = progname ? 1+progname : argv[0];
+        while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghp:P:sSt:v"))) {
+                switch (c) {
+                case 'a':
+                        oneshot = atoi(optarg);
+                        break;
+                case 'A':
+                        periodic = atoi(optarg);
+                        break;
+                case 'c':
+                        capabilities = 1;
+                        break;
+                case 'd':
+                        device = optarg;
+                        break;
+                case 'e':
+                        extts = atoi(optarg);
+                        break;
+                case 'f':
+                        adjfreq = atoi(optarg);
+                        break;
+                case 'g':
+                        gettime = 1;
+                        break;
+                case 'p':
+                        perout = atoi(optarg);
+                        break;
+                case 'P':
+                        pps = atoi(optarg);
+                        break;
+                case 's':
+                        settime = 1;
+                        break;
+                case 'S':
+                        settime = 2;
+                        break;
+                case 't':
+                        adjtime = atoi(optarg);
+                        break;
+                case 'h':
+                        usage(progname);
+                        return 0;
+                case '?':
+                default:
+                        usage(progname);
+                        return -1;
+                }
+        }
+
+        fd = open(device, O_RDWR);
+        if (fd < 0) {
+                fprintf(stderr, "opening %s: %s\n", device, strerror(errno));
+                return -1;
+        }
+
+        clkid = get_clockid(fd);
+        if (CLOCK_INVALID == clkid) {
+                fprintf(stderr, "failed to read clock id\n");
+                return -1;
+        }
+
+        if (capabilities) {
+                if (ioctl(fd, PTP_CLOCK_GETCAPS, &caps)) {
+                        perror("PTP_CLOCK_GETCAPS");
+                } else {
+                        printf("capabilities:\n"
+                               "  %d maximum frequency adjustment (ppb)\n"
+                               "  %d programmable alarms\n"
+                               "  %d external time stamp channels\n"
+                               "  %d programmable periodic signals\n"
+                               "  %d pulse per second\n",
+                               caps.max_adj,
+                               caps.n_alarm,
+                               caps.n_ext_ts,
+                               caps.n_per_out,
+                               caps.pps);
+                }
+        }
+
+        if (0x7fffffff != adjfreq) {
+                memset(&tx, 0, sizeof(tx));
+                tx.modes = ADJ_FREQUENCY;
+                tx.freq = ppb_to_scaled_ppm(adjfreq);
+                if (clock_adjtime(clkid, &tx)) {
+                        perror("clock_adjtime");
+                } else {
+                        puts("frequency adjustment okay");
+                }
+        }
+
+        if (adjtime) {
+                memset(&tx, 0, sizeof(tx));
+                tx.modes = ADJ_SETOFFSET;
+                tx.time.tv_sec = adjtime;
+                tx.time.tv_usec = 0;
+                if (clock_adjtime(clkid, &tx) < 0) {
+                        perror("clock_adjtime");
+                } else {
+                        puts("time shift okay");
+                }
+        }
+
+        if (gettime) {
+                if (clock_gettime(clkid, &ts)) {
+                        perror("clock_gettime");
+                } else {
+                        printf("clock time: %ld.%09ld or %s",
+                               ts.tv_sec, ts.tv_nsec, ctime(&ts.tv_sec));
+                }
+        }
+
+        if (settime == 1) {
+                clock_gettime(CLOCK_REALTIME, &ts);
+                if (clock_settime(clkid, &ts)) {
+                        perror("clock_settime");
+                } else {
+                        puts("set time okay");
+                }
+        }
+
+        if (settime == 2) {
+                clock_gettime(clkid, &ts);
+                if (clock_settime(CLOCK_REALTIME, &ts)) {
+                        perror("clock_settime");
+                } else {
+                        puts("set time okay");
+                }
+        }
+
+        if (extts) {
+                memset(&extts_request, 0, sizeof(extts_request));
+                extts_request.index = 0;
+                extts_request.flags = PTP_ENABLE_FEATURE;
+                if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
+                        perror("PTP_EXTTS_REQUEST");
+                        extts = 0;
+                } else {
+                        puts("external time stamp request okay");
+                }
+                for (; extts; extts--) {
+                        cnt = read(fd, &event, sizeof(event));
+                        if (cnt != sizeof(event)) {
+                                perror("read");
+                                break;
+                        }
+                        printf("event index %u at %lld.%09u\n", event.index,
+                               event.t.sec, event.t.nsec);
+                        fflush(stdout);
+                }
+                /* Disable the feature again. */
+                extts_request.flags = 0;
+                if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
+                        perror("PTP_EXTTS_REQUEST");
+                }
+        }
+
+        if (oneshot) {
+                install_handler(SIGALRM, handle_alarm);
+                /* Create a timer. */
+                sigevent.sigev_notify = SIGEV_SIGNAL;
+                sigevent.sigev_signo = SIGALRM;
+                if (timer_create(clkid, &sigevent, &timerid)) {
+                        perror("timer_create");
+                        return -1;
+                }
+                /* Start the timer. */
+                memset(&timeout, 0, sizeof(timeout));
+                timeout.it_value.tv_sec = oneshot;
+                if (timer_settime(timerid, 0, &timeout, NULL)) {
+                        perror("timer_settime");
+                        return -1;
+                }
+                pause();
+                timer_delete(timerid);
+        }
+
+        if (periodic) {
+                install_handler(SIGALRM, handle_alarm);
+                /* Create a timer. */
+                sigevent.sigev_notify = SIGEV_SIGNAL;
+                sigevent.sigev_signo = SIGALRM;
+                if (timer_create(clkid, &sigevent, &timerid)) {
+                        perror("timer_create");
+                        return -1;
+                }
+                /* Start the timer. */
+                memset(&timeout, 0, sizeof(timeout));
+                timeout.it_interval.tv_sec = periodic;
+                timeout.it_value.tv_sec = periodic;
+                if (timer_settime(timerid, 0, &timeout, NULL)) {
+                        perror("timer_settime");
+                        return -1;
+                }
+                while (1) {
+                        pause();
+                }
+                timer_delete(timerid);
+        }
+
+        if (perout >= 0) {
+                if (clock_gettime(clkid, &ts)) {
+                        perror("clock_gettime");
+                        return -1;
+                }
+                memset(&perout_request, 0, sizeof(perout_request));
+                perout_request.index = 0;
+                perout_request.start.sec = ts.tv_sec + 2;
+                perout_request.start.nsec = 0;
+                perout_request.period.sec = 0;
+                perout_request.period.nsec = perout;
+                if (ioctl(fd, PTP_PEROUT_REQUEST, &perout_request)) {
+                        perror("PTP_PEROUT_REQUEST");
+                } else {
+                        puts("periodic output request okay");
+                }
+        }
+
+        if (pps != -1) {
+                int enable = pps ? 1 : 0;
+                if (ioctl(fd, PTP_ENABLE_PPS, enable)) {
+                        perror("PTP_ENABLE_PPS");
+                } else {
+                        puts("pps for system time request okay");
+                }
+        }
+
+        close(fd);
+        return 0;
+}
diff --git a/Documentation/ptp/testptp.mk b/Documentation/ptp/testptp.mk
new file mode 100644
index 000000000000..4ef2d9755421
--- /dev/null
+++ b/Documentation/ptp/testptp.mk
@@ -0,0 +1,33 @@
+# PTP 1588 clock support - User space test program
+#
+# Copyright (C) 2010 OMICRON electronics GmbH
+#
+#  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; either version 2 of the License, or
+#  (at your option) any later version.
+#
+#  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; if not, write to the Free Software
+#  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+CC        = $(CROSS_COMPILE)gcc
+INC       = -I$(KBUILD_OUTPUT)/usr/include
+CFLAGS    = -Wall $(INC)
+LDLIBS    = -lrt
+PROGS     = testptp
+
+all: $(PROGS)
+
+testptp: testptp.o
+
+clean:
+        rm -f testptp.o
+
+distclean: clean
+        rm -f $(PROGS)
diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index 9b7e1904db1c..5d0fc8bfcdb9 100644
--- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
@@ -1182,6 +1182,16 @@
   forge.net/>  and explains these in detail, as well as
   some other issues.
 
+  There is also a related point-to-point only "ucast" transport.
+  This is useful when your network does not support multicast, and
+  all network connections are simple point to point links.
+
+  The full set of command line options for this transport are
+
+
+       ethn=ucast,ethernet address,remote address,listen port,remote port
+
+
 
 
   66..66..  TTUUNN//TTAAPP wwiitthh tthhee uummll__nneett hheellppeerr
diff --git a/Documentation/vm/locking b/Documentation/vm/locking
index 25fadb448760..f61228bd6395 100644
--- a/Documentation/vm/locking
+++ b/Documentation/vm/locking
@@ -66,7 +66,7 @@ in some cases it is not really needed. Eg, vm_start is modified by
 expand_stack(), it is hard to come up with a destructive scenario without 
 having the vmlist protection in this case.
 
-The page_table_lock nests with the inode i_mmap_lock and the kmem cache
+The page_table_lock nests with the inode i_mmap_mutex and the kmem cache
 c_spinlock spinlocks.  This is okay, since the kmem code asks for pages after
 dropping c_spinlock.  The page_table_lock also nests with pagecache_lock and
 pagemap_lru_lock spinlocks, and no code asks for memory with these locks
diff --git a/MAINTAINERS b/MAINTAINERS
index 88a5bef09473..a26c9ee7703d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -287,35 +287,35 @@ F:	sound/pci/ad1889.*
 
 AD525X ANALOG DEVICES DIGITAL POTENTIOMETERS DRIVER
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/AD5254
 S:      Supported
 F:      drivers/misc/ad525x_dpot.c
 
 AD5398 CURRENT REGULATOR DRIVER (AD5398/AD5821)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/AD5398
 S:      Supported
 F:      drivers/regulator/ad5398.c
 
 AD714X CAPACITANCE TOUCH SENSOR DRIVER (AD7142/3/7/8/7A)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/AD7142
 S:      Supported
 F:      drivers/input/misc/ad714x.c
 
 AD7877 TOUCHSCREEN DRIVER
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/AD7877
 S:      Supported
 F:      drivers/input/touchscreen/ad7877.c
 
 AD7879 TOUCHSCREEN DRIVER (AD7879/AD7889)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/AD7879
 S:      Supported
 F:      drivers/input/touchscreen/ad7879.c
@@ -341,7 +341,7 @@ F:	drivers/net/wireless/adm8211.*
 
 ADP5520 BACKLIGHT DRIVER WITH IO EXPANDER (ADP5520/ADP5501)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/ADP5520
 S:      Supported
 F:      drivers/mfd/adp5520.c
@@ -352,7 +352,7 @@ F:	drivers/input/keyboard/adp5520-keys.c
 
 ADP5588 QWERTY KEYPAD AND IO EXPANDER DRIVER (ADP5588/ADP5587)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/ADP5588
 S:      Supported
 F:      drivers/input/keyboard/adp5588-keys.c
@@ -360,7 +360,7 @@ F:	drivers/gpio/adp5588-gpio.c
 
 ADP8860 BACKLIGHT DRIVER (ADP8860/ADP8861/ADP8863)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/ADP8860
 S:      Supported
 F:      drivers/video/backlight/adp8860_bl.c
@@ -387,7 +387,7 @@ F:	drivers/hwmon/adt7475.c
 
 ADXL34X THREE-AXIS DIGITAL ACCELEROMETER DRIVER (ADXL345/ADXL346)
 M:      Michael Hennerich <michael.hennerich@analog.com>
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 W:      http://wiki.analog.com/ADXL345
 S:      Supported
 F:      drivers/input/misc/adxl34x.c
@@ -533,7 +533,7 @@ S:	Maintained
 F:      drivers/infiniband/hw/amso1100/
 
 ANALOG DEVICES INC ASOC CODEC DRIVERS
-L:      device-driver-devel@blackfin.uclinux.org
+L:      device-drivers-devel@blackfin.uclinux.org
 L:      alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:      http://wiki.analog.com/
 S:      Supported
@@ -2041,9 +2041,8 @@ F:	net/ax25/ax25_timer.c
 F:      net/ax25/sysctl_net_ax25.c
 
 DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
-M:      Tobias Ringstrom <tori@unhappy.mine.nu>
 L:      netdev@vger.kernel.org
-S:      Maintained
+S:      Orphan
 F:      Documentation/networking/dmfe.txt
 F:      drivers/net/tulip/dmfe.c
 
@@ -3905,7 +3904,6 @@ F:	drivers/*/*/*pasemi*
 LINUX SECURITY MODULE (LSM) FRAMEWORK
 M:      Chris Wright <chrisw@sous-sol.org>
 L:      linux-security-module@vger.kernel.org
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/chrisw/lsm-2.6.git
 S:      Supported
 
 LIS3LV02D ACCELEROMETER DRIVER
diff --git a/Makefile b/Makefile
index 6b73d1eed1ea..529d93fa2430 100644
--- a/Makefile
+++ b/Makefile
@@ -220,6 +220,14 @@ ifeq ($(ARCH),sh64)
        SRCARCH := sh
 endif
 
+# Additional ARCH settings for tile
+ifeq ($(ARCH),tilepro)
+       SRCARCH := tile
+endif
+ifeq ($(ARCH),tilegx)
+       SRCARCH := tile
+endif
+
 # Where to locate arch specific headers
 hdr-arch  := $(SRCARCH)
 
@@ -1009,7 +1017,8 @@ include/generated/utsrelease.h: include/config/kernel.release FORCE
 
 PHONY += headerdep
 headerdep:
-        $(Q)find include/ -name '*.h' | xargs --max-args 1 scripts/headerdep.pl
+        $(Q)find $(srctree)/include/ -name '*.h' | xargs --max-args 1 \
+        $(srctree)/scripts/headerdep.pl -I$(srctree)/include
 
 # ---------------------------------------------------------------------------
 
@@ -1417,13 +1426,15 @@ tags TAGS cscope gtags: FORCE
 # Scripts to check various things for consistency
 # ---------------------------------------------------------------------------
 
+PHONY += includecheck versioncheck coccicheck namespacecheck export_report
+
 includecheck:
-        find * $(RCS_FIND_IGNORE) \
+        find $(srctree)/* $(RCS_FIND_IGNORE) \
                 -name '*.[hcS]' -type f -print | sort \
                 | xargs $(PERL) -w $(srctree)/scripts/checkincludes.pl
 
 versioncheck:
-        find * $(RCS_FIND_IGNORE) \
+        find $(srctree)/* $(RCS_FIND_IGNORE) \
                 -name '*.[hcS]' -type f -print | sort \
                 | xargs $(PERL) -w $(srctree)/scripts/checkversion.pl
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 8d24bacaa61e..26b0e2397a57 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -175,4 +175,7 @@ config HAVE_ARCH_JUMP_LABEL
 config HAVE_ARCH_MUTEX_CPU_RELAX
         bool
 
+config HAVE_RCU_TABLE_FREE
+        bool
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 9808998cc073..e3a82775f9da 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -12,6 +12,7 @@ config ALPHA
         select GENERIC_IRQ_PROBE
         select AUTO_IRQ_AFFINITY if SMP
         select GENERIC_IRQ_SHOW
+        select ARCH_WANT_OPTIONAL_GPIOLIB
         help
           The Alpha is a 64-bit general-purpose processor designed and
           marketed by the Digital Equipment Corporation of blessed memory,
@@ -51,6 +52,9 @@ config GENERIC_CALIBRATE_DELAY
 config GENERIC_CMOS_UPDATE
         def_bool y
 
+config GENERIC_GPIO
+        def_bool y
+
 config ZONE_DMA
         bool
         default y
diff --git a/arch/alpha/include/asm/gpio.h b/arch/alpha/include/asm/gpio.h
new file mode 100644
index 000000000000..7dc6a6343c06
--- /dev/null
+++ b/arch/alpha/include/asm/gpio.h
@@ -0,0 +1,55 @@
+/*
+ * Generic GPIO API implementation for Alpha.
+ *
+ * A stright copy of that for PowerPC which was:
+ *
+ * Copyright (c) 2007-2008  MontaVista Software, Inc.
+ *
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_ALPHA_GPIO_H
+#define _ASM_ALPHA_GPIO_H
+
+#include <linux/errno.h>
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+/*
+ * We don't (yet) implement inlined/rapid versions for on-chip gpios.
+ * Just call gpiolib.
+ */
+static inline int gpio_get_value(unsigned int gpio)
+{
+        return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned int gpio, int value)
+{
+        __gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned int gpio)
+{
+        return __gpio_cansleep(gpio);
+}
+
+static inline int gpio_to_irq(unsigned int gpio)
+{
+        return __gpio_to_irq(gpio);
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+        return -EINVAL;
+}
+
+#endif /* CONFIG_GPIOLIB */
+
+#endif /* _ASM_ALPHA_GPIO_H */
diff --git a/arch/alpha/include/asm/smp.h b/arch/alpha/include/asm/smp.h
index 3f390e8cc0b3..c46e714aa3e0 100644
--- a/arch/alpha/include/asm/smp.h
+++ b/arch/alpha/include/asm/smp.h
@@ -39,8 +39,6 @@ struct cpuinfo_alpha {
 
 extern struct cpuinfo_alpha cpu_data[NR_CPUS];
 
-#define PROC_CHANGE_PENALTY     20
-
 #define hard_smp_processor_id() __hard_smp_processor_id()
 #define raw_smp_processor_id()  (current_thread_info()->cpu)
 
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 3ec35066f1dc..838eac128409 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -121,7 +121,7 @@ common_shutdown_1(void *generic_ptr)
         /* Wait for the secondaries to halt. */
         set_cpu_present(boot_cpuid, false);
         set_cpu_possible(boot_cpuid, false);
-        while (cpus_weight(cpu_present_map))
+        while (cpumask_weight(cpu_present_mask))
                 barrier();
 #endif
 
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index edbddcbd5bc6..cc0fd862cf26 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -1257,7 +1257,7 @@ show_cpuinfo(struct seq_file *f, void *slot)
 #ifdef CONFIG_SMP
         seq_printf(f, "cpus active\t\t: %u\n"
                       "cpu active mask\t\t: %016lx\n",
-                       num_online_cpus(), cpus_addr(cpu_possible_map)[0]);
+                       num_online_cpus(), cpumask_bits(cpu_possible_mask)[0]);
 #endif
 
         show_cache_size (f, "L1 Icache", alpha_l1i_cacheshape);
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 5a621c6d22ab..d739703608fc 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -451,7 +451,7 @@ setup_smp(void)
         }
 
         printk(KERN_INFO "SMP: %d CPUs probed -- cpu_present_map = %lx\n",
-               smp_num_probed, cpu_present_map.bits[0]);
+               smp_num_probed, cpumask_bits(cpu_present_mask)[0]);
 }
 
 /*
@@ -629,8 +629,9 @@ smp_send_reschedule(int cpu)
 void
 smp_send_stop(void)
 {
-        cpumask_t to_whom = cpu_possible_map;
-        cpu_clear(smp_processor_id(), to_whom);
+        cpumask_t to_whom;
+        cpumask_copy(&to_whom, cpu_possible_mask);
+        cpumask_clear_cpu(smp_processor_id(), &to_whom);
 #ifdef DEBUG_IPI_MSG
         if (hard_smp_processor_id() != boot_cpu_id)
                 printk(KERN_WARNING "smp_send_stop: Not on boot cpu.\n");
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 5ac00fd4cd0c..f8856829c22a 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -140,7 +140,7 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 
         for (cpu = 0; cpu < 4; cpu++) {
                 unsigned long aff = cpu_irq_affinity[cpu];
-                if (cpu_isset(cpu, affinity))
+                if (cpumask_test_cpu(cpu, &affinity))
                         aff |= 1UL << irq;
                 else
                         aff &= ~(1UL << irq);
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index fea0e4620994..6994407e242a 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -65,10 +65,11 @@ titan_update_irq_hw(unsigned long mask)
         register int bcpu = boot_cpuid;
 
 #ifdef CONFIG_SMP
-        cpumask_t cpm = cpu_present_map;
+        cpumask_t cpm;
         volatile unsigned long *dim0, *dim1, *dim2, *dim3;
         unsigned long mask0, mask1, mask2, mask3, dummy;
 
+        cpumask_copy(&cpm, cpu_present_mask);
         mask &= ~isa_enable;
         mask0 = mask & titan_cpu_irq_affinity[0];
         mask1 = mask & titan_cpu_irq_affinity[1];
@@ -84,10 +85,10 @@ titan_update_irq_hw(unsigned long mask)
         dim1 = &cchip->dim1.csr;
         dim2 = &cchip->dim2.csr;
         dim3 = &cchip->dim3.csr;
-        if (!cpu_isset(0, cpm)) dim0 = &dummy;
-        if (!cpu_isset(1, cpm)) dim1 = &dummy;
-        if (!cpu_isset(2, cpm)) dim2 = &dummy;
-        if (!cpu_isset(3, cpm)) dim3 = &dummy;
+        if (!cpumask_test_cpu(0, &cpm)) dim0 = &dummy;
+        if (!cpumask_test_cpu(1, &cpm)) dim1 = &dummy;
+        if (!cpumask_test_cpu(2, &cpm)) dim2 = &dummy;
+        if (!cpumask_test_cpu(3, &cpm)) dim3 = &dummy;
 
         *dim0 = mask0;
         *dim1 = mask1;
@@ -137,7 +138,7 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
         int cpu;
 
         for (cpu = 0; cpu < 4; cpu++) {
-                if (cpu_isset(cpu, affinity))
+                if (cpumask_test_cpu(cpu, &affinity))
                         titan_cpu_irq_affinity[cpu] |= 1UL << irq;
                 else
                         titan_cpu_irq_affinity[cpu] &= ~(1UL << irq);
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 86425ab53bf5..69d0c5761e2f 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -32,8 +32,6 @@
 #include <asm/console.h>
 #include <asm/tlb.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 extern void die_if_kernel(char *,struct pt_regs *,long);
 
 static struct pcb_struct original_pcb;
diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c
index 7b2c56d8f930..3973ae395772 100644
--- a/arch/alpha/mm/numa.c
+++ b/arch/alpha/mm/numa.c
@@ -313,6 +313,7 @@ void __init paging_init(void)
                         zones_size[ZONE_DMA] = dma_local_pfn;
                         zones_size[ZONE_NORMAL] = (end_pfn - start_pfn) - dma_local_pfn;
                 }
+                node_set_state(nid, N_NORMAL_MEMORY);
                 free_area_init_node(nid, zones_size, start_pfn, NULL);
         }
 
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 03d01d783e3b..81cbe40c159c 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -63,13 +63,6 @@ config DEBUG_USER
               8 - SIGSEGV faults
              16 - SIGBUS faults
 
-config DEBUG_STACK_USAGE
-        bool "Enable stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T output.
-
 # These options are only for real kernel hackers who want to get their hands dirty.
 config DEBUG_LL
         bool "Kernel low-level debugging functions"
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index a87664f54f93..d2b514fd76f4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -20,12 +20,6 @@
 
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
-/*
- * at the moment, there's not a big penalty for changing CPUs
- * (the >big< penalty is running SMP in the first place)
- */
-#define PROC_CHANGE_PENALTY             15
-
 struct seq_file;
 
 /*
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 82dfe5d0c41e..265f908c4a6e 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -41,12 +41,12 @@
  */
 #if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7)
 #define tlb_fast_mode(tlb)      0
-#define FREE_PTE_NR             500
 #else
 #define tlb_fast_mode(tlb)      1
-#define FREE_PTE_NR             0
 #endif
 
+#define MMU_GATHER_BUNDLE       8
+
 /*
  * TLB handling.  This allows us to remove pages from the page
  * tables, and efficiently handle the TLB issues.
@@ -58,7 +58,9 @@ struct mmu_gather {
         unsigned long           range_start;
         unsigned long           range_end;
         unsigned int            nr;
-        struct page             *pages[FREE_PTE_NR];
+        unsigned int            max;
+        struct page             **pages;
+        struct page             *local[MMU_GATHER_BUNDLE];
 };
 
 DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
@@ -97,26 +99,37 @@ static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
         }
 }
 
+static inline void __tlb_alloc_page(struct mmu_gather *tlb)
+{
+        unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+
+        if (addr) {
+                tlb->pages = (void *)addr;
+                tlb->max = PAGE_SIZE / sizeof(struct page *);
+        }
+}
+
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
         tlb_flush(tlb);
         if (!tlb_fast_mode(tlb)) {
                 free_pages_and_swap_cache(tlb->pages, tlb->nr);
                 tlb->nr = 0;
+                if (tlb->pages == tlb->local)
+                        __tlb_alloc_page(tlb);
         }
 }
 
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
 {
-        struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
         tlb->mm = mm;
-        tlb->fullmm = full_mm_flush;
+        tlb->fullmm = fullmm;
         tlb->vma = NULL;
+        tlb->max = ARRAY_SIZE(tlb->local);
+        tlb->pages = tlb->local;
         tlb->nr = 0;
-
-        return tlb;
+        __tlb_alloc_page(tlb);
 }
 
 static inline void
@@ -127,7 +140,8 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
         /* keep the page table cache within bounds */
         check_pgt_cache();
 
-        put_cpu_var(mmu_gathers);
+        if (tlb->pages != tlb->local)
+                free_pages((unsigned long)tlb->pages, 0);
 }
 
 /*
@@ -162,15 +176,22 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
                 tlb_flush(tlb);
 }
 
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
         if (tlb_fast_mode(tlb)) {
                 free_page_and_swap_cache(page);
-        } else {
-                tlb->pages[tlb->nr++] = page;
-                if (tlb->nr >= FREE_PTE_NR)
-                        tlb_flush_mmu(tlb);
+                return 1; /* avoid calling tlb_flush_mmu */
         }
+
+        tlb->pages[tlb->nr++] = page;
+        VM_BUG_ON(tlb->nr > tlb->max);
+        return tlb->max - tlb->nr;
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        if (!__tlb_remove_page(tlb, page))
+                tlb_flush_mmu(tlb);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
diff --git a/arch/arm/mach-ixp4xx/include/mach/ixp46x_ts.h b/arch/arm/mach-ixp4xx/include/mach/ixp46x_ts.h
new file mode 100644
index 000000000000..292d55ed2113
--- /dev/null
+++ b/arch/arm/mach-ixp4xx/include/mach/ixp46x_ts.h
@@ -0,0 +1,78 @@
+/*
+ * PTP 1588 clock using the IXP46X
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _IXP46X_TS_H_
+#define _IXP46X_TS_H_
+
+#define DEFAULT_ADDEND 0xF0000029
+#define TICKS_NS_SHIFT 4
+
+struct ixp46x_channel_ctl {
+        u32 ch_control;  /* 0x40 Time Synchronization Channel Control */
+        u32 ch_event;    /* 0x44 Time Synchronization Channel Event */
+        u32 tx_snap_lo;  /* 0x48 Transmit Snapshot Low Register */
+        u32 tx_snap_hi;  /* 0x4C Transmit Snapshot High Register */
+        u32 rx_snap_lo;  /* 0x50 Receive Snapshot Low Register */
+        u32 rx_snap_hi;  /* 0x54 Receive Snapshot High Register */
+        u32 src_uuid_lo; /* 0x58 Source UUID0 Low Register */
+        u32 src_uuid_hi; /* 0x5C Sequence Identifier/Source UUID0 High */
+};
+
+struct ixp46x_ts_regs {
+        u32 control;     /* 0x00 Time Sync Control Register */
+        u32 event;       /* 0x04 Time Sync Event Register */
+        u32 addend;      /* 0x08 Time Sync Addend Register */
+        u32 accum;       /* 0x0C Time Sync Accumulator Register */
+        u32 test;        /* 0x10 Time Sync Test Register */
+        u32 unused;      /* 0x14 */
+        u32 rsystime_lo; /* 0x18 RawSystemTime_Low Register */
+        u32 rsystime_hi; /* 0x1C RawSystemTime_High Register */
+        u32 systime_lo;  /* 0x20 SystemTime_Low Register */
+        u32 systime_hi;  /* 0x24 SystemTime_High Register */
+        u32 trgt_lo;     /* 0x28 TargetTime_Low Register */
+        u32 trgt_hi;     /* 0x2C TargetTime_High Register */
+        u32 asms_lo;     /* 0x30 Auxiliary Slave Mode Snapshot Low  */
+        u32 asms_hi;     /* 0x34 Auxiliary Slave Mode Snapshot High */
+        u32 amms_lo;     /* 0x38 Auxiliary Master Mode Snapshot Low */
+        u32 amms_hi;     /* 0x3C Auxiliary Master Mode Snapshot High */
+
+        struct ixp46x_channel_ctl channel[3];
+};
+
+/* 0x00 Time Sync Control Register Bits */
+#define TSCR_AMM (1<<3)
+#define TSCR_ASM (1<<2)
+#define TSCR_TTM (1<<1)
+#define TSCR_RST (1<<0)
+
+/* 0x04 Time Sync Event Register Bits */
+#define TSER_SNM (1<<3)
+#define TSER_SNS (1<<2)
+#define TTIPEND  (1<<1)
+
+/* 0x40 Time Synchronization Channel Control Register Bits */
+#define MASTER_MODE   (1<<0)
+#define TIMESTAMP_ALL (1<<1)
+
+/* 0x44 Time Synchronization Channel Event Register Bits */
+#define TX_SNAPSHOT_LOCKED (1<<0)
+#define RX_SNAPSHOT_LOCKED (1<<1)
+
+#endif
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index 9afd087cc29c..23244cd0a5b6 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -37,8 +37,8 @@
 #include <plat/common.h>
 #include <plat/dma.h>
 #include <plat/gpmc.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 
 #include <plat/gpmc-smc91x.h>
 
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 56702c5e577f..93edd7fcf451 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -36,7 +36,7 @@
 #include <plat/usb.h>
 #include <plat/mmc.h>
 #include <plat/omap4-keypad.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #include "mux.h"
 #include "hsmmc.h"
@@ -680,6 +680,15 @@ static struct omap_dss_device sdp4430_hdmi_device = {
         .name = "hdmi",
         .driver_name = "hdmi_panel",
         .type = OMAP_DISPLAY_TYPE_HDMI,
+        .clocks = {
+                .dispc  = {
+                        .dispc_fclk_src = OMAP_DSS_CLK_SRC_FCK,
+                },
+                .hdmi   = {
+                        .regn   = 15,
+                        .regm2  = 1,
+                },
+        },
         .platform_enable = sdp4430_panel_enable_hdmi,
         .platform_disable = sdp4430_panel_disable_hdmi,
         .channel = OMAP_DSS_CHANNEL_DIGIT,
diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c
index ce7d5e6e4150..ff8c59be36e5 100644
--- a/arch/arm/mach-omap2/board-am3517evm.c
+++ b/arch/arm/mach-omap2/board-am3517evm.c
@@ -34,8 +34,8 @@
 #include <plat/board.h>
 #include <plat/common.h>
 #include <plat/usb.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 
 #include "mux.h"
 #include "control.h"
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index 02a12b41c0ff..9340f6a06f4a 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -45,8 +45,8 @@
 #include <plat/nand.h>
 #include <plat/gpmc.h>
 #include <plat/usb.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 #include <plat/mcspi.h>
 
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index 65f9fde2c567..1d1b56a29fb1 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -45,8 +45,8 @@
 #include <plat/gpmc.h>
 #include <plat/nand.h>
 #include <plat/usb.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 
 #include <plat/mcspi.h>
 #include <linux/input/matrix_keypad.h>
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 34cf982b9679..3da64d361651 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -31,8 +31,8 @@
 #include <plat/common.h>
 #include <plat/gpmc.h>
 #include <plat/usb.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 #include <plat/onenand.h>
 
 #include "mux.h"
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 33007fd4a083..97750d483a70 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -41,8 +41,8 @@
 
 #include <plat/board.h>
 #include <plat/common.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 #include <plat/gpmc.h>
 #include <plat/nand.h>
 #include <plat/usb.h>
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index 5a1a916e5cc8..7f94cccdb076 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -44,8 +44,8 @@
 #include <plat/usb.h>
 #include <plat/common.h>
 #include <plat/mcspi.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 
 #include "mux.h"
 #include "sdram-micron-mt46h32m32lf-6.h"
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 07dba888f450..1db15492d82b 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -46,7 +46,7 @@
 #include <mach/hardware.h>
 #include <plat/mcspi.h>
 #include <plat/usb.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/nand.h>
 
 #include "mux.h"
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index a6e0b9161c99..a72c90a08c8a 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -39,8 +39,8 @@
 #include <plat/gpmc.h>
 #include <plat/nand.h>
 #include <plat/usb.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 
 #include <plat/mcspi.h>
 #include <linux/input/matrix_keypad.h>
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index f3a7b1011914..e4973ac77cbc 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -34,13 +34,13 @@
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #include <plat/board.h>
 #include <plat/common.h>
 #include <plat/usb.h>
 #include <plat/mmc.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omap-panel-generic-dpi.h>
 #include "timer-gp.h"
 
 #include "hsmmc.h"
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 59ca33326b8c..9d192ff3b9ac 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -43,8 +43,8 @@
 
 #include <plat/board.h>
 #include <plat/common.h>
-#include <plat/display.h>
-#include <plat/panel-generic-dpi.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-generic-dpi.h>
 #include <mach/gpio.h>
 #include <plat/gpmc.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-omap2/board-rx51-video.c b/arch/arm/mach-omap2/board-rx51-video.c
index 89a66db8b77d..2df10b6a5940 100644
--- a/arch/arm/mach-omap2/board-rx51-video.c
+++ b/arch/arm/mach-omap2/board-rx51-video.c
@@ -15,7 +15,7 @@
 #include <linux/spi/spi.h>
 #include <linux/mm.h>
 #include <asm/mach-types.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/vram.h>
 #include <plat/mcspi.h>
 
diff --git a/arch/arm/mach-omap2/board-zoom-display.c b/arch/arm/mach-omap2/board-zoom-display.c
index 37b84c2b850f..60e8645db59d 100644
--- a/arch/arm/mach-omap2/board-zoom-display.c
+++ b/arch/arm/mach-omap2/board-zoom-display.c
@@ -15,7 +15,7 @@
 #include <linux/i2c/twl.h>
 #include <linux/spi/spi.h>
 #include <plat/mcspi.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define LCD_PANEL_RESET_GPIO_PROD       96
 #define LCD_PANEL_RESET_GPIO_PILOT      55
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 256d23fb79ab..543fcb8b518c 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -22,7 +22,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/omap_hwmod.h>
 #include <plat/omap_device.h>
 
@@ -56,37 +56,58 @@ static bool opt_clock_available(const char *clk_role)
         return false;
 }
 
+struct omap_dss_hwmod_data {
+        const char *oh_name;
+        const char *dev_name;
+        const int id;
+};
+
+static const struct omap_dss_hwmod_data omap2_dss_hwmod_data[] __initdata = {
+        { "dss_core", "omapdss_dss", -1 },
+        { "dss_dispc", "omapdss_dispc", -1 },
+        { "dss_rfbi", "omapdss_rfbi", -1 },
+        { "dss_venc", "omapdss_venc", -1 },
+};
+
+static const struct omap_dss_hwmod_data omap3_dss_hwmod_data[] __initdata = {
+        { "dss_core", "omapdss_dss", -1 },
+        { "dss_dispc", "omapdss_dispc", -1 },
+        { "dss_rfbi", "omapdss_rfbi", -1 },
+        { "dss_venc", "omapdss_venc", -1 },
+        { "dss_dsi1", "omapdss_dsi1", -1 },
+};
+
+static const struct omap_dss_hwmod_data omap4_dss_hwmod_data[] __initdata = {
+        { "dss_core", "omapdss_dss", -1 },
+        { "dss_dispc", "omapdss_dispc", -1 },
+        { "dss_rfbi", "omapdss_rfbi", -1 },
+        { "dss_venc", "omapdss_venc", -1 },
+        { "dss_dsi1", "omapdss_dsi1", -1 },
+        { "dss_dsi2", "omapdss_dsi2", -1 },
+        { "dss_hdmi", "omapdss_hdmi", -1 },
+};
+
 int __init omap_display_init(struct omap_dss_board_info *board_data)
 {
         int r = 0;
         struct omap_hwmod *oh;
         struct omap_device *od;
-        int i;
+        int i, oh_count;
         struct omap_display_platform_data pdata;
-
-        /*
-         * omap: valid DSS hwmod names
-         * omap2,3,4: dss_core, dss_dispc, dss_rfbi, dss_venc
-         * omap3,4: dss_dsi1
-         * omap4: dss_dsi2, dss_hdmi
-         */
-        char *oh_name[] = { "dss_core", "dss_dispc", "dss_rfbi", "dss_venc",
-                "dss_dsi1", "dss_dsi2", "dss_hdmi" };
-        char *dev_name[] = { "omapdss_dss", "omapdss_dispc", "omapdss_rfbi",
-                "omapdss_venc", "omapdss_dsi1", "omapdss_dsi2",
-                "omapdss_hdmi" };
-        int oh_count;
+        const struct omap_dss_hwmod_data *curr_dss_hwmod;
 
         memset(&pdata, 0, sizeof(pdata));
 
-        if (cpu_is_omap24xx())
-                oh_count = ARRAY_SIZE(oh_name) - 3;
-                /* last 3 hwmod dev in oh_name are not available for omap2 */
-        else if (cpu_is_omap44xx())
-                oh_count = ARRAY_SIZE(oh_name);
-        else
-                oh_count = ARRAY_SIZE(oh_name) - 2;
-                /* last 2 hwmod dev in oh_name are not available for omap3 */
+        if (cpu_is_omap24xx()) {
+                curr_dss_hwmod = omap2_dss_hwmod_data;
+                oh_count = ARRAY_SIZE(omap2_dss_hwmod_data);
+        } else if (cpu_is_omap34xx()) {
+                curr_dss_hwmod = omap3_dss_hwmod_data;
+                oh_count = ARRAY_SIZE(omap3_dss_hwmod_data);
+        } else {
+                curr_dss_hwmod = omap4_dss_hwmod_data;
+                oh_count = ARRAY_SIZE(omap4_dss_hwmod_data);
+        }
 
         /* opt_clks are always associated with dss hwmod */
         oh_core = omap_hwmod_lookup("dss_core");
@@ -100,19 +121,21 @@ int __init omap_display_init(struct omap_dss_board_info *board_data)
         pdata.opt_clock_available = opt_clock_available;
 
         for (i = 0; i < oh_count; i++) {
-                oh = omap_hwmod_lookup(oh_name[i]);
+                oh = omap_hwmod_lookup(curr_dss_hwmod[i].oh_name);
                 if (!oh) {
-                        pr_err("Could not look up %s\n", oh_name[i]);
+                        pr_err("Could not look up %s\n",
+                                curr_dss_hwmod[i].oh_name);
                         return -ENODEV;
                 }
 
-                od = omap_device_build(dev_name[i], -1, oh, &pdata,
+                od = omap_device_build(curr_dss_hwmod[i].dev_name,
+                                curr_dss_hwmod[i].id, oh, &pdata,
                                 sizeof(struct omap_display_platform_data),
                                 omap_dss_latency,
                                 ARRAY_SIZE(omap_dss_latency), 0);
 
                 if (WARN((IS_ERR(od)), "Could not build omap_device for %s\n",
-                                oh_name[i]))
+                                curr_dss_hwmod[i].oh_name))
                         return -ENODEV;
         }
         omap_display_device.dev.platform_data = board_data;
diff --git a/arch/arm/mach-omap2/include/mach/board-zoom.h b/arch/arm/mach-omap2/include/mach/board-zoom.h
index d20bd9c1a106..775fdc3b000b 100644
--- a/arch/arm/mach-omap2/include/mach/board-zoom.h
+++ b/arch/arm/mach-omap2/include/mach/board-zoom.h
@@ -1,7 +1,7 @@
 /*
  * Defines for zoom boards
  */
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define ZOOM_NAND_CS    0
 
diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile
index e2507f66f9d5..612b27000c3e 100644
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@@ -30,6 +30,11 @@ obj-$(CONFIG_ARCH_SH7377)	+= entry-intc.o
 obj-$(CONFIG_ARCH_SH7372)       += entry-intc.o
 obj-$(CONFIG_ARCH_SH73A0)       += entry-gic.o
 
+# PM objects
+obj-$(CONFIG_SUSPEND)           += suspend.o
+obj-$(CONFIG_CPU_IDLE)          += cpuidle.o
+obj-$(CONFIG_ARCH_SH7372)       += pm-sh7372.o sleep-sh7372.o
+
 # Board objects
 obj-$(CONFIG_MACH_G3EVM)        += board-g3evm.o
 obj-$(CONFIG_MACH_G4EVM)        += board-g4evm.o
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index 3e6f0aab460b..c95258c274c1 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -34,6 +34,8 @@
 #include <linux/input/sh_keysc.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/sh_mmcif.h>
+#include <linux/mmc/sh_mobile_sdhi.h>
+#include <linux/mfd/tmio.h>
 #include <linux/sh_clk.h>
 #include <video/sh_mobile_lcdc.h>
 #include <video/sh_mipi_dsi.h>
@@ -156,10 +158,19 @@ static struct resource sh_mmcif_resources[] = {
         },
 };
 
+static struct sh_mmcif_dma sh_mmcif_dma = {
+        .chan_priv_rx   = {
+                .slave_id       = SHDMA_SLAVE_MMCIF_RX,
+        },
+        .chan_priv_tx   = {
+                .slave_id       = SHDMA_SLAVE_MMCIF_TX,
+        },
+};
 static struct sh_mmcif_plat_data sh_mmcif_platdata = {
         .sup_pclk       = 0,
         .ocr            = MMC_VDD_165_195,
         .caps           = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+        .dma            = &sh_mmcif_dma,
 };
 
 static struct platform_device mmc_device = {
@@ -296,11 +307,13 @@ static struct platform_device lcdc0_device = {
 /* MIPI-DSI */
 static struct resource mipidsi0_resources[] = {
         [0] = {
+                .name   = "DSI0",
                 .start  = 0xfeab0000,
                 .end    = 0xfeab3fff,
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
+                .name   = "DSI0",
                 .start  = 0xfeab4000,
                 .end    = 0xfeab7fff,
                 .flags  = IORESOURCE_MEM,
@@ -325,6 +338,89 @@ static struct platform_device mipidsi0_device = {
         },
 };
 
+static struct sh_mobile_sdhi_info sdhi0_info = {
+        .dma_slave_tx   = SHDMA_SLAVE_SDHI0_TX,
+        .dma_slave_rx   = SHDMA_SLAVE_SDHI0_RX,
+        .tmio_caps      = MMC_CAP_SD_HIGHSPEED,
+        .tmio_ocr_mask  = MMC_VDD_27_28 | MMC_VDD_28_29,
+};
+
+static struct resource sdhi0_resources[] = {
+        [0] = {
+                .name   = "SDHI0",
+                .start  = 0xee100000,
+                .end    = 0xee1000ff,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .start  = gic_spi(83),
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = gic_spi(84),
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = gic_spi(85),
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device sdhi0_device = {
+        .name           = "sh_mobile_sdhi",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(sdhi0_resources),
+        .resource       = sdhi0_resources,
+        .dev    = {
+                .platform_data  = &sdhi0_info,
+        },
+};
+
+void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
+{
+        gpio_set_value(GPIO_PORT114, state);
+}
+
+static struct sh_mobile_sdhi_info sh_sdhi1_platdata = {
+        .dma_slave_tx   = SHDMA_SLAVE_SDHI1_TX,
+        .dma_slave_rx   = SHDMA_SLAVE_SDHI1_RX,
+        .tmio_flags     = TMIO_MMC_WRPROTECT_DISABLE,
+        .tmio_caps      = MMC_CAP_NONREMOVABLE,
+        .tmio_ocr_mask  = MMC_VDD_32_33 | MMC_VDD_33_34,
+        .set_pwr        = ag5evm_sdhi1_set_pwr,
+};
+
+static struct resource sdhi1_resources[] = {
+        [0] = {
+                .name   = "SDHI1",
+                .start  = 0xee120000,
+                .end    = 0xee1200ff,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .start  = gic_spi(87),
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = gic_spi(88),
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = gic_spi(89),
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device sdhi1_device = {
+        .name           = "sh_mobile_sdhi",
+        .id             = 1,
+        .dev            = {
+                .platform_data  = &sh_sdhi1_platdata,
+        },
+        .num_resources  = ARRAY_SIZE(sdhi1_resources),
+        .resource       = sdhi1_resources,
+};
+
 static struct platform_device *ag5evm_devices[] __initdata = {
         &eth_device,
         &keysc_device,
@@ -333,6 +429,8 @@ static struct platform_device *ag5evm_devices[] __initdata = {
         &irda_device,
         &lcdc0_device,
         &mipidsi0_device,
+        &sdhi0_device,
+        &sdhi1_device,
 };
 
 static struct map_desc ag5evm_io_desc[] __initdata = {
@@ -454,6 +552,26 @@ static void __init ag5evm_init(void)
         /* MIPI-DSI clock setup */
         __raw_writel(0x2a809010, DSI0PHYCR);
 
+        /* enable SDHI0 on CN15 [SD I/F] */
+        gpio_request(GPIO_FN_SDHICD0, NULL);
+        gpio_request(GPIO_FN_SDHIWP0, NULL);
+        gpio_request(GPIO_FN_SDHICMD0, NULL);
+        gpio_request(GPIO_FN_SDHICLK0, NULL);
+        gpio_request(GPIO_FN_SDHID0_3, NULL);
+        gpio_request(GPIO_FN_SDHID0_2, NULL);
+        gpio_request(GPIO_FN_SDHID0_1, NULL);
+        gpio_request(GPIO_FN_SDHID0_0, NULL);
+
+        /* enable SDHI1 on CN4 [WLAN I/F] */
+        gpio_request(GPIO_FN_SDHICLK1, NULL);
+        gpio_request(GPIO_FN_SDHICMD1_PU, NULL);
+        gpio_request(GPIO_FN_SDHID1_3_PU, NULL);
+        gpio_request(GPIO_FN_SDHID1_2_PU, NULL);
+        gpio_request(GPIO_FN_SDHID1_1_PU, NULL);
+        gpio_request(GPIO_FN_SDHID1_0_PU, NULL);
+        gpio_request(GPIO_PORT114, "sdhi1_power");
+        gpio_direction_output(GPIO_PORT114, 0);
+
 #ifdef CONFIG_CACHE_L2X0
         /* Shared attribute override enable, 64K*8way */
         l2x0_init(__io(0xf0100000), 0x00460000, 0xc2000fff);
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 1e35fa976d64..08acb6ec8139 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -316,8 +316,16 @@ static struct resource sdhi0_resources[] = {
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
-                .start  = evt2irq(0x0e00) /* SDHI0 */,
-                .flags  = IORESOURCE_IRQ,
+                .start  = evt2irq(0x0e00) /* SDHI0_SDHI0I0 */,
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = evt2irq(0x0e20) /* SDHI0_SDHI0I1 */,
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = evt2irq(0x0e40) /* SDHI0_SDHI0I2 */,
+                .flags  = IORESOURCE_IRQ,
         },
 };
 
@@ -349,8 +357,16 @@ static struct resource sdhi1_resources[] = {
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
-                .start  = evt2irq(0x0e80),
-                .flags  = IORESOURCE_IRQ,
+                .start  = evt2irq(0x0e80), /* SDHI1_SDHI1I0 */
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = evt2irq(0x0ea0), /* SDHI1_SDHI1I1 */
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = evt2irq(0x0ec0), /* SDHI1_SDHI1I2 */
+                .flags  = IORESOURCE_IRQ,
         },
 };
 
@@ -980,11 +996,6 @@ static void __init hdmi_init_pm_clock(void)
                 goto out;
         }
 
-        ret = clk_enable(&sh7372_pllc2_clk);
-        if (ret < 0) {
-                pr_err("Cannot enable pllc2 clock\n");
-                goto out;
-        }
         pr_debug("PLLC2 set frequency %lu\n", rate);
 
         ret = clk_set_parent(hdmi_ick, &sh7372_pllc2_clk);
@@ -1343,6 +1354,7 @@ static void __init ap4evb_init(void)
 
         hdmi_init_pm_clock();
         fsi_init_pm_clock();
+        sh7372_pm_init();
 }
 
 static void __init ap4evb_timer_init(void)
diff --git a/arch/arm/mach-shmobile/board-g4evm.c b/arch/arm/mach-shmobile/board-g4evm.c
index c87a7b7c5832..8e3c5559f27f 100644
--- a/arch/arm/mach-shmobile/board-g4evm.c
+++ b/arch/arm/mach-shmobile/board-g4evm.c
@@ -205,7 +205,7 @@ static struct resource sdhi0_resources[] = {
         [0] = {
                 .name   = "SDHI0",
                 .start  = 0xe6d50000,
-                .end    = 0xe6d50nff,
+                .end    = 0xe6d500ff,
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 7da2ca24229d..448ddbe43335 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -43,6 +43,7 @@
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
 #include <linux/usb/r8a66597.h>
+#include <linux/usb/renesas_usbhs.h>
 
 #include <video/sh_mobile_hdmi.h>
 #include <video/sh_mobile_lcdc.h>
@@ -143,7 +144,30 @@
  * open      | external VBUS | Function
  *
  * *1
- * CN31 is used as Host in Linux.
+ * CN31 is used as
+ * CONFIG_USB_R8A66597_HCD      Host
+ * CONFIG_USB_RENESAS_USBHS     Function
+ *
+ * CAUTION
+ *
+ * renesas_usbhs driver can use external interrupt mode
+ * (which come from USB-PHY) or autonomy mode (it use own interrupt)
+ * for detecting connection/disconnection when Function.
+ * USB will be power OFF while it has been disconnecting
+ * if external interrupt mode, and it is always power ON if autonomy mode,
+ *
+ * mackerel can not use external interrupt (IRQ7-PORT167) mode on "USB0",
+ * because Touchscreen is using IRQ7-PORT40.
+ * It is impossible to use IRQ7 demux on this board.
+ *
+ * We can use external interrupt mode USB-Function on "USB1".
+ * USB1 can become Host by r8a66597, and become Function by renesas_usbhs.
+ * But don't select both drivers in same time.
+ * These uses same IRQ number for request_irq(), and aren't supporting
+ * IRQF_SHARD / IORESOURCE_IRQ_SHAREABLE.
+ *
+ * Actually these are old/new version of USB driver.
+ * This mean its register will be broken if it supports SHARD IRQ,
  */
 
 /*
@@ -185,6 +209,7 @@
  * FIXME !!
  *
  * gpio_no_direction
+ * gpio_pull_down
  * are quick_hack.
  *
  * current gpio frame work doesn't have
@@ -196,6 +221,16 @@ static void __init gpio_no_direction(u32 addr)
         __raw_writeb(0x00, addr);
 }
 
+static void __init gpio_pull_down(u32 addr)
+{
+        u8 data = __raw_readb(addr);
+
+        data &= 0x0F;
+        data |= 0xA0;
+
+        __raw_writeb(data, addr);
+}
+
 /* MTD */
 static struct mtd_partition nor_flash_partitions[] = {
         {
@@ -458,12 +493,6 @@ static void __init hdmi_init_pm_clock(void)
                 goto out;
         }
 
-        ret = clk_enable(&sh7372_pllc2_clk);
-        if (ret < 0) {
-                pr_err("Cannot enable pllc2 clock\n");
-                goto out;
-        }
-
         pr_debug("PLLC2 set frequency %lu\n", rate);
 
         ret = clk_set_parent(hdmi_ick, &sh7372_pllc2_clk);
@@ -515,6 +544,157 @@ static struct platform_device usb1_host_device = {
         .resource       = usb1_host_resources,
 };
 
+/* USB1 (Function) */
+#define USB_PHY_MODE            (1 << 4)
+#define USB_PHY_INT_EN          ((1 << 3) | (1 << 2))
+#define USB_PHY_ON              (1 << 1)
+#define USB_PHY_OFF             (1 << 0)
+#define USB_PHY_INT_CLR         (USB_PHY_ON | USB_PHY_OFF)
+
+struct usbhs_private {
+        unsigned int irq;
+        unsigned int usbphyaddr;
+        unsigned int usbcrcaddr;
+        struct renesas_usbhs_platform_info info;
+};
+
+#define usbhs_get_priv(pdev)                            \
+        container_of(renesas_usbhs_get_info(pdev),      \
+                     struct usbhs_private, info)
+
+#define usbhs_is_connected(priv)                        \
+        (!((1 << 7) & __raw_readw(priv->usbcrcaddr)))
+
+static int usbhs1_get_id(struct platform_device *pdev)
+{
+        return USBHS_GADGET;
+}
+
+static int usbhs1_get_vbus(struct platform_device *pdev)
+{
+        return usbhs_is_connected(usbhs_get_priv(pdev));
+}
+
+static irqreturn_t usbhs1_interrupt(int irq, void *data)
+{
+        struct platform_device *pdev = data;
+        struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+        dev_dbg(&pdev->dev, "%s\n", __func__);
+
+        renesas_usbhs_call_notify_hotplug(pdev);
+
+        /* clear status */
+        __raw_writew(__raw_readw(priv->usbphyaddr) | USB_PHY_INT_CLR,
+                     priv->usbphyaddr);
+
+        return IRQ_HANDLED;
+}
+
+static int usbhs1_hardware_init(struct platform_device *pdev)
+{
+        struct usbhs_private *priv = usbhs_get_priv(pdev);
+        int ret;
+
+        irq_set_irq_type(priv->irq, IRQ_TYPE_LEVEL_HIGH);
+
+        /* clear interrupt status */
+        __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr);
+
+        ret = request_irq(priv->irq, usbhs1_interrupt, 0,
+                          dev_name(&pdev->dev), pdev);
+        if (ret) {
+                dev_err(&pdev->dev, "request_irq err\n");
+                return ret;
+        }
+
+        /* enable USB phy interrupt */
+        __raw_writew(USB_PHY_MODE | USB_PHY_INT_EN, priv->usbphyaddr);
+
+        return 0;
+}
+
+static void usbhs1_hardware_exit(struct platform_device *pdev)
+{
+        struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+        /* clear interrupt status */
+        __raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->usbphyaddr);
+
+        free_irq(priv->irq, pdev);
+}
+
+static void usbhs1_phy_reset(struct platform_device *pdev)
+{
+        struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+        /* init phy */
+        __raw_writew(0x8a0a, priv->usbcrcaddr);
+}
+
+static u32 usbhs1_pipe_cfg[] = {
+        USB_ENDPOINT_XFER_CONTROL,
+        USB_ENDPOINT_XFER_ISOC,
+        USB_ENDPOINT_XFER_ISOC,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_INT,
+        USB_ENDPOINT_XFER_INT,
+        USB_ENDPOINT_XFER_INT,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+        USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usbhs_private usbhs1_private = {
+        .irq            = evt2irq(0x0300),      /* IRQ8 */
+        .usbphyaddr     = 0xE60581E2,           /* USBPHY1INTAP */
+        .usbcrcaddr     = 0xE6058130,           /* USBCR4 */
+        .info = {
+                .platform_callback = {
+                        .hardware_init  = usbhs1_hardware_init,
+                        .hardware_exit  = usbhs1_hardware_exit,
+                        .phy_reset      = usbhs1_phy_reset,
+                        .get_id         = usbhs1_get_id,
+                        .get_vbus       = usbhs1_get_vbus,
+                },
+                .driver_param = {
+                        .buswait_bwait  = 4,
+                        .pipe_type      = usbhs1_pipe_cfg,
+                        .pipe_size      = ARRAY_SIZE(usbhs1_pipe_cfg),
+                },
+        },
+};
+
+static struct resource usbhs1_resources[] = {
+        [0] = {
+                .name   = "USBHS",
+                .start  = 0xE68B0000,
+                .end    = 0xE68B00E6 - 1,
+                .flags  = IORESOURCE_MEM,
+        },
+        [1] = {
+                .start  = evt2irq(0x1ce0) /* USB1_USB1I0 */,
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device usbhs1_device = {
+        .name   = "renesas_usbhs",
+        .id     = 1,
+        .dev = {
+                .platform_data          = &usbhs1_private.info,
+        },
+        .num_resources  = ARRAY_SIZE(usbhs1_resources),
+        .resource       = usbhs1_resources,
+};
+
+
 /* LED */
 static struct gpio_led mackerel_leds[] = {
         {
@@ -690,7 +870,15 @@ static struct resource sdhi0_resources[] = {
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
-                .start  = evt2irq(0x0e00) /* SDHI0 */,
+                .start  = evt2irq(0x0e00) /* SDHI0_SDHI0I0 */,
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = evt2irq(0x0e20) /* SDHI0_SDHI0I1 */,
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = evt2irq(0x0e40) /* SDHI0_SDHI0I2 */,
                 .flags  = IORESOURCE_IRQ,
         },
 };
@@ -705,7 +893,7 @@ static struct platform_device sdhi0_device = {
         },
 };
 
-#if !defined(CONFIG_MMC_SH_MMCIF)
+#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
 /* SDHI1 */
 static struct sh_mobile_sdhi_info sdhi1_info = {
         .dma_slave_tx   = SHDMA_SLAVE_SDHI1_TX,
@@ -725,7 +913,15 @@ static struct resource sdhi1_resources[] = {
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
-                .start  = evt2irq(0x0e80),
+                .start  = evt2irq(0x0e80), /* SDHI1_SDHI1I0 */
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = evt2irq(0x0ea0), /* SDHI1_SDHI1I1 */
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = evt2irq(0x0ec0), /* SDHI1_SDHI1I2 */
                 .flags  = IORESOURCE_IRQ,
         },
 };
@@ -768,7 +964,15 @@ static struct resource sdhi2_resources[] = {
                 .flags  = IORESOURCE_MEM,
         },
         [1] = {
-                .start  = evt2irq(0x1200),
+                .start  = evt2irq(0x1200), /* SDHI2_SDHI2I0 */
+                .flags  = IORESOURCE_IRQ,
+        },
+        [2] = {
+                .start  = evt2irq(0x1220), /* SDHI2_SDHI2I1 */
+                .flags  = IORESOURCE_IRQ,
+        },
+        [3] = {
+                .start  = evt2irq(0x1240), /* SDHI2_SDHI2I2 */
                 .flags  = IORESOURCE_IRQ,
         },
 };
@@ -803,6 +1007,15 @@ static struct resource sh_mmcif_resources[] = {
         },
 };
 
+static struct sh_mmcif_dma sh_mmcif_dma = {
+        .chan_priv_rx   = {
+                .slave_id       = SHDMA_SLAVE_MMCIF_RX,
+        },
+        .chan_priv_tx   = {
+                .slave_id       = SHDMA_SLAVE_MMCIF_TX,
+        },
+};
+
 static struct sh_mmcif_plat_data sh_mmcif_plat = {
         .sup_pclk       = 0,
         .ocr            = MMC_VDD_165_195 | MMC_VDD_32_33 | MMC_VDD_33_34,
@@ -810,6 +1023,7 @@ static struct sh_mmcif_plat_data sh_mmcif_plat = {
                           MMC_CAP_8_BIT_DATA |
                           MMC_CAP_NEEDS_POLL,
         .get_cd         = slot_cn7_get_cd,
+        .dma            = &sh_mmcif_dma,
 };
 
 static struct platform_device sh_mmcif_device = {
@@ -858,37 +1072,23 @@ static struct soc_camera_link camera_link = {
         .priv           = &camera_info,
 };
 
-static void dummy_release(struct device *dev)
+static struct platform_device *camera_device;
+
+static void mackerel_camera_release(struct device *dev)
 {
+        soc_camera_platform_release(&camera_device);
 }
 
-static struct platform_device camera_device = {
-        .name           = "soc_camera_platform",
-        .dev            = {
-                .platform_data  = &camera_info,
-                .release        = dummy_release,
-        },
-};
-
 static int mackerel_camera_add(struct soc_camera_link *icl,
                                struct device *dev)
 {
-        if (icl != &camera_link)
-                return -ENODEV;
-
-        camera_info.dev = dev;
-
-        return platform_device_register(&camera_device);
+        return soc_camera_platform_add(icl, dev, &camera_device, &camera_link,
+                                       mackerel_camera_release, 0);
 }
 
 static void mackerel_camera_del(struct soc_camera_link *icl)
 {
-        if (icl != &camera_link)
-                return;
-
-        platform_device_unregister(&camera_device);
-        memset(&camera_device.dev.kobj, 0,
-               sizeof(camera_device.dev.kobj));
+        soc_camera_platform_del(icl, camera_device, &camera_link);
 }
 
 static struct sh_mobile_ceu_info sh_mobile_ceu_info = {
@@ -935,12 +1135,13 @@ static struct platform_device *mackerel_devices[] __initdata = {
         &smc911x_device,
         &lcdc_device,
         &usb1_host_device,
+        &usbhs1_device,
         &leds_device,
         &fsi_device,
         &fsi_ak4643_device,
         &fsi_hdmi_device,
         &sdhi0_device,
-#if !defined(CONFIG_MMC_SH_MMCIF)
+#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
         &sdhi1_device,
 #endif
         &sdhi2_device,
@@ -1030,6 +1231,7 @@ static void __init mackerel_map_io(void)
 
 #define GPIO_PORT9CR    0xE6051009
 #define GPIO_PORT10CR   0xE605100A
+#define GPIO_PORT168CR  0xE60520A8
 #define SRCR4           0xe61580bc
 #define USCCR1          0xE6058144
 static void __init mackerel_init(void)
@@ -1088,6 +1290,7 @@ static void __init mackerel_init(void)
         gpio_request(GPIO_FN_OVCN_1_114, NULL);
         gpio_request(GPIO_FN_EXTLP_1,    NULL);
         gpio_request(GPIO_FN_OVCN2_1,    NULL);
+        gpio_pull_down(GPIO_PORT168CR);
 
         /* setup USB phy */
         __raw_writew(0x8a0a, 0xE6058130);       /* USBCR4 */
@@ -1140,7 +1343,7 @@ static void __init mackerel_init(void)
         gpio_request(GPIO_FN_SDHID0_1, NULL);
         gpio_request(GPIO_FN_SDHID0_0, NULL);
 
-#if !defined(CONFIG_MMC_SH_MMCIF)
+#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
         /* enable SDHI1 */
         gpio_request(GPIO_FN_SDHICMD1, NULL);
         gpio_request(GPIO_FN_SDHICLK1, NULL);
@@ -1216,6 +1419,7 @@ static void __init mackerel_init(void)
         platform_add_devices(mackerel_devices, ARRAY_SIZE(mackerel_devices));
 
         hdmi_init_pm_clock();
+        sh7372_pm_init();
 }
 
 static void __init mackerel_timer_init(void)
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index e9731b5a73ed..d17eb66f4ac2 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -44,6 +44,11 @@
 #define DSI1PCKCR       0xe6150098
 #define PLLC01CR        0xe6150028
 #define PLLC2CR         0xe615002c
+#define RMSTPCR0        0xe6150110
+#define RMSTPCR1        0xe6150114
+#define RMSTPCR2        0xe6150118
+#define RMSTPCR3        0xe615011c
+#define RMSTPCR4        0xe6150120
 #define SMSTPCR0        0xe6150130
 #define SMSTPCR1        0xe6150134
 #define SMSTPCR2        0xe6150138
@@ -421,9 +426,6 @@ static unsigned long fsidiv_recalc(struct clk *clk)
 
         value = __raw_readl(clk->mapping->base);
 
-        if ((value & 0x3) != 0x3)
-                return 0;
-
         value >>= 16;
         if (value < 2)
                 return 0;
@@ -504,7 +506,7 @@ static struct clk *late_main_clks[] = {
 enum { MSTP001,
        MSTP131, MSTP130,
        MSTP129, MSTP128, MSTP127, MSTP126, MSTP125,
-       MSTP118, MSTP117, MSTP116,
+       MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
        MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
@@ -527,6 +529,7 @@ static struct clk mstp_clks[MSTP_NR] = {
         [MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX */
         [MSTP117] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 17, 0), /* LCDC1 */
         [MSTP116] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 16, 0), /* IIC0 */
+        [MSTP113] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 13, 0), /* MERAM */
         [MSTP106] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 6, 0), /* JPU */
         [MSTP101] = MSTP(&div4_clks[DIV4_M1], SMSTPCR1, 1, 0), /* VPU */
         [MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
@@ -617,6 +620,7 @@ static struct clk_lookup lookups[] = {
         CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX0 */
         CLKDEV_DEV_ID("sh_mobile_lcdc_fb.1", &mstp_clks[MSTP117]), /* LCDC1 */
         CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* IIC0 */
+        CLKDEV_DEV_ID("sh_mobile_meram.0", &mstp_clks[MSTP113]), /* MERAM */
         CLKDEV_DEV_ID("uio_pdrv_genirq.5", &mstp_clks[MSTP106]), /* JPU */
         CLKDEV_DEV_ID("uio_pdrv_genirq.0", &mstp_clks[MSTP101]), /* VPU */
         CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
@@ -634,6 +638,7 @@ static struct clk_lookup lookups[] = {
         CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* IIC1 */
         CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP322]), /* USB0 */
         CLKDEV_DEV_ID("r8a66597_udc.0", &mstp_clks[MSTP322]), /* USB0 */
+        CLKDEV_DEV_ID("renesas_usbhs.0", &mstp_clks[MSTP322]), /* USB0 */
         CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */
         CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
         CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMC */
@@ -644,6 +649,7 @@ static struct clk_lookup lookups[] = {
         CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* IIC4 */
         CLKDEV_DEV_ID("r8a66597_hcd.1", &mstp_clks[MSTP406]), /* USB1 */
         CLKDEV_DEV_ID("r8a66597_udc.1", &mstp_clks[MSTP406]), /* USB1 */
+        CLKDEV_DEV_ID("renesas_usbhs.1", &mstp_clks[MSTP406]), /* USB1 */
         CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
 
         CLKDEV_ICK_ID("ick", "sh-mobile-hdmi", &div6_reparent_clks[DIV6_HDMI]),
@@ -655,6 +661,13 @@ void __init sh7372_clock_init(void)
 {
         int k, ret = 0;
 
+        /* make sure MSTP bits on the RT/SH4AL-DSP side are off */
+        __raw_writel(0xe4ef8087, RMSTPCR0);
+        __raw_writel(0xffffffff, RMSTPCR1);
+        __raw_writel(0x37c7f7ff, RMSTPCR2);
+        __raw_writel(0xffffffff, RMSTPCR3);
+        __raw_writel(0xffe0fffd, RMSTPCR4);
+
         for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
                 ret = clk_register(main_clks[k]);
 
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index 7e58904c1c8c..bcacb1e8cf85 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -266,7 +266,8 @@ enum { MSTP001,
         MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP100,
         MSTP219,
         MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-        MSTP331, MSTP329, MSTP325, MSTP323, MSTP312,
+        MSTP331, MSTP329, MSTP325, MSTP323, MSTP318,
+        MSTP314, MSTP313, MSTP312, MSTP311,
         MSTP411, MSTP410, MSTP403,
         MSTP_NR };
 
@@ -295,7 +296,11 @@ static struct clk mstp_clks[MSTP_NR] = {
         [MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
         [MSTP325] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 25, 0), /* IrDA */
         [MSTP323] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 23, 0), /* IIC1 */
+        [MSTP318] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 18, 0), /* SY-DMAC */
+        [MSTP314] = MSTP(&div6_clks[DIV6_SDHI0], SMSTPCR3, 14, 0), /* SDHI0 */
+        [MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */
         [MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */
+        [MSTP311] = MSTP(&div6_clks[DIV6_SDHI2], SMSTPCR3, 11, 0), /* SDHI2 */
         [MSTP411] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 11, 0), /* IIC3 */
         [MSTP410] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 10, 0), /* IIC4 */
         [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */
@@ -313,6 +318,9 @@ static struct clk_lookup lookups[] = {
         CLKDEV_CON_ID("vck1_clk", &div6_clks[DIV6_VCK1]),
         CLKDEV_CON_ID("vck2_clk", &div6_clks[DIV6_VCK2]),
         CLKDEV_CON_ID("vck3_clk", &div6_clks[DIV6_VCK3]),
+        CLKDEV_CON_ID("sdhi0_clk", &div6_clks[DIV6_SDHI0]),
+        CLKDEV_CON_ID("sdhi1_clk", &div6_clks[DIV6_SDHI1]),
+        CLKDEV_CON_ID("sdhi2_clk", &div6_clks[DIV6_SDHI2]),
         CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSIT]),
         CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.1", &div6_clks[DIV6_DSIT]),
         CLKDEV_ICK_ID("dsi0p_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSI0P]),
@@ -341,7 +349,11 @@ static struct clk_lookup lookups[] = {
         CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */
         CLKDEV_DEV_ID("sh_irda.0", &mstp_clks[MSTP325]), /* IrDA */
         CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* I2C1 */
+        CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP318]), /* SY-DMAC */
+        CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */
+        CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
         CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */
+        CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP311]), /* SDHI2 */
         CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* I2C3 */
         CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* I2C4 */
         CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
@@ -351,6 +363,11 @@ void __init sh73a0_clock_init(void)
 {
         int k, ret = 0;
 
+        /* Set SDHI clocks to a known state */
+        __raw_writel(0x108, SD0CKCR);
+        __raw_writel(0x108, SD1CKCR);
+        __raw_writel(0x108, SD2CKCR);
+
         /* detect main clock parent */
         switch ((__raw_readl(CKSCR) >> 24) & 0x03) {
         case 0:
diff --git a/arch/arm/mach-shmobile/cpuidle.c b/arch/arm/mach-shmobile/cpuidle.c
new file mode 100644
index 000000000000..2e44f11f592e
--- /dev/null
+++ b/arch/arm/mach-shmobile/cpuidle.c
@@ -0,0 +1,92 @@
+/*
+ * CPUIdle support code for SH-Mobile ARM
+ *
+ *  Copyright (C) 2011 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/pm.h>
+#include <linux/cpuidle.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <asm/system.h>
+#include <asm/io.h>
+
+static void shmobile_enter_wfi(void)
+{
+        cpu_do_idle();
+}
+
+void (*shmobile_cpuidle_modes[CPUIDLE_STATE_MAX])(void) = {
+        shmobile_enter_wfi, /* regular sleep mode */
+};
+
+static int shmobile_cpuidle_enter(struct cpuidle_device *dev,
+                                  struct cpuidle_state *state)
+{
+        ktime_t before, after;
+        int requested_state = state - &dev->states[0];
+
+        dev->last_state = &dev->states[requested_state];
+        before = ktime_get();
+
+        local_irq_disable();
+        local_fiq_disable();
+
+        shmobile_cpuidle_modes[requested_state]();
+
+        local_irq_enable();
+        local_fiq_enable();
+
+        after = ktime_get();
+        return ktime_to_ns(ktime_sub(after, before)) >> 10;
+}
+
+static struct cpuidle_device shmobile_cpuidle_dev;
+static struct cpuidle_driver shmobile_cpuidle_driver = {
+        .name =         "shmobile_cpuidle",
+        .owner =        THIS_MODULE,
+};
+
+void (*shmobile_cpuidle_setup)(struct cpuidle_device *dev);
+
+static int shmobile_cpuidle_init(void)
+{
+        struct cpuidle_device *dev = &shmobile_cpuidle_dev;
+        struct cpuidle_state *state;
+        int i;
+
+        cpuidle_register_driver(&shmobile_cpuidle_driver);
+
+        for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
+                dev->states[i].name[0] = '\0';
+                dev->states[i].desc[0] = '\0';
+                dev->states[i].enter = shmobile_cpuidle_enter;
+        }
+
+        i = CPUIDLE_DRIVER_STATE_START;
+
+        state = &dev->states[i++];
+        snprintf(state->name, CPUIDLE_NAME_LEN, "C1");
+        strncpy(state->desc, "WFI", CPUIDLE_DESC_LEN);
+        state->exit_latency = 1;
+        state->target_residency = 1 * 2;
+        state->power_usage = 3;
+        state->flags = 0;
+        state->flags |= CPUIDLE_FLAG_TIME_VALID;
+
+        dev->safe_state = state;
+        dev->state_count = i;
+
+        if (shmobile_cpuidle_setup)
+                shmobile_cpuidle_setup(dev);
+
+        cpuidle_register_device(dev);
+
+        return 0;
+}
+late_initcall(shmobile_cpuidle_init);
diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index d4cec6b4c7d9..26079d933d91 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -24,4 +24,4 @@
         .align  12
 ENTRY(shmobile_secondary_vector)
         ldr     pc, 1f
-1:      .long   secondary_startup - PAGE_OFFSET + PHYS_OFFSET
+1:      .long   secondary_startup - PAGE_OFFSET + PLAT_PHYS_OFFSET
diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h
index 013ac0ee8256..06aecb31d9c7 100644
--- a/arch/arm/mach-shmobile/include/mach/common.h
+++ b/arch/arm/mach-shmobile/include/mach/common.h
@@ -8,6 +8,10 @@ struct clk;
 extern int clk_init(void);
 extern void shmobile_handle_irq_intc(struct pt_regs *);
 extern void shmobile_handle_irq_gic(struct pt_regs *);
+extern struct platform_suspend_ops shmobile_suspend_ops;
+struct cpuidle_device;
+extern void (*shmobile_cpuidle_modes[])(void);
+extern void (*shmobile_cpuidle_setup)(struct cpuidle_device *dev);
 
 extern void sh7367_init_irq(void);
 extern void sh7367_add_early_devices(void);
@@ -30,6 +34,9 @@ extern void sh7372_add_early_devices(void);
 extern void sh7372_add_standard_devices(void);
 extern void sh7372_clock_init(void);
 extern void sh7372_pinmux_init(void);
+extern void sh7372_pm_init(void);
+extern void sh7372_cpu_suspend(void);
+extern void sh7372_cpu_resume(void);
 extern struct clk sh7372_extal1_clk;
 extern struct clk sh7372_extal2_clk;
 
diff --git a/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt b/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt
index 3029aba38688..9f134dfeffdc 100644
--- a/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt
+++ b/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt
@@ -87,8 +87,7 @@ WAIT 1, 0xFE40009C
 ED 0xFE400354, 0x01AD8002
 
 LIST "SCIF0 - Serial port for earlyprintk"
-EB 0xE6053098, 0x11
 EB 0xE6053098, 0xe1
 EW 0xE6C40000, 0x0000
 EB 0xE6C40004, 0x19
-EW 0xE6C40008, 0x3000
+EW 0xE6C40008, 0x0030
diff --git a/arch/arm/mach-shmobile/include/mach/head-mackerel.txt b/arch/arm/mach-shmobile/include/mach/head-mackerel.txt
index 3029aba38688..9f134dfeffdc 100644
--- a/arch/arm/mach-shmobile/include/mach/head-mackerel.txt
+++ b/arch/arm/mach-shmobile/include/mach/head-mackerel.txt
@@ -87,8 +87,7 @@ WAIT 1, 0xFE40009C
 ED 0xFE400354, 0x01AD8002
 
 LIST "SCIF0 - Serial port for earlyprintk"
-EB 0xE6053098, 0x11
 EB 0xE6053098, 0xe1
 EW 0xE6C40000, 0x0000
 EB 0xE6C40004, 0x19
-EW 0xE6C40008, 0x3000
+EW 0xE6C40008, 0x0030
diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h
index 5736efcca60c..df20d7670172 100644
--- a/arch/arm/mach-shmobile/include/mach/sh7372.h
+++ b/arch/arm/mach-shmobile/include/mach/sh7372.h
@@ -435,6 +435,7 @@ enum {
 
 /* DMA slave IDs */
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SCIF0_TX,
         SHDMA_SLAVE_SCIF0_RX,
         SHDMA_SLAVE_SCIF1_TX,
diff --git a/arch/arm/mach-shmobile/include/mach/sh73a0.h b/arch/arm/mach-shmobile/include/mach/sh73a0.h
index ceb2cdc92bf9..216c3d695ef1 100644
--- a/arch/arm/mach-shmobile/include/mach/sh73a0.h
+++ b/arch/arm/mach-shmobile/include/mach/sh73a0.h
@@ -463,5 +463,35 @@ enum {
         GPIO_FN_FSIAIBT_PU,
         GPIO_FN_FSIAISLD_PU,
 };
+/* DMA slave IDs */
+enum {
+        SHDMA_SLAVE_INVALID,
+        SHDMA_SLAVE_SCIF0_TX,
+        SHDMA_SLAVE_SCIF0_RX,
+        SHDMA_SLAVE_SCIF1_TX,
+        SHDMA_SLAVE_SCIF1_RX,
+        SHDMA_SLAVE_SCIF2_TX,
+        SHDMA_SLAVE_SCIF2_RX,
+        SHDMA_SLAVE_SCIF3_TX,
+        SHDMA_SLAVE_SCIF3_RX,
+        SHDMA_SLAVE_SCIF4_TX,
+        SHDMA_SLAVE_SCIF4_RX,
+        SHDMA_SLAVE_SCIF5_TX,
+        SHDMA_SLAVE_SCIF5_RX,
+        SHDMA_SLAVE_SCIF6_TX,
+        SHDMA_SLAVE_SCIF6_RX,
+        SHDMA_SLAVE_SCIF7_TX,
+        SHDMA_SLAVE_SCIF7_RX,
+        SHDMA_SLAVE_SCIF8_TX,
+        SHDMA_SLAVE_SCIF8_RX,
+        SHDMA_SLAVE_SDHI0_TX,
+        SHDMA_SLAVE_SDHI0_RX,
+        SHDMA_SLAVE_SDHI1_TX,
+        SHDMA_SLAVE_SDHI1_RX,
+        SHDMA_SLAVE_SDHI2_TX,
+        SHDMA_SLAVE_SDHI2_RX,
+        SHDMA_SLAVE_MMCIF_TX,
+        SHDMA_SLAVE_MMCIF_RX,
+};
 
 #endif /* __ASM_SH73A0_H__ */
diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c
index 7a4960f9c1e3..3b28743c77eb 100644
--- a/arch/arm/mach-shmobile/intc-sh7372.c
+++ b/arch/arm/mach-shmobile/intc-sh7372.c
@@ -27,8 +27,6 @@
 
 enum {
         UNUSED_INTCA = 0,
-        ENABLED,
-        DISABLED,
 
         /* interrupt sources INTCA */
         IRQ0A, IRQ1A, IRQ2A, IRQ3A, IRQ4A, IRQ5A, IRQ6A, IRQ7A,
@@ -49,14 +47,14 @@ enum {
         MSIOF2, MSIOF1,
         SCIFA4, SCIFA5, SCIFB,
         FLCTL_FLSTEI, FLCTL_FLTENDI, FLCTL_FLTREQ0I, FLCTL_FLTREQ1I,
-        SDHI0,
-        SDHI1,
+        SDHI0_SDHI0I0, SDHI0_SDHI0I1, SDHI0_SDHI0I2, SDHI0_SDHI0I3,
+        SDHI1_SDHI1I0, SDHI1_SDHI1I1, SDHI1_SDHI1I2,
         IRREM,
         IRDA,
         TPU0,
         TTI20,
         DDM,
-        SDHI2,
+        SDHI2_SDHI2I0, SDHI2_SDHI2I1, SDHI2_SDHI2I2, SDHI2_SDHI2I3,
         RWDT0,
         DMAC1_1_DEI0, DMAC1_1_DEI1, DMAC1_1_DEI2, DMAC1_1_DEI3,
         DMAC1_2_DEI4, DMAC1_2_DEI5, DMAC1_2_DADERR,
@@ -84,7 +82,7 @@ enum {
 
         /* interrupt groups INTCA */
         DMAC1_1, DMAC1_2, DMAC2_1, DMAC2_2, DMAC3_1, DMAC3_2, SHWYSTAT,
-        AP_ARM1, AP_ARM2, SPU2, FLCTL, IIC1
+        AP_ARM1, AP_ARM2, SPU2, FLCTL, IIC1, SDHI0, SDHI1, SDHI2
 };
 
 static struct intc_vect intca_vectors[] __initdata = {
@@ -125,17 +123,17 @@ static struct intc_vect intca_vectors[] __initdata = {
         INTC_VECT(SCIFB, 0x0d60),
         INTC_VECT(FLCTL_FLSTEI, 0x0d80), INTC_VECT(FLCTL_FLTENDI, 0x0da0),
         INTC_VECT(FLCTL_FLTREQ0I, 0x0dc0), INTC_VECT(FLCTL_FLTREQ1I, 0x0de0),
-        INTC_VECT(SDHI0, 0x0e00), INTC_VECT(SDHI0, 0x0e20),
-        INTC_VECT(SDHI0, 0x0e40), INTC_VECT(SDHI0, 0x0e60),
-        INTC_VECT(SDHI1, 0x0e80), INTC_VECT(SDHI1, 0x0ea0),
-        INTC_VECT(SDHI1, 0x0ec0),
+        INTC_VECT(SDHI0_SDHI0I0, 0x0e00), INTC_VECT(SDHI0_SDHI0I1, 0x0e20),
+        INTC_VECT(SDHI0_SDHI0I2, 0x0e40), INTC_VECT(SDHI0_SDHI0I3, 0x0e60),
+        INTC_VECT(SDHI1_SDHI1I0, 0x0e80), INTC_VECT(SDHI1_SDHI1I1, 0x0ea0),
+        INTC_VECT(SDHI1_SDHI1I2, 0x0ec0),
         INTC_VECT(IRREM, 0x0f60),
         INTC_VECT(IRDA, 0x0480),
         INTC_VECT(TPU0, 0x04a0),
         INTC_VECT(TTI20, 0x1100),
         INTC_VECT(DDM, 0x1140),
-        INTC_VECT(SDHI2, 0x1200), INTC_VECT(SDHI2, 0x1220),
-        INTC_VECT(SDHI2, 0x1240), INTC_VECT(SDHI2, 0x1260),
+        INTC_VECT(SDHI2_SDHI2I0, 0x1200), INTC_VECT(SDHI2_SDHI2I1, 0x1220),
+        INTC_VECT(SDHI2_SDHI2I2, 0x1240), INTC_VECT(SDHI2_SDHI2I3, 0x1260),
         INTC_VECT(RWDT0, 0x1280),
         INTC_VECT(DMAC1_1_DEI0, 0x2000), INTC_VECT(DMAC1_1_DEI1, 0x2020),
         INTC_VECT(DMAC1_1_DEI2, 0x2040), INTC_VECT(DMAC1_1_DEI3, 0x2060),
@@ -195,6 +193,12 @@ static struct intc_group intca_groups[] __initdata = {
         INTC_GROUP(FLCTL, FLCTL_FLSTEI, FLCTL_FLTENDI,
                    FLCTL_FLTREQ0I, FLCTL_FLTREQ1I),
         INTC_GROUP(IIC1, IIC1_ALI1, IIC1_TACKI1, IIC1_WAITI1, IIC1_DTEI1),
+        INTC_GROUP(SDHI0, SDHI0_SDHI0I0, SDHI0_SDHI0I1,
+                   SDHI0_SDHI0I2, SDHI0_SDHI0I3),
+        INTC_GROUP(SDHI1, SDHI1_SDHI1I0, SDHI1_SDHI1I1,
+                   SDHI1_SDHI1I2),
+        INTC_GROUP(SDHI2, SDHI2_SDHI2I0, SDHI2_SDHI2I1,
+                   SDHI2_SDHI2I2, SDHI2_SDHI2I3),
         INTC_GROUP(SHWYSTAT, SHWYSTAT_RT, SHWYSTAT_HS, SHWYSTAT_COM),
 };
 
@@ -230,10 +234,10 @@ static struct intc_mask_reg intca_mask_registers[] __initdata = {
           { SCIFB, SCIFA5, SCIFA4, MSIOF1,
             0, 0, MSIOF2, 0 } },
         { 0xe694009c, 0xe69400dc, 8, /* IMR7A / IMCR7A */
-          { DISABLED, ENABLED, ENABLED, ENABLED,
+          { SDHI0_SDHI0I3, SDHI0_SDHI0I2, SDHI0_SDHI0I1, SDHI0_SDHI0I0,
             FLCTL_FLTREQ1I, FLCTL_FLTREQ0I, FLCTL_FLTENDI, FLCTL_FLSTEI } },
         { 0xe69400a0, 0xe69400e0, 8, /* IMR8A / IMCR8A */
-          { 0, ENABLED, ENABLED, ENABLED,
+          { 0, SDHI1_SDHI1I2, SDHI1_SDHI1I1, SDHI1_SDHI1I0,
             TTI20, USBHSDMAC0_USHDMI, 0, 0 } },
         { 0xe69400a4, 0xe69400e4, 8, /* IMR9A / IMCR9A */
           { CMT1_CMT13, CMT1_CMT12, CMT1_CMT11, CMT1_CMT10,
@@ -248,7 +252,7 @@ static struct intc_mask_reg intca_mask_registers[] __initdata = {
           { 0, 0, TPU0, 0,
             0, 0, 0, 0 } },
         { 0xe69400b4, 0xe69400f4, 8, /* IMR13A / IMCR13A */
-          { DISABLED, DISABLED, ENABLED, ENABLED,
+          { SDHI2_SDHI2I3, SDHI2_SDHI2I2, SDHI2_SDHI2I1, SDHI2_SDHI2I0,
             0, CMT3, 0, RWDT0 } },
         { 0xe6950080, 0xe69500c0, 8, /* IMR0A3 / IMCR0A3 */
           { SHWYSTAT_RT, SHWYSTAT_HS, SHWYSTAT_COM, 0,
@@ -354,14 +358,10 @@ static struct intc_mask_reg intca_ack_registers[] __initdata = {
           { IRQ24A, IRQ25A, IRQ26A, IRQ27A, IRQ28A, IRQ29A, IRQ30A, IRQ31A } },
 };
 
-static struct intc_desc intca_desc __initdata = {
-        .name = "sh7372-intca",
-        .force_enable = ENABLED,
-        .force_disable = DISABLED,
-        .hw = INTC_HW_DESC(intca_vectors, intca_groups,
-                           intca_mask_registers, intca_prio_registers,
-                           intca_sense_registers, intca_ack_registers),
-};
+static DECLARE_INTC_DESC_ACK(intca_desc, "sh7372-intca",
+                             intca_vectors, intca_groups,
+                             intca_mask_registers, intca_prio_registers,
+                             intca_sense_registers, intca_ack_registers);
 
 enum {
         UNUSED_INTCS = 0,
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
new file mode 100644
index 000000000000..8e4aadf14c9f
--- /dev/null
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -0,0 +1,108 @@
+/*
+ * sh7372 Power management support
+ *
+ *  Copyright (C) 2011 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/pm.h>
+#include <linux/suspend.h>
+#include <linux/cpuidle.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/tlbflush.h>
+#include <mach/common.h>
+
+#define SMFRAM 0xe6a70000
+#define SYSTBCR 0xe6150024
+#define SBAR 0xe6180020
+#define APARMBAREA 0xe6f10020
+
+static void sh7372_enter_core_standby(void)
+{
+        void __iomem *smfram = (void __iomem *)SMFRAM;
+
+        __raw_writel(0, APARMBAREA); /* translate 4k */
+        __raw_writel(__pa(sh7372_cpu_resume), SBAR); /* set reset vector */
+        __raw_writel(0x10, SYSTBCR); /* enable core standby */
+
+        __raw_writel(0, smfram + 0x3c); /* clear page table address */
+
+        sh7372_cpu_suspend();
+        cpu_init();
+
+        /* if page table address is non-NULL then we have been powered down */
+        if (__raw_readl(smfram + 0x3c)) {
+                __raw_writel(__raw_readl(smfram + 0x40),
+                             __va(__raw_readl(smfram + 0x3c)));
+
+                flush_tlb_all();
+                set_cr(__raw_readl(smfram + 0x38));
+        }
+
+        __raw_writel(0, SYSTBCR); /* disable core standby */
+        __raw_writel(0, SBAR); /* disable reset vector translation */
+}
+
+#ifdef CONFIG_CPU_IDLE
+static void sh7372_cpuidle_setup(struct cpuidle_device *dev)
+{
+        struct cpuidle_state *state;
+        int i = dev->state_count;
+
+        state = &dev->states[i];
+        snprintf(state->name, CPUIDLE_NAME_LEN, "C2");
+        strncpy(state->desc, "Core Standby Mode", CPUIDLE_DESC_LEN);
+        state->exit_latency = 10;
+        state->target_residency = 20 + 10;
+        state->power_usage = 1; /* perhaps not */
+        state->flags = 0;
+        state->flags |= CPUIDLE_FLAG_TIME_VALID;
+        shmobile_cpuidle_modes[i] = sh7372_enter_core_standby;
+
+        dev->state_count = i + 1;
+}
+
+static void sh7372_cpuidle_init(void)
+{
+        shmobile_cpuidle_setup = sh7372_cpuidle_setup;
+}
+#else
+static void sh7372_cpuidle_init(void) {}
+#endif
+
+#ifdef CONFIG_SUSPEND
+static int sh7372_enter_suspend(suspend_state_t suspend_state)
+{
+        sh7372_enter_core_standby();
+        return 0;
+}
+
+static void sh7372_suspend_init(void)
+{
+        shmobile_suspend_ops.enter = sh7372_enter_suspend;
+}
+#else
+static void sh7372_suspend_init(void) {}
+#endif
+
+#define DBGREG1 0xe6100020
+#define DBGREG9 0xe6100040
+
+void __init sh7372_pm_init(void)
+{
+        /* enable DBG hardware block to kick SYSC */
+        __raw_writel(0x0000a500, DBGREG9);
+        __raw_writel(0x0000a501, DBGREG9);
+        __raw_writel(0x00000000, DBGREG1);
+
+        sh7372_suspend_init();
+        sh7372_cpuidle_init();
+}
diff --git a/arch/arm/mach-shmobile/setup-sh7367.c b/arch/arm/mach-shmobile/setup-sh7367.c
index ce28141662da..2c10190dbb55 100644
--- a/arch/arm/mach-shmobile/setup-sh7367.c
+++ b/arch/arm/mach-shmobile/setup-sh7367.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/platform_device.h>
+#include <linux/uio_driver.h>
 #include <linux/delay.h>
 #include <linux/input.h>
 #include <linux/io.h>
@@ -195,6 +196,214 @@ static struct platform_device cmt10_device = {
         .num_resources  = ARRAY_SIZE(cmt10_resources),
 };
 
+/* VPU */
+static struct uio_info vpu_platform_data = {
+        .name = "VPU5",
+        .version = "0",
+        .irq = intcs_evt2irq(0x980),
+};
+
+static struct resource vpu_resources[] = {
+        [0] = {
+                .name   = "VPU",
+                .start  = 0xfe900000,
+                .end    = 0xfe902807,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device vpu_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 0,
+        .dev = {
+                .platform_data  = &vpu_platform_data,
+        },
+        .resource       = vpu_resources,
+        .num_resources  = ARRAY_SIZE(vpu_resources),
+};
+
+/* VEU0 */
+static struct uio_info veu0_platform_data = {
+        .name = "VEU0",
+        .version = "0",
+        .irq = intcs_evt2irq(0x700),
+};
+
+static struct resource veu0_resources[] = {
+        [0] = {
+                .name   = "VEU0",
+                .start  = 0xfe920000,
+                .end    = 0xfe9200b7,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu0_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 1,
+        .dev = {
+                .platform_data  = &veu0_platform_data,
+        },
+        .resource       = veu0_resources,
+        .num_resources  = ARRAY_SIZE(veu0_resources),
+};
+
+/* VEU1 */
+static struct uio_info veu1_platform_data = {
+        .name = "VEU1",
+        .version = "0",
+        .irq = intcs_evt2irq(0x720),
+};
+
+static struct resource veu1_resources[] = {
+        [0] = {
+                .name   = "VEU1",
+                .start  = 0xfe924000,
+                .end    = 0xfe9240b7,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu1_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 2,
+        .dev = {
+                .platform_data  = &veu1_platform_data,
+        },
+        .resource       = veu1_resources,
+        .num_resources  = ARRAY_SIZE(veu1_resources),
+};
+
+/* VEU2 */
+static struct uio_info veu2_platform_data = {
+        .name = "VEU2",
+        .version = "0",
+        .irq = intcs_evt2irq(0x740),
+};
+
+static struct resource veu2_resources[] = {
+        [0] = {
+                .name   = "VEU2",
+                .start  = 0xfe928000,
+                .end    = 0xfe9280b7,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu2_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 3,
+        .dev = {
+                .platform_data  = &veu2_platform_data,
+        },
+        .resource       = veu2_resources,
+        .num_resources  = ARRAY_SIZE(veu2_resources),
+};
+
+/* VEU3 */
+static struct uio_info veu3_platform_data = {
+        .name = "VEU3",
+        .version = "0",
+        .irq = intcs_evt2irq(0x760),
+};
+
+static struct resource veu3_resources[] = {
+        [0] = {
+                .name   = "VEU3",
+                .start  = 0xfe92c000,
+                .end    = 0xfe92c0b7,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu3_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 4,
+        .dev = {
+                .platform_data  = &veu3_platform_data,
+        },
+        .resource       = veu3_resources,
+        .num_resources  = ARRAY_SIZE(veu3_resources),
+};
+
+/* VEU2H */
+static struct uio_info veu2h_platform_data = {
+        .name = "VEU2H",
+        .version = "0",
+        .irq = intcs_evt2irq(0x520),
+};
+
+static struct resource veu2h_resources[] = {
+        [0] = {
+                .name   = "VEU2H",
+                .start  = 0xfe93c000,
+                .end    = 0xfe93c27b,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu2h_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 5,
+        .dev = {
+                .platform_data  = &veu2h_platform_data,
+        },
+        .resource       = veu2h_resources,
+        .num_resources  = ARRAY_SIZE(veu2h_resources),
+};
+
+/* JPU */
+static struct uio_info jpu_platform_data = {
+        .name = "JPU",
+        .version = "0",
+        .irq = intcs_evt2irq(0x560),
+};
+
+static struct resource jpu_resources[] = {
+        [0] = {
+                .name   = "JPU",
+                .start  = 0xfe980000,
+                .end    = 0xfe9902d3,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device jpu_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 6,
+        .dev = {
+                .platform_data  = &jpu_platform_data,
+        },
+        .resource       = jpu_resources,
+        .num_resources  = ARRAY_SIZE(jpu_resources),
+};
+
+/* SPU1 */
+static struct uio_info spu1_platform_data = {
+        .name = "SPU1",
+        .version = "0",
+        .irq = evt2irq(0xfc0),
+};
+
+static struct resource spu1_resources[] = {
+        [0] = {
+                .name   = "SPU1",
+                .start  = 0xfe300000,
+                .end    = 0xfe3fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device spu1_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 7,
+        .dev = {
+                .platform_data  = &spu1_platform_data,
+        },
+        .resource       = spu1_resources,
+        .num_resources  = ARRAY_SIZE(spu1_resources),
+};
+
 static struct platform_device *sh7367_early_devices[] __initdata = {
         &scif0_device,
         &scif1_device,
@@ -206,10 +415,24 @@ static struct platform_device *sh7367_early_devices[] __initdata = {
         &cmt10_device,
 };
 
+static struct platform_device *sh7367_devices[] __initdata = {
+        &vpu_device,
+        &veu0_device,
+        &veu1_device,
+        &veu2_device,
+        &veu3_device,
+        &veu2h_device,
+        &jpu_device,
+        &spu1_device,
+};
+
 void __init sh7367_add_standard_devices(void)
 {
         platform_add_devices(sh7367_early_devices,
                              ARRAY_SIZE(sh7367_early_devices));
+
+        platform_add_devices(sh7367_devices,
+                            ARRAY_SIZE(sh7367_devices));
 }
 
 #define SYMSTPCR2 0xe6158048
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index ff0494f3d00c..cd807eea69e2 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/platform_device.h>
+#include <linux/uio_driver.h>
 #include <linux/delay.h>
 #include <linux/input.h>
 #include <linux/io.h>
@@ -601,6 +602,214 @@ static struct platform_device dma2_device = {
         },
 };
 
+/* VPU */
+static struct uio_info vpu_platform_data = {
+        .name = "VPU5HG",
+        .version = "0",
+        .irq = intcs_evt2irq(0x980),
+};
+
+static struct resource vpu_resources[] = {
+        [0] = {
+                .name   = "VPU",
+                .start  = 0xfe900000,
+                .end    = 0xfe900157,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device vpu_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 0,
+        .dev = {
+                .platform_data  = &vpu_platform_data,
+        },
+        .resource       = vpu_resources,
+        .num_resources  = ARRAY_SIZE(vpu_resources),
+};
+
+/* VEU0 */
+static struct uio_info veu0_platform_data = {
+        .name = "VEU0",
+        .version = "0",
+        .irq = intcs_evt2irq(0x700),
+};
+
+static struct resource veu0_resources[] = {
+        [0] = {
+                .name   = "VEU0",
+                .start  = 0xfe920000,
+                .end    = 0xfe9200cb,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu0_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 1,
+        .dev = {
+                .platform_data  = &veu0_platform_data,
+        },
+        .resource       = veu0_resources,
+        .num_resources  = ARRAY_SIZE(veu0_resources),
+};
+
+/* VEU1 */
+static struct uio_info veu1_platform_data = {
+        .name = "VEU1",
+        .version = "0",
+        .irq = intcs_evt2irq(0x720),
+};
+
+static struct resource veu1_resources[] = {
+        [0] = {
+                .name   = "VEU1",
+                .start  = 0xfe924000,
+                .end    = 0xfe9240cb,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu1_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 2,
+        .dev = {
+                .platform_data  = &veu1_platform_data,
+        },
+        .resource       = veu1_resources,
+        .num_resources  = ARRAY_SIZE(veu1_resources),
+};
+
+/* VEU2 */
+static struct uio_info veu2_platform_data = {
+        .name = "VEU2",
+        .version = "0",
+        .irq = intcs_evt2irq(0x740),
+};
+
+static struct resource veu2_resources[] = {
+        [0] = {
+                .name   = "VEU2",
+                .start  = 0xfe928000,
+                .end    = 0xfe928307,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu2_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 3,
+        .dev = {
+                .platform_data  = &veu2_platform_data,
+        },
+        .resource       = veu2_resources,
+        .num_resources  = ARRAY_SIZE(veu2_resources),
+};
+
+/* VEU3 */
+static struct uio_info veu3_platform_data = {
+        .name = "VEU3",
+        .version = "0",
+        .irq = intcs_evt2irq(0x760),
+};
+
+static struct resource veu3_resources[] = {
+        [0] = {
+                .name   = "VEU3",
+                .start  = 0xfe92c000,
+                .end    = 0xfe92c307,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu3_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 4,
+        .dev = {
+                .platform_data  = &veu3_platform_data,
+        },
+        .resource       = veu3_resources,
+        .num_resources  = ARRAY_SIZE(veu3_resources),
+};
+
+/* JPU */
+static struct uio_info jpu_platform_data = {
+        .name = "JPU",
+        .version = "0",
+        .irq = intcs_evt2irq(0x560),
+};
+
+static struct resource jpu_resources[] = {
+        [0] = {
+                .name   = "JPU",
+                .start  = 0xfe980000,
+                .end    = 0xfe9902d3,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device jpu_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 5,
+        .dev = {
+                .platform_data  = &jpu_platform_data,
+        },
+        .resource       = jpu_resources,
+        .num_resources  = ARRAY_SIZE(jpu_resources),
+};
+
+/* SPU2DSP0 */
+static struct uio_info spu0_platform_data = {
+        .name = "SPU2DSP0",
+        .version = "0",
+        .irq = evt2irq(0x1800),
+};
+
+static struct resource spu0_resources[] = {
+        [0] = {
+                .name   = "SPU2DSP0",
+                .start  = 0xfe200000,
+                .end    = 0xfe2fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device spu0_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 6,
+        .dev = {
+                .platform_data  = &spu0_platform_data,
+        },
+        .resource       = spu0_resources,
+        .num_resources  = ARRAY_SIZE(spu0_resources),
+};
+
+/* SPU2DSP1 */
+static struct uio_info spu1_platform_data = {
+        .name = "SPU2DSP1",
+        .version = "0",
+        .irq = evt2irq(0x1820),
+};
+
+static struct resource spu1_resources[] = {
+        [0] = {
+                .name   = "SPU2DSP1",
+                .start  = 0xfe300000,
+                .end    = 0xfe3fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device spu1_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 7,
+        .dev = {
+                .platform_data  = &spu1_platform_data,
+        },
+        .resource       = spu1_resources,
+        .num_resources  = ARRAY_SIZE(spu1_resources),
+};
+
 static struct platform_device *sh7372_early_devices[] __initdata = {
         &scif0_device,
         &scif1_device,
@@ -620,6 +829,14 @@ static struct platform_device *sh7372_late_devices[] __initdata = {
         &dma0_device,
         &dma1_device,
         &dma2_device,
+        &vpu_device,
+        &veu0_device,
+        &veu1_device,
+        &veu2_device,
+        &veu3_device,
+        &jpu_device,
+        &spu0_device,
+        &spu1_device,
 };
 
 void __init sh7372_add_standard_devices(void)
diff --git a/arch/arm/mach-shmobile/setup-sh7377.c b/arch/arm/mach-shmobile/setup-sh7377.c
index 8099b0b8a934..bb405b8e459b 100644
--- a/arch/arm/mach-shmobile/setup-sh7377.c
+++ b/arch/arm/mach-shmobile/setup-sh7377.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/platform_device.h>
+#include <linux/uio_driver.h>
 #include <linux/delay.h>
 #include <linux/input.h>
 #include <linux/io.h>
@@ -38,7 +39,7 @@ static struct plat_sci_port scif0_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { evt2irq(0xc00), evt2irq(0xc00),
                             evt2irq(0xc00), evt2irq(0xc00) },
 };
@@ -57,7 +58,7 @@ static struct plat_sci_port scif1_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { evt2irq(0xc20), evt2irq(0xc20),
                             evt2irq(0xc20), evt2irq(0xc20) },
 };
@@ -76,7 +77,7 @@ static struct plat_sci_port scif2_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { evt2irq(0xc40), evt2irq(0xc40),
                             evt2irq(0xc40), evt2irq(0xc40) },
 };
@@ -95,7 +96,7 @@ static struct plat_sci_port scif3_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { evt2irq(0xc60), evt2irq(0xc60),
                             evt2irq(0xc60), evt2irq(0xc60) },
 };
@@ -114,7 +115,7 @@ static struct plat_sci_port scif4_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { evt2irq(0xd20), evt2irq(0xd20),
                             evt2irq(0xd20), evt2irq(0xd20) },
 };
@@ -133,7 +134,7 @@ static struct plat_sci_port scif5_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { evt2irq(0xd40), evt2irq(0xd40),
                             evt2irq(0xd40), evt2irq(0xd40) },
 };
@@ -152,7 +153,7 @@ static struct plat_sci_port scif6_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFA,
         .irqs           = { intcs_evt2irq(0x1a80), intcs_evt2irq(0x1a80),
                             intcs_evt2irq(0x1a80), intcs_evt2irq(0x1a80) },
 };
@@ -171,7 +172,7 @@ static struct plat_sci_port scif7_platform_data = {
         .flags          = UPF_BOOT_AUTOCONF,
         .scscr          = SCSCR_RE | SCSCR_TE,
         .scbrr_algo_id  = SCBRR_ALGO_4,
-        .type           = PORT_SCIF,
+        .type           = PORT_SCIFB,
         .irqs           = { evt2irq(0xd60), evt2irq(0xd60),
                             evt2irq(0xd60), evt2irq(0xd60) },
 };
@@ -215,6 +216,214 @@ static struct platform_device cmt10_device = {
         .num_resources  = ARRAY_SIZE(cmt10_resources),
 };
 
+/* VPU */
+static struct uio_info vpu_platform_data = {
+        .name = "VPU5HG",
+        .version = "0",
+        .irq = intcs_evt2irq(0x980),
+};
+
+static struct resource vpu_resources[] = {
+        [0] = {
+                .name   = "VPU",
+                .start  = 0xfe900000,
+                .end    = 0xfe900157,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device vpu_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 0,
+        .dev = {
+                .platform_data  = &vpu_platform_data,
+        },
+        .resource       = vpu_resources,
+        .num_resources  = ARRAY_SIZE(vpu_resources),
+};
+
+/* VEU0 */
+static struct uio_info veu0_platform_data = {
+        .name = "VEU0",
+        .version = "0",
+        .irq = intcs_evt2irq(0x700),
+};
+
+static struct resource veu0_resources[] = {
+        [0] = {
+                .name   = "VEU0",
+                .start  = 0xfe920000,
+                .end    = 0xfe9200cb,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu0_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 1,
+        .dev = {
+                .platform_data  = &veu0_platform_data,
+        },
+        .resource       = veu0_resources,
+        .num_resources  = ARRAY_SIZE(veu0_resources),
+};
+
+/* VEU1 */
+static struct uio_info veu1_platform_data = {
+        .name = "VEU1",
+        .version = "0",
+        .irq = intcs_evt2irq(0x720),
+};
+
+static struct resource veu1_resources[] = {
+        [0] = {
+                .name   = "VEU1",
+                .start  = 0xfe924000,
+                .end    = 0xfe9240cb,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu1_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 2,
+        .dev = {
+                .platform_data  = &veu1_platform_data,
+        },
+        .resource       = veu1_resources,
+        .num_resources  = ARRAY_SIZE(veu1_resources),
+};
+
+/* VEU2 */
+static struct uio_info veu2_platform_data = {
+        .name = "VEU2",
+        .version = "0",
+        .irq = intcs_evt2irq(0x740),
+};
+
+static struct resource veu2_resources[] = {
+        [0] = {
+                .name   = "VEU2",
+                .start  = 0xfe928000,
+                .end    = 0xfe928307,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu2_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 3,
+        .dev = {
+                .platform_data  = &veu2_platform_data,
+        },
+        .resource       = veu2_resources,
+        .num_resources  = ARRAY_SIZE(veu2_resources),
+};
+
+/* VEU3 */
+static struct uio_info veu3_platform_data = {
+        .name = "VEU3",
+        .version = "0",
+        .irq = intcs_evt2irq(0x760),
+};
+
+static struct resource veu3_resources[] = {
+        [0] = {
+                .name   = "VEU3",
+                .start  = 0xfe92c000,
+                .end    = 0xfe92c307,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device veu3_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 4,
+        .dev = {
+                .platform_data  = &veu3_platform_data,
+        },
+        .resource       = veu3_resources,
+        .num_resources  = ARRAY_SIZE(veu3_resources),
+};
+
+/* JPU */
+static struct uio_info jpu_platform_data = {
+        .name = "JPU",
+        .version = "0",
+        .irq = intcs_evt2irq(0x560),
+};
+
+static struct resource jpu_resources[] = {
+        [0] = {
+                .name   = "JPU",
+                .start  = 0xfe980000,
+                .end    = 0xfe9902d3,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device jpu_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 5,
+        .dev = {
+                .platform_data  = &jpu_platform_data,
+        },
+        .resource       = jpu_resources,
+        .num_resources  = ARRAY_SIZE(jpu_resources),
+};
+
+/* SPU2DSP0 */
+static struct uio_info spu0_platform_data = {
+        .name = "SPU2DSP0",
+        .version = "0",
+        .irq = evt2irq(0x1800),
+};
+
+static struct resource spu0_resources[] = {
+        [0] = {
+                .name   = "SPU2DSP0",
+                .start  = 0xfe200000,
+                .end    = 0xfe2fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device spu0_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 6,
+        .dev = {
+                .platform_data  = &spu0_platform_data,
+        },
+        .resource       = spu0_resources,
+        .num_resources  = ARRAY_SIZE(spu0_resources),
+};
+
+/* SPU2DSP1 */
+static struct uio_info spu1_platform_data = {
+        .name = "SPU2DSP1",
+        .version = "0",
+        .irq = evt2irq(0x1820),
+};
+
+static struct resource spu1_resources[] = {
+        [0] = {
+                .name   = "SPU2DSP1",
+                .start  = 0xfe300000,
+                .end    = 0xfe3fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device spu1_device = {
+        .name           = "uio_pdrv_genirq",
+        .id             = 7,
+        .dev = {
+                .platform_data  = &spu1_platform_data,
+        },
+        .resource       = spu1_resources,
+        .num_resources  = ARRAY_SIZE(spu1_resources),
+};
+
 static struct platform_device *sh7377_early_devices[] __initdata = {
         &scif0_device,
         &scif1_device,
@@ -227,10 +436,24 @@ static struct platform_device *sh7377_early_devices[] __initdata = {
         &cmt10_device,
 };
 
+static struct platform_device *sh7377_devices[] __initdata = {
+        &vpu_device,
+        &veu0_device,
+        &veu1_device,
+        &veu2_device,
+        &veu3_device,
+        &jpu_device,
+        &spu0_device,
+        &spu1_device,
+};
+
 void __init sh7377_add_standard_devices(void)
 {
         platform_add_devices(sh7377_early_devices,
                             ARRAY_SIZE(sh7377_early_devices));
+
+        platform_add_devices(sh7377_devices,
+                            ARRAY_SIZE(sh7377_devices));
 }
 
 #define SMSTPCR3 0xe615013c
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index 685c40a2f5e6..e46821c0a62e 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -27,9 +27,11 @@
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_dma.h>
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <mach/hardware.h>
+#include <mach/sh73a0.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
@@ -392,6 +394,242 @@ static struct platform_device i2c4_device = {
         .num_resources  = ARRAY_SIZE(i2c4_resources),
 };
 
+/* Transmit sizes and respective CHCR register values */
+enum {
+        XMIT_SZ_8BIT            = 0,
+        XMIT_SZ_16BIT           = 1,
+        XMIT_SZ_32BIT           = 2,
+        XMIT_SZ_64BIT           = 7,
+        XMIT_SZ_128BIT          = 3,
+        XMIT_SZ_256BIT          = 4,
+        XMIT_SZ_512BIT          = 5,
+};
+
+/* log2(size / 8) - used to calculate number of transfers */
+#define TS_SHIFT {                      \
+        [XMIT_SZ_8BIT]          = 0,    \
+        [XMIT_SZ_16BIT]         = 1,    \
+        [XMIT_SZ_32BIT]         = 2,    \
+        [XMIT_SZ_64BIT]         = 3,    \
+        [XMIT_SZ_128BIT]        = 4,    \
+        [XMIT_SZ_256BIT]        = 5,    \
+        [XMIT_SZ_512BIT]        = 6,    \
+}
+
+#define TS_INDEX2VAL(i) ((((i) & 3) << 3) | (((i) & 0xc) << (20 - 2)))
+#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL((xmit_sz)))
+#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL((xmit_sz)))
+
+static const struct sh_dmae_slave_config sh73a0_dmae_slaves[] = {
+        {
+                .slave_id       = SHDMA_SLAVE_SCIF0_TX,
+                .addr           = 0xe6c40020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x21,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF0_RX,
+                .addr           = 0xe6c40024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x22,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF1_TX,
+                .addr           = 0xe6c50020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x25,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF1_RX,
+                .addr           = 0xe6c50024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x26,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF2_TX,
+                .addr           = 0xe6c60020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x29,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF2_RX,
+                .addr           = 0xe6c60024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x2a,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF3_TX,
+                .addr           = 0xe6c70020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x2d,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF3_RX,
+                .addr           = 0xe6c70024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x2e,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF4_TX,
+                .addr           = 0xe6c80020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x39,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF4_RX,
+                .addr           = 0xe6c80024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x3a,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF5_TX,
+                .addr           = 0xe6cb0020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x35,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF5_RX,
+                .addr           = 0xe6cb0024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x36,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF6_TX,
+                .addr           = 0xe6cc0020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x1d,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF6_RX,
+                .addr           = 0xe6cc0024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x1e,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF7_TX,
+                .addr           = 0xe6cd0020,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x19,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF7_RX,
+                .addr           = 0xe6cd0024,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x1a,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF8_TX,
+                .addr           = 0xe6c30040,
+                .chcr           = CHCR_TX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x3d,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SCIF8_RX,
+                .addr           = 0xe6c30060,
+                .chcr           = CHCR_RX(XMIT_SZ_8BIT),
+                .mid_rid        = 0x3e,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SDHI0_TX,
+                .addr           = 0xee100030,
+                .chcr           = CHCR_TX(XMIT_SZ_16BIT),
+                .mid_rid        = 0xc1,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SDHI0_RX,
+                .addr           = 0xee100030,
+                .chcr           = CHCR_RX(XMIT_SZ_16BIT),
+                .mid_rid        = 0xc2,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SDHI1_TX,
+                .addr           = 0xee120030,
+                .chcr           = CHCR_TX(XMIT_SZ_16BIT),
+                .mid_rid        = 0xc9,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SDHI1_RX,
+                .addr           = 0xee120030,
+                .chcr           = CHCR_RX(XMIT_SZ_16BIT),
+                .mid_rid        = 0xca,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SDHI2_TX,
+                .addr           = 0xee140030,
+                .chcr           = CHCR_TX(XMIT_SZ_16BIT),
+                .mid_rid        = 0xcd,
+        }, {
+                .slave_id       = SHDMA_SLAVE_SDHI2_RX,
+                .addr           = 0xee140030,
+                .chcr           = CHCR_RX(XMIT_SZ_16BIT),
+                .mid_rid        = 0xce,
+        }, {
+                .slave_id       = SHDMA_SLAVE_MMCIF_TX,
+                .addr           = 0xe6bd0034,
+                .chcr           = CHCR_TX(XMIT_SZ_32BIT),
+                .mid_rid        = 0xd1,
+        }, {
+                .slave_id       = SHDMA_SLAVE_MMCIF_RX,
+                .addr           = 0xe6bd0034,
+                .chcr           = CHCR_RX(XMIT_SZ_32BIT),
+                .mid_rid        = 0xd2,
+        },
+};
+
+#define DMAE_CHANNEL(_offset)                                   \
+        {                                                       \
+                .offset         = _offset - 0x20,               \
+                .dmars          = _offset - 0x20 + 0x40,        \
+        }
+
+static const struct sh_dmae_channel sh73a0_dmae_channels[] = {
+        DMAE_CHANNEL(0x8000),
+        DMAE_CHANNEL(0x8080),
+        DMAE_CHANNEL(0x8100),
+        DMAE_CHANNEL(0x8180),
+        DMAE_CHANNEL(0x8200),
+        DMAE_CHANNEL(0x8280),
+        DMAE_CHANNEL(0x8300),
+        DMAE_CHANNEL(0x8380),
+        DMAE_CHANNEL(0x8400),
+        DMAE_CHANNEL(0x8480),
+        DMAE_CHANNEL(0x8500),
+        DMAE_CHANNEL(0x8580),
+        DMAE_CHANNEL(0x8600),
+        DMAE_CHANNEL(0x8680),
+        DMAE_CHANNEL(0x8700),
+        DMAE_CHANNEL(0x8780),
+        DMAE_CHANNEL(0x8800),
+        DMAE_CHANNEL(0x8880),
+        DMAE_CHANNEL(0x8900),
+        DMAE_CHANNEL(0x8980),
+};
+
+static const unsigned int ts_shift[] = TS_SHIFT;
+
+static struct sh_dmae_pdata sh73a0_dmae_platform_data = {
+        .slave          = sh73a0_dmae_slaves,
+        .slave_num      = ARRAY_SIZE(sh73a0_dmae_slaves),
+        .channel        = sh73a0_dmae_channels,
+        .channel_num    = ARRAY_SIZE(sh73a0_dmae_channels),
+        .ts_low_shift   = 3,
+        .ts_low_mask    = 0x18,
+        .ts_high_shift  = (20 - 2),     /* 2 bits for shifted low TS */
+        .ts_high_mask   = 0x00300000,
+        .ts_shift       = ts_shift,
+        .ts_shift_num   = ARRAY_SIZE(ts_shift),
+        .dmaor_init     = DMAOR_DME,
+};
+
+static struct resource sh73a0_dmae_resources[] = {
+        {
+                /* Registers including DMAOR and channels including DMARSx */
+                .start  = 0xfe000020,
+                .end    = 0xfe008a00 - 1,
+                .flags  = IORESOURCE_MEM,
+        },
+        {
+                /* DMA error IRQ */
+                .start  = gic_spi(129),
+                .end    = gic_spi(129),
+                .flags  = IORESOURCE_IRQ,
+        },
+        {
+                /* IRQ for channels 0-19 */
+                .start  = gic_spi(109),
+                .end    = gic_spi(128),
+                .flags  = IORESOURCE_IRQ,
+        },
+};
+
+static struct platform_device dma0_device = {
+        .name           = "sh-dma-engine",
+        .id             = 0,
+        .resource       = sh73a0_dmae_resources,
+        .num_resources  = ARRAY_SIZE(sh73a0_dmae_resources),
+        .dev            = {
+                .platform_data  = &sh73a0_dmae_platform_data,
+        },
+};
+
 static struct platform_device *sh73a0_early_devices[] __initdata = {
         &scif0_device,
         &scif1_device,
@@ -413,10 +651,16 @@ static struct platform_device *sh73a0_late_devices[] __initdata = {
         &i2c2_device,
         &i2c3_device,
         &i2c4_device,
+        &dma0_device,
 };
 
+#define SRCR2          0xe61580b0
+
 void __init sh73a0_add_standard_devices(void)
 {
+        /* Clear software reset bit on SY-DMAC module */
+        __raw_writel(__raw_readl(SRCR2) & ~(1 << 18), SRCR2);
+
         platform_add_devices(sh73a0_early_devices,
                             ARRAY_SIZE(sh73a0_early_devices));
         platform_add_devices(sh73a0_late_devices,
diff --git a/arch/arm/mach-shmobile/sleep-sh7372.S b/arch/arm/mach-shmobile/sleep-sh7372.S
new file mode 100644
index 000000000000..d37d3ca4d18f
--- /dev/null
+++ b/arch/arm/mach-shmobile/sleep-sh7372.S
@@ -0,0 +1,260 @@
+/*
+ * sh7372 lowlevel sleep code for "Core Standby Mode"
+ *
+ * Copyright (C) 2011 Magnus Damm
+ *
+ * In "Core Standby Mode" the ARM core is off, but L2 cache is still on
+ *
+ * Based on mach-omap2/sleep34xx.S
+ *
+ * (C) Copyright 2007 Texas Instruments
+ * Karthik Dasu <karthik-dp@ti.com>
+ *
+ * (C) Copyright 2004 Texas Instruments, <www.ti.com>
+ * Richard Woodruff <r-woodruff2@ti.com>
+ *
+ * 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; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * 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; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#define SMFRAM 0xe6a70000
+
+        .align
+kernel_flush:
+        .word   v7_flush_dcache_all
+
+        .align  3
+ENTRY(sh7372_cpu_suspend)
+        stmfd   sp!, {r0-r12, lr}       @ save registers on stack
+
+        ldr     r8, =SMFRAM
+
+        mov     r4, sp                  @ Store sp
+        mrs     r5, spsr                @ Store spsr
+        mov     r6, lr                  @ Store lr
+        stmia   r8!, {r4-r6}
+
+        mrc     p15, 0, r4, c1, c0, 2   @ Coprocessor access control register
+        mrc     p15, 0, r5, c2, c0, 0   @ TTBR0
+        mrc     p15, 0, r6, c2, c0, 1   @ TTBR1
+        mrc     p15, 0, r7, c2, c0, 2   @ TTBCR
+        stmia   r8!, {r4-r7}
+
+        mrc     p15, 0, r4, c3, c0, 0   @ Domain access Control Register
+        mrc     p15, 0, r5, c10, c2, 0  @ PRRR
+        mrc     p15, 0, r6, c10, c2, 1  @ NMRR
+        stmia   r8!,{r4-r6}
+
+        mrc     p15, 0, r4, c13, c0, 1  @ Context ID
+        mrc     p15, 0, r5, c13, c0, 2  @ User r/w thread and process ID
+        mrc     p15, 0, r6, c12, c0, 0  @ Secure or NS vector base address
+        mrs     r7, cpsr                @ Store current cpsr
+        stmia   r8!, {r4-r7}
+
+        mrc     p15, 0, r4, c1, c0, 0   @ save control register
+        stmia   r8!, {r4}
+
+        /*
+         * jump out to kernel flush routine
+         *  - reuse that code is better
+         *  - it executes in a cached space so is faster than refetch per-block
+         *  - should be faster and will change with kernel
+         *  - 'might' have to copy address, load and jump to it
+         * Flush all data from the L1 data cache before disabling
+         * SCTLR.C bit.
+         */
+        ldr     r1, kernel_flush
+        mov     lr, pc
+        bx      r1
+
+        /*
+         * Clear the SCTLR.C bit to prevent further data cache
+         * allocation. Clearing SCTLR.C would make all the data accesses
+         * strongly ordered and would not hit the cache.
+         */
+        mrc     p15, 0, r0, c1, c0, 0
+        bic     r0, r0, #(1 << 2)       @ Disable the C bit
+        mcr     p15, 0, r0, c1, c0, 0
+        isb
+
+        /*
+         * Invalidate L1 data cache. Even though only invalidate is
+         * necessary exported flush API is used here. Doing clean
+         * on already clean cache would be almost NOP.
+         */
+        ldr     r1, kernel_flush
+        blx     r1
+        /*
+         * The kernel doesn't interwork: v7_flush_dcache_all in particluar will
+         * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled.
+         * This sequence switches back to ARM.  Note that .align may insert a
+         * nop: bx pc needs to be word-aligned in order to work.
+         */
+ THUMB( .thumb          )
+ THUMB( .align          )
+ THUMB( bx      pc      )
+ THUMB( nop             )
+        .arm
+
+        /* Data memory barrier and Data sync barrier */
+        dsb
+        dmb
+
+/*
+ * ===================================
+ * == WFI instruction => Enter idle ==
+ * ===================================
+ */
+        wfi                             @ wait for interrupt
+
+/*
+ * ===================================
+ * == Resume path for non-OFF modes ==
+ * ===================================
+ */
+        mrc     p15, 0, r0, c1, c0, 0
+        tst     r0, #(1 << 2)           @ Check C bit enabled?
+        orreq   r0, r0, #(1 << 2)       @ Enable the C bit if cleared
+        mcreq   p15, 0, r0, c1, c0, 0
+        isb
+
+/*
+ * ===================================
+ * == Exit point from non-OFF modes ==
+ * ===================================
+ */
+        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
+
+        .pool
+
+        .align  12
+        .text
+        .global sh7372_cpu_resume
+sh7372_cpu_resume:
+
+        mov     r1, #0
+        /*
+         * Invalidate all instruction caches to PoU
+         * and flush branch target cache
+         */
+        mcr     p15, 0, r1, c7, c5, 0
+
+        ldr     r3, =SMFRAM
+
+        ldmia   r3!, {r4-r6}
+        mov     sp, r4                  @ Restore sp
+        msr     spsr_cxsf, r5           @ Restore spsr
+        mov     lr, r6                  @ Restore lr
+
+        ldmia   r3!, {r4-r7}
+        mcr     p15, 0, r4, c1, c0, 2   @ Coprocessor access Control Register
+        mcr     p15, 0, r5, c2, c0, 0   @ TTBR0
+        mcr     p15, 0, r6, c2, c0, 1   @ TTBR1
+        mcr     p15, 0, r7, c2, c0, 2   @ TTBCR
+
+        ldmia   r3!,{r4-r6}
+        mcr     p15, 0, r4, c3, c0, 0   @ Domain access Control Register
+        mcr     p15, 0, r5, c10, c2, 0  @ PRRR
+        mcr     p15, 0, r6, c10, c2, 1  @ NMRR
+
+        ldmia   r3!,{r4-r7}
+        mcr     p15, 0, r4, c13, c0, 1  @ Context ID
+        mcr     p15, 0, r5, c13, c0, 2  @ User r/w thread and process ID
+        mrc     p15, 0, r6, c12, c0, 0  @ Secure or NS vector base address
+        msr     cpsr, r7                @ store cpsr
+
+        /* Starting to enable MMU here */
+        mrc     p15, 0, r7, c2, c0, 2   @ Read TTBRControl
+        /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */
+        and     r7, #0x7
+        cmp     r7, #0x0
+        beq     usettbr0
+ttbr_error:
+        /*
+         * More work needs to be done to support N[0:2] value other than 0
+         * So looping here so that the error can be detected
+         */
+        b       ttbr_error
+
+        .align
+cache_pred_disable_mask:
+        .word   0xFFFFE7FB
+ttbrbit_mask:
+        .word   0xFFFFC000
+table_index_mask:
+        .word   0xFFF00000
+table_entry:
+        .word   0x00000C02
+usettbr0:
+
+        mrc     p15, 0, r2, c2, c0, 0
+        ldr     r5, ttbrbit_mask
+        and     r2, r5
+        mov     r4, pc
+        ldr     r5, table_index_mask
+        and     r4, r5                  @ r4 = 31 to 20 bits of pc
+        /* Extract the value to be written to table entry */
+        ldr     r6, table_entry
+        /* r6 has the value to be written to table entry */
+        add     r6, r6, r4
+        /* Getting the address of table entry to modify */
+        lsr     r4, #18
+        /* r2 has the location which needs to be modified */
+        add     r2, r4
+        ldr     r4, [r2]
+        str     r6, [r2] /* modify the table entry */
+
+        mov     r7, r6
+        mov     r5, r2
+        mov     r6, r4
+        /* r5 = original page table address */
+        /* r6 = original page table data */
+
+        mov     r0, #0
+        mcr     p15, 0, r0, c7, c5, 4   @ Flush prefetch buffer
+        mcr     p15, 0, r0, c7, c5, 6   @ Invalidate branch predictor array
+        mcr     p15, 0, r0, c8, c5, 0   @ Invalidate instruction TLB
+        mcr     p15, 0, r0, c8, c6, 0   @ Invalidate data TLB
+
+        /*
+         * Restore control register. This enables the MMU.
+         * The caches and prediction are not enabled here, they
+         * will be enabled after restoring the MMU table entry.
+         */
+        ldmia   r3!, {r4}
+        stmia   r3!, {r5} /* save original page table address */
+        stmia   r3!, {r6} /* save original page table data */
+        stmia   r3!, {r7} /* save modified page table data */
+
+        ldr     r2, cache_pred_disable_mask
+        and     r4, r2
+        mcr     p15, 0, r4, c1, c0, 0
+        dsb
+        isb
+
+        ldr     r0, =restoremmu_on
+        bx      r0
+
+/*
+ * ==============================
+ * == Exit point from OFF mode ==
+ * ==============================
+ */
+restoremmu_on:
+
+        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index a156d2108df1..3ffdbc92ba82 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -59,6 +59,11 @@ unsigned int __init sh73a0_get_core_count(void)
 {
         void __iomem *scu_base = scu_base_addr();
 
+#ifdef CONFIG_HAVE_ARM_TWD
+        /* twd_base needs to be initialized before percpu_timer_setup() */
+        twd_base = (void __iomem *)0xf0000600;
+#endif
+
         return scu_get_core_count(scu_base);
 }
 
@@ -82,10 +87,6 @@ int __cpuinit sh73a0_boot_secondary(unsigned int cpu)
 
 void __init sh73a0_smp_prepare_cpus(void)
 {
-#ifdef CONFIG_HAVE_ARM_TWD
-        twd_base = (void __iomem *)0xf0000600;
-#endif
-
         scu_enable(scu_base_addr());
 
         /* Map the reset vector (in headsmp.S) */
diff --git a/arch/arm/mach-shmobile/suspend.c b/arch/arm/mach-shmobile/suspend.c
new file mode 100644
index 000000000000..c1febe13f709
--- /dev/null
+++ b/arch/arm/mach-shmobile/suspend.c
@@ -0,0 +1,47 @@
+/*
+ * Suspend-to-RAM support code for SH-Mobile ARM
+ *
+ *  Copyright (C) 2011 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/pm.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <asm/system.h>
+#include <asm/io.h>
+
+static int shmobile_suspend_default_enter(suspend_state_t suspend_state)
+{
+        cpu_do_idle();
+        return 0;
+}
+
+static int shmobile_suspend_begin(suspend_state_t state)
+{
+        disable_hlt();
+        return 0;
+}
+
+static void shmobile_suspend_end(void)
+{
+        enable_hlt();
+}
+
+struct platform_suspend_ops shmobile_suspend_ops = {
+        .begin          = shmobile_suspend_begin,
+        .end            = shmobile_suspend_end,
+        .enter          = shmobile_suspend_default_enter,
+        .valid          = suspend_valid_only_mem,
+};
+
+static int __init shmobile_suspend_init(void)
+{
+        suspend_set_ops(&shmobile_suspend_ops);
+        return 0;
+}
+late_initcall(shmobile_suspend_init);
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 58626013aa32..54429d015954 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -12,9 +12,12 @@ menu "Ux500 SoC"
 
 config UX500_SOC_DB5500
         bool "DB5500"
+        select MFD_DB5500_PRCMU
 
 config UX500_SOC_DB8500
         bool "DB8500"
+        select MFD_DB8500_PRCMU
+        select REGULATOR_DB8500_PRCMU
 
 endmenu
 
diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index b549a8fb4231..1694916e6822 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -5,7 +5,7 @@
 obj-y                           := clock.o cpu.o devices.o devices-common.o \
                                    id.o usb.o
 obj-$(CONFIG_UX500_SOC_DB5500)  += cpu-db5500.o dma-db5500.o
-obj-$(CONFIG_UX500_SOC_DB8500)  += cpu-db8500.o devices-db8500.o prcmu.o
+obj-$(CONFIG_UX500_SOC_DB8500)  += cpu-db8500.o devices-db8500.o
 obj-$(CONFIG_MACH_U8500)        += board-mop500.o board-mop500-sdi.o \
                                 board-mop500-regulators.o \
                                 board-mop500-uib.o board-mop500-stuib.o \
@@ -17,4 +17,4 @@ obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug.o
 obj-$(CONFIG_LOCAL_TIMERS)      += localtimer.o
 obj-$(CONFIG_U5500_MODEM_IRQ)   += modem-irq-db5500.o
 obj-$(CONFIG_U5500_MBOX)        += mbox-db5500.o
-obj-$(CONFIG_CPU_FREQ)          += cpufreq.o
+
diff --git a/arch/arm/mach-ux500/cpu-db5500.c b/arch/arm/mach-ux500/cpu-db5500.c
index c9dc2eff3cb2..c01bc19e3c5e 100644
--- a/arch/arm/mach-ux500/cpu-db5500.c
+++ b/arch/arm/mach-ux500/cpu-db5500.c
@@ -188,6 +188,8 @@ void __init u5500_map_io(void)
         ux500_map_io();
 
         iotable_init(u5500_io_desc, ARRAY_SIZE(u5500_io_desc));
+
+        _PRCMU_BASE = __io_address(U5500_PRCMU_BASE);
 }
 
 static int usb_db5500_rx_dma_cfg[] = {
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 516126cb357d..c3c417656bd9 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -87,6 +87,8 @@ void __init u8500_map_io(void)
                 iotable_init(u8500_v1_io_desc, ARRAY_SIZE(u8500_v1_io_desc));
         else if (cpu_is_u8500v2())
                 iotable_init(u8500_v2_io_desc, ARRAY_SIZE(u8500_v2_io_desc));
+
+        _PRCMU_BASE = __io_address(U8500_PRCMU_BASE);
 }
 
 static struct resource db8500_pmu_resources[] = {
@@ -129,9 +131,14 @@ static struct platform_device db8500_pmu_device = {
         .dev.platform_data      = &db8500_pmu_platdata,
 };
 
+static struct platform_device db8500_prcmu_device = {
+        .name                   = "db8500-prcmu",
+};
+
 static struct platform_device *platform_devs[] __initdata = {
         &u8500_dma40_device,
         &db8500_pmu_device,
+        &db8500_prcmu_device,
 };
 
 static resource_size_t __initdata db8500_gpio_base[] = {
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
index 5a43107c6232..1da23bb87c16 100644
--- a/arch/arm/mach-ux500/cpu.c
+++ b/arch/arm/mach-ux500/cpu.c
@@ -8,6 +8,8 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/clk.h>
+#include <linux/mfd/db8500-prcmu.h>
+#include <linux/mfd/db5500-prcmu.h>
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -19,10 +21,11 @@
 #include <mach/hardware.h>
 #include <mach/setup.h>
 #include <mach/devices.h>
-#include <mach/prcmu.h>
 
 #include "clock.h"
 
+void __iomem *_PRCMU_BASE;
+
 #ifdef CONFIG_CACHE_L2X0
 static void __iomem *l2x0_base;
 #endif
@@ -47,6 +50,8 @@ void __init ux500_init_irq(void)
          * Init clocks here so that they are available for system timer
          * initialization.
          */
+        if (cpu_is_u5500())
+                db5500_prcmu_early_init();
         if (cpu_is_u8500())
                 prcmu_early_init();
         clk_init();
diff --git a/arch/arm/mach-ux500/cpufreq.c b/arch/arm/mach-ux500/cpufreq.c
deleted file mode 100644
index 5c5b747f134d..000000000000
--- a/arch/arm/mach-ux500/cpufreq.c
+++ /dev/null
@@ -1,211 +0,0 @@
-/*
- * CPU frequency scaling for u8500
- * Inspired by linux/arch/arm/mach-davinci/cpufreq.c
- *
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License Terms: GNU General Public License v2
- *
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- * Author: Martin Persson <martin.persson@stericsson.com>
- * Author: Jonas Aaberg <jonas.aberg@stericsson.com>
- *
- */
-
-#include <linux/platform_device.h>
-#include <linux/kernel.h>
-#include <linux/cpufreq.h>
-#include <linux/delay.h>
-
-#include <mach/hardware.h>
-#include <mach/prcmu.h>
-#include <mach/prcmu-defs.h>
-
-#define DRIVER_NAME "cpufreq-u8500"
-#define CPUFREQ_NAME "u8500"
-
-static struct device *dev;
-
-static struct cpufreq_frequency_table freq_table[] = {
-        [0] = {
-                .index = 0,
-                .frequency = 200000,
-        },
-        [1] = {
-                .index = 1,
-                .frequency = 300000,
-        },
-        [2] = {
-                .index = 2,
-                .frequency = 600000,
-        },
-        [3] = {
-                /* Used for CPU_OPP_MAX, if available */
-                .index = 3,
-                .frequency = CPUFREQ_TABLE_END,
-        },
-        [4] = {
-                .index = 4,
-                .frequency = CPUFREQ_TABLE_END,
-        },
-};
-
-static enum prcmu_cpu_opp index2opp[] = {
-        CPU_OPP_EXT_CLK,
-        CPU_OPP_50,
-        CPU_OPP_100,
-        CPU_OPP_MAX
-};
-
-static int u8500_cpufreq_verify_speed(struct cpufreq_policy *policy)
-{
-        return cpufreq_frequency_table_verify(policy, freq_table);
-}
-
-static int u8500_cpufreq_target(struct cpufreq_policy *policy,
-                                unsigned int target_freq,
-                                unsigned int relation)
-{
-        struct cpufreq_freqs freqs;
-        unsigned int index;
-        int ret = 0;
-
-        /*
-         * Ensure desired rate is within allowed range.  Some govenors
-         * (ondemand) will just pass target_freq=0 to get the minimum.
-         */
-        if (target_freq < policy->cpuinfo.min_freq)
-                target_freq = policy->cpuinfo.min_freq;
-        if (target_freq > policy->cpuinfo.max_freq)
-                target_freq = policy->cpuinfo.max_freq;
-
-        ret = cpufreq_frequency_table_target(policy, freq_table,
-                                             target_freq, relation, &index);
-        if (ret < 0) {
-                dev_err(dev, "Could not look up next frequency\n");
-                return ret;
-        }
-
-        freqs.old = policy->cur;
-        freqs.new = freq_table[index].frequency;
-        freqs.cpu = policy->cpu;
-
-        if (freqs.old == freqs.new) {
-                dev_dbg(dev, "Current and target frequencies are equal\n");
-                return 0;
-        }
-
-        dev_dbg(dev, "transition: %u --> %u\n", freqs.old, freqs.new);
-        cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
-        ret = prcmu_set_cpu_opp(index2opp[index]);
-        if (ret < 0) {
-                dev_err(dev, "Failed to set OPP level\n");
-                return ret;
-        }
-
-        cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
-        return ret;
-}
-
-static unsigned int u8500_cpufreq_getspeed(unsigned int cpu)
-{
-        int i;
-
-        for (i = 0; prcmu_get_cpu_opp() != index2opp[i]; i++)
-                ;
-        return freq_table[i].frequency;
-}
-
-static int __cpuinit u8500_cpu_init(struct cpufreq_policy *policy)
-{
-        int res;
-
-        BUILD_BUG_ON(ARRAY_SIZE(index2opp) + 1 != ARRAY_SIZE(freq_table));
-
-        if (cpu_is_u8500v2()) {
-                freq_table[1].frequency = 400000;
-                freq_table[2].frequency = 800000;
-                if (prcmu_has_arm_maxopp())
-                        freq_table[3].frequency = 1000000;
-        }
-
-        /* get policy fields based on the table */
-        res = cpufreq_frequency_table_cpuinfo(policy, freq_table);
-        if (!res)
-                cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
-        else {
-                dev_err(dev, "u8500-cpufreq : Failed to read policy table\n");
-                return res;
-        }
-
-        policy->min = policy->cpuinfo.min_freq;
-        policy->max = policy->cpuinfo.max_freq;
-        policy->cur = u8500_cpufreq_getspeed(policy->cpu);
-        policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
-        /*
-         * FIXME : Need to take time measurement across the target()
-         *         function with no/some/all drivers in the notification
-         *         list.
-         */
-        policy->cpuinfo.transition_latency = 200 * 1000; /* in ns */
-
-        /* policy sharing between dual CPUs */
-        cpumask_copy(policy->cpus, &cpu_present_map);
-
-        policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-
-        return res;
-}
-
-static struct freq_attr *u8500_cpufreq_attr[] = {
-        &cpufreq_freq_attr_scaling_available_freqs,
-        NULL,
-};
-static int u8500_cpu_exit(struct cpufreq_policy *policy)
-{
-        cpufreq_frequency_table_put_attr(policy->cpu);
-        return 0;
-}
-
-static struct cpufreq_driver u8500_driver = {
-        .owner = THIS_MODULE,
-        .flags = CPUFREQ_STICKY,
-        .verify = u8500_cpufreq_verify_speed,
-        .target = u8500_cpufreq_target,
-        .get = u8500_cpufreq_getspeed,
-        .init = u8500_cpu_init,
-        .exit = u8500_cpu_exit,
-        .name = CPUFREQ_NAME,
-        .attr = u8500_cpufreq_attr,
-};
-
-static int __init u8500_cpufreq_probe(struct platform_device *pdev)
-{
-        dev = &pdev->dev;
-        return cpufreq_register_driver(&u8500_driver);
-}
-
-static int __exit u8500_cpufreq_remove(struct platform_device *pdev)
-{
-        return cpufreq_unregister_driver(&u8500_driver);
-}
-
-static struct platform_driver u8500_cpufreq_driver = {
-        .driver = {
-                .name    = DRIVER_NAME,
-                .owner   = THIS_MODULE,
-        },
-        .remove = __exit_p(u8500_cpufreq_remove),
-};
-
-static int __init u8500_cpufreq_init(void)
-{
-        return platform_driver_probe(&u8500_cpufreq_driver,
-                                     &u8500_cpufreq_probe);
-}
-
-device_initcall(u8500_cpufreq_init);
diff --git a/arch/arm/mach-ux500/include/mach/db5500-regs.h b/arch/arm/mach-ux500/include/mach/db5500-regs.h
index bd88c1e74060..6ad983294103 100644
--- a/arch/arm/mach-ux500/include/mach/db5500-regs.h
+++ b/arch/arm/mach-ux500/include/mach/db5500-regs.h
@@ -17,6 +17,8 @@
 #define U5500_GIC_DIST_BASE     0xA0411000
 #define U5500_GIC_CPU_BASE      0xA0410100
 #define U5500_DMA_BASE          0x90030000
+#define U5500_STM_BASE          0x90020000
+#define U5500_STM_REG_BASE      (U5500_STM_BASE + 0xF000)
 #define U5500_MCDE_BASE         0xA0400000
 #define U5500_MODEM_BASE        0xB0000000
 #define U5500_L2CC_BASE         0xA0412000
@@ -29,7 +31,9 @@
 #define U5500_NAND0_BASE        0x60000000
 #define U5500_NAND1_BASE        0x70000000
 #define U5500_TWD_BASE          0xa0410600
+#define U5500_ICN_BASE          0xA0040000
 #define U5500_B2R2_BASE         0xa0200000
+#define U5500_BOOT_ROM_BASE     0x90000000
 
 #define U5500_FSMC_BASE         (U5500_PER1_BASE + 0x0000)
 #define U5500_SDI0_BASE         (U5500_PER1_BASE + 0x1000)
@@ -60,6 +64,7 @@
 #define U5500_MSP1_BASE         (U5500_PER4_BASE + 0x9000)
 #define U5500_GPIO2_BASE        (U5500_PER4_BASE + 0xA000)
 #define U5500_CDETECT_BASE      (U5500_PER4_BASE + 0xF000)
+#define U5500_PRCMU_TCDM_BASE   (U5500_PER4_BASE + 0x18000)
 
 #define U5500_SPI0_BASE         (U5500_PER5_BASE + 0x0000)
 #define U5500_SPI1_BASE         (U5500_PER5_BASE + 0x1000)
@@ -83,7 +88,7 @@
 #define U5500_HASH0_BASE        (U5500_PER6_BASE + 0x1000)
 #define U5500_HASH1_BASE        (U5500_PER6_BASE + 0x2000)
 #define U5500_PKA_BASE          (U5500_PER6_BASE + 0x4000)
-#define U5500_PKAM_BASE         (U5500_PER6_BASE + 0x5000)
+#define U5500_PKAM_BASE         (U5500_PER6_BASE + 0x5100)
 #define U5500_MTU0_BASE         (U5500_PER6_BASE + 0x6000)
 #define U5500_MTU1_BASE         (U5500_PER6_BASE + 0x7000)
 #define U5500_CR_BASE           (U5500_PER6_BASE + 0x8000)
@@ -114,8 +119,19 @@
 #define U5500_MBOX2_LOCAL_START (U5500_MBOX_BASE + 0x20)
 #define U5500_MBOX2_LOCAL_END   (U5500_MBOX_BASE + 0x3F)
 
-#define U5500_ESRAM_BASE                0x40000000
+#define U5500_ACCCON_BASE_SEC   (0xBFFF0000)
+#define U5500_ACCCON_BASE               (0xBFFF1000)
+#define U5500_ACCCON_CPUVEC_RESET_ADDR_OFFSET (0x00000020)
+#define U5500_ACCCON_ACC_CPU_CTRL_OFFSET (0x000000BC)
+
+#define U5500_ESRAM_BASE                0x40000000
 #define U5500_ESRAM_DMA_LCPA_OFFSET     0x10000
 #define U5500_DMA_LCPA_BASE    (U5500_ESRAM_BASE + U5500_ESRAM_DMA_LCPA_OFFSET)
 
+#define U5500_MCDE_SIZE         0x1000
+#define U5500_DSI_LINK_SIZE     0x1000
+#define U5500_DSI_LINK_COUNT    0x2
+#define U5500_DSI_LINK1_BASE    (U5500_MCDE_BASE + U5500_MCDE_SIZE)
+#define U5500_DSI_LINK2_BASE    (U5500_DSI_LINK1_BASE + U5500_DSI_LINK_SIZE)
+
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/db8500-regs.h b/arch/arm/mach-ux500/include/mach/db8500-regs.h
index 16647b255378..049997109cf9 100644
--- a/arch/arm/mach-ux500/include/mach/db8500-regs.h
+++ b/arch/arm/mach-ux500/include/mach/db8500-regs.h
@@ -15,8 +15,13 @@
 #define U8500_ESRAM_BANK2       (U8500_ESRAM_BANK1 + U8500_ESRAM_BANK_SIZE)
 #define U8500_ESRAM_BANK3       (U8500_ESRAM_BANK2 + U8500_ESRAM_BANK_SIZE)
 #define U8500_ESRAM_BANK4       (U8500_ESRAM_BANK3 + U8500_ESRAM_BANK_SIZE)
-/* Use bank 4 for DMA LCPA */
-#define U8500_DMA_LCPA_BASE     U8500_ESRAM_BANK4
+/*
+ * on V1 DMA uses 4KB for logical parameters position is right after the 64KB
+ * reserved for security
+ */
+#define U8500_ESRAM_DMA_LCPA_OFFSET     0x10000
+
+#define U8500_DMA_LCPA_BASE    (U8500_ESRAM_BANK0 + U8500_ESRAM_DMA_LCPA_OFFSET)
 #define U8500_DMA_LCPA_BASE_ED  (U8500_ESRAM_BANK4 + 0x4000)
 
 #define U8500_PER3_BASE         0x80000000
@@ -27,9 +32,12 @@
 #define U8500_B2R2_BASE         0x80130000
 #define U8500_HSEM_BASE         0x80140000
 #define U8500_PER4_BASE         0x80150000
+#define U8500_TPIU_BASE         0x80190000
 #define U8500_ICN_BASE          0x81000000
 
 #define U8500_BOOT_ROM_BASE     0x90000000
+/* ASIC ID is at 0xbf4 offset within this region */
+#define U8500_ASIC_ID_BASE      0x9001D000
 
 #define U8500_PER6_BASE         0xa03c0000
 #define U8500_PER5_BASE         0xa03e0000
@@ -70,13 +78,15 @@
 
 /* per6 base addresses */
 #define U8500_RNG_BASE          (U8500_PER6_BASE + 0x0000)
-#define U8500_PKA_BASE          (U8500_PER6_BASE + 0x1000)
-#define U8500_PKAM_BASE         (U8500_PER6_BASE + 0x2000)
+#define U8500_HASH0_BASE        (U8500_PER6_BASE + 0x1000)
+#define U8500_HASH1_BASE        (U8500_PER6_BASE + 0x2000)
+#define U8500_PKA_BASE          (U8500_PER6_BASE + 0x4000)
+#define U8500_PKAM_BASE         (U8500_PER6_BASE + 0x5100)
 #define U8500_MTU0_BASE         (U8500_PER6_BASE + 0x6000) /* v1 */
 #define U8500_MTU1_BASE         (U8500_PER6_BASE + 0x7000) /* v1 */
 #define U8500_CR_BASE           (U8500_PER6_BASE + 0x8000) /* v1 */
-#define U8500_CRYPTO0_BASE      (U8500_PER6_BASE + 0xa000)
-#define U8500_CRYPTO1_BASE      (U8500_PER6_BASE + 0xb000)
+#define U8500_CRYP0_BASE        (U8500_PER6_BASE + 0xa000)
+#define U8500_CRYP1_BASE        (U8500_PER6_BASE + 0xb000)
 #define U8500_CLKRST6_BASE      (U8500_PER6_BASE + 0xf000)
 
 /* per5 base addresses */
@@ -93,7 +103,8 @@
 #define U8500_DMC_BASE          (U8500_PER4_BASE + 0x06000)
 #define U8500_PRCMU_BASE        (U8500_PER4_BASE + 0x07000)
 #define U8500_PRCMU_TCDM_BASE_V1 (U8500_PER4_BASE + 0x0f000)
-#define U8500_PRCMU_TCDM_BASE   (U8500_PER4_BASE + 0x68000)
+#define U8500_PRCMU_TCDM_BASE   (U8500_PER4_BASE + 0x68000)
+#define U8500_PRCMU_TCPM_BASE   (U8500_PER4_BASE + 0x60000)
 
 /* per3 base addresses */
 #define U8500_FSMC_BASE         (U8500_PER3_BASE + 0x0000)
@@ -124,6 +135,7 @@
 #define U8500_I2C1_BASE         (U8500_PER1_BASE + 0x2000)
 #define U8500_MSP0_BASE         (U8500_PER1_BASE + 0x3000)
 #define U8500_MSP1_BASE         (U8500_PER1_BASE + 0x4000)
+#define U8500_MSP3_BASE         (U8500_PER1_BASE + 0x5000)
 #define U8500_SDI0_BASE         (U8500_PER1_BASE + 0x6000)
 #define U8500_I2C2_BASE         (U8500_PER1_BASE + 0x8000)
 #define U8500_SPI3_BASE         (U8500_PER1_BASE + 0x9000)
@@ -143,4 +155,15 @@
 #define U8500_GPIOBANK7_BASE    (U8500_GPIO2_BASE + 0x80)
 #define U8500_GPIOBANK8_BASE    U8500_GPIO3_BASE
 
+#define U8500_MCDE_SIZE         0x1000
+#define U8500_DSI_LINK_SIZE     0x1000
+#define U8500_DSI_LINK1_BASE    (U8500_MCDE_BASE + U8500_MCDE_SIZE)
+#define U8500_DSI_LINK2_BASE    (U8500_DSI_LINK1_BASE + U8500_DSI_LINK_SIZE)
+#define U8500_DSI_LINK3_BASE    (U8500_DSI_LINK2_BASE + U8500_DSI_LINK_SIZE)
+#define U8500_DSI_LINK_COUNT    0x3
+
+/* Modem and APE physical addresses */
+#define U8500_MODEM_BASE        0xe000000
+#define U8500_APE_BASE          0x6000000
+
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/hardware.h b/arch/arm/mach-ux500/include/mach/hardware.h
index bf63f2631ba0..2c6f71049f2e 100644
--- a/arch/arm/mach-ux500/include/mach/hardware.h
+++ b/arch/arm/mach-ux500/include/mach/hardware.h
@@ -35,6 +35,7 @@
 #ifndef __ASSEMBLY__
 
 #include <mach/id.h>
+extern void __iomem *_PRCMU_BASE;
 
 #define ARRAY_AND_SIZE(x)       (x), ARRAY_SIZE(x)
 
diff --git a/arch/arm/mach-ux500/include/mach/id.h b/arch/arm/mach-ux500/include/mach/id.h
index f1288d10b6ab..02b541a37ee5 100644
--- a/arch/arm/mach-ux500/include/mach/id.h
+++ b/arch/arm/mach-ux500/include/mach/id.h
@@ -75,6 +75,26 @@ static inline bool __attribute_const__ cpu_is_u8500v2(void)
         return cpu_is_u8500() && ((dbx500_revision() & 0xf0) == 0xB0);
 }
 
+static inline bool cpu_is_u8500v20(void)
+{
+        return cpu_is_u8500() && (dbx500_revision() == 0xB0);
+}
+
+static inline bool cpu_is_u8500v21(void)
+{
+        return cpu_is_u8500() && (dbx500_revision() == 0xB1);
+}
+
+static inline bool cpu_is_u8500v20_or_later(void)
+{
+        return cpu_is_u8500() && !cpu_is_u8500v10() && !cpu_is_u8500v11();
+}
+
+static inline bool ux500_is_svp(void)
+{
+        return false;
+}
+
 #define ux500_unknown_soc()     BUG()
 
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h b/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h
index 97ef55f84934..47969909836c 100644
--- a/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h
+++ b/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h
@@ -50,6 +50,11 @@
 
 #define MOP500_IRQ_END          MOP500_NR_IRQS
 
+/*
+ * We may have several boards, but only one will run at a
+ * time, so the one with most IRQs will bump this ahead,
+ * but the IRQ_BOARD_START remains the same for either board.
+ */
 #if MOP500_IRQ_END > IRQ_BOARD_END
 #undef IRQ_BOARD_END
 #define IRQ_BOARD_END   MOP500_IRQ_END
diff --git a/arch/arm/mach-ux500/include/mach/irqs-board-u5500.h b/arch/arm/mach-ux500/include/mach/irqs-board-u5500.h
new file mode 100644
index 000000000000..29d972c7717b
--- /dev/null
+++ b/arch/arm/mach-ux500/include/mach/irqs-board-u5500.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#ifndef __MACH_IRQS_BOARD_U5500_H
+#define __MACH_IRQS_BOARD_U5500_H
+
+#define AB5500_NR_IRQS          5
+#define IRQ_AB5500_BASE         IRQ_BOARD_START
+#define IRQ_AB5500_END          (IRQ_AB5500_BASE + AB5500_NR_IRQS)
+
+#define U5500_IRQ_END           IRQ_AB5500_END
+
+#if IRQ_BOARD_END < U5500_IRQ_END
+#undef IRQ_BOARD_END
+#define IRQ_BOARD_END           U5500_IRQ_END
+#endif
+
+#endif
diff --git a/arch/arm/mach-ux500/include/mach/irqs-db5500.h b/arch/arm/mach-ux500/include/mach/irqs-db5500.h
index bfa123dbec3b..77239776a6f2 100644
--- a/arch/arm/mach-ux500/include/mach/irqs-db5500.h
+++ b/arch/arm/mach-ux500/include/mach/irqs-db5500.h
@@ -83,4 +83,31 @@
 #define IRQ_DB5500_GPIO6                (IRQ_SHPI_START + 125)
 #define IRQ_DB5500_GPIO7                (IRQ_SHPI_START + 126)
 
+#ifdef CONFIG_UX500_SOC_DB5500
+
+/*
+ * After the GPIO ones we reserve a range of IRQ:s in which virtual
+ * IRQ:s representing modem IRQ:s can be allocated
+ */
+#define IRQ_MODEM_EVENTS_BASE   IRQ_SOC_START
+#define IRQ_MODEM_EVENTS_NBR    72
+#define IRQ_MODEM_EVENTS_END    (IRQ_MODEM_EVENTS_BASE + IRQ_MODEM_EVENTS_NBR)
+
+/* List of virtual IRQ:s that are allocated from the range above */
+#define MBOX_PAIR0_VIRT_IRQ     (IRQ_MODEM_EVENTS_BASE + 43)
+#define MBOX_PAIR1_VIRT_IRQ     (IRQ_MODEM_EVENTS_BASE + 45)
+#define MBOX_PAIR2_VIRT_IRQ     (IRQ_MODEM_EVENTS_BASE + 41)
+
+/*
+ * We may have several SoCs, but only one will run at a
+ * time, so the one with most IRQs will bump this ahead,
+ * but the IRQ_SOC_START remains the same for either SoC.
+ */
+#if IRQ_SOC_END < IRQ_MODEM_EVENTS_END
+#undef IRQ_SOC_END
+#define IRQ_SOC_END             IRQ_MODEM_EVENTS_END
+#endif
+
+#endif /* CONFIG_UX500_SOC_DB5500 */
+
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/irqs-db8500.h b/arch/arm/mach-ux500/include/mach/irqs-db8500.h
index 8b5d9f0a1633..68bc14974608 100644
--- a/arch/arm/mach-ux500/include/mach/irqs-db8500.h
+++ b/arch/arm/mach-ux500/include/mach/irqs-db8500.h
@@ -93,4 +93,58 @@
 #define IRQ_DB8500_GPIO7                (IRQ_SHPI_START + 126)
 #define IRQ_DB8500_GPIO8                (IRQ_SHPI_START + 127)
 
+#define IRQ_CA_WAKE_REQ_ED                      (IRQ_SHPI_START + 71)
+#define IRQ_AC_READ_NOTIFICATION_0_ED           (IRQ_SHPI_START + 66)
+#define IRQ_AC_READ_NOTIFICATION_1_ED           (IRQ_SHPI_START + 64)
+#define IRQ_CA_MSG_PEND_NOTIFICATION_0_ED       (IRQ_SHPI_START + 67)
+#define IRQ_CA_MSG_PEND_NOTIFICATION_1_ED       (IRQ_SHPI_START + 65)
+
+#define IRQ_CA_WAKE_REQ_V1                      (IRQ_SHPI_START + 83)
+#define IRQ_AC_READ_NOTIFICATION_0_V1           (IRQ_SHPI_START + 78)
+#define IRQ_AC_READ_NOTIFICATION_1_V1           (IRQ_SHPI_START + 76)
+#define IRQ_CA_MSG_PEND_NOTIFICATION_0_V1       (IRQ_SHPI_START + 79)
+#define IRQ_CA_MSG_PEND_NOTIFICATION_1_V1       (IRQ_SHPI_START + 77)
+
+#ifdef CONFIG_UX500_SOC_DB8500
+
+/* Virtual interrupts corresponding to the PRCMU wakeups.  */
+#define IRQ_PRCMU_BASE IRQ_SOC_START
+#define NUM_PRCMU_WAKEUPS (IRQ_PRCMU_END - IRQ_PRCMU_BASE)
+
+#define IRQ_PRCMU_RTC (IRQ_PRCMU_BASE)
+#define IRQ_PRCMU_RTT0 (IRQ_PRCMU_BASE + 1)
+#define IRQ_PRCMU_RTT1 (IRQ_PRCMU_BASE + 2)
+#define IRQ_PRCMU_HSI0 (IRQ_PRCMU_BASE + 3)
+#define IRQ_PRCMU_HSI1 (IRQ_PRCMU_BASE + 4)
+#define IRQ_PRCMU_CA_WAKE (IRQ_PRCMU_BASE + 5)
+#define IRQ_PRCMU_USB (IRQ_PRCMU_BASE + 6)
+#define IRQ_PRCMU_ABB (IRQ_PRCMU_BASE + 7)
+#define IRQ_PRCMU_ABB_FIFO (IRQ_PRCMU_BASE + 8)
+#define IRQ_PRCMU_ARM (IRQ_PRCMU_BASE + 9)
+#define IRQ_PRCMU_MODEM_SW_RESET_REQ (IRQ_PRCMU_BASE + 10)
+#define IRQ_PRCMU_GPIO0 (IRQ_PRCMU_BASE + 11)
+#define IRQ_PRCMU_GPIO1 (IRQ_PRCMU_BASE + 12)
+#define IRQ_PRCMU_GPIO2 (IRQ_PRCMU_BASE + 13)
+#define IRQ_PRCMU_GPIO3 (IRQ_PRCMU_BASE + 14)
+#define IRQ_PRCMU_GPIO4 (IRQ_PRCMU_BASE + 15)
+#define IRQ_PRCMU_GPIO5 (IRQ_PRCMU_BASE + 16)
+#define IRQ_PRCMU_GPIO6 (IRQ_PRCMU_BASE + 17)
+#define IRQ_PRCMU_GPIO7 (IRQ_PRCMU_BASE + 18)
+#define IRQ_PRCMU_GPIO8 (IRQ_PRCMU_BASE + 19)
+#define IRQ_PRCMU_CA_SLEEP (IRQ_PRCMU_BASE + 20)
+#define IRQ_PRCMU_HOTMON_LOW (IRQ_PRCMU_BASE + 21)
+#define IRQ_PRCMU_HOTMON_HIGH (IRQ_PRCMU_BASE + 22)
+#define IRQ_PRCMU_END (IRQ_PRCMU_BASE + 23)
+
+/*
+ * We may have several SoCs, but only one will run at a
+ * time, so the one with most IRQs will bump this ahead,
+ * but the IRQ_SOC_START remains the same for either SoC.
+ */
+#if IRQ_SOC_END < IRQ_PRCMU_END
+#undef IRQ_SOC_END
+#define IRQ_SOC_END IRQ_PRCMU_END
+#endif
+
+#endif /* CONFIG_UX500_SOC_DB8500 */
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/irqs.h b/arch/arm/mach-ux500/include/mach/irqs.h
index ba1294c13c4d..9db68d264c5f 100644
--- a/arch/arm/mach-ux500/include/mach/irqs.h
+++ b/arch/arm/mach-ux500/include/mach/irqs.h
@@ -10,49 +10,47 @@
 #ifndef ASM_ARCH_IRQS_H
 #define ASM_ARCH_IRQS_H
 
-#include <mach/irqs-db5500.h>
-#include <mach/irqs-db8500.h>
+#include <mach/hardware.h>
 
-#define IRQ_LOCALTIMER                  29
-#define IRQ_LOCALWDOG                   30
+#define IRQ_LOCALTIMER                  29
+#define IRQ_LOCALWDOG                   30
 
 /* Shared Peripheral Interrupt (SHPI) */
 #define IRQ_SHPI_START                  32
 
-/* Interrupt numbers generic for shared peripheral */
+/*
+ * MTU0 preserved for now until plat-nomadik is taught not to use it.  Don't
+ * add any other IRQs here, use the irqs-dbx500.h files.
+ */
 #define IRQ_MTU0                (IRQ_SHPI_START + 4)
 
-/* There are 128 shared peripheral interrupts assigned to
- * INTID[160:32]. The first 32 interrupts are reserved.
- */
-#define DBX500_NR_INTERNAL_IRQS         161
+#define DBX500_NR_INTERNAL_IRQS         160
 
 /* After chip-specific IRQ numbers we have the GPIO ones */
 #define NOMADIK_NR_GPIO                 288
 #define NOMADIK_GPIO_TO_IRQ(gpio)       ((gpio) + DBX500_NR_INTERNAL_IRQS)
 #define NOMADIK_IRQ_TO_GPIO(irq)        ((irq) - DBX500_NR_INTERNAL_IRQS)
-#define IRQ_BOARD_START                 NOMADIK_GPIO_TO_IRQ(NOMADIK_NR_GPIO)
+#define IRQ_GPIO_END                    NOMADIK_GPIO_TO_IRQ(NOMADIK_NR_GPIO)
+
+#define IRQ_SOC_START           IRQ_GPIO_END
+/* This will be overridden by SoC-specific irq headers */
+#define IRQ_SOC_END             IRQ_SOC_START
 
+#include <mach/irqs-db5500.h>
+#include <mach/irqs-db8500.h>
+
+#define IRQ_BOARD_START         IRQ_SOC_END
 /* This will be overridden by board-specific irq headers */
-#define IRQ_BOARD_END                   IRQ_BOARD_START
+#define IRQ_BOARD_END           IRQ_BOARD_START
 
 #ifdef CONFIG_MACH_U8500
 #include <mach/irqs-board-mop500.h>
 #endif
 
-/*
- * After the board specific IRQ:s we reserve a range of IRQ:s in which virtual
- * IRQ:s representing modem IRQ:s can be allocated
- */
-#define IRQ_MODEM_EVENTS_BASE (IRQ_BOARD_END + 1)
-#define IRQ_MODEM_EVENTS_NBR 72
-#define IRQ_MODEM_EVENTS_END (IRQ_MODEM_EVENTS_BASE + IRQ_MODEM_EVENTS_NBR)
-
-/* List of virtual IRQ:s that are allocated from the range above */
-#define MBOX_PAIR0_VIRT_IRQ (IRQ_MODEM_EVENTS_BASE + 43)
-#define MBOX_PAIR1_VIRT_IRQ (IRQ_MODEM_EVENTS_BASE + 45)
-#define MBOX_PAIR2_VIRT_IRQ (IRQ_MODEM_EVENTS_BASE + 41)
+#ifdef CONFIG_MACH_U5500
+#include <mach/irqs-board-u5500.h>
+#endif
 
-#define NR_IRQS                         IRQ_MODEM_EVENTS_END
+#define NR_IRQS                 IRQ_BOARD_END
 
 #endif /* ASM_ARCH_IRQS_H */
diff --git a/arch/arm/mach-ux500/include/mach/prcmu-defs.h b/arch/arm/mach-ux500/include/mach/prcmu-defs.h
deleted file mode 100644
index 848ba64b561f..000000000000
--- a/arch/arm/mach-ux500/include/mach/prcmu-defs.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- * Author: Martin Persson <martin.persson@stericsson.com>
- *
- * License Terms: GNU General Public License v2
- *
- * PRCM Unit definitions
- */
-
-#ifndef __MACH_PRCMU_DEFS_H
-#define __MACH_PRCMU_DEFS_H
-
-enum prcmu_cpu_opp {
-        CPU_OPP_INIT      = 0x00,
-        CPU_OPP_NO_CHANGE = 0x01,
-        CPU_OPP_100       = 0x02,
-        CPU_OPP_50        = 0x03,
-        CPU_OPP_MAX       = 0x04,
-        CPU_OPP_EXT_CLK   = 0x07
-};
-enum prcmu_ape_opp {
-        APE_OPP_NO_CHANGE = 0x00,
-        APE_OPP_100       = 0x02,
-        APE_OPP_50        = 0x03,
-};
-
-#endif /* __MACH_PRCMU_DEFS_H */
diff --git a/arch/arm/mach-ux500/include/mach/prcmu.h b/arch/arm/mach-ux500/include/mach/prcmu.h
deleted file mode 100644
index c49e456162ef..000000000000
--- a/arch/arm/mach-ux500/include/mach/prcmu.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
- *
- * License Terms: GNU General Public License v2
- *
- * PRCM Unit f/w API
- */
-#ifndef __MACH_PRCMU_H
-#define __MACH_PRCMU_H
-#include <mach/prcmu-defs.h>
-
-void __init prcmu_early_init(void);
-int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
-int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
-int prcmu_set_ape_opp(enum prcmu_ape_opp opp);
-int prcmu_set_cpu_opp(enum prcmu_cpu_opp opp);
-int prcmu_set_ape_cpu_opps(enum prcmu_ape_opp ape_opp,
-                           enum prcmu_cpu_opp cpu_opp);
-int prcmu_get_ape_opp(void);
-int prcmu_get_cpu_opp(void);
-bool prcmu_has_arm_maxopp(void);
-
-#endif /* __MACH_PRCMU_H */
diff --git a/arch/arm/mach-ux500/prcmu.c b/arch/arm/mach-ux500/prcmu.c
deleted file mode 100644
index c522d26ef348..000000000000
--- a/arch/arm/mach-ux500/prcmu.c
+++ /dev/null
@@ -1,394 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License Terms: GNU General Public License v2
- * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
- *
- * U8500 PRCM Unit interface driver
- *
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/completion.h>
-#include <linux/jiffies.h>
-#include <linux/bitops.h>
-#include <linux/interrupt.h>
-
-#include <mach/hardware.h>
-#include <mach/prcmu-regs.h>
-#include <mach/prcmu-defs.h>
-
-/* Global var to runtime determine TCDM base for v2 or v1 */
-static __iomem void *tcdm_base;
-
-#define _MBOX_HEADER            (tcdm_base + 0xFE8)
-#define MBOX_HEADER_REQ_MB0     (_MBOX_HEADER + 0x0)
-
-#define REQ_MB1 (tcdm_base + 0xFD0)
-#define REQ_MB5 (tcdm_base + 0xE44)
-
-#define REQ_MB1_ARMOPP          (REQ_MB1 + 0x0)
-#define REQ_MB1_APEOPP          (REQ_MB1 + 0x1)
-#define REQ_MB1_BOOSTOPP        (REQ_MB1 + 0x2)
-
-#define ACK_MB1 (tcdm_base + 0xE04)
-#define ACK_MB5 (tcdm_base + 0xDF4)
-
-#define ACK_MB1_CURR_ARMOPP             (ACK_MB1 + 0x0)
-#define ACK_MB1_CURR_APEOPP             (ACK_MB1 + 0x1)
-
-#define REQ_MB5_I2C_SLAVE_OP (REQ_MB5)
-#define REQ_MB5_I2C_HW_BITS (REQ_MB5 + 1)
-#define REQ_MB5_I2C_REG (REQ_MB5 + 2)
-#define REQ_MB5_I2C_VAL (REQ_MB5 + 3)
-
-#define ACK_MB5_I2C_STATUS (ACK_MB5 + 1)
-#define ACK_MB5_I2C_VAL (ACK_MB5 + 3)
-
-#define PRCM_AVS_VARM_MAX_OPP           (tcdm_base + 0x2E4)
-#define PRCM_AVS_ISMODEENABLE           7
-#define PRCM_AVS_ISMODEENABLE_MASK      (1 << PRCM_AVS_ISMODEENABLE)
-
-#define I2C_WRITE(slave) \
-        (((slave) << 1) | (cpu_is_u8500v2() ? BIT(6) : 0))
-#define I2C_READ(slave) \
-        (((slave) << 1) | (cpu_is_u8500v2() ? BIT(6) : 0) | BIT(0))
-#define I2C_STOP_EN BIT(3)
-
-enum mb1_h {
-        MB1H_ARM_OPP = 1,
-        MB1H_APE_OPP,
-        MB1H_ARM_APE_OPP,
-};
-
-static struct {
-        struct mutex lock;
-        struct completion work;
-        struct {
-                u8 arm_opp;
-                u8 ape_opp;
-                u8 arm_status;
-                u8 ape_status;
-        } ack;
-} mb1_transfer;
-
-enum ack_mb5_status {
-        I2C_WR_OK = 0x01,
-        I2C_RD_OK = 0x02,
-};
-
-#define MBOX_BIT BIT
-#define NUM_MBOX 8
-
-static struct {
-        struct mutex lock;
-        struct completion work;
-        bool failed;
-        struct {
-                u8 status;
-                u8 value;
-        } ack;
-} mb5_transfer;
-
-/**
- * prcmu_abb_read() - Read register value(s) from the ABB.
- * @slave:      The I2C slave address.
- * @reg:        The (start) register address.
- * @value:      The read out value(s).
- * @size:       The number of registers to read.
- *
- * Reads register value(s) from the ABB.
- * @size has to be 1 for the current firmware version.
- */
-int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
-{
-        int r;
-
-        if (size != 1)
-                return -EINVAL;
-
-        r = mutex_lock_interruptible(&mb5_transfer.lock);
-        if (r)
-                return r;
-
-        while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
-                cpu_relax();
-
-        writeb(I2C_READ(slave), REQ_MB5_I2C_SLAVE_OP);
-        writeb(I2C_STOP_EN, REQ_MB5_I2C_HW_BITS);
-        writeb(reg, REQ_MB5_I2C_REG);
-
-        writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
-        if (!wait_for_completion_timeout(&mb5_transfer.work,
-                        msecs_to_jiffies(500))) {
-                pr_err("prcmu: prcmu_abb_read timed out.\n");
-                r = -EIO;
-                goto unlock_and_return;
-        }
-        r = ((mb5_transfer.ack.status == I2C_RD_OK) ? 0 : -EIO);
-        if (!r)
-                *value = mb5_transfer.ack.value;
-
-unlock_and_return:
-        mutex_unlock(&mb5_transfer.lock);
-        return r;
-}
-EXPORT_SYMBOL(prcmu_abb_read);
-
-/**
- * prcmu_abb_write() - Write register value(s) to the ABB.
- * @slave:      The I2C slave address.
- * @reg:        The (start) register address.
- * @value:      The value(s) to write.
- * @size:       The number of registers to write.
- *
- * Reads register value(s) from the ABB.
- * @size has to be 1 for the current firmware version.
- */
-int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
-{
-        int r;
-
-        if (size != 1)
-                return -EINVAL;
-
-        r = mutex_lock_interruptible(&mb5_transfer.lock);
-        if (r)
-                return r;
-
-
-        while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
-                cpu_relax();
-
-        writeb(I2C_WRITE(slave), REQ_MB5_I2C_SLAVE_OP);
-        writeb(I2C_STOP_EN, REQ_MB5_I2C_HW_BITS);
-        writeb(reg, REQ_MB5_I2C_REG);
-        writeb(*value, REQ_MB5_I2C_VAL);
-
-        writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
-        if (!wait_for_completion_timeout(&mb5_transfer.work,
-                        msecs_to_jiffies(500))) {
-                pr_err("prcmu: prcmu_abb_write timed out.\n");
-                r = -EIO;
-                goto unlock_and_return;
-        }
-        r = ((mb5_transfer.ack.status == I2C_WR_OK) ? 0 : -EIO);
-
-unlock_and_return:
-        mutex_unlock(&mb5_transfer.lock);
-        return r;
-}
-EXPORT_SYMBOL(prcmu_abb_write);
-
-static int set_ape_cpu_opps(u8 header, enum prcmu_ape_opp ape_opp,
-                            enum prcmu_cpu_opp cpu_opp)
-{
-        bool do_ape;
-        bool do_arm;
-        int err = 0;
-
-        do_ape = ((header == MB1H_APE_OPP) || (header == MB1H_ARM_APE_OPP));
-        do_arm = ((header == MB1H_ARM_OPP) || (header == MB1H_ARM_APE_OPP));
-
-        mutex_lock(&mb1_transfer.lock);
-
-        while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
-                cpu_relax();
-
-        writeb(0, MBOX_HEADER_REQ_MB0);
-        writeb(cpu_opp, REQ_MB1_ARMOPP);
-        writeb(ape_opp, REQ_MB1_APEOPP);
-        writeb(0, REQ_MB1_BOOSTOPP);
-        writel(MBOX_BIT(1), PRCM_MBOX_CPU_SET);
-        wait_for_completion(&mb1_transfer.work);
-        if ((do_ape) && (mb1_transfer.ack.ape_status != 0))
-                err = -EIO;
-        if ((do_arm) && (mb1_transfer.ack.arm_status != 0))
-                err = -EIO;
-
-        mutex_unlock(&mb1_transfer.lock);
-
-        return err;
-}
-
-/**
- * prcmu_set_ape_opp() - Set the OPP of the APE.
- * @opp:        The OPP to set.
- *
- * This function sets the OPP of the APE.
- */
-int prcmu_set_ape_opp(enum prcmu_ape_opp opp)
-{
-        return set_ape_cpu_opps(MB1H_APE_OPP, opp, APE_OPP_NO_CHANGE);
-}
-EXPORT_SYMBOL(prcmu_set_ape_opp);
-
-/**
- * prcmu_set_cpu_opp() - Set the OPP of the CPU.
- * @opp:        The OPP to set.
- *
- * This function sets the OPP of the CPU.
- */
-int prcmu_set_cpu_opp(enum prcmu_cpu_opp opp)
-{
-        return set_ape_cpu_opps(MB1H_ARM_OPP, CPU_OPP_NO_CHANGE, opp);
-}
-EXPORT_SYMBOL(prcmu_set_cpu_opp);
-
-/**
- * prcmu_set_ape_cpu_opps() - Set the OPPs of the APE and the CPU.
- * @ape_opp:    The APE OPP to set.
- * @cpu_opp:    The CPU OPP to set.
- *
- * This function sets the OPPs of the APE and the CPU.
- */
-int prcmu_set_ape_cpu_opps(enum prcmu_ape_opp ape_opp,
-                           enum prcmu_cpu_opp cpu_opp)
-{
-        return set_ape_cpu_opps(MB1H_ARM_APE_OPP, ape_opp, cpu_opp);
-}
-EXPORT_SYMBOL(prcmu_set_ape_cpu_opps);
-
-/**
- * prcmu_get_ape_opp() - Get the OPP of the APE.
- *
- * This function gets the OPP of the APE.
- */
-enum prcmu_ape_opp prcmu_get_ape_opp(void)
-{
-        return readb(ACK_MB1_CURR_APEOPP);
-}
-EXPORT_SYMBOL(prcmu_get_ape_opp);
-
-/**
- * prcmu_get_cpu_opp() - Get the OPP of the CPU.
- *
- * This function gets the OPP of the CPU. The OPP is specified in %%.
- * PRCMU_OPP_EXT is a special OPP value, not specified in %%.
- */
-int prcmu_get_cpu_opp(void)
-{
-        return readb(ACK_MB1_CURR_ARMOPP);
-}
-EXPORT_SYMBOL(prcmu_get_cpu_opp);
-
-bool prcmu_has_arm_maxopp(void)
-{
-        return (readb(PRCM_AVS_VARM_MAX_OPP) & PRCM_AVS_ISMODEENABLE_MASK)
-                == PRCM_AVS_ISMODEENABLE_MASK;
-}
-
-static void read_mailbox_0(void)
-{
-        writel(MBOX_BIT(0), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_1(void)
-{
-        mb1_transfer.ack.arm_opp = readb(ACK_MB1_CURR_ARMOPP);
-        mb1_transfer.ack.ape_opp = readb(ACK_MB1_CURR_APEOPP);
-        complete(&mb1_transfer.work);
-        writel(MBOX_BIT(1), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_2(void)
-{
-        writel(MBOX_BIT(2), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_3(void)
-{
-        writel(MBOX_BIT(3), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_4(void)
-{
-        writel(MBOX_BIT(4), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_5(void)
-{
-        mb5_transfer.ack.status = readb(ACK_MB5_I2C_STATUS);
-        mb5_transfer.ack.value = readb(ACK_MB5_I2C_VAL);
-        complete(&mb5_transfer.work);
-        writel(MBOX_BIT(5), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_6(void)
-{
-        writel(MBOX_BIT(6), PRCM_ARM_IT1_CLEAR);
-}
-
-static void read_mailbox_7(void)
-{
-        writel(MBOX_BIT(7), PRCM_ARM_IT1_CLEAR);
-}
-
-static void (* const read_mailbox[NUM_MBOX])(void) = {
-        read_mailbox_0,
-        read_mailbox_1,
-        read_mailbox_2,
-        read_mailbox_3,
-        read_mailbox_4,
-        read_mailbox_5,
-        read_mailbox_6,
-        read_mailbox_7
-};
-
-static irqreturn_t prcmu_irq_handler(int irq, void *data)
-{
-        u32 bits;
-        u8 n;
-
-        bits = (readl(PRCM_ARM_IT1_VAL) & (MBOX_BIT(NUM_MBOX) - 1));
-        if (unlikely(!bits))
-                return IRQ_NONE;
-
-        for (n = 0; bits; n++) {
-                if (bits & MBOX_BIT(n)) {
-                        bits -= MBOX_BIT(n);
-                        read_mailbox[n]();
-                }
-        }
-        return IRQ_HANDLED;
-}
-
-void __init prcmu_early_init(void)
-{
-        if (cpu_is_u8500v11() || cpu_is_u8500ed()) {
-                tcdm_base = __io_address(U8500_PRCMU_TCDM_BASE_V1);
-        } else if (cpu_is_u8500v2()) {
-                tcdm_base = __io_address(U8500_PRCMU_TCDM_BASE);
-        } else {
-                pr_err("prcmu: Unsupported chip version\n");
-                BUG();
-        }
-}
-
-static int __init prcmu_init(void)
-{
-        if (cpu_is_u8500ed()) {
-                pr_err("prcmu: Unsupported chip version\n");
-                return 0;
-        }
-
-        mutex_init(&mb1_transfer.lock);
-        init_completion(&mb1_transfer.work);
-        mutex_init(&mb5_transfer.lock);
-        init_completion(&mb5_transfer.work);
-
-        /* Clean up the mailbox interrupts after pre-kernel code. */
-        writel((MBOX_BIT(NUM_MBOX) - 1), PRCM_ARM_IT1_CLEAR);
-
-        return request_irq(IRQ_DB8500_PRCMU1, prcmu_irq_handler, 0,
-                           "prcmu", NULL);
-}
-
-arch_initcall(prcmu_init);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 76f82ae44efb..3f17ea146f0e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -85,7 +85,7 @@ void show_mem(unsigned int filter)
         struct meminfo * mi = &meminfo;
 
         printk("Mem-info:\n");
-        show_free_areas();
+        show_free_areas(filter);
 
         for_each_bank (i, mi) {
                 struct membank *bank = &mi->bank[i];
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6cf76b3b68d1..08a92368d9d3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -31,8 +31,6 @@
 
 #include "mm.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * empty_zero_page is a special page that is used for
  * zero-initialized data and COW.
diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c
index a7314d44b17b..2798c2d4a1cf 100644
--- a/arch/avr32/mm/init.c
+++ b/arch/avr32/mm/init.c
@@ -25,8 +25,6 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_data;
 
 struct page *empty_zero_page;
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 8addb1220b4f..a18180f2d007 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -24,11 +24,13 @@ config BLACKFIN
         select HAVE_FUNCTION_TRACER
         select HAVE_FUNCTION_TRACE_MCOUNT_TEST
         select HAVE_IDE
+        select HAVE_IRQ_WORK
         select HAVE_KERNEL_GZIP if RAMKERNEL
         select HAVE_KERNEL_BZIP2 if RAMKERNEL
         select HAVE_KERNEL_LZMA if RAMKERNEL
         select HAVE_KERNEL_LZO if RAMKERNEL
         select HAVE_OPROFILE
+        select HAVE_PERF_EVENTS
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select HAVE_GENERIC_HARDIRQS
         select GENERIC_ATOMIC64
diff --git a/arch/blackfin/Kconfig.debug b/arch/blackfin/Kconfig.debug
index 2641731f24cd..e2a3d4c8ab9a 100644
--- a/arch/blackfin/Kconfig.debug
+++ b/arch/blackfin/Kconfig.debug
@@ -9,15 +9,6 @@ config DEBUG_STACKOVERFLOW
           This option will cause messages to be printed if free stack space
           drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-        bool "Enable stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T output.
-
-          This option will slow down process creation somewhat.
-
 config DEBUG_VERBOSE
         bool "Verbose fault messages"
         default y
@@ -32,7 +23,7 @@ config DEBUG_VERBOSE
           Most people should say N here.
 
 config DEBUG_MMRS
-        bool "Generate Blackfin MMR tree"
+        tristate "Generate Blackfin MMR tree"
         select DEBUG_FS
         help
           Create a tree of Blackfin MMRs via the debugfs tree.  If
diff --git a/arch/blackfin/configs/BF527-EZKIT-V2_defconfig b/arch/blackfin/configs/BF527-EZKIT-V2_defconfig
index 95cf2ba9de17..8465b3e6b862 100644
--- a/arch/blackfin/configs/BF527-EZKIT-V2_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT-V2_defconfig
@@ -121,13 +121,11 @@ CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
 # CONFIG_LOGO_BLACKFIN_VGA16 is not set
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_SOC=m
-CONFIG_SND_BF5XX_I2S=m
-CONFIG_SND_BF5XX_SOC_SSM2602=m
-CONFIG_SND_BF5XX_AC97=m
-CONFIG_SND_BF5XX_SOC_AD1980=m
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SOC=y
+CONFIG_SND_BF5XX_I2S=y
+CONFIG_SND_BF5XX_SOC_SSM2602=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig
index 8be8e33fac52..5e7321b26040 100644
--- a/arch/blackfin/configs/BF527-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT_defconfig
@@ -96,7 +96,7 @@ CONFIG_SERIAL_BFIN_UART1=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_BLACKFIN_TWI=m
+CONFIG_I2C_BLACKFIN_TWI=y
 CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100
 CONFIG_SPI=y
 CONFIG_SPI_BFIN=y
@@ -115,13 +115,11 @@ CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
 # CONFIG_LOGO_BLACKFIN_VGA16 is not set
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_SOC=m
-CONFIG_SND_BF5XX_I2S=m
-CONFIG_SND_BF5XX_SOC_SSM2602=m
-CONFIG_SND_BF5XX_AC97=m
-CONFIG_SND_BF5XX_SOC_AD1980=m
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SOC=y
+CONFIG_SND_BF5XX_I2S=y
+CONFIG_SND_BF5XX_SOC_SSM2602=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
diff --git a/arch/blackfin/configs/BF533-STAMP_defconfig b/arch/blackfin/configs/BF533-STAMP_defconfig
index 0aafde6c8c2d..b90d3792ed52 100644
--- a/arch/blackfin/configs/BF533-STAMP_defconfig
+++ b/arch/blackfin/configs/BF533-STAMP_defconfig
@@ -99,8 +99,6 @@ CONFIG_SND_PCM_OSS=m
 CONFIG_SND_SOC=m
 CONFIG_SND_BF5XX_I2S=m
 CONFIG_SND_BF5XX_SOC_AD73311=m
-CONFIG_SND_BF5XX_AC97=m
-CONFIG_SND_BF5XX_SOC_AD1980=m
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_BFIN=y
diff --git a/arch/blackfin/configs/BF537-STAMP_defconfig b/arch/blackfin/configs/BF537-STAMP_defconfig
index c9077fb58135..005362537a7b 100644
--- a/arch/blackfin/configs/BF537-STAMP_defconfig
+++ b/arch/blackfin/configs/BF537-STAMP_defconfig
@@ -110,8 +110,6 @@ CONFIG_SND_PCM_OSS=m
 CONFIG_SND_SOC=m
 CONFIG_SND_BF5XX_I2S=m
 CONFIG_SND_BF5XX_SOC_AD73311=m
-CONFIG_SND_BF5XX_AC97=m
-CONFIG_SND_BF5XX_SOC_AD1980=m
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_BFIN=y
diff --git a/arch/blackfin/include/asm/bfin-global.h b/arch/blackfin/include/asm/bfin-global.h
index 121cc04d877d..17bcbf60bcae 100644
--- a/arch/blackfin/include/asm/bfin-global.h
+++ b/arch/blackfin/include/asm/bfin-global.h
@@ -49,16 +49,6 @@ extern void dump_bfin_trace_buffer(void);
 #define dump_bfin_trace_buffer()
 #endif
 
-/* init functions only */
-extern int init_arch_irq(void);
-extern void init_exception_vectors(void);
-extern void program_IAR(void);
-
-extern asmlinkage void lower_to_irq14(void);
-extern asmlinkage void bfin_return_from_exception(void);
-extern asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs);
-extern int bfin_internal_set_wake(unsigned int irq, unsigned int state);
-
 extern void *l1_data_A_sram_alloc(size_t);
 extern void *l1_data_B_sram_alloc(size_t);
 extern void *l1_inst_sram_alloc(size_t);
diff --git a/arch/blackfin/include/asm/bfin_pfmon.h b/arch/blackfin/include/asm/bfin_pfmon.h
new file mode 100644
index 000000000000..accd47e2db40
--- /dev/null
+++ b/arch/blackfin/include/asm/bfin_pfmon.h
@@ -0,0 +1,44 @@
+/*
+ * Blackfin Performance Monitor definitions
+ *
+ * Copyright 2005-2011 Analog Devices Inc.
+ *
+ * Licensed under the ADI BSD license or GPL-2 (or later).
+ */
+
+#ifndef __ASM_BFIN_PFMON_H__
+#define __ASM_BFIN_PFMON_H__
+
+/* PFCTL Masks */
+#define PFMON_MASK      0xff
+#define PFCEN_MASK      0x3
+#define PFCEN_DISABLE   0x0
+#define PFCEN_ENABLE_USER       0x1
+#define PFCEN_ENABLE_SUPV       0x2
+#define PFCEN_ENABLE_ALL        (PFCEN_ENABLE_USER | PFCEN_ENABLE_SUPV)
+
+#define PFPWR_P 0
+#define PEMUSW0_P       2
+#define PFCEN0_P        3
+#define PFMON0_P        5
+#define PEMUSW1_P       13
+#define PFCEN1_P        14
+#define PFMON1_P        16
+#define PFCNT0_P        24
+#define PFCNT1_P        25
+
+#define PFPWR   (1 << PFPWR_P)
+#define PEMUSW(n, x)    ((x) << ((n) ? PEMUSW1_P : PEMUSW0_P))
+#define PEMUSW0 PEMUSW(0, 1)
+#define PEMUSW1 PEMUSW(1, 1)
+#define PFCEN(n, x)     ((x) << ((n) ? PFCEN1_P : PFCEN0_P))
+#define PFCEN0  PFCEN(0, PFCEN_MASK)
+#define PFCEN1  PFCEN(1, PFCEN_MASK)
+#define PFCNT(n, x)     ((x) << ((n) ? PFCNT1_P : PFCNT0_P))
+#define PFCNT0  PFCNT(0, 1)
+#define PFCNT1  PFCNT(1, 1)
+#define PFMON(n, x)     ((x) << ((n) ? PFMON1_P : PFMON0_P))
+#define PFMON0  PFMON(0, PFMON_MASK)
+#define PFMON1  PFMON(1, PFMON_MASK)
+
+#endif
diff --git a/arch/blackfin/include/asm/bfin_sport.h b/arch/blackfin/include/asm/bfin_sport.h
index d27600c262c2..f8568a31d0ab 100644
--- a/arch/blackfin/include/asm/bfin_sport.h
+++ b/arch/blackfin/include/asm/bfin_sport.h
@@ -100,6 +100,10 @@ struct sport_register {
 };
 #undef __BFP
 
+struct bfin_snd_platform_data {
+        const unsigned short *pin_req;
+};
+
 #define bfin_read_sport_rx32(base) \
 ({ \
         struct sport_register *__mmrs = (void *)base; \
diff --git a/arch/blackfin/include/asm/cacheflush.h b/arch/blackfin/include/asm/cacheflush.h
index 77135b62818e..9a5b2c572ebf 100644
--- a/arch/blackfin/include/asm/cacheflush.h
+++ b/arch/blackfin/include/asm/cacheflush.h
@@ -39,8 +39,13 @@ extern void blackfin_invalidate_entire_icache(void);
 
 static inline void flush_icache_range(unsigned start, unsigned end)
 {
-#if defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK)
-        blackfin_dcache_flush_range(start, end);
+#if defined(CONFIG_BFIN_EXTMEM_WRITEBACK)
+        if (end <= physical_mem_end)
+                blackfin_dcache_flush_range(start, end);
+#endif
+#if defined(CONFIG_BFIN_L2_WRITEBACK)
+        if (start >= L2_START && end <= L2_START + L2_LENGTH)
+                blackfin_dcache_flush_range(start, end);
 #endif
 
         /* Make sure all write buffers in the data side of the core
@@ -52,9 +57,17 @@ static inline void flush_icache_range(unsigned start, unsigned end)
          * the pipeline.
          */
         SSYNC();
-#if defined(CONFIG_BFIN_ICACHE)
-        blackfin_icache_flush_range(start, end);
-        flush_icache_range_others(start, end);
+#if defined(CONFIG_BFIN_EXTMEM_ICACHEABLE)
+        if (end <= physical_mem_end) {
+                blackfin_icache_flush_range(start, end);
+                flush_icache_range_others(start, end);
+        }
+#endif
+#if defined(CONFIG_BFIN_L2_ICACHEABLE)
+        if (start >= L2_START && end <= L2_START + L2_LENGTH) {
+                blackfin_icache_flush_range(start, end);
+                flush_icache_range_others(start, end);
+        }
 #endif
 }
 
diff --git a/arch/blackfin/include/asm/cpu.h b/arch/blackfin/include/asm/cpu.h
index 16883e582e3c..05043786da21 100644
--- a/arch/blackfin/include/asm/cpu.h
+++ b/arch/blackfin/include/asm/cpu.h
@@ -10,11 +10,8 @@
 
 #include <linux/percpu.h>
 
-struct task_struct;
-
 struct blackfin_cpudata {
         struct cpu cpu;
-        struct task_struct *idle;
         unsigned int imemctl;
         unsigned int dmemctl;
 };
diff --git a/arch/blackfin/include/asm/def_LPBlackfin.h b/arch/blackfin/include/asm/def_LPBlackfin.h
index 7600fe0696af..823679011457 100644
--- a/arch/blackfin/include/asm/def_LPBlackfin.h
+++ b/arch/blackfin/include/asm/def_LPBlackfin.h
@@ -52,10 +52,10 @@
 
 #define bfin_read(addr) \
 ({ \
-    sizeof(*(addr)) == 1 ? bfin_read8(addr)  : \
-    sizeof(*(addr)) == 2 ? bfin_read16(addr) : \
-    sizeof(*(addr)) == 4 ? bfin_read32(addr) : \
-    ({ BUG(); 0; }); \
+        sizeof(*(addr)) == 1 ? bfin_read8(addr)  : \
+        sizeof(*(addr)) == 2 ? bfin_read16(addr) : \
+        sizeof(*(addr)) == 4 ? bfin_read32(addr) : \
+        ({ BUG(); 0; }); \
 })
 #define bfin_write(addr, val) \
 do { \
@@ -69,13 +69,13 @@ do { \
 
 #define bfin_write_or(addr, bits) \
 do { \
-        void *__addr = (void *)(addr); \
+        typeof(addr) __addr = (addr); \
         bfin_write(__addr, bfin_read(__addr) | (bits)); \
 } while (0)
 
 #define bfin_write_and(addr, bits) \
 do { \
-        void *__addr = (void *)(addr); \
+        typeof(addr) __addr = (addr); \
         bfin_write(__addr, bfin_read(__addr) & (bits)); \
 } while (0)
 
diff --git a/arch/blackfin/include/asm/irq_handler.h b/arch/blackfin/include/asm/irq_handler.h
index 7fbe42307b9a..ee73f79aef10 100644
--- a/arch/blackfin/include/asm/irq_handler.h
+++ b/arch/blackfin/include/asm/irq_handler.h
@@ -10,6 +10,16 @@
 #include <linux/types.h>
 #include <linux/linkage.h>
 
+/* init functions only */
+extern int __init init_arch_irq(void);
+extern void init_exception_vectors(void);
+extern void __init program_IAR(void);
+#ifdef init_mach_irq
+extern void __init init_mach_irq(void);
+#else
+# define init_mach_irq()
+#endif
+
 /* BASE LEVEL interrupt handler routines */
 asmlinkage void evt_exception(void);
 asmlinkage void trap(void);
@@ -37,4 +47,19 @@ extern void return_from_exception(void);
 extern int bfin_request_exception(unsigned int exception, void (*handler)(void));
 extern int bfin_free_exception(unsigned int exception, void (*handler)(void));
 
+extern asmlinkage void lower_to_irq14(void);
+extern asmlinkage void bfin_return_from_exception(void);
+extern asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs);
+extern int bfin_internal_set_wake(unsigned int irq, unsigned int state);
+
+struct irq_data;
+extern void bfin_handle_irq(unsigned irq);
+extern void bfin_ack_noop(struct irq_data *);
+extern void bfin_internal_mask_irq(unsigned int irq);
+extern void bfin_internal_unmask_irq(unsigned int irq);
+
+struct irq_desc;
+extern void bfin_demux_mac_status_irq(unsigned int, struct irq_desc *);
+extern void bfin_demux_gpio_irq(unsigned int, struct irq_desc *);
+
 #endif
diff --git a/arch/blackfin/include/asm/kgdb.h b/arch/blackfin/include/asm/kgdb.h
index 8651afe12990..3ac0c72e9fee 100644
--- a/arch/blackfin/include/asm/kgdb.h
+++ b/arch/blackfin/include/asm/kgdb.h
@@ -103,7 +103,11 @@ static inline void arch_kgdb_breakpoint(void)
         asm("EXCPT 2;");
 }
 #define BREAK_INSTR_SIZE        2
-#define CACHE_FLUSH_IS_SAFE     1
+#ifdef CONFIG_SMP
+# define CACHE_FLUSH_IS_SAFE    0
+#else
+# define CACHE_FLUSH_IS_SAFE    1
+#endif
 #define HW_INST_WATCHPOINT_NUM  6
 #define HW_WATCHPOINT_NUM       8
 #define TYPE_INST_WATCHPOINT    0
diff --git a/arch/blackfin/include/asm/perf_event.h b/arch/blackfin/include/asm/perf_event.h
new file mode 100644
index 000000000000..3d2b1716322f
--- /dev/null
+++ b/arch/blackfin/include/asm/perf_event.h
@@ -0,0 +1 @@
+#define MAX_HWEVENTS 2
diff --git a/arch/blackfin/include/asm/ptrace.h b/arch/blackfin/include/asm/ptrace.h
index 832d7c009a2c..1066d63e62b5 100644
--- a/arch/blackfin/include/asm/ptrace.h
+++ b/arch/blackfin/include/asm/ptrace.h
@@ -108,8 +108,6 @@ struct pt_regs {
 extern void show_regs(struct pt_regs *);
 
 #define arch_has_single_step()  (1)
-extern void user_enable_single_step(struct task_struct *child);
-extern void user_disable_single_step(struct task_struct *child);
 /* common code demands this function */
 #define ptrace_disable(child) user_disable_single_step(child)
 
diff --git a/arch/blackfin/include/mach-common/irq.h b/arch/blackfin/include/mach-common/irq.h
new file mode 100644
index 000000000000..cab14e911dc2
--- /dev/null
+++ b/arch/blackfin/include/mach-common/irq.h
@@ -0,0 +1,57 @@
+/*
+ * Common Blackfin IRQ definitions (i.e. the CEC)
+ *
+ * Copyright 2005-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#ifndef _MACH_COMMON_IRQ_H_
+#define _MACH_COMMON_IRQ_H_
+
+/*
+ * Core events interrupt source definitions
+ *
+ *  Event Source       Event Name
+ *  Emulation          EMU            0  (highest priority)
+ *  Reset              RST            1
+ *  NMI                NMI            2
+ *  Exception          EVX            3
+ *  Reserved           --             4
+ *  Hardware Error     IVHW           5
+ *  Core Timer         IVTMR          6
+ *  Peripherals        IVG7           7
+ *  Peripherals        IVG8           8
+ *  Peripherals        IVG9           9
+ *  Peripherals        IVG10         10
+ *  Peripherals        IVG11         11
+ *  Peripherals        IVG12         12
+ *  Peripherals        IVG13         13
+ *  Softirq            IVG14         14
+ *  System Call        IVG15         15  (lowest priority)
+ */
+
+/* The ABSTRACT IRQ definitions */
+#define IRQ_EMU                 0       /* Emulation */
+#define IRQ_RST                 1       /* reset */
+#define IRQ_NMI                 2       /* Non Maskable */
+#define IRQ_EVX                 3       /* Exception */
+#define IRQ_UNUSED              4       /* - unused interrupt */
+#define IRQ_HWERR               5       /* Hardware Error */
+#define IRQ_CORETMR             6       /* Core timer */
+
+#define BFIN_IRQ(x)             ((x) + 7)
+
+#define IVG7                    7
+#define IVG8                    8
+#define IVG9                    9
+#define IVG10                   10
+#define IVG11                   11
+#define IVG12                   12
+#define IVG13                   13
+#define IVG14                   14
+#define IVG15                   15
+
+#define NR_IRQS                 (NR_MACH_IRQS + NR_SPARE_IRQS)
+
+#endif
diff --git a/arch/blackfin/kernel/Makefile b/arch/blackfin/kernel/Makefile
index ca5ccc777772..d550b24d9e9b 100644
--- a/arch/blackfin/kernel/Makefile
+++ b/arch/blackfin/kernel/Makefile
@@ -33,7 +33,10 @@ obj-$(CONFIG_EARLY_PRINTK)           += shadow_console.o
 obj-$(CONFIG_STACKTRACE)             += stacktrace.o
 obj-$(CONFIG_DEBUG_VERBOSE)          += trace.o
 obj-$(CONFIG_BFIN_PSEUDODBG_INSNS)   += pseudodbg.o
+obj-$(CONFIG_PERF_EVENTS)            += perf_event.o
 
 # the kgdb test puts code into L2 and without linker
 # relaxation, we need to force long calls to/from it
 CFLAGS_kgdb_test.o := -mlong-calls -O0
+
+obj-$(CONFIG_DEBUG_MMRS)             += debug-mmrs.o
diff --git a/arch/blackfin/kernel/bfin_dma_5xx.c b/arch/blackfin/kernel/bfin_dma_5xx.c
index 6ce8dce753c9..71dbaa4a48af 100644
--- a/arch/blackfin/kernel/bfin_dma_5xx.c
+++ b/arch/blackfin/kernel/bfin_dma_5xx.c
@@ -36,6 +36,11 @@ static int __init blackfin_dma_init(void)
 
         printk(KERN_INFO "Blackfin DMA Controller\n");
 
+
+#if ANOMALY_05000480
+        bfin_write_DMAC_TC_PER(0x0111);
+#endif
+
         for (i = 0; i < MAX_DMA_CHANNELS; i++) {
                 atomic_set(&dma_ch[i].chan_status, 0);
                 dma_ch[i].regs = dma_io_base_addr[i];
diff --git a/arch/blackfin/kernel/bfin_gpio.c b/arch/blackfin/kernel/bfin_gpio.c
index 170cf90735ba..bcf8cf6fe412 100644
--- a/arch/blackfin/kernel/bfin_gpio.c
+++ b/arch/blackfin/kernel/bfin_gpio.c
@@ -10,10 +10,12 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <asm/blackfin.h>
 #include <asm/gpio.h>
 #include <asm/portmux.h>
 #include <linux/irq.h>
+#include <asm/irq_handler.h>
 
 #if ANOMALY_05000311 || ANOMALY_05000323
 enum {
@@ -534,7 +536,7 @@ static const unsigned int sic_iwr_irqs[] = {
 #if defined(BF533_FAMILY)
         IRQ_PROG_INTB
 #elif defined(BF537_FAMILY)
-        IRQ_PROG_INTB, IRQ_PORTG_INTB, IRQ_MAC_TX
+        IRQ_PF_INTB_WATCH, IRQ_PORTG_INTB, IRQ_PH_INTB_MAC_TX
 #elif defined(BF538_FAMILY)
         IRQ_PORTF_INTB
 #elif defined(CONFIG_BF52x) || defined(CONFIG_BF51x)
@@ -1203,35 +1205,43 @@ void bfin_reset_boot_spi_cs(unsigned short pin)
 }
 
 #if defined(CONFIG_PROC_FS)
-static int gpio_proc_read(char *buf, char **start, off_t offset,
-                          int len, int *unused_i, void *unused_v)
+static int gpio_proc_show(struct seq_file *m, void *v)
 {
-        int c, irq, gpio, outlen = 0;
+        int c, irq, gpio;
 
         for (c = 0; c < MAX_RESOURCES; c++) {
                 irq = is_reserved(gpio_irq, c, 1);
                 gpio = is_reserved(gpio, c, 1);
                 if (!check_gpio(c) && (gpio || irq))
-                        len = sprintf(buf, "GPIO_%d: \t%s%s \t\tGPIO %s\n", c,
+                        seq_printf(m, "GPIO_%d: \t%s%s \t\tGPIO %s\n", c,
                                  get_label(c), (gpio && irq) ? " *" : "",
                                  get_gpio_dir(c) ? "OUTPUT" : "INPUT");
                 else if (is_reserved(peri, c, 1))
-                        len = sprintf(buf, "GPIO_%d: \t%s \t\tPeripheral\n", c, get_label(c));
+                        seq_printf(m, "GPIO_%d: \t%s \t\tPeripheral\n", c, get_label(c));
                 else
                         continue;
-                buf += len;
-                outlen += len;
         }
-        return outlen;
+
+        return 0;
 }
 
+static int gpio_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, gpio_proc_show, NULL);
+}
+
+static const struct file_operations gpio_proc_ops = {
+        .open           = gpio_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
 static __init int gpio_register_proc(void)
 {
         struct proc_dir_entry *proc_gpio;
 
-        proc_gpio = create_proc_entry("gpio", S_IRUGO, NULL);
-        if (proc_gpio)
-                proc_gpio->read_proc = gpio_proc_read;
+        proc_gpio = proc_create("gpio", S_IRUGO, NULL, &gpio_proc_ops);
         return proc_gpio != NULL;
 }
 __initcall(gpio_register_proc);
diff --git a/arch/blackfin/kernel/bfin_ksyms.c b/arch/blackfin/kernel/bfin_ksyms.c
index 2c264b51566a..c446591b961d 100644
--- a/arch/blackfin/kernel/bfin_ksyms.c
+++ b/arch/blackfin/kernel/bfin_ksyms.c
@@ -11,6 +11,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/io.h>
+#include <asm/irq_handler.h>
 
 /* Allow people to have their own Blackfin exception handler in a module */
 EXPORT_SYMBOL(bfin_return_from_exception);
diff --git a/arch/blackfin/kernel/debug-mmrs.c b/arch/blackfin/kernel/debug-mmrs.c
new file mode 100644
index 000000000000..94b1d8a0256a
--- /dev/null
+++ b/arch/blackfin/kernel/debug-mmrs.c
@@ -0,0 +1,1860 @@
+/*
+ * debugfs interface to core/system MMRs
+ *
+ * Copyright 2007-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/blackfin.h>
+#include <asm/gpio.h>
+#include <asm/bfin_can.h>
+#include <asm/bfin_dma.h>
+#include <asm/bfin_ppi.h>
+#include <asm/bfin_serial.h>
+#include <asm/bfin5xx_spi.h>
+#include <asm/bfin_twi.h>
+
+/* Common code defines PORT_MUX on us, so redirect the MMR back locally */
+#ifdef BFIN_PORT_MUX
+#undef PORT_MUX
+#define PORT_MUX BFIN_PORT_MUX
+#endif
+
+#define _d(name, bits, addr, perms) debugfs_create_x##bits(name, perms, parent, (u##bits *)addr)
+#define d(name, bits, addr)         _d(name, bits, addr, S_IRUSR|S_IWUSR)
+#define d_RO(name, bits, addr)      _d(name, bits, addr, S_IRUSR)
+#define d_WO(name, bits, addr)      _d(name, bits, addr, S_IWUSR)
+
+#define D_RO(name, bits) d_RO(#name, bits, name)
+#define D_WO(name, bits) d_WO(#name, bits, name)
+#define D32(name)        d(#name, 32, name)
+#define D16(name)        d(#name, 16, name)
+
+#define REGS_OFF(peri, mmr) offsetof(struct bfin_##peri##_regs, mmr)
+#define __REGS(peri, sname, rname) \
+        do { \
+                struct bfin_##peri##_regs r; \
+                void *addr = (void *)(base + REGS_OFF(peri, rname)); \
+                strcpy(_buf, sname); \
+                if (sizeof(r.rname) == 2) \
+                        debugfs_create_x16(buf, S_IRUSR|S_IWUSR, parent, addr); \
+                else \
+                        debugfs_create_x32(buf, S_IRUSR|S_IWUSR, parent, addr); \
+        } while (0)
+#define REGS_STR_PFX(buf, pfx, num) \
+        ({ \
+                buf + (num >= 0 ? \
+                        sprintf(buf, #pfx "%i_", num) : \
+                        sprintf(buf, #pfx "_")); \
+        })
+#define REGS_STR_PFX_C(buf, pfx, num) \
+        ({ \
+                buf + (num >= 0 ? \
+                        sprintf(buf, #pfx "%c_", 'A' + num) : \
+                        sprintf(buf, #pfx "_")); \
+        })
+
+/*
+ * Core registers (not memory mapped)
+ */
+extern u32 last_seqstat;
+
+static int debug_cclk_get(void *data, u64 *val)
+{
+        *val = get_cclk();
+        return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_debug_cclk, debug_cclk_get, NULL, "0x%08llx\n");
+
+static int debug_sclk_get(void *data, u64 *val)
+{
+        *val = get_sclk();
+        return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_debug_sclk, debug_sclk_get, NULL, "0x%08llx\n");
+
+#define DEFINE_SYSREG(sr, pre, post) \
+static int sysreg_##sr##_get(void *data, u64 *val) \
+{ \
+        unsigned long tmp; \
+        pre; \
+        __asm__ __volatile__("%0 = " #sr ";" : "=d"(tmp)); \
+        *val = tmp; \
+        return 0; \
+} \
+static int sysreg_##sr##_set(void *data, u64 val) \
+{ \
+        unsigned long tmp = val; \
+        __asm__ __volatile__(#sr " = %0;" : : "d"(tmp)); \
+        post; \
+        return 0; \
+} \
+DEFINE_SIMPLE_ATTRIBUTE(fops_sysreg_##sr, sysreg_##sr##_get, sysreg_##sr##_set, "0x%08llx\n")
+
+DEFINE_SYSREG(cycles, , );
+DEFINE_SYSREG(cycles2, __asm__ __volatile__("%0 = cycles;" : "=d"(tmp)), );
+DEFINE_SYSREG(emudat, , );
+DEFINE_SYSREG(seqstat, , );
+DEFINE_SYSREG(syscfg, , CSYNC());
+#define D_SYSREG(sr) debugfs_create_file(#sr, S_IRUSR|S_IWUSR, parent, NULL, &fops_sysreg_##sr)
+
+/*
+ * CAN
+ */
+#define CAN_OFF(mmr)  REGS_OFF(can, mmr)
+#define __CAN(uname, lname) __REGS(can, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_can(struct dentry *parent, unsigned long base, int num)
+{
+        static struct dentry *am, *mb;
+        int i, j;
+        char buf[32], *_buf = REGS_STR_PFX(buf, CAN, num);
+
+        if (!am) {
+                am = debugfs_create_dir("am", parent);
+                mb = debugfs_create_dir("mb", parent);
+        }
+
+        __CAN(MC1, mc1);
+        __CAN(MD1, md1);
+        __CAN(TRS1, trs1);
+        __CAN(TRR1, trr1);
+        __CAN(TA1, ta1);
+        __CAN(AA1, aa1);
+        __CAN(RMP1, rmp1);
+        __CAN(RML1, rml1);
+        __CAN(MBTIF1, mbtif1);
+        __CAN(MBRIF1, mbrif1);
+        __CAN(MBIM1, mbim1);
+        __CAN(RFH1, rfh1);
+        __CAN(OPSS1, opss1);
+
+        __CAN(MC2, mc2);
+        __CAN(MD2, md2);
+        __CAN(TRS2, trs2);
+        __CAN(TRR2, trr2);
+        __CAN(TA2, ta2);
+        __CAN(AA2, aa2);
+        __CAN(RMP2, rmp2);
+        __CAN(RML2, rml2);
+        __CAN(MBTIF2, mbtif2);
+        __CAN(MBRIF2, mbrif2);
+        __CAN(MBIM2, mbim2);
+        __CAN(RFH2, rfh2);
+        __CAN(OPSS2, opss2);
+
+        __CAN(CLOCK, clock);
+        __CAN(TIMING, timing);
+        __CAN(DEBUG, debug);
+        __CAN(STATUS, status);
+        __CAN(CEC, cec);
+        __CAN(GIS, gis);
+        __CAN(GIM, gim);
+        __CAN(GIF, gif);
+        __CAN(CONTROL, control);
+        __CAN(INTR, intr);
+        __CAN(VERSION, version);
+        __CAN(MBTD, mbtd);
+        __CAN(EWR, ewr);
+        __CAN(ESR, esr);
+        /*__CAN(UCREG, ucreg); no longer exists */
+        __CAN(UCCNT, uccnt);
+        __CAN(UCRC, ucrc);
+        __CAN(UCCNF, uccnf);
+        __CAN(VERSION2, version2);
+
+        for (i = 0; i < 32; ++i) {
+                sprintf(_buf, "AM%02iL", i);
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, am,
+                        (u16 *)(base + CAN_OFF(msk[i].aml)));
+                sprintf(_buf, "AM%02iH", i);
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, am,
+                        (u16 *)(base + CAN_OFF(msk[i].amh)));
+
+                for (j = 0; j < 3; ++j) {
+                        sprintf(_buf, "MB%02i_DATA%i", i, j);
+                        debugfs_create_x16(buf, S_IRUSR|S_IWUSR, mb,
+                                (u16 *)(base + CAN_OFF(chl[i].data[j*2])));
+                }
+                sprintf(_buf, "MB%02i_LENGTH", i);
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, mb,
+                        (u16 *)(base + CAN_OFF(chl[i].dlc)));
+                sprintf(_buf, "MB%02i_TIMESTAMP", i);
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, mb,
+                        (u16 *)(base + CAN_OFF(chl[i].tsv)));
+                sprintf(_buf, "MB%02i_ID0", i);
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, mb,
+                        (u16 *)(base + CAN_OFF(chl[i].id0)));
+                sprintf(_buf, "MB%02i_ID1", i);
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, mb,
+                        (u16 *)(base + CAN_OFF(chl[i].id1)));
+        }
+}
+#define CAN(num) bfin_debug_mmrs_can(parent, CAN##num##_MC1, num)
+
+/*
+ * DMA
+ */
+#define __DMA(uname, lname) __REGS(dma, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_dma(struct dentry *parent, unsigned long base, int num, char mdma, const char *pfx)
+{
+        char buf[32], *_buf;
+
+        if (mdma)
+                _buf = buf + sprintf(buf, "%s_%c%i_", pfx, mdma, num);
+        else
+                _buf = buf + sprintf(buf, "%s%i_", pfx, num);
+
+        __DMA(NEXT_DESC_PTR, next_desc_ptr);
+        __DMA(START_ADDR, start_addr);
+        __DMA(CONFIG, config);
+        __DMA(X_COUNT, x_count);
+        __DMA(X_MODIFY, x_modify);
+        __DMA(Y_COUNT, y_count);
+        __DMA(Y_MODIFY, y_modify);
+        __DMA(CURR_DESC_PTR, curr_desc_ptr);
+        __DMA(CURR_ADDR, curr_addr);
+        __DMA(IRQ_STATUS, irq_status);
+        __DMA(PERIPHERAL_MAP, peripheral_map);
+        __DMA(CURR_X_COUNT, curr_x_count);
+        __DMA(CURR_Y_COUNT, curr_y_count);
+}
+#define _DMA(num, base, mdma, pfx) bfin_debug_mmrs_dma(parent, base, num, mdma, pfx "DMA")
+#define DMA(num)  _DMA(num, DMA##num##_NEXT_DESC_PTR, 0, "")
+#define _MDMA(num, x) \
+        do { \
+                _DMA(num, x##DMA_D##num##_CONFIG, 'D', #x); \
+                _DMA(num, x##DMA_S##num##_CONFIG, 'S', #x); \
+        } while (0)
+#define MDMA(num) _MDMA(num, M)
+#define IMDMA(num) _MDMA(num, IM)
+
+/*
+ * EPPI
+ */
+#define __EPPI(uname, lname) __REGS(eppi, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_eppi(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, EPPI, num);
+        __EPPI(STATUS, status);
+        __EPPI(HCOUNT, hcount);
+        __EPPI(HDELAY, hdelay);
+        __EPPI(VCOUNT, vcount);
+        __EPPI(VDELAY, vdelay);
+        __EPPI(FRAME, frame);
+        __EPPI(LINE, line);
+        __EPPI(CLKDIV, clkdiv);
+        __EPPI(CONTROL, control);
+        __EPPI(FS1W_HBL, fs1w_hbl);
+        __EPPI(FS1P_AVPL, fs1p_avpl);
+        __EPPI(FS2W_LVB, fs2w_lvb);
+        __EPPI(FS2P_LAVF, fs2p_lavf);
+        __EPPI(CLIP, clip);
+}
+#define EPPI(num) bfin_debug_mmrs_eppi(parent, EPPI##num##_STATUS, num)
+
+/*
+ * General Purpose Timers
+ */
+#define GPTIMER_OFF(mmr) (TIMER0_##mmr - TIMER0_CONFIG)
+#define __GPTIMER(name) \
+        do { \
+                strcpy(_buf, #name); \
+                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, parent, (u16 *)(base + GPTIMER_OFF(name))); \
+        } while (0)
+static void __init __maybe_unused
+bfin_debug_mmrs_gptimer(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, TIMER, num);
+        __GPTIMER(CONFIG);
+        __GPTIMER(COUNTER);
+        __GPTIMER(PERIOD);
+        __GPTIMER(WIDTH);
+}
+#define GPTIMER(num) bfin_debug_mmrs_gptimer(parent, TIMER##num##_CONFIG, num)
+
+/*
+ * Handshake MDMA
+ */
+#define __HMDMA(uname, lname) __REGS(hmdma, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_hmdma(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, HMDMA, num);
+        __HMDMA(CONTROL, control);
+        __HMDMA(ECINIT, ecinit);
+        __HMDMA(BCINIT, bcinit);
+        __HMDMA(ECURGENT, ecurgent);
+        __HMDMA(ECOVERFLOW, ecoverflow);
+        __HMDMA(ECOUNT, ecount);
+        __HMDMA(BCOUNT, bcount);
+}
+#define HMDMA(num) bfin_debug_mmrs_hmdma(parent, HMDMA##num##_CONTROL, num)
+
+/*
+ * Port/GPIO
+ */
+#define bfin_gpio_regs gpio_port_t
+#define __PORT(uname, lname) __REGS(gpio, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_port(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf;
+#ifdef __ADSPBF54x__
+        _buf = REGS_STR_PFX_C(buf, PORT, num);
+        __PORT(FER, port_fer);
+        __PORT(SET, data_set);
+        __PORT(CLEAR, data_clear);
+        __PORT(DIR_SET, dir_set);
+        __PORT(DIR_CLEAR, dir_clear);
+        __PORT(INEN, inen);
+        __PORT(MUX, port_mux);
+#else
+        _buf = buf + sprintf(buf, "PORT%cIO_", num);
+        __PORT(CLEAR, data_clear);
+        __PORT(SET, data_set);
+        __PORT(TOGGLE, toggle);
+        __PORT(MASKA, maska);
+        __PORT(MASKA_CLEAR, maska_clear);
+        __PORT(MASKA_SET, maska_set);
+        __PORT(MASKA_TOGGLE, maska_toggle);
+        __PORT(MASKB, maskb);
+        __PORT(MASKB_CLEAR, maskb_clear);
+        __PORT(MASKB_SET, maskb_set);
+        __PORT(MASKB_TOGGLE, maskb_toggle);
+        __PORT(DIR, dir);
+        __PORT(POLAR, polar);
+        __PORT(EDGE, edge);
+        __PORT(BOTH, both);
+        __PORT(INEN, inen);
+#endif
+        _buf[-1] = '\0';
+        d(buf, 16, base + REGS_OFF(gpio, data));
+}
+#define PORT(base, num) bfin_debug_mmrs_port(parent, base, num)
+
+/*
+ * PPI
+ */
+#define __PPI(uname, lname) __REGS(ppi, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_ppi(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, PPI, num);
+        __PPI(CONTROL, control);
+        __PPI(STATUS, status);
+        __PPI(COUNT, count);
+        __PPI(DELAY, delay);
+        __PPI(FRAME, frame);
+}
+#define PPI(num) bfin_debug_mmrs_ppi(parent, PPI##num##_STATUS, num)
+
+/*
+ * SPI
+ */
+#define __SPI(uname, lname) __REGS(spi, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_spi(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, SPI, num);
+        __SPI(CTL, ctl);
+        __SPI(FLG, flg);
+        __SPI(STAT, stat);
+        __SPI(TDBR, tdbr);
+        __SPI(RDBR, rdbr);
+        __SPI(BAUD, baud);
+        __SPI(SHADOW, shadow);
+}
+#define SPI(num) bfin_debug_mmrs_spi(parent, SPI##num##_REGBASE, num)
+
+/*
+ * SPORT
+ */
+static inline int sport_width(void *mmr)
+{
+        unsigned long lmmr = (unsigned long)mmr;
+        if ((lmmr & 0xff) == 0x10)
+                /* SPORT#_TX has 0x10 offset -> SPORT#_TCR2 has 0x04 offset */
+                lmmr -= 0xc;
+        else
+                /* SPORT#_RX has 0x18 offset -> SPORT#_RCR2 has 0x24 offset */
+                lmmr += 0xc;
+        /* extract SLEN field from control register 2 and add 1 */
+        return (bfin_read16(lmmr) & 0x1f) + 1;
+}
+static int sport_set(void *mmr, u64 val)
+{
+        unsigned long flags;
+        local_irq_save(flags);
+        if (sport_width(mmr) <= 16)
+                bfin_write16(mmr, val);
+        else
+                bfin_write32(mmr, val);
+        local_irq_restore(flags);
+        return 0;
+}
+static int sport_get(void *mmr, u64 *val)
+{
+        unsigned long flags;
+        local_irq_save(flags);
+        if (sport_width(mmr) <= 16)
+                *val = bfin_read16(mmr);
+        else
+                *val = bfin_read32(mmr);
+        local_irq_restore(flags);
+        return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_sport, sport_get, sport_set, "0x%08llx\n");
+/*DEFINE_SIMPLE_ATTRIBUTE(fops_sport_ro, sport_get, NULL, "0x%08llx\n");*/
+DEFINE_SIMPLE_ATTRIBUTE(fops_sport_wo, NULL, sport_set, "0x%08llx\n");
+#define SPORT_OFF(mmr) (SPORT0_##mmr - SPORT0_TCR1)
+#define _D_SPORT(name, perms, fops) \
+        do { \
+                strcpy(_buf, #name); \
+                debugfs_create_file(buf, perms, parent, (void *)(base + SPORT_OFF(name)), fops); \
+        } while (0)
+#define __SPORT_RW(name) _D_SPORT(name, S_IRUSR|S_IWUSR, &fops_sport)
+#define __SPORT_RO(name) _D_SPORT(name, S_IRUSR, &fops_sport_ro)
+#define __SPORT_WO(name) _D_SPORT(name, S_IWUSR, &fops_sport_wo)
+#define __SPORT(name, bits) \
+        do { \
+                strcpy(_buf, #name); \
+                debugfs_create_x##bits(buf, S_IRUSR|S_IWUSR, parent, (u##bits *)(base + SPORT_OFF(name))); \
+        } while (0)
+static void __init __maybe_unused
+bfin_debug_mmrs_sport(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, SPORT, num);
+        __SPORT(CHNL, 16);
+        __SPORT(MCMC1, 16);
+        __SPORT(MCMC2, 16);
+        __SPORT(MRCS0, 32);
+        __SPORT(MRCS1, 32);
+        __SPORT(MRCS2, 32);
+        __SPORT(MRCS3, 32);
+        __SPORT(MTCS0, 32);
+        __SPORT(MTCS1, 32);
+        __SPORT(MTCS2, 32);
+        __SPORT(MTCS3, 32);
+        __SPORT(RCLKDIV, 16);
+        __SPORT(RCR1, 16);
+        __SPORT(RCR2, 16);
+        __SPORT(RFSDIV, 16);
+        __SPORT_RW(RX);
+        __SPORT(STAT, 16);
+        __SPORT(TCLKDIV, 16);
+        __SPORT(TCR1, 16);
+        __SPORT(TCR2, 16);
+        __SPORT(TFSDIV, 16);
+        __SPORT_WO(TX);
+}
+#define SPORT(num) bfin_debug_mmrs_sport(parent, SPORT##num##_TCR1, num)
+
+/*
+ * TWI
+ */
+#define __TWI(uname, lname) __REGS(twi, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_twi(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, TWI, num);
+        __TWI(CLKDIV, clkdiv);
+        __TWI(CONTROL, control);
+        __TWI(SLAVE_CTL, slave_ctl);
+        __TWI(SLAVE_STAT, slave_stat);
+        __TWI(SLAVE_ADDR, slave_addr);
+        __TWI(MASTER_CTL, master_ctl);
+        __TWI(MASTER_STAT, master_stat);
+        __TWI(MASTER_ADDR, master_addr);
+        __TWI(INT_STAT, int_stat);
+        __TWI(INT_MASK, int_mask);
+        __TWI(FIFO_CTL, fifo_ctl);
+        __TWI(FIFO_STAT, fifo_stat);
+        __TWI(XMT_DATA8, xmt_data8);
+        __TWI(XMT_DATA16, xmt_data16);
+        __TWI(RCV_DATA8, rcv_data8);
+        __TWI(RCV_DATA16, rcv_data16);
+}
+#define TWI(num) bfin_debug_mmrs_twi(parent, TWI##num##_CLKDIV, num)
+
+/*
+ * UART
+ */
+#define __UART(uname, lname) __REGS(uart, #uname, lname)
+static void __init __maybe_unused
+bfin_debug_mmrs_uart(struct dentry *parent, unsigned long base, int num)
+{
+        char buf[32], *_buf = REGS_STR_PFX(buf, UART, num);
+#ifdef BFIN_UART_BF54X_STYLE
+        __UART(DLL, dll);
+        __UART(DLH, dlh);
+        __UART(GCTL, gctl);
+        __UART(LCR, lcr);
+        __UART(MCR, mcr);
+        __UART(LSR, lsr);
+        __UART(MSR, msr);
+        __UART(SCR, scr);
+        __UART(IER_SET, ier_set);
+        __UART(IER_CLEAR, ier_clear);
+        __UART(THR, thr);
+        __UART(RBR, rbr);
+#else
+        __UART(DLL, dll);
+        __UART(THR, thr);
+        __UART(RBR, rbr);
+        __UART(DLH, dlh);
+        __UART(IER, ier);
+        __UART(IIR, iir);
+        __UART(LCR, lcr);
+        __UART(MCR, mcr);
+        __UART(LSR, lsr);
+        __UART(MSR, msr);
+        __UART(SCR, scr);
+        __UART(GCTL, gctl);
+#endif
+}
+#define UART(num) bfin_debug_mmrs_uart(parent, UART##num##_DLL, num)
+
+/*
+ * The actual debugfs generation
+ */
+static struct dentry *debug_mmrs_dentry;
+
+static int __init bfin_debug_mmrs_init(void)
+{
+        struct dentry *top, *parent;
+
+        pr_info("debug-mmrs: setting up Blackfin MMR debugfs\n");
+
+        top = debugfs_create_dir("blackfin", NULL);
+        if (top == NULL)
+                return -1;
+
+        parent = debugfs_create_dir("core_regs", top);
+        debugfs_create_file("cclk", S_IRUSR, parent, NULL, &fops_debug_cclk);
+        debugfs_create_file("sclk", S_IRUSR, parent, NULL, &fops_debug_sclk);
+        debugfs_create_x32("last_seqstat", S_IRUSR, parent, &last_seqstat);
+        D_SYSREG(cycles);
+        D_SYSREG(cycles2);
+        D_SYSREG(emudat);
+        D_SYSREG(seqstat);
+        D_SYSREG(syscfg);
+
+        /* Core MMRs */
+        parent = debugfs_create_dir("ctimer", top);
+        D32(TCNTL);
+        D32(TCOUNT);
+        D32(TPERIOD);
+        D32(TSCALE);
+
+        parent = debugfs_create_dir("cec", top);
+        D32(EVT0);
+        D32(EVT1);
+        D32(EVT2);
+        D32(EVT3);
+        D32(EVT4);
+        D32(EVT5);
+        D32(EVT6);
+        D32(EVT7);
+        D32(EVT8);
+        D32(EVT9);
+        D32(EVT10);
+        D32(EVT11);
+        D32(EVT12);
+        D32(EVT13);
+        D32(EVT14);
+        D32(EVT15);
+        D32(EVT_OVERRIDE);
+        D32(IMASK);
+        D32(IPEND);
+        D32(ILAT);
+        D32(IPRIO);
+
+        parent = debugfs_create_dir("debug", top);
+        D32(DBGSTAT);
+        D32(DSPID);
+
+        parent = debugfs_create_dir("mmu", top);
+        D32(SRAM_BASE_ADDRESS);
+        D32(DCPLB_ADDR0);
+        D32(DCPLB_ADDR10);
+        D32(DCPLB_ADDR11);
+        D32(DCPLB_ADDR12);
+        D32(DCPLB_ADDR13);
+        D32(DCPLB_ADDR14);
+        D32(DCPLB_ADDR15);
+        D32(DCPLB_ADDR1);
+        D32(DCPLB_ADDR2);
+        D32(DCPLB_ADDR3);
+        D32(DCPLB_ADDR4);
+        D32(DCPLB_ADDR5);
+        D32(DCPLB_ADDR6);
+        D32(DCPLB_ADDR7);
+        D32(DCPLB_ADDR8);
+        D32(DCPLB_ADDR9);
+        D32(DCPLB_DATA0);
+        D32(DCPLB_DATA10);
+        D32(DCPLB_DATA11);
+        D32(DCPLB_DATA12);
+        D32(DCPLB_DATA13);
+        D32(DCPLB_DATA14);
+        D32(DCPLB_DATA15);
+        D32(DCPLB_DATA1);
+        D32(DCPLB_DATA2);
+        D32(DCPLB_DATA3);
+        D32(DCPLB_DATA4);
+        D32(DCPLB_DATA5);
+        D32(DCPLB_DATA6);
+        D32(DCPLB_DATA7);
+        D32(DCPLB_DATA8);
+        D32(DCPLB_DATA9);
+        D32(DCPLB_FAULT_ADDR);
+        D32(DCPLB_STATUS);
+        D32(DMEM_CONTROL);
+        D32(DTEST_COMMAND);
+        D32(DTEST_DATA0);
+        D32(DTEST_DATA1);
+
+        D32(ICPLB_ADDR0);
+        D32(ICPLB_ADDR1);
+        D32(ICPLB_ADDR2);
+        D32(ICPLB_ADDR3);
+        D32(ICPLB_ADDR4);
+        D32(ICPLB_ADDR5);
+        D32(ICPLB_ADDR6);
+        D32(ICPLB_ADDR7);
+        D32(ICPLB_ADDR8);
+        D32(ICPLB_ADDR9);
+        D32(ICPLB_ADDR10);
+        D32(ICPLB_ADDR11);
+        D32(ICPLB_ADDR12);
+        D32(ICPLB_ADDR13);
+        D32(ICPLB_ADDR14);
+        D32(ICPLB_ADDR15);
+        D32(ICPLB_DATA0);
+        D32(ICPLB_DATA1);
+        D32(ICPLB_DATA2);
+        D32(ICPLB_DATA3);
+        D32(ICPLB_DATA4);
+        D32(ICPLB_DATA5);
+        D32(ICPLB_DATA6);
+        D32(ICPLB_DATA7);
+        D32(ICPLB_DATA8);
+        D32(ICPLB_DATA9);
+        D32(ICPLB_DATA10);
+        D32(ICPLB_DATA11);
+        D32(ICPLB_DATA12);
+        D32(ICPLB_DATA13);
+        D32(ICPLB_DATA14);
+        D32(ICPLB_DATA15);
+        D32(ICPLB_FAULT_ADDR);
+        D32(ICPLB_STATUS);
+        D32(IMEM_CONTROL);
+        if (!ANOMALY_05000481) {
+                D32(ITEST_COMMAND);
+                D32(ITEST_DATA0);
+                D32(ITEST_DATA1);
+        }
+
+        parent = debugfs_create_dir("perf", top);
+        D32(PFCNTR0);
+        D32(PFCNTR1);
+        D32(PFCTL);
+
+        parent = debugfs_create_dir("trace", top);
+        D32(TBUF);
+        D32(TBUFCTL);
+        D32(TBUFSTAT);
+
+        parent = debugfs_create_dir("watchpoint", top);
+        D32(WPIACTL);
+        D32(WPIA0);
+        D32(WPIA1);
+        D32(WPIA2);
+        D32(WPIA3);
+        D32(WPIA4);
+        D32(WPIA5);
+        D32(WPIACNT0);
+        D32(WPIACNT1);
+        D32(WPIACNT2);
+        D32(WPIACNT3);
+        D32(WPIACNT4);
+        D32(WPIACNT5);
+        D32(WPDACTL);
+        D32(WPDA0);
+        D32(WPDA1);
+        D32(WPDACNT0);
+        D32(WPDACNT1);
+        D32(WPSTAT);
+
+        /* System MMRs */
+#ifdef ATAPI_CONTROL
+        parent = debugfs_create_dir("atapi", top);
+        D16(ATAPI_CONTROL);
+        D16(ATAPI_DEV_ADDR);
+        D16(ATAPI_DEV_RXBUF);
+        D16(ATAPI_DEV_TXBUF);
+        D16(ATAPI_DMA_TFRCNT);
+        D16(ATAPI_INT_MASK);
+        D16(ATAPI_INT_STATUS);
+        D16(ATAPI_LINE_STATUS);
+        D16(ATAPI_MULTI_TIM_0);
+        D16(ATAPI_MULTI_TIM_1);
+        D16(ATAPI_MULTI_TIM_2);
+        D16(ATAPI_PIO_TFRCNT);
+        D16(ATAPI_PIO_TIM_0);
+        D16(ATAPI_PIO_TIM_1);
+        D16(ATAPI_REG_TIM_0);
+        D16(ATAPI_SM_STATE);
+        D16(ATAPI_STATUS);
+        D16(ATAPI_TERMINATE);
+        D16(ATAPI_UDMAOUT_TFRCNT);
+        D16(ATAPI_ULTRA_TIM_0);
+        D16(ATAPI_ULTRA_TIM_1);
+        D16(ATAPI_ULTRA_TIM_2);
+        D16(ATAPI_ULTRA_TIM_3);
+        D16(ATAPI_UMAIN_TFRCNT);
+        D16(ATAPI_XFER_LEN);
+#endif
+
+#if defined(CAN_MC1) || defined(CAN0_MC1) || defined(CAN1_MC1)
+        parent = debugfs_create_dir("can", top);
+# ifdef CAN_MC1
+        bfin_debug_mmrs_can(parent, CAN_MC1, -1);
+# endif
+# ifdef CAN0_MC1
+        CAN(0);
+# endif
+# ifdef CAN1_MC1
+        CAN(1);
+# endif
+#endif
+
+#ifdef CNT_COMMAND
+        parent = debugfs_create_dir("counter", top);
+        D16(CNT_COMMAND);
+        D16(CNT_CONFIG);
+        D32(CNT_COUNTER);
+        D16(CNT_DEBOUNCE);
+        D16(CNT_IMASK);
+        D32(CNT_MAX);
+        D32(CNT_MIN);
+        D16(CNT_STATUS);
+#endif
+
+        parent = debugfs_create_dir("dmac", top);
+#ifdef DMA_TC_CNT
+        D16(DMAC_TC_CNT);
+        D16(DMAC_TC_PER);
+#endif
+#ifdef DMAC0_TC_CNT
+        D16(DMAC0_TC_CNT);
+        D16(DMAC0_TC_PER);
+#endif
+#ifdef DMAC1_TC_CNT
+        D16(DMAC1_TC_CNT);
+        D16(DMAC1_TC_PER);
+#endif
+#ifdef DMAC1_PERIMUX
+        D16(DMAC1_PERIMUX);
+#endif
+
+#ifdef __ADSPBF561__
+        /* XXX: should rewrite the MMR map */
+# define DMA0_NEXT_DESC_PTR DMA2_0_NEXT_DESC_PTR
+# define DMA1_NEXT_DESC_PTR DMA2_1_NEXT_DESC_PTR
+# define DMA2_NEXT_DESC_PTR DMA2_2_NEXT_DESC_PTR
+# define DMA3_NEXT_DESC_PTR DMA2_3_NEXT_DESC_PTR
+# define DMA4_NEXT_DESC_PTR DMA2_4_NEXT_DESC_PTR
+# define DMA5_NEXT_DESC_PTR DMA2_5_NEXT_DESC_PTR
+# define DMA6_NEXT_DESC_PTR DMA2_6_NEXT_DESC_PTR
+# define DMA7_NEXT_DESC_PTR DMA2_7_NEXT_DESC_PTR
+# define DMA8_NEXT_DESC_PTR DMA2_8_NEXT_DESC_PTR
+# define DMA9_NEXT_DESC_PTR DMA2_9_NEXT_DESC_PTR
+# define DMA10_NEXT_DESC_PTR DMA2_10_NEXT_DESC_PTR
+# define DMA11_NEXT_DESC_PTR DMA2_11_NEXT_DESC_PTR
+# define DMA12_NEXT_DESC_PTR DMA1_0_NEXT_DESC_PTR
+# define DMA13_NEXT_DESC_PTR DMA1_1_NEXT_DESC_PTR
+# define DMA14_NEXT_DESC_PTR DMA1_2_NEXT_DESC_PTR
+# define DMA15_NEXT_DESC_PTR DMA1_3_NEXT_DESC_PTR
+# define DMA16_NEXT_DESC_PTR DMA1_4_NEXT_DESC_PTR
+# define DMA17_NEXT_DESC_PTR DMA1_5_NEXT_DESC_PTR
+# define DMA18_NEXT_DESC_PTR DMA1_6_NEXT_DESC_PTR
+# define DMA19_NEXT_DESC_PTR DMA1_7_NEXT_DESC_PTR
+# define DMA20_NEXT_DESC_PTR DMA1_8_NEXT_DESC_PTR
+# define DMA21_NEXT_DESC_PTR DMA1_9_NEXT_DESC_PTR
+# define DMA22_NEXT_DESC_PTR DMA1_10_NEXT_DESC_PTR
+# define DMA23_NEXT_DESC_PTR DMA1_11_NEXT_DESC_PTR
+#endif
+        parent = debugfs_create_dir("dma", top);
+        DMA(0);
+        DMA(1);
+        DMA(1);
+        DMA(2);
+        DMA(3);
+        DMA(4);
+        DMA(5);
+        DMA(6);
+        DMA(7);
+#ifdef DMA8_NEXT_DESC_PTR
+        DMA(8);
+        DMA(9);
+        DMA(10);
+        DMA(11);
+#endif
+#ifdef DMA12_NEXT_DESC_PTR
+        DMA(12);
+        DMA(13);
+        DMA(14);
+        DMA(15);
+        DMA(16);
+        DMA(17);
+        DMA(18);
+        DMA(19);
+#endif
+#ifdef DMA20_NEXT_DESC_PTR
+        DMA(20);
+        DMA(21);
+        DMA(22);
+        DMA(23);
+#endif
+
+        parent = debugfs_create_dir("ebiu_amc", top);
+        D32(EBIU_AMBCTL0);
+        D32(EBIU_AMBCTL1);
+        D16(EBIU_AMGCTL);
+#ifdef EBIU_MBSCTL
+        D16(EBIU_MBSCTL);
+        D32(EBIU_ARBSTAT);
+        D32(EBIU_MODE);
+        D16(EBIU_FCTL);
+#endif
+
+#ifdef EBIU_SDGCTL
+        parent = debugfs_create_dir("ebiu_sdram", top);
+# ifdef __ADSPBF561__
+        D32(EBIU_SDBCTL);
+# else
+        D16(EBIU_SDBCTL);
+# endif
+        D32(EBIU_SDGCTL);
+        D16(EBIU_SDRRC);
+        D16(EBIU_SDSTAT);
+#endif
+
+#ifdef EBIU_DDRACCT
+        parent = debugfs_create_dir("ebiu_ddr", top);
+        D32(EBIU_DDRACCT);
+        D32(EBIU_DDRARCT);
+        D32(EBIU_DDRBRC0);
+        D32(EBIU_DDRBRC1);
+        D32(EBIU_DDRBRC2);
+        D32(EBIU_DDRBRC3);
+        D32(EBIU_DDRBRC4);
+        D32(EBIU_DDRBRC5);
+        D32(EBIU_DDRBRC6);
+        D32(EBIU_DDRBRC7);
+        D32(EBIU_DDRBWC0);
+        D32(EBIU_DDRBWC1);
+        D32(EBIU_DDRBWC2);
+        D32(EBIU_DDRBWC3);
+        D32(EBIU_DDRBWC4);
+        D32(EBIU_DDRBWC5);
+        D32(EBIU_DDRBWC6);
+        D32(EBIU_DDRBWC7);
+        D32(EBIU_DDRCTL0);
+        D32(EBIU_DDRCTL1);
+        D32(EBIU_DDRCTL2);
+        D32(EBIU_DDRCTL3);
+        D32(EBIU_DDRGC0);
+        D32(EBIU_DDRGC1);
+        D32(EBIU_DDRGC2);
+        D32(EBIU_DDRGC3);
+        D32(EBIU_DDRMCCL);
+        D32(EBIU_DDRMCEN);
+        D32(EBIU_DDRQUE);
+        D32(EBIU_DDRTACT);
+        D32(EBIU_ERRADD);
+        D16(EBIU_ERRMST);
+        D16(EBIU_RSTCTL);
+#endif
+
+#ifdef EMAC_ADDRHI
+        parent = debugfs_create_dir("emac", top);
+        D32(EMAC_ADDRHI);
+        D32(EMAC_ADDRLO);
+        D32(EMAC_FLC);
+        D32(EMAC_HASHHI);
+        D32(EMAC_HASHLO);
+        D32(EMAC_MMC_CTL);
+        D32(EMAC_MMC_RIRQE);
+        D32(EMAC_MMC_RIRQS);
+        D32(EMAC_MMC_TIRQE);
+        D32(EMAC_MMC_TIRQS);
+        D32(EMAC_OPMODE);
+        D32(EMAC_RXC_ALIGN);
+        D32(EMAC_RXC_ALLFRM);
+        D32(EMAC_RXC_ALLOCT);
+        D32(EMAC_RXC_BROAD);
+        D32(EMAC_RXC_DMAOVF);
+        D32(EMAC_RXC_EQ64);
+        D32(EMAC_RXC_FCS);
+        D32(EMAC_RXC_GE1024);
+        D32(EMAC_RXC_LNERRI);
+        D32(EMAC_RXC_LNERRO);
+        D32(EMAC_RXC_LONG);
+        D32(EMAC_RXC_LT1024);
+        D32(EMAC_RXC_LT128);
+        D32(EMAC_RXC_LT256);
+        D32(EMAC_RXC_LT512);
+        D32(EMAC_RXC_MACCTL);
+        D32(EMAC_RXC_MULTI);
+        D32(EMAC_RXC_OCTET);
+        D32(EMAC_RXC_OK);
+        D32(EMAC_RXC_OPCODE);
+        D32(EMAC_RXC_PAUSE);
+        D32(EMAC_RXC_SHORT);
+        D32(EMAC_RXC_TYPED);
+        D32(EMAC_RXC_UNICST);
+        D32(EMAC_RX_IRQE);
+        D32(EMAC_RX_STAT);
+        D32(EMAC_RX_STKY);
+        D32(EMAC_STAADD);
+        D32(EMAC_STADAT);
+        D32(EMAC_SYSCTL);
+        D32(EMAC_SYSTAT);
+        D32(EMAC_TXC_1COL);
+        D32(EMAC_TXC_ABORT);
+        D32(EMAC_TXC_ALLFRM);
+        D32(EMAC_TXC_ALLOCT);
+        D32(EMAC_TXC_BROAD);
+        D32(EMAC_TXC_CRSERR);
+        D32(EMAC_TXC_DEFER);
+        D32(EMAC_TXC_DMAUND);
+        D32(EMAC_TXC_EQ64);
+        D32(EMAC_TXC_GE1024);
+        D32(EMAC_TXC_GT1COL);
+        D32(EMAC_TXC_LATECL);
+        D32(EMAC_TXC_LT1024);
+        D32(EMAC_TXC_LT128);
+        D32(EMAC_TXC_LT256);
+        D32(EMAC_TXC_LT512);
+        D32(EMAC_TXC_MACCTL);
+        D32(EMAC_TXC_MULTI);
+        D32(EMAC_TXC_OCTET);
+        D32(EMAC_TXC_OK);
+        D32(EMAC_TXC_UNICST);
+        D32(EMAC_TXC_XS_COL);
+        D32(EMAC_TXC_XS_DFR);
+        D32(EMAC_TX_IRQE);
+        D32(EMAC_TX_STAT);
+        D32(EMAC_TX_STKY);
+        D32(EMAC_VLAN1);
+        D32(EMAC_VLAN2);
+        D32(EMAC_WKUP_CTL);
+        D32(EMAC_WKUP_FFCMD);
+        D32(EMAC_WKUP_FFCRC0);
+        D32(EMAC_WKUP_FFCRC1);
+        D32(EMAC_WKUP_FFMSK0);
+        D32(EMAC_WKUP_FFMSK1);
+        D32(EMAC_WKUP_FFMSK2);
+        D32(EMAC_WKUP_FFMSK3);
+        D32(EMAC_WKUP_FFOFF);
+# ifdef EMAC_PTP_ACCR
+        D32(EMAC_PTP_ACCR);
+        D32(EMAC_PTP_ADDEND);
+        D32(EMAC_PTP_ALARMHI);
+        D32(EMAC_PTP_ALARMLO);
+        D16(EMAC_PTP_CTL);
+        D32(EMAC_PTP_FOFF);
+        D32(EMAC_PTP_FV1);
+        D32(EMAC_PTP_FV2);
+        D32(EMAC_PTP_FV3);
+        D16(EMAC_PTP_ID_OFF);
+        D32(EMAC_PTP_ID_SNAP);
+        D16(EMAC_PTP_IE);
+        D16(EMAC_PTP_ISTAT);
+        D32(EMAC_PTP_OFFSET);
+        D32(EMAC_PTP_PPS_PERIOD);
+        D32(EMAC_PTP_PPS_STARTHI);
+        D32(EMAC_PTP_PPS_STARTLO);
+        D32(EMAC_PTP_RXSNAPHI);
+        D32(EMAC_PTP_RXSNAPLO);
+        D32(EMAC_PTP_TIMEHI);
+        D32(EMAC_PTP_TIMELO);
+        D32(EMAC_PTP_TXSNAPHI);
+        D32(EMAC_PTP_TXSNAPLO);
+# endif
+#endif
+
+#if defined(EPPI0_STATUS) || defined(EPPI1_STATUS) || defined(EPPI2_STATUS)
+        parent = debugfs_create_dir("eppi", top);
+# ifdef EPPI0_STATUS
+        EPPI(0);
+# endif
+# ifdef EPPI1_STATUS
+        EPPI(1);
+# endif
+# ifdef EPPI2_STATUS
+        EPPI(2);
+# endif
+#endif
+
+        parent = debugfs_create_dir("gptimer", top);
+#ifdef TIMER_DISABLE
+        D16(TIMER_DISABLE);
+        D16(TIMER_ENABLE);
+        D32(TIMER_STATUS);
+#endif
+#ifdef TIMER_DISABLE0
+        D16(TIMER_DISABLE0);
+        D16(TIMER_ENABLE0);
+        D32(TIMER_STATUS0);
+#endif
+#ifdef TIMER_DISABLE1
+        D16(TIMER_DISABLE1);
+        D16(TIMER_ENABLE1);
+        D32(TIMER_STATUS1);
+#endif
+        /* XXX: Should convert BF561 MMR names */
+#ifdef TMRS4_DISABLE
+        D16(TMRS4_DISABLE);
+        D16(TMRS4_ENABLE);
+        D32(TMRS4_STATUS);
+        D16(TMRS8_DISABLE);
+        D16(TMRS8_ENABLE);
+        D32(TMRS8_STATUS);
+#endif
+        GPTIMER(0);
+        GPTIMER(1);
+        GPTIMER(2);
+#ifdef TIMER3_CONFIG
+        GPTIMER(3);
+        GPTIMER(4);
+        GPTIMER(5);
+        GPTIMER(6);
+        GPTIMER(7);
+#endif
+#ifdef TIMER8_CONFIG
+        GPTIMER(8);
+        GPTIMER(9);
+        GPTIMER(10);
+#endif
+#ifdef TIMER11_CONFIG
+        GPTIMER(11);
+#endif
+
+#ifdef HMDMA0_CONTROL
+        parent = debugfs_create_dir("hmdma", top);
+        HMDMA(0);
+        HMDMA(1);
+#endif
+
+#ifdef HOST_CONTROL
+        parent = debugfs_create_dir("hostdp", top);
+        D16(HOST_CONTROL);
+        D16(HOST_STATUS);
+        D16(HOST_TIMEOUT);
+#endif
+
+#ifdef IMDMA_S0_CONFIG
+        parent = debugfs_create_dir("imdma", top);
+        IMDMA(0);
+        IMDMA(1);
+#endif
+
+#ifdef KPAD_CTL
+        parent = debugfs_create_dir("keypad", top);
+        D16(KPAD_CTL);
+        D16(KPAD_PRESCALE);
+        D16(KPAD_MSEL);
+        D16(KPAD_ROWCOL);
+        D16(KPAD_STAT);
+        D16(KPAD_SOFTEVAL);
+#endif
+
+        parent = debugfs_create_dir("mdma", top);
+        MDMA(0);
+        MDMA(1);
+#ifdef MDMA_D2_CONFIG
+        MDMA(2);
+        MDMA(3);
+#endif
+
+#ifdef MXVR_CONFIG
+        parent = debugfs_create_dir("mxvr", top);
+        D16(MXVR_CONFIG);
+# ifdef MXVR_PLL_CTL_0
+        D32(MXVR_PLL_CTL_0);
+# endif
+        D32(MXVR_STATE_0);
+        D32(MXVR_STATE_1);
+        D32(MXVR_INT_STAT_0);
+        D32(MXVR_INT_STAT_1);
+        D32(MXVR_INT_EN_0);
+        D32(MXVR_INT_EN_1);
+        D16(MXVR_POSITION);
+        D16(MXVR_MAX_POSITION);
+        D16(MXVR_DELAY);
+        D16(MXVR_MAX_DELAY);
+        D32(MXVR_LADDR);
+        D16(MXVR_GADDR);
+        D32(MXVR_AADDR);
+        D32(MXVR_ALLOC_0);
+        D32(MXVR_ALLOC_1);
+        D32(MXVR_ALLOC_2);
+        D32(MXVR_ALLOC_3);
+        D32(MXVR_ALLOC_4);
+        D32(MXVR_ALLOC_5);
+        D32(MXVR_ALLOC_6);
+        D32(MXVR_ALLOC_7);
+        D32(MXVR_ALLOC_8);
+        D32(MXVR_ALLOC_9);
+        D32(MXVR_ALLOC_10);
+        D32(MXVR_ALLOC_11);
+        D32(MXVR_ALLOC_12);
+        D32(MXVR_ALLOC_13);
+        D32(MXVR_ALLOC_14);
+        D32(MXVR_SYNC_LCHAN_0);
+        D32(MXVR_SYNC_LCHAN_1);
+        D32(MXVR_SYNC_LCHAN_2);
+        D32(MXVR_SYNC_LCHAN_3);
+        D32(MXVR_SYNC_LCHAN_4);
+        D32(MXVR_SYNC_LCHAN_5);
+        D32(MXVR_SYNC_LCHAN_6);
+        D32(MXVR_SYNC_LCHAN_7);
+        D32(MXVR_DMA0_CONFIG);
+        D32(MXVR_DMA0_START_ADDR);
+        D16(MXVR_DMA0_COUNT);
+        D32(MXVR_DMA0_CURR_ADDR);
+        D16(MXVR_DMA0_CURR_COUNT);
+        D32(MXVR_DMA1_CONFIG);
+        D32(MXVR_DMA1_START_ADDR);
+        D16(MXVR_DMA1_COUNT);
+        D32(MXVR_DMA1_CURR_ADDR);
+        D16(MXVR_DMA1_CURR_COUNT);
+        D32(MXVR_DMA2_CONFIG);
+        D32(MXVR_DMA2_START_ADDR);
+        D16(MXVR_DMA2_COUNT);
+        D32(MXVR_DMA2_CURR_ADDR);
+        D16(MXVR_DMA2_CURR_COUNT);
+        D32(MXVR_DMA3_CONFIG);
+        D32(MXVR_DMA3_START_ADDR);
+        D16(MXVR_DMA3_COUNT);
+        D32(MXVR_DMA3_CURR_ADDR);
+        D16(MXVR_DMA3_CURR_COUNT);
+        D32(MXVR_DMA4_CONFIG);
+        D32(MXVR_DMA4_START_ADDR);
+        D16(MXVR_DMA4_COUNT);
+        D32(MXVR_DMA4_CURR_ADDR);
+        D16(MXVR_DMA4_CURR_COUNT);
+        D32(MXVR_DMA5_CONFIG);
+        D32(MXVR_DMA5_START_ADDR);
+        D16(MXVR_DMA5_COUNT);
+        D32(MXVR_DMA5_CURR_ADDR);
+        D16(MXVR_DMA5_CURR_COUNT);
+        D32(MXVR_DMA6_CONFIG);
+        D32(MXVR_DMA6_START_ADDR);
+        D16(MXVR_DMA6_COUNT);
+        D32(MXVR_DMA6_CURR_ADDR);
+        D16(MXVR_DMA6_CURR_COUNT);
+        D32(MXVR_DMA7_CONFIG);
+        D32(MXVR_DMA7_START_ADDR);
+        D16(MXVR_DMA7_COUNT);
+        D32(MXVR_DMA7_CURR_ADDR);
+        D16(MXVR_DMA7_CURR_COUNT);
+        D16(MXVR_AP_CTL);
+        D32(MXVR_APRB_START_ADDR);
+        D32(MXVR_APRB_CURR_ADDR);
+        D32(MXVR_APTB_START_ADDR);
+        D32(MXVR_APTB_CURR_ADDR);
+        D32(MXVR_CM_CTL);
+        D32(MXVR_CMRB_START_ADDR);
+        D32(MXVR_CMRB_CURR_ADDR);
+        D32(MXVR_CMTB_START_ADDR);
+        D32(MXVR_CMTB_CURR_ADDR);
+        D32(MXVR_RRDB_START_ADDR);
+        D32(MXVR_RRDB_CURR_ADDR);
+        D32(MXVR_PAT_DATA_0);
+        D32(MXVR_PAT_EN_0);
+        D32(MXVR_PAT_DATA_1);
+        D32(MXVR_PAT_EN_1);
+        D16(MXVR_FRAME_CNT_0);
+        D16(MXVR_FRAME_CNT_1);
+        D32(MXVR_ROUTING_0);
+        D32(MXVR_ROUTING_1);
+        D32(MXVR_ROUTING_2);
+        D32(MXVR_ROUTING_3);
+        D32(MXVR_ROUTING_4);
+        D32(MXVR_ROUTING_5);
+        D32(MXVR_ROUTING_6);
+        D32(MXVR_ROUTING_7);
+        D32(MXVR_ROUTING_8);
+        D32(MXVR_ROUTING_9);
+        D32(MXVR_ROUTING_10);
+        D32(MXVR_ROUTING_11);
+        D32(MXVR_ROUTING_12);
+        D32(MXVR_ROUTING_13);
+        D32(MXVR_ROUTING_14);
+# ifdef MXVR_PLL_CTL_1
+        D32(MXVR_PLL_CTL_1);
+# endif
+        D16(MXVR_BLOCK_CNT);
+# ifdef MXVR_CLK_CTL
+        D32(MXVR_CLK_CTL);
+# endif
+# ifdef MXVR_CDRPLL_CTL
+        D32(MXVR_CDRPLL_CTL);
+# endif
+# ifdef MXVR_FMPLL_CTL
+        D32(MXVR_FMPLL_CTL);
+# endif
+# ifdef MXVR_PIN_CTL
+        D16(MXVR_PIN_CTL);
+# endif
+# ifdef MXVR_SCLK_CNT
+        D16(MXVR_SCLK_CNT);
+# endif
+#endif
+
+#ifdef NFC_ADDR
+        parent = debugfs_create_dir("nfc", top);
+        D_WO(NFC_ADDR, 16);
+        D_WO(NFC_CMD, 16);
+        D_RO(NFC_COUNT, 16);
+        D16(NFC_CTL);
+        D_WO(NFC_DATA_RD, 16);
+        D_WO(NFC_DATA_WR, 16);
+        D_RO(NFC_ECC0, 16);
+        D_RO(NFC_ECC1, 16);
+        D_RO(NFC_ECC2, 16);
+        D_RO(NFC_ECC3, 16);
+        D16(NFC_IRQMASK);
+        D16(NFC_IRQSTAT);
+        D_WO(NFC_PGCTL, 16);
+        D_RO(NFC_READ, 16);
+        D16(NFC_RST);
+        D_RO(NFC_STAT, 16);
+#endif
+
+#ifdef OTP_CONTROL
+        parent = debugfs_create_dir("otp", top);
+        D16(OTP_CONTROL);
+        D16(OTP_BEN);
+        D16(OTP_STATUS);
+        D32(OTP_TIMING);
+        D32(OTP_DATA0);
+        D32(OTP_DATA1);
+        D32(OTP_DATA2);
+        D32(OTP_DATA3);
+#endif
+
+#ifdef PIXC_CTL
+        parent = debugfs_create_dir("pixc", top);
+        D16(PIXC_CTL);
+        D16(PIXC_PPL);
+        D16(PIXC_LPF);
+        D16(PIXC_AHSTART);
+        D16(PIXC_AHEND);
+        D16(PIXC_AVSTART);
+        D16(PIXC_AVEND);
+        D16(PIXC_ATRANSP);
+        D16(PIXC_BHSTART);
+        D16(PIXC_BHEND);
+        D16(PIXC_BVSTART);
+        D16(PIXC_BVEND);
+        D16(PIXC_BTRANSP);
+        D16(PIXC_INTRSTAT);
+        D32(PIXC_RYCON);
+        D32(PIXC_GUCON);
+        D32(PIXC_BVCON);
+        D32(PIXC_CCBIAS);
+        D32(PIXC_TC);
+#endif
+
+        parent = debugfs_create_dir("pll", top);
+        D16(PLL_CTL);
+        D16(PLL_DIV);
+        D16(PLL_LOCKCNT);
+        D16(PLL_STAT);
+        D16(VR_CTL);
+        D32(CHIPID);    /* it's part of this hardware block */
+
+#if defined(PPI_STATUS) || defined(PPI0_STATUS) || defined(PPI1_STATUS)
+        parent = debugfs_create_dir("ppi", top);
+# ifdef PPI_STATUS
+        bfin_debug_mmrs_ppi(parent, PPI_STATUS, -1);
+# endif
+# ifdef PPI0_STATUS
+        PPI(0);
+# endif
+# ifdef PPI1_STATUS
+        PPI(1);
+# endif
+#endif
+
+#ifdef PWM_CTRL
+        parent = debugfs_create_dir("pwm", top);
+        D16(PWM_CTRL);
+        D16(PWM_STAT);
+        D16(PWM_TM);
+        D16(PWM_DT);
+        D16(PWM_GATE);
+        D16(PWM_CHA);
+        D16(PWM_CHB);
+        D16(PWM_CHC);
+        D16(PWM_SEG);
+        D16(PWM_SYNCWT);
+        D16(PWM_CHAL);
+        D16(PWM_CHBL);
+        D16(PWM_CHCL);
+        D16(PWM_LSI);
+        D16(PWM_STAT2);
+#endif
+
+#ifdef RSI_CONFIG
+        parent = debugfs_create_dir("rsi", top);
+        D32(RSI_ARGUMENT);
+        D16(RSI_CEATA_CONTROL);
+        D16(RSI_CLK_CONTROL);
+        D16(RSI_COMMAND);
+        D16(RSI_CONFIG);
+        D16(RSI_DATA_CNT);
+        D16(RSI_DATA_CONTROL);
+        D16(RSI_DATA_LGTH);
+        D32(RSI_DATA_TIMER);
+        D16(RSI_EMASK);
+        D16(RSI_ESTAT);
+        D32(RSI_FIFO);
+        D16(RSI_FIFO_CNT);
+        D32(RSI_MASK0);
+        D32(RSI_MASK1);
+        D16(RSI_PID0);
+        D16(RSI_PID1);
+        D16(RSI_PID2);
+        D16(RSI_PID3);
+        D16(RSI_PWR_CONTROL);
+        D16(RSI_RD_WAIT_EN);
+        D32(RSI_RESPONSE0);
+        D32(RSI_RESPONSE1);
+        D32(RSI_RESPONSE2);
+        D32(RSI_RESPONSE3);
+        D16(RSI_RESP_CMD);
+        D32(RSI_STATUS);
+        D_WO(RSI_STATUSCL, 16);
+#endif
+
+#ifdef RTC_ALARM
+        parent = debugfs_create_dir("rtc", top);
+        D32(RTC_ALARM);
+        D16(RTC_ICTL);
+        D16(RTC_ISTAT);
+        D16(RTC_PREN);
+        D32(RTC_STAT);
+        D16(RTC_SWCNT);
+#endif
+
+#ifdef SDH_CFG
+        parent = debugfs_create_dir("sdh", top);
+        D32(SDH_ARGUMENT);
+        D16(SDH_CFG);
+        D16(SDH_CLK_CTL);
+        D16(SDH_COMMAND);
+        D_RO(SDH_DATA_CNT, 16);
+        D16(SDH_DATA_CTL);
+        D16(SDH_DATA_LGTH);
+        D32(SDH_DATA_TIMER);
+        D16(SDH_E_MASK);
+        D16(SDH_E_STATUS);
+        D32(SDH_FIFO);
+        D_RO(SDH_FIFO_CNT, 16);
+        D32(SDH_MASK0);
+        D32(SDH_MASK1);
+        D_RO(SDH_PID0, 16);
+        D_RO(SDH_PID1, 16);
+        D_RO(SDH_PID2, 16);
+        D_RO(SDH_PID3, 16);
+        D_RO(SDH_PID4, 16);
+        D_RO(SDH_PID5, 16);
+        D_RO(SDH_PID6, 16);
+        D_RO(SDH_PID7, 16);
+        D16(SDH_PWR_CTL);
+        D16(SDH_RD_WAIT_EN);
+        D_RO(SDH_RESPONSE0, 32);
+        D_RO(SDH_RESPONSE1, 32);
+        D_RO(SDH_RESPONSE2, 32);
+        D_RO(SDH_RESPONSE3, 32);
+        D_RO(SDH_RESP_CMD, 16);
+        D_RO(SDH_STATUS, 32);
+        D_WO(SDH_STATUS_CLR, 16);
+#endif
+
+#ifdef SECURE_CONTROL
+        parent = debugfs_create_dir("security", top);
+        D16(SECURE_CONTROL);
+        D16(SECURE_STATUS);
+        D32(SECURE_SYSSWT);
+#endif
+
+        parent = debugfs_create_dir("sic", top);
+        D16(SWRST);
+        D16(SYSCR);
+        D16(SIC_RVECT);
+        D32(SIC_IAR0);
+        D32(SIC_IAR1);
+        D32(SIC_IAR2);
+#ifdef SIC_IAR3
+        D32(SIC_IAR3);
+#endif
+#ifdef SIC_IAR4
+        D32(SIC_IAR4);
+        D32(SIC_IAR5);
+        D32(SIC_IAR6);
+#endif
+#ifdef SIC_IAR7
+        D32(SIC_IAR7);
+#endif
+#ifdef SIC_IAR8
+        D32(SIC_IAR8);
+        D32(SIC_IAR9);
+        D32(SIC_IAR10);
+        D32(SIC_IAR11);
+#endif
+#ifdef SIC_IMASK
+        D32(SIC_IMASK);
+        D32(SIC_ISR);
+        D32(SIC_IWR);
+#endif
+#ifdef SIC_IMASK0
+        D32(SIC_IMASK0);
+        D32(SIC_IMASK1);
+        D32(SIC_ISR0);
+        D32(SIC_ISR1);
+        D32(SIC_IWR0);
+        D32(SIC_IWR1);
+#endif
+#ifdef SIC_IMASK2
+        D32(SIC_IMASK2);
+        D32(SIC_ISR2);
+        D32(SIC_IWR2);
+#endif
+#ifdef SICB_RVECT
+        D16(SICB_SWRST);
+        D16(SICB_SYSCR);
+        D16(SICB_RVECT);
+        D32(SICB_IAR0);
+        D32(SICB_IAR1);
+        D32(SICB_IAR2);
+        D32(SICB_IAR3);
+        D32(SICB_IAR4);
+        D32(SICB_IAR5);
+        D32(SICB_IAR6);
+        D32(SICB_IAR7);
+        D32(SICB_IMASK0);
+        D32(SICB_IMASK1);
+        D32(SICB_ISR0);
+        D32(SICB_ISR1);
+        D32(SICB_IWR0);
+        D32(SICB_IWR1);
+#endif
+
+        parent = debugfs_create_dir("spi", top);
+#ifdef SPI0_REGBASE
+        SPI(0);
+#endif
+#ifdef SPI1_REGBASE
+        SPI(1);
+#endif
+#ifdef SPI2_REGBASE
+        SPI(2);
+#endif
+
+        parent = debugfs_create_dir("sport", top);
+#ifdef SPORT0_STAT
+        SPORT(0);
+#endif
+#ifdef SPORT1_STAT
+        SPORT(1);
+#endif
+#ifdef SPORT2_STAT
+        SPORT(2);
+#endif
+#ifdef SPORT3_STAT
+        SPORT(3);
+#endif
+
+#if defined(TWI_CLKDIV) || defined(TWI0_CLKDIV) || defined(TWI1_CLKDIV)
+        parent = debugfs_create_dir("twi", top);
+# ifdef TWI_CLKDIV
+        bfin_debug_mmrs_twi(parent, TWI_CLKDIV, -1);
+# endif
+# ifdef TWI0_CLKDIV
+        TWI(0);
+# endif
+# ifdef TWI1_CLKDIV
+        TWI(1);
+# endif
+#endif
+
+        parent = debugfs_create_dir("uart", top);
+#ifdef BFIN_UART_DLL
+        bfin_debug_mmrs_uart(parent, BFIN_UART_DLL, -1);
+#endif
+#ifdef UART0_DLL
+        UART(0);
+#endif
+#ifdef UART1_DLL
+        UART(1);
+#endif
+#ifdef UART2_DLL
+        UART(2);
+#endif
+#ifdef UART3_DLL
+        UART(3);
+#endif
+
+#ifdef USB_FADDR
+        parent = debugfs_create_dir("usb", top);
+        D16(USB_FADDR);
+        D16(USB_POWER);
+        D16(USB_INTRTX);
+        D16(USB_INTRRX);
+        D16(USB_INTRTXE);
+        D16(USB_INTRRXE);
+        D16(USB_INTRUSB);
+        D16(USB_INTRUSBE);
+        D16(USB_FRAME);
+        D16(USB_INDEX);
+        D16(USB_TESTMODE);
+        D16(USB_GLOBINTR);
+        D16(USB_GLOBAL_CTL);
+        D16(USB_TX_MAX_PACKET);
+        D16(USB_CSR0);
+        D16(USB_TXCSR);
+        D16(USB_RX_MAX_PACKET);
+        D16(USB_RXCSR);
+        D16(USB_COUNT0);
+        D16(USB_RXCOUNT);
+        D16(USB_TXTYPE);
+        D16(USB_NAKLIMIT0);
+        D16(USB_TXINTERVAL);
+        D16(USB_RXTYPE);
+        D16(USB_RXINTERVAL);
+        D16(USB_TXCOUNT);
+        D16(USB_EP0_FIFO);
+        D16(USB_EP1_FIFO);
+        D16(USB_EP2_FIFO);
+        D16(USB_EP3_FIFO);
+        D16(USB_EP4_FIFO);
+        D16(USB_EP5_FIFO);
+        D16(USB_EP6_FIFO);
+        D16(USB_EP7_FIFO);
+        D16(USB_OTG_DEV_CTL);
+        D16(USB_OTG_VBUS_IRQ);
+        D16(USB_OTG_VBUS_MASK);
+        D16(USB_LINKINFO);
+        D16(USB_VPLEN);
+        D16(USB_HS_EOF1);
+        D16(USB_FS_EOF1);
+        D16(USB_LS_EOF1);
+        D16(USB_APHY_CNTRL);
+        D16(USB_APHY_CALIB);
+        D16(USB_APHY_CNTRL2);
+        D16(USB_PHY_TEST);
+        D16(USB_PLLOSC_CTRL);
+        D16(USB_SRP_CLKDIV);
+        D16(USB_EP_NI0_TXMAXP);
+        D16(USB_EP_NI0_TXCSR);
+        D16(USB_EP_NI0_RXMAXP);
+        D16(USB_EP_NI0_RXCSR);
+        D16(USB_EP_NI0_RXCOUNT);
+        D16(USB_EP_NI0_TXTYPE);
+        D16(USB_EP_NI0_TXINTERVAL);
+        D16(USB_EP_NI0_RXTYPE);
+        D16(USB_EP_NI0_RXINTERVAL);
+        D16(USB_EP_NI0_TXCOUNT);
+        D16(USB_EP_NI1_TXMAXP);
+        D16(USB_EP_NI1_TXCSR);
+        D16(USB_EP_NI1_RXMAXP);
+        D16(USB_EP_NI1_RXCSR);
+        D16(USB_EP_NI1_RXCOUNT);
+        D16(USB_EP_NI1_TXTYPE);
+        D16(USB_EP_NI1_TXINTERVAL);
+        D16(USB_EP_NI1_RXTYPE);
+        D16(USB_EP_NI1_RXINTERVAL);
+        D16(USB_EP_NI1_TXCOUNT);
+        D16(USB_EP_NI2_TXMAXP);
+        D16(USB_EP_NI2_TXCSR);
+        D16(USB_EP_NI2_RXMAXP);
+        D16(USB_EP_NI2_RXCSR);
+        D16(USB_EP_NI2_RXCOUNT);
+        D16(USB_EP_NI2_TXTYPE);
+        D16(USB_EP_NI2_TXINTERVAL);
+        D16(USB_EP_NI2_RXTYPE);
+        D16(USB_EP_NI2_RXINTERVAL);
+        D16(USB_EP_NI2_TXCOUNT);
+        D16(USB_EP_NI3_TXMAXP);
+        D16(USB_EP_NI3_TXCSR);
+        D16(USB_EP_NI3_RXMAXP);
+        D16(USB_EP_NI3_RXCSR);
+        D16(USB_EP_NI3_RXCOUNT);
+        D16(USB_EP_NI3_TXTYPE);
+        D16(USB_EP_NI3_TXINTERVAL);
+        D16(USB_EP_NI3_RXTYPE);
+        D16(USB_EP_NI3_RXINTERVAL);
+        D16(USB_EP_NI3_TXCOUNT);
+        D16(USB_EP_NI4_TXMAXP);
+        D16(USB_EP_NI4_TXCSR);
+        D16(USB_EP_NI4_RXMAXP);
+        D16(USB_EP_NI4_RXCSR);
+        D16(USB_EP_NI4_RXCOUNT);
+        D16(USB_EP_NI4_TXTYPE);
+        D16(USB_EP_NI4_TXINTERVAL);
+        D16(USB_EP_NI4_RXTYPE);
+        D16(USB_EP_NI4_RXINTERVAL);
+        D16(USB_EP_NI4_TXCOUNT);
+        D16(USB_EP_NI5_TXMAXP);
+        D16(USB_EP_NI5_TXCSR);
+        D16(USB_EP_NI5_RXMAXP);
+        D16(USB_EP_NI5_RXCSR);
+        D16(USB_EP_NI5_RXCOUNT);
+        D16(USB_EP_NI5_TXTYPE);
+        D16(USB_EP_NI5_TXINTERVAL);
+        D16(USB_EP_NI5_RXTYPE);
+        D16(USB_EP_NI5_RXINTERVAL);
+        D16(USB_EP_NI5_TXCOUNT);
+        D16(USB_EP_NI6_TXMAXP);
+        D16(USB_EP_NI6_TXCSR);
+        D16(USB_EP_NI6_RXMAXP);
+        D16(USB_EP_NI6_RXCSR);
+        D16(USB_EP_NI6_RXCOUNT);
+        D16(USB_EP_NI6_TXTYPE);
+        D16(USB_EP_NI6_TXINTERVAL);
+        D16(USB_EP_NI6_RXTYPE);
+        D16(USB_EP_NI6_RXINTERVAL);
+        D16(USB_EP_NI6_TXCOUNT);
+        D16(USB_EP_NI7_TXMAXP);
+        D16(USB_EP_NI7_TXCSR);
+        D16(USB_EP_NI7_RXMAXP);
+        D16(USB_EP_NI7_RXCSR);
+        D16(USB_EP_NI7_RXCOUNT);
+        D16(USB_EP_NI7_TXTYPE);
+        D16(USB_EP_NI7_TXINTERVAL);
+        D16(USB_EP_NI7_RXTYPE);
+        D16(USB_EP_NI7_RXINTERVAL);
+        D16(USB_EP_NI7_TXCOUNT);
+        D16(USB_DMA_INTERRUPT);
+        D16(USB_DMA0CONTROL);
+        D16(USB_DMA0ADDRLOW);
+        D16(USB_DMA0ADDRHIGH);
+        D16(USB_DMA0COUNTLOW);
+        D16(USB_DMA0COUNTHIGH);
+        D16(USB_DMA1CONTROL);
+        D16(USB_DMA1ADDRLOW);
+        D16(USB_DMA1ADDRHIGH);
+        D16(USB_DMA1COUNTLOW);
+        D16(USB_DMA1COUNTHIGH);
+        D16(USB_DMA2CONTROL);
+        D16(USB_DMA2ADDRLOW);
+        D16(USB_DMA2ADDRHIGH);
+        D16(USB_DMA2COUNTLOW);
+        D16(USB_DMA2COUNTHIGH);
+        D16(USB_DMA3CONTROL);
+        D16(USB_DMA3ADDRLOW);
+        D16(USB_DMA3ADDRHIGH);
+        D16(USB_DMA3COUNTLOW);
+        D16(USB_DMA3COUNTHIGH);
+        D16(USB_DMA4CONTROL);
+        D16(USB_DMA4ADDRLOW);
+        D16(USB_DMA4ADDRHIGH);
+        D16(USB_DMA4COUNTLOW);
+        D16(USB_DMA4COUNTHIGH);
+        D16(USB_DMA5CONTROL);
+        D16(USB_DMA5ADDRLOW);
+        D16(USB_DMA5ADDRHIGH);
+        D16(USB_DMA5COUNTLOW);
+        D16(USB_DMA5COUNTHIGH);
+        D16(USB_DMA6CONTROL);
+        D16(USB_DMA6ADDRLOW);
+        D16(USB_DMA6ADDRHIGH);
+        D16(USB_DMA6COUNTLOW);
+        D16(USB_DMA6COUNTHIGH);
+        D16(USB_DMA7CONTROL);
+        D16(USB_DMA7ADDRLOW);
+        D16(USB_DMA7ADDRHIGH);
+        D16(USB_DMA7COUNTLOW);
+        D16(USB_DMA7COUNTHIGH);
+#endif
+
+#ifdef WDOG_CNT
+        parent = debugfs_create_dir("watchdog", top);
+        D32(WDOG_CNT);
+        D16(WDOG_CTL);
+        D32(WDOG_STAT);
+#endif
+#ifdef WDOGA_CNT
+        parent = debugfs_create_dir("watchdog", top);
+        D32(WDOGA_CNT);
+        D16(WDOGA_CTL);
+        D32(WDOGA_STAT);
+        D32(WDOGB_CNT);
+        D16(WDOGB_CTL);
+        D32(WDOGB_STAT);
+#endif
+
+        /* BF533 glue */
+#ifdef FIO_FLAG_D
+#define PORTFIO FIO_FLAG_D
+#endif
+        /* BF561 glue */
+#ifdef FIO0_FLAG_D
+#define PORTFIO FIO0_FLAG_D
+#endif
+#ifdef FIO1_FLAG_D
+#define PORTGIO FIO1_FLAG_D
+#endif
+#ifdef FIO2_FLAG_D
+#define PORTHIO FIO2_FLAG_D
+#endif
+        parent = debugfs_create_dir("port", top);
+#ifdef PORTFIO
+        PORT(PORTFIO, 'F');
+#endif
+#ifdef PORTGIO
+        PORT(PORTGIO, 'G');
+#endif
+#ifdef PORTHIO
+        PORT(PORTHIO, 'H');
+#endif
+
+#ifdef __ADSPBF51x__
+        D16(PORTF_FER);
+        D16(PORTF_DRIVE);
+        D16(PORTF_HYSTERESIS);
+        D16(PORTF_MUX);
+
+        D16(PORTG_FER);
+        D16(PORTG_DRIVE);
+        D16(PORTG_HYSTERESIS);
+        D16(PORTG_MUX);
+
+        D16(PORTH_FER);
+        D16(PORTH_DRIVE);
+        D16(PORTH_HYSTERESIS);
+        D16(PORTH_MUX);
+
+        D16(MISCPORT_DRIVE);
+        D16(MISCPORT_HYSTERESIS);
+#endif  /* BF51x */
+
+#ifdef __ADSPBF52x__
+        D16(PORTF_FER);
+        D16(PORTF_DRIVE);
+        D16(PORTF_HYSTERESIS);
+        D16(PORTF_MUX);
+        D16(PORTF_SLEW);
+
+        D16(PORTG_FER);
+        D16(PORTG_DRIVE);
+        D16(PORTG_HYSTERESIS);
+        D16(PORTG_MUX);
+        D16(PORTG_SLEW);
+
+        D16(PORTH_FER);
+        D16(PORTH_DRIVE);
+        D16(PORTH_HYSTERESIS);
+        D16(PORTH_MUX);
+        D16(PORTH_SLEW);
+
+        D16(MISCPORT_DRIVE);
+        D16(MISCPORT_HYSTERESIS);
+        D16(MISCPORT_SLEW);
+#endif  /* BF52x */
+
+#ifdef BF537_FAMILY
+        D16(PORTF_FER);
+        D16(PORTG_FER);
+        D16(PORTH_FER);
+        D16(PORT_MUX);
+#endif  /* BF534 BF536 BF537 */
+
+#ifdef BF538_FAMILY
+        D16(PORTCIO_FER);
+        D16(PORTCIO);
+        D16(PORTCIO_CLEAR);
+        D16(PORTCIO_SET);
+        D16(PORTCIO_TOGGLE);
+        D16(PORTCIO_DIR);
+        D16(PORTCIO_INEN);
+
+        D16(PORTDIO);
+        D16(PORTDIO_CLEAR);
+        D16(PORTDIO_DIR);
+        D16(PORTDIO_FER);
+        D16(PORTDIO_INEN);
+        D16(PORTDIO_SET);
+        D16(PORTDIO_TOGGLE);
+
+        D16(PORTEIO);
+        D16(PORTEIO_CLEAR);
+        D16(PORTEIO_DIR);
+        D16(PORTEIO_FER);
+        D16(PORTEIO_INEN);
+        D16(PORTEIO_SET);
+        D16(PORTEIO_TOGGLE);
+#endif  /* BF538 BF539 */
+
+#ifdef __ADSPBF54x__
+        {
+                int num;
+                unsigned long base;
+                char *_buf, buf[32];
+
+                base = PORTA_FER;
+                for (num = 0; num < 10; ++num) {
+                        PORT(base, num);
+                        base += sizeof(struct bfin_gpio_regs);
+                }
+
+#define __PINT(uname, lname) __REGS(pint, #uname, lname)
+                parent = debugfs_create_dir("pint", top);
+                base = PINT0_MASK_SET;
+                for (num = 0; num < 4; ++num) {
+                        _buf = REGS_STR_PFX(buf, PINT, num);
+                        __PINT(MASK_SET, mask_set);
+                        __PINT(MASK_CLEAR, mask_clear);
+                        __PINT(IRQ, irq);
+                        __PINT(ASSIGN, assign);
+                        __PINT(EDGE_SET, edge_set);
+                        __PINT(EDGE_CLEAR, edge_clear);
+                        __PINT(INVERT_SET, invert_set);
+                        __PINT(INVERT_CLEAR, invert_clear);
+                        __PINT(PINSTATE, pinstate);
+                        __PINT(LATCH, latch);
+                        base += sizeof(struct bfin_pint_regs);
+                }
+
+        }
+#endif  /* BF54x */
+
+        debug_mmrs_dentry = top;
+
+        return 0;
+}
+module_init(bfin_debug_mmrs_init);
+
+static void __exit bfin_debug_mmrs_exit(void)
+{
+        debugfs_remove_recursive(debug_mmrs_dentry);
+}
+module_exit(bfin_debug_mmrs_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/arch/blackfin/kernel/ipipe.c b/arch/blackfin/kernel/ipipe.c
index f37019c847c9..486426f8a0d7 100644
--- a/arch/blackfin/kernel/ipipe.c
+++ b/arch/blackfin/kernel/ipipe.c
@@ -33,6 +33,7 @@
 #include <linux/io.h>
 #include <asm/system.h>
 #include <asm/atomic.h>
+#include <asm/irq_handler.h>
 
 DEFINE_PER_CPU(struct pt_regs, __ipipe_tick_regs);
 
diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c
index 1696d34f51c2..ff3d747154ac 100644
--- a/arch/blackfin/kernel/irqchip.c
+++ b/arch/blackfin/kernel/irqchip.c
@@ -11,6 +11,7 @@
 #include <linux/kallsyms.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <asm/irq_handler.h>
 #include <asm/trace.h>
 #include <asm/pda.h>
 
diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c
index 401eb1d8e3b4..679d0db35256 100644
--- a/arch/blackfin/kernel/nmi.c
+++ b/arch/blackfin/kernel/nmi.c
@@ -145,16 +145,16 @@ int check_nmi_wdt_touched(void)
 {
         unsigned int this_cpu = smp_processor_id();
         unsigned int cpu;
+        cpumask_t mask;
 
-        cpumask_t mask = cpu_online_map;
-
+        cpumask_copy(&mask, cpu_online_mask);
         if (!atomic_read(&nmi_touched[this_cpu]))
                 return 0;
 
         atomic_set(&nmi_touched[this_cpu], 0);
 
-        cpu_clear(this_cpu, mask);
-        for_each_cpu_mask(cpu, mask) {
+        cpumask_clear_cpu(this_cpu, &mask);
+        for_each_cpu(cpu, &mask) {
                 invalidate_dcache_range((unsigned long)(&nmi_touched[cpu]),
                                 (unsigned long)(&nmi_touched[cpu]));
                 if (!atomic_read(&nmi_touched[cpu]))
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
new file mode 100644
index 000000000000..04300f29c0e7
--- /dev/null
+++ b/arch/blackfin/kernel/perf_event.c
@@ -0,0 +1,498 @@
+/*
+ * Blackfin performance counters
+ *
+ * Copyright 2011 Analog Devices Inc.
+ *
+ * Ripped from SuperH version:
+ *
+ *  Copyright (C) 2009  Paul Mundt
+ *
+ * Heavily based on the x86 and PowerPC implementations.
+ *
+ * x86:
+ *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2009 Jaswinder Singh Rajput
+ *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
+ *
+ * ppc:
+ *  Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/perf_event.h>
+#include <asm/bfin_pfmon.h>
+
+/*
+ * We have two counters, and each counter can support an event type.
+ * The 'o' is PFCNTx=1 and 's' is PFCNTx=0
+ *
+ * 0x04 o pc invariant branches
+ * 0x06 o mispredicted branches
+ * 0x09 o predicted branches taken
+ * 0x0B o EXCPT insn
+ * 0x0C o CSYNC/SSYNC insn
+ * 0x0D o Insns committed
+ * 0x0E o Interrupts taken
+ * 0x0F o Misaligned address exceptions
+ * 0x80 o Code memory fetches stalled due to DMA
+ * 0x83 o 64bit insn fetches delivered
+ * 0x9A o data cache fills (bank a)
+ * 0x9B o data cache fills (bank b)
+ * 0x9C o data cache lines evicted (bank a)
+ * 0x9D o data cache lines evicted (bank b)
+ * 0x9E o data cache high priority fills
+ * 0x9F o data cache low priority fills
+ * 0x00 s loop 0 iterations
+ * 0x01 s loop 1 iterations
+ * 0x0A s CSYNC/SSYNC stalls
+ * 0x10 s DAG read/after write hazards
+ * 0x13 s RAW data hazards
+ * 0x81 s code TAG stalls
+ * 0x82 s code fill stalls
+ * 0x90 s processor to memory stalls
+ * 0x91 s data memory stalls not hidden by 0x90
+ * 0x92 s data store buffer full stalls
+ * 0x93 s data memory write buffer full stalls due to high->low priority
+ * 0x95 s data memory fill buffer stalls
+ * 0x96 s data TAG collision stalls
+ * 0x97 s data collision stalls
+ * 0x98 s data stalls
+ * 0x99 s data stalls sent to processor
+ */
+
+static const int event_map[] = {
+        /* use CYCLES cpu register */
+        [PERF_COUNT_HW_CPU_CYCLES]          = -1,
+        [PERF_COUNT_HW_INSTRUCTIONS]        = 0x0D,
+        [PERF_COUNT_HW_CACHE_REFERENCES]    = -1,
+        [PERF_COUNT_HW_CACHE_MISSES]        = 0x83,
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x09,
+        [PERF_COUNT_HW_BRANCH_MISSES]       = 0x06,
+        [PERF_COUNT_HW_BUS_CYCLES]          = -1,
+};
+
+#define C(x)    PERF_COUNT_HW_CACHE_##x
+
+static const int cache_events[PERF_COUNT_HW_CACHE_MAX]
+                             [PERF_COUNT_HW_CACHE_OP_MAX]
+                             [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+        [C(L1D)] = {    /* Data bank A */
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = 0,
+                        [C(RESULT_MISS)  ] = 0x9A,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = 0,
+                        [C(RESULT_MISS)  ] = 0,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = 0,
+                        [C(RESULT_MISS)  ] = 0,
+                },
+        },
+
+        [C(L1I)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = 0,
+                        [C(RESULT_MISS)  ] = 0x83,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = 0,
+                        [C(RESULT_MISS)  ] = 0,
+                },
+        },
+
+        [C(LL)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+        },
+
+        [C(DTLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+        },
+
+        [C(ITLB)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+        },
+
+        [C(BPU)] = {
+                [C(OP_READ)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_WRITE)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+                [C(OP_PREFETCH)] = {
+                        [C(RESULT_ACCESS)] = -1,
+                        [C(RESULT_MISS)  ] = -1,
+                },
+        },
+};
+
+const char *perf_pmu_name(void)
+{
+        return "bfin";
+}
+EXPORT_SYMBOL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+        return ARRAY_SIZE(event_map);
+}
+EXPORT_SYMBOL(perf_num_counters);
+
+static u64 bfin_pfmon_read(int idx)
+{
+        return bfin_read32(PFCNTR0 + (idx * 4));
+}
+
+static void bfin_pfmon_disable(struct hw_perf_event *hwc, int idx)
+{
+        bfin_write_PFCTL(bfin_read_PFCTL() & ~PFCEN(idx, PFCEN_MASK));
+}
+
+static void bfin_pfmon_enable(struct hw_perf_event *hwc, int idx)
+{
+        u32 val, mask;
+
+        val = PFPWR;
+        if (idx) {
+                mask = ~(PFCNT1 | PFMON1 | PFCEN1 | PEMUSW1);
+                /* The packed config is for event0, so shift it to event1 slots */
+                val |= (hwc->config << (PFMON1_P - PFMON0_P));
+                val |= (hwc->config & PFCNT0) << (PFCNT1_P - PFCNT0_P);
+                bfin_write_PFCNTR1(0);
+        } else {
+                mask = ~(PFCNT0 | PFMON0 | PFCEN0 | PEMUSW0);
+                val |= hwc->config;
+                bfin_write_PFCNTR0(0);
+        }
+
+        bfin_write_PFCTL((bfin_read_PFCTL() & mask) | val);
+}
+
+static void bfin_pfmon_disable_all(void)
+{
+        bfin_write_PFCTL(bfin_read_PFCTL() & ~PFPWR);
+}
+
+static void bfin_pfmon_enable_all(void)
+{
+        bfin_write_PFCTL(bfin_read_PFCTL() | PFPWR);
+}
+
+struct cpu_hw_events {
+        struct perf_event *events[MAX_HWEVENTS];
+        unsigned long used_mask[BITS_TO_LONGS(MAX_HWEVENTS)];
+};
+DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+
+static int hw_perf_cache_event(int config, int *evp)
+{
+        unsigned long type, op, result;
+        int ev;
+
+        /* unpack config */
+        type = config & 0xff;
+        op = (config >> 8) & 0xff;
+        result = (config >> 16) & 0xff;
+
+        if (type >= PERF_COUNT_HW_CACHE_MAX ||
+            op >= PERF_COUNT_HW_CACHE_OP_MAX ||
+            result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+                return -EINVAL;
+
+        ev = cache_events[type][op][result];
+        if (ev == 0)
+                return -EOPNOTSUPP;
+        if (ev == -1)
+                return -EINVAL;
+        *evp = ev;
+        return 0;
+}
+
+static void bfin_perf_event_update(struct perf_event *event,
+                                   struct hw_perf_event *hwc, int idx)
+{
+        u64 prev_raw_count, new_raw_count;
+        s64 delta;
+        int shift = 0;
+
+        /*
+         * Depending on the counter configuration, they may or may not
+         * be chained, in which case the previous counter value can be
+         * updated underneath us if the lower-half overflows.
+         *
+         * Our tactic to handle this is to first atomically read and
+         * exchange a new raw count - then add that new-prev delta
+         * count to the generic counter atomically.
+         *
+         * As there is no interrupt associated with the overflow events,
+         * this is the simplest approach for maintaining consistency.
+         */
+again:
+        prev_raw_count = local64_read(&hwc->prev_count);
+        new_raw_count = bfin_pfmon_read(idx);
+
+        if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+                             new_raw_count) != prev_raw_count)
+                goto again;
+
+        /*
+         * Now we have the new raw value and have updated the prev
+         * timestamp already. We can now calculate the elapsed delta
+         * (counter-)time and add that to the generic counter.
+         *
+         * Careful, not all hw sign-extends above the physical width
+         * of the count.
+         */
+        delta = (new_raw_count << shift) - (prev_raw_count << shift);
+        delta >>= shift;
+
+        local64_add(delta, &event->count);
+}
+
+static void bfin_pmu_stop(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        struct hw_perf_event *hwc = &event->hw;
+        int idx = hwc->idx;
+
+        if (!(event->hw.state & PERF_HES_STOPPED)) {
+                bfin_pfmon_disable(hwc, idx);
+                cpuc->events[idx] = NULL;
+                event->hw.state |= PERF_HES_STOPPED;
+        }
+
+        if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+                bfin_perf_event_update(event, &event->hw, idx);
+                event->hw.state |= PERF_HES_UPTODATE;
+        }
+}
+
+static void bfin_pmu_start(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        struct hw_perf_event *hwc = &event->hw;
+        int idx = hwc->idx;
+
+        if (WARN_ON_ONCE(idx == -1))
+                return;
+
+        if (flags & PERF_EF_RELOAD)
+                WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+        cpuc->events[idx] = event;
+        event->hw.state = 0;
+        bfin_pfmon_enable(hwc, idx);
+}
+
+static void bfin_pmu_del(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+        bfin_pmu_stop(event, PERF_EF_UPDATE);
+        __clear_bit(event->hw.idx, cpuc->used_mask);
+
+        perf_event_update_userpage(event);
+}
+
+static int bfin_pmu_add(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        struct hw_perf_event *hwc = &event->hw;
+        int idx = hwc->idx;
+        int ret = -EAGAIN;
+
+        perf_pmu_disable(event->pmu);
+
+        if (__test_and_set_bit(idx, cpuc->used_mask)) {
+                idx = find_first_zero_bit(cpuc->used_mask, MAX_HWEVENTS);
+                if (idx == MAX_HWEVENTS)
+                        goto out;
+
+                __set_bit(idx, cpuc->used_mask);
+                hwc->idx = idx;
+        }
+
+        bfin_pfmon_disable(hwc, idx);
+
+        event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+        if (flags & PERF_EF_START)
+                bfin_pmu_start(event, PERF_EF_RELOAD);
+
+        perf_event_update_userpage(event);
+        ret = 0;
+out:
+        perf_pmu_enable(event->pmu);
+        return ret;
+}
+
+static void bfin_pmu_read(struct perf_event *event)
+{
+        bfin_perf_event_update(event, &event->hw, event->hw.idx);
+}
+
+static int bfin_pmu_event_init(struct perf_event *event)
+{
+        struct perf_event_attr *attr = &event->attr;
+        struct hw_perf_event *hwc = &event->hw;
+        int config = -1;
+        int ret;
+
+        if (attr->exclude_hv || attr->exclude_idle)
+                return -EPERM;
+
+        /*
+         * All of the on-chip counters are "limited", in that they have
+         * no interrupts, and are therefore unable to do sampling without
+         * further work and timer assistance.
+         */
+        if (hwc->sample_period)
+                return -EINVAL;
+
+        ret = 0;
+        switch (attr->type) {
+        case PERF_TYPE_RAW:
+                config = PFMON(0, attr->config & PFMON_MASK) |
+                        PFCNT(0, !(attr->config & 0x100));
+                break;
+        case PERF_TYPE_HW_CACHE:
+                ret = hw_perf_cache_event(attr->config, &config);
+                break;
+        case PERF_TYPE_HARDWARE:
+                if (attr->config >= ARRAY_SIZE(event_map))
+                        return -EINVAL;
+
+                config = event_map[attr->config];
+                break;
+        }
+
+        if (config == -1)
+                return -EINVAL;
+
+        if (!attr->exclude_kernel)
+                config |= PFCEN(0, PFCEN_ENABLE_SUPV);
+        if (!attr->exclude_user)
+                config |= PFCEN(0, PFCEN_ENABLE_USER);
+
+        hwc->config |= config;
+
+        return ret;
+}
+
+static void bfin_pmu_enable(struct pmu *pmu)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        struct perf_event *event;
+        struct hw_perf_event *hwc;
+        int i;
+
+        for (i = 0; i < MAX_HWEVENTS; ++i) {
+                event = cpuc->events[i];
+                if (!event)
+                        continue;
+                hwc = &event->hw;
+                bfin_pfmon_enable(hwc, hwc->idx);
+        }
+
+        bfin_pfmon_enable_all();
+}
+
+static void bfin_pmu_disable(struct pmu *pmu)
+{
+        bfin_pfmon_disable_all();
+}
+
+static struct pmu pmu = {
+        .pmu_enable  = bfin_pmu_enable,
+        .pmu_disable = bfin_pmu_disable,
+        .event_init  = bfin_pmu_event_init,
+        .add         = bfin_pmu_add,
+        .del         = bfin_pmu_del,
+        .start       = bfin_pmu_start,
+        .stop        = bfin_pmu_stop,
+        .read        = bfin_pmu_read,
+};
+
+static void bfin_pmu_setup(int cpu)
+{
+        struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
+
+        memset(cpuhw, 0, sizeof(struct cpu_hw_events));
+}
+
+static int __cpuinit
+bfin_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+        unsigned int cpu = (long)hcpu;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
+        case CPU_UP_PREPARE:
+                bfin_write_PFCTL(0);
+                bfin_pmu_setup(cpu);
+                break;
+
+        default:
+                break;
+        }
+
+        return NOTIFY_OK;
+}
+
+static int __init bfin_pmu_init(void)
+{
+        int ret;
+
+        ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+        if (!ret)
+                perf_cpu_notifier(bfin_pmu_notifier);
+
+        return ret;
+}
+early_initcall(bfin_pmu_init);
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index b407bc8ad918..6a660fa921b5 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -171,10 +171,8 @@ asmlinkage int bfin_clone(struct pt_regs *regs)
         unsigned long newsp;
 
 #ifdef __ARCH_SYNC_CORE_DCACHE
-        if (current->rt.nr_cpus_allowed == num_possible_cpus()) {
-                current->cpus_allowed = cpumask_of_cpu(smp_processor_id());
-                current->rt.nr_cpus_allowed = 1;
-        }
+        if (current->rt.nr_cpus_allowed == num_possible_cpus())
+                set_cpus_allowed_ptr(current, cpumask_of(smp_processor_id()));
 #endif
 
         /* syscall2 puts clone_flags in r0 and usp in r1 */
diff --git a/arch/blackfin/kernel/reboot.c b/arch/blackfin/kernel/reboot.c
index 53d08dee8531..488bdc51aaa5 100644
--- a/arch/blackfin/kernel/reboot.c
+++ b/arch/blackfin/kernel/reboot.c
@@ -23,6 +23,9 @@
 __attribute__ ((__l1_text__, __noreturn__))
 static void bfin_reset(void)
 {
+        if (!ANOMALY_05000353 && !ANOMALY_05000386)
+                bfrom_SoftReset((void *)(L1_SCRATCH_START + L1_SCRATCH_LENGTH - 20));
+
         /* Wait for completion of "system" events such as cache line
          * line fills so that we avoid infinite stalls later on as
          * much as possible.  This code is in L1, so it won't trigger
@@ -30,46 +33,40 @@ static void bfin_reset(void)
          */
         __builtin_bfin_ssync();
 
-        /* The bootrom checks to see how it was reset and will
-         * automatically perform a software reset for us when
-         * it starts executing after the core reset.
-         */
-        if (ANOMALY_05000353 || ANOMALY_05000386) {
-                /* Initiate System software reset. */
-                bfin_write_SWRST(0x7);
+        /* Initiate System software reset. */
+        bfin_write_SWRST(0x7);
 
-                /* Due to the way reset is handled in the hardware, we need
-                 * to delay for 10 SCLKS.  The only reliable way to do this is
-                 * to calculate the CCLK/SCLK ratio and multiply 10.  For now,
-                 * we'll assume worse case which is a 1:15 ratio.
-                 */
-                asm(
-                        "LSETUP (1f, 1f) LC0 = %0\n"
-                        "1: nop;"
-                        :
-                        : "a" (15 * 10)
-                        : "LC0", "LB0", "LT0"
-                );
+        /* Due to the way reset is handled in the hardware, we need
+         * to delay for 10 SCLKS.  The only reliable way to do this is
+         * to calculate the CCLK/SCLK ratio and multiply 10.  For now,
+         * we'll assume worse case which is a 1:15 ratio.
+         */
+        asm(
+                "LSETUP (1f, 1f) LC0 = %0\n"
+                "1: nop;"
+                :
+                : "a" (15 * 10)
+                : "LC0", "LB0", "LT0"
+        );
 
-                /* Clear System software reset */
-                bfin_write_SWRST(0);
+        /* Clear System software reset */
+        bfin_write_SWRST(0);
 
-                /* The BF526 ROM will crash during reset */
+        /* The BF526 ROM will crash during reset */
 #if defined(__ADSPBF522__) || defined(__ADSPBF524__) || defined(__ADSPBF526__)
-                bfin_read_SWRST();
+        bfin_read_SWRST();
 #endif
 
-                /* Wait for the SWRST write to complete.  Cannot rely on SSYNC
-                 * though as the System state is all reset now.
-                 */
-                asm(
-                        "LSETUP (1f, 1f) LC1 = %0\n"
-                        "1: nop;"
-                        :
-                        : "a" (15 * 1)
-                        : "LC1", "LB1", "LT1"
-                );
-        }
+        /* Wait for the SWRST write to complete.  Cannot rely on SSYNC
+         * though as the System state is all reset now.
+         */
+        asm(
+                "LSETUP (1f, 1f) LC1 = %0\n"
+                "1: nop;"
+                :
+                : "a" (15 * 1)
+                : "LC1", "LB1", "LT1"
+        );
 
         while (1)
                 /* Issue core reset */
diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index 805c6132c779..536bd9d7e0cf 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <asm/cpu.h>
 #include <asm/fixed_code.h>
 #include <asm/early_printk.h>
+#include <asm/irq_handler.h>
 
 u16 _bfin_swrst;
 EXPORT_SYMBOL(_bfin_swrst);
@@ -105,6 +106,8 @@ void __cpuinit bfin_setup_caches(unsigned int cpu)
         bfin_dcache_init(dcplb_tbl[cpu]);
 #endif
 
+        bfin_setup_cpudata(cpu);
+
         /*
          * In cache coherence emulation mode, we need to have the
          * D-cache enabled before running any atomic operation which
@@ -163,7 +166,6 @@ void __cpuinit bfin_setup_cpudata(unsigned int cpu)
 {
         struct blackfin_cpudata *cpudata = &per_cpu(cpu_data, cpu);
 
-        cpudata->idle = current;
         cpudata->imemctl = bfin_read_IMEM_CONTROL();
         cpudata->dmemctl = bfin_read_DMEM_CONTROL();
 }
@@ -851,6 +853,7 @@ void __init native_machine_early_platform_add_devices(void)
 
 void __init setup_arch(char **cmdline_p)
 {
+        u32 mmr;
         unsigned long sclk, cclk;
 
         native_machine_early_platform_add_devices();
@@ -902,10 +905,10 @@ void __init setup_arch(char **cmdline_p)
         bfin_write_EBIU_FCTL(CONFIG_EBIU_FCTLVAL);
 #endif
 #ifdef CONFIG_BFIN_HYSTERESIS_CONTROL
-        bfin_write_PORTF_HYSTERISIS(HYST_PORTF_0_15);
-        bfin_write_PORTG_HYSTERISIS(HYST_PORTG_0_15);
-        bfin_write_PORTH_HYSTERISIS(HYST_PORTH_0_15);
-        bfin_write_MISCPORT_HYSTERISIS((bfin_read_MISCPORT_HYSTERISIS() &
+        bfin_write_PORTF_HYSTERESIS(HYST_PORTF_0_15);
+        bfin_write_PORTG_HYSTERESIS(HYST_PORTG_0_15);
+        bfin_write_PORTH_HYSTERESIS(HYST_PORTH_0_15);
+        bfin_write_MISCPORT_HYSTERESIS((bfin_read_MISCPORT_HYSTERESIS() &
                                         ~HYST_NONEGPIO_MASK) | HYST_NONEGPIO);
 #endif
 
@@ -921,17 +924,14 @@ void __init setup_arch(char **cmdline_p)
                 bfin_read_IMDMA_D1_IRQ_STATUS();
         }
 #endif
-        printk(KERN_INFO "Hardware Trace ");
-        if (bfin_read_TBUFCTL() & 0x1)
-                printk(KERN_CONT "Active ");
-        else
-                printk(KERN_CONT "Off ");
-        if (bfin_read_TBUFCTL() & 0x2)
-                printk(KERN_CONT "and Enabled\n");
-        else
-                printk(KERN_CONT "and Disabled\n");
 
-        printk(KERN_INFO "Boot Mode: %i\n", bfin_read_SYSCR() & 0xF);
+        mmr = bfin_read_TBUFCTL();
+        printk(KERN_INFO "Hardware Trace %s and %sabled\n",
+                (mmr & 0x1) ? "active" : "off",
+                (mmr & 0x2) ? "en" : "dis");
+
+        mmr = bfin_read_SYSCR();
+        printk(KERN_INFO "Boot Mode: %i\n", mmr & 0xF);
 
         /* Newer parts mirror SWRST bits in SYSCR */
 #if defined(CONFIG_BF53x) || defined(CONFIG_BF561) || \
@@ -939,7 +939,7 @@ void __init setup_arch(char **cmdline_p)
         _bfin_swrst = bfin_read_SWRST();
 #else
         /* Clear boot mode field */
-        _bfin_swrst = bfin_read_SYSCR() & ~0xf;
+        _bfin_swrst = mmr & ~0xf;
 #endif
 
 #ifdef CONFIG_DEBUG_DOUBLEFAULT_PRINT
@@ -1036,8 +1036,6 @@ void __init setup_arch(char **cmdline_p)
 static int __init topology_init(void)
 {
         unsigned int cpu;
-        /* Record CPU-private information for the boot processor. */
-        bfin_setup_cpudata(0);
 
         for_each_possible_cpu(cpu) {
                 register_cpu(&per_cpu(cpu_data, cpu).cpu, cpu);
@@ -1283,12 +1281,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                    dsup_banks, BFIN_DSUBBANKS, BFIN_DWAYS,
                    BFIN_DLINES);
 #ifdef __ARCH_SYNC_CORE_DCACHE
-        seq_printf(m, "SMP Dcache Flushes\t: %lu\n\n", dcache_invld_count[cpu_num]);
+        seq_printf(m, "dcache flushes\t: %lu\n", dcache_invld_count[cpu_num]);
 #endif
 #ifdef __ARCH_SYNC_CORE_ICACHE
-        seq_printf(m, "SMP Icache Flushes\t: %lu\n\n", icache_invld_count[cpu_num]);
+        seq_printf(m, "icache flushes\t: %lu\n", icache_invld_count[cpu_num]);
 #endif
 
+        seq_printf(m, "\n");
+
         if (cpu_num != num_possible_cpus() - 1)
                 return 0;
 
@@ -1312,13 +1312,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                               " in data cache\n");
         }
         seq_printf(m, "board name\t: %s\n", bfin_board_name);
-        seq_printf(m, "board memory\t: %ld kB (0x%p -> 0x%p)\n",
-                 physical_mem_end >> 10, (void *)0, (void *)physical_mem_end);
-        seq_printf(m, "kernel memory\t: %d kB (0x%p -> 0x%p)\n",
+        seq_printf(m, "board memory\t: %ld kB (0x%08lx -> 0x%08lx)\n",
+                physical_mem_end >> 10, 0ul, physical_mem_end);
+        seq_printf(m, "kernel memory\t: %d kB (0x%08lx -> 0x%08lx)\n",
                 ((int)memory_end - (int)_rambase) >> 10,
-                (void *)_rambase,
-                (void *)memory_end);
-        seq_printf(m, "\n");
+                _rambase, memory_end);
 
         return 0;
 }
@@ -1326,7 +1324,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
         if (*pos == 0)
-                *pos = first_cpu(cpu_online_map);
+                *pos = cpumask_first(cpu_online_mask);
         if (*pos >= num_online_cpus())
                 return NULL;
 
@@ -1335,7 +1333,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 {
-        *pos = next_cpu(*pos, cpu_online_map);
+        *pos = cpumask_next(*pos, cpu_online_mask);
 
         return c_start(m, pos);
 }
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 8d85c8c6f857..3ac5b66d14aa 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -155,14 +155,8 @@ SECTIONS
                 SECURITY_INITCALL
                 INIT_RAM_FS
 
-                . = ALIGN(4);
                 ___per_cpu_load = .;
-                ___per_cpu_start = .;
-                *(.data.percpu.first)
-                *(.data.percpu.page_aligned)
-                *(.data.percpu)
-                *(.data.percpu.shared_aligned)
-                ___per_cpu_end = .;
+                PERCPU_INPUT(32)
 
                 EXIT_DATA
                 __einitdata = .;
diff --git a/arch/blackfin/mach-bf518/include/mach/anomaly.h b/arch/blackfin/mach-bf518/include/mach/anomaly.h
index 24918c5f7ea1..d2f076fbbc9e 100644
--- a/arch/blackfin/mach-bf518/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf518/include/mach/anomaly.h
@@ -5,7 +5,7 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
@@ -141,6 +141,7 @@
 #define ANOMALY_05000364 (0)
 #define ANOMALY_05000371 (0)
 #define ANOMALY_05000380 (0)
+#define ANOMALY_05000383 (0)
 #define ANOMALY_05000386 (0)
 #define ANOMALY_05000389 (0)
 #define ANOMALY_05000400 (0)
@@ -155,6 +156,7 @@
 #define ANOMALY_05000467 (0)
 #define ANOMALY_05000474 (0)
 #define ANOMALY_05000475 (0)
+#define ANOMALY_05000480 (0)
 #define ANOMALY_05000485 (0)
 
 #endif
diff --git a/arch/blackfin/mach-bf518/include/mach/cdefBF512.h b/arch/blackfin/mach-bf518/include/mach/cdefBF512.h
index b657d37a3402..bb79627f0929 100644
--- a/arch/blackfin/mach-bf518/include/mach/cdefBF512.h
+++ b/arch/blackfin/mach-bf518/include/mach/cdefBF512.h
@@ -990,18 +990,18 @@
 #define bfin_write_PORTG_SLEW(val)              bfin_write16(PORTG_SLEW, val)
 #define bfin_read_PORTH_SLEW()                  bfin_read16(PORTH_SLEW)
 #define bfin_write_PORTH_SLEW(val)              bfin_write16(PORTH_SLEW, val)
-#define bfin_read_PORTF_HYSTERISIS()            bfin_read16(PORTF_HYSTERISIS)
-#define bfin_write_PORTF_HYSTERISIS(val)        bfin_write16(PORTF_HYSTERISIS, val)
-#define bfin_read_PORTG_HYSTERISIS()            bfin_read16(PORTG_HYSTERISIS)
-#define bfin_write_PORTG_HYSTERISIS(val)        bfin_write16(PORTG_HYSTERISIS, val)
-#define bfin_read_PORTH_HYSTERISIS()            bfin_read16(PORTH_HYSTERISIS)
-#define bfin_write_PORTH_HYSTERISIS(val)        bfin_write16(PORTH_HYSTERISIS, val)
+#define bfin_read_PORTF_HYSTERESIS()            bfin_read16(PORTF_HYSTERESIS)
+#define bfin_write_PORTF_HYSTERESIS(val)        bfin_write16(PORTF_HYSTERESIS, val)
+#define bfin_read_PORTG_HYSTERESIS()            bfin_read16(PORTG_HYSTERESIS)
+#define bfin_write_PORTG_HYSTERESIS(val)        bfin_write16(PORTG_HYSTERESIS, val)
+#define bfin_read_PORTH_HYSTERESIS()            bfin_read16(PORTH_HYSTERESIS)
+#define bfin_write_PORTH_HYSTERESIS(val)        bfin_write16(PORTH_HYSTERESIS, val)
 #define bfin_read_MISCPORT_DRIVE()              bfin_read16(MISCPORT_DRIVE)
 #define bfin_write_MISCPORT_DRIVE(val)          bfin_write16(MISCPORT_DRIVE, val)
 #define bfin_read_MISCPORT_SLEW()               bfin_read16(MISCPORT_SLEW)
 #define bfin_write_MISCPORT_SLEW(val)           bfin_write16(MISCPORT_SLEW, val)
-#define bfin_read_MISCPORT_HYSTERISIS()         bfin_read16(MISCPORT_HYSTERISIS)
-#define bfin_write_MISCPORT_HYSTERISIS(val)     bfin_write16(MISCPORT_HYSTERISIS, val)
+#define bfin_read_MISCPORT_HYSTERESIS()         bfin_read16(MISCPORT_HYSTERESIS)
+#define bfin_write_MISCPORT_HYSTERESIS(val)     bfin_write16(MISCPORT_HYSTERESIS, val)
 
 /* HOST Port Registers */
 
diff --git a/arch/blackfin/mach-bf518/include/mach/defBF512.h b/arch/blackfin/mach-bf518/include/mach/defBF512.h
index cb1172f50757..729704078cd7 100644
--- a/arch/blackfin/mach-bf518/include/mach/defBF512.h
+++ b/arch/blackfin/mach-bf518/include/mach/defBF512.h
@@ -561,12 +561,12 @@
 #define PORTF_SLEW              0xFFC03230      /* Port F slew control */
 #define PORTG_SLEW              0xFFC03234      /* Port G slew control */
 #define PORTH_SLEW              0xFFC03238      /* Port H slew control */
-#define PORTF_HYSTERISIS        0xFFC03240      /* Port F Schmitt trigger control */
-#define PORTG_HYSTERISIS        0xFFC03244      /* Port G Schmitt trigger control */
-#define PORTH_HYSTERISIS        0xFFC03248      /* Port H Schmitt trigger control */
+#define PORTF_HYSTERESIS        0xFFC03240      /* Port F Schmitt trigger control */
+#define PORTG_HYSTERESIS        0xFFC03244      /* Port G Schmitt trigger control */
+#define PORTH_HYSTERESIS        0xFFC03248      /* Port H Schmitt trigger control */
 #define MISCPORT_DRIVE          0xFFC03280      /* Misc Port drive strength control */
 #define MISCPORT_SLEW           0xFFC03284      /* Misc Port slew control */
-#define MISCPORT_HYSTERISIS     0xFFC03288      /* Misc Port Schmitt trigger control */
+#define MISCPORT_HYSTERESIS     0xFFC03288      /* Misc Port Schmitt trigger control */
 
 
 /***********************************************************************************
diff --git a/arch/blackfin/mach-bf518/include/mach/irq.h b/arch/blackfin/mach-bf518/include/mach/irq.h
index 435e76e31aaa..edf8efd457dc 100644
--- a/arch/blackfin/mach-bf518/include/mach/irq.h
+++ b/arch/blackfin/mach-bf518/include/mach/irq.h
@@ -7,38 +7,9 @@
 #ifndef _BF518_IRQ_H_
 #define _BF518_IRQ_H_
 
-/*
- * Interrupt source definitions
-        Event Source    Core Event Name
-        Core        Emulation               **
-        Events         (highest priority)  EMU         0
-        Reset                   RST         1
-        NMI                     NMI         2
-        Exception               EVX         3
-        Reserved                --          4
-        Hardware Error          IVHW        5
-        Core Timer              IVTMR       6 *
-
-        .....
-
-         Software Interrupt 1    IVG14       31
-         Software Interrupt 2    --
-         (lowest priority)  IVG15       32 *
-*/
-
-#define NR_PERI_INTS    (2 * 32)
-
-/* The ABSTRACT IRQ definitions */
-/** the first seven of the following are fixed, the rest you change if you need to **/
-#define IRQ_EMU                 0       /* Emulation */
-#define IRQ_RST                 1       /* reset */
-#define IRQ_NMI                 2       /* Non Maskable */
-#define IRQ_EVX                 3       /* Exception */
-#define IRQ_UNUSED              4       /* - unused interrupt */
-#define IRQ_HWERR               5       /* Hardware Error */
-#define IRQ_CORETMR             6       /* Core timer */
-
-#define BFIN_IRQ(x)             ((x) + 7)
+#include <mach-common/irq.h>
+
+#define NR_PERI_INTS            (2 * 32)
 
 #define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
 #define IRQ_DMA0_ERROR          BFIN_IRQ(1)     /* DMA Error 0 (generic) */
@@ -54,23 +25,23 @@
 #define IRQ_UART0_ERROR         BFIN_IRQ(12)    /* UART0 Status */
 #define IRQ_UART1_ERROR         BFIN_IRQ(13)    /* UART1 Status */
 #define IRQ_RTC                 BFIN_IRQ(14)    /* RTC */
-#define IRQ_PPI                 BFIN_IRQ(15)    /* DMA Channel 0 (PPI) */
+#define IRQ_PPI                 BFIN_IRQ(15)    /* DMA Channel 0 (PPI) */
 #define IRQ_SPORT0_RX           BFIN_IRQ(16)    /* DMA 3 Channel (SPORT0 RX) */
 #define IRQ_SPORT0_TX           BFIN_IRQ(17)    /* DMA 4 Channel (SPORT0 TX) */
 #define IRQ_RSI                 BFIN_IRQ(17)    /* DMA 4 Channel (RSI) */
 #define IRQ_SPORT1_RX           BFIN_IRQ(18)    /* DMA 5 Channel (SPORT1 RX/SPI) */
 #define IRQ_SPI1                BFIN_IRQ(18)    /* DMA 5 Channel (SPI1) */
 #define IRQ_SPORT1_TX           BFIN_IRQ(19)    /* DMA 6 Channel (SPORT1 TX) */
-#define IRQ_TWI                 BFIN_IRQ(20)    /* TWI */
-#define IRQ_SPI0                BFIN_IRQ(21)    /* DMA 7 Channel (SPI0) */
-#define IRQ_UART0_RX            BFIN_IRQ(22)    /* DMA8 Channel (UART0 RX) */
-#define IRQ_UART0_TX            BFIN_IRQ(23)    /* DMA9 Channel (UART0 TX) */
-#define IRQ_UART1_RX            BFIN_IRQ(24)    /* DMA10 Channel (UART1 RX) */
-#define IRQ_UART1_TX            BFIN_IRQ(25)    /* DMA11 Channel (UART1 TX) */
-#define IRQ_OPTSEC              BFIN_IRQ(26)    /* OTPSEC Interrupt */
-#define IRQ_CNT                 BFIN_IRQ(27)    /* GP Counter */
-#define IRQ_MAC_RX              BFIN_IRQ(28)    /* DMA1 Channel (MAC RX) */
-#define IRQ_PORTH_INTA          BFIN_IRQ(29)    /* Port H Interrupt A */
+#define IRQ_TWI                 BFIN_IRQ(20)    /* TWI */
+#define IRQ_SPI0                BFIN_IRQ(21)    /* DMA 7 Channel (SPI0) */
+#define IRQ_UART0_RX            BFIN_IRQ(22)    /* DMA8 Channel (UART0 RX) */
+#define IRQ_UART0_TX            BFIN_IRQ(23)    /* DMA9 Channel (UART0 TX) */
+#define IRQ_UART1_RX            BFIN_IRQ(24)    /* DMA10 Channel (UART1 RX) */
+#define IRQ_UART1_TX            BFIN_IRQ(25)    /* DMA11 Channel (UART1 TX) */
+#define IRQ_OPTSEC              BFIN_IRQ(26)    /* OTPSEC Interrupt */
+#define IRQ_CNT                 BFIN_IRQ(27)    /* GP Counter */
+#define IRQ_MAC_RX              BFIN_IRQ(28)    /* DMA1 Channel (MAC RX) */
+#define IRQ_PORTH_INTA          BFIN_IRQ(29)    /* Port H Interrupt A */
 #define IRQ_MAC_TX              BFIN_IRQ(30)    /* DMA2 Channel (MAC TX) */
 #define IRQ_PORTH_INTB          BFIN_IRQ(31)    /* Port H Interrupt B */
 #define IRQ_TIMER0              BFIN_IRQ(32)    /* Timer 0 */
@@ -96,101 +67,90 @@
 #define IRQ_PWM_SYNC            BFIN_IRQ(54)    /* PWM Sync Interrupt */
 #define IRQ_PTP_STAT            BFIN_IRQ(55)    /* PTP Stat Interrupt */
 
-#define SYS_IRQS                BFIN_IRQ(63)    /* 70 */
-
-#define IRQ_PF0         71
-#define IRQ_PF1         72
-#define IRQ_PF2         73
-#define IRQ_PF3         74
-#define IRQ_PF4         75
-#define IRQ_PF5         76
-#define IRQ_PF6         77
-#define IRQ_PF7         78
-#define IRQ_PF8         79
-#define IRQ_PF9         80
-#define IRQ_PF10        81
-#define IRQ_PF11        82
-#define IRQ_PF12        83
-#define IRQ_PF13        84
-#define IRQ_PF14        85
-#define IRQ_PF15        86
-
-#define IRQ_PG0         87
-#define IRQ_PG1         88
-#define IRQ_PG2         89
-#define IRQ_PG3         90
-#define IRQ_PG4         91
-#define IRQ_PG5         92
-#define IRQ_PG6         93
-#define IRQ_PG7         94
-#define IRQ_PG8         95
-#define IRQ_PG9         96
-#define IRQ_PG10        97
-#define IRQ_PG11        98
-#define IRQ_PG12        99
-#define IRQ_PG13        100
-#define IRQ_PG14        101
-#define IRQ_PG15        102
-
-#define IRQ_PH0         103
-#define IRQ_PH1         104
-#define IRQ_PH2         105
-#define IRQ_PH3         106
-#define IRQ_PH4         107
-#define IRQ_PH5         108
-#define IRQ_PH6         109
-#define IRQ_PH7         110
-#define IRQ_PH8         111
-#define IRQ_PH9         112
-#define IRQ_PH10        113
-#define IRQ_PH11        114
-#define IRQ_PH12        115
-#define IRQ_PH13        116
-#define IRQ_PH14        117
-#define IRQ_PH15        118
-
-#define GPIO_IRQ_BASE   IRQ_PF0
-
-#define IRQ_MAC_PHYINT          119 /* PHY_INT Interrupt */
-#define IRQ_MAC_MMCINT          120 /* MMC Counter Interrupt */
-#define IRQ_MAC_RXFSINT         121 /* RX Frame-Status Interrupt */
-#define IRQ_MAC_TXFSINT         122 /* TX Frame-Status Interrupt */
-#define IRQ_MAC_WAKEDET         123 /* Wake-Up Interrupt */
-#define IRQ_MAC_RXDMAERR        124 /* RX DMA Direction Error Interrupt */
-#define IRQ_MAC_TXDMAERR        125 /* TX DMA Direction Error Interrupt */
-#define IRQ_MAC_STMDONE         126 /* Station Mgt. Transfer Done Interrupt */
-
-#define NR_MACH_IRQS    (IRQ_MAC_STMDONE + 1)
-#define NR_IRQS         (NR_MACH_IRQS + NR_SPARE_IRQS)
-
-#define IVG7            7
-#define IVG8            8
-#define IVG9            9
-#define IVG10           10
-#define IVG11           11
-#define IVG12           12
-#define IVG13           13
-#define IVG14           14
-#define IVG15           15
+#define SYS_IRQS                BFIN_IRQ(63)    /* 70 */
+
+#define IRQ_PF0                 71
+#define IRQ_PF1                 72
+#define IRQ_PF2                 73
+#define IRQ_PF3                 74
+#define IRQ_PF4                 75
+#define IRQ_PF5                 76
+#define IRQ_PF6                 77
+#define IRQ_PF7                 78
+#define IRQ_PF8                 79
+#define IRQ_PF9                 80
+#define IRQ_PF10                81
+#define IRQ_PF11                82
+#define IRQ_PF12                83
+#define IRQ_PF13                84
+#define IRQ_PF14                85
+#define IRQ_PF15                86
+
+#define IRQ_PG0                 87
+#define IRQ_PG1                 88
+#define IRQ_PG2                 89
+#define IRQ_PG3                 90
+#define IRQ_PG4                 91
+#define IRQ_PG5                 92
+#define IRQ_PG6                 93
+#define IRQ_PG7                 94
+#define IRQ_PG8                 95
+#define IRQ_PG9                 96
+#define IRQ_PG10                97
+#define IRQ_PG11                98
+#define IRQ_PG12                99
+#define IRQ_PG13                100
+#define IRQ_PG14                101
+#define IRQ_PG15                102
+
+#define IRQ_PH0                 103
+#define IRQ_PH1                 104
+#define IRQ_PH2                 105
+#define IRQ_PH3                 106
+#define IRQ_PH4                 107
+#define IRQ_PH5                 108
+#define IRQ_PH6                 109
+#define IRQ_PH7                 110
+#define IRQ_PH8                 111
+#define IRQ_PH9                 112
+#define IRQ_PH10                113
+#define IRQ_PH11                114
+#define IRQ_PH12                115
+#define IRQ_PH13                116
+#define IRQ_PH14                117
+#define IRQ_PH15                118
+
+#define GPIO_IRQ_BASE           IRQ_PF0
+
+#define IRQ_MAC_PHYINT          119     /* PHY_INT Interrupt */
+#define IRQ_MAC_MMCINT          120     /* MMC Counter Interrupt */
+#define IRQ_MAC_RXFSINT         121     /* RX Frame-Status Interrupt */
+#define IRQ_MAC_TXFSINT         122     /* TX Frame-Status Interrupt */
+#define IRQ_MAC_WAKEDET         123     /* Wake-Up Interrupt */
+#define IRQ_MAC_RXDMAERR        124     /* RX DMA Direction Error Interrupt */
+#define IRQ_MAC_TXDMAERR        125     /* TX DMA Direction Error Interrupt */
+#define IRQ_MAC_STMDONE         126     /* Station Mgt. Transfer Done Interrupt */
+
+#define NR_MACH_IRQS            (IRQ_MAC_STMDONE + 1)
 
 /* IAR0 BIT FIELDS */
 #define IRQ_PLL_WAKEUP_POS      0
 #define IRQ_DMA0_ERROR_POS      4
-#define IRQ_DMAR0_BLK_POS       8
-#define IRQ_DMAR1_BLK_POS       12
-#define IRQ_DMAR0_OVR_POS       16
-#define IRQ_DMAR1_OVR_POS       20
-#define IRQ_PPI_ERROR_POS       24
-#define IRQ_MAC_ERROR_POS       28
+#define IRQ_DMAR0_BLK_POS       8
+#define IRQ_DMAR1_BLK_POS       12
+#define IRQ_DMAR0_OVR_POS       16
+#define IRQ_DMAR1_OVR_POS       20
+#define IRQ_PPI_ERROR_POS       24
+#define IRQ_MAC_ERROR_POS       28
 
 /* IAR1 BIT FIELDS */
 #define IRQ_SPORT0_ERROR_POS    0
 #define IRQ_SPORT1_ERROR_POS    4
 #define IRQ_PTP_ERROR_POS       8
-#define IRQ_UART0_ERROR_POS     16
-#define IRQ_UART1_ERROR_POS     20
-#define IRQ_RTC_POS             24
-#define IRQ_PPI_POS             28
+#define IRQ_UART0_ERROR_POS     16
+#define IRQ_UART1_ERROR_POS     20
+#define IRQ_RTC_POS             24
+#define IRQ_PPI_POS             28
 
 /* IAR2 BIT FIELDS */
 #define IRQ_SPORT0_RX_POS       0
@@ -199,19 +159,19 @@
 #define IRQ_SPORT1_RX_POS       8
 #define IRQ_SPI1_POS            8
 #define IRQ_SPORT1_TX_POS       12
-#define IRQ_TWI_POS             16
-#define IRQ_SPI0_POS            20
-#define IRQ_UART0_RX_POS        24
-#define IRQ_UART0_TX_POS        28
+#define IRQ_TWI_POS             16
+#define IRQ_SPI0_POS            20
+#define IRQ_UART0_RX_POS        24
+#define IRQ_UART0_TX_POS        28
 
 /* IAR3 BIT FIELDS */
-#define IRQ_UART1_RX_POS        0
-#define IRQ_UART1_TX_POS        4
-#define IRQ_OPTSEC_POS          8
-#define IRQ_CNT_POS             12
-#define IRQ_MAC_RX_POS          16
+#define IRQ_UART1_RX_POS        0
+#define IRQ_UART1_TX_POS        4
+#define IRQ_OPTSEC_POS          8
+#define IRQ_CNT_POS             12
+#define IRQ_MAC_RX_POS          16
 #define IRQ_PORTH_INTA_POS      20
-#define IRQ_MAC_TX_POS          24
+#define IRQ_MAC_TX_POS          24
 #define IRQ_PORTH_INTB_POS      28
 
 /* IAR4 BIT FIELDS */
@@ -227,19 +187,19 @@
 /* IAR5 BIT FIELDS */
 #define IRQ_PORTG_INTA_POS      0
 #define IRQ_PORTG_INTB_POS      4
-#define IRQ_MEM_DMA0_POS        8
-#define IRQ_MEM_DMA1_POS        12
-#define IRQ_WATCH_POS           16
+#define IRQ_MEM_DMA0_POS        8
+#define IRQ_MEM_DMA1_POS        12
+#define IRQ_WATCH_POS           16
 #define IRQ_PORTF_INTA_POS      20
 #define IRQ_PORTF_INTB_POS      24
-#define IRQ_SPI0_ERROR_POS      28
+#define IRQ_SPI0_ERROR_POS      28
 
 /* IAR6 BIT FIELDS */
-#define IRQ_SPI1_ERROR_POS      0
-#define IRQ_RSI_INT0_POS        12
-#define IRQ_RSI_INT1_POS        16
-#define IRQ_PWM_TRIP_POS        20
-#define IRQ_PWM_SYNC_POS        24
-#define IRQ_PTP_STAT_POS        28
-
-#endif                          /* _BF518_IRQ_H_ */
+#define IRQ_SPI1_ERROR_POS      0
+#define IRQ_RSI_INT0_POS        12
+#define IRQ_RSI_INT1_POS        16
+#define IRQ_PWM_TRIP_POS        20
+#define IRQ_PWM_SYNC_POS        24
+#define IRQ_PTP_STAT_POS        28
+
+#endif
diff --git a/arch/blackfin/mach-bf527/boards/ezkit.c b/arch/blackfin/mach-bf527/boards/ezkit.c
index 2cd2ff6f3043..e67ac7720668 100644
--- a/arch/blackfin/mach-bf527/boards/ezkit.c
+++ b/arch/blackfin/mach-bf527/boards/ezkit.c
@@ -26,6 +26,7 @@
 #include <asm/portmux.h>
 #include <asm/dpmc.h>
 #include <linux/spi/ad7877.h>
+#include <asm/bfin_sport.h>
 
 /*
  * Name the Board for the /proc/cpuinfo
@@ -526,11 +527,69 @@ static struct bfin5xx_spi_chip spidev_chip_info = {
 };
 #endif
 
+#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) || \
+        defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE)
+
+static const u16 bfin_snd_pin[][7] = {
+        {P_SPORT0_DTPRI, P_SPORT0_TSCLK, P_SPORT0_RFS,
+                P_SPORT0_DRPRI, P_SPORT0_RSCLK, 0, 0},
+        {P_SPORT1_DTPRI, P_SPORT1_TSCLK, P_SPORT1_RFS,
+                P_SPORT1_DRPRI, P_SPORT1_RSCLK, P_SPORT1_TFS, 0},
+};
+
+static struct bfin_snd_platform_data bfin_snd_data[] = {
+        {
+                .pin_req = &bfin_snd_pin[0][0],
+        },
+        {
+                .pin_req = &bfin_snd_pin[1][0],
+        },
+};
+
+#define BFIN_SND_RES(x) \
+        [x] = { \
+                { \
+                        .start = SPORT##x##_TCR1, \
+                        .end = SPORT##x##_TCR1, \
+                        .flags = IORESOURCE_MEM \
+                }, \
+                { \
+                        .start = CH_SPORT##x##_RX, \
+                        .end = CH_SPORT##x##_RX, \
+                        .flags = IORESOURCE_DMA, \
+                }, \
+                { \
+                        .start = CH_SPORT##x##_TX, \
+                        .end = CH_SPORT##x##_TX, \
+                        .flags = IORESOURCE_DMA, \
+                }, \
+                { \
+                        .start = IRQ_SPORT##x##_ERROR, \
+                        .end = IRQ_SPORT##x##_ERROR, \
+                        .flags = IORESOURCE_IRQ, \
+                } \
+        }
+
+static struct resource bfin_snd_resources[][4] = {
+        BFIN_SND_RES(0),
+        BFIN_SND_RES(1),
+};
+
+static struct platform_device bfin_pcm = {
+        .name = "bfin-pcm-audio",
+        .id = -1,
+};
+#endif
+
 #if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE)
 static struct platform_device bfin_i2s = {
         .name = "bfin-i2s",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
@@ -538,7 +597,11 @@ static struct platform_device bfin_i2s = {
 static struct platform_device bfin_tdm = {
         .name = "bfin-tdm",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
@@ -583,7 +646,9 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = {
                 .max_speed_hz = 3125000,     /* max spi clock (SCK) speed in HZ */
                 .bus_num = 0,
                 .chip_select = 4,
+                .platform_data = "ad1836",
                 .controller_data = &ad1836_spi_chip_info,
+                .mode = SPI_MODE_3,
         },
 #endif
 #if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE)
@@ -1211,6 +1276,11 @@ static struct platform_device *stamp_devices[] __initdata = {
         &ezkit_flash_device,
 #endif
 
+#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) || \
+        defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE)
+        &bfin_pcm,
+#endif
+
 #if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE)
         &bfin_i2s,
 #endif
diff --git a/arch/blackfin/mach-bf527/include/mach/anomaly.h b/arch/blackfin/mach-bf527/include/mach/anomaly.h
index 9358afa05c90..e66a7e89cd3c 100644
--- a/arch/blackfin/mach-bf527/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf527/include/mach/anomaly.h
@@ -5,14 +5,14 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
 
 /* This file should be up to date with:
  *  - Revision E, 03/15/2010; ADSP-BF526 Blackfin Processor Anomaly List
- *  - Revision G, 08/25/2009; ADSP-BF527 Blackfin Processor Anomaly List
+ *  - Revision H, 04/29/2010; ADSP-BF527 Blackfin Processor Anomaly List
  */
 
 #ifndef _MACH_ANOMALY_H_
@@ -220,6 +220,8 @@
 #define ANOMALY_05000483 (1)
 /* PLL_CTL Change Using bfrom_SysControl() Can Result in Processor Overclocking */
 #define ANOMALY_05000485 (_ANOMALY_BF526_BF527(< 2, < 3))
+/* The CODEC Zero-Cross Detect Feature is not Functional */
+#define ANOMALY_05000487 (1)
 /* IFLUSH sucks at life */
 #define ANOMALY_05000491 (1)
 
@@ -268,11 +270,13 @@
 #define ANOMALY_05000323 (0)
 #define ANOMALY_05000362 (1)
 #define ANOMALY_05000363 (0)
+#define ANOMALY_05000383 (0)
 #define ANOMALY_05000400 (0)
 #define ANOMALY_05000402 (0)
 #define ANOMALY_05000412 (0)
 #define ANOMALY_05000447 (0)
 #define ANOMALY_05000448 (0)
 #define ANOMALY_05000474 (0)
+#define ANOMALY_05000480 (0)
 
 #endif
diff --git a/arch/blackfin/mach-bf527/include/mach/cdefBF522.h b/arch/blackfin/mach-bf527/include/mach/cdefBF522.h
index 618dfcdfa91a..2c12e879aa4e 100644
--- a/arch/blackfin/mach-bf527/include/mach/cdefBF522.h
+++ b/arch/blackfin/mach-bf527/include/mach/cdefBF522.h
@@ -1007,18 +1007,18 @@
 #define bfin_write_PORTG_SLEW(val)              bfin_write16(PORTG_SLEW, val)
 #define bfin_read_PORTH_SLEW()                  bfin_read16(PORTH_SLEW)
 #define bfin_write_PORTH_SLEW(val)              bfin_write16(PORTH_SLEW, val)
-#define bfin_read_PORTF_HYSTERISIS()            bfin_read16(PORTF_HYSTERISIS)
-#define bfin_write_PORTF_HYSTERISIS(val)        bfin_write16(PORTF_HYSTERISIS, val)
-#define bfin_read_PORTG_HYSTERISIS()            bfin_read16(PORTG_HYSTERISIS)
-#define bfin_write_PORTG_HYSTERISIS(val)        bfin_write16(PORTG_HYSTERISIS, val)
-#define bfin_read_PORTH_HYSTERISIS()            bfin_read16(PORTH_HYSTERISIS)
-#define bfin_write_PORTH_HYSTERISIS(val)        bfin_write16(PORTH_HYSTERISIS, val)
+#define bfin_read_PORTF_HYSTERESIS()            bfin_read16(PORTF_HYSTERESIS)
+#define bfin_write_PORTF_HYSTERESIS(val)        bfin_write16(PORTF_HYSTERESIS, val)
+#define bfin_read_PORTG_HYSTERESIS()            bfin_read16(PORTG_HYSTERESIS)
+#define bfin_write_PORTG_HYSTERESIS(val)        bfin_write16(PORTG_HYSTERESIS, val)
+#define bfin_read_PORTH_HYSTERESIS()            bfin_read16(PORTH_HYSTERESIS)
+#define bfin_write_PORTH_HYSTERESIS(val)        bfin_write16(PORTH_HYSTERESIS, val)
 #define bfin_read_MISCPORT_DRIVE()              bfin_read16(MISCPORT_DRIVE)
 #define bfin_write_MISCPORT_DRIVE(val)          bfin_write16(MISCPORT_DRIVE, val)
 #define bfin_read_MISCPORT_SLEW()               bfin_read16(MISCPORT_SLEW)
 #define bfin_write_MISCPORT_SLEW(val)           bfin_write16(MISCPORT_SLEW, val)
-#define bfin_read_MISCPORT_HYSTERISIS()         bfin_read16(MISCPORT_HYSTERISIS)
-#define bfin_write_MISCPORT_HYSTERISIS(val)     bfin_write16(MISCPORT_HYSTERISIS, val)
+#define bfin_read_MISCPORT_HYSTERESIS()         bfin_read16(MISCPORT_HYSTERESIS)
+#define bfin_write_MISCPORT_HYSTERESIS(val)     bfin_write16(MISCPORT_HYSTERESIS, val)
 
 /* HOST Port Registers */
 
diff --git a/arch/blackfin/mach-bf527/include/mach/defBF522.h b/arch/blackfin/mach-bf527/include/mach/defBF522.h
index 84ef11e52644..37d353a19722 100644
--- a/arch/blackfin/mach-bf527/include/mach/defBF522.h
+++ b/arch/blackfin/mach-bf527/include/mach/defBF522.h
@@ -562,12 +562,12 @@
 #define PORTF_SLEW              0xFFC03230      /* Port F slew control */
 #define PORTG_SLEW              0xFFC03234      /* Port G slew control */
 #define PORTH_SLEW              0xFFC03238      /* Port H slew control */
-#define PORTF_HYSTERISIS        0xFFC03240      /* Port F Schmitt trigger control */
-#define PORTG_HYSTERISIS        0xFFC03244      /* Port G Schmitt trigger control */
-#define PORTH_HYSTERISIS        0xFFC03248      /* Port H Schmitt trigger control */
+#define PORTF_HYSTERESIS        0xFFC03240      /* Port F Schmitt trigger control */
+#define PORTG_HYSTERESIS        0xFFC03244      /* Port G Schmitt trigger control */
+#define PORTH_HYSTERESIS        0xFFC03248      /* Port H Schmitt trigger control */
 #define MISCPORT_DRIVE          0xFFC03280      /* Misc Port drive strength control */
 #define MISCPORT_SLEW           0xFFC03284      /* Misc Port slew control */
-#define MISCPORT_HYSTERISIS     0xFFC03288      /* Misc Port Schmitt trigger control */
+#define MISCPORT_HYSTERESIS     0xFFC03288      /* Misc Port Schmitt trigger control */
 
 
 /***********************************************************************************
diff --git a/arch/blackfin/mach-bf527/include/mach/irq.h b/arch/blackfin/mach-bf527/include/mach/irq.h
index 704d9253e41d..ed7310ff819b 100644
--- a/arch/blackfin/mach-bf527/include/mach/irq.h
+++ b/arch/blackfin/mach-bf527/include/mach/irq.h
@@ -7,38 +7,9 @@
 #ifndef _BF527_IRQ_H_
 #define _BF527_IRQ_H_
 
-/*
- * Interrupt source definitions
-        Event Source    Core Event Name
-        Core        Emulation               **
-        Events         (highest priority)  EMU         0
-        Reset                   RST         1
-        NMI                     NMI         2
-        Exception               EVX         3
-        Reserved                --          4
-        Hardware Error          IVHW        5
-        Core Timer              IVTMR       6 *
-
-        .....
-
-         Software Interrupt 1    IVG14       31
-         Software Interrupt 2    --
-         (lowest priority)  IVG15       32 *
-*/
-
-#define NR_PERI_INTS    (2 * 32)
-
-/* The ABSTRACT IRQ definitions */
-/** the first seven of the following are fixed, the rest you change if you need to **/
-#define IRQ_EMU                 0       /* Emulation */
-#define IRQ_RST                 1       /* reset */
-#define IRQ_NMI                 2       /* Non Maskable */
-#define IRQ_EVX                 3       /* Exception */
-#define IRQ_UNUSED              4       /* - unused interrupt */
-#define IRQ_HWERR               5       /* Hardware Error */
-#define IRQ_CORETMR             6       /* Core timer */
-
-#define BFIN_IRQ(x)             ((x) + 7)
+#include <mach-common/irq.h>
+
+#define NR_PERI_INTS            (2 * 32)
 
 #define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
 #define IRQ_DMA0_ERROR          BFIN_IRQ(1)     /* DMA Error 0 (generic) */
@@ -53,21 +24,21 @@
 #define IRQ_UART0_ERROR         BFIN_IRQ(12)    /* UART0 Status */
 #define IRQ_UART1_ERROR         BFIN_IRQ(13)    /* UART1 Status */
 #define IRQ_RTC                 BFIN_IRQ(14)    /* RTC */
-#define IRQ_PPI                 BFIN_IRQ(15)    /* DMA Channel 0 (PPI/NAND) */
+#define IRQ_PPI                 BFIN_IRQ(15)    /* DMA Channel 0 (PPI/NAND) */
 #define IRQ_SPORT0_RX           BFIN_IRQ(16)    /* DMA 3 Channel (SPORT0 RX) */
 #define IRQ_SPORT0_TX           BFIN_IRQ(17)    /* DMA 4 Channel (SPORT0 TX) */
 #define IRQ_SPORT1_RX           BFIN_IRQ(18)    /* DMA 5 Channel (SPORT1 RX) */
 #define IRQ_SPORT1_TX           BFIN_IRQ(19)    /* DMA 6 Channel (SPORT1 TX) */
-#define IRQ_TWI                 BFIN_IRQ(20)    /* TWI */
-#define IRQ_SPI                 BFIN_IRQ(21)    /* DMA 7 Channel (SPI) */
-#define IRQ_UART0_RX            BFIN_IRQ(22)    /* DMA8 Channel (UART0 RX) */
-#define IRQ_UART0_TX            BFIN_IRQ(23)    /* DMA9 Channel (UART0 TX) */
-#define IRQ_UART1_RX            BFIN_IRQ(24)    /* DMA10 Channel (UART1 RX) */
-#define IRQ_UART1_TX            BFIN_IRQ(25)    /* DMA11 Channel (UART1 TX) */
-#define IRQ_OPTSEC              BFIN_IRQ(26)    /* OTPSEC Interrupt */
-#define IRQ_CNT                 BFIN_IRQ(27)    /* GP Counter */
-#define IRQ_MAC_RX              BFIN_IRQ(28)    /* DMA1 Channel (MAC RX/HDMA) */
-#define IRQ_PORTH_INTA          BFIN_IRQ(29)    /* Port H Interrupt A */
+#define IRQ_TWI                 BFIN_IRQ(20)    /* TWI */
+#define IRQ_SPI                 BFIN_IRQ(21)    /* DMA 7 Channel (SPI) */
+#define IRQ_UART0_RX            BFIN_IRQ(22)    /* DMA8 Channel (UART0 RX) */
+#define IRQ_UART0_TX            BFIN_IRQ(23)    /* DMA9 Channel (UART0 TX) */
+#define IRQ_UART1_RX            BFIN_IRQ(24)    /* DMA10 Channel (UART1 RX) */
+#define IRQ_UART1_TX            BFIN_IRQ(25)    /* DMA11 Channel (UART1 TX) */
+#define IRQ_OPTSEC              BFIN_IRQ(26)    /* OTPSEC Interrupt */
+#define IRQ_CNT                 BFIN_IRQ(27)    /* GP Counter */
+#define IRQ_MAC_RX              BFIN_IRQ(28)    /* DMA1 Channel (MAC RX/HDMA) */
+#define IRQ_PORTH_INTA          BFIN_IRQ(29)    /* Port H Interrupt A */
 #define IRQ_MAC_TX              BFIN_IRQ(30)    /* DMA2 Channel (MAC TX/NAND) */
 #define IRQ_NFC                 BFIN_IRQ(30)    /* DMA2 Channel (MAC TX/NAND) */
 #define IRQ_PORTH_INTB          BFIN_IRQ(31)    /* Port H Interrupt B */
@@ -96,119 +67,108 @@
 #define IRQ_USB_INT2            BFIN_IRQ(54)    /* USB_INT2 Interrupt */
 #define IRQ_USB_DMA             BFIN_IRQ(55)    /* USB_DMAINT Interrupt */
 
-#define SYS_IRQS                BFIN_IRQ(63)    /* 70 */
-
-#define IRQ_PF0         71
-#define IRQ_PF1         72
-#define IRQ_PF2         73
-#define IRQ_PF3         74
-#define IRQ_PF4         75
-#define IRQ_PF5         76
-#define IRQ_PF6         77
-#define IRQ_PF7         78
-#define IRQ_PF8         79
-#define IRQ_PF9         80
-#define IRQ_PF10        81
-#define IRQ_PF11        82
-#define IRQ_PF12        83
-#define IRQ_PF13        84
-#define IRQ_PF14        85
-#define IRQ_PF15        86
-
-#define IRQ_PG0         87
-#define IRQ_PG1         88
-#define IRQ_PG2         89
-#define IRQ_PG3         90
-#define IRQ_PG4         91
-#define IRQ_PG5         92
-#define IRQ_PG6         93
-#define IRQ_PG7         94
-#define IRQ_PG8         95
-#define IRQ_PG9         96
-#define IRQ_PG10        97
-#define IRQ_PG11        98
-#define IRQ_PG12        99
-#define IRQ_PG13        100
-#define IRQ_PG14        101
-#define IRQ_PG15        102
-
-#define IRQ_PH0         103
-#define IRQ_PH1         104
-#define IRQ_PH2         105
-#define IRQ_PH3         106
-#define IRQ_PH4         107
-#define IRQ_PH5         108
-#define IRQ_PH6         109
-#define IRQ_PH7         110
-#define IRQ_PH8         111
-#define IRQ_PH9         112
-#define IRQ_PH10        113
-#define IRQ_PH11        114
-#define IRQ_PH12        115
-#define IRQ_PH13        116
-#define IRQ_PH14        117
-#define IRQ_PH15        118
-
-#define GPIO_IRQ_BASE   IRQ_PF0
-
-#define IRQ_MAC_PHYINT          119 /* PHY_INT Interrupt */
-#define IRQ_MAC_MMCINT          120 /* MMC Counter Interrupt */
-#define IRQ_MAC_RXFSINT         121 /* RX Frame-Status Interrupt */
-#define IRQ_MAC_TXFSINT         122 /* TX Frame-Status Interrupt */
-#define IRQ_MAC_WAKEDET         123 /* Wake-Up Interrupt */
-#define IRQ_MAC_RXDMAERR        124 /* RX DMA Direction Error Interrupt */
-#define IRQ_MAC_TXDMAERR        125 /* TX DMA Direction Error Interrupt */
-#define IRQ_MAC_STMDONE         126 /* Station Mgt. Transfer Done Interrupt */
-
-#define NR_MACH_IRQS    (IRQ_MAC_STMDONE + 1)
-#define NR_IRQS         (NR_MACH_IRQS + NR_SPARE_IRQS)
-
-#define IVG7            7
-#define IVG8            8
-#define IVG9            9
-#define IVG10           10
-#define IVG11           11
-#define IVG12           12
-#define IVG13           13
-#define IVG14           14
-#define IVG15           15
+#define SYS_IRQS                BFIN_IRQ(63)    /* 70 */
+
+#define IRQ_PF0                 71
+#define IRQ_PF1                 72
+#define IRQ_PF2                 73
+#define IRQ_PF3                 74
+#define IRQ_PF4                 75
+#define IRQ_PF5                 76
+#define IRQ_PF6                 77
+#define IRQ_PF7                 78
+#define IRQ_PF8                 79
+#define IRQ_PF9                 80
+#define IRQ_PF10                81
+#define IRQ_PF11                82
+#define IRQ_PF12                83
+#define IRQ_PF13                84
+#define IRQ_PF14                85
+#define IRQ_PF15                86
+
+#define IRQ_PG0                 87
+#define IRQ_PG1                 88
+#define IRQ_PG2                 89
+#define IRQ_PG3                 90
+#define IRQ_PG4                 91
+#define IRQ_PG5                 92
+#define IRQ_PG6                 93
+#define IRQ_PG7                 94
+#define IRQ_PG8                 95
+#define IRQ_PG9                 96
+#define IRQ_PG10                97
+#define IRQ_PG11                98
+#define IRQ_PG12                99
+#define IRQ_PG13                100
+#define IRQ_PG14                101
+#define IRQ_PG15                102
+
+#define IRQ_PH0                 103
+#define IRQ_PH1                 104
+#define IRQ_PH2                 105
+#define IRQ_PH3                 106
+#define IRQ_PH4                 107
+#define IRQ_PH5                 108
+#define IRQ_PH6                 109
+#define IRQ_PH7                 110
+#define IRQ_PH8                 111
+#define IRQ_PH9                 112
+#define IRQ_PH10                113
+#define IRQ_PH11                114
+#define IRQ_PH12                115
+#define IRQ_PH13                116
+#define IRQ_PH14                117
+#define IRQ_PH15                118
+
+#define GPIO_IRQ_BASE           IRQ_PF0
+
+#define IRQ_MAC_PHYINT          119     /* PHY_INT Interrupt */
+#define IRQ_MAC_MMCINT          120     /* MMC Counter Interrupt */
+#define IRQ_MAC_RXFSINT         121     /* RX Frame-Status Interrupt */
+#define IRQ_MAC_TXFSINT         122     /* TX Frame-Status Interrupt */
+#define IRQ_MAC_WAKEDET         123     /* Wake-Up Interrupt */
+#define IRQ_MAC_RXDMAERR        124     /* RX DMA Direction Error Interrupt */
+#define IRQ_MAC_TXDMAERR        125     /* TX DMA Direction Error Interrupt */
+#define IRQ_MAC_STMDONE         126     /* Station Mgt. Transfer Done Interrupt */
+
+#define NR_MACH_IRQS            (IRQ_MAC_STMDONE + 1)
 
 /* IAR0 BIT FIELDS */
 #define IRQ_PLL_WAKEUP_POS      0
 #define IRQ_DMA0_ERROR_POS      4
-#define IRQ_DMAR0_BLK_POS       8
-#define IRQ_DMAR1_BLK_POS       12
-#define IRQ_DMAR0_OVR_POS       16
-#define IRQ_DMAR1_OVR_POS       20
-#define IRQ_PPI_ERROR_POS       24
-#define IRQ_MAC_ERROR_POS       28
+#define IRQ_DMAR0_BLK_POS       8
+#define IRQ_DMAR1_BLK_POS       12
+#define IRQ_DMAR0_OVR_POS       16
+#define IRQ_DMAR1_OVR_POS       20
+#define IRQ_PPI_ERROR_POS       24
+#define IRQ_MAC_ERROR_POS       28
 
 /* IAR1 BIT FIELDS */
 #define IRQ_SPORT0_ERROR_POS    0
 #define IRQ_SPORT1_ERROR_POS    4
-#define IRQ_UART0_ERROR_POS     16
-#define IRQ_UART1_ERROR_POS     20
-#define IRQ_RTC_POS             24
-#define IRQ_PPI_POS             28
+#define IRQ_UART0_ERROR_POS     16
+#define IRQ_UART1_ERROR_POS     20
+#define IRQ_RTC_POS             24
+#define IRQ_PPI_POS             28
 
 /* IAR2 BIT FIELDS */
 #define IRQ_SPORT0_RX_POS       0
 #define IRQ_SPORT0_TX_POS       4
 #define IRQ_SPORT1_RX_POS       8
 #define IRQ_SPORT1_TX_POS       12
-#define IRQ_TWI_POS             16
-#define IRQ_SPI_POS             20
-#define IRQ_UART0_RX_POS        24
-#define IRQ_UART0_TX_POS        28
+#define IRQ_TWI_POS             16
+#define IRQ_SPI_POS             20
+#define IRQ_UART0_RX_POS        24
+#define IRQ_UART0_TX_POS        28
 
 /* IAR3 BIT FIELDS */
-#define IRQ_UART1_RX_POS        0
-#define IRQ_UART1_TX_POS        4
-#define IRQ_OPTSEC_POS          8
-#define IRQ_CNT_POS             12
-#define IRQ_MAC_RX_POS          16
+#define IRQ_UART1_RX_POS        0
+#define IRQ_UART1_TX_POS        4
+#define IRQ_OPTSEC_POS          8
+#define IRQ_CNT_POS             12
+#define IRQ_MAC_RX_POS          16
 #define IRQ_PORTH_INTA_POS      20
-#define IRQ_MAC_TX_POS          24
+#define IRQ_MAC_TX_POS          24
 #define IRQ_PORTH_INTB_POS      28
 
 /* IAR4 BIT FIELDS */
@@ -224,21 +184,21 @@
 /* IAR5 BIT FIELDS */
 #define IRQ_PORTG_INTA_POS      0
 #define IRQ_PORTG_INTB_POS      4
-#define IRQ_MEM_DMA0_POS        8
-#define IRQ_MEM_DMA1_POS        12
-#define IRQ_WATCH_POS           16
+#define IRQ_MEM_DMA0_POS        8
+#define IRQ_MEM_DMA1_POS        12
+#define IRQ_WATCH_POS           16
 #define IRQ_PORTF_INTA_POS      20
 #define IRQ_PORTF_INTB_POS      24
-#define IRQ_SPI_ERROR_POS       28
+#define IRQ_SPI_ERROR_POS       28
 
 /* IAR6 BIT FIELDS */
-#define IRQ_NFC_ERROR_POS       0
-#define IRQ_HDMA_ERROR_POS      4
-#define IRQ_HDMA_POS            8
-#define IRQ_USB_EINT_POS        12
-#define IRQ_USB_INT0_POS        16
-#define IRQ_USB_INT1_POS        20
-#define IRQ_USB_INT2_POS        24
-#define IRQ_USB_DMA_POS         28
-
-#endif                          /* _BF527_IRQ_H_ */
+#define IRQ_NFC_ERROR_POS       0
+#define IRQ_HDMA_ERROR_POS      4
+#define IRQ_HDMA_POS            8
+#define IRQ_USB_EINT_POS        12
+#define IRQ_USB_INT0_POS        16
+#define IRQ_USB_INT1_POS        20
+#define IRQ_USB_INT2_POS        24
+#define IRQ_USB_DMA_POS         28
+
+#endif
diff --git a/arch/blackfin/mach-bf533/include/mach/anomaly.h b/arch/blackfin/mach-bf533/include/mach/anomaly.h
index 78f872187918..72aa59440f82 100644
--- a/arch/blackfin/mach-bf533/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf533/include/mach/anomaly.h
@@ -5,13 +5,13 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
 
 /* This file should be up to date with:
- *  - Revision E, 09/18/2008; ADSP-BF531/BF532/BF533 Blackfin Processor Anomaly List
+ *  - Revision F, 05/25/2010; ADSP-BF531/BF532/BF533 Blackfin Processor Anomaly List
  */
 
 #ifndef _MACH_ANOMALY_H_
@@ -206,6 +206,10 @@
 #define ANOMALY_05000443 (1)
 /* False Hardware Error when RETI Points to Invalid Memory */
 #define ANOMALY_05000461 (1)
+/* Synchronization Problem at Startup May Cause SPORT Transmit Channels to Misalign */
+#define ANOMALY_05000462 (1)
+/* Boot Failure When SDRAM Control Signals Toggle Coming Out Of Reset */
+#define ANOMALY_05000471 (1)
 /* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */
 #define ANOMALY_05000473 (1)
 /* Possible Lockup Condition whem Modifying PLL from External Memory */
@@ -351,12 +355,14 @@
 #define ANOMALY_05000362 (1)
 #define ANOMALY_05000364 (0)
 #define ANOMALY_05000380 (0)
+#define ANOMALY_05000383 (0)
 #define ANOMALY_05000386 (1)
 #define ANOMALY_05000389 (0)
 #define ANOMALY_05000412 (0)
 #define ANOMALY_05000430 (0)
 #define ANOMALY_05000432 (0)
 #define ANOMALY_05000435 (0)
+#define ANOMALY_05000440 (0)
 #define ANOMALY_05000447 (0)
 #define ANOMALY_05000448 (0)
 #define ANOMALY_05000456 (0)
@@ -364,6 +370,7 @@
 #define ANOMALY_05000465 (0)
 #define ANOMALY_05000467 (0)
 #define ANOMALY_05000474 (0)
+#define ANOMALY_05000480 (0)
 #define ANOMALY_05000485 (0)
 
 #endif
diff --git a/arch/blackfin/mach-bf533/include/mach/irq.h b/arch/blackfin/mach-bf533/include/mach/irq.h
index 1f7e9765d954..709733754142 100644
--- a/arch/blackfin/mach-bf533/include/mach/irq.h
+++ b/arch/blackfin/mach-bf533/include/mach/irq.h
@@ -7,83 +7,36 @@
 #ifndef _BF533_IRQ_H_
 #define _BF533_IRQ_H_
 
-/*
- * Interrupt source definitions
-             Event Source    Core Event Name
-Core        Emulation               **
- Events         (highest priority)  EMU         0
-            Reset                   RST         1
-            NMI                     NMI         2
-            Exception               EVX         3
-            Reserved                --          4
-            Hardware Error          IVHW        5
-            Core Timer              IVTMR       6 *
-            PLL Wakeup Interrupt    IVG7        7
-            DMA Error (generic)     IVG7        8
-            PPI Error Interrupt     IVG7        9
-            SPORT0 Error Interrupt  IVG7        10
-            SPORT1 Error Interrupt  IVG7        11
-            SPI Error Interrupt     IVG7        12
-            UART Error Interrupt    IVG7        13
-            RTC Interrupt           IVG8        14
-            DMA0 Interrupt (PPI)    IVG8        15
-            DMA1 (SPORT0 RX)        IVG9        16
-            DMA2 (SPORT0 TX)        IVG9        17
-            DMA3 (SPORT1 RX)        IVG9        18
-            DMA4 (SPORT1 TX)        IVG9        19
-            DMA5 (PPI)              IVG10       20
-            DMA6 (UART RX)          IVG10       21
-            DMA7 (UART TX)          IVG10       22
-            Timer0                  IVG11       23
-            Timer1                  IVG11       24
-            Timer2                  IVG11       25
-            PF Interrupt A          IVG12       26
-            PF Interrupt B          IVG12       27
-            DMA8/9 Interrupt        IVG13       28
-            DMA10/11 Interrupt      IVG13       29
-            Watchdog Timer          IVG13       30
+#include <mach-common/irq.h>
 
-            Softirq                 IVG14       31
-            System Call    --
-                 (lowest priority)  IVG15       32 *
- */
-#define SYS_IRQS        31
-#define NR_PERI_INTS    24
+#define NR_PERI_INTS            24
 
-/* The ABSTRACT IRQ definitions */
-/** the first seven of the following are fixed, the rest you change if you need to **/
-#define IRQ_EMU                 0       /*Emulation */
-#define IRQ_RST                 1       /*reset */
-#define IRQ_NMI                 2       /*Non Maskable */
-#define IRQ_EVX                 3       /*Exception */
-#define IRQ_UNUSED              4       /*- unused interrupt*/
-#define IRQ_HWERR               5       /*Hardware Error */
-#define IRQ_CORETMR             6       /*Core timer */
+#define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
+#define IRQ_DMA_ERROR           BFIN_IRQ(1)     /* DMA Error (general) */
+#define IRQ_PPI_ERROR           BFIN_IRQ(2)     /* PPI Error Interrupt */
+#define IRQ_SPORT0_ERROR        BFIN_IRQ(3)     /* SPORT0 Error Interrupt */
+#define IRQ_SPORT1_ERROR        BFIN_IRQ(4)     /* SPORT1 Error Interrupt */
+#define IRQ_SPI_ERROR           BFIN_IRQ(5)     /* SPI Error Interrupt */
+#define IRQ_UART0_ERROR         BFIN_IRQ(6)     /* UART Error Interrupt */
+#define IRQ_RTC                 BFIN_IRQ(7)     /* RTC Interrupt */
+#define IRQ_PPI                 BFIN_IRQ(8)     /* DMA0 Interrupt (PPI) */
+#define IRQ_SPORT0_RX           BFIN_IRQ(9)     /* DMA1 Interrupt (SPORT0 RX) */
+#define IRQ_SPORT0_TX           BFIN_IRQ(10)    /* DMA2 Interrupt (SPORT0 TX) */
+#define IRQ_SPORT1_RX           BFIN_IRQ(11)    /* DMA3 Interrupt (SPORT1 RX) */
+#define IRQ_SPORT1_TX           BFIN_IRQ(12)    /* DMA4 Interrupt (SPORT1 TX) */
+#define IRQ_SPI                 BFIN_IRQ(13)    /* DMA5 Interrupt (SPI) */
+#define IRQ_UART0_RX            BFIN_IRQ(14)    /* DMA6 Interrupt (UART RX) */
+#define IRQ_UART0_TX            BFIN_IRQ(15)    /* DMA7 Interrupt (UART TX) */
+#define IRQ_TIMER0              BFIN_IRQ(16)    /* Timer 0 */
+#define IRQ_TIMER1              BFIN_IRQ(17)    /* Timer 1 */
+#define IRQ_TIMER2              BFIN_IRQ(18)    /* Timer 2 */
+#define IRQ_PROG_INTA           BFIN_IRQ(19)    /* Programmable Flags A (8) */
+#define IRQ_PROG_INTB           BFIN_IRQ(20)    /* Programmable Flags B (8) */
+#define IRQ_MEM_DMA0            BFIN_IRQ(21)    /* DMA8/9 Interrupt (Memory DMA Stream 0) */
+#define IRQ_MEM_DMA1            BFIN_IRQ(22)    /* DMA10/11 Interrupt (Memory DMA Stream 1) */
+#define IRQ_WATCH               BFIN_IRQ(23)    /* Watch Dog Timer */
 
-#define IRQ_PLL_WAKEUP          7       /*PLL Wakeup Interrupt */
-#define IRQ_DMA_ERROR           8       /*DMA Error (general) */
-#define IRQ_PPI_ERROR           9       /*PPI Error Interrupt */
-#define IRQ_SPORT0_ERROR        10      /*SPORT0 Error Interrupt */
-#define IRQ_SPORT1_ERROR        11      /*SPORT1 Error Interrupt */
-#define IRQ_SPI_ERROR           12      /*SPI Error Interrupt */
-#define IRQ_UART0_ERROR         13      /*UART Error Interrupt */
-#define IRQ_RTC                 14      /*RTC Interrupt */
-#define IRQ_PPI                 15      /*DMA0 Interrupt (PPI) */
-#define IRQ_SPORT0_RX           16      /*DMA1 Interrupt (SPORT0 RX) */
-#define IRQ_SPORT0_TX           17      /*DMA2 Interrupt (SPORT0 TX) */
-#define IRQ_SPORT1_RX           18      /*DMA3 Interrupt (SPORT1 RX) */
-#define IRQ_SPORT1_TX           19      /*DMA4 Interrupt (SPORT1 TX) */
-#define IRQ_SPI                 20      /*DMA5 Interrupt (SPI) */
-#define IRQ_UART0_RX            21      /*DMA6 Interrupt (UART RX) */
-#define IRQ_UART0_TX            22      /*DMA7 Interrupt (UART TX) */
-#define IRQ_TIMER0              23      /*Timer 0 */
-#define IRQ_TIMER1              24      /*Timer 1 */
-#define IRQ_TIMER2              25      /*Timer 2 */
-#define IRQ_PROG_INTA           26      /*Programmable Flags A (8) */
-#define IRQ_PROG_INTB           27      /*Programmable Flags B (8) */
-#define IRQ_MEM_DMA0            28      /*DMA8/9 Interrupt (Memory DMA Stream 0) */
-#define IRQ_MEM_DMA1            29      /*DMA10/11 Interrupt (Memory DMA Stream 1) */
-#define IRQ_WATCH               30      /*Watch Dog Timer */
+#define SYS_IRQS                31
 
 #define IRQ_PF0                 33
 #define IRQ_PF1                 34
@@ -105,46 +58,35 @@ Core        Emulation               **
 #define GPIO_IRQ_BASE           IRQ_PF0
 
 #define NR_MACH_IRQS            (IRQ_PF15 + 1)
-#define NR_IRQS                 (NR_MACH_IRQS + NR_SPARE_IRQS)
-
-#define IVG7                    7
-#define IVG8                    8
-#define IVG9                    9
-#define IVG10                   10
-#define IVG11                   11
-#define IVG12                   12
-#define IVG13                   13
-#define IVG14                   14
-#define IVG15                   15
 
-/* IAR0 BIT FIELDS*/
-#define RTC_ERROR_POS                   28
-#define UART_ERROR_POS                  24
-#define SPORT1_ERROR_POS                20
-#define SPI_ERROR_POS                   16
-#define SPORT0_ERROR_POS                12
-#define PPI_ERROR_POS                   8
-#define DMA_ERROR_POS                   4
-#define PLLWAKE_ERROR_POS               0
+/* IAR0 BIT FIELDS */
+#define RTC_ERROR_POS           28
+#define UART_ERROR_POS          24
+#define SPORT1_ERROR_POS        20
+#define SPI_ERROR_POS           16
+#define SPORT0_ERROR_POS        12
+#define PPI_ERROR_POS           8
+#define DMA_ERROR_POS           4
+#define PLLWAKE_ERROR_POS       0
 
-/* IAR1 BIT FIELDS*/
-#define DMA7_UARTTX_POS                 28
-#define DMA6_UARTRX_POS                 24
-#define DMA5_SPI_POS                    20
-#define DMA4_SPORT1TX_POS               16
-#define DMA3_SPORT1RX_POS               12
-#define DMA2_SPORT0TX_POS               8
-#define DMA1_SPORT0RX_POS               4
-#define DMA0_PPI_POS                    0
+/* IAR1 BIT FIELDS */
+#define DMA7_UARTTX_POS         28
+#define DMA6_UARTRX_POS         24
+#define DMA5_SPI_POS            20
+#define DMA4_SPORT1TX_POS       16
+#define DMA3_SPORT1RX_POS       12
+#define DMA2_SPORT0TX_POS       8
+#define DMA1_SPORT0RX_POS       4
+#define DMA0_PPI_POS            0
 
-/* IAR2 BIT FIELDS*/
-#define WDTIMER_POS                     28
-#define MEMDMA1_POS                     24
-#define MEMDMA0_POS                     20
-#define PFB_POS                         16
-#define PFA_POS                         12
-#define TIMER2_POS                      8
-#define TIMER1_POS                      4
-#define TIMER0_POS                      0
+/* IAR2 BIT FIELDS */
+#define WDTIMER_POS             28
+#define MEMDMA1_POS             24
+#define MEMDMA0_POS             20
+#define PFB_POS                 16
+#define PFA_POS                 12
+#define TIMER2_POS              8
+#define TIMER1_POS              4
+#define TIMER0_POS              0
 
-#endif                          /* _BF533_IRQ_H_ */
+#endif
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index 3fa335405b31..e16dc4560048 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -35,6 +35,7 @@
 #include <asm/reboot.h>
 #include <asm/portmux.h>
 #include <asm/dpmc.h>
+#include <asm/bfin_sport.h>
 #ifdef CONFIG_REGULATOR_FIXED_VOLTAGE
 #include <linux/regulator/fixed.h>
 #endif
@@ -2585,27 +2586,103 @@ static struct platform_device bfin_dpmc = {
         },
 };
 
-#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE)
+#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) || \
+        defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE) || \
+        defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+
+#define SPORT_REQ(x) \
+        [x] = {P_SPORT##x##_TFS, P_SPORT##x##_DTPRI, P_SPORT##x##_TSCLK, \
+                P_SPORT##x##_RFS, P_SPORT##x##_DRPRI, P_SPORT##x##_RSCLK, 0}
+
+static const u16 bfin_snd_pin[][7] = {
+        SPORT_REQ(0),
+        SPORT_REQ(1),
+};
+
+static struct bfin_snd_platform_data bfin_snd_data[] = {
+        {
+                .pin_req = &bfin_snd_pin[0][0],
+        },
+        {
+                .pin_req = &bfin_snd_pin[1][0],
+        },
+};
+
+#define BFIN_SND_RES(x) \
+        [x] = { \
+                { \
+                        .start = SPORT##x##_TCR1, \
+                        .end = SPORT##x##_TCR1, \
+                        .flags = IORESOURCE_MEM \
+                }, \
+                { \
+                        .start = CH_SPORT##x##_RX, \
+                        .end = CH_SPORT##x##_RX, \
+                        .flags = IORESOURCE_DMA, \
+                }, \
+                { \
+                        .start = CH_SPORT##x##_TX, \
+                        .end = CH_SPORT##x##_TX, \
+                        .flags = IORESOURCE_DMA, \
+                }, \
+                { \
+                        .start = IRQ_SPORT##x##_ERROR, \
+                        .end = IRQ_SPORT##x##_ERROR, \
+                        .flags = IORESOURCE_IRQ, \
+                } \
+        }
+
+static struct resource bfin_snd_resources[][4] = {
+        BFIN_SND_RES(0),
+        BFIN_SND_RES(1),
+};
+
+static struct platform_device bfin_pcm = {
+        .name = "bfin-pcm-audio",
+        .id = -1,
+};
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_AD73311) || defined(CONFIG_SND_BF5XX_SOC_AD73311_MODULE)
+static struct platform_device bfin_ad73311_codec_device = {
+        .name = "ad73311",
+        .id = -1,
+};
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_I2S) || defined(CONFIG_SND_BF5XX_SOC_I2S_MODULE)
 static struct platform_device bfin_i2s = {
         .name = "bfin-i2s",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
-#if defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE)
+#if defined(CONFIG_SND_BF5XX_SOC_TDM) || defined(CONFIG_SND_BF5XX_SOC_TDM_MODULE)
 static struct platform_device bfin_tdm = {
         .name = "bfin-tdm",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
-#if defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+#if defined(CONFIG_SND_BF5XX_SOC_AC97) || defined(CONFIG_SND_BF5XX_SOC_AC97_MODULE)
 static struct platform_device bfin_ac97 = {
         .name = "bfin-ac97",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
@@ -2796,17 +2873,28 @@ static struct platform_device *stamp_devices[] __initdata = {
         &stamp_flash_device,
 #endif
 
-#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE)
+#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) || \
+        defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE) || \
+        defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+        &bfin_pcm,
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_AD73311) || defined(CONFIG_SND_BF5XX_SOC_AD73311_MODULE)
+        &bfin_ad73311_codec_device,
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_I2S) || defined(CONFIG_SND_BF5XX_SOC_I2S_MODULE)
         &bfin_i2s,
 #endif
 
-#if defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE)
+#if defined(CONFIG_SND_BF5XX_SOC_TDM) || defined(CONFIG_SND_BF5XX_SOC_TDM_MODULE)
         &bfin_tdm,
 #endif
 
-#if defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+#if defined(CONFIG_SND_BF5XX_SOC_AC97) || defined(CONFIG_SND_BF5XX_SOC_AC97_MODULE)
         &bfin_ac97,
 #endif
+
 #if defined(CONFIG_REGULATOR_AD5398) || defined(CONFIG_REGULATOR_AD5398_MODULE)
 #if defined(CONFIG_REGULATOR_VIRTUAL_CONSUMER) || \
         defined(CONFIG_REGULATOR_VIRTUAL_CONSUMER_MODULE)
diff --git a/arch/blackfin/mach-bf537/include/mach/anomaly.h b/arch/blackfin/mach-bf537/include/mach/anomaly.h
index 43df6afd22ad..7f8e5a9f5db6 100644
--- a/arch/blackfin/mach-bf537/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf537/include/mach/anomaly.h
@@ -5,13 +5,13 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
 
 /* This file should be up to date with:
- *  - Revision D, 09/18/2008; ADSP-BF534/ADSP-BF536/ADSP-BF537 Blackfin Processor Anomaly List
+ *  - Revision E, 05/25/2010; ADSP-BF534/ADSP-BF536/ADSP-BF537 Blackfin Processor Anomaly List
  */
 
 #ifndef _MACH_ANOMALY_H_
@@ -160,12 +160,16 @@
 #define ANOMALY_05000443 (1)
 /* False Hardware Error when RETI Points to Invalid Memory */
 #define ANOMALY_05000461 (1)
+/* Synchronization Problem at Startup May Cause SPORT Transmit Channels to Misalign */
+#define ANOMALY_05000462 (1)
 /* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */
 #define ANOMALY_05000473 (1)
 /* Possible Lockup Condition whem Modifying PLL from External Memory */
 #define ANOMALY_05000475 (1)
 /* TESTSET Instruction Cannot Be Interrupted */
 #define ANOMALY_05000477 (1)
+/* Multiple Simultaneous Urgent DMA Requests May Cause DMA System Instability */
+#define ANOMALY_05000480 (__SILICON_REVISION__ < 3)
 /* Reads of ITEST_COMMAND and ITEST_DATA Registers Cause Cache Corruption */
 #define ANOMALY_05000481 (1)
 /* IFLUSH sucks at life */
@@ -204,6 +208,7 @@
 #define ANOMALY_05000363 (0)
 #define ANOMALY_05000364 (0)
 #define ANOMALY_05000380 (0)
+#define ANOMALY_05000383 (0)
 #define ANOMALY_05000386 (1)
 #define ANOMALY_05000389 (0)
 #define ANOMALY_05000400 (0)
@@ -211,6 +216,7 @@
 #define ANOMALY_05000430 (0)
 #define ANOMALY_05000432 (0)
 #define ANOMALY_05000435 (0)
+#define ANOMALY_05000440 (0)
 #define ANOMALY_05000447 (0)
 #define ANOMALY_05000448 (0)
 #define ANOMALY_05000456 (0)
diff --git a/arch/blackfin/mach-bf537/include/mach/irq.h b/arch/blackfin/mach-bf537/include/mach/irq.h
index 1a6d617c5fcf..b6ed8235bda4 100644
--- a/arch/blackfin/mach-bf537/include/mach/irq.h
+++ b/arch/blackfin/mach-bf537/include/mach/irq.h
@@ -7,193 +7,178 @@
 #ifndef _BF537_IRQ_H_
 #define _BF537_IRQ_H_
 
-/*
- * Interrupt source definitions
- *            Event Source    Core Event Name
- * Core       Emulation               **
- * Events         (highest priority)  EMU         0
- *            Reset                   RST         1
- *            NMI                     NMI         2
- *            Exception               EVX         3
- *            Reserved                --          4
- *            Hardware Error          IVHW        5
- *            Core Timer              IVTMR       6
- *  .....
- *
- *            Softirq                 IVG14
- *            System Call    --
- *               (lowest priority)    IVG15
- */
-
-#define SYS_IRQS        39
-#define NR_PERI_INTS    32
-
-/* The ABSTRACT IRQ definitions */
-/** the first seven of the following are fixed, the rest you change if you need to **/
-#define IRQ_EMU             0   /*Emulation */
-#define IRQ_RST             1   /*reset */
-#define IRQ_NMI             2   /*Non Maskable */
-#define IRQ_EVX             3   /*Exception */
-#define IRQ_UNUSED          4   /*- unused interrupt*/
-#define IRQ_HWERR           5   /*Hardware Error */
-#define IRQ_CORETMR         6   /*Core timer */
-
-#define IRQ_PLL_WAKEUP      7   /*PLL Wakeup Interrupt */
-#define IRQ_DMA_ERROR       8   /*DMA Error (general) */
-#define IRQ_GENERIC_ERROR   9   /*GENERIC Error Interrupt */
-#define IRQ_RTC             10  /*RTC Interrupt */
-#define IRQ_PPI             11  /*DMA0 Interrupt (PPI) */
-#define IRQ_SPORT0_RX       12  /*DMA3 Interrupt (SPORT0 RX) */
-#define IRQ_SPORT0_TX       13  /*DMA4 Interrupt (SPORT0 TX) */
-#define IRQ_SPORT1_RX       14  /*DMA5 Interrupt (SPORT1 RX) */
-#define IRQ_SPORT1_TX       15  /*DMA6 Interrupt (SPORT1 TX) */
-#define IRQ_TWI             16  /*TWI Interrupt */
-#define IRQ_SPI             17  /*DMA7 Interrupt (SPI) */
-#define IRQ_UART0_RX        18  /*DMA8 Interrupt (UART0 RX) */
-#define IRQ_UART0_TX        19  /*DMA9 Interrupt (UART0 TX) */
-#define IRQ_UART1_RX        20  /*DMA10 Interrupt (UART1 RX) */
-#define IRQ_UART1_TX        21  /*DMA11 Interrupt (UART1 TX) */
-#define IRQ_CAN_RX          22  /*CAN Receive Interrupt */
-#define IRQ_CAN_TX          23  /*CAN Transmit Interrupt */
-#define IRQ_MAC_RX          24  /*DMA1 (Ethernet RX) Interrupt */
-#define IRQ_MAC_TX          25  /*DMA2 (Ethernet TX) Interrupt */
-#define IRQ_TIMER0            26        /*Timer 0 */
-#define IRQ_TIMER1            27        /*Timer 1 */
-#define IRQ_TIMER2            28        /*Timer 2 */
-#define IRQ_TIMER3            29        /*Timer 3 */
-#define IRQ_TIMER4            30        /*Timer 4 */
-#define IRQ_TIMER5            31        /*Timer 5 */
-#define IRQ_TIMER6            32        /*Timer 6 */
-#define IRQ_TIMER7            33        /*Timer 7 */
-#define IRQ_PROG_INTA       34  /* PF Ports F&G (PF15:0) Interrupt A */
-#define IRQ_PORTG_INTB      35  /* PF Port G (PF15:0) Interrupt B */
-#define IRQ_MEM_DMA0        36  /*(Memory DMA Stream 0) */
-#define IRQ_MEM_DMA1        37  /*(Memory DMA Stream 1) */
-#define IRQ_PROG_INTB         38        /* PF Ports F (PF15:0) Interrupt B */
-#define IRQ_WATCH           38  /*Watch Dog Timer */
-
-#define IRQ_PPI_ERROR       42  /*PPI Error Interrupt */
-#define IRQ_CAN_ERROR       43  /*CAN Error Interrupt */
-#define IRQ_MAC_ERROR       44  /*MAC Status/Error Interrupt */
-#define IRQ_SPORT0_ERROR    45  /*SPORT0 Error Interrupt */
-#define IRQ_SPORT1_ERROR    46  /*SPORT1 Error Interrupt */
-#define IRQ_SPI_ERROR       47  /*SPI Error Interrupt */
-#define IRQ_UART0_ERROR     48  /*UART Error Interrupt */
-#define IRQ_UART1_ERROR     49  /*UART Error Interrupt */
-
-#define IRQ_PF0         50
-#define IRQ_PF1         51
-#define IRQ_PF2         52
-#define IRQ_PF3         53
-#define IRQ_PF4         54
-#define IRQ_PF5         55
-#define IRQ_PF6         56
-#define IRQ_PF7         57
-#define IRQ_PF8         58
-#define IRQ_PF9         59
-#define IRQ_PF10        60
-#define IRQ_PF11        61
-#define IRQ_PF12        62
-#define IRQ_PF13        63
-#define IRQ_PF14        64
-#define IRQ_PF15        65
-
-#define IRQ_PG0         66
-#define IRQ_PG1         67
-#define IRQ_PG2         68
-#define IRQ_PG3         69
-#define IRQ_PG4         70
-#define IRQ_PG5         71
-#define IRQ_PG6         72
-#define IRQ_PG7         73
-#define IRQ_PG8         74
-#define IRQ_PG9         75
-#define IRQ_PG10        76
-#define IRQ_PG11        77
-#define IRQ_PG12        78
-#define IRQ_PG13        79
-#define IRQ_PG14        80
-#define IRQ_PG15        81
-
-#define IRQ_PH0         82
-#define IRQ_PH1         83
-#define IRQ_PH2         84
-#define IRQ_PH3         85
-#define IRQ_PH4         86
-#define IRQ_PH5         87
-#define IRQ_PH6         88
-#define IRQ_PH7         89
-#define IRQ_PH8         90
-#define IRQ_PH9         91
-#define IRQ_PH10        92
-#define IRQ_PH11        93
-#define IRQ_PH12        94
-#define IRQ_PH13        95
-#define IRQ_PH14        96
-#define IRQ_PH15        97
-
-#define GPIO_IRQ_BASE   IRQ_PF0
-
-#define IRQ_MAC_PHYINT          98 /* PHY_INT Interrupt */
-#define IRQ_MAC_MMCINT          99 /* MMC Counter Interrupt */
-#define IRQ_MAC_RXFSINT         100 /* RX Frame-Status Interrupt */
-#define IRQ_MAC_TXFSINT         101 /* TX Frame-Status Interrupt */
-#define IRQ_MAC_WAKEDET         102 /* Wake-Up Interrupt */
-#define IRQ_MAC_RXDMAERR        103 /* RX DMA Direction Error Interrupt */
-#define IRQ_MAC_TXDMAERR        104 /* TX DMA Direction Error Interrupt */
-#define IRQ_MAC_STMDONE         105 /* Station Mgt. Transfer Done Interrupt */
-
-#define NR_MACH_IRQS    (IRQ_MAC_STMDONE + 1)
-#define NR_IRQS         (NR_MACH_IRQS + NR_SPARE_IRQS)
-
-#define IVG7            7
-#define IVG8            8
-#define IVG9            9
-#define IVG10           10
-#define IVG11           11
-#define IVG12           12
-#define IVG13           13
-#define IVG14           14
-#define IVG15           15
-
-/* IAR0 BIT FIELDS*/
-#define IRQ_PLL_WAKEUP_POS  0
-#define IRQ_DMA_ERROR_POS   4
-#define IRQ_ERROR_POS       8
-#define IRQ_RTC_POS         12
-#define IRQ_PPI_POS         16
-#define IRQ_SPORT0_RX_POS   20
-#define IRQ_SPORT0_TX_POS   24
-#define IRQ_SPORT1_RX_POS   28
-
-/* IAR1 BIT FIELDS*/
-#define IRQ_SPORT1_TX_POS   0
-#define IRQ_TWI_POS         4
-#define IRQ_SPI_POS         8
-#define IRQ_UART0_RX_POS    12
-#define IRQ_UART0_TX_POS    16
-#define IRQ_UART1_RX_POS    20
-#define IRQ_UART1_TX_POS    24
-#define IRQ_CAN_RX_POS      28
-
-/* IAR2 BIT FIELDS*/
-#define IRQ_CAN_TX_POS      0
-#define IRQ_MAC_RX_POS      4
-#define IRQ_MAC_TX_POS      8
-#define IRQ_TIMER0_POS        12
-#define IRQ_TIMER1_POS        16
-#define IRQ_TIMER2_POS        20
-#define IRQ_TIMER3_POS        24
-#define IRQ_TIMER4_POS        28
-
-/* IAR3 BIT FIELDS*/
-#define IRQ_TIMER5_POS        0
-#define IRQ_TIMER6_POS        4
-#define IRQ_TIMER7_POS        8
-#define IRQ_PROG_INTA_POS   12
-#define IRQ_PORTG_INTB_POS   16
-#define IRQ_MEM_DMA0_POS    20
-#define IRQ_MEM_DMA1_POS    24
-#define IRQ_WATCH_POS       28
-
-#endif                          /* _BF537_IRQ_H_ */
+#include <mach-common/irq.h>
+
+#define NR_PERI_INTS            32
+
+#define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
+#define IRQ_DMA_ERROR           BFIN_IRQ(1)     /* DMA Error (general) */
+#define IRQ_GENERIC_ERROR       BFIN_IRQ(2)     /* GENERIC Error Interrupt */
+#define IRQ_RTC                 BFIN_IRQ(3)     /* RTC Interrupt */
+#define IRQ_PPI                 BFIN_IRQ(4)     /* DMA0 Interrupt (PPI) */
+#define IRQ_SPORT0_RX           BFIN_IRQ(5)     /* DMA3 Interrupt (SPORT0 RX) */
+#define IRQ_SPORT0_TX           BFIN_IRQ(6)     /* DMA4 Interrupt (SPORT0 TX) */
+#define IRQ_SPORT1_RX           BFIN_IRQ(7)     /* DMA5 Interrupt (SPORT1 RX) */
+#define IRQ_SPORT1_TX           BFIN_IRQ(8)     /* DMA6 Interrupt (SPORT1 TX) */
+#define IRQ_TWI                 BFIN_IRQ(9)     /* TWI Interrupt */
+#define IRQ_SPI                 BFIN_IRQ(10)    /* DMA7 Interrupt (SPI) */
+#define IRQ_UART0_RX            BFIN_IRQ(11)    /* DMA8 Interrupt (UART0 RX) */
+#define IRQ_UART0_TX            BFIN_IRQ(12)    /* DMA9 Interrupt (UART0 TX) */
+#define IRQ_UART1_RX            BFIN_IRQ(13)    /* DMA10 Interrupt (UART1 RX) */
+#define IRQ_UART1_TX            BFIN_IRQ(14)    /* DMA11 Interrupt (UART1 TX) */
+#define IRQ_CAN_RX              BFIN_IRQ(15)    /* CAN Receive Interrupt */
+#define IRQ_CAN_TX              BFIN_IRQ(16)    /* CAN Transmit Interrupt */
+#define IRQ_PH_INTA_MAC_RX      BFIN_IRQ(17)    /* Port H Interrupt A & DMA1 Interrupt (Ethernet RX) */
+#define IRQ_PH_INTB_MAC_TX      BFIN_IRQ(18)    /* Port H Interrupt B & DMA2 Interrupt (Ethernet TX) */
+#define IRQ_TIMER0              BFIN_IRQ(19)    /* Timer 0 */
+#define IRQ_TIMER1              BFIN_IRQ(20)    /* Timer 1 */
+#define IRQ_TIMER2              BFIN_IRQ(21)    /* Timer 2 */
+#define IRQ_TIMER3              BFIN_IRQ(22)    /* Timer 3 */
+#define IRQ_TIMER4              BFIN_IRQ(23)    /* Timer 4 */
+#define IRQ_TIMER5              BFIN_IRQ(24)    /* Timer 5 */
+#define IRQ_TIMER6              BFIN_IRQ(25)    /* Timer 6 */
+#define IRQ_TIMER7              BFIN_IRQ(26)    /* Timer 7 */
+#define IRQ_PF_INTA_PG_INTA     BFIN_IRQ(27)    /* Ports F&G Interrupt A */
+#define IRQ_PORTG_INTB          BFIN_IRQ(28)    /* Port G Interrupt B */
+#define IRQ_MEM_DMA0            BFIN_IRQ(29)    /* (Memory DMA Stream 0) */
+#define IRQ_MEM_DMA1            BFIN_IRQ(30)    /* (Memory DMA Stream 1) */
+#define IRQ_PF_INTB_WATCH       BFIN_IRQ(31)    /* Watchdog & Port F Interrupt B */
+
+#define SYS_IRQS                39
+
+#define IRQ_PPI_ERROR           42      /* PPI Error Interrupt */
+#define IRQ_CAN_ERROR           43      /* CAN Error Interrupt */
+#define IRQ_MAC_ERROR           44      /* MAC Status/Error Interrupt */
+#define IRQ_SPORT0_ERROR        45      /* SPORT0 Error Interrupt */
+#define IRQ_SPORT1_ERROR        46      /* SPORT1 Error Interrupt */
+#define IRQ_SPI_ERROR           47      /* SPI Error Interrupt */
+#define IRQ_UART0_ERROR         48      /* UART Error Interrupt */
+#define IRQ_UART1_ERROR         49      /* UART Error Interrupt */
+
+#define IRQ_PF0                 50
+#define IRQ_PF1                 51
+#define IRQ_PF2                 52
+#define IRQ_PF3                 53
+#define IRQ_PF4                 54
+#define IRQ_PF5                 55
+#define IRQ_PF6                 56
+#define IRQ_PF7                 57
+#define IRQ_PF8                 58
+#define IRQ_PF9                 59
+#define IRQ_PF10                60
+#define IRQ_PF11                61
+#define IRQ_PF12                62
+#define IRQ_PF13                63
+#define IRQ_PF14                64
+#define IRQ_PF15                65
+
+#define IRQ_PG0                 66
+#define IRQ_PG1                 67
+#define IRQ_PG2                 68
+#define IRQ_PG3                 69
+#define IRQ_PG4                 70
+#define IRQ_PG5                 71
+#define IRQ_PG6                 72
+#define IRQ_PG7                 73
+#define IRQ_PG8                 74
+#define IRQ_PG9                 75
+#define IRQ_PG10                76
+#define IRQ_PG11                77
+#define IRQ_PG12                78
+#define IRQ_PG13                79
+#define IRQ_PG14                80
+#define IRQ_PG15                81
+
+#define IRQ_PH0                 82
+#define IRQ_PH1                 83
+#define IRQ_PH2                 84
+#define IRQ_PH3                 85
+#define IRQ_PH4                 86
+#define IRQ_PH5                 87
+#define IRQ_PH6                 88
+#define IRQ_PH7                 89
+#define IRQ_PH8                 90
+#define IRQ_PH9                 91
+#define IRQ_PH10                92
+#define IRQ_PH11                93
+#define IRQ_PH12                94
+#define IRQ_PH13                95
+#define IRQ_PH14                96
+#define IRQ_PH15                97
+
+#define GPIO_IRQ_BASE           IRQ_PF0
+
+#define IRQ_MAC_PHYINT          98      /* PHY_INT Interrupt */
+#define IRQ_MAC_MMCINT          99      /* MMC Counter Interrupt */
+#define IRQ_MAC_RXFSINT         100     /* RX Frame-Status Interrupt */
+#define IRQ_MAC_TXFSINT         101     /* TX Frame-Status Interrupt */
+#define IRQ_MAC_WAKEDET         102     /* Wake-Up Interrupt */
+#define IRQ_MAC_RXDMAERR        103     /* RX DMA Direction Error Interrupt */
+#define IRQ_MAC_TXDMAERR        104     /* TX DMA Direction Error Interrupt */
+#define IRQ_MAC_STMDONE         105     /* Station Mgt. Transfer Done Interrupt */
+
+#define IRQ_MAC_RX              106     /* DMA1 Interrupt (Ethernet RX) */
+#define IRQ_PORTH_INTA          107     /* Port H Interrupt A */
+
+#if 0 /* No Interrupt B support (yet) */
+#define IRQ_MAC_TX              108     /* DMA2 Interrupt (Ethernet TX) */
+#define IRQ_PORTH_INTB          109     /* Port H Interrupt B */
+#else
+#define IRQ_MAC_TX              IRQ_PH_INTB_MAC_TX
+#endif
+
+#define IRQ_PORTF_INTA          110     /* Port F Interrupt A */
+#define IRQ_PORTG_INTA          111     /* Port G Interrupt A */
+
+#if 0 /* No Interrupt B support (yet) */
+#define IRQ_WATCH               112     /* Watchdog Timer */
+#define IRQ_PORTF_INTB          113     /* Port F Interrupt B */
+#else
+#define IRQ_WATCH               IRQ_PF_INTB_WATCH
+#endif
+
+#define NR_MACH_IRQS            (113 + 1)
+
+/* IAR0 BIT FIELDS */
+#define IRQ_PLL_WAKEUP_POS      0
+#define IRQ_DMA_ERROR_POS       4
+#define IRQ_ERROR_POS           8
+#define IRQ_RTC_POS             12
+#define IRQ_PPI_POS             16
+#define IRQ_SPORT0_RX_POS       20
+#define IRQ_SPORT0_TX_POS       24
+#define IRQ_SPORT1_RX_POS       28
+
+/* IAR1 BIT FIELDS */
+#define IRQ_SPORT1_TX_POS       0
+#define IRQ_TWI_POS             4
+#define IRQ_SPI_POS             8
+#define IRQ_UART0_RX_POS        12
+#define IRQ_UART0_TX_POS        16
+#define IRQ_UART1_RX_POS        20
+#define IRQ_UART1_TX_POS        24
+#define IRQ_CAN_RX_POS          28
+
+/* IAR2 BIT FIELDS */
+#define IRQ_CAN_TX_POS          0
+#define IRQ_MAC_RX_POS          4
+#define IRQ_MAC_TX_POS          8
+#define IRQ_TIMER0_POS          12
+#define IRQ_TIMER1_POS          16
+#define IRQ_TIMER2_POS          20
+#define IRQ_TIMER3_POS          24
+#define IRQ_TIMER4_POS          28
+
+/* IAR3 BIT FIELDS */
+#define IRQ_TIMER5_POS          0
+#define IRQ_TIMER6_POS          4
+#define IRQ_TIMER7_POS          8
+#define IRQ_PROG_INTA_POS       12
+#define IRQ_PORTG_INTB_POS      16
+#define IRQ_MEM_DMA0_POS        20
+#define IRQ_MEM_DMA1_POS        24
+#define IRQ_WATCH_POS           28
+
+#define init_mach_irq init_mach_irq
+
+#endif
diff --git a/arch/blackfin/mach-bf537/ints-priority.c b/arch/blackfin/mach-bf537/ints-priority.c
index f6500622b35d..2137a209a22b 100644
--- a/arch/blackfin/mach-bf537/ints-priority.c
+++ b/arch/blackfin/mach-bf537/ints-priority.c
@@ -10,6 +10,13 @@
 #include <linux/irq.h>
 #include <asm/blackfin.h>
 
+#include <asm/irq_handler.h>
+#include <asm/bfin5xx_spi.h>
+#include <asm/bfin_sport.h>
+#include <asm/bfin_can.h>
+#include <asm/bfin_dma.h>
+#include <asm/dpmc.h>
+
 void __init program_IAR(void)
 {
         /* Program the IAR0 Register with the configured priority */
@@ -51,3 +58,159 @@ void __init program_IAR(void)
 
         SSYNC();
 }
+
+#define SPI_ERR_MASK   (BIT_STAT_TXCOL | BIT_STAT_RBSY | BIT_STAT_MODF | BIT_STAT_TXE)  /* SPI_STAT */
+#define SPORT_ERR_MASK (ROVF | RUVF | TOVF | TUVF)      /* SPORT_STAT */
+#define PPI_ERR_MASK   (0xFFFF & ~FLD)  /* PPI_STATUS */
+#define EMAC_ERR_MASK  (PHYINT | MMCINT | RXFSINT | TXFSINT | WAKEDET | RXDMAERR | TXDMAERR | STMDONE)  /* EMAC_SYSTAT */
+#define UART_ERR_MASK  (0x6)    /* UART_IIR */
+#define CAN_ERR_MASK   (EWTIF | EWRIF | EPIF | BOIF | WUIF | UIAIF | AAIF | RMLIF | UCEIF | EXTIF | ADIF)       /* CAN_GIF */
+
+static int error_int_mask;
+
+static void bf537_generic_error_mask_irq(struct irq_data *d)
+{
+        error_int_mask &= ~(1L << (d->irq - IRQ_PPI_ERROR));
+        if (!error_int_mask)
+                bfin_internal_mask_irq(IRQ_GENERIC_ERROR);
+}
+
+static void bf537_generic_error_unmask_irq(struct irq_data *d)
+{
+        bfin_internal_unmask_irq(IRQ_GENERIC_ERROR);
+        error_int_mask |= 1L << (d->irq - IRQ_PPI_ERROR);
+}
+
+static struct irq_chip bf537_generic_error_irqchip = {
+        .name = "ERROR",
+        .irq_ack = bfin_ack_noop,
+        .irq_mask_ack = bf537_generic_error_mask_irq,
+        .irq_mask = bf537_generic_error_mask_irq,
+        .irq_unmask = bf537_generic_error_unmask_irq,
+};
+
+static void bf537_demux_error_irq(unsigned int int_err_irq,
+                                  struct irq_desc *inta_desc)
+{
+        int irq = 0;
+
+#if (defined(CONFIG_BF537) || defined(CONFIG_BF536))
+        if (bfin_read_EMAC_SYSTAT() & EMAC_ERR_MASK)
+                irq = IRQ_MAC_ERROR;
+        else
+#endif
+        if (bfin_read_SPORT0_STAT() & SPORT_ERR_MASK)
+                irq = IRQ_SPORT0_ERROR;
+        else if (bfin_read_SPORT1_STAT() & SPORT_ERR_MASK)
+                irq = IRQ_SPORT1_ERROR;
+        else if (bfin_read_PPI_STATUS() & PPI_ERR_MASK)
+                irq = IRQ_PPI_ERROR;
+        else if (bfin_read_CAN_GIF() & CAN_ERR_MASK)
+                irq = IRQ_CAN_ERROR;
+        else if (bfin_read_SPI_STAT() & SPI_ERR_MASK)
+                irq = IRQ_SPI_ERROR;
+        else if ((bfin_read_UART0_IIR() & UART_ERR_MASK) == UART_ERR_MASK)
+                irq = IRQ_UART0_ERROR;
+        else if ((bfin_read_UART1_IIR() & UART_ERR_MASK) == UART_ERR_MASK)
+                irq = IRQ_UART1_ERROR;
+
+        if (irq) {
+                if (error_int_mask & (1L << (irq - IRQ_PPI_ERROR)))
+                        bfin_handle_irq(irq);
+                else {
+
+                        switch (irq) {
+                        case IRQ_PPI_ERROR:
+                                bfin_write_PPI_STATUS(PPI_ERR_MASK);
+                                break;
+#if (defined(CONFIG_BF537) || defined(CONFIG_BF536))
+                        case IRQ_MAC_ERROR:
+                                bfin_write_EMAC_SYSTAT(EMAC_ERR_MASK);
+                                break;
+#endif
+                        case IRQ_SPORT0_ERROR:
+                                bfin_write_SPORT0_STAT(SPORT_ERR_MASK);
+                                break;
+
+                        case IRQ_SPORT1_ERROR:
+                                bfin_write_SPORT1_STAT(SPORT_ERR_MASK);
+                                break;
+
+                        case IRQ_CAN_ERROR:
+                                bfin_write_CAN_GIS(CAN_ERR_MASK);
+                                break;
+
+                        case IRQ_SPI_ERROR:
+                                bfin_write_SPI_STAT(SPI_ERR_MASK);
+                                break;
+
+                        default:
+                                break;
+                        }
+
+                        pr_debug("IRQ %d:"
+                                 " MASKED PERIPHERAL ERROR INTERRUPT ASSERTED\n",
+                                 irq);
+                }
+        } else
+                pr_err("%s: IRQ ?: PERIPHERAL ERROR INTERRUPT ASSERTED BUT NO SOURCE FOUND\n",
+                       __func__);
+
+}
+
+#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+static int mac_rx_int_mask;
+
+static void bf537_mac_rx_mask_irq(struct irq_data *d)
+{
+        mac_rx_int_mask &= ~(1L << (d->irq - IRQ_MAC_RX));
+        if (!mac_rx_int_mask)
+                bfin_internal_mask_irq(IRQ_PH_INTA_MAC_RX);
+}
+
+static void bf537_mac_rx_unmask_irq(struct irq_data *d)
+{
+        bfin_internal_unmask_irq(IRQ_PH_INTA_MAC_RX);
+        mac_rx_int_mask |= 1L << (d->irq - IRQ_MAC_RX);
+}
+
+static struct irq_chip bf537_mac_rx_irqchip = {
+        .name = "ERROR",
+        .irq_ack = bfin_ack_noop,
+        .irq_mask_ack = bf537_mac_rx_mask_irq,
+        .irq_mask = bf537_mac_rx_mask_irq,
+        .irq_unmask = bf537_mac_rx_unmask_irq,
+};
+
+static void bf537_demux_mac_rx_irq(unsigned int int_irq,
+                                   struct irq_desc *desc)
+{
+        if (bfin_read_DMA1_IRQ_STATUS() & (DMA_DONE | DMA_ERR))
+                bfin_handle_irq(IRQ_MAC_RX);
+        else
+                bfin_demux_gpio_irq(int_irq, desc);
+}
+#endif
+
+void __init init_mach_irq(void)
+{
+        int irq;
+
+#if defined(CONFIG_BF537) || defined(CONFIG_BF536)
+        /* Clear EMAC Interrupt Status bits so we can demux it later */
+        bfin_write_EMAC_SYSTAT(-1);
+#endif
+
+        irq_set_chained_handler(IRQ_GENERIC_ERROR, bf537_demux_error_irq);
+        for (irq = IRQ_PPI_ERROR; irq <= IRQ_UART1_ERROR; irq++)
+                irq_set_chip_and_handler(irq, &bf537_generic_error_irqchip,
+                                         handle_level_irq);
+
+#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
+        irq_set_chained_handler(IRQ_PH_INTA_MAC_RX, bf537_demux_mac_rx_irq);
+        irq_set_chip_and_handler(IRQ_MAC_RX, &bf537_mac_rx_irqchip, handle_level_irq);
+        irq_set_chip_and_handler(IRQ_PORTH_INTA, &bf537_mac_rx_irqchip, handle_level_irq);
+
+        irq_set_chained_handler(IRQ_MAC_ERROR, bfin_demux_mac_status_irq);
+#endif
+}
diff --git a/arch/blackfin/mach-bf538/include/mach/anomaly.h b/arch/blackfin/mach-bf538/include/mach/anomaly.h
index 8774b481c78e..55e7d0712a94 100644
--- a/arch/blackfin/mach-bf538/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf538/include/mach/anomaly.h
@@ -5,14 +5,14 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
 
 /* This file should be up to date with:
- *  - Revision H, 07/10/2009; ADSP-BF538/BF538F Blackfin Processor Anomaly List
- *  - Revision M, 07/10/2009; ADSP-BF539/BF539F Blackfin Processor Anomaly List
+ *  - Revision I, 05/25/2010; ADSP-BF538/BF538F Blackfin Processor Anomaly List
+ *  - Revision N, 05/25/2010; ADSP-BF539/BF539F Blackfin Processor Anomaly List
  */
 
 #ifndef _MACH_ANOMALY_H_
@@ -179,6 +179,7 @@
 #define ANOMALY_05000363 (0)
 #define ANOMALY_05000364 (0)
 #define ANOMALY_05000380 (0)
+#define ANOMALY_05000383 (0)
 #define ANOMALY_05000386 (1)
 #define ANOMALY_05000389 (0)
 #define ANOMALY_05000400 (0)
@@ -186,6 +187,7 @@
 #define ANOMALY_05000430 (0)
 #define ANOMALY_05000432 (0)
 #define ANOMALY_05000435 (0)
+#define ANOMALY_05000440 (0)
 #define ANOMALY_05000447 (0)
 #define ANOMALY_05000448 (0)
 #define ANOMALY_05000456 (0)
@@ -193,6 +195,7 @@
 #define ANOMALY_05000465 (0)
 #define ANOMALY_05000467 (0)
 #define ANOMALY_05000474 (0)
+#define ANOMALY_05000480 (0)
 #define ANOMALY_05000485 (0)
 
 #endif
diff --git a/arch/blackfin/mach-bf538/include/mach/irq.h b/arch/blackfin/mach-bf538/include/mach/irq.h
index 7a479d224dc7..07ca069d37cd 100644
--- a/arch/blackfin/mach-bf538/include/mach/irq.h
+++ b/arch/blackfin/mach-bf538/include/mach/irq.h
@@ -7,38 +7,9 @@
 #ifndef _BF538_IRQ_H_
 #define _BF538_IRQ_H_
 
-/*
- * Interrupt source definitions
-        Event Source    Core Event Name
-        Core        Emulation               **
-        Events         (highest priority)  EMU         0
-        Reset                   RST         1
-        NMI                     NMI         2
-        Exception               EVX         3
-        Reserved                --          4
-        Hardware Error          IVHW        5
-        Core Timer              IVTMR       6 *
-
-        .....
-
-         Software Interrupt 1    IVG14       31
-         Software Interrupt 2    --
-         (lowest priority)  IVG15       32 *
-*/
-
-#define NR_PERI_INTS    (2 * 32)
-
-/* The ABSTRACT IRQ definitions */
-/** the first seven of the following are fixed, the rest you change if you need to **/
-#define IRQ_EMU                 0       /* Emulation */
-#define IRQ_RST                 1       /* reset */
-#define IRQ_NMI                 2       /* Non Maskable */
-#define IRQ_EVX                 3       /* Exception */
-#define IRQ_UNUSED              4       /* - unused interrupt */
-#define IRQ_HWERR               5       /* Hardware Error */
-#define IRQ_CORETMR             6       /* Core timer */
-
-#define BFIN_IRQ(x)             ((x) + 7)
+#include <mach-common/irq.h>
+
+#define NR_PERI_INTS            (2 * 32)
 
 #define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
 #define IRQ_DMA0_ERROR          BFIN_IRQ(1)     /* DMA Error 0 (generic) */
@@ -91,37 +62,26 @@
 
 #define SYS_IRQS                BFIN_IRQ(63)    /* 70 */
 
-#define IRQ_PF0         71
-#define IRQ_PF1         72
-#define IRQ_PF2         73
-#define IRQ_PF3         74
-#define IRQ_PF4         75
-#define IRQ_PF5         76
-#define IRQ_PF6         77
-#define IRQ_PF7         78
-#define IRQ_PF8         79
-#define IRQ_PF9         80
-#define IRQ_PF10        81
-#define IRQ_PF11        82
-#define IRQ_PF12        83
-#define IRQ_PF13        84
-#define IRQ_PF14        85
-#define IRQ_PF15        86
-
-#define GPIO_IRQ_BASE   IRQ_PF0
-
-#define NR_MACH_IRQS    (IRQ_PF15 + 1)
-#define NR_IRQS         (NR_MACH_IRQS + NR_SPARE_IRQS)
-
-#define IVG7            7
-#define IVG8            8
-#define IVG9            9
-#define IVG10           10
-#define IVG11           11
-#define IVG12           12
-#define IVG13           13
-#define IVG14           14
-#define IVG15           15
+#define IRQ_PF0                 71
+#define IRQ_PF1                 72
+#define IRQ_PF2                 73
+#define IRQ_PF3                 74
+#define IRQ_PF4                 75
+#define IRQ_PF5                 76
+#define IRQ_PF6                 77
+#define IRQ_PF7                 78
+#define IRQ_PF8                 79
+#define IRQ_PF9                 80
+#define IRQ_PF10                81
+#define IRQ_PF11                82
+#define IRQ_PF12                83
+#define IRQ_PF13                84
+#define IRQ_PF14                85
+#define IRQ_PF15                86
+
+#define GPIO_IRQ_BASE           IRQ_PF0
+
+#define NR_MACH_IRQS            (IRQ_PF15 + 1)
 
 /* IAR0 BIT FIELDS */
 #define IRQ_PLL_WAKEUP_POS      0
@@ -184,4 +144,5 @@
 #define IRQ_CAN_TX_POS          0
 #define IRQ_MEM1_DMA0_POS       4
 #define IRQ_MEM1_DMA1_POS       8
-#endif                          /* _BF538_IRQ_H_ */
+
+#endif
diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c
index 93e19a54a880..311bf9970fe7 100644
--- a/arch/blackfin/mach-bf548/boards/ezkit.c
+++ b/arch/blackfin/mach-bf548/boards/ezkit.c
@@ -22,6 +22,7 @@
 #include <asm/gpio.h>
 #include <asm/nand.h>
 #include <asm/dpmc.h>
+#include <asm/bfin_sport.h>
 #include <asm/portmux.h>
 #include <asm/bfin_sdh.h>
 #include <mach/bf54x_keys.h>
@@ -956,7 +957,15 @@ static struct mtd_partition ezkit_partitions[] = {
                 .offset     = MTDPART_OFS_APPEND,
         }, {
                 .name       = "file system(nor)",
-                .size       = MTDPART_SIZ_FULL,
+                .size       = 0x1000000 - 0x80000 - 0x400000 - 0x8000 * 4,
+                .offset     = MTDPART_OFS_APPEND,
+        }, {
+                .name       = "config(nor)",
+                .size       = 0x8000 * 3,
+                .offset     = MTDPART_OFS_APPEND,
+        }, {
+                .name       = "u-boot env(nor)",
+                .size       = 0x8000,
                 .offset     = MTDPART_OFS_APPEND,
         }
 };
@@ -1312,27 +1321,110 @@ static struct platform_device bfin_dpmc = {
         },
 };
 
-#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE)
+#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) || \
+        defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE) || \
+        defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+
+#define SPORT_REQ(x) \
+        [x] = {P_SPORT##x##_TFS, P_SPORT##x##_DTPRI, P_SPORT##x##_TSCLK, \
+                P_SPORT##x##_RFS, P_SPORT##x##_DRPRI, P_SPORT##x##_RSCLK, 0}
+
+static const u16 bfin_snd_pin[][7] = {
+        SPORT_REQ(0),
+        SPORT_REQ(1),
+};
+
+static struct bfin_snd_platform_data bfin_snd_data[] = {
+        {
+                .pin_req = &bfin_snd_pin[0][0],
+        },
+        {
+                .pin_req = &bfin_snd_pin[1][0],
+        },
+};
+
+#define BFIN_SND_RES(x) \
+        [x] = { \
+                { \
+                        .start = SPORT##x##_TCR1, \
+                        .end = SPORT##x##_TCR1, \
+                        .flags = IORESOURCE_MEM \
+                }, \
+                { \
+                        .start = CH_SPORT##x##_RX, \
+                        .end = CH_SPORT##x##_RX, \
+                        .flags = IORESOURCE_DMA, \
+                }, \
+                { \
+                        .start = CH_SPORT##x##_TX, \
+                        .end = CH_SPORT##x##_TX, \
+                        .flags = IORESOURCE_DMA, \
+                }, \
+                { \
+                        .start = IRQ_SPORT##x##_ERROR, \
+                        .end = IRQ_SPORT##x##_ERROR, \
+                        .flags = IORESOURCE_IRQ, \
+                } \
+        }
+
+static struct resource bfin_snd_resources[][4] = {
+        BFIN_SND_RES(0),
+        BFIN_SND_RES(1),
+};
+
+static struct platform_device bfin_pcm = {
+        .name = "bfin-pcm-audio",
+        .id = -1,
+};
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_AD73311) || defined(CONFIG_SND_BF5XX_SOC_AD73311_MODULE)
+static struct platform_device bfin_ad73311_codec_device = {
+        .name = "ad73311",
+        .id = -1,
+};
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_AD1980) || defined(CONFIG_SND_BF5XX_SOC_AD1980_MODULE)
+static struct platform_device bfin_ad1980_codec_device = {
+        .name = "ad1980",
+        .id = -1,
+};
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_I2S) || defined(CONFIG_SND_BF5XX_SOC_I2S_MODULE)
 static struct platform_device bfin_i2s = {
         .name = "bfin-i2s",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
-#if defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE)
+#if defined(CONFIG_SND_BF5XX_SOC_TDM) || defined(CONFIG_SND_BF5XX_SOC_TDM_MODULE)
 static struct platform_device bfin_tdm = {
         .name = "bfin-tdm",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
-#if defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+#if defined(CONFIG_SND_BF5XX_SOC_AC97) || defined(CONFIG_SND_BF5XX_SOC_AC97_MODULE)
 static struct platform_device bfin_ac97 = {
         .name = "bfin-ac97",
         .id = CONFIG_SND_BF5XX_SPORT_NUM,
-        /* TODO: add platform data here */
+        .num_resources = ARRAY_SIZE(bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM]),
+        .resource = bfin_snd_resources[CONFIG_SND_BF5XX_SPORT_NUM],
+        .dev = {
+                .platform_data = &bfin_snd_data[CONFIG_SND_BF5XX_SPORT_NUM],
+        },
 };
 #endif
 
@@ -1450,6 +1542,16 @@ static struct platform_device *ezkit_devices[] __initdata = {
         &ezkit_flash_device,
 #endif
 
+#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) || \
+        defined(CONFIG_SND_BF5XX_TDM) || defined(CONFIG_SND_BF5XX_TDM_MODULE) || \
+        defined(CONFIG_SND_BF5XX_AC97) || defined(CONFIG_SND_BF5XX_AC97_MODULE)
+        &bfin_pcm,
+#endif
+
+#if defined(CONFIG_SND_BF5XX_SOC_AD1980) || defined(CONFIG_SND_BF5XX_SOC_AD1980_MODULE)
+        &bfin_ad1980_codec_device,
+#endif
+
 #if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE)
         &bfin_i2s,
 #endif
diff --git a/arch/blackfin/mach-bf548/include/mach/anomaly.h b/arch/blackfin/mach-bf548/include/mach/anomaly.h
index ffd0537295ac..9e70785bdde3 100644
--- a/arch/blackfin/mach-bf548/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf548/include/mach/anomaly.h
@@ -5,13 +5,13 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
 
 /* This file should be up to date with:
- *  - Revision I, 07/23/2009; ADSP-BF542/BF544/BF547/BF548/BF549 Blackfin Processor Anomaly List
+ *  - Revision J, 06/03/2010; ADSP-BF542/BF544/BF547/BF548/BF549 Blackfin Processor Anomaly List
  */
 
 #ifndef _MACH_ANOMALY_H_
@@ -220,6 +220,8 @@
 #define ANOMALY_05000481 (1)
 /* Possible USB Data Corruption When Multiple Endpoints Are Accessed by the Core */
 #define ANOMALY_05000483 (1)
+/* DDR Trim May Not Be Performed for Certain VLEV Values in OTP Page PBS00L */
+#define ANOMALY_05000484 (__SILICON_REVISION__ < 3)
 /* PLL_CTL Change Using bfrom_SysControl() Can Result in Processor Overclocking */
 #define ANOMALY_05000485 (__SILICON_REVISION__ >= 2)
 /* IFLUSH sucks at life */
@@ -274,6 +276,8 @@
 #define ANOMALY_05000412 (0)
 #define ANOMALY_05000432 (0)
 #define ANOMALY_05000435 (0)
+#define ANOMALY_05000440 (0)
 #define ANOMALY_05000475 (0)
+#define ANOMALY_05000480 (0)
 
 #endif
diff --git a/arch/blackfin/mach-bf548/include/mach/irq.h b/arch/blackfin/mach-bf548/include/mach/irq.h
index 7f87787e7738..533b8095b540 100644
--- a/arch/blackfin/mach-bf548/include/mach/irq.h
+++ b/arch/blackfin/mach-bf548/include/mach/irq.h
@@ -7,38 +7,9 @@
 #ifndef _BF548_IRQ_H_
 #define _BF548_IRQ_H_
 
-/*
- * Interrupt source definitions
-            Event Source    Core Event Name
-Core        Emulation               **
-Events         (highest priority)  EMU         0
-            Reset                   RST         1
-            NMI                     NMI         2
-            Exception               EVX         3
-            Reserved                --          4
-            Hardware Error          IVHW        5
-            Core Timer              IVTMR       6 *
-
-.....
-
-            Software Interrupt 1    IVG14       31
-            Software Interrupt 2    --
-                 (lowest priority)  IVG15       32 *
- */
-
-#define NR_PERI_INTS    (32 * 3)
-
-/* The ABSTRACT IRQ definitions */
-/** the first seven of the following are fixed, the rest you change if you need to **/
-#define IRQ_EMU                 0       /* Emulation */
-#define IRQ_RST                 1       /* reset */
-#define IRQ_NMI                 2       /* Non Maskable */
-#define IRQ_EVX                 3       /* Exception */
-#define IRQ_UNUSED              4       /* - unused interrupt*/
-#define IRQ_HWERR               5       /* Hardware Error */
-#define IRQ_CORETMR             6       /* Core timer */
+#include <mach-common/irq.h>
 
-#define BFIN_IRQ(x)             ((x) + 7)
+#define NR_PERI_INTS            (3 * 32)
 
 #define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
 #define IRQ_DMAC0_ERROR         BFIN_IRQ(1)     /* DMAC0 Status Interrupt */
@@ -311,49 +282,37 @@ Events         (highest priority)  EMU         0
 #define IRQ_PJ14                BFIN_PJ_IRQ(14)         /* N/A */
 #define IRQ_PJ15                BFIN_PJ_IRQ(15)         /* N/A */
 
-#define GPIO_IRQ_BASE   IRQ_PA0
+#define GPIO_IRQ_BASE           IRQ_PA0
 
-#define NR_MACH_IRQS    (IRQ_PJ15 + 1)
-#define NR_IRQS         (NR_MACH_IRQS + NR_SPARE_IRQS)
+#define NR_MACH_IRQS            (IRQ_PJ15 + 1)
 
 /* For compatibility reasons with existing code */
 
-#define IRQ_DMAC0_ERR           IRQ_DMAC0_ERROR
-#define IRQ_EPPI0_ERR           IRQ_EPPI0_ERROR
+#define IRQ_DMAC0_ERR           IRQ_DMAC0_ERROR
+#define IRQ_EPPI0_ERR           IRQ_EPPI0_ERROR
 #define IRQ_SPORT0_ERR          IRQ_SPORT0_ERROR
 #define IRQ_SPORT1_ERR          IRQ_SPORT1_ERROR
-#define IRQ_SPI0_ERR            IRQ_SPI0_ERROR
-#define IRQ_UART0_ERR           IRQ_UART0_ERROR
-#define IRQ_DMAC1_ERR           IRQ_DMAC1_ERROR
+#define IRQ_SPI0_ERR            IRQ_SPI0_ERROR
+#define IRQ_UART0_ERR           IRQ_UART0_ERROR
+#define IRQ_DMAC1_ERR           IRQ_DMAC1_ERROR
 #define IRQ_SPORT2_ERR          IRQ_SPORT2_ERROR
 #define IRQ_SPORT3_ERR          IRQ_SPORT3_ERROR
-#define IRQ_SPI1_ERR            IRQ_SPI1_ERROR
-#define IRQ_SPI2_ERR            IRQ_SPI2_ERROR
-#define IRQ_UART1_ERR           IRQ_UART1_ERROR
-#define IRQ_UART2_ERR           IRQ_UART2_ERROR
-#define IRQ_CAN0_ERR            IRQ_CAN0_ERROR
-#define IRQ_MXVR_ERR            IRQ_MXVR_ERROR
-#define IRQ_EPPI1_ERR           IRQ_EPPI1_ERROR
-#define IRQ_EPPI2_ERR           IRQ_EPPI2_ERROR
-#define IRQ_UART3_ERR           IRQ_UART3_ERROR
-#define IRQ_HOST_ERR            IRQ_HOST_ERROR
-#define IRQ_PIXC_ERR            IRQ_PIXC_ERROR
-#define IRQ_NFC_ERR             IRQ_NFC_ERROR
-#define IRQ_ATAPI_ERR           IRQ_ATAPI_ERROR
-#define IRQ_CAN1_ERR            IRQ_CAN1_ERROR
+#define IRQ_SPI1_ERR            IRQ_SPI1_ERROR
+#define IRQ_SPI2_ERR            IRQ_SPI2_ERROR
+#define IRQ_UART1_ERR           IRQ_UART1_ERROR
+#define IRQ_UART2_ERR           IRQ_UART2_ERROR
+#define IRQ_CAN0_ERR            IRQ_CAN0_ERROR
+#define IRQ_MXVR_ERR            IRQ_MXVR_ERROR
+#define IRQ_EPPI1_ERR           IRQ_EPPI1_ERROR
+#define IRQ_EPPI2_ERR           IRQ_EPPI2_ERROR
+#define IRQ_UART3_ERR           IRQ_UART3_ERROR
+#define IRQ_HOST_ERR            IRQ_HOST_ERROR
+#define IRQ_PIXC_ERR            IRQ_PIXC_ERROR
+#define IRQ_NFC_ERR             IRQ_NFC_ERROR
+#define IRQ_ATAPI_ERR           IRQ_ATAPI_ERROR
+#define IRQ_CAN1_ERR            IRQ_CAN1_ERROR
 #define IRQ_HS_DMA_ERR          IRQ_HS_DMA_ERROR
 
-
-#define IVG7            7
-#define IVG8            8
-#define IVG9            9
-#define IVG10           10
-#define IVG11           11
-#define IVG12           12
-#define IVG13           13
-#define IVG14           14
-#define IVG15           15
-
 /* IAR0 BIT FIELDS */
 #define IRQ_PLL_WAKEUP_POS      0
 #define IRQ_DMAC0_ERR_POS       4
@@ -492,4 +451,4 @@ struct bfin_pint_regs {
 
 #endif
 
-#endif /* _BF548_IRQ_H_ */
+#endif
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index f667e7704197..5067984a62e7 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -247,7 +247,15 @@ static struct mtd_partition ezkit_partitions[] = {
                 .offset     = MTDPART_OFS_APPEND,
         }, {
                 .name       = "file system(nor)",
-                .size       = MTDPART_SIZ_FULL,
+                .size       = 0x800000 - 0x40000 - 0x1C0000 - 0x2000 * 8,
+                .offset     = MTDPART_OFS_APPEND,
+        }, {
+                .name       = "config(nor)",
+                .size       = 0x2000 * 7,
+                .offset     = MTDPART_OFS_APPEND,
+        }, {
+                .name       = "u-boot env(nor)",
+                .size       = 0x2000,
                 .offset     = MTDPART_OFS_APPEND,
         }
 };
diff --git a/arch/blackfin/mach-bf561/include/mach/anomaly.h b/arch/blackfin/mach-bf561/include/mach/anomaly.h
index 6a3499b02097..22b5ab773027 100644
--- a/arch/blackfin/mach-bf561/include/mach/anomaly.h
+++ b/arch/blackfin/mach-bf561/include/mach/anomaly.h
@@ -5,13 +5,13 @@
  * and can be replaced with that version at any time
  * DO NOT EDIT THIS FILE
  *
- * Copyright 2004-2010 Analog Devices Inc.
+ * Copyright 2004-2011 Analog Devices Inc.
  * Licensed under the ADI BSD license.
  *   https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd
  */
 
 /* This file should be up to date with:
- *  - Revision Q, 11/07/2008; ADSP-BF561 Blackfin Processor Anomaly List
+ *  - Revision R, 05/25/2010; ADSP-BF561 Blackfin Processor Anomaly List
  */
 
 #ifndef _MACH_ANOMALY_H_
@@ -290,12 +290,18 @@
 #define ANOMALY_05000428 (__SILICON_REVISION__ > 3)
 /* IFLUSH Instruction at End of Hardware Loop Causes Infinite Stall */
 #define ANOMALY_05000443 (1)
+/* SCKELOW Feature Is Not Functional */
+#define ANOMALY_05000458 (1)
 /* False Hardware Error when RETI Points to Invalid Memory */
 #define ANOMALY_05000461 (1)
+/* Synchronization Problem at Startup May Cause SPORT Transmit Channels to Misalign */
+#define ANOMALY_05000462 (1)
+/* Boot Failure When SDRAM Control Signals Toggle Coming Out Of Reset */
+#define ANOMALY_05000471 (1)
 /* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */
 #define ANOMALY_05000473 (1)
 /* Possible Lockup Condition whem Modifying PLL from External Memory */
-#define ANOMALY_05000475 (__SILICON_REVISION__ < 4)
+#define ANOMALY_05000475 (1)
 /* TESTSET Instruction Cannot Be Interrupted */
 #define ANOMALY_05000477 (1)
 /* Reads of ITEST_COMMAND and ITEST_DATA Registers Cause Cache Corruption */
@@ -314,12 +320,14 @@
 #define ANOMALY_05000353 (1)
 #define ANOMALY_05000364 (0)
 #define ANOMALY_05000380 (0)
+#define ANOMALY_05000383 (0)
 #define ANOMALY_05000386 (1)
 #define ANOMALY_05000389 (0)
 #define ANOMALY_05000400 (0)
 #define ANOMALY_05000430 (0)
 #define ANOMALY_05000432 (0)
 #define ANOMALY_05000435 (0)
+#define ANOMALY_05000440 (0)
 #define ANOMALY_05000447 (0)
 #define ANOMALY_05000448 (0)
 #define ANOMALY_05000456 (0)
@@ -327,6 +335,7 @@
 #define ANOMALY_05000465 (0)
 #define ANOMALY_05000467 (0)
 #define ANOMALY_05000474 (0)
+#define ANOMALY_05000480 (0)
 #define ANOMALY_05000485 (0)
 
 #endif
diff --git a/arch/blackfin/mach-bf561/include/mach/irq.h b/arch/blackfin/mach-bf561/include/mach/irq.h
index c95566ade51b..d6998520f70f 100644
--- a/arch/blackfin/mach-bf561/include/mach/irq.h
+++ b/arch/blackfin/mach-bf561/include/mach/irq.h
@@ -7,212 +7,98 @@
 #ifndef _BF561_IRQ_H_
 #define _BF561_IRQ_H_
 
-/***********************************************************************
- * Interrupt source definitions:
-             Event Source               Core Event Name     IRQ No
-                                                (highest priority)
-            Emulation Events                    EMU         0
-            Reset                               RST         1
-            NMI                                 NMI         2
-            Exception                           EVX         3
-            Reserved                            --          4
-            Hardware Error                      IVHW        5
-            Core Timer                          IVTMR       6 *
-
-            PLL Wakeup Interrupt                IVG7        7
-            DMA1 Error (generic)                IVG7        8
-            DMA2 Error (generic)                IVG7        9
-            IMDMA Error (generic)               IVG7        10
-            PPI1 Error Interrupt                IVG7        11
-            PPI2 Error Interrupt                IVG7        12
-            SPORT0 Error Interrupt              IVG7        13
-            SPORT1 Error Interrupt              IVG7        14
-            SPI Error Interrupt                 IVG7        15
-            UART Error Interrupt                IVG7        16
-            Reserved Interrupt                  IVG7        17
-
-            DMA1 0  Interrupt(PPI1)             IVG8        18
-            DMA1 1  Interrupt(PPI2)             IVG8        19
-            DMA1 2  Interrupt                   IVG8        20
-            DMA1 3  Interrupt                   IVG8        21
-            DMA1 4  Interrupt                   IVG8        22
-            DMA1 5  Interrupt                   IVG8        23
-            DMA1 6  Interrupt                   IVG8        24
-            DMA1 7  Interrupt                   IVG8        25
-            DMA1 8  Interrupt                   IVG8        26
-            DMA1 9  Interrupt                   IVG8        27
-            DMA1 10 Interrupt                   IVG8        28
-            DMA1 11 Interrupt                   IVG8        29
-
-            DMA2 0  (SPORT0 RX)                 IVG9        30
-            DMA2 1  (SPORT0 TX)                 IVG9        31
-            DMA2 2  (SPORT1 RX)                 IVG9        32
-            DMA2 3  (SPORT2 TX)                 IVG9        33
-            DMA2 4  (SPI)                       IVG9        34
-            DMA2 5  (UART RX)                   IVG9        35
-            DMA2 6  (UART TX)                   IVG9        36
-            DMA2 7  Interrupt                   IVG9        37
-            DMA2 8  Interrupt                   IVG9        38
-            DMA2 9  Interrupt                   IVG9        39
-            DMA2 10 Interrupt                   IVG9        40
-            DMA2 11 Interrupt                   IVG9        41
-
-            TIMER 0  Interrupt                  IVG10       42
-            TIMER 1  Interrupt                  IVG10       43
-            TIMER 2  Interrupt                  IVG10       44
-            TIMER 3  Interrupt                  IVG10       45
-            TIMER 4  Interrupt                  IVG10       46
-            TIMER 5  Interrupt                  IVG10       47
-            TIMER 6  Interrupt                  IVG10       48
-            TIMER 7  Interrupt                  IVG10       49
-            TIMER 8  Interrupt                  IVG10       50
-            TIMER 9  Interrupt                  IVG10       51
-            TIMER 10 Interrupt                  IVG10       52
-            TIMER 11 Interrupt                  IVG10       53
-
-            Programmable Flags0 A (8)           IVG11       54
-            Programmable Flags0 B (8)           IVG11       55
-            Programmable Flags1 A (8)           IVG11       56
-            Programmable Flags1 B (8)           IVG11       57
-            Programmable Flags2 A (8)           IVG11       58
-            Programmable Flags2 B (8)           IVG11       59
-
-            MDMA1 0 write/read INT              IVG8        60
-            MDMA1 1 write/read INT              IVG8        61
-
-            MDMA2 0 write/read INT              IVG9        62
-            MDMA2 1 write/read INT              IVG9        63
-
-            IMDMA 0 write/read INT              IVG12       64
-            IMDMA 1 write/read INT              IVG12       65
-
-            Watch Dog Timer                     IVG13       66
-
-            Reserved interrupt                  IVG7        67
-            Reserved interrupt                  IVG7        68
-            Supplemental interrupt 0            IVG7        69
-            supplemental interrupt 1            IVG7        70
-
-            Softirq                             IVG14
-            System Call    --
-                 (lowest priority)              IVG15
-
- **********************************************************************/
-
-#define SYS_IRQS                71
-#define NR_PERI_INTS            64
-
-/*
- * The ABSTRACT IRQ definitions
- *  the first seven of the following are fixed,
- *  the rest you change if you need to.
- */
-/* IVG 0-6*/
-#define IRQ_EMU                 0       /* Emulation                */
-#define IRQ_RST                 1       /* Reset                    */
-#define IRQ_NMI                 2       /* Non Maskable Interrupt   */
-#define IRQ_EVX                 3       /* Exception                */
-#define IRQ_UNUSED              4       /* Reserved interrupt       */
-#define IRQ_HWERR               5       /* Hardware Error           */
-#define IRQ_CORETMR             6       /* Core timer               */
-
-#define IVG_BASE                7
-/* IVG 7  */
-#define IRQ_PLL_WAKEUP          (IVG_BASE + 0)  /* PLL Wakeup Interrupt     */
-#define IRQ_DMA1_ERROR          (IVG_BASE + 1)  /* DMA1   Error (general)   */
-#define IRQ_DMA_ERROR           IRQ_DMA1_ERROR  /* DMA1   Error (general)   */
-#define IRQ_DMA2_ERROR          (IVG_BASE + 2)  /* DMA2   Error (general)   */
-#define IRQ_IMDMA_ERROR         (IVG_BASE + 3)  /* IMDMA  Error Interrupt   */
-#define IRQ_PPI1_ERROR          (IVG_BASE + 4)  /* PPI1   Error Interrupt   */
-#define IRQ_PPI_ERROR           IRQ_PPI1_ERROR  /* PPI1   Error Interrupt   */
-#define IRQ_PPI2_ERROR          (IVG_BASE + 5)  /* PPI2   Error Interrupt   */
-#define IRQ_SPORT0_ERROR        (IVG_BASE + 6)  /* SPORT0 Error Interrupt   */
-#define IRQ_SPORT1_ERROR        (IVG_BASE + 7)  /* SPORT1 Error Interrupt   */
-#define IRQ_SPI_ERROR           (IVG_BASE + 8)  /* SPI    Error Interrupt   */
-#define IRQ_UART_ERROR          (IVG_BASE + 9)  /* UART   Error Interrupt   */
-#define IRQ_RESERVED_ERROR      (IVG_BASE + 10) /* Reversed     Interrupt   */
-/* IVG 8  */
-#define IRQ_DMA1_0              (IVG_BASE + 11) /* DMA1 0  Interrupt(PPI1)  */
-#define IRQ_PPI                 IRQ_DMA1_0      /* DMA1 0  Interrupt(PPI1)  */
-#define IRQ_PPI0                IRQ_DMA1_0      /* DMA1 0  Interrupt(PPI1)  */
-#define IRQ_DMA1_1              (IVG_BASE + 12) /* DMA1 1  Interrupt(PPI2)  */
-#define IRQ_PPI1                IRQ_DMA1_1      /* DMA1 1  Interrupt(PPI2)  */
-#define IRQ_DMA1_2              (IVG_BASE + 13) /* DMA1 2  Interrupt        */
-#define IRQ_DMA1_3              (IVG_BASE + 14) /* DMA1 3  Interrupt        */
-#define IRQ_DMA1_4              (IVG_BASE + 15) /* DMA1 4  Interrupt        */
-#define IRQ_DMA1_5              (IVG_BASE + 16) /* DMA1 5  Interrupt        */
-#define IRQ_DMA1_6              (IVG_BASE + 17) /* DMA1 6  Interrupt        */
-#define IRQ_DMA1_7              (IVG_BASE + 18) /* DMA1 7  Interrupt        */
-#define IRQ_DMA1_8              (IVG_BASE + 19) /* DMA1 8  Interrupt        */
-#define IRQ_DMA1_9              (IVG_BASE + 20) /* DMA1 9  Interrupt        */
-#define IRQ_DMA1_10             (IVG_BASE + 21) /* DMA1 10 Interrupt        */
-#define IRQ_DMA1_11             (IVG_BASE + 22) /* DMA1 11 Interrupt        */
-/* IVG 9  */
-#define IRQ_DMA2_0              (IVG_BASE + 23) /* DMA2 0  (SPORT0 RX)      */
-#define IRQ_SPORT0_RX           IRQ_DMA2_0      /* DMA2 0  (SPORT0 RX)      */
-#define IRQ_DMA2_1              (IVG_BASE + 24) /* DMA2 1  (SPORT0 TX)      */
-#define IRQ_SPORT0_TX           IRQ_DMA2_1      /* DMA2 1  (SPORT0 TX)      */
-#define IRQ_DMA2_2              (IVG_BASE + 25) /* DMA2 2  (SPORT1 RX)      */
-#define IRQ_SPORT1_RX           IRQ_DMA2_2      /* DMA2 2  (SPORT1 RX)      */
-#define IRQ_DMA2_3              (IVG_BASE + 26) /* DMA2 3  (SPORT2 TX)      */
-#define IRQ_SPORT1_TX           IRQ_DMA2_3      /* DMA2 3  (SPORT2 TX)      */
-#define IRQ_DMA2_4              (IVG_BASE + 27) /* DMA2 4  (SPI)            */
-#define IRQ_SPI                 IRQ_DMA2_4      /* DMA2 4  (SPI)            */
-#define IRQ_DMA2_5              (IVG_BASE + 28) /* DMA2 5  (UART RX)        */
-#define IRQ_UART_RX             IRQ_DMA2_5      /* DMA2 5  (UART RX)        */
-#define IRQ_DMA2_6              (IVG_BASE + 29) /* DMA2 6  (UART TX)        */
-#define IRQ_UART_TX             IRQ_DMA2_6      /* DMA2 6  (UART TX)        */
-#define IRQ_DMA2_7              (IVG_BASE + 30) /* DMA2 7  Interrupt        */
-#define IRQ_DMA2_8              (IVG_BASE + 31) /* DMA2 8  Interrupt        */
-#define IRQ_DMA2_9              (IVG_BASE + 32) /* DMA2 9  Interrupt        */
-#define IRQ_DMA2_10             (IVG_BASE + 33) /* DMA2 10 Interrupt        */
-#define IRQ_DMA2_11             (IVG_BASE + 34) /* DMA2 11 Interrupt        */
-/* IVG 10 */
-#define IRQ_TIMER0              (IVG_BASE + 35) /* TIMER 0  Interrupt       */
-#define IRQ_TIMER1              (IVG_BASE + 36) /* TIMER 1  Interrupt       */
-#define IRQ_TIMER2              (IVG_BASE + 37) /* TIMER 2  Interrupt       */
-#define IRQ_TIMER3              (IVG_BASE + 38) /* TIMER 3  Interrupt       */
-#define IRQ_TIMER4              (IVG_BASE + 39) /* TIMER 4  Interrupt       */
-#define IRQ_TIMER5              (IVG_BASE + 40) /* TIMER 5  Interrupt       */
-#define IRQ_TIMER6              (IVG_BASE + 41) /* TIMER 6  Interrupt       */
-#define IRQ_TIMER7              (IVG_BASE + 42) /* TIMER 7  Interrupt       */
-#define IRQ_TIMER8              (IVG_BASE + 43) /* TIMER 8  Interrupt       */
-#define IRQ_TIMER9              (IVG_BASE + 44) /* TIMER 9  Interrupt       */
-#define IRQ_TIMER10             (IVG_BASE + 45) /* TIMER 10 Interrupt       */
-#define IRQ_TIMER11             (IVG_BASE + 46) /* TIMER 11 Interrupt       */
-/* IVG 11 */
-#define IRQ_PROG0_INTA          (IVG_BASE + 47) /* Programmable Flags0 A (8) */
-#define IRQ_PROG_INTA           IRQ_PROG0_INTA  /* Programmable Flags0 A (8) */
-#define IRQ_PROG0_INTB          (IVG_BASE + 48) /* Programmable Flags0 B (8) */
-#define IRQ_PROG_INTB           IRQ_PROG0_INTB  /* Programmable Flags0 B (8) */
-#define IRQ_PROG1_INTA          (IVG_BASE + 49) /* Programmable Flags1 A (8) */
-#define IRQ_PROG1_INTB          (IVG_BASE + 50) /* Programmable Flags1 B (8) */
-#define IRQ_PROG2_INTA          (IVG_BASE + 51) /* Programmable Flags2 A (8) */
-#define IRQ_PROG2_INTB          (IVG_BASE + 52) /* Programmable Flags2 B (8) */
-/* IVG 8  */
-#define IRQ_DMA1_WRRD0          (IVG_BASE + 53) /* MDMA1 0 write/read INT   */
-#define IRQ_DMA_WRRD0           IRQ_DMA1_WRRD0  /* MDMA1 0 write/read INT   */
+#include <mach-common/irq.h>
+
+#define NR_PERI_INTS            (2 * 32)
+
+#define IRQ_PLL_WAKEUP          BFIN_IRQ(0)     /* PLL Wakeup Interrupt */
+#define IRQ_DMA1_ERROR          BFIN_IRQ(1)     /* DMA1   Error (general) */
+#define IRQ_DMA_ERROR           IRQ_DMA1_ERROR  /* DMA1   Error (general) */
+#define IRQ_DMA2_ERROR          BFIN_IRQ(2)     /* DMA2   Error (general) */
+#define IRQ_IMDMA_ERROR         BFIN_IRQ(3)     /* IMDMA  Error Interrupt */
+#define IRQ_PPI1_ERROR          BFIN_IRQ(4)     /* PPI1   Error Interrupt */
+#define IRQ_PPI_ERROR           IRQ_PPI1_ERROR  /* PPI1   Error Interrupt */
+#define IRQ_PPI2_ERROR          BFIN_IRQ(5)     /* PPI2   Error Interrupt */
+#define IRQ_SPORT0_ERROR        BFIN_IRQ(6)     /* SPORT0 Error Interrupt */
+#define IRQ_SPORT1_ERROR        BFIN_IRQ(7)     /* SPORT1 Error Interrupt */
+#define IRQ_SPI_ERROR           BFIN_IRQ(8)     /* SPI    Error Interrupt */
+#define IRQ_UART_ERROR          BFIN_IRQ(9)     /* UART   Error Interrupt */
+#define IRQ_RESERVED_ERROR      BFIN_IRQ(10)    /* Reversed */
+#define IRQ_DMA1_0              BFIN_IRQ(11)    /* DMA1 0  Interrupt(PPI1) */
+#define IRQ_PPI                 IRQ_DMA1_0      /* DMA1 0  Interrupt(PPI1) */
+#define IRQ_PPI0                IRQ_DMA1_0      /* DMA1 0  Interrupt(PPI1) */
+#define IRQ_DMA1_1              BFIN_IRQ(12)    /* DMA1 1  Interrupt(PPI2) */
+#define IRQ_PPI1                IRQ_DMA1_1      /* DMA1 1  Interrupt(PPI2) */
+#define IRQ_DMA1_2              BFIN_IRQ(13)    /* DMA1 2  Interrupt */
+#define IRQ_DMA1_3              BFIN_IRQ(14)    /* DMA1 3  Interrupt */
+#define IRQ_DMA1_4              BFIN_IRQ(15)    /* DMA1 4  Interrupt */
+#define IRQ_DMA1_5              BFIN_IRQ(16)    /* DMA1 5  Interrupt */
+#define IRQ_DMA1_6              BFIN_IRQ(17)    /* DMA1 6  Interrupt */
+#define IRQ_DMA1_7              BFIN_IRQ(18)    /* DMA1 7  Interrupt */
+#define IRQ_DMA1_8              BFIN_IRQ(19)    /* DMA1 8  Interrupt */
+#define IRQ_DMA1_9              BFIN_IRQ(20)    /* DMA1 9  Interrupt */
+#define IRQ_DMA1_10             BFIN_IRQ(21)    /* DMA1 10 Interrupt */
+#define IRQ_DMA1_11             BFIN_IRQ(22)    /* DMA1 11 Interrupt */
+#define IRQ_DMA2_0              BFIN_IRQ(23)    /* DMA2 0  (SPORT0 RX) */
+#define IRQ_SPORT0_RX           IRQ_DMA2_0      /* DMA2 0  (SPORT0 RX) */
+#define IRQ_DMA2_1              BFIN_IRQ(24)    /* DMA2 1  (SPORT0 TX) */
+#define IRQ_SPORT0_TX           IRQ_DMA2_1      /* DMA2 1  (SPORT0 TX) */
+#define IRQ_DMA2_2              BFIN_IRQ(25)    /* DMA2 2  (SPORT1 RX) */
+#define IRQ_SPORT1_RX           IRQ_DMA2_2      /* DMA2 2  (SPORT1 RX) */
+#define IRQ_DMA2_3              BFIN_IRQ(26)    /* DMA2 3  (SPORT2 TX) */
+#define IRQ_SPORT1_TX           IRQ_DMA2_3      /* DMA2 3  (SPORT2 TX) */
+#define IRQ_DMA2_4              BFIN_IRQ(27)    /* DMA2 4  (SPI) */
+#define IRQ_SPI                 IRQ_DMA2_4      /* DMA2 4  (SPI) */
+#define IRQ_DMA2_5              BFIN_IRQ(28)    /* DMA2 5  (UART RX) */
+#define IRQ_UART_RX             IRQ_DMA2_5      /* DMA2 5  (UART RX) */
+#define IRQ_DMA2_6              BFIN_IRQ(29)    /* DMA2 6  (UART TX) */
+#define IRQ_UART_TX             IRQ_DMA2_6      /* DMA2 6  (UART TX) */
+#define IRQ_DMA2_7              BFIN_IRQ(30)    /* DMA2 7  Interrupt */
+#define IRQ_DMA2_8              BFIN_IRQ(31)    /* DMA2 8  Interrupt */
+#define IRQ_DMA2_9              BFIN_IRQ(32)    /* DMA2 9  Interrupt */
+#define IRQ_DMA2_10             BFIN_IRQ(33)    /* DMA2 10 Interrupt */
+#define IRQ_DMA2_11             BFIN_IRQ(34)    /* DMA2 11 Interrupt */
+#define IRQ_TIMER0              BFIN_IRQ(35)    /* TIMER 0  Interrupt */
+#define IRQ_TIMER1              BFIN_IRQ(36)    /* TIMER 1  Interrupt */
+#define IRQ_TIMER2              BFIN_IRQ(37)    /* TIMER 2  Interrupt */
+#define IRQ_TIMER3              BFIN_IRQ(38)    /* TIMER 3  Interrupt */
+#define IRQ_TIMER4              BFIN_IRQ(39)    /* TIMER 4  Interrupt */
+#define IRQ_TIMER5              BFIN_IRQ(40)    /* TIMER 5  Interrupt */
+#define IRQ_TIMER6              BFIN_IRQ(41)    /* TIMER 6  Interrupt */
+#define IRQ_TIMER7              BFIN_IRQ(42)    /* TIMER 7  Interrupt */
+#define IRQ_TIMER8              BFIN_IRQ(43)    /* TIMER 8  Interrupt */
+#define IRQ_TIMER9              BFIN_IRQ(44)    /* TIMER 9  Interrupt */
+#define IRQ_TIMER10             BFIN_IRQ(45)    /* TIMER 10 Interrupt */
+#define IRQ_TIMER11             BFIN_IRQ(46)    /* TIMER 11 Interrupt */
+#define IRQ_PROG0_INTA          BFIN_IRQ(47)    /* Programmable Flags0 A (8) */
+#define IRQ_PROG_INTA           IRQ_PROG0_INTA  /* Programmable Flags0 A (8) */
+#define IRQ_PROG0_INTB          BFIN_IRQ(48)    /* Programmable Flags0 B (8) */
+#define IRQ_PROG_INTB           IRQ_PROG0_INTB  /* Programmable Flags0 B (8) */
+#define IRQ_PROG1_INTA          BFIN_IRQ(49)    /* Programmable Flags1 A (8) */
+#define IRQ_PROG1_INTB          BFIN_IRQ(50)    /* Programmable Flags1 B (8) */
+#define IRQ_PROG2_INTA          BFIN_IRQ(51)    /* Programmable Flags2 A (8) */
+#define IRQ_PROG2_INTB          BFIN_IRQ(52)    /* Programmable Flags2 B (8) */
+#define IRQ_DMA1_WRRD0          BFIN_IRQ(53)    /* MDMA1 0 write/read INT */
+#define IRQ_DMA_WRRD0           IRQ_DMA1_WRRD0  /* MDMA1 0 write/read INT */
 #define IRQ_MEM_DMA0            IRQ_DMA1_WRRD0
-#define IRQ_DMA1_WRRD1          (IVG_BASE + 54) /* MDMA1 1 write/read INT   */
-#define IRQ_DMA_WRRD1           IRQ_DMA1_WRRD1  /* MDMA1 1 write/read INT   */
+#define IRQ_DMA1_WRRD1          BFIN_IRQ(54)    /* MDMA1 1 write/read INT */
+#define IRQ_DMA_WRRD1           IRQ_DMA1_WRRD1  /* MDMA1 1 write/read INT */
 #define IRQ_MEM_DMA1            IRQ_DMA1_WRRD1
-/* IVG 9  */
-#define IRQ_DMA2_WRRD0          (IVG_BASE + 55) /* MDMA2 0 write/read INT   */
+#define IRQ_DMA2_WRRD0          BFIN_IRQ(55)    /* MDMA2 0 write/read INT */
 #define IRQ_MEM_DMA2            IRQ_DMA2_WRRD0
-#define IRQ_DMA2_WRRD1          (IVG_BASE + 56) /* MDMA2 1 write/read INT   */
+#define IRQ_DMA2_WRRD1          BFIN_IRQ(56)    /* MDMA2 1 write/read INT */
 #define IRQ_MEM_DMA3            IRQ_DMA2_WRRD1
-/* IVG 12 */
-#define IRQ_IMDMA_WRRD0         (IVG_BASE + 57) /* IMDMA 0 write/read INT   */
+#define IRQ_IMDMA_WRRD0         BFIN_IRQ(57)    /* IMDMA 0 write/read INT */
 #define IRQ_IMEM_DMA0           IRQ_IMDMA_WRRD0
-#define IRQ_IMDMA_WRRD1         (IVG_BASE + 58) /* IMDMA 1 write/read INT   */
+#define IRQ_IMDMA_WRRD1         BFIN_IRQ(58)    /* IMDMA 1 write/read INT */
 #define IRQ_IMEM_DMA1           IRQ_IMDMA_WRRD1
-/* IVG 13 */
-#define IRQ_WATCH               (IVG_BASE + 59) /* Watch Dog Timer          */
-/* IVG 7  */
-#define IRQ_RESERVED_1          (IVG_BASE + 60) /* Reserved interrupt       */
-#define IRQ_RESERVED_2          (IVG_BASE + 61) /* Reserved interrupt       */
-#define IRQ_SUPPLE_0            (IVG_BASE + 62) /* Supplemental interrupt 0 */
-#define IRQ_SUPPLE_1            (IVG_BASE + 63) /* supplemental interrupt 1 */
+#define IRQ_WATCH               BFIN_IRQ(59)    /* Watch Dog Timer */
+#define IRQ_RESERVED_1          BFIN_IRQ(60)    /* Reserved interrupt */
+#define IRQ_RESERVED_2          BFIN_IRQ(61)    /* Reserved interrupt */
+#define IRQ_SUPPLE_0            BFIN_IRQ(62)    /* Supplemental interrupt 0 */
+#define IRQ_SUPPLE_1            BFIN_IRQ(63)    /* supplemental interrupt 1 */
+
+#define SYS_IRQS                71
 
 #define IRQ_PF0                 73
 #define IRQ_PF1                 74
@@ -266,158 +152,85 @@
 #define GPIO_IRQ_BASE           IRQ_PF0
 
 #define NR_MACH_IRQS            (IRQ_PF47 + 1)
-#define NR_IRQS                 (NR_MACH_IRQS + NR_SPARE_IRQS)
-
-#define IVG7                    7
-#define IVG8                    8
-#define IVG9                    9
-#define IVG10                   10
-#define IVG11                   11
-#define IVG12                   12
-#define IVG13                   13
-#define IVG14                   14
-#define IVG15                   15
-
-/*
- * DEFAULT PRIORITIES:
- */
-
-#define CONFIG_DEF_PLL_WAKEUP           7
-#define CONFIG_DEF_DMA1_ERROR           7
-#define CONFIG_DEF_DMA2_ERROR           7
-#define CONFIG_DEF_IMDMA_ERROR          7
-#define CONFIG_DEF_PPI1_ERROR           7
-#define CONFIG_DEF_PPI2_ERROR           7
-#define CONFIG_DEF_SPORT0_ERROR         7
-#define CONFIG_DEF_SPORT1_ERROR         7
-#define CONFIG_DEF_SPI_ERROR            7
-#define CONFIG_DEF_UART_ERROR           7
-#define CONFIG_DEF_RESERVED_ERROR       7
-#define CONFIG_DEF_DMA1_0               8
-#define CONFIG_DEF_DMA1_1               8
-#define CONFIG_DEF_DMA1_2               8
-#define CONFIG_DEF_DMA1_3               8
-#define CONFIG_DEF_DMA1_4               8
-#define CONFIG_DEF_DMA1_5               8
-#define CONFIG_DEF_DMA1_6               8
-#define CONFIG_DEF_DMA1_7               8
-#define CONFIG_DEF_DMA1_8               8
-#define CONFIG_DEF_DMA1_9               8
-#define CONFIG_DEF_DMA1_10              8
-#define CONFIG_DEF_DMA1_11              8
-#define CONFIG_DEF_DMA2_0               9
-#define CONFIG_DEF_DMA2_1               9
-#define CONFIG_DEF_DMA2_2               9
-#define CONFIG_DEF_DMA2_3               9
-#define CONFIG_DEF_DMA2_4               9
-#define CONFIG_DEF_DMA2_5               9
-#define CONFIG_DEF_DMA2_6               9
-#define CONFIG_DEF_DMA2_7               9
-#define CONFIG_DEF_DMA2_8               9
-#define CONFIG_DEF_DMA2_9               9
-#define CONFIG_DEF_DMA2_10              9
-#define CONFIG_DEF_DMA2_11              9
-#define CONFIG_DEF_TIMER0               10
-#define CONFIG_DEF_TIMER1               10
-#define CONFIG_DEF_TIMER2               10
-#define CONFIG_DEF_TIMER3               10
-#define CONFIG_DEF_TIMER4               10
-#define CONFIG_DEF_TIMER5               10
-#define CONFIG_DEF_TIMER6               10
-#define CONFIG_DEF_TIMER7               10
-#define CONFIG_DEF_TIMER8               10
-#define CONFIG_DEF_TIMER9               10
-#define CONFIG_DEF_TIMER10              10
-#define CONFIG_DEF_TIMER11              10
-#define CONFIG_DEF_PROG0_INTA           11
-#define CONFIG_DEF_PROG0_INTB           11
-#define CONFIG_DEF_PROG1_INTA           11
-#define CONFIG_DEF_PROG1_INTB           11
-#define CONFIG_DEF_PROG2_INTA           11
-#define CONFIG_DEF_PROG2_INTB           11
-#define CONFIG_DEF_DMA1_WRRD0           8
-#define CONFIG_DEF_DMA1_WRRD1           8
-#define CONFIG_DEF_DMA2_WRRD0           9
-#define CONFIG_DEF_DMA2_WRRD1           9
-#define CONFIG_DEF_IMDMA_WRRD0          12
-#define CONFIG_DEF_IMDMA_WRRD1          12
-#define CONFIG_DEF_WATCH                13
-#define CONFIG_DEF_RESERVED_1           7
-#define CONFIG_DEF_RESERVED_2           7
-#define CONFIG_DEF_SUPPLE_0             7
-#define CONFIG_DEF_SUPPLE_1             7
 
 /* IAR0 BIT FIELDS */
-#define IRQ_PLL_WAKEUP_POS                      0
-#define IRQ_DMA1_ERROR_POS                      4
-#define IRQ_DMA2_ERROR_POS                      8
-#define IRQ_IMDMA_ERROR_POS                     12
-#define IRQ_PPI0_ERROR_POS                      16
-#define IRQ_PPI1_ERROR_POS                      20
-#define IRQ_SPORT0_ERROR_POS            24
-#define IRQ_SPORT1_ERROR_POS            28
+#define IRQ_PLL_WAKEUP_POS      0
+#define IRQ_DMA1_ERROR_POS      4
+#define IRQ_DMA2_ERROR_POS      8
+#define IRQ_IMDMA_ERROR_POS     12
+#define IRQ_PPI0_ERROR_POS      16
+#define IRQ_PPI1_ERROR_POS      20
+#define IRQ_SPORT0_ERROR_POS    24
+#define IRQ_SPORT1_ERROR_POS    28
+
 /* IAR1 BIT FIELDS */
-#define IRQ_SPI_ERROR_POS                       0
-#define IRQ_UART_ERROR_POS                      4
-#define IRQ_RESERVED_ERROR_POS          8
-#define IRQ_DMA1_0_POS                  12
-#define IRQ_DMA1_1_POS                  16
-#define IRQ_DMA1_2_POS                  20
-#define IRQ_DMA1_3_POS                  24
-#define IRQ_DMA1_4_POS                  28
+#define IRQ_SPI_ERROR_POS       0
+#define IRQ_UART_ERROR_POS      4
+#define IRQ_RESERVED_ERROR_POS  8
+#define IRQ_DMA1_0_POS          12
+#define IRQ_DMA1_1_POS          16
+#define IRQ_DMA1_2_POS          20
+#define IRQ_DMA1_3_POS          24
+#define IRQ_DMA1_4_POS          28
+
 /* IAR2 BIT FIELDS */
-#define IRQ_DMA1_5_POS                  0
-#define IRQ_DMA1_6_POS                  4
-#define IRQ_DMA1_7_POS                  8
-#define IRQ_DMA1_8_POS                  12
-#define IRQ_DMA1_9_POS                  16
-#define IRQ_DMA1_10_POS                 20
-#define IRQ_DMA1_11_POS                 24
-#define IRQ_DMA2_0_POS                  28
+#define IRQ_DMA1_5_POS          0
+#define IRQ_DMA1_6_POS          4
+#define IRQ_DMA1_7_POS          8
+#define IRQ_DMA1_8_POS          12
+#define IRQ_DMA1_9_POS          16
+#define IRQ_DMA1_10_POS         20
+#define IRQ_DMA1_11_POS         24
+#define IRQ_DMA2_0_POS          28
+
 /* IAR3 BIT FIELDS */
-#define IRQ_DMA2_1_POS                  0
-#define IRQ_DMA2_2_POS                  4
-#define IRQ_DMA2_3_POS                  8
-#define IRQ_DMA2_4_POS                  12
-#define IRQ_DMA2_5_POS                  16
-#define IRQ_DMA2_6_POS                  20
-#define IRQ_DMA2_7_POS                  24
-#define IRQ_DMA2_8_POS                  28
+#define IRQ_DMA2_1_POS          0
+#define IRQ_DMA2_2_POS          4
+#define IRQ_DMA2_3_POS          8
+#define IRQ_DMA2_4_POS          12
+#define IRQ_DMA2_5_POS          16
+#define IRQ_DMA2_6_POS          20
+#define IRQ_DMA2_7_POS          24
+#define IRQ_DMA2_8_POS          28
+
 /* IAR4 BIT FIELDS */
-#define IRQ_DMA2_9_POS                  0
-#define IRQ_DMA2_10_POS                 4
-#define IRQ_DMA2_11_POS                 8
-#define IRQ_TIMER0_POS                  12
-#define IRQ_TIMER1_POS                  16
-#define IRQ_TIMER2_POS                  20
-#define IRQ_TIMER3_POS                  24
-#define IRQ_TIMER4_POS                  28
+#define IRQ_DMA2_9_POS          0
+#define IRQ_DMA2_10_POS         4
+#define IRQ_DMA2_11_POS         8
+#define IRQ_TIMER0_POS          12
+#define IRQ_TIMER1_POS          16
+#define IRQ_TIMER2_POS          20
+#define IRQ_TIMER3_POS          24
+#define IRQ_TIMER4_POS          28
+
 /* IAR5 BIT FIELDS */
-#define IRQ_TIMER5_POS                  0
-#define IRQ_TIMER6_POS                  4
-#define IRQ_TIMER7_POS                  8
-#define IRQ_TIMER8_POS                  12
-#define IRQ_TIMER9_POS                  16
-#define IRQ_TIMER10_POS                 20
-#define IRQ_TIMER11_POS                 24
-#define IRQ_PROG0_INTA_POS                      28
+#define IRQ_TIMER5_POS          0
+#define IRQ_TIMER6_POS          4
+#define IRQ_TIMER7_POS          8
+#define IRQ_TIMER8_POS          12
+#define IRQ_TIMER9_POS          16
+#define IRQ_TIMER10_POS         20
+#define IRQ_TIMER11_POS         24
+#define IRQ_PROG0_INTA_POS      28
+
 /* IAR6 BIT FIELDS */
-#define IRQ_PROG0_INTB_POS                      0
-#define IRQ_PROG1_INTA_POS                      4
-#define IRQ_PROG1_INTB_POS                      8
-#define IRQ_PROG2_INTA_POS                      12
-#define IRQ_PROG2_INTB_POS                      16
-#define IRQ_DMA1_WRRD0_POS                      20
-#define IRQ_DMA1_WRRD1_POS                      24
-#define IRQ_DMA2_WRRD0_POS                      28
-/* IAR7 BIT FIELDS */
-#define IRQ_DMA2_WRRD1_POS                      0
-#define IRQ_IMDMA_WRRD0_POS                     4
-#define IRQ_IMDMA_WRRD1_POS                     8
-#define IRQ_WDTIMER_POS                 12
-#define IRQ_RESERVED_1_POS                      16
-#define IRQ_RESERVED_2_POS                      20
-#define IRQ_SUPPLE_0_POS                        24
-#define IRQ_SUPPLE_1_POS                        28
+#define IRQ_PROG0_INTB_POS      0
+#define IRQ_PROG1_INTA_POS      4
+#define IRQ_PROG1_INTB_POS      8
+#define IRQ_PROG2_INTA_POS      12
+#define IRQ_PROG2_INTB_POS      16
+#define IRQ_DMA1_WRRD0_POS      20
+#define IRQ_DMA1_WRRD1_POS      24
+#define IRQ_DMA2_WRRD0_POS      28
 
-#endif                          /* _BF561_IRQ_H_ */
+/* IAR7 BIT FIELDS */
+#define IRQ_DMA2_WRRD1_POS      0
+#define IRQ_IMDMA_WRRD0_POS     4
+#define IRQ_IMDMA_WRRD1_POS     8
+#define IRQ_WDTIMER_POS         12
+#define IRQ_RESERVED_1_POS      16
+#define IRQ_RESERVED_2_POS      20
+#define IRQ_SUPPLE_0_POS        24
+#define IRQ_SUPPLE_1_POS        28
+
+#endif
diff --git a/arch/blackfin/mach-bf561/smp.c b/arch/blackfin/mach-bf561/smp.c
index 7b07740cf68c..85abd8be1343 100644
--- a/arch/blackfin/mach-bf561/smp.c
+++ b/arch/blackfin/mach-bf561/smp.c
@@ -24,17 +24,23 @@ static DEFINE_SPINLOCK(boot_lock);
 
 void __init platform_init_cpus(void)
 {
-        cpu_set(0, cpu_possible_map); /* CoreA */
-        cpu_set(1, cpu_possible_map); /* CoreB */
+        struct cpumask mask;
+
+        cpumask_set_cpu(0, &mask); /* CoreA */
+        cpumask_set_cpu(1, &mask); /* CoreB */
+        init_cpu_possible(&mask);
 }
 
 void __init platform_prepare_cpus(unsigned int max_cpus)
 {
+        struct cpumask mask;
+
         bfin_relocate_coreb_l1_mem();
 
         /* Both cores ought to be present on a bf561! */
-        cpu_set(0, cpu_present_map); /* CoreA */
-        cpu_set(1, cpu_present_map); /* CoreB */
+        cpumask_set_cpu(0, &mask); /* CoreA */
+        cpumask_set_cpu(1, &mask); /* CoreB */
+        init_cpu_present(&mask);
 }
 
 int __init setup_profiling_timer(unsigned int multiplier) /* not supported */
@@ -62,9 +68,6 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
         bfin_write_SICB_IWR1(IWR_DISABLE_ALL);
         SSYNC();
 
-        /* Store CPU-private information to the cpu_data array. */
-        bfin_setup_cpudata(cpu);
-
         /* We are done with local CPU inits, unblock the boot CPU. */
         set_cpu_online(cpu, true);
         spin_lock(&boot_lock);
diff --git a/arch/blackfin/mach-common/dpmc.c b/arch/blackfin/mach-common/dpmc.c
index 5e4112e518a9..f5685a496c58 100644
--- a/arch/blackfin/mach-common/dpmc.c
+++ b/arch/blackfin/mach-common/dpmc.c
@@ -85,10 +85,11 @@ static void bfin_wakeup_cpu(void)
 {
         unsigned int cpu;
         unsigned int this_cpu = smp_processor_id();
-        cpumask_t mask = cpu_online_map;
+        cpumask_t mask;
 
-        cpu_clear(this_cpu, mask);
-        for_each_cpu_mask(cpu, mask)
+        cpumask_copy(&mask, cpu_online_mask);
+        cpumask_clear_cpu(this_cpu, &mask);
+        for_each_cpu(cpu, &mask)
                 platform_send_ipi_cpu(cpu, IRQ_SUPPLE_0);
 }
 
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 43d9fb195c1e..1177369f9922 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -19,32 +19,14 @@
 #ifdef CONFIG_IPIPE
 #include <linux/ipipe.h>
 #endif
-#ifdef CONFIG_KGDB
-#include <linux/kgdb.h>
-#endif
 #include <asm/traps.h>
 #include <asm/blackfin.h>
 #include <asm/gpio.h>
 #include <asm/irq_handler.h>
 #include <asm/dpmc.h>
-#include <asm/bfin5xx_spi.h>
-#include <asm/bfin_sport.h>
-#include <asm/bfin_can.h>
 
 #define SIC_SYSIRQ(irq) (irq - (IRQ_CORETMR + 1))
 
-#ifdef BF537_FAMILY
-# define BF537_GENERIC_ERROR_INT_DEMUX
-# define SPI_ERR_MASK   (BIT_STAT_TXCOL | BIT_STAT_RBSY | BIT_STAT_MODF | BIT_STAT_TXE) /* SPI_STAT */
-# define SPORT_ERR_MASK (ROVF | RUVF | TOVF | TUVF)     /* SPORT_STAT */
-# define PPI_ERR_MASK   (0xFFFF & ~FLD) /* PPI_STATUS */
-# define EMAC_ERR_MASK  (PHYINT | MMCINT | RXFSINT | TXFSINT | WAKEDET | RXDMAERR | TXDMAERR | STMDONE) /* EMAC_SYSTAT */
-# define UART_ERR_MASK  (0x6)   /* UART_IIR */
-# define CAN_ERR_MASK   (EWTIF | EWRIF | EPIF | BOIF | WUIF | UIAIF | AAIF | RMLIF | UCEIF | EXTIF | ADIF)      /* CAN_GIF */
-#else
-# undef BF537_GENERIC_ERROR_INT_DEMUX
-#endif
-
 /*
  * NOTES:
  * - we have separated the physical Hardware interrupt from the
@@ -63,22 +45,19 @@ unsigned long bfin_irq_flags = 0x1f;
 EXPORT_SYMBOL(bfin_irq_flags);
 #endif
 
-/* The number of spurious interrupts */
-atomic_t num_spurious;
-
 #ifdef CONFIG_PM
 unsigned long bfin_sic_iwr[3];  /* Up to 3 SIC_IWRx registers */
 unsigned vr_wakeup;
 #endif
 
-struct ivgx {
+static struct ivgx {
         /* irq number for request_irq, available in mach-bf5xx/irq.h */
         unsigned int irqno;
         /* corresponding bit in the SIC_ISR register */
         unsigned int isrflag;
 } ivg_table[NR_PERI_INTS];
 
-struct ivg_slice {
+static struct ivg_slice {
         /* position of first irq in ivg_table for given ivg */
         struct ivgx *ifirst;
         struct ivgx *istop;
@@ -125,7 +104,7 @@ static void __init search_IAR(void)
  * This is for core internal IRQs
  */
 
-static void bfin_ack_noop(struct irq_data *d)
+void bfin_ack_noop(struct irq_data *d)
 {
         /* Dummy function.  */
 }
@@ -154,26 +133,24 @@ static void bfin_core_unmask_irq(struct irq_data *d)
         return;
 }
 
-static void bfin_internal_mask_irq(unsigned int irq)
+void bfin_internal_mask_irq(unsigned int irq)
 {
-        unsigned long flags;
+        unsigned long flags = hard_local_irq_save();
 
-#ifdef CONFIG_BF53x
-        flags = hard_local_irq_save();
-        bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() &
-                             ~(1 << SIC_SYSIRQ(irq)));
-#else
-        unsigned mask_bank, mask_bit;
-        flags = hard_local_irq_save();
-        mask_bank = SIC_SYSIRQ(irq) / 32;
-        mask_bit = SIC_SYSIRQ(irq) % 32;
+#ifdef SIC_IMASK0
+        unsigned mask_bank = SIC_SYSIRQ(irq) / 32;
+        unsigned mask_bit = SIC_SYSIRQ(irq) % 32;
         bfin_write_SIC_IMASK(mask_bank, bfin_read_SIC_IMASK(mask_bank) &
                              ~(1 << mask_bit));
-#ifdef CONFIG_SMP
+# ifdef CONFIG_SMP
         bfin_write_SICB_IMASK(mask_bank, bfin_read_SICB_IMASK(mask_bank) &
                              ~(1 << mask_bit));
+# endif
+#else
+        bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() &
+                             ~(1 << SIC_SYSIRQ(irq)));
 #endif
-#endif
+
         hard_local_irq_restore(flags);
 }
 
@@ -186,33 +163,31 @@ static void bfin_internal_mask_irq_chip(struct irq_data *d)
 static void bfin_internal_unmask_irq_affinity(unsigned int irq,
                 const struct cpumask *affinity)
 #else
-static void bfin_internal_unmask_irq(unsigned int irq)
+void bfin_internal_unmask_irq(unsigned int irq)
 #endif
 {
-        unsigned long flags;
+        unsigned long flags = hard_local_irq_save();
 
-#ifdef CONFIG_BF53x
-        flags = hard_local_irq_save();
-        bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() |
-                             (1 << SIC_SYSIRQ(irq)));
-#else
-        unsigned mask_bank, mask_bit;
-        flags = hard_local_irq_save();
-        mask_bank = SIC_SYSIRQ(irq) / 32;
-        mask_bit = SIC_SYSIRQ(irq) % 32;
-#ifdef CONFIG_SMP
+#ifdef SIC_IMASK0
+        unsigned mask_bank = SIC_SYSIRQ(irq) / 32;
+        unsigned mask_bit = SIC_SYSIRQ(irq) % 32;
+# ifdef CONFIG_SMP
         if (cpumask_test_cpu(0, affinity))
-#endif
+# endif
                 bfin_write_SIC_IMASK(mask_bank,
                         bfin_read_SIC_IMASK(mask_bank) |
                         (1 << mask_bit));
-#ifdef CONFIG_SMP
+# ifdef CONFIG_SMP
         if (cpumask_test_cpu(1, affinity))
                 bfin_write_SICB_IMASK(mask_bank,
                         bfin_read_SICB_IMASK(mask_bank) |
                         (1 << mask_bit));
+# endif
+#else
+        bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() |
+                             (1 << SIC_SYSIRQ(irq)));
 #endif
-#endif
+
         hard_local_irq_restore(flags);
 }
 
@@ -295,6 +270,8 @@ static int bfin_internal_set_wake_chip(struct irq_data *d, unsigned int state)
 {
         return bfin_internal_set_wake(d->irq, state);
 }
+#else
+# define bfin_internal_set_wake_chip NULL
 #endif
 
 static struct irq_chip bfin_core_irqchip = {
@@ -315,12 +292,10 @@ static struct irq_chip bfin_internal_irqchip = {
 #ifdef CONFIG_SMP
         .irq_set_affinity = bfin_internal_set_affinity,
 #endif
-#ifdef CONFIG_PM
         .irq_set_wake = bfin_internal_set_wake_chip,
-#endif
 };
 
-static void bfin_handle_irq(unsigned irq)
+void bfin_handle_irq(unsigned irq)
 {
 #ifdef CONFIG_IPIPE
         struct pt_regs regs;    /* Contents not used. */
@@ -332,102 +307,6 @@ static void bfin_handle_irq(unsigned irq)
 #endif  /* !CONFIG_IPIPE */
 }
 
-#ifdef BF537_GENERIC_ERROR_INT_DEMUX
-static int error_int_mask;
-
-static void bfin_generic_error_mask_irq(struct irq_data *d)
-{
-        error_int_mask &= ~(1L << (d->irq - IRQ_PPI_ERROR));
-        if (!error_int_mask)
-                bfin_internal_mask_irq(IRQ_GENERIC_ERROR);
-}
-
-static void bfin_generic_error_unmask_irq(struct irq_data *d)
-{
-        bfin_internal_unmask_irq(IRQ_GENERIC_ERROR);
-        error_int_mask |= 1L << (d->irq - IRQ_PPI_ERROR);
-}
-
-static struct irq_chip bfin_generic_error_irqchip = {
-        .name = "ERROR",
-        .irq_ack = bfin_ack_noop,
-        .irq_mask_ack = bfin_generic_error_mask_irq,
-        .irq_mask = bfin_generic_error_mask_irq,
-        .irq_unmask = bfin_generic_error_unmask_irq,
-};
-
-static void bfin_demux_error_irq(unsigned int int_err_irq,
-                                 struct irq_desc *inta_desc)
-{
-        int irq = 0;
-
-#if (defined(CONFIG_BF537) || defined(CONFIG_BF536))
-        if (bfin_read_EMAC_SYSTAT() & EMAC_ERR_MASK)
-                irq = IRQ_MAC_ERROR;
-        else
-#endif
-        if (bfin_read_SPORT0_STAT() & SPORT_ERR_MASK)
-                irq = IRQ_SPORT0_ERROR;
-        else if (bfin_read_SPORT1_STAT() & SPORT_ERR_MASK)
-                irq = IRQ_SPORT1_ERROR;
-        else if (bfin_read_PPI_STATUS() & PPI_ERR_MASK)
-                irq = IRQ_PPI_ERROR;
-        else if (bfin_read_CAN_GIF() & CAN_ERR_MASK)
-                irq = IRQ_CAN_ERROR;
-        else if (bfin_read_SPI_STAT() & SPI_ERR_MASK)
-                irq = IRQ_SPI_ERROR;
-        else if ((bfin_read_UART0_IIR() & UART_ERR_MASK) == UART_ERR_MASK)
-                irq = IRQ_UART0_ERROR;
-        else if ((bfin_read_UART1_IIR() & UART_ERR_MASK) == UART_ERR_MASK)
-                irq = IRQ_UART1_ERROR;
-
-        if (irq) {
-                if (error_int_mask & (1L << (irq - IRQ_PPI_ERROR)))
-                        bfin_handle_irq(irq);
-                else {
-
-                        switch (irq) {
-                        case IRQ_PPI_ERROR:
-                                bfin_write_PPI_STATUS(PPI_ERR_MASK);
-                                break;
-#if (defined(CONFIG_BF537) || defined(CONFIG_BF536))
-                        case IRQ_MAC_ERROR:
-                                bfin_write_EMAC_SYSTAT(EMAC_ERR_MASK);
-                                break;
-#endif
-                        case IRQ_SPORT0_ERROR:
-                                bfin_write_SPORT0_STAT(SPORT_ERR_MASK);
-                                break;
-
-                        case IRQ_SPORT1_ERROR:
-                                bfin_write_SPORT1_STAT(SPORT_ERR_MASK);
-                                break;
-
-                        case IRQ_CAN_ERROR:
-                                bfin_write_CAN_GIS(CAN_ERR_MASK);
-                                break;
-
-                        case IRQ_SPI_ERROR:
-                                bfin_write_SPI_STAT(SPI_ERR_MASK);
-                                break;
-
-                        default:
-                                break;
-                        }
-
-                        pr_debug("IRQ %d:"
-                                 " MASKED PERIPHERAL ERROR INTERRUPT ASSERTED\n",
-                                 irq);
-                }
-        } else
-                printk(KERN_ERR
-                       "%s : %s : LINE %d :\nIRQ ?: PERIPHERAL ERROR"
-                       " INTERRUPT ASSERTED BUT NO SOURCE FOUND\n",
-                       __func__, __FILE__, __LINE__);
-
-}
-#endif                          /* BF537_GENERIC_ERROR_INT_DEMUX */
-
 #if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
 static int mac_stat_int_mask;
 
@@ -468,7 +347,7 @@ static void bfin_mac_status_mask_irq(struct irq_data *d)
         unsigned int irq = d->irq;
 
         mac_stat_int_mask &= ~(1L << (irq - IRQ_MAC_PHYINT));
-#ifdef BF537_GENERIC_ERROR_INT_DEMUX
+#ifdef BF537_FAMILY
         switch (irq) {
         case IRQ_MAC_PHYINT:
                 bfin_write_EMAC_SYSCTL(bfin_read_EMAC_SYSCTL() & ~PHYIE);
@@ -487,7 +366,7 @@ static void bfin_mac_status_unmask_irq(struct irq_data *d)
 {
         unsigned int irq = d->irq;
 
-#ifdef BF537_GENERIC_ERROR_INT_DEMUX
+#ifdef BF537_FAMILY
         switch (irq) {
         case IRQ_MAC_PHYINT:
                 bfin_write_EMAC_SYSCTL(bfin_read_EMAC_SYSCTL() | PHYIE);
@@ -505,12 +384,14 @@ static void bfin_mac_status_unmask_irq(struct irq_data *d)
 #ifdef CONFIG_PM
 int bfin_mac_status_set_wake(struct irq_data *d, unsigned int state)
 {
-#ifdef BF537_GENERIC_ERROR_INT_DEMUX
+#ifdef BF537_FAMILY
         return bfin_internal_set_wake(IRQ_GENERIC_ERROR, state);
 #else
         return bfin_internal_set_wake(IRQ_MAC_ERROR, state);
 #endif
 }
+#else
+# define bfin_mac_status_set_wake NULL
 #endif
 
 static struct irq_chip bfin_mac_status_irqchip = {
@@ -519,13 +400,11 @@ static struct irq_chip bfin_mac_status_irqchip = {
         .irq_mask_ack = bfin_mac_status_mask_irq,
         .irq_mask = bfin_mac_status_mask_irq,
         .irq_unmask = bfin_mac_status_unmask_irq,
-#ifdef CONFIG_PM
         .irq_set_wake = bfin_mac_status_set_wake,
-#endif
 };
 
-static void bfin_demux_mac_status_irq(unsigned int int_err_irq,
-                                 struct irq_desc *inta_desc)
+void bfin_demux_mac_status_irq(unsigned int int_err_irq,
+                               struct irq_desc *inta_desc)
 {
         int i, irq = 0;
         u32 status = bfin_read_EMAC_SYSTAT();
@@ -680,29 +559,48 @@ static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type)
 }
 
 #ifdef CONFIG_PM
-int bfin_gpio_set_wake(struct irq_data *d, unsigned int state)
+static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state)
 {
         return gpio_pm_wakeup_ctrl(irq_to_gpio(d->irq), state);
 }
+#else
+# define bfin_gpio_set_wake NULL
 #endif
 
-static void bfin_demux_gpio_irq(unsigned int inta_irq,
-                                struct irq_desc *desc)
+static void bfin_demux_gpio_block(unsigned int irq)
 {
-        unsigned int i, gpio, mask, irq, search = 0;
+        unsigned int gpio, mask;
+
+        gpio = irq_to_gpio(irq);
+        mask = get_gpiop_data(gpio) & get_gpiop_maska(gpio);
+
+        while (mask) {
+                if (mask & 1)
+                        bfin_handle_irq(irq);
+                irq++;
+                mask >>= 1;
+        }
+}
+
+void bfin_demux_gpio_irq(unsigned int inta_irq,
+                         struct irq_desc *desc)
+{
+        unsigned int irq;
 
         switch (inta_irq) {
-#if defined(CONFIG_BF53x)
-        case IRQ_PROG_INTA:
-                irq = IRQ_PF0;
-                search = 1;
+#if defined(BF537_FAMILY)
+        case IRQ_PF_INTA_PG_INTA:
+                bfin_demux_gpio_block(IRQ_PF0);
+                irq = IRQ_PG0;
                 break;
-# if defined(BF537_FAMILY) && !(defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE))
-        case IRQ_MAC_RX:
+        case IRQ_PH_INTA_MAC_RX:
                 irq = IRQ_PH0;
                 break;
-# endif
-#elif defined(CONFIG_BF538) || defined(CONFIG_BF539)
+#elif defined(BF533_FAMILY)
+        case IRQ_PROG_INTA:
+                irq = IRQ_PF0;
+                break;
+#elif defined(BF538_FAMILY)
         case IRQ_PORTF_INTA:
                 irq = IRQ_PF0;
                 break;
@@ -732,31 +630,7 @@ static void bfin_demux_gpio_irq(unsigned int inta_irq,
                 return;
         }
 
-        if (search) {
-                for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE) {
-                        irq += i;
-
-                        mask = get_gpiop_data(i) & get_gpiop_maska(i);
-
-                        while (mask) {
-                                if (mask & 1)
-                                        bfin_handle_irq(irq);
-                                irq++;
-                                mask >>= 1;
-                        }
-                }
-        } else {
-                        gpio = irq_to_gpio(irq);
-                        mask = get_gpiop_data(gpio) & get_gpiop_maska(gpio);
-
-                        do {
-                                if (mask & 1)
-                                        bfin_handle_irq(irq);
-                                irq++;
-                                mask >>= 1;
-                        } while (mask);
-        }
-
+        bfin_demux_gpio_block(irq);
 }
 
 #else                           /* CONFIG_BF54x */
@@ -974,15 +848,11 @@ static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type)
 }
 
 #ifdef CONFIG_PM
-u32 pint_saved_masks[NR_PINT_SYS_IRQS];
-u32 pint_wakeup_masks[NR_PINT_SYS_IRQS];
-
-int bfin_gpio_set_wake(struct irq_data *d, unsigned int state)
+static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state)
 {
         u32 pint_irq;
         u32 pint_val = irq2pint_lut[d->irq - SYS_IRQS];
         u32 bank = PINT_2_BANK(pint_val);
-        u32 pintbit = PINT_BIT(pint_val);
 
         switch (bank) {
         case 0:
@@ -1003,46 +873,14 @@ int bfin_gpio_set_wake(struct irq_data *d, unsigned int state)
 
         bfin_internal_set_wake(pint_irq, state);
 
-        if (state)
-                pint_wakeup_masks[bank] |= pintbit;
-        else
-                pint_wakeup_masks[bank] &= ~pintbit;
-
         return 0;
 }
-
-u32 bfin_pm_setup(void)
-{
-        u32 val, i;
-
-        for (i = 0; i < NR_PINT_SYS_IRQS; i++) {
-                val = pint[i]->mask_clear;
-                pint_saved_masks[i] = val;
-                if (val ^ pint_wakeup_masks[i]) {
-                        pint[i]->mask_clear = val;
-                        pint[i]->mask_set = pint_wakeup_masks[i];
-                }
-        }
-
-        return 0;
-}
-
-void bfin_pm_restore(void)
-{
-        u32 i, val;
-
-        for (i = 0; i < NR_PINT_SYS_IRQS; i++) {
-                val = pint_saved_masks[i];
-                if (val ^ pint_wakeup_masks[i]) {
-                        pint[i]->mask_clear = pint[i]->mask_clear;
-                        pint[i]->mask_set = val;
-                }
-        }
-}
+#else
+# define bfin_gpio_set_wake NULL
 #endif
 
-static void bfin_demux_gpio_irq(unsigned int inta_irq,
-                                struct irq_desc *desc)
+void bfin_demux_gpio_irq(unsigned int inta_irq,
+                         struct irq_desc *desc)
 {
         u32 bank, pint_val;
         u32 request, irq;
@@ -1091,9 +929,7 @@ static struct irq_chip bfin_gpio_irqchip = {
         .irq_set_type = bfin_gpio_irq_type,
         .irq_startup = bfin_gpio_irq_startup,
         .irq_shutdown = bfin_gpio_irq_shutdown,
-#ifdef CONFIG_PM
         .irq_set_wake = bfin_gpio_set_wake,
-#endif
 };
 
 void __cpuinit init_exception_vectors(void)
@@ -1127,12 +963,12 @@ int __init init_arch_irq(void)
 {
         int irq;
         unsigned long ilat = 0;
+
         /*  Disable all the peripheral intrs  - page 4-29 HW Ref manual */
-#if defined(CONFIG_BF54x) || defined(CONFIG_BF52x) || defined(CONFIG_BF561) \
-        || defined(BF538_FAMILY) || defined(CONFIG_BF51x)
+#ifdef SIC_IMASK0
         bfin_write_SIC_IMASK0(SIC_UNMASK_ALL);
         bfin_write_SIC_IMASK1(SIC_UNMASK_ALL);
-# ifdef CONFIG_BF54x
+# ifdef SIC_IMASK2
         bfin_write_SIC_IMASK2(SIC_UNMASK_ALL);
 # endif
 # ifdef CONFIG_SMP
@@ -1145,11 +981,6 @@ int __init init_arch_irq(void)
 
         local_irq_disable();
 
-#if (defined(CONFIG_BF537) || defined(CONFIG_BF536))
-        /* Clear EMAC Interrupt Status bits so we can demux it later */
-        bfin_write_EMAC_SYSTAT(-1);
-#endif
-
 #ifdef CONFIG_BF54x
 # ifdef CONFIG_PINTx_REASSIGN
         pint[0]->assign = CONFIG_PINT0_ASSIGN;
@@ -1168,11 +999,11 @@ int __init init_arch_irq(void)
                         irq_set_chip(irq, &bfin_internal_irqchip);
 
                 switch (irq) {
-#if defined(CONFIG_BF53x)
+#if defined(BF537_FAMILY)
+                case IRQ_PH_INTA_MAC_RX:
+                case IRQ_PF_INTA_PG_INTA:
+#elif defined(BF533_FAMILY)
                 case IRQ_PROG_INTA:
-# if defined(BF537_FAMILY) && !(defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE))
-                case IRQ_MAC_RX:
-# endif
 #elif defined(CONFIG_BF54x)
                 case IRQ_PINT0:
                 case IRQ_PINT1:
@@ -1186,16 +1017,11 @@ int __init init_arch_irq(void)
                 case IRQ_PROG0_INTA:
                 case IRQ_PROG1_INTA:
                 case IRQ_PROG2_INTA:
-#elif defined(CONFIG_BF538) || defined(CONFIG_BF539)
+#elif defined(BF538_FAMILY)
                 case IRQ_PORTF_INTA:
 #endif
                         irq_set_chained_handler(irq, bfin_demux_gpio_irq);
                         break;
-#ifdef BF537_GENERIC_ERROR_INT_DEMUX
-                case IRQ_GENERIC_ERROR:
-                        irq_set_chained_handler(irq, bfin_demux_error_irq);
-                        break;
-#endif
 #if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
                 case IRQ_MAC_ERROR:
                         irq_set_chained_handler(irq,
@@ -1213,11 +1039,10 @@ int __init init_arch_irq(void)
                 case IRQ_CORETMR:
 # ifdef CONFIG_SMP
                         irq_set_handler(irq, handle_percpu_irq);
-                        break;
 # else
                         irq_set_handler(irq, handle_simple_irq);
-                        break;
 # endif
+                        break;
 #endif
 
 #ifdef CONFIG_TICKSOURCE_GPTMR0
@@ -1226,26 +1051,17 @@ int __init init_arch_irq(void)
                         break;
 #endif
 
-#ifdef CONFIG_IPIPE
                 default:
+#ifdef CONFIG_IPIPE
                         irq_set_handler(irq, handle_level_irq);
-                        break;
-#else /* !CONFIG_IPIPE */
-                default:
+#else
                         irq_set_handler(irq, handle_simple_irq);
+#endif
                         break;
-#endif /* !CONFIG_IPIPE */
                 }
         }
 
-#ifdef BF537_GENERIC_ERROR_INT_DEMUX
-        for (irq = IRQ_PPI_ERROR; irq <= IRQ_UART1_ERROR; irq++)
-                irq_set_chip_and_handler(irq, &bfin_generic_error_irqchip,
-                                         handle_level_irq);
-#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
-        irq_set_chained_handler(IRQ_MAC_ERROR, bfin_demux_mac_status_irq);
-#endif
-#endif
+        init_mach_irq();
 
 #if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)
         for (irq = IRQ_MAC_PHYINT; irq <= IRQ_MAC_STMDONE; irq++)
@@ -1307,53 +1123,54 @@ int __init init_arch_irq(void)
 #ifdef CONFIG_DO_IRQ_L1
 __attribute__((l1_text))
 #endif
-void do_irq(int vec, struct pt_regs *fp)
+static int vec_to_irq(int vec)
 {
-        if (vec == EVT_IVTMR_P) {
-                vec = IRQ_CORETMR;
-        } else {
-                struct ivgx *ivg = ivg7_13[vec - IVG7].ifirst;
-                struct ivgx *ivg_stop = ivg7_13[vec - IVG7].istop;
-#if defined(SIC_ISR0)
-                unsigned long sic_status[3];
+        struct ivgx *ivg = ivg7_13[vec - IVG7].ifirst;
+        struct ivgx *ivg_stop = ivg7_13[vec - IVG7].istop;
+        unsigned long sic_status[3];
+
+        if (likely(vec == EVT_IVTMR_P))
+                return IRQ_CORETMR;
 
-                if (smp_processor_id()) {
+#ifdef SIC_ISR
+        sic_status[0] = bfin_read_SIC_IMASK() & bfin_read_SIC_ISR();
+#else
+        if (smp_processor_id()) {
 # ifdef SICB_ISR0
-                        /* This will be optimized out in UP mode. */
-                        sic_status[0] = bfin_read_SICB_ISR0() & bfin_read_SICB_IMASK0();
-                        sic_status[1] = bfin_read_SICB_ISR1() & bfin_read_SICB_IMASK1();
-# endif
-                } else {
-                        sic_status[0] = bfin_read_SIC_ISR0() & bfin_read_SIC_IMASK0();
-                        sic_status[1] = bfin_read_SIC_ISR1() & bfin_read_SIC_IMASK1();
-                }
-# ifdef SIC_ISR2
-                sic_status[2] = bfin_read_SIC_ISR2() & bfin_read_SIC_IMASK2();
+                /* This will be optimized out in UP mode. */
+                sic_status[0] = bfin_read_SICB_ISR0() & bfin_read_SICB_IMASK0();
+                sic_status[1] = bfin_read_SICB_ISR1() & bfin_read_SICB_IMASK1();
 # endif
-                for (;; ivg++) {
-                        if (ivg >= ivg_stop) {
-                                atomic_inc(&num_spurious);
-                                return;
-                        }
-                        if (sic_status[(ivg->irqno - IVG7) / 32] & ivg->isrflag)
-                                break;
-                }
-#else
-                unsigned long sic_status;
-
-                sic_status = bfin_read_SIC_IMASK() & bfin_read_SIC_ISR();
+        } else {
+                sic_status[0] = bfin_read_SIC_ISR0() & bfin_read_SIC_IMASK0();
+                sic_status[1] = bfin_read_SIC_ISR1() & bfin_read_SIC_IMASK1();
+        }
+#endif
+#ifdef SIC_ISR2
+        sic_status[2] = bfin_read_SIC_ISR2() & bfin_read_SIC_IMASK2();
+#endif
 
-                for (;; ivg++) {
-                        if (ivg >= ivg_stop) {
-                                atomic_inc(&num_spurious);
-                                return;
-                        } else if (sic_status & ivg->isrflag)
-                                break;
-                }
+        for (;; ivg++) {
+                if (ivg >= ivg_stop)
+                        return -1;
+#ifdef SIC_ISR
+                if (sic_status[0] & ivg->isrflag)
+#else
+                if (sic_status[(ivg->irqno - IVG7) / 32] & ivg->isrflag)
 #endif
-                vec = ivg->irqno;
+                        return ivg->irqno;
         }
-        asm_do_IRQ(vec, fp);
+}
+
+#ifdef CONFIG_DO_IRQ_L1
+__attribute__((l1_text))
+#endif
+void do_irq(int vec, struct pt_regs *fp)
+{
+        int irq = vec_to_irq(vec);
+        if (irq == -1)
+                return;
+        asm_do_IRQ(irq, fp);
 }
 
 #ifdef CONFIG_IPIPE
@@ -1391,40 +1208,9 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs)
         struct ivgx *ivg = ivg7_13[vec-IVG7].ifirst;
         int irq, s = 0;
 
-        if (likely(vec == EVT_IVTMR_P))
-                irq = IRQ_CORETMR;
-        else {
-#if defined(SIC_ISR0)
-                unsigned long sic_status[3];
-
-                sic_status[0] = bfin_read_SIC_ISR0() & bfin_read_SIC_IMASK0();
-                sic_status[1] = bfin_read_SIC_ISR1() & bfin_read_SIC_IMASK1();
-# ifdef SIC_ISR2
-                sic_status[2] = bfin_read_SIC_ISR2() & bfin_read_SIC_IMASK2();
-# endif
-                for (;; ivg++) {
-                        if (ivg >= ivg_stop) {
-                                atomic_inc(&num_spurious);
-                                return 0;
-                        }
-                        if (sic_status[(ivg->irqno - IVG7) / 32] & ivg->isrflag)
-                                break;
-                }
-#else
-                unsigned long sic_status;
-
-                sic_status = bfin_read_SIC_IMASK() & bfin_read_SIC_ISR();
-
-                for (;; ivg++) {
-                        if (ivg >= ivg_stop) {
-                                atomic_inc(&num_spurious);
-                                return 0;
-                        } else if (sic_status & ivg->isrflag)
-                                break;
-                }
-#endif
-                irq = ivg->irqno;
-        }
+        irq = vec_to_irq(vec);
+        if (irq == -1)
+                return 0;
 
         if (irq == IRQ_SYSTMR) {
 #if !defined(CONFIG_GENERIC_CLOCKEVENTS) || defined(CONFIG_TICKSOURCE_GPTMR0)
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 1fbd94c44457..35e7e1eb0188 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
+#include <asm/irq_handler.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -96,7 +97,7 @@ static void ipi_cpu_stop(unsigned int cpu)
         dump_stack();
         spin_unlock(&stop_lock);
 
-        cpu_clear(cpu, cpu_online_map);
+        set_cpu_online(cpu, false);
 
         local_irq_disable();
 
@@ -146,7 +147,7 @@ static void ipi_call_function(unsigned int cpu, struct ipi_message *msg)
                  */
                 resync_core_dcache();
 #endif
-                cpu_clear(cpu, *msg->call_struct.waitmask);
+                cpumask_clear_cpu(cpu, msg->call_struct.waitmask);
         }
 }
 
@@ -222,9 +223,10 @@ static inline void smp_send_message(cpumask_t callmap, unsigned long type,
         struct ipi_message_queue *msg_queue;
         struct ipi_message *msg;
         unsigned long flags, next_msg;
-        cpumask_t waitmask = callmap; /* waitmask is shared by all cpus */
+        cpumask_t waitmask; /* waitmask is shared by all cpus */
 
-        for_each_cpu_mask(cpu, callmap) {
+        cpumask_copy(&waitmask, &callmap);
+        for_each_cpu(cpu, &callmap) {
                 msg_queue = &per_cpu(ipi_msg_queue, cpu);
                 spin_lock_irqsave(&msg_queue->lock, flags);
                 if (msg_queue->count < BFIN_IPI_MSGQ_LEN) {
@@ -246,7 +248,7 @@ static inline void smp_send_message(cpumask_t callmap, unsigned long type,
         }
 
         if (wait) {
-                while (!cpus_empty(waitmask))
+                while (!cpumask_empty(&waitmask))
                         blackfin_dcache_invalidate_range(
                                 (unsigned long)(&waitmask),
                                 (unsigned long)(&waitmask));
@@ -265,9 +267,9 @@ int smp_call_function(void (*func)(void *info), void *info, int wait)
         cpumask_t callmap;
 
         preempt_disable();
-        callmap = cpu_online_map;
-        cpu_clear(smp_processor_id(), callmap);
-        if (!cpus_empty(callmap))
+        cpumask_copy(&callmap, cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), &callmap);
+        if (!cpumask_empty(&callmap))
                 smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
 
         preempt_enable();
@@ -284,8 +286,8 @@ int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
 
         if (cpu_is_offline(cpu))
                 return 0;
-        cpus_clear(callmap);
-        cpu_set(cpu, callmap);
+        cpumask_clear(&callmap);
+        cpumask_set_cpu(cpu, &callmap);
 
         smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
 
@@ -308,9 +310,9 @@ void smp_send_stop(void)
         cpumask_t callmap;
 
         preempt_disable();
-        callmap = cpu_online_map;
-        cpu_clear(smp_processor_id(), callmap);
-        if (!cpus_empty(callmap))
+        cpumask_copy(&callmap, cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), &callmap);
+        if (!cpumask_empty(&callmap))
                 smp_send_message(callmap, BFIN_IPI_CPU_STOP, NULL, NULL, 0);
 
         preempt_enable();
diff --git a/arch/blackfin/mm/sram-alloc.c b/arch/blackfin/mm/sram-alloc.c
index dfd304a4a3ea..29d98faa1efd 100644
--- a/arch/blackfin/mm/sram-alloc.c
+++ b/arch/blackfin/mm/sram-alloc.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
@@ -764,7 +765,7 @@ EXPORT_SYMBOL(sram_alloc_with_lsl);
 /* Need to keep line of output the same.  Currently, that is 44 bytes
  * (including newline).
  */
-static int _sram_proc_read(char *buf, int *len, int count, const char *desc,
+static int _sram_proc_show(struct seq_file *m, const char *desc,
                 struct sram_piece *pfree_head,
                 struct sram_piece *pused_head)
 {
@@ -773,13 +774,13 @@ static int _sram_proc_read(char *buf, int *len, int count, const char *desc,
         if (!pfree_head || !pused_head)
                 return -1;
 
-        *len += sprintf(&buf[*len], "--- SRAM %-14s Size   PID State     \n", desc);
+        seq_printf(m, "--- SRAM %-14s Size   PID State     \n", desc);
 
         /* search the relevant memory slot */
         pslot = pused_head->next;
 
         while (pslot != NULL) {
-                *len += sprintf(&buf[*len], "%p-%p %10i %5i %-10s\n",
+                seq_printf(m, "%p-%p %10i %5i %-10s\n",
                         pslot->paddr, pslot->paddr + pslot->size,
                         pslot->size, pslot->pid, "ALLOCATED");
 
@@ -789,7 +790,7 @@ static int _sram_proc_read(char *buf, int *len, int count, const char *desc,
         pslot = pfree_head->next;
 
         while (pslot != NULL) {
-                *len += sprintf(&buf[*len], "%p-%p %10i %5i %-10s\n",
+                seq_printf(m, "%p-%p %10i %5i %-10s\n",
                         pslot->paddr, pslot->paddr + pslot->size,
                         pslot->size, pslot->pid, "FREE");
 
@@ -798,54 +799,62 @@ static int _sram_proc_read(char *buf, int *len, int count, const char *desc,
 
         return 0;
 }
-static int sram_proc_read(char *buf, char **start, off_t offset, int count,
-                int *eof, void *data)
+static int sram_proc_show(struct seq_file *m, void *v)
 {
-        int len = 0;
         unsigned int cpu;
 
         for (cpu = 0; cpu < num_possible_cpus(); ++cpu) {
-                if (_sram_proc_read(buf, &len, count, "Scratchpad",
+                if (_sram_proc_show(m, "Scratchpad",
                         &per_cpu(free_l1_ssram_head, cpu), &per_cpu(used_l1_ssram_head, cpu)))
                         goto not_done;
 #if L1_DATA_A_LENGTH != 0
-                if (_sram_proc_read(buf, &len, count, "L1 Data A",
+                if (_sram_proc_show(m, "L1 Data A",
                         &per_cpu(free_l1_data_A_sram_head, cpu),
                         &per_cpu(used_l1_data_A_sram_head, cpu)))
                         goto not_done;
 #endif
 #if L1_DATA_B_LENGTH != 0
-                if (_sram_proc_read(buf, &len, count, "L1 Data B",
+                if (_sram_proc_show(m, "L1 Data B",
                         &per_cpu(free_l1_data_B_sram_head, cpu),
                         &per_cpu(used_l1_data_B_sram_head, cpu)))
                         goto not_done;
 #endif
 #if L1_CODE_LENGTH != 0
-                if (_sram_proc_read(buf, &len, count, "L1 Instruction",
+                if (_sram_proc_show(m, "L1 Instruction",
                         &per_cpu(free_l1_inst_sram_head, cpu),
                         &per_cpu(used_l1_inst_sram_head, cpu)))
                         goto not_done;
 #endif
         }
 #if L2_LENGTH != 0
-        if (_sram_proc_read(buf, &len, count, "L2", &free_l2_sram_head,
-                &used_l2_sram_head))
+        if (_sram_proc_show(m, "L2", &free_l2_sram_head, &used_l2_sram_head))
                 goto not_done;
 #endif
-        *eof = 1;
  not_done:
-        return len;
+        return 0;
+}
+
+static int sram_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, sram_proc_show, NULL);
 }
 
+static const struct file_operations sram_proc_ops = {
+        .open           = sram_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
 static int __init sram_proc_init(void)
 {
         struct proc_dir_entry *ptr;
-        ptr = create_proc_entry("sram", S_IFREG | S_IRUGO, NULL);
+
+        ptr = proc_create("sram", S_IRUGO, NULL, &sram_proc_ops);
         if (!ptr) {
                 printk(KERN_WARNING "unable to create /proc/sram\n");
                 return -1;
         }
-        ptr->read_proc = sram_proc_read;
         return 0;
 }
 late_initcall(sram_proc_init);
diff --git a/arch/cris/arch-v32/kernel/irq.c b/arch/cris/arch-v32/kernel/irq.c
index 68a1a5901ca5..5ebe6e841820 100644
--- a/arch/cris/arch-v32/kernel/irq.c
+++ b/arch/cris/arch-v32/kernel/irq.c
@@ -266,11 +266,11 @@ static int irq_cpu(int irq)
 
 
         /* Let the interrupt stay if possible */
-        if (cpu_isset(cpu, irq_allocations[irq - FIRST_IRQ].mask))
+        if (cpumask_test_cpu(cpu, &irq_allocations[irq - FIRST_IRQ].mask))
                 goto out;
 
         /* IRQ must be moved to another CPU. */
-        cpu = first_cpu(irq_allocations[irq - FIRST_IRQ].mask);
+        cpu = cpumask_first(&irq_allocations[irq - FIRST_IRQ].mask);
         irq_allocations[irq - FIRST_IRQ].cpu = cpu;
 out:
         spin_unlock_irqrestore(&irq_lock, flags);
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index 66cc75657e2f..a0843a71aaee 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -81,7 +81,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
         /* Mark all possible CPUs as present */
         for (i = 0; i < max_cpus; i++)
-            cpu_set(i, phys_cpu_present_map);
+                cpumask_set_cpu(i, &phys_cpu_present_map);
 }
 
 void __devinit smp_prepare_boot_cpu(void)
@@ -98,7 +98,7 @@ void __devinit smp_prepare_boot_cpu(void)
         SUPP_REG_WR(RW_MM_TLB_PGD, pgd);
 
         set_cpu_online(0, true);
-        cpu_set(0, phys_cpu_present_map);
+        cpumask_set_cpu(0, &phys_cpu_present_map);
         set_cpu_possible(0, true);
 }
 
@@ -112,8 +112,9 @@ smp_boot_one_cpu(int cpuid)
 {
         unsigned timeout;
         struct task_struct *idle;
-        cpumask_t cpu_mask = CPU_MASK_NONE;
+        cpumask_t cpu_mask;
 
+        cpumask_clear(&cpu_mask);
         idle = fork_idle(cpuid);
         if (IS_ERR(idle))
                 panic("SMP: fork failed for CPU:%d", cpuid);
@@ -125,10 +126,10 @@ smp_boot_one_cpu(int cpuid)
         cpu_now_booting = cpuid;
 
         /* Kick it */
-        cpu_set(cpuid, cpu_online_map);
-        cpu_set(cpuid, cpu_mask);
+        set_cpu_online(cpuid, true);
+        cpumask_set_cpu(cpuid, &cpu_mask);
         send_ipi(IPI_BOOT, 0, cpu_mask);
-        cpu_clear(cpuid, cpu_online_map);
+        set_cpu_online(cpuid, false);
 
         /* Wait for CPU to come online */
         for (timeout = 0; timeout < 10000; timeout++) {
@@ -176,7 +177,7 @@ void __init smp_callin(void)
         notify_cpu_starting(cpu);
         local_irq_enable();
 
-        cpu_set(cpu, cpu_online_map);
+        set_cpu_online(cpu, true);
         cpu_idle();
 }
 
@@ -214,8 +215,9 @@ int __cpuinit __cpu_up(unsigned int cpu)
 
 void smp_send_reschedule(int cpu)
 {
-        cpumask_t cpu_mask = CPU_MASK_NONE;
-        cpu_set(cpu, cpu_mask);
+        cpumask_t cpu_mask;
+        cpumask_clear(&cpu_mask);
+        cpumask_set_cpu(cpu, &cpu_mask);
         send_ipi(IPI_SCHEDULE, 0, cpu_mask);
 }
 
@@ -232,7 +234,7 @@ void flush_tlb_common(struct mm_struct* mm, struct vm_area_struct* vma, unsigned
 
         spin_lock_irqsave(&tlbstate_lock, flags);
         cpu_mask = (mm == FLUSH_ALL ? cpu_all_mask : *mm_cpumask(mm));
-        cpu_clear(smp_processor_id(), cpu_mask);
+        cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
         flush_mm = mm;
         flush_vma = vma;
         flush_addr = addr;
@@ -277,10 +279,10 @@ int send_ipi(int vector, int wait, cpumask_t cpu_mask)
         int ret = 0;
 
         /* Calculate CPUs to send to. */
-        cpus_and(cpu_mask, cpu_mask, cpu_online_map);
+        cpumask_and(&cpu_mask, &cpu_mask, cpu_online_mask);
 
         /* Send the IPI. */
-        for_each_cpu_mask(i, cpu_mask)
+        for_each_cpu(i, &cpu_mask)
         {
                 ipi.vector |= vector;
                 REG_WR(intr_vect, irq_regs[i], rw_ipi, ipi);
@@ -288,7 +290,7 @@ int send_ipi(int vector, int wait, cpumask_t cpu_mask)
 
         /* Wait for IPI to finish on other CPUS */
         if (wait) {
-                for_each_cpu_mask(i, cpu_mask) {
+                for_each_cpu(i, &cpu_mask) {
                         int j;
                         for (j = 0 ; j < 1000; j++) {
                                 ipi = REG_RD(intr_vect, irq_regs[i], rw_ipi);
@@ -314,11 +316,12 @@ int send_ipi(int vector, int wait, cpumask_t cpu_mask)
  */
 int smp_call_function(void (*func)(void *info), void *info, int wait)
 {
-        cpumask_t cpu_mask = CPU_MASK_ALL;
+        cpumask_t cpu_mask;
         struct call_data_struct data;
         int ret;
 
-        cpu_clear(smp_processor_id(), cpu_mask);
+        cpumask_setall(&cpu_mask);
+        cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 
         WARN_ON(irqs_disabled());
 
diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c
index df33ab89d70f..d72ab58fd83e 100644
--- a/arch/cris/mm/init.c
+++ b/arch/cris/mm/init.c
@@ -13,8 +13,6 @@
 #include <linux/bootmem.h>
 #include <asm/tlb.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 unsigned long empty_zero_page;
 
 extern char _stext, _edata, _etext; /* From linkerscript */
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index ed64588ac3a7..fbe5f0dbae06 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -41,8 +41,6 @@
 
 #undef DEBUG
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * BAD_PAGE is the page that is used for page faults when linux
  * is out-of-memory. Older versions of linux just did a
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 23cce999eb1c..c3ffe3e54edc 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -47,21 +47,27 @@
 #include <asm/machvec.h>
 
 #ifdef CONFIG_SMP
-# define FREE_PTE_NR            2048
 # define tlb_fast_mode(tlb)     ((tlb)->nr == ~0U)
 #else
-# define FREE_PTE_NR            0
 # define tlb_fast_mode(tlb)     (1)
 #endif
 
+/*
+ * If we can't allocate a page to make a big batch of page pointers
+ * to work on, then just handle a few from the on-stack structure.
+ */
+#define IA64_GATHER_BUNDLE      8
+
 struct mmu_gather {
         struct mm_struct        *mm;
         unsigned int            nr;             /* == ~0U => fast mode */
+        unsigned int            max;
         unsigned char           fullmm;         /* non-zero means full mm flush */
         unsigned char           need_flush;     /* really unmapped some PTEs? */
         unsigned long           start_addr;
         unsigned long           end_addr;
-        struct page             *pages[FREE_PTE_NR];
+        struct page             **pages;
+        struct page             *local[IA64_GATHER_BUNDLE];
 };
 
 struct ia64_tr_entry {
@@ -90,9 +96,6 @@ extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
 #define RR_RID_MASK     0x00000000ffffff00L
 #define RR_TO_RID(val)  ((val >> 8) & 0xffffff)
 
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * Flush the TLB for address range START to END and, if not in fast mode, release the
  * freed pages that where gathered up to this point.
@@ -147,15 +150,23 @@ ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long e
         }
 }
 
-/*
- * Return a pointer to an initialized struct mmu_gather.
- */
-static inline struct mmu_gather *
-tlb_gather_mmu (struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 {
-        struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
+        unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
 
+        if (addr) {
+                tlb->pages = (void *)addr;
+                tlb->max = PAGE_SIZE / sizeof(void *);
+        }
+}
+
+
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+{
         tlb->mm = mm;
+        tlb->max = ARRAY_SIZE(tlb->local);
+        tlb->pages = tlb->local;
         /*
          * Use fast mode if only 1 CPU is online.
          *
@@ -172,7 +183,6 @@ tlb_gather_mmu (struct mm_struct *mm, unsigned int full_mm_flush)
         tlb->nr = (num_online_cpus() == 1) ? ~0U : 0;
         tlb->fullmm = full_mm_flush;
         tlb->start_addr = ~0UL;
-        return tlb;
 }
 
 /*
@@ -180,7 +190,7 @@ tlb_gather_mmu (struct mm_struct *mm, unsigned int full_mm_flush)
  * collected.
  */
 static inline void
-tlb_finish_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
+tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 {
         /*
          * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
@@ -191,7 +201,8 @@ tlb_finish_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
         /* keep the page table cache within bounds */
         check_pgt_cache();
 
-        put_cpu_var(mmu_gathers);
+        if (tlb->pages != tlb->local)
+                free_pages((unsigned long)tlb->pages, 0);
 }
 
 /*
@@ -199,18 +210,33 @@ tlb_finish_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
  * must be delayed until after the TLB has been flushed (see comments at the beginning of
  * this file).
  */
-static inline void
-tlb_remove_page (struct mmu_gather *tlb, struct page *page)
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
         tlb->need_flush = 1;
 
         if (tlb_fast_mode(tlb)) {
                 free_page_and_swap_cache(page);
-                return;
+                return 1; /* avoid calling tlb_flush_mmu */
         }
+
+        if (!tlb->nr && tlb->pages == tlb->local)
+                __tlb_alloc_page(tlb);
+
         tlb->pages[tlb->nr++] = page;
-        if (tlb->nr >= FREE_PTE_NR)
-                ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
+        VM_BUG_ON(tlb->nr > tlb->max);
+
+        return tlb->max - tlb->nr;
+}
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+        ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        if (!__tlb_remove_page(tlb, page))
+                tlb_flush_mmu(tlb);
 }
 
 /*
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 9a018cde5d84..f114a3b14c6a 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -44,13 +44,16 @@ void show_mem(unsigned int filter)
         pg_data_t *pgdat;
 
         printk(KERN_INFO "Mem-info:\n");
-        show_free_areas();
+        show_free_areas(filter);
         printk(KERN_INFO "Node memory in pages:\n");
         for_each_online_pgdat(pgdat) {
                 unsigned long present;
                 unsigned long flags;
                 int shared = 0, cached = 0, reserved = 0;
+                int nid = pgdat->node_id;
 
+                if (skip_free_areas_node(filter, nid))
+                        continue;
                 pgdat_resize_lock(pgdat, &flags);
                 present = pgdat->node_present_pages;
                 for(i = 0; i < pgdat->node_spanned_pages; i++) {
@@ -64,8 +67,7 @@ void show_mem(unsigned int filter)
                                 if (max_gap < LARGE_GAP)
                                         continue;
 #endif
-                                i = vmemmap_find_next_valid_pfn(pgdat->node_id,
-                                         i) - 1;
+                                i = vmemmap_find_next_valid_pfn(nid, i) - 1;
                                 continue;
                         }
                         if (PageReserved(page))
@@ -81,7 +83,7 @@ void show_mem(unsigned int filter)
                 total_cached += cached;
                 total_shared += shared;
                 printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-                       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+                       "shrd: %10d, swpd: %10d\n", nid,
                        present, reserved, shared, cached);
         }
         printk(KERN_INFO "%ld pages of RAM\n", total_present);
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 82ab1bc6afb1..c641333cd997 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -622,13 +622,16 @@ void show_mem(unsigned int filter)
         pg_data_t *pgdat;
 
         printk(KERN_INFO "Mem-info:\n");
-        show_free_areas();
+        show_free_areas(filter);
         printk(KERN_INFO "Node memory in pages:\n");
         for_each_online_pgdat(pgdat) {
                 unsigned long present;
                 unsigned long flags;
                 int shared = 0, cached = 0, reserved = 0;
+                int nid = pgdat->node_id;
 
+                if (skip_free_areas_node(filter, nid))
+                        continue;
                 pgdat_resize_lock(pgdat, &flags);
                 present = pgdat->node_present_pages;
                 for(i = 0; i < pgdat->node_spanned_pages; i++) {
@@ -638,8 +641,7 @@ void show_mem(unsigned int filter)
                         if (pfn_valid(pgdat->node_start_pfn + i))
                                 page = pfn_to_page(pgdat->node_start_pfn + i);
                         else {
-                                i = vmemmap_find_next_valid_pfn(pgdat->node_id,
-                                         i) - 1;
+                                i = vmemmap_find_next_valid_pfn(nid, i) - 1;
                                 continue;
                         }
                         if (PageReserved(page))
@@ -655,7 +657,7 @@ void show_mem(unsigned int filter)
                 total_cached += cached;
                 total_shared += shared;
                 printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-                       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+                       "shrd: %10d, swpd: %10d\n", nid,
                        present, reserved, shared, cached);
         }
         printk(KERN_INFO "%ld pages of RAM\n", total_present);
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index ed41759efcac..00cb0e26c64e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -36,8 +36,6 @@
 #include <asm/mca.h>
 #include <asm/paravirt.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 extern void ia64_tlb_init (void);
 
 unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;
diff --git a/arch/m32r/Kconfig.debug b/arch/m32r/Kconfig.debug
index 2e1019ddbb22..bb1afc1a31cc 100644
--- a/arch/m32r/Kconfig.debug
+++ b/arch/m32r/Kconfig.debug
@@ -9,15 +9,6 @@ config DEBUG_STACKOVERFLOW
           This option will cause messages to be printed if free stack space
           drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
 config DEBUG_PAGEALLOC
         bool "Debug page memory allocations"
         depends on DEBUG_KERNEL && BROKEN
diff --git a/arch/m32r/include/asm/smp.h b/arch/m32r/include/asm/smp.h
index e67ded1aab91..8accc1bb0263 100644
--- a/arch/m32r/include/asm/smp.h
+++ b/arch/m32r/include/asm/smp.h
@@ -94,8 +94,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #define NO_PROC_ID (0xff)       /* No processor magic marker */
 
-#define PROC_CHANGE_PENALTY     (15)    /* Schedule penalty */
-
 /*
  * M32R-mp IPI
  */
diff --git a/arch/m32r/mm/discontig.c b/arch/m32r/mm/discontig.c
index 5d2858f6eede..2c468e8b5853 100644
--- a/arch/m32r/mm/discontig.c
+++ b/arch/m32r/mm/discontig.c
@@ -149,6 +149,7 @@ unsigned long __init zone_sizes_init(void)
                 zholes_size[ZONE_DMA] = mp->holes;
                 holes += zholes_size[ZONE_DMA];
 
+                node_set_state(nid, N_NORMAL_MEMORY);
                 free_area_init_node(nid, zones_size, start_pfn, zholes_size);
         }
 
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index 73e2205ebf5a..78b660e903da 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -35,8 +35,6 @@ extern char __init_begin, __init_end;
 
 pgd_t swapper_pg_dir[1024];
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * Cache of MMU context last used.
  */
diff --git a/arch/m68k/mm/init_mm.c b/arch/m68k/mm/init_mm.c
index 8bc842554e5b..9113c2f17607 100644
--- a/arch/m68k/mm/init_mm.c
+++ b/arch/m68k/mm/init_mm.c
@@ -32,8 +32,6 @@
 #include <asm/sections.h>
 #include <asm/tlb.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 pg_data_t pg_data_map[MAX_NUMNODES];
 EXPORT_SYMBOL(pg_data_map);
 
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index c8437866d3b7..213f2d671669 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -32,8 +32,6 @@ unsigned int __page_offset;
 EXPORT_SYMBOL(__page_offset);
 
 #else
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static int init_bootmem_done;
 #endif /* CONFIG_MMU */
 
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 5358f90b4dd2..83ed00a5644a 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -76,15 +76,6 @@ config DEBUG_STACKOVERFLOW
           provides another way to check stack overflow happened on kernel mode
           stack usually caused by nested interruption.
 
-config DEBUG_STACK_USAGE
-        bool "Enable stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
 config SMTC_IDLE_HOOK_DEBUG
         bool "Enable additional debug checks before going into CPU idle loop"
         depends on DEBUG_KERNEL && MIPS_MT_SMTC
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 279599e9a779..1aadeb42c5a5 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -64,8 +64,6 @@
 
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * We have up to 8 empty zeroed pages so we can map one of the right colour
  * when needed.  This is necessary only on R4000 / R4400 SC and MC versions
diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c
index 86af0d7d0771..2623d19f4f4c 100644
--- a/arch/mn10300/kernel/irq.c
+++ b/arch/mn10300/kernel/irq.c
@@ -87,7 +87,7 @@ static void mn10300_cpupic_mask_ack(struct irq_data *d)
                 tmp2 = GxICR(irq);
 
                 irq_affinity_online[irq] =
-                        any_online_cpu(*d->affinity);
+                        cpumask_any_and(d->affinity, cpu_online_mask);
                 CROSS_GxICR(irq, irq_affinity_online[irq]) =
                         (tmp & (GxICR_LEVEL | GxICR_ENABLE)) | GxICR_DETECT;
                 tmp = CROSS_GxICR(irq, irq_affinity_online[irq]);
@@ -124,7 +124,8 @@ static void mn10300_cpupic_unmask_clear(struct irq_data *d)
         } else {
                 tmp = GxICR(irq);
 
-                irq_affinity_online[irq] = any_online_cpu(*d->affinity);
+                irq_affinity_online[irq] = cpumask_any_and(d->affinity,
+                                                           cpu_online_mask);
                 CROSS_GxICR(irq, irq_affinity_online[irq]) = (tmp & GxICR_LEVEL) | GxICR_ENABLE | GxICR_DETECT;
                 tmp = CROSS_GxICR(irq, irq_affinity_online[irq]);
         }
@@ -366,11 +367,11 @@ void migrate_irqs(void)
                 if (irqd_is_per_cpu(data))
                         continue;
 
-                if (cpu_isset(self, data->affinity) &&
-                    !cpus_intersects(irq_affinity[irq], cpu_online_map)) {
+                if (cpumask_test_cpu(self, &data->affinity) &&
+                    !cpumask_intersects(&irq_affinity[irq], cpu_online_mask)) {
                         int cpu_id;
-                        cpu_id = first_cpu(cpu_online_map);
-                        cpu_set(cpu_id, data->affinity);
+                        cpu_id = cpumask_first(cpu_online_mask);
+                        cpumask_set_cpu(cpu_id, &data->affinity);
                 }
                 /* We need to operate irq_affinity_online atomically. */
                 arch_local_cli_save(flags);
@@ -381,7 +382,8 @@ void migrate_irqs(void)
                         GxICR(irq) = x & GxICR_LEVEL;
                         tmp = GxICR(irq);
 
-                        new = any_online_cpu(data->affinity);
+                        new = cpumask_any_and(&data->affinity,
+                                              cpu_online_mask);
                         irq_affinity_online[irq] = new;
 
                         CROSS_GxICR(irq, new) =
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index 83fb27912231..9242e9fcc564 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -309,7 +309,7 @@ static void send_IPI_mask(const cpumask_t *cpumask, int irq)
         u16 tmp;
 
         for (i = 0; i < NR_CPUS; i++) {
-                if (cpu_isset(i, *cpumask)) {
+                if (cpumask_test_cpu(i, cpumask)) {
                         /* send IPI */
                         tmp = CROSS_GxICR(irq, i);
                         CROSS_GxICR(irq, i) =
@@ -342,8 +342,8 @@ void send_IPI_allbutself(int irq)
 {
         cpumask_t cpumask;
 
-        cpumask = cpu_online_map;
-        cpu_clear(smp_processor_id(), cpumask);
+        cpumask_copy(&cpumask, cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), &cpumask);
         send_IPI_mask(&cpumask, irq);
 }
 
@@ -393,8 +393,8 @@ int smp_nmi_call_function(smp_call_func_t func, void *info, int wait)
 
         data.func = func;
         data.info = info;
-        data.started = cpu_online_map;
-        cpu_clear(smp_processor_id(), data.started);
+        cpumask_copy(&data.started, cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), &data.started);
         data.wait = wait;
         if (wait)
                 data.finished = data.started;
@@ -410,14 +410,14 @@ int smp_nmi_call_function(smp_call_func_t func, void *info, int wait)
         if (CALL_FUNCTION_NMI_IPI_TIMEOUT > 0) {
                 for (cnt = 0;
                      cnt < CALL_FUNCTION_NMI_IPI_TIMEOUT &&
-                             !cpus_empty(data.started);
+                             !cpumask_empty(&data.started);
                      cnt++)
                         mdelay(1);
 
                 if (wait && cnt < CALL_FUNCTION_NMI_IPI_TIMEOUT) {
                         for (cnt = 0;
                              cnt < CALL_FUNCTION_NMI_IPI_TIMEOUT &&
-                                     !cpus_empty(data.finished);
+                                     !cpumask_empty(&data.finished);
                              cnt++)
                                 mdelay(1);
                 }
@@ -428,10 +428,10 @@ int smp_nmi_call_function(smp_call_func_t func, void *info, int wait)
         } else {
                 /* If timeout value is zero, wait until cpumask has been
                  * cleared */
-                while (!cpus_empty(data.started))
+                while (!cpumask_empty(&data.started))
                         barrier();
                 if (wait)
-                        while (!cpus_empty(data.finished))
+                        while (!cpumask_empty(&data.finished))
                                 barrier();
         }
 
@@ -472,12 +472,12 @@ void stop_this_cpu(void *unused)
 #endif  /* CONFIG_GDBSTUB */
 
         flags = arch_local_cli_save();
-        cpu_clear(smp_processor_id(), cpu_online_map);
+        set_cpu_online(smp_processor_id(), false);
 
         while (!stopflag)
                 cpu_relax();
 
-        cpu_set(smp_processor_id(), cpu_online_map);
+        set_cpu_online(smp_processor_id(), true);
         arch_local_irq_restore(flags);
 }
 
@@ -529,12 +529,13 @@ void smp_nmi_call_function_interrupt(void)
          * execute the function
          */
         smp_mb();
-        cpu_clear(smp_processor_id(), nmi_call_data->started);
+        cpumask_clear_cpu(smp_processor_id(), &nmi_call_data->started);
         (*func)(info);
 
         if (wait) {
                 smp_mb();
-                cpu_clear(smp_processor_id(), nmi_call_data->finished);
+                cpumask_clear_cpu(smp_processor_id(),
+                                  &nmi_call_data->finished);
         }
 }
 
@@ -657,7 +658,7 @@ int __init start_secondary(void *unused)
 {
         smp_cpu_init();
         smp_callin();
-        while (!cpu_isset(smp_processor_id(), smp_commenced_mask))
+        while (!cpumask_test_cpu(smp_processor_id(), &smp_commenced_mask))
                 cpu_relax();
 
         local_flush_tlb();
@@ -780,13 +781,14 @@ static int __init do_boot_cpu(int phy_id)
 
         if (send_status == 0) {
                 /* Allow AP to start initializing */
-                cpu_set(cpu_id, cpu_callout_map);
+                cpumask_set_cpu(cpu_id, &cpu_callout_map);
 
                 /* Wait for setting cpu_callin_map */
                 timeout = 0;
                 do {
                         udelay(1000);
-                        callin_status = cpu_isset(cpu_id, cpu_callin_map);
+                        callin_status = cpumask_test_cpu(cpu_id,
+                                                         &cpu_callin_map);
                 } while (callin_status == 0 && timeout++ < 5000);
 
                 if (callin_status == 0)
@@ -796,9 +798,9 @@ static int __init do_boot_cpu(int phy_id)
         }
 
         if (send_status == GxICR_REQUEST || callin_status == 0) {
-                cpu_clear(cpu_id, cpu_callout_map);
-                cpu_clear(cpu_id, cpu_callin_map);
-                cpu_clear(cpu_id, cpu_initialized);
+                cpumask_clear_cpu(cpu_id, &cpu_callout_map);
+                cpumask_clear_cpu(cpu_id, &cpu_callin_map);
+                cpumask_clear_cpu(cpu_id, &cpu_initialized);
                 cpucount--;
                 return 1;
         }
@@ -833,7 +835,7 @@ static void __init smp_callin(void)
         cpu = smp_processor_id();
         timeout = jiffies + (2 * HZ);
 
-        if (cpu_isset(cpu, cpu_callin_map)) {
+        if (cpumask_test_cpu(cpu, &cpu_callin_map)) {
                 printk(KERN_ERR "CPU#%d already present.\n", cpu);
                 BUG();
         }
@@ -841,7 +843,7 @@ static void __init smp_callin(void)
 
         /* Wait for AP startup 2s total */
         while (time_before(jiffies, timeout)) {
-                if (cpu_isset(cpu, cpu_callout_map))
+                if (cpumask_test_cpu(cpu, &cpu_callout_map))
                         break;
                 cpu_relax();
         }
@@ -861,11 +863,11 @@ static void __init smp_callin(void)
         smp_store_cpu_info(cpu);
 
         /* Allow the boot processor to continue */
-        cpu_set(cpu, cpu_callin_map);
+        cpumask_set_cpu(cpu, &cpu_callin_map);
 }
 
 /**
- * smp_online - Set cpu_online_map
+ * smp_online - Set cpu_online_mask
  */
 static void __init smp_online(void)
 {
@@ -875,7 +877,7 @@ static void __init smp_online(void)
 
         local_irq_enable();
 
-        cpu_set(cpu, cpu_online_map);
+        set_cpu_online(cpu, true);
         smp_wmb();
 }
 
@@ -892,13 +894,13 @@ void __init smp_cpus_done(unsigned int max_cpus)
 /*
  * smp_prepare_boot_cpu - Set up stuff for the boot processor.
  *
- * Set up the cpu_online_map, cpu_callout_map and cpu_callin_map of the boot
+ * Set up the cpu_online_mask, cpu_callout_map and cpu_callin_map of the boot
  * processor (CPU 0).
  */
 void __devinit smp_prepare_boot_cpu(void)
 {
-        cpu_set(0, cpu_callout_map);
-        cpu_set(0, cpu_callin_map);
+        cpumask_set_cpu(0, &cpu_callout_map);
+        cpumask_set_cpu(0, &cpu_callin_map);
         current_thread_info()->cpu = 0;
 }
 
@@ -931,16 +933,16 @@ int __devinit __cpu_up(unsigned int cpu)
                 run_wakeup_cpu(cpu);
 #endif /* CONFIG_HOTPLUG_CPU */
 
-        cpu_set(cpu, smp_commenced_mask);
+        cpumask_set_cpu(cpu, &smp_commenced_mask);
 
         /* Wait 5s total for a response */
         for (timeout = 0 ; timeout < 5000 ; timeout++) {
-                if (cpu_isset(cpu, cpu_online_map))
+                if (cpu_online(cpu))
                         break;
                 udelay(1000);
         }
 
-        BUG_ON(!cpu_isset(cpu, cpu_online_map));
+        BUG_ON(!cpu_online(cpu));
         return 0;
 }
 
@@ -986,7 +988,7 @@ int __cpu_disable(void)
                 return -EBUSY;
 
         migrate_irqs();
-        cpu_clear(cpu, current->active_mm->cpu_vm_mask);
+        cpumask_clear_cpu(cpu, &mm_cpumask(current->active_mm));
         return 0;
 }
 
@@ -1091,13 +1093,13 @@ static int hotplug_cpu_nmi_call_function(cpumask_t cpumask,
         do {
                 mn10300_local_dcache_inv_range(start, end);
                 barrier();
-        } while (!cpus_empty(nmi_call_func_mask_data.started));
+        } while (!cpumask_empty(&nmi_call_func_mask_data.started));
 
         if (wait) {
                 do {
                         mn10300_local_dcache_inv_range(start, end);
                         barrier();
-                } while (!cpus_empty(nmi_call_func_mask_data.finished));
+                } while (!cpumask_empty(&nmi_call_func_mask_data.finished));
         }
 
         spin_unlock(&smp_nmi_call_lock);
@@ -1108,9 +1110,9 @@ static void restart_wakeup_cpu(void)
 {
         unsigned int cpu = smp_processor_id();
 
-        cpu_set(cpu, cpu_callin_map);
+        cpumask_set_cpu(cpu, &cpu_callin_map);
         local_flush_tlb();
-        cpu_set(cpu, cpu_online_map);
+        set_cpu_online(cpu, true);
         smp_wmb();
 }
 
@@ -1141,8 +1143,9 @@ static void sleep_cpu(void *unused)
 static void run_sleep_cpu(unsigned int cpu)
 {
         unsigned long flags;
-        cpumask_t cpumask = cpumask_of(cpu);
+        cpumask_t cpumask;
 
+        cpumask_copy(&cpumask, &cpumask_of(cpu));
         flags = arch_local_cli_save();
         hotplug_cpu_nmi_call_function(cpumask, prepare_sleep_cpu, NULL, 1);
         hotplug_cpu_nmi_call_function(cpumask, sleep_cpu, NULL, 0);
diff --git a/arch/mn10300/mm/cache-smp.c b/arch/mn10300/mm/cache-smp.c
index 4a6e9a4b5b27..2d23b9eeee62 100644
--- a/arch/mn10300/mm/cache-smp.c
+++ b/arch/mn10300/mm/cache-smp.c
@@ -74,7 +74,7 @@ void smp_cache_interrupt(void)
                 break;
         }
 
-        cpu_clear(smp_processor_id(), smp_cache_ipi_map);
+        cpumask_clear_cpu(smp_processor_id(), &smp_cache_ipi_map);
 }
 
 /**
@@ -94,12 +94,12 @@ void smp_cache_call(unsigned long opr_mask,
         smp_cache_mask = opr_mask;
         smp_cache_start = start;
         smp_cache_end = end;
-        smp_cache_ipi_map = cpu_online_map;
-        cpu_clear(smp_processor_id(), smp_cache_ipi_map);
+        cpumask_copy(&smp_cache_ipi_map, cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), &smp_cache_ipi_map);
 
         send_IPI_allbutself(FLUSH_CACHE_IPI);
 
-        while (!cpus_empty(smp_cache_ipi_map))
+        while (!cpumask_empty(&smp_cache_ipi_map))
                 /* nothing. lockup detection does not belong here */
                 mb();
 }
diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c
index 48907cc3bdb7..13801824e3ee 100644
--- a/arch/mn10300/mm/init.c
+++ b/arch/mn10300/mm/init.c
@@ -37,8 +37,6 @@
 #include <asm/tlb.h>
 #include <asm/sections.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 unsigned long highstart_pfn, highend_pfn;
 
 #ifdef CONFIG_MN10300_HAS_ATOMIC_OPS_UNIT
diff --git a/arch/mn10300/mm/tlb-smp.c b/arch/mn10300/mm/tlb-smp.c
index 0b6a5ad1960e..9a777498a916 100644
--- a/arch/mn10300/mm/tlb-smp.c
+++ b/arch/mn10300/mm/tlb-smp.c
@@ -64,7 +64,7 @@ void smp_flush_tlb(void *unused)
 
         cpu_id = get_cpu();
 
-        if (!cpu_isset(cpu_id, flush_cpumask))
+        if (!cpumask_test_cpu(cpu_id, &flush_cpumask))
                 /* This was a BUG() but until someone can quote me the line
                  * from the intel manual that guarantees an IPI to multiple
                  * CPUs is retried _only_ on the erroring CPUs its staying as a
@@ -80,7 +80,7 @@ void smp_flush_tlb(void *unused)
                 local_flush_tlb_page(flush_mm, flush_va);
 
         smp_mb__before_clear_bit();
-        cpu_clear(cpu_id, flush_cpumask);
+        cpumask_clear_cpu(cpu_id, &flush_cpumask);
         smp_mb__after_clear_bit();
 out:
         put_cpu();
@@ -103,11 +103,11 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
          * - we do not send IPIs to as-yet unbooted CPUs.
          */
         BUG_ON(!mm);
-        BUG_ON(cpus_empty(cpumask));
-        BUG_ON(cpu_isset(smp_processor_id(), cpumask));
+        BUG_ON(cpumask_empty(&cpumask));
+        BUG_ON(cpumask_test_cpu(smp_processor_id(), &cpumask));
 
-        cpus_and(tmp, cpumask, cpu_online_map);
-        BUG_ON(!cpus_equal(cpumask, tmp));
+        cpumask_and(&tmp, &cpumask, cpu_online_mask);
+        BUG_ON(!cpumask_equal(&cpumask, &tmp));
 
         /* I'm not happy about this global shared spinlock in the MM hot path,
          * but we'll see how contended it is.
@@ -128,7 +128,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
         /* FIXME: if NR_CPUS>=3, change send_IPI_mask */
         smp_call_function(smp_flush_tlb, NULL, 1);
 
-        while (!cpus_empty(flush_cpumask))
+        while (!cpumask_empty(&flush_cpumask))
                 /* Lockup detection does not belong here */
                 smp_mb();
 
@@ -146,11 +146,11 @@ void flush_tlb_mm(struct mm_struct *mm)
         cpumask_t cpu_mask;
 
         preempt_disable();
-        cpu_mask = mm->cpu_vm_mask;
-        cpu_clear(smp_processor_id(), cpu_mask);
+        cpumask_copy(&cpu_mask, mm_cpumask(mm));
+        cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 
         local_flush_tlb();
-        if (!cpus_empty(cpu_mask))
+        if (!cpumask_empty(&cpu_mask))
                 flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
 
         preempt_enable();
@@ -165,11 +165,11 @@ void flush_tlb_current_task(void)
         cpumask_t cpu_mask;
 
         preempt_disable();
-        cpu_mask = mm->cpu_vm_mask;
-        cpu_clear(smp_processor_id(), cpu_mask);
+        cpumask_copy(&cpu_mask, mm_cpumask(mm));
+        cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 
         local_flush_tlb();
-        if (!cpus_empty(cpu_mask))
+        if (!cpumask_empty(&cpu_mask))
                 flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
 
         preempt_enable();
@@ -186,11 +186,11 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
         cpumask_t cpu_mask;
 
         preempt_disable();
-        cpu_mask = mm->cpu_vm_mask;
-        cpu_clear(smp_processor_id(), cpu_mask);
+        cpumask_copy(&cpu_mask, mm_cpumask(mm));
+        cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 
         local_flush_tlb_page(mm, va);
-        if (!cpus_empty(cpu_mask))
+        if (!cpumask_empty(&cpu_mask))
                 flush_tlb_others(cpu_mask, mm, va);
 
         preempt_enable();
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
index 2e73623feb6b..e8f8037d872b 100644
--- a/arch/parisc/include/asm/smp.h
+++ b/arch/parisc/include/asm/smp.h
@@ -33,15 +33,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #endif /* !ASSEMBLY */
 
-/*
- *      This magic constant controls our willingness to transfer
- *      a process across CPUs. Such a transfer incurs cache and tlb
- *      misses. The current value is inherited from i386. Still needs
- *      to be tuned for parisc.
- */
- 
-#define PROC_CHANGE_PENALTY     15              /* Schedule penalty */
-
 #define raw_smp_processor_id()  (current_thread_info()->cpu)
 
 #else /* CONFIG_SMP */
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 5fa1e273006e..82f364e209fc 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -31,8 +31,6 @@
 #include <asm/mmzone.h>
 #include <asm/sections.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 extern int  data_start;
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -686,7 +684,7 @@ void show_mem(unsigned int filter)
         int shared = 0, cached = 0;
 
         printk(KERN_INFO "Mem-info:\n");
-        show_free_areas();
+        show_free_areas(filter);
 #ifndef CONFIG_DISCONTIGMEM
         i = max_mapnr;
         while (i-- > 0) {
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a3128ca0fe11..423145a6f7ba 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -140,6 +140,7 @@ config PPC
         select IRQ_PER_CPU
         select GENERIC_IRQ_SHOW
         select GENERIC_IRQ_SHOW_LEVEL
+        select HAVE_RCU_TABLE_FREE if SMP
 
 config EARLY_PRINTK
         bool
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index a597dd77b903..e72dcf6a421d 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -35,27 +35,6 @@ config DEBUG_STACKOVERFLOW
           This option will cause messages to be printed if free stack space
           drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
-config DEBUG_PER_CPU_MAPS
-        bool "Debug access to per_cpu maps"
-        depends on DEBUG_KERNEL
-        depends on SMP
-        default n
-        ---help---
-          Say Y to verify that the per_cpu map being accessed has
-          been setup.  Adds a fair amount of code to kernel memory
-          and decreases performance.
-
-          Say N if unsure.
-
 config HCALL_STATS
         bool "Hypervisor call instrumentation"
         depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 761faa7b6964..ac1eb320c7b4 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -176,6 +176,19 @@
                         sleep = <&pmc 0x00300000>;
                 };
 
+                ptp_clock@24E00 {
+                        compatible = "fsl,etsec-ptp";
+                        reg = <0x24E00 0xB0>;
+                        interrupts = <12 0x8 13 0x8>;
+                        interrupt-parent = < &ipic >;
+                        fsl,tclk-period = <10>;
+                        fsl,tmr-prsc    = <100>;
+                        fsl,tmr-add     = <0x999999A4>;
+                        fsl,tmr-fiper1  = <0x3B9AC9F6>;
+                        fsl,tmr-fiper2  = <0x00018696>;
+                        fsl,max-adj     = <659999998>;
+                };
+
                 enet0: ethernet@24000 {
                         #address-cells = <1>;
                         #size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/mpc8572ds.dts b/arch/powerpc/boot/dts/mpc8572ds.dts
index cafc1285c140..f6c04d25e916 100644
--- a/arch/powerpc/boot/dts/mpc8572ds.dts
+++ b/arch/powerpc/boot/dts/mpc8572ds.dts
@@ -324,6 +324,19 @@
                         };
                 };
 
+                ptp_clock@24E00 {
+                        compatible = "fsl,etsec-ptp";
+                        reg = <0x24E00 0xB0>;
+                        interrupts = <68 2 69 2 70 2 71 2>;
+                        interrupt-parent = < &mpic >;
+                        fsl,tclk-period = <5>;
+                        fsl,tmr-prsc = <200>;
+                        fsl,tmr-add = <0xAAAAAAAB>;
+                        fsl,tmr-fiper1 = <0x3B9AC9FB>;
+                        fsl,tmr-fiper2 = <0x3B9AC9FB>;
+                        fsl,max-adj = <499999999>;
+                };
+
                 enet0: ethernet@24000 {
                         #address-cells = <1>;
                         #size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/p2020ds.dts b/arch/powerpc/boot/dts/p2020ds.dts
index 2bcf3683d223..dae403100f2f 100644
--- a/arch/powerpc/boot/dts/p2020ds.dts
+++ b/arch/powerpc/boot/dts/p2020ds.dts
@@ -178,6 +178,19 @@
 
                 };
 
+                ptp_clock@24E00 {
+                        compatible = "fsl,etsec-ptp";
+                        reg = <0x24E00 0xB0>;
+                        interrupts = <68 2 69 2 70 2>;
+                        interrupt-parent = < &mpic >;
+                        fsl,tclk-period = <5>;
+                        fsl,tmr-prsc = <200>;
+                        fsl,tmr-add = <0xCCCCCCCD>;
+                        fsl,tmr-fiper1 = <0x3B9AC9FB>;
+                        fsl,tmr-fiper2 = <0x0001869B>;
+                        fsl,max-adj = <249999999>;
+                };
+
                 enet0: ethernet@24000 {
                         tbi-handle = <&tbi0>;
                         phy-handle = <&phy0>;
diff --git a/arch/powerpc/boot/dts/p2020rdb.dts b/arch/powerpc/boot/dts/p2020rdb.dts
index 3782a58f13be..1d7a05f3021e 100644
--- a/arch/powerpc/boot/dts/p2020rdb.dts
+++ b/arch/powerpc/boot/dts/p2020rdb.dts
@@ -224,6 +224,19 @@
                         status = "disabled";
                 };
 
+                ptp_clock@24E00 {
+                        compatible = "fsl,etsec-ptp";
+                        reg = <0x24E00 0xB0>;
+                        interrupts = <68 2 69 2 70 2>;
+                        interrupt-parent = < &mpic >;
+                        fsl,tclk-period = <5>;
+                        fsl,tmr-prsc = <200>;
+                        fsl,tmr-add = <0xCCCCCCCD>;
+                        fsl,tmr-fiper1 = <0x3B9AC9FB>;
+                        fsl,tmr-fiper2 = <0x0001869B>;
+                        fsl,max-adj = <249999999>;
+                };
+
                 enet0: ethernet@24000 {
                         fixed-link = <1 1 1000 0 0>;
                         phy-connection-type = "rgmii-id";
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index abe8532bd14e..bf301ac62f35 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -31,14 +31,29 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(void);
+struct mmu_gather;
+extern void tlb_remove_table(struct mmu_gather *, void *);
+
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+        unsigned long pgf = (unsigned long)table;
+        BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+        pgf |= shift;
+        tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+        void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+        unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+        pgtable_free(table, shift);
+}
 #else /* CONFIG_SMP */
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
         pgtable_free(table, shift);
 }
-static inline void pte_free_finish(void) { }
 #endif /* !CONFIG_SMP */
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index d8529ef13b23..37c353e8af7c 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -139,10 +139,12 @@ static inline struct thread_info *current_thread_info(void)
 #define TLF_NAPPING             0       /* idle thread enabled NAP mode */
 #define TLF_SLEEPING            1       /* suspend code enabled SLEEP mode */
 #define TLF_RESTORE_SIGMASK     2       /* Restore signal mask in do_signal */
+#define TLF_LAZY_MMU            3       /* tlb_batch is active */
 
 #define _TLF_NAPPING            (1 << TLF_NAPPING)
 #define _TLF_SLEEPING           (1 << TLF_SLEEPING)
 #define _TLF_RESTORE_SIGMASK    (1 << TLF_RESTORE_SIGMASK)
+#define _TLF_LAZY_MMU           (1 << TLF_LAZY_MMU)
 
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 095043d79946..91e52df3d81d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -395,6 +395,9 @@ struct task_struct *__switch_to(struct task_struct *prev,
         struct thread_struct *new_thread, *old_thread;
         unsigned long flags;
         struct task_struct *last;
+#ifdef CONFIG_PPC_BOOK3S_64
+        struct ppc64_tlb_batch *batch;
+#endif
 
 #ifdef CONFIG_SMP
         /* avoid complexity of lazy save/restore of fpu
@@ -513,7 +516,17 @@ struct task_struct *__switch_to(struct task_struct *prev,
                 old_thread->accum_tb += (current_tb - start_tb);
                 new_thread->start_tb = current_tb;
         }
-#endif
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+        batch = &__get_cpu_var(ppc64_tlb_batch);
+        if (batch->active) {
+                current_thread_info()->local_flags |= _TLF_LAZY_MMU;
+                if (batch->index)
+                        __flush_tlb_pending(batch);
+                batch->active = 0;
+        }
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
         local_irq_save(flags);
 
@@ -528,6 +541,14 @@ struct task_struct *__switch_to(struct task_struct *prev,
         hard_irq_disable();
         last = _switch(old_thread, new_thread);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+        if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
+                current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
+                batch = &__get_cpu_var(ppc64_tlb_batch);
+                batch->active = 1;
+        }
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
         local_irq_restore(flags);
 
         return last;
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 6a3997f98dfb..af40c8768a78 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -33,110 +33,6 @@
 
 #include "mmu_decl.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-#ifdef CONFIG_SMP
-
-/*
- * Handle batching of page table freeing on SMP. Page tables are
- * queued up and send to be freed later by RCU in order to avoid
- * freeing a page table page that is being walked without locks
- */
-
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-        struct rcu_head rcu;
-        unsigned int    index;
-        unsigned long   tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-        ((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-          / sizeof(unsigned long))
-
-static void pte_free_smp_sync(void *arg)
-{
-        /* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(void *table, unsigned shift)
-{
-        pte_freelist_forced_free++;
-
-        smp_call_function(pte_free_smp_sync, NULL, 1);
-
-        pgtable_free(table, shift);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-        struct pte_freelist_batch *batch =
-                container_of(head, struct pte_freelist_batch, rcu);
-        unsigned int i;
-
-        for (i = 0; i < batch->index; i++) {
-                void *table = (void *)(batch->tables[i] & ~MAX_PGTABLE_INDEX_SIZE);
-                unsigned shift = batch->tables[i] & MAX_PGTABLE_INDEX_SIZE;
-
-                pgtable_free(table, shift);
-        }
-
-        free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-        call_rcu_sched(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
-        /* This is safe since tlb_gather_mmu has disabled preemption */
-        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-        unsigned long pgf;
-
-        if (atomic_read(&tlb->mm->mm_users) < 2 ||
-            cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
-                pgtable_free(table, shift);
-                return;
-        }
-
-        if (*batchp == NULL) {
-                *batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-                if (*batchp == NULL) {
-                        pgtable_free_now(table, shift);
-                        return;
-                }
-                (*batchp)->index = 0;
-        }
-        BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-        pgf = (unsigned long)table | shift;
-        (*batchp)->tables[(*batchp)->index++] = pgf;
-        if ((*batchp)->index == PTE_FREELIST_SIZE) {
-                pte_free_submit(*batchp);
-                *batchp = NULL;
-        }
-}
-
-void pte_free_finish(void)
-{
-        /* This is safe since tlb_gather_mmu has disabled preemption */
-        struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-        if (*batchp == NULL)
-                return;
-        pte_free_submit(*batchp);
-        *batchp = NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 static inline int is_exec_fault(void)
 {
         return current->thread.regs && TRAP(current->thread.regs) == 0x400;
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 690566b66e8e..27b863c14941 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -71,9 +71,6 @@ void tlb_flush(struct mmu_gather *tlb)
                  */
                 _tlbia();
         }
-
-        /* Push out batch of freed page tables */
-        pte_free_finish();
 }
 
 /*
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index c14d09f614f3..31f18207970b 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
 
 void tlb_flush(struct mmu_gather *tlb)
 {
-        struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+        struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
 
         /* If there's a TLB batch pending, then we must flush it because the
          * pages are going to be freed and we really don't want to have a CPU
@@ -164,8 +164,7 @@ void tlb_flush(struct mmu_gather *tlb)
         if (tlbbatch->index)
                 __flush_tlb_pending(tlbbatch);
 
-        /* Push out batch of freed page tables */
-        pte_free_finish();
+        put_cpu_var(ppc64_tlb_batch);
 }
 
 /**
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 2a030d89bbc6..0bdad3aecc67 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -299,9 +299,6 @@ EXPORT_SYMBOL(flush_tlb_range);
 void tlb_flush(struct mmu_gather *tlb)
 {
         flush_tlb_mm(tlb->mm);
-
-        /* Push out batch of freed page tables */
-        pte_free_finish();
 }
 
 /*
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 9074a54c4d10..77eee5477a52 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -29,65 +29,77 @@
 #include <asm/smp.h>
 #include <asm/tlbflush.h>
 
-#ifndef CONFIG_SMP
-#define TLB_NR_PTRS     1
-#else
-#define TLB_NR_PTRS     508
-#endif
-
 struct mmu_gather {
         struct mm_struct *mm;
         unsigned int fullmm;
         unsigned int nr_ptes;
         unsigned int nr_pxds;
-        void *array[TLB_NR_PTRS];
+        unsigned int max;
+        void **array;
+        void *local[8];
 };
 
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm,
-                                                unsigned int full_mm_flush)
+static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 {
-        struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
+        unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
 
+        if (addr) {
+                tlb->array = (void *) addr;
+                tlb->max = PAGE_SIZE / sizeof(void *);
+        }
+}
+
+static inline void tlb_gather_mmu(struct mmu_gather *tlb,
+                                  struct mm_struct *mm,
+                                  unsigned int full_mm_flush)
+{
         tlb->mm = mm;
+        tlb->max = ARRAY_SIZE(tlb->local);
+        tlb->array = tlb->local;
         tlb->fullmm = full_mm_flush;
-        tlb->nr_ptes = 0;
-        tlb->nr_pxds = TLB_NR_PTRS;
         if (tlb->fullmm)
                 __tlb_flush_mm(mm);
-        return tlb;
+        else
+                __tlb_alloc_page(tlb);
+        tlb->nr_ptes = 0;
+        tlb->nr_pxds = tlb->max;
 }
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb,
-                                 unsigned long start, unsigned long end)
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-        if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < TLB_NR_PTRS))
+        if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < tlb->max))
                 __tlb_flush_mm(tlb->mm);
         while (tlb->nr_ptes > 0)
                 page_table_free_rcu(tlb->mm, tlb->array[--tlb->nr_ptes]);
-        while (tlb->nr_pxds < TLB_NR_PTRS)
+        while (tlb->nr_pxds < tlb->max)
                 crst_table_free_rcu(tlb->mm, tlb->array[tlb->nr_pxds++]);
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
                                   unsigned long start, unsigned long end)
 {
-        tlb_flush_mmu(tlb, start, end);
+        tlb_flush_mmu(tlb);
 
         rcu_table_freelist_finish();
 
         /* keep the page table cache within bounds */
         check_pgt_cache();
 
-        put_cpu_var(mmu_gathers);
+        if (tlb->array != tlb->local)
+                free_pages((unsigned long) tlb->array, 0);
 }
 
 /*
  * Release the page cache reference for a pte removed by
- * tlb_ptep_clear_flush. In both flush modes the tlb fo a page cache page
+ * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
  * has already been freed, so just do free_page_and_swap_cache.
  */
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        free_page_and_swap_cache(page);
+        return 1; /* avoid calling tlb_flush_mmu */
+}
+
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
         free_page_and_swap_cache(page);
@@ -103,7 +115,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
         if (!tlb->fullmm) {
                 tlb->array[tlb->nr_ptes++] = pte;
                 if (tlb->nr_ptes >= tlb->nr_pxds)
-                        tlb_flush_mmu(tlb, 0, 0);
+                        tlb_flush_mmu(tlb);
         } else
                 page_table_free(tlb->mm, (unsigned long *) pte);
 }
@@ -124,7 +136,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
         if (!tlb->fullmm) {
                 tlb->array[--tlb->nr_pxds] = pmd;
                 if (tlb->nr_ptes >= tlb->nr_pxds)
-                        tlb_flush_mmu(tlb, 0, 0);
+                        tlb_flush_mmu(tlb);
         } else
                 crst_table_free(tlb->mm, (unsigned long *) pmd);
 #endif
@@ -146,7 +158,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
         if (!tlb->fullmm) {
                 tlb->array[--tlb->nr_pxds] = pud;
                 if (tlb->nr_ptes >= tlb->nr_pxds)
-                        tlb_flush_mmu(tlb, 0, 0);
+                        tlb_flush_mmu(tlb);
         } else
                 crst_table_free(tlb->mm, (unsigned long *) pud);
 #endif
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 8d4330642512..14c6fae6fe6b 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -36,7 +36,6 @@ struct rcu_table_freelist {
         ((PAGE_SIZE - sizeof(struct rcu_table_freelist)) \
           / sizeof(unsigned long))
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 static DEFINE_PER_CPU(struct rcu_table_freelist *, rcu_table_freelist);
 
 static void __page_table_free(struct mm_struct *mm, unsigned long *table);
diff --git a/arch/score/Kconfig.debug b/arch/score/Kconfig.debug
index 451ed54ce646..a1f346df0a71 100644
--- a/arch/score/Kconfig.debug
+++ b/arch/score/Kconfig.debug
@@ -16,15 +16,6 @@ config CMDLINE
           other cases you can specify kernel args so that you don't have
           to set them up in board prom initialization routines.
 
-config DEBUG_STACK_USAGE
-        bool "Enable stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
 config RUNTIME_DEBUG
         bool "Enable run-time debugging"
         depends on DEBUG_KERNEL
diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c
index 50fdec54c70a..cee6bce1e30c 100644
--- a/arch/score/mm/init.c
+++ b/arch/score/mm/init.c
@@ -38,8 +38,6 @@
 #include <asm/sections.h>
 #include <asm/tlb.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 unsigned long empty_zero_page;
 EXPORT_SYMBOL_GPL(empty_zero_page);
 
diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug
index 1553d56cf4e0..c1d5a820b1aa 100644
--- a/arch/sh/Kconfig.debug
+++ b/arch/sh/Kconfig.debug
@@ -28,15 +28,6 @@ config STACK_DEBUG
           every function call and will therefore incur a major
           performance hit. Most users should say N.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
 config 4KSTACKS
         bool "Use 4Kb for kernel stacks instead of 8Kb"
         depends on DEBUG_KERNEL && (MMU || BROKEN) && !PAGE_SIZE_64KB
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 75abb38dffd5..6c308d8b9a50 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -23,8 +23,6 @@ struct mmu_gather {
         unsigned long           start, end;
 };
 
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static inline void init_tlb_gather(struct mmu_gather *tlb)
 {
         tlb->start = TASK_SIZE;
@@ -36,17 +34,13 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
         }
 }
 
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
 {
-        struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
         tlb->mm = mm;
         tlb->fullmm = full_mm_flush;
 
         init_tlb_gather(tlb);
-
-        return tlb;
 }
 
 static inline void
@@ -57,8 +51,6 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 
         /* keep the page table cache within bounds */
         check_pgt_cache();
-
-        put_cpu_var(mmu_gathers);
 }
 
 static inline void
@@ -91,7 +83,21 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
         }
 }
 
-#define tlb_remove_page(tlb,page)       free_page_and_swap_cache(page)
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+}
+
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        free_page_and_swap_cache(page);
+        return 1; /* avoid calling tlb_flush_mmu */
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        __tlb_remove_page(tlb, page);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)   pte_free((tlb)->mm, ptep)
 #define pmd_free_tlb(tlb, pmdp, addr)   pmd_free((tlb)->mm, pmdp)
 #define pud_free_tlb(tlb, pudp, addr)   pud_free((tlb)->mm, pudp)
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 0d3f912e3334..58a93fb3d965 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -28,7 +28,6 @@
 #include <asm/cache.h>
 #include <asm/sizes.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 void __init generic_mem_init(void)
diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug
index d9a795efbc04..6db35fba79fd 100644
--- a/arch/sparc/Kconfig.debug
+++ b/arch/sparc/Kconfig.debug
@@ -6,15 +6,6 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
-config DEBUG_STACK_USAGE
-        bool "Enable stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
 config DEBUG_DCFLUSH
         bool "D-cache flush debugging"
         depends on SPARC64 && DEBUG_KERNEL
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5bdfa2c6e400..4e5e0878144f 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -78,4 +78,7 @@ static inline void check_pgt_cache(void)
         quicklist_trim(0, NULL, 25, 16);
 }
 
+#define __pte_free_tlb(tlb, pte, addr)  pte_free((tlb)->mm, pte)
+#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+
 #endif /* _SPARC64_PGALLOC_H */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index b77128c80524..1e03c5a6b4f7 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -655,9 +655,11 @@ static inline int pte_special(pte_t pte)
 #define pte_unmap(pte)                  do { } while (0)
 
 /* Actual page table PTE updates.  */
-extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig);
+extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+                          pte_t *ptep, pte_t orig, int fullmm);
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+                             pte_t *ptep, pte_t pte, int fullmm)
 {
         pte_t orig = *ptep;
 
@@ -670,12 +672,19 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *p
          *             and SUN4V pte layout, so this inline test is fine.
          */
         if (likely(mm != &init_mm) && (pte_val(orig) & _PAGE_VALID))
-                tlb_batch_add(mm, addr, ptep, orig);
+                tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
+#define set_pte_at(mm,addr,ptep,pte)    \
+        __set_pte_at((mm), (addr), (ptep), (pte), 0)
+
 #define pte_clear(mm,addr,ptep)         \
         set_pte_at((mm), (addr), (ptep), __pte(0UL))
 
+#define __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
+#define pte_clear_not_present_full(mm,addr,ptep,fullmm) \
+        __set_pte_at((mm), (addr), (ptep), __pte(0UL), (fullmm))
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 #define __HAVE_ARCH_MOVE_PTE
 #define move_pte(pte, prot, old_addr, new_addr)                         \
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index dca406b9b6fc..190e18913cc6 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -7,66 +7,11 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 
-#define TLB_BATCH_NR    192
-
-/*
- * For UP we don't need to worry about TLB flush
- * and page free order so much..
- */
-#ifdef CONFIG_SMP
-  #define FREE_PTE_NR   506
-  #define tlb_fast_mode(bp) ((bp)->pages_nr == ~0U)
-#else
-  #define FREE_PTE_NR   1
-  #define tlb_fast_mode(bp) 1
-#endif
-
-struct mmu_gather {
-        struct mm_struct *mm;
-        unsigned int pages_nr;
-        unsigned int need_flush;
-        unsigned int fullmm;
-        unsigned int tlb_nr;
-        unsigned long vaddrs[TLB_BATCH_NR];
-        struct page *pages[FREE_PTE_NR];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 #ifdef CONFIG_SMP
 extern void smp_flush_tlb_pending(struct mm_struct *,
                                   unsigned long, unsigned long *);
 #endif
 
-extern void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
-extern void flush_tlb_pending(void);
-
-static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
-{
-        struct mmu_gather *mp = &get_cpu_var(mmu_gathers);
-
-        BUG_ON(mp->tlb_nr);
-
-        mp->mm = mm;
-        mp->pages_nr = num_online_cpus() > 1 ? 0U : ~0U;
-        mp->fullmm = full_mm_flush;
-
-        return mp;
-}
-
-
-static inline void tlb_flush_mmu(struct mmu_gather *mp)
-{
-        if (!mp->fullmm)
-                flush_tlb_pending();
-        if (mp->need_flush) {
-                free_pages_and_swap_cache(mp->pages, mp->pages_nr);
-                mp->pages_nr = 0;
-                mp->need_flush = 0;
-        }
-
-}
-
 #ifdef CONFIG_SMP
 extern void smp_flush_tlb_mm(struct mm_struct *mm);
 #define do_flush_tlb_mm(mm) smp_flush_tlb_mm(mm)
@@ -74,38 +19,14 @@ extern void smp_flush_tlb_mm(struct mm_struct *mm);
 #define do_flush_tlb_mm(mm) __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT)
 #endif
 
-static inline void tlb_finish_mmu(struct mmu_gather *mp, unsigned long start, unsigned long end)
-{
-        tlb_flush_mmu(mp);
-
-        if (mp->fullmm)
-                mp->fullmm = 0;
-
-        /* keep the page table cache within bounds */
-        check_pgt_cache();
-
-        put_cpu_var(mmu_gathers);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *mp, struct page *page)
-{
-        if (tlb_fast_mode(mp)) {
-                free_page_and_swap_cache(page);
-                return;
-        }
-        mp->need_flush = 1;
-        mp->pages[mp->pages_nr++] = page;
-        if (mp->pages_nr >= FREE_PTE_NR)
-                tlb_flush_mmu(mp);
-}
-
-#define tlb_remove_tlb_entry(mp,ptep,addr) do { } while (0)
-#define pte_free_tlb(mp, ptepage, addr) pte_free((mp)->mm, ptepage)
-#define pmd_free_tlb(mp, pmdp, addr) pmd_free((mp)->mm, pmdp)
-#define pud_free_tlb(tlb,pudp, addr) __pud_free_tlb(tlb,pudp,addr)
+extern void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
+extern void flush_tlb_pending(void);
 
-#define tlb_migrate_finish(mm)  do { } while (0)
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma)   do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#define tlb_flush(tlb)  flush_tlb_pending()
+
+#include <asm-generic/tlb.h>
 
 #endif /* _SPARC64_TLB_H */
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index fbb675dbe0c9..2ef463494153 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -5,9 +5,17 @@
 #include <asm/mmu_context.h>
 
 /* TSB flush operations. */
-struct mmu_gather;
+
+#define TLB_BATCH_NR    192
+
+struct tlb_batch {
+        struct mm_struct *mm;
+        unsigned long tlb_nr;
+        unsigned long vaddrs[TLB_BATCH_NR];
+};
+
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
-extern void flush_tsb_user(struct mmu_gather *mp);
+extern void flush_tsb_user(struct tlb_batch *tb);
 
 /* TLB flush operations. */
 
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 3609bdee9ed2..3249d3f3234d 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -82,7 +82,7 @@ static void prom_sync_me(void)
                              "nop\n\t" : : "r" (&trapbase));
 
         prom_printf("PROM SYNC COMMAND...\n");
-        show_free_areas();
+        show_free_areas(0);
         if(current->pid != 0) {
                 local_irq_enable();
                 sys_sync();
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 4c31e2b6e71b..ca217327e8d2 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -37,8 +37,6 @@
 #include <asm/prom.h>
 #include <asm/leon.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 unsigned long *sparc_valid_addr_bitmap;
 EXPORT_SYMBOL(sparc_valid_addr_bitmap);
 
@@ -78,7 +76,7 @@ void __init kmap_init(void)
 void show_mem(unsigned int filter)
 {
         printk("Mem-info:\n");
-        show_free_areas();
+        show_free_areas(filter);
         printk("Free swap:       %6ldkB\n",
                nr_swap_pages << (PAGE_SHIFT-10));
         printk("%ld pages of RAM\n", totalram_pages);
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index d8f21e24a82f..b1f279cd00bf 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -19,33 +19,34 @@
 
 /* Heavily inspired by the ppc64 code.  */
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
 
 void flush_tlb_pending(void)
 {
-        struct mmu_gather *mp = &get_cpu_var(mmu_gathers);
+        struct tlb_batch *tb = &get_cpu_var(tlb_batch);
 
-        if (mp->tlb_nr) {
-                flush_tsb_user(mp);
+        if (tb->tlb_nr) {
+                flush_tsb_user(tb);
 
-                if (CTX_VALID(mp->mm->context)) {
+                if (CTX_VALID(tb->mm->context)) {
 #ifdef CONFIG_SMP
-                        smp_flush_tlb_pending(mp->mm, mp->tlb_nr,
-                                              &mp->vaddrs[0]);
+                        smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
+                                              &tb->vaddrs[0]);
 #else
-                        __flush_tlb_pending(CTX_HWBITS(mp->mm->context),
-                                            mp->tlb_nr, &mp->vaddrs[0]);
+                        __flush_tlb_pending(CTX_HWBITS(tb->mm->context),
+                                            tb->tlb_nr, &tb->vaddrs[0]);
 #endif
                 }
-                mp->tlb_nr = 0;
+                tb->tlb_nr = 0;
         }
 
-        put_cpu_var(mmu_gathers);
+        put_cpu_var(tlb_batch);
 }
 
-void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig)
+void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+                   pte_t *ptep, pte_t orig, int fullmm)
 {
-        struct mmu_gather *mp = &__get_cpu_var(mmu_gathers);
+        struct tlb_batch *tb = &get_cpu_var(tlb_batch);
         unsigned long nr;
 
         vaddr &= PAGE_MASK;
@@ -77,21 +78,25 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t
 
 no_cache_flush:
 
-        if (mp->fullmm)
+        if (fullmm) {
+                put_cpu_var(tlb_batch);
                 return;
+        }
 
-        nr = mp->tlb_nr;
+        nr = tb->tlb_nr;
 
-        if (unlikely(nr != 0 && mm != mp->mm)) {
+        if (unlikely(nr != 0 && mm != tb->mm)) {
                 flush_tlb_pending();
                 nr = 0;
         }
 
         if (nr == 0)
-                mp->mm = mm;
+                tb->mm = mm;
 
-        mp->vaddrs[nr] = vaddr;
-        mp->tlb_nr = ++nr;
+        tb->vaddrs[nr] = vaddr;
+        tb->tlb_nr = ++nr;
         if (nr >= TLB_BATCH_NR)
                 flush_tlb_pending();
+
+        put_cpu_var(tlb_batch);
 }
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 101d7c82870b..948461513499 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -47,12 +47,13 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
         }
 }
 
-static void __flush_tsb_one(struct mmu_gather *mp, unsigned long hash_shift, unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+                            unsigned long tsb, unsigned long nentries)
 {
         unsigned long i;
 
-        for (i = 0; i < mp->tlb_nr; i++) {
-                unsigned long v = mp->vaddrs[i];
+        for (i = 0; i < tb->tlb_nr; i++) {
+                unsigned long v = tb->vaddrs[i];
                 unsigned long tag, ent, hash;
 
                 v &= ~0x1UL;
@@ -65,9 +66,9 @@ static void __flush_tsb_one(struct mmu_gather *mp, unsigned long hash_shift, uns
         }
 }
 
-void flush_tsb_user(struct mmu_gather *mp)
+void flush_tsb_user(struct tlb_batch *tb)
 {
-        struct mm_struct *mm = mp->mm;
+        struct mm_struct *mm = tb->mm;
         unsigned long nentries, base, flags;
 
         spin_lock_irqsave(&mm->context.lock, flags);
@@ -76,7 +77,7 @@ void flush_tsb_user(struct mmu_gather *mp)
         nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
         if (tlb_type == cheetah_plus || tlb_type == hypervisor)
                 base = __pa(base);
-        __flush_tsb_one(mp, PAGE_SHIFT, base, nentries);
+        __flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
 
 #ifdef CONFIG_HUGETLB_PAGE
         if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
@@ -84,7 +85,7 @@ void flush_tsb_user(struct mmu_gather *mp)
                 nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
                 if (tlb_type == cheetah_plus || tlb_type == hypervisor)
                         base = __pa(base);
-                __flush_tsb_one(mp, HPAGE_SHIFT, base, nentries);
+                __flush_tsb_one(tb, HPAGE_SHIFT, base, nentries);
         }
 #endif
         spin_unlock_irqrestore(&mm->context.lock, flags);
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index e32b0c23c4c8..635e1bfb1c5d 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -339,6 +339,14 @@ config NO_IOPORT
 
 source "drivers/pci/Kconfig"
 
+config HOTPLUG
+        bool "Support for hot-pluggable devices"
+        ---help---
+          Say Y here if you want to plug devices into your computer while
+          the system is running, and be able to use them quickly.  In many
+          cases, the devices can likewise be unplugged at any time too.
+          One well-known example of this is USB.
+
 source "drivers/pci/hotplug/Kconfig"
 
 endmenu
diff --git a/arch/tile/Kconfig.debug b/arch/tile/Kconfig.debug
index 9bc161a02c71..ddbfc3322d7f 100644
--- a/arch/tile/Kconfig.debug
+++ b/arch/tile/Kconfig.debug
@@ -21,15 +21,6 @@ config DEBUG_STACKOVERFLOW
           This option will cause messages to be printed if free stack space
           drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
 config DEBUG_EXTRA_FLAGS
         string "Additional compiler arguments when building with '-g'"
         depends on DEBUG_INFO
diff --git a/arch/tile/configs/tile_defconfig b/arch/tile/configs/tile_defconfig
deleted file mode 100644
index 0fe54445fda5..000000000000
--- a/arch/tile/configs/tile_defconfig
+++ /dev/null
@@ -1,71 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="usr/contents.txt"
-CONFIG_EXPERT=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_HZ_100=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-CONFIG_IPV6=y
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=y
-# CONFIG_NETDEV_10000 is not set
-# CONFIG_WLAN is not set
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_HW_RANDOM is not set
-CONFIG_WATCHDOG=y
-CONFIG_WATCHDOG_NOWAYOUT=y
-# CONFIG_HID_SUPPORT is not set
-CONFIG_RTC_CLASS=y
-# CONFIG_RTC_INTF_SYSFS is not set
-# CONFIG_RTC_INTF_PROC is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_FUSE_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=m
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_NFS_FS=m
-CONFIG_NFS_V3=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_FRAME_WARN=2048
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_SPINLOCK_SLEEP=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_VM=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_EXTRA_FLAGS="-femit-struct-debug-baseonly"
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
new file mode 100644
index 000000000000..09f1c7fad8bf
--- /dev/null
+++ b/arch/tile/configs/tilegx_defconfig
@@ -0,0 +1,1833 @@
+#
+# Automatically generated make config: don't edit
+# Linux/tilegx 2.6.39-rc5 Kernel Configuration
+# Wed May  4 11:08:04 2011
+#
+CONFIG_TILE=y
+CONFIG_MMU=y
+CONFIG_GENERIC_CSUM=y
+CONFIG_SEMAPHORE_SLEEPERS=y
+CONFIG_HAVE_ARCH_ALLOC_REMAP=y
+CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
+CONFIG_SYS_SUPPORTS_HUGETLBFS=y
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_DEFAULT_MIGRATION_COST=10000000
+CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
+CONFIG_ARCH_DMA_ADDR_T_64BIT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
+CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_SMP=y
+# CONFIG_DEBUG_COPY_FROM_USER is not set
+CONFIG_HVC_TILE=y
+CONFIG_TILEGX=y
+CONFIG_64BIT=y
+CONFIG_ARCH_DEFCONFIG="arch/tile/configs/tilegx_defconfig"
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_CONSTRUCTORS=y
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_CROSS_COMPILE=""
+CONFIG_LOCALVERSION=""
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+# CONFIG_FHANDLE is not set
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_AUDIT=y
+CONFIG_HAVE_GENERIC_HARDIRQS=y
+
+#
+# IRQ subsystem
+#
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_IRQ_SHOW=y
+CONFIG_GENERIC_PENDING_IRQ=y
+
+#
+# RCU Subsystem
+#
+CONFIG_TREE_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_FANOUT=64
+# CONFIG_RCU_FANOUT_EXACT is not set
+# CONFIG_RCU_FAST_NO_HZ is not set
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=19
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_NS=y
+# CONFIG_CGROUP_FREEZER is not set
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CPUSETS=y
+CONFIG_PROC_PID_CPUSET=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_BLK_CGROUP=y
+# CONFIG_DEBUG_BLK_CGROUP is not set
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
+CONFIG_NET_NS=y
+# CONFIG_SCHED_AUTOGROUP is not set
+CONFIG_MM_OWNER=y
+# CONFIG_SYSFS_DEPRECATED is not set
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="usr/contents.txt"
+CONFIG_INITRAMFS_ROOT_UID=0
+CONFIG_INITRAMFS_ROOT_GID=0
+CONFIG_RD_GZIP=y
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+CONFIG_INITRAMFS_COMPRESSION_NONE=y
+# CONFIG_INITRAMFS_COMPRESSION_GZIP is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_EXPERT=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_EMBEDDED=y
+
+#
+# Kernel Performance Events And Counters
+#
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_PCI_QUIRKS=y
+CONFIG_SLUB_DEBUG=y
+# CONFIG_COMPAT_BRK is not set
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
+# CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+CONFIG_USE_GENERIC_SMP_HELPERS=y
+
+#
+# GCOV-based kernel profiling
+#
+# CONFIG_GCOV_KERNEL is not set
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_STOP_MACHINE=y
+CONFIG_BLOCK=y
+CONFIG_BLK_DEV_BSG=y
+CONFIG_BLK_DEV_INTEGRITY=y
+# CONFIG_BLK_DEV_THROTTLING is not set
+CONFIG_BLOCK_COMPAT=y
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_CFQ_GROUP_IOSCHED=y
+# CONFIG_DEFAULT_DEADLINE is not set
+CONFIG_DEFAULT_CFQ=y
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_PADATA=y
+# CONFIG_INLINE_SPIN_TRYLOCK is not set
+# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK is not set
+# CONFIG_INLINE_SPIN_LOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQ is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set
+CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_INLINE_SPIN_UNLOCK_BH is not set
+CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
+# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_READ_TRYLOCK is not set
+# CONFIG_INLINE_READ_LOCK is not set
+# CONFIG_INLINE_READ_LOCK_BH is not set
+# CONFIG_INLINE_READ_LOCK_IRQ is not set
+# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set
+CONFIG_INLINE_READ_UNLOCK=y
+# CONFIG_INLINE_READ_UNLOCK_BH is not set
+CONFIG_INLINE_READ_UNLOCK_IRQ=y
+# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_WRITE_TRYLOCK is not set
+# CONFIG_INLINE_WRITE_LOCK is not set
+# CONFIG_INLINE_WRITE_LOCK_BH is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQ is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set
+CONFIG_INLINE_WRITE_UNLOCK=y
+# CONFIG_INLINE_WRITE_UNLOCK_BH is not set
+CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
+# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set
+CONFIG_MUTEX_SPIN_ON_OWNER=y
+
+#
+# Tilera-specific configuration
+#
+CONFIG_NR_CPUS=100
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+CONFIG_HZ_100=y
+# CONFIG_HZ_250 is not set
+# CONFIG_HZ_300 is not set
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=100
+CONFIG_SCHED_HRTICK=y
+# CONFIG_KEXEC is not set
+CONFIG_COMPAT=y
+CONFIG_SYSVIPC_COMPAT=y
+# CONFIG_HIGHMEM is not set
+CONFIG_NUMA=y
+CONFIG_NODES_SHIFT=2
+CONFIG_PAGE_OFFSET=0xC0000000
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_DISCONTIGMEM_MANUAL=y
+CONFIG_DISCONTIGMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_NEED_MULTIPLE_NODES=y
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_COMPACTION is not set
+CONFIG_MIGRATION=y
+CONFIG_PHYS_ADDR_T_64BIT=y
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_VIRT_TO_BUS=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
+# CONFIG_CMDLINE_BOOL is not set
+CONFIG_VMALLOC_RESERVE=0x1000000
+CONFIG_HARDWALL=y
+CONFIG_KERNEL_PL=1
+
+#
+# Bus options
+#
+CONFIG_PCI=y
+CONFIG_PCI_DOMAINS=y
+# CONFIG_NO_IOMEM is not set
+# CONFIG_NO_IOPORT is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+CONFIG_PCI_DEBUG=y
+# CONFIG_PCI_STUB is not set
+# CONFIG_PCI_IOV is not set
+# CONFIG_HOTPLUG_PCI is not set
+
+#
+# Executable file formats
+#
+CONFIG_KCORE_ELF=y
+CONFIG_BINFMT_ELF=y
+CONFIG_COMPAT_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
+CONFIG_BINFMT_MISC=y
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=y
+CONFIG_XFRM_SUB_POLICY=y
+CONFIG_XFRM_MIGRATE=y
+CONFIG_XFRM_STATISTICS=y
+CONFIG_XFRM_IPCOMP=m
+CONFIG_NET_KEY=m
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+# CONFIG_IP_FIB_TRIE_STATS is not set
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_ROUTE_CLASSID=y
+# CONFIG_IP_PNP is not set
+CONFIG_NET_IPIP=m
+# CONFIG_NET_IPGRE_DEMUX is not set
+CONFIG_IP_MROUTE=y
+# CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+# CONFIG_ARPD is not set
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
+CONFIG_INET_XFRM_TUNNEL=m
+CONFIG_INET_TUNNEL=m
+CONFIG_INET_XFRM_MODE_TRANSPORT=m
+CONFIG_INET_XFRM_MODE_TUNNEL=m
+CONFIG_INET_XFRM_MODE_BEET=m
+CONFIG_INET_LRO=y
+CONFIG_INET_DIAG=m
+CONFIG_INET_TCP_DIAG=m
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_TCP_CONG_BIC=m
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_TCP_CONG_WESTWOOD=m
+CONFIG_TCP_CONG_HTCP=m
+CONFIG_TCP_CONG_HSTCP=m
+CONFIG_TCP_CONG_HYBLA=m
+CONFIG_TCP_CONG_VEGAS=m
+CONFIG_TCP_CONG_SCALABLE=m
+CONFIG_TCP_CONG_LP=m
+CONFIG_TCP_CONG_VENO=m
+CONFIG_TCP_CONG_YEAH=m
+CONFIG_TCP_CONG_ILLINOIS=m
+CONFIG_DEFAULT_CUBIC=y
+# CONFIG_DEFAULT_RENO is not set
+CONFIG_DEFAULT_TCP_CONG="cubic"
+CONFIG_TCP_MD5SIG=y
+CONFIG_IPV6=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=m
+CONFIG_INET6_ESP=m
+CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_MIP6=m
+CONFIG_INET6_XFRM_TUNNEL=m
+CONFIG_INET6_TUNNEL=m
+CONFIG_INET6_XFRM_MODE_TRANSPORT=m
+CONFIG_INET6_XFRM_MODE_TUNNEL=m
+CONFIG_INET6_XFRM_MODE_BEET=m
+CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_SIT=m
+# CONFIG_IPV6_SIT_6RD is not set
+CONFIG_IPV6_NDISC_NODETYPE=y
+CONFIG_IPV6_TUNNEL=m
+CONFIG_IPV6_MULTIPLE_TABLES=y
+# CONFIG_IPV6_SUBTREES is not set
+CONFIG_IPV6_MROUTE=y
+# CONFIG_IPV6_MROUTE_MULTIPLE_TABLES is not set
+CONFIG_IPV6_PIMSM_V2=y
+CONFIG_NETLABEL=y
+CONFIG_NETWORK_SECMARK=y
+# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_BRIDGE_NETFILTER=y
+
+#
+# Core Netfilter Configuration
+#
+CONFIG_NETFILTER_NETLINK=m
+CONFIG_NETFILTER_NETLINK_QUEUE=m
+CONFIG_NETFILTER_NETLINK_LOG=m
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_MARK=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+# CONFIG_NF_CONNTRACK_TIMESTAMP is not set
+CONFIG_NF_CT_PROTO_DCCP=m
+CONFIG_NF_CT_PROTO_GRE=m
+CONFIG_NF_CT_PROTO_SCTP=m
+CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CONNTRACK_AMANDA=m
+CONFIG_NF_CONNTRACK_FTP=m
+CONFIG_NF_CONNTRACK_H323=m
+CONFIG_NF_CONNTRACK_IRC=m
+CONFIG_NF_CONNTRACK_BROADCAST=m
+CONFIG_NF_CONNTRACK_NETBIOS_NS=m
+# CONFIG_NF_CONNTRACK_SNMP is not set
+CONFIG_NF_CONNTRACK_PPTP=m
+CONFIG_NF_CONNTRACK_SANE=m
+CONFIG_NF_CONNTRACK_SIP=m
+CONFIG_NF_CONNTRACK_TFTP=m
+# CONFIG_NF_CT_NETLINK is not set
+CONFIG_NETFILTER_TPROXY=m
+CONFIG_NETFILTER_XTABLES=y
+
+#
+# Xtables combined modules
+#
+CONFIG_NETFILTER_XT_MARK=m
+CONFIG_NETFILTER_XT_CONNMARK=m
+
+#
+# Xtables targets
+#
+# CONFIG_NETFILTER_XT_TARGET_AUDIT is not set
+# CONFIG_NETFILTER_XT_TARGET_CHECKSUM is not set
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
+CONFIG_NETFILTER_XT_TARGET_CT=m
+CONFIG_NETFILTER_XT_TARGET_DSCP=m
+CONFIG_NETFILTER_XT_TARGET_HL=m
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
+CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NFLOG=m
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
+CONFIG_NETFILTER_XT_TARGET_RATEEST=m
+CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
+CONFIG_NETFILTER_XT_TARGET_TRACE=m
+CONFIG_NETFILTER_XT_TARGET_SECMARK=m
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
+CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
+
+#
+# Xtables matches
+#
+# CONFIG_NETFILTER_XT_MATCH_ADDRTYPE is not set
+CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
+CONFIG_NETFILTER_XT_MATCH_COMMENT=m
+CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+# CONFIG_NETFILTER_XT_MATCH_CPU is not set
+CONFIG_NETFILTER_XT_MATCH_DCCP=m
+# CONFIG_NETFILTER_XT_MATCH_DEVGROUP is not set
+CONFIG_NETFILTER_XT_MATCH_DSCP=m
+CONFIG_NETFILTER_XT_MATCH_ESP=m
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
+CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_HL=m
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
+CONFIG_NETFILTER_XT_MATCH_IPVS=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NETFILTER_XT_MATCH_LIMIT=m
+CONFIG_NETFILTER_XT_MATCH_MAC=m
+CONFIG_NETFILTER_XT_MATCH_MARK=m
+CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_OSF=m
+CONFIG_NETFILTER_XT_MATCH_OWNER=m
+CONFIG_NETFILTER_XT_MATCH_POLICY=m
+CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
+CONFIG_NETFILTER_XT_MATCH_QUOTA=m
+CONFIG_NETFILTER_XT_MATCH_RATEEST=m
+CONFIG_NETFILTER_XT_MATCH_REALM=m
+CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SCTP=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
+CONFIG_NETFILTER_XT_MATCH_STRING=m
+CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_TIME=m
+CONFIG_NETFILTER_XT_MATCH_U32=m
+# CONFIG_IP_SET is not set
+CONFIG_IP_VS=m
+CONFIG_IP_VS_IPV6=y
+# CONFIG_IP_VS_DEBUG is not set
+CONFIG_IP_VS_TAB_BITS=12
+
+#
+# IPVS transport protocol load balancing support
+#
+CONFIG_IP_VS_PROTO_TCP=y
+CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_AH_ESP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+CONFIG_IP_VS_PROTO_SCTP=y
+
+#
+# IPVS scheduler
+#
+CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
+CONFIG_IP_VS_LC=m
+CONFIG_IP_VS_WLC=m
+CONFIG_IP_VS_LBLC=m
+CONFIG_IP_VS_LBLCR=m
+# CONFIG_IP_VS_DH is not set
+# CONFIG_IP_VS_SH is not set
+CONFIG_IP_VS_SED=m
+CONFIG_IP_VS_NQ=m
+
+#
+# IPVS application helper
+#
+# CONFIG_IP_VS_NFCT is not set
+# CONFIG_IP_VS_PE_SIP is not set
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_NF_DEFRAG_IPV4=y
+CONFIG_NF_CONNTRACK_IPV4=y
+# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_IP_NF_QUEUE=m
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=m
+CONFIG_IP_NF_MATCH_ECN=m
+CONFIG_IP_NF_MATCH_TTL=m
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_LOG=m
+CONFIG_IP_NF_TARGET_ULOG=m
+# CONFIG_NF_NAT is not set
+CONFIG_IP_NF_MANGLE=m
+# CONFIG_IP_NF_TARGET_CLUSTERIP is not set
+CONFIG_IP_NF_TARGET_ECN=m
+CONFIG_IP_NF_TARGET_TTL=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_SECURITY=m
+CONFIG_IP_NF_ARPTABLES=m
+CONFIG_IP_NF_ARPFILTER=m
+CONFIG_IP_NF_ARP_MANGLE=m
+
+#
+# IPv6: Netfilter Configuration
+#
+CONFIG_NF_DEFRAG_IPV6=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_IP6_NF_QUEUE=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_MATCH_AH=m
+CONFIG_IP6_NF_MATCH_EUI64=m
+CONFIG_IP6_NF_MATCH_FRAG=m
+CONFIG_IP6_NF_MATCH_OPTS=m
+CONFIG_IP6_NF_MATCH_HL=m
+CONFIG_IP6_NF_MATCH_IPV6HEADER=m
+CONFIG_IP6_NF_MATCH_MH=m
+CONFIG_IP6_NF_MATCH_RT=m
+CONFIG_IP6_NF_TARGET_HL=m
+CONFIG_IP6_NF_TARGET_LOG=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_RAW=m
+CONFIG_IP6_NF_SECURITY=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_BROUTE=m
+CONFIG_BRIDGE_EBT_T_FILTER=m
+CONFIG_BRIDGE_EBT_T_NAT=m
+CONFIG_BRIDGE_EBT_802_3=m
+CONFIG_BRIDGE_EBT_AMONG=m
+CONFIG_BRIDGE_EBT_ARP=m
+CONFIG_BRIDGE_EBT_IP=m
+CONFIG_BRIDGE_EBT_IP6=m
+CONFIG_BRIDGE_EBT_LIMIT=m
+CONFIG_BRIDGE_EBT_MARK=m
+CONFIG_BRIDGE_EBT_PKTTYPE=m
+CONFIG_BRIDGE_EBT_STP=m
+CONFIG_BRIDGE_EBT_VLAN=m
+CONFIG_BRIDGE_EBT_ARPREPLY=m
+CONFIG_BRIDGE_EBT_DNAT=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE_EBT_REDIRECT=m
+CONFIG_BRIDGE_EBT_SNAT=m
+CONFIG_BRIDGE_EBT_LOG=m
+CONFIG_BRIDGE_EBT_ULOG=m
+CONFIG_BRIDGE_EBT_NFLOG=m
+# CONFIG_IP_DCCP is not set
+CONFIG_IP_SCTP=m
+# CONFIG_SCTP_DBG_MSG is not set
+# CONFIG_SCTP_DBG_OBJCNT is not set
+# CONFIG_SCTP_HMAC_NONE is not set
+# CONFIG_SCTP_HMAC_SHA1 is not set
+CONFIG_SCTP_HMAC_MD5=y
+CONFIG_RDS=m
+CONFIG_RDS_TCP=m
+# CONFIG_RDS_DEBUG is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_L2TP is not set
+CONFIG_STP=m
+CONFIG_GARP=m
+CONFIG_BRIDGE=m
+CONFIG_BRIDGE_IGMP_SNOOPING=y
+CONFIG_NET_DSA=y
+CONFIG_NET_DSA_TAG_DSA=y
+CONFIG_NET_DSA_TAG_EDSA=y
+CONFIG_NET_DSA_TAG_TRAILER=y
+CONFIG_NET_DSA_MV88E6XXX=y
+CONFIG_NET_DSA_MV88E6060=y
+CONFIG_NET_DSA_MV88E6XXX_NEED_PPU=y
+CONFIG_NET_DSA_MV88E6131=y
+CONFIG_NET_DSA_MV88E6123_61_65=y
+CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
+# CONFIG_DECNET is not set
+CONFIG_LLC=m
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+CONFIG_PHONET=m
+# CONFIG_IEEE802154 is not set
+CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+CONFIG_NET_SCH_CBQ=m
+CONFIG_NET_SCH_HTB=m
+CONFIG_NET_SCH_HFSC=m
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_MULTIQ=m
+CONFIG_NET_SCH_RED=m
+# CONFIG_NET_SCH_SFB is not set
+CONFIG_NET_SCH_SFQ=m
+CONFIG_NET_SCH_TEQL=m
+CONFIG_NET_SCH_TBF=m
+CONFIG_NET_SCH_GRED=m
+CONFIG_NET_SCH_DSMARK=m
+CONFIG_NET_SCH_NETEM=m
+CONFIG_NET_SCH_DRR=m
+# CONFIG_NET_SCH_MQPRIO is not set
+# CONFIG_NET_SCH_CHOKE is not set
+CONFIG_NET_SCH_INGRESS=m
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_TCINDEX=m
+CONFIG_NET_CLS_ROUTE4=m
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_CLS_U32=m
+CONFIG_CLS_U32_PERF=y
+CONFIG_CLS_U32_MARK=y
+CONFIG_NET_CLS_RSVP=m
+CONFIG_NET_CLS_RSVP6=m
+CONFIG_NET_CLS_FLOW=m
+CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+CONFIG_NET_EMATCH_CMP=m
+CONFIG_NET_EMATCH_NBYTE=m
+CONFIG_NET_EMATCH_U32=m
+CONFIG_NET_EMATCH_META=m
+CONFIG_NET_EMATCH_TEXT=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_ACT_POLICE=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_GACT_PROB=y
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_IPT=m
+CONFIG_NET_ACT_NAT=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_ACT_SIMP=m
+CONFIG_NET_ACT_SKBEDIT=m
+# CONFIG_NET_ACT_CSUM is not set
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_SCH_FIFO=y
+CONFIG_DCB=y
+CONFIG_DNS_RESOLVER=y
+# CONFIG_BATMAN_ADV is not set
+CONFIG_RPS=y
+CONFIG_RFS_ACCEL=y
+CONFIG_XPS=y
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+CONFIG_FIB_RULES=y
+# CONFIG_WIRELESS is not set
+# CONFIG_WIMAX is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+# CONFIG_CAIF is not set
+# CONFIG_CEPH_LIB is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+CONFIG_CONNECTOR=y
+CONFIG_PROC_EVENTS=y
+# CONFIG_MTD is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_COW_COMMON is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_CRYPTOLOOP=m
+# CONFIG_BLK_DEV_DRBD is not set
+# CONFIG_BLK_DEV_NBD is not set
+CONFIG_BLK_DEV_SX8=m
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_BLK_DEV_XIP is not set
+# CONFIG_CDROM_PKTCDVD is not set
+CONFIG_ATA_OVER_ETH=y
+# CONFIG_BLK_DEV_RBD is not set
+# CONFIG_SENSORS_LIS3LV02D is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_AD525X_DPOT is not set
+# CONFIG_PHANTOM is not set
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+# CONFIG_ICS932S401 is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_HP_ILO is not set
+# CONFIG_APDS9802ALS is not set
+# CONFIG_ISL29003 is not set
+# CONFIG_ISL29020 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_SENSORS_BH1780 is not set
+# CONFIG_SENSORS_BH1770 is not set
+# CONFIG_SENSORS_APDS990X is not set
+# CONFIG_HMC6352 is not set
+# CONFIG_DS1682 is not set
+# CONFIG_BMP085 is not set
+# CONFIG_PCH_PHUB is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_AT24 is not set
+# CONFIG_EEPROM_LEGACY is not set
+# CONFIG_EEPROM_MAX6875 is not set
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_CB710_CORE is not set
+
+#
+# Texas Instruments shared transport line discipline
+#
+# CONFIG_SENSORS_LIS3_I2C is not set
+
+#
+# SCSI device support
+#
+CONFIG_SCSI_MOD=m
+CONFIG_RAID_ATTRS=m
+CONFIG_SCSI=m
+CONFIG_SCSI_DMA=y
+CONFIG_SCSI_TGT=m
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=m
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+# CONFIG_CHR_DEV_SG is not set
+# CONFIG_CHR_DEV_SCH is not set
+# CONFIG_SCSI_MULTI_LUN is not set
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_LOGGING=y
+# CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
+
+#
+# SCSI Transports
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+CONFIG_SCSI_SAS_ATTRS=m
+# CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+CONFIG_SCSI_LOWLEVEL=y
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_ISCSI_BOOT_SYSFS is not set
+# CONFIG_SCSI_CXGB3_ISCSI is not set
+# CONFIG_SCSI_CXGB4_ISCSI is not set
+# CONFIG_SCSI_BNX2_ISCSI is not set
+# CONFIG_SCSI_BNX2X_FCOE is not set
+# CONFIG_BE2ISCSI is not set
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_HPSA is not set
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_3W_SAS is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_MVSAS is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
+# CONFIG_SCSI_ARCMSR is not set
+# CONFIG_MEGARAID_NEWGEN is not set
+# CONFIG_MEGARAID_LEGACY is not set
+# CONFIG_MEGARAID_SAS is not set
+# CONFIG_SCSI_MPT2SAS is not set
+# CONFIG_SCSI_HPTIOP is not set
+# CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
+# CONFIG_FCOE is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_STEX is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_IPR is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+# CONFIG_SCSI_QLA_FC is not set
+# CONFIG_SCSI_QLA_ISCSI is not set
+# CONFIG_SCSI_LPFC is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_PMCRAID is not set
+# CONFIG_SCSI_PM8001 is not set
+# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_BFA_FC is not set
+# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
+CONFIG_ATA=m
+# CONFIG_ATA_NONSTANDARD is not set
+CONFIG_ATA_VERBOSE_ERROR=y
+CONFIG_SATA_PMP=y
+
+#
+# Controllers with non-SFF native interface
+#
+# CONFIG_SATA_AHCI is not set
+# CONFIG_SATA_AHCI_PLATFORM is not set
+# CONFIG_SATA_INIC162X is not set
+# CONFIG_SATA_ACARD_AHCI is not set
+CONFIG_SATA_SIL24=m
+CONFIG_ATA_SFF=y
+
+#
+# SFF controllers with custom DMA interface
+#
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_SX4 is not set
+CONFIG_ATA_BMDMA=y
+
+#
+# SATA SFF controllers with BMDMA
+#
+# CONFIG_ATA_PIIX is not set
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_SVW is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+
+#
+# PATA SFF controllers with BMDMA
+#
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARASAN_CF is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_ATP867X is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CS5536 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_PATA_HPT366 is not set
+# CONFIG_PATA_HPT37X is not set
+# CONFIG_PATA_HPT3X2N is not set
+# CONFIG_PATA_HPT3X3 is not set
+# CONFIG_PATA_IT8213 is not set
+# CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_MARVELL is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NINJA32 is not set
+# CONFIG_PATA_NS87415 is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RDC is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SCH is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_TOSHIBA is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
+
+#
+# PIO-only SFF controllers
+#
+# CONFIG_PATA_CMD640_PCI is not set
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_PLATFORM is not set
+# CONFIG_PATA_RZ1000 is not set
+
+#
+# Generic fallback / legacy drivers
+#
+# CONFIG_ATA_GENERIC is not set
+# CONFIG_PATA_LEGACY is not set
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_MD_AUTODETECT=y
+CONFIG_MD_LINEAR=m
+CONFIG_MD_RAID0=m
+CONFIG_MD_RAID1=m
+CONFIG_MD_RAID10=m
+CONFIG_MD_RAID456=m
+CONFIG_MULTICORE_RAID456=y
+# CONFIG_MD_MULTIPATH is not set
+CONFIG_MD_FAULTY=m
+CONFIG_BLK_DEV_DM=m
+CONFIG_DM_DEBUG=y
+CONFIG_DM_CRYPT=m
+CONFIG_DM_SNAPSHOT=m
+CONFIG_DM_MIRROR=m
+# CONFIG_DM_RAID is not set
+CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_ZERO=m
+CONFIG_DM_MULTIPATH=m
+CONFIG_DM_MULTIPATH_QL=m
+CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_DELAY=m
+CONFIG_DM_UEVENT=y
+# CONFIG_DM_FLAKEY is not set
+# CONFIG_TARGET_CORE is not set
+# CONFIG_FUSION is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_FIREWIRE is not set
+# CONFIG_FIREWIRE_NOSY is not set
+# CONFIG_I2O is not set
+CONFIG_NETDEVICES=y
+CONFIG_IFB=m
+CONFIG_DUMMY=m
+CONFIG_BONDING=m
+CONFIG_MACVLAN=m
+CONFIG_MACVTAP=m
+# CONFIG_EQUALIZER is not set
+CONFIG_TUN=y
+CONFIG_VETH=m
+# CONFIG_ARCNET is not set
+# CONFIG_MII is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+# CONFIG_SMSC_PHY is not set
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_BCM63XX_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_MICREL_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
+# CONFIG_NET_ETHERNET is not set
+CONFIG_NETDEV_1000=y
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 is not set
+CONFIG_E1000E=m
+# CONFIG_IP1000 is not set
+# CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SIS190 is not set
+# CONFIG_SKGE is not set
+# CONFIG_SKY2 is not set
+# CONFIG_VIA_VELOCITY is not set
+# CONFIG_TIGON3 is not set
+# CONFIG_BNX2 is not set
+# CONFIG_CNIC is not set
+# CONFIG_QLA3XXX is not set
+# CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
+# CONFIG_JME is not set
+# CONFIG_STMMAC_ETH is not set
+# CONFIG_PCH_GBE is not set
+# CONFIG_NETDEV_10000 is not set
+# CONFIG_TR is not set
+# CONFIG_WLAN is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
+# CONFIG_WAN is not set
+
+#
+# CAIF transport drivers
+#
+# CONFIG_TILE_NET is not set
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+# CONFIG_NET_FC is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_VMXNET3 is not set
+# CONFIG_ISDN is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+# CONFIG_INPUT_SPARSEKMAP is not set
+
+#
+# Userland interfaces
+#
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input Device Drivers
+#
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_NOZOMI is not set
+# CONFIG_N_GSM is not set
+CONFIG_DEVKMEM=y
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+# CONFIG_SERIAL_MFD_HSU is not set
+# CONFIG_SERIAL_JSM is not set
+# CONFIG_SERIAL_TIMBERDALE is not set
+# CONFIG_SERIAL_ALTERA_JTAGUART is not set
+# CONFIG_SERIAL_ALTERA_UART is not set
+# CONFIG_SERIAL_PCH_UART is not set
+# CONFIG_TTY_PRINTK is not set
+CONFIG_HVC_DRIVER=y
+# CONFIG_IPMI_HANDLER is not set
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_TIMERIOMEM=m
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# PCMCIA character devices
+#
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+CONFIG_DEVPORT=y
+# CONFIG_RAMOOPS is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_COMPAT=y
+CONFIG_I2C_CHARDEV=y
+# CONFIG_I2C_MUX is not set
+CONFIG_I2C_HELPER_AUTO=y
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# PC SMBus host controller drivers
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+# CONFIG_I2C_I801 is not set
+# CONFIG_I2C_ISCH is not set
+# CONFIG_I2C_PIIX4 is not set
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_INTEL_MID is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_PXA_PCI is not set
+# CONFIG_I2C_SIMTEC is not set
+# CONFIG_I2C_XILINX is not set
+# CONFIG_I2C_EG20T is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_SPI is not set
+
+#
+# PPS support
+#
+# CONFIG_PPS is not set
+
+#
+# PPS generators support
+#
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+CONFIG_MFD_SUPPORT=y
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_88PM860X is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_TPS6105X is not set
+# CONFIG_TPS6507X is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_MFD_STMPE is not set
+# CONFIG_MFD_TC3589X is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_PMIC_ADP5520 is not set
+# CONFIG_MFD_MAX8925 is not set
+# CONFIG_MFD_MAX8997 is not set
+# CONFIG_MFD_MAX8998 is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM831X_I2C is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_WM8994 is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_ABX500_CORE is not set
+# CONFIG_LPC_SCH is not set
+# CONFIG_MFD_RDC321X is not set
+# CONFIG_MFD_JANZ_CMODIO is not set
+# CONFIG_MFD_VX855 is not set
+# CONFIG_MFD_WL1273_CORE is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_MEDIA_SUPPORT is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGA_ARB is not set
+# CONFIG_DRM is not set
+# CONFIG_STUB_POULSBO is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_SOUND is not set
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_UWB is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_NFC_DEVICES is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_INFINIBAND is not set
+# CONFIG_EDAC is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# I2C RTC drivers
+#
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_DS3232 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_ISL12022 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_BQ32K is not set
+# CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
+# CONFIG_RTC_DRV_RX8025 is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_MSM6242 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_RP5C01 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+CONFIG_RTC_DRV_TILE=y
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+# CONFIG_UIO is not set
+# CONFIG_STAGING is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+CONFIG_EXT2_FS_XIP=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_DEFAULTS_TO_ORDERED=y
+CONFIG_EXT3_FS_XATTR=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_XATTR=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+# CONFIG_EXT4_DEBUG is not set
+CONFIG_FS_XIP=y
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_JBD2=y
+CONFIG_JBD2_DEBUG=y
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+CONFIG_XFS_FS=m
+CONFIG_XFS_QUOTA=y
+CONFIG_XFS_POSIX_ACL=y
+# CONFIG_XFS_RT is not set
+# CONFIG_XFS_DEBUG is not set
+CONFIG_GFS2_FS=m
+CONFIG_GFS2_FS_LOCKING_DLM=y
+# CONFIG_OCFS2_FS is not set
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
+# CONFIG_NILFS2_FS is not set
+CONFIG_FS_POSIX_ACL=y
+CONFIG_EXPORTFS=y
+CONFIG_FILE_LOCKING=y
+CONFIG_FSNOTIFY=y
+CONFIG_DNOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_FANOTIFY is not set
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+# CONFIG_QUOTA_DEBUG is not set
+CONFIG_QUOTA_TREE=y
+# CONFIG_QFMT_V1 is not set
+CONFIG_QFMT_V2=y
+CONFIG_QUOTACTL=y
+# CONFIG_AUTOFS4_FS is not set
+CONFIG_FUSE_FS=y
+CONFIG_CUSE=m
+CONFIG_GENERIC_ACL=y
+
+#
+# Caches
+#
+CONFIG_FSCACHE=m
+CONFIG_FSCACHE_STATS=y
+# CONFIG_FSCACHE_HISTOGRAM is not set
+# CONFIG_FSCACHE_DEBUG is not set
+# CONFIG_FSCACHE_OBJECT_LIST is not set
+CONFIG_CACHEFILES=m
+# CONFIG_CACHEFILES_DEBUG is not set
+# CONFIG_CACHEFILES_HISTOGRAM is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=m
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=m
+CONFIG_UDF_NLS=y
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=m
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=m
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="ascii"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_HUGETLB_PAGE=y
+CONFIG_CONFIGFS_FS=m
+CONFIG_MISC_FILESYSTEMS=y
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+CONFIG_ECRYPT_FS=m
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
+CONFIG_CRAMFS=m
+CONFIG_SQUASHFS=m
+# CONFIG_SQUASHFS_XATTR is not set
+# CONFIG_SQUASHFS_LZO is not set
+# CONFIG_SQUASHFS_XZ is not set
+# CONFIG_SQUASHFS_EMBEDDED is not set
+CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE=3
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_PSTORE is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=m
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_PNFS_FILE_LAYOUT=m
+CONFIG_NFS_FSCACHE=y
+# CONFIG_NFS_USE_LEGACY_DNS is not set
+CONFIG_NFS_USE_KERNEL_DNS=y
+# CONFIG_NFS_USE_NEW_IDMAPPER is not set
+CONFIG_NFSD=m
+CONFIG_NFSD_DEPRECATED=y
+CONFIG_NFSD_V2_ACL=y
+CONFIG_NFSD_V3=y
+CONFIG_NFSD_V3_ACL=y
+CONFIG_NFSD_V4=y
+CONFIG_LOCKD=m
+CONFIG_LOCKD_V4=y
+CONFIG_NFS_ACL_SUPPORT=m
+CONFIG_NFS_COMMON=y
+CONFIG_SUNRPC=m
+CONFIG_SUNRPC_GSS=m
+CONFIG_RPCSEC_GSS_KRB5=m
+# CONFIG_CEPH_FS is not set
+CONFIG_CIFS=m
+CONFIG_CIFS_STATS=y
+# CONFIG_CIFS_STATS2 is not set
+CONFIG_CIFS_WEAK_PW_HASH=y
+CONFIG_CIFS_UPCALL=y
+CONFIG_CIFS_XATTR=y
+CONFIG_CIFS_POSIX=y
+# CONFIG_CIFS_DEBUG2 is not set
+CONFIG_CIFS_DFS_UPCALL=y
+CONFIG_CIFS_FSCACHE=y
+# CONFIG_CIFS_ACL is not set
+CONFIG_CIFS_EXPERIMENTAL=y
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_ACORN_PARTITION is not set
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+# CONFIG_ATARI_PARTITION is not set
+CONFIG_MAC_PARTITION=y
+CONFIG_MSDOS_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+# CONFIG_LDM_PARTITION is not set
+CONFIG_SGI_PARTITION=y
+# CONFIG_ULTRIX_PARTITION is not set
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
+# CONFIG_SYSV68_PARTITION is not set
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_737=m
+CONFIG_NLS_CODEPAGE_775=m
+CONFIG_NLS_CODEPAGE_850=m
+CONFIG_NLS_CODEPAGE_852=m
+CONFIG_NLS_CODEPAGE_855=m
+CONFIG_NLS_CODEPAGE_857=m
+CONFIG_NLS_CODEPAGE_860=m
+CONFIG_NLS_CODEPAGE_861=m
+CONFIG_NLS_CODEPAGE_862=m
+CONFIG_NLS_CODEPAGE_863=m
+CONFIG_NLS_CODEPAGE_864=m
+CONFIG_NLS_CODEPAGE_865=m
+CONFIG_NLS_CODEPAGE_866=m
+CONFIG_NLS_CODEPAGE_869=m
+CONFIG_NLS_CODEPAGE_936=m
+CONFIG_NLS_CODEPAGE_950=m
+CONFIG_NLS_CODEPAGE_932=m
+CONFIG_NLS_CODEPAGE_949=m
+CONFIG_NLS_CODEPAGE_874=m
+CONFIG_NLS_ISO8859_8=m
+CONFIG_NLS_CODEPAGE_1250=m
+CONFIG_NLS_CODEPAGE_1251=m
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=m
+CONFIG_NLS_ISO8859_2=m
+CONFIG_NLS_ISO8859_3=m
+CONFIG_NLS_ISO8859_4=m
+CONFIG_NLS_ISO8859_5=m
+CONFIG_NLS_ISO8859_6=m
+CONFIG_NLS_ISO8859_7=m
+CONFIG_NLS_ISO8859_9=m
+CONFIG_NLS_ISO8859_13=m
+CONFIG_NLS_ISO8859_14=m
+CONFIG_NLS_ISO8859_15=m
+CONFIG_NLS_KOI8_R=m
+CONFIG_NLS_KOI8_U=m
+CONFIG_NLS_UTF8=m
+CONFIG_DLM=m
+CONFIG_DLM_DEBUG=y
+
+#
+# Kernel hacking
+#
+# CONFIG_PRINTK_TIME is not set
+CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=2048
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_STRIP_ASM_SYMS=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_CHECK=y
+# CONFIG_DEBUG_SECTION_MISMATCH is not set
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_LOCKUP_DETECTOR=y
+# CONFIG_HARDLOCKUP_DETECTOR is not set
+# CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE=0
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
+CONFIG_SCHED_DEBUG=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_SLUB_DEBUG_ON is not set
+# CONFIG_SLUB_STATS is not set
+# CONFIG_DEBUG_KMEMLEAK is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_LOCK_ALLOC is not set
+# CONFIG_PROVE_LOCKING is not set
+# CONFIG_SPARSE_RCU_POINTER is not set
+# CONFIG_LOCK_STAT is not set
+CONFIG_DEBUG_SPINLOCK_SLEEP=y
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
+# CONFIG_DEBUG_KOBJECT is not set
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_REDUCED=y
+CONFIG_DEBUG_VM=y
+# CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_LIST=y
+# CONFIG_TEST_LIST_SORT is not set
+# CONFIG_DEBUG_SG is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+CONFIG_DEBUG_CREDENTIALS=y
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+# CONFIG_LKDTM is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+CONFIG_TRACING_SUPPORT=y
+CONFIG_FTRACE=y
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_ENABLE_DEFAULT_TRACERS is not set
+CONFIG_BRANCH_PROFILE_NONE=y
+# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
+# CONFIG_PROFILE_ALL_BRANCHES is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_BUILD_DOCSRC is not set
+CONFIG_DYNAMIC_DEBUG=y
+# CONFIG_ATOMIC64_SELFTEST is not set
+CONFIG_ASYNC_RAID6_TEST=m
+# CONFIG_SAMPLES is not set
+# CONFIG_TEST_KSTRTOX is not set
+CONFIG_EARLY_PRINTK=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_DEBUG_STACK_USAGE is not set
+CONFIG_DEBUG_EXTRA_FLAGS=""
+
+#
+# Security options
+#
+CONFIG_KEYS=y
+CONFIG_KEYS_DEBUG_PROC_KEYS=y
+# CONFIG_SECURITY_DMESG_RESTRICT is not set
+CONFIG_SECURITY=y
+CONFIG_SECURITYFS=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_NETWORK_XFRM=y
+# CONFIG_SECURITY_PATH is not set
+CONFIG_LSM_MMAP_MIN_ADDR=65536
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_SELINUX_DEVELOP=y
+CONFIG_SECURITY_SELINUX_AVC_STATS=y
+CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
+# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
+# CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_SECURITY_APPARMOR is not set
+# CONFIG_IMA is not set
+CONFIG_DEFAULT_SECURITY_SELINUX=y
+# CONFIG_DEFAULT_SECURITY_DAC is not set
+CONFIG_DEFAULT_SECURITY="selinux"
+CONFIG_XOR_BLOCKS=m
+CONFIG_ASYNC_CORE=m
+CONFIG_ASYNC_MEMCPY=m
+CONFIG_ASYNC_XOR=m
+CONFIG_ASYNC_PQ=m
+CONFIG_ASYNC_RAID6_RECOV=m
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ALGAPI2=y
+CONFIG_CRYPTO_AEAD=m
+CONFIG_CRYPTO_AEAD2=y
+CONFIG_CRYPTO_BLKCIPHER=m
+CONFIG_CRYPTO_BLKCIPHER2=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_HASH2=y
+CONFIG_CRYPTO_RNG=m
+CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=m
+CONFIG_CRYPTO_PCOMP2=y
+CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_MANAGER2=y
+CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
+CONFIG_CRYPTO_GF128MUL=m
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_PCRYPT=m
+CONFIG_CRYPTO_WORKQUEUE=y
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_AUTHENC=m
+CONFIG_CRYPTO_TEST=m
+
+#
+# Authenticated Encryption with Associated Data
+#
+CONFIG_CRYPTO_CCM=m
+CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_SEQIV=m
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=m
+CONFIG_CRYPTO_CTR=m
+CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
+
+#
+# Hash modes
+#
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_XCBC=m
+CONFIG_CRYPTO_VMAC=m
+
+#
+# Digest
+#
+CONFIG_CRYPTO_CRC32C=y
+CONFIG_CRYPTO_GHASH=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_FCRYPT=m
+CONFIG_CRYPTO_KHAZAD=m
+# CONFIG_CRYPTO_SALSA20 is not set
+CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_TWOFISH_COMMON=m
+
+#
+# Compression
+#
+CONFIG_CRYPTO_DEFLATE=m
+CONFIG_CRYPTO_ZLIB=m
+CONFIG_CRYPTO_LZO=m
+
+#
+# Random Number Generation
+#
+CONFIG_CRYPTO_ANSI_CPRNG=m
+# CONFIG_CRYPTO_USER_API_HASH is not set
+# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
+CONFIG_CRYPTO_HW=y
+CONFIG_CRYPTO_DEV_HIFN_795X=m
+CONFIG_CRYPTO_DEV_HIFN_795X_RNG=y
+# CONFIG_BINARY_PRINTF is not set
+
+#
+# Library routines
+#
+CONFIG_RAID6_PQ=m
+CONFIG_BITREVERSE=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_FIND_LAST_BIT=y
+# CONFIG_CRC_CCITT is not set
+CONFIG_CRC16=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=m
+CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
+CONFIG_LIBCRC32C=m
+CONFIG_AUDIT_GENERIC=y
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=m
+CONFIG_LZO_COMPRESS=m
+CONFIG_LZO_DECOMPRESS=m
+# CONFIG_XZ_DEC is not set
+# CONFIG_XZ_DEC_BCJ is not set
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_TEXTSEARCH=y
+CONFIG_TEXTSEARCH_KMP=m
+CONFIG_TEXTSEARCH_BM=m
+CONFIG_TEXTSEARCH_FSM=m
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
+CONFIG_CPU_RMAP=y
+CONFIG_NLATTR=y
+# CONFIG_AVERAGE is not set
+# CONFIG_VIRTUALIZATION is not set
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
new file mode 100644
index 000000000000..f58dc362b944
--- /dev/null
+++ b/arch/tile/configs/tilepro_defconfig
@@ -0,0 +1,1163 @@
+#
+# Automatically generated make config: don't edit
+# Linux/tile 2.6.39-rc5 Kernel Configuration
+# Tue May  3 09:15:02 2011
+#
+CONFIG_TILE=y
+CONFIG_MMU=y
+CONFIG_GENERIC_CSUM=y
+CONFIG_SEMAPHORE_SLEEPERS=y
+CONFIG_HAVE_ARCH_ALLOC_REMAP=y
+CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
+CONFIG_SYS_SUPPORTS_HUGETLBFS=y
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_DEFAULT_MIGRATION_COST=10000000
+CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
+CONFIG_ARCH_DMA_ADDR_T_64BIT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
+CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_SMP=y
+# CONFIG_DEBUG_COPY_FROM_USER is not set
+CONFIG_HVC_TILE=y
+# CONFIG_TILEGX is not set
+CONFIG_ARCH_DEFCONFIG="arch/tile/configs/tile_defconfig"
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_CONSTRUCTORS=y
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_CROSS_COMPILE=""
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+CONFIG_FHANDLE=y
+# CONFIG_TASKSTATS is not set
+# CONFIG_AUDIT is not set
+CONFIG_HAVE_GENERIC_HARDIRQS=y
+
+#
+# IRQ subsystem
+#
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_IRQ_SHOW=y
+CONFIG_GENERIC_PENDING_IRQ=y
+
+#
+# RCU Subsystem
+#
+CONFIG_TREE_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_FANOUT=32
+# CONFIG_RCU_FANOUT_EXACT is not set
+# CONFIG_RCU_FAST_NO_HZ is not set
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=17
+# CONFIG_CGROUPS is not set
+# CONFIG_NAMESPACES is not set
+# CONFIG_SCHED_AUTOGROUP is not set
+# CONFIG_SYSFS_DEPRECATED is not set
+# CONFIG_RELAY is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE="usr/contents.txt"
+CONFIG_INITRAMFS_ROOT_UID=0
+CONFIG_INITRAMFS_ROOT_GID=0
+CONFIG_RD_GZIP=y
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+CONFIG_INITRAMFS_COMPRESSION_NONE=y
+# CONFIG_INITRAMFS_COMPRESSION_GZIP is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_EXPERT=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_EMBEDDED=y
+
+#
+# Kernel Performance Events And Counters
+#
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_PCI_QUIRKS=y
+CONFIG_SLUB_DEBUG=y
+# CONFIG_COMPAT_BRK is not set
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
+# CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+CONFIG_USE_GENERIC_SMP_HELPERS=y
+
+#
+# GCOV-based kernel profiling
+#
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_STOP_MACHINE=y
+CONFIG_BLOCK=y
+CONFIG_LBDAF=y
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_DEFAULT_NOOP=y
+CONFIG_DEFAULT_IOSCHED="noop"
+# CONFIG_INLINE_SPIN_TRYLOCK is not set
+# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK is not set
+# CONFIG_INLINE_SPIN_LOCK_BH is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQ is not set
+# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set
+CONFIG_INLINE_SPIN_UNLOCK=y
+# CONFIG_INLINE_SPIN_UNLOCK_BH is not set
+CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
+# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_READ_TRYLOCK is not set
+# CONFIG_INLINE_READ_LOCK is not set
+# CONFIG_INLINE_READ_LOCK_BH is not set
+# CONFIG_INLINE_READ_LOCK_IRQ is not set
+# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set
+CONFIG_INLINE_READ_UNLOCK=y
+# CONFIG_INLINE_READ_UNLOCK_BH is not set
+CONFIG_INLINE_READ_UNLOCK_IRQ=y
+# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set
+# CONFIG_INLINE_WRITE_TRYLOCK is not set
+# CONFIG_INLINE_WRITE_LOCK is not set
+# CONFIG_INLINE_WRITE_LOCK_BH is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQ is not set
+# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set
+CONFIG_INLINE_WRITE_UNLOCK=y
+# CONFIG_INLINE_WRITE_UNLOCK_BH is not set
+CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
+# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set
+CONFIG_MUTEX_SPIN_ON_OWNER=y
+
+#
+# Tilera-specific configuration
+#
+CONFIG_NR_CPUS=64
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+CONFIG_HZ_100=y
+# CONFIG_HZ_250 is not set
+# CONFIG_HZ_300 is not set
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=100
+CONFIG_SCHED_HRTICK=y
+# CONFIG_KEXEC is not set
+CONFIG_HIGHMEM=y
+CONFIG_NUMA=y
+CONFIG_NODES_SHIFT=2
+# CONFIG_VMSPLIT_3_75G is not set
+# CONFIG_VMSPLIT_3_5G is not set
+CONFIG_VMSPLIT_3G=y
+# CONFIG_VMSPLIT_2_75G is not set
+# CONFIG_VMSPLIT_2_5G is not set
+# CONFIG_VMSPLIT_2_25G is not set
+# CONFIG_VMSPLIT_2G is not set
+# CONFIG_VMSPLIT_1G is not set
+CONFIG_PAGE_OFFSET=0xC0000000
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_DISCONTIGMEM_MANUAL=y
+CONFIG_DISCONTIGMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_NEED_MULTIPLE_NODES=y
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_COMPACTION is not set
+CONFIG_MIGRATION=y
+CONFIG_PHYS_ADDR_T_64BIT=y
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_BOUNCE=y
+CONFIG_VIRT_TO_BUS=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
+# CONFIG_CMDLINE_BOOL is not set
+CONFIG_VMALLOC_RESERVE=0x1000000
+CONFIG_HARDWALL=y
+CONFIG_KERNEL_PL=1
+
+#
+# Bus options
+#
+CONFIG_PCI=y
+CONFIG_PCI_DOMAINS=y
+# CONFIG_NO_IOMEM is not set
+# CONFIG_NO_IOPORT is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCI_DEBUG is not set
+# CONFIG_PCI_STUB is not set
+# CONFIG_PCI_IOV is not set
+# CONFIG_HOTPLUG_PCI is not set
+
+#
+# Executable file formats
+#
+CONFIG_KCORE_ELF=y
+CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
+# CONFIG_NET_KEY is not set
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+# CONFIG_IP_ADVANCED_ROUTER is not set
+# CONFIG_IP_PNP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE_DEMUX is not set
+# CONFIG_IP_MROUTE is not set
+# CONFIG_ARPD is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_INET_AH is not set
+# CONFIG_INET_ESP is not set
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+CONFIG_INET_TUNNEL=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+CONFIG_INET_XFRM_MODE_BEET=y
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
+CONFIG_IPV6=y
+# CONFIG_IPV6_PRIVACY is not set
+# CONFIG_IPV6_ROUTER_PREF is not set
+# CONFIG_IPV6_OPTIMISTIC_DAD is not set
+# CONFIG_INET6_AH is not set
+# CONFIG_INET6_ESP is not set
+# CONFIG_INET6_IPCOMP is not set
+# CONFIG_IPV6_MIP6 is not set
+# CONFIG_INET6_XFRM_TUNNEL is not set
+# CONFIG_INET6_TUNNEL is not set
+CONFIG_INET6_XFRM_MODE_TRANSPORT=y
+CONFIG_INET6_XFRM_MODE_TUNNEL=y
+CONFIG_INET6_XFRM_MODE_BEET=y
+# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
+CONFIG_IPV6_SIT=y
+# CONFIG_IPV6_SIT_6RD is not set
+CONFIG_IPV6_NDISC_NODETYPE=y
+# CONFIG_IPV6_TUNNEL is not set
+# CONFIG_IPV6_MULTIPLE_TABLES is not set
+# CONFIG_IPV6_MROUTE is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
+# CONFIG_NETFILTER is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_RDS is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_L2TP is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
+# CONFIG_IEEE802154 is not set
+# CONFIG_NET_SCHED is not set
+# CONFIG_DCB is not set
+# CONFIG_BATMAN_ADV is not set
+CONFIG_RPS=y
+CONFIG_RFS_ACCEL=y
+CONFIG_XPS=y
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+# CONFIG_WIRELESS is not set
+# CONFIG_WIMAX is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+# CONFIG_CAIF is not set
+# CONFIG_CEPH_LIB is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_DEVTMPFS is not set
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_CONNECTOR is not set
+# CONFIG_MTD is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_CPQ_DA is not set
+# CONFIG_BLK_CPQ_CISS_DA is not set
+# CONFIG_BLK_DEV_DAC960 is not set
+# CONFIG_BLK_DEV_UMEM is not set
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+
+#
+# DRBD disabled because PROC_FS, INET or CONNECTOR not selected
+#
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_SX8 is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+# CONFIG_BLK_DEV_RBD is not set
+# CONFIG_SENSORS_LIS3LV02D is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_PHANTOM is not set
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_HP_ILO is not set
+# CONFIG_PCH_PHUB is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_CB710_CORE is not set
+
+#
+# Texas Instruments shared transport line discipline
+#
+
+#
+# SCSI device support
+#
+CONFIG_SCSI_MOD=y
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
+# CONFIG_SCSI_TGT is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=y
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+# CONFIG_CHR_DEV_SG is not set
+# CONFIG_CHR_DEV_SCH is not set
+# CONFIG_SCSI_MULTI_LUN is not set
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_LOGGING=y
+# CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
+
+#
+# SCSI Transports
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+# CONFIG_SCSI_SAS_ATTRS is not set
+# CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+CONFIG_SCSI_LOWLEVEL=y
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_ISCSI_BOOT_SYSFS is not set
+# CONFIG_SCSI_CXGB3_ISCSI is not set
+# CONFIG_SCSI_CXGB4_ISCSI is not set
+# CONFIG_SCSI_BNX2_ISCSI is not set
+# CONFIG_SCSI_BNX2X_FCOE is not set
+# CONFIG_BE2ISCSI is not set
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_HPSA is not set
+# CONFIG_SCSI_3W_9XXX is not set
+# CONFIG_SCSI_3W_SAS is not set
+# CONFIG_SCSI_ACARD is not set
+# CONFIG_SCSI_AACRAID is not set
+# CONFIG_SCSI_AIC7XXX is not set
+# CONFIG_SCSI_AIC7XXX_OLD is not set
+# CONFIG_SCSI_AIC79XX is not set
+# CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_MVSAS is not set
+# CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
+# CONFIG_SCSI_ARCMSR is not set
+# CONFIG_MEGARAID_NEWGEN is not set
+# CONFIG_MEGARAID_LEGACY is not set
+# CONFIG_MEGARAID_SAS is not set
+# CONFIG_SCSI_MPT2SAS is not set
+# CONFIG_SCSI_HPTIOP is not set
+# CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
+# CONFIG_FCOE is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_IPS is not set
+# CONFIG_SCSI_INITIO is not set
+# CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_STEX is not set
+# CONFIG_SCSI_SYM53C8XX_2 is not set
+# CONFIG_SCSI_QLOGIC_1280 is not set
+# CONFIG_SCSI_QLA_FC is not set
+# CONFIG_SCSI_QLA_ISCSI is not set
+# CONFIG_SCSI_LPFC is not set
+# CONFIG_SCSI_DC395x is not set
+# CONFIG_SCSI_DC390T is not set
+# CONFIG_SCSI_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_PMCRAID is not set
+# CONFIG_SCSI_PM8001 is not set
+# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_BFA_FC is not set
+# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+# CONFIG_TARGET_CORE is not set
+# CONFIG_FUSION is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_FIREWIRE is not set
+# CONFIG_FIREWIRE_NOSY is not set
+# CONFIG_I2O is not set
+CONFIG_NETDEVICES=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
+# CONFIG_EQUALIZER is not set
+CONFIG_TUN=y
+# CONFIG_VETH is not set
+# CONFIG_ARCNET is not set
+# CONFIG_MII is not set
+# CONFIG_PHYLIB is not set
+# CONFIG_NET_ETHERNET is not set
+CONFIG_NETDEV_1000=y
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 is not set
+# CONFIG_E1000E is not set
+# CONFIG_IP1000 is not set
+# CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+# CONFIG_R8169 is not set
+# CONFIG_SIS190 is not set
+# CONFIG_SKGE is not set
+# CONFIG_SKY2 is not set
+# CONFIG_VIA_VELOCITY is not set
+# CONFIG_TIGON3 is not set
+# CONFIG_BNX2 is not set
+# CONFIG_CNIC is not set
+# CONFIG_QLA3XXX is not set
+# CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
+# CONFIG_JME is not set
+# CONFIG_STMMAC_ETH is not set
+# CONFIG_PCH_GBE is not set
+# CONFIG_NETDEV_10000 is not set
+# CONFIG_TR is not set
+# CONFIG_WLAN is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
+# CONFIG_WAN is not set
+
+#
+# CAIF transport drivers
+#
+CONFIG_TILE_NET=y
+# CONFIG_FDDI is not set
+# CONFIG_HIPPI is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+# CONFIG_NET_FC is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_VMXNET3 is not set
+# CONFIG_ISDN is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+# CONFIG_INPUT_SPARSEKMAP is not set
+
+#
+# Userland interfaces
+#
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input Device Drivers
+#
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_NOZOMI is not set
+# CONFIG_N_GSM is not set
+CONFIG_DEVKMEM=y
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+# CONFIG_SERIAL_MFD_HSU is not set
+# CONFIG_SERIAL_JSM is not set
+# CONFIG_SERIAL_TIMBERDALE is not set
+# CONFIG_SERIAL_ALTERA_JTAGUART is not set
+# CONFIG_SERIAL_ALTERA_UART is not set
+# CONFIG_SERIAL_PCH_UART is not set
+# CONFIG_TTY_PRINTK is not set
+CONFIG_HVC_DRIVER=y
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# PCMCIA character devices
+#
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+CONFIG_DEVPORT=y
+# CONFIG_RAMOOPS is not set
+# CONFIG_I2C is not set
+# CONFIG_SPI is not set
+
+#
+# PPS support
+#
+# CONFIG_PPS is not set
+
+#
+# PPS generators support
+#
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+CONFIG_HWMON=y
+# CONFIG_HWMON_VID is not set
+# CONFIG_HWMON_DEBUG_CHIP is not set
+
+#
+# Native drivers
+#
+# CONFIG_SENSORS_I5K_AMB is not set
+# CONFIG_SENSORS_F71805F is not set
+# CONFIG_SENSORS_F71882FG is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_SIS5595 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_SCH5627 is not set
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_VT8231 is not set
+# CONFIG_SENSORS_W83627HF is not set
+# CONFIG_SENSORS_W83627EHF is not set
+# CONFIG_THERMAL is not set
+CONFIG_WATCHDOG=y
+CONFIG_WATCHDOG_NOWAYOUT=y
+
+#
+# Watchdog Device Drivers
+#
+# CONFIG_SOFT_WATCHDOG is not set
+# CONFIG_ALIM7101_WDT is not set
+
+#
+# PCI-based Watchdog Cards
+#
+# CONFIG_PCIPCWATCHDOG is not set
+# CONFIG_WDTPCI is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+CONFIG_MFD_SUPPORT=y
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_ABX500_CORE is not set
+# CONFIG_LPC_SCH is not set
+# CONFIG_MFD_RDC321X is not set
+# CONFIG_MFD_JANZ_CMODIO is not set
+# CONFIG_MFD_VX855 is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_MEDIA_SUPPORT is not set
+
+#
+# Graphics support
+#
+CONFIG_VGA_ARB=y
+CONFIG_VGA_ARB_MAX_GPUS=16
+# CONFIG_DRM is not set
+# CONFIG_STUB_POULSBO is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_SOUND is not set
+# CONFIG_HID_SUPPORT is not set
+CONFIG_USB_SUPPORT=y
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+CONFIG_USB_ARCH_HAS_EHCI=y
+# CONFIG_USB is not set
+# CONFIG_USB_OTG_WHITELIST is not set
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
+
+#
+# Enable Host or Gadget support to see Inventra options
+#
+
+#
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# OTG and related infrastructure
+#
+# CONFIG_UWB is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_NFC_DEVICES is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_INFINIBAND is not set
+CONFIG_EDAC=y
+
+#
+# Reporting subsystems
+#
+# CONFIG_EDAC_DEBUG is not set
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_TILE=y
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+# CONFIG_RTC_INTF_SYSFS is not set
+# CONFIG_RTC_INTF_PROC is not set
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_MSM6242 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_RP5C01 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+CONFIG_RTC_DRV_TILE=y
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+# CONFIG_UIO is not set
+# CONFIG_STAGING is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+# CONFIG_EXT2_FS_XIP is not set
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT3_FS_XATTR=y
+# CONFIG_EXT3_FS_POSIX_ACL is not set
+# CONFIG_EXT3_FS_SECURITY is not set
+# CONFIG_EXT4_FS is not set
+CONFIG_JBD=y
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+CONFIG_EXPORTFS=y
+CONFIG_FILE_LOCKING=y
+CONFIG_FSNOTIFY=y
+CONFIG_DNOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_FANOTIFY is not set
+# CONFIG_QUOTA is not set
+# CONFIG_QUOTACTL is not set
+# CONFIG_AUTOFS4_FS is not set
+CONFIG_FUSE_FS=y
+# CONFIG_CUSE is not set
+
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=m
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+# CONFIG_PROC_KCORE is not set
+CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+CONFIG_HUGETLBFS=y
+CONFIG_HUGETLB_PAGE=y
+# CONFIG_CONFIGFS_FS is not set
+CONFIG_MISC_FILESYSTEMS=y
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_SQUASHFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_PSTORE is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=m
+CONFIG_NFS_V3=y
+# CONFIG_NFS_V3_ACL is not set
+# CONFIG_NFS_V4 is not set
+# CONFIG_NFSD is not set
+CONFIG_LOCKD=m
+CONFIG_LOCKD_V4=y
+CONFIG_NFS_COMMON=y
+CONFIG_SUNRPC=m
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_CEPH_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+
+#
+# Kernel hacking
+#
+# CONFIG_PRINTK_TIME is not set
+CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4
+CONFIG_ENABLE_WARN_DEPRECATED=y
+CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=2048
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_STRIP_ASM_SYMS is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_SECTION_MISMATCH is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_SHIRQ is not set
+# CONFIG_LOCKUP_DETECTOR is not set
+# CONFIG_HARDLOCKUP_DETECTOR is not set
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
+CONFIG_SCHED_DEBUG=y
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_SLUB_DEBUG_ON is not set
+# CONFIG_SLUB_STATS is not set
+# CONFIG_DEBUG_KMEMLEAK is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_LOCK_ALLOC is not set
+# CONFIG_PROVE_LOCKING is not set
+# CONFIG_SPARSE_RCU_POINTER is not set
+# CONFIG_LOCK_STAT is not set
+CONFIG_DEBUG_SPINLOCK_SLEEP=y
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_HIGHMEM is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_DEBUG_INFO_REDUCED is not set
+CONFIG_DEBUG_VM=y
+# CONFIG_DEBUG_WRITECOUNT is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_TEST_LIST_SORT is not set
+# CONFIG_DEBUG_SG is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+# CONFIG_DEBUG_CREDENTIALS is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+CONFIG_TRACING_SUPPORT=y
+CONFIG_FTRACE=y
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_ENABLE_DEFAULT_TRACERS is not set
+CONFIG_BRANCH_PROFILE_NONE=y
+# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
+# CONFIG_PROFILE_ALL_BRANCHES is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_ATOMIC64_SELFTEST is not set
+# CONFIG_SAMPLES is not set
+# CONFIG_TEST_KSTRTOX is not set
+CONFIG_EARLY_PRINTK=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_DEBUG_STACK_USAGE is not set
+CONFIG_DEBUG_EXTRA_FLAGS="-femit-struct-debug-baseonly"
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY_DMESG_RESTRICT is not set
+# CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+CONFIG_DEFAULT_SECURITY_DAC=y
+CONFIG_DEFAULT_SECURITY=""
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+CONFIG_CRYPTO_ALGAPI=m
+CONFIG_CRYPTO_ALGAPI2=m
+CONFIG_CRYPTO_RNG=m
+CONFIG_CRYPTO_RNG2=m
+# CONFIG_CRYPTO_MANAGER is not set
+# CONFIG_CRYPTO_MANAGER2 is not set
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_PCRYPT is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+# CONFIG_CRYPTO_VMAC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_GHASH is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=m
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+CONFIG_CRYPTO_ANSI_CPRNG=m
+# CONFIG_CRYPTO_USER_API_HASH is not set
+# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
+CONFIG_CRYPTO_HW=y
+# CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+CONFIG_GENERIC_FIND_FIRST_BIT=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_FIND_LAST_BIT=y
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_ZLIB_INFLATE=y
+# CONFIG_XZ_DEC is not set
+# CONFIG_XZ_DEC_BCJ is not set
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
+CONFIG_CPU_RMAP=y
+CONFIG_NLATTR=y
+# CONFIG_AVERAGE is not set
+CONFIG_HAVE_KVM=y
+# CONFIG_VIRTUALIZATION is not set
diff --git a/arch/tile/include/arch/chip_tilegx.h b/arch/tile/include/arch/chip_tilegx.h
new file mode 100644
index 000000000000..ea8e4f2c9483
--- /dev/null
+++ b/arch/tile/include/arch/chip_tilegx.h
@@ -0,0 +1,258 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/*
+ * @file
+ * Global header file.
+ * This header file specifies defines for TILE-Gx.
+ */
+
+#ifndef __ARCH_CHIP_H__
+#define __ARCH_CHIP_H__
+
+/** Specify chip version.
+ * When possible, prefer the CHIP_xxx symbols below for future-proofing.
+ * This is intended for cross-compiling; native compilation should
+ * use the predefined __tile_chip__ symbol.
+ */
+#define TILE_CHIP 10
+
+/** Specify chip revision.
+ * This provides for the case of a respin of a particular chip type;
+ * the normal value for this symbol is "0".
+ * This is intended for cross-compiling; native compilation should
+ * use the predefined __tile_chip_rev__ symbol.
+ */
+#define TILE_CHIP_REV 0
+
+/** The name of this architecture. */
+#define CHIP_ARCH_NAME "tilegx"
+
+/** The ELF e_machine type for binaries for this chip. */
+#define CHIP_ELF_TYPE() EM_TILEGX
+
+/** The alternate ELF e_machine type for binaries for this chip. */
+#define CHIP_COMPAT_ELF_TYPE() 0x2597
+
+/** What is the native word size of the machine? */
+#define CHIP_WORD_SIZE() 64
+
+/** How many bits of a virtual address are used. Extra bits must be
+ * the sign extension of the low bits.
+ */
+#define CHIP_VA_WIDTH() 42
+
+/** How many bits are in a physical address? */
+#define CHIP_PA_WIDTH() 40
+
+/** Size of the L2 cache, in bytes. */
+#define CHIP_L2_CACHE_SIZE() 262144
+
+/** Log size of an L2 cache line in bytes. */
+#define CHIP_L2_LOG_LINE_SIZE() 6
+
+/** Size of an L2 cache line, in bytes. */
+#define CHIP_L2_LINE_SIZE() (1 << CHIP_L2_LOG_LINE_SIZE())
+
+/** Associativity of the L2 cache. */
+#define CHIP_L2_ASSOC() 8
+
+/** Size of the L1 data cache, in bytes. */
+#define CHIP_L1D_CACHE_SIZE() 32768
+
+/** Log size of an L1 data cache line in bytes. */
+#define CHIP_L1D_LOG_LINE_SIZE() 6
+
+/** Size of an L1 data cache line, in bytes. */
+#define CHIP_L1D_LINE_SIZE() (1 << CHIP_L1D_LOG_LINE_SIZE())
+
+/** Associativity of the L1 data cache. */
+#define CHIP_L1D_ASSOC() 2
+
+/** Size of the L1 instruction cache, in bytes. */
+#define CHIP_L1I_CACHE_SIZE() 32768
+
+/** Log size of an L1 instruction cache line in bytes. */
+#define CHIP_L1I_LOG_LINE_SIZE() 6
+
+/** Size of an L1 instruction cache line, in bytes. */
+#define CHIP_L1I_LINE_SIZE() (1 << CHIP_L1I_LOG_LINE_SIZE())
+
+/** Associativity of the L1 instruction cache. */
+#define CHIP_L1I_ASSOC() 2
+
+/** Stride with which flush instructions must be issued. */
+#define CHIP_FLUSH_STRIDE() CHIP_L2_LINE_SIZE()
+
+/** Stride with which inv instructions must be issued. */
+#define CHIP_INV_STRIDE() CHIP_L2_LINE_SIZE()
+
+/** Stride with which finv instructions must be issued. */
+#define CHIP_FINV_STRIDE() CHIP_L2_LINE_SIZE()
+
+/** Can the local cache coherently cache data that is homed elsewhere? */
+#define CHIP_HAS_COHERENT_LOCAL_CACHE() 1
+
+/** How many simultaneous outstanding victims can the L2 cache have? */
+#define CHIP_MAX_OUTSTANDING_VICTIMS() 128
+
+/** Does the TLB support the NC and NOALLOC bits? */
+#define CHIP_HAS_NC_AND_NOALLOC_BITS() 1
+
+/** Does the chip support hash-for-home caching? */
+#define CHIP_HAS_CBOX_HOME_MAP() 1
+
+/** Number of entries in the chip's home map tables. */
+#define CHIP_CBOX_HOME_MAP_SIZE() 128
+
+/** Do uncacheable requests miss in the cache regardless of whether
+ * there is matching data? */
+#define CHIP_HAS_ENFORCED_UNCACHEABLE_REQUESTS() 1
+
+/** Does the mf instruction wait for victims? */
+#define CHIP_HAS_MF_WAITS_FOR_VICTIMS() 0
+
+/** Does the chip have an "inv" instruction that doesn't also flush? */
+#define CHIP_HAS_INV() 1
+
+/** Does the chip have a "wh64" instruction? */
+#define CHIP_HAS_WH64() 1
+
+/** Does this chip have a 'dword_align' instruction? */
+#define CHIP_HAS_DWORD_ALIGN() 0
+
+/** Number of performance counters. */
+#define CHIP_PERFORMANCE_COUNTERS() 4
+
+/** Does this chip have auxiliary performance counters? */
+#define CHIP_HAS_AUX_PERF_COUNTERS() 1
+
+/** Is the CBOX_MSR1 SPR supported? */
+#define CHIP_HAS_CBOX_MSR1() 0
+
+/** Is the TILE_RTF_HWM SPR supported? */
+#define CHIP_HAS_TILE_RTF_HWM() 1
+
+/** Is the TILE_WRITE_PENDING SPR supported? */
+#define CHIP_HAS_TILE_WRITE_PENDING() 0
+
+/** Is the PROC_STATUS SPR supported? */
+#define CHIP_HAS_PROC_STATUS_SPR() 1
+
+/** Is the DSTREAM_PF SPR supported? */
+#define CHIP_HAS_DSTREAM_PF() 1
+
+/** Log of the number of mshims we have. */
+#define CHIP_LOG_NUM_MSHIMS() 2
+
+/** Are the bases of the interrupt vector areas fixed? */
+#define CHIP_HAS_FIXED_INTVEC_BASE() 0
+
+/** Are the interrupt masks split up into 2 SPRs? */
+#define CHIP_HAS_SPLIT_INTR_MASK() 0
+
+/** Is the cycle count split up into 2 SPRs? */
+#define CHIP_HAS_SPLIT_CYCLE() 0
+
+/** Does the chip have a static network? */
+#define CHIP_HAS_SN() 0
+
+/** Does the chip have a static network processor? */
+#define CHIP_HAS_SN_PROC() 0
+
+/** Size of the L1 static network processor instruction cache, in bytes. */
+/* #define CHIP_L1SNI_CACHE_SIZE() -- does not apply to chip 10 */
+
+/** Does the chip have DMA support in each tile? */
+#define CHIP_HAS_TILE_DMA() 0
+
+/** Does the chip have the second revision of the directly accessible
+ *  dynamic networks?  This encapsulates a number of characteristics,
+ *  including the absence of the catch-all, the absence of inline message
+ *  tags, the absence of support for network context-switching, and so on.
+ */
+#define CHIP_HAS_REV1_XDN() 1
+
+/** Does the chip have cmpexch and similar (fetchadd, exch, etc.)? */
+#define CHIP_HAS_CMPEXCH() 1
+
+/** Does the chip have memory-mapped I/O support? */
+#define CHIP_HAS_MMIO() 1
+
+/** Does the chip have post-completion interrupts? */
+#define CHIP_HAS_POST_COMPLETION_INTERRUPTS() 1
+
+/** Does the chip have native single step support? */
+#define CHIP_HAS_SINGLE_STEP() 1
+
+#ifndef __OPEN_SOURCE__  /* features only relevant to hypervisor-level code */
+
+/** How many entries are present in the instruction TLB? */
+#define CHIP_ITLB_ENTRIES() 16
+
+/** How many entries are present in the data TLB? */
+#define CHIP_DTLB_ENTRIES() 32
+
+/** How many MAF entries does the XAUI shim have? */
+#define CHIP_XAUI_MAF_ENTRIES() 32
+
+/** Does the memory shim have a source-id table? */
+#define CHIP_HAS_MSHIM_SRCID_TABLE() 0
+
+/** Does the L1 instruction cache clear on reset? */
+#define CHIP_HAS_L1I_CLEAR_ON_RESET() 1
+
+/** Does the chip come out of reset with valid coordinates on all tiles?
+ * Note that if defined, this also implies that the upper left is 1,1.
+ */
+#define CHIP_HAS_VALID_TILE_COORD_RESET() 1
+
+/** Does the chip have unified packet formats? */
+#define CHIP_HAS_UNIFIED_PACKET_FORMATS() 1
+
+/** Does the chip support write reordering? */
+#define CHIP_HAS_WRITE_REORDERING() 1
+
+/** Does the chip support Y-X routing as well as X-Y? */
+#define CHIP_HAS_Y_X_ROUTING() 1
+
+/** Is INTCTRL_3 managed with the correct MPL? */
+#define CHIP_HAS_INTCTRL_3_STATUS_FIX() 1
+
+/** Is it possible to configure the chip to be big-endian? */
+#define CHIP_HAS_BIG_ENDIAN_CONFIG() 1
+
+/** Is the CACHE_RED_WAY_OVERRIDDEN SPR supported? */
+#define CHIP_HAS_CACHE_RED_WAY_OVERRIDDEN() 0
+
+/** Is the DIAG_TRACE_WAY SPR supported? */
+#define CHIP_HAS_DIAG_TRACE_WAY() 0
+
+/** Is the MEM_STRIPE_CONFIG SPR supported? */
+#define CHIP_HAS_MEM_STRIPE_CONFIG() 1
+
+/** Are the TLB_PERF SPRs supported? */
+#define CHIP_HAS_TLB_PERF() 1
+
+/** Is the VDN_SNOOP_SHIM_CTL SPR supported? */
+#define CHIP_HAS_VDN_SNOOP_SHIM_CTL() 0
+
+/** Does the chip support rev1 DMA packets? */
+#define CHIP_HAS_REV1_DMA_PACKETS() 1
+
+/** Does the chip have an IPI shim? */
+#define CHIP_HAS_IPI() 1
+
+#endif /* !__OPEN_SOURCE__ */
+#endif /* __ARCH_CHIP_H__ */
diff --git a/arch/tile/include/arch/icache.h b/arch/tile/include/arch/icache.h
index 5c87c9016338..762eafa8a11e 100644
--- a/arch/tile/include/arch/icache.h
+++ b/arch/tile/include/arch/icache.h
@@ -16,7 +16,7 @@
 /**
  * @file
  *
- * Support for invalidating bytes in the instruction
+ * Support for invalidating bytes in the instruction cache.
  */
 
 #ifndef __ARCH_ICACHE_H__
@@ -30,11 +30,10 @@
  *
  * @param addr The start of memory to be invalidated.
  * @param size The number of bytes to be invalidated.
- * @param page_size The system's page size, typically the PAGE_SIZE constant
- * in sys/page.h.  This value must be a power of two no larger
- * than the page containing the code to be invalidated. If the value
- * is smaller than the actual page size, this function will still
- * work, but may run slower than necessary.
+ * @param page_size The system's page size, e.g. getpagesize() in userspace.
+ * This value must be a power of two no larger than the page containing
+ * the code to be invalidated. If the value is smaller than the actual page
+ * size, this function will still work, but may run slower than necessary.
  */
 static __inline void
 invalidate_icache(const void* addr, unsigned long size,
diff --git a/arch/tile/include/arch/interrupts_64.h b/arch/tile/include/arch/interrupts_64.h
new file mode 100644
index 000000000000..5bb58b2e4e6f
--- /dev/null
+++ b/arch/tile/include/arch/interrupts_64.h
@@ -0,0 +1,276 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef __ARCH_INTERRUPTS_H__
+#define __ARCH_INTERRUPTS_H__
+
+/** Mask for an interrupt. */
+#ifdef __ASSEMBLER__
+/* Note: must handle breaking interrupts into high and low words manually. */
+#define INT_MASK(intno) (1 << (intno))
+#else
+#define INT_MASK(intno) (1ULL << (intno))
+#endif
+
+
+/** Where a given interrupt executes */
+#define INTERRUPT_VECTOR(i, pl) (0xFC000000 + ((pl) << 24) + ((i) << 8))
+
+/** Where to store a vector for a given interrupt. */
+#define USER_INTERRUPT_VECTOR(i) INTERRUPT_VECTOR(i, 0)
+
+/** The base address of user-level interrupts. */
+#define USER_INTERRUPT_VECTOR_BASE INTERRUPT_VECTOR(0, 0)
+
+
+/** Additional synthetic interrupt. */
+#define INT_BREAKPOINT (63)
+
+#define INT_MEM_ERROR    0
+#define INT_SINGLE_STEP_3    1
+#define INT_SINGLE_STEP_2    2
+#define INT_SINGLE_STEP_1    3
+#define INT_SINGLE_STEP_0    4
+#define INT_IDN_COMPLETE    5
+#define INT_UDN_COMPLETE    6
+#define INT_ITLB_MISS    7
+#define INT_ILL    8
+#define INT_GPV    9
+#define INT_IDN_ACCESS   10
+#define INT_UDN_ACCESS   11
+#define INT_SWINT_3   12
+#define INT_SWINT_2   13
+#define INT_SWINT_1   14
+#define INT_SWINT_0   15
+#define INT_ILL_TRANS   16
+#define INT_UNALIGN_DATA   17
+#define INT_DTLB_MISS   18
+#define INT_DTLB_ACCESS   19
+#define INT_IDN_FIREWALL   20
+#define INT_UDN_FIREWALL   21
+#define INT_TILE_TIMER   22
+#define INT_AUX_TILE_TIMER   23
+#define INT_IDN_TIMER   24
+#define INT_UDN_TIMER   25
+#define INT_IDN_AVAIL   26
+#define INT_UDN_AVAIL   27
+#define INT_IPI_3   28
+#define INT_IPI_2   29
+#define INT_IPI_1   30
+#define INT_IPI_0   31
+#define INT_PERF_COUNT   32
+#define INT_AUX_PERF_COUNT   33
+#define INT_INTCTRL_3   34
+#define INT_INTCTRL_2   35
+#define INT_INTCTRL_1   36
+#define INT_INTCTRL_0   37
+#define INT_BOOT_ACCESS   38
+#define INT_WORLD_ACCESS   39
+#define INT_I_ASID   40
+#define INT_D_ASID   41
+#define INT_DOUBLE_FAULT   42
+
+#define NUM_INTERRUPTS 43
+
+#ifndef __ASSEMBLER__
+#define QUEUED_INTERRUPTS ( \
+    INT_MASK(INT_MEM_ERROR) | \
+    INT_MASK(INT_IDN_COMPLETE) | \
+    INT_MASK(INT_UDN_COMPLETE) | \
+    INT_MASK(INT_IDN_FIREWALL) | \
+    INT_MASK(INT_UDN_FIREWALL) | \
+    INT_MASK(INT_TILE_TIMER) | \
+    INT_MASK(INT_AUX_TILE_TIMER) | \
+    INT_MASK(INT_IDN_TIMER) | \
+    INT_MASK(INT_UDN_TIMER) | \
+    INT_MASK(INT_IDN_AVAIL) | \
+    INT_MASK(INT_UDN_AVAIL) | \
+    INT_MASK(INT_IPI_3) | \
+    INT_MASK(INT_IPI_2) | \
+    INT_MASK(INT_IPI_1) | \
+    INT_MASK(INT_IPI_0) | \
+    INT_MASK(INT_PERF_COUNT) | \
+    INT_MASK(INT_AUX_PERF_COUNT) | \
+    INT_MASK(INT_INTCTRL_3) | \
+    INT_MASK(INT_INTCTRL_2) | \
+    INT_MASK(INT_INTCTRL_1) | \
+    INT_MASK(INT_INTCTRL_0) | \
+    INT_MASK(INT_BOOT_ACCESS) | \
+    INT_MASK(INT_WORLD_ACCESS) | \
+    INT_MASK(INT_I_ASID) | \
+    INT_MASK(INT_D_ASID) | \
+    INT_MASK(INT_DOUBLE_FAULT) | \
+    0)
+#define NONQUEUED_INTERRUPTS ( \
+    INT_MASK(INT_SINGLE_STEP_3) | \
+    INT_MASK(INT_SINGLE_STEP_2) | \
+    INT_MASK(INT_SINGLE_STEP_1) | \
+    INT_MASK(INT_SINGLE_STEP_0) | \
+    INT_MASK(INT_ITLB_MISS) | \
+    INT_MASK(INT_ILL) | \
+    INT_MASK(INT_GPV) | \
+    INT_MASK(INT_IDN_ACCESS) | \
+    INT_MASK(INT_UDN_ACCESS) | \
+    INT_MASK(INT_SWINT_3) | \
+    INT_MASK(INT_SWINT_2) | \
+    INT_MASK(INT_SWINT_1) | \
+    INT_MASK(INT_SWINT_0) | \
+    INT_MASK(INT_ILL_TRANS) | \
+    INT_MASK(INT_UNALIGN_DATA) | \
+    INT_MASK(INT_DTLB_MISS) | \
+    INT_MASK(INT_DTLB_ACCESS) | \
+    0)
+#define CRITICAL_MASKED_INTERRUPTS ( \
+    INT_MASK(INT_MEM_ERROR) | \
+    INT_MASK(INT_SINGLE_STEP_3) | \
+    INT_MASK(INT_SINGLE_STEP_2) | \
+    INT_MASK(INT_SINGLE_STEP_1) | \
+    INT_MASK(INT_SINGLE_STEP_0) | \
+    INT_MASK(INT_IDN_COMPLETE) | \
+    INT_MASK(INT_UDN_COMPLETE) | \
+    INT_MASK(INT_IDN_FIREWALL) | \
+    INT_MASK(INT_UDN_FIREWALL) | \
+    INT_MASK(INT_TILE_TIMER) | \
+    INT_MASK(INT_AUX_TILE_TIMER) | \
+    INT_MASK(INT_IDN_TIMER) | \
+    INT_MASK(INT_UDN_TIMER) | \
+    INT_MASK(INT_IDN_AVAIL) | \
+    INT_MASK(INT_UDN_AVAIL) | \
+    INT_MASK(INT_IPI_3) | \
+    INT_MASK(INT_IPI_2) | \
+    INT_MASK(INT_IPI_1) | \
+    INT_MASK(INT_IPI_0) | \
+    INT_MASK(INT_PERF_COUNT) | \
+    INT_MASK(INT_AUX_PERF_COUNT) | \
+    INT_MASK(INT_INTCTRL_3) | \
+    INT_MASK(INT_INTCTRL_2) | \
+    INT_MASK(INT_INTCTRL_1) | \
+    INT_MASK(INT_INTCTRL_0) | \
+    0)
+#define CRITICAL_UNMASKED_INTERRUPTS ( \
+    INT_MASK(INT_ITLB_MISS) | \
+    INT_MASK(INT_ILL) | \
+    INT_MASK(INT_GPV) | \
+    INT_MASK(INT_IDN_ACCESS) | \
+    INT_MASK(INT_UDN_ACCESS) | \
+    INT_MASK(INT_SWINT_3) | \
+    INT_MASK(INT_SWINT_2) | \
+    INT_MASK(INT_SWINT_1) | \
+    INT_MASK(INT_SWINT_0) | \
+    INT_MASK(INT_ILL_TRANS) | \
+    INT_MASK(INT_UNALIGN_DATA) | \
+    INT_MASK(INT_DTLB_MISS) | \
+    INT_MASK(INT_DTLB_ACCESS) | \
+    INT_MASK(INT_BOOT_ACCESS) | \
+    INT_MASK(INT_WORLD_ACCESS) | \
+    INT_MASK(INT_I_ASID) | \
+    INT_MASK(INT_D_ASID) | \
+    INT_MASK(INT_DOUBLE_FAULT) | \
+    0)
+#define MASKABLE_INTERRUPTS ( \
+    INT_MASK(INT_MEM_ERROR) | \
+    INT_MASK(INT_SINGLE_STEP_3) | \
+    INT_MASK(INT_SINGLE_STEP_2) | \
+    INT_MASK(INT_SINGLE_STEP_1) | \
+    INT_MASK(INT_SINGLE_STEP_0) | \
+    INT_MASK(INT_IDN_COMPLETE) | \
+    INT_MASK(INT_UDN_COMPLETE) | \
+    INT_MASK(INT_IDN_FIREWALL) | \
+    INT_MASK(INT_UDN_FIREWALL) | \
+    INT_MASK(INT_TILE_TIMER) | \
+    INT_MASK(INT_AUX_TILE_TIMER) | \
+    INT_MASK(INT_IDN_TIMER) | \
+    INT_MASK(INT_UDN_TIMER) | \
+    INT_MASK(INT_IDN_AVAIL) | \
+    INT_MASK(INT_UDN_AVAIL) | \
+    INT_MASK(INT_IPI_3) | \
+    INT_MASK(INT_IPI_2) | \
+    INT_MASK(INT_IPI_1) | \
+    INT_MASK(INT_IPI_0) | \
+    INT_MASK(INT_PERF_COUNT) | \
+    INT_MASK(INT_AUX_PERF_COUNT) | \
+    INT_MASK(INT_INTCTRL_3) | \
+    INT_MASK(INT_INTCTRL_2) | \
+    INT_MASK(INT_INTCTRL_1) | \
+    INT_MASK(INT_INTCTRL_0) | \
+    0)
+#define UNMASKABLE_INTERRUPTS ( \
+    INT_MASK(INT_ITLB_MISS) | \
+    INT_MASK(INT_ILL) | \
+    INT_MASK(INT_GPV) | \
+    INT_MASK(INT_IDN_ACCESS) | \
+    INT_MASK(INT_UDN_ACCESS) | \
+    INT_MASK(INT_SWINT_3) | \
+    INT_MASK(INT_SWINT_2) | \
+    INT_MASK(INT_SWINT_1) | \
+    INT_MASK(INT_SWINT_0) | \
+    INT_MASK(INT_ILL_TRANS) | \
+    INT_MASK(INT_UNALIGN_DATA) | \
+    INT_MASK(INT_DTLB_MISS) | \
+    INT_MASK(INT_DTLB_ACCESS) | \
+    INT_MASK(INT_BOOT_ACCESS) | \
+    INT_MASK(INT_WORLD_ACCESS) | \
+    INT_MASK(INT_I_ASID) | \
+    INT_MASK(INT_D_ASID) | \
+    INT_MASK(INT_DOUBLE_FAULT) | \
+    0)
+#define SYNC_INTERRUPTS ( \
+    INT_MASK(INT_SINGLE_STEP_3) | \
+    INT_MASK(INT_SINGLE_STEP_2) | \
+    INT_MASK(INT_SINGLE_STEP_1) | \
+    INT_MASK(INT_SINGLE_STEP_0) | \
+    INT_MASK(INT_IDN_COMPLETE) | \
+    INT_MASK(INT_UDN_COMPLETE) | \
+    INT_MASK(INT_ITLB_MISS) | \
+    INT_MASK(INT_ILL) | \
+    INT_MASK(INT_GPV) | \
+    INT_MASK(INT_IDN_ACCESS) | \
+    INT_MASK(INT_UDN_ACCESS) | \
+    INT_MASK(INT_SWINT_3) | \
+    INT_MASK(INT_SWINT_2) | \
+    INT_MASK(INT_SWINT_1) | \
+    INT_MASK(INT_SWINT_0) | \
+    INT_MASK(INT_ILL_TRANS) | \
+    INT_MASK(INT_UNALIGN_DATA) | \
+    INT_MASK(INT_DTLB_MISS) | \
+    INT_MASK(INT_DTLB_ACCESS) | \
+    0)
+#define NON_SYNC_INTERRUPTS ( \
+    INT_MASK(INT_MEM_ERROR) | \
+    INT_MASK(INT_IDN_FIREWALL) | \
+    INT_MASK(INT_UDN_FIREWALL) | \
+    INT_MASK(INT_TILE_TIMER) | \
+    INT_MASK(INT_AUX_TILE_TIMER) | \
+    INT_MASK(INT_IDN_TIMER) | \
+    INT_MASK(INT_UDN_TIMER) | \
+    INT_MASK(INT_IDN_AVAIL) | \
+    INT_MASK(INT_UDN_AVAIL) | \
+    INT_MASK(INT_IPI_3) | \
+    INT_MASK(INT_IPI_2) | \
+    INT_MASK(INT_IPI_1) | \
+    INT_MASK(INT_IPI_0) | \
+    INT_MASK(INT_PERF_COUNT) | \
+    INT_MASK(INT_AUX_PERF_COUNT) | \
+    INT_MASK(INT_INTCTRL_3) | \
+    INT_MASK(INT_INTCTRL_2) | \
+    INT_MASK(INT_INTCTRL_1) | \
+    INT_MASK(INT_INTCTRL_0) | \
+    INT_MASK(INT_BOOT_ACCESS) | \
+    INT_MASK(INT_WORLD_ACCESS) | \
+    INT_MASK(INT_I_ASID) | \
+    INT_MASK(INT_D_ASID) | \
+    INT_MASK(INT_DOUBLE_FAULT) | \
+    0)
+#endif /* !__ASSEMBLER__ */
+#endif /* !__ARCH_INTERRUPTS_H__ */
diff --git a/arch/tile/include/arch/spr_def.h b/arch/tile/include/arch/spr_def.h
index 442fcba0d122..f548efeb2de3 100644
--- a/arch/tile/include/arch/spr_def.h
+++ b/arch/tile/include/arch/spr_def.h
@@ -12,6 +12,15 @@
  *   more details.
  */
 
+/* Include the proper base SPR definition file. */
+#ifdef __tilegx__
+#include <arch/spr_def_64.h>
+#else
+#include <arch/spr_def_32.h>
+#endif
+
+#ifdef __KERNEL__
+
 /*
  * In addition to including the proper base SPR definition file, depending
  * on machine architecture, this file defines several macros which allow
@@ -29,7 +38,6 @@
 #define _concat4(a, b, c, d)  __concat4(a, b, c, d)
 
 #ifdef __tilegx__
-#include <arch/spr_def_64.h>
 
 /* TILE-Gx dependent, protection-level dependent SPRs. */
 
@@ -65,7 +73,6 @@
         _concat4(INT_SINGLE_STEP_, CONFIG_KERNEL_PL,,)
 
 #else
-#include <arch/spr_def_32.h>
 
 /* TILEPro dependent, protection-level dependent SPRs. */
 
@@ -102,3 +109,5 @@
         _concat4(SPR_INTCTRL_, CONFIG_KERNEL_PL, _STATUS,)
 #define INT_INTCTRL_K \
         _concat4(INT_INTCTRL_, CONFIG_KERNEL_PL,,)
+
+#endif /* __KERNEL__ */
diff --git a/arch/tile/include/arch/spr_def_64.h b/arch/tile/include/arch/spr_def_64.h
new file mode 100644
index 000000000000..cd3e5f95d5fd
--- /dev/null
+++ b/arch/tile/include/arch/spr_def_64.h
@@ -0,0 +1,173 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef __DOXYGEN__
+
+#ifndef __ARCH_SPR_DEF_H__
+#define __ARCH_SPR_DEF_H__
+
+#define SPR_AUX_PERF_COUNT_0 0x2105
+#define SPR_AUX_PERF_COUNT_1 0x2106
+#define SPR_AUX_PERF_COUNT_CTL 0x2107
+#define SPR_AUX_PERF_COUNT_STS 0x2108
+#define SPR_CMPEXCH_VALUE 0x2780
+#define SPR_CYCLE 0x2781
+#define SPR_DONE 0x2705
+#define SPR_DSTREAM_PF 0x2706
+#define SPR_EVENT_BEGIN 0x2782
+#define SPR_EVENT_END 0x2783
+#define SPR_EX_CONTEXT_0_0 0x2580
+#define SPR_EX_CONTEXT_0_1 0x2581
+#define SPR_EX_CONTEXT_0_1__PL_SHIFT 0
+#define SPR_EX_CONTEXT_0_1__PL_RMASK 0x3
+#define SPR_EX_CONTEXT_0_1__PL_MASK  0x3
+#define SPR_EX_CONTEXT_0_1__ICS_SHIFT 2
+#define SPR_EX_CONTEXT_0_1__ICS_RMASK 0x1
+#define SPR_EX_CONTEXT_0_1__ICS_MASK  0x4
+#define SPR_EX_CONTEXT_1_0 0x2480
+#define SPR_EX_CONTEXT_1_1 0x2481
+#define SPR_EX_CONTEXT_1_1__PL_SHIFT 0
+#define SPR_EX_CONTEXT_1_1__PL_RMASK 0x3
+#define SPR_EX_CONTEXT_1_1__PL_MASK  0x3
+#define SPR_EX_CONTEXT_1_1__ICS_SHIFT 2
+#define SPR_EX_CONTEXT_1_1__ICS_RMASK 0x1
+#define SPR_EX_CONTEXT_1_1__ICS_MASK  0x4
+#define SPR_EX_CONTEXT_2_0 0x2380
+#define SPR_EX_CONTEXT_2_1 0x2381
+#define SPR_EX_CONTEXT_2_1__PL_SHIFT 0
+#define SPR_EX_CONTEXT_2_1__PL_RMASK 0x3
+#define SPR_EX_CONTEXT_2_1__PL_MASK  0x3
+#define SPR_EX_CONTEXT_2_1__ICS_SHIFT 2
+#define SPR_EX_CONTEXT_2_1__ICS_RMASK 0x1
+#define SPR_EX_CONTEXT_2_1__ICS_MASK  0x4
+#define SPR_FAIL 0x2707
+#define SPR_ILL_TRANS_REASON__I_STREAM_VA_RMASK 0x1
+#define SPR_INTCTRL_0_STATUS 0x2505
+#define SPR_INTCTRL_1_STATUS 0x2405
+#define SPR_INTCTRL_2_STATUS 0x2305
+#define SPR_INTERRUPT_CRITICAL_SECTION 0x2708
+#define SPR_INTERRUPT_MASK_0 0x2506
+#define SPR_INTERRUPT_MASK_1 0x2406
+#define SPR_INTERRUPT_MASK_2 0x2306
+#define SPR_INTERRUPT_MASK_RESET_0 0x2507
+#define SPR_INTERRUPT_MASK_RESET_1 0x2407
+#define SPR_INTERRUPT_MASK_RESET_2 0x2307
+#define SPR_INTERRUPT_MASK_SET_0 0x2508
+#define SPR_INTERRUPT_MASK_SET_1 0x2408
+#define SPR_INTERRUPT_MASK_SET_2 0x2308
+#define SPR_INTERRUPT_VECTOR_BASE_0 0x2509
+#define SPR_INTERRUPT_VECTOR_BASE_1 0x2409
+#define SPR_INTERRUPT_VECTOR_BASE_2 0x2309
+#define SPR_INTERRUPT_VECTOR_BASE_3 0x2209
+#define SPR_IPI_EVENT_0 0x1f05
+#define SPR_IPI_EVENT_1 0x1e05
+#define SPR_IPI_EVENT_2 0x1d05
+#define SPR_IPI_EVENT_RESET_0 0x1f06
+#define SPR_IPI_EVENT_RESET_1 0x1e06
+#define SPR_IPI_EVENT_RESET_2 0x1d06
+#define SPR_IPI_EVENT_SET_0 0x1f07
+#define SPR_IPI_EVENT_SET_1 0x1e07
+#define SPR_IPI_EVENT_SET_2 0x1d07
+#define SPR_IPI_MASK_0 0x1f08
+#define SPR_IPI_MASK_1 0x1e08
+#define SPR_IPI_MASK_2 0x1d08
+#define SPR_IPI_MASK_RESET_0 0x1f09
+#define SPR_IPI_MASK_RESET_1 0x1e09
+#define SPR_IPI_MASK_RESET_2 0x1d09
+#define SPR_IPI_MASK_SET_0 0x1f0a
+#define SPR_IPI_MASK_SET_1 0x1e0a
+#define SPR_IPI_MASK_SET_2 0x1d0a
+#define SPR_MPL_AUX_TILE_TIMER_SET_0 0x1700
+#define SPR_MPL_AUX_TILE_TIMER_SET_1 0x1701
+#define SPR_MPL_AUX_TILE_TIMER_SET_2 0x1702
+#define SPR_MPL_INTCTRL_0_SET_0 0x2500
+#define SPR_MPL_INTCTRL_0_SET_1 0x2501
+#define SPR_MPL_INTCTRL_0_SET_2 0x2502
+#define SPR_MPL_INTCTRL_1_SET_0 0x2400
+#define SPR_MPL_INTCTRL_1_SET_1 0x2401
+#define SPR_MPL_INTCTRL_1_SET_2 0x2402
+#define SPR_MPL_INTCTRL_2_SET_0 0x2300
+#define SPR_MPL_INTCTRL_2_SET_1 0x2301
+#define SPR_MPL_INTCTRL_2_SET_2 0x2302
+#define SPR_MPL_UDN_ACCESS_SET_0 0x0b00
+#define SPR_MPL_UDN_ACCESS_SET_1 0x0b01
+#define SPR_MPL_UDN_ACCESS_SET_2 0x0b02
+#define SPR_MPL_UDN_AVAIL_SET_0 0x1b00
+#define SPR_MPL_UDN_AVAIL_SET_1 0x1b01
+#define SPR_MPL_UDN_AVAIL_SET_2 0x1b02
+#define SPR_MPL_UDN_COMPLETE_SET_0 0x0600
+#define SPR_MPL_UDN_COMPLETE_SET_1 0x0601
+#define SPR_MPL_UDN_COMPLETE_SET_2 0x0602
+#define SPR_MPL_UDN_FIREWALL_SET_0 0x1500
+#define SPR_MPL_UDN_FIREWALL_SET_1 0x1501
+#define SPR_MPL_UDN_FIREWALL_SET_2 0x1502
+#define SPR_MPL_UDN_TIMER_SET_0 0x1900
+#define SPR_MPL_UDN_TIMER_SET_1 0x1901
+#define SPR_MPL_UDN_TIMER_SET_2 0x1902
+#define SPR_MPL_WORLD_ACCESS_SET_0 0x2700
+#define SPR_MPL_WORLD_ACCESS_SET_1 0x2701
+#define SPR_MPL_WORLD_ACCESS_SET_2 0x2702
+#define SPR_PASS 0x2709
+#define SPR_PERF_COUNT_0 0x2005
+#define SPR_PERF_COUNT_1 0x2006
+#define SPR_PERF_COUNT_CTL 0x2007
+#define SPR_PERF_COUNT_DN_CTL 0x2008
+#define SPR_PERF_COUNT_STS 0x2009
+#define SPR_PROC_STATUS 0x2784
+#define SPR_SIM_CONTROL 0x2785
+#define SPR_SINGLE_STEP_CONTROL_0 0x0405
+#define SPR_SINGLE_STEP_CONTROL_0__CANCELED_MASK  0x1
+#define SPR_SINGLE_STEP_CONTROL_0__INHIBIT_MASK  0x2
+#define SPR_SINGLE_STEP_CONTROL_1 0x0305
+#define SPR_SINGLE_STEP_CONTROL_1__CANCELED_MASK  0x1
+#define SPR_SINGLE_STEP_CONTROL_1__INHIBIT_MASK  0x2
+#define SPR_SINGLE_STEP_CONTROL_2 0x0205
+#define SPR_SINGLE_STEP_CONTROL_2__CANCELED_MASK  0x1
+#define SPR_SINGLE_STEP_CONTROL_2__INHIBIT_MASK  0x2
+#define SPR_SINGLE_STEP_EN_0_0 0x250a
+#define SPR_SINGLE_STEP_EN_0_1 0x240a
+#define SPR_SINGLE_STEP_EN_0_2 0x230a
+#define SPR_SINGLE_STEP_EN_1_0 0x250b
+#define SPR_SINGLE_STEP_EN_1_1 0x240b
+#define SPR_SINGLE_STEP_EN_1_2 0x230b
+#define SPR_SINGLE_STEP_EN_2_0 0x250c
+#define SPR_SINGLE_STEP_EN_2_1 0x240c
+#define SPR_SINGLE_STEP_EN_2_2 0x230c
+#define SPR_SYSTEM_SAVE_0_0 0x2582
+#define SPR_SYSTEM_SAVE_0_1 0x2583
+#define SPR_SYSTEM_SAVE_0_2 0x2584
+#define SPR_SYSTEM_SAVE_0_3 0x2585
+#define SPR_SYSTEM_SAVE_1_0 0x2482
+#define SPR_SYSTEM_SAVE_1_1 0x2483
+#define SPR_SYSTEM_SAVE_1_2 0x2484
+#define SPR_SYSTEM_SAVE_1_3 0x2485
+#define SPR_SYSTEM_SAVE_2_0 0x2382
+#define SPR_SYSTEM_SAVE_2_1 0x2383
+#define SPR_SYSTEM_SAVE_2_2 0x2384
+#define SPR_SYSTEM_SAVE_2_3 0x2385
+#define SPR_TILE_COORD 0x270b
+#define SPR_TILE_RTF_HWM 0x270c
+#define SPR_TILE_TIMER_CONTROL 0x1605
+#define SPR_UDN_AVAIL_EN 0x1b05
+#define SPR_UDN_DATA_AVAIL 0x0b80
+#define SPR_UDN_DEADLOCK_TIMEOUT 0x1906
+#define SPR_UDN_DEMUX_COUNT_0 0x0b05
+#define SPR_UDN_DEMUX_COUNT_1 0x0b06
+#define SPR_UDN_DEMUX_COUNT_2 0x0b07
+#define SPR_UDN_DEMUX_COUNT_3 0x0b08
+#define SPR_UDN_DIRECTION_PROTECT 0x1505
+
+#endif /* !defined(__ARCH_SPR_DEF_H__) */
+
+#endif /* !defined(__DOXYGEN__) */
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index 75a16028a952..739cfe0499d1 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -130,17 +130,52 @@ static inline int atomic_read(const atomic_t *v)
  */
 #define atomic_inc_not_zero(v)          atomic_add_unless((v), 1, 0)
 
-
-/*
- * We define xchg() and cmpxchg() in the included headers.
- * Note that we do not define __HAVE_ARCH_CMPXCHG, since that would imply
- * that cmpxchg() is an efficient operation, which is not particularly true.
- */
-
 /* Nonexistent functions intended to cause link errors. */
 extern unsigned long __xchg_called_with_bad_pointer(void);
 extern unsigned long __cmpxchg_called_with_bad_pointer(void);
 
+#define xchg(ptr, x)                                                    \
+        ({                                                              \
+                typeof(*(ptr)) __x;                                     \
+                switch (sizeof(*(ptr))) {                               \
+                case 4:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic_xchg( \
+                                (atomic_t *)(ptr),                      \
+                                (u32)(typeof((x)-(x)))(x));             \
+                        break;                                          \
+                case 8:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic64_xchg( \
+                                (atomic64_t *)(ptr),                    \
+                                (u64)(typeof((x)-(x)))(x));             \
+                        break;                                          \
+                default:                                                \
+                        __xchg_called_with_bad_pointer();               \
+                }                                                       \
+                __x;                                                    \
+        })
+
+#define cmpxchg(ptr, o, n)                                              \
+        ({                                                              \
+                typeof(*(ptr)) __x;                                     \
+                switch (sizeof(*(ptr))) {                               \
+                case 4:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic_cmpxchg( \
+                                (atomic_t *)(ptr),                      \
+                                (u32)(typeof((o)-(o)))(o),              \
+                                (u32)(typeof((n)-(n)))(n));             \
+                        break;                                          \
+                case 8:                                                 \
+                        __x = (typeof(__x))(typeof(__x-__x))atomic64_cmpxchg( \
+                                (atomic64_t *)(ptr),                    \
+                                (u64)(typeof((o)-(o)))(o),              \
+                                (u64)(typeof((n)-(n)))(n));             \
+                        break;                                          \
+                default:                                                \
+                        __cmpxchg_called_with_bad_pointer();            \
+                }                                                       \
+                __x;                                                    \
+        })
+
 #define tas(ptr) (xchg((ptr), 1))
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index ed359aee8837..92a8bee32311 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -110,16 +110,6 @@ static inline void atomic_set(atomic_t *v, int n)
         _atomic_xchg(v, n);
 }
 
-#define xchg(ptr, x) ((typeof(*(ptr))) \
-  ((sizeof(*(ptr)) == sizeof(atomic_t)) ? \
-   atomic_xchg((atomic_t *)(ptr), (long)(x)) : \
-   __xchg_called_with_bad_pointer()))
-
-#define cmpxchg(ptr, o, n) ((typeof(*(ptr))) \
-  ((sizeof(*(ptr)) == sizeof(atomic_t)) ? \
-   atomic_cmpxchg((atomic_t *)(ptr), (long)(o), (long)(n)) : \
-   __cmpxchg_called_with_bad_pointer()))
-
 /* A 64bit atomic type */
 
 typedef struct {
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
new file mode 100644
index 000000000000..1c1e60d8ccb6
--- /dev/null
+++ b/arch/tile/include/asm/atomic_64.h
@@ -0,0 +1,156 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * Do not include directly; use <asm/atomic.h>.
+ */
+
+#ifndef _ASM_TILE_ATOMIC_64_H
+#define _ASM_TILE_ATOMIC_64_H
+
+#ifndef __ASSEMBLY__
+
+#include <arch/spr_def.h>
+
+/* First, the 32-bit atomic ops that are "real" on our 64-bit platform. */
+
+#define atomic_set(v, i) ((v)->counter = (i))
+
+/*
+ * The smp_mb() operations throughout are to support the fact that
+ * Linux requires memory barriers before and after the operation,
+ * on any routine which updates memory and returns a value.
+ */
+
+static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
+{
+        int val;
+        __insn_mtspr(SPR_CMPEXCH_VALUE, o);
+        smp_mb();  /* barrier for proper semantics */
+        val = __insn_cmpexch4((void *)&v->counter, n);
+        smp_mb();  /* barrier for proper semantics */
+        return val;
+}
+
+static inline int atomic_xchg(atomic_t *v, int n)
+{
+        int val;
+        smp_mb();  /* barrier for proper semantics */
+        val = __insn_exch4((void *)&v->counter, n);
+        smp_mb();  /* barrier for proper semantics */
+        return val;
+}
+
+static inline void atomic_add(int i, atomic_t *v)
+{
+        __insn_fetchadd4((void *)&v->counter, i);
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+        int val;
+        smp_mb();  /* barrier for proper semantics */
+        val = __insn_fetchadd4((void *)&v->counter, i) + i;
+        barrier();  /* the "+ i" above will wait on memory */
+        return val;
+}
+
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+        int guess, oldval = v->counter;
+        do {
+                if (oldval == u)
+                        break;
+                guess = oldval;
+                oldval = atomic_cmpxchg(v, guess, guess + a);
+        } while (guess != oldval);
+        return oldval != u;
+}
+
+/* Now the true 64-bit operations. */
+
+#define ATOMIC64_INIT(i)        { (i) }
+
+#define atomic64_read(v)                ((v)->counter)
+#define atomic64_set(v, i) ((v)->counter = (i))
+
+static inline long atomic64_cmpxchg(atomic64_t *v, long o, long n)
+{
+        long val;
+        smp_mb();  /* barrier for proper semantics */
+        __insn_mtspr(SPR_CMPEXCH_VALUE, o);
+        val = __insn_cmpexch((void *)&v->counter, n);
+        smp_mb();  /* barrier for proper semantics */
+        return val;
+}
+
+static inline long atomic64_xchg(atomic64_t *v, long n)
+{
+        long val;
+        smp_mb();  /* barrier for proper semantics */
+        val = __insn_exch((void *)&v->counter, n);
+        smp_mb();  /* barrier for proper semantics */
+        return val;
+}
+
+static inline void atomic64_add(long i, atomic64_t *v)
+{
+        __insn_fetchadd((void *)&v->counter, i);
+}
+
+static inline long atomic64_add_return(long i, atomic64_t *v)
+{
+        int val;
+        smp_mb();  /* barrier for proper semantics */
+        val = __insn_fetchadd((void *)&v->counter, i) + i;
+        barrier();  /* the "+ i" above will wait on memory */
+        return val;
+}
+
+static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+        long guess, oldval = v->counter;
+        do {
+                if (oldval == u)
+                        break;
+                guess = oldval;
+                oldval = atomic64_cmpxchg(v, guess, guess + a);
+        } while (guess != oldval);
+        return oldval != u;
+}
+
+#define atomic64_sub_return(i, v)       atomic64_add_return(-(i), (v))
+#define atomic64_sub(i, v)              atomic64_add(-(i), (v))
+#define atomic64_inc_return(v)          atomic64_add_return(1, (v))
+#define atomic64_dec_return(v)          atomic64_sub_return(1, (v))
+#define atomic64_inc(v)                 atomic64_add(1, (v))
+#define atomic64_dec(v)                 atomic64_sub(1, (v))
+
+#define atomic64_inc_and_test(v)        (atomic64_inc_return(v) == 0)
+#define atomic64_dec_and_test(v)        (atomic64_dec_return(v) == 0)
+#define atomic64_sub_and_test(i, v)     (atomic64_sub_return((i), (v)) == 0)
+#define atomic64_add_negative(i, v)     (atomic64_add_return((i), (v)) < 0)
+
+#define atomic64_inc_not_zero(v)        atomic64_add_unless((v), 1, 0)
+
+/* Atomic dec and inc don't implement barrier, so provide them if needed. */
+#define smp_mb__before_atomic_dec()     smp_mb()
+#define smp_mb__after_atomic_dec()      smp_mb()
+#define smp_mb__before_atomic_inc()     smp_mb()
+#define smp_mb__after_atomic_inc()      smp_mb()
+
+/* Define this to indicate that cmpxchg is an efficient operation. */
+#define __HAVE_ARCH_CMPXCHG
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_TILE_ATOMIC_64_H */
diff --git a/arch/tile/include/asm/backtrace.h b/arch/tile/include/asm/backtrace.h
index f18887d82399..bd5399a69edf 100644
--- a/arch/tile/include/asm/backtrace.h
+++ b/arch/tile/include/asm/backtrace.h
@@ -12,80 +12,41 @@
  *   more details.
  */
 
-#ifndef _TILE_BACKTRACE_H
-#define _TILE_BACKTRACE_H
-
-
+#ifndef _ASM_TILE_BACKTRACE_H
+#define _ASM_TILE_BACKTRACE_H
 
 #include <linux/types.h>
 
-#include <arch/chip.h>
-
-#if defined(__tile__)
-typedef unsigned long VirtualAddress;
-#elif CHIP_VA_WIDTH() > 32
-typedef unsigned long long VirtualAddress;
-#else
-typedef unsigned int VirtualAddress;
-#endif
-
-
-/** Reads 'size' bytes from 'address' and writes the data to 'result'.
+/* Reads 'size' bytes from 'address' and writes the data to 'result'.
  * Returns true if successful, else false (e.g. memory not readable).
  */
 typedef bool (*BacktraceMemoryReader)(void *result,
-                                      VirtualAddress address,
+                                      unsigned long address,
                                       unsigned int size,
                                       void *extra);
 
 typedef struct {
-        /** Current PC. */
-        VirtualAddress pc;
+        /* Current PC. */
+        unsigned long pc;
 
-        /** Current stack pointer value. */
-        VirtualAddress sp;
+        /* Current stack pointer value. */
+        unsigned long sp;
 
-        /** Current frame pointer value (i.e. caller's stack pointer) */
-        VirtualAddress fp;
+        /* Current frame pointer value (i.e. caller's stack pointer) */
+        unsigned long fp;
 
-        /** Internal use only: caller's PC for first frame. */
-        VirtualAddress initial_frame_caller_pc;
+        /* Internal use only: caller's PC for first frame. */
+        unsigned long initial_frame_caller_pc;
 
-        /** Internal use only: callback to read memory. */
+        /* Internal use only: callback to read memory. */
         BacktraceMemoryReader read_memory_func;
 
-        /** Internal use only: arbitrary argument to read_memory_func. */
+        /* Internal use only: arbitrary argument to read_memory_func. */
         void *read_memory_func_extra;
 
 } BacktraceIterator;
 
 
-/** Initializes a backtracer to start from the given location.
- *
- * If the frame pointer cannot be determined it is set to -1.
- *
- * @param state The state to be filled in.
- * @param read_memory_func A callback that reads memory. If NULL, a default
- *        value is provided.
- * @param read_memory_func_extra An arbitrary argument to read_memory_func.
- * @param pc The current PC.
- * @param lr The current value of the 'lr' register.
- * @param sp The current value of the 'sp' register.
- * @param r52 The current value of the 'r52' register.
- */
-extern void backtrace_init(BacktraceIterator *state,
-                           BacktraceMemoryReader read_memory_func,
-                           void *read_memory_func_extra,
-                           VirtualAddress pc, VirtualAddress lr,
-                           VirtualAddress sp, VirtualAddress r52);
-
-
-/** Advances the backtracing state to the calling frame, returning
- * true iff successful.
- */
-extern bool backtrace_next(BacktraceIterator *state);
-
-
 typedef enum {
 
         /* We have no idea what the caller's pc is. */
@@ -138,7 +99,7 @@ enum {
 };
 
 
-/** Internal constants used to define 'info' operands. */
+/* Internal constants used to define 'info' operands. */
 enum {
         /* 0 and 1 are reserved, as are all negative numbers. */
 
@@ -147,13 +108,10 @@ enum {
         CALLER_SP_IN_R52_BASE = 4,
 
         CALLER_SP_OFFSET_BASE = 8,
-
-        /* Marks the entry point of certain functions. */
-        ENTRY_POINT_INFO_OP = 16
 };
 
 
-/** Current backtracer state describing where it thinks the caller is. */
+/* Current backtracer state describing where it thinks the caller is. */
 typedef struct {
         /*
          * Public fields
@@ -192,7 +150,13 @@ typedef struct {
 
 } CallerLocation;
 
+extern void backtrace_init(BacktraceIterator *state,
+                          BacktraceMemoryReader read_memory_func,
+                          void *read_memory_func_extra,
+                          unsigned long pc, unsigned long lr,
+                          unsigned long sp, unsigned long r52);
 
 
+extern bool backtrace_next(BacktraceIterator *state);
 
-#endif /* _TILE_BACKTRACE_H */
+#endif /* _ASM_TILE_BACKTRACE_H */
diff --git a/arch/tile/include/asm/bitops.h b/arch/tile/include/asm/bitops.h
index 132e6bbd07e9..16f1fa51fea1 100644
--- a/arch/tile/include/asm/bitops.h
+++ b/arch/tile/include/asm/bitops.h
@@ -122,6 +122,7 @@ static inline unsigned long __arch_hweight64(__u64 w)
 #include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
 
 #endif /* _ASM_TILE_BITOPS_H */
diff --git a/arch/tile/include/asm/bitops_32.h b/arch/tile/include/asm/bitops_32.h
index 2638be51a164..d31ab905cfa7 100644
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -126,7 +126,6 @@ static inline int test_and_change_bit(unsigned nr,
 #define smp_mb__before_clear_bit()      smp_mb()
 #define smp_mb__after_clear_bit()       do {} while (0)
 
-#include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/ext2-atomic.h>
 
 #endif /* _ASM_TILE_BITOPS_32_H */
diff --git a/arch/tile/include/asm/bitops_64.h b/arch/tile/include/asm/bitops_64.h
new file mode 100644
index 000000000000..99615e8d2d8b
--- /dev/null
+++ b/arch/tile/include/asm/bitops_64.h
@@ -0,0 +1,105 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_BITOPS_64_H
+#define _ASM_TILE_BITOPS_64_H
+
+#include <linux/compiler.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+
+/* See <asm/bitops.h> for API comments. */
+
+static inline void set_bit(unsigned nr, volatile unsigned long *addr)
+{
+        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
+        __insn_fetchor((void *)(addr + nr / BITS_PER_LONG), mask);
+}
+
+static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
+{
+        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
+        __insn_fetchand((void *)(addr + nr / BITS_PER_LONG), ~mask);
+}
+
+#define smp_mb__before_clear_bit()      smp_mb()
+#define smp_mb__after_clear_bit()       smp_mb()
+
+
+static inline void change_bit(unsigned nr, volatile unsigned long *addr)
+{
+        unsigned long old, mask = (1UL << (nr % BITS_PER_LONG));
+        long guess, oldval;
+        addr += nr / BITS_PER_LONG;
+        old = *addr;
+        do {
+                guess = oldval;
+                oldval = atomic64_cmpxchg((atomic64_t *)addr,
+                                          guess, guess ^ mask);
+        } while (guess != oldval);
+}
+
+
+/*
+ * The test_and_xxx_bit() routines require a memory fence before we
+ * start the operation, and after the operation completes.  We use
+ * smp_mb() before, and rely on the "!= 0" comparison, plus a compiler
+ * barrier(), to block until the atomic op is complete.
+ */
+
+static inline int test_and_set_bit(unsigned nr, volatile unsigned long *addr)
+{
+        int val;
+        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
+        smp_mb();  /* barrier for proper semantics */
+        val = (__insn_fetchor((void *)(addr + nr / BITS_PER_LONG), mask)
+               & mask) != 0;
+        barrier();
+        return val;
+}
+
+
+static inline int test_and_clear_bit(unsigned nr, volatile unsigned long *addr)
+{
+        int val;
+        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
+        smp_mb();  /* barrier for proper semantics */
+        val = (__insn_fetchand((void *)(addr + nr / BITS_PER_LONG), ~mask)
+               & mask) != 0;
+        barrier();
+        return val;
+}
+
+
+static inline int test_and_change_bit(unsigned nr,
+                                      volatile unsigned long *addr)
+{
+        unsigned long mask = (1UL << (nr % BITS_PER_LONG));
+        long guess, oldval = *addr;
+        addr += nr / BITS_PER_LONG;
+        oldval = *addr;
+        do {
+                guess = oldval;
+                oldval = atomic64_cmpxchg((atomic64_t *)addr,
+                                          guess, guess ^ mask);
+        } while (guess != oldval);
+        return (oldval & mask) != 0;
+}
+
+#define ext2_set_bit_atomic(lock, nr, addr)                     \
+        test_and_set_bit((nr), (unsigned long *)(addr))
+#define ext2_clear_bit_atomic(lock, nr, addr)                   \
+        test_and_clear_bit((nr), (unsigned long *)(addr))
+
+#endif /* _ASM_TILE_BITOPS_64_H */
diff --git a/arch/tile/include/asm/cacheflush.h b/arch/tile/include/asm/cacheflush.h
index 12fb0fb330ee..e925f4bb498f 100644
--- a/arch/tile/include/asm/cacheflush.h
+++ b/arch/tile/include/asm/cacheflush.h
@@ -116,22 +116,28 @@ static inline void __finv_buffer(void *buffer, size_t size)
 }
 
 
-/* Invalidate a VA range, then memory fence. */
+/* Invalidate a VA range and wait for it to be complete. */
 static inline void inv_buffer(void *buffer, size_t size)
 {
         __inv_buffer(buffer, size);
-        mb_incoherent();
+        mb();
 }
 
-/* Flush a VA range, then memory fence. */
-static inline void flush_buffer(void *buffer, size_t size)
+/*
+ * Flush a locally-homecached VA range and wait for the evicted
+ * cachelines to hit memory.
+ */
+static inline void flush_buffer_local(void *buffer, size_t size)
 {
         __flush_buffer(buffer, size);
         mb_incoherent();
 }
 
-/* Flush & invalidate a VA range, then memory fence. */
-static inline void finv_buffer(void *buffer, size_t size)
+/*
+ * Flush and invalidate a locally-homecached VA range and wait for the
+ * evicted cachelines to hit memory.
+ */
+static inline void finv_buffer_local(void *buffer, size_t size)
 {
         __finv_buffer(buffer, size);
         mb_incoherent();
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index c3ae570c0a5d..bf95f55b82b0 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -215,8 +215,8 @@ struct compat_sigaction;
 struct compat_siginfo;
 struct compat_sigaltstack;
 long compat_sys_execve(const char __user *path,
-                       const compat_uptr_t __user *argv,
-                       const compat_uptr_t __user *envp, struct pt_regs *);
+                       compat_uptr_t __user *argv,
+                       compat_uptr_t __user *envp, struct pt_regs *);
 long compat_sys_rt_sigaction(int sig, struct compat_sigaction __user *act,
                              struct compat_sigaction __user *oact,
                              size_t sigsetsize);
diff --git a/arch/tile/include/asm/dma-mapping.h b/arch/tile/include/asm/dma-mapping.h
index 15e1dceecc64..eaa06d175b39 100644
--- a/arch/tile/include/asm/dma-mapping.h
+++ b/arch/tile/include/asm/dma-mapping.h
@@ -65,7 +65,8 @@ extern void dma_sync_single_range_for_cpu(struct device *, dma_addr_t,
 extern void dma_sync_single_range_for_device(struct device *, dma_addr_t,
                                              unsigned long offset, size_t,
                                              enum dma_data_direction);
-extern void dma_cache_sync(void *vaddr, size_t, enum dma_data_direction);
+extern void dma_cache_sync(struct device *dev, void *vaddr, size_t,
+                           enum dma_data_direction);
 
 static inline int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/tile/include/asm/fb.h b/arch/tile/include/asm/fb.h
new file mode 100644
index 000000000000..3a4988e8df45
--- /dev/null
+++ b/arch/tile/include/asm/fb.h
@@ -0,0 +1 @@
+#include <asm-generic/fb.h>
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index d3cbb9b14cbe..c9ea1652af03 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -52,6 +52,7 @@ extern void iounmap(volatile void __iomem *addr);
 #endif
 
 #define ioremap_nocache(physaddr, size)         ioremap(physaddr, size)
+#define ioremap_wc(physaddr, size)              ioremap(physaddr, size)
 #define ioremap_writethrough(physaddr, size)    ioremap(physaddr, size)
 #define ioremap_fullcache(physaddr, size)       ioremap(physaddr, size)
 
@@ -161,6 +162,15 @@ static inline void _tile_writeq(u64 val, unsigned long addr)
 #define iowrite32 writel
 #define iowrite64 writeq
 
+static inline void memset_io(void *dst, int val, size_t len)
+{
+        int x;
+        BUG_ON((unsigned long)dst & 0x3);
+        val = (val & 0xff) * 0x01010101;
+        for (x = 0; x < len; x += 4)
+                writel(val, dst + x);
+}
+
 static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
                                  size_t len)
 {
@@ -269,6 +279,11 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
         ioport_panic();
 }
 
+#define ioread16be(addr)        be16_to_cpu(ioread16(addr))
+#define ioread32be(addr)        be32_to_cpu(ioread32(addr))
+#define iowrite16be(v, addr)    iowrite16(be16_to_cpu(v), (addr))
+#define iowrite32be(v, addr)    iowrite32(be32_to_cpu(v), (addr))
+
 #define ioread8_rep(p, dst, count) \
         insb((unsigned long) (p), (dst), (count))
 #define ioread16_rep(p, dst, count) \
@@ -283,4 +298,7 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 #define iowrite32_rep(p, src, count) \
         outsl((unsigned long) (p), (src), (count))
 
+#define virt_to_bus     virt_to_phys
+#define bus_to_virt     phys_to_virt
+
 #endif /* _ASM_TILE_IO_H */
diff --git a/arch/tile/include/asm/irq.h b/arch/tile/include/asm/irq.h
index 572fd3ef1d73..94e9a511de84 100644
--- a/arch/tile/include/asm/irq.h
+++ b/arch/tile/include/asm/irq.h
@@ -23,6 +23,8 @@
 /* IRQ numbers used for linux IPIs. */
 #define IRQ_RESCHEDULE 1
 
+#define irq_canonicalize(irq)   (irq)
+
 void ack_bad_irq(unsigned int irq);
 
 /*
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index 9bc0d0725c28..15fb24641120 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -100,8 +100,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
                 __get_cpu_var(current_asid) = asid;
 
                 /* Clear cpu from the old mm, and set it in the new one. */
-                cpumask_clear_cpu(cpu, &prev->cpu_vm_mask);
-                cpumask_set_cpu(cpu, &next->cpu_vm_mask);
+                cpumask_clear_cpu(cpu, mm_cpumask(prev));
+                cpumask_set_cpu(cpu, mm_cpumask(next));
 
                 /* Re-load page tables */
                 install_page_table(next->pgd, asid);
diff --git a/arch/tile/include/asm/opcode-tile_32.h b/arch/tile/include/asm/opcode-tile_32.h
index eda60ecbae3d..03df7b1e77bf 100644
--- a/arch/tile/include/asm/opcode-tile_32.h
+++ b/arch/tile/include/asm/opcode-tile_32.h
@@ -1502,5 +1502,12 @@ extern int parse_insn_tile(tile_bundle_bits bits,
                            decoded[TILE_MAX_INSTRUCTIONS_PER_BUNDLE]);
 
 
+/* Given a set of bundle bits and a specific pipe, returns which
+ * instruction the bundle contains in that pipe.
+ */
+extern const struct tile_opcode *
+find_opcode(tile_bundle_bits bits, tile_pipeline pipe);
+
+
 
 #endif /* opcode_tile_h */
diff --git a/arch/tile/include/asm/opcode-tile_64.h b/arch/tile/include/asm/opcode-tile_64.h
index eda60ecbae3d..c0633466cd5c 100644
--- a/arch/tile/include/asm/opcode-tile_64.h
+++ b/arch/tile/include/asm/opcode-tile_64.h
@@ -5,863 +5,711 @@
 #ifndef opcode_tile_h
 #define opcode_tile_h
 
-typedef unsigned long long tile_bundle_bits;
+typedef unsigned long long tilegx_bundle_bits;
 
 
 enum
 {
-  TILE_MAX_OPERANDS = 5 /* mm */
+  TILEGX_MAX_OPERANDS = 4 /* bfexts */
 };
 
 typedef enum
 {
-  TILE_OPC_BPT,
-  TILE_OPC_INFO,
-  TILE_OPC_INFOL,
-  TILE_OPC_J,
-  TILE_OPC_JAL,
-  TILE_OPC_MOVE,
-  TILE_OPC_MOVE_SN,
-  TILE_OPC_MOVEI,
-  TILE_OPC_MOVEI_SN,
-  TILE_OPC_MOVELI,
-  TILE_OPC_MOVELI_SN,
-  TILE_OPC_MOVELIS,
-  TILE_OPC_PREFETCH,
-  TILE_OPC_RAISE,
-  TILE_OPC_ADD,
-  TILE_OPC_ADD_SN,
-  TILE_OPC_ADDB,
-  TILE_OPC_ADDB_SN,
-  TILE_OPC_ADDBS_U,
-  TILE_OPC_ADDBS_U_SN,
-  TILE_OPC_ADDH,
-  TILE_OPC_ADDH_SN,
-  TILE_OPC_ADDHS,
-  TILE_OPC_ADDHS_SN,
-  TILE_OPC_ADDI,
-  TILE_OPC_ADDI_SN,
-  TILE_OPC_ADDIB,
-  TILE_OPC_ADDIB_SN,
-  TILE_OPC_ADDIH,
-  TILE_OPC_ADDIH_SN,
-  TILE_OPC_ADDLI,
-  TILE_OPC_ADDLI_SN,
-  TILE_OPC_ADDLIS,
-  TILE_OPC_ADDS,
-  TILE_OPC_ADDS_SN,
-  TILE_OPC_ADIFFB_U,
-  TILE_OPC_ADIFFB_U_SN,
-  TILE_OPC_ADIFFH,
-  TILE_OPC_ADIFFH_SN,
-  TILE_OPC_AND,
-  TILE_OPC_AND_SN,
-  TILE_OPC_ANDI,
-  TILE_OPC_ANDI_SN,
-  TILE_OPC_AULI,
-  TILE_OPC_AVGB_U,
-  TILE_OPC_AVGB_U_SN,
-  TILE_OPC_AVGH,
-  TILE_OPC_AVGH_SN,
-  TILE_OPC_BBNS,
-  TILE_OPC_BBNS_SN,
-  TILE_OPC_BBNST,
-  TILE_OPC_BBNST_SN,
-  TILE_OPC_BBS,
-  TILE_OPC_BBS_SN,
-  TILE_OPC_BBST,
-  TILE_OPC_BBST_SN,
-  TILE_OPC_BGEZ,
-  TILE_OPC_BGEZ_SN,
-  TILE_OPC_BGEZT,
-  TILE_OPC_BGEZT_SN,
-  TILE_OPC_BGZ,
-  TILE_OPC_BGZ_SN,
-  TILE_OPC_BGZT,
-  TILE_OPC_BGZT_SN,
-  TILE_OPC_BITX,
-  TILE_OPC_BITX_SN,
-  TILE_OPC_BLEZ,
-  TILE_OPC_BLEZ_SN,
-  TILE_OPC_BLEZT,
-  TILE_OPC_BLEZT_SN,
-  TILE_OPC_BLZ,
-  TILE_OPC_BLZ_SN,
-  TILE_OPC_BLZT,
-  TILE_OPC_BLZT_SN,
-  TILE_OPC_BNZ,
-  TILE_OPC_BNZ_SN,
-  TILE_OPC_BNZT,
-  TILE_OPC_BNZT_SN,
-  TILE_OPC_BYTEX,
-  TILE_OPC_BYTEX_SN,
-  TILE_OPC_BZ,
-  TILE_OPC_BZ_SN,
-  TILE_OPC_BZT,
-  TILE_OPC_BZT_SN,
-  TILE_OPC_CLZ,
-  TILE_OPC_CLZ_SN,
-  TILE_OPC_CRC32_32,
-  TILE_OPC_CRC32_32_SN,
-  TILE_OPC_CRC32_8,
-  TILE_OPC_CRC32_8_SN,
-  TILE_OPC_CTZ,
-  TILE_OPC_CTZ_SN,
-  TILE_OPC_DRAIN,
-  TILE_OPC_DTLBPR,
-  TILE_OPC_DWORD_ALIGN,
-  TILE_OPC_DWORD_ALIGN_SN,
-  TILE_OPC_FINV,
-  TILE_OPC_FLUSH,
-  TILE_OPC_FNOP,
-  TILE_OPC_ICOH,
-  TILE_OPC_ILL,
-  TILE_OPC_INTHB,
-  TILE_OPC_INTHB_SN,
-  TILE_OPC_INTHH,
-  TILE_OPC_INTHH_SN,
-  TILE_OPC_INTLB,
-  TILE_OPC_INTLB_SN,
-  TILE_OPC_INTLH,
-  TILE_OPC_INTLH_SN,
-  TILE_OPC_INV,
-  TILE_OPC_IRET,
-  TILE_OPC_JALB,
-  TILE_OPC_JALF,
-  TILE_OPC_JALR,
-  TILE_OPC_JALRP,
-  TILE_OPC_JB,
-  TILE_OPC_JF,
-  TILE_OPC_JR,
-  TILE_OPC_JRP,
-  TILE_OPC_LB,
-  TILE_OPC_LB_SN,
-  TILE_OPC_LB_U,
-  TILE_OPC_LB_U_SN,
-  TILE_OPC_LBADD,
-  TILE_OPC_LBADD_SN,
-  TILE_OPC_LBADD_U,
-  TILE_OPC_LBADD_U_SN,
-  TILE_OPC_LH,
-  TILE_OPC_LH_SN,
-  TILE_OPC_LH_U,
-  TILE_OPC_LH_U_SN,
-  TILE_OPC_LHADD,
-  TILE_OPC_LHADD_SN,
-  TILE_OPC_LHADD_U,
-  TILE_OPC_LHADD_U_SN,
-  TILE_OPC_LNK,
-  TILE_OPC_LNK_SN,
-  TILE_OPC_LW,
-  TILE_OPC_LW_SN,
-  TILE_OPC_LW_NA,
-  TILE_OPC_LW_NA_SN,
-  TILE_OPC_LWADD,
-  TILE_OPC_LWADD_SN,
-  TILE_OPC_LWADD_NA,
-  TILE_OPC_LWADD_NA_SN,
-  TILE_OPC_MAXB_U,
-  TILE_OPC_MAXB_U_SN,
-  TILE_OPC_MAXH,
-  TILE_OPC_MAXH_SN,
-  TILE_OPC_MAXIB_U,
-  TILE_OPC_MAXIB_U_SN,
-  TILE_OPC_MAXIH,
-  TILE_OPC_MAXIH_SN,
-  TILE_OPC_MF,
-  TILE_OPC_MFSPR,
-  TILE_OPC_MINB_U,
-  TILE_OPC_MINB_U_SN,
-  TILE_OPC_MINH,
-  TILE_OPC_MINH_SN,
-  TILE_OPC_MINIB_U,
-  TILE_OPC_MINIB_U_SN,
-  TILE_OPC_MINIH,
-  TILE_OPC_MINIH_SN,
-  TILE_OPC_MM,
-  TILE_OPC_MNZ,
-  TILE_OPC_MNZ_SN,
-  TILE_OPC_MNZB,
-  TILE_OPC_MNZB_SN,
-  TILE_OPC_MNZH,
-  TILE_OPC_MNZH_SN,
-  TILE_OPC_MTSPR,
-  TILE_OPC_MULHH_SS,
-  TILE_OPC_MULHH_SS_SN,
-  TILE_OPC_MULHH_SU,
-  TILE_OPC_MULHH_SU_SN,
-  TILE_OPC_MULHH_UU,
-  TILE_OPC_MULHH_UU_SN,
-  TILE_OPC_MULHHA_SS,
-  TILE_OPC_MULHHA_SS_SN,
-  TILE_OPC_MULHHA_SU,
-  TILE_OPC_MULHHA_SU_SN,
-  TILE_OPC_MULHHA_UU,
-  TILE_OPC_MULHHA_UU_SN,
-  TILE_OPC_MULHHSA_UU,
-  TILE_OPC_MULHHSA_UU_SN,
-  TILE_OPC_MULHL_SS,
-  TILE_OPC_MULHL_SS_SN,
-  TILE_OPC_MULHL_SU,
-  TILE_OPC_MULHL_SU_SN,
-  TILE_OPC_MULHL_US,
-  TILE_OPC_MULHL_US_SN,
-  TILE_OPC_MULHL_UU,
-  TILE_OPC_MULHL_UU_SN,
-  TILE_OPC_MULHLA_SS,
-  TILE_OPC_MULHLA_SS_SN,
-  TILE_OPC_MULHLA_SU,
-  TILE_OPC_MULHLA_SU_SN,
-  TILE_OPC_MULHLA_US,
-  TILE_OPC_MULHLA_US_SN,
-  TILE_OPC_MULHLA_UU,
-  TILE_OPC_MULHLA_UU_SN,
-  TILE_OPC_MULHLSA_UU,
-  TILE_OPC_MULHLSA_UU_SN,
-  TILE_OPC_MULLL_SS,
-  TILE_OPC_MULLL_SS_SN,
-  TILE_OPC_MULLL_SU,
-  TILE_OPC_MULLL_SU_SN,
-  TILE_OPC_MULLL_UU,
-  TILE_OPC_MULLL_UU_SN,
-  TILE_OPC_MULLLA_SS,
-  TILE_OPC_MULLLA_SS_SN,
-  TILE_OPC_MULLLA_SU,
-  TILE_OPC_MULLLA_SU_SN,
-  TILE_OPC_MULLLA_UU,
-  TILE_OPC_MULLLA_UU_SN,
-  TILE_OPC_MULLLSA_UU,
-  TILE_OPC_MULLLSA_UU_SN,
-  TILE_OPC_MVNZ,
-  TILE_OPC_MVNZ_SN,
-  TILE_OPC_MVZ,
-  TILE_OPC_MVZ_SN,
-  TILE_OPC_MZ,
-  TILE_OPC_MZ_SN,
-  TILE_OPC_MZB,
-  TILE_OPC_MZB_SN,
-  TILE_OPC_MZH,
-  TILE_OPC_MZH_SN,
-  TILE_OPC_NAP,
-  TILE_OPC_NOP,
-  TILE_OPC_NOR,
-  TILE_OPC_NOR_SN,
-  TILE_OPC_OR,
-  TILE_OPC_OR_SN,
-  TILE_OPC_ORI,
-  TILE_OPC_ORI_SN,
-  TILE_OPC_PACKBS_U,
-  TILE_OPC_PACKBS_U_SN,
-  TILE_OPC_PACKHB,
-  TILE_OPC_PACKHB_SN,
-  TILE_OPC_PACKHS,
-  TILE_OPC_PACKHS_SN,
-  TILE_OPC_PACKLB,
-  TILE_OPC_PACKLB_SN,
-  TILE_OPC_PCNT,
-  TILE_OPC_PCNT_SN,
-  TILE_OPC_RL,
-  TILE_OPC_RL_SN,
-  TILE_OPC_RLI,
-  TILE_OPC_RLI_SN,
-  TILE_OPC_S1A,
-  TILE_OPC_S1A_SN,
-  TILE_OPC_S2A,
-  TILE_OPC_S2A_SN,
-  TILE_OPC_S3A,
-  TILE_OPC_S3A_SN,
-  TILE_OPC_SADAB_U,
-  TILE_OPC_SADAB_U_SN,
-  TILE_OPC_SADAH,
-  TILE_OPC_SADAH_SN,
-  TILE_OPC_SADAH_U,
-  TILE_OPC_SADAH_U_SN,
-  TILE_OPC_SADB_U,
-  TILE_OPC_SADB_U_SN,
-  TILE_OPC_SADH,
-  TILE_OPC_SADH_SN,
-  TILE_OPC_SADH_U,
-  TILE_OPC_SADH_U_SN,
-  TILE_OPC_SB,
-  TILE_OPC_SBADD,
-  TILE_OPC_SEQ,
-  TILE_OPC_SEQ_SN,
-  TILE_OPC_SEQB,
-  TILE_OPC_SEQB_SN,
-  TILE_OPC_SEQH,
-  TILE_OPC_SEQH_SN,
-  TILE_OPC_SEQI,
-  TILE_OPC_SEQI_SN,
-  TILE_OPC_SEQIB,
-  TILE_OPC_SEQIB_SN,
-  TILE_OPC_SEQIH,
-  TILE_OPC_SEQIH_SN,
-  TILE_OPC_SH,
-  TILE_OPC_SHADD,
-  TILE_OPC_SHL,
-  TILE_OPC_SHL_SN,
-  TILE_OPC_SHLB,
-  TILE_OPC_SHLB_SN,
-  TILE_OPC_SHLH,
-  TILE_OPC_SHLH_SN,
-  TILE_OPC_SHLI,
-  TILE_OPC_SHLI_SN,
-  TILE_OPC_SHLIB,
-  TILE_OPC_SHLIB_SN,
-  TILE_OPC_SHLIH,
-  TILE_OPC_SHLIH_SN,
-  TILE_OPC_SHR,
-  TILE_OPC_SHR_SN,
-  TILE_OPC_SHRB,
-  TILE_OPC_SHRB_SN,
-  TILE_OPC_SHRH,
-  TILE_OPC_SHRH_SN,
-  TILE_OPC_SHRI,
-  TILE_OPC_SHRI_SN,
-  TILE_OPC_SHRIB,
-  TILE_OPC_SHRIB_SN,
-  TILE_OPC_SHRIH,
-  TILE_OPC_SHRIH_SN,
-  TILE_OPC_SLT,
-  TILE_OPC_SLT_SN,
-  TILE_OPC_SLT_U,
-  TILE_OPC_SLT_U_SN,
-  TILE_OPC_SLTB,
-  TILE_OPC_SLTB_SN,
-  TILE_OPC_SLTB_U,
-  TILE_OPC_SLTB_U_SN,
-  TILE_OPC_SLTE,
-  TILE_OPC_SLTE_SN,
-  TILE_OPC_SLTE_U,
-  TILE_OPC_SLTE_U_SN,
-  TILE_OPC_SLTEB,
-  TILE_OPC_SLTEB_SN,
-  TILE_OPC_SLTEB_U,
-  TILE_OPC_SLTEB_U_SN,
-  TILE_OPC_SLTEH,
-  TILE_OPC_SLTEH_SN,
-  TILE_OPC_SLTEH_U,
-  TILE_OPC_SLTEH_U_SN,
-  TILE_OPC_SLTH,
-  TILE_OPC_SLTH_SN,
-  TILE_OPC_SLTH_U,
-  TILE_OPC_SLTH_U_SN,
-  TILE_OPC_SLTI,
-  TILE_OPC_SLTI_SN,
-  TILE_OPC_SLTI_U,
-  TILE_OPC_SLTI_U_SN,
-  TILE_OPC_SLTIB,
-  TILE_OPC_SLTIB_SN,
-  TILE_OPC_SLTIB_U,
-  TILE_OPC_SLTIB_U_SN,
-  TILE_OPC_SLTIH,
-  TILE_OPC_SLTIH_SN,
-  TILE_OPC_SLTIH_U,
-  TILE_OPC_SLTIH_U_SN,
-  TILE_OPC_SNE,
-  TILE_OPC_SNE_SN,
-  TILE_OPC_SNEB,
-  TILE_OPC_SNEB_SN,
-  TILE_OPC_SNEH,
-  TILE_OPC_SNEH_SN,
-  TILE_OPC_SRA,
-  TILE_OPC_SRA_SN,
-  TILE_OPC_SRAB,
-  TILE_OPC_SRAB_SN,
-  TILE_OPC_SRAH,
-  TILE_OPC_SRAH_SN,
-  TILE_OPC_SRAI,
-  TILE_OPC_SRAI_SN,
-  TILE_OPC_SRAIB,
-  TILE_OPC_SRAIB_SN,
-  TILE_OPC_SRAIH,
-  TILE_OPC_SRAIH_SN,
-  TILE_OPC_SUB,
-  TILE_OPC_SUB_SN,
-  TILE_OPC_SUBB,
-  TILE_OPC_SUBB_SN,
-  TILE_OPC_SUBBS_U,
-  TILE_OPC_SUBBS_U_SN,
-  TILE_OPC_SUBH,
-  TILE_OPC_SUBH_SN,
-  TILE_OPC_SUBHS,
-  TILE_OPC_SUBHS_SN,
-  TILE_OPC_SUBS,
-  TILE_OPC_SUBS_SN,
-  TILE_OPC_SW,
-  TILE_OPC_SWADD,
-  TILE_OPC_SWINT0,
-  TILE_OPC_SWINT1,
-  TILE_OPC_SWINT2,
-  TILE_OPC_SWINT3,
-  TILE_OPC_TBLIDXB0,
-  TILE_OPC_TBLIDXB0_SN,
-  TILE_OPC_TBLIDXB1,
-  TILE_OPC_TBLIDXB1_SN,
-  TILE_OPC_TBLIDXB2,
-  TILE_OPC_TBLIDXB2_SN,
-  TILE_OPC_TBLIDXB3,
-  TILE_OPC_TBLIDXB3_SN,
-  TILE_OPC_TNS,
-  TILE_OPC_TNS_SN,
-  TILE_OPC_WH64,
-  TILE_OPC_XOR,
-  TILE_OPC_XOR_SN,
-  TILE_OPC_XORI,
-  TILE_OPC_XORI_SN,
-  TILE_OPC_NONE
-} tile_mnemonic;
+  TILEGX_OPC_BPT,
+  TILEGX_OPC_INFO,
+  TILEGX_OPC_INFOL,
+  TILEGX_OPC_MOVE,
+  TILEGX_OPC_MOVEI,
+  TILEGX_OPC_MOVELI,
+  TILEGX_OPC_PREFETCH,
+  TILEGX_OPC_PREFETCH_ADD_L1,
+  TILEGX_OPC_PREFETCH_ADD_L1_FAULT,
+  TILEGX_OPC_PREFETCH_ADD_L2,
+  TILEGX_OPC_PREFETCH_ADD_L2_FAULT,
+  TILEGX_OPC_PREFETCH_ADD_L3,
+  TILEGX_OPC_PREFETCH_ADD_L3_FAULT,
+  TILEGX_OPC_PREFETCH_L1,
+  TILEGX_OPC_PREFETCH_L1_FAULT,
+  TILEGX_OPC_PREFETCH_L2,
+  TILEGX_OPC_PREFETCH_L2_FAULT,
+  TILEGX_OPC_PREFETCH_L3,
+  TILEGX_OPC_PREFETCH_L3_FAULT,
+  TILEGX_OPC_RAISE,
+  TILEGX_OPC_ADD,
+  TILEGX_OPC_ADDI,
+  TILEGX_OPC_ADDLI,
+  TILEGX_OPC_ADDX,
+  TILEGX_OPC_ADDXI,
+  TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXSC,
+  TILEGX_OPC_AND,
+  TILEGX_OPC_ANDI,
+  TILEGX_OPC_BEQZ,
+  TILEGX_OPC_BEQZT,
+  TILEGX_OPC_BFEXTS,
+  TILEGX_OPC_BFEXTU,
+  TILEGX_OPC_BFINS,
+  TILEGX_OPC_BGEZ,
+  TILEGX_OPC_BGEZT,
+  TILEGX_OPC_BGTZ,
+  TILEGX_OPC_BGTZT,
+  TILEGX_OPC_BLBC,
+  TILEGX_OPC_BLBCT,
+  TILEGX_OPC_BLBS,
+  TILEGX_OPC_BLBST,
+  TILEGX_OPC_BLEZ,
+  TILEGX_OPC_BLEZT,
+  TILEGX_OPC_BLTZ,
+  TILEGX_OPC_BLTZT,
+  TILEGX_OPC_BNEZ,
+  TILEGX_OPC_BNEZT,
+  TILEGX_OPC_CLZ,
+  TILEGX_OPC_CMOVEQZ,
+  TILEGX_OPC_CMOVNEZ,
+  TILEGX_OPC_CMPEQ,
+  TILEGX_OPC_CMPEQI,
+  TILEGX_OPC_CMPEXCH,
+  TILEGX_OPC_CMPEXCH4,
+  TILEGX_OPC_CMPLES,
+  TILEGX_OPC_CMPLEU,
+  TILEGX_OPC_CMPLTS,
+  TILEGX_OPC_CMPLTSI,
+  TILEGX_OPC_CMPLTU,
+  TILEGX_OPC_CMPLTUI,
+  TILEGX_OPC_CMPNE,
+  TILEGX_OPC_CMUL,
+  TILEGX_OPC_CMULA,
+  TILEGX_OPC_CMULAF,
+  TILEGX_OPC_CMULF,
+  TILEGX_OPC_CMULFR,
+  TILEGX_OPC_CMULH,
+  TILEGX_OPC_CMULHR,
+  TILEGX_OPC_CRC32_32,
+  TILEGX_OPC_CRC32_8,
+  TILEGX_OPC_CTZ,
+  TILEGX_OPC_DBLALIGN,
+  TILEGX_OPC_DBLALIGN2,
+  TILEGX_OPC_DBLALIGN4,
+  TILEGX_OPC_DBLALIGN6,
+  TILEGX_OPC_DRAIN,
+  TILEGX_OPC_DTLBPR,
+  TILEGX_OPC_EXCH,
+  TILEGX_OPC_EXCH4,
+  TILEGX_OPC_FDOUBLE_ADD_FLAGS,
+  TILEGX_OPC_FDOUBLE_ADDSUB,
+  TILEGX_OPC_FDOUBLE_MUL_FLAGS,
+  TILEGX_OPC_FDOUBLE_PACK1,
+  TILEGX_OPC_FDOUBLE_PACK2,
+  TILEGX_OPC_FDOUBLE_SUB_FLAGS,
+  TILEGX_OPC_FDOUBLE_UNPACK_MAX,
+  TILEGX_OPC_FDOUBLE_UNPACK_MIN,
+  TILEGX_OPC_FETCHADD,
+  TILEGX_OPC_FETCHADD4,
+  TILEGX_OPC_FETCHADDGEZ,
+  TILEGX_OPC_FETCHADDGEZ4,
+  TILEGX_OPC_FETCHAND,
+  TILEGX_OPC_FETCHAND4,
+  TILEGX_OPC_FETCHOR,
+  TILEGX_OPC_FETCHOR4,
+  TILEGX_OPC_FINV,
+  TILEGX_OPC_FLUSH,
+  TILEGX_OPC_FLUSHWB,
+  TILEGX_OPC_FNOP,
+  TILEGX_OPC_FSINGLE_ADD1,
+  TILEGX_OPC_FSINGLE_ADDSUB2,
+  TILEGX_OPC_FSINGLE_MUL1,
+  TILEGX_OPC_FSINGLE_MUL2,
+  TILEGX_OPC_FSINGLE_PACK1,
+  TILEGX_OPC_FSINGLE_PACK2,
+  TILEGX_OPC_FSINGLE_SUB1,
+  TILEGX_OPC_ICOH,
+  TILEGX_OPC_ILL,
+  TILEGX_OPC_INV,
+  TILEGX_OPC_IRET,
+  TILEGX_OPC_J,
+  TILEGX_OPC_JAL,
+  TILEGX_OPC_JALR,
+  TILEGX_OPC_JALRP,
+  TILEGX_OPC_JR,
+  TILEGX_OPC_JRP,
+  TILEGX_OPC_LD,
+  TILEGX_OPC_LD1S,
+  TILEGX_OPC_LD1S_ADD,
+  TILEGX_OPC_LD1U,
+  TILEGX_OPC_LD1U_ADD,
+  TILEGX_OPC_LD2S,
+  TILEGX_OPC_LD2S_ADD,
+  TILEGX_OPC_LD2U,
+  TILEGX_OPC_LD2U_ADD,
+  TILEGX_OPC_LD4S,
+  TILEGX_OPC_LD4S_ADD,
+  TILEGX_OPC_LD4U,
+  TILEGX_OPC_LD4U_ADD,
+  TILEGX_OPC_LD_ADD,
+  TILEGX_OPC_LDNA,
+  TILEGX_OPC_LDNA_ADD,
+  TILEGX_OPC_LDNT,
+  TILEGX_OPC_LDNT1S,
+  TILEGX_OPC_LDNT1S_ADD,
+  TILEGX_OPC_LDNT1U,
+  TILEGX_OPC_LDNT1U_ADD,
+  TILEGX_OPC_LDNT2S,
+  TILEGX_OPC_LDNT2S_ADD,
+  TILEGX_OPC_LDNT2U,
+  TILEGX_OPC_LDNT2U_ADD,
+  TILEGX_OPC_LDNT4S,
+  TILEGX_OPC_LDNT4S_ADD,
+  TILEGX_OPC_LDNT4U,
+  TILEGX_OPC_LDNT4U_ADD,
+  TILEGX_OPC_LDNT_ADD,
+  TILEGX_OPC_LNK,
+  TILEGX_OPC_MF,
+  TILEGX_OPC_MFSPR,
+  TILEGX_OPC_MM,
+  TILEGX_OPC_MNZ,
+  TILEGX_OPC_MTSPR,
+  TILEGX_OPC_MUL_HS_HS,
+  TILEGX_OPC_MUL_HS_HU,
+  TILEGX_OPC_MUL_HS_LS,
+  TILEGX_OPC_MUL_HS_LU,
+  TILEGX_OPC_MUL_HU_HU,
+  TILEGX_OPC_MUL_HU_LS,
+  TILEGX_OPC_MUL_HU_LU,
+  TILEGX_OPC_MUL_LS_LS,
+  TILEGX_OPC_MUL_LS_LU,
+  TILEGX_OPC_MUL_LU_LU,
+  TILEGX_OPC_MULA_HS_HS,
+  TILEGX_OPC_MULA_HS_HU,
+  TILEGX_OPC_MULA_HS_LS,
+  TILEGX_OPC_MULA_HS_LU,
+  TILEGX_OPC_MULA_HU_HU,
+  TILEGX_OPC_MULA_HU_LS,
+  TILEGX_OPC_MULA_HU_LU,
+  TILEGX_OPC_MULA_LS_LS,
+  TILEGX_OPC_MULA_LS_LU,
+  TILEGX_OPC_MULA_LU_LU,
+  TILEGX_OPC_MULAX,
+  TILEGX_OPC_MULX,
+  TILEGX_OPC_MZ,
+  TILEGX_OPC_NAP,
+  TILEGX_OPC_NOP,
+  TILEGX_OPC_NOR,
+  TILEGX_OPC_OR,
+  TILEGX_OPC_ORI,
+  TILEGX_OPC_PCNT,
+  TILEGX_OPC_REVBITS,
+  TILEGX_OPC_REVBYTES,
+  TILEGX_OPC_ROTL,
+  TILEGX_OPC_ROTLI,
+  TILEGX_OPC_SHL,
+  TILEGX_OPC_SHL16INSLI,
+  TILEGX_OPC_SHL1ADD,
+  TILEGX_OPC_SHL1ADDX,
+  TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL2ADDX,
+  TILEGX_OPC_SHL3ADD,
+  TILEGX_OPC_SHL3ADDX,
+  TILEGX_OPC_SHLI,
+  TILEGX_OPC_SHLX,
+  TILEGX_OPC_SHLXI,
+  TILEGX_OPC_SHRS,
+  TILEGX_OPC_SHRSI,
+  TILEGX_OPC_SHRU,
+  TILEGX_OPC_SHRUI,
+  TILEGX_OPC_SHRUX,
+  TILEGX_OPC_SHRUXI,
+  TILEGX_OPC_SHUFFLEBYTES,
+  TILEGX_OPC_ST,
+  TILEGX_OPC_ST1,
+  TILEGX_OPC_ST1_ADD,
+  TILEGX_OPC_ST2,
+  TILEGX_OPC_ST2_ADD,
+  TILEGX_OPC_ST4,
+  TILEGX_OPC_ST4_ADD,
+  TILEGX_OPC_ST_ADD,
+  TILEGX_OPC_STNT,
+  TILEGX_OPC_STNT1,
+  TILEGX_OPC_STNT1_ADD,
+  TILEGX_OPC_STNT2,
+  TILEGX_OPC_STNT2_ADD,
+  TILEGX_OPC_STNT4,
+  TILEGX_OPC_STNT4_ADD,
+  TILEGX_OPC_STNT_ADD,
+  TILEGX_OPC_SUB,
+  TILEGX_OPC_SUBX,
+  TILEGX_OPC_SUBXSC,
+  TILEGX_OPC_SWINT0,
+  TILEGX_OPC_SWINT1,
+  TILEGX_OPC_SWINT2,
+  TILEGX_OPC_SWINT3,
+  TILEGX_OPC_TBLIDXB0,
+  TILEGX_OPC_TBLIDXB1,
+  TILEGX_OPC_TBLIDXB2,
+  TILEGX_OPC_TBLIDXB3,
+  TILEGX_OPC_V1ADD,
+  TILEGX_OPC_V1ADDI,
+  TILEGX_OPC_V1ADDUC,
+  TILEGX_OPC_V1ADIFFU,
+  TILEGX_OPC_V1AVGU,
+  TILEGX_OPC_V1CMPEQ,
+  TILEGX_OPC_V1CMPEQI,
+  TILEGX_OPC_V1CMPLES,
+  TILEGX_OPC_V1CMPLEU,
+  TILEGX_OPC_V1CMPLTS,
+  TILEGX_OPC_V1CMPLTSI,
+  TILEGX_OPC_V1CMPLTU,
+  TILEGX_OPC_V1CMPLTUI,
+  TILEGX_OPC_V1CMPNE,
+  TILEGX_OPC_V1DDOTPU,
+  TILEGX_OPC_V1DDOTPUA,
+  TILEGX_OPC_V1DDOTPUS,
+  TILEGX_OPC_V1DDOTPUSA,
+  TILEGX_OPC_V1DOTP,
+  TILEGX_OPC_V1DOTPA,
+  TILEGX_OPC_V1DOTPU,
+  TILEGX_OPC_V1DOTPUA,
+  TILEGX_OPC_V1DOTPUS,
+  TILEGX_OPC_V1DOTPUSA,
+  TILEGX_OPC_V1INT_H,
+  TILEGX_OPC_V1INT_L,
+  TILEGX_OPC_V1MAXU,
+  TILEGX_OPC_V1MAXUI,
+  TILEGX_OPC_V1MINU,
+  TILEGX_OPC_V1MINUI,
+  TILEGX_OPC_V1MNZ,
+  TILEGX_OPC_V1MULTU,
+  TILEGX_OPC_V1MULU,
+  TILEGX_OPC_V1MULUS,
+  TILEGX_OPC_V1MZ,
+  TILEGX_OPC_V1SADAU,
+  TILEGX_OPC_V1SADU,
+  TILEGX_OPC_V1SHL,
+  TILEGX_OPC_V1SHLI,
+  TILEGX_OPC_V1SHRS,
+  TILEGX_OPC_V1SHRSI,
+  TILEGX_OPC_V1SHRU,
+  TILEGX_OPC_V1SHRUI,
+  TILEGX_OPC_V1SUB,
+  TILEGX_OPC_V1SUBUC,
+  TILEGX_OPC_V2ADD,
+  TILEGX_OPC_V2ADDI,
+  TILEGX_OPC_V2ADDSC,
+  TILEGX_OPC_V2ADIFFS,
+  TILEGX_OPC_V2AVGS,
+  TILEGX_OPC_V2CMPEQ,
+  TILEGX_OPC_V2CMPEQI,
+  TILEGX_OPC_V2CMPLES,
+  TILEGX_OPC_V2CMPLEU,
+  TILEGX_OPC_V2CMPLTS,
+  TILEGX_OPC_V2CMPLTSI,
+  TILEGX_OPC_V2CMPLTU,
+  TILEGX_OPC_V2CMPLTUI,
+  TILEGX_OPC_V2CMPNE,
+  TILEGX_OPC_V2DOTP,
+  TILEGX_OPC_V2DOTPA,
+  TILEGX_OPC_V2INT_H,
+  TILEGX_OPC_V2INT_L,
+  TILEGX_OPC_V2MAXS,
+  TILEGX_OPC_V2MAXSI,
+  TILEGX_OPC_V2MINS,
+  TILEGX_OPC_V2MINSI,
+  TILEGX_OPC_V2MNZ,
+  TILEGX_OPC_V2MULFSC,
+  TILEGX_OPC_V2MULS,
+  TILEGX_OPC_V2MULTS,
+  TILEGX_OPC_V2MZ,
+  TILEGX_OPC_V2PACKH,
+  TILEGX_OPC_V2PACKL,
+  TILEGX_OPC_V2PACKUC,
+  TILEGX_OPC_V2SADAS,
+  TILEGX_OPC_V2SADAU,
+  TILEGX_OPC_V2SADS,
+  TILEGX_OPC_V2SADU,
+  TILEGX_OPC_V2SHL,
+  TILEGX_OPC_V2SHLI,
+  TILEGX_OPC_V2SHLSC,
+  TILEGX_OPC_V2SHRS,
+  TILEGX_OPC_V2SHRSI,
+  TILEGX_OPC_V2SHRU,
+  TILEGX_OPC_V2SHRUI,
+  TILEGX_OPC_V2SUB,
+  TILEGX_OPC_V2SUBSC,
+  TILEGX_OPC_V4ADD,
+  TILEGX_OPC_V4ADDSC,
+  TILEGX_OPC_V4INT_H,
+  TILEGX_OPC_V4INT_L,
+  TILEGX_OPC_V4PACKSC,
+  TILEGX_OPC_V4SHL,
+  TILEGX_OPC_V4SHLSC,
+  TILEGX_OPC_V4SHRS,
+  TILEGX_OPC_V4SHRU,
+  TILEGX_OPC_V4SUB,
+  TILEGX_OPC_V4SUBSC,
+  TILEGX_OPC_WH64,
+  TILEGX_OPC_XOR,
+  TILEGX_OPC_XORI,
+  TILEGX_OPC_NONE
+} tilegx_mnemonic;
 
 /* 64-bit pattern for a { bpt ; nop } bundle. */
-#define TILE_BPT_BUNDLE 0x400b3cae70166000ULL
+#define TILEGX_BPT_BUNDLE 0x286a44ae51485000ULL
 
 
-#define TILE_ELF_MACHINE_CODE EM_TILEPRO
+#define TILE_ELF_MACHINE_CODE EM_TILE64
 
-#define TILE_ELF_NAME "elf32-tilepro"
+#define TILE_ELF_NAME "elf32-tile64"
 
 
 static __inline unsigned int
-get_BrOff_SN(tile_bundle_bits num)
+get_BFEnd_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 0)) & 0x3ff);
+  return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_BrOff_X1(tile_bundle_bits n)
+get_BFOpcodeExtension_X0(tilegx_bundle_bits num)
 {
-  return (((unsigned int)(n >> 43)) & 0x00007fff) |
-         (((unsigned int)(n >> 20)) & 0x00018000);
+  const unsigned int n = (unsigned int)num;
+  return (((n >> 24)) & 0xf);
 }
 
 static __inline unsigned int
-get_BrType_X1(tile_bundle_bits n)
+get_BFStart_X0(tilegx_bundle_bits num)
 {
-  return (((unsigned int)(n >> 31)) & 0xf);
+  const unsigned int n = (unsigned int)num;
+  return (((n >> 18)) & 0x3f);
 }
 
 static __inline unsigned int
-get_Dest_Imm8_X1(tile_bundle_bits n)
+get_BrOff_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 31)) & 0x0000003f) |
-         (((unsigned int)(n >> 43)) & 0x000000c0);
+         (((unsigned int)(n >> 37)) & 0x0001ffc0);
 }
 
 static __inline unsigned int
-get_Dest_SN(tile_bundle_bits num)
+get_BrType_X1(tilegx_bundle_bits n)
 {
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 2)) & 0x3);
+  return (((unsigned int)(n >> 54)) & 0x1f);
 }
 
 static __inline unsigned int
-get_Dest_X0(tile_bundle_bits num)
+get_Dest_Imm8_X1(tilegx_bundle_bits n)
+{
+  return (((unsigned int)(n >> 31)) & 0x0000003f) |
+         (((unsigned int)(n >> 43)) & 0x000000c0);
+}
+
+static __inline unsigned int
+get_Dest_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 0)) & 0x3f);
 }
 
 static __inline unsigned int
-get_Dest_X1(tile_bundle_bits n)
+get_Dest_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 31)) & 0x3f);
 }
 
 static __inline unsigned int
-get_Dest_Y0(tile_bundle_bits num)
+get_Dest_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 0)) & 0x3f);
 }
 
 static __inline unsigned int
-get_Dest_Y1(tile_bundle_bits n)
+get_Dest_Y1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 31)) & 0x3f);
 }
 
 static __inline unsigned int
-get_Imm16_X0(tile_bundle_bits num)
+get_Imm16_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 12)) & 0xffff);
 }
 
 static __inline unsigned int
-get_Imm16_X1(tile_bundle_bits n)
+get_Imm16_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 43)) & 0xffff);
 }
 
 static __inline unsigned int
-get_Imm8_SN(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 0)) & 0xff);
-}
-
-static __inline unsigned int
-get_Imm8_X0(tile_bundle_bits num)
+get_Imm8OpcodeExtension_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 12)) & 0xff);
+  return (((n >> 20)) & 0xff);
 }
 
 static __inline unsigned int
-get_Imm8_X1(tile_bundle_bits n)
+get_Imm8OpcodeExtension_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 43)) & 0xff);
+  return (((unsigned int)(n >> 51)) & 0xff);
 }
 
 static __inline unsigned int
-get_Imm8_Y0(tile_bundle_bits num)
+get_Imm8_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 12)) & 0xff);
 }
 
 static __inline unsigned int
-get_Imm8_Y1(tile_bundle_bits n)
+get_Imm8_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 43)) & 0xff);
 }
 
 static __inline unsigned int
-get_ImmOpcodeExtension_X0(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 20)) & 0x7f);
-}
-
-static __inline unsigned int
-get_ImmOpcodeExtension_X1(tile_bundle_bits n)
-{
-  return (((unsigned int)(n >> 51)) & 0x7f);
-}
-
-static __inline unsigned int
-get_ImmRROpcodeExtension_SN(tile_bundle_bits num)
+get_Imm8_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 8)) & 0x3);
-}
-
-static __inline unsigned int
-get_JOffLong_X1(tile_bundle_bits n)
-{
-  return (((unsigned int)(n >> 43)) & 0x00007fff) |
-         (((unsigned int)(n >> 20)) & 0x00018000) |
-         (((unsigned int)(n >> 14)) & 0x001e0000) |
-         (((unsigned int)(n >> 16)) & 0x07e00000) |
-         (((unsigned int)(n >> 31)) & 0x18000000);
-}
-
-static __inline unsigned int
-get_JOff_X1(tile_bundle_bits n)
-{
-  return (((unsigned int)(n >> 43)) & 0x00007fff) |
-         (((unsigned int)(n >> 20)) & 0x00018000) |
-         (((unsigned int)(n >> 14)) & 0x001e0000) |
-         (((unsigned int)(n >> 16)) & 0x07e00000) |
-         (((unsigned int)(n >> 31)) & 0x08000000);
-}
-
-static __inline unsigned int
-get_MF_Imm15_X1(tile_bundle_bits n)
-{
-  return (((unsigned int)(n >> 37)) & 0x00003fff) |
-         (((unsigned int)(n >> 44)) & 0x00004000);
+  return (((n >> 12)) & 0xff);
 }
 
 static __inline unsigned int
-get_MMEnd_X0(tile_bundle_bits num)
+get_Imm8_Y1(tilegx_bundle_bits n)
 {
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 18)) & 0x1f);
+  return (((unsigned int)(n >> 43)) & 0xff);
 }
 
 static __inline unsigned int
-get_MMEnd_X1(tile_bundle_bits n)
+get_JumpOff_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 49)) & 0x1f);
+  return (((unsigned int)(n >> 31)) & 0x7ffffff);
 }
 
 static __inline unsigned int
-get_MMStart_X0(tile_bundle_bits num)
+get_JumpOpcodeExtension_X1(tilegx_bundle_bits n)
 {
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 23)) & 0x1f);
+  return (((unsigned int)(n >> 58)) & 0x1);
 }
 
 static __inline unsigned int
-get_MMStart_X1(tile_bundle_bits n)
+get_MF_Imm14_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 54)) & 0x1f);
+  return (((unsigned int)(n >> 37)) & 0x3fff);
 }
 
 static __inline unsigned int
-get_MT_Imm15_X1(tile_bundle_bits n)
+get_MT_Imm14_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 31)) & 0x0000003f) |
-         (((unsigned int)(n >> 37)) & 0x00003fc0) |
-         (((unsigned int)(n >> 44)) & 0x00004000);
+         (((unsigned int)(n >> 37)) & 0x00003fc0);
 }
 
 static __inline unsigned int
-get_Mode(tile_bundle_bits n)
+get_Mode(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 63)) & 0x1);
+  return (((unsigned int)(n >> 62)) & 0x3);
 }
 
 static __inline unsigned int
-get_NoRegOpcodeExtension_SN(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 0)) & 0xf);
-}
-
-static __inline unsigned int
-get_Opcode_SN(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 10)) & 0x3f);
-}
-
-static __inline unsigned int
-get_Opcode_X0(tile_bundle_bits num)
+get_Opcode_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 28)) & 0x7);
 }
 
 static __inline unsigned int
-get_Opcode_X1(tile_bundle_bits n)
+get_Opcode_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 59)) & 0xf);
+  return (((unsigned int)(n >> 59)) & 0x7);
 }
 
 static __inline unsigned int
-get_Opcode_Y0(tile_bundle_bits num)
+get_Opcode_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 27)) & 0xf);
 }
 
 static __inline unsigned int
-get_Opcode_Y1(tile_bundle_bits n)
+get_Opcode_Y1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 59)) & 0xf);
+  return (((unsigned int)(n >> 58)) & 0xf);
 }
 
 static __inline unsigned int
-get_Opcode_Y2(tile_bundle_bits n)
+get_Opcode_Y2(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 56)) & 0x7);
-}
-
-static __inline unsigned int
-get_RROpcodeExtension_SN(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 4)) & 0xf);
+  return (((n >> 26)) & 0x00000001) |
+         (((unsigned int)(n >> 56)) & 0x00000002);
 }
 
 static __inline unsigned int
-get_RRROpcodeExtension_X0(tile_bundle_bits num)
+get_RRROpcodeExtension_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 18)) & 0x1ff);
+  return (((n >> 18)) & 0x3ff);
 }
 
 static __inline unsigned int
-get_RRROpcodeExtension_X1(tile_bundle_bits n)
+get_RRROpcodeExtension_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 49)) & 0x1ff);
+  return (((unsigned int)(n >> 49)) & 0x3ff);
 }
 
 static __inline unsigned int
-get_RRROpcodeExtension_Y0(tile_bundle_bits num)
+get_RRROpcodeExtension_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 18)) & 0x3);
 }
 
 static __inline unsigned int
-get_RRROpcodeExtension_Y1(tile_bundle_bits n)
+get_RRROpcodeExtension_Y1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 49)) & 0x3);
 }
 
 static __inline unsigned int
-get_RouteOpcodeExtension_SN(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 0)) & 0x3ff);
-}
-
-static __inline unsigned int
-get_S_X0(tile_bundle_bits num)
+get_ShAmt_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 27)) & 0x1);
+  return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_S_X1(tile_bundle_bits n)
+get_ShAmt_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 58)) & 0x1);
+  return (((unsigned int)(n >> 43)) & 0x3f);
 }
 
 static __inline unsigned int
-get_ShAmt_X0(tile_bundle_bits num)
+get_ShAmt_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 12)) & 0x1f);
+  return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_ShAmt_X1(tile_bundle_bits n)
+get_ShAmt_Y1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 43)) & 0x1f);
+  return (((unsigned int)(n >> 43)) & 0x3f);
 }
 
 static __inline unsigned int
-get_ShAmt_Y0(tile_bundle_bits num)
+get_ShiftOpcodeExtension_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 12)) & 0x1f);
+  return (((n >> 18)) & 0x3ff);
 }
 
 static __inline unsigned int
-get_ShAmt_Y1(tile_bundle_bits n)
+get_ShiftOpcodeExtension_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 43)) & 0x1f);
+  return (((unsigned int)(n >> 49)) & 0x3ff);
 }
 
 static __inline unsigned int
-get_SrcA_X0(tile_bundle_bits num)
+get_ShiftOpcodeExtension_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 6)) & 0x3f);
+  return (((n >> 18)) & 0x3);
 }
 
 static __inline unsigned int
-get_SrcA_X1(tile_bundle_bits n)
+get_ShiftOpcodeExtension_Y1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 37)) & 0x3f);
+  return (((unsigned int)(n >> 49)) & 0x3);
 }
 
 static __inline unsigned int
-get_SrcA_Y0(tile_bundle_bits num)
+get_SrcA_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 6)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcA_Y1(tile_bundle_bits n)
+get_SrcA_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 37)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcA_Y2(tile_bundle_bits n)
+get_SrcA_Y0(tilegx_bundle_bits num)
 {
-  return (((n >> 26)) & 0x00000001) |
-         (((unsigned int)(n >> 50)) & 0x0000003e);
+  const unsigned int n = (unsigned int)num;
+  return (((n >> 6)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcBDest_Y2(tile_bundle_bits num)
+get_SrcA_Y1(tilegx_bundle_bits n)
 {
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 20)) & 0x3f);
+  return (((unsigned int)(n >> 37)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcB_X0(tile_bundle_bits num)
+get_SrcA_Y2(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 12)) & 0x3f);
+  return (((n >> 20)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcB_X1(tile_bundle_bits n)
+get_SrcBDest_Y2(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 43)) & 0x3f);
+  return (((unsigned int)(n >> 51)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcB_Y0(tile_bundle_bits num)
+get_SrcB_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
   return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_SrcB_Y1(tile_bundle_bits n)
+get_SrcB_X1(tilegx_bundle_bits n)
 {
   return (((unsigned int)(n >> 43)) & 0x3f);
 }
 
 static __inline unsigned int
-get_Src_SN(tile_bundle_bits num)
+get_SrcB_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 0)) & 0x3);
-}
-
-static __inline unsigned int
-get_UnOpcodeExtension_X0(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 12)) & 0x1f);
-}
-
-static __inline unsigned int
-get_UnOpcodeExtension_X1(tile_bundle_bits n)
-{
-  return (((unsigned int)(n >> 43)) & 0x1f);
-}
-
-static __inline unsigned int
-get_UnOpcodeExtension_Y0(tile_bundle_bits num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((n >> 12)) & 0x1f);
+  return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_UnOpcodeExtension_Y1(tile_bundle_bits n)
+get_SrcB_Y1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 43)) & 0x1f);
+  return (((unsigned int)(n >> 43)) & 0x3f);
 }
 
 static __inline unsigned int
-get_UnShOpcodeExtension_X0(tile_bundle_bits num)
+get_UnaryOpcodeExtension_X0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 17)) & 0x3ff);
+  return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_UnShOpcodeExtension_X1(tile_bundle_bits n)
+get_UnaryOpcodeExtension_X1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 48)) & 0x3ff);
+  return (((unsigned int)(n >> 43)) & 0x3f);
 }
 
 static __inline unsigned int
-get_UnShOpcodeExtension_Y0(tile_bundle_bits num)
+get_UnaryOpcodeExtension_Y0(tilegx_bundle_bits num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((n >> 17)) & 0x7);
+  return (((n >> 12)) & 0x3f);
 }
 
 static __inline unsigned int
-get_UnShOpcodeExtension_Y1(tile_bundle_bits n)
+get_UnaryOpcodeExtension_Y1(tilegx_bundle_bits n)
 {
-  return (((unsigned int)(n >> 48)) & 0x7);
+  return (((unsigned int)(n >> 43)) & 0x3f);
 }
 
 
@@ -874,546 +722,441 @@ sign_extend(int n, int num_bits)
 
 
 
-static __inline tile_bundle_bits
-create_BrOff_SN(int num)
+static __inline tilegx_bundle_bits
+create_BFEnd_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x3ff) << 0);
+  return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
-create_BrOff_X1(int num)
+static __inline tilegx_bundle_bits
+create_BFOpcodeExtension_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x00007fff)) << 43) |
-         (((tile_bundle_bits)(n & 0x00018000)) << 20);
+  return ((n & 0xf) << 24);
 }
 
-static __inline tile_bundle_bits
-create_BrType_X1(int num)
+static __inline tilegx_bundle_bits
+create_BFStart_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0xf)) << 31);
+  return ((n & 0x3f) << 18);
 }
 
-static __inline tile_bundle_bits
-create_Dest_Imm8_X1(int num)
+static __inline tilegx_bundle_bits
+create_BrOff_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x0000003f)) << 31) |
-         (((tile_bundle_bits)(n & 0x000000c0)) << 43);
+  return (((tilegx_bundle_bits)(n & 0x0000003f)) << 31) |
+         (((tilegx_bundle_bits)(n & 0x0001ffc0)) << 37);
 }
 
-static __inline tile_bundle_bits
-create_Dest_SN(int num)
+static __inline tilegx_bundle_bits
+create_BrType_X1(int num)
+{
+  const unsigned int n = (unsigned int)num;
+  return (((tilegx_bundle_bits)(n & 0x1f)) << 54);
+}
+
+static __inline tilegx_bundle_bits
+create_Dest_Imm8_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x3) << 2);
+  return (((tilegx_bundle_bits)(n & 0x0000003f)) << 31) |
+         (((tilegx_bundle_bits)(n & 0x000000c0)) << 43);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Dest_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3f) << 0);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Dest_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3f)) << 31);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 31);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Dest_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3f) << 0);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Dest_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3f)) << 31);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 31);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Imm16_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0xffff) << 12);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Imm16_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0xffff)) << 43);
+  return (((tilegx_bundle_bits)(n & 0xffff)) << 43);
 }
 
-static __inline tile_bundle_bits
-create_Imm8_SN(int num)
+static __inline tilegx_bundle_bits
+create_Imm8OpcodeExtension_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0xff) << 0);
+  return ((n & 0xff) << 20);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
+create_Imm8OpcodeExtension_X1(int num)
+{
+  const unsigned int n = (unsigned int)num;
+  return (((tilegx_bundle_bits)(n & 0xff)) << 51);
+}
+
+static __inline tilegx_bundle_bits
 create_Imm8_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0xff) << 12);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Imm8_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0xff)) << 43);
+  return (((tilegx_bundle_bits)(n & 0xff)) << 43);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Imm8_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0xff) << 12);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Imm8_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0xff)) << 43);
-}
-
-static __inline tile_bundle_bits
-create_ImmOpcodeExtension_X0(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0x7f) << 20);
-}
-
-static __inline tile_bundle_bits
-create_ImmOpcodeExtension_X1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x7f)) << 51);
-}
-
-static __inline tile_bundle_bits
-create_ImmRROpcodeExtension_SN(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0x3) << 8);
-}
-
-static __inline tile_bundle_bits
-create_JOffLong_X1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x00007fff)) << 43) |
-         (((tile_bundle_bits)(n & 0x00018000)) << 20) |
-         (((tile_bundle_bits)(n & 0x001e0000)) << 14) |
-         (((tile_bundle_bits)(n & 0x07e00000)) << 16) |
-         (((tile_bundle_bits)(n & 0x18000000)) << 31);
-}
-
-static __inline tile_bundle_bits
-create_JOff_X1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x00007fff)) << 43) |
-         (((tile_bundle_bits)(n & 0x00018000)) << 20) |
-         (((tile_bundle_bits)(n & 0x001e0000)) << 14) |
-         (((tile_bundle_bits)(n & 0x07e00000)) << 16) |
-         (((tile_bundle_bits)(n & 0x08000000)) << 31);
-}
-
-static __inline tile_bundle_bits
-create_MF_Imm15_X1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x00003fff)) << 37) |
-         (((tile_bundle_bits)(n & 0x00004000)) << 44);
+  return (((tilegx_bundle_bits)(n & 0xff)) << 43);
 }
 
-static __inline tile_bundle_bits
-create_MMEnd_X0(int num)
+static __inline tilegx_bundle_bits
+create_JumpOff_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x1f) << 18);
+  return (((tilegx_bundle_bits)(n & 0x7ffffff)) << 31);
 }
 
-static __inline tile_bundle_bits
-create_MMEnd_X1(int num)
+static __inline tilegx_bundle_bits
+create_JumpOpcodeExtension_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1f)) << 49);
+  return (((tilegx_bundle_bits)(n & 0x1)) << 58);
 }
 
-static __inline tile_bundle_bits
-create_MMStart_X0(int num)
+static __inline tilegx_bundle_bits
+create_MF_Imm14_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x1f) << 23);
+  return (((tilegx_bundle_bits)(n & 0x3fff)) << 37);
 }
 
-static __inline tile_bundle_bits
-create_MMStart_X1(int num)
+static __inline tilegx_bundle_bits
+create_MT_Imm14_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1f)) << 54);
+  return (((tilegx_bundle_bits)(n & 0x0000003f)) << 31) |
+         (((tilegx_bundle_bits)(n & 0x00003fc0)) << 37);
 }
 
-static __inline tile_bundle_bits
-create_MT_Imm15_X1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x0000003f)) << 31) |
-         (((tile_bundle_bits)(n & 0x00003fc0)) << 37) |
-         (((tile_bundle_bits)(n & 0x00004000)) << 44);
-}
-
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Mode(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1)) << 63);
+  return (((tilegx_bundle_bits)(n & 0x3)) << 62);
 }
 
-static __inline tile_bundle_bits
-create_NoRegOpcodeExtension_SN(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0xf) << 0);
-}
-
-static __inline tile_bundle_bits
-create_Opcode_SN(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0x3f) << 10);
-}
-
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Opcode_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x7) << 28);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Opcode_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0xf)) << 59);
+  return (((tilegx_bundle_bits)(n & 0x7)) << 59);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Opcode_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0xf) << 27);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Opcode_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0xf)) << 59);
+  return (((tilegx_bundle_bits)(n & 0xf)) << 58);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_Opcode_Y2(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x7)) << 56);
-}
-
-static __inline tile_bundle_bits
-create_RROpcodeExtension_SN(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0xf) << 4);
+  return ((n & 0x00000001) << 26) |
+         (((tilegx_bundle_bits)(n & 0x00000002)) << 56);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_RRROpcodeExtension_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x1ff) << 18);
+  return ((n & 0x3ff) << 18);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_RRROpcodeExtension_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1ff)) << 49);
+  return (((tilegx_bundle_bits)(n & 0x3ff)) << 49);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_RRROpcodeExtension_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3) << 18);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_RRROpcodeExtension_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3)) << 49);
+  return (((tilegx_bundle_bits)(n & 0x3)) << 49);
 }
 
-static __inline tile_bundle_bits
-create_RouteOpcodeExtension_SN(int num)
+static __inline tilegx_bundle_bits
+create_ShAmt_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x3ff) << 0);
+  return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
-create_S_X0(int num)
+static __inline tilegx_bundle_bits
+create_ShAmt_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x1) << 27);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 43);
 }
 
-static __inline tile_bundle_bits
-create_S_X1(int num)
+static __inline tilegx_bundle_bits
+create_ShAmt_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1)) << 58);
+  return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
-create_ShAmt_X0(int num)
+static __inline tilegx_bundle_bits
+create_ShAmt_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x1f) << 12);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 43);
 }
 
-static __inline tile_bundle_bits
-create_ShAmt_X1(int num)
+static __inline tilegx_bundle_bits
+create_ShiftOpcodeExtension_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1f)) << 43);
+  return ((n & 0x3ff) << 18);
 }
 
-static __inline tile_bundle_bits
-create_ShAmt_Y0(int num)
+static __inline tilegx_bundle_bits
+create_ShiftOpcodeExtension_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x1f) << 12);
+  return (((tilegx_bundle_bits)(n & 0x3ff)) << 49);
 }
 
-static __inline tile_bundle_bits
-create_ShAmt_Y1(int num)
+static __inline tilegx_bundle_bits
+create_ShiftOpcodeExtension_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1f)) << 43);
+  return ((n & 0x3) << 18);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
+create_ShiftOpcodeExtension_Y1(int num)
+{
+  const unsigned int n = (unsigned int)num;
+  return (((tilegx_bundle_bits)(n & 0x3)) << 49);
+}
+
+static __inline tilegx_bundle_bits
 create_SrcA_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3f) << 6);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcA_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3f)) << 37);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 37);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcA_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3f) << 6);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcA_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3f)) << 37);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 37);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcA_Y2(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x00000001) << 26) |
-         (((tile_bundle_bits)(n & 0x0000003e)) << 50);
+  return ((n & 0x3f) << 20);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcBDest_Y2(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x3f) << 20);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 51);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcB_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcB_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3f)) << 43);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 43);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcB_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
   return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
+static __inline tilegx_bundle_bits
 create_SrcB_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3f)) << 43);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 43);
 }
 
-static __inline tile_bundle_bits
-create_Src_SN(int num)
+static __inline tilegx_bundle_bits
+create_UnaryOpcodeExtension_X0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x3) << 0);
-}
-
-static __inline tile_bundle_bits
-create_UnOpcodeExtension_X0(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0x1f) << 12);
-}
-
-static __inline tile_bundle_bits
-create_UnOpcodeExtension_X1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1f)) << 43);
-}
-
-static __inline tile_bundle_bits
-create_UnOpcodeExtension_Y0(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0x1f) << 12);
-}
-
-static __inline tile_bundle_bits
-create_UnOpcodeExtension_Y1(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x1f)) << 43);
-}
-
-static __inline tile_bundle_bits
-create_UnShOpcodeExtension_X0(int num)
-{
-  const unsigned int n = (unsigned int)num;
-  return ((n & 0x3ff) << 17);
+  return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
-create_UnShOpcodeExtension_X1(int num)
+static __inline tilegx_bundle_bits
+create_UnaryOpcodeExtension_X1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x3ff)) << 48);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 43);
 }
 
-static __inline tile_bundle_bits
-create_UnShOpcodeExtension_Y0(int num)
+static __inline tilegx_bundle_bits
+create_UnaryOpcodeExtension_Y0(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return ((n & 0x7) << 17);
+  return ((n & 0x3f) << 12);
 }
 
-static __inline tile_bundle_bits
-create_UnShOpcodeExtension_Y1(int num)
+static __inline tilegx_bundle_bits
+create_UnaryOpcodeExtension_Y1(int num)
 {
   const unsigned int n = (unsigned int)num;
-  return (((tile_bundle_bits)(n & 0x7)) << 48);
+  return (((tilegx_bundle_bits)(n & 0x3f)) << 43);
 }
 
 
-
 typedef enum
 {
-  TILE_PIPELINE_X0,
-  TILE_PIPELINE_X1,
-  TILE_PIPELINE_Y0,
-  TILE_PIPELINE_Y1,
-  TILE_PIPELINE_Y2,
-} tile_pipeline;
+  TILEGX_PIPELINE_X0,
+  TILEGX_PIPELINE_X1,
+  TILEGX_PIPELINE_Y0,
+  TILEGX_PIPELINE_Y1,
+  TILEGX_PIPELINE_Y2,
+} tilegx_pipeline;
 
-#define tile_is_x_pipeline(p) ((int)(p) <= (int)TILE_PIPELINE_X1)
+#define tilegx_is_x_pipeline(p) ((int)(p) <= (int)TILEGX_PIPELINE_X1)
 
 typedef enum
 {
-  TILE_OP_TYPE_REGISTER,
-  TILE_OP_TYPE_IMMEDIATE,
-  TILE_OP_TYPE_ADDRESS,
-  TILE_OP_TYPE_SPR
-} tile_operand_type;
+  TILEGX_OP_TYPE_REGISTER,
+  TILEGX_OP_TYPE_IMMEDIATE,
+  TILEGX_OP_TYPE_ADDRESS,
+  TILEGX_OP_TYPE_SPR
+} tilegx_operand_type;
 
-/* This is the bit that determines if a bundle is in the Y encoding. */
-#define TILE_BUNDLE_Y_ENCODING_MASK ((tile_bundle_bits)1 << 63)
+/* These are the bits that determine if a bundle is in the X encoding. */
+#define TILEGX_BUNDLE_MODE_MASK ((tilegx_bundle_bits)3 << 62)
 
 enum
 {
   /* Maximum number of instructions in a bundle (2 for X, 3 for Y). */
-  TILE_MAX_INSTRUCTIONS_PER_BUNDLE = 3,
+  TILEGX_MAX_INSTRUCTIONS_PER_BUNDLE = 3,
 
   /* How many different pipeline encodings are there? X0, X1, Y0, Y1, Y2. */
-  TILE_NUM_PIPELINE_ENCODINGS = 5,
+  TILEGX_NUM_PIPELINE_ENCODINGS = 5,
 
-  /* Log base 2 of TILE_BUNDLE_SIZE_IN_BYTES. */
-  TILE_LOG2_BUNDLE_SIZE_IN_BYTES = 3,
+  /* Log base 2 of TILEGX_BUNDLE_SIZE_IN_BYTES. */
+  TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES = 3,
 
   /* Instructions take this many bytes. */
-  TILE_BUNDLE_SIZE_IN_BYTES = 1 << TILE_LOG2_BUNDLE_SIZE_IN_BYTES,
+  TILEGX_BUNDLE_SIZE_IN_BYTES = 1 << TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES,
 
-  /* Log base 2 of TILE_BUNDLE_ALIGNMENT_IN_BYTES. */
-  TILE_LOG2_BUNDLE_ALIGNMENT_IN_BYTES = 3,
+  /* Log base 2 of TILEGX_BUNDLE_ALIGNMENT_IN_BYTES. */
+  TILEGX_LOG2_BUNDLE_ALIGNMENT_IN_BYTES = 3,
 
   /* Bundles should be aligned modulo this number of bytes. */
-  TILE_BUNDLE_ALIGNMENT_IN_BYTES =
-    (1 << TILE_LOG2_BUNDLE_ALIGNMENT_IN_BYTES),
-
-  /* Log base 2 of TILE_SN_INSTRUCTION_SIZE_IN_BYTES. */
-  TILE_LOG2_SN_INSTRUCTION_SIZE_IN_BYTES = 1,
-
-  /* Static network instructions take this many bytes. */
-  TILE_SN_INSTRUCTION_SIZE_IN_BYTES =
-    (1 << TILE_LOG2_SN_INSTRUCTION_SIZE_IN_BYTES),
+  TILEGX_BUNDLE_ALIGNMENT_IN_BYTES =
+    (1 << TILEGX_LOG2_BUNDLE_ALIGNMENT_IN_BYTES),
 
   /* Number of registers (some are magic, such as network I/O). */
-  TILE_NUM_REGISTERS = 64,
-
-  /* Number of static network registers. */
-  TILE_NUM_SN_REGISTERS = 4
+  TILEGX_NUM_REGISTERS = 64,
 };
 
 
-struct tile_operand
+struct tilegx_operand
 {
   /* Is this operand a register, immediate or address? */
-  tile_operand_type type;
+  tilegx_operand_type type;
 
   /* The default relocation type for this operand.  */
   signed int default_reloc : 16;
@@ -1437,27 +1180,27 @@ struct tile_operand
   unsigned int rightshift : 2;
 
   /* Return the bits for this operand to be ORed into an existing bundle. */
-  tile_bundle_bits (*insert) (int op);
+  tilegx_bundle_bits (*insert) (int op);
 
   /* Extract this operand and return it. */
-  unsigned int (*extract) (tile_bundle_bits bundle);
+  unsigned int (*extract) (tilegx_bundle_bits bundle);
 };
 
 
-extern const struct tile_operand tile_operands[];
+extern const struct tilegx_operand tilegx_operands[];
 
 /* One finite-state machine per pipe for rapid instruction decoding. */
 extern const unsigned short * const
-tile_bundle_decoder_fsms[TILE_NUM_PIPELINE_ENCODINGS];
+tilegx_bundle_decoder_fsms[TILEGX_NUM_PIPELINE_ENCODINGS];
 
 
-struct tile_opcode
+struct tilegx_opcode
 {
   /* The opcode mnemonic, e.g. "add" */
   const char *name;
 
   /* The enum value for this mnemonic. */
-  tile_mnemonic mnemonic;
+  tilegx_mnemonic mnemonic;
 
   /* A bit mask of which of the five pipes this instruction
      is compatible with:
@@ -1478,29 +1221,28 @@ struct tile_opcode
   unsigned char can_bundle;
 
   /* The description of the operands. Each of these is an
-   * index into the tile_operands[] table. */
-  unsigned char operands[TILE_NUM_PIPELINE_ENCODINGS][TILE_MAX_OPERANDS];
+   * index into the tilegx_operands[] table. */
+  unsigned char operands[TILEGX_NUM_PIPELINE_ENCODINGS][TILEGX_MAX_OPERANDS];
 
 };
 
-extern const struct tile_opcode tile_opcodes[];
-
+extern const struct tilegx_opcode tilegx_opcodes[];
 
 /* Used for non-textual disassembly into structs. */
-struct tile_decoded_instruction
+struct tilegx_decoded_instruction
 {
-  const struct tile_opcode *opcode;
-  const struct tile_operand *operands[TILE_MAX_OPERANDS];
-  int operand_values[TILE_MAX_OPERANDS];
+  const struct tilegx_opcode *opcode;
+  const struct tilegx_operand *operands[TILEGX_MAX_OPERANDS];
+  long long operand_values[TILEGX_MAX_OPERANDS];
 };
 
 
 /* Disassemble a bundle into a struct for machine processing. */
-extern int parse_insn_tile(tile_bundle_bits bits,
-                           unsigned int pc,
-                           struct tile_decoded_instruction
-                           decoded[TILE_MAX_INSTRUCTIONS_PER_BUNDLE]);
+extern int parse_insn_tilegx(tilegx_bundle_bits bits,
+                             unsigned long long pc,
+                             struct tilegx_decoded_instruction
+                             decoded[TILEGX_MAX_INSTRUCTIONS_PER_BUNDLE]);
 
 
 
-#endif /* opcode_tile_h */
+#endif /* opcode_tilegx_h */
diff --git a/arch/tile/include/asm/opcode_constants_64.h b/arch/tile/include/asm/opcode_constants_64.h
index 227d033b180c..710192869476 100644
--- a/arch/tile/include/asm/opcode_constants_64.h
+++ b/arch/tile/include/asm/opcode_constants_64.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -19,462 +19,591 @@
 #define _TILE_OPCODE_CONSTANTS_H
 enum
 {
-  ADDBS_U_SPECIAL_0_OPCODE_X0 = 98,
-  ADDBS_U_SPECIAL_0_OPCODE_X1 = 68,
-  ADDB_SPECIAL_0_OPCODE_X0 = 1,
-  ADDB_SPECIAL_0_OPCODE_X1 = 1,
-  ADDHS_SPECIAL_0_OPCODE_X0 = 99,
-  ADDHS_SPECIAL_0_OPCODE_X1 = 69,
-  ADDH_SPECIAL_0_OPCODE_X0 = 2,
-  ADDH_SPECIAL_0_OPCODE_X1 = 2,
-  ADDIB_IMM_0_OPCODE_X0 = 1,
-  ADDIB_IMM_0_OPCODE_X1 = 1,
-  ADDIH_IMM_0_OPCODE_X0 = 2,
-  ADDIH_IMM_0_OPCODE_X1 = 2,
-  ADDI_IMM_0_OPCODE_X0 = 3,
-  ADDI_IMM_0_OPCODE_X1 = 3,
-  ADDI_IMM_1_OPCODE_SN = 1,
-  ADDI_OPCODE_Y0 = 9,
-  ADDI_OPCODE_Y1 = 7,
-  ADDLIS_OPCODE_X0 = 1,
-  ADDLIS_OPCODE_X1 = 2,
-  ADDLI_OPCODE_X0 = 2,
-  ADDLI_OPCODE_X1 = 3,
-  ADDS_SPECIAL_0_OPCODE_X0 = 96,
-  ADDS_SPECIAL_0_OPCODE_X1 = 66,
-  ADD_SPECIAL_0_OPCODE_X0 = 3,
-  ADD_SPECIAL_0_OPCODE_X1 = 3,
-  ADD_SPECIAL_0_OPCODE_Y0 = 0,
-  ADD_SPECIAL_0_OPCODE_Y1 = 0,
-  ADIFFB_U_SPECIAL_0_OPCODE_X0 = 4,
-  ADIFFH_SPECIAL_0_OPCODE_X0 = 5,
-  ANDI_IMM_0_OPCODE_X0 = 1,
-  ANDI_IMM_0_OPCODE_X1 = 4,
-  ANDI_OPCODE_Y0 = 10,
-  ANDI_OPCODE_Y1 = 8,
-  AND_SPECIAL_0_OPCODE_X0 = 6,
-  AND_SPECIAL_0_OPCODE_X1 = 4,
-  AND_SPECIAL_2_OPCODE_Y0 = 0,
-  AND_SPECIAL_2_OPCODE_Y1 = 0,
-  AULI_OPCODE_X0 = 3,
-  AULI_OPCODE_X1 = 4,
-  AVGB_U_SPECIAL_0_OPCODE_X0 = 7,
-  AVGH_SPECIAL_0_OPCODE_X0 = 8,
-  BBNST_BRANCH_OPCODE_X1 = 15,
-  BBNS_BRANCH_OPCODE_X1 = 14,
-  BBNS_OPCODE_SN = 63,
-  BBST_BRANCH_OPCODE_X1 = 13,
-  BBS_BRANCH_OPCODE_X1 = 12,
-  BBS_OPCODE_SN = 62,
-  BGEZT_BRANCH_OPCODE_X1 = 7,
-  BGEZ_BRANCH_OPCODE_X1 = 6,
-  BGEZ_OPCODE_SN = 61,
-  BGZT_BRANCH_OPCODE_X1 = 5,
-  BGZ_BRANCH_OPCODE_X1 = 4,
-  BGZ_OPCODE_SN = 58,
-  BITX_UN_0_SHUN_0_OPCODE_X0 = 1,
-  BITX_UN_0_SHUN_0_OPCODE_Y0 = 1,
-  BLEZT_BRANCH_OPCODE_X1 = 11,
-  BLEZ_BRANCH_OPCODE_X1 = 10,
-  BLEZ_OPCODE_SN = 59,
-  BLZT_BRANCH_OPCODE_X1 = 9,
-  BLZ_BRANCH_OPCODE_X1 = 8,
-  BLZ_OPCODE_SN = 60,
-  BNZT_BRANCH_OPCODE_X1 = 3,
-  BNZ_BRANCH_OPCODE_X1 = 2,
-  BNZ_OPCODE_SN = 57,
-  BPT_NOREG_RR_IMM_0_OPCODE_SN = 1,
-  BRANCH_OPCODE_X1 = 5,
-  BYTEX_UN_0_SHUN_0_OPCODE_X0 = 2,
-  BYTEX_UN_0_SHUN_0_OPCODE_Y0 = 2,
-  BZT_BRANCH_OPCODE_X1 = 1,
-  BZ_BRANCH_OPCODE_X1 = 0,
-  BZ_OPCODE_SN = 56,
-  CLZ_UN_0_SHUN_0_OPCODE_X0 = 3,
-  CLZ_UN_0_SHUN_0_OPCODE_Y0 = 3,
-  CRC32_32_SPECIAL_0_OPCODE_X0 = 9,
-  CRC32_8_SPECIAL_0_OPCODE_X0 = 10,
-  CTZ_UN_0_SHUN_0_OPCODE_X0 = 4,
-  CTZ_UN_0_SHUN_0_OPCODE_Y0 = 4,
-  DRAIN_UN_0_SHUN_0_OPCODE_X1 = 1,
-  DTLBPR_UN_0_SHUN_0_OPCODE_X1 = 2,
-  DWORD_ALIGN_SPECIAL_0_OPCODE_X0 = 95,
-  FINV_UN_0_SHUN_0_OPCODE_X1 = 3,
-  FLUSH_UN_0_SHUN_0_OPCODE_X1 = 4,
-  FNOP_NOREG_RR_IMM_0_OPCODE_SN = 3,
-  FNOP_UN_0_SHUN_0_OPCODE_X0 = 5,
-  FNOP_UN_0_SHUN_0_OPCODE_X1 = 5,
-  FNOP_UN_0_SHUN_0_OPCODE_Y0 = 5,
-  FNOP_UN_0_SHUN_0_OPCODE_Y1 = 1,
-  HALT_NOREG_RR_IMM_0_OPCODE_SN = 0,
-  ICOH_UN_0_SHUN_0_OPCODE_X1 = 6,
-  ILL_UN_0_SHUN_0_OPCODE_X1 = 7,
-  ILL_UN_0_SHUN_0_OPCODE_Y1 = 2,
-  IMM_0_OPCODE_SN = 0,
-  IMM_0_OPCODE_X0 = 4,
-  IMM_0_OPCODE_X1 = 6,
-  IMM_1_OPCODE_SN = 1,
-  IMM_OPCODE_0_X0 = 5,
-  INTHB_SPECIAL_0_OPCODE_X0 = 11,
-  INTHB_SPECIAL_0_OPCODE_X1 = 5,
-  INTHH_SPECIAL_0_OPCODE_X0 = 12,
-  INTHH_SPECIAL_0_OPCODE_X1 = 6,
-  INTLB_SPECIAL_0_OPCODE_X0 = 13,
-  INTLB_SPECIAL_0_OPCODE_X1 = 7,
-  INTLH_SPECIAL_0_OPCODE_X0 = 14,
-  INTLH_SPECIAL_0_OPCODE_X1 = 8,
-  INV_UN_0_SHUN_0_OPCODE_X1 = 8,
-  IRET_UN_0_SHUN_0_OPCODE_X1 = 9,
-  JALB_OPCODE_X1 = 13,
-  JALF_OPCODE_X1 = 12,
-  JALRP_SPECIAL_0_OPCODE_X1 = 9,
-  JALRR_IMM_1_OPCODE_SN = 3,
-  JALR_RR_IMM_0_OPCODE_SN = 5,
-  JALR_SPECIAL_0_OPCODE_X1 = 10,
-  JB_OPCODE_X1 = 11,
-  JF_OPCODE_X1 = 10,
-  JRP_SPECIAL_0_OPCODE_X1 = 11,
-  JRR_IMM_1_OPCODE_SN = 2,
-  JR_RR_IMM_0_OPCODE_SN = 4,
-  JR_SPECIAL_0_OPCODE_X1 = 12,
-  LBADD_IMM_0_OPCODE_X1 = 22,
-  LBADD_U_IMM_0_OPCODE_X1 = 23,
-  LB_OPCODE_Y2 = 0,
-  LB_UN_0_SHUN_0_OPCODE_X1 = 10,
-  LB_U_OPCODE_Y2 = 1,
-  LB_U_UN_0_SHUN_0_OPCODE_X1 = 11,
-  LHADD_IMM_0_OPCODE_X1 = 24,
-  LHADD_U_IMM_0_OPCODE_X1 = 25,
-  LH_OPCODE_Y2 = 2,
-  LH_UN_0_SHUN_0_OPCODE_X1 = 12,
-  LH_U_OPCODE_Y2 = 3,
-  LH_U_UN_0_SHUN_0_OPCODE_X1 = 13,
-  LNK_SPECIAL_0_OPCODE_X1 = 13,
-  LWADD_IMM_0_OPCODE_X1 = 26,
-  LWADD_NA_IMM_0_OPCODE_X1 = 27,
-  LW_NA_UN_0_SHUN_0_OPCODE_X1 = 24,
-  LW_OPCODE_Y2 = 4,
-  LW_UN_0_SHUN_0_OPCODE_X1 = 14,
-  MAXB_U_SPECIAL_0_OPCODE_X0 = 15,
-  MAXB_U_SPECIAL_0_OPCODE_X1 = 14,
-  MAXH_SPECIAL_0_OPCODE_X0 = 16,
-  MAXH_SPECIAL_0_OPCODE_X1 = 15,
-  MAXIB_U_IMM_0_OPCODE_X0 = 4,
-  MAXIB_U_IMM_0_OPCODE_X1 = 5,
-  MAXIH_IMM_0_OPCODE_X0 = 5,
-  MAXIH_IMM_0_OPCODE_X1 = 6,
-  MFSPR_IMM_0_OPCODE_X1 = 7,
-  MF_UN_0_SHUN_0_OPCODE_X1 = 15,
-  MINB_U_SPECIAL_0_OPCODE_X0 = 17,
-  MINB_U_SPECIAL_0_OPCODE_X1 = 16,
-  MINH_SPECIAL_0_OPCODE_X0 = 18,
-  MINH_SPECIAL_0_OPCODE_X1 = 17,
-  MINIB_U_IMM_0_OPCODE_X0 = 6,
-  MINIB_U_IMM_0_OPCODE_X1 = 8,
-  MINIH_IMM_0_OPCODE_X0 = 7,
-  MINIH_IMM_0_OPCODE_X1 = 9,
-  MM_OPCODE_X0 = 6,
-  MM_OPCODE_X1 = 7,
-  MNZB_SPECIAL_0_OPCODE_X0 = 19,
-  MNZB_SPECIAL_0_OPCODE_X1 = 18,
-  MNZH_SPECIAL_0_OPCODE_X0 = 20,
-  MNZH_SPECIAL_0_OPCODE_X1 = 19,
-  MNZ_SPECIAL_0_OPCODE_X0 = 21,
-  MNZ_SPECIAL_0_OPCODE_X1 = 20,
-  MNZ_SPECIAL_1_OPCODE_Y0 = 0,
-  MNZ_SPECIAL_1_OPCODE_Y1 = 1,
-  MOVEI_IMM_1_OPCODE_SN = 0,
-  MOVE_RR_IMM_0_OPCODE_SN = 8,
-  MTSPR_IMM_0_OPCODE_X1 = 10,
-  MULHHA_SS_SPECIAL_0_OPCODE_X0 = 22,
-  MULHHA_SS_SPECIAL_7_OPCODE_Y0 = 0,
-  MULHHA_SU_SPECIAL_0_OPCODE_X0 = 23,
-  MULHHA_UU_SPECIAL_0_OPCODE_X0 = 24,
-  MULHHA_UU_SPECIAL_7_OPCODE_Y0 = 1,
-  MULHHSA_UU_SPECIAL_0_OPCODE_X0 = 25,
-  MULHH_SS_SPECIAL_0_OPCODE_X0 = 26,
-  MULHH_SS_SPECIAL_6_OPCODE_Y0 = 0,
-  MULHH_SU_SPECIAL_0_OPCODE_X0 = 27,
-  MULHH_UU_SPECIAL_0_OPCODE_X0 = 28,
-  MULHH_UU_SPECIAL_6_OPCODE_Y0 = 1,
-  MULHLA_SS_SPECIAL_0_OPCODE_X0 = 29,
-  MULHLA_SU_SPECIAL_0_OPCODE_X0 = 30,
-  MULHLA_US_SPECIAL_0_OPCODE_X0 = 31,
-  MULHLA_UU_SPECIAL_0_OPCODE_X0 = 32,
-  MULHLSA_UU_SPECIAL_0_OPCODE_X0 = 33,
-  MULHLSA_UU_SPECIAL_5_OPCODE_Y0 = 0,
-  MULHL_SS_SPECIAL_0_OPCODE_X0 = 34,
-  MULHL_SU_SPECIAL_0_OPCODE_X0 = 35,
-  MULHL_US_SPECIAL_0_OPCODE_X0 = 36,
-  MULHL_UU_SPECIAL_0_OPCODE_X0 = 37,
-  MULLLA_SS_SPECIAL_0_OPCODE_X0 = 38,
-  MULLLA_SS_SPECIAL_7_OPCODE_Y0 = 2,
-  MULLLA_SU_SPECIAL_0_OPCODE_X0 = 39,
-  MULLLA_UU_SPECIAL_0_OPCODE_X0 = 40,
-  MULLLA_UU_SPECIAL_7_OPCODE_Y0 = 3,
-  MULLLSA_UU_SPECIAL_0_OPCODE_X0 = 41,
-  MULLL_SS_SPECIAL_0_OPCODE_X0 = 42,
-  MULLL_SS_SPECIAL_6_OPCODE_Y0 = 2,
-  MULLL_SU_SPECIAL_0_OPCODE_X0 = 43,
-  MULLL_UU_SPECIAL_0_OPCODE_X0 = 44,
-  MULLL_UU_SPECIAL_6_OPCODE_Y0 = 3,
-  MVNZ_SPECIAL_0_OPCODE_X0 = 45,
-  MVNZ_SPECIAL_1_OPCODE_Y0 = 1,
-  MVZ_SPECIAL_0_OPCODE_X0 = 46,
-  MVZ_SPECIAL_1_OPCODE_Y0 = 2,
-  MZB_SPECIAL_0_OPCODE_X0 = 47,
-  MZB_SPECIAL_0_OPCODE_X1 = 21,
-  MZH_SPECIAL_0_OPCODE_X0 = 48,
-  MZH_SPECIAL_0_OPCODE_X1 = 22,
-  MZ_SPECIAL_0_OPCODE_X0 = 49,
-  MZ_SPECIAL_0_OPCODE_X1 = 23,
-  MZ_SPECIAL_1_OPCODE_Y0 = 3,
-  MZ_SPECIAL_1_OPCODE_Y1 = 2,
-  NAP_UN_0_SHUN_0_OPCODE_X1 = 16,
-  NOP_NOREG_RR_IMM_0_OPCODE_SN = 2,
-  NOP_UN_0_SHUN_0_OPCODE_X0 = 6,
-  NOP_UN_0_SHUN_0_OPCODE_X1 = 17,
-  NOP_UN_0_SHUN_0_OPCODE_Y0 = 6,
-  NOP_UN_0_SHUN_0_OPCODE_Y1 = 3,
-  NOREG_RR_IMM_0_OPCODE_SN = 0,
-  NOR_SPECIAL_0_OPCODE_X0 = 50,
-  NOR_SPECIAL_0_OPCODE_X1 = 24,
-  NOR_SPECIAL_2_OPCODE_Y0 = 1,
-  NOR_SPECIAL_2_OPCODE_Y1 = 1,
-  ORI_IMM_0_OPCODE_X0 = 8,
-  ORI_IMM_0_OPCODE_X1 = 11,
-  ORI_OPCODE_Y0 = 11,
-  ORI_OPCODE_Y1 = 9,
-  OR_SPECIAL_0_OPCODE_X0 = 51,
-  OR_SPECIAL_0_OPCODE_X1 = 25,
-  OR_SPECIAL_2_OPCODE_Y0 = 2,
-  OR_SPECIAL_2_OPCODE_Y1 = 2,
-  PACKBS_U_SPECIAL_0_OPCODE_X0 = 103,
-  PACKBS_U_SPECIAL_0_OPCODE_X1 = 73,
-  PACKHB_SPECIAL_0_OPCODE_X0 = 52,
-  PACKHB_SPECIAL_0_OPCODE_X1 = 26,
-  PACKHS_SPECIAL_0_OPCODE_X0 = 102,
-  PACKHS_SPECIAL_0_OPCODE_X1 = 72,
-  PACKLB_SPECIAL_0_OPCODE_X0 = 53,
-  PACKLB_SPECIAL_0_OPCODE_X1 = 27,
-  PCNT_UN_0_SHUN_0_OPCODE_X0 = 7,
-  PCNT_UN_0_SHUN_0_OPCODE_Y0 = 7,
-  RLI_SHUN_0_OPCODE_X0 = 1,
-  RLI_SHUN_0_OPCODE_X1 = 1,
-  RLI_SHUN_0_OPCODE_Y0 = 1,
-  RLI_SHUN_0_OPCODE_Y1 = 1,
-  RL_SPECIAL_0_OPCODE_X0 = 54,
-  RL_SPECIAL_0_OPCODE_X1 = 28,
-  RL_SPECIAL_3_OPCODE_Y0 = 0,
-  RL_SPECIAL_3_OPCODE_Y1 = 0,
-  RR_IMM_0_OPCODE_SN = 0,
-  S1A_SPECIAL_0_OPCODE_X0 = 55,
-  S1A_SPECIAL_0_OPCODE_X1 = 29,
-  S1A_SPECIAL_0_OPCODE_Y0 = 1,
-  S1A_SPECIAL_0_OPCODE_Y1 = 1,
-  S2A_SPECIAL_0_OPCODE_X0 = 56,
-  S2A_SPECIAL_0_OPCODE_X1 = 30,
-  S2A_SPECIAL_0_OPCODE_Y0 = 2,
-  S2A_SPECIAL_0_OPCODE_Y1 = 2,
-  S3A_SPECIAL_0_OPCODE_X0 = 57,
-  S3A_SPECIAL_0_OPCODE_X1 = 31,
-  S3A_SPECIAL_5_OPCODE_Y0 = 1,
-  S3A_SPECIAL_5_OPCODE_Y1 = 1,
-  SADAB_U_SPECIAL_0_OPCODE_X0 = 58,
-  SADAH_SPECIAL_0_OPCODE_X0 = 59,
-  SADAH_U_SPECIAL_0_OPCODE_X0 = 60,
-  SADB_U_SPECIAL_0_OPCODE_X0 = 61,
-  SADH_SPECIAL_0_OPCODE_X0 = 62,
-  SADH_U_SPECIAL_0_OPCODE_X0 = 63,
-  SBADD_IMM_0_OPCODE_X1 = 28,
-  SB_OPCODE_Y2 = 5,
-  SB_SPECIAL_0_OPCODE_X1 = 32,
-  SEQB_SPECIAL_0_OPCODE_X0 = 64,
-  SEQB_SPECIAL_0_OPCODE_X1 = 33,
-  SEQH_SPECIAL_0_OPCODE_X0 = 65,
-  SEQH_SPECIAL_0_OPCODE_X1 = 34,
-  SEQIB_IMM_0_OPCODE_X0 = 9,
-  SEQIB_IMM_0_OPCODE_X1 = 12,
-  SEQIH_IMM_0_OPCODE_X0 = 10,
-  SEQIH_IMM_0_OPCODE_X1 = 13,
-  SEQI_IMM_0_OPCODE_X0 = 11,
-  SEQI_IMM_0_OPCODE_X1 = 14,
-  SEQI_OPCODE_Y0 = 12,
-  SEQI_OPCODE_Y1 = 10,
-  SEQ_SPECIAL_0_OPCODE_X0 = 66,
-  SEQ_SPECIAL_0_OPCODE_X1 = 35,
-  SEQ_SPECIAL_5_OPCODE_Y0 = 2,
-  SEQ_SPECIAL_5_OPCODE_Y1 = 2,
-  SHADD_IMM_0_OPCODE_X1 = 29,
-  SHL8II_IMM_0_OPCODE_SN = 3,
-  SHLB_SPECIAL_0_OPCODE_X0 = 67,
-  SHLB_SPECIAL_0_OPCODE_X1 = 36,
-  SHLH_SPECIAL_0_OPCODE_X0 = 68,
-  SHLH_SPECIAL_0_OPCODE_X1 = 37,
-  SHLIB_SHUN_0_OPCODE_X0 = 2,
-  SHLIB_SHUN_0_OPCODE_X1 = 2,
-  SHLIH_SHUN_0_OPCODE_X0 = 3,
-  SHLIH_SHUN_0_OPCODE_X1 = 3,
-  SHLI_SHUN_0_OPCODE_X0 = 4,
-  SHLI_SHUN_0_OPCODE_X1 = 4,
-  SHLI_SHUN_0_OPCODE_Y0 = 2,
-  SHLI_SHUN_0_OPCODE_Y1 = 2,
-  SHL_SPECIAL_0_OPCODE_X0 = 69,
-  SHL_SPECIAL_0_OPCODE_X1 = 38,
-  SHL_SPECIAL_3_OPCODE_Y0 = 1,
-  SHL_SPECIAL_3_OPCODE_Y1 = 1,
-  SHR1_RR_IMM_0_OPCODE_SN = 9,
-  SHRB_SPECIAL_0_OPCODE_X0 = 70,
-  SHRB_SPECIAL_0_OPCODE_X1 = 39,
-  SHRH_SPECIAL_0_OPCODE_X0 = 71,
-  SHRH_SPECIAL_0_OPCODE_X1 = 40,
-  SHRIB_SHUN_0_OPCODE_X0 = 5,
-  SHRIB_SHUN_0_OPCODE_X1 = 5,
-  SHRIH_SHUN_0_OPCODE_X0 = 6,
-  SHRIH_SHUN_0_OPCODE_X1 = 6,
-  SHRI_SHUN_0_OPCODE_X0 = 7,
-  SHRI_SHUN_0_OPCODE_X1 = 7,
-  SHRI_SHUN_0_OPCODE_Y0 = 3,
-  SHRI_SHUN_0_OPCODE_Y1 = 3,
-  SHR_SPECIAL_0_OPCODE_X0 = 72,
-  SHR_SPECIAL_0_OPCODE_X1 = 41,
-  SHR_SPECIAL_3_OPCODE_Y0 = 2,
-  SHR_SPECIAL_3_OPCODE_Y1 = 2,
-  SHUN_0_OPCODE_X0 = 7,
-  SHUN_0_OPCODE_X1 = 8,
-  SHUN_0_OPCODE_Y0 = 13,
-  SHUN_0_OPCODE_Y1 = 11,
-  SH_OPCODE_Y2 = 6,
-  SH_SPECIAL_0_OPCODE_X1 = 42,
-  SLTB_SPECIAL_0_OPCODE_X0 = 73,
-  SLTB_SPECIAL_0_OPCODE_X1 = 43,
-  SLTB_U_SPECIAL_0_OPCODE_X0 = 74,
-  SLTB_U_SPECIAL_0_OPCODE_X1 = 44,
-  SLTEB_SPECIAL_0_OPCODE_X0 = 75,
-  SLTEB_SPECIAL_0_OPCODE_X1 = 45,
-  SLTEB_U_SPECIAL_0_OPCODE_X0 = 76,
-  SLTEB_U_SPECIAL_0_OPCODE_X1 = 46,
-  SLTEH_SPECIAL_0_OPCODE_X0 = 77,
-  SLTEH_SPECIAL_0_OPCODE_X1 = 47,
-  SLTEH_U_SPECIAL_0_OPCODE_X0 = 78,
-  SLTEH_U_SPECIAL_0_OPCODE_X1 = 48,
-  SLTE_SPECIAL_0_OPCODE_X0 = 79,
-  SLTE_SPECIAL_0_OPCODE_X1 = 49,
-  SLTE_SPECIAL_4_OPCODE_Y0 = 0,
-  SLTE_SPECIAL_4_OPCODE_Y1 = 0,
-  SLTE_U_SPECIAL_0_OPCODE_X0 = 80,
-  SLTE_U_SPECIAL_0_OPCODE_X1 = 50,
-  SLTE_U_SPECIAL_4_OPCODE_Y0 = 1,
-  SLTE_U_SPECIAL_4_OPCODE_Y1 = 1,
-  SLTH_SPECIAL_0_OPCODE_X0 = 81,
-  SLTH_SPECIAL_0_OPCODE_X1 = 51,
-  SLTH_U_SPECIAL_0_OPCODE_X0 = 82,
-  SLTH_U_SPECIAL_0_OPCODE_X1 = 52,
-  SLTIB_IMM_0_OPCODE_X0 = 12,
-  SLTIB_IMM_0_OPCODE_X1 = 15,
-  SLTIB_U_IMM_0_OPCODE_X0 = 13,
-  SLTIB_U_IMM_0_OPCODE_X1 = 16,
-  SLTIH_IMM_0_OPCODE_X0 = 14,
-  SLTIH_IMM_0_OPCODE_X1 = 17,
-  SLTIH_U_IMM_0_OPCODE_X0 = 15,
-  SLTIH_U_IMM_0_OPCODE_X1 = 18,
-  SLTI_IMM_0_OPCODE_X0 = 16,
-  SLTI_IMM_0_OPCODE_X1 = 19,
-  SLTI_OPCODE_Y0 = 14,
-  SLTI_OPCODE_Y1 = 12,
-  SLTI_U_IMM_0_OPCODE_X0 = 17,
-  SLTI_U_IMM_0_OPCODE_X1 = 20,
-  SLTI_U_OPCODE_Y0 = 15,
-  SLTI_U_OPCODE_Y1 = 13,
-  SLT_SPECIAL_0_OPCODE_X0 = 83,
-  SLT_SPECIAL_0_OPCODE_X1 = 53,
-  SLT_SPECIAL_4_OPCODE_Y0 = 2,
-  SLT_SPECIAL_4_OPCODE_Y1 = 2,
-  SLT_U_SPECIAL_0_OPCODE_X0 = 84,
-  SLT_U_SPECIAL_0_OPCODE_X1 = 54,
-  SLT_U_SPECIAL_4_OPCODE_Y0 = 3,
-  SLT_U_SPECIAL_4_OPCODE_Y1 = 3,
-  SNEB_SPECIAL_0_OPCODE_X0 = 85,
-  SNEB_SPECIAL_0_OPCODE_X1 = 55,
-  SNEH_SPECIAL_0_OPCODE_X0 = 86,
-  SNEH_SPECIAL_0_OPCODE_X1 = 56,
-  SNE_SPECIAL_0_OPCODE_X0 = 87,
-  SNE_SPECIAL_0_OPCODE_X1 = 57,
-  SNE_SPECIAL_5_OPCODE_Y0 = 3,
-  SNE_SPECIAL_5_OPCODE_Y1 = 3,
-  SPECIAL_0_OPCODE_X0 = 0,
-  SPECIAL_0_OPCODE_X1 = 1,
-  SPECIAL_0_OPCODE_Y0 = 1,
-  SPECIAL_0_OPCODE_Y1 = 1,
-  SPECIAL_1_OPCODE_Y0 = 2,
-  SPECIAL_1_OPCODE_Y1 = 2,
-  SPECIAL_2_OPCODE_Y0 = 3,
-  SPECIAL_2_OPCODE_Y1 = 3,
-  SPECIAL_3_OPCODE_Y0 = 4,
-  SPECIAL_3_OPCODE_Y1 = 4,
-  SPECIAL_4_OPCODE_Y0 = 5,
-  SPECIAL_4_OPCODE_Y1 = 5,
-  SPECIAL_5_OPCODE_Y0 = 6,
-  SPECIAL_5_OPCODE_Y1 = 6,
-  SPECIAL_6_OPCODE_Y0 = 7,
-  SPECIAL_7_OPCODE_Y0 = 8,
-  SRAB_SPECIAL_0_OPCODE_X0 = 88,
-  SRAB_SPECIAL_0_OPCODE_X1 = 58,
-  SRAH_SPECIAL_0_OPCODE_X0 = 89,
-  SRAH_SPECIAL_0_OPCODE_X1 = 59,
-  SRAIB_SHUN_0_OPCODE_X0 = 8,
-  SRAIB_SHUN_0_OPCODE_X1 = 8,
-  SRAIH_SHUN_0_OPCODE_X0 = 9,
-  SRAIH_SHUN_0_OPCODE_X1 = 9,
-  SRAI_SHUN_0_OPCODE_X0 = 10,
-  SRAI_SHUN_0_OPCODE_X1 = 10,
-  SRAI_SHUN_0_OPCODE_Y0 = 4,
-  SRAI_SHUN_0_OPCODE_Y1 = 4,
-  SRA_SPECIAL_0_OPCODE_X0 = 90,
-  SRA_SPECIAL_0_OPCODE_X1 = 60,
-  SRA_SPECIAL_3_OPCODE_Y0 = 3,
-  SRA_SPECIAL_3_OPCODE_Y1 = 3,
-  SUBBS_U_SPECIAL_0_OPCODE_X0 = 100,
-  SUBBS_U_SPECIAL_0_OPCODE_X1 = 70,
-  SUBB_SPECIAL_0_OPCODE_X0 = 91,
-  SUBB_SPECIAL_0_OPCODE_X1 = 61,
-  SUBHS_SPECIAL_0_OPCODE_X0 = 101,
-  SUBHS_SPECIAL_0_OPCODE_X1 = 71,
-  SUBH_SPECIAL_0_OPCODE_X0 = 92,
-  SUBH_SPECIAL_0_OPCODE_X1 = 62,
-  SUBS_SPECIAL_0_OPCODE_X0 = 97,
-  SUBS_SPECIAL_0_OPCODE_X1 = 67,
-  SUB_SPECIAL_0_OPCODE_X0 = 93,
-  SUB_SPECIAL_0_OPCODE_X1 = 63,
-  SUB_SPECIAL_0_OPCODE_Y0 = 3,
-  SUB_SPECIAL_0_OPCODE_Y1 = 3,
-  SWADD_IMM_0_OPCODE_X1 = 30,
-  SWINT0_UN_0_SHUN_0_OPCODE_X1 = 18,
-  SWINT1_UN_0_SHUN_0_OPCODE_X1 = 19,
-  SWINT2_UN_0_SHUN_0_OPCODE_X1 = 20,
-  SWINT3_UN_0_SHUN_0_OPCODE_X1 = 21,
-  SW_OPCODE_Y2 = 7,
-  SW_SPECIAL_0_OPCODE_X1 = 64,
-  TBLIDXB0_UN_0_SHUN_0_OPCODE_X0 = 8,
-  TBLIDXB0_UN_0_SHUN_0_OPCODE_Y0 = 8,
-  TBLIDXB1_UN_0_SHUN_0_OPCODE_X0 = 9,
-  TBLIDXB1_UN_0_SHUN_0_OPCODE_Y0 = 9,
-  TBLIDXB2_UN_0_SHUN_0_OPCODE_X0 = 10,
-  TBLIDXB2_UN_0_SHUN_0_OPCODE_Y0 = 10,
-  TBLIDXB3_UN_0_SHUN_0_OPCODE_X0 = 11,
-  TBLIDXB3_UN_0_SHUN_0_OPCODE_Y0 = 11,
-  TNS_UN_0_SHUN_0_OPCODE_X1 = 22,
-  UN_0_SHUN_0_OPCODE_X0 = 11,
-  UN_0_SHUN_0_OPCODE_X1 = 11,
-  UN_0_SHUN_0_OPCODE_Y0 = 5,
-  UN_0_SHUN_0_OPCODE_Y1 = 5,
-  WH64_UN_0_SHUN_0_OPCODE_X1 = 23,
-  XORI_IMM_0_OPCODE_X0 = 2,
-  XORI_IMM_0_OPCODE_X1 = 21,
-  XOR_SPECIAL_0_OPCODE_X0 = 94,
-  XOR_SPECIAL_0_OPCODE_X1 = 65,
-  XOR_SPECIAL_2_OPCODE_Y0 = 3,
-  XOR_SPECIAL_2_OPCODE_Y1 = 3
+  ADDI_IMM8_OPCODE_X0 = 1,
+  ADDI_IMM8_OPCODE_X1 = 1,
+  ADDI_OPCODE_Y0 = 0,
+  ADDI_OPCODE_Y1 = 1,
+  ADDLI_OPCODE_X0 = 1,
+  ADDLI_OPCODE_X1 = 0,
+  ADDXI_IMM8_OPCODE_X0 = 2,
+  ADDXI_IMM8_OPCODE_X1 = 2,
+  ADDXI_OPCODE_Y0 = 1,
+  ADDXI_OPCODE_Y1 = 2,
+  ADDXLI_OPCODE_X0 = 2,
+  ADDXLI_OPCODE_X1 = 1,
+  ADDXSC_RRR_0_OPCODE_X0 = 1,
+  ADDXSC_RRR_0_OPCODE_X1 = 1,
+  ADDX_RRR_0_OPCODE_X0 = 2,
+  ADDX_RRR_0_OPCODE_X1 = 2,
+  ADDX_RRR_0_OPCODE_Y0 = 0,
+  ADDX_SPECIAL_0_OPCODE_Y1 = 0,
+  ADD_RRR_0_OPCODE_X0 = 3,
+  ADD_RRR_0_OPCODE_X1 = 3,
+  ADD_RRR_0_OPCODE_Y0 = 1,
+  ADD_SPECIAL_0_OPCODE_Y1 = 1,
+  ANDI_IMM8_OPCODE_X0 = 3,
+  ANDI_IMM8_OPCODE_X1 = 3,
+  ANDI_OPCODE_Y0 = 2,
+  ANDI_OPCODE_Y1 = 3,
+  AND_RRR_0_OPCODE_X0 = 4,
+  AND_RRR_0_OPCODE_X1 = 4,
+  AND_RRR_5_OPCODE_Y0 = 0,
+  AND_RRR_5_OPCODE_Y1 = 0,
+  BEQZT_BRANCH_OPCODE_X1 = 16,
+  BEQZ_BRANCH_OPCODE_X1 = 17,
+  BFEXTS_BF_OPCODE_X0 = 4,
+  BFEXTU_BF_OPCODE_X0 = 5,
+  BFINS_BF_OPCODE_X0 = 6,
+  BF_OPCODE_X0 = 3,
+  BGEZT_BRANCH_OPCODE_X1 = 18,
+  BGEZ_BRANCH_OPCODE_X1 = 19,
+  BGTZT_BRANCH_OPCODE_X1 = 20,
+  BGTZ_BRANCH_OPCODE_X1 = 21,
+  BLBCT_BRANCH_OPCODE_X1 = 22,
+  BLBC_BRANCH_OPCODE_X1 = 23,
+  BLBST_BRANCH_OPCODE_X1 = 24,
+  BLBS_BRANCH_OPCODE_X1 = 25,
+  BLEZT_BRANCH_OPCODE_X1 = 26,
+  BLEZ_BRANCH_OPCODE_X1 = 27,
+  BLTZT_BRANCH_OPCODE_X1 = 28,
+  BLTZ_BRANCH_OPCODE_X1 = 29,
+  BNEZT_BRANCH_OPCODE_X1 = 30,
+  BNEZ_BRANCH_OPCODE_X1 = 31,
+  BRANCH_OPCODE_X1 = 2,
+  CMOVEQZ_RRR_0_OPCODE_X0 = 5,
+  CMOVEQZ_RRR_4_OPCODE_Y0 = 0,
+  CMOVNEZ_RRR_0_OPCODE_X0 = 6,
+  CMOVNEZ_RRR_4_OPCODE_Y0 = 1,
+  CMPEQI_IMM8_OPCODE_X0 = 4,
+  CMPEQI_IMM8_OPCODE_X1 = 4,
+  CMPEQI_OPCODE_Y0 = 3,
+  CMPEQI_OPCODE_Y1 = 4,
+  CMPEQ_RRR_0_OPCODE_X0 = 7,
+  CMPEQ_RRR_0_OPCODE_X1 = 5,
+  CMPEQ_RRR_3_OPCODE_Y0 = 0,
+  CMPEQ_RRR_3_OPCODE_Y1 = 2,
+  CMPEXCH4_RRR_0_OPCODE_X1 = 6,
+  CMPEXCH_RRR_0_OPCODE_X1 = 7,
+  CMPLES_RRR_0_OPCODE_X0 = 8,
+  CMPLES_RRR_0_OPCODE_X1 = 8,
+  CMPLES_RRR_2_OPCODE_Y0 = 0,
+  CMPLES_RRR_2_OPCODE_Y1 = 0,
+  CMPLEU_RRR_0_OPCODE_X0 = 9,
+  CMPLEU_RRR_0_OPCODE_X1 = 9,
+  CMPLEU_RRR_2_OPCODE_Y0 = 1,
+  CMPLEU_RRR_2_OPCODE_Y1 = 1,
+  CMPLTSI_IMM8_OPCODE_X0 = 5,
+  CMPLTSI_IMM8_OPCODE_X1 = 5,
+  CMPLTSI_OPCODE_Y0 = 4,
+  CMPLTSI_OPCODE_Y1 = 5,
+  CMPLTS_RRR_0_OPCODE_X0 = 10,
+  CMPLTS_RRR_0_OPCODE_X1 = 10,
+  CMPLTS_RRR_2_OPCODE_Y0 = 2,
+  CMPLTS_RRR_2_OPCODE_Y1 = 2,
+  CMPLTUI_IMM8_OPCODE_X0 = 6,
+  CMPLTUI_IMM8_OPCODE_X1 = 6,
+  CMPLTU_RRR_0_OPCODE_X0 = 11,
+  CMPLTU_RRR_0_OPCODE_X1 = 11,
+  CMPLTU_RRR_2_OPCODE_Y0 = 3,
+  CMPLTU_RRR_2_OPCODE_Y1 = 3,
+  CMPNE_RRR_0_OPCODE_X0 = 12,
+  CMPNE_RRR_0_OPCODE_X1 = 12,
+  CMPNE_RRR_3_OPCODE_Y0 = 1,
+  CMPNE_RRR_3_OPCODE_Y1 = 3,
+  CMULAF_RRR_0_OPCODE_X0 = 13,
+  CMULA_RRR_0_OPCODE_X0 = 14,
+  CMULFR_RRR_0_OPCODE_X0 = 15,
+  CMULF_RRR_0_OPCODE_X0 = 16,
+  CMULHR_RRR_0_OPCODE_X0 = 17,
+  CMULH_RRR_0_OPCODE_X0 = 18,
+  CMUL_RRR_0_OPCODE_X0 = 19,
+  CNTLZ_UNARY_OPCODE_X0 = 1,
+  CNTLZ_UNARY_OPCODE_Y0 = 1,
+  CNTTZ_UNARY_OPCODE_X0 = 2,
+  CNTTZ_UNARY_OPCODE_Y0 = 2,
+  CRC32_32_RRR_0_OPCODE_X0 = 20,
+  CRC32_8_RRR_0_OPCODE_X0 = 21,
+  DBLALIGN2_RRR_0_OPCODE_X0 = 22,
+  DBLALIGN2_RRR_0_OPCODE_X1 = 13,
+  DBLALIGN4_RRR_0_OPCODE_X0 = 23,
+  DBLALIGN4_RRR_0_OPCODE_X1 = 14,
+  DBLALIGN6_RRR_0_OPCODE_X0 = 24,
+  DBLALIGN6_RRR_0_OPCODE_X1 = 15,
+  DBLALIGN_RRR_0_OPCODE_X0 = 25,
+  DRAIN_UNARY_OPCODE_X1 = 1,
+  DTLBPR_UNARY_OPCODE_X1 = 2,
+  EXCH4_RRR_0_OPCODE_X1 = 16,
+  EXCH_RRR_0_OPCODE_X1 = 17,
+  FDOUBLE_ADDSUB_RRR_0_OPCODE_X0 = 26,
+  FDOUBLE_ADD_FLAGS_RRR_0_OPCODE_X0 = 27,
+  FDOUBLE_MUL_FLAGS_RRR_0_OPCODE_X0 = 28,
+  FDOUBLE_PACK1_RRR_0_OPCODE_X0 = 29,
+  FDOUBLE_PACK2_RRR_0_OPCODE_X0 = 30,
+  FDOUBLE_SUB_FLAGS_RRR_0_OPCODE_X0 = 31,
+  FDOUBLE_UNPACK_MAX_RRR_0_OPCODE_X0 = 32,
+  FDOUBLE_UNPACK_MIN_RRR_0_OPCODE_X0 = 33,
+  FETCHADD4_RRR_0_OPCODE_X1 = 18,
+  FETCHADDGEZ4_RRR_0_OPCODE_X1 = 19,
+  FETCHADDGEZ_RRR_0_OPCODE_X1 = 20,
+  FETCHADD_RRR_0_OPCODE_X1 = 21,
+  FETCHAND4_RRR_0_OPCODE_X1 = 22,
+  FETCHAND_RRR_0_OPCODE_X1 = 23,
+  FETCHOR4_RRR_0_OPCODE_X1 = 24,
+  FETCHOR_RRR_0_OPCODE_X1 = 25,
+  FINV_UNARY_OPCODE_X1 = 3,
+  FLUSHWB_UNARY_OPCODE_X1 = 4,
+  FLUSH_UNARY_OPCODE_X1 = 5,
+  FNOP_UNARY_OPCODE_X0 = 3,
+  FNOP_UNARY_OPCODE_X1 = 6,
+  FNOP_UNARY_OPCODE_Y0 = 3,
+  FNOP_UNARY_OPCODE_Y1 = 8,
+  FSINGLE_ADD1_RRR_0_OPCODE_X0 = 34,
+  FSINGLE_ADDSUB2_RRR_0_OPCODE_X0 = 35,
+  FSINGLE_MUL1_RRR_0_OPCODE_X0 = 36,
+  FSINGLE_MUL2_RRR_0_OPCODE_X0 = 37,
+  FSINGLE_PACK1_UNARY_OPCODE_X0 = 4,
+  FSINGLE_PACK1_UNARY_OPCODE_Y0 = 4,
+  FSINGLE_PACK2_RRR_0_OPCODE_X0 = 38,
+  FSINGLE_SUB1_RRR_0_OPCODE_X0 = 39,
+  ICOH_UNARY_OPCODE_X1 = 7,
+  ILL_UNARY_OPCODE_X1 = 8,
+  ILL_UNARY_OPCODE_Y1 = 9,
+  IMM8_OPCODE_X0 = 4,
+  IMM8_OPCODE_X1 = 3,
+  INV_UNARY_OPCODE_X1 = 9,
+  IRET_UNARY_OPCODE_X1 = 10,
+  JALRP_UNARY_OPCODE_X1 = 11,
+  JALRP_UNARY_OPCODE_Y1 = 10,
+  JALR_UNARY_OPCODE_X1 = 12,
+  JALR_UNARY_OPCODE_Y1 = 11,
+  JAL_JUMP_OPCODE_X1 = 0,
+  JRP_UNARY_OPCODE_X1 = 13,
+  JRP_UNARY_OPCODE_Y1 = 12,
+  JR_UNARY_OPCODE_X1 = 14,
+  JR_UNARY_OPCODE_Y1 = 13,
+  JUMP_OPCODE_X1 = 4,
+  J_JUMP_OPCODE_X1 = 1,
+  LD1S_ADD_IMM8_OPCODE_X1 = 7,
+  LD1S_OPCODE_Y2 = 0,
+  LD1S_UNARY_OPCODE_X1 = 15,
+  LD1U_ADD_IMM8_OPCODE_X1 = 8,
+  LD1U_OPCODE_Y2 = 1,
+  LD1U_UNARY_OPCODE_X1 = 16,
+  LD2S_ADD_IMM8_OPCODE_X1 = 9,
+  LD2S_OPCODE_Y2 = 2,
+  LD2S_UNARY_OPCODE_X1 = 17,
+  LD2U_ADD_IMM8_OPCODE_X1 = 10,
+  LD2U_OPCODE_Y2 = 3,
+  LD2U_UNARY_OPCODE_X1 = 18,
+  LD4S_ADD_IMM8_OPCODE_X1 = 11,
+  LD4S_OPCODE_Y2 = 1,
+  LD4S_UNARY_OPCODE_X1 = 19,
+  LD4U_ADD_IMM8_OPCODE_X1 = 12,
+  LD4U_OPCODE_Y2 = 2,
+  LD4U_UNARY_OPCODE_X1 = 20,
+  LDNA_UNARY_OPCODE_X1 = 21,
+  LDNT1S_ADD_IMM8_OPCODE_X1 = 13,
+  LDNT1S_UNARY_OPCODE_X1 = 22,
+  LDNT1U_ADD_IMM8_OPCODE_X1 = 14,
+  LDNT1U_UNARY_OPCODE_X1 = 23,
+  LDNT2S_ADD_IMM8_OPCODE_X1 = 15,
+  LDNT2S_UNARY_OPCODE_X1 = 24,
+  LDNT2U_ADD_IMM8_OPCODE_X1 = 16,
+  LDNT2U_UNARY_OPCODE_X1 = 25,
+  LDNT4S_ADD_IMM8_OPCODE_X1 = 17,
+  LDNT4S_UNARY_OPCODE_X1 = 26,
+  LDNT4U_ADD_IMM8_OPCODE_X1 = 18,
+  LDNT4U_UNARY_OPCODE_X1 = 27,
+  LDNT_ADD_IMM8_OPCODE_X1 = 19,
+  LDNT_UNARY_OPCODE_X1 = 28,
+  LD_ADD_IMM8_OPCODE_X1 = 20,
+  LD_OPCODE_Y2 = 3,
+  LD_UNARY_OPCODE_X1 = 29,
+  LNK_UNARY_OPCODE_X1 = 30,
+  LNK_UNARY_OPCODE_Y1 = 14,
+  LWNA_ADD_IMM8_OPCODE_X1 = 21,
+  MFSPR_IMM8_OPCODE_X1 = 22,
+  MF_UNARY_OPCODE_X1 = 31,
+  MM_BF_OPCODE_X0 = 7,
+  MNZ_RRR_0_OPCODE_X0 = 40,
+  MNZ_RRR_0_OPCODE_X1 = 26,
+  MNZ_RRR_4_OPCODE_Y0 = 2,
+  MNZ_RRR_4_OPCODE_Y1 = 2,
+  MODE_OPCODE_YA2 = 1,
+  MODE_OPCODE_YB2 = 2,
+  MODE_OPCODE_YC2 = 3,
+  MTSPR_IMM8_OPCODE_X1 = 23,
+  MULAX_RRR_0_OPCODE_X0 = 41,
+  MULAX_RRR_3_OPCODE_Y0 = 2,
+  MULA_HS_HS_RRR_0_OPCODE_X0 = 42,
+  MULA_HS_HS_RRR_9_OPCODE_Y0 = 0,
+  MULA_HS_HU_RRR_0_OPCODE_X0 = 43,
+  MULA_HS_LS_RRR_0_OPCODE_X0 = 44,
+  MULA_HS_LU_RRR_0_OPCODE_X0 = 45,
+  MULA_HU_HU_RRR_0_OPCODE_X0 = 46,
+  MULA_HU_HU_RRR_9_OPCODE_Y0 = 1,
+  MULA_HU_LS_RRR_0_OPCODE_X0 = 47,
+  MULA_HU_LU_RRR_0_OPCODE_X0 = 48,
+  MULA_LS_LS_RRR_0_OPCODE_X0 = 49,
+  MULA_LS_LS_RRR_9_OPCODE_Y0 = 2,
+  MULA_LS_LU_RRR_0_OPCODE_X0 = 50,
+  MULA_LU_LU_RRR_0_OPCODE_X0 = 51,
+  MULA_LU_LU_RRR_9_OPCODE_Y0 = 3,
+  MULX_RRR_0_OPCODE_X0 = 52,
+  MULX_RRR_3_OPCODE_Y0 = 3,
+  MUL_HS_HS_RRR_0_OPCODE_X0 = 53,
+  MUL_HS_HS_RRR_8_OPCODE_Y0 = 0,
+  MUL_HS_HU_RRR_0_OPCODE_X0 = 54,
+  MUL_HS_LS_RRR_0_OPCODE_X0 = 55,
+  MUL_HS_LU_RRR_0_OPCODE_X0 = 56,
+  MUL_HU_HU_RRR_0_OPCODE_X0 = 57,
+  MUL_HU_HU_RRR_8_OPCODE_Y0 = 1,
+  MUL_HU_LS_RRR_0_OPCODE_X0 = 58,
+  MUL_HU_LU_RRR_0_OPCODE_X0 = 59,
+  MUL_LS_LS_RRR_0_OPCODE_X0 = 60,
+  MUL_LS_LS_RRR_8_OPCODE_Y0 = 2,
+  MUL_LS_LU_RRR_0_OPCODE_X0 = 61,
+  MUL_LU_LU_RRR_0_OPCODE_X0 = 62,
+  MUL_LU_LU_RRR_8_OPCODE_Y0 = 3,
+  MZ_RRR_0_OPCODE_X0 = 63,
+  MZ_RRR_0_OPCODE_X1 = 27,
+  MZ_RRR_4_OPCODE_Y0 = 3,
+  MZ_RRR_4_OPCODE_Y1 = 3,
+  NAP_UNARY_OPCODE_X1 = 32,
+  NOP_UNARY_OPCODE_X0 = 5,
+  NOP_UNARY_OPCODE_X1 = 33,
+  NOP_UNARY_OPCODE_Y0 = 5,
+  NOP_UNARY_OPCODE_Y1 = 15,
+  NOR_RRR_0_OPCODE_X0 = 64,
+  NOR_RRR_0_OPCODE_X1 = 28,
+  NOR_RRR_5_OPCODE_Y0 = 1,
+  NOR_RRR_5_OPCODE_Y1 = 1,
+  ORI_IMM8_OPCODE_X0 = 7,
+  ORI_IMM8_OPCODE_X1 = 24,
+  OR_RRR_0_OPCODE_X0 = 65,
+  OR_RRR_0_OPCODE_X1 = 29,
+  OR_RRR_5_OPCODE_Y0 = 2,
+  OR_RRR_5_OPCODE_Y1 = 2,
+  PCNT_UNARY_OPCODE_X0 = 6,
+  PCNT_UNARY_OPCODE_Y0 = 6,
+  REVBITS_UNARY_OPCODE_X0 = 7,
+  REVBITS_UNARY_OPCODE_Y0 = 7,
+  REVBYTES_UNARY_OPCODE_X0 = 8,
+  REVBYTES_UNARY_OPCODE_Y0 = 8,
+  ROTLI_SHIFT_OPCODE_X0 = 1,
+  ROTLI_SHIFT_OPCODE_X1 = 1,
+  ROTLI_SHIFT_OPCODE_Y0 = 0,
+  ROTLI_SHIFT_OPCODE_Y1 = 0,
+  ROTL_RRR_0_OPCODE_X0 = 66,
+  ROTL_RRR_0_OPCODE_X1 = 30,
+  ROTL_RRR_6_OPCODE_Y0 = 0,
+  ROTL_RRR_6_OPCODE_Y1 = 0,
+  RRR_0_OPCODE_X0 = 5,
+  RRR_0_OPCODE_X1 = 5,
+  RRR_0_OPCODE_Y0 = 5,
+  RRR_0_OPCODE_Y1 = 6,
+  RRR_1_OPCODE_Y0 = 6,
+  RRR_1_OPCODE_Y1 = 7,
+  RRR_2_OPCODE_Y0 = 7,
+  RRR_2_OPCODE_Y1 = 8,
+  RRR_3_OPCODE_Y0 = 8,
+  RRR_3_OPCODE_Y1 = 9,
+  RRR_4_OPCODE_Y0 = 9,
+  RRR_4_OPCODE_Y1 = 10,
+  RRR_5_OPCODE_Y0 = 10,
+  RRR_5_OPCODE_Y1 = 11,
+  RRR_6_OPCODE_Y0 = 11,
+  RRR_6_OPCODE_Y1 = 12,
+  RRR_7_OPCODE_Y0 = 12,
+  RRR_7_OPCODE_Y1 = 13,
+  RRR_8_OPCODE_Y0 = 13,
+  RRR_9_OPCODE_Y0 = 14,
+  SHIFT_OPCODE_X0 = 6,
+  SHIFT_OPCODE_X1 = 6,
+  SHIFT_OPCODE_Y0 = 15,
+  SHIFT_OPCODE_Y1 = 14,
+  SHL16INSLI_OPCODE_X0 = 7,
+  SHL16INSLI_OPCODE_X1 = 7,
+  SHL1ADDX_RRR_0_OPCODE_X0 = 67,
+  SHL1ADDX_RRR_0_OPCODE_X1 = 31,
+  SHL1ADDX_RRR_7_OPCODE_Y0 = 1,
+  SHL1ADDX_RRR_7_OPCODE_Y1 = 1,
+  SHL1ADD_RRR_0_OPCODE_X0 = 68,
+  SHL1ADD_RRR_0_OPCODE_X1 = 32,
+  SHL1ADD_RRR_1_OPCODE_Y0 = 0,
+  SHL1ADD_RRR_1_OPCODE_Y1 = 0,
+  SHL2ADDX_RRR_0_OPCODE_X0 = 69,
+  SHL2ADDX_RRR_0_OPCODE_X1 = 33,
+  SHL2ADDX_RRR_7_OPCODE_Y0 = 2,
+  SHL2ADDX_RRR_7_OPCODE_Y1 = 2,
+  SHL2ADD_RRR_0_OPCODE_X0 = 70,
+  SHL2ADD_RRR_0_OPCODE_X1 = 34,
+  SHL2ADD_RRR_1_OPCODE_Y0 = 1,
+  SHL2ADD_RRR_1_OPCODE_Y1 = 1,
+  SHL3ADDX_RRR_0_OPCODE_X0 = 71,
+  SHL3ADDX_RRR_0_OPCODE_X1 = 35,
+  SHL3ADDX_RRR_7_OPCODE_Y0 = 3,
+  SHL3ADDX_RRR_7_OPCODE_Y1 = 3,
+  SHL3ADD_RRR_0_OPCODE_X0 = 72,
+  SHL3ADD_RRR_0_OPCODE_X1 = 36,
+  SHL3ADD_RRR_1_OPCODE_Y0 = 2,
+  SHL3ADD_RRR_1_OPCODE_Y1 = 2,
+  SHLI_SHIFT_OPCODE_X0 = 2,
+  SHLI_SHIFT_OPCODE_X1 = 2,
+  SHLI_SHIFT_OPCODE_Y0 = 1,
+  SHLI_SHIFT_OPCODE_Y1 = 1,
+  SHLXI_SHIFT_OPCODE_X0 = 3,
+  SHLXI_SHIFT_OPCODE_X1 = 3,
+  SHLX_RRR_0_OPCODE_X0 = 73,
+  SHLX_RRR_0_OPCODE_X1 = 37,
+  SHL_RRR_0_OPCODE_X0 = 74,
+  SHL_RRR_0_OPCODE_X1 = 38,
+  SHL_RRR_6_OPCODE_Y0 = 1,
+  SHL_RRR_6_OPCODE_Y1 = 1,
+  SHRSI_SHIFT_OPCODE_X0 = 4,
+  SHRSI_SHIFT_OPCODE_X1 = 4,
+  SHRSI_SHIFT_OPCODE_Y0 = 2,
+  SHRSI_SHIFT_OPCODE_Y1 = 2,
+  SHRS_RRR_0_OPCODE_X0 = 75,
+  SHRS_RRR_0_OPCODE_X1 = 39,
+  SHRS_RRR_6_OPCODE_Y0 = 2,
+  SHRS_RRR_6_OPCODE_Y1 = 2,
+  SHRUI_SHIFT_OPCODE_X0 = 5,
+  SHRUI_SHIFT_OPCODE_X1 = 5,
+  SHRUI_SHIFT_OPCODE_Y0 = 3,
+  SHRUI_SHIFT_OPCODE_Y1 = 3,
+  SHRUXI_SHIFT_OPCODE_X0 = 6,
+  SHRUXI_SHIFT_OPCODE_X1 = 6,
+  SHRUX_RRR_0_OPCODE_X0 = 76,
+  SHRUX_RRR_0_OPCODE_X1 = 40,
+  SHRU_RRR_0_OPCODE_X0 = 77,
+  SHRU_RRR_0_OPCODE_X1 = 41,
+  SHRU_RRR_6_OPCODE_Y0 = 3,
+  SHRU_RRR_6_OPCODE_Y1 = 3,
+  SHUFFLEBYTES_RRR_0_OPCODE_X0 = 78,
+  ST1_ADD_IMM8_OPCODE_X1 = 25,
+  ST1_OPCODE_Y2 = 0,
+  ST1_RRR_0_OPCODE_X1 = 42,
+  ST2_ADD_IMM8_OPCODE_X1 = 26,
+  ST2_OPCODE_Y2 = 1,
+  ST2_RRR_0_OPCODE_X1 = 43,
+  ST4_ADD_IMM8_OPCODE_X1 = 27,
+  ST4_OPCODE_Y2 = 2,
+  ST4_RRR_0_OPCODE_X1 = 44,
+  STNT1_ADD_IMM8_OPCODE_X1 = 28,
+  STNT1_RRR_0_OPCODE_X1 = 45,
+  STNT2_ADD_IMM8_OPCODE_X1 = 29,
+  STNT2_RRR_0_OPCODE_X1 = 46,
+  STNT4_ADD_IMM8_OPCODE_X1 = 30,
+  STNT4_RRR_0_OPCODE_X1 = 47,
+  STNT_ADD_IMM8_OPCODE_X1 = 31,
+  STNT_RRR_0_OPCODE_X1 = 48,
+  ST_ADD_IMM8_OPCODE_X1 = 32,
+  ST_OPCODE_Y2 = 3,
+  ST_RRR_0_OPCODE_X1 = 49,
+  SUBXSC_RRR_0_OPCODE_X0 = 79,
+  SUBXSC_RRR_0_OPCODE_X1 = 50,
+  SUBX_RRR_0_OPCODE_X0 = 80,
+  SUBX_RRR_0_OPCODE_X1 = 51,
+  SUBX_RRR_0_OPCODE_Y0 = 2,
+  SUBX_RRR_0_OPCODE_Y1 = 2,
+  SUB_RRR_0_OPCODE_X0 = 81,
+  SUB_RRR_0_OPCODE_X1 = 52,
+  SUB_RRR_0_OPCODE_Y0 = 3,
+  SUB_RRR_0_OPCODE_Y1 = 3,
+  SWINT0_UNARY_OPCODE_X1 = 34,
+  SWINT1_UNARY_OPCODE_X1 = 35,
+  SWINT2_UNARY_OPCODE_X1 = 36,
+  SWINT3_UNARY_OPCODE_X1 = 37,
+  TBLIDXB0_UNARY_OPCODE_X0 = 9,
+  TBLIDXB0_UNARY_OPCODE_Y0 = 9,
+  TBLIDXB1_UNARY_OPCODE_X0 = 10,
+  TBLIDXB1_UNARY_OPCODE_Y0 = 10,
+  TBLIDXB2_UNARY_OPCODE_X0 = 11,
+  TBLIDXB2_UNARY_OPCODE_Y0 = 11,
+  TBLIDXB3_UNARY_OPCODE_X0 = 12,
+  TBLIDXB3_UNARY_OPCODE_Y0 = 12,
+  UNARY_RRR_0_OPCODE_X0 = 82,
+  UNARY_RRR_0_OPCODE_X1 = 53,
+  UNARY_RRR_1_OPCODE_Y0 = 3,
+  UNARY_RRR_1_OPCODE_Y1 = 3,
+  V1ADDI_IMM8_OPCODE_X0 = 8,
+  V1ADDI_IMM8_OPCODE_X1 = 33,
+  V1ADDUC_RRR_0_OPCODE_X0 = 83,
+  V1ADDUC_RRR_0_OPCODE_X1 = 54,
+  V1ADD_RRR_0_OPCODE_X0 = 84,
+  V1ADD_RRR_0_OPCODE_X1 = 55,
+  V1ADIFFU_RRR_0_OPCODE_X0 = 85,
+  V1AVGU_RRR_0_OPCODE_X0 = 86,
+  V1CMPEQI_IMM8_OPCODE_X0 = 9,
+  V1CMPEQI_IMM8_OPCODE_X1 = 34,
+  V1CMPEQ_RRR_0_OPCODE_X0 = 87,
+  V1CMPEQ_RRR_0_OPCODE_X1 = 56,
+  V1CMPLES_RRR_0_OPCODE_X0 = 88,
+  V1CMPLES_RRR_0_OPCODE_X1 = 57,
+  V1CMPLEU_RRR_0_OPCODE_X0 = 89,
+  V1CMPLEU_RRR_0_OPCODE_X1 = 58,
+  V1CMPLTSI_IMM8_OPCODE_X0 = 10,
+  V1CMPLTSI_IMM8_OPCODE_X1 = 35,
+  V1CMPLTS_RRR_0_OPCODE_X0 = 90,
+  V1CMPLTS_RRR_0_OPCODE_X1 = 59,
+  V1CMPLTUI_IMM8_OPCODE_X0 = 11,
+  V1CMPLTUI_IMM8_OPCODE_X1 = 36,
+  V1CMPLTU_RRR_0_OPCODE_X0 = 91,
+  V1CMPLTU_RRR_0_OPCODE_X1 = 60,
+  V1CMPNE_RRR_0_OPCODE_X0 = 92,
+  V1CMPNE_RRR_0_OPCODE_X1 = 61,
+  V1DDOTPUA_RRR_0_OPCODE_X0 = 161,
+  V1DDOTPUSA_RRR_0_OPCODE_X0 = 93,
+  V1DDOTPUS_RRR_0_OPCODE_X0 = 94,
+  V1DDOTPU_RRR_0_OPCODE_X0 = 162,
+  V1DOTPA_RRR_0_OPCODE_X0 = 95,
+  V1DOTPUA_RRR_0_OPCODE_X0 = 163,
+  V1DOTPUSA_RRR_0_OPCODE_X0 = 96,
+  V1DOTPUS_RRR_0_OPCODE_X0 = 97,
+  V1DOTPU_RRR_0_OPCODE_X0 = 164,
+  V1DOTP_RRR_0_OPCODE_X0 = 98,
+  V1INT_H_RRR_0_OPCODE_X0 = 99,
+  V1INT_H_RRR_0_OPCODE_X1 = 62,
+  V1INT_L_RRR_0_OPCODE_X0 = 100,
+  V1INT_L_RRR_0_OPCODE_X1 = 63,
+  V1MAXUI_IMM8_OPCODE_X0 = 12,
+  V1MAXUI_IMM8_OPCODE_X1 = 37,
+  V1MAXU_RRR_0_OPCODE_X0 = 101,
+  V1MAXU_RRR_0_OPCODE_X1 = 64,
+  V1MINUI_IMM8_OPCODE_X0 = 13,
+  V1MINUI_IMM8_OPCODE_X1 = 38,
+  V1MINU_RRR_0_OPCODE_X0 = 102,
+  V1MINU_RRR_0_OPCODE_X1 = 65,
+  V1MNZ_RRR_0_OPCODE_X0 = 103,
+  V1MNZ_RRR_0_OPCODE_X1 = 66,
+  V1MULTU_RRR_0_OPCODE_X0 = 104,
+  V1MULUS_RRR_0_OPCODE_X0 = 105,
+  V1MULU_RRR_0_OPCODE_X0 = 106,
+  V1MZ_RRR_0_OPCODE_X0 = 107,
+  V1MZ_RRR_0_OPCODE_X1 = 67,
+  V1SADAU_RRR_0_OPCODE_X0 = 108,
+  V1SADU_RRR_0_OPCODE_X0 = 109,
+  V1SHLI_SHIFT_OPCODE_X0 = 7,
+  V1SHLI_SHIFT_OPCODE_X1 = 7,
+  V1SHL_RRR_0_OPCODE_X0 = 110,
+  V1SHL_RRR_0_OPCODE_X1 = 68,
+  V1SHRSI_SHIFT_OPCODE_X0 = 8,
+  V1SHRSI_SHIFT_OPCODE_X1 = 8,
+  V1SHRS_RRR_0_OPCODE_X0 = 111,
+  V1SHRS_RRR_0_OPCODE_X1 = 69,
+  V1SHRUI_SHIFT_OPCODE_X0 = 9,
+  V1SHRUI_SHIFT_OPCODE_X1 = 9,
+  V1SHRU_RRR_0_OPCODE_X0 = 112,
+  V1SHRU_RRR_0_OPCODE_X1 = 70,
+  V1SUBUC_RRR_0_OPCODE_X0 = 113,
+  V1SUBUC_RRR_0_OPCODE_X1 = 71,
+  V1SUB_RRR_0_OPCODE_X0 = 114,
+  V1SUB_RRR_0_OPCODE_X1 = 72,
+  V2ADDI_IMM8_OPCODE_X0 = 14,
+  V2ADDI_IMM8_OPCODE_X1 = 39,
+  V2ADDSC_RRR_0_OPCODE_X0 = 115,
+  V2ADDSC_RRR_0_OPCODE_X1 = 73,
+  V2ADD_RRR_0_OPCODE_X0 = 116,
+  V2ADD_RRR_0_OPCODE_X1 = 74,
+  V2ADIFFS_RRR_0_OPCODE_X0 = 117,
+  V2AVGS_RRR_0_OPCODE_X0 = 118,
+  V2CMPEQI_IMM8_OPCODE_X0 = 15,
+  V2CMPEQI_IMM8_OPCODE_X1 = 40,
+  V2CMPEQ_RRR_0_OPCODE_X0 = 119,
+  V2CMPEQ_RRR_0_OPCODE_X1 = 75,
+  V2CMPLES_RRR_0_OPCODE_X0 = 120,
+  V2CMPLES_RRR_0_OPCODE_X1 = 76,
+  V2CMPLEU_RRR_0_OPCODE_X0 = 121,
+  V2CMPLEU_RRR_0_OPCODE_X1 = 77,
+  V2CMPLTSI_IMM8_OPCODE_X0 = 16,
+  V2CMPLTSI_IMM8_OPCODE_X1 = 41,
+  V2CMPLTS_RRR_0_OPCODE_X0 = 122,
+  V2CMPLTS_RRR_0_OPCODE_X1 = 78,
+  V2CMPLTUI_IMM8_OPCODE_X0 = 17,
+  V2CMPLTUI_IMM8_OPCODE_X1 = 42,
+  V2CMPLTU_RRR_0_OPCODE_X0 = 123,
+  V2CMPLTU_RRR_0_OPCODE_X1 = 79,
+  V2CMPNE_RRR_0_OPCODE_X0 = 124,
+  V2CMPNE_RRR_0_OPCODE_X1 = 80,
+  V2DOTPA_RRR_0_OPCODE_X0 = 125,
+  V2DOTP_RRR_0_OPCODE_X0 = 126,
+  V2INT_H_RRR_0_OPCODE_X0 = 127,
+  V2INT_H_RRR_0_OPCODE_X1 = 81,
+  V2INT_L_RRR_0_OPCODE_X0 = 128,
+  V2INT_L_RRR_0_OPCODE_X1 = 82,
+  V2MAXSI_IMM8_OPCODE_X0 = 18,
+  V2MAXSI_IMM8_OPCODE_X1 = 43,
+  V2MAXS_RRR_0_OPCODE_X0 = 129,
+  V2MAXS_RRR_0_OPCODE_X1 = 83,
+  V2MINSI_IMM8_OPCODE_X0 = 19,
+  V2MINSI_IMM8_OPCODE_X1 = 44,
+  V2MINS_RRR_0_OPCODE_X0 = 130,
+  V2MINS_RRR_0_OPCODE_X1 = 84,
+  V2MNZ_RRR_0_OPCODE_X0 = 131,
+  V2MNZ_RRR_0_OPCODE_X1 = 85,
+  V2MULFSC_RRR_0_OPCODE_X0 = 132,
+  V2MULS_RRR_0_OPCODE_X0 = 133,
+  V2MULTS_RRR_0_OPCODE_X0 = 134,
+  V2MZ_RRR_0_OPCODE_X0 = 135,
+  V2MZ_RRR_0_OPCODE_X1 = 86,
+  V2PACKH_RRR_0_OPCODE_X0 = 136,
+  V2PACKH_RRR_0_OPCODE_X1 = 87,
+  V2PACKL_RRR_0_OPCODE_X0 = 137,
+  V2PACKL_RRR_0_OPCODE_X1 = 88,
+  V2PACKUC_RRR_0_OPCODE_X0 = 138,
+  V2PACKUC_RRR_0_OPCODE_X1 = 89,
+  V2SADAS_RRR_0_OPCODE_X0 = 139,
+  V2SADAU_RRR_0_OPCODE_X0 = 140,
+  V2SADS_RRR_0_OPCODE_X0 = 141,
+  V2SADU_RRR_0_OPCODE_X0 = 142,
+  V2SHLI_SHIFT_OPCODE_X0 = 10,
+  V2SHLI_SHIFT_OPCODE_X1 = 10,
+  V2SHLSC_RRR_0_OPCODE_X0 = 143,
+  V2SHLSC_RRR_0_OPCODE_X1 = 90,
+  V2SHL_RRR_0_OPCODE_X0 = 144,
+  V2SHL_RRR_0_OPCODE_X1 = 91,
+  V2SHRSI_SHIFT_OPCODE_X0 = 11,
+  V2SHRSI_SHIFT_OPCODE_X1 = 11,
+  V2SHRS_RRR_0_OPCODE_X0 = 145,
+  V2SHRS_RRR_0_OPCODE_X1 = 92,
+  V2SHRUI_SHIFT_OPCODE_X0 = 12,
+  V2SHRUI_SHIFT_OPCODE_X1 = 12,
+  V2SHRU_RRR_0_OPCODE_X0 = 146,
+  V2SHRU_RRR_0_OPCODE_X1 = 93,
+  V2SUBSC_RRR_0_OPCODE_X0 = 147,
+  V2SUBSC_RRR_0_OPCODE_X1 = 94,
+  V2SUB_RRR_0_OPCODE_X0 = 148,
+  V2SUB_RRR_0_OPCODE_X1 = 95,
+  V4ADDSC_RRR_0_OPCODE_X0 = 149,
+  V4ADDSC_RRR_0_OPCODE_X1 = 96,
+  V4ADD_RRR_0_OPCODE_X0 = 150,
+  V4ADD_RRR_0_OPCODE_X1 = 97,
+  V4INT_H_RRR_0_OPCODE_X0 = 151,
+  V4INT_H_RRR_0_OPCODE_X1 = 98,
+  V4INT_L_RRR_0_OPCODE_X0 = 152,
+  V4INT_L_RRR_0_OPCODE_X1 = 99,
+  V4PACKSC_RRR_0_OPCODE_X0 = 153,
+  V4PACKSC_RRR_0_OPCODE_X1 = 100,
+  V4SHLSC_RRR_0_OPCODE_X0 = 154,
+  V4SHLSC_RRR_0_OPCODE_X1 = 101,
+  V4SHL_RRR_0_OPCODE_X0 = 155,
+  V4SHL_RRR_0_OPCODE_X1 = 102,
+  V4SHRS_RRR_0_OPCODE_X0 = 156,
+  V4SHRS_RRR_0_OPCODE_X1 = 103,
+  V4SHRU_RRR_0_OPCODE_X0 = 157,
+  V4SHRU_RRR_0_OPCODE_X1 = 104,
+  V4SUBSC_RRR_0_OPCODE_X0 = 158,
+  V4SUBSC_RRR_0_OPCODE_X1 = 105,
+  V4SUB_RRR_0_OPCODE_X0 = 159,
+  V4SUB_RRR_0_OPCODE_X1 = 106,
+  WH64_UNARY_OPCODE_X1 = 38,
+  XORI_IMM8_OPCODE_X0 = 20,
+  XORI_IMM8_OPCODE_X1 = 45,
+  XOR_RRR_0_OPCODE_X0 = 160,
+  XOR_RRR_0_OPCODE_X1 = 107,
+  XOR_RRR_5_OPCODE_Y0 = 3,
+  XOR_RRR_5_OPCODE_Y1 = 3
 };
 
 #endif /* !_TILE_OPCODE_CONSTANTS_H */
diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h
index 3eb53525bf9d..db93518fac03 100644
--- a/arch/tile/include/asm/page.h
+++ b/arch/tile/include/asm/page.h
@@ -16,7 +16,8 @@
 #define _ASM_TILE_PAGE_H
 
 #include <linux/const.h>
-#include <hv/pagesize.h>
+#include <hv/hypervisor.h>
+#include <arch/chip.h>
 
 /* PAGE_SHIFT and HPAGE_SHIFT determine the page sizes. */
 #define PAGE_SHIFT      HV_LOG2_PAGE_SIZE_SMALL
@@ -28,8 +29,6 @@
 #define PAGE_MASK       (~(PAGE_SIZE - 1))
 #define HPAGE_MASK      (~(HPAGE_SIZE - 1))
 
-#ifdef __KERNEL__
-
 /*
  * If the Kconfig doesn't specify, set a maximum zone order that
  * is enough so that we can create huge pages from small pages given
@@ -39,9 +38,6 @@
 #define CONFIG_FORCE_MAX_ZONEORDER (HPAGE_SHIFT - PAGE_SHIFT + 1)
 #endif
 
-#include <hv/hypervisor.h>
-#include <arch/chip.h>
-
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
@@ -91,6 +87,10 @@ typedef struct page *pgtable_t;
 /* Must be a macro since it is used to create constants. */
 #define __pgprot(val) hv_pte(val)
 
+/* Rarely-used initializers, typically with a "zero" value. */
+#define __pte(x) hv_pte(x)
+#define __pgd(x) hv_pte(x)
+
 static inline u64 pgprot_val(pgprot_t pgprot)
 {
         return hv_pte_val(pgprot);
@@ -110,6 +110,8 @@ static inline u64 pgd_val(pgd_t pgd)
 
 typedef HV_PTE pmd_t;
 
+#define __pmd(x) hv_pte(x)
+
 static inline u64 pmd_val(pmd_t pmd)
 {
         return hv_pte_val(pmd);
@@ -318,7 +320,7 @@ static inline int pfn_valid(unsigned long pfn)
 
 /* Provide as macros since these require some other headers included. */
 #define page_to_pa(page) ((phys_addr_t)(page_to_pfn(page)) << PAGE_SHIFT)
-#define virt_to_page(kaddr) pfn_to_page(kaddr_to_pfn(kaddr))
+#define virt_to_page(kaddr) pfn_to_page(kaddr_to_pfn((void *)(kaddr)))
 #define page_to_virt(page) pfn_to_kaddr(page_to_pfn(page))
 
 struct mm_struct;
@@ -331,6 +333,4 @@ extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
 
 #include <asm-generic/memory_model.h>
 
-#endif /* __KERNEL__ */
-
 #endif /* _ASM_TILE_PAGE_H */
diff --git a/arch/tile/include/asm/parport.h b/arch/tile/include/asm/parport.h
new file mode 100644
index 000000000000..cf252af64590
--- /dev/null
+++ b/arch/tile/include/asm/parport.h
@@ -0,0 +1 @@
+#include <asm-generic/parport.h>
diff --git a/arch/tile/include/asm/pci.h b/arch/tile/include/asm/pci.h
index c3fc458a0d32..7f03cefed1b9 100644
--- a/arch/tile/include/asm/pci.h
+++ b/arch/tile/include/asm/pci.h
@@ -46,7 +46,8 @@ struct pci_controller {
  */
 #define PCI_DMA_BUS_IS_PHYS     1
 
-int __init tile_pci_init(void);
+int __devinit tile_pci_init(void);
+int __devinit pcibios_init(void);
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
 static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) {}
diff --git a/arch/tile/include/asm/pgtable_64.h b/arch/tile/include/asm/pgtable_64.h
new file mode 100644
index 000000000000..fd80328523b4
--- /dev/null
+++ b/arch/tile/include/asm/pgtable_64.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ */
+
+#ifndef _ASM_TILE_PGTABLE_64_H
+#define _ASM_TILE_PGTABLE_64_H
+
+/* The level-0 page table breaks the address space into 32-bit chunks. */
+#define PGDIR_SHIFT     HV_LOG2_L1_SPAN
+#define PGDIR_SIZE      HV_L1_SPAN
+#define PGDIR_MASK      (~(PGDIR_SIZE-1))
+#define PTRS_PER_PGD    HV_L0_ENTRIES
+#define SIZEOF_PGD      (PTRS_PER_PGD * sizeof(pgd_t))
+
+/*
+ * The level-1 index is defined by the huge page size.  A PMD is composed
+ * of PTRS_PER_PMD pgd_t's and is the middle level of the page table.
+ */
+#define PMD_SHIFT       HV_LOG2_PAGE_SIZE_LARGE
+#define PMD_SIZE        HV_PAGE_SIZE_LARGE
+#define PMD_MASK        (~(PMD_SIZE-1))
+#define PTRS_PER_PMD    (1 << (PGDIR_SHIFT - PMD_SHIFT))
+#define SIZEOF_PMD      (PTRS_PER_PMD * sizeof(pmd_t))
+
+/*
+ * The level-2 index is defined by the difference between the huge
+ * page size and the normal page size.  A PTE is composed of
+ * PTRS_PER_PTE pte_t's and is the bottom level of the page table.
+ * Note that the hypervisor docs use PTE for what we call pte_t, so
+ * this nomenclature is somewhat confusing.
+ */
+#define PTRS_PER_PTE (1 << (HV_LOG2_PAGE_SIZE_LARGE - HV_LOG2_PAGE_SIZE_SMALL))
+#define SIZEOF_PTE      (PTRS_PER_PTE * sizeof(pte_t))
+
+/*
+ * Align the vmalloc area to an L2 page table, and leave a guard page
+ * at the beginning and end.  The vmalloc code also puts in an internal
+ * guard page between each allocation.
+ */
+#define _VMALLOC_END    HUGE_VMAP_BASE
+#define VMALLOC_END     (_VMALLOC_END - PAGE_SIZE)
+#define VMALLOC_START   (_VMALLOC_START + PAGE_SIZE)
+
+#define HUGE_VMAP_END   (HUGE_VMAP_BASE + PGDIR_SIZE)
+
+#ifndef __ASSEMBLY__
+
+/* We have no pud since we are a three-level page table. */
+#include <asm-generic/pgtable-nopud.h>
+
+static inline int pud_none(pud_t pud)
+{
+        return pud_val(pud) == 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+        return pud_val(pud) & _PAGE_PRESENT;
+}
+
+#define pmd_ERROR(e) \
+        pr_err("%s:%d: bad pmd 0x%016llx.\n", __FILE__, __LINE__, pmd_val(e))
+
+static inline void pud_clear(pud_t *pudp)
+{
+        __pte_clear(&pudp->pgd);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+        return ((pud_val(pud) & _PAGE_ALL) != _PAGE_TABLE);
+}
+
+/* Return the page-table frame number (ptfn) that a pud_t points at. */
+#define pud_ptfn(pud) hv_pte_get_ptfn((pud).pgd)
+
+/*
+ * A given kernel pud_t maps to a kernel pmd_t table at a specific
+ * virtual address.  Since kernel pmd_t tables can be aligned at
+ * sub-page granularity, this macro can return non-page-aligned
+ * pointers, despite its name.
+ */
+#define pud_page_vaddr(pud) \
+        (__va((phys_addr_t)pud_ptfn(pud) << HV_LOG2_PAGE_TABLE_ALIGN))
+
+/*
+ * A pud_t points to a pmd_t array.  Since we can have multiple per
+ * page, we don't have a one-to-one mapping of pud_t's to pages.
+ */
+#define pud_page(pud) pfn_to_page(HV_PTFN_TO_PFN(pud_ptfn(pud)))
+
+static inline unsigned long pud_index(unsigned long address)
+{
+        return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
+#define pmd_offset(pud, address) \
+        ((pmd_t *)pud_page_vaddr(*(pud)) + pmd_index(address))
+
+static inline void __set_pmd(pmd_t *pmdp, pmd_t pmdval)
+{
+        set_pte(pmdp, pmdval);
+}
+
+/* Create a pmd from a PTFN and pgprot. */
+static inline pmd_t ptfn_pmd(unsigned long ptfn, pgprot_t prot)
+{
+        return hv_pte_set_ptfn(prot, ptfn);
+}
+
+/* Return the page-table frame number (ptfn) that a pmd_t points at. */
+static inline unsigned long pmd_ptfn(pmd_t pmd)
+{
+        return hv_pte_get_ptfn(pmd);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+        __pte_clear(pmdp);
+}
+
+/* Normalize an address to having the correct high bits set. */
+#define pgd_addr_normalize pgd_addr_normalize
+static inline unsigned long pgd_addr_normalize(unsigned long addr)
+{
+        return ((long)addr << (CHIP_WORD_SIZE() - CHIP_VA_WIDTH())) >>
+                (CHIP_WORD_SIZE() - CHIP_VA_WIDTH());
+}
+
+/* We don't define any pgds for these addresses. */
+static inline int pgd_addr_invalid(unsigned long addr)
+{
+        return addr >= MEM_HV_START ||
+                (addr > MEM_LOW_END && addr < MEM_HIGH_START);
+}
+
+/*
+ * Use atomic instructions to provide atomicity against the hypervisor.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+                                            unsigned long addr, pte_t *ptep)
+{
+        return (__insn_fetchand(&ptep->val, ~HV_PTE_ACCESSED) >>
+                HV_PTE_INDEX_ACCESSED) & 0x1;
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+                                      unsigned long addr, pte_t *ptep)
+{
+        __insn_fetchand(&ptep->val, ~HV_PTE_WRITABLE);
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+                                       unsigned long addr, pte_t *ptep)
+{
+        return hv_pte(__insn_exch(&ptep->val, 0UL));
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_TILE_PGTABLE_64_H */
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index e6889474038a..34c1e01ffb5e 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -215,6 +215,8 @@ static inline void release_thread(struct task_struct *dead_task)
 
 extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
+extern int do_work_pending(struct pt_regs *regs, u32 flags);
+
 
 /*
  * Return saved (kernel) PC of a blocked thread.
@@ -255,10 +257,6 @@ static inline void cpu_relax(void)
         barrier();
 }
 
-struct siginfo;
-extern void arch_coredump_signal(struct siginfo *, struct pt_regs *);
-#define arch_coredump_signal arch_coredump_signal
-
 /* Info on this processor (see fs/proc/cpuinfo.c) */
 struct seq_operations;
 extern const struct seq_operations cpuinfo_op;
@@ -269,9 +267,6 @@ extern char chip_model[64];
 /* Data on which physical memory controller corresponds to which NUMA node. */
 extern int node_controller[];
 
-/* Do we dump information to the console when a user application crashes? */
-extern int show_crashinfo;
-
 #if CHIP_HAS_CBOX_HOME_MAP()
 /* Does the heap allocator return hash-for-home pages by default? */
 extern int hash_default;
diff --git a/arch/tile/include/asm/serial.h b/arch/tile/include/asm/serial.h
new file mode 100644
index 000000000000..a0cb0caff152
--- /dev/null
+++ b/arch/tile/include/asm/serial.h
@@ -0,0 +1 @@
+#include <asm-generic/serial.h>
diff --git a/arch/tile/include/asm/signal.h b/arch/tile/include/asm/signal.h
index 81d92a45cd4b..1e1e616783eb 100644
--- a/arch/tile/include/asm/signal.h
+++ b/arch/tile/include/asm/signal.h
@@ -28,6 +28,10 @@ struct pt_regs;
 int restore_sigcontext(struct pt_regs *, struct sigcontext __user *);
 int setup_sigcontext(struct sigcontext __user *, struct pt_regs *);
 void do_signal(struct pt_regs *regs);
+void signal_fault(const char *type, struct pt_regs *,
+                  void __user *frame, int sig);
+void trace_unhandled_signal(const char *type, struct pt_regs *regs,
+                            unsigned long address, int signo);
 #endif
 
 #endif /* _ASM_TILE_SIGNAL_H */
diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h
new file mode 100644
index 000000000000..72be5904e020
--- /dev/null
+++ b/arch/tile/include/asm/spinlock_64.h
@@ -0,0 +1,161 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * 64-bit SMP ticket spinlocks, allowing only a single CPU anywhere
+ * (the type definitions are in asm/spinlock_types.h)
+ */
+
+#ifndef _ASM_TILE_SPINLOCK_64_H
+#define _ASM_TILE_SPINLOCK_64_H
+
+/* Shifts and masks for the various fields in "lock". */
+#define __ARCH_SPIN_CURRENT_SHIFT       17
+#define __ARCH_SPIN_NEXT_MASK           0x7fff
+#define __ARCH_SPIN_NEXT_OVERFLOW       0x8000
+
+/*
+ * Return the "current" portion of a ticket lock value,
+ * i.e. the number that currently owns the lock.
+ */
+static inline int arch_spin_current(u32 val)
+{
+        return val >> __ARCH_SPIN_CURRENT_SHIFT;
+}
+
+/*
+ * Return the "next" portion of a ticket lock value,
+ * i.e. the number that the next task to try to acquire the lock will get.
+ */
+static inline int arch_spin_next(u32 val)
+{
+        return val & __ARCH_SPIN_NEXT_MASK;
+}
+
+/* The lock is locked if a task would have to wait to get it. */
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+        u32 val = lock->lock;
+        return arch_spin_current(val) != arch_spin_next(val);
+}
+
+/* Bump the current ticket so the next task owns the lock. */
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+        wmb();  /* guarantee anything modified under the lock is visible */
+        __insn_fetchadd4(&lock->lock, 1U << __ARCH_SPIN_CURRENT_SHIFT);
+}
+
+void arch_spin_unlock_wait(arch_spinlock_t *lock);
+
+void arch_spin_lock_slow(arch_spinlock_t *lock, u32 val);
+
+/* Grab the "next" ticket number and bump it atomically.
+ * If the current ticket is not ours, go to the slow path.
+ * We also take the slow path if the "next" value overflows.
+ */
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+        u32 val = __insn_fetchadd4(&lock->lock, 1);
+        u32 ticket = val & (__ARCH_SPIN_NEXT_MASK | __ARCH_SPIN_NEXT_OVERFLOW);
+        if (unlikely(arch_spin_current(val) != ticket))
+                arch_spin_lock_slow(lock, ticket);
+}
+
+/* Try to get the lock, and return whether we succeeded. */
+int arch_spin_trylock(arch_spinlock_t *lock);
+
+/* We cannot take an interrupt after getting a ticket, so don't enable them. */
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * We use fetchadd() for readers, and fetchor() with the sign bit
+ * for writers.
+ */
+
+#define __WRITE_LOCK_BIT (1 << 31)
+
+static inline int arch_write_val_locked(int val)
+{
+        return val < 0;  /* Optimize "val & __WRITE_LOCK_BIT". */
+}
+
+/**
+ * read_can_lock - would read_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static inline int arch_read_can_lock(arch_rwlock_t *rw)
+{
+        return !arch_write_val_locked(rw->lock);
+}
+
+/**
+ * write_can_lock - would write_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static inline int arch_write_can_lock(arch_rwlock_t *rw)
+{
+        return rw->lock == 0;
+}
+
+extern void __read_lock_failed(arch_rwlock_t *rw);
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+        u32 val = __insn_fetchaddgez4(&rw->lock, 1);
+        if (unlikely(arch_write_val_locked(val)))
+                __read_lock_failed(rw);
+}
+
+extern void __write_lock_failed(arch_rwlock_t *rw, u32 val);
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+        u32 val = __insn_fetchor4(&rw->lock, __WRITE_LOCK_BIT);
+        if (unlikely(val != 0))
+                __write_lock_failed(rw, val);
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+        __insn_mf();
+        __insn_fetchadd4(&rw->lock, -1);
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+        __insn_mf();
+        rw->lock = 0;
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+        return !arch_write_val_locked(__insn_fetchaddgez4(&rw->lock, 1));
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+        u32 val = __insn_fetchor4(&rw->lock, __WRITE_LOCK_BIT);
+        if (likely(val == 0))
+                return 1;
+        if (!arch_write_val_locked(val))
+                __insn_fetchand4(&rw->lock, ~__WRITE_LOCK_BIT);
+        return 0;
+}
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#endif /* _ASM_TILE_SPINLOCK_64_H */
diff --git a/arch/tile/include/asm/stat.h b/arch/tile/include/asm/stat.h
index b16e5db8f0e7..c0db34d56be3 100644
--- a/arch/tile/include/asm/stat.h
+++ b/arch/tile/include/asm/stat.h
@@ -1,4 +1,4 @@
-#ifdef CONFIG_COMPAT
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 #define __ARCH_WANT_STAT64      /* Used for compat_sys_stat64() etc. */
 #endif
 #include <asm-generic/stat.h>
diff --git a/arch/tile/include/asm/swab.h b/arch/tile/include/asm/swab.h
index 25c686a00f1d..7c37b38f6c8d 100644
--- a/arch/tile/include/asm/swab.h
+++ b/arch/tile/include/asm/swab.h
@@ -18,12 +18,6 @@
 /* Tile gcc is always >= 4.3.0, so we use __builtin_bswap. */
 #define __arch_swab32(x) __builtin_bswap32(x)
 #define __arch_swab64(x) __builtin_bswap64(x)
-
-/* Use the variant that is natural for the wordsize. */
-#ifdef CONFIG_64BIT
-#define __arch_swab16(x) (__builtin_bswap64(x) >> 48)
-#else
 #define __arch_swab16(x) (__builtin_bswap32(x) >> 16)
-#endif
 
 #endif /* _ASM_TILE_SWAB_H */
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 3405b52853b8..bc4f562bd459 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -125,6 +125,7 @@ extern void cpu_idle_on_new_stack(struct thread_info *old_ti,
 #define TIF_SYSCALL_AUDIT       5       /* syscall auditing active */
 #define TIF_SECCOMP             6       /* secure computing */
 #define TIF_MEMDIE              7       /* OOM killer at work */
+#define TIF_NOTIFY_RESUME       8       /* callback before returning to user */
 
 #define _TIF_SIGPENDING         (1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED       (1<<TIF_NEED_RESCHED)
@@ -134,10 +135,12 @@ extern void cpu_idle_on_new_stack(struct thread_info *old_ti,
 #define _TIF_SYSCALL_AUDIT      (1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP            (1<<TIF_SECCOMP)
 #define _TIF_MEMDIE             (1<<TIF_MEMDIE)
+#define _TIF_NOTIFY_RESUME      (1<<TIF_NOTIFY_RESUME)
 
 /* Work to do on any return to user space. */
 #define _TIF_ALLWORK_MASK \
-  (_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SINGLESTEP|_TIF_ASYNC_TLB)
+  (_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SINGLESTEP|\
+   _TIF_ASYNC_TLB|_TIF_NOTIFY_RESUME)
 
 /*
  * Thread-synchronous status.
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index 343172d422a9..6fdd0c860193 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -44,25 +44,64 @@ static inline const struct cpumask *cpumask_of_node(int node)
 /* For now, use numa node -1 for global allocation. */
 #define pcibus_to_node(bus)             ((void)(bus), -1)
 
+/*
+ * TILE architecture has many cores integrated in one processor, so we need
+ * setup bigger balance_interval for both CPU/NODE scheduling domains to
+ * reduce process scheduling costs.
+ */
+
+/* sched_domains SD_CPU_INIT for TILE architecture */
+#define SD_CPU_INIT (struct sched_domain) {                             \
+        .min_interval           = 4,                                    \
+        .max_interval           = 128,                                  \
+        .busy_factor            = 64,                                   \
+        .imbalance_pct          = 125,                                  \
+        .cache_nice_tries       = 1,                                    \
+        .busy_idx               = 2,                                    \
+        .idle_idx               = 1,                                    \
+        .newidle_idx            = 0,                                    \
+        .wake_idx               = 0,                                    \
+        .forkexec_idx           = 0,                                    \
+                                                                        \
+        .flags                  = 1*SD_LOAD_BALANCE                     \
+                                | 1*SD_BALANCE_NEWIDLE                  \
+                                | 1*SD_BALANCE_EXEC                     \
+                                | 1*SD_BALANCE_FORK                     \
+                                | 0*SD_BALANCE_WAKE                     \
+                                | 0*SD_WAKE_AFFINE                      \
+                                | 0*SD_PREFER_LOCAL                     \
+                                | 0*SD_SHARE_CPUPOWER                   \
+                                | 0*SD_SHARE_PKG_RESOURCES              \
+                                | 0*SD_SERIALIZE                        \
+                                ,                                       \
+        .last_balance           = jiffies,                              \
+        .balance_interval       = 32,                                   \
+}
+
 /* sched_domains SD_NODE_INIT for TILE architecture */
-#define SD_NODE_INIT (struct sched_domain) {            \
-        .min_interval           = 8,                    \
-        .max_interval           = 32,                   \
-        .busy_factor            = 32,                   \
-        .imbalance_pct          = 125,                  \
-        .cache_nice_tries       = 1,                    \
-        .busy_idx               = 3,                    \
-        .idle_idx               = 1,                    \
-        .newidle_idx            = 2,                    \
-        .wake_idx               = 1,                    \
-        .flags                  = SD_LOAD_BALANCE       \
-                                | SD_BALANCE_NEWIDLE    \
-                                | SD_BALANCE_EXEC       \
-                                | SD_BALANCE_FORK       \
-                                | SD_WAKE_AFFINE        \
-                                | SD_SERIALIZE,         \
-        .last_balance           = jiffies,              \
-        .balance_interval       = 1,                    \
+#define SD_NODE_INIT (struct sched_domain) {                            \
+        .min_interval           = 16,                                   \
+        .max_interval           = 512,                                  \
+        .busy_factor            = 32,                                   \
+        .imbalance_pct          = 125,                                  \
+        .cache_nice_tries       = 1,                                    \
+        .busy_idx               = 3,                                    \
+        .idle_idx               = 1,                                    \
+        .newidle_idx            = 2,                                    \
+        .wake_idx               = 1,                                    \
+        .flags                  = 1*SD_LOAD_BALANCE                     \
+                                | 1*SD_BALANCE_NEWIDLE                  \
+                                | 1*SD_BALANCE_EXEC                     \
+                                | 1*SD_BALANCE_FORK                     \
+                                | 0*SD_BALANCE_WAKE                     \
+                                | 0*SD_WAKE_AFFINE                      \
+                                | 0*SD_PREFER_LOCAL                     \
+                                | 0*SD_SHARE_CPUPOWER                   \
+                                | 0*SD_SHARE_PKG_RESOURCES              \
+                                | 1*SD_SERIALIZE                        \
+                                ,                                       \
+        .last_balance           = jiffies,                              \
+        .balance_interval       = 128,                                  \
 }
 
 /* By definition, we create nodes based on online memory. */
diff --git a/arch/tile/include/asm/traps.h b/arch/tile/include/asm/traps.h
index d06e35f57201..5f20f920f932 100644
--- a/arch/tile/include/asm/traps.h
+++ b/arch/tile/include/asm/traps.h
@@ -15,10 +15,14 @@
 #ifndef _ASM_TILE_TRAPS_H
 #define _ASM_TILE_TRAPS_H
 
+#include <arch/chip.h>
+
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *, int fault_num,
                    unsigned long address, unsigned long write);
+#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
 void do_async_page_fault(struct pt_regs *);
+#endif
 
 #ifndef __tilegx__
 /*
diff --git a/arch/tile/include/asm/unistd.h b/arch/tile/include/asm/unistd.h
index b35c2db71199..f70bf1c541f1 100644
--- a/arch/tile/include/asm/unistd.h
+++ b/arch/tile/include/asm/unistd.h
@@ -15,7 +15,7 @@
 #if !defined(_ASM_TILE_UNISTD_H) || defined(__SYSCALL)
 #define _ASM_TILE_UNISTD_H
 
-#ifndef __LP64__
+#if !defined(__LP64__) || defined(__SYSCALL_COMPAT)
 /* Use the flavor of this syscall that matches the 32-bit API better. */
 #define __ARCH_WANT_SYNC_FILE_RANGE2
 #endif
diff --git a/arch/tile/include/hv/pagesize.h b/arch/tile/include/asm/vga.h
index 58bed114fedd..7b46e754d611 100644
--- a/arch/tile/include/hv/pagesize.h
+++ b/arch/tile/include/asm/vga.h
@@ -10,23 +10,30 @@
  *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
  *   NON INFRINGEMENT.  See the GNU General Public License for
  *   more details.
+ *
+ * Access to VGA videoram.
  */
 
-/**
- * @file pagesize.h
- */
+#ifndef _ASM_TILE_VGA_H
+#define _ASM_TILE_VGA_H
 
-#ifndef _HV_PAGESIZE_H
-#define _HV_PAGESIZE_H
+#include <asm/io.h>
 
-/** The log2 of the size of small pages, in bytes. This value should
- * be verified at runtime by calling hv_sysconf(HV_SYSCONF_PAGE_SIZE_SMALL).
- */
-#define HV_LOG2_PAGE_SIZE_SMALL 16
+#define VT_BUF_HAVE_RW
 
-/** The log2 of the size of large pages, in bytes. This value should be
- * verified at runtime by calling hv_sysconf(HV_SYSCONF_PAGE_SIZE_LARGE).
- */
-#define HV_LOG2_PAGE_SIZE_LARGE 24
+static inline void scr_writew(u16 val, volatile u16 *addr)
+{
+        __raw_writew(val, (volatile u16 __iomem *) addr);
+}
+
+static inline u16 scr_readw(volatile const u16 *addr)
+{
+        return __raw_readw((volatile const u16 __iomem *) addr);
+}
+
+#define vga_readb(a)    readb((u8 __iomem *)(a))
+#define vga_writeb(v,a) writeb(v, (u8 __iomem *)(a))
+
+#define VGA_MAP_MEM(x,s)        ((unsigned long) ioremap(x, s))
 
-#endif /* _HV_PAGESIZE_H */
+#endif
diff --git a/arch/tile/include/hv/hypervisor.h b/arch/tile/include/hv/hypervisor.h
index ee41bca4c8c4..72ec1e972f15 100644
--- a/arch/tile/include/hv/hypervisor.h
+++ b/arch/tile/include/hv/hypervisor.h
@@ -22,8 +22,6 @@
 
 #include <arch/chip.h>
 
-#include <hv/pagesize.h>
-
 /* Linux builds want unsigned long constants, but assembler wants numbers */
 #ifdef __ASSEMBLER__
 /** One, for assembler */
@@ -44,11 +42,21 @@
  */
 #define HV_L1_SPAN (__HV_SIZE_ONE << HV_LOG2_L1_SPAN)
 
+/** The log2 of the size of small pages, in bytes. This value should
+ * be verified at runtime by calling hv_sysconf(HV_SYSCONF_PAGE_SIZE_SMALL).
+ */
+#define HV_LOG2_PAGE_SIZE_SMALL 16
+
 /** The size of small pages, in bytes. This value should be verified
  * at runtime by calling hv_sysconf(HV_SYSCONF_PAGE_SIZE_SMALL).
  */
 #define HV_PAGE_SIZE_SMALL (__HV_SIZE_ONE << HV_LOG2_PAGE_SIZE_SMALL)
 
+/** The log2 of the size of large pages, in bytes. This value should be
+ * verified at runtime by calling hv_sysconf(HV_SYSCONF_PAGE_SIZE_LARGE).
+ */
+#define HV_LOG2_PAGE_SIZE_LARGE 24
+
 /** The size of large pages, in bytes. This value should be verified
  * at runtime by calling hv_sysconf(HV_SYSCONF_PAGE_SIZE_LARGE).
  */
diff --git a/arch/tile/kernel/backtrace.c b/arch/tile/kernel/backtrace.c
index 55a6a74974b4..1dc71eabfc5a 100644
--- a/arch/tile/kernel/backtrace.c
+++ b/arch/tile/kernel/backtrace.c
@@ -14,19 +14,11 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-
 #include <asm/backtrace.h>
-
-#include <arch/chip.h>
-
 #include <asm/opcode-tile.h>
+#include <arch/abi.h>
 
-
-#define TREG_SP 54
-#define TREG_LR 55
-
-
-#if TILE_CHIP >= 10
+#ifdef __tilegx__
 #define tile_bundle_bits tilegx_bundle_bits
 #define TILE_MAX_INSTRUCTIONS_PER_BUNDLE TILEGX_MAX_INSTRUCTIONS_PER_BUNDLE
 #define TILE_BUNDLE_ALIGNMENT_IN_BYTES TILEGX_BUNDLE_ALIGNMENT_IN_BYTES
@@ -47,7 +39,7 @@ typedef long long bt_int_reg_t;
 typedef int bt_int_reg_t;
 #endif
 
-/** A decoded bundle used for backtracer analysis. */
+/* A decoded bundle used for backtracer analysis. */
 struct BacktraceBundle {
         tile_bundle_bits bits;
         int num_insns;
@@ -56,23 +48,7 @@ struct BacktraceBundle {
 };
 
 
-/* This implementation only makes sense for native tools. */
-/** Default function to read memory. */
-static bool bt_read_memory(void *result, VirtualAddress addr,
-                           unsigned int size, void *extra)
-{
-        /* FIXME: this should do some horrible signal stuff to catch
-         * SEGV cleanly and fail.
-         *
-         * Or else the caller should do the setjmp for efficiency.
-         */
-
-        memcpy(result, (const void *)addr, size);
-        return true;
-}
-
-
-/** Locates an instruction inside the given bundle that
+/* Locates an instruction inside the given bundle that
  * has the specified mnemonic, and whose first 'num_operands_to_match'
  * operands exactly match those in 'operand_values'.
  */
@@ -107,13 +83,13 @@ static const struct tile_decoded_instruction *find_matching_insn(
         return NULL;
 }
 
-/** Does this bundle contain an 'iret' instruction? */
+/* Does this bundle contain an 'iret' instruction? */
 static inline bool bt_has_iret(const struct BacktraceBundle *bundle)
 {
         return find_matching_insn(bundle, TILE_OPC_IRET, NULL, 0) != NULL;
 }
 
-/** Does this bundle contain an 'addi sp, sp, OFFSET' or
+/* Does this bundle contain an 'addi sp, sp, OFFSET' or
  * 'addli sp, sp, OFFSET' instruction, and if so, what is OFFSET?
  */
 static bool bt_has_addi_sp(const struct BacktraceBundle *bundle, int *adjust)
@@ -124,7 +100,7 @@ static bool bt_has_addi_sp(const struct BacktraceBundle *bundle, int *adjust)
                 find_matching_insn(bundle, TILE_OPC_ADDI, vals, 2);
         if (insn == NULL)
                 insn = find_matching_insn(bundle, TILE_OPC_ADDLI, vals, 2);
-#if TILE_CHIP >= 10
+#ifdef __tilegx__
         if (insn == NULL)
                 insn = find_matching_insn(bundle, TILEGX_OPC_ADDXLI, vals, 2);
         if (insn == NULL)
@@ -137,7 +113,7 @@ static bool bt_has_addi_sp(const struct BacktraceBundle *bundle, int *adjust)
         return true;
 }
 
-/** Does this bundle contain any 'info OP' or 'infol OP'
+/* Does this bundle contain any 'info OP' or 'infol OP'
  * instruction, and if so, what are their OP?  Note that OP is interpreted
  * as an unsigned value by this code since that's what the caller wants.
  * Returns the number of info ops found.
@@ -161,7 +137,7 @@ static int bt_get_info_ops(const struct BacktraceBundle *bundle,
         return num_ops;
 }
 
-/** Does this bundle contain a jrp instruction, and if so, to which
+/* Does this bundle contain a jrp instruction, and if so, to which
  * register is it jumping?
  */
 static bool bt_has_jrp(const struct BacktraceBundle *bundle, int *target_reg)
@@ -175,7 +151,7 @@ static bool bt_has_jrp(const struct BacktraceBundle *bundle, int *target_reg)
         return true;
 }
 
-/** Does this bundle modify the specified register in any way? */
+/* Does this bundle modify the specified register in any way? */
 static bool bt_modifies_reg(const struct BacktraceBundle *bundle, int reg)
 {
         int i, j;
@@ -195,34 +171,34 @@ static bool bt_modifies_reg(const struct BacktraceBundle *bundle, int reg)
         return false;
 }
 
-/** Does this bundle modify sp? */
+/* Does this bundle modify sp? */
 static inline bool bt_modifies_sp(const struct BacktraceBundle *bundle)
 {
         return bt_modifies_reg(bundle, TREG_SP);
 }
 
-/** Does this bundle modify lr? */
+/* Does this bundle modify lr? */
 static inline bool bt_modifies_lr(const struct BacktraceBundle *bundle)
 {
         return bt_modifies_reg(bundle, TREG_LR);
 }
 
-/** Does this bundle contain the instruction 'move fp, sp'? */
+/* Does this bundle contain the instruction 'move fp, sp'? */
 static inline bool bt_has_move_r52_sp(const struct BacktraceBundle *bundle)
 {
         static const int vals[2] = { 52, TREG_SP };
         return find_matching_insn(bundle, TILE_OPC_MOVE, vals, 2) != NULL;
 }
 
-/** Does this bundle contain a store of lr to sp? */
+/* Does this bundle contain a store of lr to sp? */
 static inline bool bt_has_sw_sp_lr(const struct BacktraceBundle *bundle)
 {
         static const int vals[2] = { TREG_SP, TREG_LR };
         return find_matching_insn(bundle, OPCODE_STORE, vals, 2) != NULL;
 }
 
-#if TILE_CHIP >= 10
-/** Track moveli values placed into registers. */
+#ifdef __tilegx__
+/* Track moveli values placed into registers. */
 static inline void bt_update_moveli(const struct BacktraceBundle *bundle,
                                     int moveli_args[])
 {
@@ -238,7 +214,7 @@ static inline void bt_update_moveli(const struct BacktraceBundle *bundle,
         }
 }
 
-/** Does this bundle contain an 'add sp, sp, reg' instruction
+/* Does this bundle contain an 'add sp, sp, reg' instruction
  * from a register that we saw a moveli into, and if so, what
  * is the value in the register?
  */
@@ -260,11 +236,11 @@ static bool bt_has_add_sp(const struct BacktraceBundle *bundle, int *adjust,
 }
 #endif
 
-/** Locates the caller's PC and SP for a program starting at the
+/* Locates the caller's PC and SP for a program starting at the
  * given address.
  */
 static void find_caller_pc_and_caller_sp(CallerLocation *location,
-                                         const VirtualAddress start_pc,
+                                         const unsigned long start_pc,
                                          BacktraceMemoryReader read_memory_func,
                                          void *read_memory_func_extra)
 {
@@ -288,9 +264,9 @@ static void find_caller_pc_and_caller_sp(CallerLocation *location,
         tile_bundle_bits prefetched_bundles[32];
         int num_bundles_prefetched = 0;
         int next_bundle = 0;
-        VirtualAddress pc;
+        unsigned long pc;
 
-#if TILE_CHIP >= 10
+#ifdef __tilegx__
         /* Naively try to track moveli values to support addx for -m32. */
         int moveli_args[TILEGX_NUM_REGISTERS] = { 0 };
 #endif
@@ -369,10 +345,6 @@ static void find_caller_pc_and_caller_sp(CallerLocation *location,
                                         /* Weird; reserved value, ignore it. */
                                         continue;
                                 }
-                                if (info_operand & ENTRY_POINT_INFO_OP) {
-                                        /* This info op is ignored by the backtracer. */
-                                        continue;
-                                }
 
                                 /* Skip info ops which are not in the
                                  * "one_ago" mode we want right now.
@@ -453,7 +425,7 @@ static void find_caller_pc_and_caller_sp(CallerLocation *location,
                 if (!sp_determined) {
                         int adjust;
                         if (bt_has_addi_sp(&bundle, &adjust)
-#if TILE_CHIP >= 10
+#ifdef __tilegx__
                             || bt_has_add_sp(&bundle, &adjust, moveli_args)
 #endif
                                 ) {
@@ -504,7 +476,7 @@ static void find_caller_pc_and_caller_sp(CallerLocation *location,
                                 }
                         }
 
-#if TILE_CHIP >= 10
+#ifdef __tilegx__
                         /* Track moveli arguments for -m32 mode. */
                         bt_update_moveli(&bundle, moveli_args);
 #endif
@@ -546,18 +518,26 @@ static void find_caller_pc_and_caller_sp(CallerLocation *location,
         }
 }
 
+/* Initializes a backtracer to start from the given location.
+ *
+ * If the frame pointer cannot be determined it is set to -1.
+ *
+ * state: The state to be filled in.
+ * read_memory_func: A callback that reads memory.
+ * read_memory_func_extra: An arbitrary argument to read_memory_func.
+ * pc: The current PC.
+ * lr: The current value of the 'lr' register.
+ * sp: The current value of the 'sp' register.
+ * r52: The current value of the 'r52' register.
+ */
 void backtrace_init(BacktraceIterator *state,
                     BacktraceMemoryReader read_memory_func,
                     void *read_memory_func_extra,
-                    VirtualAddress pc, VirtualAddress lr,
-                    VirtualAddress sp, VirtualAddress r52)
+                    unsigned long pc, unsigned long lr,
+                    unsigned long sp, unsigned long r52)
 {
         CallerLocation location;
-        VirtualAddress fp, initial_frame_caller_pc;
-
-        if (read_memory_func == NULL) {
-                read_memory_func = bt_read_memory;
-        }
+        unsigned long fp, initial_frame_caller_pc;
 
         /* Find out where we are in the initial frame. */
         find_caller_pc_and_caller_sp(&location, pc,
@@ -630,12 +610,15 @@ void backtrace_init(BacktraceIterator *state,
 /* Handle the case where the register holds more bits than the VA. */
 static bool valid_addr_reg(bt_int_reg_t reg)
 {
-        return ((VirtualAddress)reg == reg);
+        return ((unsigned long)reg == reg);
 }
 
+/* Advances the backtracing state to the calling frame, returning
+ * true iff successful.
+ */
 bool backtrace_next(BacktraceIterator *state)
 {
-        VirtualAddress next_fp, next_pc;
+        unsigned long next_fp, next_pc;
         bt_int_reg_t next_frame[2];
 
         if (state->fp == -1) {
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index dbc213adf5e1..bf5e9d70266c 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -135,26 +135,15 @@ long tile_compat_sys_msgrcv(int msqid,
 
 /* Provide the compat syscall number to call mapping. */
 #undef __SYSCALL
-#define __SYSCALL(nr, call) [nr] = (compat_##call),
+#define __SYSCALL(nr, call) [nr] = (call),
 
 /* The generic versions of these don't work for Tile. */
 #define compat_sys_msgrcv tile_compat_sys_msgrcv
 #define compat_sys_msgsnd tile_compat_sys_msgsnd
 
 /* See comments in sys.c */
-#define compat_sys_fadvise64 sys32_fadvise64
 #define compat_sys_fadvise64_64 sys32_fadvise64_64
 #define compat_sys_readahead sys32_readahead
-#define compat_sys_sync_file_range compat_sys_sync_file_range2
-
-/* We leverage the "struct stat64" type for 32-bit time_t/nsec. */
-#define compat_sys_stat64 sys_stat64
-#define compat_sys_lstat64 sys_lstat64
-#define compat_sys_fstat64 sys_fstat64
-#define compat_sys_fstatat64 sys_fstatat64
-
-/* The native sys_ptrace dynamically handles compat binaries. */
-#define compat_sys_ptrace sys_ptrace
 
 /* Call the trampolines to manage pt_regs where necessary. */
 #define compat_sys_execve _compat_sys_execve
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index dbb0dfc7bece..a7869ad62776 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -317,7 +317,7 @@ long compat_sys_rt_sigreturn(struct pt_regs *regs)
         return 0;
 
 badframe:
-        force_sig(SIGSEGV, current);
+        signal_fault("bad sigreturn frame", regs, frame, 0);
         return 0;
 }
 
@@ -431,6 +431,6 @@ int compat_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         return 0;
 
 give_sigsegv:
-        force_sigsegv(sig, current);
+        signal_fault("bad setup frame", regs, frame, sig);
         return -EFAULT;
 }
diff --git a/arch/tile/kernel/futex_64.S b/arch/tile/kernel/futex_64.S
new file mode 100644
index 000000000000..f465d1eda20f
--- /dev/null
+++ b/arch/tile/kernel/futex_64.S
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * Atomically access user memory, but use MMU to avoid propagating
+ * kernel exceptions.
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/futex.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+
+/*
+ * Provide a set of atomic memory operations supporting <asm/futex.h>.
+ *
+ * r0: user address to manipulate
+ * r1: new value to write, or for cmpxchg, old value to compare against
+ * r2: (cmpxchg only) new value to write
+ *
+ * Return __get_user struct, r0 with value, r1 with error.
+ */
+#define FUTEX_OP(name, ...) \
+STD_ENTRY(futex_##name)                 \
+        __VA_ARGS__;                    \
+        {                               \
+         move   r1, zero;               \
+         jrp    lr                      \
+        };                              \
+        STD_ENDPROC(futex_##name);      \
+        .pushsection __ex_table,"a";    \
+        .quad 1b, get_user_fault;       \
+        .popsection
+
+        .pushsection .fixup,"ax"
+get_user_fault:
+        { movei r1, -EFAULT; jrp lr }
+        ENDPROC(get_user_fault)
+        .popsection
+
+FUTEX_OP(cmpxchg, mtspr CMPEXCH_VALUE, r1; 1: cmpexch4 r0, r0, r2)
+FUTEX_OP(set, 1: exch4 r0, r0, r1)
+FUTEX_OP(add, 1: fetchadd4 r0, r0, r1)
+FUTEX_OP(or, 1: fetchor4 r0, r0, r1)
+FUTEX_OP(andn, nor r1, r1, zero; 1: fetchand4 r0, r0, r1)
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index e910530436e6..3bddef710de4 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -268,12 +268,10 @@ void __kprobes do_hardwall_trap(struct pt_regs* regs, int fault_num)
         found_processes = 0;
         list_for_each_entry(p, &rect->task_head, thread.hardwall_list) {
                 BUG_ON(p->thread.hardwall != rect);
-                if (p->sighand) {
+                if (!(p->flags & PF_EXITING)) {
                         found_processes = 1;
                         pr_notice("hardwall: killing %d\n", p->pid);
-                        spin_lock(&p->sighand->siglock);
-                        __group_send_sig_info(info.si_signo, &info, p);
-                        spin_unlock(&p->sighand->siglock);
+                        do_send_sig_info(info.si_signo, &info, p, false);
                 }
         }
         if (!found_processes)
diff --git a/arch/tile/kernel/head_64.S b/arch/tile/kernel/head_64.S
new file mode 100644
index 000000000000..6bc3a932fe45
--- /dev/null
+++ b/arch/tile/kernel/head_64.S
@@ -0,0 +1,269 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * TILE startup code.
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/thread_info.h>
+#include <asm/processor.h>
+#include <asm/asm-offsets.h>
+#include <hv/hypervisor.h>
+#include <arch/chip.h>
+#include <arch/spr_def.h>
+
+/*
+ * This module contains the entry code for kernel images. It performs the
+ * minimal setup needed to call the generic C routines.
+ */
+
+        __HEAD
+ENTRY(_start)
+        /* Notify the hypervisor of what version of the API we want */
+        {
+          movei r1, TILE_CHIP
+          movei r2, TILE_CHIP_REV
+        }
+        {
+          moveli r0, _HV_VERSION
+          jal hv_init
+        }
+        /* Get a reasonable default ASID in r0 */
+        {
+          move r0, zero
+          jal hv_inquire_asid
+        }
+
+        /*
+         * Install the default page table.  The relocation required to
+         * statically define the table is a bit too complex, so we have
+         * to plug in the pointer from the L0 to the L1 table by hand.
+         * We only do this on the first cpu to boot, though, since the
+         * other CPUs should see a properly-constructed page table.
+         */
+        {
+          v4int_l r2, zero, r0    /* ASID for hv_install_context */
+          moveli r4, hw1_last(swapper_pgprot - PAGE_OFFSET)
+        }
+        {
+          shl16insli r4, r4, hw0(swapper_pgprot - PAGE_OFFSET)
+        }
+        {
+          ld r1, r4               /* access_pte for hv_install_context */
+        }
+        {
+          moveli r0, hw1_last(.Lsv_data_pmd - PAGE_OFFSET)
+          moveli r6, hw1_last(temp_data_pmd - PAGE_OFFSET)
+        }
+        {
+          /* After initializing swapper_pgprot, HV_PTE_GLOBAL is set. */
+          bfextu r7, r1, HV_PTE_INDEX_GLOBAL, HV_PTE_INDEX_GLOBAL
+          inv r4
+        }
+        bnez r7, .Lno_write
+        {
+          shl16insli r0, r0, hw0(.Lsv_data_pmd - PAGE_OFFSET)
+          shl16insli r6, r6, hw0(temp_data_pmd - PAGE_OFFSET)
+        }
+        {
+          /* Cut off the low bits of the PT address. */
+          shrui r6, r6, HV_LOG2_PAGE_TABLE_ALIGN
+          /* Start with our access pte. */
+          move r5, r1
+        }
+        {
+          /* Stuff the address into the page table pointer slot of the PTE. */
+          bfins r5, r6, HV_PTE_INDEX_PTFN, \
+                        HV_PTE_INDEX_PTFN + HV_PTE_PTFN_BITS - 1
+        }
+        {
+          /* Store the L0 data PTE. */
+          st r0, r5
+          addli r6, r6, (temp_code_pmd - temp_data_pmd) >> \
+                        HV_LOG2_PAGE_TABLE_ALIGN
+        }
+        {
+          addli r0, r0, .Lsv_code_pmd - .Lsv_data_pmd
+          bfins r5, r6, HV_PTE_INDEX_PTFN, \
+                        HV_PTE_INDEX_PTFN + HV_PTE_PTFN_BITS - 1
+        }
+        /* Store the L0 code PTE. */
+        st r0, r5
+
+.Lno_write:
+        moveli lr, hw2_last(1f)
+        {
+          shl16insli lr, lr, hw1(1f)
+          moveli r0, hw1_last(swapper_pg_dir - PAGE_OFFSET)
+        }
+        {
+          shl16insli lr, lr, hw0(1f)
+          shl16insli r0, r0, hw0(swapper_pg_dir - PAGE_OFFSET)
+        }
+        {
+          move r3, zero
+          j hv_install_context
+        }
+1:
+
+        /* Install the interrupt base. */
+        moveli r0, hw2_last(MEM_SV_START)
+        shl16insli r0, r0, hw1(MEM_SV_START)
+        shl16insli r0, r0, hw0(MEM_SV_START)
+        mtspr SPR_INTERRUPT_VECTOR_BASE_K, r0
+
+        /*
+         * Get our processor number and save it away in SAVE_K_0.
+         * Extract stuff from the topology structure: r4 = y, r6 = x,
+         * r5 = width.  FIXME: consider whether we want to just make these
+         * 64-bit values (and if so fix smp_topology write below, too).
+         */
+        jal hv_inquire_topology
+        {
+          v4int_l r5, zero, r1    /* r5 = width */
+          shrui r4, r0, 32        /* r4 = y */
+        }
+        {
+          v4int_l r6, zero, r0    /* r6 = x */
+          mul_lu_lu r4, r4, r5
+        }
+        {
+          add r4, r4, r6          /* r4 == cpu == y*width + x */
+        }
+
+#ifdef CONFIG_SMP
+        /*
+         * Load up our per-cpu offset.  When the first (master) tile
+         * boots, this value is still zero, so we will load boot_pc
+         * with start_kernel, and boot_sp with init_stack + THREAD_SIZE.
+         * The master tile initializes the per-cpu offset array, so that
+         * when subsequent (secondary) tiles boot, they will instead load
+         * from their per-cpu versions of boot_sp and boot_pc.
+         */
+        moveli r5, hw2_last(__per_cpu_offset)
+        shl16insli r5, r5, hw1(__per_cpu_offset)
+        shl16insli r5, r5, hw0(__per_cpu_offset)
+        shl3add r5, r4, r5
+        ld r5, r5
+        bnez r5, 1f
+
+        /*
+         * Save the width and height to the smp_topology variable
+         * for later use.
+         */
+        moveli r0, hw2_last(smp_topology + HV_TOPOLOGY_WIDTH_OFFSET)
+        shl16insli r0, r0, hw1(smp_topology + HV_TOPOLOGY_WIDTH_OFFSET)
+        shl16insli r0, r0, hw0(smp_topology + HV_TOPOLOGY_WIDTH_OFFSET)
+        st r0, r1
+1:
+#else
+        move r5, zero
+#endif
+
+        /* Load and go with the correct pc and sp. */
+        {
+          moveli r1, hw2_last(boot_sp)
+          moveli r0, hw2_last(boot_pc)
+        }
+        {
+          shl16insli r1, r1, hw1(boot_sp)
+          shl16insli r0, r0, hw1(boot_pc)
+        }
+        {
+          shl16insli r1, r1, hw0(boot_sp)
+          shl16insli r0, r0, hw0(boot_pc)
+        }
+        {
+          add r1, r1, r5
+          add r0, r0, r5
+        }
+        ld r0, r0
+        ld sp, r1
+        or r4, sp, r4
+        mtspr SPR_SYSTEM_SAVE_K_0, r4  /* save ksp0 + cpu */
+        addi sp, sp, -STACK_TOP_DELTA
+        {
+          move lr, zero   /* stop backtraces in the called function */
+          jr r0
+        }
+        ENDPROC(_start)
+
+__PAGE_ALIGNED_BSS
+        .align PAGE_SIZE
+ENTRY(empty_zero_page)
+        .fill PAGE_SIZE,1,0
+        END(empty_zero_page)
+
+        .macro PTE cpa, bits1
+        .quad HV_PTE_PAGE | HV_PTE_DIRTY | HV_PTE_PRESENT | HV_PTE_ACCESSED |\
+              HV_PTE_GLOBAL | (HV_PTE_MODE_CACHE_NO_L3 << HV_PTE_INDEX_MODE) |\
+              (\bits1) | (HV_CPA_TO_PFN(\cpa) << HV_PTE_INDEX_PFN)
+        .endm
+
+__PAGE_ALIGNED_DATA
+        .align PAGE_SIZE
+ENTRY(swapper_pg_dir)
+        .org swapper_pg_dir + HV_L0_INDEX(PAGE_OFFSET) * HV_PTE_SIZE
+.Lsv_data_pmd:
+        .quad 0  /* PTE temp_data_pmd - PAGE_OFFSET, 0 */
+        .org swapper_pg_dir + HV_L0_INDEX(MEM_SV_START) * HV_PTE_SIZE
+.Lsv_code_pmd:
+        .quad 0  /* PTE temp_code_pmd - PAGE_OFFSET, 0 */
+        .org swapper_pg_dir + HV_L0_SIZE
+        END(swapper_pg_dir)
+
+        .align HV_PAGE_TABLE_ALIGN
+ENTRY(temp_data_pmd)
+        /*
+         * We fill the PAGE_OFFSET pmd with huge pages with
+         * VA = PA + PAGE_OFFSET.  We remap things with more precise access
+         * permissions later.
+         */
+        .set addr, 0
+        .rept HV_L1_ENTRIES
+        PTE addr, HV_PTE_READABLE | HV_PTE_WRITABLE
+        .set addr, addr + HV_PAGE_SIZE_LARGE
+        .endr
+        .org temp_data_pmd + HV_L1_SIZE
+        END(temp_data_pmd)
+
+        .align HV_PAGE_TABLE_ALIGN
+ENTRY(temp_code_pmd)
+        /*
+         * We fill the MEM_SV_START pmd with huge pages with
+         * VA = PA + PAGE_OFFSET.  We remap things with more precise access
+         * permissions later.
+         */
+        .set addr, 0
+        .rept HV_L1_ENTRIES
+        PTE addr, HV_PTE_READABLE | HV_PTE_EXECUTABLE
+        .set addr, addr + HV_PAGE_SIZE_LARGE
+        .endr
+        .org temp_code_pmd + HV_L1_SIZE
+        END(temp_code_pmd)
+
+        /*
+         * Isolate swapper_pgprot to its own cache line, since each cpu
+         * starting up will read it using VA-is-PA and local homing.
+         * This would otherwise likely conflict with other data on the cache
+         * line, once we have set its permanent home in the page tables.
+         */
+        __INITDATA
+        .align CHIP_L2_LINE_SIZE()
+ENTRY(swapper_pgprot)
+        .quad HV_PTE_PRESENT | (HV_PTE_MODE_CACHE_NO_L3 << HV_PTE_INDEX_MODE)
+        .align CHIP_L2_LINE_SIZE()
+        END(swapper_pgprot)
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index fffcfa6b3a62..72ade79b621b 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -851,14 +851,27 @@ STD_ENTRY(interrupt_return)
         /* Check to see if there is any work to do before returning to user. */
         {
          addi   r29, r32, THREAD_INFO_FLAGS_OFFSET
-         moveli r28, lo16(_TIF_ALLWORK_MASK)
+         moveli r1, lo16(_TIF_ALLWORK_MASK)
         }
         {
          lw     r29, r29
-         auli   r28, r28, ha16(_TIF_ALLWORK_MASK)
+         auli   r1, r1, ha16(_TIF_ALLWORK_MASK)
         }
-        and     r28, r29, r28
-        bnz     r28, .Lwork_pending
+        and     r1, r29, r1
+        bzt     r1, .Lrestore_all
+
+        /*
+         * Make sure we have all the registers saved for signal
+         * handling or single-step.  Call out to C code to figure out
+         * exactly what we need to do for each flag bit, then if
+         * necessary, reload the flags and recheck.
+         */
+        push_extra_callee_saves r0
+        {
+         PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
+         jal    do_work_pending
+        }
+        bnz     r0, .Lresume_userspace
 
         /*
          * In the NMI case we
@@ -1099,99 +1112,6 @@ STD_ENTRY(interrupt_return)
         pop_reg r50
         pop_reg r51, sp, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(51)
         j .Lcontinue_restore_regs
-
-.Lwork_pending:
-        /* Mask the reschedule flag */
-        andi    r28, r29, _TIF_NEED_RESCHED
-
-        {
-         /*
-          * If the NEED_RESCHED flag is called, we call schedule(), which
-          * may drop this context right here and go do something else.
-          * On return, jump back to .Lresume_userspace and recheck.
-          */
-         bz     r28, .Lasync_tlb
-
-         /* Mask the async-tlb flag */
-         andi   r28, r29, _TIF_ASYNC_TLB
-        }
-
-        jal     schedule
-        FEEDBACK_REENTER(interrupt_return)
-
-        /* Reload the flags and check again */
-        j       .Lresume_userspace
-
-.Lasync_tlb:
-        {
-         bz     r28, .Lneed_sigpending
-
-         /* Mask the sigpending flag */
-         andi   r28, r29, _TIF_SIGPENDING
-        }
-
-        PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
-        jal     do_async_page_fault
-        FEEDBACK_REENTER(interrupt_return)
-
-        /*
-         * Go restart the "resume userspace" process.  We may have
-         * fired a signal, and we need to disable interrupts again.
-         */
-        j       .Lresume_userspace
-
-.Lneed_sigpending:
-        /*
-         * At this point we are either doing signal handling or single-step,
-         * so either way make sure we have all the registers saved.
-         */
-        push_extra_callee_saves r0
-
-        {
-         /* If no signal pending, skip to singlestep check */
-         bz     r28, .Lneed_singlestep
-
-         /* Mask the singlestep flag */
-         andi   r28, r29, _TIF_SINGLESTEP
-        }
-
-        jal     do_signal
-        FEEDBACK_REENTER(interrupt_return)
-
-        /* Reload the flags and check again */
-        j       .Lresume_userspace
-
-.Lneed_singlestep:
-        {
-         /* Get a pointer to the EX1 field */
-         PTREGS_PTR(r29, PTREGS_OFFSET_EX1)
-
-         /* If we get here, our bit must be set. */
-         bz     r28, .Lwork_confusion
-        }
-        /* If we are in priv mode, don't single step */
-        lw      r28, r29
-        andi    r28, r28, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
-        bnz     r28, .Lrestore_all
-
-        /* Allow interrupts within the single step code */
-        TRACE_IRQS_ON  /* Note: clobbers registers r0-r29 */
-        IRQ_ENABLE(r20, r21)
-
-        /* try to single-step the current instruction */
-        PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
-        jal     single_step_once
-        FEEDBACK_REENTER(interrupt_return)
-
-        /* Re-disable interrupts.  TRACE_IRQS_OFF in .Lrestore_all. */
-        IRQ_DISABLE(r20,r21)
-
-        j       .Lrestore_all
-
-.Lwork_confusion:
-        move    r0, r28
-        panic   "thread_info allwork flags unhandled on userspace resume: %#x"
-
         STD_ENDPROC(interrupt_return)
 
         /*
@@ -1550,7 +1470,10 @@ STD_ENTRY(_sys_clone)
  * We place it in the __HEAD section to ensure it is relatively
  * near to the intvec_SWINT_1 code (reachable by a conditional branch).
  *
- * Must match register usage in do_page_fault().
+ * Our use of ATOMIC_LOCK_REG here must match do_page_fault_ics().
+ *
+ * As we do in lib/atomic_asm_32.S, we bypass a store if the value we
+ * would store is the same as the value we just loaded.
  */
         __HEAD
         .align 64
@@ -1611,17 +1534,7 @@ ENTRY(sys_cmpxchg)
         {
          shri   r20, r25, 32 - ATOMIC_HASH_L1_SHIFT
          slt_u  r23, r0, r23
-
-         /*
-          * Ensure that the TLB is loaded before we take out the lock.
-          * On TILEPro, this will start fetching the value all the way
-          * into our L1 as well (and if it gets modified before we
-          * grab the lock, it will be invalidated from our cache
-          * before we reload it).  On tile64, we'll start fetching it
-          * into our L1 if we're the home, and if we're not, we'll
-          * still at least start fetching it into the home's L2.
-          */
-         lw     r26, r0
+         lw     r26, r0  /* see comment in the "#else" for the "lw r26". */
         }
         {
          s2a    r21, r20, r21
@@ -1637,18 +1550,9 @@ ENTRY(sys_cmpxchg)
          bbs    r23, .Lcmpxchg64
          andi   r23, r0, 7       /* Precompute alignment for cmpxchg64. */
         }
-
         {
-         /*
-          * We very carefully align the code that actually runs with
-          * the lock held (nine bundles) so that we know it is all in
-          * the icache when we start.  This instruction (the jump) is
-          * at the start of the first cache line, address zero mod 64;
-          * we jump to somewhere in the second cache line to issue the
-          * tns, then jump back to finish up.
-          */
          s2a    ATOMIC_LOCK_REG_NAME, r25, r21
-         j      .Lcmpxchg32_tns
+         j      .Lcmpxchg32_tns   /* see comment in the #else for the jump. */
         }
 
 #else /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
@@ -1713,24 +1617,25 @@ ENTRY(sys_cmpxchg)
         {
          /*
           * We very carefully align the code that actually runs with
-          * the lock held (nine bundles) so that we know it is all in
+          * the lock held (twelve bundles) so that we know it is all in
           * the icache when we start.  This instruction (the jump) is
           * at the start of the first cache line, address zero mod 64;
-          * we jump to somewhere in the second cache line to issue the
-          * tns, then jump back to finish up.
+          * we jump to the very end of the second cache line to get that
+          * line loaded in the icache, then fall through to issue the tns
+          * in the third cache line, at which point it's all cached.
+          * Note that is for performance, not correctness.
           */
          j      .Lcmpxchg32_tns
         }
 
 #endif /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
 
-        ENTRY(__sys_cmpxchg_grab_lock)
+/* Symbol for do_page_fault_ics() to use to compare against the PC. */
+.global __sys_cmpxchg_grab_lock
+__sys_cmpxchg_grab_lock:
 
         /*
          * Perform the actual cmpxchg or atomic_update.
-         * Note that the system <arch/atomic.h> header relies on
-         * atomic_update() to always perform an "mf", so don't make
-         * it optional or conditional without modifying that code.
          */
 .Ldo_cmpxchg32:
         {
@@ -1748,10 +1653,13 @@ ENTRY(sys_cmpxchg)
         }
         {
          mvnz   r24, r23, r25    /* Use atomic_update value if appropriate. */
-         bbns   r22, .Lcmpxchg32_mismatch
+         bbns   r22, .Lcmpxchg32_nostore
         }
+        seq     r22, r24, r21    /* Are we storing the value we loaded? */
+        bbs     r22, .Lcmpxchg32_nostore
         sw      r0, r24
 
+        /* The following instruction is the start of the second cache line. */
         /* Do slow mtspr here so the following "mf" waits less. */
         {
          move   sp, r27
@@ -1759,7 +1667,6 @@ ENTRY(sys_cmpxchg)
         }
         mf
 
-        /* The following instruction is the start of the second cache line. */
         {
          move   r0, r21
          sw     ATOMIC_LOCK_REG_NAME, zero
@@ -1767,7 +1674,7 @@ ENTRY(sys_cmpxchg)
         iret
 
         /* Duplicated code here in the case where we don't overlap "mf" */
-.Lcmpxchg32_mismatch:
+.Lcmpxchg32_nostore:
         {
          move   r0, r21
          sw     ATOMIC_LOCK_REG_NAME, zero
@@ -1783,8 +1690,6 @@ ENTRY(sys_cmpxchg)
          * and for 64-bit cmpxchg.  We provide it as a macro and put
          * it into both versions.  We can't share the code literally
          * since it depends on having the right branch-back address.
-         * Note that the first few instructions should share the cache
-         * line with the second half of the actual locked code.
          */
         .macro  cmpxchg_lock, bitwidth
 
@@ -1810,7 +1715,7 @@ ENTRY(sys_cmpxchg)
         }
         /*
          * The preceding instruction is the last thing that must be
-         * on the second cache line.
+         * hot in the icache before we do the "tns" above.
          */
 
 #ifdef CONFIG_SMP
@@ -1841,6 +1746,12 @@ ENTRY(sys_cmpxchg)
         .endm
 
 .Lcmpxchg32_tns:
+        /*
+         * This is the last instruction on the second cache line.
+         * The nop here loads the second line, then we fall through
+         * to the tns to load the third line before we take the lock.
+         */
+        nop
         cmpxchg_lock 32
 
         /*
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
new file mode 100644
index 000000000000..79c93e10ba27
--- /dev/null
+++ b/arch/tile/kernel/intvec_64.S
@@ -0,0 +1,1231 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * Linux interrupt vectors.
+ */
+
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <asm/ptrace.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/asm-offsets.h>
+#include <asm/types.h>
+#include <hv/hypervisor.h>
+#include <arch/abi.h>
+#include <arch/interrupts.h>
+#include <arch/spr_def.h>
+
+#ifdef CONFIG_PREEMPT
+# error "No support for kernel preemption currently"
+#endif
+
+#define PTREGS_PTR(reg, ptreg) addli reg, sp, C_ABI_SAVE_AREA_SIZE + (ptreg)
+
+#define PTREGS_OFFSET_SYSCALL PTREGS_OFFSET_REG(TREG_SYSCALL_NR)
+
+
+        .macro  push_reg reg, ptr=sp, delta=-8
+        {
+         st     \ptr, \reg
+         addli  \ptr, \ptr, \delta
+        }
+        .endm
+
+        .macro  pop_reg reg, ptr=sp, delta=8
+        {
+         ld     \reg, \ptr
+         addli  \ptr, \ptr, \delta
+        }
+        .endm
+
+        .macro  pop_reg_zero reg, zreg, ptr=sp, delta=8
+        {
+         move   \zreg, zero
+         ld     \reg, \ptr
+         addi   \ptr, \ptr, \delta
+        }
+        .endm
+
+        .macro  push_extra_callee_saves reg
+        PTREGS_PTR(\reg, PTREGS_OFFSET_REG(51))
+        push_reg r51, \reg
+        push_reg r50, \reg
+        push_reg r49, \reg
+        push_reg r48, \reg
+        push_reg r47, \reg
+        push_reg r46, \reg
+        push_reg r45, \reg
+        push_reg r44, \reg
+        push_reg r43, \reg
+        push_reg r42, \reg
+        push_reg r41, \reg
+        push_reg r40, \reg
+        push_reg r39, \reg
+        push_reg r38, \reg
+        push_reg r37, \reg
+        push_reg r36, \reg
+        push_reg r35, \reg
+        push_reg r34, \reg, PTREGS_OFFSET_BASE - PTREGS_OFFSET_REG(34)
+        .endm
+
+        .macro  panic str
+        .pushsection .rodata, "a"
+1:
+        .asciz  "\str"
+        .popsection
+        {
+         moveli r0, hw2_last(1b)
+        }
+        {
+         shl16insli r0, r0, hw1(1b)
+        }
+        {
+         shl16insli r0, r0, hw0(1b)
+         jal    panic
+        }
+        .endm
+
+
+#ifdef __COLLECT_LINKER_FEEDBACK__
+        .pushsection .text.intvec_feedback,"ax"
+intvec_feedback:
+        .popsection
+#endif
+
+        /*
+         * Default interrupt handler.
+         *
+         * vecnum is where we'll put this code.
+         * c_routine is the C routine we'll call.
+         *
+         * The C routine is passed two arguments:
+         * - A pointer to the pt_regs state.
+         * - The interrupt vector number.
+         *
+         * The "processing" argument specifies the code for processing
+         * the interrupt. Defaults to "handle_interrupt".
+         */
+        .macro  int_hand vecnum, vecname, c_routine, processing=handle_interrupt
+        .org    (\vecnum << 8)
+intvec_\vecname:
+        /* Temporarily save a register so we have somewhere to work. */
+
+        mtspr   SPR_SYSTEM_SAVE_K_1, r0
+        mfspr   r0, SPR_EX_CONTEXT_K_1
+
+        andi    r0, r0, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+
+        .ifc    \vecnum, INT_DOUBLE_FAULT
+        /*
+         * For double-faults from user-space, fall through to the normal
+         * register save and stack setup path.  Otherwise, it's the
+         * hypervisor giving us one last chance to dump diagnostics, and we
+         * branch to the kernel_double_fault routine to do so.
+         */
+        beqz    r0, 1f
+        j       _kernel_double_fault
+1:
+        .else
+        /*
+         * If we're coming from user-space, then set sp to the top of
+         * the kernel stack.  Otherwise, assume sp is already valid.
+         */
+        {
+         bnez   r0, 0f
+         move   r0, sp
+        }
+        .endif
+
+        .ifc    \c_routine, do_page_fault
+        /*
+         * The page_fault handler may be downcalled directly by the
+         * hypervisor even when Linux is running and has ICS set.
+         *
+         * In this case the contents of EX_CONTEXT_K_1 reflect the
+         * previous fault and can't be relied on to choose whether or
+         * not to reinitialize the stack pointer.  So we add a test
+         * to see whether SYSTEM_SAVE_K_2 has the high bit set,
+         * and if so we don't reinitialize sp, since we must be coming
+         * from Linux.  (In fact the precise case is !(val & ~1),
+         * but any Linux PC has to have the high bit set.)
+         *
+         * Note that the hypervisor *always* sets SYSTEM_SAVE_K_2 for
+         * any path that turns into a downcall to one of our TLB handlers.
+         *
+         * FIXME: if we end up never using this path, perhaps we should
+         * prevent the hypervisor from generating downcalls in this case.
+         * The advantage of getting a downcall is we can panic in Linux.
+         */
+        mfspr   r0, SPR_SYSTEM_SAVE_K_2
+        {
+         bltz   r0, 0f    /* high bit in S_S_1_2 is for a PC to use */
+         move   r0, sp
+        }
+        .endif
+
+
+        /*
+         * SYSTEM_SAVE_K_0 holds the cpu number in the low bits, and
+         * the current stack top in the higher bits.  So we recover
+         * our stack top by just masking off the low bits, then
+         * point sp at the top aligned address on the actual stack page.
+         */
+        mfspr   r0, SPR_SYSTEM_SAVE_K_0
+        mm      r0, zero, LOG2_THREAD_SIZE, 63
+
+0:
+        /*
+         * Align the stack mod 64 so we can properly predict what
+         * cache lines we need to write-hint to reduce memory fetch
+         * latency as we enter the kernel.  The layout of memory is
+         * as follows, with cache line 0 at the lowest VA, and cache
+         * line 8 just below the r0 value this "andi" computes.
+         * Note that we never write to cache line 8, and we skip
+         * cache lines 1-3 for syscalls.
+         *
+         *    cache line 8: ptregs padding (two words)
+         *    cache line 7: sp, lr, pc, ex1, faultnum, orig_r0, flags, cmpexch
+         *    cache line 6: r46...r53 (tp)
+         *    cache line 5: r38...r45
+         *    cache line 4: r30...r37
+         *    cache line 3: r22...r29
+         *    cache line 2: r14...r21
+         *    cache line 1: r6...r13
+         *    cache line 0: 2 x frame, r0..r5
+         */
+        andi    r0, r0, -64
+
+        /*
+         * Push the first four registers on the stack, so that we can set
+         * them to vector-unique values before we jump to the common code.
+         *
+         * Registers are pushed on the stack as a struct pt_regs,
+         * with the sp initially just above the struct, and when we're
+         * done, sp points to the base of the struct, minus
+         * C_ABI_SAVE_AREA_SIZE, so we can directly jal to C code.
+         *
+         * This routine saves just the first four registers, plus the
+         * stack context so we can do proper backtracing right away,
+         * and defers to handle_interrupt to save the rest.
+         * The backtracer needs pc, ex1, lr, sp, r52, and faultnum.
+         */
+        addli   r0, r0, PTREGS_OFFSET_LR - (PTREGS_SIZE + KSTK_PTREGS_GAP)
+        wh64    r0   /* cache line 7 */
+        {
+         st     r0, lr
+         addli  r0, r0, PTREGS_OFFSET_SP - PTREGS_OFFSET_LR
+        }
+        {
+         st     r0, sp
+         addli  sp, r0, PTREGS_OFFSET_REG(52) - PTREGS_OFFSET_SP
+        }
+        wh64    sp   /* cache line 6 */
+        {
+         st     sp, r52
+         addli  sp, sp, PTREGS_OFFSET_REG(1) - PTREGS_OFFSET_REG(52)
+        }
+        wh64    sp   /* cache line 0 */
+        {
+         st     sp, r1
+         addli  sp, sp, PTREGS_OFFSET_REG(2) - PTREGS_OFFSET_REG(1)
+        }
+        {
+         st     sp, r2
+         addli  sp, sp, PTREGS_OFFSET_REG(3) - PTREGS_OFFSET_REG(2)
+        }
+        {
+         st     sp, r3
+         addli  sp, sp, PTREGS_OFFSET_PC - PTREGS_OFFSET_REG(3)
+        }
+        mfspr   r0, SPR_EX_CONTEXT_K_0
+        .ifc \processing,handle_syscall
+        /*
+         * Bump the saved PC by one bundle so that when we return, we won't
+         * execute the same swint instruction again.  We need to do this while
+         * we're in the critical section.
+         */
+        addi    r0, r0, 8
+        .endif
+        {
+         st     sp, r0
+         addli  sp, sp, PTREGS_OFFSET_EX1 - PTREGS_OFFSET_PC
+        }
+        mfspr   r0, SPR_EX_CONTEXT_K_1
+        {
+         st     sp, r0
+         addi   sp, sp, PTREGS_OFFSET_FAULTNUM - PTREGS_OFFSET_EX1
+        /*
+         * Use r0 for syscalls so it's a temporary; use r1 for interrupts
+         * so that it gets passed through unchanged to the handler routine.
+         * Note that the .if conditional confusingly spans bundles.
+         */
+         .ifc \processing,handle_syscall
+         movei  r0, \vecnum
+        }
+        {
+         st     sp, r0
+         .else
+         movei  r1, \vecnum
+        }
+        {
+         st     sp, r1
+         .endif
+         addli  sp, sp, PTREGS_OFFSET_REG(0) - PTREGS_OFFSET_FAULTNUM
+        }
+        mfspr   r0, SPR_SYSTEM_SAVE_K_1    /* Original r0 */
+        {
+         st     sp, r0
+         addi   sp, sp, -PTREGS_OFFSET_REG(0) - 8
+        }
+        {
+         st     sp, zero        /* write zero into "Next SP" frame pointer */
+         addi   sp, sp, -8      /* leave SP pointing at bottom of frame */
+        }
+        .ifc \processing,handle_syscall
+        j       handle_syscall
+        .else
+        /* Capture per-interrupt SPR context to registers. */
+        .ifc \c_routine, do_page_fault
+        mfspr   r2, SPR_SYSTEM_SAVE_K_3   /* address of page fault */
+        mfspr   r3, SPR_SYSTEM_SAVE_K_2   /* info about page fault */
+        .else
+        .ifc \vecnum, INT_ILL_TRANS
+        mfspr   r2, ILL_TRANS_REASON
+        .else
+        .ifc \vecnum, INT_DOUBLE_FAULT
+        mfspr   r2, SPR_SYSTEM_SAVE_K_2   /* double fault info from HV */
+        .else
+        .ifc \c_routine, do_trap
+        mfspr   r2, GPV_REASON
+        .else
+        .ifc \c_routine, op_handle_perf_interrupt
+        mfspr   r2, PERF_COUNT_STS
+#if CHIP_HAS_AUX_PERF_COUNTERS()
+        .else
+        .ifc \c_routine, op_handle_aux_perf_interrupt
+        mfspr   r2, AUX_PERF_COUNT_STS
+        .endif
+#endif
+        .endif
+        .endif
+        .endif
+        .endif
+        .endif
+        /* Put function pointer in r0 */
+        moveli  r0, hw2_last(\c_routine)
+        shl16insli r0, r0, hw1(\c_routine)
+        {
+         shl16insli r0, r0, hw0(\c_routine)
+         j       \processing
+        }
+        .endif
+        ENDPROC(intvec_\vecname)
+
+#ifdef __COLLECT_LINKER_FEEDBACK__
+        .pushsection .text.intvec_feedback,"ax"
+        .org    (\vecnum << 5)
+        FEEDBACK_ENTER_EXPLICIT(intvec_\vecname, .intrpt1, 1 << 8)
+        jrp     lr
+        .popsection
+#endif
+
+        .endm
+
+
+        /*
+         * Save the rest of the registers that we didn't save in the actual
+         * vector itself.  We can't use r0-r10 inclusive here.
+         */
+        .macro  finish_interrupt_save, function
+
+        /* If it's a syscall, save a proper orig_r0, otherwise just zero. */
+        PTREGS_PTR(r52, PTREGS_OFFSET_ORIG_R0)
+        {
+         .ifc \function,handle_syscall
+         st     r52, r0
+         .else
+         st     r52, zero
+         .endif
+         PTREGS_PTR(r52, PTREGS_OFFSET_TP)
+        }
+        st      r52, tp
+        {
+         mfspr  tp, CMPEXCH_VALUE
+         PTREGS_PTR(r52, PTREGS_OFFSET_CMPEXCH)
+        }
+
+        /*
+         * For ordinary syscalls, we save neither caller- nor callee-
+         * save registers, since the syscall invoker doesn't expect the
+         * caller-saves to be saved, and the called kernel functions will
+         * take care of saving the callee-saves for us.
+         *
+         * For interrupts we save just the caller-save registers.  Saving
+         * them is required (since the "caller" can't save them).  Again,
+         * the called kernel functions will restore the callee-save
+         * registers for us appropriately.
+         *
+         * On return, we normally restore nothing special for syscalls,
+         * and just the caller-save registers for interrupts.
+         *
+         * However, there are some important caveats to all this:
+         *
+         * - We always save a few callee-save registers to give us
+         *   some scratchpad registers to carry across function calls.
+         *
+         * - fork/vfork/etc require us to save all the callee-save
+         *   registers, which we do in PTREGS_SYSCALL_ALL_REGS, below.
+         *
+         * - We always save r0..r5 and r10 for syscalls, since we need
+         *   to reload them a bit later for the actual kernel call, and
+         *   since we might need them for -ERESTARTNOINTR, etc.
+         *
+         * - Before invoking a signal handler, we save the unsaved
+         *   callee-save registers so they are visible to the
+         *   signal handler or any ptracer.
+         *
+         * - If the unsaved callee-save registers are modified, we set
+         *   a bit in pt_regs so we know to reload them from pt_regs
+         *   and not just rely on the kernel function unwinding.
+         *   (Done for ptrace register writes and SA_SIGINFO handler.)
+         */
+        {
+         st     r52, tp
+         PTREGS_PTR(r52, PTREGS_OFFSET_REG(33))
+        }
+        wh64    r52    /* cache line 4 */
+        push_reg r33, r52
+        push_reg r32, r52
+        push_reg r31, r52
+        .ifc \function,handle_syscall
+        push_reg r30, r52, PTREGS_OFFSET_SYSCALL - PTREGS_OFFSET_REG(30)
+        push_reg TREG_SYSCALL_NR_NAME, r52, \
+          PTREGS_OFFSET_REG(5) - PTREGS_OFFSET_SYSCALL
+        .else
+
+        push_reg r30, r52, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(30)
+        wh64    r52   /* cache line 3 */
+        push_reg r29, r52
+        push_reg r28, r52
+        push_reg r27, r52
+        push_reg r26, r52
+        push_reg r25, r52
+        push_reg r24, r52
+        push_reg r23, r52
+        push_reg r22, r52
+        wh64    r52   /* cache line 2 */
+        push_reg r21, r52
+        push_reg r20, r52
+        push_reg r19, r52
+        push_reg r18, r52
+        push_reg r17, r52
+        push_reg r16, r52
+        push_reg r15, r52
+        push_reg r14, r52
+        wh64    r52   /* cache line 1 */
+        push_reg r13, r52
+        push_reg r12, r52
+        push_reg r11, r52
+        push_reg r10, r52
+        push_reg r9, r52
+        push_reg r8, r52
+        push_reg r7, r52
+        push_reg r6, r52
+
+        .endif
+
+        push_reg r5, r52
+        st      r52, r4
+
+        /* Load tp with our per-cpu offset. */
+#ifdef CONFIG_SMP
+        {
+         mfspr  r20, SPR_SYSTEM_SAVE_K_0
+         moveli r21, hw2_last(__per_cpu_offset)
+        }
+        {
+         shl16insli r21, r21, hw1(__per_cpu_offset)
+         bfextu r20, r20, 0, LOG2_THREAD_SIZE-1
+        }
+        shl16insli r21, r21, hw0(__per_cpu_offset)
+        shl3add r20, r20, r21
+        ld      tp, r20
+#else
+        move    tp, zero
+#endif
+
+        /*
+         * If we will be returning to the kernel, we will need to
+         * reset the interrupt masks to the state they had before.
+         * Set DISABLE_IRQ in flags iff we came from PL1 with irqs disabled.
+         */
+        mfspr   r32, SPR_EX_CONTEXT_K_1
+        {
+         andi   r32, r32, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+         PTREGS_PTR(r21, PTREGS_OFFSET_FLAGS)
+        }
+        beqzt   r32, 1f       /* zero if from user space */
+        IRQS_DISABLED(r32)    /* zero if irqs enabled */
+#if PT_FLAGS_DISABLE_IRQ != 1
+# error Value of IRQS_DISABLED used to set PT_FLAGS_DISABLE_IRQ; fix
+#endif
+1:
+        .ifnc \function,handle_syscall
+        /* Record the fact that we saved the caller-save registers above. */
+        ori     r32, r32, PT_FLAGS_CALLER_SAVES
+        .endif
+        st      r21, r32
+
+#ifdef __COLLECT_LINKER_FEEDBACK__
+        /*
+         * Notify the feedback routines that we were in the
+         * appropriate fixed interrupt vector area.  Note that we
+         * still have ICS set at this point, so we can't invoke any
+         * atomic operations or we will panic.  The feedback
+         * routines internally preserve r0..r10 and r30 up.
+         */
+        .ifnc \function,handle_syscall
+        shli    r20, r1, 5
+        .else
+        moveli  r20, INT_SWINT_1 << 5
+        .endif
+        moveli  r21, hw2_last(intvec_feedback)
+        shl16insli r21, r21, hw1(intvec_feedback)
+        shl16insli r21, r21, hw0(intvec_feedback)
+        add     r20, r20, r21
+        jalr    r20
+
+        /* And now notify the feedback routines that we are here. */
+        FEEDBACK_ENTER(\function)
+#endif
+
+        /*
+         * we've captured enough state to the stack (including in
+         * particular our EX_CONTEXT state) that we can now release
+         * the interrupt critical section and replace it with our
+         * standard "interrupts disabled" mask value.  This allows
+         * synchronous interrupts (and profile interrupts) to punch
+         * through from this point onwards.
+         */
+        .ifc \function,handle_nmi
+        IRQ_DISABLE_ALL(r20)
+        .else
+        IRQ_DISABLE(r20, r21)
+        .endif
+        mtspr   INTERRUPT_CRITICAL_SECTION, zero
+
+        /*
+         * Prepare the first 256 stack bytes to be rapidly accessible
+         * without having to fetch the background data.
+         */
+        addi    r52, sp, -64
+        {
+         wh64   r52
+         addi   r52, r52, -64
+        }
+        {
+         wh64   r52
+         addi   r52, r52, -64
+        }
+        {
+         wh64   r52
+         addi   r52, r52, -64
+        }
+        wh64    r52
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+        .ifnc \function,handle_nmi
+        /*
+         * We finally have enough state set up to notify the irq
+         * tracing code that irqs were disabled on entry to the handler.
+         * The TRACE_IRQS_OFF call clobbers registers r0-r29.
+         * For syscalls, we already have the register state saved away
+         * on the stack, so we don't bother to do any register saves here,
+         * and later we pop the registers back off the kernel stack.
+         * For interrupt handlers, save r0-r3 in callee-saved registers.
+         */
+        .ifnc \function,handle_syscall
+        { move r30, r0; move r31, r1 }
+        { move r32, r2; move r33, r3 }
+        .endif
+        TRACE_IRQS_OFF
+        .ifnc \function,handle_syscall
+        { move r0, r30; move r1, r31 }
+        { move r2, r32; move r3, r33 }
+        .endif
+        .endif
+#endif
+
+        .endm
+
+        /*
+         * Redispatch a downcall.
+         */
+        .macro  dc_dispatch vecnum, vecname
+        .org    (\vecnum << 8)
+intvec_\vecname:
+        j       hv_downcall_dispatch
+        ENDPROC(intvec_\vecname)
+        .endm
+
+        /*
+         * Common code for most interrupts.  The C function we're eventually
+         * going to is in r0, and the faultnum is in r1; the original
+         * values for those registers are on the stack.
+         */
+        .pushsection .text.handle_interrupt,"ax"
+handle_interrupt:
+        finish_interrupt_save handle_interrupt
+
+        /* Jump to the C routine; it should enable irqs as soon as possible. */
+        {
+         jalr   r0
+         PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
+        }
+        FEEDBACK_REENTER(handle_interrupt)
+        {
+         movei  r30, 0   /* not an NMI */
+         j      interrupt_return
+        }
+        STD_ENDPROC(handle_interrupt)
+
+/*
+ * This routine takes a boolean in r30 indicating if this is an NMI.
+ * If so, we also expect a boolean in r31 indicating whether to
+ * re-enable the oprofile interrupts.
+ */
+STD_ENTRY(interrupt_return)
+        /* If we're resuming to kernel space, don't check thread flags. */
+        {
+         bnez   r30, .Lrestore_all  /* NMIs don't special-case user-space */
+         PTREGS_PTR(r29, PTREGS_OFFSET_EX1)
+        }
+        ld      r29, r29
+        andi    r29, r29, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+        {
+         beqzt  r29, .Lresume_userspace
+         PTREGS_PTR(r29, PTREGS_OFFSET_PC)
+        }
+
+        /* If we're resuming to _cpu_idle_nap, bump PC forward by 8. */
+        moveli  r27, hw2_last(_cpu_idle_nap)
+        {
+         ld     r28, r29
+         shl16insli r27, r27, hw1(_cpu_idle_nap)
+        }
+        {
+         shl16insli r27, r27, hw0(_cpu_idle_nap)
+        }
+        {
+         cmpeq  r27, r27, r28
+        }
+        {
+         blbc   r27, .Lrestore_all
+         addi   r28, r28, 8
+        }
+        st      r29, r28
+        j       .Lrestore_all
+
+.Lresume_userspace:
+        FEEDBACK_REENTER(interrupt_return)
+
+        /*
+         * Disable interrupts so as to make sure we don't
+         * miss an interrupt that sets any of the thread flags (like
+         * need_resched or sigpending) between sampling and the iret.
+         * Routines like schedule() or do_signal() may re-enable
+         * interrupts before returning.
+         */
+        IRQ_DISABLE(r20, r21)
+        TRACE_IRQS_OFF  /* Note: clobbers registers r0-r29 */
+
+        /* Get base of stack in r32; note r30/31 are used as arguments here. */
+        GET_THREAD_INFO(r32)
+
+
+        /* Check to see if there is any work to do before returning to user. */
+        {
+         addi   r29, r32, THREAD_INFO_FLAGS_OFFSET
+         moveli r1, hw1_last(_TIF_ALLWORK_MASK)
+        }
+        {
+         ld     r29, r29
+         shl16insli r1, r1, hw0(_TIF_ALLWORK_MASK)
+        }
+        and     r1, r29, r1
+        beqzt   r1, .Lrestore_all
+
+        /*
+         * Make sure we have all the registers saved for signal
+         * handling or single-step.  Call out to C code to figure out
+         * exactly what we need to do for each flag bit, then if
+         * necessary, reload the flags and recheck.
+         */
+        push_extra_callee_saves r0
+        {
+         PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
+         jal    do_work_pending
+        }
+        bnez    r0, .Lresume_userspace
+
+        /*
+         * In the NMI case we
+         * omit the call to single_process_check_nohz, which normally checks
+         * to see if we should start or stop the scheduler tick, because
+         * we can't call arbitrary Linux code from an NMI context.
+         * We always call the homecache TLB deferral code to re-trigger
+         * the deferral mechanism.
+         *
+         * The other chunk of responsibility this code has is to reset the
+         * interrupt masks appropriately to reset irqs and NMIs.  We have
+         * to call TRACE_IRQS_OFF and TRACE_IRQS_ON to support all the
+         * lockdep-type stuff, but we can't set ICS until afterwards, since
+         * ICS can only be used in very tight chunks of code to avoid
+         * tripping over various assertions that it is off.
+         */
+.Lrestore_all:
+        PTREGS_PTR(r0, PTREGS_OFFSET_EX1)
+        {
+         ld      r0, r0
+         PTREGS_PTR(r32, PTREGS_OFFSET_FLAGS)
+        }
+        {
+         andi   r0, r0, SPR_EX_CONTEXT_1_1__PL_MASK
+         ld     r32, r32
+        }
+        bnez    r0, 1f
+        j       2f
+#if PT_FLAGS_DISABLE_IRQ != 1
+# error Assuming PT_FLAGS_DISABLE_IRQ == 1 so we can use blbct below
+#endif
+1:      blbct   r32, 2f
+        IRQ_DISABLE(r20,r21)
+        TRACE_IRQS_OFF
+        movei   r0, 1
+        mtspr   INTERRUPT_CRITICAL_SECTION, r0
+        beqzt   r30, .Lrestore_regs
+        j       3f
+2:      TRACE_IRQS_ON
+        movei   r0, 1
+        mtspr   INTERRUPT_CRITICAL_SECTION, r0
+        IRQ_ENABLE(r20, r21)
+        beqzt   r30, .Lrestore_regs
+3:
+
+
+        /*
+         * We now commit to returning from this interrupt, since we will be
+         * doing things like setting EX_CONTEXT SPRs and unwinding the stack
+         * frame.  No calls should be made to any other code after this point.
+         * This code should only be entered with ICS set.
+         * r32 must still be set to ptregs.flags.
+         * We launch loads to each cache line separately first, so we can
+         * get some parallelism out of the memory subsystem.
+         * We start zeroing caller-saved registers throughout, since
+         * that will save some cycles if this turns out to be a syscall.
+         */
+.Lrestore_regs:
+        FEEDBACK_REENTER(interrupt_return)   /* called from elsewhere */
+
+        /*
+         * Rotate so we have one high bit and one low bit to test.
+         * - low bit says whether to restore all the callee-saved registers,
+         *   or just r30-r33, and r52 up.
+         * - high bit (i.e. sign bit) says whether to restore all the
+         *   caller-saved registers, or just r0.
+         */
+#if PT_FLAGS_CALLER_SAVES != 2 || PT_FLAGS_RESTORE_REGS != 4
+# error Rotate trick does not work :-)
+#endif
+        {
+         rotli  r20, r32, 62
+         PTREGS_PTR(sp, PTREGS_OFFSET_REG(0))
+        }
+
+        /*
+         * Load cache lines 0, 4, 6 and 7, in that order, then use
+         * the last loaded value, which makes it likely that the other
+         * cache lines have also loaded, at which point we should be
+         * able to safely read all the remaining words on those cache
+         * lines without waiting for the memory subsystem.
+         */
+        pop_reg r0, sp, PTREGS_OFFSET_REG(30) - PTREGS_OFFSET_REG(0)
+        pop_reg r30, sp, PTREGS_OFFSET_REG(52) - PTREGS_OFFSET_REG(30)
+        pop_reg_zero r52, r3, sp, PTREGS_OFFSET_CMPEXCH - PTREGS_OFFSET_REG(52)
+        pop_reg_zero r21, r27, sp, PTREGS_OFFSET_EX1 - PTREGS_OFFSET_CMPEXCH
+        pop_reg_zero lr, r2, sp, PTREGS_OFFSET_PC - PTREGS_OFFSET_EX1
+        {
+         mtspr  CMPEXCH_VALUE, r21
+         move   r4, zero
+        }
+        pop_reg r21, sp, PTREGS_OFFSET_REG(31) - PTREGS_OFFSET_PC
+        {
+         mtspr  SPR_EX_CONTEXT_K_1, lr
+         andi   lr, lr, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+        }
+        {
+         mtspr  SPR_EX_CONTEXT_K_0, r21
+         move   r5, zero
+        }
+
+        /* Restore callee-saveds that we actually use. */
+        pop_reg_zero r31, r6
+        pop_reg_zero r32, r7
+        pop_reg_zero r33, r8, sp, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(33)
+
+        /*
+         * If we modified other callee-saveds, restore them now.
+         * This is rare, but could be via ptrace or signal handler.
+         */
+        {
+         move   r9, zero
+         blbs   r20, .Lrestore_callees
+        }
+.Lcontinue_restore_regs:
+
+        /* Check if we're returning from a syscall. */
+        {
+         move   r10, zero
+         bltzt  r20, 1f  /* no, so go restore callee-save registers */
+        }
+
+        /*
+         * Check if we're returning to userspace.
+         * Note that if we're not, we don't worry about zeroing everything.
+         */
+        {
+         addli  sp, sp, PTREGS_OFFSET_LR - PTREGS_OFFSET_REG(29)
+         bnez   lr, .Lkernel_return
+        }
+
+        /*
+         * On return from syscall, we've restored r0 from pt_regs, but we
+         * clear the remainder of the caller-saved registers.  We could
+         * restore the syscall arguments, but there's not much point,
+         * and it ensures user programs aren't trying to use the
+         * caller-saves if we clear them, as well as avoiding leaking
+         * kernel pointers into userspace.
+         */
+        pop_reg_zero lr, r11, sp, PTREGS_OFFSET_TP - PTREGS_OFFSET_LR
+        pop_reg_zero tp, r12, sp, PTREGS_OFFSET_SP - PTREGS_OFFSET_TP
+        {
+         ld     sp, sp
+         move   r13, zero
+         move   r14, zero
+        }
+        { move r15, zero; move r16, zero }
+        { move r17, zero; move r18, zero }
+        { move r19, zero; move r20, zero }
+        { move r21, zero; move r22, zero }
+        { move r23, zero; move r24, zero }
+        { move r25, zero; move r26, zero }
+
+        /* Set r1 to errno if we are returning an error, otherwise zero. */
+        {
+         moveli r29, 4096
+         sub    r1, zero, r0
+        }
+        {
+         move   r28, zero
+         cmpltu r29, r1, r29
+        }
+        {
+         mnz    r1, r29, r1
+         move   r29, zero
+        }
+        iret
+
+        /*
+         * Not a syscall, so restore caller-saved registers.
+         * First kick off loads for cache lines 1-3, which we're touching
+         * for the first time here.
+         */
+        .align 64
+1:      pop_reg r29, sp, PTREGS_OFFSET_REG(21) - PTREGS_OFFSET_REG(29)
+        pop_reg r21, sp, PTREGS_OFFSET_REG(13) - PTREGS_OFFSET_REG(21)
+        pop_reg r13, sp, PTREGS_OFFSET_REG(1) - PTREGS_OFFSET_REG(13)
+        pop_reg r1
+        pop_reg r2
+        pop_reg r3
+        pop_reg r4
+        pop_reg r5
+        pop_reg r6
+        pop_reg r7
+        pop_reg r8
+        pop_reg r9
+        pop_reg r10
+        pop_reg r11
+        pop_reg r12, sp, 16
+        /* r13 already restored above */
+        pop_reg r14
+        pop_reg r15
+        pop_reg r16
+        pop_reg r17
+        pop_reg r18
+        pop_reg r19
+        pop_reg r20, sp, 16
+        /* r21 already restored above */
+        pop_reg r22
+        pop_reg r23
+        pop_reg r24
+        pop_reg r25
+        pop_reg r26
+        pop_reg r27
+        pop_reg r28, sp, PTREGS_OFFSET_LR - PTREGS_OFFSET_REG(28)
+        /* r29 already restored above */
+        bnez    lr, .Lkernel_return
+        pop_reg lr, sp, PTREGS_OFFSET_TP - PTREGS_OFFSET_LR
+        pop_reg tp, sp, PTREGS_OFFSET_SP - PTREGS_OFFSET_TP
+        ld      sp, sp
+        iret
+
+        /*
+         * We can't restore tp when in kernel mode, since a thread might
+         * have migrated from another cpu and brought a stale tp value.
+         */
+.Lkernel_return:
+        pop_reg lr, sp, PTREGS_OFFSET_SP - PTREGS_OFFSET_LR
+        ld      sp, sp
+        iret
+
+        /* Restore callee-saved registers from r34 to r51. */
+.Lrestore_callees:
+        addli  sp, sp, PTREGS_OFFSET_REG(34) - PTREGS_OFFSET_REG(29)
+        pop_reg r34
+        pop_reg r35
+        pop_reg r36
+        pop_reg r37
+        pop_reg r38
+        pop_reg r39
+        pop_reg r40
+        pop_reg r41
+        pop_reg r42
+        pop_reg r43
+        pop_reg r44
+        pop_reg r45
+        pop_reg r46
+        pop_reg r47
+        pop_reg r48
+        pop_reg r49
+        pop_reg r50
+        pop_reg r51, sp, PTREGS_OFFSET_REG(29) - PTREGS_OFFSET_REG(51)
+        j .Lcontinue_restore_regs
+        STD_ENDPROC(interrupt_return)
+
+        /*
+         * "NMI" interrupts mask ALL interrupts before calling the
+         * handler, and don't check thread flags, etc., on the way
+         * back out.  In general, the only things we do here for NMIs
+         * are register save/restore and dataplane kernel-TLB management.
+         * We don't (for example) deal with start/stop of the sched tick.
+         */
+        .pushsection .text.handle_nmi,"ax"
+handle_nmi:
+        finish_interrupt_save handle_nmi
+        {
+         jalr   r0
+         PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
+        }
+        FEEDBACK_REENTER(handle_nmi)
+        {
+         movei  r30, 1
+         move   r31, r0
+        }
+        j       interrupt_return
+        STD_ENDPROC(handle_nmi)
+
+        /*
+         * Parallel code for syscalls to handle_interrupt.
+         */
+        .pushsection .text.handle_syscall,"ax"
+handle_syscall:
+        finish_interrupt_save handle_syscall
+
+        /* Enable irqs. */
+        TRACE_IRQS_ON
+        IRQ_ENABLE(r20, r21)
+
+        /* Bump the counter for syscalls made on this tile. */
+        moveli r20, hw2_last(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
+        shl16insli r20, r20, hw1(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
+        shl16insli r20, r20, hw0(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
+        add     r20, r20, tp
+        ld4s    r21, r20
+        addi    r21, r21, 1
+        st4     r20, r21
+
+        /* Trace syscalls, if requested. */
+        GET_THREAD_INFO(r31)
+        addi    r31, r31, THREAD_INFO_FLAGS_OFFSET
+        ld      r30, r31
+        andi    r30, r30, _TIF_SYSCALL_TRACE
+        {
+         addi   r30, r31, THREAD_INFO_STATUS_OFFSET - THREAD_INFO_FLAGS_OFFSET
+         beqzt  r30, .Lrestore_syscall_regs
+        }
+        jal     do_syscall_trace
+        FEEDBACK_REENTER(handle_syscall)
+
+        /*
+         * We always reload our registers from the stack at this
+         * point.  They might be valid, if we didn't build with
+         * TRACE_IRQFLAGS, and this isn't a dataplane tile, and we're not
+         * doing syscall tracing, but there are enough cases now that it
+         * seems simplest just to do the reload unconditionally.
+         */
+.Lrestore_syscall_regs:
+        {
+         ld     r30, r30
+         PTREGS_PTR(r11, PTREGS_OFFSET_REG(0))
+        }
+        pop_reg r0,  r11
+        pop_reg r1,  r11
+        pop_reg r2,  r11
+        pop_reg r3,  r11
+        pop_reg r4,  r11
+        pop_reg r5,  r11, PTREGS_OFFSET_SYSCALL - PTREGS_OFFSET_REG(5)
+        {
+         ld     TREG_SYSCALL_NR_NAME, r11
+         moveli r21, __NR_syscalls
+        }
+
+        /* Ensure that the syscall number is within the legal range. */
+        {
+         moveli r20, hw2(sys_call_table)
+         blbs   r30, .Lcompat_syscall
+        }
+        {
+         cmpltu r21, TREG_SYSCALL_NR_NAME, r21
+         shl16insli r20, r20, hw1(sys_call_table)
+        }
+        {
+         blbc   r21, .Linvalid_syscall
+         shl16insli r20, r20, hw0(sys_call_table)
+        }
+.Lload_syscall_pointer:
+        shl3add r20, TREG_SYSCALL_NR_NAME, r20
+        ld      r20, r20
+
+        /* Jump to syscall handler. */
+        jalr    r20
+.Lhandle_syscall_link: /* value of "lr" after "jalr r20" above */
+
+        /*
+         * Write our r0 onto the stack so it gets restored instead
+         * of whatever the user had there before.
+         * In compat mode, sign-extend r0 before storing it.
+         */
+        {
+         PTREGS_PTR(r29, PTREGS_OFFSET_REG(0))
+         blbct  r30, 1f
+        }
+        addxi   r0, r0, 0
+1:      st      r29, r0
+
+.Lsyscall_sigreturn_skip:
+        FEEDBACK_REENTER(handle_syscall)
+
+        /* Do syscall trace again, if requested. */
+        ld      r30, r31
+        andi    r30, r30, _TIF_SYSCALL_TRACE
+        beqzt   r30, 1f
+        jal     do_syscall_trace
+        FEEDBACK_REENTER(handle_syscall)
+1:      j       .Lresume_userspace   /* jump into middle of interrupt_return */
+
+.Lcompat_syscall:
+        /*
+         * Load the base of the compat syscall table in r20, and
+         * range-check the syscall number (duplicated from 64-bit path).
+         * Sign-extend all the user's passed arguments to make them consistent.
+         * Also save the original "r(n)" values away in "r(11+n)" in
+         * case the syscall table entry wants to validate them.
+         */
+        moveli  r20, hw2(compat_sys_call_table)
+        {
+         cmpltu r21, TREG_SYSCALL_NR_NAME, r21
+         shl16insli r20, r20, hw1(compat_sys_call_table)
+        }
+        {
+         blbc   r21, .Linvalid_syscall
+         shl16insli r20, r20, hw0(compat_sys_call_table)
+        }
+        { move r11, r0; addxi r0, r0, 0 }
+        { move r12, r1; addxi r1, r1, 0 }
+        { move r13, r2; addxi r2, r2, 0 }
+        { move r14, r3; addxi r3, r3, 0 }
+        { move r15, r4; addxi r4, r4, 0 }
+        { move r16, r5; addxi r5, r5, 0 }
+        j .Lload_syscall_pointer
+
+.Linvalid_syscall:
+        /* Report an invalid syscall back to the user program */
+        {
+         PTREGS_PTR(r29, PTREGS_OFFSET_REG(0))
+         movei  r28, -ENOSYS
+        }
+        st      r29, r28
+        j       .Lresume_userspace   /* jump into middle of interrupt_return */
+        STD_ENDPROC(handle_syscall)
+
+        /* Return the address for oprofile to suppress in backtraces. */
+STD_ENTRY_SECTION(handle_syscall_link_address, .text.handle_syscall)
+        lnk     r0
+        {
+         addli  r0, r0, .Lhandle_syscall_link - .
+         jrp    lr
+        }
+        STD_ENDPROC(handle_syscall_link_address)
+
+STD_ENTRY(ret_from_fork)
+        jal     sim_notify_fork
+        jal     schedule_tail
+        FEEDBACK_REENTER(ret_from_fork)
+        j       .Lresume_userspace
+        STD_ENDPROC(ret_from_fork)
+
+/* Various stub interrupt handlers and syscall handlers */
+
+STD_ENTRY_LOCAL(_kernel_double_fault)
+        mfspr   r1, SPR_EX_CONTEXT_K_0
+        move    r2, lr
+        move    r3, sp
+        move    r4, r52
+        addi    sp, sp, -C_ABI_SAVE_AREA_SIZE
+        j       kernel_double_fault
+        STD_ENDPROC(_kernel_double_fault)
+
+STD_ENTRY_LOCAL(bad_intr)
+        mfspr   r2, SPR_EX_CONTEXT_K_0
+        panic   "Unhandled interrupt %#x: PC %#lx"
+        STD_ENDPROC(bad_intr)
+
+/* Put address of pt_regs in reg and jump. */
+#define PTREGS_SYSCALL(x, reg)                          \
+        STD_ENTRY(_##x);                                \
+        {                                               \
+         PTREGS_PTR(reg, PTREGS_OFFSET_BASE);           \
+         j      x                                       \
+        };                                              \
+        STD_ENDPROC(_##x)
+
+/*
+ * Special-case sigreturn to not write r0 to the stack on return.
+ * This is technically more efficient, but it also avoids difficulties
+ * in the 64-bit OS when handling 32-bit compat code, since we must not
+ * sign-extend r0 for the sigreturn return-value case.
+ */
+#define PTREGS_SYSCALL_SIGRETURN(x, reg)                \
+        STD_ENTRY(_##x);                                \
+        addli   lr, lr, .Lsyscall_sigreturn_skip - .Lhandle_syscall_link; \
+        {                                               \
+         PTREGS_PTR(reg, PTREGS_OFFSET_BASE);           \
+         j      x                                       \
+        };                                              \
+        STD_ENDPROC(_##x)
+
+PTREGS_SYSCALL(sys_execve, r3)
+PTREGS_SYSCALL(sys_sigaltstack, r2)
+PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
+#ifdef CONFIG_COMPAT
+PTREGS_SYSCALL(compat_sys_execve, r3)
+PTREGS_SYSCALL(compat_sys_sigaltstack, r2)
+PTREGS_SYSCALL_SIGRETURN(compat_sys_rt_sigreturn, r0)
+#endif
+
+/* Save additional callee-saves to pt_regs, put address in r4 and jump. */
+STD_ENTRY(_sys_clone)
+        push_extra_callee_saves r4
+        j       sys_clone
+        STD_ENDPROC(_sys_clone)
+
+/* The single-step support may need to read all the registers. */
+int_unalign:
+        push_extra_callee_saves r0
+        j       do_trap
+
+/* Include .intrpt1 array of interrupt vectors */
+        .section ".intrpt1", "ax"
+
+#define op_handle_perf_interrupt bad_intr
+#define op_handle_aux_perf_interrupt bad_intr
+
+#ifndef CONFIG_HARDWALL
+#define do_hardwall_trap bad_intr
+#endif
+
+        int_hand     INT_MEM_ERROR, MEM_ERROR, bad_intr
+        int_hand     INT_SINGLE_STEP_3, SINGLE_STEP_3, bad_intr
+#if CONFIG_KERNEL_PL == 2
+        int_hand     INT_SINGLE_STEP_2, SINGLE_STEP_2, gx_singlestep_handle
+        int_hand     INT_SINGLE_STEP_1, SINGLE_STEP_1, bad_intr
+#else
+        int_hand     INT_SINGLE_STEP_2, SINGLE_STEP_2, bad_intr
+        int_hand     INT_SINGLE_STEP_1, SINGLE_STEP_1, gx_singlestep_handle
+#endif
+        int_hand     INT_SINGLE_STEP_0, SINGLE_STEP_0, bad_intr
+        int_hand     INT_IDN_COMPLETE, IDN_COMPLETE, bad_intr
+        int_hand     INT_UDN_COMPLETE, UDN_COMPLETE, bad_intr
+        int_hand     INT_ITLB_MISS, ITLB_MISS, do_page_fault
+        int_hand     INT_ILL, ILL, do_trap
+        int_hand     INT_GPV, GPV, do_trap
+        int_hand     INT_IDN_ACCESS, IDN_ACCESS, do_trap
+        int_hand     INT_UDN_ACCESS, UDN_ACCESS, do_trap
+        int_hand     INT_SWINT_3, SWINT_3, do_trap
+        int_hand     INT_SWINT_2, SWINT_2, do_trap
+        int_hand     INT_SWINT_1, SWINT_1, SYSCALL, handle_syscall
+        int_hand     INT_SWINT_0, SWINT_0, do_trap
+        int_hand     INT_ILL_TRANS, ILL_TRANS, do_trap
+        int_hand     INT_UNALIGN_DATA, UNALIGN_DATA, int_unalign
+        int_hand     INT_DTLB_MISS, DTLB_MISS, do_page_fault
+        int_hand     INT_DTLB_ACCESS, DTLB_ACCESS, do_page_fault
+        int_hand     INT_IDN_FIREWALL, IDN_FIREWALL, bad_intr
+        int_hand     INT_UDN_FIREWALL, UDN_FIREWALL, do_hardwall_trap
+        int_hand     INT_TILE_TIMER, TILE_TIMER, do_timer_interrupt
+        int_hand     INT_IDN_TIMER, IDN_TIMER, bad_intr
+        int_hand     INT_UDN_TIMER, UDN_TIMER, bad_intr
+        int_hand     INT_IDN_AVAIL, IDN_AVAIL, bad_intr
+        int_hand     INT_UDN_AVAIL, UDN_AVAIL, bad_intr
+        int_hand     INT_IPI_3, IPI_3, bad_intr
+#if CONFIG_KERNEL_PL == 2
+        int_hand     INT_IPI_2, IPI_2, tile_dev_intr
+        int_hand     INT_IPI_1, IPI_1, bad_intr
+#else
+        int_hand     INT_IPI_2, IPI_2, bad_intr
+        int_hand     INT_IPI_1, IPI_1, tile_dev_intr
+#endif
+        int_hand     INT_IPI_0, IPI_0, bad_intr
+        int_hand     INT_PERF_COUNT, PERF_COUNT, \
+                     op_handle_perf_interrupt, handle_nmi
+        int_hand     INT_AUX_PERF_COUNT, AUX_PERF_COUNT, \
+                     op_handle_perf_interrupt, handle_nmi
+        int_hand     INT_INTCTRL_3, INTCTRL_3, bad_intr
+#if CONFIG_KERNEL_PL == 2
+        dc_dispatch  INT_INTCTRL_2, INTCTRL_2
+        int_hand     INT_INTCTRL_1, INTCTRL_1, bad_intr
+#else
+        int_hand     INT_INTCTRL_2, INTCTRL_2, bad_intr
+        dc_dispatch  INT_INTCTRL_1, INTCTRL_1
+#endif
+        int_hand     INT_INTCTRL_0, INTCTRL_0, bad_intr
+        int_hand     INT_MESSAGE_RCV_DWNCL, MESSAGE_RCV_DWNCL, \
+                     hv_message_intr
+        int_hand     INT_DEV_INTR_DWNCL, DEV_INTR_DWNCL, bad_intr
+        int_hand     INT_I_ASID, I_ASID, bad_intr
+        int_hand     INT_D_ASID, D_ASID, bad_intr
+        int_hand     INT_DOUBLE_FAULT, DOUBLE_FAULT, do_trap
+
+        /* Synthetic interrupt delivered only by the simulator */
+        int_hand     INT_BREAKPOINT, BREAKPOINT, do_breakpoint
diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c
index e2ab82b7c7e7..f68df69f1f67 100644
--- a/arch/tile/kernel/module.c
+++ b/arch/tile/kernel/module.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <asm/opcode-tile.h>
 #include <asm/pgtable.h>
+#include <asm/homecache.h>
 
 #ifdef __tilegx__
 # define Elf_Rela Elf64_Rela
@@ -86,8 +87,13 @@ error:
 void module_free(struct module *mod, void *module_region)
 {
         vfree(module_region);
+
+        /* Globally flush the L1 icache. */
+        flush_remote(0, HV_FLUSH_EVICT_L1I, cpu_online_mask,
+                     0, 0, 0, NULL, NULL, 0);
+
         /*
-         * FIXME: If module_region == mod->init_region, trim exception
+         * FIXME: If module_region == mod->module_init, trim exception
          * table entries.
          */
 }
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index 658752b2835e..658f2ce426a4 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -244,7 +244,7 @@ EXPORT_SYMBOL(dma_sync_single_range_for_device);
  * dma_alloc_noncoherent() returns non-cacheable memory, so there's no
  * need to do any flushing here.
  */
-void dma_cache_sync(void *vaddr, size_t size,
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
                     enum dma_data_direction direction)
 {
 }
diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c
index ea38f0c9ec7c..6d4cb5d7a9fd 100644
--- a/arch/tile/kernel/pci.c
+++ b/arch/tile/kernel/pci.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -59,6 +59,7 @@ int __write_once tile_plx_gen1;
 
 static struct pci_controller controllers[TILE_NUM_PCIE];
 static int num_controllers;
+static int pci_scan_flags[TILE_NUM_PCIE];
 
 static struct pci_ops tile_cfg_ops;
 
@@ -79,7 +80,7 @@ EXPORT_SYMBOL(pcibios_align_resource);
  * controller_id is the controller number, config type is 0 or 1 for
  * config0 or config1 operations.
  */
-static int __init tile_pcie_open(int controller_id, int config_type)
+static int __devinit tile_pcie_open(int controller_id, int config_type)
 {
         char filename[32];
         int fd;
@@ -95,7 +96,7 @@ static int __init tile_pcie_open(int controller_id, int config_type)
 /*
  * Get the IRQ numbers from the HV and set up the handlers for them.
  */
-static int __init tile_init_irqs(int controller_id,
+static int __devinit tile_init_irqs(int controller_id,
                                  struct pci_controller *controller)
 {
         char filename[32];
@@ -139,71 +140,74 @@ static int __init tile_init_irqs(int controller_id,
  *
  * Returns the number of controllers discovered.
  */
-int __init tile_pci_init(void)
+int __devinit tile_pci_init(void)
 {
         int i;
 
         pr_info("PCI: Searching for controllers...\n");
 
+        /* Re-init number of PCIe controllers to support hot-plug feature. */
+        num_controllers = 0;
+
         /* Do any configuration we need before using the PCIe */
 
         for (i = 0; i < TILE_NUM_PCIE; i++) {
-                int hv_cfg_fd0 = -1;
-                int hv_cfg_fd1 = -1;
-                int hv_mem_fd = -1;
-                char name[32];
-                struct pci_controller *controller;
-
                 /*
-                 * Open the fd to the HV.  If it fails then this
-                 * device doesn't exist.
+                 * To see whether we need a real config op based on
+                 * the results of pcibios_init(), to support PCIe hot-plug.
                  */
-                hv_cfg_fd0 = tile_pcie_open(i, 0);
-                if (hv_cfg_fd0 < 0)
-                        continue;
-                hv_cfg_fd1 = tile_pcie_open(i, 1);
-                if (hv_cfg_fd1 < 0) {
-                        pr_err("PCI: Couldn't open config fd to HV "
-                            "for controller %d\n", i);
-                        goto err_cont;
-                }
-
-                sprintf(name, "pcie/%d/mem", i);
-                hv_mem_fd = hv_dev_open((HV_VirtAddr)name, 0);
-                if (hv_mem_fd < 0) {
-                        pr_err("PCI: Could not open mem fd to HV!\n");
-                        goto err_cont;
-                }
+                if (pci_scan_flags[i] == 0) {
+                        int hv_cfg_fd0 = -1;
+                        int hv_cfg_fd1 = -1;
+                        int hv_mem_fd = -1;
+                        char name[32];
+                        struct pci_controller *controller;
+
+                        /*
+                         * Open the fd to the HV.  If it fails then this
+                         * device doesn't exist.
+                         */
+                        hv_cfg_fd0 = tile_pcie_open(i, 0);
+                        if (hv_cfg_fd0 < 0)
+                                continue;
+                        hv_cfg_fd1 = tile_pcie_open(i, 1);
+                        if (hv_cfg_fd1 < 0) {
+                                pr_err("PCI: Couldn't open config fd to HV "
+                                    "for controller %d\n", i);
+                                goto err_cont;
+                        }
 
-                pr_info("PCI: Found PCI controller #%d\n", i);
+                        sprintf(name, "pcie/%d/mem", i);
+                        hv_mem_fd = hv_dev_open((HV_VirtAddr)name, 0);
+                        if (hv_mem_fd < 0) {
+                                pr_err("PCI: Could not open mem fd to HV!\n");
+                                goto err_cont;
+                        }
 
-                controller = &controllers[num_controllers];
+                        pr_info("PCI: Found PCI controller #%d\n", i);
 
-                if (tile_init_irqs(i, controller)) {
-                        pr_err("PCI: Could not initialize "
-                               "IRQs, aborting.\n");
-                        goto err_cont;
-                }
+                        controller = &controllers[i];
 
-                controller->index = num_controllers;
-                controller->hv_cfg_fd[0] = hv_cfg_fd0;
-                controller->hv_cfg_fd[1] = hv_cfg_fd1;
-                controller->hv_mem_fd = hv_mem_fd;
-                controller->first_busno = 0;
-                controller->last_busno = 0xff;
-                controller->ops = &tile_cfg_ops;
+                        controller->index = i;
+                        controller->hv_cfg_fd[0] = hv_cfg_fd0;
+                        controller->hv_cfg_fd[1] = hv_cfg_fd1;
+                        controller->hv_mem_fd = hv_mem_fd;
+                        controller->first_busno = 0;
+                        controller->last_busno = 0xff;
+                        controller->ops = &tile_cfg_ops;
 
-                num_controllers++;
-                continue;
+                        num_controllers++;
+                        continue;
 
 err_cont:
-                if (hv_cfg_fd0 >= 0)
-                        hv_dev_close(hv_cfg_fd0);
-                if (hv_cfg_fd1 >= 0)
-                        hv_dev_close(hv_cfg_fd1);
-                if (hv_mem_fd >= 0)
-                        hv_dev_close(hv_mem_fd);
-                continue;
+                        if (hv_cfg_fd0 >= 0)
+                                hv_dev_close(hv_cfg_fd0);
+                        if (hv_cfg_fd1 >= 0)
+                                hv_dev_close(hv_cfg_fd1);
+                        if (hv_mem_fd >= 0)
+                                hv_dev_close(hv_mem_fd);
+                        continue;
+                }
         }
 
         /*
@@ -232,7 +236,7 @@ static int tile_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
 }
 
 
-static void __init fixup_read_and_payload_sizes(void)
+static void __devinit fixup_read_and_payload_sizes(void)
 {
         struct pci_dev *dev = NULL;
         int smallest_max_payload = 0x1; /* Tile maxes out at 256 bytes. */
@@ -282,7 +286,7 @@ static void __init fixup_read_and_payload_sizes(void)
  * The controllers have been set up by the time we get here, by a call to
  * tile_pci_init.
  */
-static int __init pcibios_init(void)
+int __devinit pcibios_init(void)
 {
         int i;
 
@@ -296,25 +300,36 @@ static int __init pcibios_init(void)
         mdelay(250);
 
         /* Scan all of the recorded PCI controllers.  */
-        for (i = 0; i < num_controllers; i++) {
-                struct pci_controller *controller = &controllers[i];
-                struct pci_bus *bus;
-
-                pr_info("PCI: initializing controller #%d\n", i);
-
+        for (i = 0; i < TILE_NUM_PCIE; i++) {
                 /*
-                 * This comes from the generic Linux PCI driver.
-                 *
-                 * It reads the PCI tree for this bus into the Linux
-                 * data structures.
-                 *
-                 * This is inlined in linux/pci.h and calls into
-                 * pci_scan_bus_parented() in probe.c.
+                 * Do real pcibios init ops if the controller is initialized
+                 * by tile_pci_init() successfully and not initialized by
+                 * pcibios_init() yet to support PCIe hot-plug.
                  */
-                bus = pci_scan_bus(0, controller->ops, controller);
-                controller->root_bus = bus;
-                controller->last_busno = bus->subordinate;
+                if (pci_scan_flags[i] == 0 && controllers[i].ops != NULL) {
+                        struct pci_controller *controller = &controllers[i];
+                        struct pci_bus *bus;
 
+                        if (tile_init_irqs(i, controller)) {
+                                pr_err("PCI: Could not initialize IRQs\n");
+                                continue;
+                        }
+
+                        pr_info("PCI: initializing controller #%d\n", i);
+
+                        /*
+                         * This comes from the generic Linux PCI driver.
+                         *
+                         * It reads the PCI tree for this bus into the Linux
+                         * data structures.
+                         *
+                         * This is inlined in linux/pci.h and calls into
+                         * pci_scan_bus_parented() in probe.c.
+                         */
+                        bus = pci_scan_bus(0, controller->ops, controller);
+                        controller->root_bus = bus;
+                        controller->last_busno = bus->subordinate;
+                }
         }
 
         /* Do machine dependent PCI interrupt routing */
@@ -326,34 +341,45 @@ static int __init pcibios_init(void)
          * It allocates all of the resources (I/O memory, etc)
          * associated with the devices read in above.
          */
-
         pci_assign_unassigned_resources();
 
         /* Configure the max_read_size and max_payload_size values. */
         fixup_read_and_payload_sizes();
 
         /* Record the I/O resources in the PCI controller structure. */
-        for (i = 0; i < num_controllers; i++) {
-                struct pci_bus *root_bus = controllers[i].root_bus;
-                struct pci_bus *next_bus;
-                struct pci_dev *dev;
-
-                list_for_each_entry(dev, &root_bus->devices, bus_list) {
-                        /* Find the PCI host controller, ie. the 1st bridge. */
-                        if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI &&
-                                (PCI_SLOT(dev->devfn) == 0)) {
-                                next_bus = dev->subordinate;
-                                controllers[i].mem_resources[0] =
-                                        *next_bus->resource[0];
-                                controllers[i].mem_resources[1] =
-                                         *next_bus->resource[1];
-                                controllers[i].mem_resources[2] =
-                                         *next_bus->resource[2];
-
-                                break;
+        for (i = 0; i < TILE_NUM_PCIE; i++) {
+                /*
+                 * Do real pcibios init ops if the controller is initialized
+                 * by tile_pci_init() successfully and not initialized by
+                 * pcibios_init() yet to support PCIe hot-plug.
+                 */
+                if (pci_scan_flags[i] == 0 && controllers[i].ops != NULL) {
+                        struct pci_bus *root_bus = controllers[i].root_bus;
+                        struct pci_bus *next_bus;
+                        struct pci_dev *dev;
+
+                        list_for_each_entry(dev, &root_bus->devices, bus_list) {
+                                /*
+                                 * Find the PCI host controller, ie. the 1st
+                                 * bridge.
+                                 */
+                                if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI &&
+                                        (PCI_SLOT(dev->devfn) == 0)) {
+                                        next_bus = dev->subordinate;
+                                        controllers[i].mem_resources[0] =
+                                                *next_bus->resource[0];
+                                        controllers[i].mem_resources[1] =
+                                                 *next_bus->resource[1];
+                                        controllers[i].mem_resources[2] =
+                                                 *next_bus->resource[2];
+
+                                        /* Setup flags. */
+                                        pci_scan_flags[i] = 1;
+
+                                        break;
+                                }
                         }
                 }
-
         }
 
         return 0;
@@ -381,7 +407,7 @@ char __devinit *pcibios_setup(char *str)
 /*
  * This is called from the generic Linux layer.
  */
-void __init pcibios_update_irq(struct pci_dev *dev, int irq)
+void __devinit pcibios_update_irq(struct pci_dev *dev, int irq)
 {
         pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
 }
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index d0065103eb7b..9c45d8bbdf57 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -25,10 +25,13 @@
 #include <linux/hardirq.h>
 #include <linux/syscalls.h>
 #include <linux/kernel.h>
+#include <linux/tracehook.h>
+#include <linux/signal.h>
 #include <asm/system.h>
 #include <asm/stack.h>
 #include <asm/homecache.h>
 #include <asm/syscalls.h>
+#include <asm/traps.h>
 #ifdef CONFIG_HARDWALL
 #include <asm/hardwall.h>
 #endif
@@ -546,6 +549,51 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
         return __switch_to(prev, next, next_current_ksp0(next));
 }
 
+/*
+ * This routine is called on return from interrupt if any of the
+ * TIF_WORK_MASK flags are set in thread_info->flags.  It is
+ * entered with interrupts disabled so we don't miss an event
+ * that modified the thread_info flags.  If any flag is set, we
+ * handle it and return, and the calling assembly code will
+ * re-disable interrupts, reload the thread flags, and call back
+ * if more flags need to be handled.
+ *
+ * We return whether we need to check the thread_info flags again
+ * or not.  Note that we don't clear TIF_SINGLESTEP here, so it's
+ * important that it be tested last, and then claim that we don't
+ * need to recheck the flags.
+ */
+int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
+{
+        if (thread_info_flags & _TIF_NEED_RESCHED) {
+                schedule();
+                return 1;
+        }
+#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
+        if (thread_info_flags & _TIF_ASYNC_TLB) {
+                do_async_page_fault(regs);
+                return 1;
+        }
+#endif
+        if (thread_info_flags & _TIF_SIGPENDING) {
+                do_signal(regs);
+                return 1;
+        }
+        if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+                clear_thread_flag(TIF_NOTIFY_RESUME);
+                tracehook_notify_resume(regs);
+                if (current->replacement_session_keyring)
+                        key_replace_session_keyring();
+                return 1;
+        }
+        if (thread_info_flags & _TIF_SINGLESTEP) {
+                if ((regs->ex1 & SPR_EX_CONTEXT_1_1__PL_MASK) == 0)
+                        single_step_once(regs);
+                return 0;
+        }
+        panic("work_pending: bad flags %#x\n", thread_info_flags);
+}
+
 /* Note there is an implicit fifth argument if (clone_flags & CLONE_SETTLS). */
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
                 void __user *, parent_tidptr, void __user *, child_tidptr,
@@ -582,8 +630,8 @@ out:
 
 #ifdef CONFIG_COMPAT
 long compat_sys_execve(const char __user *path,
-                       const compat_uptr_t __user *argv,
-                       const compat_uptr_t __user *envp,
+                       compat_uptr_t __user *argv,
+                       compat_uptr_t __user *envp,
                        struct pt_regs *regs)
 {
         long error;
diff --git a/arch/tile/kernel/regs_64.S b/arch/tile/kernel/regs_64.S
new file mode 100644
index 000000000000..f748c1e85285
--- /dev/null
+++ b/arch/tile/kernel/regs_64.S
@@ -0,0 +1,145 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/system.h>
+#include <asm/ptrace.h>
+#include <asm/asm-offsets.h>
+#include <arch/spr_def.h>
+#include <asm/processor.h>
+
+/*
+ * See <asm/system.h>; called with prev and next task_struct pointers.
+ * "prev" is returned in r0 for _switch_to and also for ret_from_fork.
+ *
+ * We want to save pc/sp in "prev", and get the new pc/sp from "next".
+ * We also need to save all the callee-saved registers on the stack.
+ *
+ * Intel enables/disables access to the hardware cycle counter in
+ * seccomp (secure computing) environments if necessary, based on
+ * has_secure_computing().  We might want to do this at some point,
+ * though it would require virtualizing the other SPRs under WORLD_ACCESS.
+ *
+ * Since we're saving to the stack, we omit sp from this list.
+ * And for parallels with other architectures, we save lr separately,
+ * in the thread_struct itself (as the "pc" field).
+ *
+ * This code also needs to be aligned with process.c copy_thread()
+ */
+
+#if CALLEE_SAVED_REGS_COUNT != 24
+# error Mismatch between <asm/system.h> and kernel/entry.S
+#endif
+#define FRAME_SIZE ((2 + CALLEE_SAVED_REGS_COUNT) * 8)
+
+#define SAVE_REG(r) { st r12, r; addi r12, r12, 8 }
+#define LOAD_REG(r) { ld r, r12; addi r12, r12, 8 }
+#define FOR_EACH_CALLEE_SAVED_REG(f)                                    \
+                                                        f(r30); f(r31); \
+        f(r32); f(r33); f(r34); f(r35); f(r36); f(r37); f(r38); f(r39); \
+        f(r40); f(r41); f(r42); f(r43); f(r44); f(r45); f(r46); f(r47); \
+        f(r48); f(r49); f(r50); f(r51); f(r52);
+
+STD_ENTRY_SECTION(__switch_to, .sched.text)
+        {
+          move r10, sp
+          st sp, lr
+        }
+        {
+          addli r11, sp, -FRAME_SIZE + 8
+          addli sp, sp, -FRAME_SIZE
+        }
+        {
+          st r11, r10
+          addli r4, r1, TASK_STRUCT_THREAD_KSP_OFFSET
+        }
+        {
+          ld r13, r4   /* Load new sp to a temp register early. */
+          addi r12, sp, 16
+        }
+        FOR_EACH_CALLEE_SAVED_REG(SAVE_REG)
+        addli r3, r0, TASK_STRUCT_THREAD_KSP_OFFSET
+        {
+          st r3, sp
+          addli r3, r0, TASK_STRUCT_THREAD_PC_OFFSET
+        }
+        {
+          st r3, lr
+          addli r4, r1, TASK_STRUCT_THREAD_PC_OFFSET
+        }
+        {
+          ld lr, r4
+          addi r12, r13, 16
+        }
+        {
+          /* Update sp and ksp0 simultaneously to avoid backtracer warnings. */
+          move sp, r13
+          mtspr SPR_SYSTEM_SAVE_K_0, r2
+        }
+        FOR_EACH_CALLEE_SAVED_REG(LOAD_REG)
+.L__switch_to_pc:
+        {
+          addli sp, sp, FRAME_SIZE
+          jrp lr   /* r0 is still valid here, so return it */
+        }
+        STD_ENDPROC(__switch_to)
+
+/* Return a suitable address for the backtracer for suspended threads */
+STD_ENTRY_SECTION(get_switch_to_pc, .sched.text)
+        lnk r0
+        {
+          addli r0, r0, .L__switch_to_pc - .
+          jrp lr
+        }
+        STD_ENDPROC(get_switch_to_pc)
+
+STD_ENTRY(get_pt_regs)
+        .irp reg, r0, r1, r2, r3, r4, r5, r6, r7, \
+                 r8, r9, r10, r11, r12, r13, r14, r15, \
+                 r16, r17, r18, r19, r20, r21, r22, r23, \
+                 r24, r25, r26, r27, r28, r29, r30, r31, \
+                 r32, r33, r34, r35, r36, r37, r38, r39, \
+                 r40, r41, r42, r43, r44, r45, r46, r47, \
+                 r48, r49, r50, r51, r52, tp, sp
+        {
+         st r0, \reg
+         addi r0, r0, 8
+        }
+        .endr
+        {
+         st r0, lr
+         addi r0, r0, PTREGS_OFFSET_PC - PTREGS_OFFSET_LR
+        }
+        lnk r1
+        {
+         st r0, r1
+         addi r0, r0, PTREGS_OFFSET_EX1 - PTREGS_OFFSET_PC
+        }
+        mfspr r1, INTERRUPT_CRITICAL_SECTION
+        shli r1, r1, SPR_EX_CONTEXT_1_1__ICS_SHIFT
+        ori r1, r1, KERNEL_PL
+        {
+         st r0, r1
+         addi r0, r0, PTREGS_OFFSET_FAULTNUM - PTREGS_OFFSET_EX1
+        }
+        {
+         st r0, zero       /* clear faultnum */
+         addi r0, r0, PTREGS_OFFSET_ORIG_R0 - PTREGS_OFFSET_FAULTNUM
+        }
+        {
+         st r0, zero       /* clear orig_r0 */
+         addli r0, r0, -PTREGS_OFFSET_ORIG_R0    /* restore r0 to base */
+        }
+        jrp lr
+        STD_ENDPROC(get_pt_regs)
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 3696b1832566..6cdc9ba55fe0 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -912,6 +912,8 @@ void __cpuinit setup_cpu(int boot)
 #endif
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+
 static int __initdata set_initramfs_file;
 static char __initdata initramfs_file[128] = "initramfs.cpio.gz";
 
@@ -969,6 +971,10 @@ void __init free_initrd_mem(unsigned long begin, unsigned long end)
         free_bootmem(__pa(begin), end - begin);
 }
 
+#else
+static inline void load_hv_initrd(void) {}
+#endif /* CONFIG_BLK_DEV_INITRD */
+
 static void __init validate_hv(void)
 {
         /*
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 1260321155f1..bedaf4e9f3a7 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -39,7 +39,6 @@
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-
 SYSCALL_DEFINE3(sigaltstack, const stack_t __user *, uss,
                 stack_t __user *, uoss, struct pt_regs *, regs)
 {
@@ -78,6 +77,13 @@ int restore_sigcontext(struct pt_regs *regs,
         return err;
 }
 
+void signal_fault(const char *type, struct pt_regs *regs,
+                  void __user *frame, int sig)
+{
+        trace_unhandled_signal(type, regs, (unsigned long)frame, SIGSEGV);
+        force_sigsegv(sig, current);
+}
+
 /* The assembly shim for this function arranges to ignore the return value. */
 SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
 {
@@ -105,7 +111,7 @@ SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
         return 0;
 
 badframe:
-        force_sig(SIGSEGV, current);
+        signal_fault("bad sigreturn frame", regs, frame, 0);
         return 0;
 }
 
@@ -231,7 +237,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         return 0;
 
 give_sigsegv:
-        force_sigsegv(sig, current);
+        signal_fault("bad setup frame", regs, frame, sig);
         return -EFAULT;
 }
 
@@ -245,7 +251,6 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 {
         int ret;
 
-
         /* Are we from a system call? */
         if (regs->faultnum == INT_SWINT_1) {
                 /* If so, check system call restarting.. */
@@ -363,3 +368,118 @@ done:
         /* Avoid double syscall restart if there are nested signals. */
         regs->faultnum = INT_SWINT_1_SIGRETURN;
 }
+
+int show_unhandled_signals = 1;
+
+static int __init crashinfo(char *str)
+{
+        unsigned long val;
+        const char *word;
+
+        if (*str == '\0')
+                val = 2;
+        else if (*str != '=' || strict_strtoul(++str, 0, &val) != 0)
+                return 0;
+        show_unhandled_signals = val;
+        switch (show_unhandled_signals) {
+        case 0:
+                word = "No";
+                break;
+        case 1:
+                word = "One-line";
+                break;
+        default:
+                word = "Detailed";
+                break;
+        }
+        pr_info("%s crash reports will be generated on the console\n", word);
+        return 1;
+}
+__setup("crashinfo", crashinfo);
+
+static void dump_mem(void __user *address)
+{
+        void __user *addr;
+        enum { region_size = 256, bytes_per_line = 16 };
+        int i, j, k;
+        int found_readable_mem = 0;
+
+        pr_err("\n");
+        if (!access_ok(VERIFY_READ, address, 1)) {
+                pr_err("Not dumping at address 0x%lx (kernel address)\n",
+                       (unsigned long)address);
+                return;
+        }
+
+        addr = (void __user *)
+                (((unsigned long)address & -bytes_per_line) - region_size/2);
+        if (addr > address)
+                addr = NULL;
+        for (i = 0; i < region_size;
+             addr += bytes_per_line, i += bytes_per_line) {
+                unsigned char buf[bytes_per_line];
+                char line[100];
+                if (copy_from_user(buf, addr, bytes_per_line))
+                        continue;
+                if (!found_readable_mem) {
+                        pr_err("Dumping memory around address 0x%lx:\n",
+                               (unsigned long)address);
+                        found_readable_mem = 1;
+                }
+                j = sprintf(line, REGFMT":", (unsigned long)addr);
+                for (k = 0; k < bytes_per_line; ++k)
+                        j += sprintf(&line[j], " %02x", buf[k]);
+                pr_err("%s\n", line);
+        }
+        if (!found_readable_mem)
+                pr_err("No readable memory around address 0x%lx\n",
+                       (unsigned long)address);
+}
+
+void trace_unhandled_signal(const char *type, struct pt_regs *regs,
+                            unsigned long address, int sig)
+{
+        struct task_struct *tsk = current;
+
+        if (show_unhandled_signals == 0)
+                return;
+
+        /* If the signal is handled, don't show it here. */
+        if (!is_global_init(tsk)) {
+                void __user *handler =
+                        tsk->sighand->action[sig-1].sa.sa_handler;
+                if (handler != SIG_IGN && handler != SIG_DFL)
+                        return;
+        }
+
+        /* Rate-limit the one-line output, not the detailed output. */
+        if (show_unhandled_signals <= 1 && !printk_ratelimit())
+                return;
+
+        printk("%s%s[%d]: %s at %lx pc "REGFMT" signal %d",
+               task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+               tsk->comm, task_pid_nr(tsk), type, address, regs->pc, sig);
+
+        print_vma_addr(KERN_CONT " in ", regs->pc);
+
+        printk(KERN_CONT "\n");
+
+        if (show_unhandled_signals > 1) {
+                switch (sig) {
+                case SIGILL:
+                case SIGFPE:
+                case SIGSEGV:
+                case SIGBUS:
+                        pr_err("User crash: signal %d,"
+                               " trap %ld, address 0x%lx\n",
+                               sig, regs->faultnum, address);
+                        show_regs(regs);
+                        dump_mem((void __user *)address);
+                        break;
+                default:
+                        pr_err("User crash: signal %d, trap %ld\n",
+                               sig, regs->faultnum);
+                        break;
+                }
+        }
+}
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 84a729e06ec4..4032ca8e51b6 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -186,6 +186,8 @@ static tile_bundle_bits rewrite_load_store_unaligned(
                         .si_code = SEGV_MAPERR,
                         .si_addr = addr
                 };
+                trace_unhandled_signal("segfault", regs,
+                                       (unsigned long)addr, SIGSEGV);
                 force_sig_info(info.si_signo, &info, current);
                 return (tile_bundle_bits) 0;
         }
@@ -196,6 +198,8 @@ static tile_bundle_bits rewrite_load_store_unaligned(
                         .si_code = BUS_ADRALN,
                         .si_addr = addr
                 };
+                trace_unhandled_signal("unaligned trap", regs,
+                                       (unsigned long)addr, SIGBUS);
                 force_sig_info(info.si_signo, &info, current);
                 return (tile_bundle_bits) 0;
         }
@@ -318,6 +322,14 @@ void single_step_once(struct pt_regs *regs)
 "    .popsection\n"
         );
 
+        /*
+         * Enable interrupts here to allow touching userspace and the like.
+         * The callers expect this: do_trap() already has interrupts
+         * enabled, and do_work_pending() handles functions that enable
+         * interrupts internally.
+         */
+        local_irq_enable();
+
         if (state == NULL) {
                 /* allocate a page of writable, executable memory */
                 state = kmalloc(sizeof(struct single_step_state), GFP_KERNEL);
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index dd81713a90dc..37ee4d037e0b 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -36,7 +36,7 @@
 #define KBT_LOOP        3  /* Backtrace entered a loop */
 
 /* Is address on the specified kernel stack? */
-static int in_kernel_stack(struct KBacktraceIterator *kbt, VirtualAddress sp)
+static int in_kernel_stack(struct KBacktraceIterator *kbt, unsigned long sp)
 {
         ulong kstack_base = (ulong) kbt->task->stack;
         if (kstack_base == 0)  /* corrupt task pointer; just follow stack... */
@@ -45,7 +45,7 @@ static int in_kernel_stack(struct KBacktraceIterator *kbt, VirtualAddress sp)
 }
 
 /* Is address valid for reading? */
-static int valid_address(struct KBacktraceIterator *kbt, VirtualAddress address)
+static int valid_address(struct KBacktraceIterator *kbt, unsigned long address)
 {
         HV_PTE *l1_pgtable = kbt->pgtable;
         HV_PTE *l2_pgtable;
@@ -97,7 +97,7 @@ static int valid_address(struct KBacktraceIterator *kbt, VirtualAddress address)
 }
 
 /* Callback for backtracer; basically a glorified memcpy */
-static bool read_memory_func(void *result, VirtualAddress address,
+static bool read_memory_func(void *result, unsigned long address,
                              unsigned int size, void *vkbt)
 {
         int retval;
@@ -124,7 +124,7 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 {
         const char *fault = NULL;  /* happy compiler */
         char fault_buf[64];
-        VirtualAddress sp = kbt->it.sp;
+        unsigned long sp = kbt->it.sp;
         struct pt_regs *p;
 
         if (!in_kernel_stack(kbt, sp))
@@ -163,7 +163,7 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 }
 
 /* Is the pc pointing to a sigreturn trampoline? */
-static int is_sigreturn(VirtualAddress pc)
+static int is_sigreturn(unsigned long pc)
 {
         return (pc == VDSO_BASE);
 }
@@ -260,7 +260,7 @@ static void validate_stack(struct pt_regs *regs)
 void KBacktraceIterator_init(struct KBacktraceIterator *kbt,
                              struct task_struct *t, struct pt_regs *regs)
 {
-        VirtualAddress pc, lr, sp, r52;
+        unsigned long pc, lr, sp, r52;
         int is_current;
 
         /*
@@ -331,7 +331,7 @@ EXPORT_SYMBOL(KBacktraceIterator_end);
 
 void KBacktraceIterator_next(struct KBacktraceIterator *kbt)
 {
-        VirtualAddress old_pc = kbt->it.pc, old_sp = kbt->it.sp;
+        unsigned long old_pc = kbt->it.pc, old_sp = kbt->it.sp;
         kbt->new_context = 0;
         if (!backtrace_next(&kbt->it) && !KBacktraceIterator_restart(kbt)) {
                 kbt->end = KBT_DONE;
diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c
index e2187d24a9b4..cb44ba7ccd2d 100644
--- a/arch/tile/kernel/sys.c
+++ b/arch/tile/kernel/sys.c
@@ -56,13 +56,6 @@ ssize_t sys32_readahead(int fd, u32 offset_lo, u32 offset_hi, u32 count)
         return sys_readahead(fd, ((loff_t)offset_hi << 32) | offset_lo, count);
 }
 
-long sys32_fadvise64(int fd, u32 offset_lo, u32 offset_hi,
-                     u32 len, int advice)
-{
-        return sys_fadvise64_64(fd, ((loff_t)offset_hi << 32) | offset_lo,
-                                len, advice);
-}
-
 int sys32_fadvise64_64(int fd, u32 offset_lo, u32 offset_hi,
                        u32 len_lo, u32 len_hi, int advice)
 {
@@ -103,10 +96,8 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 
 #ifndef __tilegx__
 /* See comments at the top of the file. */
-#define sys_fadvise64 sys32_fadvise64
 #define sys_fadvise64_64 sys32_fadvise64_64
 #define sys_readahead sys32_readahead
-#define sys_sync_file_range sys_sync_file_range2
 #endif
 
 /* Call the trampolines to manage pt_regs where necessary. */
diff --git a/arch/tile/kernel/tile-desc_32.c b/arch/tile/kernel/tile-desc_32.c
index 69af0e150f78..7e31a1285788 100644
--- a/arch/tile/kernel/tile-desc_32.c
+++ b/arch/tile/kernel/tile-desc_32.c
@@ -2413,12 +2413,13 @@ const struct tile_operand tile_operands[43] =
 
 
 
-/* Given a set of bundle bits and the lookup FSM for a specific pipe,
- * returns which instruction the bundle contains in that pipe.
+/* Given a set of bundle bits and a specific pipe, returns which
+ * instruction the bundle contains in that pipe.
  */
-static const struct tile_opcode *
-find_opcode(tile_bundle_bits bits, const unsigned short *table)
+const struct tile_opcode *
+find_opcode(tile_bundle_bits bits, tile_pipeline pipe)
 {
+  const unsigned short *table = tile_bundle_decoder_fsms[pipe];
   int index = 0;
 
   while (1)
@@ -2465,7 +2466,7 @@ parse_insn_tile(tile_bundle_bits bits,
     int i;
 
     d = &decoded[num_instructions++];
-    opc = find_opcode (bits, tile_bundle_decoder_fsms[pipe]);
+    opc = find_opcode (bits, (tile_pipeline)pipe);
     d->opcode = opc;
 
     /* Decode each operand, sign extending, etc. as appropriate. */
diff --git a/arch/tile/kernel/tile-desc_64.c b/arch/tile/kernel/tile-desc_64.c
new file mode 100644
index 000000000000..d57007bed77f
--- /dev/null
+++ b/arch/tile/kernel/tile-desc_64.c
@@ -0,0 +1,2200 @@
+/* This define is BFD_RELOC_##x for real bfd, or -1 for everyone else. */
+#define BFD_RELOC(x) -1
+
+/* Special registers. */
+#define TREG_LR 55
+#define TREG_SN 56
+#define TREG_ZERO 63
+
+/* FIXME: Rename this. */
+#include <asm/opcode-tile_64.h>
+
+#include <linux/stddef.h>
+
+const struct tilegx_opcode tilegx_opcodes[334] =
+{
+ { "bpt", TILEGX_OPC_BPT, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "info", TILEGX_OPC_INFO, 0xf, 1, TREG_ZERO, 1,
+    { { 0 }, { 1 }, { 2 }, { 3 }, { 0, } },
+  },
+  { "infol", TILEGX_OPC_INFOL, 0x3, 1, TREG_ZERO, 1,
+    { { 4 }, { 5 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "move", TILEGX_OPC_MOVE, 0xf, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 8, 9 }, { 10, 11 }, { 12, 13 }, { 0, } },
+  },
+  { "movei", TILEGX_OPC_MOVEI, 0xf, 2, TREG_ZERO, 1,
+    { { 6, 0 }, { 8, 1 }, { 10, 2 }, { 12, 3 }, { 0, } },
+  },
+  { "moveli", TILEGX_OPC_MOVELI, 0x3, 2, TREG_ZERO, 1,
+    { { 6, 4 }, { 8, 5 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch", TILEGX_OPC_PREFETCH, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "prefetch_add_l1", TILEGX_OPC_PREFETCH_ADD_L1, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch_add_l1_fault", TILEGX_OPC_PREFETCH_ADD_L1_FAULT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch_add_l2", TILEGX_OPC_PREFETCH_ADD_L2, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch_add_l2_fault", TILEGX_OPC_PREFETCH_ADD_L2_FAULT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch_add_l3", TILEGX_OPC_PREFETCH_ADD_L3, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch_add_l3_fault", TILEGX_OPC_PREFETCH_ADD_L3_FAULT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "prefetch_l1", TILEGX_OPC_PREFETCH_L1, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "prefetch_l1_fault", TILEGX_OPC_PREFETCH_L1_FAULT, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "prefetch_l2", TILEGX_OPC_PREFETCH_L2, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "prefetch_l2_fault", TILEGX_OPC_PREFETCH_L2_FAULT, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "prefetch_l3", TILEGX_OPC_PREFETCH_L3, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "prefetch_l3_fault", TILEGX_OPC_PREFETCH_L3_FAULT, 0x12, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 14 } },
+  },
+  { "raise", TILEGX_OPC_RAISE, 0x2, 0, TREG_ZERO, 1,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "add", TILEGX_OPC_ADD, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "addi", TILEGX_OPC_ADDI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 10, 11, 2 }, { 12, 13, 3 }, { 0, } },
+  },
+  { "addli", TILEGX_OPC_ADDLI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 4 }, { 8, 9, 5 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "addx", TILEGX_OPC_ADDX, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "addxi", TILEGX_OPC_ADDXI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 10, 11, 2 }, { 12, 13, 3 }, { 0, } },
+  },
+  { "addxli", TILEGX_OPC_ADDXLI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 4 }, { 8, 9, 5 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "addxsc", TILEGX_OPC_ADDXSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "and", TILEGX_OPC_AND, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "andi", TILEGX_OPC_ANDI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 10, 11, 2 }, { 12, 13, 3 }, { 0, } },
+  },
+  { "beqz", TILEGX_OPC_BEQZ, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "beqzt", TILEGX_OPC_BEQZT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bfexts", TILEGX_OPC_BFEXTS, 0x1, 4, TREG_ZERO, 1,
+    { { 6, 7, 21, 22 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bfextu", TILEGX_OPC_BFEXTU, 0x1, 4, TREG_ZERO, 1,
+    { { 6, 7, 21, 22 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bfins", TILEGX_OPC_BFINS, 0x1, 4, TREG_ZERO, 1,
+    { { 23, 7, 21, 22 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bgez", TILEGX_OPC_BGEZ, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bgezt", TILEGX_OPC_BGEZT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bgtz", TILEGX_OPC_BGTZ, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bgtzt", TILEGX_OPC_BGTZT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "blbc", TILEGX_OPC_BLBC, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "blbct", TILEGX_OPC_BLBCT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "blbs", TILEGX_OPC_BLBS, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "blbst", TILEGX_OPC_BLBST, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "blez", TILEGX_OPC_BLEZ, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "blezt", TILEGX_OPC_BLEZT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bltz", TILEGX_OPC_BLTZ, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bltzt", TILEGX_OPC_BLTZT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bnez", TILEGX_OPC_BNEZ, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "bnezt", TILEGX_OPC_BNEZT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 20 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "clz", TILEGX_OPC_CLZ, 0x5, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 0, }, { 10, 11 }, { 0, }, { 0, } },
+  },
+  { "cmoveqz", TILEGX_OPC_CMOVEQZ, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "cmovnez", TILEGX_OPC_CMOVNEZ, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "cmpeq", TILEGX_OPC_CMPEQ, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "cmpeqi", TILEGX_OPC_CMPEQI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 10, 11, 2 }, { 12, 13, 3 }, { 0, } },
+  },
+  { "cmpexch", TILEGX_OPC_CMPEXCH, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmpexch4", TILEGX_OPC_CMPEXCH4, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmples", TILEGX_OPC_CMPLES, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "cmpleu", TILEGX_OPC_CMPLEU, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "cmplts", TILEGX_OPC_CMPLTS, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "cmpltsi", TILEGX_OPC_CMPLTSI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 10, 11, 2 }, { 12, 13, 3 }, { 0, } },
+  },
+  { "cmpltu", TILEGX_OPC_CMPLTU, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "cmpltui", TILEGX_OPC_CMPLTUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmpne", TILEGX_OPC_CMPNE, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "cmul", TILEGX_OPC_CMUL, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmula", TILEGX_OPC_CMULA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmulaf", TILEGX_OPC_CMULAF, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmulf", TILEGX_OPC_CMULF, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmulfr", TILEGX_OPC_CMULFR, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmulh", TILEGX_OPC_CMULH, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "cmulhr", TILEGX_OPC_CMULHR, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "crc32_32", TILEGX_OPC_CRC32_32, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "crc32_8", TILEGX_OPC_CRC32_8, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ctz", TILEGX_OPC_CTZ, 0x5, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 0, }, { 10, 11 }, { 0, }, { 0, } },
+  },
+  { "dblalign", TILEGX_OPC_DBLALIGN, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "dblalign2", TILEGX_OPC_DBLALIGN2, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "dblalign4", TILEGX_OPC_DBLALIGN4, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "dblalign6", TILEGX_OPC_DBLALIGN6, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "drain", TILEGX_OPC_DRAIN, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "dtlbpr", TILEGX_OPC_DTLBPR, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "exch", TILEGX_OPC_EXCH, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "exch4", TILEGX_OPC_EXCH4, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_add_flags", TILEGX_OPC_FDOUBLE_ADD_FLAGS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_addsub", TILEGX_OPC_FDOUBLE_ADDSUB, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_mul_flags", TILEGX_OPC_FDOUBLE_MUL_FLAGS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_pack1", TILEGX_OPC_FDOUBLE_PACK1, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_pack2", TILEGX_OPC_FDOUBLE_PACK2, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_sub_flags", TILEGX_OPC_FDOUBLE_SUB_FLAGS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_unpack_max", TILEGX_OPC_FDOUBLE_UNPACK_MAX, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fdouble_unpack_min", TILEGX_OPC_FDOUBLE_UNPACK_MIN, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchadd", TILEGX_OPC_FETCHADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchadd4", TILEGX_OPC_FETCHADD4, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchaddgez", TILEGX_OPC_FETCHADDGEZ, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchaddgez4", TILEGX_OPC_FETCHADDGEZ4, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchand", TILEGX_OPC_FETCHAND, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchand4", TILEGX_OPC_FETCHAND4, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchor", TILEGX_OPC_FETCHOR, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fetchor4", TILEGX_OPC_FETCHOR4, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "finv", TILEGX_OPC_FINV, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "flush", TILEGX_OPC_FLUSH, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "flushwb", TILEGX_OPC_FLUSHWB, 0x2, 0, TREG_ZERO, 1,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fnop", TILEGX_OPC_FNOP, 0xf, 0, TREG_ZERO, 1,
+    { {  }, {  }, {  }, {  }, { 0, } },
+  },
+  { "fsingle_add1", TILEGX_OPC_FSINGLE_ADD1, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fsingle_addsub2", TILEGX_OPC_FSINGLE_ADDSUB2, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fsingle_mul1", TILEGX_OPC_FSINGLE_MUL1, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fsingle_mul2", TILEGX_OPC_FSINGLE_MUL2, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fsingle_pack1", TILEGX_OPC_FSINGLE_PACK1, 0x5, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 0, }, { 10, 11 }, { 0, }, { 0, } },
+  },
+  { "fsingle_pack2", TILEGX_OPC_FSINGLE_PACK2, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "fsingle_sub1", TILEGX_OPC_FSINGLE_SUB1, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "icoh", TILEGX_OPC_ICOH, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ill", TILEGX_OPC_ILL, 0xa, 0, TREG_ZERO, 1,
+    { { 0, }, {  }, { 0, }, {  }, { 0, } },
+  },
+  { "inv", TILEGX_OPC_INV, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "iret", TILEGX_OPC_IRET, 0x2, 0, TREG_ZERO, 1,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "j", TILEGX_OPC_J, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 25 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "jal", TILEGX_OPC_JAL, 0x2, 1, TREG_LR, 1,
+    { { 0, }, { 25 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "jalr", TILEGX_OPC_JALR, 0xa, 1, TREG_LR, 1,
+    { { 0, }, { 9 }, { 0, }, { 13 }, { 0, } },
+  },
+  { "jalrp", TILEGX_OPC_JALRP, 0xa, 1, TREG_LR, 1,
+    { { 0, }, { 9 }, { 0, }, { 13 }, { 0, } },
+  },
+  { "jr", TILEGX_OPC_JR, 0xa, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 13 }, { 0, } },
+  },
+  { "jrp", TILEGX_OPC_JRP, 0xa, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 13 }, { 0, } },
+  },
+  { "ld", TILEGX_OPC_LD, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld1s", TILEGX_OPC_LD1S, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld1s_add", TILEGX_OPC_LD1S_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ld1u", TILEGX_OPC_LD1U, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld1u_add", TILEGX_OPC_LD1U_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ld2s", TILEGX_OPC_LD2S, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld2s_add", TILEGX_OPC_LD2S_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ld2u", TILEGX_OPC_LD2U, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld2u_add", TILEGX_OPC_LD2U_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ld4s", TILEGX_OPC_LD4S, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld4s_add", TILEGX_OPC_LD4S_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ld4u", TILEGX_OPC_LD4U, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 26, 14 } },
+  },
+  { "ld4u_add", TILEGX_OPC_LD4U_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ld_add", TILEGX_OPC_LD_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldna", TILEGX_OPC_LDNA, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldna_add", TILEGX_OPC_LDNA_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt", TILEGX_OPC_LDNT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt1s", TILEGX_OPC_LDNT1S, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt1s_add", TILEGX_OPC_LDNT1S_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt1u", TILEGX_OPC_LDNT1U, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt1u_add", TILEGX_OPC_LDNT1U_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt2s", TILEGX_OPC_LDNT2S, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt2s_add", TILEGX_OPC_LDNT2S_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt2u", TILEGX_OPC_LDNT2U, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt2u_add", TILEGX_OPC_LDNT2U_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt4s", TILEGX_OPC_LDNT4S, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt4s_add", TILEGX_OPC_LDNT4S_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt4u", TILEGX_OPC_LDNT4U, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt4u_add", TILEGX_OPC_LDNT4U_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "ldnt_add", TILEGX_OPC_LDNT_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 8, 15, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "lnk", TILEGX_OPC_LNK, 0xa, 1, TREG_ZERO, 1,
+    { { 0, }, { 8 }, { 0, }, { 12 }, { 0, } },
+  },
+  { "mf", TILEGX_OPC_MF, 0x2, 0, TREG_ZERO, 1,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mfspr", TILEGX_OPC_MFSPR, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 8, 27 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mm", TILEGX_OPC_MM, 0x1, 4, TREG_ZERO, 1,
+    { { 23, 7, 21, 22 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mnz", TILEGX_OPC_MNZ, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "mtspr", TILEGX_OPC_MTSPR, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 28, 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_hs_hs", TILEGX_OPC_MUL_HS_HS, 0x5, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 10, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mul_hs_hu", TILEGX_OPC_MUL_HS_HU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_hs_ls", TILEGX_OPC_MUL_HS_LS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_hs_lu", TILEGX_OPC_MUL_HS_LU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_hu_hu", TILEGX_OPC_MUL_HU_HU, 0x5, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 10, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mul_hu_ls", TILEGX_OPC_MUL_HU_LS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_hu_lu", TILEGX_OPC_MUL_HU_LU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_ls_ls", TILEGX_OPC_MUL_LS_LS, 0x5, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 10, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mul_ls_lu", TILEGX_OPC_MUL_LS_LU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mul_lu_lu", TILEGX_OPC_MUL_LU_LU, 0x5, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 10, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mula_hs_hs", TILEGX_OPC_MULA_HS_HS, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mula_hs_hu", TILEGX_OPC_MULA_HS_HU, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mula_hs_ls", TILEGX_OPC_MULA_HS_LS, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mula_hs_lu", TILEGX_OPC_MULA_HS_LU, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mula_hu_hu", TILEGX_OPC_MULA_HU_HU, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mula_hu_ls", TILEGX_OPC_MULA_HU_LS, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mula_hu_lu", TILEGX_OPC_MULA_HU_LU, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mula_ls_ls", TILEGX_OPC_MULA_LS_LS, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mula_ls_lu", TILEGX_OPC_MULA_LS_LU, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "mula_lu_lu", TILEGX_OPC_MULA_LU_LU, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mulax", TILEGX_OPC_MULAX, 0x5, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 24, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mulx", TILEGX_OPC_MULX, 0x5, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 10, 11, 18 }, { 0, }, { 0, } },
+  },
+  { "mz", TILEGX_OPC_MZ, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "nap", TILEGX_OPC_NAP, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "nop", TILEGX_OPC_NOP, 0xf, 0, TREG_ZERO, 1,
+    { {  }, {  }, {  }, {  }, { 0, } },
+  },
+  { "nor", TILEGX_OPC_NOR, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "or", TILEGX_OPC_OR, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "ori", TILEGX_OPC_ORI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "pcnt", TILEGX_OPC_PCNT, 0x5, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 0, }, { 10, 11 }, { 0, }, { 0, } },
+  },
+  { "revbits", TILEGX_OPC_REVBITS, 0x5, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 0, }, { 10, 11 }, { 0, }, { 0, } },
+  },
+  { "revbytes", TILEGX_OPC_REVBYTES, 0x5, 2, TREG_ZERO, 1,
+    { { 6, 7 }, { 0, }, { 10, 11 }, { 0, }, { 0, } },
+  },
+  { "rotl", TILEGX_OPC_ROTL, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "rotli", TILEGX_OPC_ROTLI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 10, 11, 31 }, { 12, 13, 32 }, { 0, } },
+  },
+  { "shl", TILEGX_OPC_SHL, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shl16insli", TILEGX_OPC_SHL16INSLI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 4 }, { 8, 9, 5 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "shl1add", TILEGX_OPC_SHL1ADD, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shl1addx", TILEGX_OPC_SHL1ADDX, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shl2add", TILEGX_OPC_SHL2ADD, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shl2addx", TILEGX_OPC_SHL2ADDX, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shl3add", TILEGX_OPC_SHL3ADD, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shl3addx", TILEGX_OPC_SHL3ADDX, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shli", TILEGX_OPC_SHLI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 10, 11, 31 }, { 12, 13, 32 }, { 0, } },
+  },
+  { "shlx", TILEGX_OPC_SHLX, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "shlxi", TILEGX_OPC_SHLXI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "shrs", TILEGX_OPC_SHRS, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shrsi", TILEGX_OPC_SHRSI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 10, 11, 31 }, { 12, 13, 32 }, { 0, } },
+  },
+  { "shru", TILEGX_OPC_SHRU, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "shrui", TILEGX_OPC_SHRUI, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 10, 11, 31 }, { 12, 13, 32 }, { 0, } },
+  },
+  { "shrux", TILEGX_OPC_SHRUX, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "shruxi", TILEGX_OPC_SHRUXI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "shufflebytes", TILEGX_OPC_SHUFFLEBYTES, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "st", TILEGX_OPC_ST, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 14, 33 } },
+  },
+  { "st1", TILEGX_OPC_ST1, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 14, 33 } },
+  },
+  { "st1_add", TILEGX_OPC_ST1_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "st2", TILEGX_OPC_ST2, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 14, 33 } },
+  },
+  { "st2_add", TILEGX_OPC_ST2_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "st4", TILEGX_OPC_ST4, 0x12, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 14, 33 } },
+  },
+  { "st4_add", TILEGX_OPC_ST4_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "st_add", TILEGX_OPC_ST_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt", TILEGX_OPC_STNT, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt1", TILEGX_OPC_STNT1, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt1_add", TILEGX_OPC_STNT1_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt2", TILEGX_OPC_STNT2, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt2_add", TILEGX_OPC_STNT2_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt4", TILEGX_OPC_STNT4, 0x2, 2, TREG_ZERO, 1,
+    { { 0, }, { 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt4_add", TILEGX_OPC_STNT4_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "stnt_add", TILEGX_OPC_STNT_ADD, 0x2, 3, TREG_ZERO, 1,
+    { { 0, }, { 15, 17, 34 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "sub", TILEGX_OPC_SUB, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "subx", TILEGX_OPC_SUBX, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "subxsc", TILEGX_OPC_SUBXSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "swint0", TILEGX_OPC_SWINT0, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "swint1", TILEGX_OPC_SWINT1, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "swint2", TILEGX_OPC_SWINT2, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "swint3", TILEGX_OPC_SWINT3, 0x2, 0, TREG_ZERO, 0,
+    { { 0, }, {  }, { 0, }, { 0, }, { 0, } },
+  },
+  { "tblidxb0", TILEGX_OPC_TBLIDXB0, 0x5, 2, TREG_ZERO, 1,
+    { { 23, 7 }, { 0, }, { 24, 11 }, { 0, }, { 0, } },
+  },
+  { "tblidxb1", TILEGX_OPC_TBLIDXB1, 0x5, 2, TREG_ZERO, 1,
+    { { 23, 7 }, { 0, }, { 24, 11 }, { 0, }, { 0, } },
+  },
+  { "tblidxb2", TILEGX_OPC_TBLIDXB2, 0x5, 2, TREG_ZERO, 1,
+    { { 23, 7 }, { 0, }, { 24, 11 }, { 0, }, { 0, } },
+  },
+  { "tblidxb3", TILEGX_OPC_TBLIDXB3, 0x5, 2, TREG_ZERO, 1,
+    { { 23, 7 }, { 0, }, { 24, 11 }, { 0, }, { 0, } },
+  },
+  { "v1add", TILEGX_OPC_V1ADD, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1addi", TILEGX_OPC_V1ADDI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1adduc", TILEGX_OPC_V1ADDUC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1adiffu", TILEGX_OPC_V1ADIFFU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1avgu", TILEGX_OPC_V1AVGU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpeq", TILEGX_OPC_V1CMPEQ, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpeqi", TILEGX_OPC_V1CMPEQI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmples", TILEGX_OPC_V1CMPLES, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpleu", TILEGX_OPC_V1CMPLEU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmplts", TILEGX_OPC_V1CMPLTS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpltsi", TILEGX_OPC_V1CMPLTSI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpltu", TILEGX_OPC_V1CMPLTU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpltui", TILEGX_OPC_V1CMPLTUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1cmpne", TILEGX_OPC_V1CMPNE, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1ddotpu", TILEGX_OPC_V1DDOTPU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1ddotpua", TILEGX_OPC_V1DDOTPUA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1ddotpus", TILEGX_OPC_V1DDOTPUS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1ddotpusa", TILEGX_OPC_V1DDOTPUSA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1dotp", TILEGX_OPC_V1DOTP, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1dotpa", TILEGX_OPC_V1DOTPA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1dotpu", TILEGX_OPC_V1DOTPU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1dotpua", TILEGX_OPC_V1DOTPUA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1dotpus", TILEGX_OPC_V1DOTPUS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1dotpusa", TILEGX_OPC_V1DOTPUSA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1int_h", TILEGX_OPC_V1INT_H, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1int_l", TILEGX_OPC_V1INT_L, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1maxu", TILEGX_OPC_V1MAXU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1maxui", TILEGX_OPC_V1MAXUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1minu", TILEGX_OPC_V1MINU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1minui", TILEGX_OPC_V1MINUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1mnz", TILEGX_OPC_V1MNZ, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1multu", TILEGX_OPC_V1MULTU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1mulu", TILEGX_OPC_V1MULU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1mulus", TILEGX_OPC_V1MULUS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1mz", TILEGX_OPC_V1MZ, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1sadau", TILEGX_OPC_V1SADAU, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1sadu", TILEGX_OPC_V1SADU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1shl", TILEGX_OPC_V1SHL, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1shli", TILEGX_OPC_V1SHLI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1shrs", TILEGX_OPC_V1SHRS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1shrsi", TILEGX_OPC_V1SHRSI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1shru", TILEGX_OPC_V1SHRU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1shrui", TILEGX_OPC_V1SHRUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1sub", TILEGX_OPC_V1SUB, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v1subuc", TILEGX_OPC_V1SUBUC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2add", TILEGX_OPC_V2ADD, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2addi", TILEGX_OPC_V2ADDI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2addsc", TILEGX_OPC_V2ADDSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2adiffs", TILEGX_OPC_V2ADIFFS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2avgs", TILEGX_OPC_V2AVGS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpeq", TILEGX_OPC_V2CMPEQ, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpeqi", TILEGX_OPC_V2CMPEQI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmples", TILEGX_OPC_V2CMPLES, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpleu", TILEGX_OPC_V2CMPLEU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmplts", TILEGX_OPC_V2CMPLTS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpltsi", TILEGX_OPC_V2CMPLTSI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpltu", TILEGX_OPC_V2CMPLTU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpltui", TILEGX_OPC_V2CMPLTUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2cmpne", TILEGX_OPC_V2CMPNE, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2dotp", TILEGX_OPC_V2DOTP, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2dotpa", TILEGX_OPC_V2DOTPA, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2int_h", TILEGX_OPC_V2INT_H, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2int_l", TILEGX_OPC_V2INT_L, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2maxs", TILEGX_OPC_V2MAXS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2maxsi", TILEGX_OPC_V2MAXSI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2mins", TILEGX_OPC_V2MINS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2minsi", TILEGX_OPC_V2MINSI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2mnz", TILEGX_OPC_V2MNZ, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2mulfsc", TILEGX_OPC_V2MULFSC, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2muls", TILEGX_OPC_V2MULS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2mults", TILEGX_OPC_V2MULTS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2mz", TILEGX_OPC_V2MZ, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2packh", TILEGX_OPC_V2PACKH, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2packl", TILEGX_OPC_V2PACKL, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2packuc", TILEGX_OPC_V2PACKUC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2sadas", TILEGX_OPC_V2SADAS, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2sadau", TILEGX_OPC_V2SADAU, 0x1, 3, TREG_ZERO, 1,
+    { { 23, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2sads", TILEGX_OPC_V2SADS, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2sadu", TILEGX_OPC_V2SADU, 0x1, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 0, }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shl", TILEGX_OPC_V2SHL, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shli", TILEGX_OPC_V2SHLI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shlsc", TILEGX_OPC_V2SHLSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shrs", TILEGX_OPC_V2SHRS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shrsi", TILEGX_OPC_V2SHRSI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shru", TILEGX_OPC_V2SHRU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2shrui", TILEGX_OPC_V2SHRUI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 29 }, { 8, 9, 30 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2sub", TILEGX_OPC_V2SUB, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v2subsc", TILEGX_OPC_V2SUBSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4add", TILEGX_OPC_V4ADD, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4addsc", TILEGX_OPC_V4ADDSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4int_h", TILEGX_OPC_V4INT_H, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4int_l", TILEGX_OPC_V4INT_L, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4packsc", TILEGX_OPC_V4PACKSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4shl", TILEGX_OPC_V4SHL, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4shlsc", TILEGX_OPC_V4SHLSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4shrs", TILEGX_OPC_V4SHRS, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4shru", TILEGX_OPC_V4SHRU, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4sub", TILEGX_OPC_V4SUB, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "v4subsc", TILEGX_OPC_V4SUBSC, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "wh64", TILEGX_OPC_WH64, 0x2, 1, TREG_ZERO, 1,
+    { { 0, }, { 9 }, { 0, }, { 0, }, { 0, } },
+  },
+  { "xor", TILEGX_OPC_XOR, 0xf, 3, TREG_ZERO, 1,
+    { { 6, 7, 16 }, { 8, 9, 17 }, { 10, 11, 18 }, { 12, 13, 19 }, { 0, } },
+  },
+  { "xori", TILEGX_OPC_XORI, 0x3, 3, TREG_ZERO, 1,
+    { { 6, 7, 0 }, { 8, 9, 1 }, { 0, }, { 0, }, { 0, } },
+  },
+  { NULL, TILEGX_OPC_NONE, 0, 0, TREG_ZERO, 0, { { 0, } },
+  }
+};
+#define BITFIELD(start, size) ((start) | (((1 << (size)) - 1) << 6))
+#define CHILD(array_index) (TILEGX_OPC_NONE + (array_index))
+
+static const unsigned short decode_X0_fsm[936] =
+{
+  BITFIELD(22, 9) /* index 0 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_BFEXTS,
+  TILEGX_OPC_BFEXTS, TILEGX_OPC_BFEXTS, TILEGX_OPC_BFEXTS, TILEGX_OPC_BFEXTU,
+  TILEGX_OPC_BFEXTU, TILEGX_OPC_BFEXTU, TILEGX_OPC_BFEXTU, TILEGX_OPC_BFINS,
+  TILEGX_OPC_BFINS, TILEGX_OPC_BFINS, TILEGX_OPC_BFINS, TILEGX_OPC_MM,
+  TILEGX_OPC_MM, TILEGX_OPC_MM, TILEGX_OPC_MM, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, CHILD(528), CHILD(578),
+  CHILD(583), CHILD(588), CHILD(593), CHILD(598), TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, CHILD(603), CHILD(620), CHILD(637), CHILD(654), CHILD(671),
+  CHILD(703), CHILD(797), CHILD(814), CHILD(831), CHILD(848), CHILD(865),
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, CHILD(889), TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  CHILD(906), CHILD(906), CHILD(906), CHILD(906), CHILD(906),
+  BITFIELD(6, 2) /* index 513 */,
+  TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, CHILD(518),
+  BITFIELD(8, 2) /* index 518 */,
+  TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, CHILD(523),
+  BITFIELD(10, 2) /* index 523 */,
+  TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_MOVELI,
+  BITFIELD(20, 2) /* index 528 */,
+  TILEGX_OPC_NONE, CHILD(533), TILEGX_OPC_ADDXI, CHILD(548),
+  BITFIELD(6, 2) /* index 533 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(538),
+  BITFIELD(8, 2) /* index 538 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(543),
+  BITFIELD(10, 2) /* index 543 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_MOVEI,
+  BITFIELD(0, 2) /* index 548 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(553),
+  BITFIELD(2, 2) /* index 553 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(558),
+  BITFIELD(4, 2) /* index 558 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(563),
+  BITFIELD(6, 2) /* index 563 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(568),
+  BITFIELD(8, 2) /* index 568 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(573),
+  BITFIELD(10, 2) /* index 573 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_INFO,
+  BITFIELD(20, 2) /* index 578 */,
+  TILEGX_OPC_CMPEQI, TILEGX_OPC_CMPLTSI, TILEGX_OPC_CMPLTUI, TILEGX_OPC_ORI,
+  BITFIELD(20, 2) /* index 583 */,
+  TILEGX_OPC_V1ADDI, TILEGX_OPC_V1CMPEQI, TILEGX_OPC_V1CMPLTSI,
+  TILEGX_OPC_V1CMPLTUI,
+  BITFIELD(20, 2) /* index 588 */,
+  TILEGX_OPC_V1MAXUI, TILEGX_OPC_V1MINUI, TILEGX_OPC_V2ADDI,
+  TILEGX_OPC_V2CMPEQI,
+  BITFIELD(20, 2) /* index 593 */,
+  TILEGX_OPC_V2CMPLTSI, TILEGX_OPC_V2CMPLTUI, TILEGX_OPC_V2MAXSI,
+  TILEGX_OPC_V2MINSI,
+  BITFIELD(20, 2) /* index 598 */,
+  TILEGX_OPC_XORI, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(18, 4) /* index 603 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_ADDXSC, TILEGX_OPC_ADDX, TILEGX_OPC_ADD,
+  TILEGX_OPC_AND, TILEGX_OPC_CMOVEQZ, TILEGX_OPC_CMOVNEZ, TILEGX_OPC_CMPEQ,
+  TILEGX_OPC_CMPLES, TILEGX_OPC_CMPLEU, TILEGX_OPC_CMPLTS, TILEGX_OPC_CMPLTU,
+  TILEGX_OPC_CMPNE, TILEGX_OPC_CMULAF, TILEGX_OPC_CMULA, TILEGX_OPC_CMULFR,
+  BITFIELD(18, 4) /* index 620 */,
+  TILEGX_OPC_CMULF, TILEGX_OPC_CMULHR, TILEGX_OPC_CMULH, TILEGX_OPC_CMUL,
+  TILEGX_OPC_CRC32_32, TILEGX_OPC_CRC32_8, TILEGX_OPC_DBLALIGN2,
+  TILEGX_OPC_DBLALIGN4, TILEGX_OPC_DBLALIGN6, TILEGX_OPC_DBLALIGN,
+  TILEGX_OPC_FDOUBLE_ADDSUB, TILEGX_OPC_FDOUBLE_ADD_FLAGS,
+  TILEGX_OPC_FDOUBLE_MUL_FLAGS, TILEGX_OPC_FDOUBLE_PACK1,
+  TILEGX_OPC_FDOUBLE_PACK2, TILEGX_OPC_FDOUBLE_SUB_FLAGS,
+  BITFIELD(18, 4) /* index 637 */,
+  TILEGX_OPC_FDOUBLE_UNPACK_MAX, TILEGX_OPC_FDOUBLE_UNPACK_MIN,
+  TILEGX_OPC_FSINGLE_ADD1, TILEGX_OPC_FSINGLE_ADDSUB2,
+  TILEGX_OPC_FSINGLE_MUL1, TILEGX_OPC_FSINGLE_MUL2, TILEGX_OPC_FSINGLE_PACK2,
+  TILEGX_OPC_FSINGLE_SUB1, TILEGX_OPC_MNZ, TILEGX_OPC_MULAX,
+  TILEGX_OPC_MULA_HS_HS, TILEGX_OPC_MULA_HS_HU, TILEGX_OPC_MULA_HS_LS,
+  TILEGX_OPC_MULA_HS_LU, TILEGX_OPC_MULA_HU_HU, TILEGX_OPC_MULA_HU_LS,
+  BITFIELD(18, 4) /* index 654 */,
+  TILEGX_OPC_MULA_HU_LU, TILEGX_OPC_MULA_LS_LS, TILEGX_OPC_MULA_LS_LU,
+  TILEGX_OPC_MULA_LU_LU, TILEGX_OPC_MULX, TILEGX_OPC_MUL_HS_HS,
+  TILEGX_OPC_MUL_HS_HU, TILEGX_OPC_MUL_HS_LS, TILEGX_OPC_MUL_HS_LU,
+  TILEGX_OPC_MUL_HU_HU, TILEGX_OPC_MUL_HU_LS, TILEGX_OPC_MUL_HU_LU,
+  TILEGX_OPC_MUL_LS_LS, TILEGX_OPC_MUL_LS_LU, TILEGX_OPC_MUL_LU_LU,
+  TILEGX_OPC_MZ,
+  BITFIELD(18, 4) /* index 671 */,
+  TILEGX_OPC_NOR, CHILD(688), TILEGX_OPC_ROTL, TILEGX_OPC_SHL1ADDX,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL2ADDX, TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL3ADDX, TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHLX, TILEGX_OPC_SHL,
+  TILEGX_OPC_SHRS, TILEGX_OPC_SHRUX, TILEGX_OPC_SHRU, TILEGX_OPC_SHUFFLEBYTES,
+  TILEGX_OPC_SUBXSC,
+  BITFIELD(12, 2) /* index 688 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(693),
+  BITFIELD(14, 2) /* index 693 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(698),
+  BITFIELD(16, 2) /* index 698 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_MOVE,
+  BITFIELD(18, 4) /* index 703 */,
+  TILEGX_OPC_SUBX, TILEGX_OPC_SUB, CHILD(720), TILEGX_OPC_V1ADDUC,
+  TILEGX_OPC_V1ADD, TILEGX_OPC_V1ADIFFU, TILEGX_OPC_V1AVGU,
+  TILEGX_OPC_V1CMPEQ, TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLEU,
+  TILEGX_OPC_V1CMPLTS, TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPNE,
+  TILEGX_OPC_V1DDOTPUSA, TILEGX_OPC_V1DDOTPUS, TILEGX_OPC_V1DOTPA,
+  BITFIELD(12, 4) /* index 720 */,
+  TILEGX_OPC_NONE, CHILD(737), CHILD(742), CHILD(747), CHILD(752), CHILD(757),
+  CHILD(762), CHILD(767), CHILD(772), CHILD(777), CHILD(782), CHILD(787),
+  CHILD(792), TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 737 */,
+  TILEGX_OPC_CLZ, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 742 */,
+  TILEGX_OPC_CTZ, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 747 */,
+  TILEGX_OPC_FNOP, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 752 */,
+  TILEGX_OPC_FSINGLE_PACK1, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 757 */,
+  TILEGX_OPC_NOP, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 762 */,
+  TILEGX_OPC_PCNT, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 767 */,
+  TILEGX_OPC_REVBITS, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 772 */,
+  TILEGX_OPC_REVBYTES, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 777 */,
+  TILEGX_OPC_TBLIDXB0, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 782 */,
+  TILEGX_OPC_TBLIDXB1, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 787 */,
+  TILEGX_OPC_TBLIDXB2, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(16, 2) /* index 792 */,
+  TILEGX_OPC_TBLIDXB3, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(18, 4) /* index 797 */,
+  TILEGX_OPC_V1DOTPUSA, TILEGX_OPC_V1DOTPUS, TILEGX_OPC_V1DOTP,
+  TILEGX_OPC_V1INT_H, TILEGX_OPC_V1INT_L, TILEGX_OPC_V1MAXU,
+  TILEGX_OPC_V1MINU, TILEGX_OPC_V1MNZ, TILEGX_OPC_V1MULTU, TILEGX_OPC_V1MULUS,
+  TILEGX_OPC_V1MULU, TILEGX_OPC_V1MZ, TILEGX_OPC_V1SADAU, TILEGX_OPC_V1SADU,
+  TILEGX_OPC_V1SHL, TILEGX_OPC_V1SHRS,
+  BITFIELD(18, 4) /* index 814 */,
+  TILEGX_OPC_V1SHRU, TILEGX_OPC_V1SUBUC, TILEGX_OPC_V1SUB, TILEGX_OPC_V2ADDSC,
+  TILEGX_OPC_V2ADD, TILEGX_OPC_V2ADIFFS, TILEGX_OPC_V2AVGS,
+  TILEGX_OPC_V2CMPEQ, TILEGX_OPC_V2CMPLES, TILEGX_OPC_V2CMPLEU,
+  TILEGX_OPC_V2CMPLTS, TILEGX_OPC_V2CMPLTU, TILEGX_OPC_V2CMPNE,
+  TILEGX_OPC_V2DOTPA, TILEGX_OPC_V2DOTP, TILEGX_OPC_V2INT_H,
+  BITFIELD(18, 4) /* index 831 */,
+  TILEGX_OPC_V2INT_L, TILEGX_OPC_V2MAXS, TILEGX_OPC_V2MINS, TILEGX_OPC_V2MNZ,
+  TILEGX_OPC_V2MULFSC, TILEGX_OPC_V2MULS, TILEGX_OPC_V2MULTS, TILEGX_OPC_V2MZ,
+  TILEGX_OPC_V2PACKH, TILEGX_OPC_V2PACKL, TILEGX_OPC_V2PACKUC,
+  TILEGX_OPC_V2SADAS, TILEGX_OPC_V2SADAU, TILEGX_OPC_V2SADS,
+  TILEGX_OPC_V2SADU, TILEGX_OPC_V2SHLSC,
+  BITFIELD(18, 4) /* index 848 */,
+  TILEGX_OPC_V2SHL, TILEGX_OPC_V2SHRS, TILEGX_OPC_V2SHRU, TILEGX_OPC_V2SUBSC,
+  TILEGX_OPC_V2SUB, TILEGX_OPC_V4ADDSC, TILEGX_OPC_V4ADD, TILEGX_OPC_V4INT_H,
+  TILEGX_OPC_V4INT_L, TILEGX_OPC_V4PACKSC, TILEGX_OPC_V4SHLSC,
+  TILEGX_OPC_V4SHL, TILEGX_OPC_V4SHRS, TILEGX_OPC_V4SHRU, TILEGX_OPC_V4SUBSC,
+  TILEGX_OPC_V4SUB,
+  BITFIELD(18, 3) /* index 865 */,
+  CHILD(874), CHILD(877), CHILD(880), CHILD(883), CHILD(886), TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(21, 1) /* index 874 */,
+  TILEGX_OPC_XOR, TILEGX_OPC_NONE,
+  BITFIELD(21, 1) /* index 877 */,
+  TILEGX_OPC_V1DDOTPUA, TILEGX_OPC_NONE,
+  BITFIELD(21, 1) /* index 880 */,
+  TILEGX_OPC_V1DDOTPU, TILEGX_OPC_NONE,
+  BITFIELD(21, 1) /* index 883 */,
+  TILEGX_OPC_V1DOTPUA, TILEGX_OPC_NONE,
+  BITFIELD(21, 1) /* index 886 */,
+  TILEGX_OPC_V1DOTPU, TILEGX_OPC_NONE,
+  BITFIELD(18, 4) /* index 889 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_ROTLI, TILEGX_OPC_SHLI, TILEGX_OPC_SHLXI,
+  TILEGX_OPC_SHRSI, TILEGX_OPC_SHRUI, TILEGX_OPC_SHRUXI, TILEGX_OPC_V1SHLI,
+  TILEGX_OPC_V1SHRSI, TILEGX_OPC_V1SHRUI, TILEGX_OPC_V2SHLI,
+  TILEGX_OPC_V2SHRSI, TILEGX_OPC_V2SHRUI, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE,
+  BITFIELD(0, 2) /* index 906 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(911),
+  BITFIELD(2, 2) /* index 911 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(916),
+  BITFIELD(4, 2) /* index 916 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(921),
+  BITFIELD(6, 2) /* index 921 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(926),
+  BITFIELD(8, 2) /* index 926 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(931),
+  BITFIELD(10, 2) /* index 931 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  TILEGX_OPC_INFOL,
+};
+
+static const unsigned short decode_X1_fsm[1206] =
+{
+  BITFIELD(53, 9) /* index 0 */,
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513), CHILD(513),
+  CHILD(513), CHILD(513), CHILD(513), CHILD(513), TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI,
+  TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_ADDXLI, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_BEQZT,
+  TILEGX_OPC_BEQZT, TILEGX_OPC_BEQZ, TILEGX_OPC_BEQZ, TILEGX_OPC_BGEZT,
+  TILEGX_OPC_BGEZT, TILEGX_OPC_BGEZ, TILEGX_OPC_BGEZ, TILEGX_OPC_BGTZT,
+  TILEGX_OPC_BGTZT, TILEGX_OPC_BGTZ, TILEGX_OPC_BGTZ, TILEGX_OPC_BLBCT,
+  TILEGX_OPC_BLBCT, TILEGX_OPC_BLBC, TILEGX_OPC_BLBC, TILEGX_OPC_BLBST,
+  TILEGX_OPC_BLBST, TILEGX_OPC_BLBS, TILEGX_OPC_BLBS, TILEGX_OPC_BLEZT,
+  TILEGX_OPC_BLEZT, TILEGX_OPC_BLEZ, TILEGX_OPC_BLEZ, TILEGX_OPC_BLTZT,
+  TILEGX_OPC_BLTZT, TILEGX_OPC_BLTZ, TILEGX_OPC_BLTZ, TILEGX_OPC_BNEZT,
+  TILEGX_OPC_BNEZT, TILEGX_OPC_BNEZ, TILEGX_OPC_BNEZ, CHILD(528), CHILD(578),
+  CHILD(598), CHILD(663), CHILD(683), CHILD(688), CHILD(693), CHILD(698),
+  CHILD(703), CHILD(708), CHILD(713), CHILD(718), TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL,
+  TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_JAL, TILEGX_OPC_J, TILEGX_OPC_J,
+  TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J,
+  TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J,
+  TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J,
+  TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J,
+  TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J,
+  TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J, TILEGX_OPC_J,
+  CHILD(723), CHILD(740), CHILD(772), CHILD(789), CHILD(1108), CHILD(1125),
+  CHILD(1142), TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, CHILD(1159), TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176), CHILD(1176),
+  CHILD(1176),
+  BITFIELD(37, 2) /* index 513 */,
+  TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, CHILD(518),
+  BITFIELD(39, 2) /* index 518 */,
+  TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, CHILD(523),
+  BITFIELD(41, 2) /* index 523 */,
+  TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_ADDLI, TILEGX_OPC_MOVELI,
+  BITFIELD(51, 2) /* index 528 */,
+  TILEGX_OPC_NONE, CHILD(533), TILEGX_OPC_ADDXI, CHILD(548),
+  BITFIELD(37, 2) /* index 533 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(538),
+  BITFIELD(39, 2) /* index 538 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(543),
+  BITFIELD(41, 2) /* index 543 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_MOVEI,
+  BITFIELD(31, 2) /* index 548 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(553),
+  BITFIELD(33, 2) /* index 553 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(558),
+  BITFIELD(35, 2) /* index 558 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(563),
+  BITFIELD(37, 2) /* index 563 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(568),
+  BITFIELD(39, 2) /* index 568 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(573),
+  BITFIELD(41, 2) /* index 573 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_INFO,
+  BITFIELD(51, 2) /* index 578 */,
+  TILEGX_OPC_CMPEQI, TILEGX_OPC_CMPLTSI, TILEGX_OPC_CMPLTUI, CHILD(583),
+  BITFIELD(31, 2) /* index 583 */,
+  TILEGX_OPC_LD1S_ADD, TILEGX_OPC_LD1S_ADD, TILEGX_OPC_LD1S_ADD, CHILD(588),
+  BITFIELD(33, 2) /* index 588 */,
+  TILEGX_OPC_LD1S_ADD, TILEGX_OPC_LD1S_ADD, TILEGX_OPC_LD1S_ADD, CHILD(593),
+  BITFIELD(35, 2) /* index 593 */,
+  TILEGX_OPC_LD1S_ADD, TILEGX_OPC_LD1S_ADD, TILEGX_OPC_LD1S_ADD,
+  TILEGX_OPC_PREFETCH_ADD_L1_FAULT,
+  BITFIELD(51, 2) /* index 598 */,
+  CHILD(603), CHILD(618), CHILD(633), CHILD(648),
+  BITFIELD(31, 2) /* index 603 */,
+  TILEGX_OPC_LD1U_ADD, TILEGX_OPC_LD1U_ADD, TILEGX_OPC_LD1U_ADD, CHILD(608),
+  BITFIELD(33, 2) /* index 608 */,
+  TILEGX_OPC_LD1U_ADD, TILEGX_OPC_LD1U_ADD, TILEGX_OPC_LD1U_ADD, CHILD(613),
+  BITFIELD(35, 2) /* index 613 */,
+  TILEGX_OPC_LD1U_ADD, TILEGX_OPC_LD1U_ADD, TILEGX_OPC_LD1U_ADD,
+  TILEGX_OPC_PREFETCH_ADD_L1,
+  BITFIELD(31, 2) /* index 618 */,
+  TILEGX_OPC_LD2S_ADD, TILEGX_OPC_LD2S_ADD, TILEGX_OPC_LD2S_ADD, CHILD(623),
+  BITFIELD(33, 2) /* index 623 */,
+  TILEGX_OPC_LD2S_ADD, TILEGX_OPC_LD2S_ADD, TILEGX_OPC_LD2S_ADD, CHILD(628),
+  BITFIELD(35, 2) /* index 628 */,
+  TILEGX_OPC_LD2S_ADD, TILEGX_OPC_LD2S_ADD, TILEGX_OPC_LD2S_ADD,
+  TILEGX_OPC_PREFETCH_ADD_L2_FAULT,
+  BITFIELD(31, 2) /* index 633 */,
+  TILEGX_OPC_LD2U_ADD, TILEGX_OPC_LD2U_ADD, TILEGX_OPC_LD2U_ADD, CHILD(638),
+  BITFIELD(33, 2) /* index 638 */,
+  TILEGX_OPC_LD2U_ADD, TILEGX_OPC_LD2U_ADD, TILEGX_OPC_LD2U_ADD, CHILD(643),
+  BITFIELD(35, 2) /* index 643 */,
+  TILEGX_OPC_LD2U_ADD, TILEGX_OPC_LD2U_ADD, TILEGX_OPC_LD2U_ADD,
+  TILEGX_OPC_PREFETCH_ADD_L2,
+  BITFIELD(31, 2) /* index 648 */,
+  TILEGX_OPC_LD4S_ADD, TILEGX_OPC_LD4S_ADD, TILEGX_OPC_LD4S_ADD, CHILD(653),
+  BITFIELD(33, 2) /* index 653 */,
+  TILEGX_OPC_LD4S_ADD, TILEGX_OPC_LD4S_ADD, TILEGX_OPC_LD4S_ADD, CHILD(658),
+  BITFIELD(35, 2) /* index 658 */,
+  TILEGX_OPC_LD4S_ADD, TILEGX_OPC_LD4S_ADD, TILEGX_OPC_LD4S_ADD,
+  TILEGX_OPC_PREFETCH_ADD_L3_FAULT,
+  BITFIELD(51, 2) /* index 663 */,
+  CHILD(668), TILEGX_OPC_LDNT1S_ADD, TILEGX_OPC_LDNT1U_ADD,
+  TILEGX_OPC_LDNT2S_ADD,
+  BITFIELD(31, 2) /* index 668 */,
+  TILEGX_OPC_LD4U_ADD, TILEGX_OPC_LD4U_ADD, TILEGX_OPC_LD4U_ADD, CHILD(673),
+  BITFIELD(33, 2) /* index 673 */,
+  TILEGX_OPC_LD4U_ADD, TILEGX_OPC_LD4U_ADD, TILEGX_OPC_LD4U_ADD, CHILD(678),
+  BITFIELD(35, 2) /* index 678 */,
+  TILEGX_OPC_LD4U_ADD, TILEGX_OPC_LD4U_ADD, TILEGX_OPC_LD4U_ADD,
+  TILEGX_OPC_PREFETCH_ADD_L3,
+  BITFIELD(51, 2) /* index 683 */,
+  TILEGX_OPC_LDNT2U_ADD, TILEGX_OPC_LDNT4S_ADD, TILEGX_OPC_LDNT4U_ADD,
+  TILEGX_OPC_LDNT_ADD,
+  BITFIELD(51, 2) /* index 688 */,
+  TILEGX_OPC_LD_ADD, TILEGX_OPC_LDNA_ADD, TILEGX_OPC_MFSPR, TILEGX_OPC_MTSPR,
+  BITFIELD(51, 2) /* index 693 */,
+  TILEGX_OPC_ORI, TILEGX_OPC_ST1_ADD, TILEGX_OPC_ST2_ADD, TILEGX_OPC_ST4_ADD,
+  BITFIELD(51, 2) /* index 698 */,
+  TILEGX_OPC_STNT1_ADD, TILEGX_OPC_STNT2_ADD, TILEGX_OPC_STNT4_ADD,
+  TILEGX_OPC_STNT_ADD,
+  BITFIELD(51, 2) /* index 703 */,
+  TILEGX_OPC_ST_ADD, TILEGX_OPC_V1ADDI, TILEGX_OPC_V1CMPEQI,
+  TILEGX_OPC_V1CMPLTSI,
+  BITFIELD(51, 2) /* index 708 */,
+  TILEGX_OPC_V1CMPLTUI, TILEGX_OPC_V1MAXUI, TILEGX_OPC_V1MINUI,
+  TILEGX_OPC_V2ADDI,
+  BITFIELD(51, 2) /* index 713 */,
+  TILEGX_OPC_V2CMPEQI, TILEGX_OPC_V2CMPLTSI, TILEGX_OPC_V2CMPLTUI,
+  TILEGX_OPC_V2MAXSI,
+  BITFIELD(51, 2) /* index 718 */,
+  TILEGX_OPC_V2MINSI, TILEGX_OPC_XORI, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(49, 4) /* index 723 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_ADDXSC, TILEGX_OPC_ADDX, TILEGX_OPC_ADD,
+  TILEGX_OPC_AND, TILEGX_OPC_CMPEQ, TILEGX_OPC_CMPEXCH4, TILEGX_OPC_CMPEXCH,
+  TILEGX_OPC_CMPLES, TILEGX_OPC_CMPLEU, TILEGX_OPC_CMPLTS, TILEGX_OPC_CMPLTU,
+  TILEGX_OPC_CMPNE, TILEGX_OPC_DBLALIGN2, TILEGX_OPC_DBLALIGN4,
+  TILEGX_OPC_DBLALIGN6,
+  BITFIELD(49, 4) /* index 740 */,
+  TILEGX_OPC_EXCH4, TILEGX_OPC_EXCH, TILEGX_OPC_FETCHADD4,
+  TILEGX_OPC_FETCHADDGEZ4, TILEGX_OPC_FETCHADDGEZ, TILEGX_OPC_FETCHADD,
+  TILEGX_OPC_FETCHAND4, TILEGX_OPC_FETCHAND, TILEGX_OPC_FETCHOR4,
+  TILEGX_OPC_FETCHOR, TILEGX_OPC_MNZ, TILEGX_OPC_MZ, TILEGX_OPC_NOR,
+  CHILD(757), TILEGX_OPC_ROTL, TILEGX_OPC_SHL1ADDX,
+  BITFIELD(43, 2) /* index 757 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(762),
+  BITFIELD(45, 2) /* index 762 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(767),
+  BITFIELD(47, 2) /* index 767 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_MOVE,
+  BITFIELD(49, 4) /* index 772 */,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL2ADDX, TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL3ADDX, TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHLX, TILEGX_OPC_SHL,
+  TILEGX_OPC_SHRS, TILEGX_OPC_SHRUX, TILEGX_OPC_SHRU, TILEGX_OPC_ST1,
+  TILEGX_OPC_ST2, TILEGX_OPC_ST4, TILEGX_OPC_STNT1, TILEGX_OPC_STNT2,
+  TILEGX_OPC_STNT4,
+  BITFIELD(46, 7) /* index 789 */,
+  TILEGX_OPC_STNT, TILEGX_OPC_STNT, TILEGX_OPC_STNT, TILEGX_OPC_STNT,
+  TILEGX_OPC_STNT, TILEGX_OPC_STNT, TILEGX_OPC_STNT, TILEGX_OPC_STNT,
+  TILEGX_OPC_ST, TILEGX_OPC_ST, TILEGX_OPC_ST, TILEGX_OPC_ST, TILEGX_OPC_ST,
+  TILEGX_OPC_ST, TILEGX_OPC_ST, TILEGX_OPC_ST, TILEGX_OPC_SUBXSC,
+  TILEGX_OPC_SUBXSC, TILEGX_OPC_SUBXSC, TILEGX_OPC_SUBXSC, TILEGX_OPC_SUBXSC,
+  TILEGX_OPC_SUBXSC, TILEGX_OPC_SUBXSC, TILEGX_OPC_SUBXSC, TILEGX_OPC_SUBX,
+  TILEGX_OPC_SUBX, TILEGX_OPC_SUBX, TILEGX_OPC_SUBX, TILEGX_OPC_SUBX,
+  TILEGX_OPC_SUBX, TILEGX_OPC_SUBX, TILEGX_OPC_SUBX, TILEGX_OPC_SUB,
+  TILEGX_OPC_SUB, TILEGX_OPC_SUB, TILEGX_OPC_SUB, TILEGX_OPC_SUB,
+  TILEGX_OPC_SUB, TILEGX_OPC_SUB, TILEGX_OPC_SUB, CHILD(918), CHILD(927),
+  CHILD(1006), CHILD(1090), CHILD(1099), TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_V1ADDUC, TILEGX_OPC_V1ADDUC, TILEGX_OPC_V1ADDUC,
+  TILEGX_OPC_V1ADDUC, TILEGX_OPC_V1ADDUC, TILEGX_OPC_V1ADDUC,
+  TILEGX_OPC_V1ADDUC, TILEGX_OPC_V1ADDUC, TILEGX_OPC_V1ADD, TILEGX_OPC_V1ADD,
+  TILEGX_OPC_V1ADD, TILEGX_OPC_V1ADD, TILEGX_OPC_V1ADD, TILEGX_OPC_V1ADD,
+  TILEGX_OPC_V1ADD, TILEGX_OPC_V1ADD, TILEGX_OPC_V1CMPEQ, TILEGX_OPC_V1CMPEQ,
+  TILEGX_OPC_V1CMPEQ, TILEGX_OPC_V1CMPEQ, TILEGX_OPC_V1CMPEQ,
+  TILEGX_OPC_V1CMPEQ, TILEGX_OPC_V1CMPEQ, TILEGX_OPC_V1CMPEQ,
+  TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLES,
+  TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLES,
+  TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLES, TILEGX_OPC_V1CMPLEU,
+  TILEGX_OPC_V1CMPLEU, TILEGX_OPC_V1CMPLEU, TILEGX_OPC_V1CMPLEU,
+  TILEGX_OPC_V1CMPLEU, TILEGX_OPC_V1CMPLEU, TILEGX_OPC_V1CMPLEU,
+  TILEGX_OPC_V1CMPLEU, TILEGX_OPC_V1CMPLTS, TILEGX_OPC_V1CMPLTS,
+  TILEGX_OPC_V1CMPLTS, TILEGX_OPC_V1CMPLTS, TILEGX_OPC_V1CMPLTS,
+  TILEGX_OPC_V1CMPLTS, TILEGX_OPC_V1CMPLTS, TILEGX_OPC_V1CMPLTS,
+  TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPLTU,
+  TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPLTU,
+  TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPLTU, TILEGX_OPC_V1CMPNE,
+  TILEGX_OPC_V1CMPNE, TILEGX_OPC_V1CMPNE, TILEGX_OPC_V1CMPNE,
+  TILEGX_OPC_V1CMPNE, TILEGX_OPC_V1CMPNE, TILEGX_OPC_V1CMPNE,
+  TILEGX_OPC_V1CMPNE, TILEGX_OPC_V1INT_H, TILEGX_OPC_V1INT_H,
+  TILEGX_OPC_V1INT_H, TILEGX_OPC_V1INT_H, TILEGX_OPC_V1INT_H,
+  TILEGX_OPC_V1INT_H, TILEGX_OPC_V1INT_H, TILEGX_OPC_V1INT_H,
+  TILEGX_OPC_V1INT_L, TILEGX_OPC_V1INT_L, TILEGX_OPC_V1INT_L,
+  TILEGX_OPC_V1INT_L, TILEGX_OPC_V1INT_L, TILEGX_OPC_V1INT_L,
+  TILEGX_OPC_V1INT_L, TILEGX_OPC_V1INT_L,
+  BITFIELD(43, 3) /* index 918 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_DRAIN, TILEGX_OPC_DTLBPR, TILEGX_OPC_FINV,
+  TILEGX_OPC_FLUSHWB, TILEGX_OPC_FLUSH, TILEGX_OPC_FNOP, TILEGX_OPC_ICOH,
+  BITFIELD(43, 3) /* index 927 */,
+  CHILD(936), TILEGX_OPC_INV, TILEGX_OPC_IRET, TILEGX_OPC_JALRP,
+  TILEGX_OPC_JALR, TILEGX_OPC_JRP, TILEGX_OPC_JR, CHILD(991),
+  BITFIELD(31, 2) /* index 936 */,
+  CHILD(941), CHILD(966), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(33, 2) /* index 941 */,
+  TILEGX_OPC_ILL, TILEGX_OPC_ILL, TILEGX_OPC_ILL, CHILD(946),
+  BITFIELD(35, 2) /* index 946 */,
+  TILEGX_OPC_ILL, CHILD(951), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(37, 2) /* index 951 */,
+  TILEGX_OPC_ILL, CHILD(956), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(39, 2) /* index 956 */,
+  TILEGX_OPC_ILL, CHILD(961), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(41, 2) /* index 961 */,
+  TILEGX_OPC_ILL, TILEGX_OPC_ILL, TILEGX_OPC_BPT, TILEGX_OPC_ILL,
+  BITFIELD(33, 2) /* index 966 */,
+  TILEGX_OPC_ILL, TILEGX_OPC_ILL, TILEGX_OPC_ILL, CHILD(971),
+  BITFIELD(35, 2) /* index 971 */,
+  TILEGX_OPC_ILL, CHILD(976), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(37, 2) /* index 976 */,
+  TILEGX_OPC_ILL, CHILD(981), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(39, 2) /* index 981 */,
+  TILEGX_OPC_ILL, CHILD(986), TILEGX_OPC_ILL, TILEGX_OPC_ILL,
+  BITFIELD(41, 2) /* index 986 */,
+  TILEGX_OPC_ILL, TILEGX_OPC_ILL, TILEGX_OPC_RAISE, TILEGX_OPC_ILL,
+  BITFIELD(31, 2) /* index 991 */,
+  TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, CHILD(996),
+  BITFIELD(33, 2) /* index 996 */,
+  TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, CHILD(1001),
+  BITFIELD(35, 2) /* index 1001 */,
+  TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, TILEGX_OPC_LD1S,
+  TILEGX_OPC_PREFETCH_L1_FAULT,
+  BITFIELD(43, 3) /* index 1006 */,
+  CHILD(1015), CHILD(1030), CHILD(1045), CHILD(1060), CHILD(1075),
+  TILEGX_OPC_LDNA, TILEGX_OPC_LDNT1S, TILEGX_OPC_LDNT1U,
+  BITFIELD(31, 2) /* index 1015 */,
+  TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, CHILD(1020),
+  BITFIELD(33, 2) /* index 1020 */,
+  TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, CHILD(1025),
+  BITFIELD(35, 2) /* index 1025 */,
+  TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_PREFETCH,
+  BITFIELD(31, 2) /* index 1030 */,
+  TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, CHILD(1035),
+  BITFIELD(33, 2) /* index 1035 */,
+  TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, CHILD(1040),
+  BITFIELD(35, 2) /* index 1040 */,
+  TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, TILEGX_OPC_LD2S,
+  TILEGX_OPC_PREFETCH_L2_FAULT,
+  BITFIELD(31, 2) /* index 1045 */,
+  TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, CHILD(1050),
+  BITFIELD(33, 2) /* index 1050 */,
+  TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, CHILD(1055),
+  BITFIELD(35, 2) /* index 1055 */,
+  TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_PREFETCH_L2,
+  BITFIELD(31, 2) /* index 1060 */,
+  TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, CHILD(1065),
+  BITFIELD(33, 2) /* index 1065 */,
+  TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, CHILD(1070),
+  BITFIELD(35, 2) /* index 1070 */,
+  TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, TILEGX_OPC_LD4S,
+  TILEGX_OPC_PREFETCH_L3_FAULT,
+  BITFIELD(31, 2) /* index 1075 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, CHILD(1080),
+  BITFIELD(33, 2) /* index 1080 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, CHILD(1085),
+  BITFIELD(35, 2) /* index 1085 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, TILEGX_OPC_PREFETCH_L3,
+  BITFIELD(43, 3) /* index 1090 */,
+  TILEGX_OPC_LDNT2S, TILEGX_OPC_LDNT2U, TILEGX_OPC_LDNT4S, TILEGX_OPC_LDNT4U,
+  TILEGX_OPC_LDNT, TILEGX_OPC_LD, TILEGX_OPC_LNK, TILEGX_OPC_MF,
+  BITFIELD(43, 3) /* index 1099 */,
+  TILEGX_OPC_NAP, TILEGX_OPC_NOP, TILEGX_OPC_SWINT0, TILEGX_OPC_SWINT1,
+  TILEGX_OPC_SWINT2, TILEGX_OPC_SWINT3, TILEGX_OPC_WH64, TILEGX_OPC_NONE,
+  BITFIELD(49, 4) /* index 1108 */,
+  TILEGX_OPC_V1MAXU, TILEGX_OPC_V1MINU, TILEGX_OPC_V1MNZ, TILEGX_OPC_V1MZ,
+  TILEGX_OPC_V1SHL, TILEGX_OPC_V1SHRS, TILEGX_OPC_V1SHRU, TILEGX_OPC_V1SUBUC,
+  TILEGX_OPC_V1SUB, TILEGX_OPC_V2ADDSC, TILEGX_OPC_V2ADD, TILEGX_OPC_V2CMPEQ,
+  TILEGX_OPC_V2CMPLES, TILEGX_OPC_V2CMPLEU, TILEGX_OPC_V2CMPLTS,
+  TILEGX_OPC_V2CMPLTU,
+  BITFIELD(49, 4) /* index 1125 */,
+  TILEGX_OPC_V2CMPNE, TILEGX_OPC_V2INT_H, TILEGX_OPC_V2INT_L,
+  TILEGX_OPC_V2MAXS, TILEGX_OPC_V2MINS, TILEGX_OPC_V2MNZ, TILEGX_OPC_V2MZ,
+  TILEGX_OPC_V2PACKH, TILEGX_OPC_V2PACKL, TILEGX_OPC_V2PACKUC,
+  TILEGX_OPC_V2SHLSC, TILEGX_OPC_V2SHL, TILEGX_OPC_V2SHRS, TILEGX_OPC_V2SHRU,
+  TILEGX_OPC_V2SUBSC, TILEGX_OPC_V2SUB,
+  BITFIELD(49, 4) /* index 1142 */,
+  TILEGX_OPC_V4ADDSC, TILEGX_OPC_V4ADD, TILEGX_OPC_V4INT_H,
+  TILEGX_OPC_V4INT_L, TILEGX_OPC_V4PACKSC, TILEGX_OPC_V4SHLSC,
+  TILEGX_OPC_V4SHL, TILEGX_OPC_V4SHRS, TILEGX_OPC_V4SHRU, TILEGX_OPC_V4SUBSC,
+  TILEGX_OPC_V4SUB, TILEGX_OPC_XOR, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(49, 4) /* index 1159 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_ROTLI, TILEGX_OPC_SHLI, TILEGX_OPC_SHLXI,
+  TILEGX_OPC_SHRSI, TILEGX_OPC_SHRUI, TILEGX_OPC_SHRUXI, TILEGX_OPC_V1SHLI,
+  TILEGX_OPC_V1SHRSI, TILEGX_OPC_V1SHRUI, TILEGX_OPC_V2SHLI,
+  TILEGX_OPC_V2SHRSI, TILEGX_OPC_V2SHRUI, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE,
+  BITFIELD(31, 2) /* index 1176 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(1181),
+  BITFIELD(33, 2) /* index 1181 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(1186),
+  BITFIELD(35, 2) /* index 1186 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(1191),
+  BITFIELD(37, 2) /* index 1191 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(1196),
+  BITFIELD(39, 2) /* index 1196 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  CHILD(1201),
+  BITFIELD(41, 2) /* index 1201 */,
+  TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI, TILEGX_OPC_SHL16INSLI,
+  TILEGX_OPC_INFOL,
+};
+
+static const unsigned short decode_Y0_fsm[178] =
+{
+  BITFIELD(27, 4) /* index 0 */,
+  CHILD(17), TILEGX_OPC_ADDXI, CHILD(32), TILEGX_OPC_CMPEQI,
+  TILEGX_OPC_CMPLTSI, CHILD(62), CHILD(67), CHILD(118), CHILD(123),
+  CHILD(128), CHILD(133), CHILD(153), CHILD(158), CHILD(163), CHILD(168),
+  CHILD(173),
+  BITFIELD(6, 2) /* index 17 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(22),
+  BITFIELD(8, 2) /* index 22 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(27),
+  BITFIELD(10, 2) /* index 27 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_MOVEI,
+  BITFIELD(0, 2) /* index 32 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(37),
+  BITFIELD(2, 2) /* index 37 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(42),
+  BITFIELD(4, 2) /* index 42 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(47),
+  BITFIELD(6, 2) /* index 47 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(52),
+  BITFIELD(8, 2) /* index 52 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(57),
+  BITFIELD(10, 2) /* index 57 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_INFO,
+  BITFIELD(18, 2) /* index 62 */,
+  TILEGX_OPC_ADDX, TILEGX_OPC_ADD, TILEGX_OPC_SUBX, TILEGX_OPC_SUB,
+  BITFIELD(15, 5) /* index 67 */,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD,
+  TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD,
+  TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD, CHILD(100),
+  CHILD(109), TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(12, 3) /* index 100 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_CLZ, TILEGX_OPC_CTZ, TILEGX_OPC_FNOP,
+  TILEGX_OPC_FSINGLE_PACK1, TILEGX_OPC_NOP, TILEGX_OPC_PCNT,
+  TILEGX_OPC_REVBITS,
+  BITFIELD(12, 3) /* index 109 */,
+  TILEGX_OPC_REVBYTES, TILEGX_OPC_TBLIDXB0, TILEGX_OPC_TBLIDXB1,
+  TILEGX_OPC_TBLIDXB2, TILEGX_OPC_TBLIDXB3, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  TILEGX_OPC_NONE,
+  BITFIELD(18, 2) /* index 118 */,
+  TILEGX_OPC_CMPLES, TILEGX_OPC_CMPLEU, TILEGX_OPC_CMPLTS, TILEGX_OPC_CMPLTU,
+  BITFIELD(18, 2) /* index 123 */,
+  TILEGX_OPC_CMPEQ, TILEGX_OPC_CMPNE, TILEGX_OPC_MULAX, TILEGX_OPC_MULX,
+  BITFIELD(18, 2) /* index 128 */,
+  TILEGX_OPC_CMOVEQZ, TILEGX_OPC_CMOVNEZ, TILEGX_OPC_MNZ, TILEGX_OPC_MZ,
+  BITFIELD(18, 2) /* index 133 */,
+  TILEGX_OPC_AND, TILEGX_OPC_NOR, CHILD(138), TILEGX_OPC_XOR,
+  BITFIELD(12, 2) /* index 138 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(143),
+  BITFIELD(14, 2) /* index 143 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(148),
+  BITFIELD(16, 2) /* index 148 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_MOVE,
+  BITFIELD(18, 2) /* index 153 */,
+  TILEGX_OPC_ROTL, TILEGX_OPC_SHL, TILEGX_OPC_SHRS, TILEGX_OPC_SHRU,
+  BITFIELD(18, 2) /* index 158 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_SHL1ADDX, TILEGX_OPC_SHL2ADDX,
+  TILEGX_OPC_SHL3ADDX,
+  BITFIELD(18, 2) /* index 163 */,
+  TILEGX_OPC_MUL_HS_HS, TILEGX_OPC_MUL_HU_HU, TILEGX_OPC_MUL_LS_LS,
+  TILEGX_OPC_MUL_LU_LU,
+  BITFIELD(18, 2) /* index 168 */,
+  TILEGX_OPC_MULA_HS_HS, TILEGX_OPC_MULA_HU_HU, TILEGX_OPC_MULA_LS_LS,
+  TILEGX_OPC_MULA_LU_LU,
+  BITFIELD(18, 2) /* index 173 */,
+  TILEGX_OPC_ROTLI, TILEGX_OPC_SHLI, TILEGX_OPC_SHRSI, TILEGX_OPC_SHRUI,
+};
+
+static const unsigned short decode_Y1_fsm[167] =
+{
+  BITFIELD(58, 4) /* index 0 */,
+  TILEGX_OPC_NONE, CHILD(17), TILEGX_OPC_ADDXI, CHILD(32), TILEGX_OPC_CMPEQI,
+  TILEGX_OPC_CMPLTSI, CHILD(62), CHILD(67), CHILD(117), CHILD(122),
+  CHILD(127), CHILD(132), CHILD(152), CHILD(157), CHILD(162), TILEGX_OPC_NONE,
+  BITFIELD(37, 2) /* index 17 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(22),
+  BITFIELD(39, 2) /* index 22 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, CHILD(27),
+  BITFIELD(41, 2) /* index 27 */,
+  TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_ADDI, TILEGX_OPC_MOVEI,
+  BITFIELD(31, 2) /* index 32 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(37),
+  BITFIELD(33, 2) /* index 37 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(42),
+  BITFIELD(35, 2) /* index 42 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(47),
+  BITFIELD(37, 2) /* index 47 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(52),
+  BITFIELD(39, 2) /* index 52 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, CHILD(57),
+  BITFIELD(41, 2) /* index 57 */,
+  TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_ANDI, TILEGX_OPC_INFO,
+  BITFIELD(49, 2) /* index 62 */,
+  TILEGX_OPC_ADDX, TILEGX_OPC_ADD, TILEGX_OPC_SUBX, TILEGX_OPC_SUB,
+  BITFIELD(47, 4) /* index 67 */,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL1ADD,
+  TILEGX_OPC_SHL1ADD, TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL2ADD,
+  TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL2ADD, TILEGX_OPC_SHL3ADD,
+  TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD, TILEGX_OPC_SHL3ADD, CHILD(84),
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_NONE,
+  BITFIELD(43, 3) /* index 84 */,
+  CHILD(93), CHILD(96), CHILD(99), CHILD(102), CHILD(105), CHILD(108),
+  CHILD(111), CHILD(114),
+  BITFIELD(46, 1) /* index 93 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_FNOP,
+  BITFIELD(46, 1) /* index 96 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_ILL,
+  BITFIELD(46, 1) /* index 99 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_JALRP,
+  BITFIELD(46, 1) /* index 102 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_JALR,
+  BITFIELD(46, 1) /* index 105 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_JRP,
+  BITFIELD(46, 1) /* index 108 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_JR,
+  BITFIELD(46, 1) /* index 111 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_LNK,
+  BITFIELD(46, 1) /* index 114 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_NOP,
+  BITFIELD(49, 2) /* index 117 */,
+  TILEGX_OPC_CMPLES, TILEGX_OPC_CMPLEU, TILEGX_OPC_CMPLTS, TILEGX_OPC_CMPLTU,
+  BITFIELD(49, 2) /* index 122 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_CMPEQ, TILEGX_OPC_CMPNE,
+  BITFIELD(49, 2) /* index 127 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_NONE, TILEGX_OPC_MNZ, TILEGX_OPC_MZ,
+  BITFIELD(49, 2) /* index 132 */,
+  TILEGX_OPC_AND, TILEGX_OPC_NOR, CHILD(137), TILEGX_OPC_XOR,
+  BITFIELD(43, 2) /* index 137 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(142),
+  BITFIELD(45, 2) /* index 142 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, CHILD(147),
+  BITFIELD(47, 2) /* index 147 */,
+  TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_OR, TILEGX_OPC_MOVE,
+  BITFIELD(49, 2) /* index 152 */,
+  TILEGX_OPC_ROTL, TILEGX_OPC_SHL, TILEGX_OPC_SHRS, TILEGX_OPC_SHRU,
+  BITFIELD(49, 2) /* index 157 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_SHL1ADDX, TILEGX_OPC_SHL2ADDX,
+  TILEGX_OPC_SHL3ADDX,
+  BITFIELD(49, 2) /* index 162 */,
+  TILEGX_OPC_ROTLI, TILEGX_OPC_SHLI, TILEGX_OPC_SHRSI, TILEGX_OPC_SHRUI,
+};
+
+static const unsigned short decode_Y2_fsm[118] =
+{
+  BITFIELD(62, 2) /* index 0 */,
+  TILEGX_OPC_NONE, CHILD(5), CHILD(66), CHILD(109),
+  BITFIELD(55, 3) /* index 5 */,
+  CHILD(14), CHILD(14), CHILD(14), CHILD(17), CHILD(40), CHILD(40), CHILD(40),
+  CHILD(43),
+  BITFIELD(26, 1) /* index 14 */,
+  TILEGX_OPC_LD1S, TILEGX_OPC_LD1U,
+  BITFIELD(26, 1) /* index 17 */,
+  CHILD(20), CHILD(30),
+  BITFIELD(51, 2) /* index 20 */,
+  TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, CHILD(25),
+  BITFIELD(53, 2) /* index 25 */,
+  TILEGX_OPC_LD1S, TILEGX_OPC_LD1S, TILEGX_OPC_LD1S,
+  TILEGX_OPC_PREFETCH_L1_FAULT,
+  BITFIELD(51, 2) /* index 30 */,
+  TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, CHILD(35),
+  BITFIELD(53, 2) /* index 35 */,
+  TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_LD1U, TILEGX_OPC_PREFETCH,
+  BITFIELD(26, 1) /* index 40 */,
+  TILEGX_OPC_LD2S, TILEGX_OPC_LD2U,
+  BITFIELD(26, 1) /* index 43 */,
+  CHILD(46), CHILD(56),
+  BITFIELD(51, 2) /* index 46 */,
+  TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, CHILD(51),
+  BITFIELD(53, 2) /* index 51 */,
+  TILEGX_OPC_LD2S, TILEGX_OPC_LD2S, TILEGX_OPC_LD2S,
+  TILEGX_OPC_PREFETCH_L2_FAULT,
+  BITFIELD(51, 2) /* index 56 */,
+  TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, CHILD(61),
+  BITFIELD(53, 2) /* index 61 */,
+  TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_LD2U, TILEGX_OPC_PREFETCH_L2,
+  BITFIELD(56, 2) /* index 66 */,
+  CHILD(71), CHILD(74), CHILD(90), CHILD(93),
+  BITFIELD(26, 1) /* index 71 */,
+  TILEGX_OPC_NONE, TILEGX_OPC_LD4S,
+  BITFIELD(26, 1) /* index 74 */,
+  TILEGX_OPC_NONE, CHILD(77),
+  BITFIELD(51, 2) /* index 77 */,
+  TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, CHILD(82),
+  BITFIELD(53, 2) /* index 82 */,
+  TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, TILEGX_OPC_LD4S, CHILD(87),
+  BITFIELD(55, 1) /* index 87 */,
+  TILEGX_OPC_LD4S, TILEGX_OPC_PREFETCH_L3_FAULT,
+  BITFIELD(26, 1) /* index 90 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_LD,
+  BITFIELD(26, 1) /* index 93 */,
+  CHILD(96), TILEGX_OPC_LD,
+  BITFIELD(51, 2) /* index 96 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, CHILD(101),
+  BITFIELD(53, 2) /* index 101 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, TILEGX_OPC_LD4U, CHILD(106),
+  BITFIELD(55, 1) /* index 106 */,
+  TILEGX_OPC_LD4U, TILEGX_OPC_PREFETCH_L3,
+  BITFIELD(26, 1) /* index 109 */,
+  CHILD(112), CHILD(115),
+  BITFIELD(57, 1) /* index 112 */,
+  TILEGX_OPC_ST1, TILEGX_OPC_ST4,
+  BITFIELD(57, 1) /* index 115 */,
+  TILEGX_OPC_ST2, TILEGX_OPC_ST,
+};
+
+#undef BITFIELD
+#undef CHILD
+const unsigned short * const
+tilegx_bundle_decoder_fsms[TILEGX_NUM_PIPELINE_ENCODINGS] =
+{
+  decode_X0_fsm,
+  decode_X1_fsm,
+  decode_Y0_fsm,
+  decode_Y1_fsm,
+  decode_Y2_fsm
+};
+const struct tilegx_operand tilegx_operands[35] =
+{
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_IMM8_X0),
+    8, 1, 0, 0, 0, 0,
+    create_Imm8_X0, get_Imm8_X0
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_IMM8_X1),
+    8, 1, 0, 0, 0, 0,
+    create_Imm8_X1, get_Imm8_X1
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_IMM8_Y0),
+    8, 1, 0, 0, 0, 0,
+    create_Imm8_Y0, get_Imm8_Y0
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_IMM8_Y1),
+    8, 1, 0, 0, 0, 0,
+    create_Imm8_Y1, get_Imm8_Y1
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_IMM16_X0_HW0_LAST),
+    16, 1, 0, 0, 0, 0,
+    create_Imm16_X0, get_Imm16_X0
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_IMM16_X1_HW0_LAST),
+    16, 1, 0, 0, 0, 0,
+    create_Imm16_X1, get_Imm16_X1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 0, 1, 0, 0,
+    create_Dest_X0, get_Dest_X0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcA_X0, get_SrcA_X0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 0, 1, 0, 0,
+    create_Dest_X1, get_Dest_X1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcA_X1, get_SrcA_X1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 0, 1, 0, 0,
+    create_Dest_Y0, get_Dest_Y0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcA_Y0, get_SrcA_Y0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 0, 1, 0, 0,
+    create_Dest_Y1, get_Dest_Y1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcA_Y1, get_SrcA_Y1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcA_Y2, get_SrcA_Y2
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 1, 0, 0,
+    create_SrcA_X1, get_SrcA_X1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcB_X0, get_SrcB_X0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcB_X1, get_SrcB_X1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcB_Y0, get_SrcB_Y0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcB_Y1, get_SrcB_Y1
+  },
+  {
+    TILEGX_OP_TYPE_ADDRESS, BFD_RELOC(TILEGX_BROFF_X1),
+    17, 1, 0, 0, 1, TILEGX_LOG2_BUNDLE_ALIGNMENT_IN_BYTES,
+    create_BrOff_X1, get_BrOff_X1
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(NONE),
+    6, 0, 0, 0, 0, 0,
+    create_BFStart_X0, get_BFStart_X0
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(NONE),
+    6, 0, 0, 0, 0, 0,
+    create_BFEnd_X0, get_BFEnd_X0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 1, 0, 0,
+    create_Dest_X0, get_Dest_X0
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 1, 0, 0,
+    create_Dest_Y0, get_Dest_Y0
+  },
+  {
+    TILEGX_OP_TYPE_ADDRESS, BFD_RELOC(TILEGX_JUMPOFF_X1),
+    27, 1, 0, 0, 1, TILEGX_LOG2_BUNDLE_ALIGNMENT_IN_BYTES,
+    create_JumpOff_X1, get_JumpOff_X1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 0, 1, 0, 0,
+    create_SrcBDest_Y2, get_SrcBDest_Y2
+  },
+  {
+    TILEGX_OP_TYPE_SPR, BFD_RELOC(TILEGX_MF_IMM14_X1),
+    14, 0, 0, 0, 0, 0,
+    create_MF_Imm14_X1, get_MF_Imm14_X1
+  },
+  {
+    TILEGX_OP_TYPE_SPR, BFD_RELOC(TILEGX_MT_IMM14_X1),
+    14, 0, 0, 0, 0, 0,
+    create_MT_Imm14_X1, get_MT_Imm14_X1
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_SHAMT_X0),
+    6, 0, 0, 0, 0, 0,
+    create_ShAmt_X0, get_ShAmt_X0
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_SHAMT_X1),
+    6, 0, 0, 0, 0, 0,
+    create_ShAmt_X1, get_ShAmt_X1
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_SHAMT_Y0),
+    6, 0, 0, 0, 0, 0,
+    create_ShAmt_Y0, get_ShAmt_Y0
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_SHAMT_Y1),
+    6, 0, 0, 0, 0, 0,
+    create_ShAmt_Y1, get_ShAmt_Y1
+  },
+  {
+    TILEGX_OP_TYPE_REGISTER, BFD_RELOC(NONE),
+    6, 0, 1, 0, 0, 0,
+    create_SrcBDest_Y2, get_SrcBDest_Y2
+  },
+  {
+    TILEGX_OP_TYPE_IMMEDIATE, BFD_RELOC(TILEGX_DEST_IMM8_X1),
+    8, 1, 0, 0, 0, 0,
+    create_Dest_Imm8_X1, get_Dest_Imm8_X1
+  }
+};
+
+
+
+
+/* Given a set of bundle bits and the lookup FSM for a specific pipe,
+ * returns which instruction the bundle contains in that pipe.
+ */
+static const struct tilegx_opcode *
+find_opcode(tilegx_bundle_bits bits, const unsigned short *table)
+{
+  int index = 0;
+
+  while (1)
+  {
+    unsigned short bitspec = table[index];
+    unsigned int bitfield =
+      ((unsigned int)(bits >> (bitspec & 63))) & (bitspec >> 6);
+
+    unsigned short next = table[index + 1 + bitfield];
+    if (next <= TILEGX_OPC_NONE)
+      return &tilegx_opcodes[next];
+
+    index = next - TILEGX_OPC_NONE;
+  }
+}
+
+
+int
+parse_insn_tilegx(tilegx_bundle_bits bits,
+                  unsigned long long pc,
+                  struct tilegx_decoded_instruction
+                  decoded[TILEGX_MAX_INSTRUCTIONS_PER_BUNDLE])
+{
+  int num_instructions = 0;
+  int pipe;
+
+  int min_pipe, max_pipe;
+  if ((bits & TILEGX_BUNDLE_MODE_MASK) == 0)
+  {
+    min_pipe = TILEGX_PIPELINE_X0;
+    max_pipe = TILEGX_PIPELINE_X1;
+  }
+  else
+  {
+    min_pipe = TILEGX_PIPELINE_Y0;
+    max_pipe = TILEGX_PIPELINE_Y2;
+  }
+
+  /* For each pipe, find an instruction that fits. */
+  for (pipe = min_pipe; pipe <= max_pipe; pipe++)
+  {
+    const struct tilegx_opcode *opc;
+    struct tilegx_decoded_instruction *d;
+    int i;
+
+    d = &decoded[num_instructions++];
+    opc = find_opcode (bits, tilegx_bundle_decoder_fsms[pipe]);
+    d->opcode = opc;
+
+    /* Decode each operand, sign extending, etc. as appropriate. */
+    for (i = 0; i < opc->num_operands; i++)
+    {
+      const struct tilegx_operand *op =
+        &tilegx_operands[opc->operands[pipe][i]];
+      int raw_opval = op->extract (bits);
+      long long opval;
+
+      if (op->is_signed)
+      {
+        /* Sign-extend the operand. */
+        int shift = (int)((sizeof(int) * 8) - op->num_bits);
+        raw_opval = (raw_opval << shift) >> shift;
+      }
+
+      /* Adjust PC-relative scaled branch offsets. */
+      if (op->type == TILEGX_OP_TYPE_ADDRESS)
+        opval = (raw_opval * TILEGX_BUNDLE_SIZE_IN_BYTES) + pc;
+      else
+        opval = raw_opval;
+
+      /* Record the final value. */
+      d->operands[i] = op;
+      d->operand_values[i] = opval;
+    }
+  }
+
+  return num_instructions;
+}
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 49a605be94c5..c4be58cc5d50 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/delay.h>
+#include <linux/module.h>
 #include <asm/irq_regs.h>
 #include <asm/traps.h>
 #include <hv/hypervisor.h>
@@ -56,6 +57,7 @@ cycles_t get_cycles(void)
 
         return (((cycles_t)high) << 32) | low;
 }
+EXPORT_SYMBOL(get_cycles);
 #endif
 
 /*
diff --git a/arch/tile/kernel/tlb.c b/arch/tile/kernel/tlb.c
index 2dffc1044d83..a5f241c24cac 100644
--- a/arch/tile/kernel/tlb.c
+++ b/arch/tile/kernel/tlb.c
@@ -34,13 +34,13 @@ void flush_tlb_mm(struct mm_struct *mm)
 {
         HV_Remote_ASID asids[NR_CPUS];
         int i = 0, cpu;
-        for_each_cpu(cpu, &mm->cpu_vm_mask) {
+        for_each_cpu(cpu, mm_cpumask(mm)) {
                 HV_Remote_ASID *asid = &asids[i++];
                 asid->y = cpu / smp_topology.width;
                 asid->x = cpu % smp_topology.width;
                 asid->asid = per_cpu(current_asid, cpu);
         }
-        flush_remote(0, HV_FLUSH_EVICT_L1I, &mm->cpu_vm_mask,
+        flush_remote(0, HV_FLUSH_EVICT_L1I, mm_cpumask(mm),
                      0, 0, 0, NULL, asids, i);
 }
 
@@ -54,8 +54,8 @@ void flush_tlb_page_mm(const struct vm_area_struct *vma, struct mm_struct *mm,
 {
         unsigned long size = hv_page_size(vma);
         int cache = (vma->vm_flags & VM_EXEC) ? HV_FLUSH_EVICT_L1I : 0;
-        flush_remote(0, cache, &mm->cpu_vm_mask,
-                     va, size, size, &mm->cpu_vm_mask, NULL, 0);
+        flush_remote(0, cache, mm_cpumask(mm),
+                     va, size, size, mm_cpumask(mm), NULL, 0);
 }
 
 void flush_tlb_page(const struct vm_area_struct *vma, unsigned long va)
@@ -70,8 +70,8 @@ void flush_tlb_range(const struct vm_area_struct *vma,
         unsigned long size = hv_page_size(vma);
         struct mm_struct *mm = vma->vm_mm;
         int cache = (vma->vm_flags & VM_EXEC) ? HV_FLUSH_EVICT_L1I : 0;
-        flush_remote(0, cache, &mm->cpu_vm_mask, start, end - start, size,
-                     &mm->cpu_vm_mask, NULL, 0);
+        flush_remote(0, cache, mm_cpumask(mm), start, end - start, size,
+                     mm_cpumask(mm), NULL, 0);
 }
 
 void flush_tlb_all(void)
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 5474fc2e77e8..f9803dfa7357 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -308,6 +308,7 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
         info.si_addr = (void __user *)address;
         if (signo == SIGILL)
                 info.si_trapno = fault_num;
+        trace_unhandled_signal("trap", regs, address, signo);
         force_sig_info(signo, &info, current);
 }
 
diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index 82f64cc63658..24448734f6f1 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -59,7 +59,7 @@
  * bad kernel addresses).
  *
  * Note that if the value we would store is the same as what we
- * loaded, we bypass the load.  Other platforms with true atomics can
+ * loaded, we bypass the store.  Other platforms with true atomics can
  * make the guarantee that a non-atomic __clear_bit(), for example,
  * can safely race with an atomic test_and_set_bit(); this example is
  * from bit_spinlock.h in slub_lock() / slub_unlock().  We can't do
diff --git a/arch/tile/lib/cacheflush.c b/arch/tile/lib/cacheflush.c
index 35c1d8ca5f38..8928aace7a64 100644
--- a/arch/tile/lib/cacheflush.c
+++ b/arch/tile/lib/cacheflush.c
@@ -15,6 +15,7 @@
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <arch/icache.h>
+#include <arch/spr_def.h>
 
 
 void __flush_icache_range(unsigned long start, unsigned long end)
@@ -39,6 +40,18 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
         char *p, *base;
         size_t step_size, load_count;
         const unsigned long STRIPE_WIDTH = 8192;
+#ifdef __tilegx__
+        /*
+         * On TILE-Gx, we must disable the dstream prefetcher before doing
+         * a cache flush; otherwise, we could end up with data in the cache
+         * that we don't want there.  Note that normally we'd do an mf
+         * after the SPR write to disabling the prefetcher, but we do one
+         * below, before any further loads, so there's no need to do it
+         * here.
+         */
+        uint_reg_t old_dstream_pf = __insn_mfspr(SPR_DSTREAM_PF);
+        __insn_mtspr(SPR_DSTREAM_PF, 0);
+#endif
 
         /*
          * Flush and invalidate the buffer out of the local L1/L2
@@ -122,4 +135,9 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
 
         /* Wait for the load+inv's (and thus finvs) to have completed. */
         __insn_mf();
+
+#ifdef __tilegx__
+        /* Reenable the prefetcher. */
+        __insn_mtspr(SPR_DSTREAM_PF, old_dstream_pf);
+#endif
 }
diff --git a/arch/tile/lib/memchr_64.c b/arch/tile/lib/memchr_64.c
new file mode 100644
index 000000000000..84fdc8d8e735
--- /dev/null
+++ b/arch/tile/lib/memchr_64.c
@@ -0,0 +1,71 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+void *memchr(const void *s, int c, size_t n)
+{
+        const uint64_t *last_word_ptr;
+        const uint64_t *p;
+        const char *last_byte_ptr;
+        uintptr_t s_int;
+        uint64_t goal, before_mask, v, bits;
+        char *ret;
+
+        if (__builtin_expect(n == 0, 0)) {
+                /* Don't dereference any memory if the array is empty. */
+                return NULL;
+        }
+
+        /* Get an aligned pointer. */
+        s_int = (uintptr_t) s;
+        p = (const uint64_t *)(s_int & -8);
+
+        /* Create eight copies of the byte for which we are looking. */
+        goal = 0x0101010101010101ULL * (uint8_t) c;
+
+        /* Read the first word, but munge it so that bytes before the array
+         * will not match goal.
+         *
+         * Note that this shift count expression works because we know
+         * shift counts are taken mod 64.
+         */
+        before_mask = (1ULL << (s_int << 3)) - 1;
+        v = (*p | before_mask) ^ (goal & before_mask);
+
+        /* Compute the address of the last byte. */
+        last_byte_ptr = (const char *)s + n - 1;
+
+        /* Compute the address of the word containing the last byte. */
+        last_word_ptr = (const uint64_t *)((uintptr_t) last_byte_ptr & -8);
+
+        while ((bits = __insn_v1cmpeq(v, goal)) == 0) {
+                if (__builtin_expect(p == last_word_ptr, 0)) {
+                        /* We already read the last word in the array,
+                         * so give up.
+                         */
+                        return NULL;
+                }
+                v = *++p;
+        }
+
+        /* We found a match, but it might be in a byte past the end
+         * of the array.
+         */
+        ret = ((char *)p) + (__insn_ctz(bits) >> 3);
+        return (ret <= last_byte_ptr) ? ret : NULL;
+}
+EXPORT_SYMBOL(memchr);
diff --git a/arch/tile/lib/memcpy_64.c b/arch/tile/lib/memcpy_64.c
new file mode 100644
index 000000000000..3fab9a6a2bbe
--- /dev/null
+++ b/arch/tile/lib/memcpy_64.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#define __memcpy memcpy
+/* EXPORT_SYMBOL() is in arch/tile/lib/exports.c since this should be asm. */
+
+/* Must be 8 bytes in size. */
+#define word_t uint64_t
+
+#if CHIP_L2_LINE_SIZE() != 64 && CHIP_L2_LINE_SIZE() != 128
+#error "Assumes 64 or 128 byte line size"
+#endif
+
+/* How many cache lines ahead should we prefetch? */
+#define PREFETCH_LINES_AHEAD 3
+
+/*
+ * Provide "base versions" of load and store for the normal code path.
+ * The kernel provides other versions for userspace copies.
+ */
+#define ST(p, v) (*(p) = (v))
+#define LD(p) (*(p))
+
+#ifndef USERCOPY_FUNC
+#define ST1 ST
+#define ST2 ST
+#define ST4 ST
+#define ST8 ST
+#define LD1 LD
+#define LD2 LD
+#define LD4 LD
+#define LD8 LD
+#define RETVAL dstv
+void *memcpy(void *__restrict dstv, const void *__restrict srcv, size_t n)
+#else
+/*
+ * Special kernel version will provide implementation of the LDn/STn
+ * macros to return a count of uncopied bytes due to mm fault.
+ */
+#define RETVAL 0
+int USERCOPY_FUNC(void *__restrict dstv, const void *__restrict srcv, size_t n)
+#endif
+{
+        char *__restrict dst1 = (char *)dstv;
+        const char *__restrict src1 = (const char *)srcv;
+        const char *__restrict src1_end;
+        const char *__restrict prefetch;
+        word_t *__restrict dst8;    /* 8-byte pointer to destination memory. */
+        word_t final; /* Final bytes to write to trailing word, if any */
+        long i;
+
+        if (n < 16) {
+                for (; n; n--)
+                        ST1(dst1++, LD1(src1++));
+                return RETVAL;
+        }
+
+        /*
+         * Locate the end of source memory we will copy.  Don't
+         * prefetch past this.
+         */
+        src1_end = src1 + n - 1;
+
+        /* Prefetch ahead a few cache lines, but not past the end. */
+        prefetch = src1;
+        for (i = 0; i < PREFETCH_LINES_AHEAD; i++) {
+                __insn_prefetch(prefetch);
+                prefetch += CHIP_L2_LINE_SIZE();
+                prefetch = (prefetch > src1_end) ? prefetch : src1;
+        }
+
+        /* Copy bytes until dst is word-aligned. */
+        for (; (uintptr_t)dst1 & (sizeof(word_t) - 1); n--)
+                ST1(dst1++, LD1(src1++));
+
+        /* 8-byte pointer to destination memory. */
+        dst8 = (word_t *)dst1;
+
+        if (__builtin_expect((uintptr_t)src1 & (sizeof(word_t) - 1), 0)) {
+                /*
+                 * Misaligned copy.  Copy 8 bytes at a time, but don't
+                 * bother with other fanciness.
+                 *
+                 * TODO: Consider prefetching and using wh64 as well.
+                 */
+
+                /* Create an aligned src8. */
+                const word_t *__restrict src8 =
+                        (const word_t *)((uintptr_t)src1 & -sizeof(word_t));
+                word_t b;
+
+                word_t a = LD8(src8++);
+                for (; n >= sizeof(word_t); n -= sizeof(word_t)) {
+                        b = LD8(src8++);
+                        a = __insn_dblalign(a, b, src1);
+                        ST8(dst8++, a);
+                        a = b;
+                }
+
+                if (n == 0)
+                        return RETVAL;
+
+                b = ((const char *)src8 <= src1_end) ? *src8 : 0;
+
+                /*
+                 * Final source bytes to write to trailing partial
+                 * word, if any.
+                 */
+                final = __insn_dblalign(a, b, src1);
+        } else {
+                /* Aligned copy. */
+
+                const word_t* __restrict src8 = (const word_t *)src1;
+
+                /* src8 and dst8 are both word-aligned. */
+                if (n >= CHIP_L2_LINE_SIZE()) {
+                        /* Copy until 'dst' is cache-line-aligned. */
+                        for (; (uintptr_t)dst8 & (CHIP_L2_LINE_SIZE() - 1);
+                             n -= sizeof(word_t))
+                                ST8(dst8++, LD8(src8++));
+
+                        for (; n >= CHIP_L2_LINE_SIZE(); ) {
+                                __insn_wh64(dst8);
+
+                                /*
+                                 * Prefetch and advance to next line
+                                 * to prefetch, but don't go past the end
+                                 */
+                                __insn_prefetch(prefetch);
+                                prefetch += CHIP_L2_LINE_SIZE();
+                                prefetch = (prefetch > src1_end) ? prefetch :
+                                        (const char *)src8;
+
+                                /*
+                                 * Copy an entire cache line.  Manually
+                                 * unrolled to avoid idiosyncracies of
+                                 * compiler unrolling.
+                                 */
+#define COPY_WORD(offset) ({ ST8(dst8+offset, LD8(src8+offset)); n -= 8; })
+                                COPY_WORD(0);
+                                COPY_WORD(1);
+                                COPY_WORD(2);
+                                COPY_WORD(3);
+                                COPY_WORD(4);
+                                COPY_WORD(5);
+                                COPY_WORD(6);
+                                COPY_WORD(7);
+#if CHIP_L2_LINE_SIZE() == 128
+                                COPY_WORD(8);
+                                COPY_WORD(9);
+                                COPY_WORD(10);
+                                COPY_WORD(11);
+                                COPY_WORD(12);
+                                COPY_WORD(13);
+                                COPY_WORD(14);
+                                COPY_WORD(15);
+#elif CHIP_L2_LINE_SIZE() != 64
+# error Fix code that assumes particular L2 cache line sizes
+#endif
+
+                                dst8 += CHIP_L2_LINE_SIZE() / sizeof(word_t);
+                                src8 += CHIP_L2_LINE_SIZE() / sizeof(word_t);
+                        }
+                }
+
+                for (; n >= sizeof(word_t); n -= sizeof(word_t))
+                        ST8(dst8++, LD8(src8++));
+
+                if (__builtin_expect(n == 0, 1))
+                        return RETVAL;
+
+                final = LD8(src8);
+        }
+
+        /* n != 0 if we get here.  Write out any trailing bytes. */
+        dst1 = (char *)dst8;
+        if (n & 4) {
+                ST4((uint32_t *)dst1, final);
+                dst1 += 4;
+                final >>= 32;
+                n &= 3;
+        }
+        if (n & 2) {
+                ST2((uint16_t *)dst1, final);
+                dst1 += 2;
+                final >>= 16;
+                n &= 1;
+        }
+        if (n)
+                ST1((uint8_t *)dst1, final);
+
+        return RETVAL;
+}
+
+
+#ifdef USERCOPY_FUNC
+#undef ST1
+#undef ST2
+#undef ST4
+#undef ST8
+#undef LD1
+#undef LD2
+#undef LD4
+#undef LD8
+#undef USERCOPY_FUNC
+#endif
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
new file mode 100644
index 000000000000..4763b3aff1cc
--- /dev/null
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * Do memcpy(), but trap and return "n" when a load or store faults.
+ *
+ * Note: this idiom only works when memcpy() compiles to a leaf function.
+ * If "sp" is updated during memcpy, the "jrp lr" will be incorrect.
+ *
+ * Also note that we are capturing "n" from the containing scope here.
+ */
+
+#define _ST(p, inst, v)                                         \
+        ({                                                      \
+                asm("1: " #inst " %0, %1;"                      \
+                    ".pushsection .coldtext.memcpy,\"ax\";"     \
+                    "2: { move r0, %2; jrp lr };"               \
+                    ".section __ex_table,\"a\";"                \
+                    ".quad 1b, 2b;"                             \
+                    ".popsection"                               \
+                    : "=m" (*(p)) : "r" (v), "r" (n));          \
+        })
+
+#define _LD(p, inst)                                            \
+        ({                                                      \
+                unsigned long __v;                              \
+                asm("1: " #inst " %0, %1;"                      \
+                    ".pushsection .coldtext.memcpy,\"ax\";"     \
+                    "2: { move r0, %2; jrp lr };"               \
+                    ".section __ex_table,\"a\";"                \
+                    ".quad 1b, 2b;"                             \
+                    ".popsection"                               \
+                    : "=r" (__v) : "m" (*(p)), "r" (n));        \
+                __v;                                            \
+        })
+
+#define USERCOPY_FUNC __copy_to_user_inatomic
+#define ST1(p, v) _ST((p), st1, (v))
+#define ST2(p, v) _ST((p), st2, (v))
+#define ST4(p, v) _ST((p), st4, (v))
+#define ST8(p, v) _ST((p), st, (v))
+#define LD1 LD
+#define LD2 LD
+#define LD4 LD
+#define LD8 LD
+#include "memcpy_64.c"
+
+#define USERCOPY_FUNC __copy_from_user_inatomic
+#define ST1 ST
+#define ST2 ST
+#define ST4 ST
+#define ST8 ST
+#define LD1(p) _LD((p), ld1u)
+#define LD2(p) _LD((p), ld2u)
+#define LD4(p) _LD((p), ld4u)
+#define LD8(p) _LD((p), ld)
+#include "memcpy_64.c"
+
+#define USERCOPY_FUNC __copy_in_user_inatomic
+#define ST1(p, v) _ST((p), st1, (v))
+#define ST2(p, v) _ST((p), st2, (v))
+#define ST4(p, v) _ST((p), st4, (v))
+#define ST8(p, v) _ST((p), st, (v))
+#define LD1(p) _LD((p), ld1u)
+#define LD2(p) _LD((p), ld2u)
+#define LD4(p) _LD((p), ld4u)
+#define LD8(p) _LD((p), ld)
+#include "memcpy_64.c"
+
+unsigned long __copy_from_user_zeroing(void *to, const void __user *from,
+                                       unsigned long n)
+{
+        unsigned long rc = __copy_from_user_inatomic(to, from, n);
+        if (unlikely(rc))
+                memset(to + n - rc, 0, rc);
+        return rc;
+}
diff --git a/arch/tile/lib/memset_64.c b/arch/tile/lib/memset_64.c
new file mode 100644
index 000000000000..3873085711d5
--- /dev/null
+++ b/arch/tile/lib/memset_64.c
@@ -0,0 +1,145 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <arch/chip.h>
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+#undef memset
+
+void *memset(void *s, int c, size_t n)
+{
+        uint64_t *out64;
+        int n64, to_align64;
+        uint64_t v64;
+        uint8_t *out8 = s;
+
+        /* Experimentation shows that a trivial tight loop is a win up until
+         * around a size of 20, where writing a word at a time starts to win.
+         */
+#define BYTE_CUTOFF 20
+
+#if BYTE_CUTOFF < 7
+        /* This must be at least at least this big, or some code later
+         * on doesn't work.
+         */
+#error "BYTE_CUTOFF is too small"
+#endif
+
+        if (n < BYTE_CUTOFF) {
+                /* Strangely, this turns out to be the tightest way to
+                 * write this loop.
+                 */
+                if (n != 0) {
+                        do {
+                                /* Strangely, combining these into one line
+                                 * performs worse.
+                                 */
+                                *out8 = c;
+                                out8++;
+                        } while (--n != 0);
+                }
+
+                return s;
+        }
+
+        /* Align 'out8'. We know n >= 7 so this won't write past the end. */
+        while (((uintptr_t) out8 & 7) != 0) {
+                *out8++ = c;
+                --n;
+        }
+
+        /* Align 'n'. */
+        while (n & 7)
+                out8[--n] = c;
+
+        out64 = (uint64_t *) out8;
+        n64 = n >> 3;
+
+        /* Tile input byte out to 64 bits. */
+        /* KLUDGE */
+        v64 = 0x0101010101010101ULL * (uint8_t)c;
+
+        /* This must be at least 8 or the following loop doesn't work. */
+#define CACHE_LINE_SIZE_IN_DOUBLEWORDS (CHIP_L2_LINE_SIZE() / 8)
+
+        /* Determine how many words we need to emit before the 'out32'
+         * pointer becomes aligned modulo the cache line size.
+         */
+        to_align64 = (-((uintptr_t)out64 >> 3)) &
+                (CACHE_LINE_SIZE_IN_DOUBLEWORDS - 1);
+
+        /* Only bother aligning and using wh64 if there is at least
+         * one full cache line to process.  This check also prevents
+         * overrunning the end of the buffer with alignment words.
+         */
+        if (to_align64 <= n64 - CACHE_LINE_SIZE_IN_DOUBLEWORDS) {
+                int lines_left;
+
+                /* Align out64 mod the cache line size so we can use wh64. */
+                n64 -= to_align64;
+                for (; to_align64 != 0; to_align64--) {
+                        *out64 = v64;
+                        out64++;
+                }
+
+                /* Use unsigned divide to turn this into a right shift. */
+                lines_left = (unsigned)n64 / CACHE_LINE_SIZE_IN_DOUBLEWORDS;
+
+                do {
+                        /* Only wh64 a few lines at a time, so we don't
+                         * exceed the maximum number of victim lines.
+                         */
+                        int x = ((lines_left < CHIP_MAX_OUTSTANDING_VICTIMS())
+                                  ? lines_left
+                                  : CHIP_MAX_OUTSTANDING_VICTIMS());
+                        uint64_t *wh = out64;
+                        int i = x;
+                        int j;
+
+                        lines_left -= x;
+
+                        do {
+                                __insn_wh64(wh);
+                                wh += CACHE_LINE_SIZE_IN_DOUBLEWORDS;
+                        } while (--i);
+
+                        for (j = x * (CACHE_LINE_SIZE_IN_DOUBLEWORDS / 4);
+                             j != 0; j--) {
+                                *out64++ = v64;
+                                *out64++ = v64;
+                                *out64++ = v64;
+                                *out64++ = v64;
+                        }
+                } while (lines_left != 0);
+
+                /* We processed all full lines above, so only this many
+                 * words remain to be processed.
+                 */
+                n64 &= CACHE_LINE_SIZE_IN_DOUBLEWORDS - 1;
+        }
+
+        /* Now handle any leftover values. */
+        if (n64 != 0) {
+                do {
+                        *out64 = v64;
+                        out64++;
+                } while (--n64 != 0);
+        }
+
+        return s;
+}
+EXPORT_SYMBOL(memset);
diff --git a/arch/tile/lib/spinlock_64.c b/arch/tile/lib/spinlock_64.c
new file mode 100644
index 000000000000..d6fb9581e980
--- /dev/null
+++ b/arch/tile/lib/spinlock_64.c
@@ -0,0 +1,104 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <asm/processor.h>
+
+#include "spinlock_common.h"
+
+/*
+ * Read the spinlock value without allocating in our cache and without
+ * causing an invalidation to another cpu with a copy of the cacheline.
+ * This is important when we are spinning waiting for the lock.
+ */
+static inline u32 arch_spin_read_noalloc(void *lock)
+{
+        return atomic_cmpxchg((atomic_t *)lock, -1, -1);
+}
+
+/*
+ * Wait until the high bits (current) match my ticket.
+ * If we notice the overflow bit set on entry, we clear it.
+ */
+void arch_spin_lock_slow(arch_spinlock_t *lock, u32 my_ticket)
+{
+        if (unlikely(my_ticket & __ARCH_SPIN_NEXT_OVERFLOW)) {
+                __insn_fetchand4(&lock->lock, ~__ARCH_SPIN_NEXT_OVERFLOW);
+                my_ticket &= ~__ARCH_SPIN_NEXT_OVERFLOW;
+        }
+
+        for (;;) {
+                u32 val = arch_spin_read_noalloc(lock);
+                u32 delta = my_ticket - arch_spin_current(val);
+                if (delta == 0)
+                        return;
+                relax((128 / CYCLES_PER_RELAX_LOOP) * delta);
+        }
+}
+EXPORT_SYMBOL(arch_spin_lock_slow);
+
+/*
+ * Check the lock to see if it is plausible, and try to get it with cmpxchg().
+ */
+int arch_spin_trylock(arch_spinlock_t *lock)
+{
+        u32 val = arch_spin_read_noalloc(lock);
+        if (unlikely(arch_spin_current(val) != arch_spin_next(val)))
+                return 0;
+        return cmpxchg(&lock->lock, val, (val + 1) & ~__ARCH_SPIN_NEXT_OVERFLOW)
+                == val;
+}
+EXPORT_SYMBOL(arch_spin_trylock);
+
+void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+        u32 iterations = 0;
+        while (arch_spin_is_locked(lock))
+                delay_backoff(iterations++);
+}
+EXPORT_SYMBOL(arch_spin_unlock_wait);
+
+/*
+ * If the read lock fails due to a writer, we retry periodically
+ * until the value is positive and we write our incremented reader count.
+ */
+void __read_lock_failed(arch_rwlock_t *rw)
+{
+        u32 val;
+        int iterations = 0;
+        do {
+                delay_backoff(iterations++);
+                val = __insn_fetchaddgez4(&rw->lock, 1);
+        } while (unlikely(arch_write_val_locked(val)));
+}
+EXPORT_SYMBOL(__read_lock_failed);
+
+/*
+ * If we failed because there were readers, clear the "writer" bit
+ * so we don't block additional readers.  Otherwise, there was another
+ * writer anyway, so our "fetchor" made no difference.  Then wait,
+ * issuing periodic fetchor instructions, till we get the lock.
+ */
+void __write_lock_failed(arch_rwlock_t *rw, u32 val)
+{
+        int iterations = 0;
+        do {
+                if (!arch_write_val_locked(val))
+                        val = __insn_fetchand4(&rw->lock, ~__WRITE_LOCK_BIT);
+                delay_backoff(iterations++);
+                val = __insn_fetchor4(&rw->lock, __WRITE_LOCK_BIT);
+        } while (val != 0);
+}
+EXPORT_SYMBOL(__write_lock_failed);
diff --git a/arch/tile/lib/strchr_64.c b/arch/tile/lib/strchr_64.c
new file mode 100644
index 000000000000..617a9273aaa8
--- /dev/null
+++ b/arch/tile/lib/strchr_64.c
@@ -0,0 +1,67 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+#undef strchr
+
+char *strchr(const char *s, int c)
+{
+        int z, g;
+
+        /* Get an aligned pointer. */
+        const uintptr_t s_int = (uintptr_t) s;
+        const uint64_t *p = (const uint64_t *)(s_int & -8);
+
+        /* Create eight copies of the byte for which we are looking. */
+        const uint64_t goal = 0x0101010101010101ULL * (uint8_t) c;
+
+        /* Read the first aligned word, but force bytes before the string to
+         * match neither zero nor goal (we make sure the high bit of each
+         * byte is 1, and the low 7 bits are all the opposite of the goal
+         * byte).
+         *
+         * Note that this shift count expression works because we know shift
+         * counts are taken mod 64.
+         */
+        const uint64_t before_mask = (1ULL << (s_int << 3)) - 1;
+        uint64_t v = (*p | before_mask) ^
+                (goal & __insn_v1shrsi(before_mask, 1));
+
+        uint64_t zero_matches, goal_matches;
+        while (1) {
+                /* Look for a terminating '\0'. */
+                zero_matches = __insn_v1cmpeqi(v, 0);
+
+                /* Look for the goal byte. */
+                goal_matches = __insn_v1cmpeq(v, goal);
+
+                if (__builtin_expect((zero_matches | goal_matches) != 0, 0))
+                        break;
+
+                v = *++p;
+        }
+
+        z = __insn_ctz(zero_matches);
+        g = __insn_ctz(goal_matches);
+
+        /* If we found c before '\0' we got a match. Note that if c == '\0'
+         * then g == z, and we correctly return the address of the '\0'
+         * rather than NULL.
+         */
+        return (g <= z) ? ((char *)p) + (g >> 3) : NULL;
+}
+EXPORT_SYMBOL(strchr);
diff --git a/arch/tile/lib/strlen_64.c b/arch/tile/lib/strlen_64.c
new file mode 100644
index 000000000000..1c92d46202a8
--- /dev/null
+++ b/arch/tile/lib/strlen_64.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+#undef strlen
+
+size_t strlen(const char *s)
+{
+        /* Get an aligned pointer. */
+        const uintptr_t s_int = (uintptr_t) s;
+        const uint64_t *p = (const uint64_t *)(s_int & -8);
+
+        /* Read the first word, but force bytes before the string to be nonzero.
+         * This expression works because we know shift counts are taken mod 64.
+         */
+        uint64_t v = *p | ((1ULL << (s_int << 3)) - 1);
+
+        uint64_t bits;
+        while ((bits = __insn_v1cmpeqi(v, 0)) == 0)
+                v = *++p;
+
+        return ((const char *)p) + (__insn_ctz(bits) >> 3) - s;
+}
+EXPORT_SYMBOL(strlen);
diff --git a/arch/tile/lib/usercopy_64.S b/arch/tile/lib/usercopy_64.S
new file mode 100644
index 000000000000..2ff44f87b78e
--- /dev/null
+++ b/arch/tile/lib/usercopy_64.S
@@ -0,0 +1,196 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/cache.h>
+#include <arch/chip.h>
+
+/* Access user memory, but use MMU to avoid propagating kernel exceptions. */
+
+        .pushsection .fixup,"ax"
+
+get_user_fault:
+        { movei r1, -EFAULT; move r0, zero }
+        jrp lr
+        ENDPROC(get_user_fault)
+
+put_user_fault:
+        { movei r0, -EFAULT; jrp lr }
+        ENDPROC(put_user_fault)
+
+        .popsection
+
+/*
+ * __get_user_N functions take a pointer in r0, and return 0 in r1
+ * on success, with the value in r0; or else -EFAULT in r1.
+ */
+#define __get_user_N(bytes, LOAD) \
+        STD_ENTRY(__get_user_##bytes); \
+1:      { LOAD r0, r0; move r1, zero }; \
+        jrp lr; \
+        STD_ENDPROC(__get_user_##bytes); \
+        .pushsection __ex_table,"a"; \
+        .quad 1b, get_user_fault; \
+        .popsection
+
+__get_user_N(1, ld1u)
+__get_user_N(2, ld2u)
+__get_user_N(4, ld4u)
+__get_user_N(8, ld)
+
+/*
+ * __put_user_N functions take a value in r0 and a pointer in r1,
+ * and return 0 in r0 on success or -EFAULT on failure.
+ */
+#define __put_user_N(bytes, STORE) \
+        STD_ENTRY(__put_user_##bytes); \
+1:      { STORE r1, r0; move r0, zero }; \
+        jrp lr; \
+        STD_ENDPROC(__put_user_##bytes); \
+        .pushsection __ex_table,"a"; \
+        .quad 1b, put_user_fault; \
+        .popsection
+
+__put_user_N(1, st1)
+__put_user_N(2, st2)
+__put_user_N(4, st4)
+__put_user_N(8, st)
+
+/*
+ * strnlen_user_asm takes the pointer in r0, and the length bound in r1.
+ * It returns the length, including the terminating NUL, or zero on exception.
+ * If length is greater than the bound, returns one plus the bound.
+ */
+STD_ENTRY(strnlen_user_asm)
+        { beqz r1, 2f; addi r3, r0, -1 }  /* bias down to include NUL */
+1:      { ld1u r4, r0; addi r1, r1, -1 }
+        beqz r4, 2f
+        { bnezt r1, 1b; addi r0, r0, 1 }
+2:      { sub r0, r0, r3; jrp lr }
+        STD_ENDPROC(strnlen_user_asm)
+        .pushsection .fixup,"ax"
+strnlen_user_fault:
+        { move r0, zero; jrp lr }
+        ENDPROC(strnlen_user_fault)
+        .section __ex_table,"a"
+        .quad 1b, strnlen_user_fault
+        .popsection
+
+/*
+ * strncpy_from_user_asm takes the kernel target pointer in r0,
+ * the userspace source pointer in r1, and the length bound (including
+ * the trailing NUL) in r2.  On success, it returns the string length
+ * (not including the trailing NUL), or -EFAULT on failure.
+ */
+STD_ENTRY(strncpy_from_user_asm)
+        { beqz r2, 2f; move r3, r0 }
+1:      { ld1u r4, r1; addi r1, r1, 1; addi r2, r2, -1 }
+        { st1 r0, r4; addi r0, r0, 1 }
+        beqz r2, 2f
+        bnezt r4, 1b
+        addi r0, r0, -1   /* don't count the trailing NUL */
+2:      { sub r0, r0, r3; jrp lr }
+        STD_ENDPROC(strncpy_from_user_asm)
+        .pushsection .fixup,"ax"
+strncpy_from_user_fault:
+        { movei r0, -EFAULT; jrp lr }
+        ENDPROC(strncpy_from_user_fault)
+        .section __ex_table,"a"
+        .quad 1b, strncpy_from_user_fault
+        .popsection
+
+/*
+ * clear_user_asm takes the user target address in r0 and the
+ * number of bytes to zero in r1.
+ * It returns the number of uncopiable bytes (hopefully zero) in r0.
+ * Note that we don't use a separate .fixup section here since we fall
+ * through into the "fixup" code as the last straight-line bundle anyway.
+ */
+STD_ENTRY(clear_user_asm)
+        { beqz r1, 2f; or r2, r0, r1 }
+        andi r2, r2, 7
+        beqzt r2, .Lclear_aligned_user_asm
+1:      { st1 r0, zero; addi r0, r0, 1; addi r1, r1, -1 }
+        bnezt r1, 1b
+2:      { move r0, r1; jrp lr }
+        .pushsection __ex_table,"a"
+        .quad 1b, 2b
+        .popsection
+
+.Lclear_aligned_user_asm:
+1:      { st r0, zero; addi r0, r0, 8; addi r1, r1, -8 }
+        bnezt r1, 1b
+2:      { move r0, r1; jrp lr }
+        STD_ENDPROC(clear_user_asm)
+        .pushsection __ex_table,"a"
+        .quad 1b, 2b
+        .popsection
+
+/*
+ * flush_user_asm takes the user target address in r0 and the
+ * number of bytes to flush in r1.
+ * It returns the number of unflushable bytes (hopefully zero) in r0.
+ */
+STD_ENTRY(flush_user_asm)
+        beqz r1, 2f
+        { movei r2, L2_CACHE_BYTES; add r1, r0, r1 }
+        { sub r2, zero, r2; addi r1, r1, L2_CACHE_BYTES-1 }
+        { and r0, r0, r2; and r1, r1, r2 }
+        { sub r1, r1, r0 }
+1:      { flush r0; addi r1, r1, -CHIP_FLUSH_STRIDE() }
+        { addi r0, r0, CHIP_FLUSH_STRIDE(); bnezt r1, 1b }
+2:      { move r0, r1; jrp lr }
+        STD_ENDPROC(flush_user_asm)
+        .pushsection __ex_table,"a"
+        .quad 1b, 2b
+        .popsection
+
+/*
+ * inv_user_asm takes the user target address in r0 and the
+ * number of bytes to invalidate in r1.
+ * It returns the number of not inv'able bytes (hopefully zero) in r0.
+ */
+STD_ENTRY(inv_user_asm)
+        beqz r1, 2f
+        { movei r2, L2_CACHE_BYTES; add r1, r0, r1 }
+        { sub r2, zero, r2; addi r1, r1, L2_CACHE_BYTES-1 }
+        { and r0, r0, r2; and r1, r1, r2 }
+        { sub r1, r1, r0 }
+1:      { inv r0; addi r1, r1, -CHIP_INV_STRIDE() }
+        { addi r0, r0, CHIP_INV_STRIDE(); bnezt r1, 1b }
+2:      { move r0, r1; jrp lr }
+        STD_ENDPROC(inv_user_asm)
+        .pushsection __ex_table,"a"
+        .quad 1b, 2b
+        .popsection
+
+/*
+ * finv_user_asm takes the user target address in r0 and the
+ * number of bytes to flush-invalidate in r1.
+ * It returns the number of not finv'able bytes (hopefully zero) in r0.
+ */
+STD_ENTRY(finv_user_asm)
+        beqz r1, 2f
+        { movei r2, L2_CACHE_BYTES; add r1, r0, r1 }
+        { sub r2, zero, r2; addi r1, r1, L2_CACHE_BYTES-1 }
+        { and r0, r0, r2; and r1, r1, r2 }
+        { sub r1, r1, r0 }
+1:      { finv r0; addi r1, r1, -CHIP_FINV_STRIDE() }
+        { addi r0, r0, CHIP_FINV_STRIDE(); bnezt r1, 1b }
+2:      { move r0, r1; jrp lr }
+        STD_ENDPROC(finv_user_asm)
+        .pushsection __ex_table,"a"
+        .quad 1b, 2b
+        .popsection
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 51f8663bf074..25b7b90fd620 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -43,8 +43,11 @@
 
 #include <arch/interrupts.h>
 
-static noinline void force_sig_info_fault(int si_signo, int si_code,
-        unsigned long address, int fault_num, struct task_struct *tsk)
+static noinline void force_sig_info_fault(const char *type, int si_signo,
+                                          int si_code, unsigned long address,
+                                          int fault_num,
+                                          struct task_struct *tsk,
+                                          struct pt_regs *regs)
 {
         siginfo_t info;
 
@@ -59,6 +62,7 @@ static noinline void force_sig_info_fault(int si_signo, int si_code,
         info.si_code = si_code;
         info.si_addr = (void __user *)address;
         info.si_trapno = fault_num;
+        trace_unhandled_signal(type, regs, address, si_signo);
         force_sig_info(si_signo, &info, tsk);
 }
 
@@ -71,11 +75,12 @@ SYSCALL_DEFINE2(cmpxchg_badaddr, unsigned long, address,
                 struct pt_regs *, regs)
 {
         if (address >= PAGE_OFFSET)
-                force_sig_info_fault(SIGSEGV, SEGV_MAPERR, address,
-                                     INT_DTLB_MISS, current);
+                force_sig_info_fault("atomic segfault", SIGSEGV, SEGV_MAPERR,
+                                     address, INT_DTLB_MISS, current, regs);
         else
-                force_sig_info_fault(SIGBUS, BUS_ADRALN, address,
-                                     INT_UNALIGN_DATA, current);
+                force_sig_info_fault("atomic alignment fault", SIGBUS,
+                                     BUS_ADRALN, address,
+                                     INT_UNALIGN_DATA, current, regs);
 
         /*
          * Adjust pc to point at the actual instruction, which is unusual
@@ -471,8 +476,8 @@ bad_area_nosemaphore:
                  */
                 local_irq_enable();
 
-                force_sig_info_fault(SIGSEGV, si_code, address,
-                                     fault_num, tsk);
+                force_sig_info_fault("segfault", SIGSEGV, si_code, address,
+                                     fault_num, tsk, regs);
                 return 0;
         }
 
@@ -547,7 +552,8 @@ do_sigbus:
         if (is_kernel_mode)
                 goto no_context;
 
-        force_sig_info_fault(SIGBUS, BUS_ADRERR, address, fault_num, tsk);
+        force_sig_info_fault("bus error", SIGBUS, BUS_ADRERR, address,
+                             fault_num, tsk, regs);
         return 0;
 }
 
@@ -732,6 +738,7 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
                 panic("Bad fault number %d in do_page_fault", fault_num);
         }
 
+#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
         if (EX1_PL(regs->ex1) != USER_PL) {
                 struct async_tlb *async;
                 switch (fault_num) {
@@ -775,6 +782,7 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
                         return;
                 }
         }
+#endif
 
         handle_page_fault(regs, fault_num, is_page_fault, address, write);
 }
@@ -801,8 +809,6 @@ static void handle_async_page_fault(struct pt_regs *regs,
                                   async->address, async->is_write);
         }
 }
-#endif /* CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC() */
-
 
 /*
  * This routine effectively re-issues asynchronous page faults
@@ -824,6 +830,8 @@ void do_async_page_fault(struct pt_regs *regs)
         handle_async_page_fault(regs, &current->thread.sn_async_tlb);
 #endif
 }
+#endif /* CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC() */
+
 
 void vmalloc_sync_all(void)
 {
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index d6e87fda2fb2..4e10c4023028 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -60,8 +60,6 @@ unsigned long VMALLOC_RESERVE = CONFIG_VMALLOC_RESERVE;
 EXPORT_SYMBOL(VMALLOC_RESERVE);
 #endif
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /* Create an L2 page table */
 static pte_t * __init alloc_pte(void)
 {
diff --git a/arch/tile/mm/migrate_64.S b/arch/tile/mm/migrate_64.S
new file mode 100644
index 000000000000..e76fea688beb
--- /dev/null
+++ b/arch/tile/mm/migrate_64.S
@@ -0,0 +1,187 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * This routine is a helper for migrating the home of a set of pages to
+ * a new cpu.  See the documentation in homecache.c for more information.
+ */
+
+#include <linux/linkage.h>
+#include <linux/threads.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
+#include <asm/types.h>
+#include <asm/asm-offsets.h>
+#include <hv/hypervisor.h>
+
+        .text
+
+/*
+ * First, some definitions that apply to all the code in the file.
+ */
+
+/* Locals (caller-save) */
+#define r_tmp           r10
+#define r_save_sp       r11
+
+/* What we save where in the stack frame; must include all callee-saves. */
+#define FRAME_SP        8
+#define FRAME_R30       16
+#define FRAME_R31       24
+#define FRAME_R32       32
+#define FRAME_R33       40
+#define FRAME_SIZE      48
+
+
+
+
+/*
+ * On entry:
+ *
+ *   r0 the new context PA to install (moved to r_context)
+ *   r1 PTE to use for context access (moved to r_access)
+ *   r2 ASID to use for new context (moved to r_asid)
+ *   r3 pointer to cpumask with just this cpu set in it (r_my_cpumask)
+ */
+
+/* Arguments (caller-save) */
+#define r_context_in    r0
+#define r_access_in     r1
+#define r_asid_in       r2
+#define r_my_cpumask    r3
+
+/* Locals (callee-save); must not be more than FRAME_xxx above. */
+#define r_save_ics      r30
+#define r_context       r31
+#define r_access        r32
+#define r_asid          r33
+
+/*
+ * Caller-save locals and frame constants are the same as
+ * for homecache_migrate_stack_and_flush.
+ */
+
+STD_ENTRY(flush_and_install_context)
+        /*
+         * Create a stack frame; we can't touch it once we flush the
+         * cache until we install the new page table and flush the TLB.
+         */
+        {
+         move r_save_sp, sp
+         st sp, lr
+         addi sp, sp, -FRAME_SIZE
+        }
+        addi r_tmp, sp, FRAME_SP
+        {
+         st r_tmp, r_save_sp
+         addi r_tmp, sp, FRAME_R30
+        }
+        {
+         st r_tmp, r30
+         addi r_tmp, sp, FRAME_R31
+        }
+        {
+         st r_tmp, r31
+         addi r_tmp, sp, FRAME_R32
+        }
+        {
+         st r_tmp, r32
+         addi r_tmp, sp, FRAME_R33
+        }
+        st r_tmp, r33
+
+        /* Move some arguments to callee-save registers. */
+        {
+         move r_context, r_context_in
+         move r_access, r_access_in
+        }
+        move r_asid, r_asid_in
+
+        /* Disable interrupts, since we can't use our stack. */
+        {
+         mfspr r_save_ics, INTERRUPT_CRITICAL_SECTION
+         movei r_tmp, 1
+        }
+        mtspr INTERRUPT_CRITICAL_SECTION, r_tmp
+
+        /* First, flush our L2 cache. */
+        {
+         move r0, zero  /* cache_pa */
+         moveli r1, hw2_last(HV_FLUSH_EVICT_L2)  /* cache_control */
+        }
+        {
+         shl16insli r1, r1, hw1(HV_FLUSH_EVICT_L2)
+         move r2, r_my_cpumask  /* cache_cpumask */
+        }
+        {
+         shl16insli r1, r1, hw0(HV_FLUSH_EVICT_L2)
+         move r3, zero  /* tlb_va */
+        }
+        {
+         move r4, zero  /* tlb_length */
+         move r5, zero  /* tlb_pgsize */
+        }
+        {
+         move r6, zero  /* tlb_cpumask */
+         move r7, zero  /* asids */
+        }
+        {
+         move r8, zero  /* asidcount */
+         jal hv_flush_remote
+        }
+        bnez r0, 1f
+
+        /* Now install the new page table. */
+        {
+         move r0, r_context
+         move r1, r_access
+        }
+        {
+         move r2, r_asid
+         movei r3, HV_CTX_DIRECTIO
+        }
+        jal hv_install_context
+        bnez r0, 1f
+
+        /* Finally, flush the TLB. */
+        {
+         movei r0, 0   /* preserve_global */
+         jal hv_flush_all
+        }
+
+1:      /* Reset interrupts back how they were before. */
+        mtspr INTERRUPT_CRITICAL_SECTION, r_save_ics
+
+        /* Restore the callee-saved registers and return. */
+        addli lr, sp, FRAME_SIZE
+        {
+         ld lr, lr
+         addli r_tmp, sp, FRAME_R30
+        }
+        {
+         ld r30, r_tmp
+         addli r_tmp, sp, FRAME_R31
+        }
+        {
+         ld r31, r_tmp
+         addli r_tmp, sp, FRAME_R32
+        }
+        {
+         ld r32, r_tmp
+         addli r_tmp, sp, FRAME_R33
+        }
+        {
+         ld r33, r_tmp
+         addi sp, sp, FRAME_SIZE
+        }
+        jrp lr
+        STD_ENDPROC(flush_and_install_context)
diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug
index 8fce5e536b0f..68205fd3b08c 100644
--- a/arch/um/Kconfig.debug
+++ b/arch/um/Kconfig.debug
@@ -28,13 +28,13 @@ config GCOV
           If you're involved in UML kernel development and want to use gcov,
           say Y.  If you're unsure, say N.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        default N
-        help
-          Track the maximum kernel stack usage - this will look at each
-          kernel stack at process exit and log it if it's the deepest
-          stack seen so far.
+config EARLY_PRINTK
+        bool "Early printk"
+        default y
+        ---help---
+          Write kernel log output directly to stdout.
+
+          This is useful for kernel debugging when your machine crashes very
+          early before the console code is initialized.
 
-          This option will slow down process creation and destruction somewhat.
 endmenu
diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index 1d9b6ae967b0..e7582e1d248c 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -9,7 +9,7 @@
 slip-objs := slip_kern.o slip_user.o
 slirp-objs := slirp_kern.o slirp_user.o
 daemon-objs := daemon_kern.o daemon_user.o
-mcast-objs := mcast_kern.o mcast_user.o
+umcast-objs := umcast_kern.o umcast_user.o
 net-objs := net_kern.o net_user.o
 mconsole-objs := mconsole_kern.o mconsole_user.o
 hostaudio-objs := hostaudio_kern.o
@@ -44,7 +44,7 @@ obj-$(CONFIG_UML_NET_SLIP) += slip.o slip_common.o
 obj-$(CONFIG_UML_NET_SLIRP) += slirp.o slip_common.o
 obj-$(CONFIG_UML_NET_DAEMON) += daemon.o 
 obj-$(CONFIG_UML_NET_VDE) += vde.o
-obj-$(CONFIG_UML_NET_MCAST) += mcast.o 
+obj-$(CONFIG_UML_NET_MCAST) += umcast.o
 obj-$(CONFIG_UML_NET_PCAP) += pcap.o
 obj-$(CONFIG_UML_NET) += net.o 
 obj-$(CONFIG_MCONSOLE) += mconsole.o
diff --git a/arch/um/drivers/mcast.h b/arch/um/drivers/mcast.h
deleted file mode 100644
index 6fa282e896be..000000000000
--- a/arch/um/drivers/mcast.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* 
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __DRIVERS_MCAST_H
-#define __DRIVERS_MCAST_H
-
-#include "net_user.h"
-
-struct mcast_data {
-        char *addr;
-        unsigned short port;
-        void *mcast_addr;
-        int ttl;
-        void *dev;
-};
-
-extern const struct net_user_info mcast_user_info;
-
-extern int mcast_user_write(int fd, void *buf, int len, 
-                            struct mcast_data *pri);
-
-#endif
diff --git a/arch/um/drivers/mcast_kern.c b/arch/um/drivers/mcast_kern.c
deleted file mode 100644
index ffc6416d5ed7..000000000000
--- a/arch/um/drivers/mcast_kern.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * user-mode-linux networking multicast transport
- * Copyright (C) 2001 by Harald Welte <laforge@gnumonks.org>
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- *
- * based on the existing uml-networking code, which is
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- *
- * Licensed under the GPL.
- */
-
-#include "linux/init.h"
-#include <linux/netdevice.h>
-#include "mcast.h"
-#include "net_kern.h"
-
-struct mcast_init {
-        char *addr;
-        int port;
-        int ttl;
-};
-
-static void mcast_init(struct net_device *dev, void *data)
-{
-        struct uml_net_private *pri;
-        struct mcast_data *dpri;
-        struct mcast_init *init = data;
-
-        pri = netdev_priv(dev);
-        dpri = (struct mcast_data *) pri->user;
-        dpri->addr = init->addr;
-        dpri->port = init->port;
-        dpri->ttl = init->ttl;
-        dpri->dev = dev;
-
-        printk("mcast backend multicast address: %s:%u, TTL:%u\n",
-               dpri->addr, dpri->port, dpri->ttl);
-}
-
-static int mcast_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-        return net_recvfrom(fd, skb_mac_header(skb),
-                            skb->dev->mtu + ETH_HEADER_OTHER);
-}
-
-static int mcast_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-        return mcast_user_write(fd, skb->data, skb->len,
-                                (struct mcast_data *) &lp->user);
-}
-
-static const struct net_kern_info mcast_kern_info = {
-        .init                   = mcast_init,
-        .protocol               = eth_protocol,
-        .read                   = mcast_read,
-        .write                  = mcast_write,
-};
-
-static int mcast_setup(char *str, char **mac_out, void *data)
-{
-        struct mcast_init *init = data;
-        char *port_str = NULL, *ttl_str = NULL, *remain;
-        char *last;
-
-        *init = ((struct mcast_init)
-                { .addr         = "239.192.168.1",
-                  .port         = 1102,
-                  .ttl          = 1 });
-
-        remain = split_if_spec(str, mac_out, &init->addr, &port_str, &ttl_str,
-                               NULL);
-        if (remain != NULL) {
-                printk(KERN_ERR "mcast_setup - Extra garbage on "
-                       "specification : '%s'\n", remain);
-                return 0;
-        }
-
-        if (port_str != NULL) {
-                init->port = simple_strtoul(port_str, &last, 10);
-                if ((*last != '\0') || (last == port_str)) {
-                        printk(KERN_ERR "mcast_setup - Bad port : '%s'\n",
-                               port_str);
-                        return 0;
-                }
-        }
-
-        if (ttl_str != NULL) {
-                init->ttl = simple_strtoul(ttl_str, &last, 10);
-                if ((*last != '\0') || (last == ttl_str)) {
-                        printk(KERN_ERR "mcast_setup - Bad ttl : '%s'\n",
-                               ttl_str);
-                        return 0;
-                }
-        }
-
-        printk(KERN_INFO "Configured mcast device: %s:%u-%u\n", init->addr,
-               init->port, init->ttl);
-
-        return 1;
-}
-
-static struct transport mcast_transport = {
-        .list           = LIST_HEAD_INIT(mcast_transport.list),
-        .name           = "mcast",
-        .setup          = mcast_setup,
-        .user           = &mcast_user_info,
-        .kern           = &mcast_kern_info,
-        .private_size   = sizeof(struct mcast_data),
-        .setup_size     = sizeof(struct mcast_init),
-};
-
-static int register_mcast(void)
-{
-        register_transport(&mcast_transport);
-        return 0;
-}
-
-late_initcall(register_mcast);
diff --git a/arch/um/drivers/mcast_user.c b/arch/um/drivers/mcast_user.c
deleted file mode 100644
index ee19e91568a2..000000000000
--- a/arch/um/drivers/mcast_user.c
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * user-mode-linux networking multicast transport
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 by Harald Welte <laforge@gnumonks.org>
- *
- * based on the existing uml-networking code, which is
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- *
- * Licensed under the GPL.
- *
- */
-
-#include <unistd.h>
-#include <errno.h>
-#include <netinet/in.h>
-#include "kern_constants.h"
-#include "mcast.h"
-#include "net_user.h"
-#include "um_malloc.h"
-#include "user.h"
-
-static struct sockaddr_in *new_addr(char *addr, unsigned short port)
-{
-        struct sockaddr_in *sin;
-
-        sin = uml_kmalloc(sizeof(struct sockaddr_in), UM_GFP_KERNEL);
-        if (sin == NULL) {
-                printk(UM_KERN_ERR "new_addr: allocation of sockaddr_in "
-                       "failed\n");
-                return NULL;
-        }
-        sin->sin_family = AF_INET;
-        sin->sin_addr.s_addr = in_aton(addr);
-        sin->sin_port = htons(port);
-        return sin;
-}
-
-static int mcast_user_init(void *data, void *dev)
-{
-        struct mcast_data *pri = data;
-
-        pri->mcast_addr = new_addr(pri->addr, pri->port);
-        pri->dev = dev;
-        return 0;
-}
-
-static void mcast_remove(void *data)
-{
-        struct mcast_data *pri = data;
-
-        kfree(pri->mcast_addr);
-        pri->mcast_addr = NULL;
-}
-
-static int mcast_open(void *data)
-{
-        struct mcast_data *pri = data;
-        struct sockaddr_in *sin = pri->mcast_addr;
-        struct ip_mreq mreq;
-        int fd, yes = 1, err = -EINVAL;
-
-
-        if ((sin->sin_addr.s_addr == 0) || (sin->sin_port == 0))
-                goto out;
-
-        fd = socket(AF_INET, SOCK_DGRAM, 0);
-
-        if (fd < 0) {
-                err = -errno;
-                printk(UM_KERN_ERR "mcast_open : data socket failed, "
-                       "errno = %d\n", errno);
-                goto out;
-        }
-
-        if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0) {
-                err = -errno;
-                printk(UM_KERN_ERR "mcast_open: SO_REUSEADDR failed, "
-                       "errno = %d\n", errno);
-                goto out_close;
-        }
-
-        /* set ttl according to config */
-        if (setsockopt(fd, SOL_IP, IP_MULTICAST_TTL, &pri->ttl,
-                       sizeof(pri->ttl)) < 0) {
-                err = -errno;
-                printk(UM_KERN_ERR "mcast_open: IP_MULTICAST_TTL failed, "
-                       "error = %d\n", errno);
-                goto out_close;
-        }
-
-        /* set LOOP, so data does get fed back to local sockets */
-        if (setsockopt(fd, SOL_IP, IP_MULTICAST_LOOP, &yes, sizeof(yes)) < 0) {
-                err = -errno;
-                printk(UM_KERN_ERR "mcast_open: IP_MULTICAST_LOOP failed, "
-                       "error = %d\n", errno);
-                goto out_close;
-        }
-
-        /* bind socket to mcast address */
-        if (bind(fd, (struct sockaddr *) sin, sizeof(*sin)) < 0) {
-                err = -errno;
-                printk(UM_KERN_ERR "mcast_open : data bind failed, "
-                       "errno = %d\n", errno);
-                goto out_close;
-        }
-
-        /* subscribe to the multicast group */
-        mreq.imr_multiaddr.s_addr = sin->sin_addr.s_addr;
-        mreq.imr_interface.s_addr = 0;
-        if (setsockopt(fd, SOL_IP, IP_ADD_MEMBERSHIP,
-                       &mreq, sizeof(mreq)) < 0) {
-                err = -errno;
-                printk(UM_KERN_ERR "mcast_open: IP_ADD_MEMBERSHIP failed, "
-                       "error = %d\n", errno);
-                printk(UM_KERN_ERR "There appears not to be a multicast-"
-                       "capable network interface on the host.\n");
-                printk(UM_KERN_ERR "eth0 should be configured in order to use "
-                       "the multicast transport.\n");
-                goto out_close;
-        }
-
-        return fd;
-
- out_close:
-        close(fd);
- out:
-        return err;
-}
-
-static void mcast_close(int fd, void *data)
-{
-        struct ip_mreq mreq;
-        struct mcast_data *pri = data;
-        struct sockaddr_in *sin = pri->mcast_addr;
-
-        mreq.imr_multiaddr.s_addr = sin->sin_addr.s_addr;
-        mreq.imr_interface.s_addr = 0;
-        if (setsockopt(fd, SOL_IP, IP_DROP_MEMBERSHIP,
-                       &mreq, sizeof(mreq)) < 0) {
-                printk(UM_KERN_ERR "mcast_open: IP_DROP_MEMBERSHIP failed, "
-                       "error = %d\n", errno);
-        }
-
-        close(fd);
-}
-
-int mcast_user_write(int fd, void *buf, int len, struct mcast_data *pri)
-{
-        struct sockaddr_in *data_addr = pri->mcast_addr;
-
-        return net_sendto(fd, buf, len, data_addr, sizeof(*data_addr));
-}
-
-const struct net_user_info mcast_user_info = {
-        .init           = mcast_user_init,
-        .open           = mcast_open,
-        .close          = mcast_close,
-        .remove         = mcast_remove,
-        .add_address    = NULL,
-        .delete_address = NULL,
-        .mtu            = ETH_MAX_PACKET,
-        .max_packet     = ETH_MAX_PACKET + ETH_HEADER_OTHER,
-};
diff --git a/arch/um/drivers/umcast.h b/arch/um/drivers/umcast.h
new file mode 100644
index 000000000000..6f8c0fe890fb
--- /dev/null
+++ b/arch/um/drivers/umcast.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __DRIVERS_UMCAST_H
+#define __DRIVERS_UMCAST_H
+
+#include "net_user.h"
+
+struct umcast_data {
+        char *addr;
+        unsigned short lport;
+        unsigned short rport;
+        void *listen_addr;
+        void *remote_addr;
+        int ttl;
+        int unicast;
+        void *dev;
+};
+
+extern const struct net_user_info umcast_user_info;
+
+extern int umcast_user_write(int fd, void *buf, int len,
+                             struct umcast_data *pri);
+
+#endif
diff --git a/arch/um/drivers/umcast_kern.c b/arch/um/drivers/umcast_kern.c
new file mode 100644
index 000000000000..42dab11d2ecf
--- /dev/null
+++ b/arch/um/drivers/umcast_kern.c
@@ -0,0 +1,188 @@
+/*
+ * user-mode-linux networking multicast transport
+ * Copyright (C) 2001 by Harald Welte <laforge@gnumonks.org>
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ *
+ * based on the existing uml-networking code, which is
+ * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
+ * James Leu (jleu@mindspring.net).
+ * Copyright (C) 2001 by various other people who didn't put their name here.
+ *
+ * Licensed under the GPL.
+ */
+
+#include "linux/init.h"
+#include <linux/netdevice.h>
+#include "umcast.h"
+#include "net_kern.h"
+
+struct umcast_init {
+        char *addr;
+        int lport;
+        int rport;
+        int ttl;
+        bool unicast;
+};
+
+static void umcast_init(struct net_device *dev, void *data)
+{
+        struct uml_net_private *pri;
+        struct umcast_data *dpri;
+        struct umcast_init *init = data;
+
+        pri = netdev_priv(dev);
+        dpri = (struct umcast_data *) pri->user;
+        dpri->addr = init->addr;
+        dpri->lport = init->lport;
+        dpri->rport = init->rport;
+        dpri->unicast = init->unicast;
+        dpri->ttl = init->ttl;
+        dpri->dev = dev;
+
+        if (dpri->unicast) {
+                printk(KERN_INFO "ucast backend address: %s:%u listen port: "
+                       "%u\n", dpri->addr, dpri->rport, dpri->lport);
+        } else {
+                printk(KERN_INFO "mcast backend multicast address: %s:%u, "
+                       "TTL:%u\n", dpri->addr, dpri->lport, dpri->ttl);
+        }
+}
+
+static int umcast_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
+{
+        return net_recvfrom(fd, skb_mac_header(skb),
+                            skb->dev->mtu + ETH_HEADER_OTHER);
+}
+
+static int umcast_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
+{
+        return umcast_user_write(fd, skb->data, skb->len,
+                                (struct umcast_data *) &lp->user);
+}
+
+static const struct net_kern_info umcast_kern_info = {
+        .init                   = umcast_init,
+        .protocol               = eth_protocol,
+        .read                   = umcast_read,
+        .write                  = umcast_write,
+};
+
+static int mcast_setup(char *str, char **mac_out, void *data)
+{
+        struct umcast_init *init = data;
+        char *port_str = NULL, *ttl_str = NULL, *remain;
+        char *last;
+
+        *init = ((struct umcast_init)
+                { .addr = "239.192.168.1",
+                  .lport        = 1102,
+                  .ttl  = 1 });
+
+        remain = split_if_spec(str, mac_out, &init->addr, &port_str, &ttl_str,
+                               NULL);
+        if (remain != NULL) {
+                printk(KERN_ERR "mcast_setup - Extra garbage on "
+                       "specification : '%s'\n", remain);
+                return 0;
+        }
+
+        if (port_str != NULL) {
+                init->lport = simple_strtoul(port_str, &last, 10);
+                if ((*last != '\0') || (last == port_str)) {
+                        printk(KERN_ERR "mcast_setup - Bad port : '%s'\n",
+                               port_str);
+                        return 0;
+                }
+        }
+
+        if (ttl_str != NULL) {
+                init->ttl = simple_strtoul(ttl_str, &last, 10);
+                if ((*last != '\0') || (last == ttl_str)) {
+                        printk(KERN_ERR "mcast_setup - Bad ttl : '%s'\n",
+                               ttl_str);
+                        return 0;
+                }
+        }
+
+        init->unicast = false;
+        init->rport = init->lport;
+
+        printk(KERN_INFO "Configured mcast device: %s:%u-%u\n", init->addr,
+               init->lport, init->ttl);
+
+        return 1;
+}
+
+static int ucast_setup(char *str, char **mac_out, void *data)
+{
+        struct umcast_init *init = data;
+        char *lport_str = NULL, *rport_str = NULL, *remain;
+        char *last;
+
+        *init = ((struct umcast_init)
+                { .addr         = "",
+                  .lport        = 1102,
+                  .rport        = 1102 });
+
+        remain = split_if_spec(str, mac_out, &init->addr,
+                               &lport_str, &rport_str, NULL);
+        if (remain != NULL) {
+                printk(KERN_ERR "ucast_setup - Extra garbage on "
+                       "specification : '%s'\n", remain);
+                return 0;
+        }
+
+        if (lport_str != NULL) {
+                init->lport = simple_strtoul(lport_str, &last, 10);
+                if ((*last != '\0') || (last == lport_str)) {
+                        printk(KERN_ERR "ucast_setup - Bad listen port : "
+                               "'%s'\n", lport_str);
+                        return 0;
+                }
+        }
+
+        if (rport_str != NULL) {
+                init->rport = simple_strtoul(rport_str, &last, 10);
+                if ((*last != '\0') || (last == rport_str)) {
+                        printk(KERN_ERR "ucast_setup - Bad remote port : "
+                               "'%s'\n", rport_str);
+                        return 0;
+                }
+        }
+
+        init->unicast = true;
+
+        printk(KERN_INFO "Configured ucast device: :%u -> %s:%u\n",
+               init->lport, init->addr, init->rport);
+
+        return 1;
+}
+
+static struct transport mcast_transport = {
+        .list   = LIST_HEAD_INIT(mcast_transport.list),
+        .name   = "mcast",
+        .setup  = mcast_setup,
+        .user   = &umcast_user_info,
+        .kern   = &umcast_kern_info,
+        .private_size   = sizeof(struct umcast_data),
+        .setup_size     = sizeof(struct umcast_init),
+};
+
+static struct transport ucast_transport = {
+        .list   = LIST_HEAD_INIT(ucast_transport.list),
+        .name   = "ucast",
+        .setup  = ucast_setup,
+        .user   = &umcast_user_info,
+        .kern   = &umcast_kern_info,
+        .private_size   = sizeof(struct umcast_data),
+        .setup_size     = sizeof(struct umcast_init),
+};
+
+static int register_umcast(void)
+{
+        register_transport(&mcast_transport);
+        register_transport(&ucast_transport);
+        return 0;
+}
+
+late_initcall(register_umcast);
diff --git a/arch/um/drivers/umcast_user.c b/arch/um/drivers/umcast_user.c
new file mode 100644
index 000000000000..59c56fd6f52a
--- /dev/null
+++ b/arch/um/drivers/umcast_user.c
@@ -0,0 +1,186 @@
+/*
+ * user-mode-linux networking multicast transport
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2001 by Harald Welte <laforge@gnumonks.org>
+ *
+ * based on the existing uml-networking code, which is
+ * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
+ * James Leu (jleu@mindspring.net).
+ * Copyright (C) 2001 by various other people who didn't put their name here.
+ *
+ * Licensed under the GPL.
+ *
+ */
+
+#include <unistd.h>
+#include <errno.h>
+#include <netinet/in.h>
+#include "kern_constants.h"
+#include "umcast.h"
+#include "net_user.h"
+#include "um_malloc.h"
+#include "user.h"
+
+static struct sockaddr_in *new_addr(char *addr, unsigned short port)
+{
+        struct sockaddr_in *sin;
+
+        sin = uml_kmalloc(sizeof(struct sockaddr_in), UM_GFP_KERNEL);
+        if (sin == NULL) {
+                printk(UM_KERN_ERR "new_addr: allocation of sockaddr_in "
+                       "failed\n");
+                return NULL;
+        }
+        sin->sin_family = AF_INET;
+        if (addr)
+                sin->sin_addr.s_addr = in_aton(addr);
+        else
+                sin->sin_addr.s_addr = INADDR_ANY;
+        sin->sin_port = htons(port);
+        return sin;
+}
+
+static int umcast_user_init(void *data, void *dev)
+{
+        struct umcast_data *pri = data;
+
+        pri->remote_addr = new_addr(pri->addr, pri->rport);
+        if (pri->unicast)
+                pri->listen_addr = new_addr(NULL, pri->lport);
+        else
+                pri->listen_addr = pri->remote_addr;
+        pri->dev = dev;
+        return 0;
+}
+
+static void umcast_remove(void *data)
+{
+        struct umcast_data *pri = data;
+
+        kfree(pri->listen_addr);
+        if (pri->unicast)
+                kfree(pri->remote_addr);
+        pri->listen_addr = pri->remote_addr = NULL;
+}
+
+static int umcast_open(void *data)
+{
+        struct umcast_data *pri = data;
+        struct sockaddr_in *lsin = pri->listen_addr;
+        struct sockaddr_in *rsin = pri->remote_addr;
+        struct ip_mreq mreq;
+        int fd, yes = 1, err = -EINVAL;
+
+
+        if ((!pri->unicast && lsin->sin_addr.s_addr == 0) ||
+            (rsin->sin_addr.s_addr == 0) ||
+            (lsin->sin_port == 0) || (rsin->sin_port == 0))
+                goto out;
+
+        fd = socket(AF_INET, SOCK_DGRAM, 0);
+
+        if (fd < 0) {
+                err = -errno;
+                printk(UM_KERN_ERR "umcast_open : data socket failed, "
+                       "errno = %d\n", errno);
+                goto out;
+        }
+
+        if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0) {
+                err = -errno;
+                printk(UM_KERN_ERR "umcast_open: SO_REUSEADDR failed, "
+                       "errno = %d\n", errno);
+                goto out_close;
+        }
+
+        if (!pri->unicast) {
+                /* set ttl according to config */
+                if (setsockopt(fd, SOL_IP, IP_MULTICAST_TTL, &pri->ttl,
+                               sizeof(pri->ttl)) < 0) {
+                        err = -errno;
+                        printk(UM_KERN_ERR "umcast_open: IP_MULTICAST_TTL "
+                               "failed, error = %d\n", errno);
+                        goto out_close;
+                }
+
+                /* set LOOP, so data does get fed back to local sockets */
+                if (setsockopt(fd, SOL_IP, IP_MULTICAST_LOOP,
+                               &yes, sizeof(yes)) < 0) {
+                        err = -errno;
+                        printk(UM_KERN_ERR "umcast_open: IP_MULTICAST_LOOP "
+                               "failed, error = %d\n", errno);
+                        goto out_close;
+                }
+        }
+
+        /* bind socket to the address */
+        if (bind(fd, (struct sockaddr *) lsin, sizeof(*lsin)) < 0) {
+                err = -errno;
+                printk(UM_KERN_ERR "umcast_open : data bind failed, "
+                       "errno = %d\n", errno);
+                goto out_close;
+        }
+
+        if (!pri->unicast) {
+                /* subscribe to the multicast group */
+                mreq.imr_multiaddr.s_addr = lsin->sin_addr.s_addr;
+                mreq.imr_interface.s_addr = 0;
+                if (setsockopt(fd, SOL_IP, IP_ADD_MEMBERSHIP,
+                               &mreq, sizeof(mreq)) < 0) {
+                        err = -errno;
+                        printk(UM_KERN_ERR "umcast_open: IP_ADD_MEMBERSHIP "
+                               "failed, error = %d\n", errno);
+                        printk(UM_KERN_ERR "There appears not to be a "
+                               "multicast-capable network interface on the "
+                               "host.\n");
+                        printk(UM_KERN_ERR "eth0 should be configured in order "
+                               "to use the multicast transport.\n");
+                        goto out_close;
+                }
+        }
+
+        return fd;
+
+ out_close:
+        close(fd);
+ out:
+        return err;
+}
+
+static void umcast_close(int fd, void *data)
+{
+        struct umcast_data *pri = data;
+
+        if (!pri->unicast) {
+                struct ip_mreq mreq;
+                struct sockaddr_in *lsin = pri->listen_addr;
+
+                mreq.imr_multiaddr.s_addr = lsin->sin_addr.s_addr;
+                mreq.imr_interface.s_addr = 0;
+                if (setsockopt(fd, SOL_IP, IP_DROP_MEMBERSHIP,
+                               &mreq, sizeof(mreq)) < 0) {
+                        printk(UM_KERN_ERR "umcast_close: IP_DROP_MEMBERSHIP "
+                               "failed, error = %d\n", errno);
+                }
+        }
+
+        close(fd);
+}
+
+int umcast_user_write(int fd, void *buf, int len, struct umcast_data *pri)
+{
+        struct sockaddr_in *data_addr = pri->remote_addr;
+
+        return net_sendto(fd, buf, len, data_addr, sizeof(*data_addr));
+}
+
+const struct net_user_info umcast_user_info = {
+        .init   = umcast_user_init,
+        .open   = umcast_open,
+        .close  = umcast_close,
+        .remove = umcast_remove,
+        .add_address    = NULL,
+        .delete_address = NULL,
+        .mtu    = ETH_MAX_PACKET,
+        .max_packet     = ETH_MAX_PACKET + ETH_HEADER_OTHER,
+};
diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c
index da2caa5a21ef..8ac7146c237f 100644
--- a/arch/um/drivers/xterm.c
+++ b/arch/um/drivers/xterm.c
@@ -90,7 +90,7 @@ static int xterm_open(int input, int output, int primary, void *d,
         int pid, fd, new, err;
         char title[256], file[] = "/tmp/xterm-pipeXXXXXX";
         char *argv[] = { terminal_emulator, title_switch, title, exec_switch,
-                         "/usr/lib/uml/port-helper", "-uml-socket",
+                         OS_LIB_PATH "/uml/port-helper", "-uml-socket",
                          file, NULL };
 
         if (access(argv[4], X_OK) < 0)
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index d1d1b0d8a0cd..98d01bc4fa92 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -14,6 +14,8 @@ struct task_struct;
 #include "registers.h"
 #include "sysdep/archsetjmp.h"
 
+#include <linux/prefetch.h>
+
 struct mm_struct;
 
 struct thread_struct {
diff --git a/arch/um/include/asm/smp.h b/arch/um/include/asm/smp.h
index f27a96313174..4a4b09d4f366 100644
--- a/arch/um/include/asm/smp.h
+++ b/arch/um/include/asm/smp.h
@@ -11,7 +11,6 @@
 
 #define cpu_logical_map(n) (n)
 #define cpu_number_map(n) (n)
-#define PROC_CHANGE_PENALTY     15 /* Pick a number, any number */
 extern int hard_smp_processor_id(void);
 #define NO_PROC_ID -1
 
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 660caedac9eb..4febacd1a8a1 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -22,9 +22,6 @@ struct mmu_gather {
         unsigned int            fullmm; /* non-zero means full mm flush */
 };
 
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
                                           unsigned long address)
 {
@@ -47,27 +44,20 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
         }
 }
 
-/* tlb_gather_mmu
- *      Return a pointer to an initialized struct mmu_gather.
- */
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
 {
-        struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
         tlb->mm = mm;
         tlb->fullmm = full_mm_flush;
 
         init_tlb_gather(tlb);
-
-        return tlb;
 }
 
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
                                unsigned long end);
 
 static inline void
-tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+tlb_flush_mmu(struct mmu_gather *tlb)
 {
         if (!tlb->need_flush)
                 return;
@@ -83,12 +73,10 @@ tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 static inline void
 tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 {
-        tlb_flush_mmu(tlb, start, end);
+        tlb_flush_mmu(tlb);
 
         /* keep the page table cache within bounds */
         check_pgt_cache();
-
-        put_cpu_var(mmu_gathers);
 }
 
 /* tlb_remove_page
@@ -96,11 +84,16 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
  *      while handling the additional races in SMP caused by other CPUs
  *      caching valid mappings in their TLBs.
  */
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
         tlb->need_flush = 1;
         free_page_and_swap_cache(page);
-        return;
+        return 1; /* avoid calling tlb_flush_mmu */
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        __tlb_remove_page(tlb, page);
 }
 
 /**
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index c4617baaa4f2..83c7c2ecd614 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -29,6 +29,12 @@
 #define OS_ACC_R_OK    4       /* Test for read permission.  */
 #define OS_ACC_RW_OK   (OS_ACC_W_OK | OS_ACC_R_OK) /* Test for RW permission */
 
+#ifdef CONFIG_64BIT
+#define OS_LIB_PATH     "/usr/lib64/"
+#else
+#define OS_LIB_PATH     "/usr/lib/"
+#endif
+
 /*
  * types taken from stat_file() in hostfs_user.c
  * (if they are wrong here, they are wrong there...).
@@ -238,6 +244,7 @@ extern int raw(int fd);
 extern void setup_machinename(char *machine_out);
 extern void setup_hostinfo(char *buf, int len);
 extern void os_dump_core(void) __attribute__ ((noreturn));
+extern void um_early_printk(const char *s, unsigned int n);
 
 /* time.c */
 extern void idle_sleep(unsigned long long nsecs);
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 1119233597a1..c4491c15afb2 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -17,6 +17,7 @@ obj-y = config.o exec.o exitcode.o init_task.o irq.o ksyms.o mem.o \
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)     += gprof_syms.o
 obj-$(CONFIG_GCOV)      += gmon_syms.o
+obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 
 USER_OBJS := config.o
 
diff --git a/arch/um/kernel/early_printk.c b/arch/um/kernel/early_printk.c
new file mode 100644
index 000000000000..ec649bf72f68
--- /dev/null
+++ b/arch/um/kernel/early_printk.c
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2011 Richard Weinberger <richrd@nod.at>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/console.h>
+#include <linux/init.h>
+#include "os.h"
+
+static void early_console_write(struct console *con, const char *s, unsigned int n)
+{
+        um_early_printk(s, n);
+}
+
+static struct console early_console = {
+        .name = "earlycon",
+        .write = early_console_write,
+        .flags = CON_BOOT,
+        .index = -1,
+};
+
+static int __init setup_early_printk(char *buf)
+{
+        register_console(&early_console);
+
+        return 0;
+}
+
+early_param("earlyprintk", setup_early_printk);
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index eefb107d2d73..155206a66908 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -7,9 +7,6 @@
 #include "asm/pgalloc.h"
 #include "asm/tlb.h"
 
-/* For some reason, mmu_gathers are referenced when CONFIG_SMP is off. */
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 #ifdef CONFIG_SMP
 
 #include "linux/sched.h"
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 637c6505dc00..8c7b8823d1f0 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -113,6 +113,27 @@ out_of_memory:
         return 0;
 }
 
+static void show_segv_info(struct uml_pt_regs *regs)
+{
+        struct task_struct *tsk = current;
+        struct faultinfo *fi = UPT_FAULTINFO(regs);
+
+        if (!unhandled_signal(tsk, SIGSEGV))
+                return;
+
+        if (!printk_ratelimit())
+                return;
+
+        printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
+                task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+                tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
+                (void *)UPT_IP(regs), (void *)UPT_SP(regs),
+                fi->error_code);
+
+        print_vma_addr(KERN_CONT " in ", UPT_IP(regs));
+        printk(KERN_CONT "\n");
+}
+
 static void bad_segv(struct faultinfo fi, unsigned long ip)
 {
         struct siginfo si;
@@ -141,6 +162,7 @@ void segv_handler(int sig, struct uml_pt_regs *regs)
         struct faultinfo * fi = UPT_FAULTINFO(regs);
 
         if (UPT_IS_USER(regs) && !SEGV_IS_FIXABLE(fi)) {
+                show_segv_info(regs);
                 bad_segv(*fi, UPT_IP(regs));
                 return;
         }
@@ -202,6 +224,8 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
                       address, ip);
         }
 
+        show_segv_info(regs);
+
         if (err == -EACCES) {
                 si.si_signo = SIGBUS;
                 si.si_errno = 0;
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index eee69b9f52c9..fb2a97a75fb1 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -78,7 +78,7 @@ static void install_fatal_handler(int sig)
         }
 }
 
-#define UML_LIB_PATH    ":/usr/lib/uml"
+#define UML_LIB_PATH    ":" OS_LIB_PATH "/uml"
 
 static void setup_env_path(void)
 {
@@ -142,7 +142,6 @@ int __init main(int argc, char **argv, char **envp)
          */
         install_fatal_handler(SIGINT);
         install_fatal_handler(SIGTERM);
-        install_fatal_handler(SIGHUP);
 
         scan_elf_aux(envp);
 
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index e0477c3ee894..0c45dc8efb05 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -253,6 +253,7 @@ void init_new_thread_signals(void)
                     SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH, SIGALRM,
                     SIGVTALRM, -1);
         signal(SIGWINCH, SIG_IGN);
+        signal(SIGTERM, SIG_DFL);
 }
 
 int run_kernel_thread(int (*fn)(void *), void *arg, jmp_buf **jmp_ptr)
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 42827cafa6af..5803b1887672 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -139,3 +139,8 @@ void os_dump_core(void)
 
         uml_abort();
 }
+
+void um_early_printk(const char *s, unsigned int n)
+{
+        printf("%.*s", n, s);
+}
diff --git a/arch/unicore32/Kconfig.debug b/arch/unicore32/Kconfig.debug
index 3140151ede45..ae2ec334c3c6 100644
--- a/arch/unicore32/Kconfig.debug
+++ b/arch/unicore32/Kconfig.debug
@@ -27,13 +27,6 @@ config EARLY_PRINTK
           with klogd/syslogd or the X server. You should normally N here,
           unless you want to debug such a crash.
 
-config DEBUG_STACK_USAGE
-        bool "Enable stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        help
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T output.
-
 # These options are only for real kernel hackers who want to get their hands dirty.
 config DEBUG_LL
         bool "Kernel low-level debugging functions"
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index 1fc02633f700..2d3e7112d2a3 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -62,7 +62,7 @@ void show_mem(unsigned int filter)
         struct meminfo *mi = &meminfo;
 
         printk(KERN_DEFAULT "Mem-info:\n");
-        show_free_areas();
+        show_free_areas(filter);
 
         for_each_bank(i, mi) {
                 struct membank *bank = &mi->bank[i];
diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c
index db2d334941b4..3e5c3e5a0b45 100644
--- a/arch/unicore32/mm/mmu.c
+++ b/arch/unicore32/mm/mmu.c
@@ -30,8 +30,6 @@
 
 #include "mm.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * empty_zero_page is a special page that is used for
  * zero-initialized data and COW.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dcf25b71f6d7..483775f42d2a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -17,8 +17,6 @@ config X86_64
 config X86
         def_bool y
         select HAVE_AOUT if X86_32
-        select HAVE_READQ
-        select HAVE_WRITEQ
         select HAVE_UNSTABLE_SCHED_CLOCK
         select HAVE_IDE
         select HAVE_OPROFILE
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 615e18810f48..c0f8a5c88910 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -66,26 +66,6 @@ config DEBUG_STACKOVERFLOW
           This option will cause messages to be printed if free stack space
           drops below a certain limit.
 
-config DEBUG_STACK_USAGE
-        bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
-        ---help---
-          Enables the display of the minimum amount of free stack which each
-          task has ever had available in the sysrq-T and sysrq-P debug output.
-
-          This option will slow down process creation somewhat.
-
-config DEBUG_PER_CPU_MAPS
-        bool "Debug access to per_cpu maps"
-        depends on DEBUG_KERNEL
-        depends on SMP
-        ---help---
-          Say Y to verify that the per_cpu map being accessed has
-          been setup.  Adds a fair amount of code to kernel memory
-          and decreases performance.
-
-          Say N if unsure.
-
 config X86_PTDUMP
         bool "Export kernel pagetable layout to userspace via debugfs"
         depends on DEBUG_KERNEL
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 072273082528..d02804d650c4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -38,7 +38,6 @@
 
 #include <linux/string.h>
 #include <linux/compiler.h>
-#include <asm-generic/int-ll64.h>
 #include <asm/page.h>
 
 #include <xen/xen.h>
@@ -87,27 +86,6 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
 
-#else
-
-static inline __u64 readq(const volatile void __iomem *addr)
-{
-        const volatile u32 __iomem *p = addr;
-        u32 low, high;
-
-        low = readl(p);
-        high = readl(p + 1);
-
-        return low + ((u64)high << 32);
-}
-
-static inline void writeq(__u64 val, volatile void __iomem *addr)
-{
-        writel(val, addr);
-        writel(val >> 32, addr+4);
-}
-
-#endif
-
 #define readq_relaxed(a)        readq(a)
 
 #define __raw_readq(a)          readq(a)
@@ -117,6 +95,8 @@ static inline void writeq(__u64 val, volatile void __iomem *addr)
 #define readq                   readq
 #define writeq                  writeq
 
+#endif
+
 /**
  *      virt_to_phys    -       map virtual addresses to physical
  *      @address: address to remap
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 605e5ae19c7f..a3e5948670c2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -946,6 +946,8 @@ void __init setup_arch(char **cmdline_p)
         if (init_ohci1394_dma_early)
                 init_ohci1394_dma_on_all_controllers();
 #endif
+        /* Allocate bigger log buffer */
+        setup_log_buf(1);
 
         reserve_initrd();
 
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 998e972f3b1a..30ac65df7d4e 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -110,7 +110,6 @@ static struct mm_struct tboot_mm = {
         .mmap_sem       = __RWSEM_INITIALIZER(init_mm.mmap_sem),
         .page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
         .mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
-        .cpu_vm_mask    = CPU_MASK_ALL,
 };
 
 static inline void switch_to_tboot_pt(void)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 28418054b880..bd14bb4c8594 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3545,10 +3545,11 @@ static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm,
         return kvm_mmu_prepare_zap_page(kvm, page, invalid_list);
 }
 
-static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
 {
         struct kvm *kvm;
         struct kvm *kvm_freed = NULL;
+        int nr_to_scan = sc->nr_to_scan;
 
         if (nr_to_scan == 0)
                 goto out;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index bcb394dfbb35..f7a2a054a3c0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -965,7 +965,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
         struct mm_struct *mm;
         int fault;
         int write = error_code & PF_WRITE;
-        unsigned int flags = FAULT_FLAG_ALLOW_RETRY |
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
                                         (write ? FAULT_FLAG_WRITE : 0);
 
         tsk = current;
@@ -1139,6 +1139,16 @@ good_area:
         }
 
         /*
+         * Pagefault was interrupted by SIGKILL. We have no reason to
+         * continue pagefault.
+         */
+        if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+                if (!(error_code & PF_USER))
+                        no_context(regs, error_code, address);
+                return;
+        }
+
+        /*
          * Major/minor page fault accounting is only done on the
          * initial attempt. If we go through a retry, it is extremely
          * likely that the page will be found in page cache at that point.
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index d4203988504a..f581a18c0d4d 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -72,7 +72,7 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
         if (!vma_shareable(vma, addr))
                 return;
 
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
                 if (svma == vma)
                         continue;
@@ -97,7 +97,7 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
                 put_page(virt_to_page(spte));
         spin_unlock(&mm->page_table_lock);
 out:
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
 }
 
 /*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 37b8b0fe8320..30326443ab81 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -16,8 +16,6 @@
 #include <asm/tlb.h>
 #include <asm/proto.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 unsigned long __initdata pgt_buf_start;
 unsigned long __meminitdata pgt_buf_end;
 unsigned long __meminitdata pgt_buf_top;
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index 161bb89e98c8..7a5591a71f85 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -171,10 +171,6 @@ extern void copy_user_page(void*, void*, unsigned long, struct page*);
 #define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #define page_to_phys(page)      (page_to_pfn(page) << PAGE_SHIFT)
 
-#ifdef CONFIG_MMU
-#define WANT_PAGE_VIRTUAL
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_EXEC | \
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 4bb91a970f1f..ca81654f3ec2 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -14,8 +14,6 @@
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 void __init paging_init(void)
 {
         memset(swapper_pg_dir, 0, PAGE_SIZE);
diff --git a/arch/xtensa/mm/pgtable.c b/arch/xtensa/mm/pgtable.c
deleted file mode 100644
index 697992738205..000000000000
--- a/arch/xtensa/mm/pgtable.c
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * arch/xtensa/mm/pgtable.c
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- *
- * Chris Zankel <chris@zankel.net>
- */
-
-#if (DCACHE_SIZE > PAGE_SIZE)
-
-pte_t* pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
-{
-        pte_t *pte = NULL, *p;
-        int color = ADDR_COLOR(address);
-        int i;
-
-        p = (pte_t*) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, COLOR_ORDER);
-
-        if (likely(p)) {
-                split_page(virt_to_page(p), COLOR_ORDER);
-
-                for (i = 0; i < COLOR_SIZE; i++) {
-                        if (ADDR_COLOR(p) == color)
-                                pte = p;
-                        else
-                                free_page(p);
-                        p += PTRS_PER_PTE;
-                }
-                clear_page(pte);
-        }
-        return pte;
-}
-
-#ifdef PROFILING
-
-int mask;
-int hit;
-int flush;
-
-#endif
-
-struct page* pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-        struct page *page = NULL, *p;
-        int color = ADDR_COLOR(address);
-
-        p = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
-
-        if (likely(p)) {
-                split_page(p, COLOR_ORDER);
-
-                for (i = 0; i < PAGE_ORDER; i++) {
-                        if (PADDR_COLOR(page_address(p)) == color)
-                                page = p;
-                        else
-                                __free_page(p);
-                        p++;
-                }
-                clear_highpage(page);
-        }
-
-        return page;
-}
-
-#endif
-
-
-
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 471fdcc5df85..07371cfdfae6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -385,25 +385,40 @@ void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time,
 
         spin_lock_irqsave(&blkg->stats_lock, flags);
         blkg->stats.time += time;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
         blkg->stats.unaccounted_time += unaccounted_time;
+#endif
         spin_unlock_irqrestore(&blkg->stats_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
 
+/*
+ * should be called under rcu read lock or queue lock to make sure blkg pointer
+ * is valid.
+ */
 void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
                                 uint64_t bytes, bool direction, bool sync)
 {
-        struct blkio_group_stats *stats;
+        struct blkio_group_stats_cpu *stats_cpu;
         unsigned long flags;
 
-        spin_lock_irqsave(&blkg->stats_lock, flags);
-        stats = &blkg->stats;
-        stats->sectors += bytes >> 9;
-        blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction,
-                        sync);
-        blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes,
-                        direction, sync);
-        spin_unlock_irqrestore(&blkg->stats_lock, flags);
+        /*
+         * Disabling interrupts to provide mutual exclusion between two
+         * writes on same cpu. It probably is not needed for 64bit. Not
+         * optimizing that case yet.
+         */
+        local_irq_save(flags);
+
+        stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+        u64_stats_update_begin(&stats_cpu->syncp);
+        stats_cpu->sectors += bytes >> 9;
+        blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICED],
+                        1, direction, sync);
+        blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICE_BYTES],
+                        bytes, direction, sync);
+        u64_stats_update_end(&stats_cpu->syncp);
+        local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
 
@@ -426,18 +441,44 @@ void blkiocg_update_completion_stats(struct blkio_group *blkg,
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
 
+/*  Merged stats are per cpu.  */
 void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
                                         bool sync)
 {
+        struct blkio_group_stats_cpu *stats_cpu;
         unsigned long flags;
 
-        spin_lock_irqsave(&blkg->stats_lock, flags);
-        blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction,
-                        sync);
-        spin_unlock_irqrestore(&blkg->stats_lock, flags);
+        /*
+         * Disabling interrupts to provide mutual exclusion between two
+         * writes on same cpu. It probably is not needed for 64bit. Not
+         * optimizing that case yet.
+         */
+        local_irq_save(flags);
+
+        stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+        u64_stats_update_begin(&stats_cpu->syncp);
+        blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
+                                direction, sync);
+        u64_stats_update_end(&stats_cpu->syncp);
+        local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
+/*
+ * This function allocates the per cpu stats for blkio_group. Should be called
+ * from sleepable context as alloc_per_cpu() requires that.
+ */
+int blkio_alloc_blkg_stats(struct blkio_group *blkg)
+{
+        /* Allocate memory for per cpu stats */
+        blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
+        if (!blkg->stats_cpu)
+                return -ENOMEM;
+        return 0;
+}
+EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
+
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
                 struct blkio_group *blkg, void *key, dev_t dev,
                 enum blkio_policy_id plid)
@@ -508,6 +549,30 @@ struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
 }
 EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
 
+static void blkio_reset_stats_cpu(struct blkio_group *blkg)
+{
+        struct blkio_group_stats_cpu *stats_cpu;
+        int i, j, k;
+        /*
+         * Note: On 64 bit arch this should not be an issue. This has the
+         * possibility of returning some inconsistent value on 32bit arch
+         * as 64bit update on 32bit is non atomic. Taking care of this
+         * corner case makes code very complicated, like sending IPIs to
+         * cpus, taking care of stats of offline cpus etc.
+         *
+         * reset stats is anyway more of a debug feature and this sounds a
+         * corner case. So I am not complicating the code yet until and
+         * unless this becomes a real issue.
+         */
+        for_each_possible_cpu(i) {
+                stats_cpu = per_cpu_ptr(blkg->stats_cpu, i);
+                stats_cpu->sectors = 0;
+                for(j = 0; j < BLKIO_STAT_CPU_NR; j++)
+                        for (k = 0; k < BLKIO_STAT_TOTAL; k++)
+                                stats_cpu->stat_arr_cpu[j][k] = 0;
+        }
+}
+
 static int
 blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 {
@@ -552,7 +617,11 @@ blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
                 }
 #endif
                 spin_unlock(&blkg->stats_lock);
+
+                /* Reset Per cpu stats which don't take blkg->stats_lock */
+                blkio_reset_stats_cpu(blkg);
         }
+
         spin_unlock_irq(&blkcg->lock);
         return 0;
 }
@@ -598,6 +667,59 @@ static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
         return val;
 }
 
+
+static uint64_t blkio_read_stat_cpu(struct blkio_group *blkg,
+                        enum stat_type_cpu type, enum stat_sub_type sub_type)
+{
+        int cpu;
+        struct blkio_group_stats_cpu *stats_cpu;
+        u64 val = 0, tval;
+
+        for_each_possible_cpu(cpu) {
+                unsigned int start;
+                stats_cpu  = per_cpu_ptr(blkg->stats_cpu, cpu);
+
+                do {
+                        start = u64_stats_fetch_begin(&stats_cpu->syncp);
+                        if (type == BLKIO_STAT_CPU_SECTORS)
+                                tval = stats_cpu->sectors;
+                        else
+                                tval = stats_cpu->stat_arr_cpu[type][sub_type];
+                } while(u64_stats_fetch_retry(&stats_cpu->syncp, start));
+
+                val += tval;
+        }
+
+        return val;
+}
+
+static uint64_t blkio_get_stat_cpu(struct blkio_group *blkg,
+                struct cgroup_map_cb *cb, dev_t dev, enum stat_type_cpu type)
+{
+        uint64_t disk_total, val;
+        char key_str[MAX_KEY_LEN];
+        enum stat_sub_type sub_type;
+
+        if (type == BLKIO_STAT_CPU_SECTORS) {
+                val = blkio_read_stat_cpu(blkg, type, 0);
+                return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, val, cb, dev);
+        }
+
+        for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
+                        sub_type++) {
+                blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
+                val = blkio_read_stat_cpu(blkg, type, sub_type);
+                cb->fill(cb, key_str, val);
+        }
+
+        disk_total = blkio_read_stat_cpu(blkg, type, BLKIO_STAT_READ) +
+                        blkio_read_stat_cpu(blkg, type, BLKIO_STAT_WRITE);
+
+        blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
+        cb->fill(cb, key_str, disk_total);
+        return disk_total;
+}
+
 /* This should be called with blkg->stats_lock held */
 static uint64_t blkio_get_stat(struct blkio_group *blkg,
                 struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
@@ -609,9 +731,6 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg,
         if (type == BLKIO_STAT_TIME)
                 return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
                                         blkg->stats.time, cb, dev);
-        if (type == BLKIO_STAT_SECTORS)
-                return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
-                                        blkg->stats.sectors, cb, dev);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
         if (type == BLKIO_STAT_UNACCOUNTED_TIME)
                 return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
@@ -1075,8 +1194,8 @@ static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
 }
 
 static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
-                struct cftype *cft, struct cgroup_map_cb *cb, enum stat_type type,
-                bool show_total)
+                struct cftype *cft, struct cgroup_map_cb *cb,
+                enum stat_type type, bool show_total, bool pcpu)
 {
         struct blkio_group *blkg;
         struct hlist_node *n;
@@ -1087,10 +1206,15 @@ static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
                 if (blkg->dev) {
                         if (!cftype_blkg_same_policy(cft, blkg))
                                 continue;
-                        spin_lock_irq(&blkg->stats_lock);
-                        cgroup_total += blkio_get_stat(blkg, cb, blkg->dev,
-                                                type);
-                        spin_unlock_irq(&blkg->stats_lock);
+                        if (pcpu)
+                                cgroup_total += blkio_get_stat_cpu(blkg, cb,
+                                                blkg->dev, type);
+                        else {
+                                spin_lock_irq(&blkg->stats_lock);
+                                cgroup_total += blkio_get_stat(blkg, cb,
+                                                blkg->dev, type);
+                                spin_unlock_irq(&blkg->stats_lock);
+                        }
                 }
         }
         if (show_total)
@@ -1114,47 +1238,47 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
                 switch(name) {
                 case BLKIO_PROP_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_TIME, 0);
+                                                BLKIO_STAT_TIME, 0, 0);
                 case BLKIO_PROP_sectors:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_SECTORS, 0);
+                                                BLKIO_STAT_CPU_SECTORS, 0, 1);
                 case BLKIO_PROP_io_service_bytes:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_SERVICE_BYTES, 1);
+                                        BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
                 case BLKIO_PROP_io_serviced:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_SERVICED, 1);
+                                                BLKIO_STAT_CPU_SERVICED, 1, 1);
                 case BLKIO_PROP_io_service_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_SERVICE_TIME, 1);
+                                                BLKIO_STAT_SERVICE_TIME, 1, 0);
                 case BLKIO_PROP_io_wait_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_WAIT_TIME, 1);
+                                                BLKIO_STAT_WAIT_TIME, 1, 0);
                 case BLKIO_PROP_io_merged:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_MERGED, 1);
+                                                BLKIO_STAT_CPU_MERGED, 1, 1);
                 case BLKIO_PROP_io_queued:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_QUEUED, 1);
+                                                BLKIO_STAT_QUEUED, 1, 0);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
                 case BLKIO_PROP_unaccounted_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_UNACCOUNTED_TIME, 0);
+                                        BLKIO_STAT_UNACCOUNTED_TIME, 0, 0);
                 case BLKIO_PROP_dequeue:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_DEQUEUE, 0);
+                                                BLKIO_STAT_DEQUEUE, 0, 0);
                 case BLKIO_PROP_avg_queue_size:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+                                        BLKIO_STAT_AVG_QUEUE_SIZE, 0, 0);
                 case BLKIO_PROP_group_wait_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_GROUP_WAIT_TIME, 0);
+                                        BLKIO_STAT_GROUP_WAIT_TIME, 0, 0);
                 case BLKIO_PROP_idle_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_IDLE_TIME, 0);
+                                                BLKIO_STAT_IDLE_TIME, 0, 0);
                 case BLKIO_PROP_empty_time:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_EMPTY_TIME, 0);
+                                                BLKIO_STAT_EMPTY_TIME, 0, 0);
 #endif
                 default:
                         BUG();
@@ -1164,10 +1288,10 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
                 switch(name){
                 case BLKIO_THROTL_io_service_bytes:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_SERVICE_BYTES, 1);
+                                                BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
                 case BLKIO_THROTL_io_serviced:
                         return blkio_read_blkg_stats(blkcg, cft, cb,
-                                                BLKIO_STAT_SERVICED, 1);
+                                                BLKIO_STAT_CPU_SERVICED, 1, 1);
                 default:
                         BUG();
                 }
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index c774930cc206..a71d2904ffb9 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/u64_stats_sync.h>
 
 enum blkio_policy_id {
         BLKIO_POLICY_PROP = 0,          /* Proportional Bandwidth division */
@@ -36,22 +37,15 @@ enum stat_type {
          * request completion for IOs doen by this cgroup. This may not be
          * accurate when NCQ is turned on. */
         BLKIO_STAT_SERVICE_TIME = 0,
-        /* Total bytes transferred */
-        BLKIO_STAT_SERVICE_BYTES,
-        /* Total IOs serviced, post merge */
-        BLKIO_STAT_SERVICED,
         /* Total time spent waiting in scheduler queue in ns */
         BLKIO_STAT_WAIT_TIME,
-        /* Number of IOs merged */
-        BLKIO_STAT_MERGED,
         /* Number of IOs queued up */
         BLKIO_STAT_QUEUED,
         /* All the single valued stats go below this */
         BLKIO_STAT_TIME,
-        BLKIO_STAT_SECTORS,
+#ifdef CONFIG_DEBUG_BLK_CGROUP
         /* Time not charged to this cgroup */
         BLKIO_STAT_UNACCOUNTED_TIME,
-#ifdef CONFIG_DEBUG_BLK_CGROUP
         BLKIO_STAT_AVG_QUEUE_SIZE,
         BLKIO_STAT_IDLE_TIME,
         BLKIO_STAT_EMPTY_TIME,
@@ -60,6 +54,18 @@ enum stat_type {
 #endif
 };
 
+/* Per cpu stats */
+enum stat_type_cpu {
+        BLKIO_STAT_CPU_SECTORS,
+        /* Total bytes transferred */
+        BLKIO_STAT_CPU_SERVICE_BYTES,
+        /* Total IOs serviced, post merge */
+        BLKIO_STAT_CPU_SERVICED,
+        /* Number of IOs merged */
+        BLKIO_STAT_CPU_MERGED,
+        BLKIO_STAT_CPU_NR
+};
+
 enum stat_sub_type {
         BLKIO_STAT_READ = 0,
         BLKIO_STAT_WRITE,
@@ -116,11 +122,11 @@ struct blkio_cgroup {
 struct blkio_group_stats {
         /* total disk time and nr sectors dispatched by this group */
         uint64_t time;
-        uint64_t sectors;
-        /* Time not charged to this cgroup */
-        uint64_t unaccounted_time;
         uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];
 #ifdef CONFIG_DEBUG_BLK_CGROUP
+        /* Time not charged to this cgroup */
+        uint64_t unaccounted_time;
+
         /* Sum of number of IOs queued across all samples */
         uint64_t avg_queue_size_sum;
         /* Count of samples taken for average */
@@ -145,6 +151,13 @@ struct blkio_group_stats {
 #endif
 };
 
+/* Per cpu blkio group stats */
+struct blkio_group_stats_cpu {
+        uint64_t sectors;
+        uint64_t stat_arr_cpu[BLKIO_STAT_CPU_NR][BLKIO_STAT_TOTAL];
+        struct u64_stats_sync syncp;
+};
+
 struct blkio_group {
         /* An rcu protected unique identifier for the group */
         void *key;
@@ -160,6 +173,8 @@ struct blkio_group {
         /* Need to serialize the stats in the case of reset/update */
         spinlock_t stats_lock;
         struct blkio_group_stats stats;
+        /* Per cpu stats pointer */
+        struct blkio_group_stats_cpu __percpu *stats_cpu;
 };
 
 struct blkio_policy_node {
@@ -295,6 +310,7 @@ extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
         struct blkio_group *blkg, void *key, dev_t dev,
         enum blkio_policy_id plid);
+extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
                                                 void *key);
@@ -322,6 +338,8 @@ static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
                 struct blkio_group *blkg, void *key, dev_t dev,
                 enum blkio_policy_id plid) {}
 
+static inline int blkio_alloc_blkg_stats(struct blkio_group *blkg) { return 0; }
+
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 3fe00a14822a..c8303e9d919d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -569,8 +569,6 @@ int blk_get_queue(struct request_queue *q)
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
-        BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
         if (rq->cmd_flags & REQ_ELVPRIV)
                 elv_put_request(q, rq);
         mempool_free(rq, q->rq.rq_pool);
@@ -1110,14 +1108,6 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 {
         const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
-        /*
-         * Debug stuff, kill later
-         */
-        if (!rq_mergeable(req)) {
-                blk_dump_rq_flags(req, "back");
-                return false;
-        }
-
         if (!ll_back_merge_fn(q, req, bio))
                 return false;
 
@@ -1132,6 +1122,7 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
         req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
         drive_stat_acct(req, 0);
+        elv_bio_merged(q, req, bio);
         return true;
 }
 
@@ -1141,14 +1132,6 @@ static bool bio_attempt_front_merge(struct request_queue *q,
         const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
         sector_t sector;
 
-        /*
-         * Debug stuff, kill later
-         */
-        if (!rq_mergeable(req)) {
-                blk_dump_rq_flags(req, "front");
-                return false;
-        }
-
         if (!ll_front_merge_fn(q, req, bio))
                 return false;
 
@@ -1173,6 +1156,7 @@ static bool bio_attempt_front_merge(struct request_queue *q,
         req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
         drive_stat_acct(req, 0);
+        elv_bio_merged(q, req, bio);
         return true;
 }
 
@@ -1258,14 +1242,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
         el_ret = elv_merge(q, &req, bio);
         if (el_ret == ELEVATOR_BACK_MERGE) {
-                BUG_ON(req->cmd_flags & REQ_ON_PLUG);
                 if (bio_attempt_back_merge(q, req, bio)) {
                         if (!attempt_back_merge(q, req))
                                 elv_merged_request(q, req, el_ret);
                         goto out_unlock;
                 }
         } else if (el_ret == ELEVATOR_FRONT_MERGE) {
-                BUG_ON(req->cmd_flags & REQ_ON_PLUG);
                 if (bio_attempt_front_merge(q, req, bio)) {
                         if (!attempt_front_merge(q, req))
                                 elv_merged_request(q, req, el_ret);
@@ -1320,10 +1302,6 @@ get_rq:
                         if (__rq->q != q)
                                 plug->should_sort = 1;
                 }
-                /*
-                 * Debug flag, kill later
-                 */
-                req->cmd_flags |= REQ_ON_PLUG;
                 list_add_tail(&req->queuelist, &plug->list);
                 drive_stat_acct(req, 1);
         } else {
@@ -1550,7 +1528,8 @@ static inline void __generic_make_request(struct bio *bio)
                         goto end_io;
                 }
 
-                blk_throtl_bio(q, &bio);
+                if (blk_throtl_bio(q, &bio))
+                        goto end_io;
 
                 /*
                  * If bio = NULL, bio has been throttled and will be submitted
@@ -2748,7 +2727,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
         while (!list_empty(&list)) {
                 rq = list_entry_rq(list.next);
                 list_del_init(&rq->queuelist);
-                BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
                 BUG_ON(!rq->q);
                 if (rq->q != q) {
                         /*
@@ -2760,8 +2738,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
                         depth = 0;
                         spin_lock(q->queue_lock);
                 }
-                rq->cmd_flags &= ~REQ_ON_PLUG;
-
                 /*
                  * rq is already accounted, so use raw insert
                  */
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 81e31819a597..8a0e7ec056e7 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -56,7 +56,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
         spin_lock_irq(q->queue_lock);
         __elv_add_request(q, rq, where);
         __blk_run_queue(q);
-        /* the queue is stopped so it won't be plugged+unplugged */
+        /* the queue is stopped so it won't be run */
         if (rq->cmd_type == REQ_TYPE_PM_RESUME)
                 q->request_fn(q);
         spin_unlock_irq(q->queue_lock);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 6c9b5e189e62..bb21e4c36f70 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -212,13 +212,19 @@ static void flush_end_io(struct request *flush_rq, int error)
         }
 
         /*
-         * Moving a request silently to empty queue_head may stall the
-         * queue.  Kick the queue in those cases.  This function is called
-         * from request completion path and calling directly into
-         * request_fn may confuse the driver.  Always use kblockd.
+         * Kick the queue to avoid stall for two cases:
+         * 1. Moving a request silently to empty queue_head may stall the
+         * queue.
+         * 2. When flush request is running in non-queueable queue, the
+         * queue is hold. Restart the queue after flush request is finished
+         * to avoid stall.
+         * This function is called from request completion path and calling
+         * directly into request_fn may confuse the driver.  Always use
+         * kblockd.
          */
-        if (queued)
+        if (queued || q->flush_queue_delayed)
                 blk_run_queue_async(q);
+        q->flush_queue_delayed = 0;
 }
 
 /**
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index b791022beef3..c898049dafd5 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -96,6 +96,9 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
                 INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
                 INIT_HLIST_HEAD(&ret->cic_list);
                 ret->ioc_data = NULL;
+#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
+                ret->cgroup_changed = 0;
+#endif
         }
 
         return ret;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 25de73e4759b..78e627e2581d 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -9,17 +9,20 @@
 
 #include "blk.h"
 
-static void blkdev_discard_end_io(struct bio *bio, int err)
-{
-        if (err) {
-                if (err == -EOPNOTSUPP)
-                        set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-                clear_bit(BIO_UPTODATE, &bio->bi_flags);
-        }
+struct bio_batch {
+        atomic_t                done;
+        unsigned long           flags;
+        struct completion       *wait;
+};
 
-        if (bio->bi_private)
-                complete(bio->bi_private);
+static void bio_batch_end_io(struct bio *bio, int err)
+{
+        struct bio_batch *bb = bio->bi_private;
 
+        if (err && (err != -EOPNOTSUPP))
+                clear_bit(BIO_UPTODATE, &bb->flags);
+        if (atomic_dec_and_test(&bb->done))
+                complete(bb->wait);
         bio_put(bio);
 }
 
@@ -41,6 +44,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
         struct request_queue *q = bdev_get_queue(bdev);
         int type = REQ_WRITE | REQ_DISCARD;
         unsigned int max_discard_sectors;
+        struct bio_batch bb;
         struct bio *bio;
         int ret = 0;
 
@@ -67,7 +71,11 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
                 type |= REQ_SECURE;
         }
 
-        while (nr_sects && !ret) {
+        atomic_set(&bb.done, 1);
+        bb.flags = 1 << BIO_UPTODATE;
+        bb.wait = &wait;
+
+        while (nr_sects) {
                 bio = bio_alloc(gfp_mask, 1);
                 if (!bio) {
                         ret = -ENOMEM;
@@ -75,9 +83,9 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
                 }
 
                 bio->bi_sector = sector;
-                bio->bi_end_io = blkdev_discard_end_io;
+                bio->bi_end_io = bio_batch_end_io;
                 bio->bi_bdev = bdev;
-                bio->bi_private = &wait;
+                bio->bi_private = &bb;
 
                 if (nr_sects > max_discard_sectors) {
                         bio->bi_size = max_discard_sectors << 9;
@@ -88,45 +96,21 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
                         nr_sects = 0;
                 }
 
-                bio_get(bio);
+                atomic_inc(&bb.done);
                 submit_bio(type, bio);
+        }
 
+        /* Wait for bios in-flight */
+        if (!atomic_dec_and_test(&bb.done))
                 wait_for_completion(&wait);
 
-                if (bio_flagged(bio, BIO_EOPNOTSUPP))
-                        ret = -EOPNOTSUPP;
-                else if (!bio_flagged(bio, BIO_UPTODATE))
-                        ret = -EIO;
-                bio_put(bio);
-        }
+        if (!test_bit(BIO_UPTODATE, &bb.flags))
+                ret = -EIO;
 
         return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
-struct bio_batch
-{
-        atomic_t                done;
-        unsigned long           flags;
-        struct completion       *wait;
-};
-
-static void bio_batch_end_io(struct bio *bio, int err)
-{
-        struct bio_batch *bb = bio->bi_private;
-
-        if (err) {
-                if (err == -EOPNOTSUPP)
-                        set_bit(BIO_EOPNOTSUPP, &bb->flags);
-                else
-                        clear_bit(BIO_UPTODATE, &bb->flags);
-        }
-        if (bb)
-                if (atomic_dec_and_test(&bb->done))
-                        complete(bb->wait);
-        bio_put(bio);
-}
-
 /**
  * blkdev_issue_zeroout - generate number of zero filed write bios
  * @bdev:       blockdev to issue
@@ -151,7 +135,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
         bb.flags = 1 << BIO_UPTODATE;
         bb.wait = &wait;
 
-submit:
         ret = 0;
         while (nr_sects != 0) {
                 bio = bio_alloc(gfp_mask,
@@ -168,9 +151,6 @@ submit:
 
                 while (nr_sects != 0) {
                         sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
-                        if (sz == 0)
-                                /* bio has maximum size possible */
-                                break;
                         ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
                         nr_sects -= ret >> 9;
                         sector += ret >> 9;
@@ -190,16 +170,6 @@ submit:
                 /* One of bios in the batch was completed with error.*/
                 ret = -EIO;
 
-        if (ret)
-                goto out;
-
-        if (test_bit(BIO_EOPNOTSUPP, &bb.flags)) {
-                ret = -EOPNOTSUPP;
-                goto out;
-        }
-        if (nr_sects != 0)
-                goto submit;
-out:
         return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 1fa769293597..fa1eb0449a05 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -120,7 +120,7 @@ void blk_set_default_limits(struct queue_limits *lim)
         lim->discard_granularity = 0;
         lim->discard_alignment = 0;
         lim->discard_misaligned = 0;
-        lim->discard_zeroes_data = -1;
+        lim->discard_zeroes_data = 1;
         lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
         lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
         lim->alignment_offset = 0;
@@ -166,6 +166,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 
         blk_set_default_limits(&q->limits);
         blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
+        q->limits.discard_zeroes_data = 0;
 
         /*
          * by default assume old behaviour and bounce for any highmem page
@@ -790,6 +791,12 @@ void blk_queue_flush(struct request_queue *q, unsigned int flush)
 }
 EXPORT_SYMBOL_GPL(blk_queue_flush);
 
+void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
+{
+        q->flush_not_queueable = !queueable;
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
+
 static int __init blk_settings_init(void)
 {
         blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index bd236313f35d..d935bd859c87 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -152,7 +152,8 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 {
-        return queue_var_show(q->limits.max_discard_sectors << 9, page);
+        return sprintf(page, "%llu\n",
+                       (unsigned long long)q->limits.max_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 252a81a306f7..a62be8d0dc1b 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -78,6 +78,8 @@ struct throtl_grp {
 
         /* Some throttle limits got updated for the group */
         int limits_changed;
+
+        struct rcu_head rcu_head;
 };
 
 struct throtl_data
@@ -88,7 +90,7 @@ struct throtl_data
         /* service tree for active throtl groups */
         struct throtl_rb_root tg_service_tree;
 
-        struct throtl_grp root_tg;
+        struct throtl_grp *root_tg;
         struct request_queue *queue;
 
         /* Total Number of queued bios on READ and WRITE lists */
@@ -151,56 +153,44 @@ static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg)
         return tg;
 }
 
-static void throtl_put_tg(struct throtl_grp *tg)
+static void throtl_free_tg(struct rcu_head *head)
 {
-        BUG_ON(atomic_read(&tg->ref) <= 0);
-        if (!atomic_dec_and_test(&tg->ref))
-                return;
+        struct throtl_grp *tg;
+
+        tg = container_of(head, struct throtl_grp, rcu_head);
+        free_percpu(tg->blkg.stats_cpu);
         kfree(tg);
 }
 
-static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
-                        struct blkio_cgroup *blkcg)
+static void throtl_put_tg(struct throtl_grp *tg)
 {
-        struct throtl_grp *tg = NULL;
-        void *key = td;
-        struct backing_dev_info *bdi = &td->queue->backing_dev_info;
-        unsigned int major, minor;
+        BUG_ON(atomic_read(&tg->ref) <= 0);
+        if (!atomic_dec_and_test(&tg->ref))
+                return;
 
         /*
-         * TODO: Speed up blkiocg_lookup_group() by maintaining a radix
-         * tree of blkg (instead of traversing through hash list all
-         * the time.
+         * A group is freed in rcu manner. But having an rcu lock does not
+         * mean that one can access all the fields of blkg and assume these
+         * are valid. For example, don't try to follow throtl_data and
+         * request queue links.
+         *
+         * Having a reference to blkg under an rcu allows acess to only
+         * values local to groups like group stats and group rate limits
          */
+        call_rcu(&tg->rcu_head, throtl_free_tg);
+}
 
-        /*
-         * This is the common case when there are no blkio cgroups.
-         * Avoid lookup in this case
-         */
-        if (blkcg == &blkio_root_cgroup)
-                tg = &td->root_tg;
-        else
-                tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
-
-        /* Fill in device details for root group */
-        if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
-                sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-                tg->blkg.dev = MKDEV(major, minor);
-                goto done;
-        }
-
-        if (tg)
-                goto done;
-
-        tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
-        if (!tg)
-                goto done;
-
+static void throtl_init_group(struct throtl_grp *tg)
+{
         INIT_HLIST_NODE(&tg->tg_node);
         RB_CLEAR_NODE(&tg->rb_node);
         bio_list_init(&tg->bio_lists[0]);
         bio_list_init(&tg->bio_lists[1]);
-        td->limits_changed = false;
+        tg->limits_changed = false;
+
+        /* Practically unlimited BW */
+        tg->bps[0] = tg->bps[1] = -1;
+        tg->iops[0] = tg->iops[1] = -1;
 
         /*
          * Take the initial reference that will be released on destroy
@@ -209,33 +199,181 @@ static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
          * exit or cgroup deletion path depending on who is exiting first.
          */
         atomic_set(&tg->ref, 1);
+}
+
+/* Should be called with rcu read lock held (needed for blkcg) */
+static void
+throtl_add_group_to_td_list(struct throtl_data *td, struct throtl_grp *tg)
+{
+        hlist_add_head(&tg->tg_node, &td->tg_list);
+        td->nr_undestroyed_grps++;
+}
+
+static void
+__throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
+{
+        struct backing_dev_info *bdi = &td->queue->backing_dev_info;
+        unsigned int major, minor;
+
+        if (!tg || tg->blkg.dev)
+                return;
+
+        /*
+         * Fill in device details for a group which might not have been
+         * filled at group creation time as queue was being instantiated
+         * and driver had not attached a device yet
+         */
+        if (bdi->dev && dev_name(bdi->dev)) {
+                sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+                tg->blkg.dev = MKDEV(major, minor);
+        }
+}
+
+/*
+ * Should be called with without queue lock held. Here queue lock will be
+ * taken rarely. It will be taken only once during life time of a group
+ * if need be
+ */
+static void
+throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
+{
+        if (!tg || tg->blkg.dev)
+                return;
+
+        spin_lock_irq(td->queue->queue_lock);
+        __throtl_tg_fill_dev_details(td, tg);
+        spin_unlock_irq(td->queue->queue_lock);
+}
+
+static void throtl_init_add_tg_lists(struct throtl_data *td,
+                        struct throtl_grp *tg, struct blkio_cgroup *blkcg)
+{
+        __throtl_tg_fill_dev_details(td, tg);
 
         /* Add group onto cgroup list */
-        sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
         blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td,
-                                MKDEV(major, minor), BLKIO_POLICY_THROTL);
+                                tg->blkg.dev, BLKIO_POLICY_THROTL);
 
         tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
         tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
         tg->iops[READ] = blkcg_get_read_iops(blkcg, tg->blkg.dev);
         tg->iops[WRITE] = blkcg_get_write_iops(blkcg, tg->blkg.dev);
 
-        hlist_add_head(&tg->tg_node, &td->tg_list);
-        td->nr_undestroyed_grps++;
-done:
+        throtl_add_group_to_td_list(td, tg);
+}
+
+/* Should be called without queue lock and outside of rcu period */
+static struct throtl_grp *throtl_alloc_tg(struct throtl_data *td)
+{
+        struct throtl_grp *tg = NULL;
+        int ret;
+
+        tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
+        if (!tg)
+                return NULL;
+
+        ret = blkio_alloc_blkg_stats(&tg->blkg);
+
+        if (ret) {
+                kfree(tg);
+                return NULL;
+        }
+
+        throtl_init_group(tg);
         return tg;
 }
 
-static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+static struct
+throtl_grp *throtl_find_tg(struct throtl_data *td, struct blkio_cgroup *blkcg)
 {
         struct throtl_grp *tg = NULL;
+        void *key = td;
+
+        /*
+         * This is the common case when there are no blkio cgroups.
+         * Avoid lookup in this case
+         */
+        if (blkcg == &blkio_root_cgroup)
+                tg = td->root_tg;
+        else
+                tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+        __throtl_tg_fill_dev_details(td, tg);
+        return tg;
+}
+
+/*
+ * This function returns with queue lock unlocked in case of error, like
+ * request queue is no more
+ */
+static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+{
+        struct throtl_grp *tg = NULL, *__tg = NULL;
         struct blkio_cgroup *blkcg;
+        struct request_queue *q = td->queue;
 
         rcu_read_lock();
         blkcg = task_blkio_cgroup(current);
-        tg = throtl_find_alloc_tg(td, blkcg);
-        if (!tg)
-                tg = &td->root_tg;
+        tg = throtl_find_tg(td, blkcg);
+        if (tg) {
+                rcu_read_unlock();
+                return tg;
+        }
+
+        /*
+         * Need to allocate a group. Allocation of group also needs allocation
+         * of per cpu stats which in-turn takes a mutex() and can block. Hence
+         * we need to drop rcu lock and queue_lock before we call alloc
+         *
+         * Take the request queue reference to make sure queue does not
+         * go away once we return from allocation.
+         */
+        blk_get_queue(q);
+        rcu_read_unlock();
+        spin_unlock_irq(q->queue_lock);
+
+        tg = throtl_alloc_tg(td);
+        /*
+         * We might have slept in group allocation. Make sure queue is not
+         * dead
+         */
+        if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+                blk_put_queue(q);
+                if (tg)
+                        kfree(tg);
+
+                return ERR_PTR(-ENODEV);
+        }
+        blk_put_queue(q);
+
+        /* Group allocated and queue is still alive. take the lock */
+        spin_lock_irq(q->queue_lock);
+
+        /*
+         * Initialize the new group. After sleeping, read the blkcg again.
+         */
+        rcu_read_lock();
+        blkcg = task_blkio_cgroup(current);
+
+        /*
+         * If some other thread already allocated the group while we were
+         * not holding queue lock, free up the group
+         */
+        __tg = throtl_find_tg(td, blkcg);
+
+        if (__tg) {
+                kfree(tg);
+                rcu_read_unlock();
+                return __tg;
+        }
+
+        /* Group allocation failed. Account the IO to root group */
+        if (!tg) {
+                tg = td->root_tg;
+                return tg;
+        }
+
+        throtl_init_add_tg_lists(td, tg, blkcg);
         rcu_read_unlock();
         return tg;
 }
@@ -544,6 +682,12 @@ static bool tg_with_in_bps_limit(struct throtl_data *td, struct throtl_grp *tg,
         return 0;
 }
 
+static bool tg_no_rule_group(struct throtl_grp *tg, bool rw) {
+        if (tg->bps[rw] == -1 && tg->iops[rw] == -1)
+                return 1;
+        return 0;
+}
+
 /*
  * Returns whether one can dispatch a bio or not. Also returns approx number
  * of jiffies to wait before this bio is with-in IO rate and can be dispatched
@@ -608,10 +752,6 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
         tg->bytes_disp[rw] += bio->bi_size;
         tg->io_disp[rw]++;
 
-        /*
-         * TODO: This will take blkg->stats_lock. Figure out a way
-         * to avoid this cost.
-         */
         blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync);
 }
 
@@ -989,15 +1129,51 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
         struct throtl_grp *tg;
         struct bio *bio = *biop;
         bool rw = bio_data_dir(bio), update_disptime = true;
+        struct blkio_cgroup *blkcg;
 
         if (bio->bi_rw & REQ_THROTTLED) {
                 bio->bi_rw &= ~REQ_THROTTLED;
                 return 0;
         }
 
+        /*
+         * A throtl_grp pointer retrieved under rcu can be used to access
+         * basic fields like stats and io rates. If a group has no rules,
+         * just update the dispatch stats in lockless manner and return.
+         */
+
+        rcu_read_lock();
+        blkcg = task_blkio_cgroup(current);
+        tg = throtl_find_tg(td, blkcg);
+        if (tg) {
+                throtl_tg_fill_dev_details(td, tg);
+
+                if (tg_no_rule_group(tg, rw)) {
+                        blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
+                                        rw, bio->bi_rw & REQ_SYNC);
+                        rcu_read_unlock();
+                        return 0;
+                }
+        }
+        rcu_read_unlock();
+
+        /*
+         * Either group has not been allocated yet or it is not an unlimited
+         * IO group
+         */
+
         spin_lock_irq(q->queue_lock);
         tg = throtl_get_tg(td);
 
+        if (IS_ERR(tg)) {
+                if (PTR_ERR(tg) == -ENODEV) {
+                        /*
+                         * Queue is gone. No queue lock held here.
+                         */
+                        return -ENODEV;
+                }
+        }
+
         if (tg->nr_queued[rw]) {
                 /*
                  * There is already another bio queued in same dir. No
@@ -1060,39 +1236,24 @@ int blk_throtl_init(struct request_queue *q)
         INIT_HLIST_HEAD(&td->tg_list);
         td->tg_service_tree = THROTL_RB_ROOT;
         td->limits_changed = false;
+        INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
 
-        /* Init root group */
-        tg = &td->root_tg;
-        INIT_HLIST_NODE(&tg->tg_node);
-        RB_CLEAR_NODE(&tg->rb_node);
-        bio_list_init(&tg->bio_lists[0]);
-        bio_list_init(&tg->bio_lists[1]);
-
-        /* Practically unlimited BW */
-        tg->bps[0] = tg->bps[1] = -1;
-        tg->iops[0] = tg->iops[1] = -1;
-        td->limits_changed = false;
+        /* alloc and Init root group. */
+        td->queue = q;
+        tg = throtl_alloc_tg(td);
 
-        /*
-         * Set root group reference to 2. One reference will be dropped when
-         * all groups on tg_list are being deleted during queue exit. Other
-         * reference will remain there as we don't want to delete this group
-         * as it is statically allocated and gets destroyed when throtl_data
-         * goes away.
-         */
-        atomic_set(&tg->ref, 2);
-        hlist_add_head(&tg->tg_node, &td->tg_list);
-        td->nr_undestroyed_grps++;
+        if (!tg) {
+                kfree(td);
+                return -ENOMEM;
+        }
 
-        INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
+        td->root_tg = tg;
 
         rcu_read_lock();
-        blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td,
-                                        0, BLKIO_POLICY_THROTL);
+        throtl_init_add_tg_lists(td, tg, &blkio_root_cgroup);
         rcu_read_unlock();
 
         /* Attach throtl data to request queue */
-        td->queue = q;
         q->td = td;
         return 0;
 }
diff --git a/block/blk.h b/block/blk.h
index 61263463e38e..d6586287adc9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -62,7 +62,28 @@ static inline struct request *__elv_next_request(struct request_queue *q)
                         return rq;
                 }
 
-                if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
+                /*
+                 * Flush request is running and flush request isn't queueable
+                 * in the drive, we can hold the queue till flush request is
+                 * finished. Even we don't do this, driver can't dispatch next
+                 * requests and will requeue them. And this can improve
+                 * throughput too. For example, we have request flush1, write1,
+                 * flush 2. flush1 is dispatched, then queue is hold, write1
+                 * isn't inserted to queue. After flush1 is finished, flush2
+                 * will be dispatched. Since disk cache is already clean,
+                 * flush2 will be finished very soon, so looks like flush2 is
+                 * folded to flush1.
+                 * Since the queue is hold, a flag is set to indicate the queue
+                 * should be restarted later. Please see flush_end_io() for
+                 * details.
+                 */
+                if (q->flush_pending_idx != q->flush_running_idx &&
+                                !queue_flush_queueable(q)) {
+                        q->flush_queue_delayed = 1;
+                        return NULL;
+                }
+                if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags) ||
+                    !q->elevator->ops->elevator_dispatch_fn(q, 0))
                         return NULL;
         }
 }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ab7a9e6a9b1c..7c52d6888924 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -300,7 +300,9 @@ struct cfq_data {
 
         /* List of cfq groups being managed on this device*/
         struct hlist_head cfqg_list;
-        struct rcu_head rcu;
+
+        /* Number of groups which are on blkcg->blkg_list */
+        unsigned int nr_blkcg_linked_grps;
 };
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
@@ -665,15 +667,11 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
         if (rq2 == NULL)
                 return rq1;
 
-        if (rq_is_sync(rq1) && !rq_is_sync(rq2))
-                return rq1;
-        else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
-                return rq2;
-        if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
-                return rq1;
-        else if ((rq2->cmd_flags & REQ_META) &&
-                 !(rq1->cmd_flags & REQ_META))
-                return rq2;
+        if (rq_is_sync(rq1) != rq_is_sync(rq2))
+                return rq_is_sync(rq1) ? rq1 : rq2;
+
+        if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META)
+                return rq1->cmd_flags & REQ_META ? rq1 : rq2;
 
         s1 = blk_rq_pos(rq1);
         s2 = blk_rq_pos(rq2);
@@ -1014,28 +1012,47 @@ void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
         cfqg->needs_update = true;
 }
 
-static struct cfq_group * cfq_find_alloc_cfqg(struct cfq_data *cfqd,
-                struct blkio_cgroup *blkcg, int create)
+static void cfq_init_add_cfqg_lists(struct cfq_data *cfqd,
+                        struct cfq_group *cfqg, struct blkio_cgroup *blkcg)
 {
-        struct cfq_group *cfqg = NULL;
-        void *key = cfqd;
-        int i, j;
-        struct cfq_rb_root *st;
         struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
         unsigned int major, minor;
 
-        cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
-        if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+        /*
+         * Add group onto cgroup list. It might happen that bdi->dev is
+         * not initialized yet. Initialize this new group without major
+         * and minor info and this info will be filled in once a new thread
+         * comes for IO.
+         */
+        if (bdi->dev) {
                 sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-                cfqg->blkg.dev = MKDEV(major, minor);
-                goto done;
-        }
-        if (cfqg || !create)
-                goto done;
+                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);
+
+        cfqd->nr_blkcg_linked_grps++;
+        cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+
+        /* Add group on cfqd list */
+        hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+}
+
+/*
+ * Should be called from sleepable context. No request queue lock as per
+ * cpu stats are allocated dynamically and alloc_percpu needs to be called
+ * from sleepable context.
+ */
+static struct cfq_group * cfq_alloc_cfqg(struct cfq_data *cfqd)
+{
+        struct cfq_group *cfqg = NULL;
+        int i, j, ret;
+        struct cfq_rb_root *st;
 
         cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
         if (!cfqg)
-                goto done;
+                return NULL;
 
         for_each_cfqg_st(cfqg, i, j, st)
                 *st = CFQ_RB_ROOT;
@@ -1049,43 +1066,94 @@ static struct cfq_group * cfq_find_alloc_cfqg(struct cfq_data *cfqd,
          */
         cfqg->ref = 1;
 
+        ret = blkio_alloc_blkg_stats(&cfqg->blkg);
+        if (ret) {
+                kfree(cfqg);
+                return NULL;
+        }
+
+        return cfqg;
+}
+
+static struct cfq_group *
+cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
+{
+        struct cfq_group *cfqg = NULL;
+        void *key = cfqd;
+        struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+        unsigned int major, minor;
+
         /*
-         * Add group onto cgroup list. It might happen that bdi->dev is
-         * not initialized 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.
+         * This is the common case when there are no blkio cgroups.
+         * Avoid lookup in this case
          */
-        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);
+        if (blkcg == &blkio_root_cgroup)
+                cfqg = &cfqd->root_group;
+        else
+                cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
 
-        /* Add group on cfqd list */
-        hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+        if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+                sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+                cfqg->blkg.dev = MKDEV(major, minor);
+        }
 
-done:
         return cfqg;
 }
 
 /*
- * Search for the cfq group current task belongs to. If create = 1, then also
- * create the cfq group if it does not exist. request_queue lock must be held.
+ * Search for the cfq group current task belongs to. request_queue lock must
+ * be held.
  */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 {
         struct blkio_cgroup *blkcg;
-        struct cfq_group *cfqg = NULL;
+        struct cfq_group *cfqg = NULL, *__cfqg = NULL;
+        struct request_queue *q = cfqd->queue;
 
         rcu_read_lock();
         blkcg = task_blkio_cgroup(current);
-        cfqg = cfq_find_alloc_cfqg(cfqd, blkcg, create);
-        if (!cfqg && create)
+        cfqg = cfq_find_cfqg(cfqd, blkcg);
+        if (cfqg) {
+                rcu_read_unlock();
+                return cfqg;
+        }
+
+        /*
+         * Need to allocate a group. Allocation of group also needs allocation
+         * of per cpu stats which in-turn takes a mutex() and can block. Hence
+         * we need to drop rcu lock and queue_lock before we call alloc.
+         *
+         * Not taking any queue reference here and assuming that queue is
+         * around by the time we return. CFQ queue allocation code does
+         * the same. It might be racy though.
+         */
+
+        rcu_read_unlock();
+        spin_unlock_irq(q->queue_lock);
+
+        cfqg = cfq_alloc_cfqg(cfqd);
+
+        spin_lock_irq(q->queue_lock);
+
+        rcu_read_lock();
+        blkcg = task_blkio_cgroup(current);
+
+        /*
+         * If some other thread already allocated the group while we were
+         * not holding queue lock, free up the group
+         */
+        __cfqg = cfq_find_cfqg(cfqd, blkcg);
+
+        if (__cfqg) {
+                kfree(cfqg);
+                rcu_read_unlock();
+                return __cfqg;
+        }
+
+        if (!cfqg)
                 cfqg = &cfqd->root_group;
+
+        cfq_init_add_cfqg_lists(cfqd, cfqg, blkcg);
         rcu_read_unlock();
         return cfqg;
 }
@@ -1118,6 +1186,7 @@ static void cfq_put_cfqg(struct cfq_group *cfqg)
                 return;
         for_each_cfqg_st(cfqg, i, j, st)
                 BUG_ON(!RB_EMPTY_ROOT(&st->rb));
+        free_percpu(cfqg->blkg.stats_cpu);
         kfree(cfqg);
 }
 
@@ -1176,7 +1245,7 @@ void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
 }
 
 #else /* GROUP_IOSCHED */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 {
         return &cfqd->root_group;
 }
@@ -1210,7 +1279,6 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
         struct cfq_rb_root *service_tree;
         int left;
         int new_cfqq = 1;
-        int group_changed = 0;
 
         service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
                                                 cfqq_type(cfqq));
@@ -1281,7 +1349,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
         rb_link_node(&cfqq->rb_node, parent, p);
         rb_insert_color(&cfqq->rb_node, &service_tree->rb);
         service_tree->count++;
-        if ((add_front || !new_cfqq) && !group_changed)
+        if (add_front || !new_cfqq)
                 return;
         cfq_group_notify_queue_add(cfqd, cfqq->cfqg);
 }
@@ -2029,7 +2097,7 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
         WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);
 
-        return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
+        return 2 * base_rq * (IOPRIO_BE_NR - cfqq->ioprio);
 }
 
 /*
@@ -2911,7 +2979,7 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
         struct cfq_group *cfqg;
 
 retry:
-        cfqg = cfq_get_cfqg(cfqd, 1);
+        cfqg = cfq_get_cfqg(cfqd);
         cic = cfq_cic_lookup(cfqd, ioc);
         /* cic always exists here */
         cfqq = cic_to_cfqq(cic, is_sync);
@@ -3815,15 +3883,11 @@ static void cfq_put_async_queues(struct cfq_data *cfqd)
                 cfq_put_queue(cfqd->async_idle_cfqq);
 }
 
-static void cfq_cfqd_free(struct rcu_head *head)
-{
-        kfree(container_of(head, struct cfq_data, rcu));
-}
-
 static void cfq_exit_queue(struct elevator_queue *e)
 {
         struct cfq_data *cfqd = e->elevator_data;
         struct request_queue *q = cfqd->queue;
+        bool wait = false;
 
         cfq_shutdown_timer_wq(cfqd);
 
@@ -3842,7 +3906,13 @@ static void cfq_exit_queue(struct elevator_queue *e)
 
         cfq_put_async_queues(cfqd);
         cfq_release_cfq_groups(cfqd);
-        cfq_blkiocg_del_blkio_group(&cfqd->root_group.blkg);
+
+        /*
+         * If there are groups which we could not unlink from blkcg list,
+         * wait for a rcu period for them to be freed.
+         */
+        if (cfqd->nr_blkcg_linked_grps)
+                wait = true;
 
         spin_unlock_irq(q->queue_lock);
 
@@ -3852,8 +3922,25 @@ static void cfq_exit_queue(struct elevator_queue *e)
         ida_remove(&cic_index_ida, cfqd->cic_index);
         spin_unlock(&cic_index_lock);
 
-        /* Wait for cfqg->blkg->key accessors to exit their grace periods. */
-        call_rcu(&cfqd->rcu, cfq_cfqd_free);
+        /*
+         * Wait for cfqg->blkg->key accessors to exit their grace periods.
+         * Do this wait only if there are other unlinked groups out
+         * there. This can happen if cgroup deletion path claimed the
+         * responsibility of cleaning up a group before queue cleanup code
+         * get to the group.
+         *
+         * Do not call synchronize_rcu() unconditionally as there are drivers
+         * which create/delete request queue hundreds of times during scan/boot
+         * and synchronize_rcu() can take significant time and slow down boot.
+         */
+        if (wait)
+                synchronize_rcu();
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+        /* Free up per cpu stats for root group */
+        free_percpu(cfqd->root_group.blkg.stats_cpu);
+#endif
+        kfree(cfqd);
 }
 
 static int cfq_alloc_cic_index(void)
@@ -3886,8 +3973,12 @@ static void *cfq_init_queue(struct request_queue *q)
                 return NULL;
 
         cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
-        if (!cfqd)
+        if (!cfqd) {
+                spin_lock(&cic_index_lock);
+                ida_remove(&cic_index_ida, i);
+                spin_unlock(&cic_index_lock);
                 return NULL;
+        }
 
         /*
          * Don't need take queue_lock in the routine, since we are
@@ -3909,14 +4000,29 @@ static void *cfq_init_queue(struct request_queue *q)
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
         /*
-         * Take a reference to root group which we never drop. This is just
-         * to make sure that cfq_put_cfqg() does not try to kfree root group
+         * Set root group reference to 2. One reference will be dropped when
+         * all groups on cfqd->cfqg_list are being deleted during queue exit.
+         * Other reference will remain there as we don't want to delete this
+         * group as it is statically allocated and gets destroyed when
+         * throtl_data goes away.
          */
-        cfqg->ref = 1;
+        cfqg->ref = 2;
+
+        if (blkio_alloc_blkg_stats(&cfqg->blkg)) {
+                kfree(cfqg);
+                kfree(cfqd);
+                return NULL;
+        }
+
         rcu_read_lock();
+
         cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
                                         (void *)cfqd, 0);
         rcu_read_unlock();
+        cfqd->nr_blkcg_linked_grps++;
+
+        /* Add group on cfqd->cfqg_list */
+        hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 #endif
         /*
          * Not strictly needed (since RB_ROOT just clears the node and we
diff --git a/block/elevator.c b/block/elevator.c
index 45ca1e34f582..b0b38ce0dcb6 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -155,13 +155,8 @@ static struct elevator_type *elevator_get(const char *name)
 
         e = elevator_find(name);
         if (!e) {
-                char elv[ELV_NAME_MAX + strlen("-iosched")];
-
                 spin_unlock(&elv_list_lock);
-
-                snprintf(elv, sizeof(elv), "%s-iosched", name);
-
-                request_module("%s", elv);
+                request_module("%s-iosched", name);
                 spin_lock(&elv_list_lock);
                 e = elevator_find(name);
         }
@@ -421,8 +416,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
         struct list_head *entry;
         int stop_flags;
 
-        BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
         if (q->last_merge == rq)
                 q->last_merge = NULL;
 
@@ -661,8 +654,6 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
         rq->q = q;
 
-        BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
         if (rq->cmd_flags & REQ_SOFTBARRIER) {
                 /* barriers are scheduling boundary, update end_sector */
                 if (rq->cmd_type == REQ_TYPE_FS ||
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 61631edfecc2..3bb154d8c8cc 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -54,6 +54,8 @@ source "drivers/spi/Kconfig"
 
 source "drivers/pps/Kconfig"
 
+source "drivers/ptp/Kconfig"
+
 source "drivers/gpio/Kconfig"
 
 source "drivers/w1/Kconfig"
diff --git a/drivers/Makefile b/drivers/Makefile
index 145aeadb6c03..6b17f5864340 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -75,6 +75,7 @@ obj-$(CONFIG_I2O)		+= message/
 obj-$(CONFIG_RTC_LIB)           += rtc/
 obj-y                           += i2c/ media/
 obj-$(CONFIG_PPS)               += pps/
+obj-$(CONFIG_PTP_1588_CLOCK)    += ptp/
 obj-$(CONFIG_W1)                += w1/
 obj-$(CONFIG_POWER_SUPPLY)      += power/
 obj-$(CONFIG_HWMON)             += hwmon/
@@ -94,7 +95,7 @@ obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
 obj-$(CONFIG_DMA_ENGINE)        += dma/
 obj-$(CONFIG_MMC)               += mmc/
 obj-$(CONFIG_MEMSTICK)          += memstick/
-obj-$(CONFIG_NEW_LEDS)          += leds/
+obj-y                           += leds/
 obj-$(CONFIG_INFINIBAND)        += infiniband/
 obj-$(CONFIG_SGI_SN)            += sn/
 obj-y                           += firmware/
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 096aebfe7f32..f74b2ea11f21 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -101,6 +101,14 @@ static DEFINE_MUTEX(einj_mutex);
 
 static struct einj_parameter *einj_param;
 
+#ifndef writeq
+static inline void writeq(__u64 val, volatile void __iomem *addr)
+{
+        writel(val, addr);
+        writel(val >> 32, addr+4);
+}
+#endif
+
 static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 {
         apei_exec_ctx_init(ctx, einj_ins_type, ARRAY_SIZE(einj_ins_type),
diff --git a/drivers/acpi/atomicio.c b/drivers/acpi/atomicio.c
index 542e53903891..7489b89c300f 100644
--- a/drivers/acpi/atomicio.c
+++ b/drivers/acpi/atomicio.c
@@ -280,9 +280,11 @@ static int acpi_atomic_read_mem(u64 paddr, u64 *val, u32 width)
         case 32:
                 *val = readl(addr);
                 break;
+#ifdef readq
         case 64:
                 *val = readq(addr);
                 break;
+#endif
         default:
                 return -EINVAL;
         }
@@ -307,9 +309,11 @@ static int acpi_atomic_write_mem(u64 paddr, u64 val, u32 width)
         case 32:
                 writel(val, addr);
                 break;
+#ifdef writeq
         case 64:
                 writeq(val, addr);
                 break;
+#endif
         default:
                 return -EINVAL;
         }
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 30ea95f43e79..d51f9795c064 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1089,21 +1089,21 @@ static int atapi_drain_needed(struct request *rq)
 static int ata_scsi_dev_config(struct scsi_device *sdev,
                                struct ata_device *dev)
 {
+        struct request_queue *q = sdev->request_queue;
+
         if (!ata_id_has_unload(dev->id))
                 dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
         /* configure max sectors */
-        blk_queue_max_hw_sectors(sdev->request_queue, dev->max_sectors);
+        blk_queue_max_hw_sectors(q, dev->max_sectors);
 
         if (dev->class == ATA_DEV_ATAPI) {
-                struct request_queue *q = sdev->request_queue;
                 void *buf;
 
                 sdev->sector_size = ATA_SECT_SIZE;
 
                 /* set DMA padding */
-                blk_queue_update_dma_pad(sdev->request_queue,
-                                         ATA_DMA_PAD_SZ - 1);
+                blk_queue_update_dma_pad(q, ATA_DMA_PAD_SZ - 1);
 
                 /* configure draining */
                 buf = kmalloc(ATAPI_MAX_DRAIN, q->bounce_gfp | GFP_KERNEL);
@@ -1131,8 +1131,7 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
                         "sector_size=%u > PAGE_SIZE, PIO may malfunction\n",
                         sdev->sector_size);
 
-        blk_queue_update_dma_alignment(sdev->request_queue,
-                                       sdev->sector_size - 1);
+        blk_queue_update_dma_alignment(q, sdev->sector_size - 1);
 
         if (dev->flags & ATA_DFLAG_AN)
                 set_bit(SDEV_EVT_MEDIA_CHANGE, sdev->supported_events);
@@ -1145,6 +1144,8 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
                 scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
         }
 
+        blk_queue_flush_queueable(q, false);
+
         dev->sdev = sdev;
         return 0;
 }
diff --git a/drivers/base/node.c b/drivers/base/node.c
index b3b72d64e805..793f796c4da3 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
+#include <linux/vmstat.h>
 #include <linux/node.h>
 #include <linux/hugetlb.h>
 #include <linux/compaction.h>
@@ -179,11 +180,14 @@ static ssize_t node_read_vmstat(struct sys_device *dev,
                                 struct sysdev_attribute *attr, char *buf)
 {
         int nid = dev->id;
-        return sprintf(buf,
-                "nr_written %lu\n"
-                "nr_dirtied %lu\n",
-                node_page_state(nid, NR_WRITTEN),
-                node_page_state(nid, NR_DIRTIED));
+        int i;
+        int n = 0;
+
+        for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+                n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
+                             node_page_state(nid, i));
+
+        return n;
 }
 static SYSDEV_ATTR(vmstat, S_IRUGO, node_read_vmstat, NULL);
 
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 83c32cb72582..717d6e4e18d3 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -470,6 +470,27 @@ config XEN_BLKDEV_FRONTEND
           block device driver.  It communicates with a back-end driver
           in another domain which drives the actual block device.
 
+config XEN_BLKDEV_BACKEND
+        tristate "Block-device backend driver"
+        depends on XEN_BACKEND
+        help
+          The block-device backend driver allows the kernel to export its
+          block devices to other guests via a high-performance shared-memory
+          interface.
+
+          The corresponding Linux frontend driver is enabled by the
+          CONFIG_XEN_BLKDEV_FRONTEND configuration option.
+
+          The backend driver attaches itself to a any block device specified
+          in the XenBus configuration. There are no limits to what the block
+          device as long as it has a major and minor.
+
+          If you are compiling a kernel to run in a Xen block backend driver
+          domain (often this is domain 0) you should say Y here. To
+          compile this driver as a module, chose M here: the module
+          will be called xen-blkback.
+
+
 config VIRTIO_BLK
         tristate "Virtio block driver (EXPERIMENTAL)"
         depends on EXPERIMENTAL && VIRTIO
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 40528ba56d1b..76646e9a1c91 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_BLK_DEV_UB)	+= ub.o
 obj-$(CONFIG_BLK_DEV_HD)        += hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)       += xen-blkfront.o
+obj-$(CONFIG_XEN_BLKDEV_BACKEND)        += xen-blkback/
 obj-$(CONFIG_BLK_DEV_DRBD)     += drbd/
 obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 9bf13988f1a2..8f4ef656a1af 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -64,6 +64,10 @@ MODULE_DESCRIPTION("Driver for HP Smart Array Controllers");
 MODULE_SUPPORTED_DEVICE("HP Smart Array Controllers");
 MODULE_VERSION("3.6.26");
 MODULE_LICENSE("GPL");
+static int cciss_tape_cmds = 6;
+module_param(cciss_tape_cmds, int, 0644);
+MODULE_PARM_DESC(cciss_tape_cmds,
+        "number of commands to allocate for tape devices (default: 6)");
 
 static DEFINE_MUTEX(cciss_mutex);
 static struct proc_dir_entry *proc_cciss;
@@ -194,6 +198,8 @@ static int __devinit cciss_find_cfg_addrs(struct pci_dev *pdev,
 static int __devinit cciss_pci_find_memory_BAR(struct pci_dev *pdev,
         unsigned long *memory_bar);
 static inline u32 cciss_tag_discard_error_bits(ctlr_info_t *h, u32 tag);
+static __devinit int write_driver_ver_to_cfgtable(
+        CfgTable_struct __iomem *cfgtable);
 
 /* performant mode helper functions */
 static void  calc_bucket_map(int *bucket, int num_buckets, int nsgs,
@@ -556,7 +562,7 @@ static void __devinit cciss_procinit(ctlr_info_t *h)
 #define to_hba(n) container_of(n, struct ctlr_info, dev)
 #define to_drv(n) container_of(n, drive_info_struct, dev)
 
-/* List of controllers which cannot be reset on kexec with reset_devices */
+/* List of controllers which cannot be hard reset on kexec with reset_devices */
 static u32 unresettable_controller[] = {
         0x324a103C, /* Smart Array P712m */
         0x324b103C, /* SmartArray P711m */
@@ -574,23 +580,45 @@ static u32 unresettable_controller[] = {
         0x409D0E11, /* Smart Array 6400 EM */
 };
 
-static int ctlr_is_resettable(struct ctlr_info *h)
+/* List of controllers which cannot even be soft reset */
+static u32 soft_unresettable_controller[] = {
+        0x409C0E11, /* Smart Array 6400 */
+        0x409D0E11, /* Smart Array 6400 EM */
+};
+
+static int ctlr_is_hard_resettable(u32 board_id)
 {
         int i;
 
         for (i = 0; i < ARRAY_SIZE(unresettable_controller); i++)
-                if (unresettable_controller[i] == h->board_id)
+                if (unresettable_controller[i] == board_id)
                         return 0;
         return 1;
 }
 
+static int ctlr_is_soft_resettable(u32 board_id)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(soft_unresettable_controller); i++)
+                if (soft_unresettable_controller[i] == board_id)
+                        return 0;
+        return 1;
+}
+
+static int ctlr_is_resettable(u32 board_id)
+{
+        return ctlr_is_hard_resettable(board_id) ||
+                ctlr_is_soft_resettable(board_id);
+}
+
 static ssize_t host_show_resettable(struct device *dev,
                                     struct device_attribute *attr,
                                     char *buf)
 {
         struct ctlr_info *h = to_hba(dev);
 
-        return snprintf(buf, 20, "%d\n", ctlr_is_resettable(h));
+        return snprintf(buf, 20, "%d\n", ctlr_is_resettable(h->board_id));
 }
 static DEVICE_ATTR(resettable, S_IRUGO, host_show_resettable, NULL);
 
@@ -2567,7 +2595,7 @@ static int fill_cmd(ctlr_info_t *h, CommandList_struct *c, __u8 cmd, void *buff,
                 }
         } else if (cmd_type == TYPE_MSG) {
                 switch (cmd) {
-                case 0: /* ABORT message */
+                case CCISS_ABORT_MSG:
                         c->Request.CDBLen = 12;
                         c->Request.Type.Attribute = ATTR_SIMPLE;
                         c->Request.Type.Direction = XFER_WRITE;
@@ -2577,16 +2605,16 @@ static int fill_cmd(ctlr_info_t *h, CommandList_struct *c, __u8 cmd, void *buff,
                         /* buff contains the tag of the command to abort */
                         memcpy(&c->Request.CDB[4], buff, 8);
                         break;
-                case 1: /* RESET message */
+                case CCISS_RESET_MSG:
                         c->Request.CDBLen = 16;
                         c->Request.Type.Attribute = ATTR_SIMPLE;
                         c->Request.Type.Direction = XFER_NONE;
                         c->Request.Timeout = 0;
                         memset(&c->Request.CDB[0], 0, sizeof(c->Request.CDB));
                         c->Request.CDB[0] = cmd;        /* reset */
-                        c->Request.CDB[1] = 0x03;       /* reset a target */
+                        c->Request.CDB[1] = CCISS_RESET_TYPE_TARGET;
                         break;
-                case 3: /* No-Op message */
+                case CCISS_NOOP_MSG:
                         c->Request.CDBLen = 1;
                         c->Request.Type.Attribute = ATTR_SIMPLE;
                         c->Request.Type.Direction = XFER_WRITE;
@@ -2615,6 +2643,31 @@ static int fill_cmd(ctlr_info_t *h, CommandList_struct *c, __u8 cmd, void *buff,
         return status;
 }
 
+static int __devinit cciss_send_reset(ctlr_info_t *h, unsigned char *scsi3addr,
+        u8 reset_type)
+{
+        CommandList_struct *c;
+        int return_status;
+
+        c = cmd_alloc(h);
+        if (!c)
+                return -ENOMEM;
+        return_status = fill_cmd(h, c, CCISS_RESET_MSG, NULL, 0, 0,
+                CTLR_LUNID, TYPE_MSG);
+        c->Request.CDB[1] = reset_type; /* fill_cmd defaults to target reset */
+        if (return_status != IO_OK) {
+                cmd_special_free(h, c);
+                return return_status;
+        }
+        c->waiting = NULL;
+        enqueue_cmd_and_start_io(h, c);
+        /* Don't wait for completion, the reset won't complete.  Don't free
+         * the command either.  This is the last command we will send before
+         * re-initializing everything, so it doesn't matter and won't leak.
+         */
+        return 0;
+}
+
 static int check_target_status(ctlr_info_t *h, CommandList_struct *c)
 {
         switch (c->err_info->ScsiStatus) {
@@ -3461,6 +3514,63 @@ static inline u32 process_nonindexed_cmd(ctlr_info_t *h, u32 raw_tag)
         return next_command(h);
 }
 
+/* Some controllers, like p400, will give us one interrupt
+ * after a soft reset, even if we turned interrupts off.
+ * Only need to check for this in the cciss_xxx_discard_completions
+ * functions.
+ */
+static int ignore_bogus_interrupt(ctlr_info_t *h)
+{
+        if (likely(!reset_devices))
+                return 0;
+
+        if (likely(h->interrupts_enabled))
+                return 0;
+
+        dev_info(&h->pdev->dev, "Received interrupt while interrupts disabled "
+                "(known firmware bug.)  Ignoring.\n");
+
+        return 1;
+}
+
+static irqreturn_t cciss_intx_discard_completions(int irq, void *dev_id)
+{
+        ctlr_info_t *h = dev_id;
+        unsigned long flags;
+        u32 raw_tag;
+
+        if (ignore_bogus_interrupt(h))
+                return IRQ_NONE;
+
+        if (interrupt_not_for_us(h))
+                return IRQ_NONE;
+        spin_lock_irqsave(&h->lock, flags);
+        while (interrupt_pending(h)) {
+                raw_tag = get_next_completion(h);
+                while (raw_tag != FIFO_EMPTY)
+                        raw_tag = next_command(h);
+        }
+        spin_unlock_irqrestore(&h->lock, flags);
+        return IRQ_HANDLED;
+}
+
+static irqreturn_t cciss_msix_discard_completions(int irq, void *dev_id)
+{
+        ctlr_info_t *h = dev_id;
+        unsigned long flags;
+        u32 raw_tag;
+
+        if (ignore_bogus_interrupt(h))
+                return IRQ_NONE;
+
+        spin_lock_irqsave(&h->lock, flags);
+        raw_tag = get_next_completion(h);
+        while (raw_tag != FIFO_EMPTY)
+                raw_tag = next_command(h);
+        spin_unlock_irqrestore(&h->lock, flags);
+        return IRQ_HANDLED;
+}
+
 static irqreturn_t do_cciss_intx(int irq, void *dev_id)
 {
         ctlr_info_t *h = dev_id;
@@ -4078,6 +4188,9 @@ static int __devinit cciss_find_cfgtables(ctlr_info_t *h)
                 cfg_base_addr_index) + cfg_offset, sizeof(h->cfgtable));
         if (!h->cfgtable)
                 return -ENOMEM;
+        rc = write_driver_ver_to_cfgtable(h->cfgtable);
+        if (rc)
+                return rc;
         /* Find performant mode table. */
         trans_offset = readl(&h->cfgtable->TransMethodOffset);
         h->transtable = remap_pci_mem(pci_resource_start(h->pdev,
@@ -4112,7 +4225,7 @@ static void __devinit cciss_get_max_perf_mode_cmds(struct ctlr_info *h)
 static void __devinit cciss_find_board_params(ctlr_info_t *h)
 {
         cciss_get_max_perf_mode_cmds(h);
-        h->nr_cmds = h->max_commands - 4; /* Allow room for some ioctls */
+        h->nr_cmds = h->max_commands - 4 - cciss_tape_cmds;
         h->maxsgentries = readl(&(h->cfgtable->MaxSGElements));
         /*
          * Limit in-command s/g elements to 32 save dma'able memory.
@@ -4348,7 +4461,7 @@ static __devinit int cciss_message(struct pci_dev *pdev, unsigned char opcode, u
                 tag = readl(vaddr + SA5_REPLY_PORT_OFFSET);
                 if ((tag & ~3) == paddr32)
                         break;
-                schedule_timeout_uninterruptible(HZ);
+                msleep(CCISS_POST_RESET_NOOP_TIMEOUT_MSECS);
         }
 
         iounmap(vaddr);
@@ -4375,11 +4488,10 @@ static __devinit int cciss_message(struct pci_dev *pdev, unsigned char opcode, u
         return 0;
 }
 
-#define cciss_soft_reset_controller(p) cciss_message(p, 1, 0)
 #define cciss_noop(p) cciss_message(p, 3, 0)
 
 static int cciss_controller_hard_reset(struct pci_dev *pdev,
-        void * __iomem vaddr, bool use_doorbell)
+        void * __iomem vaddr, u32 use_doorbell)
 {
         u16 pmcsr;
         int pos;
@@ -4390,8 +4502,7 @@ static int cciss_controller_hard_reset(struct pci_dev *pdev,
                  * other way using the doorbell register.
                  */
                 dev_info(&pdev->dev, "using doorbell to reset controller\n");
-                writel(DOORBELL_CTLR_RESET, vaddr + SA5_DOORBELL);
-                msleep(1000);
+                writel(use_doorbell, vaddr + SA5_DOORBELL);
         } else { /* Try to do it the PCI power state way */
 
                 /* Quoting from the Open CISS Specification: "The Power
@@ -4422,12 +4533,64 @@ static int cciss_controller_hard_reset(struct pci_dev *pdev,
                 pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
                 pmcsr |= PCI_D0;
                 pci_write_config_word(pdev, pos + PCI_PM_CTRL, pmcsr);
-
-                msleep(500);
         }
         return 0;
 }
 
+static __devinit void init_driver_version(char *driver_version, int len)
+{
+        memset(driver_version, 0, len);
+        strncpy(driver_version, "cciss " DRIVER_NAME, len - 1);
+}
+
+static __devinit int write_driver_ver_to_cfgtable(
+        CfgTable_struct __iomem *cfgtable)
+{
+        char *driver_version;
+        int i, size = sizeof(cfgtable->driver_version);
+
+        driver_version = kmalloc(size, GFP_KERNEL);
+        if (!driver_version)
+                return -ENOMEM;
+
+        init_driver_version(driver_version, size);
+        for (i = 0; i < size; i++)
+                writeb(driver_version[i], &cfgtable->driver_version[i]);
+        kfree(driver_version);
+        return 0;
+}
+
+static __devinit void read_driver_ver_from_cfgtable(
+        CfgTable_struct __iomem *cfgtable, unsigned char *driver_ver)
+{
+        int i;
+
+        for (i = 0; i < sizeof(cfgtable->driver_version); i++)
+                driver_ver[i] = readb(&cfgtable->driver_version[i]);
+}
+
+static __devinit int controller_reset_failed(
+        CfgTable_struct __iomem *cfgtable)
+{
+
+        char *driver_ver, *old_driver_ver;
+        int rc, size = sizeof(cfgtable->driver_version);
+
+        old_driver_ver = kmalloc(2 * size, GFP_KERNEL);
+        if (!old_driver_ver)
+                return -ENOMEM;
+        driver_ver = old_driver_ver + size;
+
+        /* After a reset, the 32 bytes of "driver version" in the cfgtable
+         * should have been changed, otherwise we know the reset failed.
+         */
+        init_driver_version(old_driver_ver, size);
+        read_driver_ver_from_cfgtable(cfgtable, driver_ver);
+        rc = !memcmp(driver_ver, old_driver_ver, size);
+        kfree(old_driver_ver);
+        return rc;
+}
+
 /* This does a hard reset of the controller using PCI power management
  * states or using the doorbell register. */
 static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
@@ -4437,10 +4600,10 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
         u64 cfg_base_addr_index;
         void __iomem *vaddr;
         unsigned long paddr;
-        u32 misc_fw_support, active_transport;
+        u32 misc_fw_support;
         int rc;
         CfgTable_struct __iomem *cfgtable;
-        bool use_doorbell;
+        u32 use_doorbell;
         u32 board_id;
         u16 command_register;
 
@@ -4464,12 +4627,16 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
          * likely not be happy.  Just forbid resetting this conjoined mess.
          */
         cciss_lookup_board_id(pdev, &board_id);
-        if (board_id == 0x409C0E11 || board_id == 0x409D0E11) {
+        if (!ctlr_is_resettable(board_id)) {
                 dev_warn(&pdev->dev, "Cannot reset Smart Array 640x "
                                 "due to shared cache module.");
                 return -ENODEV;
         }
 
+        /* if controller is soft- but not hard resettable... */
+        if (!ctlr_is_hard_resettable(board_id))
+                return -ENOTSUPP; /* try soft reset later. */
+
         /* Save the PCI command register */
         pci_read_config_word(pdev, 4, &command_register);
         /* Turn the board off.  This is so that later pci_restore_state()
@@ -4497,16 +4664,28 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
                 rc = -ENOMEM;
                 goto unmap_vaddr;
         }
+        rc = write_driver_ver_to_cfgtable(cfgtable);
+        if (rc)
+                goto unmap_vaddr;
 
-        /* If reset via doorbell register is supported, use that. */
-        misc_fw_support = readl(&cfgtable->misc_fw_support);
-        use_doorbell = misc_fw_support & MISC_FW_DOORBELL_RESET;
-
-        /* The doorbell reset seems to cause lockups on some Smart
-         * Arrays (e.g. P410, P410i, maybe others).  Until this is
-         * fixed or at least isolated, avoid the doorbell reset.
+        /* If reset via doorbell register is supported, use that.
+         * There are two such methods.  Favor the newest method.
          */
-        use_doorbell = 0;
+        misc_fw_support = readl(&cfgtable->misc_fw_support);
+        use_doorbell = misc_fw_support & MISC_FW_DOORBELL_RESET2;
+        if (use_doorbell) {
+                use_doorbell = DOORBELL_CTLR_RESET2;
+        } else {
+                use_doorbell = misc_fw_support & MISC_FW_DOORBELL_RESET;
+                if (use_doorbell) {
+                        dev_warn(&pdev->dev, "Controller claims that "
+                                "'Bit 2 doorbell reset' is "
+                                "supported, but not 'bit 5 doorbell reset'.  "
+                                "Firmware update is recommended.\n");
+                        rc = -ENOTSUPP; /* use the soft reset */
+                        goto unmap_cfgtable;
+                }
+        }
 
         rc = cciss_controller_hard_reset(pdev, vaddr, use_doorbell);
         if (rc)
@@ -4524,30 +4703,31 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
         msleep(CCISS_POST_RESET_PAUSE_MSECS);
 
         /* Wait for board to become not ready, then ready. */
-        dev_info(&pdev->dev, "Waiting for board to become ready.\n");
+        dev_info(&pdev->dev, "Waiting for board to reset.\n");
         rc = cciss_wait_for_board_state(pdev, vaddr, BOARD_NOT_READY);
-        if (rc) /* Don't bail, might be E500, etc. which can't be reset */
-                dev_warn(&pdev->dev,
-                        "failed waiting for board to become not ready\n");
+        if (rc) {
+                dev_warn(&pdev->dev, "Failed waiting for board to hard reset."
+                                "  Will try soft reset.\n");
+                rc = -ENOTSUPP; /* Not expected, but try soft reset later */
+                goto unmap_cfgtable;
+        }
         rc = cciss_wait_for_board_state(pdev, vaddr, BOARD_READY);
         if (rc) {
                 dev_warn(&pdev->dev,
-                        "failed waiting for board to become ready\n");
+                        "failed waiting for board to become ready "
+                        "after hard reset\n");
                 goto unmap_cfgtable;
         }
-        dev_info(&pdev->dev, "board ready.\n");
 
-        /* Controller should be in simple mode at this point.  If it's not,
-         * It means we're on one of those controllers which doesn't support
-         * the doorbell reset method and on which the PCI power management reset
-         * method doesn't work (P800, for example.)
-         * In those cases, don't try to proceed, as it generally doesn't work.
-         */
-        active_transport = readl(&cfgtable->TransportActive);
-        if (active_transport & PERFORMANT_MODE) {
-                dev_warn(&pdev->dev, "Unable to successfully reset controller,"
-                        " Ignoring controller.\n");
-                rc = -ENODEV;
+        rc = controller_reset_failed(vaddr);
+        if (rc < 0)
+                goto unmap_cfgtable;
+        if (rc) {
+                dev_warn(&pdev->dev, "Unable to successfully hard reset "
+                        "controller. Will try soft reset.\n");
+                rc = -ENOTSUPP; /* Not expected, but try soft reset later */
+        } else {
+                dev_info(&pdev->dev, "Board ready after hard reset.\n");
         }
 
 unmap_cfgtable:
@@ -4574,11 +4754,12 @@ static __devinit int cciss_init_reset_devices(struct pci_dev *pdev)
          * due to concerns about shared bbwc between 6402/6404 pair.
          */
         if (rc == -ENOTSUPP)
-                return 0; /* just try to do the kdump anyhow. */
+                return rc; /* just try to do the kdump anyhow. */
         if (rc)
                 return -ENODEV;
 
         /* Now try to get the controller to respond to a no-op */
+        dev_warn(&pdev->dev, "Waiting for controller to respond to no-op\n");
         for (i = 0; i < CCISS_POST_RESET_NOOP_RETRIES; i++) {
                 if (cciss_noop(pdev) == 0)
                         break;
@@ -4591,6 +4772,148 @@ static __devinit int cciss_init_reset_devices(struct pci_dev *pdev)
         return 0;
 }
 
+static __devinit int cciss_allocate_cmd_pool(ctlr_info_t *h)
+{
+        h->cmd_pool_bits = kmalloc(
+                DIV_ROUND_UP(h->nr_cmds, BITS_PER_LONG) *
+                sizeof(unsigned long), GFP_KERNEL);
+        h->cmd_pool = pci_alloc_consistent(h->pdev,
+                h->nr_cmds * sizeof(CommandList_struct),
+                &(h->cmd_pool_dhandle));
+        h->errinfo_pool = pci_alloc_consistent(h->pdev,
+                h->nr_cmds * sizeof(ErrorInfo_struct),
+                &(h->errinfo_pool_dhandle));
+        if ((h->cmd_pool_bits == NULL)
+                || (h->cmd_pool == NULL)
+                || (h->errinfo_pool == NULL)) {
+                dev_err(&h->pdev->dev, "out of memory");
+                return -ENOMEM;
+        }
+        return 0;
+}
+
+static __devinit int cciss_allocate_scatterlists(ctlr_info_t *h)
+{
+        int i;
+
+        /* zero it, so that on free we need not know how many were alloc'ed */
+        h->scatter_list = kzalloc(h->max_commands *
+                                sizeof(struct scatterlist *), GFP_KERNEL);
+        if (!h->scatter_list)
+                return -ENOMEM;
+
+        for (i = 0; i < h->nr_cmds; i++) {
+                h->scatter_list[i] = kmalloc(sizeof(struct scatterlist) *
+                                                h->maxsgentries, GFP_KERNEL);
+                if (h->scatter_list[i] == NULL) {
+                        dev_err(&h->pdev->dev, "could not allocate "
+                                "s/g lists\n");
+                        return -ENOMEM;
+                }
+        }
+        return 0;
+}
+
+static void cciss_free_scatterlists(ctlr_info_t *h)
+{
+        int i;
+
+        if (h->scatter_list) {
+                for (i = 0; i < h->nr_cmds; i++)
+                        kfree(h->scatter_list[i]);
+                kfree(h->scatter_list);
+        }
+}
+
+static void cciss_free_cmd_pool(ctlr_info_t *h)
+{
+        kfree(h->cmd_pool_bits);
+        if (h->cmd_pool)
+                pci_free_consistent(h->pdev,
+                        h->nr_cmds * sizeof(CommandList_struct),
+                        h->cmd_pool, h->cmd_pool_dhandle);
+        if (h->errinfo_pool)
+                pci_free_consistent(h->pdev,
+                        h->nr_cmds * sizeof(ErrorInfo_struct),
+                        h->errinfo_pool, h->errinfo_pool_dhandle);
+}
+
+static int cciss_request_irq(ctlr_info_t *h,
+        irqreturn_t (*msixhandler)(int, void *),
+        irqreturn_t (*intxhandler)(int, void *))
+{
+        if (h->msix_vector || h->msi_vector) {
+                if (!request_irq(h->intr[PERF_MODE_INT], msixhandler,
+                                IRQF_DISABLED, h->devname, h))
+                        return 0;
+                dev_err(&h->pdev->dev, "Unable to get msi irq %d"
+                        " for %s\n", h->intr[PERF_MODE_INT],
+                        h->devname);
+                return -1;
+        }
+
+        if (!request_irq(h->intr[PERF_MODE_INT], intxhandler,
+                        IRQF_DISABLED, h->devname, h))
+                return 0;
+        dev_err(&h->pdev->dev, "Unable to get irq %d for %s\n",
+                h->intr[PERF_MODE_INT], h->devname);
+        return -1;
+}
+
+static int __devinit cciss_kdump_soft_reset(ctlr_info_t *h)
+{
+        if (cciss_send_reset(h, CTLR_LUNID, CCISS_RESET_TYPE_CONTROLLER)) {
+                dev_warn(&h->pdev->dev, "Resetting array controller failed.\n");
+                return -EIO;
+        }
+
+        dev_info(&h->pdev->dev, "Waiting for board to soft reset.\n");
+        if (cciss_wait_for_board_state(h->pdev, h->vaddr, BOARD_NOT_READY)) {
+                dev_warn(&h->pdev->dev, "Soft reset had no effect.\n");
+                return -1;
+        }
+
+        dev_info(&h->pdev->dev, "Board reset, awaiting READY status.\n");
+        if (cciss_wait_for_board_state(h->pdev, h->vaddr, BOARD_READY)) {
+                dev_warn(&h->pdev->dev, "Board failed to become ready "
+                        "after soft reset.\n");
+                return -1;
+        }
+
+        return 0;
+}
+
+static void cciss_undo_allocations_after_kdump_soft_reset(ctlr_info_t *h)
+{
+        int ctlr = h->ctlr;
+
+        free_irq(h->intr[PERF_MODE_INT], h);
+#ifdef CONFIG_PCI_MSI
+        if (h->msix_vector)
+                pci_disable_msix(h->pdev);
+        else if (h->msi_vector)
+                pci_disable_msi(h->pdev);
+#endif /* CONFIG_PCI_MSI */
+        cciss_free_sg_chain_blocks(h->cmd_sg_list, h->nr_cmds);
+        cciss_free_scatterlists(h);
+        cciss_free_cmd_pool(h);
+        kfree(h->blockFetchTable);
+        if (h->reply_pool)
+                pci_free_consistent(h->pdev, h->max_commands * sizeof(__u64),
+                                h->reply_pool, h->reply_pool_dhandle);
+        if (h->transtable)
+                iounmap(h->transtable);
+        if (h->cfgtable)
+                iounmap(h->cfgtable);
+        if (h->vaddr)
+                iounmap(h->vaddr);
+        unregister_blkdev(h->major, h->devname);
+        cciss_destroy_hba_sysfs_entry(h);
+        pci_release_regions(h->pdev);
+        kfree(h);
+        hba[ctlr] = NULL;
+}
+
 /*
  *  This is it.  Find all the controllers and register them.  I really hate
  *  stealing all these major device numbers.
@@ -4601,15 +4924,28 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 {
         int i;
         int j = 0;
-        int k = 0;
         int rc;
+        int try_soft_reset = 0;
         int dac, return_code;
         InquiryData_struct *inq_buff;
         ctlr_info_t *h;
+        unsigned long flags;
 
         rc = cciss_init_reset_devices(pdev);
-        if (rc)
-                return rc;
+        if (rc) {
+                if (rc != -ENOTSUPP)
+                        return rc;
+                /* If the reset fails in a particular way (it has no way to do
+                 * a proper hard reset, so returns -ENOTSUPP) we can try to do
+                 * a soft reset once we get the controller configured up to the
+                 * point that it can accept a command.
+                 */
+                try_soft_reset = 1;
+                rc = 0;
+        }
+
+reinit_after_soft_reset:
+
         i = alloc_cciss_hba(pdev);
         if (i < 0)
                 return -1;
@@ -4627,6 +4963,11 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
         sprintf(h->devname, "cciss%d", i);
         h->ctlr = i;
 
+        if (cciss_tape_cmds < 2)
+                cciss_tape_cmds = 2;
+        if (cciss_tape_cmds > 16)
+                cciss_tape_cmds = 16;
+
         init_completion(&h->scan_wait);
 
         if (cciss_create_hba_sysfs_entry(h))
@@ -4662,62 +5003,20 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 
         /* make sure the board interrupts are off */
         h->access.set_intr_mask(h, CCISS_INTR_OFF);
-        if (h->msi_vector || h->msix_vector) {
-                if (request_irq(h->intr[PERF_MODE_INT],
-                                do_cciss_msix_intr,
-                                IRQF_DISABLED, h->devname, h)) {
-                        dev_err(&h->pdev->dev, "Unable to get irq %d for %s\n",
-                               h->intr[PERF_MODE_INT], h->devname);
-                        goto clean2;
-                }
-        } else {
-                if (request_irq(h->intr[PERF_MODE_INT], do_cciss_intx,
-                                IRQF_DISABLED, h->devname, h)) {
-                        dev_err(&h->pdev->dev, "Unable to get irq %d for %s\n",
-                               h->intr[PERF_MODE_INT], h->devname);
-                        goto clean2;
-                }
-        }
+        rc = cciss_request_irq(h, do_cciss_msix_intr, do_cciss_intx);
+        if (rc)
+                goto clean2;
 
         dev_info(&h->pdev->dev, "%s: <0x%x> at PCI %s IRQ %d%s using DAC\n",
                h->devname, pdev->device, pci_name(pdev),
                h->intr[PERF_MODE_INT], dac ? "" : " not");
 
-        h->cmd_pool_bits =
-            kmalloc(DIV_ROUND_UP(h->nr_cmds, BITS_PER_LONG)
-                        * sizeof(unsigned long), GFP_KERNEL);
-        h->cmd_pool = (CommandList_struct *)
-            pci_alloc_consistent(h->pdev,
-                    h->nr_cmds * sizeof(CommandList_struct),
-                    &(h->cmd_pool_dhandle));
-        h->errinfo_pool = (ErrorInfo_struct *)
-            pci_alloc_consistent(h->pdev,
-                    h->nr_cmds * sizeof(ErrorInfo_struct),
-                    &(h->errinfo_pool_dhandle));
-        if ((h->cmd_pool_bits == NULL)
-            || (h->cmd_pool == NULL)
-            || (h->errinfo_pool == NULL)) {
-                dev_err(&h->pdev->dev, "out of memory");
+        if (cciss_allocate_cmd_pool(h))
                 goto clean4;
-        }
 
-        /* Need space for temp scatter list */
-        h->scatter_list = kmalloc(h->max_commands *
-                                                sizeof(struct scatterlist *),
-                                                GFP_KERNEL);
-        if (!h->scatter_list)
+        if (cciss_allocate_scatterlists(h))
                 goto clean4;
 
-        for (k = 0; k < h->nr_cmds; k++) {
-                h->scatter_list[k] = kmalloc(sizeof(struct scatterlist) *
-                                                        h->maxsgentries,
-                                                        GFP_KERNEL);
-                if (h->scatter_list[k] == NULL) {
-                        dev_err(&h->pdev->dev,
-                                "could not allocate s/g lists\n");
-                        goto clean4;
-                }
-        }
         h->cmd_sg_list = cciss_allocate_sg_chain_blocks(h,
                 h->chainsize, h->nr_cmds);
         if (!h->cmd_sg_list && h->chainsize > 0)
@@ -4741,6 +5040,62 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
                 h->gendisk[j] = NULL;
         }
 
+        /* At this point, the controller is ready to take commands.
+         * Now, if reset_devices and the hard reset didn't work, try
+         * the soft reset and see if that works.
+         */
+        if (try_soft_reset) {
+
+                /* This is kind of gross.  We may or may not get a completion
+                 * from the soft reset command, and if we do, then the value
+                 * from the fifo may or may not be valid.  So, we wait 10 secs
+                 * after the reset throwing away any completions we get during
+                 * that time.  Unregister the interrupt handler and register
+                 * fake ones to scoop up any residual completions.
+                 */
+                spin_lock_irqsave(&h->lock, flags);
+                h->access.set_intr_mask(h, CCISS_INTR_OFF);
+                spin_unlock_irqrestore(&h->lock, flags);
+                free_irq(h->intr[PERF_MODE_INT], h);
+                rc = cciss_request_irq(h, cciss_msix_discard_completions,
+                                        cciss_intx_discard_completions);
+                if (rc) {
+                        dev_warn(&h->pdev->dev, "Failed to request_irq after "
+                                "soft reset.\n");
+                        goto clean4;
+                }
+
+                rc = cciss_kdump_soft_reset(h);
+                if (rc) {
+                        dev_warn(&h->pdev->dev, "Soft reset failed.\n");
+                        goto clean4;
+                }
+
+                dev_info(&h->pdev->dev, "Board READY.\n");
+                dev_info(&h->pdev->dev,
+                        "Waiting for stale completions to drain.\n");
+                h->access.set_intr_mask(h, CCISS_INTR_ON);
+                msleep(10000);
+                h->access.set_intr_mask(h, CCISS_INTR_OFF);
+
+                rc = controller_reset_failed(h->cfgtable);
+                if (rc)
+                        dev_info(&h->pdev->dev,
+                                "Soft reset appears to have failed.\n");
+
+                /* since the controller's reset, we have to go back and re-init
+                 * everything.  Easiest to just forget what we've done and do it
+                 * all over again.
+                 */
+                cciss_undo_allocations_after_kdump_soft_reset(h);
+                try_soft_reset = 0;
+                if (rc)
+                        /* don't go to clean4, we already unallocated */
+                        return -ENODEV;
+
+                goto reinit_after_soft_reset;
+        }
+
         cciss_scsi_setup(h);
 
         /* Turn the interrupts on so we can service requests */
@@ -4775,21 +5130,9 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
         return 1;
 
 clean4:
-        kfree(h->cmd_pool_bits);
-        /* Free up sg elements */
-        for (k-- ; k >= 0; k--)
-                kfree(h->scatter_list[k]);
-        kfree(h->scatter_list);
+        cciss_free_cmd_pool(h);
+        cciss_free_scatterlists(h);
         cciss_free_sg_chain_blocks(h->cmd_sg_list, h->nr_cmds);
-        if (h->cmd_pool)
-                pci_free_consistent(h->pdev,
-                                    h->nr_cmds * sizeof(CommandList_struct),
-                                    h->cmd_pool, h->cmd_pool_dhandle);
-        if (h->errinfo_pool)
-                pci_free_consistent(h->pdev,
-                                    h->nr_cmds * sizeof(ErrorInfo_struct),
-                                    h->errinfo_pool,
-                                    h->errinfo_pool_dhandle);
         free_irq(h->intr[PERF_MODE_INT], h);
 clean2:
         unregister_blkdev(h->major, h->devname);
@@ -4887,16 +5230,16 @@ static void __devexit cciss_remove_one(struct pci_dev *pdev)
         iounmap(h->cfgtable);
         iounmap(h->vaddr);
 
-        pci_free_consistent(h->pdev, h->nr_cmds * sizeof(CommandList_struct),
-                            h->cmd_pool, h->cmd_pool_dhandle);
-        pci_free_consistent(h->pdev, h->nr_cmds * sizeof(ErrorInfo_struct),
-                            h->errinfo_pool, h->errinfo_pool_dhandle);
-        kfree(h->cmd_pool_bits);
+        cciss_free_cmd_pool(h);
         /* Free up sg elements */
         for (j = 0; j < h->nr_cmds; j++)
                 kfree(h->scatter_list[j]);
         kfree(h->scatter_list);
         cciss_free_sg_chain_blocks(h->cmd_sg_list, h->nr_cmds);
+        kfree(h->blockFetchTable);
+        if (h->reply_pool)
+                pci_free_consistent(h->pdev, h->max_commands * sizeof(__u64),
+                                h->reply_pool, h->reply_pool_dhandle);
         /*
          * Deliberately omit pci_disable_device(): it does something nasty to
          * Smart Array controllers that pci_enable_device does not undo
diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h
index 554bbd907d14..16b4d58d84dd 100644
--- a/drivers/block/cciss.h
+++ b/drivers/block/cciss.h
@@ -200,7 +200,7 @@ struct ctlr_info
  * the above.
  */
 #define CCISS_BOARD_READY_WAIT_SECS (120)
-#define CCISS_BOARD_NOT_READY_WAIT_SECS (10)
+#define CCISS_BOARD_NOT_READY_WAIT_SECS (100)
 #define CCISS_BOARD_READY_POLL_INTERVAL_MSECS (100)
 #define CCISS_BOARD_READY_ITERATIONS \
         ((CCISS_BOARD_READY_WAIT_SECS * 1000) / \
@@ -209,8 +209,9 @@ struct ctlr_info
         ((CCISS_BOARD_NOT_READY_WAIT_SECS * 1000) / \
                 CCISS_BOARD_READY_POLL_INTERVAL_MSECS)
 #define CCISS_POST_RESET_PAUSE_MSECS (3000)
-#define CCISS_POST_RESET_NOOP_INTERVAL_MSECS (1000)
+#define CCISS_POST_RESET_NOOP_INTERVAL_MSECS (4000)
 #define CCISS_POST_RESET_NOOP_RETRIES (12)
+#define CCISS_POST_RESET_NOOP_TIMEOUT_MSECS (10000)
 
 /* 
         Send the command to the hardware 
@@ -239,11 +240,13 @@ static void SA5_intr_mask(ctlr_info_t *h, unsigned long val)
         { /* Turn interrupts on */
                 h->interrupts_enabled = 1;
                 writel(0, h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
+                (void) readl(h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
         } else /* Turn them off */
         {
                 h->interrupts_enabled = 0;
                 writel( SA5_INTR_OFF, 
                         h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
+                (void) readl(h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
         }
 }
 /*
@@ -257,11 +260,13 @@ static void SA5B_intr_mask(ctlr_info_t *h, unsigned long val)
         { /* Turn interrupts on */
                 h->interrupts_enabled = 1;
                 writel(0, h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
+                (void) readl(h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
         } else /* Turn them off */
         {
                 h->interrupts_enabled = 0;
                 writel( SA5B_INTR_OFF,
                         h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
+                (void) readl(h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
         }
 }
 
@@ -271,10 +276,12 @@ static void SA5_performant_intr_mask(ctlr_info_t *h, unsigned long val)
         if (val) { /* turn on interrupts */
                 h->interrupts_enabled = 1;
                 writel(0, h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
+                (void) readl(h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
         } else {
                 h->interrupts_enabled = 0;
                 writel(SA5_PERF_INTR_OFF,
                                 h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
+                (void) readl(h->vaddr + SA5_REPLY_INTR_MASK_OFFSET);
         }
 }
 
diff --git a/drivers/block/cciss_cmd.h b/drivers/block/cciss_cmd.h
index cd441bef031f..d9be6b4d49a6 100644
--- a/drivers/block/cciss_cmd.h
+++ b/drivers/block/cciss_cmd.h
@@ -53,6 +53,7 @@
 #define CFGTBL_ChangeReq        0x00000001l
 #define CFGTBL_AccCmds          0x00000001l
 #define DOORBELL_CTLR_RESET     0x00000004l
+#define DOORBELL_CTLR_RESET2    0x00000020l
 
 #define CFGTBL_Trans_Simple     0x00000002l
 #define CFGTBL_Trans_Performant 0x00000004l
@@ -142,6 +143,14 @@ typedef struct _ReadCapdata_struct_16
 #define BMIC_CACHE_FLUSH 0xc2
 #define CCISS_CACHE_FLUSH 0x01  /* C2 was already being used by CCISS */
 
+#define CCISS_ABORT_MSG 0x00
+#define CCISS_RESET_MSG 0x01
+#define CCISS_RESET_TYPE_CONTROLLER 0x00
+#define CCISS_RESET_TYPE_BUS 0x01
+#define CCISS_RESET_TYPE_TARGET 0x03
+#define CCISS_RESET_TYPE_LUN 0x04
+#define CCISS_NOOP_MSG 0x03
+
 /* Command List Structure */
 #define CTLR_LUNID "\0\0\0\0\0\0\0\0"
 
@@ -235,6 +244,8 @@ typedef struct _CfgTable_struct {
   u8               reserved[0x78 - 0x58];
   u32              misc_fw_support; /* offset 0x78 */
 #define MISC_FW_DOORBELL_RESET (0x02)
+#define MISC_FW_DOORBELL_RESET2 (0x10)
+        u8         driver_version[32];
 } CfgTable_struct;
 
 struct TransTable_struct {
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index df793803f5ae..696100241a6f 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -84,7 +84,6 @@ static struct scsi_host_template cciss_driver_template = {
         .proc_name              = "cciss",
         .proc_info              = cciss_scsi_proc_info,
         .queuecommand           = cciss_scsi_queue_command,
-        .can_queue              = SCSI_CCISS_CAN_QUEUE,
         .this_id                = 7,
         .cmd_per_lun            = 1,
         .use_clustering         = DISABLE_CLUSTERING,
@@ -108,16 +107,13 @@ struct cciss_scsi_cmd_stack_elem_t {
 
 #pragma pack()
 
-#define CMD_STACK_SIZE (SCSI_CCISS_CAN_QUEUE * \
-                CCISS_MAX_SCSI_DEVS_PER_HBA + 2)
-                        // plus two for init time usage
-
 #pragma pack(1)
 struct cciss_scsi_cmd_stack_t {
         struct cciss_scsi_cmd_stack_elem_t *pool;
-        struct cciss_scsi_cmd_stack_elem_t *elem[CMD_STACK_SIZE];
+        struct cciss_scsi_cmd_stack_elem_t **elem;
         dma_addr_t cmd_pool_handle;
         int top;
+        int nelems;
 };
 #pragma pack()
 
@@ -191,7 +187,7 @@ scsi_cmd_free(ctlr_info_t *h, CommandList_struct *c)
         sa = h->scsi_ctlr;
         stk = &sa->cmd_stack; 
         stk->top++;
-        if (stk->top >= CMD_STACK_SIZE) {
+        if (stk->top >= stk->nelems) {
                 dev_err(&h->pdev->dev,
                         "scsi_cmd_free called too many times.\n");
                 BUG();
@@ -206,13 +202,14 @@ scsi_cmd_stack_setup(ctlr_info_t *h, struct cciss_scsi_adapter_data_t *sa)
         struct cciss_scsi_cmd_stack_t *stk;
         size_t size;
 
+        stk = &sa->cmd_stack;
+        stk->nelems = cciss_tape_cmds + 2;
         sa->cmd_sg_list = cciss_allocate_sg_chain_blocks(h,
-                h->chainsize, CMD_STACK_SIZE);
+                h->chainsize, stk->nelems);
         if (!sa->cmd_sg_list && h->chainsize > 0)
                 return -ENOMEM;
 
-        stk = &sa->cmd_stack; 
-        size = sizeof(struct cciss_scsi_cmd_stack_elem_t) * CMD_STACK_SIZE;
+        size = sizeof(struct cciss_scsi_cmd_stack_elem_t) * stk->nelems;
 
         /* Check alignment, see cciss_cmd.h near CommandList_struct def. */
         BUILD_BUG_ON((sizeof(*stk->pool) % COMMANDLIST_ALIGNMENT) != 0);
@@ -221,18 +218,23 @@ scsi_cmd_stack_setup(ctlr_info_t *h, struct cciss_scsi_adapter_data_t *sa)
                 pci_alloc_consistent(h->pdev, size, &stk->cmd_pool_handle);
 
         if (stk->pool == NULL) {
-                cciss_free_sg_chain_blocks(sa->cmd_sg_list, CMD_STACK_SIZE);
+                cciss_free_sg_chain_blocks(sa->cmd_sg_list, stk->nelems);
                 sa->cmd_sg_list = NULL;
                 return -ENOMEM;
         }
-
-        for (i=0; i<CMD_STACK_SIZE; i++) {
+        stk->elem = kmalloc(sizeof(stk->elem[0]) * stk->nelems, GFP_KERNEL);
+        if (!stk->elem) {
+                pci_free_consistent(h->pdev, size, stk->pool,
+                stk->cmd_pool_handle);
+                return -1;
+        }
+        for (i = 0; i < stk->nelems; i++) {
                 stk->elem[i] = &stk->pool[i];
                 stk->elem[i]->busaddr = (__u32) (stk->cmd_pool_handle + 
                         (sizeof(struct cciss_scsi_cmd_stack_elem_t) * i));
                 stk->elem[i]->cmdindex = i;
         }
-        stk->top = CMD_STACK_SIZE-1;
+        stk->top = stk->nelems-1;
         return 0;
 }
 
@@ -245,16 +247,18 @@ scsi_cmd_stack_free(ctlr_info_t *h)
 
         sa = h->scsi_ctlr;
         stk = &sa->cmd_stack; 
-        if (stk->top != CMD_STACK_SIZE-1) {
+        if (stk->top != stk->nelems-1) {
                 dev_warn(&h->pdev->dev,
                         "bug: %d scsi commands are still outstanding.\n",
-                        CMD_STACK_SIZE - stk->top);
+                        stk->nelems - stk->top);
         }
-        size = sizeof(struct cciss_scsi_cmd_stack_elem_t) * CMD_STACK_SIZE;
+        size = sizeof(struct cciss_scsi_cmd_stack_elem_t) * stk->nelems;
 
         pci_free_consistent(h->pdev, size, stk->pool, stk->cmd_pool_handle);
         stk->pool = NULL;
-        cciss_free_sg_chain_blocks(sa->cmd_sg_list, CMD_STACK_SIZE);
+        cciss_free_sg_chain_blocks(sa->cmd_sg_list, stk->nelems);
+        kfree(stk->elem);
+        stk->elem = NULL;
 }
 
 #if 0
@@ -859,6 +863,7 @@ cciss_scsi_detect(ctlr_info_t *h)
         sh->io_port = 0;        // good enough?  FIXME, 
         sh->n_io_port = 0;      // I don't think we use these two...
         sh->this_id = SELF_SCSI_ID;  
+        sh->can_queue = cciss_tape_cmds;
         sh->sg_tablesize = h->maxsgentries;
         sh->max_cmd_len = MAX_COMMAND_SIZE;
 
diff --git a/drivers/block/cciss_scsi.h b/drivers/block/cciss_scsi.h
index 6d5822fe851a..e71d986727ca 100644
--- a/drivers/block/cciss_scsi.h
+++ b/drivers/block/cciss_scsi.h
@@ -36,13 +36,9 @@
                    addressible natively, and may in fact turn
                    out to be not scsi at all. */
 
-#define SCSI_CCISS_CAN_QUEUE 2
 
 /* 
 
-Note, cmd_per_lun could give us some trouble, so I'm setting it very low.
-Likewise, SCSI_CCISS_CAN_QUEUE is set very conservatively.
-
 If the upper scsi layer tries to track how many commands we have 
 outstanding, it will be operating under the misapprehension that it is
 the only one sending us requests.  We also have the block interface,
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index c6828b68d77b..09ef9a878ef0 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -28,7 +28,7 @@
 #include "drbd_int.h"
 #include "drbd_wrappers.h"
 
-/* We maintain a trivial check sum in our on disk activity log.
+/* We maintain a trivial checksum in our on disk activity log.
  * With that we can ensure correct operation even when the storage
  * device might do a partial (last) sector write while losing power.
  */
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 76210ba401ac..f440a02dfdb1 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -74,7 +74,7 @@
  *      as we are "attached" to a local disk, which at 32 GiB for 1PiB storage
  *      seems excessive.
  *
- *      We plan to reduce the amount of in-core bitmap pages by pageing them in
+ *      We plan to reduce the amount of in-core bitmap pages by paging them in
  *      and out against their on-disk location as necessary, but need to make
  *      sure we don't cause too much meta data IO, and must not deadlock in
  *      tight memory situations. This needs some more work.
@@ -200,7 +200,7 @@ void drbd_bm_unlock(struct drbd_conf *mdev)
  * we if bits have been cleared since last IO. */
 #define BM_PAGE_LAZY_WRITEOUT   28
 
-/* store_page_idx uses non-atomic assingment. It is only used directly after
+/* store_page_idx uses non-atomic assignment. It is only used directly after
  * allocating the page.  All other bm_set_page_* and bm_clear_page_* need to
  * use atomic bit manipulation, as set_out_of_sync (and therefore bitmap
  * changes) may happen from various contexts, and wait_on_bit/wake_up_bit
@@ -318,7 +318,7 @@ static void bm_unmap(unsigned long *p_addr)
 /* word offset from start of bitmap to word number _in_page_
  * modulo longs per page
 #define MLPP(X) ((X) % (PAGE_SIZE/sizeof(long))
- hm, well, Philipp thinks gcc might not optimze the % into & (... - 1)
+ hm, well, Philipp thinks gcc might not optimize the % into & (... - 1)
  so do it explicitly:
  */
 #define MLPP(X) ((X) & ((PAGE_SIZE/sizeof(long))-1))
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d871b14ed5a1..ef2ceed3be4b 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -700,7 +700,7 @@ struct drbd_request {
          * see drbd_endio_pri(). */
         struct bio *private_bio;
 
-        struct hlist_node colision;
+        struct hlist_node collision;
         sector_t sector;
         unsigned int size;
         unsigned int epoch; /* barrier_nr */
@@ -766,7 +766,7 @@ struct digest_info {
 
 struct drbd_epoch_entry {
         struct drbd_work w;
-        struct hlist_node colision;
+        struct hlist_node collision;
         struct drbd_epoch *epoch; /* for writes */
         struct drbd_conf *mdev;
         struct page *pages;
@@ -1129,6 +1129,8 @@ struct drbd_conf {
         int rs_in_flight; /* resync sectors in flight (to proxy, in proxy and from proxy) */
         int rs_planed;    /* resync sectors already planned */
         atomic_t ap_in_flight; /* App sectors in flight (waiting for ack) */
+        int peer_max_bio_size;
+        int local_max_bio_size;
 };
 
 static inline struct drbd_conf *minor_to_mdev(unsigned int minor)
@@ -1218,8 +1220,6 @@ extern void drbd_free_resources(struct drbd_conf *mdev);
 extern void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr,
                        unsigned int set_size);
 extern void tl_clear(struct drbd_conf *mdev);
-enum drbd_req_event;
-extern void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what);
 extern void _tl_add_barrier(struct drbd_conf *, struct drbd_tl_epoch *);
 extern void drbd_free_sock(struct drbd_conf *mdev);
 extern int drbd_send(struct drbd_conf *mdev, struct socket *sock,
@@ -1434,6 +1434,7 @@ struct bm_extent {
  * hash table. */
 #define HT_SHIFT 8
 #define DRBD_MAX_BIO_SIZE (1U<<(9+HT_SHIFT))
+#define DRBD_MAX_BIO_SIZE_SAFE (1 << 12)       /* Works always = 4k */
 
 #define DRBD_MAX_SIZE_H80_PACKET (1 << 15) /* The old header only allows packets up to 32Kib data */
 
@@ -1518,9 +1519,9 @@ extern void drbd_resume_io(struct drbd_conf *mdev);
 extern char *ppsize(char *buf, unsigned long long size);
 extern sector_t drbd_new_dev_size(struct drbd_conf *, struct drbd_backing_dev *, int);
 enum determine_dev_size { dev_size_error = -1, unchanged = 0, shrunk = 1, grew = 2 };
-extern enum determine_dev_size drbd_determin_dev_size(struct drbd_conf *, enum dds_flags) __must_hold(local);
+extern enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *, enum dds_flags) __must_hold(local);
 extern void resync_after_online_grow(struct drbd_conf *);
-extern void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int) __must_hold(local);
+extern void drbd_reconsider_max_bio_size(struct drbd_conf *mdev);
 extern enum drbd_state_rv drbd_set_role(struct drbd_conf *mdev,
                                         enum drbd_role new_role,
                                         int force);
@@ -1828,6 +1829,8 @@ static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, int forcedetach,
                 if (!forcedetach) {
                         if (__ratelimit(&drbd_ratelimit_state))
                                 dev_err(DEV, "Local IO failed in %s.\n", where);
+                        if (mdev->state.disk > D_INCONSISTENT)
+                                _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_HARD, NULL);
                         break;
                 }
                 /* NOTE fall through to detach case if forcedetach set */
@@ -2153,6 +2156,10 @@ static inline int get_net_conf(struct drbd_conf *mdev)
 static inline void put_ldev(struct drbd_conf *mdev)
 {
         int i = atomic_dec_return(&mdev->local_cnt);
+
+        /* This may be called from some endio handler,
+         * so we must not sleep here. */
+
         __release(local);
         D_ASSERT(i >= 0);
         if (i == 0) {
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 5b525c179f39..0358e55356c8 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -745,6 +745,9 @@ is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
                   mdev->agreed_pro_version < 88)
                 rv = SS_NOT_SUPPORTED;
 
+        else if (ns.conn >= C_CONNECTED && ns.pdsk == D_UNKNOWN)
+                rv = SS_CONNECTED_OUTDATES;
+
         return rv;
 }
 
@@ -1565,6 +1568,10 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
                 put_ldev(mdev);
         }
 
+        /* Notify peer that I had a local IO error, and did not detached.. */
+        if (os.disk == D_UP_TO_DATE && ns.disk == D_INCONSISTENT)
+                drbd_send_state(mdev);
+
         /* Disks got bigger while they were detached */
         if (ns.disk > D_NEGOTIATING && ns.pdsk > D_NEGOTIATING &&
             test_and_clear_bit(RESYNC_AFTER_NEG, &mdev->flags)) {
@@ -2064,7 +2071,7 @@ int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags fl
 {
         struct p_sizes p;
         sector_t d_size, u_size;
-        int q_order_type;
+        int q_order_type, max_bio_size;
         int ok;
 
         if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
@@ -2072,17 +2079,20 @@ int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags fl
                 d_size = drbd_get_max_capacity(mdev->ldev);
                 u_size = mdev->ldev->dc.disk_size;
                 q_order_type = drbd_queue_order_type(mdev);
+                max_bio_size = queue_max_hw_sectors(mdev->ldev->backing_bdev->bd_disk->queue) << 9;
+                max_bio_size = min_t(int, max_bio_size, DRBD_MAX_BIO_SIZE);
                 put_ldev(mdev);
         } else {
                 d_size = 0;
                 u_size = 0;
                 q_order_type = QUEUE_ORDERED_NONE;
+                max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */
         }
 
         p.d_size = cpu_to_be64(d_size);
         p.u_size = cpu_to_be64(u_size);
         p.c_size = cpu_to_be64(trigger_reply ? 0 : drbd_get_capacity(mdev->this_bdev));
-        p.max_bio_size = cpu_to_be32(queue_max_hw_sectors(mdev->rq_queue) << 9);
+        p.max_bio_size = cpu_to_be32(max_bio_size);
         p.queue_order_type = cpu_to_be16(q_order_type);
         p.dds_flags = cpu_to_be16(flags);
 
@@ -2722,7 +2732,7 @@ int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req)
 
                 /* double check digest, sometimes buffers have been modified in flight. */
                 if (dgs > 0 && dgs <= 64) {
-                        /* 64 byte, 512 bit, is the larges digest size
+                        /* 64 byte, 512 bit, is the largest digest size
                          * currently supported in kernel crypto. */
                         unsigned char digest[64];
                         drbd_csum_bio(mdev, mdev->integrity_w_tfm, req->master_bio, digest);
@@ -3041,6 +3051,8 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
         mdev->agreed_pro_version = PRO_VERSION_MAX;
         mdev->write_ordering = WO_bdev_flush;
         mdev->resync_wenr = LC_FREE;
+        mdev->peer_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE;
+        mdev->local_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE;
 }
 
 void drbd_mdev_cleanup(struct drbd_conf *mdev)
@@ -3275,7 +3287,7 @@ static void drbd_delete_device(unsigned int minor)
 
         drbd_release_ee_lists(mdev);
 
-        /* should be free'd on disconnect? */
+        /* should be freed on disconnect? */
         kfree(mdev->ee_hash);
         /*
         mdev->ee_hash_s = 0;
@@ -3415,7 +3427,9 @@ struct drbd_conf *drbd_new_device(unsigned int minor)
         q->backing_dev_info.congested_data = mdev;
 
         blk_queue_make_request(q, drbd_make_request);
-        blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE >> 9);
+        /* Setting the max_hw_sectors to an odd value of 8kibyte here
+           This triggers a max_bio_size message upon first attach or connect */
+        blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
         blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
         blk_queue_merge_bvec(q, drbd_merge_bvec);
         q->queue_lock = &mdev->req_lock;
@@ -3627,7 +3641,8 @@ struct meta_data_on_disk {
               /* `-- act_log->nr_elements <-- sync_conf.al_extents */
         u32 bm_offset;         /* offset to the bitmap, from here */
         u32 bm_bytes_per_bit;  /* BM_BLOCK_SIZE */
-        u32 reserved_u32[4];
+        u32 la_peer_max_bio_size;   /* last peer max_bio_size */
+        u32 reserved_u32[3];
 
 } __packed;
 
@@ -3668,6 +3683,7 @@ void drbd_md_sync(struct drbd_conf *mdev)
         buffer->device_uuid = cpu_to_be64(mdev->ldev->md.device_uuid);
 
         buffer->bm_offset = cpu_to_be32(mdev->ldev->md.bm_offset);
+        buffer->la_peer_max_bio_size = cpu_to_be32(mdev->peer_max_bio_size);
 
         D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset);
         sector = mdev->ldev->md.md_offset;
@@ -3751,6 +3767,15 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
         mdev->sync_conf.al_extents = be32_to_cpu(buffer->al_nr_extents);
         bdev->md.device_uuid = be64_to_cpu(buffer->device_uuid);
 
+        spin_lock_irq(&mdev->req_lock);
+        if (mdev->state.conn < C_CONNECTED) {
+                int peer;
+                peer = be32_to_cpu(buffer->la_peer_max_bio_size);
+                peer = max_t(int, peer, DRBD_MAX_BIO_SIZE_SAFE);
+                mdev->peer_max_bio_size = peer;
+        }
+        spin_unlock_irq(&mdev->req_lock);
+
         if (mdev->sync_conf.al_extents < 7)
                 mdev->sync_conf.al_extents = 127;
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 03b29f78a37d..515bcd948a43 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -272,9 +272,28 @@ static int _try_outdate_peer_async(void *data)
 {
         struct drbd_conf *mdev = (struct drbd_conf *)data;
         enum drbd_disk_state nps;
+        union drbd_state ns;
 
         nps = drbd_try_outdate_peer(mdev);
-        drbd_request_state(mdev, NS(pdsk, nps));
+
+        /* Not using
+           drbd_request_state(mdev, NS(pdsk, nps));
+           here, because we might were able to re-establish the connection
+           in the meantime. This can only partially be solved in the state's
+           engine is_valid_state() and is_valid_state_transition()
+           functions.
+
+           nps can be D_INCONSISTENT, D_OUTDATED or D_UNKNOWN.
+           pdsk == D_INCONSISTENT while conn >= C_CONNECTED is valid,
+           therefore we have to have the pre state change check here.
+        */
+        spin_lock_irq(&mdev->req_lock);
+        ns = mdev->state;
+        if (ns.conn < C_WF_REPORT_PARAMS) {
+                ns.pdsk = nps;
+                _drbd_set_state(mdev, ns, CS_VERBOSE, NULL);
+        }
+        spin_unlock_irq(&mdev->req_lock);
 
         return 0;
 }
@@ -577,7 +596,7 @@ void drbd_resume_io(struct drbd_conf *mdev)
  * Returns 0 on success, negative return values indicate errors.
  * You should call drbd_md_sync() after calling this function.
  */
-enum determine_dev_size drbd_determin_dev_size(struct drbd_conf *mdev, enum dds_flags flags) __must_hold(local)
+enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags) __must_hold(local)
 {
         sector_t prev_first_sect, prev_size; /* previous meta location */
         sector_t la_size;
@@ -773,30 +792,78 @@ static int drbd_check_al_size(struct drbd_conf *mdev)
         return 0;
 }
 
-void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_bio_size) __must_hold(local)
+static void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_bio_size)
 {
         struct request_queue * const q = mdev->rq_queue;
-        struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue;
-        int max_segments = mdev->ldev->dc.max_bio_bvecs;
-        int max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
+        int max_hw_sectors = max_bio_size >> 9;
+        int max_segments = 0;
+
+        if (get_ldev_if_state(mdev, D_ATTACHING)) {
+                struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue;
+
+                max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
+                max_segments = mdev->ldev->dc.max_bio_bvecs;
+                put_ldev(mdev);
+        }
 
         blk_queue_logical_block_size(q, 512);
         blk_queue_max_hw_sectors(q, max_hw_sectors);
         /* This is the workaround for "bio would need to, but cannot, be split" */
         blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
         blk_queue_segment_boundary(q, PAGE_CACHE_SIZE-1);
-        blk_queue_stack_limits(q, b);
 
-        dev_info(DEV, "max BIO size = %u\n", queue_max_hw_sectors(q) << 9);
+        if (get_ldev_if_state(mdev, D_ATTACHING)) {
+                struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue;
+
+                blk_queue_stack_limits(q, b);
 
-        if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
-                dev_info(DEV, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
-                     q->backing_dev_info.ra_pages,
-                     b->backing_dev_info.ra_pages);
-                q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
+                if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
+                        dev_info(DEV, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
+                                 q->backing_dev_info.ra_pages,
+                                 b->backing_dev_info.ra_pages);
+                        q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
+                }
+                put_ldev(mdev);
         }
 }
 
+void drbd_reconsider_max_bio_size(struct drbd_conf *mdev)
+{
+        int now, new, local, peer;
+
+        now = queue_max_hw_sectors(mdev->rq_queue) << 9;
+        local = mdev->local_max_bio_size; /* Eventually last known value, from volatile memory */
+        peer = mdev->peer_max_bio_size; /* Eventually last known value, from meta data */
+
+        if (get_ldev_if_state(mdev, D_ATTACHING)) {
+                local = queue_max_hw_sectors(mdev->ldev->backing_bdev->bd_disk->queue) << 9;
+                mdev->local_max_bio_size = local;
+                put_ldev(mdev);
+        }
+
+        /* We may ignore peer limits if the peer is modern enough.
+           Because new from 8.3.8 onwards the peer can use multiple
+           BIOs for a single peer_request */
+        if (mdev->state.conn >= C_CONNECTED) {
+                if (mdev->agreed_pro_version < 94)
+                        peer = mdev->peer_max_bio_size;
+                else if (mdev->agreed_pro_version == 94)
+                        peer = DRBD_MAX_SIZE_H80_PACKET;
+                else /* drbd 8.3.8 onwards */
+                        peer = DRBD_MAX_BIO_SIZE;
+        }
+
+        new = min_t(int, local, peer);
+
+        if (mdev->state.role == R_PRIMARY && new < now)
+                dev_err(DEV, "ASSERT FAILED new < now; (%d < %d)\n", new, now);
+
+        if (new != now)
+                dev_info(DEV, "max BIO size = %u\n", new);
+
+        drbd_setup_queue_param(mdev, new);
+}
+
 /* serialize deconfig (worker exiting, doing cleanup)
  * and reconfig (drbdsetup disk, drbdsetup net)
  *
@@ -865,7 +932,6 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
         struct block_device *bdev;
         struct lru_cache *resync_lru = NULL;
         union drbd_state ns, os;
-        unsigned int max_bio_size;
         enum drbd_state_rv rv;
         int cp_discovered = 0;
         int logical_block_size;
@@ -1117,20 +1183,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
         mdev->read_cnt = 0;
         mdev->writ_cnt = 0;
 
-        max_bio_size = DRBD_MAX_BIO_SIZE;
-        if (mdev->state.conn == C_CONNECTED) {
-                /* We are Primary, Connected, and now attach a new local
-                 * backing store. We must not increase the user visible maximum
-                 * bio size on this device to something the peer may not be
-                 * able to handle. */
-                if (mdev->agreed_pro_version < 94)
-                        max_bio_size = queue_max_hw_sectors(mdev->rq_queue) << 9;
-                else if (mdev->agreed_pro_version == 94)
-                        max_bio_size = DRBD_MAX_SIZE_H80_PACKET;
-                /* else: drbd 8.3.9 and later, stay with default */
-        }
-
-        drbd_setup_queue_param(mdev, max_bio_size);
+        drbd_reconsider_max_bio_size(mdev);
 
         /* If I am currently not R_PRIMARY,
          * but meta data primary indicator is set,
@@ -1152,7 +1205,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
             !drbd_md_test_flag(mdev->ldev, MDF_CONNECTED_IND))
                 set_bit(USE_DEGR_WFC_T, &mdev->flags);
 
-        dd = drbd_determin_dev_size(mdev, 0);
+        dd = drbd_determine_dev_size(mdev, 0);
         if (dd == dev_size_error) {
                 retcode = ERR_NOMEM_BITMAP;
                 goto force_diskless_dec;
@@ -1281,11 +1334,19 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
                           struct drbd_nl_cfg_reply *reply)
 {
+        enum drbd_ret_code retcode;
+        int ret;
         drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
-        reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS));
-        if (mdev->state.disk == D_DISKLESS)
-                wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
+        retcode = drbd_request_state(mdev, NS(disk, D_FAILED));
+        /* D_FAILED will transition to DISKLESS. */
+        ret = wait_event_interruptible(mdev->misc_wait,
+                        mdev->state.disk != D_FAILED);
         drbd_resume_io(mdev);
+        if ((int)retcode == (int)SS_IS_DISKLESS)
+                retcode = SS_NOTHING_TO_DO;
+        if (ret)
+                retcode = ERR_INTR;
+        reply->ret_code = retcode;
         return 0;
 }
 
@@ -1658,7 +1719,7 @@ static int drbd_nl_resize(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 
         mdev->ldev->dc.disk_size = (sector_t)rs.resize_size;
         ddsf = (rs.resize_force ? DDSF_FORCED : 0) | (rs.no_resync ? DDSF_NO_RESYNC : 0);
-        dd = drbd_determin_dev_size(mdev, ddsf);
+        dd = drbd_determine_dev_size(mdev, ddsf);
         drbd_md_sync(mdev);
         put_ldev(mdev);
         if (dd == dev_size_error) {
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index fd26666c0b08..25d32c5aa50a 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -333,7 +333,7 @@ struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev,
         if (!page)
                 goto fail;
 
-        INIT_HLIST_NODE(&e->colision);
+        INIT_HLIST_NODE(&e->collision);
         e->epoch = NULL;
         e->mdev = mdev;
         e->pages = page;
@@ -356,7 +356,7 @@ void drbd_free_some_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e, int i
                 kfree(e->digest);
         drbd_pp_free(mdev, e->pages, is_net);
         D_ASSERT(atomic_read(&e->pending_bios) == 0);
-        D_ASSERT(hlist_unhashed(&e->colision));
+        D_ASSERT(hlist_unhashed(&e->collision));
         mempool_free(e, drbd_ee_mempool);
 }
 
@@ -787,7 +787,7 @@ static int drbd_connect(struct drbd_conf *mdev)
                 }
 
                 if (sock && msock) {
-                        schedule_timeout_interruptible(HZ / 10);
+                        schedule_timeout_interruptible(mdev->net_conf->ping_timeo*HZ/10);
                         ok = drbd_socket_okay(mdev, &sock);
                         ok = drbd_socket_okay(mdev, &msock) && ok;
                         if (ok)
@@ -899,11 +899,6 @@ retry:
 
         drbd_thread_start(&mdev->asender);
 
-        if (mdev->agreed_pro_version < 95 && get_ldev(mdev)) {
-                drbd_setup_queue_param(mdev, DRBD_MAX_SIZE_H80_PACKET);
-                put_ldev(mdev);
-        }
-
         if (drbd_send_protocol(mdev) == -1)
                 return -1;
         drbd_send_sync_param(mdev, &mdev->sync_conf);
@@ -1418,7 +1413,7 @@ static int e_end_resync_block(struct drbd_conf *mdev, struct drbd_work *w, int u
         sector_t sector = e->sector;
         int ok;
 
-        D_ASSERT(hlist_unhashed(&e->colision));
+        D_ASSERT(hlist_unhashed(&e->collision));
 
         if (likely((e->flags & EE_WAS_ERROR) == 0)) {
                 drbd_set_in_sync(mdev, sector, e->size);
@@ -1487,7 +1482,7 @@ static int receive_DataReply(struct drbd_conf *mdev, enum drbd_packets cmd, unsi
                 return false;
         }
 
-        /* hlist_del(&req->colision) is done in _req_may_be_done, to avoid
+        /* hlist_del(&req->collision) is done in _req_may_be_done, to avoid
          * special casing it there for the various failure cases.
          * still no race with drbd_fail_pending_reads */
         ok = recv_dless_read(mdev, req, sector, data_size);
@@ -1558,11 +1553,11 @@ static int e_end_block(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
          * P_WRITE_ACK / P_NEG_ACK, to get the sequence number right.  */
         if (mdev->net_conf->two_primaries) {
                 spin_lock_irq(&mdev->req_lock);
-                D_ASSERT(!hlist_unhashed(&e->colision));
-                hlist_del_init(&e->colision);
+                D_ASSERT(!hlist_unhashed(&e->collision));
+                hlist_del_init(&e->collision);
                 spin_unlock_irq(&mdev->req_lock);
         } else {
-                D_ASSERT(hlist_unhashed(&e->colision));
+                D_ASSERT(hlist_unhashed(&e->collision));
         }
 
         drbd_may_finish_epoch(mdev, e->epoch, EV_PUT + (cancel ? EV_CLEANUP : 0));
@@ -1579,8 +1574,8 @@ static int e_send_discard_ack(struct drbd_conf *mdev, struct drbd_work *w, int u
         ok = drbd_send_ack(mdev, P_DISCARD_ACK, e);
 
         spin_lock_irq(&mdev->req_lock);
-        D_ASSERT(!hlist_unhashed(&e->colision));
-        hlist_del_init(&e->colision);
+        D_ASSERT(!hlist_unhashed(&e->collision));
+        hlist_del_init(&e->collision);
         spin_unlock_irq(&mdev->req_lock);
 
         dec_unacked(mdev);
@@ -1755,7 +1750,7 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 
                 spin_lock_irq(&mdev->req_lock);
 
-                hlist_add_head(&e->colision, ee_hash_slot(mdev, sector));
+                hlist_add_head(&e->collision, ee_hash_slot(mdev, sector));
 
 #define OVERLAPS overlaps(i->sector, i->size, sector, size)
                 slot = tl_hash_slot(mdev, sector);
@@ -1765,7 +1760,7 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
                         int have_conflict = 0;
                         prepare_to_wait(&mdev->misc_wait, &wait,
                                 TASK_INTERRUPTIBLE);
-                        hlist_for_each_entry(i, n, slot, colision) {
+                        hlist_for_each_entry(i, n, slot, collision) {
                                 if (OVERLAPS) {
                                         /* only ALERT on first iteration,
                                          * we may be woken up early... */
@@ -1804,7 +1799,7 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
                         }
 
                         if (signal_pending(current)) {
-                                hlist_del_init(&e->colision);
+                                hlist_del_init(&e->collision);
 
                                 spin_unlock_irq(&mdev->req_lock);
 
@@ -1862,7 +1857,7 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
         dev_err(DEV, "submit failed, triggering re-connect\n");
         spin_lock_irq(&mdev->req_lock);
         list_del(&e->w.list);
-        hlist_del_init(&e->colision);
+        hlist_del_init(&e->collision);
         spin_unlock_irq(&mdev->req_lock);
         if (e->flags & EE_CALL_AL_COMPLETE_IO)
                 drbd_al_complete_io(mdev, e->sector);
@@ -2916,12 +2911,6 @@ disconnect:
         return false;
 }
 
-static void drbd_setup_order_type(struct drbd_conf *mdev, int peer)
-{
-        /* sorry, we currently have no working implementation
-         * of distributed TCQ */
-}
-
 /* warn if the arguments differ by more than 12.5% */
 static void warn_if_differ_considerably(struct drbd_conf *mdev,
         const char *s, sector_t a, sector_t b)
@@ -2939,7 +2928,6 @@ static int receive_sizes(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 {
         struct p_sizes *p = &mdev->data.rbuf.sizes;
         enum determine_dev_size dd = unchanged;
-        unsigned int max_bio_size;
         sector_t p_size, p_usize, my_usize;
         int ldsc = 0; /* local disk size changed */
         enum dds_flags ddsf;
@@ -2994,7 +2982,7 @@ static int receive_sizes(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 
         ddsf = be16_to_cpu(p->dds_flags);
         if (get_ldev(mdev)) {
-                dd = drbd_determin_dev_size(mdev, ddsf);
+                dd = drbd_determine_dev_size(mdev, ddsf);
                 put_ldev(mdev);
                 if (dd == dev_size_error)
                         return false;
@@ -3004,23 +2992,15 @@ static int receive_sizes(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
                 drbd_set_my_capacity(mdev, p_size);
         }
 
+        mdev->peer_max_bio_size = be32_to_cpu(p->max_bio_size);
+        drbd_reconsider_max_bio_size(mdev);
+
         if (get_ldev(mdev)) {
                 if (mdev->ldev->known_size != drbd_get_capacity(mdev->ldev->backing_bdev)) {
                         mdev->ldev->known_size = drbd_get_capacity(mdev->ldev->backing_bdev);
                         ldsc = 1;
                 }
 
-                if (mdev->agreed_pro_version < 94)
-                        max_bio_size = be32_to_cpu(p->max_bio_size);
-                else if (mdev->agreed_pro_version == 94)
-                        max_bio_size = DRBD_MAX_SIZE_H80_PACKET;
-                else /* drbd 8.3.8 onwards */
-                        max_bio_size = DRBD_MAX_BIO_SIZE;
-
-                if (max_bio_size != queue_max_hw_sectors(mdev->rq_queue) << 9)
-                        drbd_setup_queue_param(mdev, max_bio_size);
-
-                drbd_setup_order_type(mdev, be16_to_cpu(p->queue_order_type));
                 put_ldev(mdev);
         }
 
@@ -4275,7 +4255,7 @@ static struct drbd_request *_ack_id_to_req(struct drbd_conf *mdev,
         struct hlist_node *n;
         struct drbd_request *req;
 
-        hlist_for_each_entry(req, n, slot, colision) {
+        hlist_for_each_entry(req, n, slot, collision) {
                 if ((unsigned long)req == (unsigned long)id) {
                         if (req->sector != sector) {
                                 dev_err(DEV, "_ack_id_to_req: found req %p but it has "
@@ -4554,6 +4534,7 @@ int drbd_asender(struct drbd_thread *thi)
         int received = 0;
         int expect   = sizeof(struct p_header80);
         int empty;
+        int ping_timeout_active = 0;
 
         sprintf(current->comm, "drbd%d_asender", mdev_to_minor(mdev));
 
@@ -4566,6 +4547,7 @@ int drbd_asender(struct drbd_thread *thi)
                         ERR_IF(!drbd_send_ping(mdev)) goto reconnect;
                         mdev->meta.socket->sk->sk_rcvtimeo =
                                 mdev->net_conf->ping_timeo*HZ/10;
+                        ping_timeout_active = 1;
                 }
 
                 /* conditionally cork;
@@ -4620,8 +4602,7 @@ int drbd_asender(struct drbd_thread *thi)
                         dev_err(DEV, "meta connection shut down by peer.\n");
                         goto reconnect;
                 } else if (rv == -EAGAIN) {
-                        if (mdev->meta.socket->sk->sk_rcvtimeo ==
-                            mdev->net_conf->ping_timeo*HZ/10) {
+                        if (ping_timeout_active) {
                                 dev_err(DEV, "PingAck did not arrive in time.\n");
                                 goto reconnect;
                         }
@@ -4660,6 +4641,11 @@ int drbd_asender(struct drbd_thread *thi)
                         if (!cmd->process(mdev, h))
                                 goto reconnect;
 
+                        /* the idle_timeout (ping-int)
+                         * has been restored in got_PingAck() */
+                        if (cmd == get_asender_cmd(P_PING_ACK))
+                                ping_timeout_active = 0;
+
                         buf      = h;
                         received = 0;
                         expect   = sizeof(struct p_header80);
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 5c0c8be1bb0a..3424d675b769 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -163,7 +163,7 @@ static void _about_to_complete_local_write(struct drbd_conf *mdev,
                  * they must have been failed on the spot */
 #define OVERLAPS overlaps(sector, size, i->sector, i->size)
                 slot = tl_hash_slot(mdev, sector);
-                hlist_for_each_entry(i, n, slot, colision) {
+                hlist_for_each_entry(i, n, slot, collision) {
                         if (OVERLAPS) {
                                 dev_alert(DEV, "LOGIC BUG: completed: %p %llus +%u; "
                                       "other: %p %llus +%u\n",
@@ -187,7 +187,7 @@ static void _about_to_complete_local_write(struct drbd_conf *mdev,
 #undef OVERLAPS
 #define OVERLAPS overlaps(sector, size, e->sector, e->size)
                 slot = ee_hash_slot(mdev, req->sector);
-                hlist_for_each_entry(e, n, slot, colision) {
+                hlist_for_each_entry(e, n, slot, collision) {
                         if (OVERLAPS) {
                                 wake_up(&mdev->misc_wait);
                                 break;
@@ -260,8 +260,8 @@ void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m)
 
                 /* remove the request from the conflict detection
                  * respective block_id verification hash */
-                if (!hlist_unhashed(&req->colision))
-                        hlist_del(&req->colision);
+                if (!hlist_unhashed(&req->collision))
+                        hlist_del(&req->collision);
                 else
                         D_ASSERT((s & (RQ_NET_MASK & ~RQ_NET_DONE)) == 0);
 
@@ -329,7 +329,7 @@ static int _req_conflicts(struct drbd_request *req)
         struct hlist_node *n;
         struct hlist_head *slot;
 
-        D_ASSERT(hlist_unhashed(&req->colision));
+        D_ASSERT(hlist_unhashed(&req->collision));
 
         if (!get_net_conf(mdev))
                 return 0;
@@ -341,7 +341,7 @@ static int _req_conflicts(struct drbd_request *req)
 
 #define OVERLAPS overlaps(i->sector, i->size, sector, size)
         slot = tl_hash_slot(mdev, sector);
-        hlist_for_each_entry(i, n, slot, colision) {
+        hlist_for_each_entry(i, n, slot, collision) {
                 if (OVERLAPS) {
                         dev_alert(DEV, "%s[%u] Concurrent local write detected! "
                               "[DISCARD L] new: %llus +%u; "
@@ -359,7 +359,7 @@ static int _req_conflicts(struct drbd_request *req)
 #undef OVERLAPS
 #define OVERLAPS overlaps(e->sector, e->size, sector, size)
                 slot = ee_hash_slot(mdev, sector);
-                hlist_for_each_entry(e, n, slot, colision) {
+                hlist_for_each_entry(e, n, slot, collision) {
                         if (OVERLAPS) {
                                 dev_alert(DEV, "%s[%u] Concurrent remote write detected!"
                                       " [DISCARD L] new: %llus +%u; "
@@ -491,7 +491,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 
                 /* so we can verify the handle in the answer packet
                  * corresponding hlist_del is in _req_may_be_done() */
-                hlist_add_head(&req->colision, ar_hash_slot(mdev, req->sector));
+                hlist_add_head(&req->collision, ar_hash_slot(mdev, req->sector));
 
                 set_bit(UNPLUG_REMOTE, &mdev->flags);
 
@@ -507,7 +507,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
                 /* assert something? */
                 /* from drbd_make_request_common only */
 
-                hlist_add_head(&req->colision, tl_hash_slot(mdev, req->sector));
+                hlist_add_head(&req->collision, tl_hash_slot(mdev, req->sector));
                 /* corresponding hlist_del is in _req_may_be_done() */
 
                 /* NOTE
@@ -1033,7 +1033,7 @@ fail_conflicting:
         err = 0;
 
 fail_free_complete:
-        if (rw == WRITE && local)
+        if (req->rq_state & RQ_IN_ACT_LOG)
                 drbd_al_complete_io(mdev, sector);
 fail_and_free_req:
         if (local) {
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 32e2c3e6a813..68a234a5fdc5 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -256,7 +256,7 @@ static inline struct drbd_request *_ar_id_to_req(struct drbd_conf *mdev,
         struct hlist_node *n;
         struct drbd_request *req;
 
-        hlist_for_each_entry(req, n, slot, colision) {
+        hlist_for_each_entry(req, n, slot, collision) {
                 if ((unsigned long)req == (unsigned long)id) {
                         D_ASSERT(req->sector == sector);
                         return req;
@@ -291,7 +291,7 @@ static inline struct drbd_request *drbd_req_new(struct drbd_conf *mdev,
                 req->epoch       = 0;
                 req->sector      = bio_src->bi_sector;
                 req->size        = bio_src->bi_size;
-                INIT_HLIST_NODE(&req->colision);
+                INIT_HLIST_NODE(&req->collision);
                 INIT_LIST_HEAD(&req->tl_requests);
                 INIT_LIST_HEAD(&req->w.list);
         }
@@ -323,6 +323,7 @@ extern int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 extern void complete_master_bio(struct drbd_conf *mdev,
                 struct bio_and_error *m);
 extern void request_timer_fn(unsigned long data);
+extern void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what);
 
 /* use this if you don't want to deal with calling complete_master_bio()
  * outside the spinlock, e.g. when walking some list on cleanup. */
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index f7e6c92f8d03..4d76b06b6b20 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -126,7 +126,7 @@ static void drbd_endio_write_sec_final(struct drbd_epoch_entry *e) __releases(lo
         list_del(&e->w.list); /* has been on active_ee or sync_ee */
         list_add_tail(&e->w.list, &mdev->done_ee);
 
-        /* No hlist_del_init(&e->colision) here, we did not send the Ack yet,
+        /* No hlist_del_init(&e->collision) here, we did not send the Ack yet,
          * neither did we wake possibly waiting conflicting requests.
          * done from "drbd_process_done_ee" within the appropriate w.cb
          * (e_end_block/e_end_resync_block) or from _drbd_clear_done_ee */
@@ -297,42 +297,48 @@ void drbd_csum_bio(struct drbd_conf *mdev, struct crypto_hash *tfm, struct bio *
         crypto_hash_final(&desc, digest);
 }
 
-static int w_e_send_csum(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
+/* TODO merge common code with w_e_end_ov_req */
+int w_e_send_csum(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 {
         struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w);
         int digest_size;
         void *digest;
-        int ok;
+        int ok = 1;
 
         D_ASSERT(e->block_id == DRBD_MAGIC + 0xbeef);
 
-        if (unlikely(cancel)) {
-                drbd_free_ee(mdev, e);
-                return 1;
-        }
+        if (unlikely(cancel))
+                goto out;
 
-        if (likely((e->flags & EE_WAS_ERROR) == 0)) {
-                digest_size = crypto_hash_digestsize(mdev->csums_tfm);
-                digest = kmalloc(digest_size, GFP_NOIO);
-                if (digest) {
-                        drbd_csum_ee(mdev, mdev->csums_tfm, e, digest);
+        if (likely((e->flags & EE_WAS_ERROR) != 0))
+                goto out;
 
-                        inc_rs_pending(mdev);
-                        ok = drbd_send_drequest_csum(mdev,
-                                                     e->sector,
-                                                     e->size,
-                                                     digest,
-                                                     digest_size,
-                                                     P_CSUM_RS_REQUEST);
-                        kfree(digest);
-                } else {
-                        dev_err(DEV, "kmalloc() of digest failed.\n");
-                        ok = 0;
-                }
-        } else
-                ok = 1;
+        digest_size = crypto_hash_digestsize(mdev->csums_tfm);
+        digest = kmalloc(digest_size, GFP_NOIO);
+        if (digest) {
+                sector_t sector = e->sector;
+                unsigned int size = e->size;
+                drbd_csum_ee(mdev, mdev->csums_tfm, e, digest);
+                /* Free e and pages before send.
+                 * In case we block on congestion, we could otherwise run into
+                 * some distributed deadlock, if the other side blocks on
+                 * congestion as well, because our receiver blocks in
+                 * drbd_pp_alloc due to pp_in_use > max_buffers. */
+                drbd_free_ee(mdev, e);
+                e = NULL;
+                inc_rs_pending(mdev);
+                ok = drbd_send_drequest_csum(mdev, sector, size,
+                                             digest, digest_size,
+                                             P_CSUM_RS_REQUEST);
+                kfree(digest);
+        } else {
+                dev_err(DEV, "kmalloc() of digest failed.\n");
+                ok = 0;
+        }
 
-        drbd_free_ee(mdev, e);
+out:
+        if (e)
+                drbd_free_ee(mdev, e);
 
         if (unlikely(!ok))
                 dev_err(DEV, "drbd_send_drequest(..., csum) failed\n");
@@ -834,7 +840,7 @@ int drbd_resync_finished(struct drbd_conf *mdev)
                         const int ratio =
                                 (t == 0)     ? 0 :
                         (t < 100000) ? ((s*100)/t) : (s/(t/100));
-                        dev_info(DEV, "%u %% had equal check sums, eliminated: %luK; "
+                        dev_info(DEV, "%u %% had equal checksums, eliminated: %luK; "
                              "transferred %luK total %luK\n",
                              ratio,
                              Bit2KB(mdev->rs_same_csum),
@@ -1071,9 +1077,12 @@ int w_e_end_csum_rs_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
         return ok;
 }
 
+/* TODO merge common code with w_e_send_csum */
 int w_e_end_ov_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 {
         struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w);
+        sector_t sector = e->sector;
+        unsigned int size = e->size;
         int digest_size;
         void *digest;
         int ok = 1;
@@ -1093,17 +1102,25 @@ int w_e_end_ov_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
         else
                 memset(digest, 0, digest_size);
 
+        /* Free e and pages before send.
+         * In case we block on congestion, we could otherwise run into
+         * some distributed deadlock, if the other side blocks on
+         * congestion as well, because our receiver blocks in
+         * drbd_pp_alloc due to pp_in_use > max_buffers. */
+        drbd_free_ee(mdev, e);
+        e = NULL;
         inc_rs_pending(mdev);
-        ok = drbd_send_drequest_csum(mdev, e->sector, e->size,
-                                     digest, digest_size, P_OV_REPLY);
+        ok = drbd_send_drequest_csum(mdev, sector, size,
+                                     digest, digest_size,
+                                     P_OV_REPLY);
         if (!ok)
                 dec_rs_pending(mdev);
         kfree(digest);
 
 out:
-        drbd_free_ee(mdev, e);
+        if (e)
+                drbd_free_ee(mdev, e);
         dec_unacked(mdev);
-
         return ok;
 }
 
@@ -1122,8 +1139,10 @@ int w_e_end_ov_reply(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 {
         struct drbd_epoch_entry *e = container_of(w, struct drbd_epoch_entry, w);
         struct digest_info *di;
-        int digest_size;
         void *digest;
+        sector_t sector = e->sector;
+        unsigned int size = e->size;
+        int digest_size;
         int ok, eq = 0;
 
         if (unlikely(cancel)) {
@@ -1153,16 +1172,21 @@ int w_e_end_ov_reply(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
                 }
         }
 
-        dec_unacked(mdev);
+                /* Free e and pages before send.
+                 * In case we block on congestion, we could otherwise run into
+                 * some distributed deadlock, if the other side blocks on
+                 * congestion as well, because our receiver blocks in
+                 * drbd_pp_alloc due to pp_in_use > max_buffers. */
+        drbd_free_ee(mdev, e);
         if (!eq)
-                drbd_ov_oos_found(mdev, e->sector, e->size);
+                drbd_ov_oos_found(mdev, sector, size);
         else
                 ov_oos_print(mdev);
 
-        ok = drbd_send_ack_ex(mdev, P_OV_RESULT, e->sector, e->size,
+        ok = drbd_send_ack_ex(mdev, P_OV_RESULT, sector, size,
                               eq ? ID_IN_SYNC : ID_OUT_OF_SYNC);
 
-        drbd_free_ee(mdev, e);
+        dec_unacked(mdev);
 
         --mdev->ov_left;
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a076a14ca72d..c59a672a3de0 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1658,7 +1658,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
         struct kobject *kobj;
 
         mutex_lock(&loop_devices_mutex);
-        lo = loop_init_one(dev & MINORMASK);
+        lo = loop_init_one(MINOR(dev) >> part_shift);
         kobj = lo ? get_disk(lo->lo_disk) : ERR_PTR(-ENOMEM);
         mutex_unlock(&loop_devices_mutex);
 
@@ -1691,15 +1691,18 @@ static int __init loop_init(void)
         if (max_part > 0)
                 part_shift = fls(max_part);
 
+        if ((1UL << part_shift) > DISK_MAX_PARTS)
+                return -EINVAL;
+
         if (max_loop > 1UL << (MINORBITS - part_shift))
                 return -EINVAL;
 
         if (max_loop) {
                 nr = max_loop;
-                range = max_loop;
+                range = max_loop << part_shift;
         } else {
                 nr = 8;
-                range = 1UL << (MINORBITS - part_shift);
+                range = 1UL << MINORBITS;
         }
 
         if (register_blkdev(LOOP_MAJOR, "loop"))
@@ -1738,7 +1741,7 @@ static void __exit loop_exit(void)
         unsigned long range;
         struct loop_device *lo, *next;
 
-        range = max_loop ? max_loop :  1UL << (MINORBITS - part_shift);
+        range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
         list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
                 loop_del_one(lo);
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 8690e31d9932..a0aabd904a51 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -320,6 +320,8 @@ static void pcd_init_units(void)
                 disk->first_minor = unit;
                 strcpy(disk->disk_name, cd->name);      /* umm... */
                 disk->fops = &pcd_bdops;
+                disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+                disk->events = DISK_EVENT_MEDIA_CHANGE;
         }
 }
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 9712fad82bc6..1278098624e6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1191,14 +1191,19 @@ static int rbd_req_sync_notify_ack(struct rbd_device *dev,
 static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 {
         struct rbd_device *dev = (struct rbd_device *)data;
+        int rc;
+
         if (!dev)
                 return;
 
         dout("rbd_watch_cb %s notify_id=%lld opcode=%d\n", dev->obj_md_name,
                 notify_id, (int)opcode);
         mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-        __rbd_update_snaps(dev);
+        rc = __rbd_update_snaps(dev);
         mutex_unlock(&ctl_mutex);
+        if (rc)
+                pr_warning(DRV_NAME "%d got notification but failed to update"
+                           " snaps: %d\n", dev->major, rc);
 
         rbd_req_sync_notify_ack(dev, ver, notify_id, dev->obj_md_name);
 }
@@ -1597,7 +1602,7 @@ static int rbd_header_add_snap(struct rbd_device *dev,
         int name_len = strlen(snap_name);
         u64 new_snapid;
         int ret;
-        void *data, *data_start, *data_end;
+        void *data, *p, *e;
         u64 ver;
 
         /* we should create a snapshot only if we're pointing at the head */
@@ -1614,16 +1619,16 @@ static int rbd_header_add_snap(struct rbd_device *dev,
         if (!data)
                 return -ENOMEM;
 
-        data_start = data;
-        data_end = data + name_len + 16;
+        p = data;
+        e = 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);
+        ceph_encode_string_safe(&p, e, snap_name, name_len, bad);
+        ceph_encode_64_safe(&p, e, new_snapid, bad);
 
         ret = rbd_req_sync_exec(dev, dev->obj_md_name, "rbd", "snap_add",
-                                data_start, data - data_start, &ver);
+                                data, p - data, &ver);
 
-        kfree(data_start);
+        kfree(data);
 
         if (ret < 0)
                 return ret;
@@ -1659,6 +1664,9 @@ static int __rbd_update_snaps(struct rbd_device *rbd_dev)
         if (ret < 0)
                 return ret;
 
+        /* resized? */
+        set_capacity(rbd_dev->disk, h.image_size / 512ULL);
+
         down_write(&rbd_dev->header.snap_rwsem);
 
         snap_seq = rbd_dev->header.snapc->seq;
@@ -1716,7 +1724,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
         if (!disk)
                 goto out;
 
-        sprintf(disk->disk_name, DRV_NAME "%d", rbd_dev->id);
+        snprintf(disk->disk_name, sizeof(disk->disk_name), DRV_NAME "%d",
+                 rbd_dev->id);
         disk->major = rbd_dev->major;
         disk->first_minor = 0;
         disk->fops = &rbd_bd_ops;
diff --git a/drivers/block/xen-blkback/Makefile b/drivers/block/xen-blkback/Makefile
new file mode 100644
index 000000000000..e491c1b76878
--- /dev/null
+++ b/drivers/block/xen-blkback/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_XEN_BLKDEV_BACKEND) := xen-blkback.o
+
+xen-blkback-y   := blkback.o xenbus.o
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
new file mode 100644
index 000000000000..c73910cc28c9
--- /dev/null
+++ b/drivers/block/xen-blkback/blkback.c
@@ -0,0 +1,824 @@
+/******************************************************************************
+ *
+ * Back-end of the driver for virtual block devices. This portion of the
+ * driver exports a 'unified' block-device interface that can be accessed
+ * by any operating system that implements a compatible front end. A
+ * reference front-end implementation can be found in:
+ *  drivers/block/xen-blkfront.c
+ *
+ * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
+ * Copyright (c) 2005, Christopher Clark
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/list.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+
+#include <xen/events.h>
+#include <xen/page.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include "common.h"
+
+/*
+ * These are rather arbitrary. They are fairly large because adjacent requests
+ * pulled from a communication ring are quite likely to end up being part of
+ * the same scatter/gather request at the disc.
+ *
+ * ** TRY INCREASING 'xen_blkif_reqs' IF WRITE SPEEDS SEEM TOO LOW **
+ *
+ * This will increase the chances of being able to write whole tracks.
+ * 64 should be enough to keep us competitive with Linux.
+ */
+static int xen_blkif_reqs = 64;
+module_param_named(reqs, xen_blkif_reqs, int, 0);
+MODULE_PARM_DESC(reqs, "Number of blkback requests to allocate");
+
+/* Run-time switchable: /sys/module/blkback/parameters/ */
+static unsigned int log_stats;
+module_param(log_stats, int, 0644);
+
+/*
+ * Each outstanding request that we've passed to the lower device layers has a
+ * 'pending_req' allocated to it. Each buffer_head that completes decrements
+ * the pendcnt towards zero. When it hits zero, the specified domain has a
+ * response queued for it, with the saved 'id' passed back.
+ */
+struct pending_req {
+        struct xen_blkif        *blkif;
+        u64                     id;
+        int                     nr_pages;
+        atomic_t                pendcnt;
+        unsigned short          operation;
+        int                     status;
+        struct list_head        free_list;
+};
+
+#define BLKBACK_INVALID_HANDLE (~0)
+
+struct xen_blkbk {
+        struct pending_req      *pending_reqs;
+        /* List of all 'pending_req' available */
+        struct list_head        pending_free;
+        /* And its spinlock. */
+        spinlock_t              pending_free_lock;
+        wait_queue_head_t       pending_free_wq;
+        /* The list of all pages that are available. */
+        struct page             **pending_pages;
+        /* And the grant handles that are available. */
+        grant_handle_t          *pending_grant_handles;
+};
+
+static struct xen_blkbk *blkbk;
+
+/*
+ * Little helpful macro to figure out the index and virtual address of the
+ * pending_pages[..]. For each 'pending_req' we have have up to
+ * BLKIF_MAX_SEGMENTS_PER_REQUEST (11) pages. The seg would be from 0 through
+ * 10 and would index in the pending_pages[..].
+ */
+static inline int vaddr_pagenr(struct pending_req *req, int seg)
+{
+        return (req - blkbk->pending_reqs) *
+                BLKIF_MAX_SEGMENTS_PER_REQUEST + seg;
+}
+
+#define pending_page(req, seg) pending_pages[vaddr_pagenr(req, seg)]
+
+static inline unsigned long vaddr(struct pending_req *req, int seg)
+{
+        unsigned long pfn = page_to_pfn(blkbk->pending_page(req, seg));
+        return (unsigned long)pfn_to_kaddr(pfn);
+}
+
+#define pending_handle(_req, _seg) \
+        (blkbk->pending_grant_handles[vaddr_pagenr(_req, _seg)])
+
+
+static int do_block_io_op(struct xen_blkif *blkif);
+static int dispatch_rw_block_io(struct xen_blkif *blkif,
+                                struct blkif_request *req,
+                                struct pending_req *pending_req);
+static void make_response(struct xen_blkif *blkif, u64 id,
+                          unsigned short op, int st);
+
+/*
+ * Retrieve from the 'pending_reqs' a free pending_req structure to be used.
+ */
+static struct pending_req *alloc_req(void)
+{
+        struct pending_req *req = NULL;
+        unsigned long flags;
+
+        spin_lock_irqsave(&blkbk->pending_free_lock, flags);
+        if (!list_empty(&blkbk->pending_free)) {
+                req = list_entry(blkbk->pending_free.next, struct pending_req,
+                                 free_list);
+                list_del(&req->free_list);
+        }
+        spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
+        return req;
+}
+
+/*
+ * Return the 'pending_req' structure back to the freepool. We also
+ * wake up the thread if it was waiting for a free page.
+ */
+static void free_req(struct pending_req *req)
+{
+        unsigned long flags;
+        int was_empty;
+
+        spin_lock_irqsave(&blkbk->pending_free_lock, flags);
+        was_empty = list_empty(&blkbk->pending_free);
+        list_add(&req->free_list, &blkbk->pending_free);
+        spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
+        if (was_empty)
+                wake_up(&blkbk->pending_free_wq);
+}
+
+/*
+ * Routines for managing virtual block devices (vbds).
+ */
+static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif,
+                             int operation)
+{
+        struct xen_vbd *vbd = &blkif->vbd;
+        int rc = -EACCES;
+
+        if ((operation != READ) && vbd->readonly)
+                goto out;
+
+        if (likely(req->nr_sects)) {
+                blkif_sector_t end = req->sector_number + req->nr_sects;
+
+                if (unlikely(end < req->sector_number))
+                        goto out;
+                if (unlikely(end > vbd_sz(vbd)))
+                        goto out;
+        }
+
+        req->dev  = vbd->pdevice;
+        req->bdev = vbd->bdev;
+        rc = 0;
+
+ out:
+        return rc;
+}
+
+static void xen_vbd_resize(struct xen_blkif *blkif)
+{
+        struct xen_vbd *vbd = &blkif->vbd;
+        struct xenbus_transaction xbt;
+        int err;
+        struct xenbus_device *dev = xen_blkbk_xenbus(blkif->be);
+        unsigned long long new_size = vbd_sz(vbd);
+
+        pr_info(DRV_PFX "VBD Resize: Domid: %d, Device: (%d, %d)\n",
+                blkif->domid, MAJOR(vbd->pdevice), MINOR(vbd->pdevice));
+        pr_info(DRV_PFX "VBD Resize: new size %llu\n", new_size);
+        vbd->size = new_size;
+again:
+        err = xenbus_transaction_start(&xbt);
+        if (err) {
+                pr_warn(DRV_PFX "Error starting transaction");
+                return;
+        }
+        err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",
+                            (unsigned long long)vbd_sz(vbd));
+        if (err) {
+                pr_warn(DRV_PFX "Error writing new size");
+                goto abort;
+        }
+        /*
+         * Write the current state; we will use this to synchronize
+         * the front-end. If the current state is "connected" the
+         * front-end will get the new size information online.
+         */
+        err = xenbus_printf(xbt, dev->nodename, "state", "%d", dev->state);
+        if (err) {
+                pr_warn(DRV_PFX "Error writing the state");
+                goto abort;
+        }
+
+        err = xenbus_transaction_end(xbt, 0);
+        if (err == -EAGAIN)
+                goto again;
+        if (err)
+                pr_warn(DRV_PFX "Error ending transaction");
+        return;
+abort:
+        xenbus_transaction_end(xbt, 1);
+}
+
+/*
+ * Notification from the guest OS.
+ */
+static void blkif_notify_work(struct xen_blkif *blkif)
+{
+        blkif->waiting_reqs = 1;
+        wake_up(&blkif->wq);
+}
+
+irqreturn_t xen_blkif_be_int(int irq, void *dev_id)
+{
+        blkif_notify_work(dev_id);
+        return IRQ_HANDLED;
+}
+
+/*
+ * SCHEDULER FUNCTIONS
+ */
+
+static void print_stats(struct xen_blkif *blkif)
+{
+        pr_info("xen-blkback (%s): oo %3d  |  rd %4d  |  wr %4d  |  f %4d\n",
+                 current->comm, blkif->st_oo_req,
+                 blkif->st_rd_req, blkif->st_wr_req, blkif->st_f_req);
+        blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000);
+        blkif->st_rd_req = 0;
+        blkif->st_wr_req = 0;
+        blkif->st_oo_req = 0;
+}
+
+int xen_blkif_schedule(void *arg)
+{
+        struct xen_blkif *blkif = arg;
+        struct xen_vbd *vbd = &blkif->vbd;
+
+        xen_blkif_get(blkif);
+
+        while (!kthread_should_stop()) {
+                if (try_to_freeze())
+                        continue;
+                if (unlikely(vbd->size != vbd_sz(vbd)))
+                        xen_vbd_resize(blkif);
+
+                wait_event_interruptible(
+                        blkif->wq,
+                        blkif->waiting_reqs || kthread_should_stop());
+                wait_event_interruptible(
+                        blkbk->pending_free_wq,
+                        !list_empty(&blkbk->pending_free) ||
+                        kthread_should_stop());
+
+                blkif->waiting_reqs = 0;
+                smp_mb(); /* clear flag *before* checking for work */
+
+                if (do_block_io_op(blkif))
+                        blkif->waiting_reqs = 1;
+
+                if (log_stats && time_after(jiffies, blkif->st_print))
+                        print_stats(blkif);
+        }
+
+        if (log_stats)
+                print_stats(blkif);
+
+        blkif->xenblkd = NULL;
+        xen_blkif_put(blkif);
+
+        return 0;
+}
+
+struct seg_buf {
+        unsigned long buf;
+        unsigned int nsec;
+};
+/*
+ * Unmap the grant references, and also remove the M2P over-rides
+ * used in the 'pending_req'.
+ */
+static void xen_blkbk_unmap(struct pending_req *req)
+{
+        struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+        unsigned int i, invcount = 0;
+        grant_handle_t handle;
+        int ret;
+
+        for (i = 0; i < req->nr_pages; i++) {
+                handle = pending_handle(req, i);
+                if (handle == BLKBACK_INVALID_HANDLE)
+                        continue;
+                gnttab_set_unmap_op(&unmap[invcount], vaddr(req, i),
+                                    GNTMAP_host_map, handle);
+                pending_handle(req, i) = BLKBACK_INVALID_HANDLE;
+                invcount++;
+        }
+
+        ret = HYPERVISOR_grant_table_op(
+                GNTTABOP_unmap_grant_ref, unmap, invcount);
+        BUG_ON(ret);
+        /*
+         * Note, we use invcount, so nr->pages, so we can't index
+         * using vaddr(req, i).
+         */
+        for (i = 0; i < invcount; i++) {
+                ret = m2p_remove_override(
+                        virt_to_page(unmap[i].host_addr), false);
+                if (ret) {
+                        pr_alert(DRV_PFX "Failed to remove M2P override for %lx\n",
+                                 (unsigned long)unmap[i].host_addr);
+                        continue;
+                }
+        }
+}
+
+static int xen_blkbk_map(struct blkif_request *req,
+                         struct pending_req *pending_req,
+                         struct seg_buf seg[])
+{
+        struct gnttab_map_grant_ref map[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+        int i;
+        int nseg = req->nr_segments;
+        int ret = 0;
+
+        /*
+         * Fill out preq.nr_sects with proper amount of sectors, and setup
+         * assign map[..] with the PFN of the page in our domain with the
+         * corresponding grant reference for each page.
+         */
+        for (i = 0; i < nseg; i++) {
+                uint32_t flags;
+
+                flags = GNTMAP_host_map;
+                if (pending_req->operation != BLKIF_OP_READ)
+                        flags |= GNTMAP_readonly;
+                gnttab_set_map_op(&map[i], vaddr(pending_req, i), flags,
+                                  req->u.rw.seg[i].gref,
+                                  pending_req->blkif->domid);
+        }
+
+        ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map, nseg);
+        BUG_ON(ret);
+
+        /*
+         * Now swizzle the MFN in our domain with the MFN from the other domain
+         * so that when we access vaddr(pending_req,i) it has the contents of
+         * the page from the other domain.
+         */
+        for (i = 0; i < nseg; i++) {
+                if (unlikely(map[i].status != 0)) {
+                        pr_debug(DRV_PFX "invalid buffer -- could not remap it\n");
+                        map[i].handle = BLKBACK_INVALID_HANDLE;
+                        ret |= 1;
+                }
+
+                pending_handle(pending_req, i) = map[i].handle;
+
+                if (ret)
+                        continue;
+
+                ret = m2p_add_override(PFN_DOWN(map[i].dev_bus_addr),
+                        blkbk->pending_page(pending_req, i), false);
+                if (ret) {
+                        pr_alert(DRV_PFX "Failed to install M2P override for %lx (ret: %d)\n",
+                                 (unsigned long)map[i].dev_bus_addr, ret);
+                        /* We could switch over to GNTTABOP_copy */
+                        continue;
+                }
+
+                seg[i].buf  = map[i].dev_bus_addr |
+                        (req->u.rw.seg[i].first_sect << 9);
+        }
+        return ret;
+}
+
+/*
+ * Completion callback on the bio's. Called as bh->b_end_io()
+ */
+
+static void __end_block_io_op(struct pending_req *pending_req, int error)
+{
+        /* An error fails the entire request. */
+        if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) &&
+            (error == -EOPNOTSUPP)) {
+                pr_debug(DRV_PFX "flush diskcache op failed, not supported\n");
+                xen_blkbk_flush_diskcache(XBT_NIL, pending_req->blkif->be, 0);
+                pending_req->status = BLKIF_RSP_EOPNOTSUPP;
+        } else if (error) {
+                pr_debug(DRV_PFX "Buffer not up-to-date at end of operation,"
+                         " error=%d\n", error);
+                pending_req->status = BLKIF_RSP_ERROR;
+        }
+
+        /*
+         * If all of the bio's have completed it is time to unmap
+         * the grant references associated with 'request' and provide
+         * the proper response on the ring.
+         */
+        if (atomic_dec_and_test(&pending_req->pendcnt)) {
+                xen_blkbk_unmap(pending_req);
+                make_response(pending_req->blkif, pending_req->id,
+                              pending_req->operation, pending_req->status);
+                xen_blkif_put(pending_req->blkif);
+                free_req(pending_req);
+        }
+}
+
+/*
+ * bio callback.
+ */
+static void end_block_io_op(struct bio *bio, int error)
+{
+        __end_block_io_op(bio->bi_private, error);
+        bio_put(bio);
+}
+
+
+
+/*
+ * Function to copy the from the ring buffer the 'struct blkif_request'
+ * (which has the sectors we want, number of them, grant references, etc),
+ * and transmute  it to the block API to hand it over to the proper block disk.
+ */
+static int do_block_io_op(struct xen_blkif *blkif)
+{
+        union blkif_back_rings *blk_rings = &blkif->blk_rings;
+        struct blkif_request req;
+        struct pending_req *pending_req;
+        RING_IDX rc, rp;
+        int more_to_do = 0;
+
+        rc = blk_rings->common.req_cons;
+        rp = blk_rings->common.sring->req_prod;
+        rmb(); /* Ensure we see queued requests up to 'rp'. */
+
+        while (rc != rp) {
+
+                if (RING_REQUEST_CONS_OVERFLOW(&blk_rings->common, rc))
+                        break;
+
+                if (kthread_should_stop()) {
+                        more_to_do = 1;
+                        break;
+                }
+
+                pending_req = alloc_req();
+                if (NULL == pending_req) {
+                        blkif->st_oo_req++;
+                        more_to_do = 1;
+                        break;
+                }
+
+                switch (blkif->blk_protocol) {
+                case BLKIF_PROTOCOL_NATIVE:
+                        memcpy(&req, RING_GET_REQUEST(&blk_rings->native, rc), sizeof(req));
+                        break;
+                case BLKIF_PROTOCOL_X86_32:
+                        blkif_get_x86_32_req(&req, RING_GET_REQUEST(&blk_rings->x86_32, rc));
+                        break;
+                case BLKIF_PROTOCOL_X86_64:
+                        blkif_get_x86_64_req(&req, RING_GET_REQUEST(&blk_rings->x86_64, rc));
+                        break;
+                default:
+                        BUG();
+                }
+                blk_rings->common.req_cons = ++rc; /* before make_response() */
+
+                /* Apply all sanity checks to /private copy/ of request. */
+                barrier();
+
+                if (dispatch_rw_block_io(blkif, &req, pending_req))
+                        break;
+
+                /* Yield point for this unbounded loop. */
+                cond_resched();
+        }
+
+        return more_to_do;
+}
+
+/*
+ * Transmutation of the 'struct blkif_request' to a proper 'struct bio'
+ * and call the 'submit_bio' to pass it to the underlying storage.
+ */
+static int dispatch_rw_block_io(struct xen_blkif *blkif,
+                                struct blkif_request *req,
+                                struct pending_req *pending_req)
+{
+        struct phys_req preq;
+        struct seg_buf seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+        unsigned int nseg;
+        struct bio *bio = NULL;
+        struct bio *biolist[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+        int i, nbio = 0;
+        int operation;
+        struct blk_plug plug;
+
+        switch (req->operation) {
+        case BLKIF_OP_READ:
+                blkif->st_rd_req++;
+                operation = READ;
+                break;
+        case BLKIF_OP_WRITE:
+                blkif->st_wr_req++;
+                operation = WRITE_ODIRECT;
+                break;
+        case BLKIF_OP_FLUSH_DISKCACHE:
+                blkif->st_f_req++;
+                operation = WRITE_FLUSH;
+                break;
+        case BLKIF_OP_WRITE_BARRIER:
+        default:
+                operation = 0; /* make gcc happy */
+                goto fail_response;
+                break;
+        }
+
+        /* Check that the number of segments is sane. */
+        nseg = req->nr_segments;
+        if (unlikely(nseg == 0 && operation != WRITE_FLUSH) ||
+            unlikely(nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+                pr_debug(DRV_PFX "Bad number of segments in request (%d)\n",
+                         nseg);
+                /* Haven't submitted any bio's yet. */
+                goto fail_response;
+        }
+
+        preq.dev           = req->handle;
+        preq.sector_number = req->u.rw.sector_number;
+        preq.nr_sects      = 0;
+
+        pending_req->blkif     = blkif;
+        pending_req->id        = req->id;
+        pending_req->operation = req->operation;
+        pending_req->status    = BLKIF_RSP_OKAY;
+        pending_req->nr_pages  = nseg;
+
+        for (i = 0; i < nseg; i++) {
+                seg[i].nsec = req->u.rw.seg[i].last_sect -
+                        req->u.rw.seg[i].first_sect + 1;
+                if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
+                    (req->u.rw.seg[i].last_sect < req->u.rw.seg[i].first_sect))
+                        goto fail_response;
+                preq.nr_sects += seg[i].nsec;
+
+        }
+
+        if (xen_vbd_translate(&preq, blkif, operation) != 0) {
+                pr_debug(DRV_PFX "access denied: %s of [%llu,%llu] on dev=%04x\n",
+                         operation == READ ? "read" : "write",
+                         preq.sector_number,
+                         preq.sector_number + preq.nr_sects, preq.dev);
+                goto fail_response;
+        }
+
+        /*
+         * This check _MUST_ be done after xen_vbd_translate as the preq.bdev
+         * is set there.
+         */
+        for (i = 0; i < nseg; i++) {
+                if (((int)preq.sector_number|(int)seg[i].nsec) &
+                    ((bdev_logical_block_size(preq.bdev) >> 9) - 1)) {
+                        pr_debug(DRV_PFX "Misaligned I/O request from domain %d",
+                                 blkif->domid);
+                        goto fail_response;
+                }
+        }
+
+        /*
+         * If we have failed at this point, we need to undo the M2P override,
+         * set gnttab_set_unmap_op on all of the grant references and perform
+         * the hypercall to unmap the grants - that is all done in
+         * xen_blkbk_unmap.
+         */
+        if (xen_blkbk_map(req, pending_req, seg))
+                goto fail_flush;
+
+        /* This corresponding xen_blkif_put is done in __end_block_io_op */
+        xen_blkif_get(blkif);
+
+        for (i = 0; i < nseg; i++) {
+                while ((bio == NULL) ||
+                       (bio_add_page(bio,
+                                     blkbk->pending_page(pending_req, i),
+                                     seg[i].nsec << 9,
+                                     seg[i].buf & ~PAGE_MASK) == 0)) {
+
+                        bio = bio_alloc(GFP_KERNEL, nseg-i);
+                        if (unlikely(bio == NULL))
+                                goto fail_put_bio;
+
+                        biolist[nbio++] = bio;
+                        bio->bi_bdev    = preq.bdev;
+                        bio->bi_private = pending_req;
+                        bio->bi_end_io  = end_block_io_op;
+                        bio->bi_sector  = preq.sector_number;
+                }
+
+                preq.sector_number += seg[i].nsec;
+        }
+
+        /* This will be hit if the operation was a flush. */
+        if (!bio) {
+                BUG_ON(operation != WRITE_FLUSH);
+
+                bio = bio_alloc(GFP_KERNEL, 0);
+                if (unlikely(bio == NULL))
+                        goto fail_put_bio;
+
+                biolist[nbio++] = bio;
+                bio->bi_bdev    = preq.bdev;
+                bio->bi_private = pending_req;
+                bio->bi_end_io  = end_block_io_op;
+        }
+
+        /*
+         * We set it one so that the last submit_bio does not have to call
+         * atomic_inc.
+         */
+        atomic_set(&pending_req->pendcnt, nbio);
+
+        /* Get a reference count for the disk queue and start sending I/O */
+        blk_start_plug(&plug);
+
+        for (i = 0; i < nbio; i++)
+                submit_bio(operation, biolist[i]);
+
+        /* Let the I/Os go.. */
+        blk_finish_plug(&plug);
+
+        if (operation == READ)
+                blkif->st_rd_sect += preq.nr_sects;
+        else if (operation == WRITE || operation == WRITE_FLUSH)
+                blkif->st_wr_sect += preq.nr_sects;
+
+        return 0;
+
+ fail_flush:
+        xen_blkbk_unmap(pending_req);
+ fail_response:
+        /* Haven't submitted any bio's yet. */
+        make_response(blkif, req->id, req->operation, BLKIF_RSP_ERROR);
+        free_req(pending_req);
+        msleep(1); /* back off a bit */
+        return -EIO;
+
+ fail_put_bio:
+        for (i = 0; i < nbio; i++)
+                bio_put(biolist[i]);
+        __end_block_io_op(pending_req, -EINVAL);
+        msleep(1); /* back off a bit */
+        return -EIO;
+}
+
+
+
+/*
+ * Put a response on the ring on how the operation fared.
+ */
+static void make_response(struct xen_blkif *blkif, u64 id,
+                          unsigned short op, int st)
+{
+        struct blkif_response  resp;
+        unsigned long     flags;
+        union blkif_back_rings *blk_rings = &blkif->blk_rings;
+        int more_to_do = 0;
+        int notify;
+
+        resp.id        = id;
+        resp.operation = op;
+        resp.status    = st;
+
+        spin_lock_irqsave(&blkif->blk_ring_lock, flags);
+        /* Place on the response ring for the relevant domain. */
+        switch (blkif->blk_protocol) {
+        case BLKIF_PROTOCOL_NATIVE:
+                memcpy(RING_GET_RESPONSE(&blk_rings->native, blk_rings->native.rsp_prod_pvt),
+                       &resp, sizeof(resp));
+                break;
+        case BLKIF_PROTOCOL_X86_32:
+                memcpy(RING_GET_RESPONSE(&blk_rings->x86_32, blk_rings->x86_32.rsp_prod_pvt),
+                       &resp, sizeof(resp));
+                break;
+        case BLKIF_PROTOCOL_X86_64:
+                memcpy(RING_GET_RESPONSE(&blk_rings->x86_64, blk_rings->x86_64.rsp_prod_pvt),
+                       &resp, sizeof(resp));
+                break;
+        default:
+                BUG();
+        }
+        blk_rings->common.rsp_prod_pvt++;
+        RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&blk_rings->common, notify);
+        if (blk_rings->common.rsp_prod_pvt == blk_rings->common.req_cons) {
+                /*
+                 * Tail check for pending requests. Allows frontend to avoid
+                 * notifications if requests are already in flight (lower
+                 * overheads and promotes batching).
+                 */
+                RING_FINAL_CHECK_FOR_REQUESTS(&blk_rings->common, more_to_do);
+
+        } else if (RING_HAS_UNCONSUMED_REQUESTS(&blk_rings->common)) {
+                more_to_do = 1;
+        }
+
+        spin_unlock_irqrestore(&blkif->blk_ring_lock, flags);
+
+        if (more_to_do)
+                blkif_notify_work(blkif);
+        if (notify)
+                notify_remote_via_irq(blkif->irq);
+}
+
+static int __init xen_blkif_init(void)
+{
+        int i, mmap_pages;
+        int rc = 0;
+
+        if (!xen_pv_domain())
+                return -ENODEV;
+
+        blkbk = kzalloc(sizeof(struct xen_blkbk), GFP_KERNEL);
+        if (!blkbk) {
+                pr_alert(DRV_PFX "%s: out of memory!\n", __func__);
+                return -ENOMEM;
+        }
+
+        mmap_pages = xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+        blkbk->pending_reqs          = kmalloc(sizeof(blkbk->pending_reqs[0]) *
+                                        xen_blkif_reqs, GFP_KERNEL);
+        blkbk->pending_grant_handles = kzalloc(sizeof(blkbk->pending_grant_handles[0]) *
+                                        mmap_pages, GFP_KERNEL);
+        blkbk->pending_pages         = kzalloc(sizeof(blkbk->pending_pages[0]) *
+                                        mmap_pages, GFP_KERNEL);
+
+        if (!blkbk->pending_reqs || !blkbk->pending_grant_handles ||
+            !blkbk->pending_pages) {
+                rc = -ENOMEM;
+                goto out_of_memory;
+        }
+
+        for (i = 0; i < mmap_pages; i++) {
+                blkbk->pending_grant_handles[i] = BLKBACK_INVALID_HANDLE;
+                blkbk->pending_pages[i] = alloc_page(GFP_KERNEL);
+                if (blkbk->pending_pages[i] == NULL) {
+                        rc = -ENOMEM;
+                        goto out_of_memory;
+                }
+        }
+        rc = xen_blkif_interface_init();
+        if (rc)
+                goto failed_init;
+
+        memset(blkbk->pending_reqs, 0, sizeof(blkbk->pending_reqs));
+
+        INIT_LIST_HEAD(&blkbk->pending_free);
+        spin_lock_init(&blkbk->pending_free_lock);
+        init_waitqueue_head(&blkbk->pending_free_wq);
+
+        for (i = 0; i < xen_blkif_reqs; i++)
+                list_add_tail(&blkbk->pending_reqs[i].free_list,
+                              &blkbk->pending_free);
+
+        rc = xen_blkif_xenbus_init();
+        if (rc)
+                goto failed_init;
+
+        return 0;
+
+ out_of_memory:
+        pr_alert(DRV_PFX "%s: out of memory\n", __func__);
+ failed_init:
+        kfree(blkbk->pending_reqs);
+        kfree(blkbk->pending_grant_handles);
+        for (i = 0; i < mmap_pages; i++) {
+                if (blkbk->pending_pages[i])
+                        __free_page(blkbk->pending_pages[i]);
+        }
+        kfree(blkbk->pending_pages);
+        kfree(blkbk);
+        blkbk = NULL;
+        return rc;
+}
+
+module_init(xen_blkif_init);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
new file mode 100644
index 000000000000..9e40b283a468
--- /dev/null
+++ b/drivers/block/xen-blkback/common.h
@@ -0,0 +1,233 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __XEN_BLKIF__BACKEND__COMMON_H__
+#define __XEN_BLKIF__BACKEND__COMMON_H__
+
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+#include <linux/wait.h>
+#include <linux/io.h>
+#include <asm/setup.h>
+#include <asm/pgalloc.h>
+#include <asm/hypervisor.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/ring.h>
+#include <xen/interface/io/blkif.h>
+#include <xen/interface/io/protocols.h>
+
+#define DRV_PFX "xen-blkback:"
+#define DPRINTK(fmt, args...)                           \
+        pr_debug(DRV_PFX "(%s:%d) " fmt ".\n",  \
+                 __func__, __LINE__, ##args)
+
+
+/* Not a real protocol.  Used to generate ring structs which contain
+ * the elements common to all protocols only.  This way we get a
+ * compiler-checkable way to use common struct elements, so we can
+ * avoid using switch(protocol) in a number of places.  */
+struct blkif_common_request {
+        char dummy;
+};
+struct blkif_common_response {
+        char dummy;
+};
+
+/* i386 protocol version */
+#pragma pack(push, 4)
+struct blkif_x86_32_request {
+        uint8_t        operation;    /* BLKIF_OP_???                         */
+        uint8_t        nr_segments;  /* number of segments                   */
+        blkif_vdev_t   handle;       /* only for read/write requests         */
+        uint64_t       id;           /* private guest value, echoed in resp  */
+        blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
+        struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+};
+struct blkif_x86_32_response {
+        uint64_t        id;              /* copied from request */
+        uint8_t         operation;       /* copied from request */
+        int16_t         status;          /* BLKIF_RSP_???       */
+};
+#pragma pack(pop)
+
+/* x86_64 protocol version */
+struct blkif_x86_64_request {
+        uint8_t        operation;    /* BLKIF_OP_???                         */
+        uint8_t        nr_segments;  /* number of segments                   */
+        blkif_vdev_t   handle;       /* only for read/write requests         */
+        uint64_t       __attribute__((__aligned__(8))) id;
+        blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
+        struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+};
+struct blkif_x86_64_response {
+        uint64_t       __attribute__((__aligned__(8))) id;
+        uint8_t         operation;       /* copied from request */
+        int16_t         status;          /* BLKIF_RSP_???       */
+};
+
+DEFINE_RING_TYPES(blkif_common, struct blkif_common_request,
+                  struct blkif_common_response);
+DEFINE_RING_TYPES(blkif_x86_32, struct blkif_x86_32_request,
+                  struct blkif_x86_32_response);
+DEFINE_RING_TYPES(blkif_x86_64, struct blkif_x86_64_request,
+                  struct blkif_x86_64_response);
+
+union blkif_back_rings {
+        struct blkif_back_ring        native;
+        struct blkif_common_back_ring common;
+        struct blkif_x86_32_back_ring x86_32;
+        struct blkif_x86_64_back_ring x86_64;
+};
+
+enum blkif_protocol {
+        BLKIF_PROTOCOL_NATIVE = 1,
+        BLKIF_PROTOCOL_X86_32 = 2,
+        BLKIF_PROTOCOL_X86_64 = 3,
+};
+
+struct xen_vbd {
+        /* What the domain refers to this vbd as. */
+        blkif_vdev_t            handle;
+        /* Non-zero -> read-only */
+        unsigned char           readonly;
+        /* VDISK_xxx */
+        unsigned char           type;
+        /* phys device that this vbd maps to. */
+        u32                     pdevice;
+        struct block_device     *bdev;
+        /* Cached size parameter. */
+        sector_t                size;
+        bool                    flush_support;
+};
+
+struct backend_info;
+
+struct xen_blkif {
+        /* Unique identifier for this interface. */
+        domid_t                 domid;
+        unsigned int            handle;
+        /* Physical parameters of the comms window. */
+        unsigned int            irq;
+        /* Comms information. */
+        enum blkif_protocol     blk_protocol;
+        union blkif_back_rings  blk_rings;
+        struct vm_struct        *blk_ring_area;
+        /* The VBD attached to this interface. */
+        struct xen_vbd          vbd;
+        /* Back pointer to the backend_info. */
+        struct backend_info     *be;
+        /* Private fields. */
+        spinlock_t              blk_ring_lock;
+        atomic_t                refcnt;
+
+        wait_queue_head_t       wq;
+        /* One thread per one blkif. */
+        struct task_struct      *xenblkd;
+        unsigned int            waiting_reqs;
+
+        /* statistics */
+        unsigned long           st_print;
+        int                     st_rd_req;
+        int                     st_wr_req;
+        int                     st_oo_req;
+        int                     st_f_req;
+        int                     st_rd_sect;
+        int                     st_wr_sect;
+
+        wait_queue_head_t       waiting_to_free;
+
+        grant_handle_t          shmem_handle;
+        grant_ref_t             shmem_ref;
+};
+
+
+#define vbd_sz(_v)      ((_v)->bdev->bd_part ? \
+                         (_v)->bdev->bd_part->nr_sects : \
+                          get_capacity((_v)->bdev->bd_disk))
+
+#define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt))
+#define xen_blkif_put(_b)                               \
+        do {                                            \
+                if (atomic_dec_and_test(&(_b)->refcnt)) \
+                        wake_up(&(_b)->waiting_to_free);\
+        } while (0)
+
+struct phys_req {
+        unsigned short          dev;
+        unsigned short          nr_sects;
+        struct block_device     *bdev;
+        blkif_sector_t          sector_number;
+};
+int xen_blkif_interface_init(void);
+
+int xen_blkif_xenbus_init(void);
+
+irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
+int xen_blkif_schedule(void *arg);
+
+int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
+                              struct backend_info *be, int state);
+
+struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
+
+static inline void blkif_get_x86_32_req(struct blkif_request *dst,
+                                        struct blkif_x86_32_request *src)
+{
+        int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+        dst->operation = src->operation;
+        dst->nr_segments = src->nr_segments;
+        dst->handle = src->handle;
+        dst->id = src->id;
+        dst->u.rw.sector_number = src->sector_number;
+        barrier();
+        if (n > dst->nr_segments)
+                n = dst->nr_segments;
+        for (i = 0; i < n; i++)
+                dst->u.rw.seg[i] = src->seg[i];
+}
+
+static inline void blkif_get_x86_64_req(struct blkif_request *dst,
+                                        struct blkif_x86_64_request *src)
+{
+        int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+        dst->operation = src->operation;
+        dst->nr_segments = src->nr_segments;
+        dst->handle = src->handle;
+        dst->id = src->id;
+        dst->u.rw.sector_number = src->sector_number;
+        barrier();
+        if (n > dst->nr_segments)
+                n = dst->nr_segments;
+        for (i = 0; i < n; i++)
+                dst->u.rw.seg[i] = src->seg[i];
+}
+
+#endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
new file mode 100644
index 000000000000..34570823355b
--- /dev/null
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -0,0 +1,768 @@
+/*  Xenbus code for blkif backend
+    Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au>
+    Copyright (C) 2005 XenSource Ltd
+
+    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; either version 2 of the License, or
+    (at your option) any later version.
+
+    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.
+
+*/
+
+#include <stdarg.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include "common.h"
+
+struct backend_info {
+        struct xenbus_device    *dev;
+        struct xen_blkif        *blkif;
+        struct xenbus_watch     backend_watch;
+        unsigned                major;
+        unsigned                minor;
+        char                    *mode;
+};
+
+static struct kmem_cache *xen_blkif_cachep;
+static void connect(struct backend_info *);
+static int connect_ring(struct backend_info *);
+static void backend_changed(struct xenbus_watch *, const char **,
+                            unsigned int);
+
+struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be)
+{
+        return be->dev;
+}
+
+static int blkback_name(struct xen_blkif *blkif, char *buf)
+{
+        char *devpath, *devname;
+        struct xenbus_device *dev = blkif->be->dev;
+
+        devpath = xenbus_read(XBT_NIL, dev->nodename, "dev", NULL);
+        if (IS_ERR(devpath))
+                return PTR_ERR(devpath);
+
+        devname = strstr(devpath, "/dev/");
+        if (devname != NULL)
+                devname += strlen("/dev/");
+        else
+                devname  = devpath;
+
+        snprintf(buf, TASK_COMM_LEN, "blkback.%d.%s", blkif->domid, devname);
+        kfree(devpath);
+
+        return 0;
+}
+
+static void xen_update_blkif_status(struct xen_blkif *blkif)
+{
+        int err;
+        char name[TASK_COMM_LEN];
+
+        /* Not ready to connect? */
+        if (!blkif->irq || !blkif->vbd.bdev)
+                return;
+
+        /* Already connected? */
+        if (blkif->be->dev->state == XenbusStateConnected)
+                return;
+
+        /* Attempt to connect: exit if we fail to. */
+        connect(blkif->be);
+        if (blkif->be->dev->state != XenbusStateConnected)
+                return;
+
+        err = blkback_name(blkif, name);
+        if (err) {
+                xenbus_dev_error(blkif->be->dev, err, "get blkback dev name");
+                return;
+        }
+
+        err = filemap_write_and_wait(blkif->vbd.bdev->bd_inode->i_mapping);
+        if (err) {
+                xenbus_dev_error(blkif->be->dev, err, "block flush");
+                return;
+        }
+        invalidate_inode_pages2(blkif->vbd.bdev->bd_inode->i_mapping);
+
+        blkif->xenblkd = kthread_run(xen_blkif_schedule, blkif, name);
+        if (IS_ERR(blkif->xenblkd)) {
+                err = PTR_ERR(blkif->xenblkd);
+                blkif->xenblkd = NULL;
+                xenbus_dev_error(blkif->be->dev, err, "start xenblkd");
+        }
+}
+
+static struct xen_blkif *xen_blkif_alloc(domid_t domid)
+{
+        struct xen_blkif *blkif;
+
+        blkif = kmem_cache_alloc(xen_blkif_cachep, GFP_KERNEL);
+        if (!blkif)
+                return ERR_PTR(-ENOMEM);
+
+        memset(blkif, 0, sizeof(*blkif));
+        blkif->domid = domid;
+        spin_lock_init(&blkif->blk_ring_lock);
+        atomic_set(&blkif->refcnt, 1);
+        init_waitqueue_head(&blkif->wq);
+        blkif->st_print = jiffies;
+        init_waitqueue_head(&blkif->waiting_to_free);
+
+        return blkif;
+}
+
+static int map_frontend_page(struct xen_blkif *blkif, unsigned long shared_page)
+{
+        struct gnttab_map_grant_ref op;
+
+        gnttab_set_map_op(&op, (unsigned long)blkif->blk_ring_area->addr,
+                          GNTMAP_host_map, shared_page, blkif->domid);
+
+        if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
+                BUG();
+
+        if (op.status) {
+                DPRINTK("Grant table operation failure !\n");
+                return op.status;
+        }
+
+        blkif->shmem_ref = shared_page;
+        blkif->shmem_handle = op.handle;
+
+        return 0;
+}
+
+static void unmap_frontend_page(struct xen_blkif *blkif)
+{
+        struct gnttab_unmap_grant_ref op;
+
+        gnttab_set_unmap_op(&op, (unsigned long)blkif->blk_ring_area->addr,
+                            GNTMAP_host_map, blkif->shmem_handle);
+
+        if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
+                BUG();
+}
+
+static int xen_blkif_map(struct xen_blkif *blkif, unsigned long shared_page,
+                         unsigned int evtchn)
+{
+        int err;
+
+        /* Already connected through? */
+        if (blkif->irq)
+                return 0;
+
+        blkif->blk_ring_area = alloc_vm_area(PAGE_SIZE);
+        if (!blkif->blk_ring_area)
+                return -ENOMEM;
+
+        err = map_frontend_page(blkif, shared_page);
+        if (err) {
+                free_vm_area(blkif->blk_ring_area);
+                return err;
+        }
+
+        switch (blkif->blk_protocol) {
+        case BLKIF_PROTOCOL_NATIVE:
+        {
+                struct blkif_sring *sring;
+                sring = (struct blkif_sring *)blkif->blk_ring_area->addr;
+                BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE);
+                break;
+        }
+        case BLKIF_PROTOCOL_X86_32:
+        {
+                struct blkif_x86_32_sring *sring_x86_32;
+                sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring_area->addr;
+                BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE);
+                break;
+        }
+        case BLKIF_PROTOCOL_X86_64:
+        {
+                struct blkif_x86_64_sring *sring_x86_64;
+                sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring_area->addr;
+                BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE);
+                break;
+        }
+        default:
+                BUG();
+        }
+
+        err = bind_interdomain_evtchn_to_irqhandler(blkif->domid, evtchn,
+                                                    xen_blkif_be_int, 0,
+                                                    "blkif-backend", blkif);
+        if (err < 0) {
+                unmap_frontend_page(blkif);
+                free_vm_area(blkif->blk_ring_area);
+                blkif->blk_rings.common.sring = NULL;
+                return err;
+        }
+        blkif->irq = err;
+
+        return 0;
+}
+
+static void xen_blkif_disconnect(struct xen_blkif *blkif)
+{
+        if (blkif->xenblkd) {
+                kthread_stop(blkif->xenblkd);
+                blkif->xenblkd = NULL;
+        }
+
+        atomic_dec(&blkif->refcnt);
+        wait_event(blkif->waiting_to_free, atomic_read(&blkif->refcnt) == 0);
+        atomic_inc(&blkif->refcnt);
+
+        if (blkif->irq) {
+                unbind_from_irqhandler(blkif->irq, blkif);
+                blkif->irq = 0;
+        }
+
+        if (blkif->blk_rings.common.sring) {
+                unmap_frontend_page(blkif);
+                free_vm_area(blkif->blk_ring_area);
+                blkif->blk_rings.common.sring = NULL;
+        }
+}
+
+void xen_blkif_free(struct xen_blkif *blkif)
+{
+        if (!atomic_dec_and_test(&blkif->refcnt))
+                BUG();
+        kmem_cache_free(xen_blkif_cachep, blkif);
+}
+
+int __init xen_blkif_interface_init(void)
+{
+        xen_blkif_cachep = kmem_cache_create("blkif_cache",
+                                             sizeof(struct xen_blkif),
+                                             0, 0, NULL);
+        if (!xen_blkif_cachep)
+                return -ENOMEM;
+
+        return 0;
+}
+
+/*
+ *  sysfs interface for VBD I/O requests
+ */
+
+#define VBD_SHOW(name, format, args...)                                 \
+        static ssize_t show_##name(struct device *_dev,                 \
+                                   struct device_attribute *attr,       \
+                                   char *buf)                           \
+        {                                                               \
+                struct xenbus_device *dev = to_xenbus_device(_dev);     \
+                struct backend_info *be = dev_get_drvdata(&dev->dev);   \
+                                                                        \
+                return sprintf(buf, format, ##args);                    \
+        }                                                               \
+        static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+
+VBD_SHOW(oo_req,  "%d\n", be->blkif->st_oo_req);
+VBD_SHOW(rd_req,  "%d\n", be->blkif->st_rd_req);
+VBD_SHOW(wr_req,  "%d\n", be->blkif->st_wr_req);
+VBD_SHOW(f_req,  "%d\n", be->blkif->st_f_req);
+VBD_SHOW(rd_sect, "%d\n", be->blkif->st_rd_sect);
+VBD_SHOW(wr_sect, "%d\n", be->blkif->st_wr_sect);
+
+static struct attribute *xen_vbdstat_attrs[] = {
+        &dev_attr_oo_req.attr,
+        &dev_attr_rd_req.attr,
+        &dev_attr_wr_req.attr,
+        &dev_attr_f_req.attr,
+        &dev_attr_rd_sect.attr,
+        &dev_attr_wr_sect.attr,
+        NULL
+};
+
+static struct attribute_group xen_vbdstat_group = {
+        .name = "statistics",
+        .attrs = xen_vbdstat_attrs,
+};
+
+VBD_SHOW(physical_device, "%x:%x\n", be->major, be->minor);
+VBD_SHOW(mode, "%s\n", be->mode);
+
+int xenvbd_sysfs_addif(struct xenbus_device *dev)
+{
+        int error;
+
+        error = device_create_file(&dev->dev, &dev_attr_physical_device);
+        if (error)
+                goto fail1;
+
+        error = device_create_file(&dev->dev, &dev_attr_mode);
+        if (error)
+                goto fail2;
+
+        error = sysfs_create_group(&dev->dev.kobj, &xen_vbdstat_group);
+        if (error)
+                goto fail3;
+
+        return 0;
+
+fail3:  sysfs_remove_group(&dev->dev.kobj, &xen_vbdstat_group);
+fail2:  device_remove_file(&dev->dev, &dev_attr_mode);
+fail1:  device_remove_file(&dev->dev, &dev_attr_physical_device);
+        return error;
+}
+
+void xenvbd_sysfs_delif(struct xenbus_device *dev)
+{
+        sysfs_remove_group(&dev->dev.kobj, &xen_vbdstat_group);
+        device_remove_file(&dev->dev, &dev_attr_mode);
+        device_remove_file(&dev->dev, &dev_attr_physical_device);
+}
+
+
+static void xen_vbd_free(struct xen_vbd *vbd)
+{
+        if (vbd->bdev)
+                blkdev_put(vbd->bdev, vbd->readonly ? FMODE_READ : FMODE_WRITE);
+        vbd->bdev = NULL;
+}
+
+static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
+                          unsigned major, unsigned minor, int readonly,
+                          int cdrom)
+{
+        struct xen_vbd *vbd;
+        struct block_device *bdev;
+        struct request_queue *q;
+
+        vbd = &blkif->vbd;
+        vbd->handle   = handle;
+        vbd->readonly = readonly;
+        vbd->type     = 0;
+
+        vbd->pdevice  = MKDEV(major, minor);
+
+        bdev = blkdev_get_by_dev(vbd->pdevice, vbd->readonly ?
+                                 FMODE_READ : FMODE_WRITE, NULL);
+
+        if (IS_ERR(bdev)) {
+                DPRINTK("xen_vbd_create: device %08x could not be opened.\n",
+                        vbd->pdevice);
+                return -ENOENT;
+        }
+
+        vbd->bdev = bdev;
+        vbd->size = vbd_sz(vbd);
+
+        if (vbd->bdev->bd_disk == NULL) {
+                DPRINTK("xen_vbd_create: device %08x doesn't exist.\n",
+                        vbd->pdevice);
+                xen_vbd_free(vbd);
+                return -ENOENT;
+        }
+
+        if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom)
+                vbd->type |= VDISK_CDROM;
+        if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE)
+                vbd->type |= VDISK_REMOVABLE;
+
+        q = bdev_get_queue(bdev);
+        if (q && q->flush_flags)
+                vbd->flush_support = true;
+
+        DPRINTK("Successful creation of handle=%04x (dom=%u)\n",
+                handle, blkif->domid);
+        return 0;
+}
+static int xen_blkbk_remove(struct xenbus_device *dev)
+{
+        struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+        DPRINTK("");
+
+        if (be->major || be->minor)
+                xenvbd_sysfs_delif(dev);
+
+        if (be->backend_watch.node) {
+                unregister_xenbus_watch(&be->backend_watch);
+                kfree(be->backend_watch.node);
+                be->backend_watch.node = NULL;
+        }
+
+        if (be->blkif) {
+                xen_blkif_disconnect(be->blkif);
+                xen_vbd_free(&be->blkif->vbd);
+                xen_blkif_free(be->blkif);
+                be->blkif = NULL;
+        }
+
+        kfree(be);
+        dev_set_drvdata(&dev->dev, NULL);
+        return 0;
+}
+
+int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
+                              struct backend_info *be, int state)
+{
+        struct xenbus_device *dev = be->dev;
+        int err;
+
+        err = xenbus_printf(xbt, dev->nodename, "feature-flush-cache",
+                            "%d", state);
+        if (err)
+                xenbus_dev_fatal(dev, err, "writing feature-flush-cache");
+
+        return err;
+}
+
+/*
+ * Entry point to this code when a new device is created.  Allocate the basic
+ * structures, and watch the store waiting for the hotplug scripts to tell us
+ * the device's physical major and minor numbers.  Switch to InitWait.
+ */
+static int xen_blkbk_probe(struct xenbus_device *dev,
+                           const struct xenbus_device_id *id)
+{
+        int err;
+        struct backend_info *be = kzalloc(sizeof(struct backend_info),
+                                          GFP_KERNEL);
+        if (!be) {
+                xenbus_dev_fatal(dev, -ENOMEM,
+                                 "allocating backend structure");
+                return -ENOMEM;
+        }
+        be->dev = dev;
+        dev_set_drvdata(&dev->dev, be);
+
+        be->blkif = xen_blkif_alloc(dev->otherend_id);
+        if (IS_ERR(be->blkif)) {
+                err = PTR_ERR(be->blkif);
+                be->blkif = NULL;
+                xenbus_dev_fatal(dev, err, "creating block interface");
+                goto fail;
+        }
+
+        /* setup back pointer */
+        be->blkif->be = be;
+
+        err = xenbus_watch_pathfmt(dev, &be->backend_watch, backend_changed,
+                                   "%s/%s", dev->nodename, "physical-device");
+        if (err)
+                goto fail;
+
+        err = xenbus_switch_state(dev, XenbusStateInitWait);
+        if (err)
+                goto fail;
+
+        return 0;
+
+fail:
+        DPRINTK("failed");
+        xen_blkbk_remove(dev);
+        return err;
+}
+
+
+/*
+ * Callback received when the hotplug scripts have placed the physical-device
+ * node.  Read it and the mode node, and create a vbd.  If the frontend is
+ * ready, connect.
+ */
+static void backend_changed(struct xenbus_watch *watch,
+                            const char **vec, unsigned int len)
+{
+        int err;
+        unsigned major;
+        unsigned minor;
+        struct backend_info *be
+                = container_of(watch, struct backend_info, backend_watch);
+        struct xenbus_device *dev = be->dev;
+        int cdrom = 0;
+        char *device_type;
+
+        DPRINTK("");
+
+        err = xenbus_scanf(XBT_NIL, dev->nodename, "physical-device", "%x:%x",
+                           &major, &minor);
+        if (XENBUS_EXIST_ERR(err)) {
+                /*
+                 * Since this watch will fire once immediately after it is
+                 * registered, we expect this.  Ignore it, and wait for the
+                 * hotplug scripts.
+                 */
+                return;
+        }
+        if (err != 2) {
+                xenbus_dev_fatal(dev, err, "reading physical-device");
+                return;
+        }
+
+        if ((be->major || be->minor) &&
+            ((be->major != major) || (be->minor != minor))) {
+                pr_warn(DRV_PFX "changing physical device (from %x:%x to %x:%x) not supported.\n",
+                        be->major, be->minor, major, minor);
+                return;
+        }
+
+        be->mode = xenbus_read(XBT_NIL, dev->nodename, "mode", NULL);
+        if (IS_ERR(be->mode)) {
+                err = PTR_ERR(be->mode);
+                be->mode = NULL;
+                xenbus_dev_fatal(dev, err, "reading mode");
+                return;
+        }
+
+        device_type = xenbus_read(XBT_NIL, dev->otherend, "device-type", NULL);
+        if (!IS_ERR(device_type)) {
+                cdrom = strcmp(device_type, "cdrom") == 0;
+                kfree(device_type);
+        }
+
+        if (be->major == 0 && be->minor == 0) {
+                /* Front end dir is a number, which is used as the handle. */
+
+                char *p = strrchr(dev->otherend, '/') + 1;
+                long handle;
+                err = strict_strtoul(p, 0, &handle);
+                if (err)
+                        return;
+
+                be->major = major;
+                be->minor = minor;
+
+                err = xen_vbd_create(be->blkif, handle, major, minor,
+                                 (NULL == strchr(be->mode, 'w')), cdrom);
+                if (err) {
+                        be->major = 0;
+                        be->minor = 0;
+                        xenbus_dev_fatal(dev, err, "creating vbd structure");
+                        return;
+                }
+
+                err = xenvbd_sysfs_addif(dev);
+                if (err) {
+                        xen_vbd_free(&be->blkif->vbd);
+                        be->major = 0;
+                        be->minor = 0;
+                        xenbus_dev_fatal(dev, err, "creating sysfs entries");
+                        return;
+                }
+
+                /* We're potentially connected now */
+                xen_update_blkif_status(be->blkif);
+        }
+}
+
+
+/*
+ * Callback received when the frontend's state changes.
+ */
+static void frontend_changed(struct xenbus_device *dev,
+                             enum xenbus_state frontend_state)
+{
+        struct backend_info *be = dev_get_drvdata(&dev->dev);
+        int err;
+
+        DPRINTK("%s", xenbus_strstate(frontend_state));
+
+        switch (frontend_state) {
+        case XenbusStateInitialising:
+                if (dev->state == XenbusStateClosed) {
+                        pr_info(DRV_PFX "%s: prepare for reconnect\n",
+                                dev->nodename);
+                        xenbus_switch_state(dev, XenbusStateInitWait);
+                }
+                break;
+
+        case XenbusStateInitialised:
+        case XenbusStateConnected:
+                /*
+                 * Ensure we connect even when two watches fire in
+                 * close successsion and we miss the intermediate value
+                 * of frontend_state.
+                 */
+                if (dev->state == XenbusStateConnected)
+                        break;
+
+                /*
+                 * Enforce precondition before potential leak point.
+                 * blkif_disconnect() is idempotent.
+                 */
+                xen_blkif_disconnect(be->blkif);
+
+                err = connect_ring(be);
+                if (err)
+                        break;
+                xen_update_blkif_status(be->blkif);
+                break;
+
+        case XenbusStateClosing:
+                xen_blkif_disconnect(be->blkif);
+                xenbus_switch_state(dev, XenbusStateClosing);
+                break;
+
+        case XenbusStateClosed:
+                xenbus_switch_state(dev, XenbusStateClosed);
+                if (xenbus_dev_is_online(dev))
+                        break;
+                /* fall through if not online */
+        case XenbusStateUnknown:
+                /* implies blkif_disconnect() via blkback_remove() */
+                device_unregister(&dev->dev);
+                break;
+
+        default:
+                xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
+                                 frontend_state);
+                break;
+        }
+}
+
+
+/* ** Connection ** */
+
+
+/*
+ * Write the physical details regarding the block device to the store, and
+ * switch to Connected state.
+ */
+static void connect(struct backend_info *be)
+{
+        struct xenbus_transaction xbt;
+        int err;
+        struct xenbus_device *dev = be->dev;
+
+        DPRINTK("%s", dev->otherend);
+
+        /* Supply the information about the device the frontend needs */
+again:
+        err = xenbus_transaction_start(&xbt);
+        if (err) {
+                xenbus_dev_fatal(dev, err, "starting transaction");
+                return;
+        }
+
+        err = xen_blkbk_flush_diskcache(xbt, be, be->blkif->vbd.flush_support);
+        if (err)
+                goto abort;
+
+        err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",
+                            (unsigned long long)vbd_sz(&be->blkif->vbd));
+        if (err) {
+                xenbus_dev_fatal(dev, err, "writing %s/sectors",
+                                 dev->nodename);
+                goto abort;
+        }
+
+        /* FIXME: use a typename instead */
+        err = xenbus_printf(xbt, dev->nodename, "info", "%u",
+                            be->blkif->vbd.type |
+                            (be->blkif->vbd.readonly ? VDISK_READONLY : 0));
+        if (err) {
+                xenbus_dev_fatal(dev, err, "writing %s/info",
+                                 dev->nodename);
+                goto abort;
+        }
+        err = xenbus_printf(xbt, dev->nodename, "sector-size", "%lu",
+                            (unsigned long)
+                            bdev_logical_block_size(be->blkif->vbd.bdev));
+        if (err) {
+                xenbus_dev_fatal(dev, err, "writing %s/sector-size",
+                                 dev->nodename);
+                goto abort;
+        }
+
+        err = xenbus_transaction_end(xbt, 0);
+        if (err == -EAGAIN)
+                goto again;
+        if (err)
+                xenbus_dev_fatal(dev, err, "ending transaction");
+
+        err = xenbus_switch_state(dev, XenbusStateConnected);
+        if (err)
+                xenbus_dev_fatal(dev, err, "switching to Connected state",
+                                 dev->nodename);
+
+        return;
+ abort:
+        xenbus_transaction_end(xbt, 1);
+}
+
+
+static int connect_ring(struct backend_info *be)
+{
+        struct xenbus_device *dev = be->dev;
+        unsigned long ring_ref;
+        unsigned int evtchn;
+        char protocol[64] = "";
+        int err;
+
+        DPRINTK("%s", dev->otherend);
+
+        err = xenbus_gather(XBT_NIL, dev->otherend, "ring-ref", "%lu",
+                            &ring_ref, "event-channel", "%u", &evtchn, NULL);
+        if (err) {
+                xenbus_dev_fatal(dev, err,
+                                 "reading %s/ring-ref and event-channel",
+                                 dev->otherend);
+                return err;
+        }
+
+        be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
+        err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
+                            "%63s", protocol, NULL);
+        if (err)
+                strcpy(protocol, "unspecified, assuming native");
+        else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE))
+                be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
+        else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_32))
+                be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_32;
+        else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_64))
+                be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_64;
+        else {
+                xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol);
+                return -1;
+        }
+        pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s)\n",
+                ring_ref, evtchn, be->blkif->blk_protocol, protocol);
+
+        /* Map the shared frame, irq etc. */
+        err = xen_blkif_map(be->blkif, ring_ref, evtchn);
+        if (err) {
+                xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u",
+                                 ring_ref, evtchn);
+                return err;
+        }
+
+        return 0;
+}
+
+
+/* ** Driver Registration ** */
+
+
+static const struct xenbus_device_id xen_blkbk_ids[] = {
+        { "vbd" },
+        { "" }
+};
+
+
+static struct xenbus_driver xen_blkbk = {
+        .name = "vbd",
+        .owner = THIS_MODULE,
+        .ids = xen_blkbk_ids,
+        .probe = xen_blkbk_probe,
+        .remove = xen_blkbk_remove,
+        .otherend_changed = frontend_changed
+};
+
+
+int xen_blkif_xenbus_init(void)
+{
+        return xenbus_register_backend(&xen_blkbk);
+}
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 9cb8668ff5f4..b536a9cef917 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -97,6 +97,7 @@ struct blkfront_info
         struct blk_shadow shadow[BLK_RING_SIZE];
         unsigned long shadow_free;
         unsigned int feature_flush;
+        unsigned int flush_op;
         int is_ready;
 };
 
@@ -250,8 +251,7 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
 
 /*
  * Generate a Xen blkfront IO request from a blk layer request.  Reads
- * and writes are handled as expected.  Since we lack a loose flush
- * request, we map flushes into a full ordered barrier.
+ * and writes are handled as expected.
  *
  * @req: a request struct
  */
@@ -293,14 +293,13 @@ static int blkif_queue_request(struct request *req)
 
         if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
                 /*
-                 * Ideally we could just do an unordered
-                 * flush-to-disk, but all we have is a full write
-                 * barrier at the moment.  However, a barrier write is
+                 * Ideally we can do an unordered flush-to-disk. In case the
+                 * backend onlysupports barriers, use that. A barrier request
                  * a superset of FUA, so we can implement it the same
                  * way.  (It's also a FLUSH+FUA, since it is
                  * guaranteed ordered WRT previous writes.)
                  */
-                ring_req->operation = BLKIF_OP_WRITE_BARRIER;
+                ring_req->operation = info->flush_op;
         }
 
         ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
@@ -433,8 +432,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 static void xlvbd_flush(struct blkfront_info *info)
 {
         blk_queue_flush(info->rq, info->feature_flush);
-        printk(KERN_INFO "blkfront: %s: barriers %s\n",
+        printk(KERN_INFO "blkfront: %s: %s: %s\n",
                info->gd->disk_name,
+               info->flush_op == BLKIF_OP_WRITE_BARRIER ?
+                "barrier" : (info->flush_op == BLKIF_OP_FLUSH_DISKCACHE ?
+                "flush diskcache" : "barrier or flush"),
                info->feature_flush ? "enabled" : "disabled");
 }
 
@@ -720,15 +722,20 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
                 error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
                 switch (bret->operation) {
+                case BLKIF_OP_FLUSH_DISKCACHE:
                 case BLKIF_OP_WRITE_BARRIER:
                         if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
-                                printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
+                                printk(KERN_WARNING "blkfront: %s: write %s op failed\n",
+                                       info->flush_op == BLKIF_OP_WRITE_BARRIER ?
+                                       "barrier" :  "flush disk cache",
                                        info->gd->disk_name);
                                 error = -EOPNOTSUPP;
                         }
                         if (unlikely(bret->status == BLKIF_RSP_ERROR &&
                                      info->shadow[id].req.nr_segments == 0)) {
-                                printk(KERN_WARNING "blkfront: %s: empty write barrier op failed\n",
+                                printk(KERN_WARNING "blkfront: %s: empty write %s op failed\n",
+                                       info->flush_op == BLKIF_OP_WRITE_BARRIER ?
+                                       "barrier" :  "flush disk cache",
                                        info->gd->disk_name);
                                 error = -EOPNOTSUPP;
                         }
@@ -736,6 +743,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
                                 if (error == -EOPNOTSUPP)
                                         error = 0;
                                 info->feature_flush = 0;
+                                info->flush_op = 0;
                                 xlvbd_flush(info);
                         }
                         /* fall through */
@@ -1100,7 +1108,7 @@ static void blkfront_connect(struct blkfront_info *info)
         unsigned long sector_size;
         unsigned int binfo;
         int err;
-        int barrier;
+        int barrier, flush;
 
         switch (info->connected) {
         case BLKIF_STATE_CONNECTED:
@@ -1140,8 +1148,11 @@ static void blkfront_connect(struct blkfront_info *info)
                 return;
         }
 
+        info->feature_flush = 0;
+        info->flush_op = 0;
+
         err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-                            "feature-barrier", "%lu", &barrier,
+                            "feature-barrier", "%d", &barrier,
                             NULL);
 
         /*
@@ -1151,11 +1162,23 @@ static void blkfront_connect(struct blkfront_info *info)
          *
          * If there are barriers, then we use flush.
          */
-        info->feature_flush = 0;
-
-        if (!err && barrier)
+        if (!err && barrier) {
                 info->feature_flush = REQ_FLUSH | REQ_FUA;
+                info->flush_op = BLKIF_OP_WRITE_BARRIER;
+        }
+        /*
+         * And if there is "feature-flush-cache" use that above
+         * barriers.
+         */
+        err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+                            "feature-flush-cache", "%d", &flush,
+                            NULL);
 
+        if (!err && flush) {
+                info->feature_flush = REQ_FLUSH;
+                info->flush_op = BLKIF_OP_FLUSH_DISKCACHE;
+        }
+                
         err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
         if (err) {
                 xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index e427fbe45999..ae15a4ddaa9b 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -625,7 +625,9 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
         blk_queue_max_hw_sectors(q, 4096 / 512);
         gendisk->queue = q;
         gendisk->fops = &viocd_fops;
-        gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE;
+        gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE |
+                         GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+        gendisk->events = DISK_EVENT_MEDIA_CHANGE;
         set_capacity(gendisk, 0);
         gendisk->private_data = d;
         d->viocd_disk = gendisk;
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index c7f1a6f16b6e..e2fc2d21fa61 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -39,3 +39,5 @@ obj-$(CONFIG_X86_CPUFREQ_NFORCE2)	+= cpufreq-nforce2.o
 
 ##################################################################################d
 
+# ARM SoC drivers
+obj-$(CONFIG_UX500_SOC_DB8500)          += db8500-cpufreq.o
diff --git a/drivers/cpufreq/db8500-cpufreq.c b/drivers/cpufreq/db8500-cpufreq.c
new file mode 100644
index 000000000000..d90456a809f9
--- /dev/null
+++ b/drivers/cpufreq/db8500-cpufreq.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ * Author: Martin Persson <martin.persson@stericsson.com>
+ * Author: Jonas Aaberg <jonas.aberg@stericsson.com>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/mfd/db8500-prcmu.h>
+#include <mach/id.h>
+
+static struct cpufreq_frequency_table freq_table[] = {
+        [0] = {
+                .index = 0,
+                .frequency = 300000,
+        },
+        [1] = {
+                .index = 1,
+                .frequency = 600000,
+        },
+        [2] = {
+                /* Used for MAX_OPP, if available */
+                .index = 2,
+                .frequency = CPUFREQ_TABLE_END,
+        },
+        [3] = {
+                .index = 3,
+                .frequency = CPUFREQ_TABLE_END,
+        },
+};
+
+static enum arm_opp idx2opp[] = {
+        ARM_50_OPP,
+        ARM_100_OPP,
+        ARM_MAX_OPP
+};
+
+static struct freq_attr *db8500_cpufreq_attr[] = {
+        &cpufreq_freq_attr_scaling_available_freqs,
+        NULL,
+};
+
+static int db8500_cpufreq_verify_speed(struct cpufreq_policy *policy)
+{
+        return cpufreq_frequency_table_verify(policy, freq_table);
+}
+
+static int db8500_cpufreq_target(struct cpufreq_policy *policy,
+                                unsigned int target_freq,
+                                unsigned int relation)
+{
+        struct cpufreq_freqs freqs;
+        unsigned int idx;
+
+        /* scale the target frequency to one of the extremes supported */
+        if (target_freq < policy->cpuinfo.min_freq)
+                target_freq = policy->cpuinfo.min_freq;
+        if (target_freq > policy->cpuinfo.max_freq)
+                target_freq = policy->cpuinfo.max_freq;
+
+        /* Lookup the next frequency */
+        if (cpufreq_frequency_table_target
+            (policy, freq_table, target_freq, relation, &idx)) {
+                return -EINVAL;
+        }
+
+        freqs.old = policy->cur;
+        freqs.new = freq_table[idx].frequency;
+        freqs.cpu = policy->cpu;
+
+        if (freqs.old == freqs.new)
+                return 0;
+
+        /* pre-change notification */
+        cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+        /* request the PRCM unit for opp change */
+        if (prcmu_set_arm_opp(idx2opp[idx])) {
+                pr_err("db8500-cpufreq:  Failed to set OPP level\n");
+                return -EINVAL;
+        }
+
+        /* post change notification */
+        cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+
+        return 0;
+}
+
+static unsigned int db8500_cpufreq_getspeed(unsigned int cpu)
+{
+        int i;
+        /* request the prcm to get the current ARM opp */
+        for (i = 0; prcmu_get_arm_opp() != idx2opp[i]; i++)
+                ;
+        return freq_table[i].frequency;
+}
+
+static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
+{
+        int res;
+        int i;
+
+        BUILD_BUG_ON(ARRAY_SIZE(idx2opp) + 1 != ARRAY_SIZE(freq_table));
+
+        if (cpu_is_u8500v2() && !prcmu_is_u8400()) {
+                freq_table[0].frequency = 400000;
+                freq_table[1].frequency = 800000;
+                if (prcmu_has_arm_maxopp())
+                        freq_table[2].frequency = 1000000;
+        }
+
+        /* get policy fields based on the table */
+        res = cpufreq_frequency_table_cpuinfo(policy, freq_table);
+        if (!res)
+                cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
+        else {
+                pr_err("db8500-cpufreq : Failed to read policy table\n");
+                return res;
+        }
+
+        policy->min = policy->cpuinfo.min_freq;
+        policy->max = policy->cpuinfo.max_freq;
+        policy->cur = db8500_cpufreq_getspeed(policy->cpu);
+
+        for (i = 0; freq_table[i].frequency != policy->cur; i++)
+                ;
+
+        policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+
+        /*
+         * FIXME : Need to take time measurement across the target()
+         *         function with no/some/all drivers in the notification
+         *         list.
+         */
+        policy->cpuinfo.transition_latency = 20 * 1000; /* in ns */
+
+        /* policy sharing between dual CPUs */
+        cpumask_copy(policy->cpus, &cpu_present_map);
+
+        policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+
+        return 0;
+}
+
+static struct cpufreq_driver db8500_cpufreq_driver = {
+        .flags  = CPUFREQ_STICKY,
+        .verify = db8500_cpufreq_verify_speed,
+        .target = db8500_cpufreq_target,
+        .get    = db8500_cpufreq_getspeed,
+        .init   = db8500_cpufreq_init,
+        .name   = "DB8500",
+        .attr   = db8500_cpufreq_attr,
+};
+
+static int __init db8500_cpufreq_register(void)
+{
+        if (!cpu_is_u8500v20_or_later())
+                return -ENODEV;
+
+        pr_info("cpufreq for DB8500 started\n");
+        return cpufreq_register_driver(&db8500_cpufreq_driver);
+}
+device_initcall(db8500_cpufreq_register);
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index dcc1b2139fff..636e40925b16 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -213,12 +213,17 @@ static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
                                                 struct sh_dmae_device, common);
         struct sh_dmae_pdata *pdata = shdev->pdata;
         const struct sh_dmae_channel *chan_pdata = &pdata->channel[sh_chan->id];
-        u16 __iomem *addr = shdev->dmars + chan_pdata->dmars / sizeof(u16);
+        u16 __iomem *addr = shdev->dmars;
         int shift = chan_pdata->dmars_bit;
 
         if (dmae_is_busy(sh_chan))
                 return -EBUSY;
 
+        /* in the case of a missing DMARS resource use first memory window */
+        if (!addr)
+                addr = (u16 __iomem *)shdev->chan_reg;
+        addr += chan_pdata->dmars / sizeof(u16);
+
         __raw_writew((__raw_readw(addr) & (0xff00 >> shift)) | (val << shift),
                      addr);
 
@@ -1078,7 +1083,7 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
         unsigned long irqflags = IRQF_DISABLED,
                 chan_flag[SH_DMAC_MAX_CHANNELS] = {};
         int errirq, chan_irq[SH_DMAC_MAX_CHANNELS];
-        int err, i, irq_cnt = 0, irqres = 0;
+        int err, i, irq_cnt = 0, irqres = 0, irq_cap = 0;
         struct sh_dmae_device *shdev;
         struct resource *chan, *dmars, *errirq_res, *chanirq_res;
 
@@ -1087,7 +1092,7 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
                 return -ENODEV;
 
         chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-        /* DMARS area is optional, if absent, this controller cannot do slave DMA */
+        /* DMARS area is optional */
         dmars = platform_get_resource(pdev, IORESOURCE_MEM, 1);
         /*
          * IRQ resources:
@@ -1154,7 +1159,7 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
         INIT_LIST_HEAD(&shdev->common.channels);
 
         dma_cap_set(DMA_MEMCPY, shdev->common.cap_mask);
-        if (dmars)
+        if (pdata->slave && pdata->slave_num)
                 dma_cap_set(DMA_SLAVE, shdev->common.cap_mask);
 
         shdev->common.device_alloc_chan_resources
@@ -1203,8 +1208,13 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
             !platform_get_resource(pdev, IORESOURCE_IRQ, 1)) {
                 /* Special case - all multiplexed */
                 for (; irq_cnt < pdata->channel_num; irq_cnt++) {
-                        chan_irq[irq_cnt] = chanirq_res->start;
-                        chan_flag[irq_cnt] = IRQF_SHARED;
+                        if (irq_cnt < SH_DMAC_MAX_CHANNELS) {
+                                chan_irq[irq_cnt] = chanirq_res->start;
+                                chan_flag[irq_cnt] = IRQF_SHARED;
+                        } else {
+                                irq_cap = 1;
+                                break;
+                        }
                 }
         } else {
                 do {
@@ -1218,22 +1228,32 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
                                         "Found IRQ %d for channel %d\n",
                                         i, irq_cnt);
                                 chan_irq[irq_cnt++] = i;
+
+                                if (irq_cnt >= SH_DMAC_MAX_CHANNELS)
+                                        break;
+                        }
+
+                        if (irq_cnt >= SH_DMAC_MAX_CHANNELS) {
+                                irq_cap = 1;
+                                break;
                         }
                         chanirq_res = platform_get_resource(pdev,
                                                 IORESOURCE_IRQ, ++irqres);
                 } while (irq_cnt < pdata->channel_num && chanirq_res);
         }
 
-        if (irq_cnt < pdata->channel_num)
-                goto eirqres;
-
         /* Create DMA Channel */
-        for (i = 0; i < pdata->channel_num; i++) {
+        for (i = 0; i < irq_cnt; i++) {
                 err = sh_dmae_chan_probe(shdev, i, chan_irq[i], chan_flag[i]);
                 if (err)
                         goto chan_probe_err;
         }
 
+        if (irq_cap)
+                dev_notice(&pdev->dev, "Attempting to register %d DMA "
+                           "channels when a maximum of %d are supported.\n",
+                           pdata->channel_num, SH_DMAC_MAX_CHANNELS);
+
         pm_runtime_put(&pdev->dev);
 
         platform_set_drvdata(pdev, shdev);
@@ -1243,7 +1263,7 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 
 chan_probe_err:
         sh_dmae_chan_remove(shdev);
-eirqres:
+
 #if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
         free_irq(errirq, shdev);
 eirq_err:
diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h
index 3f9d3cd06584..5ae9fc512180 100644
--- a/drivers/dma/shdma.h
+++ b/drivers/dma/shdma.h
@@ -17,7 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/list.h>
 
-#define SH_DMAC_MAX_CHANNELS 6
+#define SH_DMAC_MAX_CHANNELS 20
 #define SH_DMA_SLAVE_NUMBER 256
 #define SH_DMA_TCR_MAX 0x00FFFFFF       /* 16MB */
 
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index d41f9002da45..aa08497a075a 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -101,6 +101,19 @@ struct i3200_priv {
 
 static int nr_channels;
 
+#ifndef readq
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+        const volatile u32 __iomem *p = addr;
+        u32 low, high;
+
+        low = readl(p);
+        high = readl(p + 1);
+
+        return low + ((u64)high << 32);
+}
+#endif
+
 static int how_many_channels(struct pci_dev *pdev)
 {
         unsigned char capid0_8b; /* 8th byte of CAPID0 */
diff --git a/drivers/gpio/ml_ioh_gpio.c b/drivers/gpio/ml_ioh_gpio.c
index 0a775f7987c2..1bc621ac3536 100644
--- a/drivers/gpio/ml_ioh_gpio.c
+++ b/drivers/gpio/ml_ioh_gpio.c
@@ -15,6 +15,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
  */
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/gpio.h>
 
@@ -138,6 +139,7 @@ static int ioh_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
         return 0;
 }
 
+#ifdef CONFIG_PM
 /*
  * Save register configuration and disable interrupts.
  */
@@ -157,6 +159,7 @@ static void ioh_gpio_restore_reg_conf(struct ioh_gpio *chip)
         /* to store contents of PM register */
         iowrite32(chip->ioh_gpio_reg.pm_reg, &chip->reg->regs[chip->ch].pm);
 }
+#endif
 
 static void ioh_gpio_setup(struct ioh_gpio *chip, int num_port)
 {
diff --git a/drivers/gpio/vx855_gpio.c b/drivers/gpio/vx855_gpio.c
index 8a98ee5d5f6c..ef5aabd8b8b7 100644
--- a/drivers/gpio/vx855_gpio.c
+++ b/drivers/gpio/vx855_gpio.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/gpio.h>
+#include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/pci.h>
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c6289034e29a..0b2e167d2bce 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -56,9 +56,7 @@ static int i915_gem_phys_pwrite(struct drm_device *dev,
 static void i915_gem_free_object_tail(struct drm_i915_gem_object *obj);
 
 static int i915_gem_inactive_shrink(struct shrinker *shrinker,
-                                    int nr_to_scan,
-                                    gfp_t gfp_mask);
-
+                                    struct shrink_control *sc);
 
 /* some bookkeeping */
 static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
@@ -4092,9 +4090,7 @@ i915_gpu_is_active(struct drm_device *dev)
 }
 
 static int
-i915_gem_inactive_shrink(struct shrinker *shrinker,
-                         int nr_to_scan,
-                         gfp_t gfp_mask)
+i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 {
         struct drm_i915_private *dev_priv =
                 container_of(shrinker,
@@ -4102,6 +4098,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker,
                              mm.inactive_shrinker);
         struct drm_device *dev = dev_priv->dev;
         struct drm_i915_gem_object *obj, *next;
+        int nr_to_scan = sc->nr_to_scan;
         int cnt;
 
         if (!mutex_trylock(&dev->struct_mutex))
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 9d9d92945f8c..d948575717bf 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -395,12 +395,14 @@ static int ttm_pool_get_num_unused_pages(void)
 /**
  * Callback for mm to request pool to reduce number of page held.
  */
-static int ttm_pool_mm_shrink(struct shrinker *shrink, int shrink_pages, gfp_t gfp_mask)
+static int ttm_pool_mm_shrink(struct shrinker *shrink,
+                              struct shrink_control *sc)
 {
         static atomic_t start_pool = ATOMIC_INIT(0);
         unsigned i;
         unsigned pool_offset = atomic_add_return(1, &start_pool);
         struct ttm_page_pool *pool;
+        int shrink_pages = sc->nr_to_scan;
 
         pool_offset = pool_offset % NUM_POOLS;
         /* select start pool in round robin fashion */
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index a5ec5a7cb381..6e5123b1d341 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -1781,7 +1781,8 @@ static int ide_cd_probe(ide_drive_t *drive)
 
         ide_cd_read_toc(drive, &sense);
         g->fops = &idecd_ops;
-        g->flags |= GENHD_FL_REMOVABLE;
+        g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+        g->events = DISK_EVENT_MEDIA_CHANGE;
         add_disk(g);
         return 0;
 
diff --git a/drivers/input/input-compat.h b/drivers/input/input-compat.h
index 4d8ea32e8a00..22be27b424de 100644
--- a/drivers/input/input-compat.h
+++ b/drivers/input/input-compat.h
@@ -19,7 +19,7 @@
 
 /* Note to the author of this code: did it ever occur to
    you why the ifdefs are needed? Think about it again. -AK */
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) || defined(CONFIG_TILE)
 #  define INPUT_COMPAT_TEST is_compat_task()
 #elif defined(CONFIG_S390)
 #  define INPUT_COMPAT_TEST test_thread_flag(TIF_31BIT)
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 9bec8699b8a3..1d027b475b22 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -14,6 +14,13 @@ config LEDS_CLASS
           This option enables the led sysfs class in /sys/class/leds.  You'll
           need this to do anything useful with LEDs.  If unsure, say N.
 
+config LEDS_GPIO_REGISTER
+        bool
+        help
+          This option provides the function gpio_led_register_device.
+          As this function is used by arch code it must not be compiled as a
+          module.
+
 if NEW_LEDS
 
 comment "LED drivers"
@@ -115,13 +122,6 @@ config LEDS_ALIX2
           This option enables support for the PCEngines ALIX.2 and ALIX.3 LEDs.
           You have to set leds-alix2.force=1 for boards with Award BIOS.
 
-config LEDS_H1940
-        tristate "LED Support for iPAQ H1940 device"
-        depends on LEDS_CLASS
-        depends on ARCH_H1940
-        help
-          This option enables support for the LEDs on the h1940.
-
 config LEDS_COBALT_QUBE
         tristate "LED Support for the Cobalt Qube series front LED"
         depends on LEDS_CLASS
@@ -162,6 +162,16 @@ config LEDS_PCA9532
           LED controller. It is generally only useful
           as a platform driver
 
+config LEDS_PCA9532_GPIO
+        bool "Enable GPIO support for PCA9532"
+        depends on LEDS_PCA9532
+        depends on GPIOLIB
+        help
+          Allow unused pins on PCA9532 to be used as gpio.
+
+          To use a pin as gpio pca9532_type in pca9532_platform data needs to
+          set to PCA9532_TYPE_GPIO.
+
 config LEDS_GPIO
         tristate "LED Support for GPIO connected LEDs"
         depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 39c80fca84d2..bccb96c9bb45 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -17,11 +17,11 @@ obj-$(CONFIG_LEDS_NET48XX)		+= leds-net48xx.o
 obj-$(CONFIG_LEDS_NET5501)              += leds-net5501.o
 obj-$(CONFIG_LEDS_WRAP)                 += leds-wrap.o
 obj-$(CONFIG_LEDS_ALIX2)                += leds-alix2.o
-obj-$(CONFIG_LEDS_H1940)                += leds-h1940.o
 obj-$(CONFIG_LEDS_COBALT_QUBE)          += leds-cobalt-qube.o
 obj-$(CONFIG_LEDS_COBALT_RAQ)           += leds-cobalt-raq.o
 obj-$(CONFIG_LEDS_SUNFIRE)              += leds-sunfire.o
 obj-$(CONFIG_LEDS_PCA9532)              += leds-pca9532.o
+obj-$(CONFIG_LEDS_GPIO_REGISTER)        += leds-gpio-register.o
 obj-$(CONFIG_LEDS_GPIO)                 += leds-gpio.o
 obj-$(CONFIG_LEDS_LP3944)               += leds-lp3944.o
 obj-$(CONFIG_LEDS_LP5521)               += leds-lp5521.o
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index d5a4ade88991..dc3d3d83191a 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -131,7 +131,8 @@ static void led_set_software_blink(struct led_classdev *led_cdev,
         if (!led_cdev->blink_brightness)
                 led_cdev->blink_brightness = led_cdev->max_brightness;
 
-        if (delay_on == led_cdev->blink_delay_on &&
+        if (led_get_trigger_data(led_cdev) &&
+            delay_on == led_cdev->blink_delay_on &&
             delay_off == led_cdev->blink_delay_off)
                 return;
 
diff --git a/drivers/leds/leds-gpio-register.c b/drivers/leds/leds-gpio-register.c
new file mode 100644
index 000000000000..1c4ed5510f35
--- /dev/null
+++ b/drivers/leds/leds-gpio-register.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2011 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/leds.h>
+
+/**
+ * gpio_led_register_device - register a gpio-led device
+ * @pdata: the platform data used for the new device
+ *
+ * Makes a copy of pdata and pdata->leds and registers a new leds-gpio device
+ * with the result. This allows to have pdata and pdata-leds in .init.rodata
+ * and so saves some bytes compared to a static struct platform_device with
+ * static platform data.
+ *
+ * Returns the registered device or an error pointer.
+ */
+struct platform_device *__init gpio_led_register_device(
+                int id, const struct gpio_led_platform_data *pdata)
+{
+        struct platform_device *ret;
+        struct gpio_led_platform_data _pdata = *pdata;
+
+        _pdata.leds = kmemdup(pdata->leds,
+                        pdata->num_leds * sizeof(*pdata->leds), GFP_KERNEL);
+        if (!_pdata.leds)
+                return ERR_PTR(-ENOMEM);
+
+        ret = platform_device_register_resndata(NULL, "leds-gpio", id,
+                        NULL, 0, &_pdata, sizeof(_pdata));
+        if (IS_ERR(ret))
+                kfree(_pdata.leds);
+
+        return ret;
+}
diff --git a/drivers/leds/leds-h1940.c b/drivers/leds/leds-h1940.c
deleted file mode 100644
index 173d104d9ff2..000000000000
--- a/drivers/leds/leds-h1940.c
+++ /dev/null
@@ -1,170 +0,0 @@
-/*
- * drivers/leds/leds-h1940.c
- * Copyright (c) Arnaud Patard <arnaud.patard@rtp-net.org>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive for
- * more details.
- *
- * H1940 leds driver
- *
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/string.h>
-#include <linux/ctype.h>
-#include <linux/leds.h>
-#include <linux/gpio.h>
-
-#include <mach/regs-gpio.h>
-#include <mach/hardware.h>
-#include <mach/h1940-latch.h>
-
-/*
- * Green led.
- */
-static void h1940_greenled_set(struct led_classdev *led_dev,
-                               enum led_brightness value)
-{
-        switch (value) {
-        case LED_HALF:
-                h1940_latch_control(0, H1940_LATCH_LED_FLASH);
-                s3c2410_gpio_setpin(S3C2410_GPA7, 1);
-                break;
-        case LED_FULL:
-                h1940_latch_control(0, H1940_LATCH_LED_GREEN);
-                s3c2410_gpio_setpin(S3C2410_GPA7, 1);
-                break;
-        default:
-        case LED_OFF:
-                h1940_latch_control(H1940_LATCH_LED_FLASH, 0);
-                h1940_latch_control(H1940_LATCH_LED_GREEN, 0);
-                s3c2410_gpio_setpin(S3C2410_GPA7, 0);
-                break;
-        }
-}
-
-static struct led_classdev h1940_greenled = {
-        .name                   = "h1940:green",
-        .brightness_set         = h1940_greenled_set,
-        .default_trigger        = "h1940-charger",
-};
-
-/*
- * Red led.
- */
-static void h1940_redled_set(struct led_classdev *led_dev,
-                             enum led_brightness value)
-{
-        switch (value) {
-        case LED_HALF:
-                h1940_latch_control(0, H1940_LATCH_LED_FLASH);
-                s3c2410_gpio_setpin(S3C2410_GPA1, 1);
-                break;
-        case LED_FULL:
-                h1940_latch_control(0, H1940_LATCH_LED_RED);
-                s3c2410_gpio_setpin(S3C2410_GPA1, 1);
-                break;
-        default:
-        case LED_OFF:
-                h1940_latch_control(H1940_LATCH_LED_FLASH, 0);
-                h1940_latch_control(H1940_LATCH_LED_RED, 0);
-                s3c2410_gpio_setpin(S3C2410_GPA1, 0);
-                break;
-        }
-}
-
-static struct led_classdev h1940_redled = {
-        .name                   = "h1940:red",
-        .brightness_set         = h1940_redled_set,
-        .default_trigger        = "h1940-charger",
-};
-
-/*
- * Blue led.
- * (it can only be blue flashing led)
- */
-static void h1940_blueled_set(struct led_classdev *led_dev,
-                              enum led_brightness value)
-{
-        if (value) {
-                /* flashing Blue */
-                h1940_latch_control(0, H1940_LATCH_LED_FLASH);
-                s3c2410_gpio_setpin(S3C2410_GPA3, 1);
-        } else {
-                h1940_latch_control(H1940_LATCH_LED_FLASH, 0);
-                s3c2410_gpio_setpin(S3C2410_GPA3, 0);
-        }
-
-}
-
-static struct led_classdev h1940_blueled = {
-        .name                   = "h1940:blue",
-        .brightness_set         = h1940_blueled_set,
-        .default_trigger        = "h1940-bluetooth",
-};
-
-static int __devinit h1940leds_probe(struct platform_device *pdev)
-{
-        int ret;
-
-        ret = led_classdev_register(&pdev->dev, &h1940_greenled);
-        if (ret)
-                goto err_green;
-
-        ret = led_classdev_register(&pdev->dev, &h1940_redled);
-        if (ret)
-                goto err_red;
-
-        ret = led_classdev_register(&pdev->dev, &h1940_blueled);
-        if (ret)
-                goto err_blue;
-
-        return 0;
-
-err_blue:
-        led_classdev_unregister(&h1940_redled);
-err_red:
-        led_classdev_unregister(&h1940_greenled);
-err_green:
-        return ret;
-}
-
-static int h1940leds_remove(struct platform_device *pdev)
-{
-        led_classdev_unregister(&h1940_greenled);
-        led_classdev_unregister(&h1940_redled);
-        led_classdev_unregister(&h1940_blueled);
-        return 0;
-}
-
-
-static struct platform_driver h1940leds_driver = {
-        .driver         = {
-                .name   = "h1940-leds",
-                .owner  = THIS_MODULE,
-        },
-        .probe          = h1940leds_probe,
-        .remove         = h1940leds_remove,
-};
-
-
-static int __init h1940leds_init(void)
-{
-        return platform_driver_register(&h1940leds_driver);
-}
-
-static void __exit h1940leds_exit(void)
-{
-        platform_driver_unregister(&h1940leds_driver);
-}
-
-module_init(h1940leds_init);
-module_exit(h1940leds_exit);
-
-MODULE_AUTHOR("Arnaud Patard <arnaud.patard@rtp-net.org>");
-MODULE_DESCRIPTION("LED driver for the iPAQ H1940");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:h1940-leds");
diff --git a/drivers/leds/leds-lm3530.c b/drivers/leds/leds-lm3530.c
index b37e6186d0fa..4d7ce7631acf 100644
--- a/drivers/leds/leds-lm3530.c
+++ b/drivers/leds/leds-lm3530.c
@@ -17,6 +17,7 @@
 #include <linux/input.h>
 #include <linux/led-lm3530.h>
 #include <linux/types.h>
+#include <linux/regulator/consumer.h>
 
 #define LM3530_LED_DEV "lcd-backlight"
 #define LM3530_NAME "lm3530-led"
@@ -96,12 +97,18 @@ static struct lm3530_mode_map mode_map[] = {
  * @client: i2c client
  * @pdata: LM3530 platform data
  * @mode: mode of operation - manual, ALS, PWM
+ * @regulator: regulator
+ * @brighness: previous brightness value
+ * @enable: regulator is enabled
  */
 struct lm3530_data {
         struct led_classdev led_dev;
         struct i2c_client *client;
         struct lm3530_platform_data *pdata;
         enum lm3530_mode mode;
+        struct regulator *regulator;
+        enum led_brightness brightness;
+        bool enable;
 };
 
 static const u8 lm3530_reg[LM3530_REG_MAX] = {
@@ -172,7 +179,10 @@ static int lm3530_init_registers(struct lm3530_data *drvdata)
         brt_ramp = (pltfm->brt_ramp_fall << LM3530_BRT_RAMP_FALL_SHIFT) |
                         (pltfm->brt_ramp_rise << LM3530_BRT_RAMP_RISE_SHIFT);
 
-        brightness = pltfm->brt_val;
+        if (drvdata->brightness)
+                brightness = drvdata->brightness;
+        else
+                brightness = drvdata->brightness = pltfm->brt_val;
 
         reg_val[0] = gen_config;        /* LM3530_GEN_CONFIG */
         reg_val[1] = als_config;        /* LM3530_ALS_CONFIG */
@@ -190,6 +200,16 @@ static int lm3530_init_registers(struct lm3530_data *drvdata)
         reg_val[13] = LM3530_DEF_ZT_3;  /* LM3530_ALS_Z3T_REG */
         reg_val[14] = LM3530_DEF_ZT_4;  /* LM3530_ALS_Z4T_REG */
 
+        if (!drvdata->enable) {
+                ret = regulator_enable(drvdata->regulator);
+                if (ret) {
+                        dev_err(&drvdata->client->dev,
+                                        "Enable regulator failed\n");
+                        return ret;
+                }
+                drvdata->enable = true;
+        }
+
         for (i = 0; i < LM3530_REG_MAX; i++) {
                 ret = i2c_smbus_write_byte_data(client,
                                 lm3530_reg[i], reg_val[i]);
@@ -210,12 +230,31 @@ static void lm3530_brightness_set(struct led_classdev *led_cdev,
         switch (drvdata->mode) {
         case LM3530_BL_MODE_MANUAL:
 
+                if (!drvdata->enable) {
+                        err = lm3530_init_registers(drvdata);
+                        if (err) {
+                                dev_err(&drvdata->client->dev,
+                                        "Register Init failed: %d\n", err);
+                                break;
+                        }
+                }
+
                 /* set the brightness in brightness control register*/
                 err = i2c_smbus_write_byte_data(drvdata->client,
                                 LM3530_BRT_CTRL_REG, brt_val / 2);
                 if (err)
                         dev_err(&drvdata->client->dev,
                                 "Unable to set brightness: %d\n", err);
+                else
+                        drvdata->brightness = brt_val / 2;
+
+                if (brt_val == 0) {
+                        err = regulator_disable(drvdata->regulator);
+                        if (err)
+                                dev_err(&drvdata->client->dev,
+                                        "Disable regulator failed\n");
+                        drvdata->enable = false;
+                }
                 break;
         case LM3530_BL_MODE_ALS:
                 break;
@@ -297,20 +336,31 @@ static int __devinit lm3530_probe(struct i2c_client *client,
         drvdata->mode = pdata->mode;
         drvdata->client = client;
         drvdata->pdata = pdata;
+        drvdata->brightness = LED_OFF;
+        drvdata->enable = false;
         drvdata->led_dev.name = LM3530_LED_DEV;
         drvdata->led_dev.brightness_set = lm3530_brightness_set;
 
         i2c_set_clientdata(client, drvdata);
 
-        err = lm3530_init_registers(drvdata);
-        if (err < 0) {
-                dev_err(&client->dev, "Register Init failed: %d\n", err);
-                err = -ENODEV;
-                goto err_reg_init;
+        drvdata->regulator = regulator_get(&client->dev, "vin");
+        if (IS_ERR(drvdata->regulator)) {
+                dev_err(&client->dev, "regulator get failed\n");
+                err = PTR_ERR(drvdata->regulator);
+                drvdata->regulator = NULL;
+                goto err_regulator_get;
         }
 
-        err = led_classdev_register((struct device *)
-                                      &client->dev, &drvdata->led_dev);
+        if (drvdata->pdata->brt_val) {
+                err = lm3530_init_registers(drvdata);
+                if (err < 0) {
+                        dev_err(&client->dev,
+                                "Register Init failed: %d\n", err);
+                        err = -ENODEV;
+                        goto err_reg_init;
+                }
+        }
+        err = led_classdev_register(&client->dev, &drvdata->led_dev);
         if (err < 0) {
                 dev_err(&client->dev, "Register led class failed: %d\n", err);
                 err = -ENODEV;
@@ -330,6 +380,9 @@ err_create_file:
         led_classdev_unregister(&drvdata->led_dev);
 err_class_register:
 err_reg_init:
+        regulator_put(drvdata->regulator);
+err_regulator_get:
+        i2c_set_clientdata(client, NULL);
         kfree(drvdata);
 err_out:
         return err;
@@ -340,6 +393,10 @@ static int __devexit lm3530_remove(struct i2c_client *client)
         struct lm3530_data *drvdata = i2c_get_clientdata(client);
 
         device_remove_file(drvdata->led_dev.dev, &dev_attr_mode);
+
+        if (drvdata->enable)
+                regulator_disable(drvdata->regulator);
+        regulator_put(drvdata->regulator);
         led_classdev_unregister(&drvdata->led_dev);
         kfree(drvdata);
         return 0;
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 5bf63af09ddf..d8d3a1e910a1 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -1,13 +1,14 @@
 /*
  * pca9532.c - 16-bit Led dimmer
  *
+ * Copyright (C) 2011 Jan Weitzel
  * Copyright (C) 2008 Riku Voipio
  *
  * 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; version 2 of the License.
  *
- * Datasheet: http://www.nxp.com/acrobat/datasheets/PCA9532_3.pdf
+ * Datasheet: http://www.nxp.com/documents/data_sheet/PCA9532.pdf
  *
  */
 
@@ -19,21 +20,32 @@
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
 #include <linux/leds-pca9532.h>
+#include <linux/gpio.h>
 
-#define PCA9532_REG_PSC(i) (0x2+(i)*2)
-#define PCA9532_REG_PWM(i) (0x3+(i)*2)
-#define PCA9532_REG_LS0  0x6
-#define LED_REG(led) ((led>>2)+PCA9532_REG_LS0)
-#define LED_NUM(led) (led & 0x3)
+/* m =  num_leds*/
+#define PCA9532_REG_INPUT(i)    ((i) >> 3)
+#define PCA9532_REG_OFFSET(m)   ((m) >> 4)
+#define PCA9532_REG_PSC(m, i)   (PCA9532_REG_OFFSET(m) + 0x1 + (i) * 2)
+#define PCA9532_REG_PWM(m, i)   (PCA9532_REG_OFFSET(m) + 0x2 + (i) * 2)
+#define LED_REG(m, led)         (PCA9532_REG_OFFSET(m) + 0x5 + (led >> 2))
+#define LED_NUM(led)            (led & 0x3)
 
 #define ldev_to_led(c)       container_of(c, struct pca9532_led, ldev)
 
+struct pca9532_chip_info {
+        u8      num_leds;
+};
+
 struct pca9532_data {
         struct i2c_client *client;
         struct pca9532_led leds[16];
         struct mutex update_lock;
         struct input_dev *idev;
         struct work_struct work;
+#ifdef CONFIG_LEDS_PCA9532_GPIO
+        struct gpio_chip gpio;
+#endif
+        const struct pca9532_chip_info *chip_info;
         u8 pwm[2];
         u8 psc[2];
 };
@@ -42,16 +54,41 @@ static int pca9532_probe(struct i2c_client *client,
         const struct i2c_device_id *id);
 static int pca9532_remove(struct i2c_client *client);
 
+enum {
+        pca9530,
+        pca9531,
+        pca9532,
+        pca9533,
+};
+
 static const struct i2c_device_id pca9532_id[] = {
-        { "pca9532", 0 },
+        { "pca9530", pca9530 },
+        { "pca9531", pca9531 },
+        { "pca9532", pca9532 },
+        { "pca9533", pca9533 },
         { }
 };
 
 MODULE_DEVICE_TABLE(i2c, pca9532_id);
 
+static const struct pca9532_chip_info pca9532_chip_info_tbl[] = {
+        [pca9530] = {
+                .num_leds = 2,
+        },
+        [pca9531] = {
+                .num_leds = 8,
+        },
+        [pca9532] = {
+                .num_leds = 16,
+        },
+        [pca9533] = {
+                .num_leds = 4,
+        },
+};
+
 static struct i2c_driver pca9532_driver = {
         .driver = {
-                .name = "pca9532",
+                .name = "pca953x",
         },
         .probe = pca9532_probe,
         .remove = pca9532_remove,
@@ -68,7 +105,7 @@ static int pca9532_calcpwm(struct i2c_client *client, int pwm, int blink,
 {
         int a = 0, b = 0, i = 0;
         struct pca9532_data *data = i2c_get_clientdata(client);
-        for (i = 0; i < 16; i++) {
+        for (i = 0; i < data->chip_info->num_leds; i++) {
                 if (data->leds[i].type == PCA9532_TYPE_LED &&
                         data->leds[i].state == PCA9532_PWM0+pwm) {
                                 a++;
@@ -92,10 +129,12 @@ static int pca9532_calcpwm(struct i2c_client *client, int pwm, int blink,
 static int pca9532_setpwm(struct i2c_client *client, int pwm)
 {
         struct pca9532_data *data = i2c_get_clientdata(client);
+        u8 maxleds = data->chip_info->num_leds;
+
         mutex_lock(&data->update_lock);
-        i2c_smbus_write_byte_data(client, PCA9532_REG_PWM(pwm),
+        i2c_smbus_write_byte_data(client, PCA9532_REG_PWM(maxleds, pwm),
                 data->pwm[pwm]);
-        i2c_smbus_write_byte_data(client, PCA9532_REG_PSC(pwm),
+        i2c_smbus_write_byte_data(client, PCA9532_REG_PSC(maxleds, pwm),
                 data->psc[pwm]);
         mutex_unlock(&data->update_lock);
         return 0;
@@ -106,15 +145,16 @@ static void pca9532_setled(struct pca9532_led *led)
 {
         struct i2c_client *client = led->client;
         struct pca9532_data *data = i2c_get_clientdata(client);
+        u8 maxleds = data->chip_info->num_leds;
         char reg;
 
         mutex_lock(&data->update_lock);
-        reg = i2c_smbus_read_byte_data(client, LED_REG(led->id));
+        reg = i2c_smbus_read_byte_data(client, LED_REG(maxleds, led->id));
         /* zero led bits */
         reg = reg & ~(0x3<<LED_NUM(led->id)*2);
         /* set the new value */
         reg = reg | (led->state << LED_NUM(led->id)*2);
-        i2c_smbus_write_byte_data(client, LED_REG(led->id), reg);
+        i2c_smbus_write_byte_data(client, LED_REG(maxleds, led->id), reg);
         mutex_unlock(&data->update_lock);
 }
 
@@ -183,10 +223,12 @@ static int pca9532_event(struct input_dev *dev, unsigned int type,
 
 static void pca9532_input_work(struct work_struct *work)
 {
-        struct pca9532_data *data;
-        data = container_of(work, struct pca9532_data, work);
+        struct pca9532_data *data =
+                container_of(work, struct pca9532_data, work);
+        u8 maxleds = data->chip_info->num_leds;
+
         mutex_lock(&data->update_lock);
-        i2c_smbus_write_byte_data(data->client, PCA9532_REG_PWM(1),
+        i2c_smbus_write_byte_data(data->client, PCA9532_REG_PWM(maxleds, 1),
                 data->pwm[1]);
         mutex_unlock(&data->update_lock);
 }
@@ -200,16 +242,68 @@ static void pca9532_led_work(struct work_struct *work)
         pca9532_setled(led);
 }
 
-static void pca9532_destroy_devices(struct pca9532_data *data, int n_devs)
+#ifdef CONFIG_LEDS_PCA9532_GPIO
+static int pca9532_gpio_request_pin(struct gpio_chip *gc, unsigned offset)
+{
+        struct pca9532_data *data = container_of(gc, struct pca9532_data, gpio);
+        struct pca9532_led *led = &data->leds[offset];
+
+        if (led->type == PCA9532_TYPE_GPIO)
+                return 0;
+
+        return -EBUSY;
+}
+
+static void pca9532_gpio_set_value(struct gpio_chip *gc, unsigned offset, int val)
+{
+        struct pca9532_data *data = container_of(gc, struct pca9532_data, gpio);
+        struct pca9532_led *led = &data->leds[offset];
+
+        if (val)
+                led->state = PCA9532_ON;
+        else
+                led->state = PCA9532_OFF;
+
+        pca9532_setled(led);
+}
+
+static int pca9532_gpio_get_value(struct gpio_chip *gc, unsigned offset)
+{
+        struct pca9532_data *data = container_of(gc, struct pca9532_data, gpio);
+        unsigned char reg;
+
+        reg = i2c_smbus_read_byte_data(data->client, PCA9532_REG_INPUT(offset));
+
+        return !!(reg & (1 << (offset % 8)));
+}
+
+static int pca9532_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
+{
+        /* To use as input ensure pin is not driven */
+        pca9532_gpio_set_value(gc, offset, 0);
+
+        return 0;
+}
+
+static int pca9532_gpio_direction_output(struct gpio_chip *gc, unsigned offset, int val)
+{
+        pca9532_gpio_set_value(gc, offset, val);
+
+        return 0;
+}
+#endif /* CONFIG_LEDS_PCA9532_GPIO */
+
+static int pca9532_destroy_devices(struct pca9532_data *data, int n_devs)
 {
         int i = n_devs;
 
         if (!data)
-                return;
+                return -EINVAL;
 
         while (--i >= 0) {
                 switch (data->leds[i].type) {
                 case PCA9532_TYPE_NONE:
+                case PCA9532_TYPE_GPIO:
                         break;
                 case PCA9532_TYPE_LED:
                         led_classdev_unregister(&data->leds[i].ldev);
@@ -224,23 +318,38 @@ static void pca9532_destroy_devices(struct pca9532_data *data, int n_devs)
                         break;
                 }
         }
+
+#ifdef CONFIG_LEDS_PCA9532_GPIO
+        if (data->gpio.dev) {
+                int err = gpiochip_remove(&data->gpio);
+                if (err) {
+                        dev_err(&data->client->dev, "%s failed, %d\n",
+                                                "gpiochip_remove()", err);
+                        return err;
+                }
+        }
+#endif
+
+        return 0;
 }
 
 static int pca9532_configure(struct i2c_client *client,
         struct pca9532_data *data, struct pca9532_platform_data *pdata)
 {
         int i, err = 0;
+        int gpios = 0;
+        u8 maxleds = data->chip_info->num_leds;
 
         for (i = 0; i < 2; i++) {
                 data->pwm[i] = pdata->pwm[i];
                 data->psc[i] = pdata->psc[i];
-                i2c_smbus_write_byte_data(client, PCA9532_REG_PWM(i),
+                i2c_smbus_write_byte_data(client, PCA9532_REG_PWM(maxleds, i),
                         data->pwm[i]);
-                i2c_smbus_write_byte_data(client, PCA9532_REG_PSC(i),
+                i2c_smbus_write_byte_data(client, PCA9532_REG_PSC(maxleds, i),
                         data->psc[i]);
         }
 
-        for (i = 0; i < 16; i++) {
+        for (i = 0; i < data->chip_info->num_leds; i++) {
                 struct pca9532_led *led = &data->leds[i];
                 struct pca9532_led *pled = &pdata->leds[i];
                 led->client = client;
@@ -249,6 +358,9 @@ static int pca9532_configure(struct i2c_client *client,
                 switch (led->type) {
                 case PCA9532_TYPE_NONE:
                         break;
+                case PCA9532_TYPE_GPIO:
+                        gpios++;
+                        break;
                 case PCA9532_TYPE_LED:
                         led->state = pled->state;
                         led->name = pled->name;
@@ -297,6 +409,34 @@ static int pca9532_configure(struct i2c_client *client,
                         break;
                 }
         }
+
+#ifdef CONFIG_LEDS_PCA9532_GPIO
+        if (gpios) {
+                data->gpio.label = "gpio-pca9532";
+                data->gpio.direction_input = pca9532_gpio_direction_input;
+                data->gpio.direction_output = pca9532_gpio_direction_output;
+                data->gpio.set = pca9532_gpio_set_value;
+                data->gpio.get = pca9532_gpio_get_value;
+                data->gpio.request = pca9532_gpio_request_pin;
+                data->gpio.can_sleep = 1;
+                data->gpio.base = pdata->gpio_base;
+                data->gpio.ngpio = data->chip_info->num_leds;
+                data->gpio.dev = &client->dev;
+                data->gpio.owner = THIS_MODULE;
+
+                err = gpiochip_add(&data->gpio);
+                if (err) {
+                        /* Use data->gpio.dev as a flag for freeing gpiochip */
+                        data->gpio.dev = NULL;
+                        dev_warn(&client->dev, "could not add gpiochip\n");
+                } else {
+                        dev_info(&client->dev, "gpios %i...%i\n",
+                                data->gpio.base, data->gpio.base +
+                                data->gpio.ngpio - 1);
+                }
+        }
+#endif
+
         return 0;
 
 exit:
@@ -322,6 +462,8 @@ static int pca9532_probe(struct i2c_client *client,
         if (!data)
                 return -ENOMEM;
 
+        data->chip_info = &pca9532_chip_info_tbl[id->driver_data];
+
         dev_info(&client->dev, "setting platform data\n");
         i2c_set_clientdata(client, data);
         data->client = client;
@@ -337,7 +479,12 @@ static int pca9532_probe(struct i2c_client *client,
 static int pca9532_remove(struct i2c_client *client)
 {
         struct pca9532_data *data = i2c_get_clientdata(client);
-        pca9532_destroy_devices(data, 16);
+        int err;
+
+        err = pca9532_destroy_devices(data, data->chip_info->num_leds);
+        if (err)
+                return err;
+
         kfree(data);
         return 0;
 }
diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h
index 2dd8ecbfdc31..e77c7f8dcdd4 100644
--- a/drivers/leds/leds.h
+++ b/drivers/leds/leds.h
@@ -40,10 +40,17 @@ void led_trigger_set_default(struct led_classdev *led_cdev);
 void led_trigger_set(struct led_classdev *led_cdev,
                         struct led_trigger *trigger);
 void led_trigger_remove(struct led_classdev *led_cdev);
+
+static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
+{
+        return led_cdev->trigger_data;
+}
+
 #else
 #define led_trigger_set_default(x) do {} while (0)
 #define led_trigger_set(x, y) do {} while (0)
 #define led_trigger_remove(x) do {} while (0)
+#define led_get_trigger_data(x) (NULL)
 #endif
 
 ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/leds/ledtrig-timer.c b/drivers/leds/ledtrig-timer.c
index b09bcbeade9c..d87c9d02f786 100644
--- a/drivers/leds/ledtrig-timer.c
+++ b/drivers/leds/ledtrig-timer.c
@@ -91,6 +91,9 @@ static void timer_trig_activate(struct led_classdev *led_cdev)
         if (rc)
                 goto err_out_delayon;
 
+        led_blink_set(led_cdev, &led_cdev->blink_delay_on,
+                      &led_cdev->blink_delay_off);
+
         led_cdev->trigger_data = (void *)1;
 
         return;
diff --git a/drivers/media/video/omap/omap_vout.c b/drivers/media/video/omap/omap_vout.c
index d4fe7bc92a1d..4ada9be1d430 100644
--- a/drivers/media/video/omap/omap_vout.c
+++ b/drivers/media/video/omap/omap_vout.c
@@ -47,7 +47,7 @@
 #include <plat/dma.h>
 #include <plat/vram.h>
 #include <plat/vrfb.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #include "omap_voutlib.h"
 #include "omap_voutdef.h"
diff --git a/drivers/media/video/omap/omap_voutdef.h b/drivers/media/video/omap/omap_voutdef.h
index ea3a047f8bca..659497b84996 100644
--- a/drivers/media/video/omap/omap_voutdef.h
+++ b/drivers/media/video/omap/omap_voutdef.h
@@ -11,7 +11,7 @@
 #ifndef OMAP_VOUTDEF_H
 #define OMAP_VOUTDEF_H
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define YUYV_BPP        2
 #define RGB565_BPP      2
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 3ed3ff06be5d..481770ab2716 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -538,7 +538,7 @@ config AB8500_CORE
 
 config AB8500_I2C_CORE
         bool "AB8500 register access via PRCMU I2C"
-        depends on AB8500_CORE && UX500_SOC_DB8500
+        depends on AB8500_CORE && MFD_DB8500_PRCMU
         default y
         help
           This enables register access to the AB8500 chip via PRCMU I2C.
@@ -575,6 +575,26 @@ config AB3550_CORE
           LEDs, vibrator, system power and temperature, power management
           and ALSA sound.
 
+config MFD_DB8500_PRCMU
+        bool "ST-Ericsson DB8500 Power Reset Control Management Unit"
+        depends on UX500_SOC_DB8500
+        select MFD_CORE
+        help
+          Select this option to enable support for the DB8500 Power Reset
+          and Control Management Unit. This is basically an autonomous
+          system controller running an XP70 microprocessor, which is accessed
+          through a register map.
+
+config MFD_DB5500_PRCMU
+        bool "ST-Ericsson DB5500 Power Reset Control Management Unit"
+        depends on UX500_SOC_DB5500
+        select MFD_CORE
+        help
+          Select this option to enable support for the DB5500 Power Reset
+          and Control Management Unit. This is basically an autonomous
+          system controller running an XP70 microprocessor, which is accessed
+          through a register map.
+
 config MFD_CS5535
         tristate "Support for CS5535 and CS5536 southbridge core functions"
         select MFD_CORE
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 419caa9d7dcf..24aa44448daf 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -74,9 +74,12 @@ obj-$(CONFIG_AB3100_CORE)	+= ab3100-core.o
 obj-$(CONFIG_AB3100_OTP)        += ab3100-otp.o
 obj-$(CONFIG_AB3550_CORE)       += ab3550-core.o
 obj-$(CONFIG_AB8500_CORE)       += ab8500-core.o ab8500-sysctrl.o
-obj-$(CONFIG_AB8500_I2C_CORE)   += ab8500-i2c.o
 obj-$(CONFIG_AB8500_DEBUG)      += ab8500-debugfs.o
 obj-$(CONFIG_AB8500_GPADC)      += ab8500-gpadc.o
+obj-$(CONFIG_MFD_DB8500_PRCMU)  += db8500-prcmu.o
+# ab8500-i2c need to come after db8500-prcmu (which provides the channel)
+obj-$(CONFIG_AB8500_I2C_CORE)   += ab8500-i2c.o
+obj-$(CONFIG_MFD_DB5500_PRCMU)  += db5500-prcmu.o
 obj-$(CONFIG_MFD_TIMBERDALE)    += timberdale.o
 obj-$(CONFIG_PMIC_ADP5520)      += adp5520.o
 obj-$(CONFIG_LPC_SCH)           += lpc_sch.o
diff --git a/drivers/mfd/ab8500-i2c.c b/drivers/mfd/ab8500-i2c.c
index 821e6b86afd2..9be541c6b004 100644
--- a/drivers/mfd/ab8500-i2c.c
+++ b/drivers/mfd/ab8500-i2c.c
@@ -11,8 +11,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/ab8500.h>
-
-#include <mach/prcmu.h>
+#include <linux/mfd/db8500-prcmu.h>
 
 static int ab8500_i2c_write(struct ab8500 *ab8500, u16 addr, u8 data)
 {
diff --git a/arch/arm/mach-ux500/include/mach/prcmu-regs.h b/drivers/mfd/db5500-prcmu-regs.h
index 455467e88791..9a8e9e4ddd33 100644
--- a/arch/arm/mach-ux500/include/mach/prcmu-regs.h
+++ b/drivers/mfd/db5500-prcmu-regs.h
@@ -15,11 +15,20 @@
 
 #include <mach/hardware.h>
 
-#define _PRCMU_BASE             IO_ADDRESS(U8500_PRCMU_BASE)
-
 #define PRCM_ARM_PLLDIVPS       (_PRCMU_BASE + 0x118)
+#define PRCM_ARM_PLLDIVPS_ARM_BRM_RATE          0x3f
+#define PRCM_ARM_PLLDIVPS_MAX_MASK              0xf
+
+#define PRCM_PLLARM_LOCKP       (_PRCMU_BASE + 0x0a8)
+#define PRCM_PLLARM_LOCKP_PRCM_PLLARM_LOCKP3    0x2
+
 #define PRCM_ARM_CHGCLKREQ      (_PRCMU_BASE + 0x114)
+#define PRCM_ARM_CHGCLKREQ_PRCM_ARM_CHGCLKREQ   0x1
+
 #define PRCM_PLLARM_ENABLE      (_PRCMU_BASE + 0x98)
+#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_ENABLE   0x1
+#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_COUNTON  0x100
+
 #define PRCM_ARMCLKFIX_MGT      (_PRCMU_BASE + 0x0)
 #define PRCM_A9_RESETN_CLR      (_PRCMU_BASE + 0x1f4)
 #define PRCM_A9_RESETN_SET      (_PRCMU_BASE + 0x1f0)
@@ -28,7 +37,8 @@
 
 /* ARM WFI Standby signal register */
 #define PRCM_ARM_WFI_STANDBY    (_PRCMU_BASE + 0x130)
-#define PRCMU_IOCR              (_PRCMU_BASE + 0x310)
+#define PRCM_IOCR               (_PRCMU_BASE + 0x310)
+#define PRCM_IOCR_IOFORCE                       0x1
 
 /* CPU mailbox registers */
 #define PRCM_MBOX_CPU_VAL       (_PRCMU_BASE + 0x0fc)
@@ -37,6 +47,8 @@
 
 /* Dual A9 core interrupt management unit registers */
 #define PRCM_A9_MASK_REQ        (_PRCMU_BASE + 0x328)
+#define PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ       0x1
+
 #define PRCM_A9_MASK_ACK        (_PRCMU_BASE + 0x32c)
 #define PRCM_ARMITMSK31TO0      (_PRCMU_BASE + 0x11c)
 #define PRCM_ARMITMSK63TO32     (_PRCMU_BASE + 0x120)
@@ -74,14 +86,17 @@
 /* PRCMU clock/PLL/reset registers */
 #define PRCM_PLLDSI_FREQ           (_PRCMU_BASE + 0x500)
 #define PRCM_PLLDSI_ENABLE         (_PRCMU_BASE + 0x504)
+#define PRCM_PLLDSI_LOCKP          (_PRCMU_BASE + 0x508)
 #define PRCM_LCDCLK_MGT            (_PRCMU_BASE + 0x044)
 #define PRCM_MCDECLK_MGT           (_PRCMU_BASE + 0x064)
 #define PRCM_HDMICLK_MGT           (_PRCMU_BASE + 0x058)
 #define PRCM_TVCLK_MGT             (_PRCMU_BASE + 0x07c)
 #define PRCM_DSI_PLLOUT_SEL        (_PRCMU_BASE + 0x530)
 #define PRCM_DSITVCLK_DIV          (_PRCMU_BASE + 0x52C)
+#define PRCM_PLLDSI_LOCKP          (_PRCMU_BASE + 0x508)
 #define PRCM_APE_RESETN_SET        (_PRCMU_BASE + 0x1E4)
 #define PRCM_APE_RESETN_CLR        (_PRCMU_BASE + 0x1E8)
+#define PRCM_CLKOCR                (_PRCMU_BASE + 0x1CC)
 
 /* ePOD and memory power signal control registers */
 #define PRCM_EPOD_C_SET            (_PRCMU_BASE + 0x410)
@@ -92,5 +107,9 @@
 
 /* Miscellaneous unit registers */
 #define PRCM_DSI_SW_RESET          (_PRCMU_BASE + 0x324)
+#define PRCM_GPIOCR                (_PRCMU_BASE + 0x138)
+#define PRCM_GPIOCR_DBG_STM_MOD_CMD1            0x800
+#define PRCM_GPIOCR_DBG_UARTMOD_CMD0            0x1
+
 
-#endif /* __MACH_PRCMU_REGS_H */
+#endif /* __MACH_PRCMU__REGS_H */
diff --git a/drivers/mfd/db5500-prcmu.c b/drivers/mfd/db5500-prcmu.c
new file mode 100644
index 000000000000..9dbb3cab4a6f
--- /dev/null
+++ b/drivers/mfd/db5500-prcmu.c
@@ -0,0 +1,448 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
+ *
+ * U5500 PRCM Unit interface driver
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/completion.h>
+#include <linux/irq.h>
+#include <linux/jiffies.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/db5500-prcmu.h>
+#include <mach/hardware.h>
+#include <mach/irqs.h>
+#include <mach/db5500-regs.h>
+#include "db5500-prcmu-regs.h"
+
+#define _PRCM_MB_HEADER (tcdm_base + 0xFE8)
+#define PRCM_REQ_MB0_HEADER (_PRCM_MB_HEADER + 0x0)
+#define PRCM_REQ_MB1_HEADER (_PRCM_MB_HEADER + 0x1)
+#define PRCM_REQ_MB2_HEADER (_PRCM_MB_HEADER + 0x2)
+#define PRCM_REQ_MB3_HEADER (_PRCM_MB_HEADER + 0x3)
+#define PRCM_REQ_MB4_HEADER (_PRCM_MB_HEADER + 0x4)
+#define PRCM_REQ_MB5_HEADER (_PRCM_MB_HEADER + 0x5)
+#define PRCM_REQ_MB6_HEADER (_PRCM_MB_HEADER + 0x6)
+#define PRCM_REQ_MB7_HEADER (_PRCM_MB_HEADER + 0x7)
+#define PRCM_ACK_MB0_HEADER (_PRCM_MB_HEADER + 0x8)
+#define PRCM_ACK_MB1_HEADER (_PRCM_MB_HEADER + 0x9)
+#define PRCM_ACK_MB2_HEADER (_PRCM_MB_HEADER + 0xa)
+#define PRCM_ACK_MB3_HEADER (_PRCM_MB_HEADER + 0xb)
+#define PRCM_ACK_MB4_HEADER (_PRCM_MB_HEADER + 0xc)
+#define PRCM_ACK_MB5_HEADER (_PRCM_MB_HEADER + 0xd)
+#define PRCM_ACK_MB6_HEADER (_PRCM_MB_HEADER + 0xe)
+#define PRCM_ACK_MB7_HEADER (_PRCM_MB_HEADER + 0xf)
+
+/* Req Mailboxes */
+#define PRCM_REQ_MB0 (tcdm_base + 0xFD8)
+#define PRCM_REQ_MB1 (tcdm_base + 0xFCC)
+#define PRCM_REQ_MB2 (tcdm_base + 0xFC4)
+#define PRCM_REQ_MB3 (tcdm_base + 0xFC0)
+#define PRCM_REQ_MB4 (tcdm_base + 0xF98)
+#define PRCM_REQ_MB5 (tcdm_base + 0xF90)
+#define PRCM_REQ_MB6 (tcdm_base + 0xF8C)
+#define PRCM_REQ_MB7 (tcdm_base + 0xF84)
+
+/* Ack Mailboxes */
+#define PRCM_ACK_MB0 (tcdm_base + 0xF38)
+#define PRCM_ACK_MB1 (tcdm_base + 0xF30)
+#define PRCM_ACK_MB2 (tcdm_base + 0xF24)
+#define PRCM_ACK_MB3 (tcdm_base + 0xF20)
+#define PRCM_ACK_MB4 (tcdm_base + 0xF1C)
+#define PRCM_ACK_MB5 (tcdm_base + 0xF14)
+#define PRCM_ACK_MB6 (tcdm_base + 0xF0C)
+#define PRCM_ACK_MB7 (tcdm_base + 0xF08)
+
+enum mb_return_code {
+        RC_SUCCESS,
+        RC_FAIL,
+};
+
+/* Mailbox 0 headers. */
+enum mb0_header {
+        /* request */
+        RMB0H_PWR_STATE_TRANS = 1,
+        RMB0H_WAKE_UP_CFG,
+        RMB0H_RD_WAKE_UP_ACK,
+        /* acknowledge */
+        AMB0H_WAKE_UP = 1,
+};
+
+/* Mailbox 5 headers. */
+enum mb5_header {
+        MB5H_I2C_WRITE = 1,
+        MB5H_I2C_READ,
+};
+
+/* Request mailbox 5 fields. */
+#define PRCM_REQ_MB5_I2C_SLAVE (PRCM_REQ_MB5 + 0)
+#define PRCM_REQ_MB5_I2C_REG (PRCM_REQ_MB5 + 1)
+#define PRCM_REQ_MB5_I2C_SIZE (PRCM_REQ_MB5 + 2)
+#define PRCM_REQ_MB5_I2C_DATA (PRCM_REQ_MB5 + 4)
+
+/* Acknowledge mailbox 5 fields. */
+#define PRCM_ACK_MB5_RETURN_CODE (PRCM_ACK_MB5 + 0)
+#define PRCM_ACK_MB5_I2C_DATA (PRCM_ACK_MB5 + 4)
+
+#define NUM_MB 8
+#define MBOX_BIT BIT
+#define ALL_MBOX_BITS (MBOX_BIT(NUM_MB) - 1)
+
+/*
+* Used by MCDE to setup all necessary PRCMU registers
+*/
+#define PRCMU_RESET_DSIPLL                      0x00004000
+#define PRCMU_UNCLAMP_DSIPLL                    0x00400800
+
+/* HDMI CLK MGT PLLSW=001 (PLLSOC0), PLLDIV=0x8, = 50 Mhz*/
+#define PRCMU_DSI_CLOCK_SETTING                 0x00000128
+/* TVCLK_MGT PLLSW=001 (PLLSOC0) PLLDIV=0x13, = 19.05 MHZ */
+#define PRCMU_DSI_LP_CLOCK_SETTING              0x00000135
+#define PRCMU_PLLDSI_FREQ_SETTING               0x0004013C
+#define PRCMU_DSI_PLLOUT_SEL_SETTING            0x00000002
+#define PRCMU_ENABLE_ESCAPE_CLOCK_DIV           0x03000101
+#define PRCMU_DISABLE_ESCAPE_CLOCK_DIV          0x00000101
+
+#define PRCMU_ENABLE_PLLDSI                     0x00000001
+#define PRCMU_DISABLE_PLLDSI                    0x00000000
+
+#define PRCMU_DSI_RESET_SW                      0x00000003
+
+#define PRCMU_PLLDSI_LOCKP_LOCKED               0x3
+
+/*
+ * mb0_transfer - state needed for mailbox 0 communication.
+ * @lock:               The transaction lock.
+ */
+static struct {
+        spinlock_t lock;
+} mb0_transfer;
+
+/*
+ * mb5_transfer - state needed for mailbox 5 communication.
+ * @lock:       The transaction lock.
+ * @work:       The transaction completion structure.
+ * @ack:        Reply ("acknowledge") data.
+ */
+static struct {
+        struct mutex lock;
+        struct completion work;
+        struct {
+                u8 header;
+                u8 status;
+                u8 value[4];
+        } ack;
+} mb5_transfer;
+
+/* PRCMU TCDM base IO address. */
+static __iomem void *tcdm_base;
+
+/**
+ * db5500_prcmu_abb_read() - Read register value(s) from the ABB.
+ * @slave:      The I2C slave address.
+ * @reg:        The (start) register address.
+ * @value:      The read out value(s).
+ * @size:       The number of registers to read.
+ *
+ * Reads register value(s) from the ABB.
+ * @size has to be <= 4.
+ */
+int db5500_prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        int r;
+
+        if ((size < 1) || (4 < size))
+                return -EINVAL;
+
+        mutex_lock(&mb5_transfer.lock);
+
+        while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+                cpu_relax();
+        writeb(slave, PRCM_REQ_MB5_I2C_SLAVE);
+        writeb(reg, PRCM_REQ_MB5_I2C_REG);
+        writeb(size, PRCM_REQ_MB5_I2C_SIZE);
+        writeb(MB5H_I2C_READ, PRCM_REQ_MB5_HEADER);
+
+        writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
+        wait_for_completion(&mb5_transfer.work);
+
+        r = 0;
+        if ((mb5_transfer.ack.header == MB5H_I2C_READ) &&
+                (mb5_transfer.ack.status == RC_SUCCESS))
+                memcpy(value, mb5_transfer.ack.value, (size_t)size);
+        else
+                r = -EIO;
+
+        mutex_unlock(&mb5_transfer.lock);
+
+        return r;
+}
+
+/**
+ * db5500_prcmu_abb_write() - Write register value(s) to the ABB.
+ * @slave:      The I2C slave address.
+ * @reg:        The (start) register address.
+ * @value:      The value(s) to write.
+ * @size:       The number of registers to write.
+ *
+ * Writes register value(s) to the ABB.
+ * @size has to be <= 4.
+ */
+int db5500_prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        int r;
+
+        if ((size < 1) || (4 < size))
+                return -EINVAL;
+
+        mutex_lock(&mb5_transfer.lock);
+
+        while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+                cpu_relax();
+        writeb(slave, PRCM_REQ_MB5_I2C_SLAVE);
+        writeb(reg, PRCM_REQ_MB5_I2C_REG);
+        writeb(size, PRCM_REQ_MB5_I2C_SIZE);
+        memcpy_toio(PRCM_REQ_MB5_I2C_DATA, value, size);
+        writeb(MB5H_I2C_WRITE, PRCM_REQ_MB5_HEADER);
+
+        writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
+        wait_for_completion(&mb5_transfer.work);
+
+        if ((mb5_transfer.ack.header == MB5H_I2C_WRITE) &&
+                (mb5_transfer.ack.status == RC_SUCCESS))
+                r = 0;
+        else
+                r = -EIO;
+
+        mutex_unlock(&mb5_transfer.lock);
+
+        return r;
+}
+
+int db5500_prcmu_enable_dsipll(void)
+{
+        int i;
+
+        /* Enable DSIPLL_RESETN resets */
+        writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_CLR);
+        /* Unclamp DSIPLL in/out */
+        writel(PRCMU_UNCLAMP_DSIPLL, PRCM_MMIP_LS_CLAMP_CLR);
+        /* Set DSI PLL FREQ */
+        writel(PRCMU_PLLDSI_FREQ_SETTING, PRCM_PLLDSI_FREQ);
+        writel(PRCMU_DSI_PLLOUT_SEL_SETTING,
+                PRCM_DSI_PLLOUT_SEL);
+        /* Enable Escape clocks */
+        writel(PRCMU_ENABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
+
+        /* Start DSI PLL */
+        writel(PRCMU_ENABLE_PLLDSI, PRCM_PLLDSI_ENABLE);
+        /* Reset DSI PLL */
+        writel(PRCMU_DSI_RESET_SW, PRCM_DSI_SW_RESET);
+        for (i = 0; i < 10; i++) {
+                if ((readl(PRCM_PLLDSI_LOCKP) &
+                        PRCMU_PLLDSI_LOCKP_LOCKED) == PRCMU_PLLDSI_LOCKP_LOCKED)
+                        break;
+                udelay(100);
+        }
+        /* Release DSIPLL_RESETN */
+        writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_SET);
+        return 0;
+}
+
+int db5500_prcmu_disable_dsipll(void)
+{
+        /* Disable dsi pll */
+        writel(PRCMU_DISABLE_PLLDSI, PRCM_PLLDSI_ENABLE);
+        /* Disable  escapeclock */
+        writel(PRCMU_DISABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
+        return 0;
+}
+
+int db5500_prcmu_set_display_clocks(void)
+{
+        /* HDMI and TVCLK Should be handled somewhere else */
+        /* PLLDIV=8, PLLSW=2, CLKEN=1 */
+        writel(PRCMU_DSI_CLOCK_SETTING, PRCM_HDMICLK_MGT);
+        /* PLLDIV=14, PLLSW=2, CLKEN=1 */
+        writel(PRCMU_DSI_LP_CLOCK_SETTING, PRCM_TVCLK_MGT);
+        return 0;
+}
+
+static void ack_dbb_wakeup(void)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&mb0_transfer.lock, flags);
+
+        while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+                cpu_relax();
+
+        writeb(RMB0H_RD_WAKE_UP_ACK, PRCM_REQ_MB0_HEADER);
+        writel(MBOX_BIT(0), PRCM_MBOX_CPU_SET);
+
+        spin_unlock_irqrestore(&mb0_transfer.lock, flags);
+}
+
+static inline void print_unknown_header_warning(u8 n, u8 header)
+{
+        pr_warning("prcmu: Unknown message header (%d) in mailbox %d.\n",
+                header, n);
+}
+
+static bool read_mailbox_0(void)
+{
+        bool r;
+        u8 header;
+
+        header = readb(PRCM_ACK_MB0_HEADER);
+        switch (header) {
+        case AMB0H_WAKE_UP:
+                r = true;
+                break;
+        default:
+                print_unknown_header_warning(0, header);
+                r = false;
+                break;
+        }
+        writel(MBOX_BIT(0), PRCM_ARM_IT1_CLEAR);
+        return r;
+}
+
+static bool read_mailbox_1(void)
+{
+        writel(MBOX_BIT(1), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool read_mailbox_2(void)
+{
+        writel(MBOX_BIT(2), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool read_mailbox_3(void)
+{
+        writel(MBOX_BIT(3), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool read_mailbox_4(void)
+{
+        writel(MBOX_BIT(4), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool read_mailbox_5(void)
+{
+        u8 header;
+
+        header = readb(PRCM_ACK_MB5_HEADER);
+        switch (header) {
+        case MB5H_I2C_READ:
+                memcpy_fromio(mb5_transfer.ack.value, PRCM_ACK_MB5_I2C_DATA, 4);
+        case MB5H_I2C_WRITE:
+                mb5_transfer.ack.header = header;
+                mb5_transfer.ack.status = readb(PRCM_ACK_MB5_RETURN_CODE);
+                complete(&mb5_transfer.work);
+                break;
+        default:
+                print_unknown_header_warning(5, header);
+                break;
+        }
+        writel(MBOX_BIT(5), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool read_mailbox_6(void)
+{
+        writel(MBOX_BIT(6), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool read_mailbox_7(void)
+{
+        writel(MBOX_BIT(7), PRCM_ARM_IT1_CLEAR);
+        return false;
+}
+
+static bool (* const read_mailbox[NUM_MB])(void) = {
+        read_mailbox_0,
+        read_mailbox_1,
+        read_mailbox_2,
+        read_mailbox_3,
+        read_mailbox_4,
+        read_mailbox_5,
+        read_mailbox_6,
+        read_mailbox_7
+};
+
+static irqreturn_t prcmu_irq_handler(int irq, void *data)
+{
+        u32 bits;
+        u8 n;
+        irqreturn_t r;
+
+        bits = (readl(PRCM_ARM_IT1_VAL) & ALL_MBOX_BITS);
+        if (unlikely(!bits))
+                return IRQ_NONE;
+
+        r = IRQ_HANDLED;
+        for (n = 0; bits; n++) {
+                if (bits & MBOX_BIT(n)) {
+                        bits -= MBOX_BIT(n);
+                        if (read_mailbox[n]())
+                                r = IRQ_WAKE_THREAD;
+                }
+        }
+        return r;
+}
+
+static irqreturn_t prcmu_irq_thread_fn(int irq, void *data)
+{
+        ack_dbb_wakeup();
+        return IRQ_HANDLED;
+}
+
+void __init db5500_prcmu_early_init(void)
+{
+        tcdm_base = __io_address(U5500_PRCMU_TCDM_BASE);
+        spin_lock_init(&mb0_transfer.lock);
+        mutex_init(&mb5_transfer.lock);
+        init_completion(&mb5_transfer.work);
+}
+
+/**
+ * prcmu_fw_init - arch init call for the Linux PRCMU fw init logic
+ *
+ */
+int __init db5500_prcmu_init(void)
+{
+        int r = 0;
+
+        if (ux500_is_svp() || !cpu_is_u5500())
+                return -ENODEV;
+
+        /* Clean up the mailbox interrupts after pre-kernel code. */
+        writel(ALL_MBOX_BITS, PRCM_ARM_IT1_CLEAR);
+
+        r = request_threaded_irq(IRQ_DB5500_PRCMU1, prcmu_irq_handler,
+                prcmu_irq_thread_fn, 0, "prcmu", NULL);
+        if (r < 0) {
+                pr_err("prcmu: Failed to allocate IRQ_DB5500_PRCMU1.\n");
+                return -EBUSY;
+        }
+        return 0;
+}
+
+arch_initcall(db5500_prcmu_init);
diff --git a/drivers/mfd/db8500-prcmu-regs.h b/drivers/mfd/db8500-prcmu-regs.h
new file mode 100644
index 000000000000..3bbf04d58043
--- /dev/null
+++ b/drivers/mfd/db8500-prcmu-regs.h
@@ -0,0 +1,166 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * PRCM Unit registers
+ */
+#ifndef __DB8500_PRCMU_REGS_H
+#define __DB8500_PRCMU_REGS_H
+
+#include <linux/bitops.h>
+#include <mach/hardware.h>
+
+#define BITS(_start, _end) ((BIT(_end) - BIT(_start)) + BIT(_end))
+
+#define PRCM_ARM_PLLDIVPS 0x118
+#define PRCM_ARM_PLLDIVPS_ARM_BRM_RATE  BITS(0, 5)
+#define PRCM_ARM_PLLDIVPS_MAX_MASK      0xF
+
+#define PRCM_PLLARM_LOCKP 0x0A8
+#define PRCM_PLLARM_LOCKP_PRCM_PLLARM_LOCKP3 BIT(1)
+
+#define PRCM_ARM_CHGCLKREQ 0x114
+#define PRCM_ARM_CHGCLKREQ_PRCM_ARM_CHGCLKREQ BIT(0)
+
+#define PRCM_PLLARM_ENABLE 0x98
+#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_ENABLE   BIT(0)
+#define PRCM_PLLARM_ENABLE_PRCM_PLLARM_COUNTON  BIT(8)
+
+#define PRCM_ARMCLKFIX_MGT      0x0
+#define PRCM_A9_RESETN_CLR      0x1f4
+#define PRCM_A9_RESETN_SET      0x1f0
+#define PRCM_ARM_LS_CLAMP       0x30C
+#define PRCM_SRAM_A9            0x308
+
+/* ARM WFI Standby signal register */
+#define PRCM_ARM_WFI_STANDBY    0x130
+#define PRCM_IOCR               0x310
+#define PRCM_IOCR_IOFORCE BIT(0)
+
+/* CPU mailbox registers */
+#define PRCM_MBOX_CPU_VAL 0x0FC
+#define PRCM_MBOX_CPU_SET 0x100
+
+/* Dual A9 core interrupt management unit registers */
+#define PRCM_A9_MASK_REQ 0x328
+#define PRCM_A9_MASK_REQ_PRCM_A9_MASK_REQ BIT(0)
+
+#define PRCM_A9_MASK_ACK        0x32C
+#define PRCM_ARMITMSK31TO0      0x11C
+#define PRCM_ARMITMSK63TO32     0x120
+#define PRCM_ARMITMSK95TO64     0x124
+#define PRCM_ARMITMSK127TO96    0x128
+#define PRCM_POWER_STATE_VAL    0x25C
+#define PRCM_ARMITVAL31TO0      0x260
+#define PRCM_ARMITVAL63TO32     0x264
+#define PRCM_ARMITVAL95TO64     0x268
+#define PRCM_ARMITVAL127TO96    0x26C
+
+#define PRCM_HOSTACCESS_REQ 0x334
+#define PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ BIT(0)
+
+#define PRCM_ARM_IT1_CLR 0x48C
+#define PRCM_ARM_IT1_VAL 0x494
+
+#define PRCM_ITSTATUS0          0x148
+#define PRCM_ITSTATUS1          0x150
+#define PRCM_ITSTATUS2          0x158
+#define PRCM_ITSTATUS3          0x160
+#define PRCM_ITSTATUS4          0x168
+#define PRCM_ITSTATUS5          0x484
+#define PRCM_ITCLEAR5           0x488
+#define PRCM_ARMIT_MASKXP70_IT  0x1018
+
+/* System reset register */
+#define PRCM_APE_SOFTRST 0x228
+
+/* Level shifter and clamp control registers */
+#define PRCM_MMIP_LS_CLAMP_SET 0x420
+#define PRCM_MMIP_LS_CLAMP_CLR 0x424
+
+/* PRCMU HW semaphore */
+#define PRCM_SEM 0x400
+#define PRCM_SEM_PRCM_SEM BIT(0)
+
+/* PRCMU clock/PLL/reset registers */
+#define PRCM_PLLDSI_FREQ        0x500
+#define PRCM_PLLDSI_ENABLE      0x504
+#define PRCM_PLLDSI_LOCKP       0x508
+#define PRCM_DSI_PLLOUT_SEL     0x530
+#define PRCM_DSITVCLK_DIV       0x52C
+#define PRCM_APE_RESETN_SET     0x1E4
+#define PRCM_APE_RESETN_CLR     0x1E8
+
+#define PRCM_TCR                0x1C8
+#define PRCM_TCR_TENSEL_MASK    BITS(0, 7)
+#define PRCM_TCR_STOP_TIMERS    BIT(16)
+#define PRCM_TCR_DOZE_MODE      BIT(17)
+
+#define PRCM_CLKOCR                     0x1CC
+#define PRCM_CLKOCR_CLKODIV0_SHIFT      0
+#define PRCM_CLKOCR_CLKODIV0_MASK       BITS(0, 5)
+#define PRCM_CLKOCR_CLKOSEL0_SHIFT      6
+#define PRCM_CLKOCR_CLKOSEL0_MASK       BITS(6, 8)
+#define PRCM_CLKOCR_CLKODIV1_SHIFT      16
+#define PRCM_CLKOCR_CLKODIV1_MASK       BITS(16, 21)
+#define PRCM_CLKOCR_CLKOSEL1_SHIFT      22
+#define PRCM_CLKOCR_CLKOSEL1_MASK       BITS(22, 24)
+#define PRCM_CLKOCR_CLK1TYPE            BIT(28)
+
+#define PRCM_SGACLK_MGT         0x014
+#define PRCM_UARTCLK_MGT        0x018
+#define PRCM_MSP02CLK_MGT       0x01C
+#define PRCM_MSP1CLK_MGT        0x288
+#define PRCM_I2CCLK_MGT         0x020
+#define PRCM_SDMMCCLK_MGT       0x024
+#define PRCM_SLIMCLK_MGT        0x028
+#define PRCM_PER1CLK_MGT        0x02C
+#define PRCM_PER2CLK_MGT        0x030
+#define PRCM_PER3CLK_MGT        0x034
+#define PRCM_PER5CLK_MGT        0x038
+#define PRCM_PER6CLK_MGT        0x03C
+#define PRCM_PER7CLK_MGT        0x040
+#define PRCM_LCDCLK_MGT         0x044
+#define PRCM_BMLCLK_MGT         0x04C
+#define PRCM_HSITXCLK_MGT       0x050
+#define PRCM_HSIRXCLK_MGT       0x054
+#define PRCM_HDMICLK_MGT        0x058
+#define PRCM_APEATCLK_MGT       0x05C
+#define PRCM_APETRACECLK_MGT    0x060
+#define PRCM_MCDECLK_MGT        0x064
+#define PRCM_IPI2CCLK_MGT       0x068
+#define PRCM_DSIALTCLK_MGT      0x06C
+#define PRCM_DMACLK_MGT         0x074
+#define PRCM_B2R2CLK_MGT        0x078
+#define PRCM_TVCLK_MGT          0x07C
+#define PRCM_UNIPROCLK_MGT      0x278
+#define PRCM_SSPCLK_MGT         0x280
+#define PRCM_RNGCLK_MGT         0x284
+#define PRCM_UICCCLK_MGT        0x27C
+
+#define PRCM_CLK_MGT_CLKPLLDIV_MASK     BITS(0, 4)
+#define PRCM_CLK_MGT_CLKPLLSW_MASK      BITS(5, 7)
+#define PRCM_CLK_MGT_CLKEN              BIT(8)
+
+/* ePOD and memory power signal control registers */
+#define PRCM_EPOD_C_SET         0x410
+#define PRCM_SRAM_LS_SLEEP      0x304
+
+/* Debug power control unit registers */
+#define PRCM_POWER_STATE_SET 0x254
+
+/* Miscellaneous unit registers */
+#define PRCM_DSI_SW_RESET 0x324
+#define PRCM_GPIOCR             0x138
+
+/* GPIOCR register */
+#define PRCM_GPIOCR_SPI2_SELECT BIT(23)
+
+#define PRCM_DDR_SUBSYS_APE_MINBW  0x438
+
+#endif /* __DB8500_PRCMU_REGS_H */
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
new file mode 100644
index 000000000000..e63782107e2f
--- /dev/null
+++ b/drivers/mfd/db8500-prcmu.c
@@ -0,0 +1,2069 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
+ *
+ * U8500 PRCM Unit interface driver
+ *
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/completion.h>
+#include <linux/irq.h>
+#include <linux/jiffies.h>
+#include <linux/bitops.h>
+#include <linux/fs.h>
+#include <linux/platform_device.h>
+#include <linux/uaccess.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/db8500-prcmu.h>
+#include <linux/regulator/db8500-prcmu.h>
+#include <linux/regulator/machine.h>
+#include <mach/hardware.h>
+#include <mach/irqs.h>
+#include <mach/db8500-regs.h>
+#include <mach/id.h>
+#include "db8500-prcmu-regs.h"
+
+/* Offset for the firmware version within the TCPM */
+#define PRCMU_FW_VERSION_OFFSET 0xA4
+
+/* PRCMU project numbers, defined by PRCMU FW */
+#define PRCMU_PROJECT_ID_8500V1_0 1
+#define PRCMU_PROJECT_ID_8500V2_0 2
+#define PRCMU_PROJECT_ID_8400V2_0 3
+
+/* Index of different voltages to be used when accessing AVSData */
+#define PRCM_AVS_BASE           0x2FC
+#define PRCM_AVS_VBB_RET        (PRCM_AVS_BASE + 0x0)
+#define PRCM_AVS_VBB_MAX_OPP    (PRCM_AVS_BASE + 0x1)
+#define PRCM_AVS_VBB_100_OPP    (PRCM_AVS_BASE + 0x2)
+#define PRCM_AVS_VBB_50_OPP     (PRCM_AVS_BASE + 0x3)
+#define PRCM_AVS_VARM_MAX_OPP   (PRCM_AVS_BASE + 0x4)
+#define PRCM_AVS_VARM_100_OPP   (PRCM_AVS_BASE + 0x5)
+#define PRCM_AVS_VARM_50_OPP    (PRCM_AVS_BASE + 0x6)
+#define PRCM_AVS_VARM_RET       (PRCM_AVS_BASE + 0x7)
+#define PRCM_AVS_VAPE_100_OPP   (PRCM_AVS_BASE + 0x8)
+#define PRCM_AVS_VAPE_50_OPP    (PRCM_AVS_BASE + 0x9)
+#define PRCM_AVS_VMOD_100_OPP   (PRCM_AVS_BASE + 0xA)
+#define PRCM_AVS_VMOD_50_OPP    (PRCM_AVS_BASE + 0xB)
+#define PRCM_AVS_VSAFE          (PRCM_AVS_BASE + 0xC)
+
+#define PRCM_AVS_VOLTAGE                0
+#define PRCM_AVS_VOLTAGE_MASK           0x3f
+#define PRCM_AVS_ISSLOWSTARTUP          6
+#define PRCM_AVS_ISSLOWSTARTUP_MASK     (1 << PRCM_AVS_ISSLOWSTARTUP)
+#define PRCM_AVS_ISMODEENABLE           7
+#define PRCM_AVS_ISMODEENABLE_MASK      (1 << PRCM_AVS_ISMODEENABLE)
+
+#define PRCM_BOOT_STATUS        0xFFF
+#define PRCM_ROMCODE_A2P        0xFFE
+#define PRCM_ROMCODE_P2A        0xFFD
+#define PRCM_XP70_CUR_PWR_STATE 0xFFC      /* 4 BYTES */
+
+#define PRCM_SW_RST_REASON 0xFF8 /* 2 bytes */
+
+#define _PRCM_MBOX_HEADER               0xFE8 /* 16 bytes */
+#define PRCM_MBOX_HEADER_REQ_MB0        (_PRCM_MBOX_HEADER + 0x0)
+#define PRCM_MBOX_HEADER_REQ_MB1        (_PRCM_MBOX_HEADER + 0x1)
+#define PRCM_MBOX_HEADER_REQ_MB2        (_PRCM_MBOX_HEADER + 0x2)
+#define PRCM_MBOX_HEADER_REQ_MB3        (_PRCM_MBOX_HEADER + 0x3)
+#define PRCM_MBOX_HEADER_REQ_MB4        (_PRCM_MBOX_HEADER + 0x4)
+#define PRCM_MBOX_HEADER_REQ_MB5        (_PRCM_MBOX_HEADER + 0x5)
+#define PRCM_MBOX_HEADER_ACK_MB0        (_PRCM_MBOX_HEADER + 0x8)
+
+/* Req Mailboxes */
+#define PRCM_REQ_MB0 0xFDC /* 12 bytes  */
+#define PRCM_REQ_MB1 0xFD0 /* 12 bytes  */
+#define PRCM_REQ_MB2 0xFC0 /* 16 bytes  */
+#define PRCM_REQ_MB3 0xE4C /* 372 bytes  */
+#define PRCM_REQ_MB4 0xE48 /* 4 bytes  */
+#define PRCM_REQ_MB5 0xE44 /* 4 bytes  */
+
+/* Ack Mailboxes */
+#define PRCM_ACK_MB0 0xE08 /* 52 bytes  */
+#define PRCM_ACK_MB1 0xE04 /* 4 bytes */
+#define PRCM_ACK_MB2 0xE00 /* 4 bytes */
+#define PRCM_ACK_MB3 0xDFC /* 4 bytes */
+#define PRCM_ACK_MB4 0xDF8 /* 4 bytes */
+#define PRCM_ACK_MB5 0xDF4 /* 4 bytes */
+
+/* Mailbox 0 headers */
+#define MB0H_POWER_STATE_TRANS          0
+#define MB0H_CONFIG_WAKEUPS_EXE         1
+#define MB0H_READ_WAKEUP_ACK            3
+#define MB0H_CONFIG_WAKEUPS_SLEEP       4
+
+#define MB0H_WAKEUP_EXE 2
+#define MB0H_WAKEUP_SLEEP 5
+
+/* Mailbox 0 REQs */
+#define PRCM_REQ_MB0_AP_POWER_STATE     (PRCM_REQ_MB0 + 0x0)
+#define PRCM_REQ_MB0_AP_PLL_STATE       (PRCM_REQ_MB0 + 0x1)
+#define PRCM_REQ_MB0_ULP_CLOCK_STATE    (PRCM_REQ_MB0 + 0x2)
+#define PRCM_REQ_MB0_DO_NOT_WFI         (PRCM_REQ_MB0 + 0x3)
+#define PRCM_REQ_MB0_WAKEUP_8500        (PRCM_REQ_MB0 + 0x4)
+#define PRCM_REQ_MB0_WAKEUP_4500        (PRCM_REQ_MB0 + 0x8)
+
+/* Mailbox 0 ACKs */
+#define PRCM_ACK_MB0_AP_PWRSTTR_STATUS  (PRCM_ACK_MB0 + 0x0)
+#define PRCM_ACK_MB0_READ_POINTER       (PRCM_ACK_MB0 + 0x1)
+#define PRCM_ACK_MB0_WAKEUP_0_8500      (PRCM_ACK_MB0 + 0x4)
+#define PRCM_ACK_MB0_WAKEUP_0_4500      (PRCM_ACK_MB0 + 0x8)
+#define PRCM_ACK_MB0_WAKEUP_1_8500      (PRCM_ACK_MB0 + 0x1C)
+#define PRCM_ACK_MB0_WAKEUP_1_4500      (PRCM_ACK_MB0 + 0x20)
+#define PRCM_ACK_MB0_EVENT_4500_NUMBERS 20
+
+/* Mailbox 1 headers */
+#define MB1H_ARM_APE_OPP 0x0
+#define MB1H_RESET_MODEM 0x2
+#define MB1H_REQUEST_APE_OPP_100_VOLT 0x3
+#define MB1H_RELEASE_APE_OPP_100_VOLT 0x4
+#define MB1H_RELEASE_USB_WAKEUP 0x5
+
+/* Mailbox 1 Requests */
+#define PRCM_REQ_MB1_ARM_OPP                    (PRCM_REQ_MB1 + 0x0)
+#define PRCM_REQ_MB1_APE_OPP                    (PRCM_REQ_MB1 + 0x1)
+#define PRCM_REQ_MB1_APE_OPP_100_RESTORE        (PRCM_REQ_MB1 + 0x4)
+#define PRCM_REQ_MB1_ARM_OPP_100_RESTORE        (PRCM_REQ_MB1 + 0x8)
+
+/* Mailbox 1 ACKs */
+#define PRCM_ACK_MB1_CURRENT_ARM_OPP    (PRCM_ACK_MB1 + 0x0)
+#define PRCM_ACK_MB1_CURRENT_APE_OPP    (PRCM_ACK_MB1 + 0x1)
+#define PRCM_ACK_MB1_APE_VOLTAGE_STATUS (PRCM_ACK_MB1 + 0x2)
+#define PRCM_ACK_MB1_DVFS_STATUS        (PRCM_ACK_MB1 + 0x3)
+
+/* Mailbox 2 headers */
+#define MB2H_DPS        0x0
+#define MB2H_AUTO_PWR   0x1
+
+/* Mailbox 2 REQs */
+#define PRCM_REQ_MB2_SVA_MMDSP          (PRCM_REQ_MB2 + 0x0)
+#define PRCM_REQ_MB2_SVA_PIPE           (PRCM_REQ_MB2 + 0x1)
+#define PRCM_REQ_MB2_SIA_MMDSP          (PRCM_REQ_MB2 + 0x2)
+#define PRCM_REQ_MB2_SIA_PIPE           (PRCM_REQ_MB2 + 0x3)
+#define PRCM_REQ_MB2_SGA                (PRCM_REQ_MB2 + 0x4)
+#define PRCM_REQ_MB2_B2R2_MCDE          (PRCM_REQ_MB2 + 0x5)
+#define PRCM_REQ_MB2_ESRAM12            (PRCM_REQ_MB2 + 0x6)
+#define PRCM_REQ_MB2_ESRAM34            (PRCM_REQ_MB2 + 0x7)
+#define PRCM_REQ_MB2_AUTO_PM_SLEEP      (PRCM_REQ_MB2 + 0x8)
+#define PRCM_REQ_MB2_AUTO_PM_IDLE       (PRCM_REQ_MB2 + 0xC)
+
+/* Mailbox 2 ACKs */
+#define PRCM_ACK_MB2_DPS_STATUS (PRCM_ACK_MB2 + 0x0)
+#define HWACC_PWR_ST_OK 0xFE
+
+/* Mailbox 3 headers */
+#define MB3H_ANC        0x0
+#define MB3H_SIDETONE   0x1
+#define MB3H_SYSCLK     0xE
+
+/* Mailbox 3 Requests */
+#define PRCM_REQ_MB3_ANC_FIR_COEFF      (PRCM_REQ_MB3 + 0x0)
+#define PRCM_REQ_MB3_ANC_IIR_COEFF      (PRCM_REQ_MB3 + 0x20)
+#define PRCM_REQ_MB3_ANC_SHIFTER        (PRCM_REQ_MB3 + 0x60)
+#define PRCM_REQ_MB3_ANC_WARP           (PRCM_REQ_MB3 + 0x64)
+#define PRCM_REQ_MB3_SIDETONE_FIR_GAIN  (PRCM_REQ_MB3 + 0x68)
+#define PRCM_REQ_MB3_SIDETONE_FIR_COEFF (PRCM_REQ_MB3 + 0x6C)
+#define PRCM_REQ_MB3_SYSCLK_MGT         (PRCM_REQ_MB3 + 0x16C)
+
+/* Mailbox 4 headers */
+#define MB4H_DDR_INIT   0x0
+#define MB4H_MEM_ST     0x1
+#define MB4H_HOTDOG     0x12
+#define MB4H_HOTMON     0x13
+#define MB4H_HOT_PERIOD 0x14
+
+/* Mailbox 4 Requests */
+#define PRCM_REQ_MB4_DDR_ST_AP_SLEEP_IDLE       (PRCM_REQ_MB4 + 0x0)
+#define PRCM_REQ_MB4_DDR_ST_AP_DEEP_IDLE        (PRCM_REQ_MB4 + 0x1)
+#define PRCM_REQ_MB4_ESRAM0_ST                  (PRCM_REQ_MB4 + 0x3)
+#define PRCM_REQ_MB4_HOTDOG_THRESHOLD           (PRCM_REQ_MB4 + 0x0)
+#define PRCM_REQ_MB4_HOTMON_LOW                 (PRCM_REQ_MB4 + 0x0)
+#define PRCM_REQ_MB4_HOTMON_HIGH                (PRCM_REQ_MB4 + 0x1)
+#define PRCM_REQ_MB4_HOTMON_CONFIG              (PRCM_REQ_MB4 + 0x2)
+#define PRCM_REQ_MB4_HOT_PERIOD                 (PRCM_REQ_MB4 + 0x0)
+#define HOTMON_CONFIG_LOW                       BIT(0)
+#define HOTMON_CONFIG_HIGH                      BIT(1)
+
+/* Mailbox 5 Requests */
+#define PRCM_REQ_MB5_I2C_SLAVE_OP       (PRCM_REQ_MB5 + 0x0)
+#define PRCM_REQ_MB5_I2C_HW_BITS        (PRCM_REQ_MB5 + 0x1)
+#define PRCM_REQ_MB5_I2C_REG            (PRCM_REQ_MB5 + 0x2)
+#define PRCM_REQ_MB5_I2C_VAL            (PRCM_REQ_MB5 + 0x3)
+#define PRCMU_I2C_WRITE(slave) \
+        (((slave) << 1) | (cpu_is_u8500v2() ? BIT(6) : 0))
+#define PRCMU_I2C_READ(slave) \
+        (((slave) << 1) | BIT(0) | (cpu_is_u8500v2() ? BIT(6) : 0))
+#define PRCMU_I2C_STOP_EN               BIT(3)
+
+/* Mailbox 5 ACKs */
+#define PRCM_ACK_MB5_I2C_STATUS (PRCM_ACK_MB5 + 0x1)
+#define PRCM_ACK_MB5_I2C_VAL    (PRCM_ACK_MB5 + 0x3)
+#define I2C_WR_OK 0x1
+#define I2C_RD_OK 0x2
+
+#define NUM_MB 8
+#define MBOX_BIT BIT
+#define ALL_MBOX_BITS (MBOX_BIT(NUM_MB) - 1)
+
+/*
+ * Wakeups/IRQs
+ */
+
+#define WAKEUP_BIT_RTC BIT(0)
+#define WAKEUP_BIT_RTT0 BIT(1)
+#define WAKEUP_BIT_RTT1 BIT(2)
+#define WAKEUP_BIT_HSI0 BIT(3)
+#define WAKEUP_BIT_HSI1 BIT(4)
+#define WAKEUP_BIT_CA_WAKE BIT(5)
+#define WAKEUP_BIT_USB BIT(6)
+#define WAKEUP_BIT_ABB BIT(7)
+#define WAKEUP_BIT_ABB_FIFO BIT(8)
+#define WAKEUP_BIT_SYSCLK_OK BIT(9)
+#define WAKEUP_BIT_CA_SLEEP BIT(10)
+#define WAKEUP_BIT_AC_WAKE_ACK BIT(11)
+#define WAKEUP_BIT_SIDE_TONE_OK BIT(12)
+#define WAKEUP_BIT_ANC_OK BIT(13)
+#define WAKEUP_BIT_SW_ERROR BIT(14)
+#define WAKEUP_BIT_AC_SLEEP_ACK BIT(15)
+#define WAKEUP_BIT_ARM BIT(17)
+#define WAKEUP_BIT_HOTMON_LOW BIT(18)
+#define WAKEUP_BIT_HOTMON_HIGH BIT(19)
+#define WAKEUP_BIT_MODEM_SW_RESET_REQ BIT(20)
+#define WAKEUP_BIT_GPIO0 BIT(23)
+#define WAKEUP_BIT_GPIO1 BIT(24)
+#define WAKEUP_BIT_GPIO2 BIT(25)
+#define WAKEUP_BIT_GPIO3 BIT(26)
+#define WAKEUP_BIT_GPIO4 BIT(27)
+#define WAKEUP_BIT_GPIO5 BIT(28)
+#define WAKEUP_BIT_GPIO6 BIT(29)
+#define WAKEUP_BIT_GPIO7 BIT(30)
+#define WAKEUP_BIT_GPIO8 BIT(31)
+
+/*
+ * This vector maps irq numbers to the bits in the bit field used in
+ * communication with the PRCMU firmware.
+ *
+ * The reason for having this is to keep the irq numbers contiguous even though
+ * the bits in the bit field are not. (The bits also have a tendency to move
+ * around, to further complicate matters.)
+ */
+#define IRQ_INDEX(_name) ((IRQ_PRCMU_##_name) - IRQ_PRCMU_BASE)
+#define IRQ_ENTRY(_name)[IRQ_INDEX(_name)] = (WAKEUP_BIT_##_name)
+static u32 prcmu_irq_bit[NUM_PRCMU_WAKEUPS] = {
+        IRQ_ENTRY(RTC),
+        IRQ_ENTRY(RTT0),
+        IRQ_ENTRY(RTT1),
+        IRQ_ENTRY(HSI0),
+        IRQ_ENTRY(HSI1),
+        IRQ_ENTRY(CA_WAKE),
+        IRQ_ENTRY(USB),
+        IRQ_ENTRY(ABB),
+        IRQ_ENTRY(ABB_FIFO),
+        IRQ_ENTRY(CA_SLEEP),
+        IRQ_ENTRY(ARM),
+        IRQ_ENTRY(HOTMON_LOW),
+        IRQ_ENTRY(HOTMON_HIGH),
+        IRQ_ENTRY(MODEM_SW_RESET_REQ),
+        IRQ_ENTRY(GPIO0),
+        IRQ_ENTRY(GPIO1),
+        IRQ_ENTRY(GPIO2),
+        IRQ_ENTRY(GPIO3),
+        IRQ_ENTRY(GPIO4),
+        IRQ_ENTRY(GPIO5),
+        IRQ_ENTRY(GPIO6),
+        IRQ_ENTRY(GPIO7),
+        IRQ_ENTRY(GPIO8)
+};
+
+#define VALID_WAKEUPS (BIT(NUM_PRCMU_WAKEUP_INDICES) - 1)
+#define WAKEUP_ENTRY(_name)[PRCMU_WAKEUP_INDEX_##_name] = (WAKEUP_BIT_##_name)
+static u32 prcmu_wakeup_bit[NUM_PRCMU_WAKEUP_INDICES] = {
+        WAKEUP_ENTRY(RTC),
+        WAKEUP_ENTRY(RTT0),
+        WAKEUP_ENTRY(RTT1),
+        WAKEUP_ENTRY(HSI0),
+        WAKEUP_ENTRY(HSI1),
+        WAKEUP_ENTRY(USB),
+        WAKEUP_ENTRY(ABB),
+        WAKEUP_ENTRY(ABB_FIFO),
+        WAKEUP_ENTRY(ARM)
+};
+
+/*
+ * mb0_transfer - state needed for mailbox 0 communication.
+ * @lock:               The transaction lock.
+ * @dbb_events_lock:    A lock used to handle concurrent access to (parts of)
+ *                      the request data.
+ * @mask_work:          Work structure used for (un)masking wakeup interrupts.
+ * @req:                Request data that need to persist between requests.
+ */
+static struct {
+        spinlock_t lock;
+        spinlock_t dbb_irqs_lock;
+        struct work_struct mask_work;
+        struct mutex ac_wake_lock;
+        struct completion ac_wake_work;
+        struct {
+                u32 dbb_irqs;
+                u32 dbb_wakeups;
+                u32 abb_events;
+        } req;
+} mb0_transfer;
+
+/*
+ * mb1_transfer - state needed for mailbox 1 communication.
+ * @lock:       The transaction lock.
+ * @work:       The transaction completion structure.
+ * @ack:        Reply ("acknowledge") data.
+ */
+static struct {
+        struct mutex lock;
+        struct completion work;
+        struct {
+                u8 header;
+                u8 arm_opp;
+                u8 ape_opp;
+                u8 ape_voltage_status;
+        } ack;
+} mb1_transfer;
+
+/*
+ * mb2_transfer - state needed for mailbox 2 communication.
+ * @lock:            The transaction lock.
+ * @work:            The transaction completion structure.
+ * @auto_pm_lock:    The autonomous power management configuration lock.
+ * @auto_pm_enabled: A flag indicating whether autonomous PM is enabled.
+ * @req:             Request data that need to persist between requests.
+ * @ack:             Reply ("acknowledge") data.
+ */
+static struct {
+        struct mutex lock;
+        struct completion work;
+        spinlock_t auto_pm_lock;
+        bool auto_pm_enabled;
+        struct {
+                u8 status;
+        } ack;
+} mb2_transfer;
+
+/*
+ * mb3_transfer - state needed for mailbox 3 communication.
+ * @lock:               The request lock.
+ * @sysclk_lock:        A lock used to handle concurrent sysclk requests.
+ * @sysclk_work:        Work structure used for sysclk requests.
+ */
+static struct {
+        spinlock_t lock;
+        struct mutex sysclk_lock;
+        struct completion sysclk_work;
+} mb3_transfer;
+
+/*
+ * mb4_transfer - state needed for mailbox 4 communication.
+ * @lock:       The transaction lock.
+ * @work:       The transaction completion structure.
+ */
+static struct {
+        struct mutex lock;
+        struct completion work;
+} mb4_transfer;
+
+/*
+ * mb5_transfer - state needed for mailbox 5 communication.
+ * @lock:       The transaction lock.
+ * @work:       The transaction completion structure.
+ * @ack:        Reply ("acknowledge") data.
+ */
+static struct {
+        struct mutex lock;
+        struct completion work;
+        struct {
+                u8 status;
+                u8 value;
+        } ack;
+} mb5_transfer;
+
+static atomic_t ac_wake_req_state = ATOMIC_INIT(0);
+
+/* Spinlocks */
+static DEFINE_SPINLOCK(clkout_lock);
+static DEFINE_SPINLOCK(gpiocr_lock);
+
+/* Global var to runtime determine TCDM base for v2 or v1 */
+static __iomem void *tcdm_base;
+
+struct clk_mgt {
+        unsigned int offset;
+        u32 pllsw;
+};
+
+static DEFINE_SPINLOCK(clk_mgt_lock);
+
+#define CLK_MGT_ENTRY(_name)[PRCMU_##_name] = { (PRCM_##_name##_MGT), 0 }
+struct clk_mgt clk_mgt[PRCMU_NUM_REG_CLOCKS] = {
+        CLK_MGT_ENTRY(SGACLK),
+        CLK_MGT_ENTRY(UARTCLK),
+        CLK_MGT_ENTRY(MSP02CLK),
+        CLK_MGT_ENTRY(MSP1CLK),
+        CLK_MGT_ENTRY(I2CCLK),
+        CLK_MGT_ENTRY(SDMMCCLK),
+        CLK_MGT_ENTRY(SLIMCLK),
+        CLK_MGT_ENTRY(PER1CLK),
+        CLK_MGT_ENTRY(PER2CLK),
+        CLK_MGT_ENTRY(PER3CLK),
+        CLK_MGT_ENTRY(PER5CLK),
+        CLK_MGT_ENTRY(PER6CLK),
+        CLK_MGT_ENTRY(PER7CLK),
+        CLK_MGT_ENTRY(LCDCLK),
+        CLK_MGT_ENTRY(BMLCLK),
+        CLK_MGT_ENTRY(HSITXCLK),
+        CLK_MGT_ENTRY(HSIRXCLK),
+        CLK_MGT_ENTRY(HDMICLK),
+        CLK_MGT_ENTRY(APEATCLK),
+        CLK_MGT_ENTRY(APETRACECLK),
+        CLK_MGT_ENTRY(MCDECLK),
+        CLK_MGT_ENTRY(IPI2CCLK),
+        CLK_MGT_ENTRY(DSIALTCLK),
+        CLK_MGT_ENTRY(DMACLK),
+        CLK_MGT_ENTRY(B2R2CLK),
+        CLK_MGT_ENTRY(TVCLK),
+        CLK_MGT_ENTRY(SSPCLK),
+        CLK_MGT_ENTRY(RNGCLK),
+        CLK_MGT_ENTRY(UICCCLK),
+};
+
+/*
+* Used by MCDE to setup all necessary PRCMU registers
+*/
+#define PRCMU_RESET_DSIPLL              0x00004000
+#define PRCMU_UNCLAMP_DSIPLL            0x00400800
+
+#define PRCMU_CLK_PLL_DIV_SHIFT         0
+#define PRCMU_CLK_PLL_SW_SHIFT          5
+#define PRCMU_CLK_38                    (1 << 9)
+#define PRCMU_CLK_38_SRC                (1 << 10)
+#define PRCMU_CLK_38_DIV                (1 << 11)
+
+/* PLLDIV=12, PLLSW=4 (PLLDDR) */
+#define PRCMU_DSI_CLOCK_SETTING         0x0000008C
+
+/* PLLDIV=8, PLLSW=4 (PLLDDR) */
+#define PRCMU_DSI_CLOCK_SETTING_U8400   0x00000088
+
+/* DPI 50000000 Hz */
+#define PRCMU_DPI_CLOCK_SETTING         ((1 << PRCMU_CLK_PLL_SW_SHIFT) | \
+                                          (16 << PRCMU_CLK_PLL_DIV_SHIFT))
+#define PRCMU_DSI_LP_CLOCK_SETTING      0x00000E00
+
+/* D=101, N=1, R=4, SELDIV2=0 */
+#define PRCMU_PLLDSI_FREQ_SETTING       0x00040165
+
+/* D=70, N=1, R=3, SELDIV2=0 */
+#define PRCMU_PLLDSI_FREQ_SETTING_U8400 0x00030146
+
+#define PRCMU_ENABLE_PLLDSI             0x00000001
+#define PRCMU_DISABLE_PLLDSI            0x00000000
+#define PRCMU_RELEASE_RESET_DSS         0x0000400C
+#define PRCMU_DSI_PLLOUT_SEL_SETTING    0x00000202
+/* ESC clk, div0=1, div1=1, div2=3 */
+#define PRCMU_ENABLE_ESCAPE_CLOCK_DIV   0x07030101
+#define PRCMU_DISABLE_ESCAPE_CLOCK_DIV  0x00030101
+#define PRCMU_DSI_RESET_SW              0x00000007
+
+#define PRCMU_PLLDSI_LOCKP_LOCKED       0x3
+
+static struct {
+        u8 project_number;
+        u8 api_version;
+        u8 func_version;
+        u8 errata;
+} prcmu_version;
+
+
+int prcmu_enable_dsipll(void)
+{
+        int i;
+        unsigned int plldsifreq;
+
+        /* Clear DSIPLL_RESETN */
+        writel(PRCMU_RESET_DSIPLL, (_PRCMU_BASE + PRCM_APE_RESETN_CLR));
+        /* Unclamp DSIPLL in/out */
+        writel(PRCMU_UNCLAMP_DSIPLL, (_PRCMU_BASE + PRCM_MMIP_LS_CLAMP_CLR));
+
+        if (prcmu_is_u8400())
+                plldsifreq = PRCMU_PLLDSI_FREQ_SETTING_U8400;
+        else
+                plldsifreq = PRCMU_PLLDSI_FREQ_SETTING;
+        /* Set DSI PLL FREQ */
+        writel(plldsifreq, (_PRCMU_BASE + PRCM_PLLDSI_FREQ));
+        writel(PRCMU_DSI_PLLOUT_SEL_SETTING,
+                (_PRCMU_BASE + PRCM_DSI_PLLOUT_SEL));
+        /* Enable Escape clocks */
+        writel(PRCMU_ENABLE_ESCAPE_CLOCK_DIV,
+                                        (_PRCMU_BASE + PRCM_DSITVCLK_DIV));
+
+        /* Start DSI PLL */
+        writel(PRCMU_ENABLE_PLLDSI, (_PRCMU_BASE + PRCM_PLLDSI_ENABLE));
+        /* Reset DSI PLL */
+        writel(PRCMU_DSI_RESET_SW, (_PRCMU_BASE + PRCM_DSI_SW_RESET));
+        for (i = 0; i < 10; i++) {
+                if ((readl(_PRCMU_BASE + PRCM_PLLDSI_LOCKP) &
+                        PRCMU_PLLDSI_LOCKP_LOCKED)
+                                        == PRCMU_PLLDSI_LOCKP_LOCKED)
+                        break;
+                udelay(100);
+        }
+        /* Set DSIPLL_RESETN */
+        writel(PRCMU_RESET_DSIPLL, (_PRCMU_BASE + PRCM_APE_RESETN_SET));
+        return 0;
+}
+
+int prcmu_disable_dsipll(void)
+{
+        /* Disable dsi pll */
+        writel(PRCMU_DISABLE_PLLDSI, (_PRCMU_BASE + PRCM_PLLDSI_ENABLE));
+        /* Disable  escapeclock */
+        writel(PRCMU_DISABLE_ESCAPE_CLOCK_DIV,
+                                        (_PRCMU_BASE + PRCM_DSITVCLK_DIV));
+        return 0;
+}
+
+int prcmu_set_display_clocks(void)
+{
+        unsigned long flags;
+        unsigned int dsiclk;
+
+        if (prcmu_is_u8400())
+                dsiclk = PRCMU_DSI_CLOCK_SETTING_U8400;
+        else
+                dsiclk = PRCMU_DSI_CLOCK_SETTING;
+
+        spin_lock_irqsave(&clk_mgt_lock, flags);
+
+        /* Grab the HW semaphore. */
+        while ((readl(_PRCMU_BASE + PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+                cpu_relax();
+
+        writel(dsiclk, (_PRCMU_BASE + PRCM_HDMICLK_MGT));
+        writel(PRCMU_DSI_LP_CLOCK_SETTING, (_PRCMU_BASE + PRCM_TVCLK_MGT));
+        writel(PRCMU_DPI_CLOCK_SETTING, (_PRCMU_BASE + PRCM_LCDCLK_MGT));
+
+        /* Release the HW semaphore. */
+        writel(0, (_PRCMU_BASE + PRCM_SEM));
+
+        spin_unlock_irqrestore(&clk_mgt_lock, flags);
+
+        return 0;
+}
+
+/**
+ * prcmu_enable_spi2 - Enables pin muxing for SPI2 on OtherAlternateC1.
+ */
+void prcmu_enable_spi2(void)
+{
+        u32 reg;
+        unsigned long flags;
+
+        spin_lock_irqsave(&gpiocr_lock, flags);
+        reg = readl(_PRCMU_BASE + PRCM_GPIOCR);
+        writel(reg | PRCM_GPIOCR_SPI2_SELECT, _PRCMU_BASE + PRCM_GPIOCR);
+        spin_unlock_irqrestore(&gpiocr_lock, flags);
+}
+
+/**
+ * prcmu_disable_spi2 - Disables pin muxing for SPI2 on OtherAlternateC1.
+ */
+void prcmu_disable_spi2(void)
+{
+        u32 reg;
+        unsigned long flags;
+
+        spin_lock_irqsave(&gpiocr_lock, flags);
+        reg = readl(_PRCMU_BASE + PRCM_GPIOCR);
+        writel(reg & ~PRCM_GPIOCR_SPI2_SELECT, _PRCMU_BASE + PRCM_GPIOCR);
+        spin_unlock_irqrestore(&gpiocr_lock, flags);
+}
+
+bool prcmu_has_arm_maxopp(void)
+{
+        return (readb(tcdm_base + PRCM_AVS_VARM_MAX_OPP) &
+                PRCM_AVS_ISMODEENABLE_MASK) == PRCM_AVS_ISMODEENABLE_MASK;
+}
+
+bool prcmu_is_u8400(void)
+{
+        return prcmu_version.project_number == PRCMU_PROJECT_ID_8400V2_0;
+}
+
+/**
+ * prcmu_get_boot_status - PRCMU boot status checking
+ * Returns: the current PRCMU boot status
+ */
+int prcmu_get_boot_status(void)
+{
+        return readb(tcdm_base + PRCM_BOOT_STATUS);
+}
+
+/**
+ * prcmu_set_rc_a2p - This function is used to run few power state sequences
+ * @val: Value to be set, i.e. transition requested
+ * Returns: 0 on success, -EINVAL on invalid argument
+ *
+ * This function is used to run the following power state sequences -
+ * any state to ApReset,  ApDeepSleep to ApExecute, ApExecute to ApDeepSleep
+ */
+int prcmu_set_rc_a2p(enum romcode_write val)
+{
+        if (val < RDY_2_DS || val > RDY_2_XP70_RST)
+                return -EINVAL;
+        writeb(val, (tcdm_base + PRCM_ROMCODE_A2P));
+        return 0;
+}
+
+/**
+ * prcmu_get_rc_p2a - This function is used to get power state sequences
+ * Returns: the power transition that has last happened
+ *
+ * This function can return the following transitions-
+ * any state to ApReset,  ApDeepSleep to ApExecute, ApExecute to ApDeepSleep
+ */
+enum romcode_read prcmu_get_rc_p2a(void)
+{
+        return readb(tcdm_base + PRCM_ROMCODE_P2A);
+}
+
+/**
+ * prcmu_get_current_mode - Return the current XP70 power mode
+ * Returns: Returns the current AP(ARM) power mode: init,
+ * apBoot, apExecute, apDeepSleep, apSleep, apIdle, apReset
+ */
+enum ap_pwrst prcmu_get_xp70_current_state(void)
+{
+        return readb(tcdm_base + PRCM_XP70_CUR_PWR_STATE);
+}
+
+/**
+ * prcmu_config_clkout - Configure one of the programmable clock outputs.
+ * @clkout:     The CLKOUT number (0 or 1).
+ * @source:     The clock to be used (one of the PRCMU_CLKSRC_*).
+ * @div:        The divider to be applied.
+ *
+ * Configures one of the programmable clock outputs (CLKOUTs).
+ * @div should be in the range [1,63] to request a configuration, or 0 to
+ * inform that the configuration is no longer requested.
+ */
+int prcmu_config_clkout(u8 clkout, u8 source, u8 div)
+{
+        static int requests[2];
+        int r = 0;
+        unsigned long flags;
+        u32 val;
+        u32 bits;
+        u32 mask;
+        u32 div_mask;
+
+        BUG_ON(clkout > 1);
+        BUG_ON(div > 63);
+        BUG_ON((clkout == 0) && (source > PRCMU_CLKSRC_CLK009));
+
+        if (!div && !requests[clkout])
+                return -EINVAL;
+
+        switch (clkout) {
+        case 0:
+                div_mask = PRCM_CLKOCR_CLKODIV0_MASK;
+                mask = (PRCM_CLKOCR_CLKODIV0_MASK | PRCM_CLKOCR_CLKOSEL0_MASK);
+                bits = ((source << PRCM_CLKOCR_CLKOSEL0_SHIFT) |
+                        (div << PRCM_CLKOCR_CLKODIV0_SHIFT));
+                break;
+        case 1:
+                div_mask = PRCM_CLKOCR_CLKODIV1_MASK;
+                mask = (PRCM_CLKOCR_CLKODIV1_MASK | PRCM_CLKOCR_CLKOSEL1_MASK |
+                        PRCM_CLKOCR_CLK1TYPE);
+                bits = ((source << PRCM_CLKOCR_CLKOSEL1_SHIFT) |
+                        (div << PRCM_CLKOCR_CLKODIV1_SHIFT));
+                break;
+        }
+        bits &= mask;
+
+        spin_lock_irqsave(&clkout_lock, flags);
+
+        val = readl(_PRCMU_BASE + PRCM_CLKOCR);
+        if (val & div_mask) {
+                if (div) {
+                        if ((val & mask) != bits) {
+                                r = -EBUSY;
+                                goto unlock_and_return;
+                        }
+                } else {
+                        if ((val & mask & ~div_mask) != bits) {
+                                r = -EINVAL;
+                                goto unlock_and_return;
+                        }
+                }
+        }
+        writel((bits | (val & ~mask)), (_PRCMU_BASE + PRCM_CLKOCR));
+        requests[clkout] += (div ? 1 : -1);
+
+unlock_and_return:
+        spin_unlock_irqrestore(&clkout_lock, flags);
+
+        return r;
+}
+
+int prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll)
+{
+        unsigned long flags;
+
+        BUG_ON((state < PRCMU_AP_SLEEP) || (PRCMU_AP_DEEP_IDLE < state));
+
+        spin_lock_irqsave(&mb0_transfer.lock, flags);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+                cpu_relax();
+
+        writeb(MB0H_POWER_STATE_TRANS, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB0));
+        writeb(state, (tcdm_base + PRCM_REQ_MB0_AP_POWER_STATE));
+        writeb((keep_ap_pll ? 1 : 0), (tcdm_base + PRCM_REQ_MB0_AP_PLL_STATE));
+        writeb((keep_ulp_clk ? 1 : 0),
+                (tcdm_base + PRCM_REQ_MB0_ULP_CLOCK_STATE));
+        writeb(0, (tcdm_base + PRCM_REQ_MB0_DO_NOT_WFI));
+        writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+
+        spin_unlock_irqrestore(&mb0_transfer.lock, flags);
+
+        return 0;
+}
+
+/* This function should only be called while mb0_transfer.lock is held. */
+static void config_wakeups(void)
+{
+        const u8 header[2] = {
+                MB0H_CONFIG_WAKEUPS_EXE,
+                MB0H_CONFIG_WAKEUPS_SLEEP
+        };
+        static u32 last_dbb_events;
+        static u32 last_abb_events;
+        u32 dbb_events;
+        u32 abb_events;
+        unsigned int i;
+
+        dbb_events = mb0_transfer.req.dbb_irqs | mb0_transfer.req.dbb_wakeups;
+        dbb_events |= (WAKEUP_BIT_AC_WAKE_ACK | WAKEUP_BIT_AC_SLEEP_ACK);
+
+        abb_events = mb0_transfer.req.abb_events;
+
+        if ((dbb_events == last_dbb_events) && (abb_events == last_abb_events))
+                return;
+
+        for (i = 0; i < 2; i++) {
+                while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+                        cpu_relax();
+                writel(dbb_events, (tcdm_base + PRCM_REQ_MB0_WAKEUP_8500));
+                writel(abb_events, (tcdm_base + PRCM_REQ_MB0_WAKEUP_4500));
+                writeb(header[i], (tcdm_base + PRCM_MBOX_HEADER_REQ_MB0));
+                writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        }
+        last_dbb_events = dbb_events;
+        last_abb_events = abb_events;
+}
+
+void prcmu_enable_wakeups(u32 wakeups)
+{
+        unsigned long flags;
+        u32 bits;
+        int i;
+
+        BUG_ON(wakeups != (wakeups & VALID_WAKEUPS));
+
+        for (i = 0, bits = 0; i < NUM_PRCMU_WAKEUP_INDICES; i++) {
+                if (wakeups & BIT(i))
+                        bits |= prcmu_wakeup_bit[i];
+        }
+
+        spin_lock_irqsave(&mb0_transfer.lock, flags);
+
+        mb0_transfer.req.dbb_wakeups = bits;
+        config_wakeups();
+
+        spin_unlock_irqrestore(&mb0_transfer.lock, flags);
+}
+
+void prcmu_config_abb_event_readout(u32 abb_events)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&mb0_transfer.lock, flags);
+
+        mb0_transfer.req.abb_events = abb_events;
+        config_wakeups();
+
+        spin_unlock_irqrestore(&mb0_transfer.lock, flags);
+}
+
+void prcmu_get_abb_event_buffer(void __iomem **buf)
+{
+        if (readb(tcdm_base + PRCM_ACK_MB0_READ_POINTER) & 1)
+                *buf = (tcdm_base + PRCM_ACK_MB0_WAKEUP_1_4500);
+        else
+                *buf = (tcdm_base + PRCM_ACK_MB0_WAKEUP_0_4500);
+}
+
+/**
+ * prcmu_set_arm_opp - set the appropriate ARM OPP
+ * @opp: The new ARM operating point to which transition is to be made
+ * Returns: 0 on success, non-zero on failure
+ *
+ * This function sets the the operating point of the ARM.
+ */
+int prcmu_set_arm_opp(u8 opp)
+{
+        int r;
+
+        if (opp < ARM_NO_CHANGE || opp > ARM_EXTCLK)
+                return -EINVAL;
+
+        r = 0;
+
+        mutex_lock(&mb1_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+                cpu_relax();
+
+        writeb(MB1H_ARM_APE_OPP, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
+        writeb(opp, (tcdm_base + PRCM_REQ_MB1_ARM_OPP));
+        writeb(APE_NO_CHANGE, (tcdm_base + PRCM_REQ_MB1_APE_OPP));
+
+        writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb1_transfer.work);
+
+        if ((mb1_transfer.ack.header != MB1H_ARM_APE_OPP) ||
+                (mb1_transfer.ack.arm_opp != opp))
+                r = -EIO;
+
+        mutex_unlock(&mb1_transfer.lock);
+
+        return r;
+}
+
+/**
+ * prcmu_get_arm_opp - get the current ARM OPP
+ *
+ * Returns: the current ARM OPP
+ */
+int prcmu_get_arm_opp(void)
+{
+        return readb(tcdm_base + PRCM_ACK_MB1_CURRENT_ARM_OPP);
+}
+
+/**
+ * prcmu_get_ddr_opp - get the current DDR OPP
+ *
+ * Returns: the current DDR OPP
+ */
+int prcmu_get_ddr_opp(void)
+{
+        return readb(_PRCMU_BASE + PRCM_DDR_SUBSYS_APE_MINBW);
+}
+
+/**
+ * set_ddr_opp - set the appropriate DDR OPP
+ * @opp: The new DDR operating point to which transition is to be made
+ * Returns: 0 on success, non-zero on failure
+ *
+ * This function sets the operating point of the DDR.
+ */
+int prcmu_set_ddr_opp(u8 opp)
+{
+        if (opp < DDR_100_OPP || opp > DDR_25_OPP)
+                return -EINVAL;
+        /* Changing the DDR OPP can hang the hardware pre-v21 */
+        if (cpu_is_u8500v20_or_later() && !cpu_is_u8500v20())
+                writeb(opp, (_PRCMU_BASE + PRCM_DDR_SUBSYS_APE_MINBW));
+
+        return 0;
+}
+/**
+ * set_ape_opp - set the appropriate APE OPP
+ * @opp: The new APE operating point to which transition is to be made
+ * Returns: 0 on success, non-zero on failure
+ *
+ * This function sets the operating point of the APE.
+ */
+int prcmu_set_ape_opp(u8 opp)
+{
+        int r = 0;
+
+        mutex_lock(&mb1_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+                cpu_relax();
+
+        writeb(MB1H_ARM_APE_OPP, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
+        writeb(ARM_NO_CHANGE, (tcdm_base + PRCM_REQ_MB1_ARM_OPP));
+        writeb(opp, (tcdm_base + PRCM_REQ_MB1_APE_OPP));
+
+        writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb1_transfer.work);
+
+        if ((mb1_transfer.ack.header != MB1H_ARM_APE_OPP) ||
+                (mb1_transfer.ack.ape_opp != opp))
+                r = -EIO;
+
+        mutex_unlock(&mb1_transfer.lock);
+
+        return r;
+}
+
+/**
+ * prcmu_get_ape_opp - get the current APE OPP
+ *
+ * Returns: the current APE OPP
+ */
+int prcmu_get_ape_opp(void)
+{
+        return readb(tcdm_base + PRCM_ACK_MB1_CURRENT_APE_OPP);
+}
+
+/**
+ * prcmu_request_ape_opp_100_voltage - Request APE OPP 100% voltage
+ * @enable: true to request the higher voltage, false to drop a request.
+ *
+ * Calls to this function to enable and disable requests must be balanced.
+ */
+int prcmu_request_ape_opp_100_voltage(bool enable)
+{
+        int r = 0;
+        u8 header;
+        static unsigned int requests;
+
+        mutex_lock(&mb1_transfer.lock);
+
+        if (enable) {
+                if (0 != requests++)
+                        goto unlock_and_return;
+                header = MB1H_REQUEST_APE_OPP_100_VOLT;
+        } else {
+                if (requests == 0) {
+                        r = -EIO;
+                        goto unlock_and_return;
+                } else if (1 != requests--) {
+                        goto unlock_and_return;
+                }
+                header = MB1H_RELEASE_APE_OPP_100_VOLT;
+        }
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+                cpu_relax();
+
+        writeb(header, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
+
+        writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb1_transfer.work);
+
+        if ((mb1_transfer.ack.header != header) ||
+                ((mb1_transfer.ack.ape_voltage_status & BIT(0)) != 0))
+                r = -EIO;
+
+unlock_and_return:
+        mutex_unlock(&mb1_transfer.lock);
+
+        return r;
+}
+
+/**
+ * prcmu_release_usb_wakeup_state - release the state required by a USB wakeup
+ *
+ * This function releases the power state requirements of a USB wakeup.
+ */
+int prcmu_release_usb_wakeup_state(void)
+{
+        int r = 0;
+
+        mutex_lock(&mb1_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+                cpu_relax();
+
+        writeb(MB1H_RELEASE_USB_WAKEUP,
+                (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
+
+        writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb1_transfer.work);
+
+        if ((mb1_transfer.ack.header != MB1H_RELEASE_USB_WAKEUP) ||
+                ((mb1_transfer.ack.ape_voltage_status & BIT(0)) != 0))
+                r = -EIO;
+
+        mutex_unlock(&mb1_transfer.lock);
+
+        return r;
+}
+
+/**
+ * prcmu_set_epod - set the state of a EPOD (power domain)
+ * @epod_id: The EPOD to set
+ * @epod_state: The new EPOD state
+ *
+ * This function sets the state of a EPOD (power domain). It may not be called
+ * from interrupt context.
+ */
+int prcmu_set_epod(u16 epod_id, u8 epod_state)
+{
+        int r = 0;
+        bool ram_retention = false;
+        int i;
+
+        /* check argument */
+        BUG_ON(epod_id >= NUM_EPOD_ID);
+
+        /* set flag if retention is possible */
+        switch (epod_id) {
+        case EPOD_ID_SVAMMDSP:
+        case EPOD_ID_SIAMMDSP:
+        case EPOD_ID_ESRAM12:
+        case EPOD_ID_ESRAM34:
+                ram_retention = true;
+                break;
+        }
+
+        /* check argument */
+        BUG_ON(epod_state > EPOD_STATE_ON);
+        BUG_ON(epod_state == EPOD_STATE_RAMRET && !ram_retention);
+
+        /* get lock */
+        mutex_lock(&mb2_transfer.lock);
+
+        /* wait for mailbox */
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(2))
+                cpu_relax();
+
+        /* fill in mailbox */
+        for (i = 0; i < NUM_EPOD_ID; i++)
+                writeb(EPOD_STATE_NO_CHANGE, (tcdm_base + PRCM_REQ_MB2 + i));
+        writeb(epod_state, (tcdm_base + PRCM_REQ_MB2 + epod_id));
+
+        writeb(MB2H_DPS, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB2));
+
+        writel(MBOX_BIT(2), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+
+        /*
+         * The current firmware version does not handle errors correctly,
+         * and we cannot recover if there is an error.
+         * This is expected to change when the firmware is updated.
+         */
+        if (!wait_for_completion_timeout(&mb2_transfer.work,
+                        msecs_to_jiffies(20000))) {
+                pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+                        __func__);
+                r = -EIO;
+                goto unlock_and_return;
+        }
+
+        if (mb2_transfer.ack.status != HWACC_PWR_ST_OK)
+                r = -EIO;
+
+unlock_and_return:
+        mutex_unlock(&mb2_transfer.lock);
+        return r;
+}
+
+/**
+ * prcmu_configure_auto_pm - Configure autonomous power management.
+ * @sleep: Configuration for ApSleep.
+ * @idle:  Configuration for ApIdle.
+ */
+void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep,
+        struct prcmu_auto_pm_config *idle)
+{
+        u32 sleep_cfg;
+        u32 idle_cfg;
+        unsigned long flags;
+
+        BUG_ON((sleep == NULL) || (idle == NULL));
+
+        sleep_cfg = (sleep->sva_auto_pm_enable & 0xF);
+        sleep_cfg = ((sleep_cfg << 4) | (sleep->sia_auto_pm_enable & 0xF));
+        sleep_cfg = ((sleep_cfg << 8) | (sleep->sva_power_on & 0xFF));
+        sleep_cfg = ((sleep_cfg << 8) | (sleep->sia_power_on & 0xFF));
+        sleep_cfg = ((sleep_cfg << 4) | (sleep->sva_policy & 0xF));
+        sleep_cfg = ((sleep_cfg << 4) | (sleep->sia_policy & 0xF));
+
+        idle_cfg = (idle->sva_auto_pm_enable & 0xF);
+        idle_cfg = ((idle_cfg << 4) | (idle->sia_auto_pm_enable & 0xF));
+        idle_cfg = ((idle_cfg << 8) | (idle->sva_power_on & 0xFF));
+        idle_cfg = ((idle_cfg << 8) | (idle->sia_power_on & 0xFF));
+        idle_cfg = ((idle_cfg << 4) | (idle->sva_policy & 0xF));
+        idle_cfg = ((idle_cfg << 4) | (idle->sia_policy & 0xF));
+
+        spin_lock_irqsave(&mb2_transfer.auto_pm_lock, flags);
+
+        /*
+         * The autonomous power management configuration is done through
+         * fields in mailbox 2, but these fields are only used as shared
+         * variables - i.e. there is no need to send a message.
+         */
+        writel(sleep_cfg, (tcdm_base + PRCM_REQ_MB2_AUTO_PM_SLEEP));
+        writel(idle_cfg, (tcdm_base + PRCM_REQ_MB2_AUTO_PM_IDLE));
+
+        mb2_transfer.auto_pm_enabled =
+                ((sleep->sva_auto_pm_enable == PRCMU_AUTO_PM_ON) ||
+                 (sleep->sia_auto_pm_enable == PRCMU_AUTO_PM_ON) ||
+                 (idle->sva_auto_pm_enable == PRCMU_AUTO_PM_ON) ||
+                 (idle->sia_auto_pm_enable == PRCMU_AUTO_PM_ON));
+
+        spin_unlock_irqrestore(&mb2_transfer.auto_pm_lock, flags);
+}
+EXPORT_SYMBOL(prcmu_configure_auto_pm);
+
+bool prcmu_is_auto_pm_enabled(void)
+{
+        return mb2_transfer.auto_pm_enabled;
+}
+
+static int request_sysclk(bool enable)
+{
+        int r;
+        unsigned long flags;
+
+        r = 0;
+
+        mutex_lock(&mb3_transfer.sysclk_lock);
+
+        spin_lock_irqsave(&mb3_transfer.lock, flags);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(3))
+                cpu_relax();
+
+        writeb((enable ? ON : OFF), (tcdm_base + PRCM_REQ_MB3_SYSCLK_MGT));
+
+        writeb(MB3H_SYSCLK, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB3));
+        writel(MBOX_BIT(3), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+
+        spin_unlock_irqrestore(&mb3_transfer.lock, flags);
+
+        /*
+         * The firmware only sends an ACK if we want to enable the
+         * SysClk, and it succeeds.
+         */
+        if (enable && !wait_for_completion_timeout(&mb3_transfer.sysclk_work,
+                        msecs_to_jiffies(20000))) {
+                pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+                        __func__);
+                r = -EIO;
+        }
+
+        mutex_unlock(&mb3_transfer.sysclk_lock);
+
+        return r;
+}
+
+static int request_timclk(bool enable)
+{
+        u32 val = (PRCM_TCR_DOZE_MODE | PRCM_TCR_TENSEL_MASK);
+
+        if (!enable)
+                val |= PRCM_TCR_STOP_TIMERS;
+        writel(val, (_PRCMU_BASE + PRCM_TCR));
+
+        return 0;
+}
+
+static int request_reg_clock(u8 clock, bool enable)
+{
+        u32 val;
+        unsigned long flags;
+
+        spin_lock_irqsave(&clk_mgt_lock, flags);
+
+        /* Grab the HW semaphore. */
+        while ((readl(_PRCMU_BASE + PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+                cpu_relax();
+
+        val = readl(_PRCMU_BASE + clk_mgt[clock].offset);
+        if (enable) {
+                val |= (PRCM_CLK_MGT_CLKEN | clk_mgt[clock].pllsw);
+        } else {
+                clk_mgt[clock].pllsw = (val & PRCM_CLK_MGT_CLKPLLSW_MASK);
+                val &= ~(PRCM_CLK_MGT_CLKEN | PRCM_CLK_MGT_CLKPLLSW_MASK);
+        }
+        writel(val, (_PRCMU_BASE + clk_mgt[clock].offset));
+
+        /* Release the HW semaphore. */
+        writel(0, (_PRCMU_BASE + PRCM_SEM));
+
+        spin_unlock_irqrestore(&clk_mgt_lock, flags);
+
+        return 0;
+}
+
+/**
+ * prcmu_request_clock() - Request for a clock to be enabled or disabled.
+ * @clock:      The clock for which the request is made.
+ * @enable:     Whether the clock should be enabled (true) or disabled (false).
+ *
+ * This function should only be used by the clock implementation.
+ * Do not use it from any other place!
+ */
+int prcmu_request_clock(u8 clock, bool enable)
+{
+        if (clock < PRCMU_NUM_REG_CLOCKS)
+                return request_reg_clock(clock, enable);
+        else if (clock == PRCMU_TIMCLK)
+                return request_timclk(enable);
+        else if (clock == PRCMU_SYSCLK)
+                return request_sysclk(enable);
+        else
+                return -EINVAL;
+}
+
+int prcmu_config_esram0_deep_sleep(u8 state)
+{
+        if ((state > ESRAM0_DEEP_SLEEP_STATE_RET) ||
+            (state < ESRAM0_DEEP_SLEEP_STATE_OFF))
+                return -EINVAL;
+
+        mutex_lock(&mb4_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+                cpu_relax();
+
+        writeb(MB4H_MEM_ST, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
+        writeb(((DDR_PWR_STATE_OFFHIGHLAT << 4) | DDR_PWR_STATE_ON),
+               (tcdm_base + PRCM_REQ_MB4_DDR_ST_AP_SLEEP_IDLE));
+        writeb(DDR_PWR_STATE_ON,
+               (tcdm_base + PRCM_REQ_MB4_DDR_ST_AP_DEEP_IDLE));
+        writeb(state, (tcdm_base + PRCM_REQ_MB4_ESRAM0_ST));
+
+        writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb4_transfer.work);
+
+        mutex_unlock(&mb4_transfer.lock);
+
+        return 0;
+}
+
+int prcmu_config_hotdog(u8 threshold)
+{
+        mutex_lock(&mb4_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+                cpu_relax();
+
+        writeb(threshold, (tcdm_base + PRCM_REQ_MB4_HOTDOG_THRESHOLD));
+        writeb(MB4H_HOTDOG, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
+
+        writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb4_transfer.work);
+
+        mutex_unlock(&mb4_transfer.lock);
+
+        return 0;
+}
+
+int prcmu_config_hotmon(u8 low, u8 high)
+{
+        mutex_lock(&mb4_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+                cpu_relax();
+
+        writeb(low, (tcdm_base + PRCM_REQ_MB4_HOTMON_LOW));
+        writeb(high, (tcdm_base + PRCM_REQ_MB4_HOTMON_HIGH));
+        writeb((HOTMON_CONFIG_LOW | HOTMON_CONFIG_HIGH),
+                (tcdm_base + PRCM_REQ_MB4_HOTMON_CONFIG));
+        writeb(MB4H_HOTMON, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
+
+        writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb4_transfer.work);
+
+        mutex_unlock(&mb4_transfer.lock);
+
+        return 0;
+}
+
+static int config_hot_period(u16 val)
+{
+        mutex_lock(&mb4_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(4))
+                cpu_relax();
+
+        writew(val, (tcdm_base + PRCM_REQ_MB4_HOT_PERIOD));
+        writeb(MB4H_HOT_PERIOD, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB4));
+
+        writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb4_transfer.work);
+
+        mutex_unlock(&mb4_transfer.lock);
+
+        return 0;
+}
+
+int prcmu_start_temp_sense(u16 cycles32k)
+{
+        if (cycles32k == 0xFFFF)
+                return -EINVAL;
+
+        return config_hot_period(cycles32k);
+}
+
+int prcmu_stop_temp_sense(void)
+{
+        return config_hot_period(0xFFFF);
+}
+
+/**
+ * prcmu_set_clock_divider() - Configure the clock divider.
+ * @clock:      The clock for which the request is made.
+ * @divider:    The clock divider. (< 32)
+ *
+ * This function should only be used by the clock implementation.
+ * Do not use it from any other place!
+ */
+int prcmu_set_clock_divider(u8 clock, u8 divider)
+{
+        u32 val;
+        unsigned long flags;
+
+        if ((clock >= PRCMU_NUM_REG_CLOCKS) || (divider < 1) || (31 < divider))
+                return -EINVAL;
+
+        spin_lock_irqsave(&clk_mgt_lock, flags);
+
+        /* Grab the HW semaphore. */
+        while ((readl(_PRCMU_BASE + PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
+                cpu_relax();
+
+        val = readl(_PRCMU_BASE + clk_mgt[clock].offset);
+        val &= ~(PRCM_CLK_MGT_CLKPLLDIV_MASK);
+        val |= (u32)divider;
+        writel(val, (_PRCMU_BASE + clk_mgt[clock].offset));
+
+        /* Release the HW semaphore. */
+        writel(0, (_PRCMU_BASE + PRCM_SEM));
+
+        spin_unlock_irqrestore(&clk_mgt_lock, flags);
+
+        return 0;
+}
+
+/**
+ * prcmu_abb_read() - Read register value(s) from the ABB.
+ * @slave:      The I2C slave address.
+ * @reg:        The (start) register address.
+ * @value:      The read out value(s).
+ * @size:       The number of registers to read.
+ *
+ * Reads register value(s) from the ABB.
+ * @size has to be 1 for the current firmware version.
+ */
+int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        int r;
+
+        if (size != 1)
+                return -EINVAL;
+
+        mutex_lock(&mb5_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+                cpu_relax();
+
+        writeb(PRCMU_I2C_READ(slave), (tcdm_base + PRCM_REQ_MB5_I2C_SLAVE_OP));
+        writeb(PRCMU_I2C_STOP_EN, (tcdm_base + PRCM_REQ_MB5_I2C_HW_BITS));
+        writeb(reg, (tcdm_base + PRCM_REQ_MB5_I2C_REG));
+        writeb(0, (tcdm_base + PRCM_REQ_MB5_I2C_VAL));
+
+        writel(MBOX_BIT(5), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+
+        if (!wait_for_completion_timeout(&mb5_transfer.work,
+                                msecs_to_jiffies(20000))) {
+                pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+                        __func__);
+                r = -EIO;
+        } else {
+                r = ((mb5_transfer.ack.status == I2C_RD_OK) ? 0 : -EIO);
+        }
+
+        if (!r)
+                *value = mb5_transfer.ack.value;
+
+        mutex_unlock(&mb5_transfer.lock);
+
+        return r;
+}
+
+/**
+ * prcmu_abb_write() - Write register value(s) to the ABB.
+ * @slave:      The I2C slave address.
+ * @reg:        The (start) register address.
+ * @value:      The value(s) to write.
+ * @size:       The number of registers to write.
+ *
+ * Reads register value(s) from the ABB.
+ * @size has to be 1 for the current firmware version.
+ */
+int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        int r;
+
+        if (size != 1)
+                return -EINVAL;
+
+        mutex_lock(&mb5_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+                cpu_relax();
+
+        writeb(PRCMU_I2C_WRITE(slave), (tcdm_base + PRCM_REQ_MB5_I2C_SLAVE_OP));
+        writeb(PRCMU_I2C_STOP_EN, (tcdm_base + PRCM_REQ_MB5_I2C_HW_BITS));
+        writeb(reg, (tcdm_base + PRCM_REQ_MB5_I2C_REG));
+        writeb(*value, (tcdm_base + PRCM_REQ_MB5_I2C_VAL));
+
+        writel(MBOX_BIT(5), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+
+        if (!wait_for_completion_timeout(&mb5_transfer.work,
+                                msecs_to_jiffies(20000))) {
+                pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+                        __func__);
+                r = -EIO;
+        } else {
+                r = ((mb5_transfer.ack.status == I2C_WR_OK) ? 0 : -EIO);
+        }
+
+        mutex_unlock(&mb5_transfer.lock);
+
+        return r;
+}
+
+/**
+ * prcmu_ac_wake_req - should be called whenever ARM wants to wakeup Modem
+ */
+void prcmu_ac_wake_req(void)
+{
+        u32 val;
+
+        mutex_lock(&mb0_transfer.ac_wake_lock);
+
+        val = readl(_PRCMU_BASE + PRCM_HOSTACCESS_REQ);
+        if (val & PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ)
+                goto unlock_and_return;
+
+        atomic_set(&ac_wake_req_state, 1);
+
+        writel((val | PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ),
+                (_PRCMU_BASE + PRCM_HOSTACCESS_REQ));
+
+        if (!wait_for_completion_timeout(&mb0_transfer.ac_wake_work,
+                        msecs_to_jiffies(20000))) {
+                pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+                        __func__);
+        }
+
+unlock_and_return:
+        mutex_unlock(&mb0_transfer.ac_wake_lock);
+}
+
+/**
+ * prcmu_ac_sleep_req - called when ARM no longer needs to talk to modem
+ */
+void prcmu_ac_sleep_req()
+{
+        u32 val;
+
+        mutex_lock(&mb0_transfer.ac_wake_lock);
+
+        val = readl(_PRCMU_BASE + PRCM_HOSTACCESS_REQ);
+        if (!(val & PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ))
+                goto unlock_and_return;
+
+        writel((val & ~PRCM_HOSTACCESS_REQ_HOSTACCESS_REQ),
+                (_PRCMU_BASE + PRCM_HOSTACCESS_REQ));
+
+        if (!wait_for_completion_timeout(&mb0_transfer.ac_wake_work,
+                        msecs_to_jiffies(20000))) {
+                pr_err("prcmu: %s timed out (20 s) waiting for a reply.\n",
+                        __func__);
+        }
+
+        atomic_set(&ac_wake_req_state, 0);
+
+unlock_and_return:
+        mutex_unlock(&mb0_transfer.ac_wake_lock);
+}
+
+bool prcmu_is_ac_wake_requested(void)
+{
+        return (atomic_read(&ac_wake_req_state) != 0);
+}
+
+/**
+ * prcmu_system_reset - System reset
+ *
+ * Saves the reset reason code and then sets the APE_SOFRST register which
+ * fires interrupt to fw
+ */
+void prcmu_system_reset(u16 reset_code)
+{
+        writew(reset_code, (tcdm_base + PRCM_SW_RST_REASON));
+        writel(1, (_PRCMU_BASE + PRCM_APE_SOFTRST));
+}
+
+/**
+ * prcmu_reset_modem - ask the PRCMU to reset modem
+ */
+void prcmu_modem_reset(void)
+{
+        mutex_lock(&mb1_transfer.lock);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(1))
+                cpu_relax();
+
+        writeb(MB1H_RESET_MODEM, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB1));
+        writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+        wait_for_completion(&mb1_transfer.work);
+
+        /*
+         * No need to check return from PRCMU as modem should go in reset state
+         * This state is already managed by upper layer
+         */
+
+        mutex_unlock(&mb1_transfer.lock);
+}
+
+static void ack_dbb_wakeup(void)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&mb0_transfer.lock, flags);
+
+        while (readl(_PRCMU_BASE + PRCM_MBOX_CPU_VAL) & MBOX_BIT(0))
+                cpu_relax();
+
+        writeb(MB0H_READ_WAKEUP_ACK, (tcdm_base + PRCM_MBOX_HEADER_REQ_MB0));
+        writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_MBOX_CPU_SET));
+
+        spin_unlock_irqrestore(&mb0_transfer.lock, flags);
+}
+
+static inline void print_unknown_header_warning(u8 n, u8 header)
+{
+        pr_warning("prcmu: Unknown message header (%d) in mailbox %d.\n",
+                header, n);
+}
+
+static bool read_mailbox_0(void)
+{
+        bool r;
+        u32 ev;
+        unsigned int n;
+        u8 header;
+
+        header = readb(tcdm_base + PRCM_MBOX_HEADER_ACK_MB0);
+        switch (header) {
+        case MB0H_WAKEUP_EXE:
+        case MB0H_WAKEUP_SLEEP:
+                if (readb(tcdm_base + PRCM_ACK_MB0_READ_POINTER) & 1)
+                        ev = readl(tcdm_base + PRCM_ACK_MB0_WAKEUP_1_8500);
+                else
+                        ev = readl(tcdm_base + PRCM_ACK_MB0_WAKEUP_0_8500);
+
+                if (ev & (WAKEUP_BIT_AC_WAKE_ACK | WAKEUP_BIT_AC_SLEEP_ACK))
+                        complete(&mb0_transfer.ac_wake_work);
+                if (ev & WAKEUP_BIT_SYSCLK_OK)
+                        complete(&mb3_transfer.sysclk_work);
+
+                ev &= mb0_transfer.req.dbb_irqs;
+
+                for (n = 0; n < NUM_PRCMU_WAKEUPS; n++) {
+                        if (ev & prcmu_irq_bit[n])
+                                generic_handle_irq(IRQ_PRCMU_BASE + n);
+                }
+                r = true;
+                break;
+        default:
+                print_unknown_header_warning(0, header);
+                r = false;
+                break;
+        }
+        writel(MBOX_BIT(0), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        return r;
+}
+
+static bool read_mailbox_1(void)
+{
+        mb1_transfer.ack.header = readb(tcdm_base + PRCM_MBOX_HEADER_REQ_MB1);
+        mb1_transfer.ack.arm_opp = readb(tcdm_base +
+                PRCM_ACK_MB1_CURRENT_ARM_OPP);
+        mb1_transfer.ack.ape_opp = readb(tcdm_base +
+                PRCM_ACK_MB1_CURRENT_APE_OPP);
+        mb1_transfer.ack.ape_voltage_status = readb(tcdm_base +
+                PRCM_ACK_MB1_APE_VOLTAGE_STATUS);
+        writel(MBOX_BIT(1), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        complete(&mb1_transfer.work);
+        return false;
+}
+
+static bool read_mailbox_2(void)
+{
+        mb2_transfer.ack.status = readb(tcdm_base + PRCM_ACK_MB2_DPS_STATUS);
+        writel(MBOX_BIT(2), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        complete(&mb2_transfer.work);
+        return false;
+}
+
+static bool read_mailbox_3(void)
+{
+        writel(MBOX_BIT(3), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        return false;
+}
+
+static bool read_mailbox_4(void)
+{
+        u8 header;
+        bool do_complete = true;
+
+        header = readb(tcdm_base + PRCM_MBOX_HEADER_REQ_MB4);
+        switch (header) {
+        case MB4H_MEM_ST:
+        case MB4H_HOTDOG:
+        case MB4H_HOTMON:
+        case MB4H_HOT_PERIOD:
+                break;
+        default:
+                print_unknown_header_warning(4, header);
+                do_complete = false;
+                break;
+        }
+
+        writel(MBOX_BIT(4), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+
+        if (do_complete)
+                complete(&mb4_transfer.work);
+
+        return false;
+}
+
+static bool read_mailbox_5(void)
+{
+        mb5_transfer.ack.status = readb(tcdm_base + PRCM_ACK_MB5_I2C_STATUS);
+        mb5_transfer.ack.value = readb(tcdm_base + PRCM_ACK_MB5_I2C_VAL);
+        writel(MBOX_BIT(5), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        complete(&mb5_transfer.work);
+        return false;
+}
+
+static bool read_mailbox_6(void)
+{
+        writel(MBOX_BIT(6), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        return false;
+}
+
+static bool read_mailbox_7(void)
+{
+        writel(MBOX_BIT(7), (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+        return false;
+}
+
+static bool (* const read_mailbox[NUM_MB])(void) = {
+        read_mailbox_0,
+        read_mailbox_1,
+        read_mailbox_2,
+        read_mailbox_3,
+        read_mailbox_4,
+        read_mailbox_5,
+        read_mailbox_6,
+        read_mailbox_7
+};
+
+static irqreturn_t prcmu_irq_handler(int irq, void *data)
+{
+        u32 bits;
+        u8 n;
+        irqreturn_t r;
+
+        bits = (readl(_PRCMU_BASE + PRCM_ARM_IT1_VAL) & ALL_MBOX_BITS);
+        if (unlikely(!bits))
+                return IRQ_NONE;
+
+        r = IRQ_HANDLED;
+        for (n = 0; bits; n++) {
+                if (bits & MBOX_BIT(n)) {
+                        bits -= MBOX_BIT(n);
+                        if (read_mailbox[n]())
+                                r = IRQ_WAKE_THREAD;
+                }
+        }
+        return r;
+}
+
+static irqreturn_t prcmu_irq_thread_fn(int irq, void *data)
+{
+        ack_dbb_wakeup();
+        return IRQ_HANDLED;
+}
+
+static void prcmu_mask_work(struct work_struct *work)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&mb0_transfer.lock, flags);
+
+        config_wakeups();
+
+        spin_unlock_irqrestore(&mb0_transfer.lock, flags);
+}
+
+static void prcmu_irq_mask(struct irq_data *d)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&mb0_transfer.dbb_irqs_lock, flags);
+
+        mb0_transfer.req.dbb_irqs &= ~prcmu_irq_bit[d->irq - IRQ_PRCMU_BASE];
+
+        spin_unlock_irqrestore(&mb0_transfer.dbb_irqs_lock, flags);
+
+        if (d->irq != IRQ_PRCMU_CA_SLEEP)
+                schedule_work(&mb0_transfer.mask_work);
+}
+
+static void prcmu_irq_unmask(struct irq_data *d)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&mb0_transfer.dbb_irqs_lock, flags);
+
+        mb0_transfer.req.dbb_irqs |= prcmu_irq_bit[d->irq - IRQ_PRCMU_BASE];
+
+        spin_unlock_irqrestore(&mb0_transfer.dbb_irqs_lock, flags);
+
+        if (d->irq != IRQ_PRCMU_CA_SLEEP)
+                schedule_work(&mb0_transfer.mask_work);
+}
+
+static void noop(struct irq_data *d)
+{
+}
+
+static struct irq_chip prcmu_irq_chip = {
+        .name           = "prcmu",
+        .irq_disable    = prcmu_irq_mask,
+        .irq_ack        = noop,
+        .irq_mask       = prcmu_irq_mask,
+        .irq_unmask     = prcmu_irq_unmask,
+};
+
+void __init prcmu_early_init(void)
+{
+        unsigned int i;
+
+        if (cpu_is_u8500v1()) {
+                tcdm_base = __io_address(U8500_PRCMU_TCDM_BASE_V1);
+        } else if (cpu_is_u8500v2()) {
+                void *tcpm_base = ioremap_nocache(U8500_PRCMU_TCPM_BASE, SZ_4K);
+
+                if (tcpm_base != NULL) {
+                        int version;
+                        version = readl(tcpm_base + PRCMU_FW_VERSION_OFFSET);
+                        prcmu_version.project_number = version & 0xFF;
+                        prcmu_version.api_version = (version >> 8) & 0xFF;
+                        prcmu_version.func_version = (version >> 16) & 0xFF;
+                        prcmu_version.errata = (version >> 24) & 0xFF;
+                        pr_info("PRCMU firmware version %d.%d.%d\n",
+                                (version >> 8) & 0xFF, (version >> 16) & 0xFF,
+                                (version >> 24) & 0xFF);
+                        iounmap(tcpm_base);
+                }
+
+                tcdm_base = __io_address(U8500_PRCMU_TCDM_BASE);
+        } else {
+                pr_err("prcmu: Unsupported chip version\n");
+                BUG();
+        }
+
+        spin_lock_init(&mb0_transfer.lock);
+        spin_lock_init(&mb0_transfer.dbb_irqs_lock);
+        mutex_init(&mb0_transfer.ac_wake_lock);
+        init_completion(&mb0_transfer.ac_wake_work);
+        mutex_init(&mb1_transfer.lock);
+        init_completion(&mb1_transfer.work);
+        mutex_init(&mb2_transfer.lock);
+        init_completion(&mb2_transfer.work);
+        spin_lock_init(&mb2_transfer.auto_pm_lock);
+        spin_lock_init(&mb3_transfer.lock);
+        mutex_init(&mb3_transfer.sysclk_lock);
+        init_completion(&mb3_transfer.sysclk_work);
+        mutex_init(&mb4_transfer.lock);
+        init_completion(&mb4_transfer.work);
+        mutex_init(&mb5_transfer.lock);
+        init_completion(&mb5_transfer.work);
+
+        INIT_WORK(&mb0_transfer.mask_work, prcmu_mask_work);
+
+        /* Initalize irqs. */
+        for (i = 0; i < NUM_PRCMU_WAKEUPS; i++) {
+                unsigned int irq;
+
+                irq = IRQ_PRCMU_BASE + i;
+                irq_set_chip_and_handler(irq, &prcmu_irq_chip,
+                                         handle_simple_irq);
+                set_irq_flags(irq, IRQF_VALID);
+        }
+}
+
+/*
+ * Power domain switches (ePODs) modeled as regulators for the DB8500 SoC
+ */
+static struct regulator_consumer_supply db8500_vape_consumers[] = {
+        REGULATOR_SUPPLY("v-ape", NULL),
+        REGULATOR_SUPPLY("v-i2c", "nmk-i2c.0"),
+        REGULATOR_SUPPLY("v-i2c", "nmk-i2c.1"),
+        REGULATOR_SUPPLY("v-i2c", "nmk-i2c.2"),
+        REGULATOR_SUPPLY("v-i2c", "nmk-i2c.3"),
+        /* "v-mmc" changed to "vcore" in the mainline kernel */
+        REGULATOR_SUPPLY("vcore", "sdi0"),
+        REGULATOR_SUPPLY("vcore", "sdi1"),
+        REGULATOR_SUPPLY("vcore", "sdi2"),
+        REGULATOR_SUPPLY("vcore", "sdi3"),
+        REGULATOR_SUPPLY("vcore", "sdi4"),
+        REGULATOR_SUPPLY("v-dma", "dma40.0"),
+        REGULATOR_SUPPLY("v-ape", "ab8500-usb.0"),
+        /* "v-uart" changed to "vcore" in the mainline kernel */
+        REGULATOR_SUPPLY("vcore", "uart0"),
+        REGULATOR_SUPPLY("vcore", "uart1"),
+        REGULATOR_SUPPLY("vcore", "uart2"),
+        REGULATOR_SUPPLY("v-ape", "nmk-ske-keypad.0"),
+};
+
+static struct regulator_consumer_supply db8500_vsmps2_consumers[] = {
+        /* CG2900 and CW1200 power to off-chip peripherals */
+        REGULATOR_SUPPLY("gbf_1v8", "cg2900-uart.0"),
+        REGULATOR_SUPPLY("wlan_1v8", "cw1200.0"),
+        REGULATOR_SUPPLY("musb_1v8", "ab8500-usb.0"),
+        /* AV8100 regulator */
+        REGULATOR_SUPPLY("hdmi_1v8", "0-0070"),
+};
+
+static struct regulator_consumer_supply db8500_b2r2_mcde_consumers[] = {
+        REGULATOR_SUPPLY("vsupply", "b2r2.0"),
+        REGULATOR_SUPPLY("vsupply", "mcde.0"),
+};
+
+static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
+        [DB8500_REGULATOR_VAPE] = {
+                .constraints = {
+                        .name = "db8500-vape",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .consumer_supplies = db8500_vape_consumers,
+                .num_consumer_supplies = ARRAY_SIZE(db8500_vape_consumers),
+        },
+        [DB8500_REGULATOR_VARM] = {
+                .constraints = {
+                        .name = "db8500-varm",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_VMODEM] = {
+                .constraints = {
+                        .name = "db8500-vmodem",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_VPLL] = {
+                .constraints = {
+                        .name = "db8500-vpll",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_VSMPS1] = {
+                .constraints = {
+                        .name = "db8500-vsmps1",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_VSMPS2] = {
+                .constraints = {
+                        .name = "db8500-vsmps2",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .consumer_supplies = db8500_vsmps2_consumers,
+                .num_consumer_supplies = ARRAY_SIZE(db8500_vsmps2_consumers),
+        },
+        [DB8500_REGULATOR_VSMPS3] = {
+                .constraints = {
+                        .name = "db8500-vsmps3",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_VRF1] = {
+                .constraints = {
+                        .name = "db8500-vrf1",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SVAMMDSP] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-sva-mmdsp",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SVAMMDSPRET] = {
+                .constraints = {
+                        /* "ret" means "retention" */
+                        .name = "db8500-sva-mmdsp-ret",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SVAPIPE] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-sva-pipe",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SIAMMDSP] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-sia-mmdsp",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SIAMMDSPRET] = {
+                .constraints = {
+                        .name = "db8500-sia-mmdsp-ret",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SIAPIPE] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-sia-pipe",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SGA] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-sga",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_B2R2_MCDE] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-b2r2-mcde",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+                .consumer_supplies = db8500_b2r2_mcde_consumers,
+                .num_consumer_supplies = ARRAY_SIZE(db8500_b2r2_mcde_consumers),
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM12] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-esram12",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM12RET] = {
+                .constraints = {
+                        .name = "db8500-esram12-ret",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM34] = {
+                .supply_regulator = "db8500-vape",
+                .constraints = {
+                        .name = "db8500-esram34",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM34RET] = {
+                .constraints = {
+                        .name = "db8500-esram34-ret",
+                        .valid_ops_mask = REGULATOR_CHANGE_STATUS,
+                },
+        },
+};
+
+static struct mfd_cell db8500_prcmu_devs[] = {
+        {
+                .name = "db8500-prcmu-regulators",
+                .mfd_data = &db8500_regulators,
+        },
+        {
+                .name = "cpufreq-u8500",
+        },
+};
+
+/**
+ * prcmu_fw_init - arch init call for the Linux PRCMU fw init logic
+ *
+ */
+static int __init db8500_prcmu_probe(struct platform_device *pdev)
+{
+        int err = 0;
+
+        if (ux500_is_svp())
+                return -ENODEV;
+
+        /* Clean up the mailbox interrupts after pre-kernel code. */
+        writel(ALL_MBOX_BITS, (_PRCMU_BASE + PRCM_ARM_IT1_CLR));
+
+        err = request_threaded_irq(IRQ_DB8500_PRCMU1, prcmu_irq_handler,
+                prcmu_irq_thread_fn, IRQF_NO_SUSPEND, "prcmu", NULL);
+        if (err < 0) {
+                pr_err("prcmu: Failed to allocate IRQ_DB8500_PRCMU1.\n");
+                err = -EBUSY;
+                goto no_irq_return;
+        }
+
+        if (cpu_is_u8500v20_or_later())
+                prcmu_config_esram0_deep_sleep(ESRAM0_DEEP_SLEEP_STATE_RET);
+
+        err = mfd_add_devices(&pdev->dev, 0, db8500_prcmu_devs,
+                              ARRAY_SIZE(db8500_prcmu_devs), NULL,
+                              0);
+
+        if (err)
+                pr_err("prcmu: Failed to add subdevices\n");
+        else
+                pr_info("DB8500 PRCMU initialized\n");
+
+no_irq_return:
+        return err;
+}
+
+static struct platform_driver db8500_prcmu_driver = {
+        .driver = {
+                .name = "db8500-prcmu",
+                .owner = THIS_MODULE,
+        },
+};
+
+static int __init db8500_prcmu_init(void)
+{
+        return platform_driver_probe(&db8500_prcmu_driver, db8500_prcmu_probe);
+}
+
+arch_initcall(db8500_prcmu_init);
+
+MODULE_AUTHOR("Mattias Nilsson <mattias.i.nilsson@stericsson.com>");
+MODULE_DESCRIPTION("DB8500 PRCM Unit driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 209fbb70619b..776a478e6296 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_ATL2) += atlx/
 obj-$(CONFIG_ATL1E) += atl1e/
 obj-$(CONFIG_ATL1C) += atl1c/
 obj-$(CONFIG_GIANFAR) += gianfar_driver.o
+obj-$(CONFIG_PTP_1588_CLOCK_GIANFAR) += gianfar_ptp.o
 obj-$(CONFIG_TEHUTI) += tehuti.o
 obj-$(CONFIG_ENIC) += enic/
 obj-$(CONFIG_JME) += jme.o
diff --git a/drivers/net/arm/ixp4xx_eth.c b/drivers/net/arm/ixp4xx_eth.c
index 9eb9b98a7ae3..de51e8453c13 100644
--- a/drivers/net/arm/ixp4xx_eth.c
+++ b/drivers/net/arm/ixp4xx_eth.c
@@ -30,9 +30,12 @@
 #include <linux/etherdevice.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/net_tstamp.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
+#include <linux/ptp_classify.h>
 #include <linux/slab.h>
+#include <mach/ixp46x_ts.h>
 #include <mach/npe.h>
 #include <mach/qmgr.h>
 
@@ -67,6 +70,10 @@
 #define RXFREE_QUEUE(port_id)   (NPE_ID(port_id) + 26)
 #define TXDONE_QUEUE            31
 
+#define PTP_SLAVE_MODE          1
+#define PTP_MASTER_MODE         2
+#define PORT2CHANNEL(p)         NPE_ID(p->id)
+
 /* TX Control Registers */
 #define TX_CNTRL0_TX_EN         0x01
 #define TX_CNTRL0_HALFDUPLEX    0x02
@@ -171,6 +178,8 @@ struct port {
         int id;                 /* logical port ID */
         int speed, duplex;
         u8 firmware[4];
+        int hwts_tx_en;
+        int hwts_rx_en;
 };
 
 /* NPE message structure */
@@ -246,6 +255,172 @@ static int ports_open;
 static struct port *npe_port_tab[MAX_NPES];
 static struct dma_pool *dma_pool;
 
+static struct sock_filter ptp_filter[] = {
+        PTP_FILTER
+};
+
+static int ixp_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
+{
+        u8 *data = skb->data;
+        unsigned int offset;
+        u16 *hi, *id;
+        u32 lo;
+
+        if (sk_run_filter(skb, ptp_filter) != PTP_CLASS_V1_IPV4)
+                return 0;
+
+        offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
+
+        if (skb->len < offset + OFF_PTP_SEQUENCE_ID + sizeof(seqid))
+                return 0;
+
+        hi = (u16 *)(data + offset + OFF_PTP_SOURCE_UUID);
+        id = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
+
+        memcpy(&lo, &hi[1], sizeof(lo));
+
+        return (uid_hi == ntohs(*hi) &&
+                uid_lo == ntohl(lo) &&
+                seqid  == ntohs(*id));
+}
+
+static void ixp_rx_timestamp(struct port *port, struct sk_buff *skb)
+{
+        struct skb_shared_hwtstamps *shhwtstamps;
+        struct ixp46x_ts_regs *regs;
+        u64 ns;
+        u32 ch, hi, lo, val;
+        u16 uid, seq;
+
+        if (!port->hwts_rx_en)
+                return;
+
+        ch = PORT2CHANNEL(port);
+
+        regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+
+        val = __raw_readl(&regs->channel[ch].ch_event);
+
+        if (!(val & RX_SNAPSHOT_LOCKED))
+                return;
+
+        lo = __raw_readl(&regs->channel[ch].src_uuid_lo);
+        hi = __raw_readl(&regs->channel[ch].src_uuid_hi);
+
+        uid = hi & 0xffff;
+        seq = (hi >> 16) & 0xffff;
+
+        if (!ixp_ptp_match(skb, htons(uid), htonl(lo), htons(seq)))
+                goto out;
+
+        lo = __raw_readl(&regs->channel[ch].rx_snap_lo);
+        hi = __raw_readl(&regs->channel[ch].rx_snap_hi);
+        ns = ((u64) hi) << 32;
+        ns |= lo;
+        ns <<= TICKS_NS_SHIFT;
+
+        shhwtstamps = skb_hwtstamps(skb);
+        memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+        shhwtstamps->hwtstamp = ns_to_ktime(ns);
+out:
+        __raw_writel(RX_SNAPSHOT_LOCKED, &regs->channel[ch].ch_event);
+}
+
+static void ixp_tx_timestamp(struct port *port, struct sk_buff *skb)
+{
+        struct skb_shared_hwtstamps shhwtstamps;
+        struct ixp46x_ts_regs *regs;
+        struct skb_shared_info *shtx;
+        u64 ns;
+        u32 ch, cnt, hi, lo, val;
+
+        shtx = skb_shinfo(skb);
+        if (unlikely(shtx->tx_flags & SKBTX_HW_TSTAMP && port->hwts_tx_en))
+                shtx->tx_flags |= SKBTX_IN_PROGRESS;
+        else
+                return;
+
+        ch = PORT2CHANNEL(port);
+
+        regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+
+        /*
+         * This really stinks, but we have to poll for the Tx time stamp.
+         * Usually, the time stamp is ready after 4 to 6 microseconds.
+         */
+        for (cnt = 0; cnt < 100; cnt++) {
+                val = __raw_readl(&regs->channel[ch].ch_event);
+                if (val & TX_SNAPSHOT_LOCKED)
+                        break;
+                udelay(1);
+        }
+        if (!(val & TX_SNAPSHOT_LOCKED)) {
+                shtx->tx_flags &= ~SKBTX_IN_PROGRESS;
+                return;
+        }
+
+        lo = __raw_readl(&regs->channel[ch].tx_snap_lo);
+        hi = __raw_readl(&regs->channel[ch].tx_snap_hi);
+        ns = ((u64) hi) << 32;
+        ns |= lo;
+        ns <<= TICKS_NS_SHIFT;
+
+        memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+        shhwtstamps.hwtstamp = ns_to_ktime(ns);
+        skb_tstamp_tx(skb, &shhwtstamps);
+
+        __raw_writel(TX_SNAPSHOT_LOCKED, &regs->channel[ch].ch_event);
+}
+
+static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+        struct hwtstamp_config cfg;
+        struct ixp46x_ts_regs *regs;
+        struct port *port = netdev_priv(netdev);
+        int ch;
+
+        if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+                return -EFAULT;
+
+        if (cfg.flags) /* reserved for future extensions */
+                return -EINVAL;
+
+        ch = PORT2CHANNEL(port);
+        regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+
+        switch (cfg.tx_type) {
+        case HWTSTAMP_TX_OFF:
+                port->hwts_tx_en = 0;
+                break;
+        case HWTSTAMP_TX_ON:
+                port->hwts_tx_en = 1;
+                break;
+        default:
+                return -ERANGE;
+        }
+
+        switch (cfg.rx_filter) {
+        case HWTSTAMP_FILTER_NONE:
+                port->hwts_rx_en = 0;
+                break;
+        case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+                port->hwts_rx_en = PTP_SLAVE_MODE;
+                __raw_writel(0, &regs->channel[ch].ch_control);
+                break;
+        case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+                port->hwts_rx_en = PTP_MASTER_MODE;
+                __raw_writel(MASTER_MODE, &regs->channel[ch].ch_control);
+                break;
+        default:
+                return -ERANGE;
+        }
+
+        /* Clear out any old time stamps. */
+        __raw_writel(TX_SNAPSHOT_LOCKED | RX_SNAPSHOT_LOCKED,
+                     &regs->channel[ch].ch_event);
+
+        return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
 
 static int ixp4xx_mdio_cmd(struct mii_bus *bus, int phy_id, int location,
                            int write, u16 cmd)
@@ -573,6 +748,7 @@ static int eth_poll(struct napi_struct *napi, int budget)
 
                 debug_pkt(dev, "eth_poll", skb->data, skb->len);
 
+                ixp_rx_timestamp(port, skb);
                 skb->protocol = eth_type_trans(skb, dev);
                 dev->stats.rx_packets++;
                 dev->stats.rx_bytes += skb->len;
@@ -679,14 +855,12 @@ static int eth_xmit(struct sk_buff *skb, struct net_device *dev)
                 return NETDEV_TX_OK;
         }
         memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4);
-        dev_kfree_skb(skb);
 #endif
 
         phys = dma_map_single(&dev->dev, mem, bytes, DMA_TO_DEVICE);
         if (dma_mapping_error(&dev->dev, phys)) {
-#ifdef __ARMEB__
                 dev_kfree_skb(skb);
-#else
+#ifndef __ARMEB__
                 kfree(mem);
 #endif
                 dev->stats.tx_dropped++;
@@ -728,6 +902,13 @@ static int eth_xmit(struct sk_buff *skb, struct net_device *dev)
 #if DEBUG_TX
         printk(KERN_DEBUG "%s: eth_xmit end\n", dev->name);
 #endif
+
+        ixp_tx_timestamp(port, skb);
+        skb_tx_timestamp(skb);
+
+#ifndef __ARMEB__
+        dev_kfree_skb(skb);
+#endif
         return NETDEV_TX_OK;
 }
 
@@ -783,6 +964,9 @@ static int eth_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
         if (!netif_running(dev))
                 return -EINVAL;
 
+        if (cpu_is_ixp46x() && cmd == SIOCSHWTSTAMP)
+                return hwtstamp_ioctl(dev, req, cmd);
+
         return phy_mii_ioctl(port->phydev, req, cmd);
 }
 
@@ -1171,6 +1355,11 @@ static int __devinit eth_init_one(struct platform_device *pdev)
         char phy_id[MII_BUS_ID_SIZE + 3];
         int err;
 
+        if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
+                pr_err("ixp4xx_eth: bad ptp filter\n");
+                return -EINVAL;
+        }
+
         if (!(dev = alloc_etherdev(sizeof(struct port))))
                 return -ENOMEM;
 
diff --git a/drivers/net/gianfar_ptp.c b/drivers/net/gianfar_ptp.c
new file mode 100644
index 000000000000..d8e175382d1d
--- /dev/null
+++ b/drivers/net/gianfar_ptp.c
@@ -0,0 +1,588 @@
+/*
+ * PTP 1588 clock using the eTSEC
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/hrtimer.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/timex.h>
+#include <linux/io.h>
+
+#include <linux/ptp_clock_kernel.h>
+
+#include "gianfar.h"
+
+/*
+ * gianfar ptp registers
+ * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010
+ */
+struct gianfar_ptp_registers {
+        u32 tmr_ctrl;     /* Timer control register */
+        u32 tmr_tevent;   /* Timestamp event register */
+        u32 tmr_temask;   /* Timer event mask register */
+        u32 tmr_pevent;   /* Timestamp event register */
+        u32 tmr_pemask;   /* Timer event mask register */
+        u32 tmr_stat;     /* Timestamp status register */
+        u32 tmr_cnt_h;    /* Timer counter high register */
+        u32 tmr_cnt_l;    /* Timer counter low register */
+        u32 tmr_add;      /* Timer drift compensation addend register */
+        u32 tmr_acc;      /* Timer accumulator register */
+        u32 tmr_prsc;     /* Timer prescale */
+        u8  res1[4];
+        u32 tmroff_h;     /* Timer offset high */
+        u32 tmroff_l;     /* Timer offset low */
+        u8  res2[8];
+        u32 tmr_alarm1_h; /* Timer alarm 1 high register */
+        u32 tmr_alarm1_l; /* Timer alarm 1 high register */
+        u32 tmr_alarm2_h; /* Timer alarm 2 high register */
+        u32 tmr_alarm2_l; /* Timer alarm 2 high register */
+        u8  res3[48];
+        u32 tmr_fiper1;   /* Timer fixed period interval */
+        u32 tmr_fiper2;   /* Timer fixed period interval */
+        u32 tmr_fiper3;   /* Timer fixed period interval */
+        u8  res4[20];
+        u32 tmr_etts1_h;  /* Timestamp of general purpose external trigger */
+        u32 tmr_etts1_l;  /* Timestamp of general purpose external trigger */
+        u32 tmr_etts2_h;  /* Timestamp of general purpose external trigger */
+        u32 tmr_etts2_l;  /* Timestamp of general purpose external trigger */
+};
+
+/* Bit definitions for the TMR_CTRL register */
+#define ALM1P                 (1<<31) /* Alarm1 output polarity */
+#define ALM2P                 (1<<30) /* Alarm2 output polarity */
+#define FS                    (1<<28) /* FIPER start indication */
+#define PP1L                  (1<<27) /* Fiper1 pulse loopback mode enabled. */
+#define PP2L                  (1<<26) /* Fiper2 pulse loopback mode enabled. */
+#define TCLK_PERIOD_SHIFT     (16) /* 1588 timer reference clock period. */
+#define TCLK_PERIOD_MASK      (0x3ff)
+#define RTPE                  (1<<15) /* Record Tx Timestamp to PAL Enable. */
+#define FRD                   (1<<14) /* FIPER Realignment Disable */
+#define ESFDP                 (1<<11) /* External Tx/Rx SFD Polarity. */
+#define ESFDE                 (1<<10) /* External Tx/Rx SFD Enable. */
+#define ETEP2                 (1<<9) /* External trigger 2 edge polarity */
+#define ETEP1                 (1<<8) /* External trigger 1 edge polarity */
+#define COPH                  (1<<7) /* Generated clock output phase. */
+#define CIPH                  (1<<6) /* External oscillator input clock phase */
+#define TMSR                  (1<<5) /* Timer soft reset. */
+#define BYP                   (1<<3) /* Bypass drift compensated clock */
+#define TE                    (1<<2) /* 1588 timer enable. */
+#define CKSEL_SHIFT           (0)    /* 1588 Timer reference clock source */
+#define CKSEL_MASK            (0x3)
+
+/* Bit definitions for the TMR_TEVENT register */
+#define ETS2                  (1<<25) /* External trigger 2 timestamp sampled */
+#define ETS1                  (1<<24) /* External trigger 1 timestamp sampled */
+#define ALM2                  (1<<17) /* Current time = alarm time register 2 */
+#define ALM1                  (1<<16) /* Current time = alarm time register 1 */
+#define PP1                   (1<<7)  /* periodic pulse generated on FIPER1 */
+#define PP2                   (1<<6)  /* periodic pulse generated on FIPER2 */
+#define PP3                   (1<<5)  /* periodic pulse generated on FIPER3 */
+
+/* Bit definitions for the TMR_TEMASK register */
+#define ETS2EN                (1<<25) /* External trigger 2 timestamp enable */
+#define ETS1EN                (1<<24) /* External trigger 1 timestamp enable */
+#define ALM2EN                (1<<17) /* Timer ALM2 event enable */
+#define ALM1EN                (1<<16) /* Timer ALM1 event enable */
+#define PP1EN                 (1<<7) /* Periodic pulse event 1 enable */
+#define PP2EN                 (1<<6) /* Periodic pulse event 2 enable */
+
+/* Bit definitions for the TMR_PEVENT register */
+#define TXP2                  (1<<9) /* PTP transmitted timestamp im TXTS2 */
+#define TXP1                  (1<<8) /* PTP transmitted timestamp in TXTS1 */
+#define RXP                   (1<<0) /* PTP frame has been received */
+
+/* Bit definitions for the TMR_PEMASK register */
+#define TXP2EN                (1<<9) /* Transmit PTP packet event 2 enable */
+#define TXP1EN                (1<<8) /* Transmit PTP packet event 1 enable */
+#define RXPEN                 (1<<0) /* Receive PTP packet event enable */
+
+/* Bit definitions for the TMR_STAT register */
+#define STAT_VEC_SHIFT        (0) /* Timer general purpose status vector */
+#define STAT_VEC_MASK         (0x3f)
+
+/* Bit definitions for the TMR_PRSC register */
+#define PRSC_OCK_SHIFT        (0) /* Output clock division/prescale factor. */
+#define PRSC_OCK_MASK         (0xffff)
+
+
+#define DRIVER          "gianfar_ptp"
+#define DEFAULT_CKSEL   1
+#define N_ALARM         1 /* first alarm is used internally to reset fipers */
+#define N_EXT_TS        2
+#define REG_SIZE        sizeof(struct gianfar_ptp_registers)
+
+struct etsects {
+        struct gianfar_ptp_registers *regs;
+        spinlock_t lock; /* protects regs */
+        struct ptp_clock *clock;
+        struct ptp_clock_info caps;
+        struct resource *rsrc;
+        int irq;
+        u64 alarm_interval; /* for periodic alarm */
+        u64 alarm_value;
+        u32 tclk_period;  /* nanoseconds */
+        u32 tmr_prsc;
+        u32 tmr_add;
+        u32 cksel;
+        u32 tmr_fiper1;
+        u32 tmr_fiper2;
+};
+
+/*
+ * Register access functions
+ */
+
+/* Caller must hold etsects->lock. */
+static u64 tmr_cnt_read(struct etsects *etsects)
+{
+        u64 ns;
+        u32 lo, hi;
+
+        lo = gfar_read(&etsects->regs->tmr_cnt_l);
+        hi = gfar_read(&etsects->regs->tmr_cnt_h);
+        ns = ((u64) hi) << 32;
+        ns |= lo;
+        return ns;
+}
+
+/* Caller must hold etsects->lock. */
+static void tmr_cnt_write(struct etsects *etsects, u64 ns)
+{
+        u32 hi = ns >> 32;
+        u32 lo = ns & 0xffffffff;
+
+        gfar_write(&etsects->regs->tmr_cnt_l, lo);
+        gfar_write(&etsects->regs->tmr_cnt_h, hi);
+}
+
+/* Caller must hold etsects->lock. */
+static void set_alarm(struct etsects *etsects)
+{
+        u64 ns;
+        u32 lo, hi;
+
+        ns = tmr_cnt_read(etsects) + 1500000000ULL;
+        ns = div_u64(ns, 1000000000UL) * 1000000000ULL;
+        ns -= etsects->tclk_period;
+        hi = ns >> 32;
+        lo = ns & 0xffffffff;
+        gfar_write(&etsects->regs->tmr_alarm1_l, lo);
+        gfar_write(&etsects->regs->tmr_alarm1_h, hi);
+}
+
+/* Caller must hold etsects->lock. */
+static void set_fipers(struct etsects *etsects)
+{
+        u32 tmr_ctrl = gfar_read(&etsects->regs->tmr_ctrl);
+
+        gfar_write(&etsects->regs->tmr_ctrl,   tmr_ctrl & (~TE));
+        gfar_write(&etsects->regs->tmr_prsc,   etsects->tmr_prsc);
+        gfar_write(&etsects->regs->tmr_fiper1, etsects->tmr_fiper1);
+        gfar_write(&etsects->regs->tmr_fiper2, etsects->tmr_fiper2);
+        set_alarm(etsects);
+        gfar_write(&etsects->regs->tmr_ctrl,   tmr_ctrl|TE);
+}
+
+/*
+ * Interrupt service routine
+ */
+
+static irqreturn_t isr(int irq, void *priv)
+{
+        struct etsects *etsects = priv;
+        struct ptp_clock_event event;
+        u64 ns;
+        u32 ack = 0, lo, hi, mask, val;
+
+        val = gfar_read(&etsects->regs->tmr_tevent);
+
+        if (val & ETS1) {
+                ack |= ETS1;
+                hi = gfar_read(&etsects->regs->tmr_etts1_h);
+                lo = gfar_read(&etsects->regs->tmr_etts1_l);
+                event.type = PTP_CLOCK_EXTTS;
+                event.index = 0;
+                event.timestamp = ((u64) hi) << 32;
+                event.timestamp |= lo;
+                ptp_clock_event(etsects->clock, &event);
+        }
+
+        if (val & ETS2) {
+                ack |= ETS2;
+                hi = gfar_read(&etsects->regs->tmr_etts2_h);
+                lo = gfar_read(&etsects->regs->tmr_etts2_l);
+                event.type = PTP_CLOCK_EXTTS;
+                event.index = 1;
+                event.timestamp = ((u64) hi) << 32;
+                event.timestamp |= lo;
+                ptp_clock_event(etsects->clock, &event);
+        }
+
+        if (val & ALM2) {
+                ack |= ALM2;
+                if (etsects->alarm_value) {
+                        event.type = PTP_CLOCK_ALARM;
+                        event.index = 0;
+                        event.timestamp = etsects->alarm_value;
+                        ptp_clock_event(etsects->clock, &event);
+                }
+                if (etsects->alarm_interval) {
+                        ns = etsects->alarm_value + etsects->alarm_interval;
+                        hi = ns >> 32;
+                        lo = ns & 0xffffffff;
+                        spin_lock(&etsects->lock);
+                        gfar_write(&etsects->regs->tmr_alarm2_l, lo);
+                        gfar_write(&etsects->regs->tmr_alarm2_h, hi);
+                        spin_unlock(&etsects->lock);
+                        etsects->alarm_value = ns;
+                } else {
+                        gfar_write(&etsects->regs->tmr_tevent, ALM2);
+                        spin_lock(&etsects->lock);
+                        mask = gfar_read(&etsects->regs->tmr_temask);
+                        mask &= ~ALM2EN;
+                        gfar_write(&etsects->regs->tmr_temask, mask);
+                        spin_unlock(&etsects->lock);
+                        etsects->alarm_value = 0;
+                        etsects->alarm_interval = 0;
+                }
+        }
+
+        if (val & PP1) {
+                ack |= PP1;
+                event.type = PTP_CLOCK_PPS;
+                ptp_clock_event(etsects->clock, &event);
+        }
+
+        if (ack) {
+                gfar_write(&etsects->regs->tmr_tevent, ack);
+                return IRQ_HANDLED;
+        } else
+                return IRQ_NONE;
+}
+
+/*
+ * PTP clock operations
+ */
+
+static int ptp_gianfar_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+        u64 adj;
+        u32 diff, tmr_add;
+        int neg_adj = 0;
+        struct etsects *etsects = container_of(ptp, struct etsects, caps);
+
+        if (ppb < 0) {
+                neg_adj = 1;
+                ppb = -ppb;
+        }
+        tmr_add = etsects->tmr_add;
+        adj = tmr_add;
+        adj *= ppb;
+        diff = div_u64(adj, 1000000000ULL);
+
+        tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
+
+        gfar_write(&etsects->regs->tmr_add, tmr_add);
+
+        return 0;
+}
+
+static int ptp_gianfar_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+        s64 now;
+        unsigned long flags;
+        struct etsects *etsects = container_of(ptp, struct etsects, caps);
+
+        spin_lock_irqsave(&etsects->lock, flags);
+
+        now = tmr_cnt_read(etsects);
+        now += delta;
+        tmr_cnt_write(etsects, now);
+
+        spin_unlock_irqrestore(&etsects->lock, flags);
+
+        set_fipers(etsects);
+
+        return 0;
+}
+
+static int ptp_gianfar_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+        u64 ns;
+        u32 remainder;
+        unsigned long flags;
+        struct etsects *etsects = container_of(ptp, struct etsects, caps);
+
+        spin_lock_irqsave(&etsects->lock, flags);
+
+        ns = tmr_cnt_read(etsects);
+
+        spin_unlock_irqrestore(&etsects->lock, flags);
+
+        ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
+        ts->tv_nsec = remainder;
+        return 0;
+}
+
+static int ptp_gianfar_settime(struct ptp_clock_info *ptp,
+                               const struct timespec *ts)
+{
+        u64 ns;
+        unsigned long flags;
+        struct etsects *etsects = container_of(ptp, struct etsects, caps);
+
+        ns = ts->tv_sec * 1000000000ULL;
+        ns += ts->tv_nsec;
+
+        spin_lock_irqsave(&etsects->lock, flags);
+
+        tmr_cnt_write(etsects, ns);
+        set_fipers(etsects);
+
+        spin_unlock_irqrestore(&etsects->lock, flags);
+
+        return 0;
+}
+
+static int ptp_gianfar_enable(struct ptp_clock_info *ptp,
+                              struct ptp_clock_request *rq, int on)
+{
+        struct etsects *etsects = container_of(ptp, struct etsects, caps);
+        unsigned long flags;
+        u32 bit, mask;
+
+        switch (rq->type) {
+        case PTP_CLK_REQ_EXTTS:
+                switch (rq->extts.index) {
+                case 0:
+                        bit = ETS1EN;
+                        break;
+                case 1:
+                        bit = ETS2EN;
+                        break;
+                default:
+                        return -EINVAL;
+                }
+                spin_lock_irqsave(&etsects->lock, flags);
+                mask = gfar_read(&etsects->regs->tmr_temask);
+                if (on)
+                        mask |= bit;
+                else
+                        mask &= ~bit;
+                gfar_write(&etsects->regs->tmr_temask, mask);
+                spin_unlock_irqrestore(&etsects->lock, flags);
+                return 0;
+
+        case PTP_CLK_REQ_PPS:
+                spin_lock_irqsave(&etsects->lock, flags);
+                mask = gfar_read(&etsects->regs->tmr_temask);
+                if (on)
+                        mask |= PP1EN;
+                else
+                        mask &= ~PP1EN;
+                gfar_write(&etsects->regs->tmr_temask, mask);
+                spin_unlock_irqrestore(&etsects->lock, flags);
+                return 0;
+
+        default:
+                break;
+        }
+
+        return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info ptp_gianfar_caps = {
+        .owner          = THIS_MODULE,
+        .name           = "gianfar clock",
+        .max_adj        = 512000,
+        .n_alarm        = N_ALARM,
+        .n_ext_ts       = N_EXT_TS,
+        .n_per_out      = 0,
+        .pps            = 1,
+        .adjfreq        = ptp_gianfar_adjfreq,
+        .adjtime        = ptp_gianfar_adjtime,
+        .gettime        = ptp_gianfar_gettime,
+        .settime        = ptp_gianfar_settime,
+        .enable         = ptp_gianfar_enable,
+};
+
+/* OF device tree */
+
+static int get_of_u32(struct device_node *node, char *str, u32 *val)
+{
+        int plen;
+        const u32 *prop = of_get_property(node, str, &plen);
+
+        if (!prop || plen != sizeof(*prop))
+                return -1;
+        *val = *prop;
+        return 0;
+}
+
+static int gianfar_ptp_probe(struct platform_device *dev)
+{
+        struct device_node *node = dev->dev.of_node;
+        struct etsects *etsects;
+        struct timespec now;
+        int err = -ENOMEM;
+        u32 tmr_ctrl;
+        unsigned long flags;
+
+        etsects = kzalloc(sizeof(*etsects), GFP_KERNEL);
+        if (!etsects)
+                goto no_memory;
+
+        err = -ENODEV;
+
+        etsects->caps = ptp_gianfar_caps;
+        etsects->cksel = DEFAULT_CKSEL;
+
+        if (get_of_u32(node, "fsl,tclk-period", &etsects->tclk_period) ||
+            get_of_u32(node, "fsl,tmr-prsc", &etsects->tmr_prsc) ||
+            get_of_u32(node, "fsl,tmr-add", &etsects->tmr_add) ||
+            get_of_u32(node, "fsl,tmr-fiper1", &etsects->tmr_fiper1) ||
+            get_of_u32(node, "fsl,tmr-fiper2", &etsects->tmr_fiper2) ||
+            get_of_u32(node, "fsl,max-adj", &etsects->caps.max_adj)) {
+                pr_err("device tree node missing required elements\n");
+                goto no_node;
+        }
+
+        etsects->irq = platform_get_irq(dev, 0);
+
+        if (etsects->irq == NO_IRQ) {
+                pr_err("irq not in device tree\n");
+                goto no_node;
+        }
+        if (request_irq(etsects->irq, isr, 0, DRIVER, etsects)) {
+                pr_err("request_irq failed\n");
+                goto no_node;
+        }
+
+        etsects->rsrc = platform_get_resource(dev, IORESOURCE_MEM, 0);
+        if (!etsects->rsrc) {
+                pr_err("no resource\n");
+                goto no_resource;
+        }
+        if (request_resource(&ioport_resource, etsects->rsrc)) {
+                pr_err("resource busy\n");
+                goto no_resource;
+        }
+
+        spin_lock_init(&etsects->lock);
+
+        etsects->regs = ioremap(etsects->rsrc->start,
+                                1 + etsects->rsrc->end - etsects->rsrc->start);
+        if (!etsects->regs) {
+                pr_err("ioremap ptp registers failed\n");
+                goto no_ioremap;
+        }
+        getnstimeofday(&now);
+        ptp_gianfar_settime(&etsects->caps, &now);
+
+        tmr_ctrl =
+          (etsects->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT |
+          (etsects->cksel & CKSEL_MASK) << CKSEL_SHIFT;
+
+        spin_lock_irqsave(&etsects->lock, flags);
+
+        gfar_write(&etsects->regs->tmr_ctrl,   tmr_ctrl);
+        gfar_write(&etsects->regs->tmr_add,    etsects->tmr_add);
+        gfar_write(&etsects->regs->tmr_prsc,   etsects->tmr_prsc);
+        gfar_write(&etsects->regs->tmr_fiper1, etsects->tmr_fiper1);
+        gfar_write(&etsects->regs->tmr_fiper2, etsects->tmr_fiper2);
+        set_alarm(etsects);
+        gfar_write(&etsects->regs->tmr_ctrl,   tmr_ctrl|FS|RTPE|TE);
+
+        spin_unlock_irqrestore(&etsects->lock, flags);
+
+        etsects->clock = ptp_clock_register(&etsects->caps);
+        if (IS_ERR(etsects->clock)) {
+                err = PTR_ERR(etsects->clock);
+                goto no_clock;
+        }
+
+        dev_set_drvdata(&dev->dev, etsects);
+
+        return 0;
+
+no_clock:
+no_ioremap:
+        release_resource(etsects->rsrc);
+no_resource:
+        free_irq(etsects->irq, etsects);
+no_node:
+        kfree(etsects);
+no_memory:
+        return err;
+}
+
+static int gianfar_ptp_remove(struct platform_device *dev)
+{
+        struct etsects *etsects = dev_get_drvdata(&dev->dev);
+
+        gfar_write(&etsects->regs->tmr_temask, 0);
+        gfar_write(&etsects->regs->tmr_ctrl,   0);
+
+        ptp_clock_unregister(etsects->clock);
+        iounmap(etsects->regs);
+        release_resource(etsects->rsrc);
+        free_irq(etsects->irq, etsects);
+        kfree(etsects);
+
+        return 0;
+}
+
+static struct of_device_id match_table[] = {
+        { .compatible = "fsl,etsec-ptp" },
+        {},
+};
+
+static struct platform_driver gianfar_ptp_driver = {
+        .driver = {
+                .name           = "gianfar_ptp",
+                .of_match_table = match_table,
+                .owner          = THIS_MODULE,
+        },
+        .probe       = gianfar_ptp_probe,
+        .remove      = gianfar_ptp_remove,
+};
+
+/* module operations */
+
+static int __init ptp_gianfar_init(void)
+{
+        return platform_driver_register(&gianfar_ptp_driver);
+}
+
+module_init(ptp_gianfar_init);
+
+static void __exit ptp_gianfar_exit(void)
+{
+        platform_driver_unregister(&gianfar_ptp_driver);
+}
+
+module_exit(ptp_gianfar_exit);
+
+MODULE_AUTHOR("Richard Cochran <richard.cochran@omicron.at>");
+MODULE_DESCRIPTION("PTP clock using the eTSEC");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ioc3-eth.c b/drivers/net/ioc3-eth.c
index 96c95617195f..32f07f868d89 100644
--- a/drivers/net/ioc3-eth.c
+++ b/drivers/net/ioc3-eth.c
@@ -915,7 +915,7 @@ static void ioc3_alloc_rings(struct net_device *dev)
 
                         skb = ioc3_alloc_skb(RX_BUF_ALLOC_SIZE, GFP_ATOMIC);
                         if (!skb) {
-                                show_free_areas();
+                                show_free_areas(0);
                                 continue;
                         }
 
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 13bebab65d02..2333215bbb32 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_FIXED_PHY)		+= fixed.o
 obj-$(CONFIG_MDIO_BITBANG)      += mdio-bitbang.o
 obj-$(CONFIG_MDIO_GPIO)         += mdio-gpio.o
 obj-$(CONFIG_NATIONAL_PHY)      += national.o
+obj-$(CONFIG_DP83640_PHY)       += dp83640.o
 obj-$(CONFIG_STE10XP)           += ste10Xp.o
 obj-$(CONFIG_MICREL_PHY)        += micrel.o
 obj-$(CONFIG_MDIO_OCTEON)       += mdio-octeon.o
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
new file mode 100644
index 000000000000..b0c9522bb535
--- /dev/null
+++ b/drivers/net/phy/dp83640.c
@@ -0,0 +1,1100 @@
+/*
+ * Driver for the National Semiconductor DP83640 PHYTER
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/ethtool.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/ptp_classify.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "dp83640_reg.h"
+
+#define DP83640_PHY_ID  0x20005ce1
+#define PAGESEL         0x13
+#define LAYER4          0x02
+#define LAYER2          0x01
+#define MAX_RXTS        4
+#define MAX_TXTS        4
+#define N_EXT_TS        1
+#define PSF_PTPVER      2
+#define PSF_EVNT        0x4000
+#define PSF_RX          0x2000
+#define PSF_TX          0x1000
+#define EXT_EVENT       1
+#define EXT_GPIO        1
+#define CAL_EVENT       2
+#define CAL_GPIO        9
+#define CAL_TRIGGER     2
+
+/* phyter seems to miss the mark by 16 ns */
+#define ADJTIME_FIX     16
+
+#if defined(__BIG_ENDIAN)
+#define ENDIAN_FLAG     0
+#elif defined(__LITTLE_ENDIAN)
+#define ENDIAN_FLAG     PSF_ENDIAN
+#endif
+
+#define SKB_PTP_TYPE(__skb) (*(unsigned int *)((__skb)->cb))
+
+struct phy_rxts {
+        u16 ns_lo;   /* ns[15:0] */
+        u16 ns_hi;   /* overflow[1:0], ns[29:16] */
+        u16 sec_lo;  /* sec[15:0] */
+        u16 sec_hi;  /* sec[31:16] */
+        u16 seqid;   /* sequenceId[15:0] */
+        u16 msgtype; /* messageType[3:0], hash[11:0] */
+};
+
+struct phy_txts {
+        u16 ns_lo;   /* ns[15:0] */
+        u16 ns_hi;   /* overflow[1:0], ns[29:16] */
+        u16 sec_lo;  /* sec[15:0] */
+        u16 sec_hi;  /* sec[31:16] */
+};
+
+struct rxts {
+        struct list_head list;
+        unsigned long tmo;
+        u64 ns;
+        u16 seqid;
+        u8  msgtype;
+        u16 hash;
+};
+
+struct dp83640_clock;
+
+struct dp83640_private {
+        struct list_head list;
+        struct dp83640_clock *clock;
+        struct phy_device *phydev;
+        struct work_struct ts_work;
+        int hwts_tx_en;
+        int hwts_rx_en;
+        int layer;
+        int version;
+        /* remember state of cfg0 during calibration */
+        int cfg0;
+        /* remember the last event time stamp */
+        struct phy_txts edata;
+        /* list of rx timestamps */
+        struct list_head rxts;
+        struct list_head rxpool;
+        struct rxts rx_pool_data[MAX_RXTS];
+        /* protects above three fields from concurrent access */
+        spinlock_t rx_lock;
+        /* queues of incoming and outgoing packets */
+        struct sk_buff_head rx_queue;
+        struct sk_buff_head tx_queue;
+};
+
+struct dp83640_clock {
+        /* keeps the instance in the 'phyter_clocks' list */
+        struct list_head list;
+        /* we create one clock instance per MII bus */
+        struct mii_bus *bus;
+        /* protects extended registers from concurrent access */
+        struct mutex extreg_lock;
+        /* remembers which page was last selected */
+        int page;
+        /* our advertised capabilities */
+        struct ptp_clock_info caps;
+        /* protects the three fields below from concurrent access */
+        struct mutex clock_lock;
+        /* the one phyter from which we shall read */
+        struct dp83640_private *chosen;
+        /* list of the other attached phyters, not chosen */
+        struct list_head phylist;
+        /* reference to our PTP hardware clock */
+        struct ptp_clock *ptp_clock;
+};
+
+/* globals */
+
+static int chosen_phy = -1;
+static ushort cal_gpio = 4;
+
+module_param(chosen_phy, int, 0444);
+module_param(cal_gpio, ushort, 0444);
+
+MODULE_PARM_DESC(chosen_phy, \
+        "The address of the PHY to use for the ancillary clock features");
+MODULE_PARM_DESC(cal_gpio, \
+        "Which GPIO line to use for synchronizing multiple PHYs");
+
+/* a list of clocks and a mutex to protect it */
+static LIST_HEAD(phyter_clocks);
+static DEFINE_MUTEX(phyter_clocks_lock);
+
+static void rx_timestamp_work(struct work_struct *work);
+
+/* extended register access functions */
+
+#define BROADCAST_ADDR 31
+
+static inline int broadcast_write(struct mii_bus *bus, u32 regnum, u16 val)
+{
+        return mdiobus_write(bus, BROADCAST_ADDR, regnum, val);
+}
+
+/* Caller must hold extreg_lock. */
+static int ext_read(struct phy_device *phydev, int page, u32 regnum)
+{
+        struct dp83640_private *dp83640 = phydev->priv;
+        int val;
+
+        if (dp83640->clock->page != page) {
+                broadcast_write(phydev->bus, PAGESEL, page);
+                dp83640->clock->page = page;
+        }
+        val = phy_read(phydev, regnum);
+
+        return val;
+}
+
+/* Caller must hold extreg_lock. */
+static void ext_write(int broadcast, struct phy_device *phydev,
+                      int page, u32 regnum, u16 val)
+{
+        struct dp83640_private *dp83640 = phydev->priv;
+
+        if (dp83640->clock->page != page) {
+                broadcast_write(phydev->bus, PAGESEL, page);
+                dp83640->clock->page = page;
+        }
+        if (broadcast)
+                broadcast_write(phydev->bus, regnum, val);
+        else
+                phy_write(phydev, regnum, val);
+}
+
+/* Caller must hold extreg_lock. */
+static int tdr_write(int bc, struct phy_device *dev,
+                     const struct timespec *ts, u16 cmd)
+{
+        ext_write(bc, dev, PAGE4, PTP_TDR, ts->tv_nsec & 0xffff);/* ns[15:0]  */
+        ext_write(bc, dev, PAGE4, PTP_TDR, ts->tv_nsec >> 16);   /* ns[31:16] */
+        ext_write(bc, dev, PAGE4, PTP_TDR, ts->tv_sec & 0xffff); /* sec[15:0] */
+        ext_write(bc, dev, PAGE4, PTP_TDR, ts->tv_sec >> 16);    /* sec[31:16]*/
+
+        ext_write(bc, dev, PAGE4, PTP_CTL, cmd);
+
+        return 0;
+}
+
+/* convert phy timestamps into driver timestamps */
+
+static void phy2rxts(struct phy_rxts *p, struct rxts *rxts)
+{
+        u32 sec;
+
+        sec = p->sec_lo;
+        sec |= p->sec_hi << 16;
+
+        rxts->ns = p->ns_lo;
+        rxts->ns |= (p->ns_hi & 0x3fff) << 16;
+        rxts->ns += ((u64)sec) * 1000000000ULL;
+        rxts->seqid = p->seqid;
+        rxts->msgtype = (p->msgtype >> 12) & 0xf;
+        rxts->hash = p->msgtype & 0x0fff;
+        rxts->tmo = jiffies + HZ;
+}
+
+static u64 phy2txts(struct phy_txts *p)
+{
+        u64 ns;
+        u32 sec;
+
+        sec = p->sec_lo;
+        sec |= p->sec_hi << 16;
+
+        ns = p->ns_lo;
+        ns |= (p->ns_hi & 0x3fff) << 16;
+        ns += ((u64)sec) * 1000000000ULL;
+
+        return ns;
+}
+
+/* ptp clock methods */
+
+static int ptp_dp83640_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+        struct dp83640_clock *clock =
+                container_of(ptp, struct dp83640_clock, caps);
+        struct phy_device *phydev = clock->chosen->phydev;
+        u64 rate;
+        int neg_adj = 0;
+        u16 hi, lo;
+
+        if (ppb < 0) {
+                neg_adj = 1;
+                ppb = -ppb;
+        }
+        rate = ppb;
+        rate <<= 26;
+        rate = div_u64(rate, 1953125);
+
+        hi = (rate >> 16) & PTP_RATE_HI_MASK;
+        if (neg_adj)
+                hi |= PTP_RATE_DIR;
+
+        lo = rate & 0xffff;
+
+        mutex_lock(&clock->extreg_lock);
+
+        ext_write(1, phydev, PAGE4, PTP_RATEH, hi);
+        ext_write(1, phydev, PAGE4, PTP_RATEL, lo);
+
+        mutex_unlock(&clock->extreg_lock);
+
+        return 0;
+}
+
+static int ptp_dp83640_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+        struct dp83640_clock *clock =
+                container_of(ptp, struct dp83640_clock, caps);
+        struct phy_device *phydev = clock->chosen->phydev;
+        struct timespec ts;
+        int err;
+
+        delta += ADJTIME_FIX;
+
+        ts = ns_to_timespec(delta);
+
+        mutex_lock(&clock->extreg_lock);
+
+        err = tdr_write(1, phydev, &ts, PTP_STEP_CLK);
+
+        mutex_unlock(&clock->extreg_lock);
+
+        return err;
+}
+
+static int ptp_dp83640_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+        struct dp83640_clock *clock =
+                container_of(ptp, struct dp83640_clock, caps);
+        struct phy_device *phydev = clock->chosen->phydev;
+        unsigned int val[4];
+
+        mutex_lock(&clock->extreg_lock);
+
+        ext_write(0, phydev, PAGE4, PTP_CTL, PTP_RD_CLK);
+
+        val[0] = ext_read(phydev, PAGE4, PTP_TDR); /* ns[15:0] */
+        val[1] = ext_read(phydev, PAGE4, PTP_TDR); /* ns[31:16] */
+        val[2] = ext_read(phydev, PAGE4, PTP_TDR); /* sec[15:0] */
+        val[3] = ext_read(phydev, PAGE4, PTP_TDR); /* sec[31:16] */
+
+        mutex_unlock(&clock->extreg_lock);
+
+        ts->tv_nsec = val[0] | (val[1] << 16);
+        ts->tv_sec  = val[2] | (val[3] << 16);
+
+        return 0;
+}
+
+static int ptp_dp83640_settime(struct ptp_clock_info *ptp,
+                               const struct timespec *ts)
+{
+        struct dp83640_clock *clock =
+                container_of(ptp, struct dp83640_clock, caps);
+        struct phy_device *phydev = clock->chosen->phydev;
+        int err;
+
+        mutex_lock(&clock->extreg_lock);
+
+        err = tdr_write(1, phydev, ts, PTP_LOAD_CLK);
+
+        mutex_unlock(&clock->extreg_lock);
+
+        return err;
+}
+
+static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
+                              struct ptp_clock_request *rq, int on)
+{
+        struct dp83640_clock *clock =
+                container_of(ptp, struct dp83640_clock, caps);
+        struct phy_device *phydev = clock->chosen->phydev;
+        u16 evnt;
+
+        switch (rq->type) {
+        case PTP_CLK_REQ_EXTTS:
+                if (rq->extts.index != 0)
+                        return -EINVAL;
+                evnt = EVNT_WR | (EXT_EVENT & EVNT_SEL_MASK) << EVNT_SEL_SHIFT;
+                if (on) {
+                        evnt |= (EXT_GPIO & EVNT_GPIO_MASK) << EVNT_GPIO_SHIFT;
+                        evnt |= EVNT_RISE;
+                }
+                ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+                return 0;
+        default:
+                break;
+        }
+
+        return -EOPNOTSUPP;
+}
+
+static u8 status_frame_dst[6] = { 0x01, 0x1B, 0x19, 0x00, 0x00, 0x00 };
+static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
+
+static void enable_status_frames(struct phy_device *phydev, bool on)
+{
+        u16 cfg0 = 0, ver;
+
+        if (on)
+                cfg0 = PSF_EVNT_EN | PSF_RXTS_EN | PSF_TXTS_EN | ENDIAN_FLAG;
+
+        ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
+
+        ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
+        ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
+
+        if (!phydev->attached_dev) {
+                pr_warning("dp83640: expected to find an attached netdevice\n");
+                return;
+        }
+
+        if (on) {
+                if (dev_mc_add(phydev->attached_dev, status_frame_dst))
+                        pr_warning("dp83640: failed to add mc address\n");
+        } else {
+                if (dev_mc_del(phydev->attached_dev, status_frame_dst))
+                        pr_warning("dp83640: failed to delete mc address\n");
+        }
+}
+
+static bool is_status_frame(struct sk_buff *skb, int type)
+{
+        struct ethhdr *h = eth_hdr(skb);
+
+        if (PTP_CLASS_V2_L2 == type &&
+            !memcmp(h->h_source, status_frame_src, sizeof(status_frame_src)))
+                return true;
+        else
+                return false;
+}
+
+static int expired(struct rxts *rxts)
+{
+        return time_after(jiffies, rxts->tmo);
+}
+
+/* Caller must hold rx_lock. */
+static void prune_rx_ts(struct dp83640_private *dp83640)
+{
+        struct list_head *this, *next;
+        struct rxts *rxts;
+
+        list_for_each_safe(this, next, &dp83640->rxts) {
+                rxts = list_entry(this, struct rxts, list);
+                if (expired(rxts)) {
+                        list_del_init(&rxts->list);
+                        list_add(&rxts->list, &dp83640->rxpool);
+                }
+        }
+}
+
+/* synchronize the phyters so they act as one clock */
+
+static void enable_broadcast(struct phy_device *phydev, int init_page, int on)
+{
+        int val;
+        phy_write(phydev, PAGESEL, 0);
+        val = phy_read(phydev, PHYCR2);
+        if (on)
+                val |= BC_WRITE;
+        else
+                val &= ~BC_WRITE;
+        phy_write(phydev, PHYCR2, val);
+        phy_write(phydev, PAGESEL, init_page);
+}
+
+static void recalibrate(struct dp83640_clock *clock)
+{
+        s64 now, diff;
+        struct phy_txts event_ts;
+        struct timespec ts;
+        struct list_head *this;
+        struct dp83640_private *tmp;
+        struct phy_device *master = clock->chosen->phydev;
+        u16 cfg0, evnt, ptp_trig, trigger, val;
+
+        trigger = CAL_TRIGGER;
+
+        mutex_lock(&clock->extreg_lock);
+
+        /*
+         * enable broadcast, disable status frames, enable ptp clock
+         */
+        list_for_each(this, &clock->phylist) {
+                tmp = list_entry(this, struct dp83640_private, list);
+                enable_broadcast(tmp->phydev, clock->page, 1);
+                tmp->cfg0 = ext_read(tmp->phydev, PAGE5, PSF_CFG0);
+                ext_write(0, tmp->phydev, PAGE5, PSF_CFG0, 0);
+                ext_write(0, tmp->phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+        }
+        enable_broadcast(master, clock->page, 1);
+        cfg0 = ext_read(master, PAGE5, PSF_CFG0);
+        ext_write(0, master, PAGE5, PSF_CFG0, 0);
+        ext_write(0, master, PAGE4, PTP_CTL, PTP_ENABLE);
+
+        /*
+         * enable an event timestamp
+         */
+        evnt = EVNT_WR | EVNT_RISE | EVNT_SINGLE;
+        evnt |= (CAL_EVENT & EVNT_SEL_MASK) << EVNT_SEL_SHIFT;
+        evnt |= (cal_gpio & EVNT_GPIO_MASK) << EVNT_GPIO_SHIFT;
+
+        list_for_each(this, &clock->phylist) {
+                tmp = list_entry(this, struct dp83640_private, list);
+                ext_write(0, tmp->phydev, PAGE5, PTP_EVNT, evnt);
+        }
+        ext_write(0, master, PAGE5, PTP_EVNT, evnt);
+
+        /*
+         * configure a trigger
+         */
+        ptp_trig = TRIG_WR | TRIG_IF_LATE | TRIG_PULSE;
+        ptp_trig |= (trigger  & TRIG_CSEL_MASK) << TRIG_CSEL_SHIFT;
+        ptp_trig |= (cal_gpio & TRIG_GPIO_MASK) << TRIG_GPIO_SHIFT;
+        ext_write(0, master, PAGE5, PTP_TRIG, ptp_trig);
+
+        /* load trigger */
+        val = (trigger & TRIG_SEL_MASK) << TRIG_SEL_SHIFT;
+        val |= TRIG_LOAD;
+        ext_write(0, master, PAGE4, PTP_CTL, val);
+
+        /* enable trigger */
+        val &= ~TRIG_LOAD;
+        val |= TRIG_EN;
+        ext_write(0, master, PAGE4, PTP_CTL, val);
+
+        /* disable trigger */
+        val = (trigger & TRIG_SEL_MASK) << TRIG_SEL_SHIFT;
+        val |= TRIG_DIS;
+        ext_write(0, master, PAGE4, PTP_CTL, val);
+
+        /*
+         * read out and correct offsets
+         */
+        val = ext_read(master, PAGE4, PTP_STS);
+        pr_info("master PTP_STS  0x%04hx", val);
+        val = ext_read(master, PAGE4, PTP_ESTS);
+        pr_info("master PTP_ESTS 0x%04hx", val);
+        event_ts.ns_lo  = ext_read(master, PAGE4, PTP_EDATA);
+        event_ts.ns_hi  = ext_read(master, PAGE4, PTP_EDATA);
+        event_ts.sec_lo = ext_read(master, PAGE4, PTP_EDATA);
+        event_ts.sec_hi = ext_read(master, PAGE4, PTP_EDATA);
+        now = phy2txts(&event_ts);
+
+        list_for_each(this, &clock->phylist) {
+                tmp = list_entry(this, struct dp83640_private, list);
+                val = ext_read(tmp->phydev, PAGE4, PTP_STS);
+                pr_info("slave  PTP_STS  0x%04hx", val);
+                val = ext_read(tmp->phydev, PAGE4, PTP_ESTS);
+                pr_info("slave  PTP_ESTS 0x%04hx", val);
+                event_ts.ns_lo  = ext_read(tmp->phydev, PAGE4, PTP_EDATA);
+                event_ts.ns_hi  = ext_read(tmp->phydev, PAGE4, PTP_EDATA);
+                event_ts.sec_lo = ext_read(tmp->phydev, PAGE4, PTP_EDATA);
+                event_ts.sec_hi = ext_read(tmp->phydev, PAGE4, PTP_EDATA);
+                diff = now - (s64) phy2txts(&event_ts);
+                pr_info("slave offset %lld nanoseconds\n", diff);
+                diff += ADJTIME_FIX;
+                ts = ns_to_timespec(diff);
+                tdr_write(0, tmp->phydev, &ts, PTP_STEP_CLK);
+        }
+
+        /*
+         * restore status frames
+         */
+        list_for_each(this, &clock->phylist) {
+                tmp = list_entry(this, struct dp83640_private, list);
+                ext_write(0, tmp->phydev, PAGE5, PSF_CFG0, tmp->cfg0);
+        }
+        ext_write(0, master, PAGE5, PSF_CFG0, cfg0);
+
+        mutex_unlock(&clock->extreg_lock);
+}
+
+/* time stamping methods */
+
+static void decode_evnt(struct dp83640_private *dp83640,
+                        struct phy_txts *phy_txts, u16 ests)
+{
+        struct ptp_clock_event event;
+        int words = (ests >> EVNT_TS_LEN_SHIFT) & EVNT_TS_LEN_MASK;
+
+        switch (words) { /* fall through in every case */
+        case 3:
+                dp83640->edata.sec_hi = phy_txts->sec_hi;
+        case 2:
+                dp83640->edata.sec_lo = phy_txts->sec_lo;
+        case 1:
+                dp83640->edata.ns_hi = phy_txts->ns_hi;
+        case 0:
+                dp83640->edata.ns_lo = phy_txts->ns_lo;
+        }
+
+        event.type = PTP_CLOCK_EXTTS;
+        event.index = 0;
+        event.timestamp = phy2txts(&dp83640->edata);
+
+        ptp_clock_event(dp83640->clock->ptp_clock, &event);
+}
+
+static void decode_rxts(struct dp83640_private *dp83640,
+                        struct phy_rxts *phy_rxts)
+{
+        struct rxts *rxts;
+        unsigned long flags;
+
+        spin_lock_irqsave(&dp83640->rx_lock, flags);
+
+        prune_rx_ts(dp83640);
+
+        if (list_empty(&dp83640->rxpool)) {
+                pr_warning("dp83640: rx timestamp pool is empty\n");
+                goto out;
+        }
+        rxts = list_first_entry(&dp83640->rxpool, struct rxts, list);
+        list_del_init(&rxts->list);
+        phy2rxts(phy_rxts, rxts);
+        list_add_tail(&rxts->list, &dp83640->rxts);
+out:
+        spin_unlock_irqrestore(&dp83640->rx_lock, flags);
+}
+
+static void decode_txts(struct dp83640_private *dp83640,
+                        struct phy_txts *phy_txts)
+{
+        struct skb_shared_hwtstamps shhwtstamps;
+        struct sk_buff *skb;
+        u64 ns;
+
+        /* We must already have the skb that triggered this. */
+
+        skb = skb_dequeue(&dp83640->tx_queue);
+
+        if (!skb) {
+                pr_warning("dp83640: have timestamp but tx_queue empty\n");
+                return;
+        }
+        ns = phy2txts(phy_txts);
+        memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+        shhwtstamps.hwtstamp = ns_to_ktime(ns);
+        skb_complete_tx_timestamp(skb, &shhwtstamps);
+}
+
+static void decode_status_frame(struct dp83640_private *dp83640,
+                                struct sk_buff *skb)
+{
+        struct phy_rxts *phy_rxts;
+        struct phy_txts *phy_txts;
+        u8 *ptr;
+        int len, size;
+        u16 ests, type;
+
+        ptr = skb->data + 2;
+
+        for (len = skb_headlen(skb) - 2; len > sizeof(type); len -= size) {
+
+                type = *(u16 *)ptr;
+                ests = type & 0x0fff;
+                type = type & 0xf000;
+                len -= sizeof(type);
+                ptr += sizeof(type);
+
+                if (PSF_RX == type && len >= sizeof(*phy_rxts)) {
+
+                        phy_rxts = (struct phy_rxts *) ptr;
+                        decode_rxts(dp83640, phy_rxts);
+                        size = sizeof(*phy_rxts);
+
+                } else if (PSF_TX == type && len >= sizeof(*phy_txts)) {
+
+                        phy_txts = (struct phy_txts *) ptr;
+                        decode_txts(dp83640, phy_txts);
+                        size = sizeof(*phy_txts);
+
+                } else if (PSF_EVNT == type && len >= sizeof(*phy_txts)) {
+
+                        phy_txts = (struct phy_txts *) ptr;
+                        decode_evnt(dp83640, phy_txts, ests);
+                        size = sizeof(*phy_txts);
+
+                } else {
+                        size = 0;
+                        break;
+                }
+                ptr += size;
+        }
+}
+
+static int match(struct sk_buff *skb, unsigned int type, struct rxts *rxts)
+{
+        u16 *seqid;
+        unsigned int offset;
+        u8 *msgtype, *data = skb_mac_header(skb);
+
+        /* check sequenceID, messageType, 12 bit hash of offset 20-29 */
+
+        switch (type) {
+        case PTP_CLASS_V1_IPV4:
+        case PTP_CLASS_V2_IPV4:
+                offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
+                break;
+        case PTP_CLASS_V1_IPV6:
+        case PTP_CLASS_V2_IPV6:
+                offset = OFF_PTP6;
+                break;
+        case PTP_CLASS_V2_L2:
+                offset = ETH_HLEN;
+                break;
+        case PTP_CLASS_V2_VLAN:
+                offset = ETH_HLEN + VLAN_HLEN;
+                break;
+        default:
+                return 0;
+        }
+
+        if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid))
+                return 0;
+
+        if (unlikely(type & PTP_CLASS_V1))
+                msgtype = data + offset + OFF_PTP_CONTROL;
+        else
+                msgtype = data + offset;
+
+        seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
+
+        return (rxts->msgtype == (*msgtype & 0xf) &&
+                rxts->seqid   == ntohs(*seqid));
+}
+
+static void dp83640_free_clocks(void)
+{
+        struct dp83640_clock *clock;
+        struct list_head *this, *next;
+
+        mutex_lock(&phyter_clocks_lock);
+
+        list_for_each_safe(this, next, &phyter_clocks) {
+                clock = list_entry(this, struct dp83640_clock, list);
+                if (!list_empty(&clock->phylist)) {
+                        pr_warning("phy list non-empty while unloading");
+                        BUG();
+                }
+                list_del(&clock->list);
+                mutex_destroy(&clock->extreg_lock);
+                mutex_destroy(&clock->clock_lock);
+                put_device(&clock->bus->dev);
+                kfree(clock);
+        }
+
+        mutex_unlock(&phyter_clocks_lock);
+}
+
+static void dp83640_clock_init(struct dp83640_clock *clock, struct mii_bus *bus)
+{
+        INIT_LIST_HEAD(&clock->list);
+        clock->bus = bus;
+        mutex_init(&clock->extreg_lock);
+        mutex_init(&clock->clock_lock);
+        INIT_LIST_HEAD(&clock->phylist);
+        clock->caps.owner = THIS_MODULE;
+        sprintf(clock->caps.name, "dp83640 timer");
+        clock->caps.max_adj     = 1953124;
+        clock->caps.n_alarm     = 0;
+        clock->caps.n_ext_ts    = N_EXT_TS;
+        clock->caps.n_per_out   = 0;
+        clock->caps.pps         = 0;
+        clock->caps.adjfreq     = ptp_dp83640_adjfreq;
+        clock->caps.adjtime     = ptp_dp83640_adjtime;
+        clock->caps.gettime     = ptp_dp83640_gettime;
+        clock->caps.settime     = ptp_dp83640_settime;
+        clock->caps.enable      = ptp_dp83640_enable;
+        /*
+         * Get a reference to this bus instance.
+         */
+        get_device(&bus->dev);
+}
+
+static int choose_this_phy(struct dp83640_clock *clock,
+                           struct phy_device *phydev)
+{
+        if (chosen_phy == -1 && !clock->chosen)
+                return 1;
+
+        if (chosen_phy == phydev->addr)
+                return 1;
+
+        return 0;
+}
+
+static struct dp83640_clock *dp83640_clock_get(struct dp83640_clock *clock)
+{
+        if (clock)
+                mutex_lock(&clock->clock_lock);
+        return clock;
+}
+
+/*
+ * Look up and lock a clock by bus instance.
+ * If there is no clock for this bus, then create it first.
+ */
+static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus)
+{
+        struct dp83640_clock *clock = NULL, *tmp;
+        struct list_head *this;
+
+        mutex_lock(&phyter_clocks_lock);
+
+        list_for_each(this, &phyter_clocks) {
+                tmp = list_entry(this, struct dp83640_clock, list);
+                if (tmp->bus == bus) {
+                        clock = tmp;
+                        break;
+                }
+        }
+        if (clock)
+                goto out;
+
+        clock = kzalloc(sizeof(struct dp83640_clock), GFP_KERNEL);
+        if (!clock)
+                goto out;
+
+        dp83640_clock_init(clock, bus);
+        list_add_tail(&phyter_clocks, &clock->list);
+out:
+        mutex_unlock(&phyter_clocks_lock);
+
+        return dp83640_clock_get(clock);
+}
+
+static void dp83640_clock_put(struct dp83640_clock *clock)
+{
+        mutex_unlock(&clock->clock_lock);
+}
+
+static int dp83640_probe(struct phy_device *phydev)
+{
+        struct dp83640_clock *clock;
+        struct dp83640_private *dp83640;
+        int err = -ENOMEM, i;
+
+        if (phydev->addr == BROADCAST_ADDR)
+                return 0;
+
+        clock = dp83640_clock_get_bus(phydev->bus);
+        if (!clock)
+                goto no_clock;
+
+        dp83640 = kzalloc(sizeof(struct dp83640_private), GFP_KERNEL);
+        if (!dp83640)
+                goto no_memory;
+
+        dp83640->phydev = phydev;
+        INIT_WORK(&dp83640->ts_work, rx_timestamp_work);
+
+        INIT_LIST_HEAD(&dp83640->rxts);
+        INIT_LIST_HEAD(&dp83640->rxpool);
+        for (i = 0; i < MAX_RXTS; i++)
+                list_add(&dp83640->rx_pool_data[i].list, &dp83640->rxpool);
+
+        phydev->priv = dp83640;
+
+        spin_lock_init(&dp83640->rx_lock);
+        skb_queue_head_init(&dp83640->rx_queue);
+        skb_queue_head_init(&dp83640->tx_queue);
+
+        dp83640->clock = clock;
+
+        if (choose_this_phy(clock, phydev)) {
+                clock->chosen = dp83640;
+                clock->ptp_clock = ptp_clock_register(&clock->caps);
+                if (IS_ERR(clock->ptp_clock)) {
+                        err = PTR_ERR(clock->ptp_clock);
+                        goto no_register;
+                }
+        } else
+                list_add_tail(&dp83640->list, &clock->phylist);
+
+        if (clock->chosen && !list_empty(&clock->phylist))
+                recalibrate(clock);
+        else
+                enable_broadcast(dp83640->phydev, clock->page, 1);
+
+        dp83640_clock_put(clock);
+        return 0;
+
+no_register:
+        clock->chosen = NULL;
+        kfree(dp83640);
+no_memory:
+        dp83640_clock_put(clock);
+no_clock:
+        return err;
+}
+
+static void dp83640_remove(struct phy_device *phydev)
+{
+        struct dp83640_clock *clock;
+        struct list_head *this, *next;
+        struct dp83640_private *tmp, *dp83640 = phydev->priv;
+
+        if (phydev->addr == BROADCAST_ADDR)
+                return;
+
+        enable_status_frames(phydev, false);
+        cancel_work_sync(&dp83640->ts_work);
+
+        clock = dp83640_clock_get(dp83640->clock);
+
+        if (dp83640 == clock->chosen) {
+                ptp_clock_unregister(clock->ptp_clock);
+                clock->chosen = NULL;
+        } else {
+                list_for_each_safe(this, next, &clock->phylist) {
+                        tmp = list_entry(this, struct dp83640_private, list);
+                        if (tmp == dp83640) {
+                                list_del_init(&tmp->list);
+                                break;
+                        }
+                }
+        }
+
+        dp83640_clock_put(clock);
+        kfree(dp83640);
+}
+
+static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
+{
+        struct dp83640_private *dp83640 = phydev->priv;
+        struct hwtstamp_config cfg;
+        u16 txcfg0, rxcfg0;
+
+        if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+                return -EFAULT;
+
+        if (cfg.flags) /* reserved for future extensions */
+                return -EINVAL;
+
+        switch (cfg.tx_type) {
+        case HWTSTAMP_TX_OFF:
+                dp83640->hwts_tx_en = 0;
+                break;
+        case HWTSTAMP_TX_ON:
+                dp83640->hwts_tx_en = 1;
+                break;
+        default:
+                return -ERANGE;
+        }
+
+        switch (cfg.rx_filter) {
+        case HWTSTAMP_FILTER_NONE:
+                dp83640->hwts_rx_en = 0;
+                dp83640->layer = 0;
+                dp83640->version = 0;
+                break;
+        case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+        case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+        case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+                dp83640->hwts_rx_en = 1;
+                dp83640->layer = LAYER4;
+                dp83640->version = 1;
+                break;
+        case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+        case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+        case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+                dp83640->hwts_rx_en = 1;
+                dp83640->layer = LAYER4;
+                dp83640->version = 2;
+                break;
+        case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+        case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+        case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+                dp83640->hwts_rx_en = 1;
+                dp83640->layer = LAYER2;
+                dp83640->version = 2;
+                break;
+        case HWTSTAMP_FILTER_PTP_V2_EVENT:
+        case HWTSTAMP_FILTER_PTP_V2_SYNC:
+        case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+                dp83640->hwts_rx_en = 1;
+                dp83640->layer = LAYER4|LAYER2;
+                dp83640->version = 2;
+                break;
+        default:
+                return -ERANGE;
+        }
+
+        txcfg0 = (dp83640->version & TX_PTP_VER_MASK) << TX_PTP_VER_SHIFT;
+        rxcfg0 = (dp83640->version & TX_PTP_VER_MASK) << TX_PTP_VER_SHIFT;
+
+        if (dp83640->layer & LAYER2) {
+                txcfg0 |= TX_L2_EN;
+                rxcfg0 |= RX_L2_EN;
+        }
+        if (dp83640->layer & LAYER4) {
+                txcfg0 |= TX_IPV6_EN | TX_IPV4_EN;
+                rxcfg0 |= RX_IPV6_EN | RX_IPV4_EN;
+        }
+
+        if (dp83640->hwts_tx_en)
+                txcfg0 |= TX_TS_EN;
+
+        if (dp83640->hwts_rx_en)
+                rxcfg0 |= RX_TS_EN;
+
+        mutex_lock(&dp83640->clock->extreg_lock);
+
+        if (dp83640->hwts_tx_en || dp83640->hwts_rx_en) {
+                enable_status_frames(phydev, true);
+                ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+        }
+
+        ext_write(0, phydev, PAGE5, PTP_TXCFG0, txcfg0);
+        ext_write(0, phydev, PAGE5, PTP_RXCFG0, rxcfg0);
+
+        mutex_unlock(&dp83640->clock->extreg_lock);
+
+        return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
+static void rx_timestamp_work(struct work_struct *work)
+{
+        struct dp83640_private *dp83640 =
+                container_of(work, struct dp83640_private, ts_work);
+        struct list_head *this, *next;
+        struct rxts *rxts;
+        struct skb_shared_hwtstamps *shhwtstamps;
+        struct sk_buff *skb;
+        unsigned int type;
+        unsigned long flags;
+
+        /* Deliver each deferred packet, with or without a time stamp. */
+
+        while ((skb = skb_dequeue(&dp83640->rx_queue)) != NULL) {
+                type = SKB_PTP_TYPE(skb);
+                spin_lock_irqsave(&dp83640->rx_lock, flags);
+                list_for_each_safe(this, next, &dp83640->rxts) {
+                        rxts = list_entry(this, struct rxts, list);
+                        if (match(skb, type, rxts)) {
+                                shhwtstamps = skb_hwtstamps(skb);
+                                memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+                                shhwtstamps->hwtstamp = ns_to_ktime(rxts->ns);
+                                list_del_init(&rxts->list);
+                                list_add(&rxts->list, &dp83640->rxpool);
+                                break;
+                        }
+                }
+                spin_unlock_irqrestore(&dp83640->rx_lock, flags);
+                netif_rx(skb);
+        }
+
+        /* Clear out expired time stamps. */
+
+        spin_lock_irqsave(&dp83640->rx_lock, flags);
+        prune_rx_ts(dp83640);
+        spin_unlock_irqrestore(&dp83640->rx_lock, flags);
+}
+
+static bool dp83640_rxtstamp(struct phy_device *phydev,
+                             struct sk_buff *skb, int type)
+{
+        struct dp83640_private *dp83640 = phydev->priv;
+
+        if (!dp83640->hwts_rx_en)
+                return false;
+
+        if (is_status_frame(skb, type)) {
+                decode_status_frame(dp83640, skb);
+                /* Let the stack drop this frame. */
+                return false;
+        }
+
+        SKB_PTP_TYPE(skb) = type;
+        skb_queue_tail(&dp83640->rx_queue, skb);
+        schedule_work(&dp83640->ts_work);
+
+        return true;
+}
+
+static void dp83640_txtstamp(struct phy_device *phydev,
+                             struct sk_buff *skb, int type)
+{
+        struct dp83640_private *dp83640 = phydev->priv;
+
+        if (!dp83640->hwts_tx_en) {
+                kfree_skb(skb);
+                return;
+        }
+        skb_queue_tail(&dp83640->tx_queue, skb);
+        schedule_work(&dp83640->ts_work);
+}
+
+static struct phy_driver dp83640_driver = {
+        .phy_id         = DP83640_PHY_ID,
+        .phy_id_mask    = 0xfffffff0,
+        .name           = "NatSemi DP83640",
+        .features       = PHY_BASIC_FEATURES,
+        .flags          = 0,
+        .probe          = dp83640_probe,
+        .remove         = dp83640_remove,
+        .config_aneg    = genphy_config_aneg,
+        .read_status    = genphy_read_status,
+        .hwtstamp       = dp83640_hwtstamp,
+        .rxtstamp       = dp83640_rxtstamp,
+        .txtstamp       = dp83640_txtstamp,
+        .driver         = {.owner = THIS_MODULE,}
+};
+
+static int __init dp83640_init(void)
+{
+        return phy_driver_register(&dp83640_driver);
+}
+
+static void __exit dp83640_exit(void)
+{
+        dp83640_free_clocks();
+        phy_driver_unregister(&dp83640_driver);
+}
+
+MODULE_DESCRIPTION("National Semiconductor DP83640 PHY driver");
+MODULE_AUTHOR("Richard Cochran <richard.cochran@omicron.at>");
+MODULE_LICENSE("GPL");
+
+module_init(dp83640_init);
+module_exit(dp83640_exit);
+
+static struct mdio_device_id __maybe_unused dp83640_tbl[] = {
+        { DP83640_PHY_ID, 0xfffffff0 },
+        { }
+};
+
+MODULE_DEVICE_TABLE(mdio, dp83640_tbl);
diff --git a/drivers/net/phy/dp83640_reg.h b/drivers/net/phy/dp83640_reg.h
new file mode 100644
index 000000000000..e7fe41117003
--- /dev/null
+++ b/drivers/net/phy/dp83640_reg.h
@@ -0,0 +1,267 @@
+/* dp83640_reg.h
+ * Generated by regen.tcl on Thu Feb 17 10:02:48 AM CET 2011
+ */
+#ifndef HAVE_DP83640_REGISTERS
+#define HAVE_DP83640_REGISTERS
+
+#define PAGE0                     0x0000
+#define PHYCR2                    0x001c /* PHY Control Register 2 */
+
+#define PAGE4                     0x0004
+#define PTP_CTL                   0x0014 /* PTP Control Register */
+#define PTP_TDR                   0x0015 /* PTP Time Data Register */
+#define PTP_STS                   0x0016 /* PTP Status Register */
+#define PTP_TSTS                  0x0017 /* PTP Trigger Status Register */
+#define PTP_RATEL                 0x0018 /* PTP Rate Low Register */
+#define PTP_RATEH                 0x0019 /* PTP Rate High Register */
+#define PTP_RDCKSUM               0x001a /* PTP Read Checksum */
+#define PTP_WRCKSUM               0x001b /* PTP Write Checksum */
+#define PTP_TXTS                  0x001c /* PTP Transmit Timestamp Register, in four 16-bit reads */
+#define PTP_RXTS                  0x001d /* PTP Receive Timestamp Register, in six? 16-bit reads */
+#define PTP_ESTS                  0x001e /* PTP Event Status Register */
+#define PTP_EDATA                 0x001f /* PTP Event Data Register */
+
+#define PAGE5                     0x0005
+#define PTP_TRIG                  0x0014 /* PTP Trigger Configuration Register */
+#define PTP_EVNT                  0x0015 /* PTP Event Configuration Register */
+#define PTP_TXCFG0                0x0016 /* PTP Transmit Configuration Register 0 */
+#define PTP_TXCFG1                0x0017 /* PTP Transmit Configuration Register 1 */
+#define PSF_CFG0                  0x0018 /* PHY Status Frame Configuration Register 0 */
+#define PTP_RXCFG0                0x0019 /* PTP Receive Configuration Register 0 */
+#define PTP_RXCFG1                0x001a /* PTP Receive Configuration Register 1 */
+#define PTP_RXCFG2                0x001b /* PTP Receive Configuration Register 2 */
+#define PTP_RXCFG3                0x001c /* PTP Receive Configuration Register 3 */
+#define PTP_RXCFG4                0x001d /* PTP Receive Configuration Register 4 */
+#define PTP_TRDL                  0x001e /* PTP Temporary Rate Duration Low Register */
+#define PTP_TRDH                  0x001f /* PTP Temporary Rate Duration High Register */
+
+#define PAGE6                     0x0006
+#define PTP_COC                   0x0014 /* PTP Clock Output Control Register */
+#define PSF_CFG1                  0x0015 /* PHY Status Frame Configuration Register 1 */
+#define PSF_CFG2                  0x0016 /* PHY Status Frame Configuration Register 2 */
+#define PSF_CFG3                  0x0017 /* PHY Status Frame Configuration Register 3 */
+#define PSF_CFG4                  0x0018 /* PHY Status Frame Configuration Register 4 */
+#define PTP_SFDCFG                0x0019 /* PTP SFD Configuration Register */
+#define PTP_INTCTL                0x001a /* PTP Interrupt Control Register */
+#define PTP_CLKSRC                0x001b /* PTP Clock Source Register */
+#define PTP_ETR                   0x001c /* PTP Ethernet Type Register */
+#define PTP_OFF                   0x001d /* PTP Offset Register */
+#define PTP_GPIOMON               0x001e /* PTP GPIO Monitor Register */
+#define PTP_RXHASH                0x001f /* PTP Receive Hash Register */
+
+/* Bit definitions for the PHYCR2 register */
+#define BC_WRITE                  (1<<11) /* Broadcast Write Enable */
+
+/* Bit definitions for the PTP_CTL register */
+#define TRIG_SEL_SHIFT            (10)    /* PTP Trigger Select */
+#define TRIG_SEL_MASK             (0x7)
+#define TRIG_DIS                  (1<<9)  /* Disable PTP Trigger */
+#define TRIG_EN                   (1<<8)  /* Enable PTP Trigger */
+#define TRIG_READ                 (1<<7)  /* Read PTP Trigger */
+#define TRIG_LOAD                 (1<<6)  /* Load PTP Trigger */
+#define PTP_RD_CLK                (1<<5)  /* Read PTP Clock */
+#define PTP_LOAD_CLK              (1<<4)  /* Load PTP Clock */
+#define PTP_STEP_CLK              (1<<3)  /* Step PTP Clock */
+#define PTP_ENABLE                (1<<2)  /* Enable PTP Clock */
+#define PTP_DISABLE               (1<<1)  /* Disable PTP Clock */
+#define PTP_RESET                 (1<<0)  /* Reset PTP Clock */
+
+/* Bit definitions for the PTP_STS register */
+#define TXTS_RDY                  (1<<11) /* Transmit Timestamp Ready */
+#define RXTS_RDY                  (1<<10) /* Receive Timestamp Ready */
+#define TRIG_DONE                 (1<<9)  /* PTP Trigger Done */
+#define EVENT_RDY                 (1<<8)  /* PTP Event Timestamp Ready */
+#define TXTS_IE                   (1<<3)  /* Transmit Timestamp Interrupt Enable */
+#define RXTS_IE                   (1<<2)  /* Receive Timestamp Interrupt Enable */
+#define TRIG_IE                   (1<<1)  /* Trigger Interrupt Enable */
+#define EVENT_IE                  (1<<0)  /* Event Interrupt Enable */
+
+/* Bit definitions for the PTP_TSTS register */
+#define TRIG7_ERROR               (1<<15) /* Trigger 7 Error */
+#define TRIG7_ACTIVE              (1<<14) /* Trigger 7 Active */
+#define TRIG6_ERROR               (1<<13) /* Trigger 6 Error */
+#define TRIG6_ACTIVE              (1<<12) /* Trigger 6 Active */
+#define TRIG5_ERROR               (1<<11) /* Trigger 5 Error */
+#define TRIG5_ACTIVE              (1<<10) /* Trigger 5 Active */
+#define TRIG4_ERROR               (1<<9)  /* Trigger 4 Error */
+#define TRIG4_ACTIVE              (1<<8)  /* Trigger 4 Active */
+#define TRIG3_ERROR               (1<<7)  /* Trigger 3 Error */
+#define TRIG3_ACTIVE              (1<<6)  /* Trigger 3 Active */
+#define TRIG2_ERROR               (1<<5)  /* Trigger 2 Error */
+#define TRIG2_ACTIVE              (1<<4)  /* Trigger 2 Active */
+#define TRIG1_ERROR               (1<<3)  /* Trigger 1 Error */
+#define TRIG1_ACTIVE              (1<<2)  /* Trigger 1 Active */
+#define TRIG0_ERROR               (1<<1)  /* Trigger 0 Error */
+#define TRIG0_ACTIVE              (1<<0)  /* Trigger 0 Active */
+
+/* Bit definitions for the PTP_RATEH register */
+#define PTP_RATE_DIR              (1<<15) /* PTP Rate Direction */
+#define PTP_TMP_RATE              (1<<14) /* PTP Temporary Rate */
+#define PTP_RATE_HI_SHIFT         (0)     /* PTP Rate High 10-bits */
+#define PTP_RATE_HI_MASK          (0x3ff)
+
+/* Bit definitions for the PTP_ESTS register */
+#define EVNTS_MISSED_SHIFT        (8)     /* Indicates number of events missed */
+#define EVNTS_MISSED_MASK         (0x7)
+#define EVNT_TS_LEN_SHIFT         (6)     /* Indicates length of the Timestamp field in 16-bit words minus 1 */
+#define EVNT_TS_LEN_MASK          (0x3)
+#define EVNT_RF                   (1<<5)  /* Indicates whether the event is a rise or falling event */
+#define EVNT_NUM_SHIFT            (2)     /* Indicates Event Timestamp Unit which detected an event */
+#define EVNT_NUM_MASK             (0x7)
+#define MULT_EVNT                 (1<<1)  /* Indicates multiple events were detected at the same time */
+#define EVENT_DET                 (1<<0)  /* PTP Event Detected */
+
+/* Bit definitions for the PTP_EDATA register */
+#define E7_RISE                   (1<<15) /* Indicates direction of Event 7 */
+#define E7_DET                    (1<<14) /* Indicates Event 7 detected */
+#define E6_RISE                   (1<<13) /* Indicates direction of Event 6 */
+#define E6_DET                    (1<<12) /* Indicates Event 6 detected */
+#define E5_RISE                   (1<<11) /* Indicates direction of Event 5 */
+#define E5_DET                    (1<<10) /* Indicates Event 5 detected */
+#define E4_RISE                   (1<<9)  /* Indicates direction of Event 4 */
+#define E4_DET                    (1<<8)  /* Indicates Event 4 detected */
+#define E3_RISE                   (1<<7)  /* Indicates direction of Event 3 */
+#define E3_DET                    (1<<6)  /* Indicates Event 3 detected */
+#define E2_RISE                   (1<<5)  /* Indicates direction of Event 2 */
+#define E2_DET                    (1<<4)  /* Indicates Event 2 detected */
+#define E1_RISE                   (1<<3)  /* Indicates direction of Event 1 */
+#define E1_DET                    (1<<2)  /* Indicates Event 1 detected */
+#define E0_RISE                   (1<<1)  /* Indicates direction of Event 0 */
+#define E0_DET                    (1<<0)  /* Indicates Event 0 detected */
+
+/* Bit definitions for the PTP_TRIG register */
+#define TRIG_PULSE                (1<<15) /* generate a Pulse rather than a single edge */
+#define TRIG_PER                  (1<<14) /* generate a periodic signal */
+#define TRIG_IF_LATE              (1<<13) /* trigger immediately if already past */
+#define TRIG_NOTIFY               (1<<12) /* Trigger Notification Enable */
+#define TRIG_GPIO_SHIFT           (8)     /* Trigger GPIO Connection, value 1-12 */
+#define TRIG_GPIO_MASK            (0xf)
+#define TRIG_TOGGLE               (1<<7)  /* Trigger Toggle Mode Enable */
+#define TRIG_CSEL_SHIFT           (1)     /* Trigger Configuration Select */
+#define TRIG_CSEL_MASK            (0x7)
+#define TRIG_WR                   (1<<0)  /* Trigger Configuration Write */
+
+/* Bit definitions for the PTP_EVNT register */
+#define EVNT_RISE                 (1<<14) /* Event Rise Detect Enable */
+#define EVNT_FALL                 (1<<13) /* Event Fall Detect Enable */
+#define EVNT_SINGLE               (1<<12) /* enable single event capture operation */
+#define EVNT_GPIO_SHIFT           (8)     /* Event GPIO Connection, value 1-12 */
+#define EVNT_GPIO_MASK            (0xf)
+#define EVNT_SEL_SHIFT            (1)     /* Event Select */
+#define EVNT_SEL_MASK             (0x7)
+#define EVNT_WR                   (1<<0)  /* Event Configuration Write */
+
+/* Bit definitions for the PTP_TXCFG0 register */
+#define SYNC_1STEP                (1<<15) /* insert timestamp into transmit Sync Messages */
+#define DR_INSERT                 (1<<13) /* Insert Delay_Req Timestamp in Delay_Resp (dangerous) */
+#define NTP_TS_EN                 (1<<12) /* Enable Timestamping of NTP Packets */
+#define IGNORE_2STEP              (1<<11) /* Ignore Two_Step flag for One-Step operation */
+#define CRC_1STEP                 (1<<10) /* Disable checking of CRC for One-Step operation */
+#define CHK_1STEP                 (1<<9)  /* Enable UDP Checksum correction for One-Step Operation */
+#define IP1588_EN                 (1<<8)  /* Enable IEEE 1588 defined IP address filter */
+#define TX_L2_EN                  (1<<7)  /* Layer2 Timestamp Enable */
+#define TX_IPV6_EN                (1<<6)  /* IPv6 Timestamp Enable */
+#define TX_IPV4_EN                (1<<5)  /* IPv4 Timestamp Enable */
+#define TX_PTP_VER_SHIFT          (1)     /* Enable Timestamp capture for IEEE 1588 version X */
+#define TX_PTP_VER_MASK           (0xf)
+#define TX_TS_EN                  (1<<0)  /* Transmit Timestamp Enable */
+
+/* Bit definitions for the PTP_TXCFG1 register */
+#define BYTE0_MASK_SHIFT          (8)     /* Bit mask to be used for matching Byte0 of the PTP Message */
+#define BYTE0_MASK_MASK           (0xff)
+#define BYTE0_DATA_SHIFT          (0)     /* Data to be used for matching Byte0 of the PTP Message */
+#define BYTE0_DATA_MASK           (0xff)
+
+/* Bit definitions for the PSF_CFG0 register */
+#define MAC_SRC_ADD_SHIFT         (11)    /* Status Frame Mac Source Address */
+#define MAC_SRC_ADD_MASK          (0x3)
+#define MIN_PRE_SHIFT             (8)     /* Status Frame Minimum Preamble */
+#define MIN_PRE_MASK              (0x7)
+#define PSF_ENDIAN                (1<<7)  /* Status Frame Endian Control */
+#define PSF_IPV4                  (1<<6)  /* Status Frame IPv4 Enable */
+#define PSF_PCF_RD                (1<<5)  /* Control Frame Read PHY Status Frame Enable */
+#define PSF_ERR_EN                (1<<4)  /* Error PHY Status Frame Enable */
+#define PSF_TXTS_EN               (1<<3)  /* Transmit Timestamp PHY Status Frame Enable */
+#define PSF_RXTS_EN               (1<<2)  /* Receive Timestamp PHY Status Frame Enable */
+#define PSF_TRIG_EN               (1<<1)  /* Trigger PHY Status Frame Enable */
+#define PSF_EVNT_EN               (1<<0)  /* Event PHY Status Frame Enable */
+
+/* Bit definitions for the PTP_RXCFG0 register */
+#define DOMAIN_EN                 (1<<15) /* Domain Match Enable */
+#define ALT_MAST_DIS              (1<<14) /* Alternate Master Timestamp Disable */
+#define USER_IP_SEL               (1<<13) /* Selects portion of IP address accessible thru PTP_RXCFG2 */
+#define USER_IP_EN                (1<<12) /* Enable User-programmed IP address filter */
+#define RX_SLAVE                  (1<<11) /* Receive Slave Only */
+#define IP1588_EN_SHIFT           (8)     /* Enable IEEE 1588 defined IP address filters */
+#define IP1588_EN_MASK            (0xf)
+#define RX_L2_EN                  (1<<7)  /* Layer2 Timestamp Enable */
+#define RX_IPV6_EN                (1<<6)  /* IPv6 Timestamp Enable */
+#define RX_IPV4_EN                (1<<5)  /* IPv4 Timestamp Enable */
+#define RX_PTP_VER_SHIFT          (1)     /* Enable Timestamp capture for IEEE 1588 version X */
+#define RX_PTP_VER_MASK           (0xf)
+#define RX_TS_EN                  (1<<0)  /* Receive Timestamp Enable */
+
+/* Bit definitions for the PTP_RXCFG1 register */
+#define BYTE0_MASK_SHIFT          (8)     /* Bit mask to be used for matching Byte0 of the PTP Message */
+#define BYTE0_MASK_MASK           (0xff)
+#define BYTE0_DATA_SHIFT          (0)     /* Data to be used for matching Byte0 of the PTP Message */
+#define BYTE0_DATA_MASK           (0xff)
+
+/* Bit definitions for the PTP_RXCFG3 register */
+#define TS_MIN_IFG_SHIFT          (12)    /* Minimum Inter-frame Gap */
+#define TS_MIN_IFG_MASK           (0xf)
+#define ACC_UDP                   (1<<11) /* Record Timestamp if UDP Checksum Error */
+#define ACC_CRC                   (1<<10) /* Record Timestamp if CRC Error */
+#define TS_APPEND                 (1<<9)  /* Append Timestamp for L2 */
+#define TS_INSERT                 (1<<8)  /* Enable Timestamp Insertion */
+#define PTP_DOMAIN_SHIFT          (0)     /* PTP Message domainNumber field */
+#define PTP_DOMAIN_MASK           (0xff)
+
+/* Bit definitions for the PTP_RXCFG4 register */
+#define IPV4_UDP_MOD              (1<<15) /* Enable IPV4 UDP Modification */
+#define TS_SEC_EN                 (1<<14) /* Enable Timestamp Seconds */
+#define TS_SEC_LEN_SHIFT          (12)    /* Inserted Timestamp Seconds Length */
+#define TS_SEC_LEN_MASK           (0x3)
+#define RXTS_NS_OFF_SHIFT         (6)     /* Receive Timestamp Nanoseconds offset */
+#define RXTS_NS_OFF_MASK          (0x3f)
+#define RXTS_SEC_OFF_SHIFT        (0)     /* Receive Timestamp Seconds offset */
+#define RXTS_SEC_OFF_MASK         (0x3f)
+
+/* Bit definitions for the PTP_COC register */
+#define PTP_CLKOUT_EN             (1<<15) /* PTP Clock Output Enable */
+#define PTP_CLKOUT_SEL            (1<<14) /* PTP Clock Output Source Select */
+#define PTP_CLKOUT_SPEEDSEL       (1<<13) /* PTP Clock Output I/O Speed Select */
+#define PTP_CLKDIV_SHIFT          (0)     /* PTP Clock Divide-by Value */
+#define PTP_CLKDIV_MASK           (0xff)
+
+/* Bit definitions for the PSF_CFG1 register */
+#define PTPRESERVED_SHIFT         (12)    /* PTP v2 reserved field */
+#define PTPRESERVED_MASK          (0xf)
+#define VERSIONPTP_SHIFT          (8)     /* PTP v2 versionPTP field */
+#define VERSIONPTP_MASK           (0xf)
+#define TRANSPORT_SPECIFIC_SHIFT  (4)     /* PTP v2 Header transportSpecific field */
+#define TRANSPORT_SPECIFIC_MASK   (0xf)
+#define MESSAGETYPE_SHIFT         (0)     /* PTP v2 messageType field */
+#define MESSAGETYPE_MASK          (0xf)
+
+/* Bit definitions for the PTP_SFDCFG register */
+#define TX_SFD_GPIO_SHIFT         (4)     /* TX SFD GPIO Select, value 1-12 */
+#define TX_SFD_GPIO_MASK          (0xf)
+#define RX_SFD_GPIO_SHIFT         (0)     /* RX SFD GPIO Select, value 1-12 */
+#define RX_SFD_GPIO_MASK          (0xf)
+
+/* Bit definitions for the PTP_INTCTL register */
+#define PTP_INT_GPIO_SHIFT        (0)     /* PTP Interrupt GPIO Select */
+#define PTP_INT_GPIO_MASK         (0xf)
+
+/* Bit definitions for the PTP_CLKSRC register */
+#define CLK_SRC_SHIFT             (14)    /* PTP Clock Source Select */
+#define CLK_SRC_MASK              (0x3)
+#define CLK_SRC_PER_SHIFT         (0)     /* PTP Clock Source Period */
+#define CLK_SRC_PER_MASK          (0x7f)
+
+/* Bit definitions for the PTP_OFF register */
+#define PTP_OFFSET_SHIFT          (0)     /* PTP Message offset from preceding header */
+#define PTP_OFFSET_MASK           (0xff)
+
+#endif
diff --git a/drivers/net/tile/tilepro.c b/drivers/net/tile/tilepro.c
index 1e980fdd9d77..1e2af96fc29c 100644
--- a/drivers/net/tile/tilepro.c
+++ b/drivers/net/tile/tilepro.c
@@ -1658,11 +1658,9 @@ static int tile_net_stop(struct net_device *dev)
         while (tile_net_lepp_free_comps(dev, true))
                 /* loop */;
 
-        /* Wipe the EPP queue. */
+        /* Wipe the EPP queue, and wait till the stores hit the EPP. */
         memset(priv->eq, 0, sizeof(lepp_queue_t));
-
-        /* Evict the EPP queue. */
-        finv_buffer(priv->eq, EQ_SIZE);
+        mb();
 
         return 0;
 }
@@ -2398,7 +2396,7 @@ static void tile_net_cleanup(void)
                         struct net_device *dev = tile_net_devs[i];
                         struct tile_net_priv *priv = netdev_priv(dev);
                         unregister_netdev(dev);
-                        finv_buffer(priv->eq, EQ_SIZE);
+                        finv_buffer_remote(priv->eq, EQ_SIZE, 0);
                         __free_pages(priv->eq_pages, EQ_ORDER);
                         free_netdev(dev);
                 }
diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c
index 94a114aa8e28..b1396e5b2953 100644
--- a/drivers/platform/x86/ibm_rtl.c
+++ b/drivers/platform/x86/ibm_rtl.c
@@ -81,6 +81,19 @@ static void __iomem *rtl_cmd_addr;
 static u8 rtl_cmd_type;
 static u8 rtl_cmd_width;
 
+#ifndef readq
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+        const volatile u32 __iomem *p = addr;
+        u32 low, high;
+
+        low = readl(p);
+        high = readl(p + 1);
+
+        return low + ((u64)high << 32);
+}
+#endif
+
 static void __iomem *rtl_port_map(phys_addr_t addr, unsigned long len)
 {
         if (rtl_cmd_type == RTL_ADDR_TYPE_MMIO)
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 85c8ad43c0c5..5ffe7c398148 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -344,6 +344,19 @@ struct ips_driver {
 static bool
 ips_gpu_turbo_enabled(struct ips_driver *ips);
 
+#ifndef readq
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+        const volatile u32 __iomem *p = addr;
+        u32 low, high;
+
+        low = readl(p);
+        high = readl(p + 1);
+
+        return low + ((u64)high << 32);
+}
+#endif
+
 /**
  * ips_cpu_busy - is CPU busy?
  * @ips: IPS driver struct
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
new file mode 100644
index 000000000000..68d720102296
--- /dev/null
+++ b/drivers/ptp/Kconfig
@@ -0,0 +1,75 @@
+#
+# PTP clock support configuration
+#
+
+menu "PTP clock support"
+
+comment "Enable Device Drivers -> PPS to see the PTP clock options."
+        depends on PPS=n
+
+config PTP_1588_CLOCK
+        tristate "PTP clock support"
+        depends on EXPERIMENTAL
+        depends on PPS
+        help
+          The IEEE 1588 standard defines a method to precisely
+          synchronize distributed clocks over Ethernet networks. The
+          standard defines a Precision Time Protocol (PTP), which can
+          be used to achieve synchronization within a few dozen
+          microseconds. In addition, with the help of special hardware
+          time stamping units, it can be possible to achieve
+          synchronization to within a few hundred nanoseconds.
+
+          This driver adds support for PTP clocks as character
+          devices. If you want to use a PTP clock, then you should
+          also enable at least one clock driver as well.
+
+          To compile this driver as a module, choose M here: the module
+          will be called ptp.
+
+config PTP_1588_CLOCK_GIANFAR
+        tristate "Freescale eTSEC as PTP clock"
+        depends on PTP_1588_CLOCK
+        depends on GIANFAR
+        help
+          This driver adds support for using the eTSEC as a PTP
+          clock. This clock is only useful if your PTP programs are
+          getting hardware time stamps on the PTP Ethernet packets
+          using the SO_TIMESTAMPING API.
+
+          To compile this driver as a module, choose M here: the module
+          will be called gianfar_ptp.
+
+config PTP_1588_CLOCK_IXP46X
+        tristate "Intel IXP46x as PTP clock"
+        depends on PTP_1588_CLOCK
+        depends on IXP4XX_ETH
+        help
+          This driver adds support for using the IXP46X as a PTP
+          clock. This clock is only useful if your PTP programs are
+          getting hardware time stamps on the PTP Ethernet packets
+          using the SO_TIMESTAMPING API.
+
+          To compile this driver as a module, choose M here: the module
+          will be called ptp_ixp46x.
+
+comment "Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks."
+        depends on PTP_1588_CLOCK && (PHYLIB=n || NETWORK_PHY_TIMESTAMPING=n)
+
+config DP83640_PHY
+        tristate "Driver for the National Semiconductor DP83640 PHYTER"
+        depends on PTP_1588_CLOCK
+        depends on NETWORK_PHY_TIMESTAMPING
+        depends on PHYLIB
+        ---help---
+          Supports the DP83640 PHYTER with IEEE 1588 features.
+
+          This driver adds support for using the DP83640 as a PTP
+          clock. This clock is only useful if your PTP programs are
+          getting hardware time stamps on the PTP Ethernet packets
+          using the SO_TIMESTAMPING API.
+
+          In order for this to work, your MAC driver must also
+          implement the skb_tx_timetamp() function.
+
+endmenu
diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile
new file mode 100644
index 000000000000..f6933e83de72
--- /dev/null
+++ b/drivers/ptp/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for PTP 1588 clock support.
+#
+
+ptp-y                                   := ptp_clock.o ptp_chardev.o ptp_sysfs.o
+obj-$(CONFIG_PTP_1588_CLOCK)            += ptp.o
+obj-$(CONFIG_PTP_1588_CLOCK_IXP46X)     += ptp_ixp46x.o
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
new file mode 100644
index 000000000000..a8d03aeb4051
--- /dev/null
+++ b/drivers/ptp/ptp_chardev.c
@@ -0,0 +1,159 @@
+/*
+ * PTP 1588 clock support - character device implementation.
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/module.h>
+#include <linux/posix-clock.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+
+#include "ptp_private.h"
+
+int ptp_open(struct posix_clock *pc, fmode_t fmode)
+{
+        return 0;
+}
+
+long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
+{
+        struct ptp_clock_caps caps;
+        struct ptp_clock_request req;
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+        struct ptp_clock_info *ops = ptp->info;
+        int enable, err = 0;
+
+        switch (cmd) {
+
+        case PTP_CLOCK_GETCAPS:
+                memset(&caps, 0, sizeof(caps));
+                caps.max_adj = ptp->info->max_adj;
+                caps.n_alarm = ptp->info->n_alarm;
+                caps.n_ext_ts = ptp->info->n_ext_ts;
+                caps.n_per_out = ptp->info->n_per_out;
+                caps.pps = ptp->info->pps;
+                err = copy_to_user((void __user *)arg, &caps, sizeof(caps));
+                break;
+
+        case PTP_EXTTS_REQUEST:
+                if (copy_from_user(&req.extts, (void __user *)arg,
+                                   sizeof(req.extts))) {
+                        err = -EFAULT;
+                        break;
+                }
+                if (req.extts.index >= ops->n_ext_ts) {
+                        err = -EINVAL;
+                        break;
+                }
+                req.type = PTP_CLK_REQ_EXTTS;
+                enable = req.extts.flags & PTP_ENABLE_FEATURE ? 1 : 0;
+                err = ops->enable(ops, &req, enable);
+                break;
+
+        case PTP_PEROUT_REQUEST:
+                if (copy_from_user(&req.perout, (void __user *)arg,
+                                   sizeof(req.perout))) {
+                        err = -EFAULT;
+                        break;
+                }
+                if (req.perout.index >= ops->n_per_out) {
+                        err = -EINVAL;
+                        break;
+                }
+                req.type = PTP_CLK_REQ_PEROUT;
+                enable = req.perout.period.sec || req.perout.period.nsec;
+                err = ops->enable(ops, &req, enable);
+                break;
+
+        case PTP_ENABLE_PPS:
+                if (!capable(CAP_SYS_TIME))
+                        return -EPERM;
+                req.type = PTP_CLK_REQ_PPS;
+                enable = arg ? 1 : 0;
+                err = ops->enable(ops, &req, enable);
+                break;
+
+        default:
+                err = -ENOTTY;
+                break;
+        }
+        return err;
+}
+
+unsigned int ptp_poll(struct posix_clock *pc, struct file *fp, poll_table *wait)
+{
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+
+        poll_wait(fp, &ptp->tsev_wq, wait);
+
+        return queue_cnt(&ptp->tsevq) ? POLLIN : 0;
+}
+
+ssize_t ptp_read(struct posix_clock *pc,
+                 uint rdflags, char __user *buf, size_t cnt)
+{
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+        struct timestamp_event_queue *queue = &ptp->tsevq;
+        struct ptp_extts_event event[PTP_BUF_TIMESTAMPS];
+        unsigned long flags;
+        size_t qcnt, i;
+
+        if (cnt % sizeof(struct ptp_extts_event) != 0)
+                return -EINVAL;
+
+        if (cnt > sizeof(event))
+                cnt = sizeof(event);
+
+        cnt = cnt / sizeof(struct ptp_extts_event);
+
+        if (mutex_lock_interruptible(&ptp->tsevq_mux))
+                return -ERESTARTSYS;
+
+        if (wait_event_interruptible(ptp->tsev_wq,
+                                     ptp->defunct || queue_cnt(queue))) {
+                mutex_unlock(&ptp->tsevq_mux);
+                return -ERESTARTSYS;
+        }
+
+        if (ptp->defunct)
+                return -ENODEV;
+
+        spin_lock_irqsave(&queue->lock, flags);
+
+        qcnt = queue_cnt(queue);
+
+        if (cnt > qcnt)
+                cnt = qcnt;
+
+        for (i = 0; i < cnt; i++) {
+                event[i] = queue->buf[queue->head];
+                queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+        }
+
+        spin_unlock_irqrestore(&queue->lock, flags);
+
+        cnt = cnt * sizeof(struct ptp_extts_event);
+
+        mutex_unlock(&ptp->tsevq_mux);
+
+        if (copy_to_user(buf, event, cnt)) {
+                mutex_unlock(&ptp->tsevq_mux);
+                return -EFAULT;
+        }
+
+        return cnt;
+}
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
new file mode 100644
index 000000000000..cf3f9997546d
--- /dev/null
+++ b/drivers/ptp/ptp_clock.c
@@ -0,0 +1,343 @@
+/*
+ * PTP 1588 clock support
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/posix-clock.h>
+#include <linux/pps_kernel.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+#include "ptp_private.h"
+
+#define PTP_MAX_ALARMS 4
+#define PTP_MAX_CLOCKS 8
+#define PTP_PPS_DEFAULTS (PPS_CAPTUREASSERT | PPS_OFFSETASSERT)
+#define PTP_PPS_EVENT PPS_CAPTUREASSERT
+#define PTP_PPS_MODE (PTP_PPS_DEFAULTS | PPS_CANWAIT | PPS_TSFMT_TSPEC)
+
+/* private globals */
+
+static dev_t ptp_devt;
+static struct class *ptp_class;
+
+static DECLARE_BITMAP(ptp_clocks_map, PTP_MAX_CLOCKS);
+static DEFINE_MUTEX(ptp_clocks_mutex); /* protects 'ptp_clocks_map' */
+
+/* time stamp event queue operations */
+
+static inline int queue_free(struct timestamp_event_queue *q)
+{
+        return PTP_MAX_TIMESTAMPS - queue_cnt(q) - 1;
+}
+
+static void enqueue_external_timestamp(struct timestamp_event_queue *queue,
+                                       struct ptp_clock_event *src)
+{
+        struct ptp_extts_event *dst;
+        unsigned long flags;
+        s64 seconds;
+        u32 remainder;
+
+        seconds = div_u64_rem(src->timestamp, 1000000000, &remainder);
+
+        spin_lock_irqsave(&queue->lock, flags);
+
+        dst = &queue->buf[queue->tail];
+        dst->index = src->index;
+        dst->t.sec = seconds;
+        dst->t.nsec = remainder;
+
+        if (!queue_free(queue))
+                queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+
+        queue->tail = (queue->tail + 1) % PTP_MAX_TIMESTAMPS;
+
+        spin_unlock_irqrestore(&queue->lock, flags);
+}
+
+static s32 scaled_ppm_to_ppb(long ppm)
+{
+        /*
+         * The 'freq' field in the 'struct timex' is in parts per
+         * million, but with a 16 bit binary fractional field.
+         *
+         * We want to calculate
+         *
+         *    ppb = scaled_ppm * 1000 / 2^16
+         *
+         * which simplifies to
+         *
+         *    ppb = scaled_ppm * 125 / 2^13
+         */
+        s64 ppb = 1 + ppm;
+        ppb *= 125;
+        ppb >>= 13;
+        return (s32) ppb;
+}
+
+/* posix clock implementation */
+
+static int ptp_clock_getres(struct posix_clock *pc, struct timespec *tp)
+{
+        return 1; /* always round timer functions to one nanosecond */
+}
+
+static int ptp_clock_settime(struct posix_clock *pc, const struct timespec *tp)
+{
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+        return ptp->info->settime(ptp->info, tp);
+}
+
+static int ptp_clock_gettime(struct posix_clock *pc, struct timespec *tp)
+{
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+        return ptp->info->gettime(ptp->info, tp);
+}
+
+static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx)
+{
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+        struct ptp_clock_info *ops;
+        int err = -EOPNOTSUPP;
+
+        ops = ptp->info;
+
+        if (tx->modes & ADJ_SETOFFSET) {
+                struct timespec ts;
+                ktime_t kt;
+                s64 delta;
+
+                ts.tv_sec  = tx->time.tv_sec;
+                ts.tv_nsec = tx->time.tv_usec;
+
+                if (!(tx->modes & ADJ_NANO))
+                        ts.tv_nsec *= 1000;
+
+                if ((unsigned long) ts.tv_nsec >= NSEC_PER_SEC)
+                        return -EINVAL;
+
+                kt = timespec_to_ktime(ts);
+                delta = ktime_to_ns(kt);
+                err = ops->adjtime(ops, delta);
+
+        } else if (tx->modes & ADJ_FREQUENCY) {
+
+                err = ops->adjfreq(ops, scaled_ppm_to_ppb(tx->freq));
+        }
+
+        return err;
+}
+
+static struct posix_clock_operations ptp_clock_ops = {
+        .owner          = THIS_MODULE,
+        .clock_adjtime  = ptp_clock_adjtime,
+        .clock_gettime  = ptp_clock_gettime,
+        .clock_getres   = ptp_clock_getres,
+        .clock_settime  = ptp_clock_settime,
+        .ioctl          = ptp_ioctl,
+        .open           = ptp_open,
+        .poll           = ptp_poll,
+        .read           = ptp_read,
+};
+
+static void delete_ptp_clock(struct posix_clock *pc)
+{
+        struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+
+        mutex_destroy(&ptp->tsevq_mux);
+
+        /* Remove the clock from the bit map. */
+        mutex_lock(&ptp_clocks_mutex);
+        clear_bit(ptp->index, ptp_clocks_map);
+        mutex_unlock(&ptp_clocks_mutex);
+
+        kfree(ptp);
+}
+
+/* public interface */
+
+struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info)
+{
+        struct ptp_clock *ptp;
+        int err = 0, index, major = MAJOR(ptp_devt);
+
+        if (info->n_alarm > PTP_MAX_ALARMS)
+                return ERR_PTR(-EINVAL);
+
+        /* Find a free clock slot and reserve it. */
+        err = -EBUSY;
+        mutex_lock(&ptp_clocks_mutex);
+        index = find_first_zero_bit(ptp_clocks_map, PTP_MAX_CLOCKS);
+        if (index < PTP_MAX_CLOCKS)
+                set_bit(index, ptp_clocks_map);
+        else
+                goto no_slot;
+
+        /* Initialize a clock structure. */
+        err = -ENOMEM;
+        ptp = kzalloc(sizeof(struct ptp_clock), GFP_KERNEL);
+        if (ptp == NULL)
+                goto no_memory;
+
+        ptp->clock.ops = ptp_clock_ops;
+        ptp->clock.release = delete_ptp_clock;
+        ptp->info = info;
+        ptp->devid = MKDEV(major, index);
+        ptp->index = index;
+        spin_lock_init(&ptp->tsevq.lock);
+        mutex_init(&ptp->tsevq_mux);
+        init_waitqueue_head(&ptp->tsev_wq);
+
+        /* Create a new device in our class. */
+        ptp->dev = device_create(ptp_class, NULL, ptp->devid, ptp,
+                                 "ptp%d", ptp->index);
+        if (IS_ERR(ptp->dev))
+                goto no_device;
+
+        dev_set_drvdata(ptp->dev, ptp);
+
+        err = ptp_populate_sysfs(ptp);
+        if (err)
+                goto no_sysfs;
+
+        /* Register a new PPS source. */
+        if (info->pps) {
+                struct pps_source_info pps;
+                memset(&pps, 0, sizeof(pps));
+                snprintf(pps.name, PPS_MAX_NAME_LEN, "ptp%d", index);
+                pps.mode = PTP_PPS_MODE;
+                pps.owner = info->owner;
+                ptp->pps_source = pps_register_source(&pps, PTP_PPS_DEFAULTS);
+                if (!ptp->pps_source) {
+                        pr_err("failed to register pps source\n");
+                        goto no_pps;
+                }
+        }
+
+        /* Create a posix clock. */
+        err = posix_clock_register(&ptp->clock, ptp->devid);
+        if (err) {
+                pr_err("failed to create posix clock\n");
+                goto no_clock;
+        }
+
+        mutex_unlock(&ptp_clocks_mutex);
+        return ptp;
+
+no_clock:
+        if (ptp->pps_source)
+                pps_unregister_source(ptp->pps_source);
+no_pps:
+        ptp_cleanup_sysfs(ptp);
+no_sysfs:
+        device_destroy(ptp_class, ptp->devid);
+no_device:
+        mutex_destroy(&ptp->tsevq_mux);
+        kfree(ptp);
+no_memory:
+        clear_bit(index, ptp_clocks_map);
+no_slot:
+        mutex_unlock(&ptp_clocks_mutex);
+        return ERR_PTR(err);
+}
+EXPORT_SYMBOL(ptp_clock_register);
+
+int ptp_clock_unregister(struct ptp_clock *ptp)
+{
+        ptp->defunct = 1;
+        wake_up_interruptible(&ptp->tsev_wq);
+
+        /* Release the clock's resources. */
+        if (ptp->pps_source)
+                pps_unregister_source(ptp->pps_source);
+        ptp_cleanup_sysfs(ptp);
+        device_destroy(ptp_class, ptp->devid);
+
+        posix_clock_unregister(&ptp->clock);
+        return 0;
+}
+EXPORT_SYMBOL(ptp_clock_unregister);
+
+void ptp_clock_event(struct ptp_clock *ptp, struct ptp_clock_event *event)
+{
+        struct pps_event_time evt;
+
+        switch (event->type) {
+
+        case PTP_CLOCK_ALARM:
+                break;
+
+        case PTP_CLOCK_EXTTS:
+                enqueue_external_timestamp(&ptp->tsevq, event);
+                wake_up_interruptible(&ptp->tsev_wq);
+                break;
+
+        case PTP_CLOCK_PPS:
+                pps_get_ts(&evt);
+                pps_event(ptp->pps_source, &evt, PTP_PPS_EVENT, NULL);
+                break;
+        }
+}
+EXPORT_SYMBOL(ptp_clock_event);
+
+/* module operations */
+
+static void __exit ptp_exit(void)
+{
+        class_destroy(ptp_class);
+        unregister_chrdev_region(ptp_devt, PTP_MAX_CLOCKS);
+}
+
+static int __init ptp_init(void)
+{
+        int err;
+
+        ptp_class = class_create(THIS_MODULE, "ptp");
+        if (IS_ERR(ptp_class)) {
+                pr_err("ptp: failed to allocate class\n");
+                return PTR_ERR(ptp_class);
+        }
+
+        err = alloc_chrdev_region(&ptp_devt, 0, PTP_MAX_CLOCKS, "ptp");
+        if (err < 0) {
+                pr_err("ptp: failed to allocate device region\n");
+                goto no_region;
+        }
+
+        ptp_class->dev_attrs = ptp_dev_attrs;
+        pr_info("PTP clock support registered\n");
+        return 0;
+
+no_region:
+        class_destroy(ptp_class);
+        return err;
+}
+
+subsys_initcall(ptp_init);
+module_exit(ptp_exit);
+
+MODULE_AUTHOR("Richard Cochran <richard.cochran@omicron.at>");
+MODULE_DESCRIPTION("PTP clocks support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c
new file mode 100644
index 000000000000..803d665b15ef
--- /dev/null
+++ b/drivers/ptp/ptp_ixp46x.c
@@ -0,0 +1,332 @@
+/*
+ * PTP 1588 clock using the IXP46X
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/ptp_clock_kernel.h>
+#include <mach/ixp46x_ts.h>
+
+#define DRIVER          "ptp_ixp46x"
+#define N_EXT_TS        2
+#define MASTER_GPIO     8
+#define MASTER_IRQ      25
+#define SLAVE_GPIO      7
+#define SLAVE_IRQ       24
+
+struct ixp_clock {
+        struct ixp46x_ts_regs *regs;
+        struct ptp_clock *ptp_clock;
+        struct ptp_clock_info caps;
+        int exts0_enabled;
+        int exts1_enabled;
+};
+
+DEFINE_SPINLOCK(register_lock);
+
+/*
+ * Register access functions
+ */
+
+static u64 ixp_systime_read(struct ixp46x_ts_regs *regs)
+{
+        u64 ns;
+        u32 lo, hi;
+
+        lo = __raw_readl(&regs->systime_lo);
+        hi = __raw_readl(&regs->systime_hi);
+
+        ns = ((u64) hi) << 32;
+        ns |= lo;
+        ns <<= TICKS_NS_SHIFT;
+
+        return ns;
+}
+
+static void ixp_systime_write(struct ixp46x_ts_regs *regs, u64 ns)
+{
+        u32 hi, lo;
+
+        ns >>= TICKS_NS_SHIFT;
+        hi = ns >> 32;
+        lo = ns & 0xffffffff;
+
+        __raw_writel(lo, &regs->systime_lo);
+        __raw_writel(hi, &regs->systime_hi);
+}
+
+/*
+ * Interrupt service routine
+ */
+
+static irqreturn_t isr(int irq, void *priv)
+{
+        struct ixp_clock *ixp_clock = priv;
+        struct ixp46x_ts_regs *regs = ixp_clock->regs;
+        struct ptp_clock_event event;
+        u32 ack = 0, lo, hi, val;
+
+        val = __raw_readl(&regs->event);
+
+        if (val & TSER_SNS) {
+                ack |= TSER_SNS;
+                if (ixp_clock->exts0_enabled) {
+                        hi = __raw_readl(&regs->asms_hi);
+                        lo = __raw_readl(&regs->asms_lo);
+                        event.type = PTP_CLOCK_EXTTS;
+                        event.index = 0;
+                        event.timestamp = ((u64) hi) << 32;
+                        event.timestamp |= lo;
+                        event.timestamp <<= TICKS_NS_SHIFT;
+                        ptp_clock_event(ixp_clock->ptp_clock, &event);
+                }
+        }
+
+        if (val & TSER_SNM) {
+                ack |= TSER_SNM;
+                if (ixp_clock->exts1_enabled) {
+                        hi = __raw_readl(&regs->amms_hi);
+                        lo = __raw_readl(&regs->amms_lo);
+                        event.type = PTP_CLOCK_EXTTS;
+                        event.index = 1;
+                        event.timestamp = ((u64) hi) << 32;
+                        event.timestamp |= lo;
+                        event.timestamp <<= TICKS_NS_SHIFT;
+                        ptp_clock_event(ixp_clock->ptp_clock, &event);
+                }
+        }
+
+        if (val & TTIPEND)
+                ack |= TTIPEND; /* this bit seems to be always set */
+
+        if (ack) {
+                __raw_writel(ack, &regs->event);
+                return IRQ_HANDLED;
+        } else
+                return IRQ_NONE;
+}
+
+/*
+ * PTP clock operations
+ */
+
+static int ptp_ixp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+        u64 adj;
+        u32 diff, addend;
+        int neg_adj = 0;
+        struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
+        struct ixp46x_ts_regs *regs = ixp_clock->regs;
+
+        if (ppb < 0) {
+                neg_adj = 1;
+                ppb = -ppb;
+        }
+        addend = DEFAULT_ADDEND;
+        adj = addend;
+        adj *= ppb;
+        diff = div_u64(adj, 1000000000ULL);
+
+        addend = neg_adj ? addend - diff : addend + diff;
+
+        __raw_writel(addend, &regs->addend);
+
+        return 0;
+}
+
+static int ptp_ixp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+        s64 now;
+        unsigned long flags;
+        struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
+        struct ixp46x_ts_regs *regs = ixp_clock->regs;
+
+        spin_lock_irqsave(&register_lock, flags);
+
+        now = ixp_systime_read(regs);
+        now += delta;
+        ixp_systime_write(regs, now);
+
+        spin_unlock_irqrestore(&register_lock, flags);
+
+        return 0;
+}
+
+static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+        u64 ns;
+        u32 remainder;
+        unsigned long flags;
+        struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
+        struct ixp46x_ts_regs *regs = ixp_clock->regs;
+
+        spin_lock_irqsave(&register_lock, flags);
+
+        ns = ixp_systime_read(regs);
+
+        spin_unlock_irqrestore(&register_lock, flags);
+
+        ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
+        ts->tv_nsec = remainder;
+        return 0;
+}
+
+static int ptp_ixp_settime(struct ptp_clock_info *ptp,
+                           const struct timespec *ts)
+{
+        u64 ns;
+        unsigned long flags;
+        struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
+        struct ixp46x_ts_regs *regs = ixp_clock->regs;
+
+        ns = ts->tv_sec * 1000000000ULL;
+        ns += ts->tv_nsec;
+
+        spin_lock_irqsave(&register_lock, flags);
+
+        ixp_systime_write(regs, ns);
+
+        spin_unlock_irqrestore(&register_lock, flags);
+
+        return 0;
+}
+
+static int ptp_ixp_enable(struct ptp_clock_info *ptp,
+                          struct ptp_clock_request *rq, int on)
+{
+        struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
+
+        switch (rq->type) {
+        case PTP_CLK_REQ_EXTTS:
+                switch (rq->extts.index) {
+                case 0:
+                        ixp_clock->exts0_enabled = on ? 1 : 0;
+                        break;
+                case 1:
+                        ixp_clock->exts1_enabled = on ? 1 : 0;
+                        break;
+                default:
+                        return -EINVAL;
+                }
+                return 0;
+        default:
+                break;
+        }
+
+        return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info ptp_ixp_caps = {
+        .owner          = THIS_MODULE,
+        .name           = "IXP46X timer",
+        .max_adj        = 66666655,
+        .n_ext_ts       = N_EXT_TS,
+        .pps            = 0,
+        .adjfreq        = ptp_ixp_adjfreq,
+        .adjtime        = ptp_ixp_adjtime,
+        .gettime        = ptp_ixp_gettime,
+        .settime        = ptp_ixp_settime,
+        .enable         = ptp_ixp_enable,
+};
+
+/* module operations */
+
+static struct ixp_clock ixp_clock;
+
+static int setup_interrupt(int gpio)
+{
+        int irq;
+
+        gpio_line_config(gpio, IXP4XX_GPIO_IN);
+
+        irq = gpio_to_irq(gpio);
+
+        if (NO_IRQ == irq)
+                return NO_IRQ;
+
+        if (irq_set_irq_type(irq, IRQF_TRIGGER_FALLING)) {
+                pr_err("cannot set trigger type for irq %d\n", irq);
+                return NO_IRQ;
+        }
+
+        if (request_irq(irq, isr, 0, DRIVER, &ixp_clock)) {
+                pr_err("request_irq failed for irq %d\n", irq);
+                return NO_IRQ;
+        }
+
+        return irq;
+}
+
+static void __exit ptp_ixp_exit(void)
+{
+        free_irq(MASTER_IRQ, &ixp_clock);
+        free_irq(SLAVE_IRQ, &ixp_clock);
+        ptp_clock_unregister(ixp_clock.ptp_clock);
+}
+
+static int __init ptp_ixp_init(void)
+{
+        if (!cpu_is_ixp46x())
+                return -ENODEV;
+
+        ixp_clock.regs =
+                (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
+
+        ixp_clock.caps = ptp_ixp_caps;
+
+        ixp_clock.ptp_clock = ptp_clock_register(&ixp_clock.caps);
+
+        if (IS_ERR(ixp_clock.ptp_clock))
+                return PTR_ERR(ixp_clock.ptp_clock);
+
+        __raw_writel(DEFAULT_ADDEND, &ixp_clock.regs->addend);
+        __raw_writel(1, &ixp_clock.regs->trgt_lo);
+        __raw_writel(0, &ixp_clock.regs->trgt_hi);
+        __raw_writel(TTIPEND, &ixp_clock.regs->event);
+
+        if (MASTER_IRQ != setup_interrupt(MASTER_GPIO)) {
+                pr_err("failed to setup gpio %d as irq\n", MASTER_GPIO);
+                goto no_master;
+        }
+        if (SLAVE_IRQ != setup_interrupt(SLAVE_GPIO)) {
+                pr_err("failed to setup gpio %d as irq\n", SLAVE_GPIO);
+                goto no_slave;
+        }
+
+        return 0;
+no_slave:
+        free_irq(MASTER_IRQ, &ixp_clock);
+no_master:
+        ptp_clock_unregister(ixp_clock.ptp_clock);
+        return -ENODEV;
+}
+
+module_init(ptp_ixp_init);
+module_exit(ptp_ixp_exit);
+
+MODULE_AUTHOR("Richard Cochran <richard.cochran@omicron.at>");
+MODULE_DESCRIPTION("PTP clock using the IXP46X timer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
new file mode 100644
index 000000000000..4d5b5082c3b1
--- /dev/null
+++ b/drivers/ptp/ptp_private.h
@@ -0,0 +1,92 @@
+/*
+ * PTP 1588 clock support - private declarations for the core module.
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef _PTP_PRIVATE_H_
+#define _PTP_PRIVATE_H_
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/posix-clock.h>
+#include <linux/ptp_clock.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/time.h>
+
+#define PTP_MAX_TIMESTAMPS 128
+#define PTP_BUF_TIMESTAMPS 30
+
+struct timestamp_event_queue {
+        struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS];
+        int head;
+        int tail;
+        spinlock_t lock;
+};
+
+struct ptp_clock {
+        struct posix_clock clock;
+        struct device *dev;
+        struct ptp_clock_info *info;
+        dev_t devid;
+        int index; /* index into clocks.map */
+        struct pps_device *pps_source;
+        struct timestamp_event_queue tsevq; /* simple fifo for time stamps */
+        struct mutex tsevq_mux; /* one process at a time reading the fifo */
+        wait_queue_head_t tsev_wq;
+        int defunct; /* tells readers to go away when clock is being removed */
+};
+
+/*
+ * The function queue_cnt() is safe for readers to call without
+ * holding q->lock. Readers use this function to verify that the queue
+ * is nonempty before proceeding with a dequeue operation. The fact
+ * that a writer might concurrently increment the tail does not
+ * matter, since the queue remains nonempty nonetheless.
+ */
+static inline int queue_cnt(struct timestamp_event_queue *q)
+{
+        int cnt = q->tail - q->head;
+        return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt;
+}
+
+/*
+ * see ptp_chardev.c
+ */
+
+long ptp_ioctl(struct posix_clock *pc,
+               unsigned int cmd, unsigned long arg);
+
+int ptp_open(struct posix_clock *pc, fmode_t fmode);
+
+ssize_t ptp_read(struct posix_clock *pc,
+                 uint flags, char __user *buf, size_t cnt);
+
+uint ptp_poll(struct posix_clock *pc,
+              struct file *fp, poll_table *wait);
+
+/*
+ * see ptp_sysfs.c
+ */
+
+extern struct device_attribute ptp_dev_attrs[];
+
+int ptp_cleanup_sysfs(struct ptp_clock *ptp);
+
+int ptp_populate_sysfs(struct ptp_clock *ptp);
+
+#endif
diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
new file mode 100644
index 000000000000..2f93926ac976
--- /dev/null
+++ b/drivers/ptp/ptp_sysfs.c
@@ -0,0 +1,230 @@
+/*
+ * PTP 1588 clock support - sysfs interface.
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/capability.h>
+
+#include "ptp_private.h"
+
+static ssize_t clock_name_show(struct device *dev,
+                               struct device_attribute *attr, char *page)
+{
+        struct ptp_clock *ptp = dev_get_drvdata(dev);
+        return snprintf(page, PAGE_SIZE-1, "%s\n", ptp->info->name);
+}
+
+#define PTP_SHOW_INT(name)                                              \
+static ssize_t name##_show(struct device *dev,                          \
+                           struct device_attribute *attr, char *page)   \
+{                                                                       \
+        struct ptp_clock *ptp = dev_get_drvdata(dev);                   \
+        return snprintf(page, PAGE_SIZE-1, "%d\n", ptp->info->name);    \
+}
+
+PTP_SHOW_INT(max_adj);
+PTP_SHOW_INT(n_alarm);
+PTP_SHOW_INT(n_ext_ts);
+PTP_SHOW_INT(n_per_out);
+PTP_SHOW_INT(pps);
+
+#define PTP_RO_ATTR(_var, _name) {                              \
+        .attr   = { .name = __stringify(_name), .mode = 0444 }, \
+        .show   = _var##_show,                                  \
+}
+
+struct device_attribute ptp_dev_attrs[] = {
+        PTP_RO_ATTR(clock_name, clock_name),
+        PTP_RO_ATTR(max_adj,    max_adjustment),
+        PTP_RO_ATTR(n_alarm,    n_alarms),
+        PTP_RO_ATTR(n_ext_ts,   n_external_timestamps),
+        PTP_RO_ATTR(n_per_out,  n_periodic_outputs),
+        PTP_RO_ATTR(pps,        pps_available),
+        __ATTR_NULL,
+};
+
+static ssize_t extts_enable_store(struct device *dev,
+                                  struct device_attribute *attr,
+                                  const char *buf, size_t count)
+{
+        struct ptp_clock *ptp = dev_get_drvdata(dev);
+        struct ptp_clock_info *ops = ptp->info;
+        struct ptp_clock_request req = { .type = PTP_CLK_REQ_EXTTS };
+        int cnt, enable;
+        int err = -EINVAL;
+
+        cnt = sscanf(buf, "%u %d", &req.extts.index, &enable);
+        if (cnt != 2)
+                goto out;
+        if (req.extts.index >= ops->n_ext_ts)
+                goto out;
+
+        err = ops->enable(ops, &req, enable ? 1 : 0);
+        if (err)
+                goto out;
+
+        return count;
+out:
+        return err;
+}
+
+static ssize_t extts_fifo_show(struct device *dev,
+                               struct device_attribute *attr, char *page)
+{
+        struct ptp_clock *ptp = dev_get_drvdata(dev);
+        struct timestamp_event_queue *queue = &ptp->tsevq;
+        struct ptp_extts_event event;
+        unsigned long flags;
+        size_t qcnt;
+        int cnt = 0;
+
+        memset(&event, 0, sizeof(event));
+
+        if (mutex_lock_interruptible(&ptp->tsevq_mux))
+                return -ERESTARTSYS;
+
+        spin_lock_irqsave(&queue->lock, flags);
+        qcnt = queue_cnt(queue);
+        if (qcnt) {
+                event = queue->buf[queue->head];
+                queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+        }
+        spin_unlock_irqrestore(&queue->lock, flags);
+
+        if (!qcnt)
+                goto out;
+
+        cnt = snprintf(page, PAGE_SIZE, "%u %lld %u\n",
+                       event.index, event.t.sec, event.t.nsec);
+out:
+        mutex_unlock(&ptp->tsevq_mux);
+        return cnt;
+}
+
+static ssize_t period_store(struct device *dev,
+                            struct device_attribute *attr,
+                            const char *buf, size_t count)
+{
+        struct ptp_clock *ptp = dev_get_drvdata(dev);
+        struct ptp_clock_info *ops = ptp->info;
+        struct ptp_clock_request req = { .type = PTP_CLK_REQ_PEROUT };
+        int cnt, enable, err = -EINVAL;
+
+        cnt = sscanf(buf, "%u %lld %u %lld %u", &req.perout.index,
+                     &req.perout.start.sec, &req.perout.start.nsec,
+                     &req.perout.period.sec, &req.perout.period.nsec);
+        if (cnt != 5)
+                goto out;
+        if (req.perout.index >= ops->n_per_out)
+                goto out;
+
+        enable = req.perout.period.sec || req.perout.period.nsec;
+        err = ops->enable(ops, &req, enable);
+        if (err)
+                goto out;
+
+        return count;
+out:
+        return err;
+}
+
+static ssize_t pps_enable_store(struct device *dev,
+                                struct device_attribute *attr,
+                                const char *buf, size_t count)
+{
+        struct ptp_clock *ptp = dev_get_drvdata(dev);
+        struct ptp_clock_info *ops = ptp->info;
+        struct ptp_clock_request req = { .type = PTP_CLK_REQ_PPS };
+        int cnt, enable;
+        int err = -EINVAL;
+
+        if (!capable(CAP_SYS_TIME))
+                return -EPERM;
+
+        cnt = sscanf(buf, "%d", &enable);
+        if (cnt != 1)
+                goto out;
+
+        err = ops->enable(ops, &req, enable ? 1 : 0);
+        if (err)
+                goto out;
+
+        return count;
+out:
+        return err;
+}
+
+static DEVICE_ATTR(extts_enable, 0220, NULL, extts_enable_store);
+static DEVICE_ATTR(fifo,         0444, extts_fifo_show, NULL);
+static DEVICE_ATTR(period,       0220, NULL, period_store);
+static DEVICE_ATTR(pps_enable,   0220, NULL, pps_enable_store);
+
+int ptp_cleanup_sysfs(struct ptp_clock *ptp)
+{
+        struct device *dev = ptp->dev;
+        struct ptp_clock_info *info = ptp->info;
+
+        if (info->n_ext_ts) {
+                device_remove_file(dev, &dev_attr_extts_enable);
+                device_remove_file(dev, &dev_attr_fifo);
+        }
+        if (info->n_per_out)
+                device_remove_file(dev, &dev_attr_period);
+
+        if (info->pps)
+                device_remove_file(dev, &dev_attr_pps_enable);
+
+        return 0;
+}
+
+int ptp_populate_sysfs(struct ptp_clock *ptp)
+{
+        struct device *dev = ptp->dev;
+        struct ptp_clock_info *info = ptp->info;
+        int err;
+
+        if (info->n_ext_ts) {
+                err = device_create_file(dev, &dev_attr_extts_enable);
+                if (err)
+                        goto out1;
+                err = device_create_file(dev, &dev_attr_fifo);
+                if (err)
+                        goto out2;
+        }
+        if (info->n_per_out) {
+                err = device_create_file(dev, &dev_attr_period);
+                if (err)
+                        goto out3;
+        }
+        if (info->pps) {
+                err = device_create_file(dev, &dev_attr_pps_enable);
+                if (err)
+                        goto out4;
+        }
+        return 0;
+out4:
+        if (info->n_per_out)
+                device_remove_file(dev, &dev_attr_period);
+out3:
+        if (info->n_ext_ts)
+                device_remove_file(dev, &dev_attr_fifo);
+out2:
+        if (info->n_ext_ts)
+                device_remove_file(dev, &dev_attr_extts_enable);
+out1:
+        return err;
+}
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index b9f29e0d4295..f0b13a0d1851 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -274,6 +274,13 @@ config REGULATOR_AB8500
           This driver supports the regulators found on the ST-Ericsson mixed
           signal AB8500 PMIC
 
+config REGULATOR_DB8500_PRCMU
+        bool "ST-Ericsson DB8500 Voltage Domain Regulators"
+        depends on MFD_DB8500_PRCMU
+        help
+          This driver supports the voltage domain regulators controlled by the
+          DB8500 PRCMU
+
 config REGULATOR_TPS6586X
         tristate "TI TPS6586X Power regulators"
         depends on MFD_TPS6586X
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index d72a42756778..165ff5371e9e 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -41,5 +41,6 @@ obj-$(CONFIG_REGULATOR_TPS6524X) += tps6524x-regulator.o
 obj-$(CONFIG_REGULATOR_88PM8607) += 88pm8607.o
 obj-$(CONFIG_REGULATOR_ISL6271A) += isl6271a-regulator.o
 obj-$(CONFIG_REGULATOR_AB8500)  += ab8500.o
+obj-$(CONFIG_REGULATOR_DB8500_PRCMU) += db8500-prcmu.o
 
 ccflags-$(CONFIG_REGULATOR_DEBUG) += -DDEBUG
diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c
new file mode 100644
index 000000000000..1089a961616e
--- /dev/null
+++ b/drivers/regulator/db8500-prcmu.c
@@ -0,0 +1,558 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ * Authors: Sundar Iyer <sundar.iyer@stericsson.com> for ST-Ericsson
+ *          Bengt Jonsson <bengt.g.jonsson@stericsson.com> for ST-Ericsson
+ *
+ * Power domain regulators on DB8500
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/db8500-prcmu.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/db8500-prcmu.h>
+
+/*
+ * power state reference count
+ */
+static int power_state_active_cnt; /* will initialize to zero */
+static DEFINE_SPINLOCK(power_state_active_lock);
+
+static void power_state_active_enable(void)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&power_state_active_lock, flags);
+        power_state_active_cnt++;
+        spin_unlock_irqrestore(&power_state_active_lock, flags);
+}
+
+static int power_state_active_disable(void)
+{
+        int ret = 0;
+        unsigned long flags;
+
+        spin_lock_irqsave(&power_state_active_lock, flags);
+        if (power_state_active_cnt <= 0) {
+                pr_err("power state: unbalanced enable/disable calls\n");
+                ret = -EINVAL;
+                goto out;
+        }
+
+        power_state_active_cnt--;
+out:
+        spin_unlock_irqrestore(&power_state_active_lock, flags);
+        return ret;
+}
+
+/*
+ * Exported interface for CPUIdle only. This function is called when interrupts
+ * are turned off. Hence, no locking.
+ */
+int power_state_active_is_enabled(void)
+{
+        return (power_state_active_cnt > 0);
+}
+
+/**
+ * struct db8500_regulator_info - db8500 regulator information
+ * @dev: device pointer
+ * @desc: regulator description
+ * @rdev: regulator device pointer
+ * @is_enabled: status of the regulator
+ * @epod_id: id for EPOD (power domain)
+ * @is_ramret: RAM retention switch for EPOD (power domain)
+ * @operating_point: operating point (only for vape, to be removed)
+ *
+ */
+struct db8500_regulator_info {
+        struct device *dev;
+        struct regulator_desc desc;
+        struct regulator_dev *rdev;
+        bool is_enabled;
+        u16 epod_id;
+        bool is_ramret;
+        bool exclude_from_power_state;
+        unsigned int operating_point;
+};
+
+static int db8500_regulator_enable(struct regulator_dev *rdev)
+{
+        struct db8500_regulator_info *info = rdev_get_drvdata(rdev);
+
+        if (info == NULL)
+                return -EINVAL;
+
+        dev_vdbg(rdev_get_dev(rdev), "regulator-%s-enable\n",
+                info->desc.name);
+
+        info->is_enabled = true;
+        if (!info->exclude_from_power_state)
+                power_state_active_enable();
+
+        return 0;
+}
+
+static int db8500_regulator_disable(struct regulator_dev *rdev)
+{
+        struct db8500_regulator_info *info = rdev_get_drvdata(rdev);
+        int ret = 0;
+
+        if (info == NULL)
+                return -EINVAL;
+
+        dev_vdbg(rdev_get_dev(rdev), "regulator-%s-disable\n",
+                info->desc.name);
+
+        info->is_enabled = false;
+        if (!info->exclude_from_power_state)
+                ret = power_state_active_disable();
+
+        return ret;
+}
+
+static int db8500_regulator_is_enabled(struct regulator_dev *rdev)
+{
+        struct db8500_regulator_info *info = rdev_get_drvdata(rdev);
+
+        if (info == NULL)
+                return -EINVAL;
+
+        dev_vdbg(rdev_get_dev(rdev), "regulator-%s-is_enabled (is_enabled):"
+                " %i\n", info->desc.name, info->is_enabled);
+
+        return info->is_enabled;
+}
+
+/* db8500 regulator operations */
+static struct regulator_ops db8500_regulator_ops = {
+        .enable                 = db8500_regulator_enable,
+        .disable                = db8500_regulator_disable,
+        .is_enabled             = db8500_regulator_is_enabled,
+};
+
+/*
+ * EPOD control
+ */
+static bool epod_on[NUM_EPOD_ID];
+static bool epod_ramret[NUM_EPOD_ID];
+
+static int enable_epod(u16 epod_id, bool ramret)
+{
+        int ret;
+
+        if (ramret) {
+                if (!epod_on[epod_id]) {
+                        ret = prcmu_set_epod(epod_id, EPOD_STATE_RAMRET);
+                        if (ret < 0)
+                                return ret;
+                }
+                epod_ramret[epod_id] = true;
+        } else {
+                ret = prcmu_set_epod(epod_id, EPOD_STATE_ON);
+                if (ret < 0)
+                        return ret;
+                epod_on[epod_id] = true;
+        }
+
+        return 0;
+}
+
+static int disable_epod(u16 epod_id, bool ramret)
+{
+        int ret;
+
+        if (ramret) {
+                if (!epod_on[epod_id]) {
+                        ret = prcmu_set_epod(epod_id, EPOD_STATE_OFF);
+                        if (ret < 0)
+                                return ret;
+                }
+                epod_ramret[epod_id] = false;
+        } else {
+                if (epod_ramret[epod_id]) {
+                        ret = prcmu_set_epod(epod_id, EPOD_STATE_RAMRET);
+                        if (ret < 0)
+                                return ret;
+                } else {
+                        ret = prcmu_set_epod(epod_id, EPOD_STATE_OFF);
+                        if (ret < 0)
+                                return ret;
+                }
+                epod_on[epod_id] = false;
+        }
+
+        return 0;
+}
+
+/*
+ * Regulator switch
+ */
+static int db8500_regulator_switch_enable(struct regulator_dev *rdev)
+{
+        struct db8500_regulator_info *info = rdev_get_drvdata(rdev);
+        int ret;
+
+        if (info == NULL)
+                return -EINVAL;
+
+        dev_vdbg(rdev_get_dev(rdev), "regulator-switch-%s-enable\n",
+                info->desc.name);
+
+        ret = enable_epod(info->epod_id, info->is_ramret);
+        if (ret < 0) {
+                dev_err(rdev_get_dev(rdev),
+                        "regulator-switch-%s-enable: prcmu call failed\n",
+                        info->desc.name);
+                goto out;
+        }
+
+        info->is_enabled = true;
+out:
+        return ret;
+}
+
+static int db8500_regulator_switch_disable(struct regulator_dev *rdev)
+{
+        struct db8500_regulator_info *info = rdev_get_drvdata(rdev);
+        int ret;
+
+        if (info == NULL)
+                return -EINVAL;
+
+        dev_vdbg(rdev_get_dev(rdev), "regulator-switch-%s-disable\n",
+                info->desc.name);
+
+        ret = disable_epod(info->epod_id, info->is_ramret);
+        if (ret < 0) {
+                dev_err(rdev_get_dev(rdev),
+                        "regulator_switch-%s-disable: prcmu call failed\n",
+                        info->desc.name);
+                goto out;
+        }
+
+        info->is_enabled = 0;
+out:
+        return ret;
+}
+
+static int db8500_regulator_switch_is_enabled(struct regulator_dev *rdev)
+{
+        struct db8500_regulator_info *info = rdev_get_drvdata(rdev);
+
+        if (info == NULL)
+                return -EINVAL;
+
+        dev_vdbg(rdev_get_dev(rdev),
+                "regulator-switch-%s-is_enabled (is_enabled): %i\n",
+                info->desc.name, info->is_enabled);
+
+        return info->is_enabled;
+}
+
+static struct regulator_ops db8500_regulator_switch_ops = {
+        .enable                 = db8500_regulator_switch_enable,
+        .disable                = db8500_regulator_switch_disable,
+        .is_enabled             = db8500_regulator_switch_is_enabled,
+};
+
+/*
+ * Regulator information
+ */
+static struct db8500_regulator_info
+                db8500_regulator_info[DB8500_NUM_REGULATORS] = {
+        [DB8500_REGULATOR_VAPE] = {
+                .desc = {
+                        .name   = "db8500-vape",
+                        .id     = DB8500_REGULATOR_VAPE,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_VARM] = {
+                .desc = {
+                        .name   = "db8500-varm",
+                        .id     = DB8500_REGULATOR_VARM,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_VMODEM] = {
+                .desc = {
+                        .name   = "db8500-vmodem",
+                        .id     = DB8500_REGULATOR_VMODEM,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_VPLL] = {
+                .desc = {
+                        .name   = "db8500-vpll",
+                        .id     = DB8500_REGULATOR_VPLL,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_VSMPS1] = {
+                .desc = {
+                        .name   = "db8500-vsmps1",
+                        .id     = DB8500_REGULATOR_VSMPS1,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_VSMPS2] = {
+                .desc = {
+                        .name   = "db8500-vsmps2",
+                        .id     = DB8500_REGULATOR_VSMPS2,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .exclude_from_power_state = true,
+        },
+        [DB8500_REGULATOR_VSMPS3] = {
+                .desc = {
+                        .name   = "db8500-vsmps3",
+                        .id     = DB8500_REGULATOR_VSMPS3,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_VRF1] = {
+                .desc = {
+                        .name   = "db8500-vrf1",
+                        .id     = DB8500_REGULATOR_VRF1,
+                        .ops    = &db8500_regulator_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+        },
+        [DB8500_REGULATOR_SWITCH_SVAMMDSP] = {
+                .desc = {
+                        .name   = "db8500-sva-mmdsp",
+                        .id     = DB8500_REGULATOR_SWITCH_SVAMMDSP,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SVAMMDSP,
+        },
+        [DB8500_REGULATOR_SWITCH_SVAMMDSPRET] = {
+                .desc = {
+                        .name   = "db8500-sva-mmdsp-ret",
+                        .id     = DB8500_REGULATOR_SWITCH_SVAMMDSPRET,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SVAMMDSP,
+                .is_ramret = true,
+        },
+        [DB8500_REGULATOR_SWITCH_SVAPIPE] = {
+                .desc = {
+                        .name   = "db8500-sva-pipe",
+                        .id     = DB8500_REGULATOR_SWITCH_SVAPIPE,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SVAPIPE,
+        },
+        [DB8500_REGULATOR_SWITCH_SIAMMDSP] = {
+                .desc = {
+                        .name   = "db8500-sia-mmdsp",
+                        .id     = DB8500_REGULATOR_SWITCH_SIAMMDSP,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SIAMMDSP,
+        },
+        [DB8500_REGULATOR_SWITCH_SIAMMDSPRET] = {
+                .desc = {
+                        .name   = "db8500-sia-mmdsp-ret",
+                        .id     = DB8500_REGULATOR_SWITCH_SIAMMDSPRET,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SIAMMDSP,
+                .is_ramret = true,
+        },
+        [DB8500_REGULATOR_SWITCH_SIAPIPE] = {
+                .desc = {
+                        .name   = "db8500-sia-pipe",
+                        .id     = DB8500_REGULATOR_SWITCH_SIAPIPE,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SIAPIPE,
+        },
+        [DB8500_REGULATOR_SWITCH_SGA] = {
+                .desc = {
+                        .name   = "db8500-sga",
+                        .id     = DB8500_REGULATOR_SWITCH_SGA,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_SGA,
+        },
+        [DB8500_REGULATOR_SWITCH_B2R2_MCDE] = {
+                .desc = {
+                        .name   = "db8500-b2r2-mcde",
+                        .id     = DB8500_REGULATOR_SWITCH_B2R2_MCDE,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_B2R2_MCDE,
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM12] = {
+                .desc = {
+                        .name   = "db8500-esram12",
+                        .id     = DB8500_REGULATOR_SWITCH_ESRAM12,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id        = EPOD_ID_ESRAM12,
+                .is_enabled     = true,
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM12RET] = {
+                .desc = {
+                        .name   = "db8500-esram12-ret",
+                        .id     = DB8500_REGULATOR_SWITCH_ESRAM12RET,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_ESRAM12,
+                .is_ramret = true,
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM34] = {
+                .desc = {
+                        .name   = "db8500-esram34",
+                        .id     = DB8500_REGULATOR_SWITCH_ESRAM34,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id        = EPOD_ID_ESRAM34,
+                .is_enabled     = true,
+        },
+        [DB8500_REGULATOR_SWITCH_ESRAM34RET] = {
+                .desc = {
+                        .name   = "db8500-esram34-ret",
+                        .id     = DB8500_REGULATOR_SWITCH_ESRAM34RET,
+                        .ops    = &db8500_regulator_switch_ops,
+                        .type   = REGULATOR_VOLTAGE,
+                        .owner  = THIS_MODULE,
+                },
+                .epod_id = EPOD_ID_ESRAM34,
+                .is_ramret = true,
+        },
+};
+
+static int __devinit db8500_regulator_probe(struct platform_device *pdev)
+{
+        struct regulator_init_data *db8500_init_data = mfd_get_data(pdev);
+        int i, err;
+
+        /* register all regulators */
+        for (i = 0; i < ARRAY_SIZE(db8500_regulator_info); i++) {
+                struct db8500_regulator_info *info;
+                struct regulator_init_data *init_data = &db8500_init_data[i];
+
+                /* assign per-regulator data */
+                info = &db8500_regulator_info[i];
+                info->dev = &pdev->dev;
+
+                /* register with the regulator framework */
+                info->rdev = regulator_register(&info->desc, &pdev->dev,
+                                init_data, info);
+                if (IS_ERR(info->rdev)) {
+                        err = PTR_ERR(info->rdev);
+                        dev_err(&pdev->dev, "failed to register %s: err %i\n",
+                                info->desc.name, err);
+
+                        /* if failing, unregister all earlier regulators */
+                        i--;
+                        while (i >= 0) {
+                                info = &db8500_regulator_info[i];
+                                regulator_unregister(info->rdev);
+                                i--;
+                        }
+                        return err;
+                }
+
+                dev_dbg(rdev_get_dev(info->rdev),
+                        "regulator-%s-probed\n", info->desc.name);
+        }
+
+        return 0;
+}
+
+static int __exit db8500_regulator_remove(struct platform_device *pdev)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(db8500_regulator_info); i++) {
+                struct db8500_regulator_info *info;
+                info = &db8500_regulator_info[i];
+
+                dev_vdbg(rdev_get_dev(info->rdev),
+                        "regulator-%s-remove\n", info->desc.name);
+
+                regulator_unregister(info->rdev);
+        }
+
+        return 0;
+}
+
+static struct platform_driver db8500_regulator_driver = {
+        .driver = {
+                .name = "db8500-prcmu-regulators",
+                .owner = THIS_MODULE,
+        },
+        .probe = db8500_regulator_probe,
+        .remove = __exit_p(db8500_regulator_remove),
+};
+
+static int __init db8500_regulator_init(void)
+{
+        int ret;
+
+        ret = platform_driver_register(&db8500_regulator_driver);
+        if (ret < 0)
+                return -ENODEV;
+
+        return 0;
+}
+
+static void __exit db8500_regulator_exit(void)
+{
+        platform_driver_unregister(&db8500_regulator_driver);
+}
+
+arch_initcall(db8500_regulator_init);
+module_exit(db8500_regulator_exit);
+
+MODULE_AUTHOR("STMicroelectronics/ST-Ericsson");
+MODULE_DESCRIPTION("DB8500 regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 42891726ea72..b8f4e9e66cd5 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -992,4 +992,11 @@ config RTC_DRV_TEGRA
           This drive can also be built as a module. If so, the module
           will be called rtc-tegra.
 
+config RTC_DRV_TILE
+        tristate "Tilera hypervisor RTC support"
+        depends on TILE
+        help
+          Enable support for the Linux driver side of the Tilera
+          hypervisor's real-time clock interface.
+
 endif # RTC_CLASS
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index ca91c3c42e98..9574748d1c73 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -93,6 +93,7 @@ obj-$(CONFIG_RTC_DRV_STMP)	+= rtc-stmp3xxx.o
 obj-$(CONFIG_RTC_DRV_SUN4V)     += rtc-sun4v.o
 obj-$(CONFIG_RTC_DRV_TEGRA)     += rtc-tegra.o
 obj-$(CONFIG_RTC_DRV_TEST)      += rtc-test.o
+obj-$(CONFIG_RTC_DRV_TILE)      += rtc-tile.o
 obj-$(CONFIG_RTC_DRV_TWL4030)   += rtc-twl.o
 obj-$(CONFIG_RTC_DRV_TX4939)    += rtc-tx4939.o
 obj-$(CONFIG_RTC_DRV_V3020)     += rtc-v3020.o
diff --git a/drivers/rtc/rtc-tile.c b/drivers/rtc/rtc-tile.c
new file mode 100644
index 000000000000..eb65dafee66e
--- /dev/null
+++ b/drivers/rtc/rtc-tile.c
@@ -0,0 +1,162 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   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, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * Tilera-specific RTC driver.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/rtc.h>
+#include <linux/platform_device.h>
+
+/* Platform device pointer. */
+static struct platform_device *tile_rtc_platform_device;
+
+/*
+ * RTC read routine.  Gets time info from RTC chip via hypervisor syscall.
+ */
+static int read_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+        HV_RTCTime hvtm = hv_get_rtc();
+
+        tm->tm_sec = hvtm.tm_sec;
+        tm->tm_min = hvtm.tm_min;
+        tm->tm_hour = hvtm.tm_hour;
+        tm->tm_mday = hvtm.tm_mday;
+        tm->tm_mon = hvtm.tm_mon;
+        tm->tm_year = hvtm.tm_year;
+        tm->tm_wday = 0;
+        tm->tm_yday = 0;
+        tm->tm_isdst = 0;
+
+        if (rtc_valid_tm(tm) < 0)
+                dev_warn(dev, "Read invalid date/time from RTC\n");
+
+        return 0;
+}
+
+/*
+ * RTC write routine.  Sends time info to hypervisor via syscall, to be
+ * written to RTC chip.
+ */
+static int set_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+        HV_RTCTime hvtm;
+
+        hvtm.tm_sec = tm->tm_sec;
+        hvtm.tm_min = tm->tm_min;
+        hvtm.tm_hour = tm->tm_hour;
+        hvtm.tm_mday = tm->tm_mday;
+        hvtm.tm_mon = tm->tm_mon;
+        hvtm.tm_year = tm->tm_year;
+
+        hv_set_rtc(hvtm);
+
+        return 0;
+}
+
+/*
+ * RTC read/write ops.
+ */
+static const struct rtc_class_ops tile_rtc_ops = {
+        .read_time      = read_rtc_time,
+        .set_time       = set_rtc_time,
+};
+
+/*
+ * Device probe routine.
+ */
+static int __devinit tile_rtc_probe(struct platform_device *dev)
+{
+        struct rtc_device *rtc;
+
+        rtc = rtc_device_register("tile",
+                                  &dev->dev, &tile_rtc_ops, THIS_MODULE);
+
+        if (IS_ERR(rtc))
+                return PTR_ERR(rtc);
+
+        platform_set_drvdata(dev, rtc);
+
+        return 0;
+}
+
+/*
+ * Device cleanup routine.
+ */
+static int __devexit tile_rtc_remove(struct platform_device *dev)
+{
+        struct rtc_device *rtc = platform_get_drvdata(dev);
+
+        if (rtc)
+                rtc_device_unregister(rtc);
+
+        platform_set_drvdata(dev, NULL);
+
+        return 0;
+}
+
+static struct platform_driver tile_rtc_platform_driver = {
+        .driver         = {
+                .name   = "rtc-tile",
+                .owner  = THIS_MODULE,
+        },
+        .probe          = tile_rtc_probe,
+        .remove         = __devexit_p(tile_rtc_remove),
+};
+
+/*
+ * Driver init routine.
+ */
+static int __init tile_rtc_driver_init(void)
+{
+        int err;
+
+        err = platform_driver_register(&tile_rtc_platform_driver);
+        if (err)
+                return err;
+
+        tile_rtc_platform_device = platform_device_alloc("rtc-tile", 0);
+        if (tile_rtc_platform_device == NULL) {
+                err = -ENOMEM;
+                goto exit_driver_unregister;
+        }
+
+        err = platform_device_add(tile_rtc_platform_device);
+        if (err)
+                goto exit_device_put;
+
+        return 0;
+
+exit_device_put:
+        platform_device_put(tile_rtc_platform_device);
+
+exit_driver_unregister:
+        platform_driver_unregister(&tile_rtc_platform_driver);
+        return err;
+}
+
+/*
+ * Driver cleanup routine.
+ */
+static void __exit tile_rtc_driver_exit(void)
+{
+        platform_driver_unregister(&tile_rtc_platform_driver);
+}
+
+module_init(tile_rtc_driver_init);
+module_exit(tile_rtc_driver_exit);
+
+MODULE_DESCRIPTION("Tilera-specific Real Time Clock Driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:rtc-tile");
diff --git a/drivers/scsi/qla4xxx/ql4_nx.c b/drivers/scsi/qla4xxx/ql4_nx.c
index 35381cb0936e..03e522b2fe0b 100644
--- a/drivers/scsi/qla4xxx/ql4_nx.c
+++ b/drivers/scsi/qla4xxx/ql4_nx.c
@@ -655,6 +655,27 @@ static int qla4_8xxx_pci_is_same_window(struct scsi_qla_host *ha,
         return 0;
 }
 
+#ifndef readq
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+        const volatile u32 __iomem *p = addr;
+        u32 low, high;
+
+        low = readl(p);
+        high = readl(p + 1);
+
+        return low + ((u64)high << 32);
+}
+#endif
+
+#ifndef writeq
+static inline void writeq(__u64 val, volatile void __iomem *addr)
+{
+        writel(val, addr);
+        writel(val >> 32, addr+4);
+}
+#endif
+
 static int qla4_8xxx_pci_mem_read_direct(struct scsi_qla_host *ha,
                 u64 off, void *data, int size)
 {
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 95019c747cc1..4778e2707168 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -636,7 +636,7 @@ static int sr_probe(struct device *dev)
         disk->first_minor = minor;
         sprintf(disk->disk_name, "sr%d", minor);
         disk->fops = &sr_bdops;
-        disk->flags = GENHD_FL_CD;
+        disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
         disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
 
         blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);
diff --git a/drivers/staging/zcache/zcache.c b/drivers/staging/zcache/zcache.c
index b8a2b30a1572..77ac2d4d3ef1 100644
--- a/drivers/staging/zcache/zcache.c
+++ b/drivers/staging/zcache/zcache.c
@@ -1181,9 +1181,12 @@ static bool zcache_freeze;
 /*
  * zcache shrinker interface (only useful for ephemeral pages, so zbud only)
  */
-static int shrink_zcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int shrink_zcache_memory(struct shrinker *shrink,
+                                struct shrink_control *sc)
 {
         int ret = -1;
+        int nr = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
 
         if (nr >= 0) {
                 if (!(gfp_mask & __GFP_FS))
diff --git a/drivers/tty/serial/68328serial.c b/drivers/tty/serial/68328serial.c
index d5bfd41707e7..e0a77540b8ca 100644
--- a/drivers/tty/serial/68328serial.c
+++ b/drivers/tty/serial/68328serial.c
@@ -281,7 +281,7 @@ static void receive_chars(struct m68k_serial *info, unsigned short rx)
 #ifdef CONFIG_MAGIC_SYSRQ
                         } else if (ch == 0x10) { /* ^P */
                                 show_state();
-                                show_free_areas();
+                                show_free_areas(0);
                                 show_buffers();
 /*                              show_net_buffers(); */
                                 return;
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index c63d0d152af6..f2cb7503fcb2 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -15,6 +15,7 @@
  *Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307, USA.
  */
 #include <linux/serial_reg.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/serial_core.h>
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index f9916ca5ca4d..549b960667c8 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -1460,6 +1460,14 @@ config FB_S3
         ---help---
           Driver for graphics boards with S3 Trio / S3 Virge chip.
 
+config FB_S3_DDC
+        bool "DDC for S3 support"
+        depends on FB_S3
+        select FB_DDC
+        default y
+        help
+          Say Y here if you want DDC support for your S3 graphics card.
+
 config FB_SAVAGE
         tristate "S3 Savage support"
         depends on FB && PCI && EXPERIMENTAL
@@ -1983,6 +1991,18 @@ config FB_SH_MOBILE_HDMI
         ---help---
           Driver for the on-chip SH-Mobile HDMI controller.
 
+config FB_SH_MOBILE_MERAM
+        tristate "SuperH Mobile MERAM read ahead support for LCDC"
+        depends on FB_SH_MOBILE_LCDC
+        default y
+        ---help---
+          Enable MERAM support for the SH-Mobile LCD controller.
+
+          This will allow for caching of the framebuffer to provide more
+          reliable access under heavy main memory bus traffic situations.
+          Up to 4 memory channels can be configured, allowing 4 RGB or
+          2 YCbCr framebuffers to be configured.
+
 config FB_TMIO
         tristate "Toshiba Mobile IO FrameBuffer support"
         depends on FB && MFD_CORE
@@ -2246,29 +2266,43 @@ config FB_METRONOME
 config FB_MB862XX
         tristate "Fujitsu MB862xx GDC support"
         depends on FB
+        depends on PCI || (OF && PPC)
         select FB_CFB_FILLRECT
         select FB_CFB_COPYAREA
         select FB_CFB_IMAGEBLIT
         ---help---
           Frame buffer driver for Fujitsu Carmine/Coral-P(A)/Lime controllers.
 
+choice
+        prompt "GDC variant"
+        depends on FB_MB862XX
+
 config FB_MB862XX_PCI_GDC
         bool "Carmine/Coral-P(A) GDC"
-        depends on PCI && FB_MB862XX
+        depends on PCI
         ---help---
           This enables framebuffer support for Fujitsu Carmine/Coral-P(A)
           PCI graphics controller devices.
 
 config FB_MB862XX_LIME
         bool "Lime GDC"
-        depends on FB_MB862XX
-        depends on OF && !FB_MB862XX_PCI_GDC
-        depends on PPC
+        depends on OF && PPC
         select FB_FOREIGN_ENDIAN
         select FB_LITTLE_ENDIAN
         ---help---
           Framebuffer support for Fujitsu Lime GDC on host CPU bus.
 
+endchoice
+
+config FB_MB862XX_I2C
+        bool "Support I2C bus on MB862XX GDC"
+        depends on FB_MB862XX && I2C
+        default y
+        help
+          Selecting this option adds Coral-P(A)/Lime GDC I2C bus adapter
+          driver to support accessing I2C devices on controller's I2C bus.
+          These are usually some video decoder chips.
+
 config FB_EP93XX
         tristate "EP93XX frame buffer support"
         depends on FB && ARCH_EP93XX
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index 2ea44b6625fe..8b83129e209c 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -130,6 +130,7 @@ obj-$(CONFIG_FB_UDL)		  += udlfb.o
 obj-$(CONFIG_FB_XILINX)           += xilinxfb.o
 obj-$(CONFIG_SH_MIPI_DSI)         += sh_mipi_dsi.o
 obj-$(CONFIG_FB_SH_MOBILE_HDMI)   += sh_mobile_hdmi.o
+obj-$(CONFIG_FB_SH_MOBILE_MERAM)  += sh_mobile_meram.o
 obj-$(CONFIG_FB_SH_MOBILE_LCDC)   += sh_mobile_lcdcfb.o
 obj-$(CONFIG_FB_OMAP)             += omap/
 obj-y                             += omap2/
diff --git a/drivers/video/amifb.c b/drivers/video/amifb.c
index e5d6b56d4447..5ea6596dd824 100644
--- a/drivers/video/amifb.c
+++ b/drivers/video/amifb.c
@@ -2224,22 +2224,23 @@ static int amifb_ioctl(struct fb_info *info,
          * Allocate, Clear and Align a Block of Chip Memory
          */
 
-static u_long unaligned_chipptr = 0;
+static void *aligned_chipptr;
 
 static inline u_long __init chipalloc(u_long size)
 {
-        size += PAGE_SIZE-1;
-        if (!(unaligned_chipptr = (u_long)amiga_chip_alloc(size,
-                                                           "amifb [RAM]")))
-                panic("No Chip RAM for frame buffer");
-        memset((void *)unaligned_chipptr, 0, size);
-        return PAGE_ALIGN(unaligned_chipptr);
+        aligned_chipptr = amiga_chip_alloc(size, "amifb [RAM]");
+        if (!aligned_chipptr) {
+                pr_err("amifb: No Chip RAM for frame buffer");
+                return 0;
+        }
+        memset(aligned_chipptr, 0, size);
+        return (u_long)aligned_chipptr;
 }
 
 static inline void chipfree(void)
 {
-        if (unaligned_chipptr)
-                amiga_chip_free((void *)unaligned_chipptr);
+        if (aligned_chipptr)
+                amiga_chip_free(aligned_chipptr);
 }
 
 
@@ -2295,7 +2296,7 @@ default_chipset:
                             defmode = amiga_vblank == 50 ? DEFMODE_PAL
                                                          : DEFMODE_NTSC;
                         if (amiga_chip_avail()-CHIPRAM_SAFETY_LIMIT >
-                            VIDEOMEMSIZE_ECS_1M)
+                            VIDEOMEMSIZE_ECS_2M)
                                 fb_info.fix.smem_len = VIDEOMEMSIZE_ECS_2M;
                         else
                                 fb_info.fix.smem_len = VIDEOMEMSIZE_ECS_1M;
@@ -2312,7 +2313,7 @@ default_chipset:
                         maxfmode = TAG_FMODE_4;
                         defmode = DEFMODE_AGA;
                         if (amiga_chip_avail()-CHIPRAM_SAFETY_LIMIT >
-                            VIDEOMEMSIZE_AGA_1M)
+                            VIDEOMEMSIZE_AGA_2M)
                                 fb_info.fix.smem_len = VIDEOMEMSIZE_AGA_2M;
                         else
                                 fb_info.fix.smem_len = VIDEOMEMSIZE_AGA_1M;
@@ -2385,6 +2386,10 @@ default_chipset:
                             DUMMYSPRITEMEMSIZE+
                             COPINITSIZE+
                             4*COPLISTSIZE);
+        if (!chipptr) {
+                err = -ENOMEM;
+                goto amifb_error;
+        }
 
         assignchunk(videomemory, u_long, chipptr, fb_info.fix.smem_len);
         assignchunk(spritememory, u_long, chipptr, SPRITEMEMSIZE);
diff --git a/drivers/video/backlight/adp5520_bl.c b/drivers/video/backlight/adp5520_bl.c
index af3119707dbf..d1aee730d7d8 100644
--- a/drivers/video/backlight/adp5520_bl.c
+++ b/drivers/video/backlight/adp5520_bl.c
@@ -211,8 +211,12 @@ static ssize_t adp5520_bl_daylight_max_store(struct device *dev,
                         const char *buf, size_t count)
 {
         struct adp5520_bl *data = dev_get_drvdata(dev);
+        int ret;
+
+        ret = strict_strtoul(buf, 10, &data->cached_daylight_max);
+        if (ret < 0)
+                return ret;
 
-        strict_strtoul(buf, 10, &data->cached_daylight_max);
         return adp5520_store(dev, buf, count, ADP5520_DAYLIGHT_MAX);
 }
 static DEVICE_ATTR(daylight_max, 0664, adp5520_bl_daylight_max_show,
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 8b7d47386f39..fcdac872522d 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -899,7 +899,7 @@ static struct fb_ops da8xx_fb_ops = {
         .fb_blank = cfb_blank,
 };
 
-static int __init fb_probe(struct platform_device *device)
+static int __devinit fb_probe(struct platform_device *device)
 {
         struct da8xx_lcdc_platform_data *fb_pdata =
                                                 device->dev.platform_data;
@@ -1165,7 +1165,7 @@ static int fb_resume(struct platform_device *dev)
 
 static struct platform_driver da8xx_fb_driver = {
         .probe = fb_probe,
-        .remove = fb_remove,
+        .remove = __devexit_p(fb_remove),
         .suspend = fb_suspend,
         .resume = fb_resume,
         .driver = {
diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index 4eb38db36e4b..fb205843c2c7 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -242,9 +242,9 @@ static int set_system(const struct dmi_system_id *id)
                 return 0;
         }
 
-        printk(KERN_INFO "efifb: dmi detected %s - framebuffer at %p "
+        printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x "
                          "(%dx%d, stride %d)\n", id->ident,
-                         (void *)screen_info.lfb_base, screen_info.lfb_width,
+                         screen_info.lfb_base, screen_info.lfb_width,
                          screen_info.lfb_height, screen_info.lfb_linelength);
 
 
diff --git a/drivers/video/mb862xx/Makefile b/drivers/video/mb862xx/Makefile
index d7777714166b..5707ed0e31a7 100644
--- a/drivers/video/mb862xx/Makefile
+++ b/drivers/video/mb862xx/Makefile
@@ -2,4 +2,7 @@
 # Makefile for the MB862xx framebuffer driver
 #
 
-obj-$(CONFIG_FB_MB862XX)        := mb862xxfb.o mb862xxfb_accel.o
+obj-$(CONFIG_FB_MB862XX) += mb862xxfb.o
+
+mb862xxfb-y := mb862xxfbdrv.o mb862xxfb_accel.o
+mb862xxfb-$(CONFIG_FB_MB862XX_I2C) += mb862xx-i2c.o
diff --git a/drivers/video/mb862xx/mb862xx-i2c.c b/drivers/video/mb862xx/mb862xx-i2c.c
new file mode 100644
index 000000000000..cb77d3b4657d
--- /dev/null
+++ b/drivers/video/mb862xx/mb862xx-i2c.c
@@ -0,0 +1,177 @@
+/*
+ * Coral-P(A)/Lime I2C adapter driver
+ *
+ * (C) 2011 DENX Software Engineering, Anatolij Gustschin <agust@denx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/fb.h>
+#include <linux/i2c.h>
+#include <linux/io.h>
+
+#include "mb862xxfb.h"
+#include "mb862xx_reg.h"
+
+static int mb862xx_i2c_wait_event(struct i2c_adapter *adap)
+{
+        struct mb862xxfb_par *par = adap->algo_data;
+        u32 reg;
+
+        do {
+                udelay(1);
+                reg = inreg(i2c, GC_I2C_BCR);
+                if (reg & (I2C_INT | I2C_BER))
+                        break;
+        } while (1);
+
+        return (reg & I2C_BER) ? 0 : 1;
+}
+
+static int mb862xx_i2c_do_address(struct i2c_adapter *adap, int addr)
+{
+        struct mb862xxfb_par *par = adap->algo_data;
+
+        outreg(i2c, GC_I2C_DAR, addr);
+        outreg(i2c, GC_I2C_CCR, I2C_CLOCK_AND_ENABLE);
+        outreg(i2c, GC_I2C_BCR, par->i2c_rs ? I2C_REPEATED_START : I2C_START);
+        if (!mb862xx_i2c_wait_event(adap))
+                return -EIO;
+        par->i2c_rs = !(inreg(i2c, GC_I2C_BSR) & I2C_LRB);
+        return par->i2c_rs;
+}
+
+static int mb862xx_i2c_write_byte(struct i2c_adapter *adap, u8 byte)
+{
+        struct mb862xxfb_par *par = adap->algo_data;
+
+        outreg(i2c, GC_I2C_DAR, byte);
+        outreg(i2c, GC_I2C_BCR, I2C_START);
+        if (!mb862xx_i2c_wait_event(adap))
+                return -EIO;
+        return !(inreg(i2c, GC_I2C_BSR) & I2C_LRB);
+}
+
+static int mb862xx_i2c_read_byte(struct i2c_adapter *adap, u8 *byte, int last)
+{
+        struct mb862xxfb_par *par = adap->algo_data;
+
+        outreg(i2c, GC_I2C_BCR, I2C_START | (last ? 0 : I2C_ACK));
+        if (!mb862xx_i2c_wait_event(adap))
+                return 0;
+        *byte = inreg(i2c, GC_I2C_DAR);
+        return 1;
+}
+
+void mb862xx_i2c_stop(struct i2c_adapter *adap)
+{
+        struct mb862xxfb_par *par = adap->algo_data;
+
+        outreg(i2c, GC_I2C_BCR, I2C_STOP);
+        outreg(i2c, GC_I2C_CCR, I2C_DISABLE);
+        par->i2c_rs = 0;
+}
+
+static int mb862xx_i2c_read(struct i2c_adapter *adap, struct i2c_msg *m)
+{
+        int i, ret = 0;
+        int last = m->len - 1;
+
+        for (i = 0; i < m->len; i++) {
+                if (!mb862xx_i2c_read_byte(adap, &m->buf[i], i == last)) {
+                        ret = -EIO;
+                        break;
+                }
+        }
+        return ret;
+}
+
+static int mb862xx_i2c_write(struct i2c_adapter *adap, struct i2c_msg *m)
+{
+        int i, ret = 0;
+
+        for (i = 0; i < m->len; i++) {
+                if (!mb862xx_i2c_write_byte(adap, m->buf[i])) {
+                        ret = -EIO;
+                        break;
+                }
+        }
+        return ret;
+}
+
+static int mb862xx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
+                        int num)
+{
+        struct mb862xxfb_par *par = adap->algo_data;
+        struct i2c_msg *m;
+        int addr;
+        int i = 0, err = 0;
+
+        dev_dbg(par->dev, "%s: %d msgs\n", __func__, num);
+
+        for (i = 0; i < num; i++) {
+                m = &msgs[i];
+                if (!m->len) {
+                        dev_dbg(par->dev, "%s: null msgs\n", __func__);
+                        continue;
+                }
+                addr = m->addr;
+                if (m->flags & I2C_M_RD)
+                        addr |= 1;
+
+                err = mb862xx_i2c_do_address(adap, addr);
+                if (err < 0)
+                        break;
+                if (m->flags & I2C_M_RD)
+                        err = mb862xx_i2c_read(adap, m);
+                else
+                        err = mb862xx_i2c_write(adap, m);
+        }
+
+        if (i)
+                mb862xx_i2c_stop(adap);
+
+        return (err < 0) ? err : i;
+}
+
+static u32 mb862xx_func(struct i2c_adapter *adap)
+{
+        return I2C_FUNC_SMBUS_BYTE_DATA;
+}
+
+static const struct i2c_algorithm mb862xx_algo = {
+        .master_xfer    = mb862xx_xfer,
+        .functionality  = mb862xx_func,
+};
+
+static struct i2c_adapter mb862xx_i2c_adapter = {
+        .name           = "MB862xx I2C adapter",
+        .algo           = &mb862xx_algo,
+        .owner          = THIS_MODULE,
+};
+
+int mb862xx_i2c_init(struct mb862xxfb_par *par)
+{
+        int ret;
+
+        mb862xx_i2c_adapter.algo_data = par;
+        par->adap = &mb862xx_i2c_adapter;
+
+        ret = i2c_add_adapter(par->adap);
+        if (ret < 0) {
+                dev_err(par->dev, "failed to add %s\n",
+                        mb862xx_i2c_adapter.name);
+        }
+        return ret;
+}
+
+void mb862xx_i2c_exit(struct mb862xxfb_par *par)
+{
+        if (par->adap) {
+                i2c_del_adapter(par->adap);
+                par->adap = NULL;
+        }
+}
diff --git a/drivers/video/mb862xx/mb862xx_reg.h b/drivers/video/mb862xx/mb862xx_reg.h
index 2ba65e118500..9df48b8edc94 100644
--- a/drivers/video/mb862xx/mb862xx_reg.h
+++ b/drivers/video/mb862xx/mb862xx_reg.h
@@ -5,11 +5,8 @@
 #ifndef _MB862XX_REG_H
 #define _MB862XX_REG_H
 
-#ifdef MB862XX_MMIO_BOTTOM
-#define MB862XX_MMIO_BASE       0x03fc0000
-#else
 #define MB862XX_MMIO_BASE       0x01fc0000
-#endif
+#define MB862XX_MMIO_HIGH_BASE  0x03fc0000
 #define MB862XX_I2C_BASE        0x0000c000
 #define MB862XX_DISP_BASE       0x00010000
 #define MB862XX_CAP_BASE        0x00018000
@@ -23,6 +20,7 @@
 #define GC_IMASK                0x00000024
 #define GC_SRST                 0x0000002c
 #define GC_CCF                  0x00000038
+#define GC_RSW                  0x0000005c
 #define GC_CID                  0x000000f0
 #define GC_REVISION             0x00000084
 
@@ -53,10 +51,16 @@
 #define GC_L0OA0                0x00000024
 #define GC_L0DA0                0x00000028
 #define GC_L0DY_L0DX            0x0000002c
+#define GC_L1M                  0x00000030
+#define GC_L1DA                 0x00000034
 #define GC_DCM1                 0x00000100
 #define GC_L0EM                 0x00000110
 #define GC_L0WY_L0WX            0x00000114
 #define GC_L0WH_L0WW            0x00000118
+#define GC_L1EM                 0x00000120
+#define GC_L1WY_L1WX            0x00000124
+#define GC_L1WH_L1WW            0x00000128
+#define GC_DLS                  0x00000180
 #define GC_DCM2                 0x00000104
 #define GC_DCM3                 0x00000108
 #define GC_CPM_CUTC             0x000000a0
@@ -68,6 +72,11 @@
 
 #define GC_CPM_CEN0             0x00100000
 #define GC_CPM_CEN1             0x00200000
+#define GC_DCM1_DEN             0x80000000
+#define GC_DCM1_L1E             0x00020000
+#define GC_L1M_16               0x80000000
+#define GC_L1M_YC               0x40000000
+#define GC_L1M_CS               0x20000000
 
 #define GC_DCM01_ESY            0x00000004
 #define GC_DCM01_SC             0x00003f00
@@ -79,9 +88,50 @@
 #define GC_L0M_L0C_16           0x80000000
 #define GC_L0EM_L0EC_24         0x40000000
 #define GC_L0M_L0W_UNIT         64
+#define GC_L1EM_DM              0x02000000
 
 #define GC_DISP_REFCLK_400      400
 
+/* I2C */
+#define GC_I2C_BSR              0x00000000      /* BSR */
+#define GC_I2C_BCR              0x00000004      /* BCR */
+#define GC_I2C_CCR              0x00000008      /* CCR */
+#define GC_I2C_ADR              0x0000000C      /* ADR */
+#define GC_I2C_DAR              0x00000010      /* DAR */
+
+#define I2C_DISABLE             0x00000000
+#define I2C_STOP                0x00000000
+#define I2C_START               0x00000010
+#define I2C_REPEATED_START      0x00000030
+#define I2C_CLOCK_AND_ENABLE    0x0000003f
+#define I2C_READY               0x01
+#define I2C_INT                 0x01
+#define I2C_INTE                0x02
+#define I2C_ACK                 0x08
+#define I2C_BER                 0x80
+#define I2C_BEIE                0x40
+#define I2C_TRX                 0x80
+#define I2C_LRB                 0x10
+
+/* Capture registers and bits */
+#define GC_CAP_VCM              0x00000000
+#define GC_CAP_CSC              0x00000004
+#define GC_CAP_VCS              0x00000008
+#define GC_CAP_CBM              0x00000010
+#define GC_CAP_CBOA             0x00000014
+#define GC_CAP_CBLA             0x00000018
+#define GC_CAP_IMG_START        0x0000001C
+#define GC_CAP_IMG_END          0x00000020
+#define GC_CAP_CMSS             0x00000048
+#define GC_CAP_CMDS             0x0000004C
+
+#define GC_VCM_VIE              0x80000000
+#define GC_VCM_CM               0x03000000
+#define GC_VCM_VS_PAL           0x00000002
+#define GC_CBM_OO               0x80000000
+#define GC_CBM_HRV              0x00000010
+#define GC_CBM_CBST             0x00000001
+
 /* Carmine specific */
 #define MB86297_DRAW_BASE               0x00020000
 #define MB86297_DISP0_BASE              0x00100000
diff --git a/drivers/video/mb862xx/mb862xxfb.h b/drivers/video/mb862xx/mb862xxfb.h
index d7e7cb76bbf2..8550630c1e01 100644
--- a/drivers/video/mb862xx/mb862xxfb.h
+++ b/drivers/video/mb862xx/mb862xxfb.h
@@ -1,6 +1,26 @@
 #ifndef __MB862XX_H__
 #define __MB862XX_H__
 
+struct mb862xx_l1_cfg {
+        unsigned short sx;
+        unsigned short sy;
+        unsigned short sw;
+        unsigned short sh;
+        unsigned short dx;
+        unsigned short dy;
+        unsigned short dw;
+        unsigned short dh;
+        int mirror;
+};
+
+#define MB862XX_BASE            'M'
+#define MB862XX_L1_GET_CFG      _IOR(MB862XX_BASE, 0, struct mb862xx_l1_cfg*)
+#define MB862XX_L1_SET_CFG      _IOW(MB862XX_BASE, 1, struct mb862xx_l1_cfg*)
+#define MB862XX_L1_ENABLE       _IOW(MB862XX_BASE, 2, int)
+#define MB862XX_L1_CAP_CTL      _IOW(MB862XX_BASE, 3, int)
+
+#ifdef __KERNEL__
+
 #define PCI_VENDOR_ID_FUJITSU_LIMITED   0x10cf
 #define PCI_DEVICE_ID_FUJITSU_CORALP    0x2019
 #define PCI_DEVICE_ID_FUJITSU_CORALPA   0x201e
@@ -38,6 +58,8 @@ struct mb862xxfb_par {
         void __iomem            *mmio_base;     /* remapped registers */
         size_t                  mapped_vram;    /* length of remapped vram */
         size_t                  mmio_len;       /* length of register region */
+        unsigned long           cap_buf;        /* capture buffers offset */
+        size_t                  cap_len;        /* length of capture buffers */
 
         void __iomem            *host;          /* relocatable reg. bases */
         void __iomem            *i2c;
@@ -57,11 +79,23 @@ struct mb862xxfb_par {
         unsigned int            refclk;         /* disp. reference clock */
         struct mb862xx_gc_mode  *gc_mode;       /* GDC mode init data */
         int                     pre_init;       /* don't init display if 1 */
+        struct i2c_adapter      *adap;          /* GDC I2C bus adapter */
+        int                     i2c_rs;
+
+        struct mb862xx_l1_cfg   l1_cfg;
+        int                     l1_stride;
 
         u32                     pseudo_palette[16];
 };
 
 extern void mb862xxfb_init_accel(struct fb_info *info, int xres);
+#ifdef CONFIG_FB_MB862XX_I2C
+extern int mb862xx_i2c_init(struct mb862xxfb_par *par);
+extern void mb862xx_i2c_exit(struct mb862xxfb_par *par);
+#else
+static inline int mb862xx_i2c_init(struct mb862xxfb_par *par) { return 0; }
+static inline void mb862xx_i2c_exit(struct mb862xxfb_par *par) { }
+#endif
 
 #if defined(CONFIG_FB_MB862XX_LIME) && defined(CONFIG_FB_MB862XX_PCI_GDC)
 #error  "Select Lime GDC or CoralP/Carmine support, but not both together"
@@ -82,4 +116,6 @@ extern void mb862xxfb_init_accel(struct fb_info *info, int xres);
 
 #define pack(a, b)      (((a) << 16) | (b))
 
+#endif /* __KERNEL__ */
+
 #endif
diff --git a/drivers/video/mb862xx/mb862xxfb.c b/drivers/video/mb862xx/mb862xxfbdrv.c
index c76e663a6cd4..ea39336addfb 100644
--- a/drivers/video/mb862xx/mb862xxfb.c
+++ b/drivers/video/mb862xx/mb862xxfbdrv.c
@@ -27,7 +27,7 @@
 
 #define NR_PALETTE              256
 #define MB862XX_MEM_SIZE        0x1000000
-#define CORALP_MEM_SIZE         0x4000000
+#define CORALP_MEM_SIZE         0x2000000
 #define CARMINE_MEM_SIZE        0x8000000
 #define DRV_NAME                "mb862xxfb"
 
@@ -309,6 +309,97 @@ static int mb862xxfb_blank(int mode, struct fb_info *fbi)
         return 0;
 }
 
+static int mb862xxfb_ioctl(struct fb_info *fbi, unsigned int cmd,
+                           unsigned long arg)
+{
+        struct mb862xxfb_par *par = fbi->par;
+        struct mb862xx_l1_cfg *l1_cfg = &par->l1_cfg;
+        void __user *argp = (void __user *)arg;
+        int *enable;
+        u32 l1em = 0;
+
+        switch (cmd) {
+        case MB862XX_L1_GET_CFG:
+                if (copy_to_user(argp, l1_cfg, sizeof(*l1_cfg)))
+                        return -EFAULT;
+                break;
+        case MB862XX_L1_SET_CFG:
+                if (copy_from_user(l1_cfg, argp, sizeof(*l1_cfg)))
+                        return -EFAULT;
+                if ((l1_cfg->sw >= l1_cfg->dw) && (l1_cfg->sh >= l1_cfg->dh)) {
+                        /* downscaling */
+                        outreg(cap, GC_CAP_CSC,
+                                pack((l1_cfg->sh << 11) / l1_cfg->dh,
+                                     (l1_cfg->sw << 11) / l1_cfg->dw));
+                        l1em = inreg(disp, GC_L1EM);
+                        l1em &= ~GC_L1EM_DM;
+                } else if ((l1_cfg->sw <= l1_cfg->dw) &&
+                           (l1_cfg->sh <= l1_cfg->dh)) {
+                        /* upscaling */
+                        outreg(cap, GC_CAP_CSC,
+                                pack((l1_cfg->sh << 11) / l1_cfg->dh,
+                                     (l1_cfg->sw << 11) / l1_cfg->dw));
+                        outreg(cap, GC_CAP_CMSS,
+                                pack(l1_cfg->sw >> 1, l1_cfg->sh));
+                        outreg(cap, GC_CAP_CMDS,
+                                pack(l1_cfg->dw >> 1, l1_cfg->dh));
+                        l1em = inreg(disp, GC_L1EM);
+                        l1em |= GC_L1EM_DM;
+                }
+
+                if (l1_cfg->mirror) {
+                        outreg(cap, GC_CAP_CBM,
+                                inreg(cap, GC_CAP_CBM) | GC_CBM_HRV);
+                        l1em |= l1_cfg->dw * 2 - 8;
+                } else {
+                        outreg(cap, GC_CAP_CBM,
+                                inreg(cap, GC_CAP_CBM) & ~GC_CBM_HRV);
+                        l1em &= 0xffff0000;
+                }
+                outreg(disp, GC_L1EM, l1em);
+                break;
+        case MB862XX_L1_ENABLE:
+                enable = (int *)arg;
+                if (*enable) {
+                        outreg(disp, GC_L1DA, par->cap_buf);
+                        outreg(cap, GC_CAP_IMG_START,
+                                pack(l1_cfg->sy >> 1, l1_cfg->sx));
+                        outreg(cap, GC_CAP_IMG_END,
+                                pack(l1_cfg->sh, l1_cfg->sw));
+                        outreg(disp, GC_L1M, GC_L1M_16 | GC_L1M_YC | GC_L1M_CS |
+                                             (par->l1_stride << 16));
+                        outreg(disp, GC_L1WY_L1WX,
+                                pack(l1_cfg->dy, l1_cfg->dx));
+                        outreg(disp, GC_L1WH_L1WW,
+                                pack(l1_cfg->dh - 1, l1_cfg->dw));
+                        outreg(disp, GC_DLS, 1);
+                        outreg(cap, GC_CAP_VCM,
+                                GC_VCM_VIE | GC_VCM_CM | GC_VCM_VS_PAL);
+                        outreg(disp, GC_DCM1, inreg(disp, GC_DCM1) |
+                                              GC_DCM1_DEN | GC_DCM1_L1E);
+                } else {
+                        outreg(cap, GC_CAP_VCM,
+                                inreg(cap, GC_CAP_VCM) & ~GC_VCM_VIE);
+                        outreg(disp, GC_DCM1,
+                                inreg(disp, GC_DCM1) & ~GC_DCM1_L1E);
+                }
+                break;
+        case MB862XX_L1_CAP_CTL:
+                enable = (int *)arg;
+                if (*enable) {
+                        outreg(cap, GC_CAP_VCM,
+                                inreg(cap, GC_CAP_VCM) | GC_VCM_VIE);
+                } else {
+                        outreg(cap, GC_CAP_VCM,
+                                inreg(cap, GC_CAP_VCM) & ~GC_VCM_VIE);
+                }
+                break;
+        default:
+                return -EINVAL;
+        }
+        return 0;
+}
+
 /* framebuffer ops */
 static struct fb_ops mb862xxfb_ops = {
         .owner          = THIS_MODULE,
@@ -320,6 +411,7 @@ static struct fb_ops mb862xxfb_ops = {
         .fb_fillrect    = cfb_fillrect,
         .fb_copyarea    = cfb_copyarea,
         .fb_imageblit   = cfb_imageblit,
+        .fb_ioctl       = mb862xxfb_ioctl,
 };
 
 /* initialize fb_info data */
@@ -328,6 +420,7 @@ static int mb862xxfb_init_fbinfo(struct fb_info *fbi)
         struct mb862xxfb_par *par = fbi->par;
         struct mb862xx_gc_mode *mode = par->gc_mode;
         unsigned long reg;
+        int stride;
 
         fbi->fbops = &mb862xxfb_ops;
         fbi->pseudo_palette = par->pseudo_palette;
@@ -336,7 +429,6 @@ static int mb862xxfb_init_fbinfo(struct fb_info *fbi)
 
         strcpy(fbi->fix.id, DRV_NAME);
         fbi->fix.smem_start = (unsigned long)par->fb_base_phys;
-        fbi->fix.smem_len = par->mapped_vram;
         fbi->fix.mmio_start = (unsigned long)par->mmio_base_phys;
         fbi->fix.mmio_len = par->mmio_len;
         fbi->fix.accel = FB_ACCEL_NONE;
@@ -420,6 +512,28 @@ static int mb862xxfb_init_fbinfo(struct fb_info *fbi)
                          FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
         fbi->fix.line_length = (fbi->var.xres_virtual *
                                 fbi->var.bits_per_pixel) / 8;
+        fbi->fix.smem_len = fbi->fix.line_length * fbi->var.yres_virtual;
+
+        /*
+         * reserve space for capture buffers and two cursors
+         * at the end of vram: 720x576 * 2 * 2.2 + 64x64 * 16.
+         */
+        par->cap_buf = par->mapped_vram - 0x1bd800 - 0x10000;
+        par->cap_len = 0x1bd800;
+        par->l1_cfg.sx = 0;
+        par->l1_cfg.sy = 0;
+        par->l1_cfg.sw = 720;
+        par->l1_cfg.sh = 576;
+        par->l1_cfg.dx = 0;
+        par->l1_cfg.dy = 0;
+        par->l1_cfg.dw = 720;
+        par->l1_cfg.dh = 576;
+        stride = par->l1_cfg.sw * (fbi->var.bits_per_pixel / 8);
+        par->l1_stride = stride / 64 + ((stride % 64) ? 1 : 0);
+        outreg(cap, GC_CAP_CBM, GC_CBM_OO | GC_CBM_CBST |
+                                (par->l1_stride << 16));
+        outreg(cap, GC_CAP_CBOA, par->cap_buf);
+        outreg(cap, GC_CAP_CBLA, par->cap_buf + par->cap_len);
         return 0;
 }
 
@@ -742,22 +856,38 @@ static int coralp_init(struct mb862xxfb_par *par)
 
         par->refclk = GC_DISP_REFCLK_400;
 
+        if (par->mapped_vram >= 0x2000000) {
+                /* relocate gdc registers space */
+                writel(1, par->fb_base + MB862XX_MMIO_BASE + GC_RSW);
+                udelay(1); /* wait at least 20 bus cycles */
+        }
+
         ver = inreg(host, GC_CID);
         cn = (ver & GC_CID_CNAME_MSK) >> 8;
         ver = ver & GC_CID_VERSION_MSK;
         if (cn == 3) {
+                unsigned long reg;
+
                 dev_info(par->dev, "Fujitsu Coral-%s GDC Rev.%d found\n",\
                          (ver == 6) ? "P" : (ver == 8) ? "PA" : "?",
                          par->pdev->revision);
-                outreg(host, GC_CCF, GC_CCF_CGE_166 | GC_CCF_COT_133);
-                udelay(200);
-                outreg(host, GC_MMR, GC_MMR_CORALP_EVB_VAL);
-                udelay(10);
+                reg = inreg(disp, GC_DCM1);
+                if (reg & GC_DCM01_DEN && reg & GC_DCM01_L0E)
+                        par->pre_init = 1;
+
+                if (!par->pre_init) {
+                        outreg(host, GC_CCF, GC_CCF_CGE_166 | GC_CCF_COT_133);
+                        udelay(200);
+                        outreg(host, GC_MMR, GC_MMR_CORALP_EVB_VAL);
+                        udelay(10);
+                }
                 /* Clear interrupt status */
                 outreg(host, GC_IST, 0);
         } else {
                 return -ENODEV;
         }
+
+        mb862xx_i2c_init(par);
         return 0;
 }
 
@@ -899,7 +1029,13 @@ static int __devinit mb862xx_pci_probe(struct pci_dev *pdev,
         case PCI_DEVICE_ID_FUJITSU_CORALPA:
                 par->fb_base_phys = pci_resource_start(par->pdev, 0);
                 par->mapped_vram = CORALP_MEM_SIZE;
-                par->mmio_base_phys = par->fb_base_phys + MB862XX_MMIO_BASE;
+                if (par->mapped_vram >= 0x2000000) {
+                        par->mmio_base_phys = par->fb_base_phys +
+                                              MB862XX_MMIO_HIGH_BASE;
+                } else {
+                        par->mmio_base_phys = par->fb_base_phys +
+                                              MB862XX_MMIO_BASE;
+                }
                 par->mmio_len = MB862XX_MMIO_SIZE;
                 par->type = BT_CORALP;
                 break;
@@ -1009,6 +1145,8 @@ static void __devexit mb862xx_pci_remove(struct pci_dev *pdev)
                 outreg(host, GC_IMASK, 0);
         }
 
+        mb862xx_i2c_exit(par);
+
         device_remove_file(&pdev->dev, &dev_attr_dispregs);
 
         pci_set_drvdata(pdev, NULL);
diff --git a/drivers/video/omap/dispc.c b/drivers/video/omap/dispc.c
index 529483467abf..0ccd7adf47bb 100644
--- a/drivers/video/omap/dispc.c
+++ b/drivers/video/omap/dispc.c
@@ -922,14 +922,14 @@ static int get_dss_clocks(void)
                 return PTR_ERR(dispc.dss_ick);
         }
 
-        dispc.dss1_fck = clk_get(&dispc.fbdev->dssdev->dev, "dss1_fck");
+        dispc.dss1_fck = clk_get(&dispc.fbdev->dssdev->dev, "fck");
         if (IS_ERR(dispc.dss1_fck)) {
                 dev_err(dispc.fbdev->dev, "can't get dss1_fck\n");
                 clk_put(dispc.dss_ick);
                 return PTR_ERR(dispc.dss1_fck);
         }
 
-        dispc.dss_54m_fck = clk_get(&dispc.fbdev->dssdev->dev, "tv_fck");
+        dispc.dss_54m_fck = clk_get(&dispc.fbdev->dssdev->dev, "tv_clk");
         if (IS_ERR(dispc.dss_54m_fck)) {
                 dev_err(dispc.fbdev->dev, "can't get tv_fck\n");
                 clk_put(dispc.dss_ick);
diff --git a/drivers/video/omap/omapfb_main.c b/drivers/video/omap/omapfb_main.c
index e264efd0278f..b3ddd743d8a6 100644
--- a/drivers/video/omap/omapfb_main.c
+++ b/drivers/video/omap/omapfb_main.c
@@ -90,7 +90,7 @@ static void omapdss_release(struct device *dev)
 
 /* dummy device for clocks */
 static struct platform_device omapdss_device = {
-        .name           = "omapdss",
+        .name           = "omapdss_dss",
         .id             = -1,
         .dev            = {
                 .release = omapdss_release,
diff --git a/drivers/video/omap/rfbi.c b/drivers/video/omap/rfbi.c
index eada9f12efc7..0c6981f1a4a3 100644
--- a/drivers/video/omap/rfbi.c
+++ b/drivers/video/omap/rfbi.c
@@ -90,7 +90,7 @@ static int rfbi_get_clocks(void)
                 return PTR_ERR(rfbi.dss_ick);
         }
 
-        rfbi.dss1_fck = clk_get(&rfbi.fbdev->dssdev->dev, "dss1_fck");
+        rfbi.dss1_fck = clk_get(&rfbi.fbdev->dssdev->dev, "fck");
         if (IS_ERR(rfbi.dss1_fck)) {
                 dev_err(rfbi.fbdev->dev, "can't get dss1_fck\n");
                 clk_put(rfbi.dss_ick);
diff --git a/drivers/video/omap2/Makefile b/drivers/video/omap2/Makefile
index d853d05dad31..5ddef129f798 100644
--- a/drivers/video/omap2/Makefile
+++ b/drivers/video/omap2/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_OMAP2_VRAM) += vram.o
 obj-$(CONFIG_OMAP2_VRFB) += vrfb.o
 
-obj-y += dss/
-obj-y += omapfb/
+obj-$(CONFIG_OMAP2_DSS) += dss/
+obj-$(CONFIG_FB_OMAP2) += omapfb/
 obj-y += displays/
diff --git a/drivers/video/omap2/displays/Kconfig b/drivers/video/omap2/displays/Kconfig
index d18ad6b2372a..609a28073178 100644
--- a/drivers/video/omap2/displays/Kconfig
+++ b/drivers/video/omap2/displays/Kconfig
@@ -3,6 +3,7 @@ menu "OMAP2/3 Display Device Drivers"
 
 config PANEL_GENERIC_DPI
         tristate "Generic DPI Panel"
+        depends on OMAP2_DSS_DPI
         help
           Generic DPI panel driver.
           Supports DVI output for Beagle and OMAP3 SDP.
@@ -11,20 +12,20 @@ config PANEL_GENERIC_DPI
 
 config PANEL_LGPHILIPS_LB035Q02
         tristate "LG.Philips LB035Q02 LCD Panel"
-        depends on OMAP2_DSS && SPI
+        depends on OMAP2_DSS_DPI && SPI
         help
           LCD Panel used on the Gumstix Overo Palo35
 
 config PANEL_SHARP_LS037V7DW01
         tristate "Sharp LS037V7DW01 LCD Panel"
-        depends on OMAP2_DSS
+        depends on OMAP2_DSS_DPI
         select BACKLIGHT_CLASS_DEVICE
         help
           LCD Panel used in TI's SDP3430 and EVM boards
 
 config PANEL_NEC_NL8048HL11_01B
         tristate "NEC NL8048HL11-01B Panel"
-        depends on OMAP2_DSS
+        depends on OMAP2_DSS_DPI
         help
                 This NEC NL8048HL11-01B panel is TFT LCD
                 used in the Zoom2/3/3630 sdp boards.
@@ -37,7 +38,7 @@ config PANEL_TAAL
 
 config PANEL_TPO_TD043MTEA1
         tristate "TPO TD043MTEA1 LCD Panel"
-        depends on OMAP2_DSS && SPI
+        depends on OMAP2_DSS_DPI && SPI
         help
           LCD Panel used in OMAP3 Pandora
 
diff --git a/drivers/video/omap2/displays/panel-acx565akm.c b/drivers/video/omap2/displays/panel-acx565akm.c
index 7e04c921aa2a..dbd59b8e5b36 100644
--- a/drivers/video/omap2/displays/panel-acx565akm.c
+++ b/drivers/video/omap2/displays/panel-acx565akm.c
@@ -30,7 +30,7 @@
 #include <linux/backlight.h>
 #include <linux/fb.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define MIPID_CMD_READ_DISP_ID          0x04
 #define MIPID_CMD_READ_RED              0x06
diff --git a/drivers/video/omap2/displays/panel-generic-dpi.c b/drivers/video/omap2/displays/panel-generic-dpi.c
index 4a9b9ff59467..9c90f75653fb 100644
--- a/drivers/video/omap2/displays/panel-generic-dpi.c
+++ b/drivers/video/omap2/displays/panel-generic-dpi.c
@@ -33,8 +33,9 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <video/omapdss.h>
 
-#include <plat/panel-generic-dpi.h>
+#include <video/omap-panel-generic-dpi.h>
 
 struct panel_config {
         struct omap_video_timings timings;
@@ -181,6 +182,56 @@ static struct panel_config generic_dpi_panels[] = {
                 .power_off_delay        = 0,
                 .name                   = "samsung_lte430wq_f0c",
         },
+
+        /* Seiko 70WVW1TZ3Z3 */
+        {
+                {
+                        .x_res          = 800,
+                        .y_res          = 480,
+
+                        .pixel_clock    = 33000,
+
+                        .hsw            = 128,
+                        .hfp            = 10,
+                        .hbp            = 10,
+
+                        .vsw            = 2,
+                        .vfp            = 4,
+                        .vbp            = 11,
+                },
+                .acbi                   = 0x0,
+                .acb                    = 0x0,
+                .config                 = OMAP_DSS_LCD_TFT | OMAP_DSS_LCD_IVS |
+                                                OMAP_DSS_LCD_IHS,
+                .power_on_delay         = 0,
+                .power_off_delay        = 0,
+                .name                   = "seiko_70wvw1tz3",
+        },
+
+        /* Powertip PH480272T */
+        {
+                {
+                        .x_res          = 480,
+                        .y_res          = 272,
+
+                        .pixel_clock    = 9000,
+
+                        .hsw            = 40,
+                        .hfp            = 2,
+                        .hbp            = 2,
+
+                        .vsw            = 10,
+                        .vfp            = 2,
+                        .vbp            = 2,
+                },
+                .acbi                   = 0x0,
+                .acb                    = 0x0,
+                .config                 = OMAP_DSS_LCD_TFT | OMAP_DSS_LCD_IVS |
+                                          OMAP_DSS_LCD_IHS | OMAP_DSS_LCD_IEO,
+                .power_on_delay         = 0,
+                .power_off_delay        = 0,
+                .name                   = "powertip_ph480272t",
+        },
 };
 
 struct panel_drv_data {
@@ -285,7 +336,7 @@ static int generic_dpi_panel_probe(struct omap_dss_device *dssdev)
         return 0;
 }
 
-static void generic_dpi_panel_remove(struct omap_dss_device *dssdev)
+static void __exit generic_dpi_panel_remove(struct omap_dss_device *dssdev)
 {
         struct panel_drv_data *drv_data = dev_get_drvdata(&dssdev->dev);
 
@@ -358,7 +409,7 @@ static int generic_dpi_panel_check_timings(struct omap_dss_device *dssdev,
 
 static struct omap_dss_driver dpi_driver = {
         .probe          = generic_dpi_panel_probe,
-        .remove         = generic_dpi_panel_remove,
+        .remove         = __exit_p(generic_dpi_panel_remove),
 
         .enable         = generic_dpi_panel_enable,
         .disable        = generic_dpi_panel_disable,
diff --git a/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c b/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c
index 271324db2436..e0eb35be303e 100644
--- a/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c
@@ -21,7 +21,7 @@
 #include <linux/spi/spi.h>
 #include <linux/mutex.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 struct lb035q02_data {
         struct mutex lock;
diff --git a/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c b/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c
index 925e0fadff54..2ba9d0ca187c 100644
--- a/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c
+++ b/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c
@@ -22,7 +22,7 @@
 #include <linux/backlight.h>
 #include <linux/fb.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define LCD_XRES                800
 #define LCD_YRES                480
diff --git a/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c b/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c
index d2b35d2df2a6..ba38b3ad17d6 100644
--- a/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c
@@ -25,7 +25,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 struct sharp_data {
         struct backlight_device *bl;
@@ -120,7 +120,7 @@ static int sharp_ls_panel_probe(struct omap_dss_device *dssdev)
         return 0;
 }
 
-static void sharp_ls_panel_remove(struct omap_dss_device *dssdev)
+static void __exit sharp_ls_panel_remove(struct omap_dss_device *dssdev)
 {
         struct sharp_data *sd = dev_get_drvdata(&dssdev->dev);
         struct backlight_device *bl = sd->bl;
@@ -205,7 +205,7 @@ static int sharp_ls_panel_resume(struct omap_dss_device *dssdev)
 
 static struct omap_dss_driver sharp_ls_driver = {
         .probe          = sharp_ls_panel_probe,
-        .remove         = sharp_ls_panel_remove,
+        .remove         = __exit_p(sharp_ls_panel_remove),
 
         .enable         = sharp_ls_panel_enable,
         .disable        = sharp_ls_panel_disable,
diff --git a/drivers/video/omap2/displays/panel-taal.c b/drivers/video/omap2/displays/panel-taal.c
index adc9900458e1..fdd5d4ae437d 100644
--- a/drivers/video/omap2/displays/panel-taal.c
+++ b/drivers/video/omap2/displays/panel-taal.c
@@ -33,8 +33,8 @@
 #include <linux/regulator/consumer.h>
 #include <linux/mutex.h>
 
-#include <plat/display.h>
-#include <plat/nokia-dsi-panel.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-nokia-dsi.h>
 
 /* DSI Virtual channel. Hardcoded for now. */
 #define TCH 0
@@ -63,12 +63,12 @@
 #define DCS_GET_ID2             0xdb
 #define DCS_GET_ID3             0xdc
 
-#define TAAL_ESD_CHECK_PERIOD   msecs_to_jiffies(5000)
-
 static irqreturn_t taal_te_isr(int irq, void *data);
 static void taal_te_timeout_work_callback(struct work_struct *work);
 static int _taal_enable_te(struct omap_dss_device *dssdev, bool enable);
 
+static int taal_panel_reset(struct omap_dss_device *dssdev);
+
 struct panel_regulator {
         struct regulator *regulator;
         const char *name;
@@ -229,8 +229,14 @@ struct taal_data {
 
         bool intro_printed;
 
-        struct workqueue_struct *esd_wq;
+        struct workqueue_struct *workqueue;
+
         struct delayed_work esd_work;
+        unsigned esd_interval;
+
+        bool ulps_enabled;
+        unsigned ulps_timeout;
+        struct delayed_work ulps_work;
 
         struct panel_config *panel_config;
 };
@@ -242,6 +248,7 @@ static inline struct nokia_dsi_panel_data
 }
 
 static void taal_esd_work(struct work_struct *work);
+static void taal_ulps_work(struct work_struct *work);
 
 static void hw_guard_start(struct taal_data *td, int guard_msec)
 {
@@ -264,7 +271,7 @@ static int taal_dcs_read_1(struct taal_data *td, u8 dcs_cmd, u8 *data)
         int r;
         u8 buf[1];
 
-        r = dsi_vc_dcs_read(td->channel, dcs_cmd, buf, 1);
+        r = dsi_vc_dcs_read(td->dssdev, td->channel, dcs_cmd, buf, 1);
 
         if (r < 0)
                 return r;
@@ -276,7 +283,7 @@ static int taal_dcs_read_1(struct taal_data *td, u8 dcs_cmd, u8 *data)
 
 static int taal_dcs_write_0(struct taal_data *td, u8 dcs_cmd)
 {
-        return dsi_vc_dcs_write(td->channel, &dcs_cmd, 1);
+        return dsi_vc_dcs_write(td->dssdev, td->channel, &dcs_cmd, 1);
 }
 
 static int taal_dcs_write_1(struct taal_data *td, u8 dcs_cmd, u8 param)
@@ -284,7 +291,7 @@ static int taal_dcs_write_1(struct taal_data *td, u8 dcs_cmd, u8 param)
         u8 buf[2];
         buf[0] = dcs_cmd;
         buf[1] = param;
-        return dsi_vc_dcs_write(td->channel, buf, 2);
+        return dsi_vc_dcs_write(td->dssdev, td->channel, buf, 2);
 }
 
 static int taal_sleep_in(struct taal_data *td)
@@ -296,7 +303,7 @@ static int taal_sleep_in(struct taal_data *td)
         hw_guard_wait(td);
 
         cmd = DCS_SLEEP_IN;
-        r = dsi_vc_dcs_write_nosync(td->channel, &cmd, 1);
+        r = dsi_vc_dcs_write_nosync(td->dssdev, td->channel, &cmd, 1);
         if (r)
                 return r;
 
@@ -402,7 +409,7 @@ static int taal_set_update_window(struct taal_data *td,
         buf[3] = (x2 >> 8) & 0xff;
         buf[4] = (x2 >> 0) & 0xff;
 
-        r = dsi_vc_dcs_write_nosync(td->channel, buf, sizeof(buf));
+        r = dsi_vc_dcs_write_nosync(td->dssdev, td->channel, buf, sizeof(buf));
         if (r)
                 return r;
 
@@ -412,15 +419,132 @@ static int taal_set_update_window(struct taal_data *td,
         buf[3] = (y2 >> 8) & 0xff;
         buf[4] = (y2 >> 0) & 0xff;
 
-        r = dsi_vc_dcs_write_nosync(td->channel, buf, sizeof(buf));
+        r = dsi_vc_dcs_write_nosync(td->dssdev, td->channel, buf, sizeof(buf));
         if (r)
                 return r;
 
-        dsi_vc_send_bta_sync(td->channel);
+        dsi_vc_send_bta_sync(td->dssdev, td->channel);
 
         return r;
 }
 
+static void taal_queue_esd_work(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+
+        if (td->esd_interval > 0)
+                queue_delayed_work(td->workqueue, &td->esd_work,
+                                msecs_to_jiffies(td->esd_interval));
+}
+
+static void taal_cancel_esd_work(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+
+        cancel_delayed_work(&td->esd_work);
+}
+
+static void taal_queue_ulps_work(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+
+        if (td->ulps_timeout > 0)
+                queue_delayed_work(td->workqueue, &td->ulps_work,
+                                msecs_to_jiffies(td->ulps_timeout));
+}
+
+static void taal_cancel_ulps_work(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+
+        cancel_delayed_work(&td->ulps_work);
+}
+
+static int taal_enter_ulps(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        struct nokia_dsi_panel_data *panel_data = get_panel_data(dssdev);
+        int r;
+
+        if (td->ulps_enabled)
+                return 0;
+
+        taal_cancel_ulps_work(dssdev);
+
+        r = _taal_enable_te(dssdev, false);
+        if (r)
+                goto err;
+
+        disable_irq(gpio_to_irq(panel_data->ext_te_gpio));
+
+        omapdss_dsi_display_disable(dssdev, false, true);
+
+        td->ulps_enabled = true;
+
+        return 0;
+
+err:
+        dev_err(&dssdev->dev, "enter ULPS failed");
+        taal_panel_reset(dssdev);
+
+        td->ulps_enabled = false;
+
+        taal_queue_ulps_work(dssdev);
+
+        return r;
+}
+
+static int taal_exit_ulps(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        struct nokia_dsi_panel_data *panel_data = get_panel_data(dssdev);
+        int r;
+
+        if (!td->ulps_enabled)
+                return 0;
+
+        r = omapdss_dsi_display_enable(dssdev);
+        if (r)
+                goto err;
+
+        omapdss_dsi_vc_enable_hs(dssdev, td->channel, true);
+
+        r = _taal_enable_te(dssdev, true);
+        if (r)
+                goto err;
+
+        enable_irq(gpio_to_irq(panel_data->ext_te_gpio));
+
+        taal_queue_ulps_work(dssdev);
+
+        td->ulps_enabled = false;
+
+        return 0;
+
+err:
+        dev_err(&dssdev->dev, "exit ULPS failed");
+        r = taal_panel_reset(dssdev);
+
+        enable_irq(gpio_to_irq(panel_data->ext_te_gpio));
+        td->ulps_enabled = false;
+
+        taal_queue_ulps_work(dssdev);
+
+        return r;
+}
+
+static int taal_wake_up(struct omap_dss_device *dssdev)
+{
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+
+        if (td->ulps_enabled)
+                return taal_exit_ulps(dssdev);
+
+        taal_cancel_ulps_work(dssdev);
+        taal_queue_ulps_work(dssdev);
+        return 0;
+}
+
 static int taal_bl_update_status(struct backlight_device *dev)
 {
         struct omap_dss_device *dssdev = dev_get_drvdata(&dev->dev);
@@ -441,9 +565,13 @@ static int taal_bl_update_status(struct backlight_device *dev)
 
         if (td->use_dsi_bl) {
                 if (td->enabled) {
-                        dsi_bus_lock();
-                        r = taal_dcs_write_1(td, DCS_BRIGHTNESS, level);
-                        dsi_bus_unlock();
+                        dsi_bus_lock(dssdev);
+
+                        r = taal_wake_up(dssdev);
+                        if (!r)
+                                r = taal_dcs_write_1(td, DCS_BRIGHTNESS, level);
+
+                        dsi_bus_unlock(dssdev);
                 } else {
                         r = 0;
                 }
@@ -504,9 +632,13 @@ static ssize_t taal_num_errors_show(struct device *dev,
         mutex_lock(&td->lock);
 
         if (td->enabled) {
-                dsi_bus_lock();
-                r = taal_dcs_read_1(td, DCS_READ_NUM_ERRORS, &errors);
-                dsi_bus_unlock();
+                dsi_bus_lock(dssdev);
+
+                r = taal_wake_up(dssdev);
+                if (!r)
+                        r = taal_dcs_read_1(td, DCS_READ_NUM_ERRORS, &errors);
+
+                dsi_bus_unlock(dssdev);
         } else {
                 r = -ENODEV;
         }
@@ -530,9 +662,13 @@ static ssize_t taal_hw_revision_show(struct device *dev,
         mutex_lock(&td->lock);
 
         if (td->enabled) {
-                dsi_bus_lock();
-                r = taal_get_id(td, &id1, &id2, &id3);
-                dsi_bus_unlock();
+                dsi_bus_lock(dssdev);
+
+                r = taal_wake_up(dssdev);
+                if (!r)
+                        r = taal_get_id(td, &id1, &id2, &id3);
+
+                dsi_bus_unlock(dssdev);
         } else {
                 r = -ENODEV;
         }
@@ -579,6 +715,7 @@ static ssize_t store_cabc_mode(struct device *dev,
         struct omap_dss_device *dssdev = to_dss_device(dev);
         struct taal_data *td = dev_get_drvdata(&dssdev->dev);
         int i;
+        int r;
 
         for (i = 0; i < ARRAY_SIZE(cabc_modes); i++) {
                 if (sysfs_streq(cabc_modes[i], buf))
@@ -591,10 +728,19 @@ static ssize_t store_cabc_mode(struct device *dev,
         mutex_lock(&td->lock);
 
         if (td->enabled) {
-                dsi_bus_lock();
-                if (!td->cabc_broken)
-                        taal_dcs_write_1(td, DCS_WRITE_CABC, i);
-                dsi_bus_unlock();
+                dsi_bus_lock(dssdev);
+
+                if (!td->cabc_broken) {
+                        r = taal_wake_up(dssdev);
+                        if (r)
+                                goto err;
+
+                        r = taal_dcs_write_1(td, DCS_WRITE_CABC, i);
+                        if (r)
+                                goto err;
+                }
+
+                dsi_bus_unlock(dssdev);
         }
 
         td->cabc_mode = i;
@@ -602,6 +748,10 @@ static ssize_t store_cabc_mode(struct device *dev,
         mutex_unlock(&td->lock);
 
         return count;
+err:
+        dsi_bus_unlock(dssdev);
+        mutex_unlock(&td->lock);
+        return r;
 }
 
 static ssize_t show_cabc_available_modes(struct device *dev,
@@ -620,18 +770,161 @@ static ssize_t show_cabc_available_modes(struct device *dev,
         return len < PAGE_SIZE ? len : PAGE_SIZE - 1;
 }
 
+static ssize_t taal_store_esd_interval(struct device *dev,
+                struct device_attribute *attr,
+                const char *buf, size_t count)
+{
+        struct omap_dss_device *dssdev = to_dss_device(dev);
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+
+        unsigned long t;
+        int r;
+
+        r = strict_strtoul(buf, 10, &t);
+        if (r)
+                return r;
+
+        mutex_lock(&td->lock);
+        taal_cancel_esd_work(dssdev);
+        td->esd_interval = t;
+        if (td->enabled)
+                taal_queue_esd_work(dssdev);
+        mutex_unlock(&td->lock);
+
+        return count;
+}
+
+static ssize_t taal_show_esd_interval(struct device *dev,
+                struct device_attribute *attr,
+                char *buf)
+{
+        struct omap_dss_device *dssdev = to_dss_device(dev);
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        unsigned t;
+
+        mutex_lock(&td->lock);
+        t = td->esd_interval;
+        mutex_unlock(&td->lock);
+
+        return snprintf(buf, PAGE_SIZE, "%u\n", t);
+}
+
+static ssize_t taal_store_ulps(struct device *dev,
+                struct device_attribute *attr,
+                const char *buf, size_t count)
+{
+        struct omap_dss_device *dssdev = to_dss_device(dev);
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        unsigned long t;
+        int r;
+
+        r = strict_strtoul(buf, 10, &t);
+        if (r)
+                return r;
+
+        mutex_lock(&td->lock);
+
+        if (td->enabled) {
+                dsi_bus_lock(dssdev);
+
+                if (t)
+                        r = taal_enter_ulps(dssdev);
+                else
+                        r = taal_wake_up(dssdev);
+
+                dsi_bus_unlock(dssdev);
+        }
+
+        mutex_unlock(&td->lock);
+
+        if (r)
+                return r;
+
+        return count;
+}
+
+static ssize_t taal_show_ulps(struct device *dev,
+                struct device_attribute *attr,
+                char *buf)
+{
+        struct omap_dss_device *dssdev = to_dss_device(dev);
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        unsigned t;
+
+        mutex_lock(&td->lock);
+        t = td->ulps_enabled;
+        mutex_unlock(&td->lock);
+
+        return snprintf(buf, PAGE_SIZE, "%u\n", t);
+}
+
+static ssize_t taal_store_ulps_timeout(struct device *dev,
+                struct device_attribute *attr,
+                const char *buf, size_t count)
+{
+        struct omap_dss_device *dssdev = to_dss_device(dev);
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        unsigned long t;
+        int r;
+
+        r = strict_strtoul(buf, 10, &t);
+        if (r)
+                return r;
+
+        mutex_lock(&td->lock);
+        td->ulps_timeout = t;
+
+        if (td->enabled) {
+                /* taal_wake_up will restart the timer */
+                dsi_bus_lock(dssdev);
+                r = taal_wake_up(dssdev);
+                dsi_bus_unlock(dssdev);
+        }
+
+        mutex_unlock(&td->lock);
+
+        if (r)
+                return r;
+
+        return count;
+}
+
+static ssize_t taal_show_ulps_timeout(struct device *dev,
+                struct device_attribute *attr,
+                char *buf)
+{
+        struct omap_dss_device *dssdev = to_dss_device(dev);
+        struct taal_data *td = dev_get_drvdata(&dssdev->dev);
+        unsigned t;
+
+        mutex_lock(&td->lock);
+        t = td->ulps_timeout;
+        mutex_unlock(&td->lock);
+
+        return snprintf(buf, PAGE_SIZE, "%u\n", t);
+}
+
 static DEVICE_ATTR(num_dsi_errors, S_IRUGO, taal_num_errors_show, NULL);
 static DEVICE_ATTR(hw_revision, S_IRUGO, taal_hw_revision_show, NULL);
 static DEVICE_ATTR(cabc_mode, S_IRUGO | S_IWUSR,
                 show_cabc_mode, store_cabc_mode);
 static DEVICE_ATTR(cabc_available_modes, S_IRUGO,
                 show_cabc_available_modes, NULL);
+static DEVICE_ATTR(esd_interval, S_IRUGO | S_IWUSR,
+                taal_show_esd_interval, taal_store_esd_interval);
+static DEVICE_ATTR(ulps, S_IRUGO | S_IWUSR,
+                taal_show_ulps, taal_store_ulps);
+static DEVICE_ATTR(ulps_timeout, S_IRUGO | S_IWUSR,
+                taal_show_ulps_timeout, taal_store_ulps_timeout);
 
 static struct attribute *taal_attrs[] = {
         &dev_attr_num_dsi_errors.attr,
         &dev_attr_hw_revision.attr,
         &dev_attr_cabc_mode.attr,
         &dev_attr_cabc_available_modes.attr,
+        &dev_attr_esd_interval.attr,
+        &dev_attr_ulps.attr,
+        &dev_attr_ulps_timeout.attr,
         NULL,
 };
 
@@ -700,6 +993,9 @@ static int taal_probe(struct omap_dss_device *dssdev)
         }
         td->dssdev = dssdev;
         td->panel_config = panel_config;
+        td->esd_interval = panel_data->esd_interval;
+        td->ulps_enabled = false;
+        td->ulps_timeout = panel_data->ulps_timeout;
 
         mutex_init(&td->lock);
 
@@ -710,13 +1006,14 @@ static int taal_probe(struct omap_dss_device *dssdev)
         if (r)
                 goto err_reg;
 
-        td->esd_wq = create_singlethread_workqueue("taal_esd");
-        if (td->esd_wq == NULL) {
+        td->workqueue = create_singlethread_workqueue("taal_esd");
+        if (td->workqueue == NULL) {
                 dev_err(&dssdev->dev, "can't create ESD workqueue\n");
                 r = -ENOMEM;
                 goto err_wq;
         }
         INIT_DELAYED_WORK_DEFERRABLE(&td->esd_work, taal_esd_work);
+        INIT_DELAYED_WORK(&td->ulps_work, taal_ulps_work);
 
         dev_set_drvdata(&dssdev->dev, td);
 
@@ -734,8 +1031,8 @@ static int taal_probe(struct omap_dss_device *dssdev)
                 props.max_brightness = 127;
 
         props.type = BACKLIGHT_RAW;
-        bldev = backlight_device_register("taal", &dssdev->dev, dssdev,
-                                          &taal_bl_ops, &props);
+        bldev = backlight_device_register(dev_name(&dssdev->dev), &dssdev->dev,
+                                        dssdev, &taal_bl_ops, &props);
         if (IS_ERR(bldev)) {
                 r = PTR_ERR(bldev);
                 goto err_bl;
@@ -810,7 +1107,7 @@ err_irq:
 err_gpio:
         backlight_device_unregister(bldev);
 err_bl:
-        destroy_workqueue(td->esd_wq);
+        destroy_workqueue(td->workqueue);
 err_wq:
         free_regulators(panel_config->regulators, panel_config->num_regulators);
 err_reg:
@@ -819,7 +1116,7 @@ err:
         return r;
 }
 
-static void taal_remove(struct omap_dss_device *dssdev)
+static void __exit taal_remove(struct omap_dss_device *dssdev)
 {
         struct taal_data *td = dev_get_drvdata(&dssdev->dev);
         struct nokia_dsi_panel_data *panel_data = get_panel_data(dssdev);
@@ -841,8 +1138,9 @@ static void taal_remove(struct omap_dss_device *dssdev)
         taal_bl_update_status(bldev);
         backlight_device_unregister(bldev);
 
-        cancel_delayed_work(&td->esd_work);
-        destroy_workqueue(td->esd_wq);
+        taal_cancel_ulps_work(dssdev);
+        taal_cancel_esd_work(dssdev);
+        destroy_workqueue(td->workqueue);
 
         /* reset, to be sure that the panel is in a valid state */
         taal_hw_reset(dssdev);
@@ -867,7 +1165,7 @@ static int taal_power_on(struct omap_dss_device *dssdev)
 
         taal_hw_reset(dssdev);
 
-        omapdss_dsi_vc_enable_hs(td->channel, false);
+        omapdss_dsi_vc_enable_hs(dssdev, td->channel, false);
 
         r = taal_sleep_out(td);
         if (r)
@@ -924,7 +1222,7 @@ static int taal_power_on(struct omap_dss_device *dssdev)
                 td->intro_printed = true;
         }
 
-        omapdss_dsi_vc_enable_hs(td->channel, true);
+        omapdss_dsi_vc_enable_hs(dssdev, td->channel, true);
 
         return 0;
 err:
@@ -932,7 +1230,7 @@ err:
 
         taal_hw_reset(dssdev);
 
-        omapdss_dsi_display_disable(dssdev);
+        omapdss_dsi_display_disable(dssdev, true, false);
 err0:
         return r;
 }
@@ -955,15 +1253,23 @@ static void taal_power_off(struct omap_dss_device *dssdev)
                 taal_hw_reset(dssdev);
         }
 
-        omapdss_dsi_display_disable(dssdev);
+        omapdss_dsi_display_disable(dssdev, true, false);
 
         td->enabled = 0;
 }
 
+static int taal_panel_reset(struct omap_dss_device *dssdev)
+{
+        dev_err(&dssdev->dev, "performing LCD reset\n");
+
+        taal_power_off(dssdev);
+        taal_hw_reset(dssdev);
+        return taal_power_on(dssdev);
+}
+
 static int taal_enable(struct omap_dss_device *dssdev)
 {
         struct taal_data *td = dev_get_drvdata(&dssdev->dev);
-        struct nokia_dsi_panel_data *panel_data = get_panel_data(dssdev);
         int r;
 
         dev_dbg(&dssdev->dev, "enable\n");
@@ -975,18 +1281,16 @@ static int taal_enable(struct omap_dss_device *dssdev)
                 goto err;
         }
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
 
         r = taal_power_on(dssdev);
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 
         if (r)
                 goto err;
 
-        if (panel_data->use_esd_check)
-                queue_delayed_work(td->esd_wq, &td->esd_work,
-                                TAAL_ESD_CHECK_PERIOD);
+        taal_queue_esd_work(dssdev);
 
         dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
 
@@ -1007,14 +1311,17 @@ static void taal_disable(struct omap_dss_device *dssdev)
 
         mutex_lock(&td->lock);
 
-        cancel_delayed_work(&td->esd_work);
+        taal_cancel_ulps_work(dssdev);
+        taal_cancel_esd_work(dssdev);
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
 
-        if (dssdev->state == OMAP_DSS_DISPLAY_ACTIVE)
+        if (dssdev->state == OMAP_DSS_DISPLAY_ACTIVE) {
+                taal_wake_up(dssdev);
                 taal_power_off(dssdev);
+        }
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 
         dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
 
@@ -1035,13 +1342,16 @@ static int taal_suspend(struct omap_dss_device *dssdev)
                 goto err;
         }
 
-        cancel_delayed_work(&td->esd_work);
+        taal_cancel_ulps_work(dssdev);
+        taal_cancel_esd_work(dssdev);
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
 
-        taal_power_off(dssdev);
+        r = taal_wake_up(dssdev);
+        if (!r)
+                taal_power_off(dssdev);
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 
         dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
 
@@ -1056,7 +1366,6 @@ err:
 static int taal_resume(struct omap_dss_device *dssdev)
 {
         struct taal_data *td = dev_get_drvdata(&dssdev->dev);
-        struct nokia_dsi_panel_data *panel_data = get_panel_data(dssdev);
         int r;
 
         dev_dbg(&dssdev->dev, "resume\n");
@@ -1068,19 +1377,17 @@ static int taal_resume(struct omap_dss_device *dssdev)
                 goto err;
         }
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
 
         r = taal_power_on(dssdev);
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 
         if (r) {
                 dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
         } else {
                 dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-                if (panel_data->use_esd_check)
-                        queue_delayed_work(td->esd_wq, &td->esd_work,
-                                        TAAL_ESD_CHECK_PERIOD);
+                taal_queue_esd_work(dssdev);
         }
 
         mutex_unlock(&td->lock);
@@ -1095,7 +1402,7 @@ static void taal_framedone_cb(int err, void *data)
 {
         struct omap_dss_device *dssdev = data;
         dev_dbg(&dssdev->dev, "framedone, err %d\n", err);
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 }
 
 static irqreturn_t taal_te_isr(int irq, void *data)
@@ -1123,7 +1430,7 @@ static irqreturn_t taal_te_isr(int irq, void *data)
         return IRQ_HANDLED;
 err:
         dev_err(&dssdev->dev, "start update failed\n");
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
         return IRQ_HANDLED;
 }
 
@@ -1136,7 +1443,7 @@ static void taal_te_timeout_work_callback(struct work_struct *work)
         dev_err(&dssdev->dev, "TE not received for 250ms!\n");
 
         atomic_set(&td->do_update, 0);
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 }
 
 static int taal_update(struct omap_dss_device *dssdev,
@@ -1149,7 +1456,11 @@ static int taal_update(struct omap_dss_device *dssdev,
         dev_dbg(&dssdev->dev, "update %d, %d, %d x %d\n", x, y, w, h);
 
         mutex_lock(&td->lock);
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
+
+        r = taal_wake_up(dssdev);
+        if (r)
+                goto err;
 
         if (!td->enabled) {
                 r = 0;
@@ -1184,7 +1495,7 @@ static int taal_update(struct omap_dss_device *dssdev,
         mutex_unlock(&td->lock);
         return 0;
 err:
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
         mutex_unlock(&td->lock);
         return r;
 }
@@ -1196,8 +1507,8 @@ static int taal_sync(struct omap_dss_device *dssdev)
         dev_dbg(&dssdev->dev, "sync\n");
 
         mutex_lock(&td->lock);
-        dsi_bus_lock();
-        dsi_bus_unlock();
+        dsi_bus_lock(dssdev);
+        dsi_bus_unlock(dssdev);
         mutex_unlock(&td->lock);
 
         dev_dbg(&dssdev->dev, "sync done\n");
@@ -1235,9 +1546,13 @@ static int taal_enable_te(struct omap_dss_device *dssdev, bool enable)
         if (td->te_enabled == enable)
                 goto end;
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
 
         if (td->enabled) {
+                r = taal_wake_up(dssdev);
+                if (r)
+                        goto err;
+
                 r = _taal_enable_te(dssdev, enable);
                 if (r)
                         goto err;
@@ -1245,13 +1560,13 @@ static int taal_enable_te(struct omap_dss_device *dssdev, bool enable)
 
         td->te_enabled = enable;
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 end:
         mutex_unlock(&td->lock);
 
         return 0;
 err:
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
         mutex_unlock(&td->lock);
 
         return r;
@@ -1281,9 +1596,13 @@ static int taal_rotate(struct omap_dss_device *dssdev, u8 rotate)
         if (td->rotate == rotate)
                 goto end;
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
 
         if (td->enabled) {
+                r = taal_wake_up(dssdev);
+                if (r)
+                        goto err;
+
                 r = taal_set_addr_mode(td, rotate, td->mirror);
                 if (r)
                         goto err;
@@ -1291,12 +1610,12 @@ static int taal_rotate(struct omap_dss_device *dssdev, u8 rotate)
 
         td->rotate = rotate;
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 end:
         mutex_unlock(&td->lock);
         return 0;
 err:
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
         mutex_unlock(&td->lock);
         return r;
 }
@@ -1325,8 +1644,12 @@ static int taal_mirror(struct omap_dss_device *dssdev, bool enable)
         if (td->mirror == enable)
                 goto end;
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
         if (td->enabled) {
+                r = taal_wake_up(dssdev);
+                if (r)
+                        goto err;
+
                 r = taal_set_addr_mode(td, td->rotate, enable);
                 if (r)
                         goto err;
@@ -1334,12 +1657,12 @@ static int taal_mirror(struct omap_dss_device *dssdev, bool enable)
 
         td->mirror = enable;
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 end:
         mutex_unlock(&td->lock);
         return 0;
 err:
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
         mutex_unlock(&td->lock);
         return r;
 }
@@ -1369,7 +1692,11 @@ static int taal_run_test(struct omap_dss_device *dssdev, int test_num)
                 goto err1;
         }
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
+
+        r = taal_wake_up(dssdev);
+        if (r)
+                goto err2;
 
         r = taal_dcs_read_1(td, DCS_GET_ID1, &id1);
         if (r)
@@ -1381,11 +1708,11 @@ static int taal_run_test(struct omap_dss_device *dssdev, int test_num)
         if (r)
                 goto err2;
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
         mutex_unlock(&td->lock);
         return 0;
 err2:
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 err1:
         mutex_unlock(&td->lock);
         return r;
@@ -1415,7 +1742,11 @@ static int taal_memory_read(struct omap_dss_device *dssdev,
                         dssdev->panel.timings.x_res *
                         dssdev->panel.timings.y_res * 3);
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
+
+        r = taal_wake_up(dssdev);
+        if (r)
+                goto err2;
 
         /* plen 1 or 2 goes into short packet. until checksum error is fixed,
          * use short packets. plen 32 works, but bigger packets seem to cause
@@ -1427,7 +1758,7 @@ static int taal_memory_read(struct omap_dss_device *dssdev,
 
         taal_set_update_window(td, x, y, w, h);
 
-        r = dsi_vc_set_max_rx_packet_size(td->channel, plen);
+        r = dsi_vc_set_max_rx_packet_size(dssdev, td->channel, plen);
         if (r)
                 goto err2;
 
@@ -1435,7 +1766,7 @@ static int taal_memory_read(struct omap_dss_device *dssdev,
                 u8 dcs_cmd = first ? 0x2e : 0x3e;
                 first = 0;
 
-                r = dsi_vc_dcs_read(td->channel, dcs_cmd,
+                r = dsi_vc_dcs_read(dssdev, td->channel, dcs_cmd,
                                 buf + buf_used, size - buf_used);
 
                 if (r < 0) {
@@ -1461,14 +1792,35 @@ static int taal_memory_read(struct omap_dss_device *dssdev,
         r = buf_used;
 
 err3:
-        dsi_vc_set_max_rx_packet_size(td->channel, 1);
+        dsi_vc_set_max_rx_packet_size(dssdev, td->channel, 1);
 err2:
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 err1:
         mutex_unlock(&td->lock);
         return r;
 }
 
+static void taal_ulps_work(struct work_struct *work)
+{
+        struct taal_data *td = container_of(work, struct taal_data,
+                        ulps_work.work);
+        struct omap_dss_device *dssdev = td->dssdev;
+
+        mutex_lock(&td->lock);
+
+        if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE || !td->enabled) {
+                mutex_unlock(&td->lock);
+                return;
+        }
+
+        dsi_bus_lock(dssdev);
+
+        taal_enter_ulps(dssdev);
+
+        dsi_bus_unlock(dssdev);
+        mutex_unlock(&td->lock);
+}
+
 static void taal_esd_work(struct work_struct *work)
 {
         struct taal_data *td = container_of(work, struct taal_data,
@@ -1485,7 +1837,13 @@ static void taal_esd_work(struct work_struct *work)
                 return;
         }
 
-        dsi_bus_lock();
+        dsi_bus_lock(dssdev);
+
+        r = taal_wake_up(dssdev);
+        if (r) {
+                dev_err(&dssdev->dev, "failed to exit ULPS\n");
+                goto err;
+        }
 
         r = taal_dcs_read_1(td, DCS_RDDSDR, &state1);
         if (r) {
@@ -1521,22 +1879,20 @@ static void taal_esd_work(struct work_struct *work)
                         goto err;
         }
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 
-        queue_delayed_work(td->esd_wq, &td->esd_work, TAAL_ESD_CHECK_PERIOD);
+        taal_queue_esd_work(dssdev);
 
         mutex_unlock(&td->lock);
         return;
 err:
         dev_err(&dssdev->dev, "performing LCD reset\n");
 
-        taal_power_off(dssdev);
-        taal_hw_reset(dssdev);
-        taal_power_on(dssdev);
+        taal_panel_reset(dssdev);
 
-        dsi_bus_unlock();
+        dsi_bus_unlock(dssdev);
 
-        queue_delayed_work(td->esd_wq, &td->esd_work, TAAL_ESD_CHECK_PERIOD);
+        taal_queue_esd_work(dssdev);
 
         mutex_unlock(&td->lock);
 }
@@ -1557,7 +1913,7 @@ static enum omap_dss_update_mode taal_get_update_mode(
 
 static struct omap_dss_driver taal_driver = {
         .probe          = taal_probe,
-        .remove         = taal_remove,
+        .remove         = __exit_p(taal_remove),
 
         .enable         = taal_enable,
         .disable        = taal_disable,
diff --git a/drivers/video/omap2/displays/panel-tpo-td043mtea1.c b/drivers/video/omap2/displays/panel-tpo-td043mtea1.c
index dbe9d43b4850..2462b9ec6662 100644
--- a/drivers/video/omap2/displays/panel-tpo-td043mtea1.c
+++ b/drivers/video/omap2/displays/panel-tpo-td043mtea1.c
@@ -17,7 +17,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define TPO_R02_MODE(x)         ((x) & 7)
 #define TPO_R02_MODE_800x480    7
@@ -144,13 +144,15 @@ static ssize_t tpo_td043_vmirror_store(struct device *dev,
         struct device_attribute *attr, const char *buf, size_t count)
 {
         struct tpo_td043_device *tpo_td043 = dev_get_drvdata(dev);
-        long val;
+        int val;
         int ret;
 
-        ret = strict_strtol(buf, 0, &val);
+        ret = kstrtoint(buf, 0, &val);
         if (ret < 0)
                 return ret;
 
+        val = !!val;
+
         ret = tpo_td043_write_mirror(tpo_td043->spi, tpo_td043->hmirror, val);
         if (ret < 0)
                 return ret;
@@ -175,7 +177,7 @@ static ssize_t tpo_td043_mode_store(struct device *dev,
         long val;
         int ret;
 
-        ret = strict_strtol(buf, 0, &val);
+        ret = kstrtol(buf, 0, &val);
         if (ret != 0 || val & ~7)
                 return -EINVAL;
 
diff --git a/drivers/video/omap2/dss/Kconfig b/drivers/video/omap2/dss/Kconfig
index bfc5da0e9700..6b3e2da11419 100644
--- a/drivers/video/omap2/dss/Kconfig
+++ b/drivers/video/omap2/dss/Kconfig
@@ -80,7 +80,7 @@ config OMAP2_DSS_SDI
 
 config OMAP2_DSS_DSI
         bool "DSI support"
-        depends on ARCH_OMAP3
+        depends on ARCH_OMAP3 || ARCH_OMAP4
         default n
         help
           MIPI DSI (Display Serial Interface) support.
@@ -90,14 +90,6 @@ config OMAP2_DSS_DSI
 
           See http://www.mipi.org/ for DSI spesifications.
 
-config OMAP2_DSS_USE_DSI_PLL
-        bool "Use DSI PLL for PCLK (EXPERIMENTAL)"
-        default n
-        depends on OMAP2_DSS_DSI
-        help
-          Use DSI PLL to generate pixel clock.  Currently only for DPI output.
-          DSI PLL can be used to generate higher and more precise pixel clocks.
-
 config OMAP2_DSS_FAKE_VSYNC
         bool "Fake VSYNC irq from manual update displays"
         default n
@@ -125,4 +117,27 @@ config OMAP2_DSS_MIN_FCK_PER_PCK
           Max FCK is 173MHz, so this doesn't work if your PCK
           is very high.
 
+config OMAP2_DSS_SLEEP_BEFORE_RESET
+        bool "Sleep 50ms before DSS reset"
+        default y
+        help
+          For some unknown reason we may get SYNC_LOST errors from the display
+          subsystem at initialization time if we don't sleep before resetting
+          the DSS. See the source (dss.c) for more comments.
+
+          However, 50ms is quite long time to sleep, and with some
+          configurations the SYNC_LOST may never happen, so the sleep can
+          be disabled here.
+
+config OMAP2_DSS_SLEEP_AFTER_VENC_RESET
+        bool "Sleep 20ms after VENC reset"
+        default y
+        help
+          There is a 20ms sleep after VENC reset which seemed to fix the
+          reset. The reason for the bug is unclear, and it's also unclear
+          on what platforms this happens.
+
+          This option enables the sleep, and is enabled by default. You can
+          disable the sleep if it doesn't cause problems on your platform.
+
 endif
diff --git a/drivers/video/omap2/dss/core.c b/drivers/video/omap2/dss/core.c
index 1aa2ed1e786e..3da426719dd6 100644
--- a/drivers/video/omap2/dss/core.c
+++ b/drivers/video/omap2/dss/core.c
@@ -33,7 +33,7 @@
 #include <linux/device.h>
 #include <linux/regulator/consumer.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #include "dss.h"
 #include "dss_features.h"
@@ -54,6 +54,9 @@ unsigned int dss_debug;
 module_param_named(debug, dss_debug, bool, 0644);
 #endif
 
+static int omap_dss_register_device(struct omap_dss_device *);
+static void omap_dss_unregister_device(struct omap_dss_device *);
+
 /* REGULATORS */
 
 struct regulator *dss_get_vdds_dsi(void)
@@ -124,8 +127,7 @@ static int dss_initialize_debugfs(void)
 #endif
 
 #if defined(CONFIG_OMAP2_DSS_DSI) && defined(CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS)
-        debugfs_create_file("dsi_irq", S_IRUGO, dss_debugfs_dir,
-                        &dsi_dump_irqs, &dss_debug_fops);
+        dsi_create_debugfs_files_irq(dss_debugfs_dir, &dss_debug_fops);
 #endif
 
         debugfs_create_file("dss", S_IRUGO, dss_debugfs_dir,
@@ -137,8 +139,7 @@ static int dss_initialize_debugfs(void)
                         &rfbi_dump_regs, &dss_debug_fops);
 #endif
 #ifdef CONFIG_OMAP2_DSS_DSI
-        debugfs_create_file("dsi", S_IRUGO, dss_debugfs_dir,
-                        &dsi_dump_regs, &dss_debug_fops);
+        dsi_create_debugfs_files_reg(dss_debugfs_dir, &dss_debug_fops);
 #endif
 #ifdef CONFIG_OMAP2_DSS_VENC
         debugfs_create_file("venc", S_IRUGO, dss_debugfs_dir,
@@ -480,7 +481,7 @@ static void omap_dss_dev_release(struct device *dev)
         reset_device(dev, 0);
 }
 
-int omap_dss_register_device(struct omap_dss_device *dssdev)
+static int omap_dss_register_device(struct omap_dss_device *dssdev)
 {
         static int dev_num;
 
@@ -494,7 +495,7 @@ int omap_dss_register_device(struct omap_dss_device *dssdev)
         return device_register(&dssdev->dev);
 }
 
-void omap_dss_unregister_device(struct omap_dss_device *dssdev)
+static void omap_dss_unregister_device(struct omap_dss_device *dssdev)
 {
         device_unregister(&dssdev->dev);
 }
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index 7804779c9da1..7a9a2e7d9685 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -37,99 +37,15 @@
 #include <plat/sram.h>
 #include <plat/clock.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #include "dss.h"
 #include "dss_features.h"
+#include "dispc.h"
 
 /* DISPC */
 #define DISPC_SZ_REGS                   SZ_4K
 
-struct dispc_reg { u16 idx; };
-
-#define DISPC_REG(idx)                  ((const struct dispc_reg) { idx })
-
-/*
- * DISPC common registers and
- * DISPC channel registers , ch = 0 for LCD, ch = 1 for
- * DIGIT, and ch = 2 for LCD2
- */
-#define DISPC_REVISION                  DISPC_REG(0x0000)
-#define DISPC_SYSCONFIG                 DISPC_REG(0x0010)
-#define DISPC_SYSSTATUS                 DISPC_REG(0x0014)
-#define DISPC_IRQSTATUS                 DISPC_REG(0x0018)
-#define DISPC_IRQENABLE                 DISPC_REG(0x001C)
-#define DISPC_CONTROL                   DISPC_REG(0x0040)
-#define DISPC_CONTROL2                  DISPC_REG(0x0238)
-#define DISPC_CONFIG                    DISPC_REG(0x0044)
-#define DISPC_CONFIG2                   DISPC_REG(0x0620)
-#define DISPC_CAPABLE                   DISPC_REG(0x0048)
-#define DISPC_DEFAULT_COLOR(ch)         DISPC_REG(ch == 0 ? 0x004C : \
-                                        (ch == 1 ? 0x0050 : 0x03AC))
-#define DISPC_TRANS_COLOR(ch)           DISPC_REG(ch == 0 ? 0x0054 : \
-                                        (ch == 1 ? 0x0058 : 0x03B0))
-#define DISPC_LINE_STATUS               DISPC_REG(0x005C)
-#define DISPC_LINE_NUMBER               DISPC_REG(0x0060)
-#define DISPC_TIMING_H(ch)              DISPC_REG(ch != 2 ? 0x0064 : 0x0400)
-#define DISPC_TIMING_V(ch)              DISPC_REG(ch != 2 ? 0x0068 : 0x0404)
-#define DISPC_POL_FREQ(ch)              DISPC_REG(ch != 2 ? 0x006C : 0x0408)
-#define DISPC_DIVISORo(ch)              DISPC_REG(ch != 2 ? 0x0070 : 0x040C)
-#define DISPC_GLOBAL_ALPHA              DISPC_REG(0x0074)
-#define DISPC_SIZE_DIG                  DISPC_REG(0x0078)
-#define DISPC_SIZE_LCD(ch)              DISPC_REG(ch != 2 ? 0x007C : 0x03CC)
-
-/* DISPC GFX plane */
-#define DISPC_GFX_BA0                   DISPC_REG(0x0080)
-#define DISPC_GFX_BA1                   DISPC_REG(0x0084)
-#define DISPC_GFX_POSITION              DISPC_REG(0x0088)
-#define DISPC_GFX_SIZE                  DISPC_REG(0x008C)
-#define DISPC_GFX_ATTRIBUTES            DISPC_REG(0x00A0)
-#define DISPC_GFX_FIFO_THRESHOLD        DISPC_REG(0x00A4)
-#define DISPC_GFX_FIFO_SIZE_STATUS      DISPC_REG(0x00A8)
-#define DISPC_GFX_ROW_INC               DISPC_REG(0x00AC)
-#define DISPC_GFX_PIXEL_INC             DISPC_REG(0x00B0)
-#define DISPC_GFX_WINDOW_SKIP           DISPC_REG(0x00B4)
-#define DISPC_GFX_TABLE_BA              DISPC_REG(0x00B8)
-
-#define DISPC_DATA_CYCLE1(ch)           DISPC_REG(ch != 2 ? 0x01D4 : 0x03C0)
-#define DISPC_DATA_CYCLE2(ch)           DISPC_REG(ch != 2 ? 0x01D8 : 0x03C4)
-#define DISPC_DATA_CYCLE3(ch)           DISPC_REG(ch != 2 ? 0x01DC : 0x03C8)
-#define DISPC_CPR_COEF_R(ch)            DISPC_REG(ch != 2 ? 0x0220 : 0x03BC)
-#define DISPC_CPR_COEF_G(ch)            DISPC_REG(ch != 2 ? 0x0224 : 0x03B8)
-#define DISPC_CPR_COEF_B(ch)            DISPC_REG(ch != 2 ? 0x0228 : 0x03B4)
-
-#define DISPC_GFX_PRELOAD               DISPC_REG(0x022C)
-
-/* DISPC Video plane, n = 0 for VID1 and n = 1 for VID2 */
-#define DISPC_VID_REG(n, idx)           DISPC_REG(0x00BC + (n)*0x90 + idx)
-
-#define DISPC_VID_BA0(n)                DISPC_VID_REG(n, 0x0000)
-#define DISPC_VID_BA1(n)                DISPC_VID_REG(n, 0x0004)
-#define DISPC_VID_POSITION(n)           DISPC_VID_REG(n, 0x0008)
-#define DISPC_VID_SIZE(n)               DISPC_VID_REG(n, 0x000C)
-#define DISPC_VID_ATTRIBUTES(n)         DISPC_VID_REG(n, 0x0010)
-#define DISPC_VID_FIFO_THRESHOLD(n)     DISPC_VID_REG(n, 0x0014)
-#define DISPC_VID_FIFO_SIZE_STATUS(n)   DISPC_VID_REG(n, 0x0018)
-#define DISPC_VID_ROW_INC(n)            DISPC_VID_REG(n, 0x001C)
-#define DISPC_VID_PIXEL_INC(n)          DISPC_VID_REG(n, 0x0020)
-#define DISPC_VID_FIR(n)                DISPC_VID_REG(n, 0x0024)
-#define DISPC_VID_PICTURE_SIZE(n)       DISPC_VID_REG(n, 0x0028)
-#define DISPC_VID_ACCU0(n)              DISPC_VID_REG(n, 0x002C)
-#define DISPC_VID_ACCU1(n)              DISPC_VID_REG(n, 0x0030)
-
-/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
-#define DISPC_VID_FIR_COEF_H(n, i)      DISPC_REG(0x00F0 + (n)*0x90 + (i)*0x8)
-/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
-#define DISPC_VID_FIR_COEF_HV(n, i)     DISPC_REG(0x00F4 + (n)*0x90 + (i)*0x8)
-/* coef index i = {0, 1, 2, 3, 4} */
-#define DISPC_VID_CONV_COEF(n, i)       DISPC_REG(0x0130 + (n)*0x90 + (i)*0x4)
-/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
-#define DISPC_VID_FIR_COEF_V(n, i)      DISPC_REG(0x01E0 + (n)*0x20 + (i)*0x4)
-
-#define DISPC_VID_PRELOAD(n)            DISPC_REG(0x230 + (n)*0x04)
-
-#define DISPC_DIVISOR                   DISPC_REG(0x0804)
-
 #define DISPC_IRQ_MASK_ERROR            (DISPC_IRQ_GFX_FIFO_UNDERFLOW | \
                                          DISPC_IRQ_OCP_ERR | \
                                          DISPC_IRQ_VID1_FIFO_UNDERFLOW | \
@@ -167,10 +83,6 @@ struct dispc_v_coef {
 #define REG_FLD_MOD(idx, val, start, end)                               \
         dispc_write_reg(idx, FLD_MOD(dispc_read_reg(idx), val, start, end))
 
-static const struct dispc_reg dispc_reg_att[] = { DISPC_GFX_ATTRIBUTES,
-        DISPC_VID_ATTRIBUTES(0),
-        DISPC_VID_ATTRIBUTES(1) };
-
 struct dispc_irq_stats {
         unsigned long last_reset;
         unsigned irq_count;
@@ -198,25 +110,38 @@ static struct {
 #endif
 } dispc;
 
+enum omap_color_component {
+        /* used for all color formats for OMAP3 and earlier
+         * and for RGB and Y color component on OMAP4
+         */
+        DISPC_COLOR_COMPONENT_RGB_Y             = 1 << 0,
+        /* used for UV component for
+         * OMAP_DSS_COLOR_YUV2, OMAP_DSS_COLOR_UYVY, OMAP_DSS_COLOR_NV12
+         * color formats on OMAP4
+         */
+        DISPC_COLOR_COMPONENT_UV                = 1 << 1,
+};
+
 static void _omap_dispc_set_irqs(void);
 
-static inline void dispc_write_reg(const struct dispc_reg idx, u32 val)
+static inline void dispc_write_reg(const u16 idx, u32 val)
 {
-        __raw_writel(val, dispc.base + idx.idx);
+        __raw_writel(val, dispc.base + idx);
 }
 
-static inline u32 dispc_read_reg(const struct dispc_reg idx)
+static inline u32 dispc_read_reg(const u16 idx)
 {
-        return __raw_readl(dispc.base + idx.idx);
+        return __raw_readl(dispc.base + idx);
 }
 
 #define SR(reg) \
-        dispc.ctx[(DISPC_##reg).idx / sizeof(u32)] = dispc_read_reg(DISPC_##reg)
+        dispc.ctx[DISPC_##reg / sizeof(u32)] = dispc_read_reg(DISPC_##reg)
 #define RR(reg) \
-        dispc_write_reg(DISPC_##reg, dispc.ctx[(DISPC_##reg).idx / sizeof(u32)])
+        dispc_write_reg(DISPC_##reg, dispc.ctx[DISPC_##reg / sizeof(u32)])
 
 void dispc_save_context(void)
 {
+        int i;
         if (cpu_is_omap24xx())
                 return;
 
@@ -224,157 +149,153 @@ void dispc_save_context(void)
         SR(IRQENABLE);
         SR(CONTROL);
         SR(CONFIG);
-        SR(DEFAULT_COLOR(0));
-        SR(DEFAULT_COLOR(1));
-        SR(TRANS_COLOR(0));
-        SR(TRANS_COLOR(1));
+        SR(DEFAULT_COLOR(OMAP_DSS_CHANNEL_LCD));
+        SR(DEFAULT_COLOR(OMAP_DSS_CHANNEL_DIGIT));
+        SR(TRANS_COLOR(OMAP_DSS_CHANNEL_LCD));
+        SR(TRANS_COLOR(OMAP_DSS_CHANNEL_DIGIT));
         SR(LINE_NUMBER);
-        SR(TIMING_H(0));
-        SR(TIMING_V(0));
-        SR(POL_FREQ(0));
-        SR(DIVISORo(0));
+        SR(TIMING_H(OMAP_DSS_CHANNEL_LCD));
+        SR(TIMING_V(OMAP_DSS_CHANNEL_LCD));
+        SR(POL_FREQ(OMAP_DSS_CHANNEL_LCD));
+        SR(DIVISORo(OMAP_DSS_CHANNEL_LCD));
         SR(GLOBAL_ALPHA);
-        SR(SIZE_DIG);
-        SR(SIZE_LCD(0));
+        SR(SIZE_MGR(OMAP_DSS_CHANNEL_DIGIT));
+        SR(SIZE_MGR(OMAP_DSS_CHANNEL_LCD));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
                 SR(CONTROL2);
-                SR(DEFAULT_COLOR(2));
-                SR(TRANS_COLOR(2));
-                SR(SIZE_LCD(2));
-                SR(TIMING_H(2));
-                SR(TIMING_V(2));
-                SR(POL_FREQ(2));
-                SR(DIVISORo(2));
+                SR(DEFAULT_COLOR(OMAP_DSS_CHANNEL_LCD2));
+                SR(TRANS_COLOR(OMAP_DSS_CHANNEL_LCD2));
+                SR(SIZE_MGR(OMAP_DSS_CHANNEL_LCD2));
+                SR(TIMING_H(OMAP_DSS_CHANNEL_LCD2));
+                SR(TIMING_V(OMAP_DSS_CHANNEL_LCD2));
+                SR(POL_FREQ(OMAP_DSS_CHANNEL_LCD2));
+                SR(DIVISORo(OMAP_DSS_CHANNEL_LCD2));
                 SR(CONFIG2);
         }
 
-        SR(GFX_BA0);
-        SR(GFX_BA1);
-        SR(GFX_POSITION);
-        SR(GFX_SIZE);
-        SR(GFX_ATTRIBUTES);
-        SR(GFX_FIFO_THRESHOLD);
-        SR(GFX_ROW_INC);
-        SR(GFX_PIXEL_INC);
-        SR(GFX_WINDOW_SKIP);
-        SR(GFX_TABLE_BA);
-
-        SR(DATA_CYCLE1(0));
-        SR(DATA_CYCLE2(0));
-        SR(DATA_CYCLE3(0));
-
-        SR(CPR_COEF_R(0));
-        SR(CPR_COEF_G(0));
-        SR(CPR_COEF_B(0));
+        SR(OVL_BA0(OMAP_DSS_GFX));
+        SR(OVL_BA1(OMAP_DSS_GFX));
+        SR(OVL_POSITION(OMAP_DSS_GFX));
+        SR(OVL_SIZE(OMAP_DSS_GFX));
+        SR(OVL_ATTRIBUTES(OMAP_DSS_GFX));
+        SR(OVL_FIFO_THRESHOLD(OMAP_DSS_GFX));
+        SR(OVL_ROW_INC(OMAP_DSS_GFX));
+        SR(OVL_PIXEL_INC(OMAP_DSS_GFX));
+        SR(OVL_WINDOW_SKIP(OMAP_DSS_GFX));
+        SR(OVL_TABLE_BA(OMAP_DSS_GFX));
+
+        SR(DATA_CYCLE1(OMAP_DSS_CHANNEL_LCD));
+        SR(DATA_CYCLE2(OMAP_DSS_CHANNEL_LCD));
+        SR(DATA_CYCLE3(OMAP_DSS_CHANNEL_LCD));
+
+        SR(CPR_COEF_R(OMAP_DSS_CHANNEL_LCD));
+        SR(CPR_COEF_G(OMAP_DSS_CHANNEL_LCD));
+        SR(CPR_COEF_B(OMAP_DSS_CHANNEL_LCD));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
-                SR(CPR_COEF_B(2));
-                SR(CPR_COEF_G(2));
-                SR(CPR_COEF_R(2));
+                SR(CPR_COEF_B(OMAP_DSS_CHANNEL_LCD2));
+                SR(CPR_COEF_G(OMAP_DSS_CHANNEL_LCD2));
+                SR(CPR_COEF_R(OMAP_DSS_CHANNEL_LCD2));
 
-                SR(DATA_CYCLE1(2));
-                SR(DATA_CYCLE2(2));
-                SR(DATA_CYCLE3(2));
+                SR(DATA_CYCLE1(OMAP_DSS_CHANNEL_LCD2));
+                SR(DATA_CYCLE2(OMAP_DSS_CHANNEL_LCD2));
+                SR(DATA_CYCLE3(OMAP_DSS_CHANNEL_LCD2));
         }
 
-        SR(GFX_PRELOAD);
+        SR(OVL_PRELOAD(OMAP_DSS_GFX));
 
         /* VID1 */
-        SR(VID_BA0(0));
-        SR(VID_BA1(0));
-        SR(VID_POSITION(0));
-        SR(VID_SIZE(0));
-        SR(VID_ATTRIBUTES(0));
-        SR(VID_FIFO_THRESHOLD(0));
-        SR(VID_ROW_INC(0));
-        SR(VID_PIXEL_INC(0));
-        SR(VID_FIR(0));
-        SR(VID_PICTURE_SIZE(0));
-        SR(VID_ACCU0(0));
-        SR(VID_ACCU1(0));
-
-        SR(VID_FIR_COEF_H(0, 0));
-        SR(VID_FIR_COEF_H(0, 1));
-        SR(VID_FIR_COEF_H(0, 2));
-        SR(VID_FIR_COEF_H(0, 3));
-        SR(VID_FIR_COEF_H(0, 4));
-        SR(VID_FIR_COEF_H(0, 5));
-        SR(VID_FIR_COEF_H(0, 6));
-        SR(VID_FIR_COEF_H(0, 7));
-
-        SR(VID_FIR_COEF_HV(0, 0));
-        SR(VID_FIR_COEF_HV(0, 1));
-        SR(VID_FIR_COEF_HV(0, 2));
-        SR(VID_FIR_COEF_HV(0, 3));
-        SR(VID_FIR_COEF_HV(0, 4));
-        SR(VID_FIR_COEF_HV(0, 5));
-        SR(VID_FIR_COEF_HV(0, 6));
-        SR(VID_FIR_COEF_HV(0, 7));
-
-        SR(VID_CONV_COEF(0, 0));
-        SR(VID_CONV_COEF(0, 1));
-        SR(VID_CONV_COEF(0, 2));
-        SR(VID_CONV_COEF(0, 3));
-        SR(VID_CONV_COEF(0, 4));
-
-        SR(VID_FIR_COEF_V(0, 0));
-        SR(VID_FIR_COEF_V(0, 1));
-        SR(VID_FIR_COEF_V(0, 2));
-        SR(VID_FIR_COEF_V(0, 3));
-        SR(VID_FIR_COEF_V(0, 4));
-        SR(VID_FIR_COEF_V(0, 5));
-        SR(VID_FIR_COEF_V(0, 6));
-        SR(VID_FIR_COEF_V(0, 7));
-
-        SR(VID_PRELOAD(0));
+        SR(OVL_BA0(OMAP_DSS_VIDEO1));
+        SR(OVL_BA1(OMAP_DSS_VIDEO1));
+        SR(OVL_POSITION(OMAP_DSS_VIDEO1));
+        SR(OVL_SIZE(OMAP_DSS_VIDEO1));
+        SR(OVL_ATTRIBUTES(OMAP_DSS_VIDEO1));
+        SR(OVL_FIFO_THRESHOLD(OMAP_DSS_VIDEO1));
+        SR(OVL_ROW_INC(OMAP_DSS_VIDEO1));
+        SR(OVL_PIXEL_INC(OMAP_DSS_VIDEO1));
+        SR(OVL_FIR(OMAP_DSS_VIDEO1));
+        SR(OVL_PICTURE_SIZE(OMAP_DSS_VIDEO1));
+        SR(OVL_ACCU0(OMAP_DSS_VIDEO1));
+        SR(OVL_ACCU1(OMAP_DSS_VIDEO1));
+
+        for (i = 0; i < 8; i++)
+                SR(OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, i));
+
+        for (i = 0; i < 8; i++)
+                SR(OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, i));
+
+        for (i = 0; i < 5; i++)
+                SR(OVL_CONV_COEF(OMAP_DSS_VIDEO1, i));
+
+        for (i = 0; i < 8; i++)
+                SR(OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, i));
+
+        if (dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) {
+                SR(OVL_BA0_UV(OMAP_DSS_VIDEO1));
+                SR(OVL_BA1_UV(OMAP_DSS_VIDEO1));
+                SR(OVL_FIR2(OMAP_DSS_VIDEO1));
+                SR(OVL_ACCU2_0(OMAP_DSS_VIDEO1));
+                SR(OVL_ACCU2_1(OMAP_DSS_VIDEO1));
+
+                for (i = 0; i < 8; i++)
+                        SR(OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, i));
+
+                for (i = 0; i < 8; i++)
+                        SR(OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, i));
+
+                for (i = 0; i < 8; i++)
+                        SR(OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, i));
+        }
+        if (dss_has_feature(FEAT_ATTR2))
+                SR(OVL_ATTRIBUTES2(OMAP_DSS_VIDEO1));
+
+        SR(OVL_PRELOAD(OMAP_DSS_VIDEO1));
 
         /* VID2 */
-        SR(VID_BA0(1));
-        SR(VID_BA1(1));
-        SR(VID_POSITION(1));
-        SR(VID_SIZE(1));
-        SR(VID_ATTRIBUTES(1));
-        SR(VID_FIFO_THRESHOLD(1));
-        SR(VID_ROW_INC(1));
-        SR(VID_PIXEL_INC(1));
-        SR(VID_FIR(1));
-        SR(VID_PICTURE_SIZE(1));
-        SR(VID_ACCU0(1));
-        SR(VID_ACCU1(1));
-
-        SR(VID_FIR_COEF_H(1, 0));
-        SR(VID_FIR_COEF_H(1, 1));
-        SR(VID_FIR_COEF_H(1, 2));
-        SR(VID_FIR_COEF_H(1, 3));
-        SR(VID_FIR_COEF_H(1, 4));
-        SR(VID_FIR_COEF_H(1, 5));
-        SR(VID_FIR_COEF_H(1, 6));
-        SR(VID_FIR_COEF_H(1, 7));
-
-        SR(VID_FIR_COEF_HV(1, 0));
-        SR(VID_FIR_COEF_HV(1, 1));
-        SR(VID_FIR_COEF_HV(1, 2));
-        SR(VID_FIR_COEF_HV(1, 3));
-        SR(VID_FIR_COEF_HV(1, 4));
-        SR(VID_FIR_COEF_HV(1, 5));
-        SR(VID_FIR_COEF_HV(1, 6));
-        SR(VID_FIR_COEF_HV(1, 7));
-
-        SR(VID_CONV_COEF(1, 0));
-        SR(VID_CONV_COEF(1, 1));
-        SR(VID_CONV_COEF(1, 2));
-        SR(VID_CONV_COEF(1, 3));
-        SR(VID_CONV_COEF(1, 4));
-
-        SR(VID_FIR_COEF_V(1, 0));
-        SR(VID_FIR_COEF_V(1, 1));
-        SR(VID_FIR_COEF_V(1, 2));
-        SR(VID_FIR_COEF_V(1, 3));
-        SR(VID_FIR_COEF_V(1, 4));
-        SR(VID_FIR_COEF_V(1, 5));
-        SR(VID_FIR_COEF_V(1, 6));
-        SR(VID_FIR_COEF_V(1, 7));
-
-        SR(VID_PRELOAD(1));
+        SR(OVL_BA0(OMAP_DSS_VIDEO2));
+        SR(OVL_BA1(OMAP_DSS_VIDEO2));
+        SR(OVL_POSITION(OMAP_DSS_VIDEO2));
+        SR(OVL_SIZE(OMAP_DSS_VIDEO2));
+        SR(OVL_ATTRIBUTES(OMAP_DSS_VIDEO2));
+        SR(OVL_FIFO_THRESHOLD(OMAP_DSS_VIDEO2));
+        SR(OVL_ROW_INC(OMAP_DSS_VIDEO2));
+        SR(OVL_PIXEL_INC(OMAP_DSS_VIDEO2));
+        SR(OVL_FIR(OMAP_DSS_VIDEO2));
+        SR(OVL_PICTURE_SIZE(OMAP_DSS_VIDEO2));
+        SR(OVL_ACCU0(OMAP_DSS_VIDEO2));
+        SR(OVL_ACCU1(OMAP_DSS_VIDEO2));
+
+        for (i = 0; i < 8; i++)
+                SR(OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, i));
+
+        for (i = 0; i < 8; i++)
+                SR(OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, i));
+
+        for (i = 0; i < 5; i++)
+                SR(OVL_CONV_COEF(OMAP_DSS_VIDEO2, i));
+
+        for (i = 0; i < 8; i++)
+                SR(OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, i));
+
+        if (dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) {
+                SR(OVL_BA0_UV(OMAP_DSS_VIDEO2));
+                SR(OVL_BA1_UV(OMAP_DSS_VIDEO2));
+                SR(OVL_FIR2(OMAP_DSS_VIDEO2));
+                SR(OVL_ACCU2_0(OMAP_DSS_VIDEO2));
+                SR(OVL_ACCU2_1(OMAP_DSS_VIDEO2));
+
+                for (i = 0; i < 8; i++)
+                        SR(OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, i));
+
+                for (i = 0; i < 8; i++)
+                        SR(OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, i));
+
+                for (i = 0; i < 8; i++)
+                        SR(OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, i));
+        }
+        if (dss_has_feature(FEAT_ATTR2))
+                SR(OVL_ATTRIBUTES2(OMAP_DSS_VIDEO2));
+
+        SR(OVL_PRELOAD(OMAP_DSS_VIDEO2));
 
         if (dss_has_feature(FEAT_CORE_CLK_DIV))
                 SR(DIVISOR);
@@ -382,160 +303,158 @@ void dispc_save_context(void)
 
 void dispc_restore_context(void)
 {
+        int i;
         RR(SYSCONFIG);
         /*RR(IRQENABLE);*/
         /*RR(CONTROL);*/
         RR(CONFIG);
-        RR(DEFAULT_COLOR(0));
-        RR(DEFAULT_COLOR(1));
-        RR(TRANS_COLOR(0));
-        RR(TRANS_COLOR(1));
+        RR(DEFAULT_COLOR(OMAP_DSS_CHANNEL_LCD));
+        RR(DEFAULT_COLOR(OMAP_DSS_CHANNEL_DIGIT));
+        RR(TRANS_COLOR(OMAP_DSS_CHANNEL_LCD));
+        RR(TRANS_COLOR(OMAP_DSS_CHANNEL_DIGIT));
         RR(LINE_NUMBER);
-        RR(TIMING_H(0));
-        RR(TIMING_V(0));
-        RR(POL_FREQ(0));
-        RR(DIVISORo(0));
+        RR(TIMING_H(OMAP_DSS_CHANNEL_LCD));
+        RR(TIMING_V(OMAP_DSS_CHANNEL_LCD));
+        RR(POL_FREQ(OMAP_DSS_CHANNEL_LCD));
+        RR(DIVISORo(OMAP_DSS_CHANNEL_LCD));
         RR(GLOBAL_ALPHA);
-        RR(SIZE_DIG);
-        RR(SIZE_LCD(0));
+        RR(SIZE_MGR(OMAP_DSS_CHANNEL_DIGIT));
+        RR(SIZE_MGR(OMAP_DSS_CHANNEL_LCD));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
-                RR(DEFAULT_COLOR(2));
-                RR(TRANS_COLOR(2));
-                RR(SIZE_LCD(2));
-                RR(TIMING_H(2));
-                RR(TIMING_V(2));
-                RR(POL_FREQ(2));
-                RR(DIVISORo(2));
+                RR(DEFAULT_COLOR(OMAP_DSS_CHANNEL_LCD2));
+                RR(TRANS_COLOR(OMAP_DSS_CHANNEL_LCD2));
+                RR(SIZE_MGR(OMAP_DSS_CHANNEL_LCD2));
+                RR(TIMING_H(OMAP_DSS_CHANNEL_LCD2));
+                RR(TIMING_V(OMAP_DSS_CHANNEL_LCD2));
+                RR(POL_FREQ(OMAP_DSS_CHANNEL_LCD2));
+                RR(DIVISORo(OMAP_DSS_CHANNEL_LCD2));
                 RR(CONFIG2);
         }
 
-        RR(GFX_BA0);
-        RR(GFX_BA1);
-        RR(GFX_POSITION);
-        RR(GFX_SIZE);
-        RR(GFX_ATTRIBUTES);
-        RR(GFX_FIFO_THRESHOLD);
-        RR(GFX_ROW_INC);
-        RR(GFX_PIXEL_INC);
-        RR(GFX_WINDOW_SKIP);
-        RR(GFX_TABLE_BA);
-
-        RR(DATA_CYCLE1(0));
-        RR(DATA_CYCLE2(0));
-        RR(DATA_CYCLE3(0));
-
-        RR(CPR_COEF_R(0));
-        RR(CPR_COEF_G(0));
-        RR(CPR_COEF_B(0));
+        RR(OVL_BA0(OMAP_DSS_GFX));
+        RR(OVL_BA1(OMAP_DSS_GFX));
+        RR(OVL_POSITION(OMAP_DSS_GFX));
+        RR(OVL_SIZE(OMAP_DSS_GFX));
+        RR(OVL_ATTRIBUTES(OMAP_DSS_GFX));
+        RR(OVL_FIFO_THRESHOLD(OMAP_DSS_GFX));
+        RR(OVL_ROW_INC(OMAP_DSS_GFX));
+        RR(OVL_PIXEL_INC(OMAP_DSS_GFX));
+        RR(OVL_WINDOW_SKIP(OMAP_DSS_GFX));
+        RR(OVL_TABLE_BA(OMAP_DSS_GFX));
+
+
+        RR(DATA_CYCLE1(OMAP_DSS_CHANNEL_LCD));
+        RR(DATA_CYCLE2(OMAP_DSS_CHANNEL_LCD));
+        RR(DATA_CYCLE3(OMAP_DSS_CHANNEL_LCD));
+
+        RR(CPR_COEF_R(OMAP_DSS_CHANNEL_LCD));
+        RR(CPR_COEF_G(OMAP_DSS_CHANNEL_LCD));
+        RR(CPR_COEF_B(OMAP_DSS_CHANNEL_LCD));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
-                RR(DATA_CYCLE1(2));
-                RR(DATA_CYCLE2(2));
-                RR(DATA_CYCLE3(2));
+                RR(DATA_CYCLE1(OMAP_DSS_CHANNEL_LCD2));
+                RR(DATA_CYCLE2(OMAP_DSS_CHANNEL_LCD2));
+                RR(DATA_CYCLE3(OMAP_DSS_CHANNEL_LCD2));
 
-                RR(CPR_COEF_B(2));
-                RR(CPR_COEF_G(2));
-                RR(CPR_COEF_R(2));
+                RR(CPR_COEF_B(OMAP_DSS_CHANNEL_LCD2));
+                RR(CPR_COEF_G(OMAP_DSS_CHANNEL_LCD2));
+                RR(CPR_COEF_R(OMAP_DSS_CHANNEL_LCD2));
         }
 
-        RR(GFX_PRELOAD);
+        RR(OVL_PRELOAD(OMAP_DSS_GFX));
 
         /* VID1 */
-        RR(VID_BA0(0));
-        RR(VID_BA1(0));
-        RR(VID_POSITION(0));
-        RR(VID_SIZE(0));
-        RR(VID_ATTRIBUTES(0));
-        RR(VID_FIFO_THRESHOLD(0));
-        RR(VID_ROW_INC(0));
-        RR(VID_PIXEL_INC(0));
-        RR(VID_FIR(0));
-        RR(VID_PICTURE_SIZE(0));
-        RR(VID_ACCU0(0));
-        RR(VID_ACCU1(0));
-
-        RR(VID_FIR_COEF_H(0, 0));
-        RR(VID_FIR_COEF_H(0, 1));
-        RR(VID_FIR_COEF_H(0, 2));
-        RR(VID_FIR_COEF_H(0, 3));
-        RR(VID_FIR_COEF_H(0, 4));
-        RR(VID_FIR_COEF_H(0, 5));
-        RR(VID_FIR_COEF_H(0, 6));
-        RR(VID_FIR_COEF_H(0, 7));
-
-        RR(VID_FIR_COEF_HV(0, 0));
-        RR(VID_FIR_COEF_HV(0, 1));
-        RR(VID_FIR_COEF_HV(0, 2));
-        RR(VID_FIR_COEF_HV(0, 3));
-        RR(VID_FIR_COEF_HV(0, 4));
-        RR(VID_FIR_COEF_HV(0, 5));
-        RR(VID_FIR_COEF_HV(0, 6));
-        RR(VID_FIR_COEF_HV(0, 7));
-
-        RR(VID_CONV_COEF(0, 0));
-        RR(VID_CONV_COEF(0, 1));
-        RR(VID_CONV_COEF(0, 2));
-        RR(VID_CONV_COEF(0, 3));
-        RR(VID_CONV_COEF(0, 4));
-
-        RR(VID_FIR_COEF_V(0, 0));
-        RR(VID_FIR_COEF_V(0, 1));
-        RR(VID_FIR_COEF_V(0, 2));
-        RR(VID_FIR_COEF_V(0, 3));
-        RR(VID_FIR_COEF_V(0, 4));
-        RR(VID_FIR_COEF_V(0, 5));
-        RR(VID_FIR_COEF_V(0, 6));
-        RR(VID_FIR_COEF_V(0, 7));
-
-        RR(VID_PRELOAD(0));
+        RR(OVL_BA0(OMAP_DSS_VIDEO1));
+        RR(OVL_BA1(OMAP_DSS_VIDEO1));
+        RR(OVL_POSITION(OMAP_DSS_VIDEO1));
+        RR(OVL_SIZE(OMAP_DSS_VIDEO1));
+        RR(OVL_ATTRIBUTES(OMAP_DSS_VIDEO1));
+        RR(OVL_FIFO_THRESHOLD(OMAP_DSS_VIDEO1));
+        RR(OVL_ROW_INC(OMAP_DSS_VIDEO1));
+        RR(OVL_PIXEL_INC(OMAP_DSS_VIDEO1));
+        RR(OVL_FIR(OMAP_DSS_VIDEO1));
+        RR(OVL_PICTURE_SIZE(OMAP_DSS_VIDEO1));
+        RR(OVL_ACCU0(OMAP_DSS_VIDEO1));
+        RR(OVL_ACCU1(OMAP_DSS_VIDEO1));
+
+        for (i = 0; i < 8; i++)
+                RR(OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, i));
+
+        for (i = 0; i < 8; i++)
+                RR(OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, i));
+
+        for (i = 0; i < 5; i++)
+                RR(OVL_CONV_COEF(OMAP_DSS_VIDEO1, i));
+
+        for (i = 0; i < 8; i++)
+                RR(OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, i));
+
+        if (dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) {
+                RR(OVL_BA0_UV(OMAP_DSS_VIDEO1));
+                RR(OVL_BA1_UV(OMAP_DSS_VIDEO1));
+                RR(OVL_FIR2(OMAP_DSS_VIDEO1));
+                RR(OVL_ACCU2_0(OMAP_DSS_VIDEO1));
+                RR(OVL_ACCU2_1(OMAP_DSS_VIDEO1));
+
+                for (i = 0; i < 8; i++)
+                        RR(OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, i));
+
+                for (i = 0; i < 8; i++)
+                        RR(OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, i));
+
+                for (i = 0; i < 8; i++)
+                        RR(OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, i));
+        }
+        if (dss_has_feature(FEAT_ATTR2))
+                RR(OVL_ATTRIBUTES2(OMAP_DSS_VIDEO1));
+
+        RR(OVL_PRELOAD(OMAP_DSS_VIDEO1));
 
         /* VID2 */
-        RR(VID_BA0(1));
-        RR(VID_BA1(1));
-        RR(VID_POSITION(1));
-        RR(VID_SIZE(1));
-        RR(VID_ATTRIBUTES(1));
-        RR(VID_FIFO_THRESHOLD(1));
-        RR(VID_ROW_INC(1));
-        RR(VID_PIXEL_INC(1));
-        RR(VID_FIR(1));
-        RR(VID_PICTURE_SIZE(1));
-        RR(VID_ACCU0(1));
-        RR(VID_ACCU1(1));
-
-        RR(VID_FIR_COEF_H(1, 0));
-        RR(VID_FIR_COEF_H(1, 1));
-        RR(VID_FIR_COEF_H(1, 2));
-        RR(VID_FIR_COEF_H(1, 3));
-        RR(VID_FIR_COEF_H(1, 4));
-        RR(VID_FIR_COEF_H(1, 5));
-        RR(VID_FIR_COEF_H(1, 6));
-        RR(VID_FIR_COEF_H(1, 7));
-
-        RR(VID_FIR_COEF_HV(1, 0));
-        RR(VID_FIR_COEF_HV(1, 1));
-        RR(VID_FIR_COEF_HV(1, 2));
-        RR(VID_FIR_COEF_HV(1, 3));
-        RR(VID_FIR_COEF_HV(1, 4));
-        RR(VID_FIR_COEF_HV(1, 5));
-        RR(VID_FIR_COEF_HV(1, 6));
-        RR(VID_FIR_COEF_HV(1, 7));
-
-        RR(VID_CONV_COEF(1, 0));
-        RR(VID_CONV_COEF(1, 1));
-        RR(VID_CONV_COEF(1, 2));
-        RR(VID_CONV_COEF(1, 3));
-        RR(VID_CONV_COEF(1, 4));
-
-        RR(VID_FIR_COEF_V(1, 0));
-        RR(VID_FIR_COEF_V(1, 1));
-        RR(VID_FIR_COEF_V(1, 2));
-        RR(VID_FIR_COEF_V(1, 3));
-        RR(VID_FIR_COEF_V(1, 4));
-        RR(VID_FIR_COEF_V(1, 5));
-        RR(VID_FIR_COEF_V(1, 6));
-        RR(VID_FIR_COEF_V(1, 7));
-
-        RR(VID_PRELOAD(1));
+        RR(OVL_BA0(OMAP_DSS_VIDEO2));
+        RR(OVL_BA1(OMAP_DSS_VIDEO2));
+        RR(OVL_POSITION(OMAP_DSS_VIDEO2));
+        RR(OVL_SIZE(OMAP_DSS_VIDEO2));
+        RR(OVL_ATTRIBUTES(OMAP_DSS_VIDEO2));
+        RR(OVL_FIFO_THRESHOLD(OMAP_DSS_VIDEO2));
+        RR(OVL_ROW_INC(OMAP_DSS_VIDEO2));
+        RR(OVL_PIXEL_INC(OMAP_DSS_VIDEO2));
+        RR(OVL_FIR(OMAP_DSS_VIDEO2));
+        RR(OVL_PICTURE_SIZE(OMAP_DSS_VIDEO2));
+        RR(OVL_ACCU0(OMAP_DSS_VIDEO2));
+        RR(OVL_ACCU1(OMAP_DSS_VIDEO2));
+
+        for (i = 0; i < 8; i++)
+                RR(OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, i));
+
+        for (i = 0; i < 8; i++)
+                RR(OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, i));
+
+        for (i = 0; i < 5; i++)
+                RR(OVL_CONV_COEF(OMAP_DSS_VIDEO2, i));
+
+        for (i = 0; i < 8; i++)
+                RR(OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, i));
+
+        if (dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) {
+                RR(OVL_BA0_UV(OMAP_DSS_VIDEO2));
+                RR(OVL_BA1_UV(OMAP_DSS_VIDEO2));
+                RR(OVL_FIR2(OMAP_DSS_VIDEO2));
+                RR(OVL_ACCU2_0(OMAP_DSS_VIDEO2));
+                RR(OVL_ACCU2_1(OMAP_DSS_VIDEO2));
+
+                for (i = 0; i < 8; i++)
+                        RR(OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, i));
+
+                for (i = 0; i < 8; i++)
+                        RR(OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, i));
+
+                for (i = 0; i < 8; i++)
+                        RR(OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, i));
+        }
+        if (dss_has_feature(FEAT_ATTR2))
+                RR(OVL_ATTRIBUTES2(OMAP_DSS_VIDEO2));
+
+        RR(OVL_PRELOAD(OMAP_DSS_VIDEO2));
 
         if (dss_has_feature(FEAT_CORE_CLK_DIV))
                 RR(DIVISOR);
@@ -632,27 +551,43 @@ end:
 
 static void _dispc_write_firh_reg(enum omap_plane plane, int reg, u32 value)
 {
+        dispc_write_reg(DISPC_OVL_FIR_COEF_H(plane, reg), value);
+}
+
+static void _dispc_write_firhv_reg(enum omap_plane plane, int reg, u32 value)
+{
+        dispc_write_reg(DISPC_OVL_FIR_COEF_HV(plane, reg), value);
+}
+
+static void _dispc_write_firv_reg(enum omap_plane plane, int reg, u32 value)
+{
+        dispc_write_reg(DISPC_OVL_FIR_COEF_V(plane, reg), value);
+}
+
+static void _dispc_write_firh2_reg(enum omap_plane plane, int reg, u32 value)
+{
         BUG_ON(plane == OMAP_DSS_GFX);
 
-        dispc_write_reg(DISPC_VID_FIR_COEF_H(plane-1, reg), value);
+        dispc_write_reg(DISPC_OVL_FIR_COEF_H2(plane, reg), value);
 }
 
-static void _dispc_write_firhv_reg(enum omap_plane plane, int reg, u32 value)
+static void _dispc_write_firhv2_reg(enum omap_plane plane, int reg, u32 value)
 {
         BUG_ON(plane == OMAP_DSS_GFX);
 
-        dispc_write_reg(DISPC_VID_FIR_COEF_HV(plane-1, reg), value);
+        dispc_write_reg(DISPC_OVL_FIR_COEF_HV2(plane, reg), value);
 }
 
-static void _dispc_write_firv_reg(enum omap_plane plane, int reg, u32 value)
+static void _dispc_write_firv2_reg(enum omap_plane plane, int reg, u32 value)
 {
         BUG_ON(plane == OMAP_DSS_GFX);
 
-        dispc_write_reg(DISPC_VID_FIR_COEF_V(plane-1, reg), value);
+        dispc_write_reg(DISPC_OVL_FIR_COEF_V2(plane, reg), value);
 }
 
 static void _dispc_set_scale_coef(enum omap_plane plane, int hscaleup,
-                int vscaleup, int five_taps)
+                                  int vscaleup, int five_taps,
+                                  enum omap_color_component color_comp)
 {
         /* Coefficients for horizontal up-sampling */
         static const struct dispc_h_coef coef_hup[8] = {
@@ -750,8 +685,14 @@ static void _dispc_set_scale_coef(enum omap_plane plane, int hscaleup,
                         | FLD_VAL(v_coef[i].vc1, 23, 16)
                         | FLD_VAL(v_coef[i].vc2, 31, 24);
 
-                _dispc_write_firh_reg(plane, i, h);
-                _dispc_write_firhv_reg(plane, i, hv);
+                if (color_comp == DISPC_COLOR_COMPONENT_RGB_Y) {
+                        _dispc_write_firh_reg(plane, i, h);
+                        _dispc_write_firhv_reg(plane, i, hv);
+                } else {
+                        _dispc_write_firh2_reg(plane, i, h);
+                        _dispc_write_firhv2_reg(plane, i, hv);
+                }
+
         }
 
         if (five_taps) {
@@ -759,7 +700,10 @@ static void _dispc_set_scale_coef(enum omap_plane plane, int hscaleup,
                         u32 v;
                         v = FLD_VAL(v_coef[i].vc00, 7, 0)
                                 | FLD_VAL(v_coef[i].vc22, 15, 8);
-                        _dispc_write_firv_reg(plane, i, v);
+                        if (color_comp == DISPC_COLOR_COMPONENT_RGB_Y)
+                                _dispc_write_firv_reg(plane, i, v);
+                        else
+                                _dispc_write_firv2_reg(plane, i, v);
                 }
         }
 }
@@ -779,72 +723,83 @@ static void _dispc_setup_color_conv_coef(void)
 
         ct = &ctbl_bt601_5;
 
-        dispc_write_reg(DISPC_VID_CONV_COEF(0, 0), CVAL(ct->rcr, ct->ry));
-        dispc_write_reg(DISPC_VID_CONV_COEF(0, 1), CVAL(ct->gy,  ct->rcb));
-        dispc_write_reg(DISPC_VID_CONV_COEF(0, 2), CVAL(ct->gcb, ct->gcr));
-        dispc_write_reg(DISPC_VID_CONV_COEF(0, 3), CVAL(ct->bcr, ct->by));
-        dispc_write_reg(DISPC_VID_CONV_COEF(0, 4), CVAL(0,       ct->bcb));
-
-        dispc_write_reg(DISPC_VID_CONV_COEF(1, 0), CVAL(ct->rcr, ct->ry));
-        dispc_write_reg(DISPC_VID_CONV_COEF(1, 1), CVAL(ct->gy,  ct->rcb));
-        dispc_write_reg(DISPC_VID_CONV_COEF(1, 2), CVAL(ct->gcb, ct->gcr));
-        dispc_write_reg(DISPC_VID_CONV_COEF(1, 3), CVAL(ct->bcr, ct->by));
-        dispc_write_reg(DISPC_VID_CONV_COEF(1, 4), CVAL(0,       ct->bcb));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 0),
+                CVAL(ct->rcr, ct->ry));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 1),
+                CVAL(ct->gy,  ct->rcb));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 2),
+                CVAL(ct->gcb, ct->gcr));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 3),
+                CVAL(ct->bcr, ct->by));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 4),
+                CVAL(0, ct->bcb));
+
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 0),
+                CVAL(ct->rcr, ct->ry));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 1),
+                CVAL(ct->gy, ct->rcb));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 2),
+                CVAL(ct->gcb, ct->gcr));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 3),
+                CVAL(ct->bcr, ct->by));
+        dispc_write_reg(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 4),
+                CVAL(0, ct->bcb));
 
 #undef CVAL
 
-        REG_FLD_MOD(DISPC_VID_ATTRIBUTES(0), ct->full_range, 11, 11);
-        REG_FLD_MOD(DISPC_VID_ATTRIBUTES(1), ct->full_range, 11, 11);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(OMAP_DSS_VIDEO1),
+                ct->full_range, 11, 11);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(OMAP_DSS_VIDEO2),
+                ct->full_range, 11, 11);
 }
 
 
 static void _dispc_set_plane_ba0(enum omap_plane plane, u32 paddr)
 {
-        const struct dispc_reg ba0_reg[] = { DISPC_GFX_BA0,
-                DISPC_VID_BA0(0),
-                DISPC_VID_BA0(1) };
-
-        dispc_write_reg(ba0_reg[plane], paddr);
+        dispc_write_reg(DISPC_OVL_BA0(plane), paddr);
 }
 
 static void _dispc_set_plane_ba1(enum omap_plane plane, u32 paddr)
 {
-        const struct dispc_reg ba1_reg[] = { DISPC_GFX_BA1,
-                                      DISPC_VID_BA1(0),
-                                      DISPC_VID_BA1(1) };
+        dispc_write_reg(DISPC_OVL_BA1(plane), paddr);
+}
 
-        dispc_write_reg(ba1_reg[plane], paddr);
+static void _dispc_set_plane_ba0_uv(enum omap_plane plane, u32 paddr)
+{
+        dispc_write_reg(DISPC_OVL_BA0_UV(plane), paddr);
 }
 
-static void _dispc_set_plane_pos(enum omap_plane plane, int x, int y)
+static void _dispc_set_plane_ba1_uv(enum omap_plane plane, u32 paddr)
 {
-        const struct dispc_reg pos_reg[] = { DISPC_GFX_POSITION,
-                                      DISPC_VID_POSITION(0),
-                                      DISPC_VID_POSITION(1) };
+        dispc_write_reg(DISPC_OVL_BA1_UV(plane), paddr);
+}
 
+static void _dispc_set_plane_pos(enum omap_plane plane, int x, int y)
+{
         u32 val = FLD_VAL(y, 26, 16) | FLD_VAL(x, 10, 0);
-        dispc_write_reg(pos_reg[plane], val);
+
+        dispc_write_reg(DISPC_OVL_POSITION(plane), val);
 }
 
 static void _dispc_set_pic_size(enum omap_plane plane, int width, int height)
 {
-        const struct dispc_reg siz_reg[] = { DISPC_GFX_SIZE,
-                                      DISPC_VID_PICTURE_SIZE(0),
-                                      DISPC_VID_PICTURE_SIZE(1) };
         u32 val = FLD_VAL(height - 1, 26, 16) | FLD_VAL(width - 1, 10, 0);
-        dispc_write_reg(siz_reg[plane], val);
+
+        if (plane == OMAP_DSS_GFX)
+                dispc_write_reg(DISPC_OVL_SIZE(plane), val);
+        else
+                dispc_write_reg(DISPC_OVL_PICTURE_SIZE(plane), val);
 }
 
 static void _dispc_set_vid_size(enum omap_plane plane, int width, int height)
 {
         u32 val;
-        const struct dispc_reg vsi_reg[] = { DISPC_VID_SIZE(0),
-                                      DISPC_VID_SIZE(1) };
 
         BUG_ON(plane == OMAP_DSS_GFX);
 
         val = FLD_VAL(height - 1, 26, 16) | FLD_VAL(width - 1, 10, 0);
-        dispc_write_reg(vsi_reg[plane-1], val);
+
+        dispc_write_reg(DISPC_OVL_SIZE(plane), val);
 }
 
 static void _dispc_set_pre_mult_alpha(enum omap_plane plane, bool enable)
@@ -856,7 +811,7 @@ static void _dispc_set_pre_mult_alpha(enum omap_plane plane, bool enable)
                 plane == OMAP_DSS_VIDEO1)
                 return;
 
-        REG_FLD_MOD(dispc_reg_att[plane], enable ? 1 : 0, 28, 28);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), enable ? 1 : 0, 28, 28);
 }
 
 static void _dispc_setup_global_alpha(enum omap_plane plane, u8 global_alpha)
@@ -876,61 +831,93 @@ static void _dispc_setup_global_alpha(enum omap_plane plane, u8 global_alpha)
 
 static void _dispc_set_pix_inc(enum omap_plane plane, s32 inc)
 {
-        const struct dispc_reg ri_reg[] = { DISPC_GFX_PIXEL_INC,
-                                     DISPC_VID_PIXEL_INC(0),
-                                     DISPC_VID_PIXEL_INC(1) };
-
-        dispc_write_reg(ri_reg[plane], inc);
+        dispc_write_reg(DISPC_OVL_PIXEL_INC(plane), inc);
 }
 
 static void _dispc_set_row_inc(enum omap_plane plane, s32 inc)
 {
-        const struct dispc_reg ri_reg[] = { DISPC_GFX_ROW_INC,
-                                     DISPC_VID_ROW_INC(0),
-                                     DISPC_VID_ROW_INC(1) };
-
-        dispc_write_reg(ri_reg[plane], inc);
+        dispc_write_reg(DISPC_OVL_ROW_INC(plane), inc);
 }
 
 static void _dispc_set_color_mode(enum omap_plane plane,
                 enum omap_color_mode color_mode)
 {
         u32 m = 0;
-
-        switch (color_mode) {
-        case OMAP_DSS_COLOR_CLUT1:
-                m = 0x0; break;
-        case OMAP_DSS_COLOR_CLUT2:
-                m = 0x1; break;
-        case OMAP_DSS_COLOR_CLUT4:
-                m = 0x2; break;
-        case OMAP_DSS_COLOR_CLUT8:
-                m = 0x3; break;
-        case OMAP_DSS_COLOR_RGB12U:
-                m = 0x4; break;
-        case OMAP_DSS_COLOR_ARGB16:
-                m = 0x5; break;
-        case OMAP_DSS_COLOR_RGB16:
-                m = 0x6; break;
-        case OMAP_DSS_COLOR_RGB24U:
-                m = 0x8; break;
-        case OMAP_DSS_COLOR_RGB24P:
-                m = 0x9; break;
-        case OMAP_DSS_COLOR_YUV2:
-                m = 0xa; break;
-        case OMAP_DSS_COLOR_UYVY:
-                m = 0xb; break;
-        case OMAP_DSS_COLOR_ARGB32:
-                m = 0xc; break;
-        case OMAP_DSS_COLOR_RGBA32:
-                m = 0xd; break;
-        case OMAP_DSS_COLOR_RGBX32:
-                m = 0xe; break;
-        default:
-                BUG(); break;
+        if (plane != OMAP_DSS_GFX) {
+                switch (color_mode) {
+                case OMAP_DSS_COLOR_NV12:
+                        m = 0x0; break;
+                case OMAP_DSS_COLOR_RGB12U:
+                        m = 0x1; break;
+                case OMAP_DSS_COLOR_RGBA16:
+                        m = 0x2; break;
+                case OMAP_DSS_COLOR_RGBX16:
+                        m = 0x4; break;
+                case OMAP_DSS_COLOR_ARGB16:
+                        m = 0x5; break;
+                case OMAP_DSS_COLOR_RGB16:
+                        m = 0x6; break;
+                case OMAP_DSS_COLOR_ARGB16_1555:
+                        m = 0x7; break;
+                case OMAP_DSS_COLOR_RGB24U:
+                        m = 0x8; break;
+                case OMAP_DSS_COLOR_RGB24P:
+                        m = 0x9; break;
+                case OMAP_DSS_COLOR_YUV2:
+                        m = 0xa; break;
+                case OMAP_DSS_COLOR_UYVY:
+                        m = 0xb; break;
+                case OMAP_DSS_COLOR_ARGB32:
+                        m = 0xc; break;
+                case OMAP_DSS_COLOR_RGBA32:
+                        m = 0xd; break;
+                case OMAP_DSS_COLOR_RGBX32:
+                        m = 0xe; break;
+                case OMAP_DSS_COLOR_XRGB16_1555:
+                        m = 0xf; break;
+                default:
+                        BUG(); break;
+                }
+        } else {
+                switch (color_mode) {
+                case OMAP_DSS_COLOR_CLUT1:
+                        m = 0x0; break;
+                case OMAP_DSS_COLOR_CLUT2:
+                        m = 0x1; break;
+                case OMAP_DSS_COLOR_CLUT4:
+                        m = 0x2; break;
+                case OMAP_DSS_COLOR_CLUT8:
+                        m = 0x3; break;
+                case OMAP_DSS_COLOR_RGB12U:
+                        m = 0x4; break;
+                case OMAP_DSS_COLOR_ARGB16:
+                        m = 0x5; break;
+                case OMAP_DSS_COLOR_RGB16:
+                        m = 0x6; break;
+                case OMAP_DSS_COLOR_ARGB16_1555:
+                        m = 0x7; break;
+                case OMAP_DSS_COLOR_RGB24U:
+                        m = 0x8; break;
+                case OMAP_DSS_COLOR_RGB24P:
+                        m = 0x9; break;
+                case OMAP_DSS_COLOR_YUV2:
+                        m = 0xa; break;
+                case OMAP_DSS_COLOR_UYVY:
+                        m = 0xb; break;
+                case OMAP_DSS_COLOR_ARGB32:
+                        m = 0xc; break;
+                case OMAP_DSS_COLOR_RGBA32:
+                        m = 0xd; break;
+                case OMAP_DSS_COLOR_RGBX32:
+                        m = 0xe; break;
+                case OMAP_DSS_COLOR_XRGB16_1555:
+                        m = 0xf; break;
+                default:
+                        BUG(); break;
+                }
         }
 
-        REG_FLD_MOD(dispc_reg_att[plane], m, 4, 1);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), m, 4, 1);
 }
 
 static void _dispc_set_channel_out(enum omap_plane plane,
@@ -953,7 +940,7 @@ static void _dispc_set_channel_out(enum omap_plane plane,
                 return;
         }
 
-        val = dispc_read_reg(dispc_reg_att[plane]);
+        val = dispc_read_reg(DISPC_OVL_ATTRIBUTES(plane));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
                 switch (channel) {
                 case OMAP_DSS_CHANNEL_LCD:
@@ -977,7 +964,7 @@ static void _dispc_set_channel_out(enum omap_plane plane,
         } else {
                 val = FLD_MOD(val, channel, shift, shift);
         }
-        dispc_write_reg(dispc_reg_att[plane], val);
+        dispc_write_reg(DISPC_OVL_ATTRIBUTES(plane), val);
 }
 
 void dispc_set_burst_size(enum omap_plane plane,
@@ -1001,9 +988,9 @@ void dispc_set_burst_size(enum omap_plane plane,
                 return;
         }
 
-        val = dispc_read_reg(dispc_reg_att[plane]);
+        val = dispc_read_reg(DISPC_OVL_ATTRIBUTES(plane));
         val = FLD_MOD(val, burst_size, shift+1, shift);
-        dispc_write_reg(dispc_reg_att[plane], val);
+        dispc_write_reg(DISPC_OVL_ATTRIBUTES(plane), val);
 
         enable_clocks(0);
 }
@@ -1028,9 +1015,9 @@ static void _dispc_set_vid_color_conv(enum omap_plane plane, bool enable)
 
         BUG_ON(plane == OMAP_DSS_GFX);
 
-        val = dispc_read_reg(dispc_reg_att[plane]);
+        val = dispc_read_reg(DISPC_OVL_ATTRIBUTES(plane));
         val = FLD_MOD(val, enable, 9, 9);
-        dispc_write_reg(dispc_reg_att[plane], val);
+        dispc_write_reg(DISPC_OVL_ATTRIBUTES(plane), val);
 }
 
 void dispc_enable_replication(enum omap_plane plane, bool enable)
@@ -1043,7 +1030,7 @@ void dispc_enable_replication(enum omap_plane plane, bool enable)
                 bit = 10;
 
         enable_clocks(1);
-        REG_FLD_MOD(dispc_reg_att[plane], enable, bit, bit);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), enable, bit, bit);
         enable_clocks(0);
 }
 
@@ -1053,7 +1040,7 @@ void dispc_set_lcd_size(enum omap_channel channel, u16 width, u16 height)
         BUG_ON((width > (1 << 11)) || (height > (1 << 11)));
         val = FLD_VAL(height - 1, 26, 16) | FLD_VAL(width - 1, 10, 0);
         enable_clocks(1);
-        dispc_write_reg(DISPC_SIZE_LCD(channel), val);
+        dispc_write_reg(DISPC_SIZE_MGR(channel), val);
         enable_clocks(0);
 }
 
@@ -1063,15 +1050,12 @@ void dispc_set_digit_size(u16 width, u16 height)
         BUG_ON((width > (1 << 11)) || (height > (1 << 11)));
         val = FLD_VAL(height - 1, 26, 16) | FLD_VAL(width - 1, 10, 0);
         enable_clocks(1);
-        dispc_write_reg(DISPC_SIZE_DIG, val);
+        dispc_write_reg(DISPC_SIZE_MGR(OMAP_DSS_CHANNEL_DIGIT), val);
         enable_clocks(0);
 }
 
 static void dispc_read_plane_fifo_sizes(void)
 {
-        const struct dispc_reg fsz_reg[] = { DISPC_GFX_FIFO_SIZE_STATUS,
-                                      DISPC_VID_FIFO_SIZE_STATUS(0),
-                                      DISPC_VID_FIFO_SIZE_STATUS(1) };
         u32 size;
         int plane;
         u8 start, end;
@@ -1081,7 +1065,8 @@ static void dispc_read_plane_fifo_sizes(void)
         dss_feat_get_reg_field(FEAT_REG_FIFOSIZE, &start, &end);
 
         for (plane = 0; plane < ARRAY_SIZE(dispc.fifo_size); ++plane) {
-                size = FLD_GET(dispc_read_reg(fsz_reg[plane]), start, end);
+                size = FLD_GET(dispc_read_reg(DISPC_OVL_FIFO_SIZE_STATUS(plane)),
+                        start, end);
                 dispc.fifo_size[plane] = size;
         }
 
@@ -1095,23 +1080,22 @@ u32 dispc_get_plane_fifo_size(enum omap_plane plane)
 
 void dispc_setup_plane_fifo(enum omap_plane plane, u32 low, u32 high)
 {
-        const struct dispc_reg ftrs_reg[] = { DISPC_GFX_FIFO_THRESHOLD,
-                                       DISPC_VID_FIFO_THRESHOLD(0),
-                                       DISPC_VID_FIFO_THRESHOLD(1) };
         u8 hi_start, hi_end, lo_start, lo_end;
 
+        dss_feat_get_reg_field(FEAT_REG_FIFOHIGHTHRESHOLD, &hi_start, &hi_end);
+        dss_feat_get_reg_field(FEAT_REG_FIFOLOWTHRESHOLD, &lo_start, &lo_end);
+
         enable_clocks(1);
 
         DSSDBG("fifo(%d) low/high old %u/%u, new %u/%u\n",
                         plane,
-                        REG_GET(ftrs_reg[plane], 11, 0),
-                        REG_GET(ftrs_reg[plane], 27, 16),
+                        REG_GET(DISPC_OVL_FIFO_THRESHOLD(plane),
+                                lo_start, lo_end),
+                        REG_GET(DISPC_OVL_FIFO_THRESHOLD(plane),
+                                hi_start, hi_end),
                         low, high);
 
-        dss_feat_get_reg_field(FEAT_REG_FIFOHIGHTHRESHOLD, &hi_start, &hi_end);
-        dss_feat_get_reg_field(FEAT_REG_FIFOLOWTHRESHOLD, &lo_start, &lo_end);
-
-        dispc_write_reg(ftrs_reg[plane],
+        dispc_write_reg(DISPC_OVL_FIFO_THRESHOLD(plane),
                         FLD_VAL(high, hi_start, hi_end) |
                         FLD_VAL(low, lo_start, lo_end));
 
@@ -1128,106 +1112,120 @@ void dispc_enable_fifomerge(bool enable)
         enable_clocks(0);
 }
 
-static void _dispc_set_fir(enum omap_plane plane, int hinc, int vinc)
+static void _dispc_set_fir(enum omap_plane plane,
+                                int hinc, int vinc,
+                                enum omap_color_component color_comp)
 {
         u32 val;
-        const struct dispc_reg fir_reg[] = { DISPC_VID_FIR(0),
-                                      DISPC_VID_FIR(1) };
-        u8 hinc_start, hinc_end, vinc_start, vinc_end;
-
-        BUG_ON(plane == OMAP_DSS_GFX);
 
-        dss_feat_get_reg_field(FEAT_REG_FIRHINC, &hinc_start, &hinc_end);
-        dss_feat_get_reg_field(FEAT_REG_FIRVINC, &vinc_start, &vinc_end);
+        if (color_comp == DISPC_COLOR_COMPONENT_RGB_Y) {
+                u8 hinc_start, hinc_end, vinc_start, vinc_end;
 
-        val = FLD_VAL(vinc, vinc_start, vinc_end) |
-                        FLD_VAL(hinc, hinc_start, hinc_end);
+                dss_feat_get_reg_field(FEAT_REG_FIRHINC,
+                                        &hinc_start, &hinc_end);
+                dss_feat_get_reg_field(FEAT_REG_FIRVINC,
+                                        &vinc_start, &vinc_end);
+                val = FLD_VAL(vinc, vinc_start, vinc_end) |
+                                FLD_VAL(hinc, hinc_start, hinc_end);
 
-        dispc_write_reg(fir_reg[plane-1], val);
+                dispc_write_reg(DISPC_OVL_FIR(plane), val);
+        } else {
+                val = FLD_VAL(vinc, 28, 16) | FLD_VAL(hinc, 12, 0);
+                dispc_write_reg(DISPC_OVL_FIR2(plane), val);
+        }
 }
 
 static void _dispc_set_vid_accu0(enum omap_plane plane, int haccu, int vaccu)
 {
         u32 val;
-        const struct dispc_reg ac0_reg[] = { DISPC_VID_ACCU0(0),
-                                      DISPC_VID_ACCU0(1) };
         u8 hor_start, hor_end, vert_start, vert_end;
 
-        BUG_ON(plane == OMAP_DSS_GFX);
-
         dss_feat_get_reg_field(FEAT_REG_HORIZONTALACCU, &hor_start, &hor_end);
         dss_feat_get_reg_field(FEAT_REG_VERTICALACCU, &vert_start, &vert_end);
 
         val = FLD_VAL(vaccu, vert_start, vert_end) |
                         FLD_VAL(haccu, hor_start, hor_end);
 
-        dispc_write_reg(ac0_reg[plane-1], val);
+        dispc_write_reg(DISPC_OVL_ACCU0(plane), val);
 }
 
 static void _dispc_set_vid_accu1(enum omap_plane plane, int haccu, int vaccu)
 {
         u32 val;
-        const struct dispc_reg ac1_reg[] = { DISPC_VID_ACCU1(0),
-                                      DISPC_VID_ACCU1(1) };
         u8 hor_start, hor_end, vert_start, vert_end;
 
-        BUG_ON(plane == OMAP_DSS_GFX);
-
         dss_feat_get_reg_field(FEAT_REG_HORIZONTALACCU, &hor_start, &hor_end);
         dss_feat_get_reg_field(FEAT_REG_VERTICALACCU, &vert_start, &vert_end);
 
         val = FLD_VAL(vaccu, vert_start, vert_end) |
                         FLD_VAL(haccu, hor_start, hor_end);
 
-        dispc_write_reg(ac1_reg[plane-1], val);
+        dispc_write_reg(DISPC_OVL_ACCU1(plane), val);
+}
+
+static void _dispc_set_vid_accu2_0(enum omap_plane plane, int haccu, int vaccu)
+{
+        u32 val;
+
+        val = FLD_VAL(vaccu, 26, 16) | FLD_VAL(haccu, 10, 0);
+        dispc_write_reg(DISPC_OVL_ACCU2_0(plane), val);
 }
 
+static void _dispc_set_vid_accu2_1(enum omap_plane plane, int haccu, int vaccu)
+{
+        u32 val;
 
-static void _dispc_set_scaling(enum omap_plane plane,
+        val = FLD_VAL(vaccu, 26, 16) | FLD_VAL(haccu, 10, 0);
+        dispc_write_reg(DISPC_OVL_ACCU2_1(plane), val);
+}
+
+static void _dispc_set_scale_param(enum omap_plane plane,
                 u16 orig_width, u16 orig_height,
                 u16 out_width, u16 out_height,
-                bool ilace, bool five_taps,
-                bool fieldmode)
+                bool five_taps, u8 rotation,
+                enum omap_color_component color_comp)
 {
-        int fir_hinc;
-        int fir_vinc;
+        int fir_hinc, fir_vinc;
         int hscaleup, vscaleup;
-        int accu0 = 0;
-        int accu1 = 0;
-        u32 l;
-
-        BUG_ON(plane == OMAP_DSS_GFX);
 
         hscaleup = orig_width <= out_width;
         vscaleup = orig_height <= out_height;
 
-        _dispc_set_scale_coef(plane, hscaleup, vscaleup, five_taps);
+        _dispc_set_scale_coef(plane, hscaleup, vscaleup, five_taps, color_comp);
 
-        if (!orig_width || orig_width == out_width)
-                fir_hinc = 0;
-        else
-                fir_hinc = 1024 * orig_width / out_width;
+        fir_hinc = 1024 * orig_width / out_width;
+        fir_vinc = 1024 * orig_height / out_height;
 
-        if (!orig_height || orig_height == out_height)
-                fir_vinc = 0;
-        else
-                fir_vinc = 1024 * orig_height / out_height;
+        _dispc_set_fir(plane, fir_hinc, fir_vinc, color_comp);
+}
 
-        _dispc_set_fir(plane, fir_hinc, fir_vinc);
+static void _dispc_set_scaling_common(enum omap_plane plane,
+                u16 orig_width, u16 orig_height,
+                u16 out_width, u16 out_height,
+                bool ilace, bool five_taps,
+                bool fieldmode, enum omap_color_mode color_mode,
+                u8 rotation)
+{
+        int accu0 = 0;
+        int accu1 = 0;
+        u32 l;
 
-        l = dispc_read_reg(dispc_reg_att[plane]);
+        _dispc_set_scale_param(plane, orig_width, orig_height,
+                                out_width, out_height, five_taps,
+                                rotation, DISPC_COLOR_COMPONENT_RGB_Y);
+        l = dispc_read_reg(DISPC_OVL_ATTRIBUTES(plane));
 
         /* RESIZEENABLE and VERTICALTAPS */
         l &= ~((0x3 << 5) | (0x1 << 21));
-        l |= fir_hinc ? (1 << 5) : 0;
-        l |= fir_vinc ? (1 << 6) : 0;
+        l |= (orig_width != out_width) ? (1 << 5) : 0;
+        l |= (orig_height != out_height) ? (1 << 6) : 0;
         l |= five_taps ? (1 << 21) : 0;
 
         /* VRESIZECONF and HRESIZECONF */
         if (dss_has_feature(FEAT_RESIZECONF)) {
                 l &= ~(0x3 << 7);
-                l |= hscaleup ? 0 : (1 << 7);
-                l |= vscaleup ? 0 : (1 << 8);
+                l |= (orig_width <= out_width) ? 0 : (1 << 7);
+                l |= (orig_height <= out_height) ? 0 : (1 << 8);
         }
 
         /* LINEBUFFERSPLIT */
@@ -1236,7 +1234,7 @@ static void _dispc_set_scaling(enum omap_plane plane,
                 l |= five_taps ? (1 << 22) : 0;
         }
 
-        dispc_write_reg(dispc_reg_att[plane], l);
+        dispc_write_reg(DISPC_OVL_ATTRIBUTES(plane), l);
 
         /*
          * field 0 = even field = bottom field
@@ -1244,7 +1242,7 @@ static void _dispc_set_scaling(enum omap_plane plane,
          */
         if (ilace && !fieldmode) {
                 accu1 = 0;
-                accu0 = (fir_vinc / 2) & 0x3ff;
+                accu0 = ((1024 * orig_height / out_height) / 2) & 0x3ff;
                 if (accu0 >= 1024/2) {
                         accu1 = 1024/2;
                         accu0 -= accu1;
@@ -1255,6 +1253,93 @@ static void _dispc_set_scaling(enum omap_plane plane,
         _dispc_set_vid_accu1(plane, 0, accu1);
 }
 
+static void _dispc_set_scaling_uv(enum omap_plane plane,
+                u16 orig_width, u16 orig_height,
+                u16 out_width, u16 out_height,
+                bool ilace, bool five_taps,
+                bool fieldmode, enum omap_color_mode color_mode,
+                u8 rotation)
+{
+        int scale_x = out_width != orig_width;
+        int scale_y = out_height != orig_height;
+
+        if (!dss_has_feature(FEAT_HANDLE_UV_SEPARATE))
+                return;
+        if ((color_mode != OMAP_DSS_COLOR_YUV2 &&
+                        color_mode != OMAP_DSS_COLOR_UYVY &&
+                        color_mode != OMAP_DSS_COLOR_NV12)) {
+                /* reset chroma resampling for RGB formats  */
+                REG_FLD_MOD(DISPC_OVL_ATTRIBUTES2(plane), 0, 8, 8);
+                return;
+        }
+        switch (color_mode) {
+        case OMAP_DSS_COLOR_NV12:
+                /* UV is subsampled by 2 vertically*/
+                orig_height >>= 1;
+                /* UV is subsampled by 2 horz.*/
+                orig_width >>= 1;
+                break;
+        case OMAP_DSS_COLOR_YUV2:
+        case OMAP_DSS_COLOR_UYVY:
+                /*For YUV422 with 90/270 rotation,
+                 *we don't upsample chroma
+                 */
+                if (rotation == OMAP_DSS_ROT_0 ||
+                        rotation == OMAP_DSS_ROT_180)
+                        /* UV is subsampled by 2 hrz*/
+                        orig_width >>= 1;
+                /* must use FIR for YUV422 if rotated */
+                if (rotation != OMAP_DSS_ROT_0)
+                        scale_x = scale_y = true;
+                break;
+        default:
+                BUG();
+        }
+
+        if (out_width != orig_width)
+                scale_x = true;
+        if (out_height != orig_height)
+                scale_y = true;
+
+        _dispc_set_scale_param(plane, orig_width, orig_height,
+                        out_width, out_height, five_taps,
+                                rotation, DISPC_COLOR_COMPONENT_UV);
+
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES2(plane),
+                (scale_x || scale_y) ? 1 : 0, 8, 8);
+        /* set H scaling */
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), scale_x ? 1 : 0, 5, 5);
+        /* set V scaling */
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), scale_y ? 1 : 0, 6, 6);
+
+        _dispc_set_vid_accu2_0(plane, 0x80, 0);
+        _dispc_set_vid_accu2_1(plane, 0x80, 0);
+}
+
+static void _dispc_set_scaling(enum omap_plane plane,
+                u16 orig_width, u16 orig_height,
+                u16 out_width, u16 out_height,
+                bool ilace, bool five_taps,
+                bool fieldmode, enum omap_color_mode color_mode,
+                u8 rotation)
+{
+        BUG_ON(plane == OMAP_DSS_GFX);
+
+        _dispc_set_scaling_common(plane,
+                        orig_width, orig_height,
+                        out_width, out_height,
+                        ilace, five_taps,
+                        fieldmode, color_mode,
+                        rotation);
+
+        _dispc_set_scaling_uv(plane,
+                orig_width, orig_height,
+                out_width, out_height,
+                ilace, five_taps,
+                fieldmode, color_mode,
+                rotation);
+}
+
 static void _dispc_set_rotation_attrs(enum omap_plane plane, u8 rotation,
                 bool mirroring, enum omap_color_mode color_mode)
 {
@@ -1302,9 +1387,10 @@ static void _dispc_set_rotation_attrs(enum omap_plane plane, u8 rotation,
                         row_repeat = false;
         }
 
-        REG_FLD_MOD(dispc_reg_att[plane], vidrot, 13, 12);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), vidrot, 13, 12);
         if (dss_has_feature(FEAT_ROWREPEATENABLE))
-                REG_FLD_MOD(dispc_reg_att[plane], row_repeat ? 1 : 0, 18, 18);
+                REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane),
+                        row_repeat ? 1 : 0, 18, 18);
 }
 
 static int color_mode_to_bpp(enum omap_color_mode color_mode)
@@ -1317,12 +1403,17 @@ static int color_mode_to_bpp(enum omap_color_mode color_mode)
         case OMAP_DSS_COLOR_CLUT4:
                 return 4;
         case OMAP_DSS_COLOR_CLUT8:
+        case OMAP_DSS_COLOR_NV12:
                 return 8;
         case OMAP_DSS_COLOR_RGB12U:
         case OMAP_DSS_COLOR_RGB16:
         case OMAP_DSS_COLOR_ARGB16:
         case OMAP_DSS_COLOR_YUV2:
         case OMAP_DSS_COLOR_UYVY:
+        case OMAP_DSS_COLOR_RGBA16:
+        case OMAP_DSS_COLOR_RGBX16:
+        case OMAP_DSS_COLOR_ARGB16_1555:
+        case OMAP_DSS_COLOR_XRGB16_1555:
                 return 16;
         case OMAP_DSS_COLOR_RGB24P:
                 return 24;
@@ -1655,7 +1746,7 @@ static int _dispc_setup_plane(enum omap_plane plane,
                 enum omap_dss_rotation_type rotation_type,
                 u8 rotation, int mirror,
                 u8 global_alpha, u8 pre_mult_alpha,
-                enum omap_channel channel)
+                enum omap_channel channel, u32 puv_addr)
 {
         const int maxdownscale = cpu_is_omap34xx() ? 4 : 2;
         bool five_taps = 0;
@@ -1704,7 +1795,8 @@ static int _dispc_setup_plane(enum omap_plane plane,
                         return -EINVAL;
 
                 if (color_mode == OMAP_DSS_COLOR_YUV2 ||
-                        color_mode == OMAP_DSS_COLOR_UYVY)
+                        color_mode == OMAP_DSS_COLOR_UYVY ||
+                        color_mode == OMAP_DSS_COLOR_NV12)
                         cconv = 1;
 
                 /* Must use 5-tap filter? */
@@ -1778,6 +1870,12 @@ static int _dispc_setup_plane(enum omap_plane plane,
         _dispc_set_plane_ba0(plane, paddr + offset0);
         _dispc_set_plane_ba1(plane, paddr + offset1);
 
+        if (OMAP_DSS_COLOR_NV12 == color_mode) {
+                _dispc_set_plane_ba0_uv(plane, puv_addr + offset0);
+                _dispc_set_plane_ba1_uv(plane, puv_addr + offset1);
+        }
+
+
         _dispc_set_row_inc(plane, row_inc);
         _dispc_set_pix_inc(plane, pix_inc);
 
@@ -1791,7 +1889,8 @@ static int _dispc_setup_plane(enum omap_plane plane,
         if (plane != OMAP_DSS_GFX) {
                 _dispc_set_scaling(plane, width, height,
                                    out_width, out_height,
-                                   ilace, five_taps, fieldmode);
+                                   ilace, five_taps, fieldmode,
+                                   color_mode, rotation);
                 _dispc_set_vid_size(plane, out_width, out_height);
                 _dispc_set_vid_color_conv(plane, cconv);
         }
@@ -1806,7 +1905,7 @@ static int _dispc_setup_plane(enum omap_plane plane,
 
 static void _dispc_enable_plane(enum omap_plane plane, bool enable)
 {
-        REG_FLD_MOD(dispc_reg_att[plane], enable ? 1 : 0, 0, 0);
+        REG_FLD_MOD(DISPC_OVL_ATTRIBUTES(plane), enable ? 1 : 0, 0, 0);
 }
 
 static void dispc_disable_isr(void *data, u32 mask)
@@ -2353,14 +2452,20 @@ static void dispc_get_lcd_divisor(enum omap_channel channel, int *lck_div,
 
 unsigned long dispc_fclk_rate(void)
 {
+        struct platform_device *dsidev;
         unsigned long r = 0;
 
         switch (dss_get_dispc_clk_source()) {
-        case DSS_CLK_SRC_FCK:
+        case OMAP_DSS_CLK_SRC_FCK:
                 r = dss_clk_get_rate(DSS_CLK_FCK);
                 break;
-        case DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
-                r = dsi_get_pll_hsdiv_dispc_rate();
+        case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
+                dsidev = dsi_get_dsidev_from_id(0);
+                r = dsi_get_pll_hsdiv_dispc_rate(dsidev);
+                break;
+        case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
+                dsidev = dsi_get_dsidev_from_id(1);
+                r = dsi_get_pll_hsdiv_dispc_rate(dsidev);
                 break;
         default:
                 BUG();
@@ -2371,6 +2476,7 @@ unsigned long dispc_fclk_rate(void)
 
 unsigned long dispc_lclk_rate(enum omap_channel channel)
 {
+        struct platform_device *dsidev;
         int lcd;
         unsigned long r;
         u32 l;
@@ -2380,11 +2486,16 @@ unsigned long dispc_lclk_rate(enum omap_channel channel)
         lcd = FLD_GET(l, 23, 16);
 
         switch (dss_get_lcd_clk_source(channel)) {
-        case DSS_CLK_SRC_FCK:
+        case OMAP_DSS_CLK_SRC_FCK:
                 r = dss_clk_get_rate(DSS_CLK_FCK);
                 break;
-        case DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
-                r = dsi_get_pll_hsdiv_dispc_rate();
+        case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
+                dsidev = dsi_get_dsidev_from_id(0);
+                r = dsi_get_pll_hsdiv_dispc_rate(dsidev);
+                break;
+        case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
+                dsidev = dsi_get_dsidev_from_id(1);
+                r = dsi_get_pll_hsdiv_dispc_rate(dsidev);
                 break;
         default:
                 BUG();
@@ -2412,8 +2523,8 @@ void dispc_dump_clocks(struct seq_file *s)
 {
         int lcd, pcd;
         u32 l;
-        enum dss_clk_source dispc_clk_src = dss_get_dispc_clk_source();
-        enum dss_clk_source lcd_clk_src;
+        enum omap_dss_clk_source dispc_clk_src = dss_get_dispc_clk_source();
+        enum omap_dss_clk_source lcd_clk_src;
 
         enable_clocks(1);
 
@@ -2516,7 +2627,7 @@ void dispc_dump_irqs(struct seq_file *s)
 
 void dispc_dump_regs(struct seq_file *s)
 {
-#define DUMPREG(r) seq_printf(s, "%-35s %08x\n", #r, dispc_read_reg(r))
+#define DUMPREG(r) seq_printf(s, "%-50s %08x\n", #r, dispc_read_reg(r))
 
         dss_clk_enable(DSS_CLK_ICK | DSS_CLK_FCK);
 
@@ -2528,152 +2639,227 @@ void dispc_dump_regs(struct seq_file *s)
         DUMPREG(DISPC_CONTROL);
         DUMPREG(DISPC_CONFIG);
         DUMPREG(DISPC_CAPABLE);
-        DUMPREG(DISPC_DEFAULT_COLOR(0));
-        DUMPREG(DISPC_DEFAULT_COLOR(1));
-        DUMPREG(DISPC_TRANS_COLOR(0));
-        DUMPREG(DISPC_TRANS_COLOR(1));
+        DUMPREG(DISPC_DEFAULT_COLOR(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_DEFAULT_COLOR(OMAP_DSS_CHANNEL_DIGIT));
+        DUMPREG(DISPC_TRANS_COLOR(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_TRANS_COLOR(OMAP_DSS_CHANNEL_DIGIT));
         DUMPREG(DISPC_LINE_STATUS);
         DUMPREG(DISPC_LINE_NUMBER);
-        DUMPREG(DISPC_TIMING_H(0));
-        DUMPREG(DISPC_TIMING_V(0));
-        DUMPREG(DISPC_POL_FREQ(0));
-        DUMPREG(DISPC_DIVISORo(0));
+        DUMPREG(DISPC_TIMING_H(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_TIMING_V(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_POL_FREQ(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_DIVISORo(OMAP_DSS_CHANNEL_LCD));
         DUMPREG(DISPC_GLOBAL_ALPHA);
-        DUMPREG(DISPC_SIZE_DIG);
-        DUMPREG(DISPC_SIZE_LCD(0));
+        DUMPREG(DISPC_SIZE_MGR(OMAP_DSS_CHANNEL_DIGIT));
+        DUMPREG(DISPC_SIZE_MGR(OMAP_DSS_CHANNEL_LCD));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
                 DUMPREG(DISPC_CONTROL2);
                 DUMPREG(DISPC_CONFIG2);
-                DUMPREG(DISPC_DEFAULT_COLOR(2));
-                DUMPREG(DISPC_TRANS_COLOR(2));
-                DUMPREG(DISPC_TIMING_H(2));
-                DUMPREG(DISPC_TIMING_V(2));
-                DUMPREG(DISPC_POL_FREQ(2));
-                DUMPREG(DISPC_DIVISORo(2));
-                DUMPREG(DISPC_SIZE_LCD(2));
-        }
-
-        DUMPREG(DISPC_GFX_BA0);
-        DUMPREG(DISPC_GFX_BA1);
-        DUMPREG(DISPC_GFX_POSITION);
-        DUMPREG(DISPC_GFX_SIZE);
-        DUMPREG(DISPC_GFX_ATTRIBUTES);
-        DUMPREG(DISPC_GFX_FIFO_THRESHOLD);
-        DUMPREG(DISPC_GFX_FIFO_SIZE_STATUS);
-        DUMPREG(DISPC_GFX_ROW_INC);
-        DUMPREG(DISPC_GFX_PIXEL_INC);
-        DUMPREG(DISPC_GFX_WINDOW_SKIP);
-        DUMPREG(DISPC_GFX_TABLE_BA);
-
-        DUMPREG(DISPC_DATA_CYCLE1(0));
-        DUMPREG(DISPC_DATA_CYCLE2(0));
-        DUMPREG(DISPC_DATA_CYCLE3(0));
-
-        DUMPREG(DISPC_CPR_COEF_R(0));
-        DUMPREG(DISPC_CPR_COEF_G(0));
-        DUMPREG(DISPC_CPR_COEF_B(0));
+                DUMPREG(DISPC_DEFAULT_COLOR(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_TRANS_COLOR(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_TIMING_H(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_TIMING_V(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_POL_FREQ(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_DIVISORo(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_SIZE_MGR(OMAP_DSS_CHANNEL_LCD2));
+        }
+
+        DUMPREG(DISPC_OVL_BA0(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_BA1(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_POSITION(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_SIZE(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_ATTRIBUTES(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_FIFO_THRESHOLD(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_FIFO_SIZE_STATUS(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_ROW_INC(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_PIXEL_INC(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_WINDOW_SKIP(OMAP_DSS_GFX));
+        DUMPREG(DISPC_OVL_TABLE_BA(OMAP_DSS_GFX));
+
+        DUMPREG(DISPC_DATA_CYCLE1(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_DATA_CYCLE2(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_DATA_CYCLE3(OMAP_DSS_CHANNEL_LCD));
+
+        DUMPREG(DISPC_CPR_COEF_R(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_CPR_COEF_G(OMAP_DSS_CHANNEL_LCD));
+        DUMPREG(DISPC_CPR_COEF_B(OMAP_DSS_CHANNEL_LCD));
         if (dss_has_feature(FEAT_MGR_LCD2)) {
-                DUMPREG(DISPC_DATA_CYCLE1(2));
-                DUMPREG(DISPC_DATA_CYCLE2(2));
-                DUMPREG(DISPC_DATA_CYCLE3(2));
-
-                DUMPREG(DISPC_CPR_COEF_R(2));
-                DUMPREG(DISPC_CPR_COEF_G(2));
-                DUMPREG(DISPC_CPR_COEF_B(2));
-        }
-
-        DUMPREG(DISPC_GFX_PRELOAD);
-
-        DUMPREG(DISPC_VID_BA0(0));
-        DUMPREG(DISPC_VID_BA1(0));
-        DUMPREG(DISPC_VID_POSITION(0));
-        DUMPREG(DISPC_VID_SIZE(0));
-        DUMPREG(DISPC_VID_ATTRIBUTES(0));
-        DUMPREG(DISPC_VID_FIFO_THRESHOLD(0));
-        DUMPREG(DISPC_VID_FIFO_SIZE_STATUS(0));
-        DUMPREG(DISPC_VID_ROW_INC(0));
-        DUMPREG(DISPC_VID_PIXEL_INC(0));
-        DUMPREG(DISPC_VID_FIR(0));
-        DUMPREG(DISPC_VID_PICTURE_SIZE(0));
-        DUMPREG(DISPC_VID_ACCU0(0));
-        DUMPREG(DISPC_VID_ACCU1(0));
-
-        DUMPREG(DISPC_VID_BA0(1));
-        DUMPREG(DISPC_VID_BA1(1));
-        DUMPREG(DISPC_VID_POSITION(1));
-        DUMPREG(DISPC_VID_SIZE(1));
-        DUMPREG(DISPC_VID_ATTRIBUTES(1));
-        DUMPREG(DISPC_VID_FIFO_THRESHOLD(1));
-        DUMPREG(DISPC_VID_FIFO_SIZE_STATUS(1));
-        DUMPREG(DISPC_VID_ROW_INC(1));
-        DUMPREG(DISPC_VID_PIXEL_INC(1));
-        DUMPREG(DISPC_VID_FIR(1));
-        DUMPREG(DISPC_VID_PICTURE_SIZE(1));
-        DUMPREG(DISPC_VID_ACCU0(1));
-        DUMPREG(DISPC_VID_ACCU1(1));
-
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 0));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 1));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 2));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 3));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 5));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 6));
-        DUMPREG(DISPC_VID_FIR_COEF_H(0, 7));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 0));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 1));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 2));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 3));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 5));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 6));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(0, 7));
-        DUMPREG(DISPC_VID_CONV_COEF(0, 0));
-        DUMPREG(DISPC_VID_CONV_COEF(0, 1));
-        DUMPREG(DISPC_VID_CONV_COEF(0, 2));
-        DUMPREG(DISPC_VID_CONV_COEF(0, 3));
-        DUMPREG(DISPC_VID_CONV_COEF(0, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 0));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 1));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 2));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 3));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 5));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 6));
-        DUMPREG(DISPC_VID_FIR_COEF_V(0, 7));
-
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 0));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 1));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 2));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 3));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 5));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 6));
-        DUMPREG(DISPC_VID_FIR_COEF_H(1, 7));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 0));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 1));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 2));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 3));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 5));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 6));
-        DUMPREG(DISPC_VID_FIR_COEF_HV(1, 7));
-        DUMPREG(DISPC_VID_CONV_COEF(1, 0));
-        DUMPREG(DISPC_VID_CONV_COEF(1, 1));
-        DUMPREG(DISPC_VID_CONV_COEF(1, 2));
-        DUMPREG(DISPC_VID_CONV_COEF(1, 3));
-        DUMPREG(DISPC_VID_CONV_COEF(1, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 0));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 1));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 2));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 3));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 4));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 5));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 6));
-        DUMPREG(DISPC_VID_FIR_COEF_V(1, 7));
-
-        DUMPREG(DISPC_VID_PRELOAD(0));
-        DUMPREG(DISPC_VID_PRELOAD(1));
+                DUMPREG(DISPC_DATA_CYCLE1(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_DATA_CYCLE2(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_DATA_CYCLE3(OMAP_DSS_CHANNEL_LCD2));
+
+                DUMPREG(DISPC_CPR_COEF_R(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_CPR_COEF_G(OMAP_DSS_CHANNEL_LCD2));
+                DUMPREG(DISPC_CPR_COEF_B(OMAP_DSS_CHANNEL_LCD2));
+        }
+
+        DUMPREG(DISPC_OVL_PRELOAD(OMAP_DSS_GFX));
+
+        DUMPREG(DISPC_OVL_BA0(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_BA1(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_POSITION(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_SIZE(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_ATTRIBUTES(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_FIFO_THRESHOLD(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_FIFO_SIZE_STATUS(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_ROW_INC(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_PIXEL_INC(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_FIR(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_PICTURE_SIZE(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_ACCU0(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_ACCU1(OMAP_DSS_VIDEO1));
+
+        DUMPREG(DISPC_OVL_BA0(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_BA1(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_POSITION(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_SIZE(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_ATTRIBUTES(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_FIFO_THRESHOLD(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_FIFO_SIZE_STATUS(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_ROW_INC(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_PIXEL_INC(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_FIR(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_PICTURE_SIZE(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_ACCU0(OMAP_DSS_VIDEO2));
+        DUMPREG(DISPC_OVL_ACCU1(OMAP_DSS_VIDEO2));
+
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 0));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 1));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 2));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 3));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 5));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 6));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO1, 7));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 0));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 1));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 2));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 3));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 5));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 6));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO1, 7));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 0));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 1));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 2));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 3));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO1, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 0));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 1));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 2));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 3));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 5));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 6));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO1, 7));
+
+        if (dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) {
+                DUMPREG(DISPC_OVL_BA0_UV(OMAP_DSS_VIDEO1));
+                DUMPREG(DISPC_OVL_BA1_UV(OMAP_DSS_VIDEO1));
+                DUMPREG(DISPC_OVL_FIR2(OMAP_DSS_VIDEO1));
+                DUMPREG(DISPC_OVL_ACCU2_0(OMAP_DSS_VIDEO1));
+                DUMPREG(DISPC_OVL_ACCU2_1(OMAP_DSS_VIDEO1));
+
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 0));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 1));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 2));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 3));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 4));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 5));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 6));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO1, 7));
+
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 0));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 1));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 2));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 3));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 4));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 5));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 6));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO1, 7));
+
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 0));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 1));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 2));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 3));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 4));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 5));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 6));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO1, 7));
+        }
+        if (dss_has_feature(FEAT_ATTR2))
+                DUMPREG(DISPC_OVL_ATTRIBUTES2(OMAP_DSS_VIDEO1));
+
+
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 0));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 1));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 2));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 3));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 5));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 6));
+        DUMPREG(DISPC_OVL_FIR_COEF_H(OMAP_DSS_VIDEO2, 7));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 0));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 1));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 2));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 3));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 5));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 6));
+        DUMPREG(DISPC_OVL_FIR_COEF_HV(OMAP_DSS_VIDEO2, 7));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 0));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 1));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 2));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 3));
+        DUMPREG(DISPC_OVL_CONV_COEF(OMAP_DSS_VIDEO2, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 0));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 1));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 2));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 3));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 4));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 5));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 6));
+        DUMPREG(DISPC_OVL_FIR_COEF_V(OMAP_DSS_VIDEO2, 7));
+
+        if (dss_has_feature(FEAT_HANDLE_UV_SEPARATE)) {
+                DUMPREG(DISPC_OVL_BA0_UV(OMAP_DSS_VIDEO2));
+                DUMPREG(DISPC_OVL_BA1_UV(OMAP_DSS_VIDEO2));
+                DUMPREG(DISPC_OVL_FIR2(OMAP_DSS_VIDEO2));
+                DUMPREG(DISPC_OVL_ACCU2_0(OMAP_DSS_VIDEO2));
+                DUMPREG(DISPC_OVL_ACCU2_1(OMAP_DSS_VIDEO2));
+
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 0));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 1));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 2));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 3));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 4));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 5));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 6));
+                DUMPREG(DISPC_OVL_FIR_COEF_H2(OMAP_DSS_VIDEO2, 7));
+
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 0));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 1));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 2));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 3));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 4));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 5));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 6));
+                DUMPREG(DISPC_OVL_FIR_COEF_HV2(OMAP_DSS_VIDEO2, 7));
+
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 0));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 1));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 2));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 3));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 4));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 5));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 6));
+                DUMPREG(DISPC_OVL_FIR_COEF_V2(OMAP_DSS_VIDEO2, 7));
+        }
+        if (dss_has_feature(FEAT_ATTR2))
+                DUMPREG(DISPC_OVL_ATTRIBUTES2(OMAP_DSS_VIDEO2));
+
+        DUMPREG(DISPC_OVL_PRELOAD(OMAP_DSS_VIDEO1));
+        DUMPREG(DISPC_OVL_PRELOAD(OMAP_DSS_VIDEO2));
 
         dss_clk_disable(DSS_CLK_ICK | DSS_CLK_FCK);
 #undef DUMPREG
@@ -3388,11 +3574,12 @@ int dispc_setup_plane(enum omap_plane plane,
                        bool ilace,
                        enum omap_dss_rotation_type rotation_type,
                        u8 rotation, bool mirror, u8 global_alpha,
-                       u8 pre_mult_alpha, enum omap_channel channel)
+                       u8 pre_mult_alpha, enum omap_channel channel,
+                       u32 puv_addr)
 {
         int r = 0;
 
-        DSSDBG("dispc_setup_plane %d, pa %x, sw %d, %d,%d, %dx%d -> "
+        DSSDBG("dispc_setup_plane %d, pa %x, sw %d, %d, %d, %dx%d -> "
                "%dx%d, ilace %d, cmode %x, rot %d, mir %d chan %d\n",
                plane, paddr, screen_width, pos_x, pos_y,
                width, height,
@@ -3411,7 +3598,8 @@ int dispc_setup_plane(enum omap_plane plane,
                            rotation_type,
                            rotation, mirror,
                            global_alpha,
-                           pre_mult_alpha, channel);
+                           pre_mult_alpha,
+                           channel, puv_addr);
 
         enable_clocks(0);
 
diff --git a/drivers/video/omap2/dss/dispc.h b/drivers/video/omap2/dss/dispc.h
new file mode 100644
index 000000000000..6c9ee0a0efb3
--- /dev/null
+++ b/drivers/video/omap2/dss/dispc.h
@@ -0,0 +1,691 @@
+/*
+ * linux/drivers/video/omap2/dss/dispc.h
+ *
+ * Copyright (C) 2011 Texas Instruments
+ * Author: Archit Taneja <archit@ti.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 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.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __OMAP2_DISPC_REG_H
+#define __OMAP2_DISPC_REG_H
+
+/* DISPC common registers */
+#define DISPC_REVISION                  0x0000
+#define DISPC_SYSCONFIG                 0x0010
+#define DISPC_SYSSTATUS                 0x0014
+#define DISPC_IRQSTATUS                 0x0018
+#define DISPC_IRQENABLE                 0x001C
+#define DISPC_CONTROL                   0x0040
+#define DISPC_CONFIG                    0x0044
+#define DISPC_CAPABLE                   0x0048
+#define DISPC_LINE_STATUS               0x005C
+#define DISPC_LINE_NUMBER               0x0060
+#define DISPC_GLOBAL_ALPHA              0x0074
+#define DISPC_CONTROL2                  0x0238
+#define DISPC_CONFIG2                   0x0620
+#define DISPC_DIVISOR                   0x0804
+
+/* DISPC overlay registers */
+#define DISPC_OVL_BA0(n)                (DISPC_OVL_BASE(n) + \
+                                        DISPC_BA0_OFFSET(n))
+#define DISPC_OVL_BA1(n)                (DISPC_OVL_BASE(n) + \
+                                        DISPC_BA1_OFFSET(n))
+#define DISPC_OVL_BA0_UV(n)             (DISPC_OVL_BASE(n) + \
+                                        DISPC_BA0_UV_OFFSET(n))
+#define DISPC_OVL_BA1_UV(n)             (DISPC_OVL_BASE(n) + \
+                                        DISPC_BA1_UV_OFFSET(n))
+#define DISPC_OVL_POSITION(n)           (DISPC_OVL_BASE(n) + \
+                                        DISPC_POS_OFFSET(n))
+#define DISPC_OVL_SIZE(n)               (DISPC_OVL_BASE(n) + \
+                                        DISPC_SIZE_OFFSET(n))
+#define DISPC_OVL_ATTRIBUTES(n)         (DISPC_OVL_BASE(n) + \
+                                        DISPC_ATTR_OFFSET(n))
+#define DISPC_OVL_ATTRIBUTES2(n)        (DISPC_OVL_BASE(n) + \
+                                        DISPC_ATTR2_OFFSET(n))
+#define DISPC_OVL_FIFO_THRESHOLD(n)     (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIFO_THRESH_OFFSET(n))
+#define DISPC_OVL_FIFO_SIZE_STATUS(n)   (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIFO_SIZE_STATUS_OFFSET(n))
+#define DISPC_OVL_ROW_INC(n)            (DISPC_OVL_BASE(n) + \
+                                        DISPC_ROW_INC_OFFSET(n))
+#define DISPC_OVL_PIXEL_INC(n)          (DISPC_OVL_BASE(n) + \
+                                        DISPC_PIX_INC_OFFSET(n))
+#define DISPC_OVL_WINDOW_SKIP(n)        (DISPC_OVL_BASE(n) + \
+                                        DISPC_WINDOW_SKIP_OFFSET(n))
+#define DISPC_OVL_TABLE_BA(n)           (DISPC_OVL_BASE(n) + \
+                                        DISPC_TABLE_BA_OFFSET(n))
+#define DISPC_OVL_FIR(n)                (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_OFFSET(n))
+#define DISPC_OVL_FIR2(n)               (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR2_OFFSET(n))
+#define DISPC_OVL_PICTURE_SIZE(n)       (DISPC_OVL_BASE(n) + \
+                                        DISPC_PIC_SIZE_OFFSET(n))
+#define DISPC_OVL_ACCU0(n)              (DISPC_OVL_BASE(n) + \
+                                        DISPC_ACCU0_OFFSET(n))
+#define DISPC_OVL_ACCU1(n)              (DISPC_OVL_BASE(n) + \
+                                        DISPC_ACCU1_OFFSET(n))
+#define DISPC_OVL_ACCU2_0(n)            (DISPC_OVL_BASE(n) + \
+                                        DISPC_ACCU2_0_OFFSET(n))
+#define DISPC_OVL_ACCU2_1(n)            (DISPC_OVL_BASE(n) + \
+                                        DISPC_ACCU2_1_OFFSET(n))
+#define DISPC_OVL_FIR_COEF_H(n, i)      (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_COEF_H_OFFSET(n, i))
+#define DISPC_OVL_FIR_COEF_HV(n, i)     (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_COEF_HV_OFFSET(n, i))
+#define DISPC_OVL_FIR_COEF_H2(n, i)     (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_COEF_H2_OFFSET(n, i))
+#define DISPC_OVL_FIR_COEF_HV2(n, i)    (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_COEF_HV2_OFFSET(n, i))
+#define DISPC_OVL_CONV_COEF(n, i)       (DISPC_OVL_BASE(n) + \
+                                        DISPC_CONV_COEF_OFFSET(n, i))
+#define DISPC_OVL_FIR_COEF_V(n, i)      (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_COEF_V_OFFSET(n, i))
+#define DISPC_OVL_FIR_COEF_V2(n, i)     (DISPC_OVL_BASE(n) + \
+                                        DISPC_FIR_COEF_V2_OFFSET(n, i))
+#define DISPC_OVL_PRELOAD(n)            (DISPC_OVL_BASE(n) + \
+                                        DISPC_PRELOAD_OFFSET(n))
+
+/* DISPC manager/channel specific registers */
+static inline u16 DISPC_DEFAULT_COLOR(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x004C;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                return 0x0050;
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03AC;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_TRANS_COLOR(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0054;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                return 0x0058;
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03B0;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_TIMING_H(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0064;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x0400;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_TIMING_V(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0068;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x0404;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_POL_FREQ(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x006C;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x0408;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_DIVISORo(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0070;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x040C;
+        default:
+                BUG();
+        }
+}
+
+/* Named as DISPC_SIZE_LCD, DISPC_SIZE_DIGIT and DISPC_SIZE_LCD2 in TRM */
+static inline u16 DISPC_SIZE_MGR(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x007C;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                return 0x0078;
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03CC;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_DATA_CYCLE1(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x01D4;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03C0;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_DATA_CYCLE2(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x01D8;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03C4;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_DATA_CYCLE3(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x01DC;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03C8;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_CPR_COEF_R(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0220;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03BC;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_CPR_COEF_G(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0224;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03B8;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_CPR_COEF_B(enum omap_channel channel)
+{
+        switch (channel) {
+        case OMAP_DSS_CHANNEL_LCD:
+                return 0x0228;
+        case OMAP_DSS_CHANNEL_DIGIT:
+                BUG();
+        case OMAP_DSS_CHANNEL_LCD2:
+                return 0x03B4;
+        default:
+                BUG();
+        }
+}
+
+/* DISPC overlay register base addresses */
+static inline u16 DISPC_OVL_BASE(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0080;
+        case OMAP_DSS_VIDEO1:
+                return 0x00BC;
+        case OMAP_DSS_VIDEO2:
+                return 0x014C;
+        default:
+                BUG();
+        }
+}
+
+/* DISPC overlay register offsets */
+static inline u16 DISPC_BA0_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0000;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_BA1_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0004;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_BA0_UV_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0544;
+        case OMAP_DSS_VIDEO2:
+                return 0x04BC;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_BA1_UV_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0548;
+        case OMAP_DSS_VIDEO2:
+                return 0x04C0;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_POS_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0008;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_SIZE_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x000C;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_ATTR_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0020;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0010;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_ATTR2_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0568;
+        case OMAP_DSS_VIDEO2:
+                return 0x04DC;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_FIFO_THRESH_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0024;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0014;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_FIFO_SIZE_STATUS_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0028;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0018;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_ROW_INC_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x002C;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x001C;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_PIX_INC_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0030;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0020;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_WINDOW_SKIP_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0034;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                BUG();
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_TABLE_BA_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x0038;
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                BUG();
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_FIR_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0024;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_FIR2_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0580;
+        case OMAP_DSS_VIDEO2:
+                return 0x055C;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_PIC_SIZE_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0028;
+        default:
+                BUG();
+        }
+}
+
+
+static inline u16 DISPC_ACCU0_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x002C;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_ACCU2_0_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0584;
+        case OMAP_DSS_VIDEO2:
+                return 0x0560;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_ACCU1_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0030;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_ACCU2_1_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0588;
+        case OMAP_DSS_VIDEO2:
+                return 0x0564;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
+static inline u16 DISPC_FIR_COEF_H_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0034 + i * 0x8;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
+static inline u16 DISPC_FIR_COEF_H2_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x058C + i * 0x8;
+        case OMAP_DSS_VIDEO2:
+                return 0x0568 + i * 0x8;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
+static inline u16 DISPC_FIR_COEF_HV_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0038 + i * 0x8;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
+static inline u16 DISPC_FIR_COEF_HV2_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0590 + i * 8;
+        case OMAP_DSS_VIDEO2:
+                return 0x056C + i * 0x8;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4,} */
+static inline u16 DISPC_CONV_COEF_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+        case OMAP_DSS_VIDEO2:
+                return 0x0074 + i * 0x4;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
+static inline u16 DISPC_FIR_COEF_V_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x0124 + i * 0x4;
+        case OMAP_DSS_VIDEO2:
+                return 0x00B4 + i * 0x4;
+        default:
+                BUG();
+        }
+}
+
+/* coef index i = {0, 1, 2, 3, 4, 5, 6, 7} */
+static inline u16 DISPC_FIR_COEF_V2_OFFSET(enum omap_plane plane, u16 i)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                BUG();
+        case OMAP_DSS_VIDEO1:
+                return 0x05CC + i * 0x4;
+        case OMAP_DSS_VIDEO2:
+                return 0x05A8 + i * 0x4;
+        default:
+                BUG();
+        }
+}
+
+static inline u16 DISPC_PRELOAD_OFFSET(enum omap_plane plane)
+{
+        switch (plane) {
+        case OMAP_DSS_GFX:
+                return 0x01AC;
+        case OMAP_DSS_VIDEO1:
+                return 0x0174;
+        case OMAP_DSS_VIDEO2:
+                return 0x00E8;
+        default:
+                BUG();
+        }
+}
+#endif
diff --git a/drivers/video/omap2/dss/display.c b/drivers/video/omap2/dss/display.c
index a85a6f38b40c..c2dfc8c50057 100644
--- a/drivers/video/omap2/dss/display.c
+++ b/drivers/video/omap2/dss/display.c
@@ -27,7 +27,7 @@
 #include <linux/jiffies.h>
 #include <linux/platform_device.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include "dss.h"
 
 static ssize_t display_enabled_show(struct device *dev,
@@ -44,9 +44,13 @@ static ssize_t display_enabled_store(struct device *dev,
                 const char *buf, size_t size)
 {
         struct omap_dss_device *dssdev = to_dss_device(dev);
-        bool enabled, r;
+        int r, enabled;
 
-        enabled = simple_strtoul(buf, NULL, 10);
+        r = kstrtoint(buf, 0, &enabled);
+        if (r)
+                return r;
+
+        enabled = !!enabled;
 
         if (enabled != (dssdev->state != OMAP_DSS_DISPLAY_DISABLED)) {
                 if (enabled) {
@@ -82,7 +86,9 @@ static ssize_t display_upd_mode_store(struct device *dev,
         if (!dssdev->driver->set_update_mode)
                 return -EINVAL;
 
-        val = simple_strtoul(buf, NULL, 10);
+        r = kstrtoint(buf, 0, &val);
+        if (r)
+                return r;
 
         switch (val) {
         case OMAP_DSS_UPDATE_DISABLED:
@@ -114,13 +120,16 @@ static ssize_t display_tear_store(struct device *dev,
                 struct device_attribute *attr, const char *buf, size_t size)
 {
         struct omap_dss_device *dssdev = to_dss_device(dev);
-        unsigned long te;
-        int r;
+        int te, r;
 
         if (!dssdev->driver->enable_te || !dssdev->driver->get_te)
                 return -ENOENT;
 
-        te = simple_strtoul(buf, NULL, 0);
+        r = kstrtoint(buf, 0, &te);
+        if (r)
+                return r;
+
+        te = !!te;
 
         r = dssdev->driver->enable_te(dssdev, te);
         if (r)
@@ -196,13 +205,14 @@ static ssize_t display_rotate_store(struct device *dev,
                 struct device_attribute *attr, const char *buf, size_t size)
 {
         struct omap_dss_device *dssdev = to_dss_device(dev);
-        unsigned long rot;
-        int r;
+        int rot, r;
 
         if (!dssdev->driver->set_rotate || !dssdev->driver->get_rotate)
                 return -ENOENT;
 
-        rot = simple_strtoul(buf, NULL, 0);
+        r = kstrtoint(buf, 0, &rot);
+        if (r)
+                return r;
 
         r = dssdev->driver->set_rotate(dssdev, rot);
         if (r)
@@ -226,13 +236,16 @@ static ssize_t display_mirror_store(struct device *dev,
                 struct device_attribute *attr, const char *buf, size_t size)
 {
         struct omap_dss_device *dssdev = to_dss_device(dev);
-        unsigned long mirror;
-        int r;
+        int mirror, r;
 
         if (!dssdev->driver->set_mirror || !dssdev->driver->get_mirror)
                 return -ENOENT;
 
-        mirror = simple_strtoul(buf, NULL, 0);
+        r = kstrtoint(buf, 0, &mirror);
+        if (r)
+                return r;
+
+        mirror = !!mirror;
 
         r = dssdev->driver->set_mirror(dssdev, mirror);
         if (r)
@@ -259,14 +272,15 @@ static ssize_t display_wss_store(struct device *dev,
                 struct device_attribute *attr, const char *buf, size_t size)
 {
         struct omap_dss_device *dssdev = to_dss_device(dev);
-        unsigned long wss;
+        u32 wss;
         int r;
 
         if (!dssdev->driver->get_wss || !dssdev->driver->set_wss)
                 return -ENOENT;
 
-        if (strict_strtoul(buf, 0, &wss))
-                return -EINVAL;
+        r = kstrtou32(buf, 0, &wss);
+        if (r)
+                return r;
 
         if (wss > 0xfffff)
                 return -EINVAL;
diff --git a/drivers/video/omap2/dss/dpi.c b/drivers/video/omap2/dss/dpi.c
index 2d3ca4ca4a05..ff6bd30132df 100644
--- a/drivers/video/omap2/dss/dpi.c
+++ b/drivers/video/omap2/dss/dpi.c
@@ -30,16 +30,40 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/cpu.h>
 
 #include "dss.h"
 
 static struct {
         struct regulator *vdds_dsi_reg;
+        struct platform_device *dsidev;
 } dpi;
 
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
+static struct platform_device *dpi_get_dsidev(enum omap_dss_clk_source clk)
+{
+        int dsi_module;
+
+        dsi_module = clk == OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC ? 0 : 1;
+
+        return dsi_get_dsidev_from_id(dsi_module);
+}
+
+static bool dpi_use_dsi_pll(struct omap_dss_device *dssdev)
+{
+        if (dssdev->clocks.dispc.dispc_fclk_src ==
+                        OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC ||
+                        dssdev->clocks.dispc.dispc_fclk_src ==
+                        OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC ||
+                        dssdev->clocks.dispc.channel.lcd_clk_src ==
+                        OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC ||
+                        dssdev->clocks.dispc.channel.lcd_clk_src ==
+                        OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC)
+                return true;
+        else
+                return false;
+}
+
 static int dpi_set_dsi_clk(struct omap_dss_device *dssdev, bool is_tft,
                 unsigned long pck_req, unsigned long *fck, int *lck_div,
                 int *pck_div)
@@ -48,16 +72,16 @@ static int dpi_set_dsi_clk(struct omap_dss_device *dssdev, bool is_tft,
         struct dispc_clock_info dispc_cinfo;
         int r;
 
-        r = dsi_pll_calc_clock_div_pck(is_tft, pck_req, &dsi_cinfo,
-                        &dispc_cinfo);
+        r = dsi_pll_calc_clock_div_pck(dpi.dsidev, is_tft, pck_req,
+                        &dsi_cinfo, &dispc_cinfo);
         if (r)
                 return r;
 
-        r = dsi_pll_set_clock_div(&dsi_cinfo);
+        r = dsi_pll_set_clock_div(dpi.dsidev, &dsi_cinfo);
         if (r)
                 return r;
 
-        dss_select_dispc_clk_source(DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC);
+        dss_select_dispc_clk_source(dssdev->clocks.dispc.dispc_fclk_src);
 
         r = dispc_set_clock_div(dssdev->manager->id, &dispc_cinfo);
         if (r)
@@ -69,7 +93,7 @@ static int dpi_set_dsi_clk(struct omap_dss_device *dssdev, bool is_tft,
 
         return 0;
 }
-#else
+
 static int dpi_set_dispc_clk(struct omap_dss_device *dssdev, bool is_tft,
                 unsigned long pck_req, unsigned long *fck, int *lck_div,
                 int *pck_div)
@@ -96,13 +120,12 @@ static int dpi_set_dispc_clk(struct omap_dss_device *dssdev, bool is_tft,
 
         return 0;
 }
-#endif
 
 static int dpi_set_mode(struct omap_dss_device *dssdev)
 {
         struct omap_video_timings *t = &dssdev->panel.timings;
-        int lck_div, pck_div;
-        unsigned long fck;
+        int lck_div = 0, pck_div = 0;
+        unsigned long fck = 0;
         unsigned long pck;
         bool is_tft;
         int r = 0;
@@ -114,13 +137,12 @@ static int dpi_set_mode(struct omap_dss_device *dssdev)
 
         is_tft = (dssdev->panel.config & OMAP_DSS_LCD_TFT) != 0;
 
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
-        r = dpi_set_dsi_clk(dssdev, is_tft, t->pixel_clock * 1000, &fck,
-                        &lck_div, &pck_div);
-#else
-        r = dpi_set_dispc_clk(dssdev, is_tft, t->pixel_clock * 1000, &fck,
-                        &lck_div, &pck_div);
-#endif
+        if (dpi_use_dsi_pll(dssdev))
+                r = dpi_set_dsi_clk(dssdev, is_tft, t->pixel_clock * 1000,
+                                &fck, &lck_div, &pck_div);
+        else
+                r = dpi_set_dispc_clk(dssdev, is_tft, t->pixel_clock * 1000,
+                                &fck, &lck_div, &pck_div);
         if (r)
                 goto err0;
 
@@ -179,12 +201,13 @@ int omapdss_dpi_display_enable(struct omap_dss_device *dssdev)
         if (r)
                 goto err2;
 
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
-        dss_clk_enable(DSS_CLK_SYSCK);
-        r = dsi_pll_init(dssdev, 0, 1);
-        if (r)
-                goto err3;
-#endif
+        if (dpi_use_dsi_pll(dssdev)) {
+                dss_clk_enable(DSS_CLK_SYSCK);
+                r = dsi_pll_init(dpi.dsidev, 0, 1);
+                if (r)
+                        goto err3;
+        }
+
         r = dpi_set_mode(dssdev);
         if (r)
                 goto err4;
@@ -196,11 +219,11 @@ int omapdss_dpi_display_enable(struct omap_dss_device *dssdev)
         return 0;
 
 err4:
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
-        dsi_pll_uninit();
+        if (dpi_use_dsi_pll(dssdev))
+                dsi_pll_uninit(dpi.dsidev, true);
 err3:
-        dss_clk_disable(DSS_CLK_SYSCK);
-#endif
+        if (dpi_use_dsi_pll(dssdev))
+                dss_clk_disable(DSS_CLK_SYSCK);
 err2:
         dss_clk_disable(DSS_CLK_ICK | DSS_CLK_FCK);
         if (cpu_is_omap34xx())
@@ -216,11 +239,11 @@ void omapdss_dpi_display_disable(struct omap_dss_device *dssdev)
 {
         dssdev->manager->disable(dssdev->manager);
 
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
-        dss_select_dispc_clk_source(DSS_CLK_SRC_FCK);
-        dsi_pll_uninit();
-        dss_clk_disable(DSS_CLK_SYSCK);
-#endif
+        if (dpi_use_dsi_pll(dssdev)) {
+                dss_select_dispc_clk_source(OMAP_DSS_CLK_SRC_FCK);
+                dsi_pll_uninit(dpi.dsidev, true);
+                dss_clk_disable(DSS_CLK_SYSCK);
+        }
 
         dss_clk_disable(DSS_CLK_ICK | DSS_CLK_FCK);
 
@@ -251,6 +274,7 @@ int dpi_check_timings(struct omap_dss_device *dssdev,
         int lck_div, pck_div;
         unsigned long fck;
         unsigned long pck;
+        struct dispc_clock_info dispc_cinfo;
 
         if (!dispc_lcd_timings_ok(timings))
                 return -EINVAL;
@@ -260,11 +284,9 @@ int dpi_check_timings(struct omap_dss_device *dssdev,
 
         is_tft = (dssdev->panel.config & OMAP_DSS_LCD_TFT) != 0;
 
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
-        {
+        if (dpi_use_dsi_pll(dssdev)) {
                 struct dsi_clock_info dsi_cinfo;
-                struct dispc_clock_info dispc_cinfo;
-                r = dsi_pll_calc_clock_div_pck(is_tft,
+                r = dsi_pll_calc_clock_div_pck(dpi.dsidev, is_tft,
                                 timings->pixel_clock * 1000,
                                 &dsi_cinfo, &dispc_cinfo);
 
@@ -272,13 +294,8 @@ int dpi_check_timings(struct omap_dss_device *dssdev,
                         return r;
 
                 fck = dsi_cinfo.dsi_pll_hsdiv_dispc_clk;
-                lck_div = dispc_cinfo.lck_div;
-                pck_div = dispc_cinfo.pck_div;
-        }
-#else
-        {
+        } else {
                 struct dss_clock_info dss_cinfo;
-                struct dispc_clock_info dispc_cinfo;
                 r = dss_calc_clock_div(is_tft, timings->pixel_clock * 1000,
                                 &dss_cinfo, &dispc_cinfo);
 
@@ -286,10 +303,10 @@ int dpi_check_timings(struct omap_dss_device *dssdev,
                         return r;
 
                 fck = dss_cinfo.fck;
-                lck_div = dispc_cinfo.lck_div;
-                pck_div = dispc_cinfo.pck_div;
         }
-#endif
+
+        lck_div = dispc_cinfo.lck_div;
+        pck_div = dispc_cinfo.pck_div;
 
         pck = fck / lck_div / pck_div / 1000;
 
@@ -316,6 +333,12 @@ int dpi_init_display(struct omap_dss_device *dssdev)
                 dpi.vdds_dsi_reg = vdds_dsi;
         }
 
+        if (dpi_use_dsi_pll(dssdev)) {
+                enum omap_dss_clk_source dispc_fclk_src =
+                        dssdev->clocks.dispc.dispc_fclk_src;
+                dpi.dsidev = dpi_get_dsidev(dispc_fclk_src);
+        }
+
         return 0;
 }
 
diff --git a/drivers/video/omap2/dss/dsi.c b/drivers/video/omap2/dss/dsi.c
index 0a7f1a47f8e3..345757cfcbee 100644
--- a/drivers/video/omap2/dss/dsi.c
+++ b/drivers/video/omap2/dss/dsi.c
@@ -33,8 +33,11 @@
 #include <linux/regulator/consumer.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/clock.h>
 
 #include "dss.h"
@@ -56,6 +59,7 @@ struct dsi_reg { u16 idx; };
 #define DSI_IRQSTATUS                   DSI_REG(0x0018)
 #define DSI_IRQENABLE                   DSI_REG(0x001C)
 #define DSI_CTRL                        DSI_REG(0x0040)
+#define DSI_GNQ                         DSI_REG(0x0044)
 #define DSI_COMPLEXIO_CFG1              DSI_REG(0x0048)
 #define DSI_COMPLEXIO_IRQ_STATUS        DSI_REG(0x004C)
 #define DSI_COMPLEXIO_IRQ_ENABLE        DSI_REG(0x0050)
@@ -90,6 +94,7 @@ struct dsi_reg { u16 idx; };
 #define DSI_DSIPHY_CFG1                 DSI_REG(0x200 + 0x0004)
 #define DSI_DSIPHY_CFG2                 DSI_REG(0x200 + 0x0008)
 #define DSI_DSIPHY_CFG5                 DSI_REG(0x200 + 0x0014)
+#define DSI_DSIPHY_CFG10                DSI_REG(0x200 + 0x0028)
 
 /* DSI_PLL_CTRL_SCP */
 
@@ -99,11 +104,11 @@ struct dsi_reg { u16 idx; };
 #define DSI_PLL_CONFIGURATION1          DSI_REG(0x300 + 0x000C)
 #define DSI_PLL_CONFIGURATION2          DSI_REG(0x300 + 0x0010)
 
-#define REG_GET(idx, start, end) \
-        FLD_GET(dsi_read_reg(idx), start, end)
+#define REG_GET(dsidev, idx, start, end) \
+        FLD_GET(dsi_read_reg(dsidev, idx), start, end)
 
-#define REG_FLD_MOD(idx, val, start, end) \
-        dsi_write_reg(idx, FLD_MOD(dsi_read_reg(idx), val, start, end))
+#define REG_FLD_MOD(dsidev, idx, val, start, end) \
+        dsi_write_reg(dsidev, idx, FLD_MOD(dsi_read_reg(dsidev, idx), val, start, end))
 
 /* Global interrupts */
 #define DSI_IRQ_VC0             (1 << 0)
@@ -147,31 +152,50 @@ struct dsi_reg { u16 idx; };
 #define DSI_CIO_IRQ_ERRSYNCESC1         (1 << 0)
 #define DSI_CIO_IRQ_ERRSYNCESC2         (1 << 1)
 #define DSI_CIO_IRQ_ERRSYNCESC3         (1 << 2)
+#define DSI_CIO_IRQ_ERRSYNCESC4         (1 << 3)
+#define DSI_CIO_IRQ_ERRSYNCESC5         (1 << 4)
 #define DSI_CIO_IRQ_ERRESC1             (1 << 5)
 #define DSI_CIO_IRQ_ERRESC2             (1 << 6)
 #define DSI_CIO_IRQ_ERRESC3             (1 << 7)
+#define DSI_CIO_IRQ_ERRESC4             (1 << 8)
+#define DSI_CIO_IRQ_ERRESC5             (1 << 9)
 #define DSI_CIO_IRQ_ERRCONTROL1         (1 << 10)
 #define DSI_CIO_IRQ_ERRCONTROL2         (1 << 11)
 #define DSI_CIO_IRQ_ERRCONTROL3         (1 << 12)
+#define DSI_CIO_IRQ_ERRCONTROL4         (1 << 13)
+#define DSI_CIO_IRQ_ERRCONTROL5         (1 << 14)
 #define DSI_CIO_IRQ_STATEULPS1          (1 << 15)
 #define DSI_CIO_IRQ_STATEULPS2          (1 << 16)
 #define DSI_CIO_IRQ_STATEULPS3          (1 << 17)
+#define DSI_CIO_IRQ_STATEULPS4          (1 << 18)
+#define DSI_CIO_IRQ_STATEULPS5          (1 << 19)
 #define DSI_CIO_IRQ_ERRCONTENTIONLP0_1  (1 << 20)
 #define DSI_CIO_IRQ_ERRCONTENTIONLP1_1  (1 << 21)
 #define DSI_CIO_IRQ_ERRCONTENTIONLP0_2  (1 << 22)
 #define DSI_CIO_IRQ_ERRCONTENTIONLP1_2  (1 << 23)
 #define DSI_CIO_IRQ_ERRCONTENTIONLP0_3  (1 << 24)
 #define DSI_CIO_IRQ_ERRCONTENTIONLP1_3  (1 << 25)
+#define DSI_CIO_IRQ_ERRCONTENTIONLP0_4  (1 << 26)
+#define DSI_CIO_IRQ_ERRCONTENTIONLP1_4  (1 << 27)
+#define DSI_CIO_IRQ_ERRCONTENTIONLP0_5  (1 << 28)
+#define DSI_CIO_IRQ_ERRCONTENTIONLP1_5  (1 << 29)
 #define DSI_CIO_IRQ_ULPSACTIVENOT_ALL0  (1 << 30)
 #define DSI_CIO_IRQ_ULPSACTIVENOT_ALL1  (1 << 31)
 #define DSI_CIO_IRQ_ERROR_MASK \
         (DSI_CIO_IRQ_ERRSYNCESC1 | DSI_CIO_IRQ_ERRSYNCESC2 | \
-         DSI_CIO_IRQ_ERRSYNCESC3 | DSI_CIO_IRQ_ERRESC1 | DSI_CIO_IRQ_ERRESC2 | \
-         DSI_CIO_IRQ_ERRESC3 | DSI_CIO_IRQ_ERRCONTROL1 | \
-         DSI_CIO_IRQ_ERRCONTROL2 | DSI_CIO_IRQ_ERRCONTROL3 | \
+         DSI_CIO_IRQ_ERRSYNCESC3 | DSI_CIO_IRQ_ERRSYNCESC4 | \
+         DSI_CIO_IRQ_ERRSYNCESC5 | \
+         DSI_CIO_IRQ_ERRESC1 | DSI_CIO_IRQ_ERRESC2 | \
+         DSI_CIO_IRQ_ERRESC3 | DSI_CIO_IRQ_ERRESC4 | \
+         DSI_CIO_IRQ_ERRESC5 | \
+         DSI_CIO_IRQ_ERRCONTROL1 | DSI_CIO_IRQ_ERRCONTROL2 | \
+         DSI_CIO_IRQ_ERRCONTROL3 | DSI_CIO_IRQ_ERRCONTROL4 | \
+         DSI_CIO_IRQ_ERRCONTROL5 | \
          DSI_CIO_IRQ_ERRCONTENTIONLP0_1 | DSI_CIO_IRQ_ERRCONTENTIONLP1_1 | \
          DSI_CIO_IRQ_ERRCONTENTIONLP0_2 | DSI_CIO_IRQ_ERRCONTENTIONLP1_2 | \
-         DSI_CIO_IRQ_ERRCONTENTIONLP0_3 | DSI_CIO_IRQ_ERRCONTENTIONLP1_3)
+         DSI_CIO_IRQ_ERRCONTENTIONLP0_3 | DSI_CIO_IRQ_ERRCONTENTIONLP1_3 | \
+         DSI_CIO_IRQ_ERRCONTENTIONLP0_4 | DSI_CIO_IRQ_ERRCONTENTIONLP1_4 | \
+         DSI_CIO_IRQ_ERRCONTENTIONLP0_5 | DSI_CIO_IRQ_ERRCONTENTIONLP1_5)
 
 #define DSI_DT_DCS_SHORT_WRITE_0        0x05
 #define DSI_DT_DCS_SHORT_WRITE_1        0x15
@@ -208,6 +232,19 @@ enum dsi_vc_mode {
         DSI_VC_MODE_VP,
 };
 
+enum dsi_lane {
+        DSI_CLK_P       = 1 << 0,
+        DSI_CLK_N       = 1 << 1,
+        DSI_DATA1_P     = 1 << 2,
+        DSI_DATA1_N     = 1 << 3,
+        DSI_DATA2_P     = 1 << 4,
+        DSI_DATA2_N     = 1 << 5,
+        DSI_DATA3_P     = 1 << 6,
+        DSI_DATA3_N     = 1 << 7,
+        DSI_DATA4_P     = 1 << 8,
+        DSI_DATA4_N     = 1 << 9,
+};
+
 struct dsi_update_region {
         u16 x, y, w, h;
         struct omap_dss_device *device;
@@ -227,14 +264,16 @@ struct dsi_isr_tables {
         struct dsi_isr_data isr_table_cio[DSI_MAX_NR_ISRS];
 };
 
-static struct
-{
+struct dsi_data {
         struct platform_device *pdev;
         void __iomem    *base;
         int irq;
 
+        void (*dsi_mux_pads)(bool enable);
+
         struct dsi_clock_info current_cinfo;
 
+        bool vdds_dsi_enabled;
         struct regulator *vdds_dsi_reg;
 
         struct {
@@ -258,8 +297,7 @@ static struct
         struct dsi_update_region update_region;
 
         bool te_enabled;
-
-        struct workqueue_struct *workqueue;
+        bool ulps_enabled;
 
         void (*framedone_callback)(int, void *);
         void *framedone_data;
@@ -292,21 +330,63 @@ static struct
         unsigned long  regm_dispc_max, regm_dsi_max;
         unsigned long  fint_min, fint_max;
         unsigned long lpdiv_max;
-} dsi;
+
+        int num_data_lanes;
+
+        unsigned scp_clk_refcount;
+};
+
+struct dsi_packet_sent_handler_data {
+        struct platform_device *dsidev;
+        struct completion *completion;
+};
+
+static struct platform_device *dsi_pdev_map[MAX_NUM_DSI];
 
 #ifdef DEBUG
 static unsigned int dsi_perf;
 module_param_named(dsi_perf, dsi_perf, bool, 0644);
 #endif
 
-static inline void dsi_write_reg(const struct dsi_reg idx, u32 val)
+static inline struct dsi_data *dsi_get_dsidrv_data(struct platform_device *dsidev)
 {
-        __raw_writel(val, dsi.base + idx.idx);
+        return dev_get_drvdata(&dsidev->dev);
 }
 
-static inline u32 dsi_read_reg(const struct dsi_reg idx)
+static inline struct platform_device *dsi_get_dsidev_from_dssdev(struct omap_dss_device *dssdev)
 {
-        return __raw_readl(dsi.base + idx.idx);
+        return dsi_pdev_map[dssdev->phy.dsi.module];
+}
+
+struct platform_device *dsi_get_dsidev_from_id(int module)
+{
+        return dsi_pdev_map[module];
+}
+
+static int dsi_get_dsidev_id(struct platform_device *dsidev)
+{
+        /* TEMP: Pass 0 as the dsi module index till the time the dsi platform
+         * device names aren't changed to the form "omapdss_dsi.0",
+         * "omapdss_dsi.1" and so on */
+        BUG_ON(dsidev->id != -1);
+
+        return 0;
+}
+
+static inline void dsi_write_reg(struct platform_device *dsidev,
+                const struct dsi_reg idx, u32 val)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        __raw_writel(val, dsi->base + idx.idx);
+}
+
+static inline u32 dsi_read_reg(struct platform_device *dsidev,
+                const struct dsi_reg idx)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        return __raw_readl(dsi->base + idx.idx);
 }
 
 
@@ -318,21 +398,29 @@ void dsi_restore_context(void)
 {
 }
 
-void dsi_bus_lock(void)
+void dsi_bus_lock(struct omap_dss_device *dssdev)
 {
-        down(&dsi.bus_lock);
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        down(&dsi->bus_lock);
 }
 EXPORT_SYMBOL(dsi_bus_lock);
 
-void dsi_bus_unlock(void)
+void dsi_bus_unlock(struct omap_dss_device *dssdev)
 {
-        up(&dsi.bus_lock);
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        up(&dsi->bus_lock);
 }
 EXPORT_SYMBOL(dsi_bus_unlock);
 
-static bool dsi_bus_is_locked(void)
+static bool dsi_bus_is_locked(struct platform_device *dsidev)
 {
-        return dsi.bus_lock.count == 0;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        return dsi->bus_lock.count == 0;
 }
 
 static void dsi_completion_handler(void *data, u32 mask)
@@ -340,12 +428,12 @@ static void dsi_completion_handler(void *data, u32 mask)
         complete((struct completion *)data);
 }
 
-static inline int wait_for_bit_change(const struct dsi_reg idx, int bitnum,
-                int value)
+static inline int wait_for_bit_change(struct platform_device *dsidev,
+                const struct dsi_reg idx, int bitnum, int value)
 {
         int t = 100000;
 
-        while (REG_GET(idx, bitnum, bitnum) != value) {
+        while (REG_GET(dsidev, idx, bitnum, bitnum) != value) {
                 if (--t == 0)
                         return !value;
         }
@@ -354,18 +442,21 @@ static inline int wait_for_bit_change(const struct dsi_reg idx, int bitnum,
 }
 
 #ifdef DEBUG
-static void dsi_perf_mark_setup(void)
+static void dsi_perf_mark_setup(struct platform_device *dsidev)
 {
-        dsi.perf_setup_time = ktime_get();
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        dsi->perf_setup_time = ktime_get();
 }
 
-static void dsi_perf_mark_start(void)
+static void dsi_perf_mark_start(struct platform_device *dsidev)
 {
-        dsi.perf_start_time = ktime_get();
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        dsi->perf_start_time = ktime_get();
 }
 
-static void dsi_perf_show(const char *name)
+static void dsi_perf_show(struct platform_device *dsidev, const char *name)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         ktime_t t, setup_time, trans_time;
         u32 total_bytes;
         u32 setup_us, trans_us, total_us;
@@ -375,21 +466,21 @@ static void dsi_perf_show(const char *name)
 
         t = ktime_get();
 
-        setup_time = ktime_sub(dsi.perf_start_time, dsi.perf_setup_time);
+        setup_time = ktime_sub(dsi->perf_start_time, dsi->perf_setup_time);
         setup_us = (u32)ktime_to_us(setup_time);
         if (setup_us == 0)
                 setup_us = 1;
 
-        trans_time = ktime_sub(t, dsi.perf_start_time);
+        trans_time = ktime_sub(t, dsi->perf_start_time);
         trans_us = (u32)ktime_to_us(trans_time);
         if (trans_us == 0)
                 trans_us = 1;
 
         total_us = setup_us + trans_us;
 
-        total_bytes = dsi.update_region.w *
-                dsi.update_region.h *
-                dsi.update_region.device->ctrl.pixel_size / 8;
+        total_bytes = dsi->update_region.w *
+                dsi->update_region.h *
+                dsi->update_region.device->ctrl.pixel_size / 8;
 
         printk(KERN_INFO "DSI(%s): %u us + %u us = %u us (%uHz), "
                         "%u bytes, %u kbytes/sec\n",
@@ -402,9 +493,9 @@ static void dsi_perf_show(const char *name)
                         total_bytes * 1000 / total_us);
 }
 #else
-#define dsi_perf_mark_setup()
-#define dsi_perf_mark_start()
-#define dsi_perf_show(x)
+#define dsi_perf_mark_setup(x)
+#define dsi_perf_mark_start(x)
+#define dsi_perf_show(x, y)
 #endif
 
 static void print_irq_status(u32 status)
@@ -510,38 +601,42 @@ static void print_irq_status_cio(u32 status)
 }
 
 #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS
-static void dsi_collect_irq_stats(u32 irqstatus, u32 *vcstatus, u32 ciostatus)
+static void dsi_collect_irq_stats(struct platform_device *dsidev, u32 irqstatus,
+                u32 *vcstatus, u32 ciostatus)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int i;
 
-        spin_lock(&dsi.irq_stats_lock);
+        spin_lock(&dsi->irq_stats_lock);
 
-        dsi.irq_stats.irq_count++;
-        dss_collect_irq_stats(irqstatus, dsi.irq_stats.dsi_irqs);
+        dsi->irq_stats.irq_count++;
+        dss_collect_irq_stats(irqstatus, dsi->irq_stats.dsi_irqs);
 
         for (i = 0; i < 4; ++i)
-                dss_collect_irq_stats(vcstatus[i], dsi.irq_stats.vc_irqs[i]);
+                dss_collect_irq_stats(vcstatus[i], dsi->irq_stats.vc_irqs[i]);
 
-        dss_collect_irq_stats(ciostatus, dsi.irq_stats.cio_irqs);
+        dss_collect_irq_stats(ciostatus, dsi->irq_stats.cio_irqs);
 
-        spin_unlock(&dsi.irq_stats_lock);
+        spin_unlock(&dsi->irq_stats_lock);
 }
 #else
-#define dsi_collect_irq_stats(irqstatus, vcstatus, ciostatus)
+#define dsi_collect_irq_stats(dsidev, irqstatus, vcstatus, ciostatus)
 #endif
 
 static int debug_irq;
 
-static void dsi_handle_irq_errors(u32 irqstatus, u32 *vcstatus, u32 ciostatus)
+static void dsi_handle_irq_errors(struct platform_device *dsidev, u32 irqstatus,
+                u32 *vcstatus, u32 ciostatus)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int i;
 
         if (irqstatus & DSI_IRQ_ERROR_MASK) {
                 DSSERR("DSI error, irqstatus %x\n", irqstatus);
                 print_irq_status(irqstatus);
-                spin_lock(&dsi.errors_lock);
-                dsi.errors |= irqstatus & DSI_IRQ_ERROR_MASK;
-                spin_unlock(&dsi.errors_lock);
+                spin_lock(&dsi->errors_lock);
+                dsi->errors |= irqstatus & DSI_IRQ_ERROR_MASK;
+                spin_unlock(&dsi->errors_lock);
         } else if (debug_irq) {
                 print_irq_status(irqstatus);
         }
@@ -602,22 +697,27 @@ static void dsi_handle_isrs(struct dsi_isr_tables *isr_tables,
 
 static irqreturn_t omap_dsi_irq_handler(int irq, void *arg)
 {
+        struct platform_device *dsidev;
+        struct dsi_data *dsi;
         u32 irqstatus, vcstatus[4], ciostatus;
         int i;
 
-        spin_lock(&dsi.irq_lock);
+        dsidev = (struct platform_device *) arg;
+        dsi = dsi_get_dsidrv_data(dsidev);
+
+        spin_lock(&dsi->irq_lock);
 
-        irqstatus = dsi_read_reg(DSI_IRQSTATUS);
+        irqstatus = dsi_read_reg(dsidev, DSI_IRQSTATUS);
 
         /* IRQ is not for us */
         if (!irqstatus) {
-                spin_unlock(&dsi.irq_lock);
+                spin_unlock(&dsi->irq_lock);
                 return IRQ_NONE;
         }
 
-        dsi_write_reg(DSI_IRQSTATUS, irqstatus & ~DSI_IRQ_CHANNEL_MASK);
+        dsi_write_reg(dsidev, DSI_IRQSTATUS, irqstatus & ~DSI_IRQ_CHANNEL_MASK);
         /* flush posted write */
-        dsi_read_reg(DSI_IRQSTATUS);
+        dsi_read_reg(dsidev, DSI_IRQSTATUS);
 
         for (i = 0; i < 4; ++i) {
                 if ((irqstatus & (1 << i)) == 0) {
@@ -625,45 +725,47 @@ static irqreturn_t omap_dsi_irq_handler(int irq, void *arg)
                         continue;
                 }
 
-                vcstatus[i] = dsi_read_reg(DSI_VC_IRQSTATUS(i));
+                vcstatus[i] = dsi_read_reg(dsidev, DSI_VC_IRQSTATUS(i));
 
-                dsi_write_reg(DSI_VC_IRQSTATUS(i), vcstatus[i]);
+                dsi_write_reg(dsidev, DSI_VC_IRQSTATUS(i), vcstatus[i]);
                 /* flush posted write */
-                dsi_read_reg(DSI_VC_IRQSTATUS(i));
+                dsi_read_reg(dsidev, DSI_VC_IRQSTATUS(i));
         }
 
         if (irqstatus & DSI_IRQ_COMPLEXIO_ERR) {
-                ciostatus = dsi_read_reg(DSI_COMPLEXIO_IRQ_STATUS);
+                ciostatus = dsi_read_reg(dsidev, DSI_COMPLEXIO_IRQ_STATUS);
 
-                dsi_write_reg(DSI_COMPLEXIO_IRQ_STATUS, ciostatus);
+                dsi_write_reg(dsidev, DSI_COMPLEXIO_IRQ_STATUS, ciostatus);
                 /* flush posted write */
-                dsi_read_reg(DSI_COMPLEXIO_IRQ_STATUS);
+                dsi_read_reg(dsidev, DSI_COMPLEXIO_IRQ_STATUS);
         } else {
                 ciostatus = 0;
         }
 
 #ifdef DSI_CATCH_MISSING_TE
         if (irqstatus & DSI_IRQ_TE_TRIGGER)
-                del_timer(&dsi.te_timer);
+                del_timer(&dsi->te_timer);
 #endif
 
         /* make a copy and unlock, so that isrs can unregister
          * themselves */
-        memcpy(&dsi.isr_tables_copy, &dsi.isr_tables, sizeof(dsi.isr_tables));
+        memcpy(&dsi->isr_tables_copy, &dsi->isr_tables,
+                sizeof(dsi->isr_tables));
 
-        spin_unlock(&dsi.irq_lock);
+        spin_unlock(&dsi->irq_lock);
 
-        dsi_handle_isrs(&dsi.isr_tables_copy, irqstatus, vcstatus, ciostatus);
+        dsi_handle_isrs(&dsi->isr_tables_copy, irqstatus, vcstatus, ciostatus);
 
-        dsi_handle_irq_errors(irqstatus, vcstatus, ciostatus);
+        dsi_handle_irq_errors(dsidev, irqstatus, vcstatus, ciostatus);
 
-        dsi_collect_irq_stats(irqstatus, vcstatus, ciostatus);
+        dsi_collect_irq_stats(dsidev, irqstatus, vcstatus, ciostatus);
 
         return IRQ_HANDLED;
 }
 
-/* dsi.irq_lock has to be locked by the caller */
-static void _omap_dsi_configure_irqs(struct dsi_isr_data *isr_array,
+/* dsi->irq_lock has to be locked by the caller */
+static void _omap_dsi_configure_irqs(struct platform_device *dsidev,
+                struct dsi_isr_data *isr_array,
                 unsigned isr_array_size, u32 default_mask,
                 const struct dsi_reg enable_reg,
                 const struct dsi_reg status_reg)
@@ -684,61 +786,67 @@ static void _omap_dsi_configure_irqs(struct dsi_isr_data *isr_array,
                 mask |= isr_data->mask;
         }
 
-        old_mask = dsi_read_reg(enable_reg);
+        old_mask = dsi_read_reg(dsidev, enable_reg);
         /* clear the irqstatus for newly enabled irqs */
-        dsi_write_reg(status_reg, (mask ^ old_mask) & mask);
-        dsi_write_reg(enable_reg, mask);
+        dsi_write_reg(dsidev, status_reg, (mask ^ old_mask) & mask);
+        dsi_write_reg(dsidev, enable_reg, mask);
 
         /* flush posted writes */
-        dsi_read_reg(enable_reg);
-        dsi_read_reg(status_reg);
+        dsi_read_reg(dsidev, enable_reg);
+        dsi_read_reg(dsidev, status_reg);
 }
 
-/* dsi.irq_lock has to be locked by the caller */
-static void _omap_dsi_set_irqs(void)
+/* dsi->irq_lock has to be locked by the caller */
+static void _omap_dsi_set_irqs(struct platform_device *dsidev)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         u32 mask = DSI_IRQ_ERROR_MASK;
 #ifdef DSI_CATCH_MISSING_TE
         mask |= DSI_IRQ_TE_TRIGGER;
 #endif
-        _omap_dsi_configure_irqs(dsi.isr_tables.isr_table,
-                        ARRAY_SIZE(dsi.isr_tables.isr_table), mask,
+        _omap_dsi_configure_irqs(dsidev, dsi->isr_tables.isr_table,
+                        ARRAY_SIZE(dsi->isr_tables.isr_table), mask,
                         DSI_IRQENABLE, DSI_IRQSTATUS);
 }
 
-/* dsi.irq_lock has to be locked by the caller */
-static void _omap_dsi_set_irqs_vc(int vc)
+/* dsi->irq_lock has to be locked by the caller */
+static void _omap_dsi_set_irqs_vc(struct platform_device *dsidev, int vc)
 {
-        _omap_dsi_configure_irqs(dsi.isr_tables.isr_table_vc[vc],
-                        ARRAY_SIZE(dsi.isr_tables.isr_table_vc[vc]),
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        _omap_dsi_configure_irqs(dsidev, dsi->isr_tables.isr_table_vc[vc],
+                        ARRAY_SIZE(dsi->isr_tables.isr_table_vc[vc]),
                         DSI_VC_IRQ_ERROR_MASK,
                         DSI_VC_IRQENABLE(vc), DSI_VC_IRQSTATUS(vc));
 }
 
-/* dsi.irq_lock has to be locked by the caller */
-static void _omap_dsi_set_irqs_cio(void)
+/* dsi->irq_lock has to be locked by the caller */
+static void _omap_dsi_set_irqs_cio(struct platform_device *dsidev)
 {
-        _omap_dsi_configure_irqs(dsi.isr_tables.isr_table_cio,
-                        ARRAY_SIZE(dsi.isr_tables.isr_table_cio),
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        _omap_dsi_configure_irqs(dsidev, dsi->isr_tables.isr_table_cio,
+                        ARRAY_SIZE(dsi->isr_tables.isr_table_cio),
                         DSI_CIO_IRQ_ERROR_MASK,
                         DSI_COMPLEXIO_IRQ_ENABLE, DSI_COMPLEXIO_IRQ_STATUS);
 }
 
-static void _dsi_initialize_irq(void)
+static void _dsi_initialize_irq(struct platform_device *dsidev)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int vc;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
-        memset(&dsi.isr_tables, 0, sizeof(dsi.isr_tables));
+        memset(&dsi->isr_tables, 0, sizeof(dsi->isr_tables));
 
-        _omap_dsi_set_irqs();
+        _omap_dsi_set_irqs(dsidev);
         for (vc = 0; vc < 4; ++vc)
-                _omap_dsi_set_irqs_vc(vc);
-        _omap_dsi_set_irqs_cio();
+                _omap_dsi_set_irqs_vc(dsidev, vc);
+        _omap_dsi_set_irqs_cio(dsidev);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 }
 
 static int _dsi_register_isr(omap_dsi_isr_t isr, void *arg, u32 mask,
@@ -797,126 +905,137 @@ static int _dsi_unregister_isr(omap_dsi_isr_t isr, void *arg, u32 mask,
         return -EINVAL;
 }
 
-static int dsi_register_isr(omap_dsi_isr_t isr, void *arg, u32 mask)
+static int dsi_register_isr(struct platform_device *dsidev, omap_dsi_isr_t isr,
+                void *arg, u32 mask)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int r;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
-        r = _dsi_register_isr(isr, arg, mask, dsi.isr_tables.isr_table,
-                        ARRAY_SIZE(dsi.isr_tables.isr_table));
+        r = _dsi_register_isr(isr, arg, mask, dsi->isr_tables.isr_table,
+                        ARRAY_SIZE(dsi->isr_tables.isr_table));
 
         if (r == 0)
-                _omap_dsi_set_irqs();
+                _omap_dsi_set_irqs(dsidev);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 
         return r;
 }
 
-static int dsi_unregister_isr(omap_dsi_isr_t isr, void *arg, u32 mask)
+static int dsi_unregister_isr(struct platform_device *dsidev,
+                omap_dsi_isr_t isr, void *arg, u32 mask)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int r;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
-        r = _dsi_unregister_isr(isr, arg, mask, dsi.isr_tables.isr_table,
-                        ARRAY_SIZE(dsi.isr_tables.isr_table));
+        r = _dsi_unregister_isr(isr, arg, mask, dsi->isr_tables.isr_table,
+                        ARRAY_SIZE(dsi->isr_tables.isr_table));
 
         if (r == 0)
-                _omap_dsi_set_irqs();
+                _omap_dsi_set_irqs(dsidev);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 
         return r;
 }
 
-static int dsi_register_isr_vc(int channel, omap_dsi_isr_t isr, void *arg,
-                u32 mask)
+static int dsi_register_isr_vc(struct platform_device *dsidev, int channel,
+                omap_dsi_isr_t isr, void *arg, u32 mask)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int r;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
         r = _dsi_register_isr(isr, arg, mask,
-                        dsi.isr_tables.isr_table_vc[channel],
-                        ARRAY_SIZE(dsi.isr_tables.isr_table_vc[channel]));
+                        dsi->isr_tables.isr_table_vc[channel],
+                        ARRAY_SIZE(dsi->isr_tables.isr_table_vc[channel]));
 
         if (r == 0)
-                _omap_dsi_set_irqs_vc(channel);
+                _omap_dsi_set_irqs_vc(dsidev, channel);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 
         return r;
 }
 
-static int dsi_unregister_isr_vc(int channel, omap_dsi_isr_t isr, void *arg,
-                u32 mask)
+static int dsi_unregister_isr_vc(struct platform_device *dsidev, int channel,
+                omap_dsi_isr_t isr, void *arg, u32 mask)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int r;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
         r = _dsi_unregister_isr(isr, arg, mask,
-                        dsi.isr_tables.isr_table_vc[channel],
-                        ARRAY_SIZE(dsi.isr_tables.isr_table_vc[channel]));
+                        dsi->isr_tables.isr_table_vc[channel],
+                        ARRAY_SIZE(dsi->isr_tables.isr_table_vc[channel]));
 
         if (r == 0)
-                _omap_dsi_set_irqs_vc(channel);
+                _omap_dsi_set_irqs_vc(dsidev, channel);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 
         return r;
 }
 
-static int dsi_register_isr_cio(omap_dsi_isr_t isr, void *arg, u32 mask)
+static int dsi_register_isr_cio(struct platform_device *dsidev,
+                omap_dsi_isr_t isr, void *arg, u32 mask)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int r;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
-        r = _dsi_register_isr(isr, arg, mask, dsi.isr_tables.isr_table_cio,
-                        ARRAY_SIZE(dsi.isr_tables.isr_table_cio));
+        r = _dsi_register_isr(isr, arg, mask, dsi->isr_tables.isr_table_cio,
+                        ARRAY_SIZE(dsi->isr_tables.isr_table_cio));
 
         if (r == 0)
-                _omap_dsi_set_irqs_cio();
+                _omap_dsi_set_irqs_cio(dsidev);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 
         return r;
 }
 
-static int dsi_unregister_isr_cio(omap_dsi_isr_t isr, void *arg, u32 mask)
+static int dsi_unregister_isr_cio(struct platform_device *dsidev,
+                omap_dsi_isr_t isr, void *arg, u32 mask)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         int r;
 
-        spin_lock_irqsave(&dsi.irq_lock, flags);
+        spin_lock_irqsave(&dsi->irq_lock, flags);
 
-        r = _dsi_unregister_isr(isr, arg, mask, dsi.isr_tables.isr_table_cio,
-                        ARRAY_SIZE(dsi.isr_tables.isr_table_cio));
+        r = _dsi_unregister_isr(isr, arg, mask, dsi->isr_tables.isr_table_cio,
+                        ARRAY_SIZE(dsi->isr_tables.isr_table_cio));
 
         if (r == 0)
-                _omap_dsi_set_irqs_cio();
+                _omap_dsi_set_irqs_cio(dsidev);
 
-        spin_unlock_irqrestore(&dsi.irq_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_lock, flags);
 
         return r;
 }
 
-static u32 dsi_get_errors(void)
+static u32 dsi_get_errors(struct platform_device *dsidev)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         u32 e;
-        spin_lock_irqsave(&dsi.errors_lock, flags);
-        e = dsi.errors;
-        dsi.errors = 0;
-        spin_unlock_irqrestore(&dsi.errors_lock, flags);
+        spin_lock_irqsave(&dsi->errors_lock, flags);
+        e = dsi->errors;
+        dsi->errors = 0;
+        spin_unlock_irqrestore(&dsi->errors_lock, flags);
         return e;
 }
 
@@ -930,23 +1049,27 @@ static inline void enable_clocks(bool enable)
 }
 
 /* source clock for DSI PLL. this could also be PCLKFREE */
-static inline void dsi_enable_pll_clock(bool enable)
+static inline void dsi_enable_pll_clock(struct platform_device *dsidev,
+                bool enable)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
         if (enable)
                 dss_clk_enable(DSS_CLK_SYSCK);
         else
                 dss_clk_disable(DSS_CLK_SYSCK);
 
-        if (enable && dsi.pll_locked) {
-                if (wait_for_bit_change(DSI_PLL_STATUS, 1, 1) != 1)
+        if (enable && dsi->pll_locked) {
+                if (wait_for_bit_change(dsidev, DSI_PLL_STATUS, 1, 1) != 1)
                         DSSERR("cannot lock PLL when enabling clocks\n");
         }
 }
 
 #ifdef DEBUG
-static void _dsi_print_reset_status(void)
+static void _dsi_print_reset_status(struct platform_device *dsidev)
 {
         u32 l;
+        int b0, b1, b2;
 
         if (!dss_debug)
                 return;
@@ -954,35 +1077,47 @@ static void _dsi_print_reset_status(void)
         /* A dummy read using the SCP interface to any DSIPHY register is
          * required after DSIPHY reset to complete the reset of the DSI complex
          * I/O. */
-        l = dsi_read_reg(DSI_DSIPHY_CFG5);
+        l = dsi_read_reg(dsidev, DSI_DSIPHY_CFG5);
 
         printk(KERN_DEBUG "DSI resets: ");
 
-        l = dsi_read_reg(DSI_PLL_STATUS);
+        l = dsi_read_reg(dsidev, DSI_PLL_STATUS);
         printk("PLL (%d) ", FLD_GET(l, 0, 0));
 
-        l = dsi_read_reg(DSI_COMPLEXIO_CFG1);
+        l = dsi_read_reg(dsidev, DSI_COMPLEXIO_CFG1);
         printk("CIO (%d) ", FLD_GET(l, 29, 29));
 
-        l = dsi_read_reg(DSI_DSIPHY_CFG5);
-        printk("PHY (%x, %d, %d, %d)\n",
-                        FLD_GET(l, 28, 26),
+        if (dss_has_feature(FEAT_DSI_REVERSE_TXCLKESC)) {
+                b0 = 28;
+                b1 = 27;
+                b2 = 26;
+        } else {
+                b0 = 24;
+                b1 = 25;
+                b2 = 26;
+        }
+
+        l = dsi_read_reg(dsidev, DSI_DSIPHY_CFG5);
+        printk("PHY (%x%x%x, %d, %d, %d)\n",
+                        FLD_GET(l, b0, b0),
+                        FLD_GET(l, b1, b1),
+                        FLD_GET(l, b2, b2),
                         FLD_GET(l, 29, 29),
                         FLD_GET(l, 30, 30),
                         FLD_GET(l, 31, 31));
 }
 #else
-#define _dsi_print_reset_status()
+#define _dsi_print_reset_status(x)
 #endif
 
-static inline int dsi_if_enable(bool enable)
+static inline int dsi_if_enable(struct platform_device *dsidev, bool enable)
 {
         DSSDBG("dsi_if_enable(%d)\n", enable);
 
         enable = enable ? 1 : 0;
-        REG_FLD_MOD(DSI_CTRL, enable, 0, 0); /* IF_EN */
+        REG_FLD_MOD(dsidev, DSI_CTRL, enable, 0, 0); /* IF_EN */
 
-        if (wait_for_bit_change(DSI_CTRL, 0, enable) != enable) {
+        if (wait_for_bit_change(dsidev, DSI_CTRL, 0, enable) != enable) {
                         DSSERR("Failed to set dsi_if_enable to %d\n", enable);
                         return -EIO;
         }
@@ -990,31 +1125,38 @@ static inline int dsi_if_enable(bool enable)
         return 0;
 }
 
-unsigned long dsi_get_pll_hsdiv_dispc_rate(void)
+unsigned long dsi_get_pll_hsdiv_dispc_rate(struct platform_device *dsidev)
 {
-        return dsi.current_cinfo.dsi_pll_hsdiv_dispc_clk;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        return dsi->current_cinfo.dsi_pll_hsdiv_dispc_clk;
 }
 
-static unsigned long dsi_get_pll_hsdiv_dsi_rate(void)
+static unsigned long dsi_get_pll_hsdiv_dsi_rate(struct platform_device *dsidev)
 {
-        return dsi.current_cinfo.dsi_pll_hsdiv_dsi_clk;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        return dsi->current_cinfo.dsi_pll_hsdiv_dsi_clk;
 }
 
-static unsigned long dsi_get_txbyteclkhs(void)
+static unsigned long dsi_get_txbyteclkhs(struct platform_device *dsidev)
 {
-        return dsi.current_cinfo.clkin4ddr / 16;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        return dsi->current_cinfo.clkin4ddr / 16;
 }
 
-static unsigned long dsi_fclk_rate(void)
+static unsigned long dsi_fclk_rate(struct platform_device *dsidev)
 {
         unsigned long r;
+        int dsi_module = dsi_get_dsidev_id(dsidev);
 
-        if (dss_get_dsi_clk_source() == DSS_CLK_SRC_FCK) {
+        if (dss_get_dsi_clk_source(dsi_module) == OMAP_DSS_CLK_SRC_FCK) {
                 /* DSI FCLK source is DSS_CLK_FCK */
                 r = dss_clk_get_rate(DSS_CLK_FCK);
         } else {
                 /* DSI FCLK source is dsi_pll_hsdiv_dsi_clk */
-                r = dsi_get_pll_hsdiv_dsi_rate();
+                r = dsi_get_pll_hsdiv_dsi_rate(dsidev);
         }
 
         return r;
@@ -1022,31 +1164,50 @@ static unsigned long dsi_fclk_rate(void)
 
 static int dsi_set_lp_clk_divisor(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long dsi_fclk;
         unsigned lp_clk_div;
         unsigned long lp_clk;
 
-        lp_clk_div = dssdev->phy.dsi.div.lp_clk_div;
+        lp_clk_div = dssdev->clocks.dsi.lp_clk_div;
 
-        if (lp_clk_div == 0 || lp_clk_div > dsi.lpdiv_max)
+        if (lp_clk_div == 0 || lp_clk_div > dsi->lpdiv_max)
                 return -EINVAL;
 
-        dsi_fclk = dsi_fclk_rate();
+        dsi_fclk = dsi_fclk_rate(dsidev);
 
         lp_clk = dsi_fclk / 2 / lp_clk_div;
 
         DSSDBG("LP_CLK_DIV %u, LP_CLK %lu\n", lp_clk_div, lp_clk);
-        dsi.current_cinfo.lp_clk = lp_clk;
-        dsi.current_cinfo.lp_clk_div = lp_clk_div;
+        dsi->current_cinfo.lp_clk = lp_clk;
+        dsi->current_cinfo.lp_clk_div = lp_clk_div;
 
-        REG_FLD_MOD(DSI_CLK_CTRL, lp_clk_div, 12, 0);   /* LP_CLK_DIVISOR */
+        /* LP_CLK_DIVISOR */
+        REG_FLD_MOD(dsidev, DSI_CLK_CTRL, lp_clk_div, 12, 0);
 
-        REG_FLD_MOD(DSI_CLK_CTRL, dsi_fclk > 30000000 ? 1 : 0,
-                        21, 21);                /* LP_RX_SYNCHRO_ENABLE */
+        /* LP_RX_SYNCHRO_ENABLE */
+        REG_FLD_MOD(dsidev, DSI_CLK_CTRL, dsi_fclk > 30000000 ? 1 : 0, 21, 21);
 
         return 0;
 }
 
+static void dsi_enable_scp_clk(struct platform_device *dsidev)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        if (dsi->scp_clk_refcount++ == 0)
+                REG_FLD_MOD(dsidev, DSI_CLK_CTRL, 1, 14, 14); /* CIO_CLK_ICG */
+}
+
+static void dsi_disable_scp_clk(struct platform_device *dsidev)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        WARN_ON(dsi->scp_clk_refcount == 0);
+        if (--dsi->scp_clk_refcount == 0)
+                REG_FLD_MOD(dsidev, DSI_CLK_CTRL, 0, 14, 14); /* CIO_CLK_ICG */
+}
 
 enum dsi_pll_power_state {
         DSI_PLL_POWER_OFF       = 0x0,
@@ -1055,14 +1216,21 @@ enum dsi_pll_power_state {
         DSI_PLL_POWER_ON_DIV    = 0x3,
 };
 
-static int dsi_pll_power(enum dsi_pll_power_state state)
+static int dsi_pll_power(struct platform_device *dsidev,
+                enum dsi_pll_power_state state)
 {
         int t = 0;
 
-        REG_FLD_MOD(DSI_CLK_CTRL, state, 31, 30);       /* PLL_PWR_CMD */
+        /* DSI-PLL power command 0x3 is not working */
+        if (dss_has_feature(FEAT_DSI_PLL_PWR_BUG) &&
+                        state == DSI_PLL_POWER_ON_DIV)
+                state = DSI_PLL_POWER_ON_ALL;
+
+        /* PLL_PWR_CMD */
+        REG_FLD_MOD(dsidev, DSI_CLK_CTRL, state, 31, 30);
 
         /* PLL_PWR_STATUS */
-        while (FLD_GET(dsi_read_reg(DSI_CLK_CTRL), 29, 28) != state) {
+        while (FLD_GET(dsi_read_reg(dsidev, DSI_CLK_CTRL), 29, 28) != state) {
                 if (++t > 1000) {
                         DSSERR("Failed to set DSI PLL power mode to %d\n",
                                         state);
@@ -1078,16 +1246,19 @@ static int dsi_pll_power(enum dsi_pll_power_state state)
 static int dsi_calc_clock_rates(struct omap_dss_device *dssdev,
                 struct dsi_clock_info *cinfo)
 {
-        if (cinfo->regn == 0 || cinfo->regn > dsi.regn_max)
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        if (cinfo->regn == 0 || cinfo->regn > dsi->regn_max)
                 return -EINVAL;
 
-        if (cinfo->regm == 0 || cinfo->regm > dsi.regm_max)
+        if (cinfo->regm == 0 || cinfo->regm > dsi->regm_max)
                 return -EINVAL;
 
-        if (cinfo->regm_dispc > dsi.regm_dispc_max)
+        if (cinfo->regm_dispc > dsi->regm_dispc_max)
                 return -EINVAL;
 
-        if (cinfo->regm_dsi > dsi.regm_dsi_max)
+        if (cinfo->regm_dsi > dsi->regm_dsi_max)
                 return -EINVAL;
 
         if (cinfo->use_sys_clk) {
@@ -1106,7 +1277,7 @@ static int dsi_calc_clock_rates(struct omap_dss_device *dssdev,
 
         cinfo->fint = cinfo->clkin / (cinfo->regn * (cinfo->highfreq ? 2 : 1));
 
-        if (cinfo->fint > dsi.fint_max || cinfo->fint < dsi.fint_min)
+        if (cinfo->fint > dsi->fint_max || cinfo->fint < dsi->fint_min)
                 return -EINVAL;
 
         cinfo->clkin4ddr = 2 * cinfo->regm * cinfo->fint;
@@ -1129,10 +1300,11 @@ static int dsi_calc_clock_rates(struct omap_dss_device *dssdev,
         return 0;
 }
 
-int dsi_pll_calc_clock_div_pck(bool is_tft, unsigned long req_pck,
-                struct dsi_clock_info *dsi_cinfo,
+int dsi_pll_calc_clock_div_pck(struct platform_device *dsidev, bool is_tft,
+                unsigned long req_pck, struct dsi_clock_info *dsi_cinfo,
                 struct dispc_clock_info *dispc_cinfo)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         struct dsi_clock_info cur, best;
         struct dispc_clock_info best_dispc;
         int min_fck_per_pck;
@@ -1143,10 +1315,10 @@ int dsi_pll_calc_clock_div_pck(bool is_tft, unsigned long req_pck,
 
         max_dss_fck = dss_feat_get_param_max(FEAT_PARAM_DSS_FCK);
 
-        if (req_pck == dsi.cache_req_pck &&
-                        dsi.cache_cinfo.clkin == dss_sys_clk) {
+        if (req_pck == dsi->cache_req_pck &&
+                        dsi->cache_cinfo.clkin == dss_sys_clk) {
                 DSSDBG("DSI clock info found from cache\n");
-                *dsi_cinfo = dsi.cache_cinfo;
+                *dsi_cinfo = dsi->cache_cinfo;
                 dispc_find_clk_divs(is_tft, req_pck,
                         dsi_cinfo->dsi_pll_hsdiv_dispc_clk, dispc_cinfo);
                 return 0;
@@ -1176,17 +1348,17 @@ retry:
         /* no highfreq: 0.75MHz < Fint = clkin / regn < 2.1MHz */
         /* highfreq: 0.75MHz < Fint = clkin / (2*regn) < 2.1MHz */
         /* To reduce PLL lock time, keep Fint high (around 2 MHz) */
-        for (cur.regn = 1; cur.regn < dsi.regn_max; ++cur.regn) {
+        for (cur.regn = 1; cur.regn < dsi->regn_max; ++cur.regn) {
                 if (cur.highfreq == 0)
                         cur.fint = cur.clkin / cur.regn;
                 else
                         cur.fint = cur.clkin / (2 * cur.regn);
 
-                if (cur.fint > dsi.fint_max || cur.fint < dsi.fint_min)
+                if (cur.fint > dsi->fint_max || cur.fint < dsi->fint_min)
                         continue;
 
                 /* DSIPHY(MHz) = (2 * regm / regn) * (clkin / (highfreq + 1)) */
-                for (cur.regm = 1; cur.regm < dsi.regm_max; ++cur.regm) {
+                for (cur.regm = 1; cur.regm < dsi->regm_max; ++cur.regm) {
                         unsigned long a, b;
 
                         a = 2 * cur.regm * (cur.clkin/1000);
@@ -1198,8 +1370,8 @@ retry:
 
                         /* dsi_pll_hsdiv_dispc_clk(MHz) =
                          * DSIPHY(MHz) / regm_dispc  < 173MHz/186Mhz */
-                        for (cur.regm_dispc = 1; cur.regm_dispc < dsi.regm_dispc_max;
-                                        ++cur.regm_dispc) {
+                        for (cur.regm_dispc = 1; cur.regm_dispc <
+                                        dsi->regm_dispc_max; ++cur.regm_dispc) {
                                 struct dispc_clock_info cur_dispc;
                                 cur.dsi_pll_hsdiv_dispc_clk =
                                         cur.clkin4ddr / cur.regm_dispc;
@@ -1259,34 +1431,39 @@ found:
         if (dispc_cinfo)
                 *dispc_cinfo = best_dispc;
 
-        dsi.cache_req_pck = req_pck;
-        dsi.cache_clk_freq = 0;
-        dsi.cache_cinfo = best;
+        dsi->cache_req_pck = req_pck;
+        dsi->cache_clk_freq = 0;
+        dsi->cache_cinfo = best;
 
         return 0;
 }
 
-int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo)
+int dsi_pll_set_clock_div(struct platform_device *dsidev,
+                struct dsi_clock_info *cinfo)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int r = 0;
         u32 l;
-        int f;
+        int f = 0;
         u8 regn_start, regn_end, regm_start, regm_end;
         u8 regm_dispc_start, regm_dispc_end, regm_dsi_start, regm_dsi_end;
 
         DSSDBGF();
 
-        dsi.current_cinfo.fint = cinfo->fint;
-        dsi.current_cinfo.clkin4ddr = cinfo->clkin4ddr;
-        dsi.current_cinfo.dsi_pll_hsdiv_dispc_clk =
+        dsi->current_cinfo.use_sys_clk = cinfo->use_sys_clk;
+        dsi->current_cinfo.highfreq = cinfo->highfreq;
+
+        dsi->current_cinfo.fint = cinfo->fint;
+        dsi->current_cinfo.clkin4ddr = cinfo->clkin4ddr;
+        dsi->current_cinfo.dsi_pll_hsdiv_dispc_clk =
                         cinfo->dsi_pll_hsdiv_dispc_clk;
-        dsi.current_cinfo.dsi_pll_hsdiv_dsi_clk =
+        dsi->current_cinfo.dsi_pll_hsdiv_dsi_clk =
                         cinfo->dsi_pll_hsdiv_dsi_clk;
 
-        dsi.current_cinfo.regn = cinfo->regn;
-        dsi.current_cinfo.regm = cinfo->regm;
-        dsi.current_cinfo.regm_dispc = cinfo->regm_dispc;
-        dsi.current_cinfo.regm_dsi = cinfo->regm_dsi;
+        dsi->current_cinfo.regn = cinfo->regn;
+        dsi->current_cinfo.regm = cinfo->regm;
+        dsi->current_cinfo.regm_dispc = cinfo->regm_dispc;
+        dsi->current_cinfo.regm_dsi = cinfo->regm_dsi;
 
         DSSDBG("DSI Fint %ld\n", cinfo->fint);
 
@@ -1309,12 +1486,12 @@ int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo)
         DSSDBG("Clock lane freq %ld Hz\n", cinfo->clkin4ddr / 4);
 
         DSSDBG("regm_dispc = %d, %s (%s) = %lu\n", cinfo->regm_dispc,
-                dss_get_generic_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC),
-                dss_feat_get_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC),
+                dss_get_generic_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC),
+                dss_feat_get_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC),
                 cinfo->dsi_pll_hsdiv_dispc_clk);
         DSSDBG("regm_dsi = %d, %s (%s) = %lu\n", cinfo->regm_dsi,
-                dss_get_generic_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DSI),
-                dss_feat_get_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DSI),
+                dss_get_generic_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI),
+                dss_feat_get_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI),
                 cinfo->dsi_pll_hsdiv_dsi_clk);
 
         dss_feat_get_reg_field(FEAT_REG_DSIPLL_REGN, &regn_start, &regn_end);
@@ -1324,9 +1501,10 @@ int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo)
         dss_feat_get_reg_field(FEAT_REG_DSIPLL_REGM_DSI, &regm_dsi_start,
                         &regm_dsi_end);
 
-        REG_FLD_MOD(DSI_PLL_CONTROL, 0, 0, 0); /* DSI_PLL_AUTOMODE = manual */
+        /* DSI_PLL_AUTOMODE = manual */
+        REG_FLD_MOD(dsidev, DSI_PLL_CONTROL, 0, 0, 0);
 
-        l = dsi_read_reg(DSI_PLL_CONFIGURATION1);
+        l = dsi_read_reg(dsidev, DSI_PLL_CONFIGURATION1);
         l = FLD_MOD(l, 1, 0, 0);                /* DSI_PLL_STOPMODE */
         /* DSI_PLL_REGN */
         l = FLD_MOD(l, cinfo->regn - 1, regn_start, regn_end);
@@ -1338,22 +1516,22 @@ int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo)
         /* DSIPROTO_CLOCK_DIV */
         l = FLD_MOD(l, cinfo->regm_dsi > 0 ? cinfo->regm_dsi - 1 : 0,
                         regm_dsi_start, regm_dsi_end);
-        dsi_write_reg(DSI_PLL_CONFIGURATION1, l);
-
-        BUG_ON(cinfo->fint < dsi.fint_min || cinfo->fint > dsi.fint_max);
-        if (cinfo->fint < 1000000)
-                f = 0x3;
-        else if (cinfo->fint < 1250000)
-                f = 0x4;
-        else if (cinfo->fint < 1500000)
-                f = 0x5;
-        else if (cinfo->fint < 1750000)
-                f = 0x6;
-        else
-                f = 0x7;
+        dsi_write_reg(dsidev, DSI_PLL_CONFIGURATION1, l);
+
+        BUG_ON(cinfo->fint < dsi->fint_min || cinfo->fint > dsi->fint_max);
+
+        if (dss_has_feature(FEAT_DSI_PLL_FREQSEL)) {
+                f = cinfo->fint < 1000000 ? 0x3 :
+                        cinfo->fint < 1250000 ? 0x4 :
+                        cinfo->fint < 1500000 ? 0x5 :
+                        cinfo->fint < 1750000 ? 0x6 :
+                        0x7;
+        }
+
+        l = dsi_read_reg(dsidev, DSI_PLL_CONFIGURATION2);
 
-        l = dsi_read_reg(DSI_PLL_CONFIGURATION2);
-        l = FLD_MOD(l, f, 4, 1);                /* DSI_PLL_FREQSEL */
+        if (dss_has_feature(FEAT_DSI_PLL_FREQSEL))
+                l = FLD_MOD(l, f, 4, 1);        /* DSI_PLL_FREQSEL */
         l = FLD_MOD(l, cinfo->use_sys_clk ? 0 : 1,
                         11, 11);                /* DSI_PLL_CLKSEL */
         l = FLD_MOD(l, cinfo->highfreq,
@@ -1361,25 +1539,25 @@ int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo)
         l = FLD_MOD(l, 1, 13, 13);              /* DSI_PLL_REFEN */
         l = FLD_MOD(l, 0, 14, 14);              /* DSIPHY_CLKINEN */
         l = FLD_MOD(l, 1, 20, 20);              /* DSI_HSDIVBYPASS */
-        dsi_write_reg(DSI_PLL_CONFIGURATION2, l);
+        dsi_write_reg(dsidev, DSI_PLL_CONFIGURATION2, l);
 
-        REG_FLD_MOD(DSI_PLL_GO, 1, 0, 0);       /* DSI_PLL_GO */
+        REG_FLD_MOD(dsidev, DSI_PLL_GO, 1, 0, 0);       /* DSI_PLL_GO */
 
-        if (wait_for_bit_change(DSI_PLL_GO, 0, 0) != 0) {
+        if (wait_for_bit_change(dsidev, DSI_PLL_GO, 0, 0) != 0) {
                 DSSERR("dsi pll go bit not going down.\n");
                 r = -EIO;
                 goto err;
         }
 
-        if (wait_for_bit_change(DSI_PLL_STATUS, 1, 1) != 1) {
+        if (wait_for_bit_change(dsidev, DSI_PLL_STATUS, 1, 1) != 1) {
                 DSSERR("cannot lock PLL\n");
                 r = -EIO;
                 goto err;
         }
 
-        dsi.pll_locked = 1;
+        dsi->pll_locked = 1;
 
-        l = dsi_read_reg(DSI_PLL_CONFIGURATION2);
+        l = dsi_read_reg(dsidev, DSI_PLL_CONFIGURATION2);
         l = FLD_MOD(l, 0, 0, 0);        /* DSI_PLL_IDLE */
         l = FLD_MOD(l, 0, 5, 5);        /* DSI_PLL_PLLLPMODE */
         l = FLD_MOD(l, 0, 6, 6);        /* DSI_PLL_LOWCURRSTBY */
@@ -1394,52 +1572,53 @@ int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo)
         l = FLD_MOD(l, 1, 18, 18);      /* DSI_PROTO_CLOCK_EN */
         l = FLD_MOD(l, 0, 19, 19);      /* DSI_PROTO_CLOCK_PWDN */
         l = FLD_MOD(l, 0, 20, 20);      /* DSI_HSDIVBYPASS */
-        dsi_write_reg(DSI_PLL_CONFIGURATION2, l);
+        dsi_write_reg(dsidev, DSI_PLL_CONFIGURATION2, l);
 
         DSSDBG("PLL config done\n");
 err:
         return r;
 }
 
-int dsi_pll_init(struct omap_dss_device *dssdev, bool enable_hsclk,
+int dsi_pll_init(struct platform_device *dsidev, bool enable_hsclk,
                 bool enable_hsdiv)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int r = 0;
         enum dsi_pll_power_state pwstate;
 
         DSSDBG("PLL init\n");
 
-#ifdef CONFIG_OMAP2_DSS_USE_DSI_PLL
-        /*
-         * HACK: this is just a quick hack to get the USE_DSI_PLL
-         * option working. USE_DSI_PLL is itself a big hack, and
-         * should be removed.
-         */
-        if (dsi.vdds_dsi_reg == NULL) {
+        if (dsi->vdds_dsi_reg == NULL) {
                 struct regulator *vdds_dsi;
 
-                vdds_dsi = regulator_get(&dsi.pdev->dev, "vdds_dsi");
+                vdds_dsi = regulator_get(&dsi->pdev->dev, "vdds_dsi");
 
                 if (IS_ERR(vdds_dsi)) {
                         DSSERR("can't get VDDS_DSI regulator\n");
                         return PTR_ERR(vdds_dsi);
                 }
 
-                dsi.vdds_dsi_reg = vdds_dsi;
+                dsi->vdds_dsi_reg = vdds_dsi;
         }
-#endif
 
         enable_clocks(1);
-        dsi_enable_pll_clock(1);
+        dsi_enable_pll_clock(dsidev, 1);
+        /*
+         * Note: SCP CLK is not required on OMAP3, but it is required on OMAP4.
+         */
+        dsi_enable_scp_clk(dsidev);
 
-        r = regulator_enable(dsi.vdds_dsi_reg);
-        if (r)
-                goto err0;
+        if (!dsi->vdds_dsi_enabled) {
+                r = regulator_enable(dsi->vdds_dsi_reg);
+                if (r)
+                        goto err0;
+                dsi->vdds_dsi_enabled = true;
+        }
 
         /* XXX PLL does not come out of reset without this... */
         dispc_pck_free_enable(1);
 
-        if (wait_for_bit_change(DSI_PLL_STATUS, 0, 1) != 1) {
+        if (wait_for_bit_change(dsidev, DSI_PLL_STATUS, 0, 1) != 1) {
                 DSSERR("PLL not coming out of reset.\n");
                 r = -ENODEV;
                 dispc_pck_free_enable(0);
@@ -1459,7 +1638,7 @@ int dsi_pll_init(struct omap_dss_device *dssdev, bool enable_hsclk,
         else
                 pwstate = DSI_PLL_POWER_OFF;
 
-        r = dsi_pll_power(pwstate);
+        r = dsi_pll_power(dsidev, pwstate);
 
         if (r)
                 goto err1;
@@ -1468,42 +1647,53 @@ int dsi_pll_init(struct omap_dss_device *dssdev, bool enable_hsclk,
 
         return 0;
 err1:
-        regulator_disable(dsi.vdds_dsi_reg);
+        if (dsi->vdds_dsi_enabled) {
+                regulator_disable(dsi->vdds_dsi_reg);
+                dsi->vdds_dsi_enabled = false;
+        }
 err0:
+        dsi_disable_scp_clk(dsidev);
         enable_clocks(0);
-        dsi_enable_pll_clock(0);
+        dsi_enable_pll_clock(dsidev, 0);
         return r;
 }
 
-void dsi_pll_uninit(void)
+void dsi_pll_uninit(struct platform_device *dsidev, bool disconnect_lanes)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        dsi->pll_locked = 0;
+        dsi_pll_power(dsidev, DSI_PLL_POWER_OFF);
+        if (disconnect_lanes) {
+                WARN_ON(!dsi->vdds_dsi_enabled);
+                regulator_disable(dsi->vdds_dsi_reg);
+                dsi->vdds_dsi_enabled = false;
+        }
+
+        dsi_disable_scp_clk(dsidev);
         enable_clocks(0);
-        dsi_enable_pll_clock(0);
+        dsi_enable_pll_clock(dsidev, 0);
 
-        dsi.pll_locked = 0;
-        dsi_pll_power(DSI_PLL_POWER_OFF);
-        regulator_disable(dsi.vdds_dsi_reg);
         DSSDBG("PLL uninit done\n");
 }
 
-void dsi_dump_clocks(struct seq_file *s)
+static void dsi_dump_dsidev_clocks(struct platform_device *dsidev,
+                struct seq_file *s)
 {
-        int clksel;
-        struct dsi_clock_info *cinfo = &dsi.current_cinfo;
-        enum dss_clk_source dispc_clk_src, dsi_clk_src;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        struct dsi_clock_info *cinfo = &dsi->current_cinfo;
+        enum omap_dss_clk_source dispc_clk_src, dsi_clk_src;
+        int dsi_module = dsi_get_dsidev_id(dsidev);
 
         dispc_clk_src = dss_get_dispc_clk_source();
-        dsi_clk_src = dss_get_dsi_clk_source();
+        dsi_clk_src = dss_get_dsi_clk_source(dsi_module);
 
         enable_clocks(1);
 
-        clksel = REG_GET(DSI_PLL_CONFIGURATION2, 11, 11);
-
-        seq_printf(s,   "- DSI PLL -\n");
+        seq_printf(s,   "- DSI%d PLL -\n", dsi_module + 1);
 
         seq_printf(s,   "dsi pll source = %s\n",
-                        clksel == 0 ?
-                        "dss_sys_clk" : "pclkfree");
+                        cinfo->use_sys_clk ? "dss_sys_clk" : "pclkfree");
 
         seq_printf(s,   "Fint\t\t%-16luregn %u\n", cinfo->fint, cinfo->regn);
 
@@ -1515,7 +1705,7 @@ void dsi_dump_clocks(struct seq_file *s)
                         dss_feat_get_clk_source_name(dispc_clk_src),
                         cinfo->dsi_pll_hsdiv_dispc_clk,
                         cinfo->regm_dispc,
-                        dispc_clk_src == DSS_CLK_SRC_FCK ?
+                        dispc_clk_src == OMAP_DSS_CLK_SRC_FCK ?
                         "off" : "on");
 
         seq_printf(s,   "%s (%s)\t%-16luregm_dsi %u\t(%s)\n",
@@ -1523,45 +1713,55 @@ void dsi_dump_clocks(struct seq_file *s)
                         dss_feat_get_clk_source_name(dsi_clk_src),
                         cinfo->dsi_pll_hsdiv_dsi_clk,
                         cinfo->regm_dsi,
-                        dsi_clk_src == DSS_CLK_SRC_FCK ?
+                        dsi_clk_src == OMAP_DSS_CLK_SRC_FCK ?
                         "off" : "on");
 
-        seq_printf(s,   "- DSI -\n");
+        seq_printf(s,   "- DSI%d -\n", dsi_module + 1);
 
         seq_printf(s,   "dsi fclk source = %s (%s)\n",
                         dss_get_generic_clk_source_name(dsi_clk_src),
                         dss_feat_get_clk_source_name(dsi_clk_src));
 
-        seq_printf(s,   "DSI_FCLK\t%lu\n", dsi_fclk_rate());
+        seq_printf(s,   "DSI_FCLK\t%lu\n", dsi_fclk_rate(dsidev));
 
         seq_printf(s,   "DDR_CLK\t\t%lu\n",
                         cinfo->clkin4ddr / 4);
 
-        seq_printf(s,   "TxByteClkHS\t%lu\n", dsi_get_txbyteclkhs());
+        seq_printf(s,   "TxByteClkHS\t%lu\n", dsi_get_txbyteclkhs(dsidev));
 
         seq_printf(s,   "LP_CLK\t\t%lu\n", cinfo->lp_clk);
 
-        seq_printf(s,   "VP_CLK\t\t%lu\n"
-                        "VP_PCLK\t\t%lu\n",
-                        dispc_lclk_rate(OMAP_DSS_CHANNEL_LCD),
-                        dispc_pclk_rate(OMAP_DSS_CHANNEL_LCD));
-
         enable_clocks(0);
 }
 
+void dsi_dump_clocks(struct seq_file *s)
+{
+        struct platform_device *dsidev;
+        int i;
+
+        for  (i = 0; i < MAX_NUM_DSI; i++) {
+                dsidev = dsi_get_dsidev_from_id(i);
+                if (dsidev)
+                        dsi_dump_dsidev_clocks(dsidev, s);
+        }
+}
+
 #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS
-void dsi_dump_irqs(struct seq_file *s)
+static void dsi_dump_dsidev_irqs(struct platform_device *dsidev,
+                struct seq_file *s)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned long flags;
         struct dsi_irq_stats stats;
+        int dsi_module = dsi_get_dsidev_id(dsidev);
 
-        spin_lock_irqsave(&dsi.irq_stats_lock, flags);
+        spin_lock_irqsave(&dsi->irq_stats_lock, flags);
 
-        stats = dsi.irq_stats;
-        memset(&dsi.irq_stats, 0, sizeof(dsi.irq_stats));
-        dsi.irq_stats.last_reset = jiffies;
+        stats = dsi->irq_stats;
+        memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats));
+        dsi->irq_stats.last_reset = jiffies;
 
-        spin_unlock_irqrestore(&dsi.irq_stats_lock, flags);
+        spin_unlock_irqrestore(&dsi->irq_stats_lock, flags);
 
         seq_printf(s, "period %u ms\n",
                         jiffies_to_msecs(jiffies - stats.last_reset));
@@ -1570,7 +1770,7 @@ void dsi_dump_irqs(struct seq_file *s)
 #define PIS(x) \
         seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1]);
 
-        seq_printf(s, "-- DSI interrupts --\n");
+        seq_printf(s, "-- DSI%d interrupts --\n", dsi_module + 1);
         PIS(VC0);
         PIS(VC1);
         PIS(VC2);
@@ -1636,13 +1836,45 @@ void dsi_dump_irqs(struct seq_file *s)
         PIS(ULPSACTIVENOT_ALL1);
 #undef PIS
 }
+
+static void dsi1_dump_irqs(struct seq_file *s)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_id(0);
+
+        dsi_dump_dsidev_irqs(dsidev, s);
+}
+
+static void dsi2_dump_irqs(struct seq_file *s)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_id(1);
+
+        dsi_dump_dsidev_irqs(dsidev, s);
+}
+
+void dsi_create_debugfs_files_irq(struct dentry *debugfs_dir,
+                const struct file_operations *debug_fops)
+{
+        struct platform_device *dsidev;
+
+        dsidev = dsi_get_dsidev_from_id(0);
+        if (dsidev)
+                debugfs_create_file("dsi1_irqs", S_IRUGO, debugfs_dir,
+                        &dsi1_dump_irqs, debug_fops);
+
+        dsidev = dsi_get_dsidev_from_id(1);
+        if (dsidev)
+                debugfs_create_file("dsi2_irqs", S_IRUGO, debugfs_dir,
+                        &dsi2_dump_irqs, debug_fops);
+}
 #endif
 
-void dsi_dump_regs(struct seq_file *s)
+static void dsi_dump_dsidev_regs(struct platform_device *dsidev,
+                struct seq_file *s)
 {
-#define DUMPREG(r) seq_printf(s, "%-35s %08x\n", #r, dsi_read_reg(r))
+#define DUMPREG(r) seq_printf(s, "%-35s %08x\n", #r, dsi_read_reg(dsidev, r))
 
         dss_clk_enable(DSS_CLK_ICK | DSS_CLK_FCK);
+        dsi_enable_scp_clk(dsidev);
 
         DUMPREG(DSI_REVISION);
         DUMPREG(DSI_SYSCONFIG);
@@ -1714,25 +1946,57 @@ void dsi_dump_regs(struct seq_file *s)
         DUMPREG(DSI_PLL_CONFIGURATION1);
         DUMPREG(DSI_PLL_CONFIGURATION2);
 
+        dsi_disable_scp_clk(dsidev);
         dss_clk_disable(DSS_CLK_ICK | DSS_CLK_FCK);
 #undef DUMPREG
 }
 
-enum dsi_complexio_power_state {
+static void dsi1_dump_regs(struct seq_file *s)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_id(0);
+
+        dsi_dump_dsidev_regs(dsidev, s);
+}
+
+static void dsi2_dump_regs(struct seq_file *s)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_id(1);
+
+        dsi_dump_dsidev_regs(dsidev, s);
+}
+
+void dsi_create_debugfs_files_reg(struct dentry *debugfs_dir,
+                const struct file_operations *debug_fops)
+{
+        struct platform_device *dsidev;
+
+        dsidev = dsi_get_dsidev_from_id(0);
+        if (dsidev)
+                debugfs_create_file("dsi1_regs", S_IRUGO, debugfs_dir,
+                        &dsi1_dump_regs, debug_fops);
+
+        dsidev = dsi_get_dsidev_from_id(1);
+        if (dsidev)
+                debugfs_create_file("dsi2_regs", S_IRUGO, debugfs_dir,
+                        &dsi2_dump_regs, debug_fops);
+}
+enum dsi_cio_power_state {
         DSI_COMPLEXIO_POWER_OFF         = 0x0,
         DSI_COMPLEXIO_POWER_ON          = 0x1,
         DSI_COMPLEXIO_POWER_ULPS        = 0x2,
 };
 
-static int dsi_complexio_power(enum dsi_complexio_power_state state)
+static int dsi_cio_power(struct platform_device *dsidev,
+                enum dsi_cio_power_state state)
 {
         int t = 0;
 
         /* PWR_CMD */
-        REG_FLD_MOD(DSI_COMPLEXIO_CFG1, state, 28, 27);
+        REG_FLD_MOD(dsidev, DSI_COMPLEXIO_CFG1, state, 28, 27);
 
         /* PWR_STATUS */
-        while (FLD_GET(dsi_read_reg(DSI_COMPLEXIO_CFG1), 26, 25) != state) {
+        while (FLD_GET(dsi_read_reg(dsidev, DSI_COMPLEXIO_CFG1),
+                        26, 25) != state) {
                 if (++t > 1000) {
                         DSSERR("failed to set complexio power state to "
                                         "%d\n", state);
@@ -1744,9 +2008,70 @@ static int dsi_complexio_power(enum dsi_complexio_power_state state)
         return 0;
 }
 
-static void dsi_complexio_config(struct omap_dss_device *dssdev)
+/* Number of data lanes present on DSI interface */
+static inline int dsi_get_num_data_lanes(struct platform_device *dsidev)
 {
+        /* DSI on OMAP3 doesn't have register DSI_GNQ, set number
+         * of data lanes as 2 by default */
+        if (dss_has_feature(FEAT_DSI_GNQ))
+                return REG_GET(dsidev, DSI_GNQ, 11, 9); /* NB_DATA_LANES */
+        else
+                return 2;
+}
+
+/* Number of data lanes used by the dss device */
+static inline int dsi_get_num_data_lanes_dssdev(struct omap_dss_device *dssdev)
+{
+        int num_data_lanes = 0;
+
+        if (dssdev->phy.dsi.data1_lane != 0)
+                num_data_lanes++;
+        if (dssdev->phy.dsi.data2_lane != 0)
+                num_data_lanes++;
+        if (dssdev->phy.dsi.data3_lane != 0)
+                num_data_lanes++;
+        if (dssdev->phy.dsi.data4_lane != 0)
+                num_data_lanes++;
+
+        return num_data_lanes;
+}
+
+static unsigned dsi_get_line_buf_size(struct platform_device *dsidev)
+{
+        int val;
+
+        /* line buffer on OMAP3 is 1024 x 24bits */
+        /* XXX: for some reason using full buffer size causes
+         * considerable TX slowdown with update sizes that fill the
+         * whole buffer */
+        if (!dss_has_feature(FEAT_DSI_GNQ))
+                return 1023 * 3;
+
+        val = REG_GET(dsidev, DSI_GNQ, 14, 12); /* VP1_LINE_BUFFER_SIZE */
+
+        switch (val) {
+        case 1:
+                return 512 * 3;         /* 512x24 bits */
+        case 2:
+                return 682 * 3;         /* 682x24 bits */
+        case 3:
+                return 853 * 3;         /* 853x24 bits */
+        case 4:
+                return 1024 * 3;        /* 1024x24 bits */
+        case 5:
+                return 1194 * 3;        /* 1194x24 bits */
+        case 6:
+                return 1365 * 3;        /* 1365x24 bits */
+        default:
+                BUG();
+        }
+}
+
+static void dsi_set_lane_config(struct omap_dss_device *dssdev)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         u32 r;
+        int num_data_lanes_dssdev = dsi_get_num_data_lanes_dssdev(dssdev);
 
         int clk_lane   = dssdev->phy.dsi.clk_lane;
         int data1_lane = dssdev->phy.dsi.data1_lane;
@@ -1755,14 +2080,28 @@ static void dsi_complexio_config(struct omap_dss_device *dssdev)
         int data1_pol  = dssdev->phy.dsi.data1_pol;
         int data2_pol  = dssdev->phy.dsi.data2_pol;
 
-        r = dsi_read_reg(DSI_COMPLEXIO_CFG1);
+        r = dsi_read_reg(dsidev, DSI_COMPLEXIO_CFG1);
         r = FLD_MOD(r, clk_lane, 2, 0);
         r = FLD_MOD(r, clk_pol, 3, 3);
         r = FLD_MOD(r, data1_lane, 6, 4);
         r = FLD_MOD(r, data1_pol, 7, 7);
         r = FLD_MOD(r, data2_lane, 10, 8);
         r = FLD_MOD(r, data2_pol, 11, 11);
-        dsi_write_reg(DSI_COMPLEXIO_CFG1, r);
+        if (num_data_lanes_dssdev > 2) {
+                int data3_lane  = dssdev->phy.dsi.data3_lane;
+                int data3_pol  = dssdev->phy.dsi.data3_pol;
+
+                r = FLD_MOD(r, data3_lane, 14, 12);
+                r = FLD_MOD(r, data3_pol, 15, 15);
+        }
+        if (num_data_lanes_dssdev > 3) {
+                int data4_lane  = dssdev->phy.dsi.data4_lane;
+                int data4_pol  = dssdev->phy.dsi.data4_pol;
+
+                r = FLD_MOD(r, data4_lane, 18, 16);
+                r = FLD_MOD(r, data4_pol, 19, 19);
+        }
+        dsi_write_reg(dsidev, DSI_COMPLEXIO_CFG1, r);
 
         /* The configuration of the DSI complex I/O (number of data lanes,
            position, differential order) should not be changed while
@@ -1776,27 +2115,31 @@ static void dsi_complexio_config(struct omap_dss_device *dssdev)
            DSI complex I/O configuration is unknown. */
 
         /*
-        REG_FLD_MOD(DSI_CTRL, 1, 0, 0);
-        REG_FLD_MOD(DSI_CTRL, 0, 0, 0);
-        REG_FLD_MOD(DSI_CLK_CTRL, 1, 20, 20);
-        REG_FLD_MOD(DSI_CTRL, 1, 0, 0);
+        REG_FLD_MOD(dsidev, DSI_CTRL, 1, 0, 0);
+        REG_FLD_MOD(dsidev, DSI_CTRL, 0, 0, 0);
+        REG_FLD_MOD(dsidev, DSI_CLK_CTRL, 1, 20, 20);
+        REG_FLD_MOD(dsidev, DSI_CTRL, 1, 0, 0);
         */
 }
 
-static inline unsigned ns2ddr(unsigned ns)
+static inline unsigned ns2ddr(struct platform_device *dsidev, unsigned ns)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
         /* convert time in ns to ddr ticks, rounding up */
-        unsigned long ddr_clk = dsi.current_cinfo.clkin4ddr / 4;
+        unsigned long ddr_clk = dsi->current_cinfo.clkin4ddr / 4;
         return (ns * (ddr_clk / 1000 / 1000) + 999) / 1000;
 }
 
-static inline unsigned ddr2ns(unsigned ddr)
+static inline unsigned ddr2ns(struct platform_device *dsidev, unsigned ddr)
 {
-        unsigned long ddr_clk = dsi.current_cinfo.clkin4ddr / 4;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        unsigned long ddr_clk = dsi->current_cinfo.clkin4ddr / 4;
         return ddr * 1000 * 1000 / (ddr_clk / 1000);
 }
 
-static void dsi_complexio_timings(void)
+static void dsi_cio_timings(struct platform_device *dsidev)
 {
         u32 r;
         u32 ths_prepare, ths_prepare_ths_zero, ths_trail, ths_exit;
@@ -1808,139 +2151,323 @@ static void dsi_complexio_timings(void)
         /* 1 * DDR_CLK = 2 * UI */
 
         /* min 40ns + 4*UI      max 85ns + 6*UI */
-        ths_prepare = ns2ddr(70) + 2;
+        ths_prepare = ns2ddr(dsidev, 70) + 2;
 
         /* min 145ns + 10*UI */
-        ths_prepare_ths_zero = ns2ddr(175) + 2;
+        ths_prepare_ths_zero = ns2ddr(dsidev, 175) + 2;
 
         /* min max(8*UI, 60ns+4*UI) */
-        ths_trail = ns2ddr(60) + 5;
+        ths_trail = ns2ddr(dsidev, 60) + 5;
 
         /* min 100ns */
-        ths_exit = ns2ddr(145);
+        ths_exit = ns2ddr(dsidev, 145);
 
         /* tlpx min 50n */
-        tlpx_half = ns2ddr(25);
+        tlpx_half = ns2ddr(dsidev, 25);
 
         /* min 60ns */
-        tclk_trail = ns2ddr(60) + 2;
+        tclk_trail = ns2ddr(dsidev, 60) + 2;
 
         /* min 38ns, max 95ns */
-        tclk_prepare = ns2ddr(65);
+        tclk_prepare = ns2ddr(dsidev, 65);
 
         /* min tclk-prepare + tclk-zero = 300ns */
-        tclk_zero = ns2ddr(260);
+        tclk_zero = ns2ddr(dsidev, 260);
 
         DSSDBG("ths_prepare %u (%uns), ths_prepare_ths_zero %u (%uns)\n",
-                ths_prepare, ddr2ns(ths_prepare),
-                ths_prepare_ths_zero, ddr2ns(ths_prepare_ths_zero));
+                ths_prepare, ddr2ns(dsidev, ths_prepare),
+                ths_prepare_ths_zero, ddr2ns(dsidev, ths_prepare_ths_zero));
         DSSDBG("ths_trail %u (%uns), ths_exit %u (%uns)\n",
-                        ths_trail, ddr2ns(ths_trail),
-                        ths_exit, ddr2ns(ths_exit));
+                        ths_trail, ddr2ns(dsidev, ths_trail),
+                        ths_exit, ddr2ns(dsidev, ths_exit));
 
         DSSDBG("tlpx_half %u (%uns), tclk_trail %u (%uns), "
                         "tclk_zero %u (%uns)\n",
-                        tlpx_half, ddr2ns(tlpx_half),
-                        tclk_trail, ddr2ns(tclk_trail),
-                        tclk_zero, ddr2ns(tclk_zero));
+                        tlpx_half, ddr2ns(dsidev, tlpx_half),
+                        tclk_trail, ddr2ns(dsidev, tclk_trail),
+                        tclk_zero, ddr2ns(dsidev, tclk_zero));
         DSSDBG("tclk_prepare %u (%uns)\n",
-                        tclk_prepare, ddr2ns(tclk_prepare));
+                        tclk_prepare, ddr2ns(dsidev, tclk_prepare));
 
         /* program timings */
 
-        r = dsi_read_reg(DSI_DSIPHY_CFG0);
+        r = dsi_read_reg(dsidev, DSI_DSIPHY_CFG0);
         r = FLD_MOD(r, ths_prepare, 31, 24);
         r = FLD_MOD(r, ths_prepare_ths_zero, 23, 16);
         r = FLD_MOD(r, ths_trail, 15, 8);
         r = FLD_MOD(r, ths_exit, 7, 0);
-        dsi_write_reg(DSI_DSIPHY_CFG0, r);
+        dsi_write_reg(dsidev, DSI_DSIPHY_CFG0, r);
 
-        r = dsi_read_reg(DSI_DSIPHY_CFG1);
+        r = dsi_read_reg(dsidev, DSI_DSIPHY_CFG1);
         r = FLD_MOD(r, tlpx_half, 22, 16);
         r = FLD_MOD(r, tclk_trail, 15, 8);
         r = FLD_MOD(r, tclk_zero, 7, 0);
-        dsi_write_reg(DSI_DSIPHY_CFG1, r);
+        dsi_write_reg(dsidev, DSI_DSIPHY_CFG1, r);
 
-        r = dsi_read_reg(DSI_DSIPHY_CFG2);
+        r = dsi_read_reg(dsidev, DSI_DSIPHY_CFG2);
         r = FLD_MOD(r, tclk_prepare, 7, 0);
-        dsi_write_reg(DSI_DSIPHY_CFG2, r);
+        dsi_write_reg(dsidev, DSI_DSIPHY_CFG2, r);
 }
 
+static void dsi_cio_enable_lane_override(struct omap_dss_device *dssdev,
+                enum dsi_lane lanes)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        int clk_lane   = dssdev->phy.dsi.clk_lane;
+        int data1_lane = dssdev->phy.dsi.data1_lane;
+        int data2_lane = dssdev->phy.dsi.data2_lane;
+        int data3_lane = dssdev->phy.dsi.data3_lane;
+        int data4_lane = dssdev->phy.dsi.data4_lane;
+        int clk_pol    = dssdev->phy.dsi.clk_pol;
+        int data1_pol  = dssdev->phy.dsi.data1_pol;
+        int data2_pol  = dssdev->phy.dsi.data2_pol;
+        int data3_pol  = dssdev->phy.dsi.data3_pol;
+        int data4_pol  = dssdev->phy.dsi.data4_pol;
+
+        u32 l = 0;
+        u8 lptxscp_start = dsi->num_data_lanes == 2 ? 22 : 26;
+
+        if (lanes & DSI_CLK_P)
+                l |= 1 << ((clk_lane - 1) * 2 + (clk_pol ? 0 : 1));
+        if (lanes & DSI_CLK_N)
+                l |= 1 << ((clk_lane - 1) * 2 + (clk_pol ? 1 : 0));
+
+        if (lanes & DSI_DATA1_P)
+                l |= 1 << ((data1_lane - 1) * 2 + (data1_pol ? 0 : 1));
+        if (lanes & DSI_DATA1_N)
+                l |= 1 << ((data1_lane - 1) * 2 + (data1_pol ? 1 : 0));
+
+        if (lanes & DSI_DATA2_P)
+                l |= 1 << ((data2_lane - 1) * 2 + (data2_pol ? 0 : 1));
+        if (lanes & DSI_DATA2_N)
+                l |= 1 << ((data2_lane - 1) * 2 + (data2_pol ? 1 : 0));
+
+        if (lanes & DSI_DATA3_P)
+                l |= 1 << ((data3_lane - 1) * 2 + (data3_pol ? 0 : 1));
+        if (lanes & DSI_DATA3_N)
+                l |= 1 << ((data3_lane - 1) * 2 + (data3_pol ? 1 : 0));
+
+        if (lanes & DSI_DATA4_P)
+                l |= 1 << ((data4_lane - 1) * 2 + (data4_pol ? 0 : 1));
+        if (lanes & DSI_DATA4_N)
+                l |= 1 << ((data4_lane - 1) * 2 + (data4_pol ? 1 : 0));
+        /*
+         * Bits in REGLPTXSCPDAT4TO0DXDY:
+         * 17: DY0 18: DX0
+         * 19: DY1 20: DX1
+         * 21: DY2 22: DX2
+         * 23: DY3 24: DX3
+         * 25: DY4 26: DX4
+         */
+
+        /* Set the lane override configuration */
+
+        /* REGLPTXSCPDAT4TO0DXDY */
+        REG_FLD_MOD(dsidev, DSI_DSIPHY_CFG10, l, lptxscp_start, 17);
 
-static int dsi_complexio_init(struct omap_dss_device *dssdev)
+        /* Enable lane override */
+
+        /* ENLPTXSCPDAT */
+        REG_FLD_MOD(dsidev, DSI_DSIPHY_CFG10, 1, 27, 27);
+}
+
+static void dsi_cio_disable_lane_override(struct platform_device *dsidev)
 {
-        int r = 0;
+        /* Disable lane override */
+        REG_FLD_MOD(dsidev, DSI_DSIPHY_CFG10, 0, 27, 27); /* ENLPTXSCPDAT */
+        /* Reset the lane override configuration */
+        /* REGLPTXSCPDAT4TO0DXDY */
+        REG_FLD_MOD(dsidev, DSI_DSIPHY_CFG10, 0, 22, 17);
+}
+
+static int dsi_cio_wait_tx_clk_esc_reset(struct omap_dss_device *dssdev)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        int t;
+        int bits[3];
+        bool in_use[3];
+
+        if (dss_has_feature(FEAT_DSI_REVERSE_TXCLKESC)) {
+                bits[0] = 28;
+                bits[1] = 27;
+                bits[2] = 26;
+        } else {
+                bits[0] = 24;
+                bits[1] = 25;
+                bits[2] = 26;
+        }
+
+        in_use[0] = false;
+        in_use[1] = false;
+        in_use[2] = false;
+
+        if (dssdev->phy.dsi.clk_lane != 0)
+                in_use[dssdev->phy.dsi.clk_lane - 1] = true;
+        if (dssdev->phy.dsi.data1_lane != 0)
+                in_use[dssdev->phy.dsi.data1_lane - 1] = true;
+        if (dssdev->phy.dsi.data2_lane != 0)
+                in_use[dssdev->phy.dsi.data2_lane - 1] = true;
+
+        t = 100000;
+        while (true) {
+                u32 l;
+                int i;
+                int ok;
+
+                l = dsi_read_reg(dsidev, DSI_DSIPHY_CFG5);
+
+                ok = 0;
+                for (i = 0; i < 3; ++i) {
+                        if (!in_use[i] || (l & (1 << bits[i])))
+                                ok++;
+                }
+
+                if (ok == 3)
+                        break;
+
+                if (--t == 0) {
+                        for (i = 0; i < 3; ++i) {
+                                if (!in_use[i] || (l & (1 << bits[i])))
+                                        continue;
+
+                                DSSERR("CIO TXCLKESC%d domain not coming " \
+                                                "out of reset\n", i);
+                        }
+                        return -EIO;
+                }
+        }
+
+        return 0;
+}
+
+static int dsi_cio_init(struct omap_dss_device *dssdev)
+{
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        int r;
+        int num_data_lanes_dssdev = dsi_get_num_data_lanes_dssdev(dssdev);
+        u32 l;
 
-        DSSDBG("dsi_complexio_init\n");
+        DSSDBGF();
 
-        /* CIO_CLK_ICG, enable L3 clk to CIO */
-        REG_FLD_MOD(DSI_CLK_CTRL, 1, 14, 14);
+        if (dsi->dsi_mux_pads)
+                dsi->dsi_mux_pads(true);
+
+        dsi_enable_scp_clk(dsidev);
 
         /* A dummy read using the SCP interface to any DSIPHY register is
          * required after DSIPHY reset to complete the reset of the DSI complex
          * I/O. */
-        dsi_read_reg(DSI_DSIPHY_CFG5);
+        dsi_read_reg(dsidev, DSI_DSIPHY_CFG5);
 
-        if (wait_for_bit_change(DSI_DSIPHY_CFG5, 30, 1) != 1) {
-                DSSERR("ComplexIO PHY not coming out of reset.\n");
-                r = -ENODEV;
-                goto err;
+        if (wait_for_bit_change(dsidev, DSI_DSIPHY_CFG5, 30, 1) != 1) {
+                DSSERR("CIO SCP Clock domain not coming out of reset.\n");
+                r = -EIO;
+                goto err_scp_clk_dom;
         }
 
-        dsi_complexio_config(dssdev);
+        dsi_set_lane_config(dssdev);
+
+        /* set TX STOP MODE timer to maximum for this operation */
+        l = dsi_read_reg(dsidev, DSI_TIMING1);
+        l = FLD_MOD(l, 1, 15, 15);      /* FORCE_TX_STOP_MODE_IO */
+        l = FLD_MOD(l, 1, 14, 14);      /* STOP_STATE_X16_IO */
+        l = FLD_MOD(l, 1, 13, 13);      /* STOP_STATE_X4_IO */
+        l = FLD_MOD(l, 0x1fff, 12, 0);  /* STOP_STATE_COUNTER_IO */
+        dsi_write_reg(dsidev, DSI_TIMING1, l);
 
-        r = dsi_complexio_power(DSI_COMPLEXIO_POWER_ON);
+        if (dsi->ulps_enabled) {
+                u32 lane_mask = DSI_CLK_P | DSI_DATA1_P | DSI_DATA2_P;
 
+                DSSDBG("manual ulps exit\n");
+
+                /* ULPS is exited by Mark-1 state for 1ms, followed by
+                 * stop state. DSS HW cannot do this via the normal
+                 * ULPS exit sequence, as after reset the DSS HW thinks
+                 * that we are not in ULPS mode, and refuses to send the
+                 * sequence. So we need to send the ULPS exit sequence
+                 * manually.
+                 */
+
+                if (num_data_lanes_dssdev > 2)
+                        lane_mask |= DSI_DATA3_P;
+
+                if (num_data_lanes_dssdev > 3)
+                        lane_mask |= DSI_DATA4_P;
+
+                dsi_cio_enable_lane_override(dssdev, lane_mask);
+        }
+
+        r = dsi_cio_power(dsidev, DSI_COMPLEXIO_POWER_ON);
         if (r)
-                goto err;
+                goto err_cio_pwr;
 
-        if (wait_for_bit_change(DSI_COMPLEXIO_CFG1, 29, 1) != 1) {
-                DSSERR("ComplexIO not coming out of reset.\n");
+        if (wait_for_bit_change(dsidev, DSI_COMPLEXIO_CFG1, 29, 1) != 1) {
+                DSSERR("CIO PWR clock domain not coming out of reset.\n");
                 r = -ENODEV;
-                goto err;
+                goto err_cio_pwr_dom;
         }
 
-        if (wait_for_bit_change(DSI_COMPLEXIO_CFG1, 21, 1) != 1) {
-                DSSERR("ComplexIO LDO power down.\n");
-                r = -ENODEV;
-                goto err;
+        dsi_if_enable(dsidev, true);
+        dsi_if_enable(dsidev, false);
+        REG_FLD_MOD(dsidev, DSI_CLK_CTRL, 1, 20, 20); /* LP_CLK_ENABLE */
+
+        r = dsi_cio_wait_tx_clk_esc_reset(dssdev);
+        if (r)
+                goto err_tx_clk_esc_rst;
+
+        if (dsi->ulps_enabled) {
+                /* Keep Mark-1 state for 1ms (as per DSI spec) */
+                ktime_t wait = ns_to_ktime(1000 * 1000);
+                set_current_state(TASK_UNINTERRUPTIBLE);
+                schedule_hrtimeout(&wait, HRTIMER_MODE_REL);
+
+                /* Disable the override. The lanes should be set to Mark-11
+                 * state by the HW */
+                dsi_cio_disable_lane_override(dsidev);
         }
 
-        dsi_complexio_timings();
+        /* FORCE_TX_STOP_MODE_IO */
+        REG_FLD_MOD(dsidev, DSI_TIMING1, 0, 15, 15);
 
-        /*
-           The configuration of the DSI complex I/O (number of data lanes,
-           position, differential order) should not be changed while
-           DSS.DSI_CLK_CRTRL[20] LP_CLK_ENABLE bit is set to 1. For the
-           hardware to recognize a new configuration of the complex I/O (done
-           in DSS.DSI_COMPLEXIO_CFG1 register), it is recommended to follow
-           this sequence: First set the DSS.DSI_CTRL[0] IF_EN bit to 1, next
-           reset the DSS.DSI_CTRL[0] IF_EN to 0, then set DSS.DSI_CLK_CTRL[20]
-           LP_CLK_ENABLE to 1, and finally, set again the DSS.DSI_CTRL[0] IF_EN
-           bit to 1. If the sequence is not followed, the DSi complex I/O
-           configuration is undetermined.
-           */
-        dsi_if_enable(1);
-        dsi_if_enable(0);
-        REG_FLD_MOD(DSI_CLK_CTRL, 1, 20, 20); /* LP_CLK_ENABLE */
-        dsi_if_enable(1);
-        dsi_if_enable(0);
+        dsi_cio_timings(dsidev);
+
+        dsi->ulps_enabled = false;
 
         DSSDBG("CIO init done\n");
-err:
+
+        return 0;
+
+err_tx_clk_esc_rst:
+        REG_FLD_MOD(dsidev, DSI_CLK_CTRL, 0, 20, 20); /* LP_CLK_ENABLE */
+err_cio_pwr_dom:
+        dsi_cio_power(dsidev, DSI_COMPLEXIO_POWER_OFF);
+err_cio_pwr:
+        if (dsi->ulps_enabled)
+                dsi_cio_disable_lane_override(dsidev);
+err_scp_clk_dom:
+        dsi_disable_scp_clk(dsidev);
+        if (dsi->dsi_mux_pads)
+                dsi->dsi_mux_pads(false);
         return r;
 }
 
-static void dsi_complexio_uninit(void)
+static void dsi_cio_uninit(struct platform_device *dsidev)
 {
-        dsi_complexio_power(DSI_COMPLEXIO_POWER_OFF);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        dsi_cio_power(dsidev, DSI_COMPLEXIO_POWER_OFF);
+        dsi_disable_scp_clk(dsidev);
+        if (dsi->dsi_mux_pads)
+                dsi->dsi_mux_pads(false);
 }
 
-static int _dsi_wait_reset(void)
+static int _dsi_wait_reset(struct platform_device *dsidev)
 {
         int t = 0;
 
-        while (REG_GET(DSI_SYSSTATUS, 0, 0) == 0) {
+        while (REG_GET(dsidev, DSI_SYSSTATUS, 0, 0) == 0) {
                 if (++t > 5) {
                         DSSERR("soft reset failed\n");
                         return -ENODEV;
@@ -1951,28 +2478,30 @@ static int _dsi_wait_reset(void)
         return 0;
 }
 
-static int _dsi_reset(void)
+static int _dsi_reset(struct platform_device *dsidev)
 {
         /* Soft reset */
-        REG_FLD_MOD(DSI_SYSCONFIG, 1, 1, 1);
-        return _dsi_wait_reset();
+        REG_FLD_MOD(dsidev, DSI_SYSCONFIG, 1, 1, 1);
+        return _dsi_wait_reset(dsidev);
 }
 
-static void dsi_config_tx_fifo(enum fifo_size size1, enum fifo_size size2,
+static void dsi_config_tx_fifo(struct platform_device *dsidev,
+                enum fifo_size size1, enum fifo_size size2,
                 enum fifo_size size3, enum fifo_size size4)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         u32 r = 0;
         int add = 0;
         int i;
 
-        dsi.vc[0].fifo_size = size1;
-        dsi.vc[1].fifo_size = size2;
-        dsi.vc[2].fifo_size = size3;
-        dsi.vc[3].fifo_size = size4;
+        dsi->vc[0].fifo_size = size1;
+        dsi->vc[1].fifo_size = size2;
+        dsi->vc[2].fifo_size = size3;
+        dsi->vc[3].fifo_size = size4;
 
         for (i = 0; i < 4; i++) {
                 u8 v;
-                int size = dsi.vc[i].fifo_size;
+                int size = dsi->vc[i].fifo_size;
 
                 if (add + size > 4) {
                         DSSERR("Illegal FIFO configuration\n");
@@ -1985,24 +2514,26 @@ static void dsi_config_tx_fifo(enum fifo_size size1, enum fifo_size size2,
                 add += size;
         }
 
-        dsi_write_reg(DSI_TX_FIFO_VC_SIZE, r);
+        dsi_write_reg(dsidev, DSI_TX_FIFO_VC_SIZE, r);
 }
 
-static void dsi_config_rx_fifo(enum fifo_size size1, enum fifo_size size2,
+static void dsi_config_rx_fifo(struct platform_device *dsidev,
+                enum fifo_size size1, enum fifo_size size2,
                 enum fifo_size size3, enum fifo_size size4)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         u32 r = 0;
         int add = 0;
         int i;
 
-        dsi.vc[0].fifo_size = size1;
-        dsi.vc[1].fifo_size = size2;
-        dsi.vc[2].fifo_size = size3;
-        dsi.vc[3].fifo_size = size4;
+        dsi->vc[0].fifo_size = size1;
+        dsi->vc[1].fifo_size = size2;
+        dsi->vc[2].fifo_size = size3;
+        dsi->vc[3].fifo_size = size4;
 
         for (i = 0; i < 4; i++) {
                 u8 v;
-                int size = dsi.vc[i].fifo_size;
+                int size = dsi->vc[i].fifo_size;
 
                 if (add + size > 4) {
                         DSSERR("Illegal FIFO configuration\n");
@@ -2015,18 +2546,18 @@ static void dsi_config_rx_fifo(enum fifo_size size1, enum fifo_size size2,
                 add += size;
         }
 
-        dsi_write_reg(DSI_RX_FIFO_VC_SIZE, r);
+        dsi_write_reg(dsidev, DSI_RX_FIFO_VC_SIZE, r);
 }
 
-static int dsi_force_tx_stop_mode_io(void)
+static int dsi_force_tx_stop_mode_io(struct platform_device *dsidev)
 {
         u32 r;
 
-        r = dsi_read_reg(DSI_TIMING1);
+        r = dsi_read_reg(dsidev, DSI_TIMING1);
         r = FLD_MOD(r, 1, 15, 15);      /* FORCE_TX_STOP_MODE_IO */
-        dsi_write_reg(DSI_TIMING1, r);
+        dsi_write_reg(dsidev, DSI_TIMING1, r);
 
-        if (wait_for_bit_change(DSI_TIMING1, 15, 0) != 0) {
+        if (wait_for_bit_change(dsidev, DSI_TIMING1, 15, 0) != 0) {
                 DSSERR("TX_STOP bit not going down\n");
                 return -EIO;
         }
@@ -2034,16 +2565,135 @@ static int dsi_force_tx_stop_mode_io(void)
         return 0;
 }
 
-static int dsi_vc_enable(int channel, bool enable)
+static bool dsi_vc_is_enabled(struct platform_device *dsidev, int channel)
+{
+        return REG_GET(dsidev, DSI_VC_CTRL(channel), 0, 0);
+}
+
+static void dsi_packet_sent_handler_vp(void *data, u32 mask)
+{
+        struct dsi_packet_sent_handler_data *vp_data =
+                (struct dsi_packet_sent_handler_data *) data;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(vp_data->dsidev);
+        const int channel = dsi->update_channel;
+        u8 bit = dsi->te_enabled ? 30 : 31;
+
+        if (REG_GET(vp_data->dsidev, DSI_VC_TE(channel), bit, bit) == 0)
+                complete(vp_data->completion);
+}
+
+static int dsi_sync_vc_vp(struct platform_device *dsidev, int channel)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        DECLARE_COMPLETION_ONSTACK(completion);
+        struct dsi_packet_sent_handler_data vp_data = { dsidev, &completion };
+        int r = 0;
+        u8 bit;
+
+        bit = dsi->te_enabled ? 30 : 31;
+
+        r = dsi_register_isr_vc(dsidev, channel, dsi_packet_sent_handler_vp,
+                &vp_data, DSI_VC_IRQ_PACKET_SENT);
+        if (r)
+                goto err0;
+
+        /* Wait for completion only if TE_EN/TE_START is still set */
+        if (REG_GET(dsidev, DSI_VC_TE(channel), bit, bit)) {
+                if (wait_for_completion_timeout(&completion,
+                                msecs_to_jiffies(10)) == 0) {
+                        DSSERR("Failed to complete previous frame transfer\n");
+                        r = -EIO;
+                        goto err1;
+                }
+        }
+
+        dsi_unregister_isr_vc(dsidev, channel, dsi_packet_sent_handler_vp,
+                &vp_data, DSI_VC_IRQ_PACKET_SENT);
+
+        return 0;
+err1:
+        dsi_unregister_isr_vc(dsidev, channel, dsi_packet_sent_handler_vp,
+                &vp_data, DSI_VC_IRQ_PACKET_SENT);
+err0:
+        return r;
+}
+
+static void dsi_packet_sent_handler_l4(void *data, u32 mask)
+{
+        struct dsi_packet_sent_handler_data *l4_data =
+                (struct dsi_packet_sent_handler_data *) data;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(l4_data->dsidev);
+        const int channel = dsi->update_channel;
+
+        if (REG_GET(l4_data->dsidev, DSI_VC_CTRL(channel), 5, 5) == 0)
+                complete(l4_data->completion);
+}
+
+static int dsi_sync_vc_l4(struct platform_device *dsidev, int channel)
+{
+        DECLARE_COMPLETION_ONSTACK(completion);
+        struct dsi_packet_sent_handler_data l4_data = { dsidev, &completion };
+        int r = 0;
+
+        r = dsi_register_isr_vc(dsidev, channel, dsi_packet_sent_handler_l4,
+                &l4_data, DSI_VC_IRQ_PACKET_SENT);
+        if (r)
+                goto err0;
+
+        /* Wait for completion only if TX_FIFO_NOT_EMPTY is still set */
+        if (REG_GET(dsidev, DSI_VC_CTRL(channel), 5, 5)) {
+                if (wait_for_completion_timeout(&completion,
+                                msecs_to_jiffies(10)) == 0) {
+                        DSSERR("Failed to complete previous l4 transfer\n");
+                        r = -EIO;
+                        goto err1;
+                }
+        }
+
+        dsi_unregister_isr_vc(dsidev, channel, dsi_packet_sent_handler_l4,
+                &l4_data, DSI_VC_IRQ_PACKET_SENT);
+
+        return 0;
+err1:
+        dsi_unregister_isr_vc(dsidev, channel, dsi_packet_sent_handler_l4,
+                &l4_data, DSI_VC_IRQ_PACKET_SENT);
+err0:
+        return r;
+}
+
+static int dsi_sync_vc(struct platform_device *dsidev, int channel)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        WARN_ON(!dsi_bus_is_locked(dsidev));
+
+        WARN_ON(in_interrupt());
+
+        if (!dsi_vc_is_enabled(dsidev, channel))
+                return 0;
+
+        switch (dsi->vc[channel].mode) {
+        case DSI_VC_MODE_VP:
+                return dsi_sync_vc_vp(dsidev, channel);
+        case DSI_VC_MODE_L4:
+                return dsi_sync_vc_l4(dsidev, channel);
+        default:
+                BUG();
+        }
+}
+
+static int dsi_vc_enable(struct platform_device *dsidev, int channel,
+                bool enable)
 {
         DSSDBG("dsi_vc_enable channel %d, enable %d\n",
                         channel, enable);
 
         enable = enable ? 1 : 0;
 
-        REG_FLD_MOD(DSI_VC_CTRL(channel), enable, 0, 0);
+        REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), enable, 0, 0);
 
-        if (wait_for_bit_change(DSI_VC_CTRL(channel), 0, enable) != enable) {
+        if (wait_for_bit_change(dsidev, DSI_VC_CTRL(channel),
+                0, enable) != enable) {
                         DSSERR("Failed to set dsi_vc_enable to %d\n", enable);
                         return -EIO;
         }
@@ -2051,13 +2701,13 @@ static int dsi_vc_enable(int channel, bool enable)
         return 0;
 }
 
-static void dsi_vc_initial_config(int channel)
+static void dsi_vc_initial_config(struct platform_device *dsidev, int channel)
 {
         u32 r;
 
         DSSDBGF("%d", channel);
 
-        r = dsi_read_reg(DSI_VC_CTRL(channel));
+        r = dsi_read_reg(dsidev, DSI_VC_CTRL(channel));
 
         if (FLD_GET(r, 15, 15)) /* VC_BUSY */
                 DSSERR("VC(%d) busy when trying to configure it!\n",
@@ -2070,85 +2720,107 @@ static void dsi_vc_initial_config(int channel)
         r = FLD_MOD(r, 1, 7, 7); /* CS_TX_EN */
         r = FLD_MOD(r, 1, 8, 8); /* ECC_TX_EN */
         r = FLD_MOD(r, 0, 9, 9); /* MODE_SPEED, high speed on/off */
+        if (dss_has_feature(FEAT_DSI_VC_OCP_WIDTH))
+                r = FLD_MOD(r, 3, 11, 10);      /* OCP_WIDTH = 32 bit */
 
         r = FLD_MOD(r, 4, 29, 27); /* DMA_RX_REQ_NB = no dma */
         r = FLD_MOD(r, 4, 23, 21); /* DMA_TX_REQ_NB = no dma */
 
-        dsi_write_reg(DSI_VC_CTRL(channel), r);
+        dsi_write_reg(dsidev, DSI_VC_CTRL(channel), r);
 }
 
-static int dsi_vc_config_l4(int channel)
+static int dsi_vc_config_l4(struct platform_device *dsidev, int channel)
 {
-        if (dsi.vc[channel].mode == DSI_VC_MODE_L4)
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        if (dsi->vc[channel].mode == DSI_VC_MODE_L4)
                 return 0;
 
         DSSDBGF("%d", channel);
 
-        dsi_vc_enable(channel, 0);
+        dsi_sync_vc(dsidev, channel);
+
+        dsi_vc_enable(dsidev, channel, 0);
 
         /* VC_BUSY */
-        if (wait_for_bit_change(DSI_VC_CTRL(channel), 15, 0) != 0) {
+        if (wait_for_bit_change(dsidev, DSI_VC_CTRL(channel), 15, 0) != 0) {
                 DSSERR("vc(%d) busy when trying to config for L4\n", channel);
                 return -EIO;
         }
 
-        REG_FLD_MOD(DSI_VC_CTRL(channel), 0, 1, 1); /* SOURCE, 0 = L4 */
+        REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), 0, 1, 1); /* SOURCE, 0 = L4 */
+
+        /* DCS_CMD_ENABLE */
+        if (dss_has_feature(FEAT_DSI_DCS_CMD_CONFIG_VC))
+                REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), 0, 30, 30);
 
-        dsi_vc_enable(channel, 1);
+        dsi_vc_enable(dsidev, channel, 1);
 
-        dsi.vc[channel].mode = DSI_VC_MODE_L4;
+        dsi->vc[channel].mode = DSI_VC_MODE_L4;
 
         return 0;
 }
 
-static int dsi_vc_config_vp(int channel)
+static int dsi_vc_config_vp(struct platform_device *dsidev, int channel)
 {
-        if (dsi.vc[channel].mode == DSI_VC_MODE_VP)
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        if (dsi->vc[channel].mode == DSI_VC_MODE_VP)
                 return 0;
 
         DSSDBGF("%d", channel);
 
-        dsi_vc_enable(channel, 0);
+        dsi_sync_vc(dsidev, channel);
+
+        dsi_vc_enable(dsidev, channel, 0);
 
         /* VC_BUSY */
-        if (wait_for_bit_change(DSI_VC_CTRL(channel), 15, 0) != 0) {
+        if (wait_for_bit_change(dsidev, DSI_VC_CTRL(channel), 15, 0) != 0) {
                 DSSERR("vc(%d) busy when trying to config for VP\n", channel);
                 return -EIO;
         }
 
-        REG_FLD_MOD(DSI_VC_CTRL(channel), 1, 1, 1); /* SOURCE, 1 = video port */
+        /* SOURCE, 1 = video port */
+        REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), 1, 1, 1);
+
+        /* DCS_CMD_ENABLE */
+        if (dss_has_feature(FEAT_DSI_DCS_CMD_CONFIG_VC))
+                REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), 1, 30, 30);
 
-        dsi_vc_enable(channel, 1);
+        dsi_vc_enable(dsidev, channel, 1);
 
-        dsi.vc[channel].mode = DSI_VC_MODE_VP;
+        dsi->vc[channel].mode = DSI_VC_MODE_VP;
 
         return 0;
 }
 
 
-void omapdss_dsi_vc_enable_hs(int channel, bool enable)
+void omapdss_dsi_vc_enable_hs(struct omap_dss_device *dssdev, int channel,
+                bool enable)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+
         DSSDBG("dsi_vc_enable_hs(%d, %d)\n", channel, enable);
 
-        WARN_ON(!dsi_bus_is_locked());
+        WARN_ON(!dsi_bus_is_locked(dsidev));
 
-        dsi_vc_enable(channel, 0);
-        dsi_if_enable(0);
+        dsi_vc_enable(dsidev, channel, 0);
+        dsi_if_enable(dsidev, 0);
 
-        REG_FLD_MOD(DSI_VC_CTRL(channel), enable, 9, 9);
+        REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), enable, 9, 9);
 
-        dsi_vc_enable(channel, 1);
-        dsi_if_enable(1);
+        dsi_vc_enable(dsidev, channel, 1);
+        dsi_if_enable(dsidev, 1);
 
-        dsi_force_tx_stop_mode_io();
+        dsi_force_tx_stop_mode_io(dsidev);
 }
 EXPORT_SYMBOL(omapdss_dsi_vc_enable_hs);
 
-static void dsi_vc_flush_long_data(int channel)
+static void dsi_vc_flush_long_data(struct platform_device *dsidev, int channel)
 {
-        while (REG_GET(DSI_VC_CTRL(channel), 20, 20)) {
+        while (REG_GET(dsidev, DSI_VC_CTRL(channel), 20, 20)) {
                 u32 val;
-                val = dsi_read_reg(DSI_VC_SHORT_PACKET_HEADER(channel));
+                val = dsi_read_reg(dsidev, DSI_VC_SHORT_PACKET_HEADER(channel));
                 DSSDBG("\t\tb1 %#02x b2 %#02x b3 %#02x b4 %#02x\n",
                                 (val >> 0) & 0xff,
                                 (val >> 8) & 0xff,
@@ -2194,13 +2866,14 @@ static void dsi_show_rx_ack_with_err(u16 err)
                 DSSERR("\t\tDSI Protocol Violation\n");
 }
 
-static u16 dsi_vc_flush_receive_data(int channel)
+static u16 dsi_vc_flush_receive_data(struct platform_device *dsidev,
+                int channel)
 {
         /* RX_FIFO_NOT_EMPTY */
-        while (REG_GET(DSI_VC_CTRL(channel), 20, 20)) {
+        while (REG_GET(dsidev, DSI_VC_CTRL(channel), 20, 20)) {
                 u32 val;
                 u8 dt;
-                val = dsi_read_reg(DSI_VC_SHORT_PACKET_HEADER(channel));
+                val = dsi_read_reg(dsidev, DSI_VC_SHORT_PACKET_HEADER(channel));
                 DSSERR("\trawval %#08x\n", val);
                 dt = FLD_GET(val, 5, 0);
                 if (dt == DSI_DT_RX_ACK_WITH_ERR) {
@@ -2215,7 +2888,7 @@ static u16 dsi_vc_flush_receive_data(int channel)
                 } else if (dt == DSI_DT_RX_DCS_LONG_READ) {
                         DSSERR("\tDCS long response, len %d\n",
                                         FLD_GET(val, 23, 8));
-                        dsi_vc_flush_long_data(channel);
+                        dsi_vc_flush_long_data(dsidev, channel);
                 } else {
                         DSSERR("\tunknown datatype 0x%02x\n", dt);
                 }
@@ -2223,40 +2896,44 @@ static u16 dsi_vc_flush_receive_data(int channel)
         return 0;
 }
 
-static int dsi_vc_send_bta(int channel)
+static int dsi_vc_send_bta(struct platform_device *dsidev, int channel)
 {
-        if (dsi.debug_write || dsi.debug_read)
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        if (dsi->debug_write || dsi->debug_read)
                 DSSDBG("dsi_vc_send_bta %d\n", channel);
 
-        WARN_ON(!dsi_bus_is_locked());
+        WARN_ON(!dsi_bus_is_locked(dsidev));
 
-        if (REG_GET(DSI_VC_CTRL(channel), 20, 20)) {    /* RX_FIFO_NOT_EMPTY */
+        /* RX_FIFO_NOT_EMPTY */
+        if (REG_GET(dsidev, DSI_VC_CTRL(channel), 20, 20)) {
                 DSSERR("rx fifo not empty when sending BTA, dumping data:\n");
-                dsi_vc_flush_receive_data(channel);
+                dsi_vc_flush_receive_data(dsidev, channel);
         }
 
-        REG_FLD_MOD(DSI_VC_CTRL(channel), 1, 6, 6); /* BTA_EN */
+        REG_FLD_MOD(dsidev, DSI_VC_CTRL(channel), 1, 6, 6); /* BTA_EN */
 
         return 0;
 }
 
-int dsi_vc_send_bta_sync(int channel)
+int dsi_vc_send_bta_sync(struct omap_dss_device *dssdev, int channel)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         DECLARE_COMPLETION_ONSTACK(completion);
         int r = 0;
         u32 err;
 
-        r = dsi_register_isr_vc(channel, dsi_completion_handler,
+        r = dsi_register_isr_vc(dsidev, channel, dsi_completion_handler,
                         &completion, DSI_VC_IRQ_BTA);
         if (r)
                 goto err0;
 
-        r = dsi_register_isr(dsi_completion_handler, &completion,
+        r = dsi_register_isr(dsidev, dsi_completion_handler, &completion,
                         DSI_IRQ_ERROR_MASK);
         if (r)
                 goto err1;
 
-        r = dsi_vc_send_bta(channel);
+        r = dsi_vc_send_bta(dsidev, channel);
         if (r)
                 goto err2;
 
@@ -2267,41 +2944,42 @@ int dsi_vc_send_bta_sync(int channel)
                 goto err2;
         }
 
-        err = dsi_get_errors();
+        err = dsi_get_errors(dsidev);
         if (err) {
                 DSSERR("Error while sending BTA: %x\n", err);
                 r = -EIO;
                 goto err2;
         }
 err2:
-        dsi_unregister_isr(dsi_completion_handler, &completion,
+        dsi_unregister_isr(dsidev, dsi_completion_handler, &completion,
                         DSI_IRQ_ERROR_MASK);
 err1:
-        dsi_unregister_isr_vc(channel, dsi_completion_handler,
+        dsi_unregister_isr_vc(dsidev, channel, dsi_completion_handler,
                         &completion, DSI_VC_IRQ_BTA);
 err0:
         return r;
 }
 EXPORT_SYMBOL(dsi_vc_send_bta_sync);
 
-static inline void dsi_vc_write_long_header(int channel, u8 data_type,
-                u16 len, u8 ecc)
+static inline void dsi_vc_write_long_header(struct platform_device *dsidev,
+                int channel, u8 data_type, u16 len, u8 ecc)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         u32 val;
         u8 data_id;
 
-        WARN_ON(!dsi_bus_is_locked());
+        WARN_ON(!dsi_bus_is_locked(dsidev));
 
-        data_id = data_type | dsi.vc[channel].vc_id << 6;
+        data_id = data_type | dsi->vc[channel].vc_id << 6;
 
         val = FLD_VAL(data_id, 7, 0) | FLD_VAL(len, 23, 8) |
                 FLD_VAL(ecc, 31, 24);
 
-        dsi_write_reg(DSI_VC_LONG_PACKET_HEADER(channel), val);
+        dsi_write_reg(dsidev, DSI_VC_LONG_PACKET_HEADER(channel), val);
 }
 
-static inline void dsi_vc_write_long_payload(int channel,
-                u8 b1, u8 b2, u8 b3, u8 b4)
+static inline void dsi_vc_write_long_payload(struct platform_device *dsidev,
+                int channel, u8 b1, u8 b2, u8 b3, u8 b4)
 {
         u32 val;
 
@@ -2310,34 +2988,35 @@ static inline void dsi_vc_write_long_payload(int channel,
 /*      DSSDBG("\twriting %02x, %02x, %02x, %02x (%#010x)\n",
                         b1, b2, b3, b4, val); */
 
-        dsi_write_reg(DSI_VC_LONG_PACKET_PAYLOAD(channel), val);
+        dsi_write_reg(dsidev, DSI_VC_LONG_PACKET_PAYLOAD(channel), val);
 }
 
-static int dsi_vc_send_long(int channel, u8 data_type, u8 *data, u16 len,
-                u8 ecc)
+static int dsi_vc_send_long(struct platform_device *dsidev, int channel,
+                u8 data_type, u8 *data, u16 len, u8 ecc)
 {
         /*u32 val; */
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int i;
         u8 *p;
         int r = 0;
         u8 b1, b2, b3, b4;
 
-        if (dsi.debug_write)
+        if (dsi->debug_write)
                 DSSDBG("dsi_vc_send_long, %d bytes\n", len);
 
         /* len + header */
-        if (dsi.vc[channel].fifo_size * 32 * 4 < len + 4) {
+        if (dsi->vc[channel].fifo_size * 32 * 4 < len + 4) {
                 DSSERR("unable to send long packet: packet too long.\n");
                 return -EINVAL;
         }
 
-        dsi_vc_config_l4(channel);
+        dsi_vc_config_l4(dsidev, channel);
 
-        dsi_vc_write_long_header(channel, data_type, len, ecc);
+        dsi_vc_write_long_header(dsidev, channel, data_type, len, ecc);
 
         p = data;
         for (i = 0; i < len >> 2; i++) {
-                if (dsi.debug_write)
+                if (dsi->debug_write)
                         DSSDBG("\tsending full packet %d\n", i);
 
                 b1 = *p++;
@@ -2345,14 +3024,14 @@ static int dsi_vc_send_long(int channel, u8 data_type, u8 *data, u16 len,
                 b3 = *p++;
                 b4 = *p++;
 
-                dsi_vc_write_long_payload(channel, b1, b2, b3, b4);
+                dsi_vc_write_long_payload(dsidev, channel, b1, b2, b3, b4);
         }
 
         i = len % 4;
         if (i) {
                 b1 = 0; b2 = 0; b3 = 0;
 
-                if (dsi.debug_write)
+                if (dsi->debug_write)
                         DSSDBG("\tsending remainder bytes %d\n", i);
 
                 switch (i) {
@@ -2370,62 +3049,69 @@ static int dsi_vc_send_long(int channel, u8 data_type, u8 *data, u16 len,
                         break;
                 }
 
-                dsi_vc_write_long_payload(channel, b1, b2, b3, 0);
+                dsi_vc_write_long_payload(dsidev, channel, b1, b2, b3, 0);
         }
 
         return r;
 }
 
-static int dsi_vc_send_short(int channel, u8 data_type, u16 data, u8 ecc)
+static int dsi_vc_send_short(struct platform_device *dsidev, int channel,
+                u8 data_type, u16 data, u8 ecc)
 {
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         u32 r;
         u8 data_id;
 
-        WARN_ON(!dsi_bus_is_locked());
+        WARN_ON(!dsi_bus_is_locked(dsidev));
 
-        if (dsi.debug_write)
+        if (dsi->debug_write)
                 DSSDBG("dsi_vc_send_short(ch%d, dt %#x, b1 %#x, b2 %#x)\n",
                                 channel,
                                 data_type, data & 0xff, (data >> 8) & 0xff);
 
-        dsi_vc_config_l4(channel);
+        dsi_vc_config_l4(dsidev, channel);
 
-        if (FLD_GET(dsi_read_reg(DSI_VC_CTRL(channel)), 16, 16)) {
+        if (FLD_GET(dsi_read_reg(dsidev, DSI_VC_CTRL(channel)), 16, 16)) {
                 DSSERR("ERROR FIFO FULL, aborting transfer\n");
                 return -EINVAL;
         }
 
-        data_id = data_type | dsi.vc[channel].vc_id << 6;
+        data_id = data_type | dsi->vc[channel].vc_id << 6;
 
         r = (data_id << 0) | (data << 8) | (ecc << 24);
 
-        dsi_write_reg(DSI_VC_SHORT_PACKET_HEADER(channel), r);
+        dsi_write_reg(dsidev, DSI_VC_SHORT_PACKET_HEADER(channel), r);
 
         return 0;
 }
 
-int dsi_vc_send_null(int channel)
+int dsi_vc_send_null(struct omap_dss_device *dssdev, int channel)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         u8 nullpkg[] = {0, 0, 0, 0};
-        return dsi_vc_send_long(channel, DSI_DT_NULL_PACKET, nullpkg, 4, 0);
+
+        return dsi_vc_send_long(dsidev, channel, DSI_DT_NULL_PACKET, nullpkg,
+                4, 0);
 }
 EXPORT_SYMBOL(dsi_vc_send_null);
 
-int dsi_vc_dcs_write_nosync(int channel, u8 *data, int len)
+int dsi_vc_dcs_write_nosync(struct omap_dss_device *dssdev, int channel,
+                u8 *data, int len)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         int r;
 
         BUG_ON(len == 0);
 
         if (len == 1) {
-                r = dsi_vc_send_short(channel, DSI_DT_DCS_SHORT_WRITE_0,
+                r = dsi_vc_send_short(dsidev, channel, DSI_DT_DCS_SHORT_WRITE_0,
                                 data[0], 0);
         } else if (len == 2) {
-                r = dsi_vc_send_short(channel, DSI_DT_DCS_SHORT_WRITE_1,
+                r = dsi_vc_send_short(dsidev, channel, DSI_DT_DCS_SHORT_WRITE_1,
                                 data[0] | (data[1] << 8), 0);
         } else {
                 /* 0x39 = DCS Long Write */
-                r = dsi_vc_send_long(channel, DSI_DT_DCS_LONG_WRITE,
+                r = dsi_vc_send_long(dsidev, channel, DSI_DT_DCS_LONG_WRITE,
                                 data, len, 0);
         }
 
@@ -2433,21 +3119,24 @@ int dsi_vc_dcs_write_nosync(int channel, u8 *data, int len)
 }
 EXPORT_SYMBOL(dsi_vc_dcs_write_nosync);
 
-int dsi_vc_dcs_write(int channel, u8 *data, int len)
+int dsi_vc_dcs_write(struct omap_dss_device *dssdev, int channel, u8 *data,
+                int len)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         int r;
 
-        r = dsi_vc_dcs_write_nosync(channel, data, len);
+        r = dsi_vc_dcs_write_nosync(dssdev, channel, data, len);
         if (r)
                 goto err;
 
-        r = dsi_vc_send_bta_sync(channel);
+        r = dsi_vc_send_bta_sync(dssdev, channel);
         if (r)
                 goto err;
 
-        if (REG_GET(DSI_VC_CTRL(channel), 20, 20)) {    /* RX_FIFO_NOT_EMPTY */
+        /* RX_FIFO_NOT_EMPTY */
+        if (REG_GET(dsidev, DSI_VC_CTRL(channel), 20, 20)) {
                 DSSERR("rx fifo not empty after write, dumping data:\n");
-                dsi_vc_flush_receive_data(channel);
+                dsi_vc_flush_receive_data(dsidev, channel);
                 r = -EIO;
                 goto err;
         }
@@ -2460,47 +3149,51 @@ err:
 }
 EXPORT_SYMBOL(dsi_vc_dcs_write);
 
-int dsi_vc_dcs_write_0(int channel, u8 dcs_cmd)
+int dsi_vc_dcs_write_0(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd)
 {
-        return dsi_vc_dcs_write(channel, &dcs_cmd, 1);
+        return dsi_vc_dcs_write(dssdev, channel, &dcs_cmd, 1);
 }
 EXPORT_SYMBOL(dsi_vc_dcs_write_0);
 
-int dsi_vc_dcs_write_1(int channel, u8 dcs_cmd, u8 param)
+int dsi_vc_dcs_write_1(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 param)
 {
         u8 buf[2];
         buf[0] = dcs_cmd;
         buf[1] = param;
-        return dsi_vc_dcs_write(channel, buf, 2);
+        return dsi_vc_dcs_write(dssdev, channel, buf, 2);
 }
 EXPORT_SYMBOL(dsi_vc_dcs_write_1);
 
-int dsi_vc_dcs_read(int channel, u8 dcs_cmd, u8 *buf, int buflen)
+int dsi_vc_dcs_read(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 *buf, int buflen)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         u32 val;
         u8 dt;
         int r;
 
-        if (dsi.debug_read)
+        if (dsi->debug_read)
                 DSSDBG("dsi_vc_dcs_read(ch%d, dcs_cmd %x)\n", channel, dcs_cmd);
 
-        r = dsi_vc_send_short(channel, DSI_DT_DCS_READ, dcs_cmd, 0);
+        r = dsi_vc_send_short(dsidev, channel, DSI_DT_DCS_READ, dcs_cmd, 0);
         if (r)
                 goto err;
 
-        r = dsi_vc_send_bta_sync(channel);
+        r = dsi_vc_send_bta_sync(dssdev, channel);
         if (r)
                 goto err;
 
         /* RX_FIFO_NOT_EMPTY */
-        if (REG_GET(DSI_VC_CTRL(channel), 20, 20) == 0) {
+        if (REG_GET(dsidev, DSI_VC_CTRL(channel), 20, 20) == 0) {
                 DSSERR("RX fifo empty when trying to read.\n");
                 r = -EIO;
                 goto err;
         }
 
-        val = dsi_read_reg(DSI_VC_SHORT_PACKET_HEADER(channel));
-        if (dsi.debug_read)
+        val = dsi_read_reg(dsidev, DSI_VC_SHORT_PACKET_HEADER(channel));
+        if (dsi->debug_read)
                 DSSDBG("\theader: %08x\n", val);
         dt = FLD_GET(val, 5, 0);
         if (dt == DSI_DT_RX_ACK_WITH_ERR) {
@@ -2511,7 +3204,7 @@ int dsi_vc_dcs_read(int channel, u8 dcs_cmd, u8 *buf, int buflen)
 
         } else if (dt == DSI_DT_RX_SHORT_READ_1) {
                 u8 data = FLD_GET(val, 15, 8);
-                if (dsi.debug_read)
+                if (dsi->debug_read)
                         DSSDBG("\tDCS short response, 1 byte: %02x\n", data);
 
                 if (buflen < 1) {
@@ -2524,7 +3217,7 @@ int dsi_vc_dcs_read(int channel, u8 dcs_cmd, u8 *buf, int buflen)
                 return 1;
         } else if (dt == DSI_DT_RX_SHORT_READ_2) {
                 u16 data = FLD_GET(val, 23, 8);
-                if (dsi.debug_read)
+                if (dsi->debug_read)
                         DSSDBG("\tDCS short response, 2 byte: %04x\n", data);
 
                 if (buflen < 2) {
@@ -2539,7 +3232,7 @@ int dsi_vc_dcs_read(int channel, u8 dcs_cmd, u8 *buf, int buflen)
         } else if (dt == DSI_DT_RX_DCS_LONG_READ) {
                 int w;
                 int len = FLD_GET(val, 23, 8);
-                if (dsi.debug_read)
+                if (dsi->debug_read)
                         DSSDBG("\tDCS long response, len %d\n", len);
 
                 if (len > buflen) {
@@ -2550,8 +3243,9 @@ int dsi_vc_dcs_read(int channel, u8 dcs_cmd, u8 *buf, int buflen)
                 /* two byte checksum ends the packet, not included in len */
                 for (w = 0; w < len + 2;) {
                         int b;
-                        val = dsi_read_reg(DSI_VC_SHORT_PACKET_HEADER(channel));
-                        if (dsi.debug_read)
+                        val = dsi_read_reg(dsidev,
+                                DSI_VC_SHORT_PACKET_HEADER(channel));
+                        if (dsi->debug_read)
                                 DSSDBG("\t\t%02x %02x %02x %02x\n",
                                                 (val >> 0) & 0xff,
                                                 (val >> 8) & 0xff,
@@ -2582,11 +3276,12 @@ err:
 }
 EXPORT_SYMBOL(dsi_vc_dcs_read);
 
-int dsi_vc_dcs_read_1(int channel, u8 dcs_cmd, u8 *data)
+int dsi_vc_dcs_read_1(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 *data)
 {
         int r;
 
-        r = dsi_vc_dcs_read(channel, dcs_cmd, data, 1);
+        r = dsi_vc_dcs_read(dssdev, channel, dcs_cmd, data, 1);
 
         if (r < 0)
                 return r;
@@ -2598,12 +3293,13 @@ int dsi_vc_dcs_read_1(int channel, u8 dcs_cmd, u8 *data)
 }
 EXPORT_SYMBOL(dsi_vc_dcs_read_1);
 
-int dsi_vc_dcs_read_2(int channel, u8 dcs_cmd, u8 *data1, u8 *data2)
+int dsi_vc_dcs_read_2(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 *data1, u8 *data2)
 {
         u8 buf[2];
         int r;
 
-        r = dsi_vc_dcs_read(channel, dcs_cmd, buf, 2);
+        r = dsi_vc_dcs_read(dssdev, channel, dcs_cmd, buf, 2);
 
         if (r < 0)
                 return r;
@@ -2618,14 +3314,94 @@ int dsi_vc_dcs_read_2(int channel, u8 dcs_cmd, u8 *data1, u8 *data2)
 }
 EXPORT_SYMBOL(dsi_vc_dcs_read_2);
 
-int dsi_vc_set_max_rx_packet_size(int channel, u16 len)
+int dsi_vc_set_max_rx_packet_size(struct omap_dss_device *dssdev, int channel,
+                u16 len)
 {
-        return dsi_vc_send_short(channel, DSI_DT_SET_MAX_RET_PKG_SIZE,
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+
+        return dsi_vc_send_short(dsidev, channel, DSI_DT_SET_MAX_RET_PKG_SIZE,
                         len, 0);
 }
 EXPORT_SYMBOL(dsi_vc_set_max_rx_packet_size);
 
-static void dsi_set_lp_rx_timeout(unsigned ticks, bool x4, bool x16)
+static int dsi_enter_ulps(struct platform_device *dsidev)
+{
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        DECLARE_COMPLETION_ONSTACK(completion);
+        int r;
+
+        DSSDBGF();
+
+        WARN_ON(!dsi_bus_is_locked(dsidev));
+
+        WARN_ON(dsi->ulps_enabled);
+
+        if (dsi->ulps_enabled)
+                return 0;
+
+        if (REG_GET(dsidev, DSI_CLK_CTRL, 13, 13)) {
+                DSSERR("DDR_CLK_ALWAYS_ON enabled when entering ULPS\n");
+                return -EIO;
+        }
+
+        dsi_sync_vc(dsidev, 0);
+        dsi_sync_vc(dsidev, 1);
+        dsi_sync_vc(dsidev, 2);
+        dsi_sync_vc(dsidev, 3);
+
+        dsi_force_tx_stop_mode_io(dsidev);
+
+        dsi_vc_enable(dsidev, 0, false);
+        dsi_vc_enable(dsidev, 1, false);
+        dsi_vc_enable(dsidev, 2, false);
+        dsi_vc_enable(dsidev, 3, false);
+
+        if (REG_GET(dsidev, DSI_COMPLEXIO_CFG2, 16, 16)) {      /* HS_BUSY */
+                DSSERR("HS busy when enabling ULPS\n");
+                return -EIO;
+        }
+
+        if (REG_GET(dsidev, DSI_COMPLEXIO_CFG2, 17, 17)) {      /* LP_BUSY */
+                DSSERR("LP busy when enabling ULPS\n");
+                return -EIO;
+        }
+
+        r = dsi_register_isr_cio(dsidev, dsi_completion_handler, &completion,
+                        DSI_CIO_IRQ_ULPSACTIVENOT_ALL0);
+        if (r)
+                return r;
+
+        /* Assert TxRequestEsc for data lanes and TxUlpsClk for clk lane */
+        /* LANEx_ULPS_SIG2 */
+        REG_FLD_MOD(dsidev, DSI_COMPLEXIO_CFG2, (1 << 0) | (1 << 1) | (1 << 2),
+                7, 5);
+
+        if (wait_for_completion_timeout(&completion,
+                                msecs_to_jiffies(1000)) == 0) {
+                DSSERR("ULPS enable timeout\n");
+                r = -EIO;
+                goto err;
+        }
+
+        dsi_unregister_isr_cio(dsidev, dsi_completion_handler, &completion,
+                        DSI_CIO_IRQ_ULPSACTIVENOT_ALL0);
+
+        dsi_cio_power(dsidev, DSI_COMPLEXIO_POWER_ULPS);
+
+        dsi_if_enable(dsidev, false);
+
+        dsi->ulps_enabled = true;
+
+        return 0;
+
+err:
+        dsi_unregister_isr_cio(dsidev, dsi_completion_handler, &completion,
+                        DSI_CIO_IRQ_ULPSACTIVENOT_ALL0);
+        return r;
+}
+
+static void dsi_set_lp_rx_timeout(struct platform_device *dsidev,
+                unsigned ticks, bool x4, bool x16)
 {
         unsigned long fck;
         unsigned long total_ticks;
@@ -2634,14 +3410,14 @@ static void dsi_set_lp_rx_timeout(unsigned ticks, bool x4, bool x16)
         BUG_ON(ticks > 0x1fff);
 
         /* ticks in DSI_FCK */
-        fck = dsi_fclk_rate();
+        fck = dsi_fclk_rate(dsidev);
 
-        r = dsi_read_reg(DSI_TIMING2);
+        r = dsi_read_reg(dsidev, DSI_TIMING2);
         r = FLD_MOD(r, 1, 15, 15);      /* LP_RX_TO */
         r = FLD_MOD(r, x16 ? 1 : 0, 14, 14);    /* LP_RX_TO_X16 */
         r = FLD_MOD(r, x4 ? 1 : 0, 13, 13);     /* LP_RX_TO_X4 */
         r = FLD_MOD(r, ticks, 12, 0);   /* LP_RX_COUNTER */
-        dsi_write_reg(DSI_TIMING2, r);
+        dsi_write_reg(dsidev, DSI_TIMING2, r);
 
         total_ticks = ticks * (x16 ? 16 : 1) * (x4 ? 4 : 1);
 
@@ -2651,7 +3427,8 @@ static void dsi_set_lp_rx_timeout(unsigned ticks, bool x4, bool x16)
                         (total_ticks * 1000) / (fck / 1000 / 1000));
 }
 
-static void dsi_set_ta_timeout(unsigned ticks, bool x8, bool x16)
+static void dsi_set_ta_timeout(struct platform_device *dsidev, unsigned ticks,
+                bool x8, bool x16)
 {
         unsigned long fck;
         unsigned long total_ticks;
@@ -2660,14 +3437,14 @@ static void dsi_set_ta_timeout(unsigned ticks, bool x8, bool x16)
         BUG_ON(ticks > 0x1fff);
 
         /* ticks in DSI_FCK */
-        fck = dsi_fclk_rate();
+        fck = dsi_fclk_rate(dsidev);
 
-        r = dsi_read_reg(DSI_TIMING1);
+        r = dsi_read_reg(dsidev, DSI_TIMING1);
         r = FLD_MOD(r, 1, 31, 31);      /* TA_TO */
         r = FLD_MOD(r, x16 ? 1 : 0, 30, 30);    /* TA_TO_X16 */
         r = FLD_MOD(r, x8 ? 1 : 0, 29, 29);     /* TA_TO_X8 */
         r = FLD_MOD(r, ticks, 28, 16);  /* TA_TO_COUNTER */
-        dsi_write_reg(DSI_TIMING1, r);
+        dsi_write_reg(dsidev, DSI_TIMING1, r);
 
         total_ticks = ticks * (x16 ? 16 : 1) * (x8 ? 8 : 1);
 
@@ -2677,7 +3454,8 @@ static void dsi_set_ta_timeout(unsigned ticks, bool x8, bool x16)
                         (total_ticks * 1000) / (fck / 1000 / 1000));
 }
 
-static void dsi_set_stop_state_counter(unsigned ticks, bool x4, bool x16)
+static void dsi_set_stop_state_counter(struct platform_device *dsidev,
+                unsigned ticks, bool x4, bool x16)
 {
         unsigned long fck;
         unsigned long total_ticks;
@@ -2686,14 +3464,14 @@ static void dsi_set_stop_state_counter(unsigned ticks, bool x4, bool x16)
         BUG_ON(ticks > 0x1fff);
 
         /* ticks in DSI_FCK */
-        fck = dsi_fclk_rate();
+        fck = dsi_fclk_rate(dsidev);
 
-        r = dsi_read_reg(DSI_TIMING1);
+        r = dsi_read_reg(dsidev, DSI_TIMING1);
         r = FLD_MOD(r, 1, 15, 15);      /* FORCE_TX_STOP_MODE_IO */
         r = FLD_MOD(r, x16 ? 1 : 0, 14, 14);    /* STOP_STATE_X16_IO */
         r = FLD_MOD(r, x4 ? 1 : 0, 13, 13);     /* STOP_STATE_X4_IO */
         r = FLD_MOD(r, ticks, 12, 0);   /* STOP_STATE_COUNTER_IO */
-        dsi_write_reg(DSI_TIMING1, r);
+        dsi_write_reg(dsidev, DSI_TIMING1, r);
 
         total_ticks = ticks * (x16 ? 16 : 1) * (x4 ? 4 : 1);
 
@@ -2703,7 +3481,8 @@ static void dsi_set_stop_state_counter(unsigned ticks, bool x4, bool x16)
                         (total_ticks * 1000) / (fck / 1000 / 1000));
 }
 
-static void dsi_set_hs_tx_timeout(unsigned ticks, bool x4, bool x16)
+static void dsi_set_hs_tx_timeout(struct platform_device *dsidev,
+                unsigned ticks, bool x4, bool x16)
 {
         unsigned long fck;
         unsigned long total_ticks;
@@ -2712,14 +3491,14 @@ static void dsi_set_hs_tx_timeout(unsigned ticks, bool x4, bool x16)
         BUG_ON(ticks > 0x1fff);
 
         /* ticks in TxByteClkHS */
-        fck = dsi_get_txbyteclkhs();
+        fck = dsi_get_txbyteclkhs(dsidev);
 
-        r = dsi_read_reg(DSI_TIMING2);
+        r = dsi_read_reg(dsidev, DSI_TIMING2);
         r = FLD_MOD(r, 1, 31, 31);      /* HS_TX_TO */
         r = FLD_MOD(r, x16 ? 1 : 0, 30, 30);    /* HS_TX_TO_X16 */
         r = FLD_MOD(r, x4 ? 1 : 0, 29, 29);     /* HS_TX_TO_X8 (4 really) */
         r = FLD_MOD(r, ticks, 28, 16);  /* HS_TX_TO_COUNTER */
-        dsi_write_reg(DSI_TIMING2, r);
+        dsi_write_reg(dsidev, DSI_TIMING2, r);
 
         total_ticks = ticks * (x16 ? 16 : 1) * (x4 ? 4 : 1);
 
@@ -2730,24 +3509,25 @@ static void dsi_set_hs_tx_timeout(unsigned ticks, bool x4, bool x16)
 }
 static int dsi_proto_config(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         u32 r;
         int buswidth = 0;
 
-        dsi_config_tx_fifo(DSI_FIFO_SIZE_32,
+        dsi_config_tx_fifo(dsidev, DSI_FIFO_SIZE_32,
                         DSI_FIFO_SIZE_32,
                         DSI_FIFO_SIZE_32,
                         DSI_FIFO_SIZE_32);
 
-        dsi_config_rx_fifo(DSI_FIFO_SIZE_32,
+        dsi_config_rx_fifo(dsidev, DSI_FIFO_SIZE_32,
                         DSI_FIFO_SIZE_32,
                         DSI_FIFO_SIZE_32,
                         DSI_FIFO_SIZE_32);
 
         /* XXX what values for the timeouts? */
-        dsi_set_stop_state_counter(0x1000, false, false);
-        dsi_set_ta_timeout(0x1fff, true, true);
-        dsi_set_lp_rx_timeout(0x1fff, true, true);
-        dsi_set_hs_tx_timeout(0x1fff, true, true);
+        dsi_set_stop_state_counter(dsidev, 0x1000, false, false);
+        dsi_set_ta_timeout(dsidev, 0x1fff, true, true);
+        dsi_set_lp_rx_timeout(dsidev, 0x1fff, true, true);
+        dsi_set_hs_tx_timeout(dsidev, 0x1fff, true, true);
 
         switch (dssdev->ctrl.pixel_size) {
         case 16:
@@ -2763,7 +3543,7 @@ static int dsi_proto_config(struct omap_dss_device *dssdev)
                 BUG();
         }
 
-        r = dsi_read_reg(DSI_CTRL);
+        r = dsi_read_reg(dsidev, DSI_CTRL);
         r = FLD_MOD(r, 1, 1, 1);        /* CS_RX_EN */
         r = FLD_MOD(r, 1, 2, 2);        /* ECC_RX_EN */
         r = FLD_MOD(r, 1, 3, 3);        /* TX_FIFO_ARBITRATION */
@@ -2773,21 +3553,25 @@ static int dsi_proto_config(struct omap_dss_device *dssdev)
         r = FLD_MOD(r, 2, 13, 12);      /* LINE_BUFFER, 2 lines */
         r = FLD_MOD(r, 1, 14, 14);      /* TRIGGER_RESET_MODE */
         r = FLD_MOD(r, 1, 19, 19);      /* EOT_ENABLE */
-        r = FLD_MOD(r, 1, 24, 24);      /* DCS_CMD_ENABLE */
-        r = FLD_MOD(r, 0, 25, 25);      /* DCS_CMD_CODE, 1=start, 0=continue */
+        if (!dss_has_feature(FEAT_DSI_DCS_CMD_CONFIG_VC)) {
+                r = FLD_MOD(r, 1, 24, 24);      /* DCS_CMD_ENABLE */
+                /* DCS_CMD_CODE, 1=start, 0=continue */
+                r = FLD_MOD(r, 0, 25, 25);
+        }
 
-        dsi_write_reg(DSI_CTRL, r);
+        dsi_write_reg(dsidev, DSI_CTRL, r);
 
-        dsi_vc_initial_config(0);
-        dsi_vc_initial_config(1);
-        dsi_vc_initial_config(2);
-        dsi_vc_initial_config(3);
+        dsi_vc_initial_config(dsidev, 0);
+        dsi_vc_initial_config(dsidev, 1);
+        dsi_vc_initial_config(dsidev, 2);
+        dsi_vc_initial_config(dsidev, 3);
 
         return 0;
 }
 
 static void dsi_proto_timings(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         unsigned tlpx, tclk_zero, tclk_prepare, tclk_trail;
         unsigned tclk_pre, tclk_post;
         unsigned ths_prepare, ths_prepare_ths_zero, ths_zero;
@@ -2797,32 +3581,27 @@ static void dsi_proto_timings(struct omap_dss_device *dssdev)
         unsigned ths_eot;
         u32 r;
 
-        r = dsi_read_reg(DSI_DSIPHY_CFG0);
+        r = dsi_read_reg(dsidev, DSI_DSIPHY_CFG0);
         ths_prepare = FLD_GET(r, 31, 24);
         ths_prepare_ths_zero = FLD_GET(r, 23, 16);
         ths_zero = ths_prepare_ths_zero - ths_prepare;
         ths_trail = FLD_GET(r, 15, 8);
         ths_exit = FLD_GET(r, 7, 0);
 
-        r = dsi_read_reg(DSI_DSIPHY_CFG1);
+        r = dsi_read_reg(dsidev, DSI_DSIPHY_CFG1);
         tlpx = FLD_GET(r, 22, 16) * 2;
         tclk_trail = FLD_GET(r, 15, 8);
         tclk_zero = FLD_GET(r, 7, 0);
 
-        r = dsi_read_reg(DSI_DSIPHY_CFG2);
+        r = dsi_read_reg(dsidev, DSI_DSIPHY_CFG2);
         tclk_prepare = FLD_GET(r, 7, 0);
 
         /* min 8*UI */
         tclk_pre = 20;
         /* min 60ns + 52*UI */
-        tclk_post = ns2ddr(60) + 26;
+        tclk_post = ns2ddr(dsidev, 60) + 26;
 
-        /* ths_eot is 2 for 2 datalanes and 4 for 1 datalane */
-        if (dssdev->phy.dsi.data1_lane != 0 &&
-                        dssdev->phy.dsi.data2_lane != 0)
-                ths_eot = 2;
-        else
-                ths_eot = 4;
+        ths_eot = DIV_ROUND_UP(4, dsi_get_num_data_lanes_dssdev(dssdev));
 
         ddr_clk_pre = DIV_ROUND_UP(tclk_pre + tlpx + tclk_zero + tclk_prepare,
                         4);
@@ -2831,10 +3610,10 @@ static void dsi_proto_timings(struct omap_dss_device *dssdev)
         BUG_ON(ddr_clk_pre == 0 || ddr_clk_pre > 255);
         BUG_ON(ddr_clk_post == 0 || ddr_clk_post > 255);
 
-        r = dsi_read_reg(DSI_CLK_TIMING);
+        r = dsi_read_reg(dsidev, DSI_CLK_TIMING);
         r = FLD_MOD(r, ddr_clk_pre, 15, 8);
         r = FLD_MOD(r, ddr_clk_post, 7, 0);
-        dsi_write_reg(DSI_CLK_TIMING, r);
+        dsi_write_reg(dsidev, DSI_CLK_TIMING, r);
 
         DSSDBG("ddr_clk_pre %u, ddr_clk_post %u\n",
                         ddr_clk_pre,
@@ -2848,7 +3627,7 @@ static void dsi_proto_timings(struct omap_dss_device *dssdev)
 
         r = FLD_VAL(enter_hs_mode_lat, 31, 16) |
                 FLD_VAL(exit_hs_mode_lat, 15, 0);
-        dsi_write_reg(DSI_VM_TIMING7, r);
+        dsi_write_reg(dsidev, DSI_VM_TIMING7, r);
 
         DSSDBG("enter_hs_mode_lat %u, exit_hs_mode_lat %u\n",
                         enter_hs_mode_lat, exit_hs_mode_lat);
@@ -2858,25 +3637,27 @@ static void dsi_proto_timings(struct omap_dss_device *dssdev)
 #define DSI_DECL_VARS \
         int __dsi_cb = 0; u32 __dsi_cv = 0;
 
-#define DSI_FLUSH(ch) \
+#define DSI_FLUSH(dsidev, ch) \
         if (__dsi_cb > 0) { \
                 /*DSSDBG("sending long packet %#010x\n", __dsi_cv);*/ \
-                dsi_write_reg(DSI_VC_LONG_PACKET_PAYLOAD(ch), __dsi_cv); \
+                dsi_write_reg(dsidev, DSI_VC_LONG_PACKET_PAYLOAD(ch), __dsi_cv); \
                 __dsi_cb = __dsi_cv = 0; \
         }
 
-#define DSI_PUSH(ch, data) \
+#define DSI_PUSH(dsidev, ch, data) \
         do { \
                 __dsi_cv |= (data) << (__dsi_cb * 8); \
                 /*DSSDBG("cv = %#010x, cb = %d\n", __dsi_cv, __dsi_cb);*/ \
                 if (++__dsi_cb > 3) \
-                        DSI_FLUSH(ch); \
+                        DSI_FLUSH(dsidev, ch); \
         } while (0)
 
 static int dsi_update_screen_l4(struct omap_dss_device *dssdev,
                         int x, int y, int w, int h)
 {
         /* Note: supports only 24bit colors in 32bit container */
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int first = 1;
         int fifo_stalls = 0;
         int max_dsi_packet_size;
@@ -2915,7 +3696,7 @@ static int dsi_update_screen_l4(struct omap_dss_device *dssdev,
          * in fifo */
 
         /* When using CPU, max long packet size is TX buffer size */
-        max_dsi_packet_size = dsi.vc[0].fifo_size * 32 * 4;
+        max_dsi_packet_size = dsi->vc[0].fifo_size * 32 * 4;
 
         /* we seem to get better perf if we divide the tx fifo to half,
            and while the other half is being sent, we fill the other half
@@ -2944,35 +3725,36 @@ static int dsi_update_screen_l4(struct omap_dss_device *dssdev,
 #if 1
                 /* using fifo not empty */
                 /* TX_FIFO_NOT_EMPTY */
-                while (FLD_GET(dsi_read_reg(DSI_VC_CTRL(0)), 5, 5)) {
+                while (FLD_GET(dsi_read_reg(dsidev, DSI_VC_CTRL(0)), 5, 5)) {
                         fifo_stalls++;
                         if (fifo_stalls > 0xfffff) {
                                 DSSERR("fifo stalls overflow, pixels left %d\n",
                                                 pixels_left);
-                                dsi_if_enable(0);
+                                dsi_if_enable(dsidev, 0);
                                 return -EIO;
                         }
                         udelay(1);
                 }
 #elif 1
                 /* using fifo emptiness */
-                while ((REG_GET(DSI_TX_FIFO_VC_EMPTINESS, 7, 0)+1)*4 <
+                while ((REG_GET(dsidev, DSI_TX_FIFO_VC_EMPTINESS, 7, 0)+1)*4 <
                                 max_dsi_packet_size) {
                         fifo_stalls++;
                         if (fifo_stalls > 0xfffff) {
                                 DSSERR("fifo stalls overflow, pixels left %d\n",
                                                pixels_left);
-                                dsi_if_enable(0);
+                                dsi_if_enable(dsidev, 0);
                                 return -EIO;
                         }
                 }
 #else
-                while ((REG_GET(DSI_TX_FIFO_VC_EMPTINESS, 7, 0)+1)*4 == 0) {
+                while ((REG_GET(dsidev, DSI_TX_FIFO_VC_EMPTINESS,
+                                7, 0) + 1) * 4 == 0) {
                         fifo_stalls++;
                         if (fifo_stalls > 0xfffff) {
                                 DSSERR("fifo stalls overflow, pixels left %d\n",
                                                pixels_left);
-                                dsi_if_enable(0);
+                                dsi_if_enable(dsidev, 0);
                                 return -EIO;
                         }
                 }
@@ -2981,17 +3763,17 @@ static int dsi_update_screen_l4(struct omap_dss_device *dssdev,
 
                 pixels_left -= pixels;
 
-                dsi_vc_write_long_header(0, DSI_DT_DCS_LONG_WRITE,
+                dsi_vc_write_long_header(dsidev, 0, DSI_DT_DCS_LONG_WRITE,
                                 1 + pixels * bytespp, 0);
 
-                DSI_PUSH(0, dcs_cmd);
+                DSI_PUSH(dsidev, 0, dcs_cmd);
 
                 while (pixels-- > 0) {
                         u32 pix = __raw_readl(data++);
 
-                        DSI_PUSH(0, (pix >> 16) & 0xff);
-                        DSI_PUSH(0, (pix >> 8) & 0xff);
-                        DSI_PUSH(0, (pix >> 0) & 0xff);
+                        DSI_PUSH(dsidev, 0, (pix >> 16) & 0xff);
+                        DSI_PUSH(dsidev, 0, (pix >> 8) & 0xff);
+                        DSI_PUSH(dsidev, 0, (pix >> 0) & 0xff);
 
                         current_x++;
                         if (current_x == x+w) {
@@ -3000,7 +3782,7 @@ static int dsi_update_screen_l4(struct omap_dss_device *dssdev,
                         }
                 }
 
-                DSI_FLUSH(0);
+                DSI_FLUSH(dsidev, 0);
         }
 
         return 0;
@@ -3009,6 +3791,8 @@ static int dsi_update_screen_l4(struct omap_dss_device *dssdev,
 static void dsi_update_screen_dispc(struct omap_dss_device *dssdev,
                 u16 x, u16 y, u16 w, u16 h)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         unsigned bytespp;
         unsigned bytespl;
         unsigned bytespf;
@@ -3017,16 +3801,13 @@ static void dsi_update_screen_dispc(struct omap_dss_device *dssdev,
         unsigned packet_len;
         u32 l;
         int r;
-        const unsigned channel = dsi.update_channel;
-        /* line buffer is 1024 x 24bits */
-        /* XXX: for some reason using full buffer size causes considerable TX
-         * slowdown with update sizes that fill the whole buffer */
-        const unsigned line_buf_size = 1023 * 3;
+        const unsigned channel = dsi->update_channel;
+        const unsigned line_buf_size = dsi_get_line_buf_size(dsidev);
 
         DSSDBG("dsi_update_screen_dispc(%d,%d %dx%d)\n",
                         x, y, w, h);
 
-        dsi_vc_config_vp(channel);
+        dsi_vc_config_vp(dsidev, channel);
 
         bytespp = dssdev->ctrl.pixel_size / 8;
         bytespl = w * bytespp;
@@ -3047,15 +3828,16 @@ static void dsi_update_screen_dispc(struct omap_dss_device *dssdev,
                 total_len += (bytespf % packet_payload) + 1;
 
         l = FLD_VAL(total_len, 23, 0); /* TE_SIZE */
-        dsi_write_reg(DSI_VC_TE(channel), l);
+        dsi_write_reg(dsidev, DSI_VC_TE(channel), l);
 
-        dsi_vc_write_long_header(channel, DSI_DT_DCS_LONG_WRITE, packet_len, 0);
+        dsi_vc_write_long_header(dsidev, channel, DSI_DT_DCS_LONG_WRITE,
+                packet_len, 0);
 
-        if (dsi.te_enabled)
+        if (dsi->te_enabled)
                 l = FLD_MOD(l, 1, 30, 30); /* TE_EN */
         else
                 l = FLD_MOD(l, 1, 31, 31); /* TE_START */
-        dsi_write_reg(DSI_VC_TE(channel), l);
+        dsi_write_reg(dsidev, DSI_VC_TE(channel), l);
 
         /* We put SIDLEMODE to no-idle for the duration of the transfer,
          * because DSS interrupts are not capable of waking up the CPU and the
@@ -3065,23 +3847,23 @@ static void dsi_update_screen_dispc(struct omap_dss_device *dssdev,
          */
         dispc_disable_sidle();
 
-        dsi_perf_mark_start();
+        dsi_perf_mark_start(dsidev);
 
-        r = queue_delayed_work(dsi.workqueue, &dsi.framedone_timeout_work,
-                        msecs_to_jiffies(250));
+        r = schedule_delayed_work(&dsi->framedone_timeout_work,
+                msecs_to_jiffies(250));
         BUG_ON(r == 0);
 
         dss_start_update(dssdev);
 
-        if (dsi.te_enabled) {
+        if (dsi->te_enabled) {
                 /* disable LP_RX_TO, so that we can receive TE.  Time to wait
                  * for TE is longer than the timer allows */
-                REG_FLD_MOD(DSI_TIMING2, 0, 15, 15); /* LP_RX_TO */
+                REG_FLD_MOD(dsidev, DSI_TIMING2, 0, 15, 15); /* LP_RX_TO */
 
-                dsi_vc_send_bta(channel);
+                dsi_vc_send_bta(dsidev, channel);
 
 #ifdef DSI_CATCH_MISSING_TE
-                mod_timer(&dsi.te_timer, jiffies + msecs_to_jiffies(250));
+                mod_timer(&dsi->te_timer, jiffies + msecs_to_jiffies(250));
 #endif
         }
 }
@@ -3093,41 +3875,28 @@ static void dsi_te_timeout(unsigned long arg)
 }
 #endif
 
-static void dsi_framedone_bta_callback(void *data, u32 mask);
-
-static void dsi_handle_framedone(int error)
+static void dsi_handle_framedone(struct platform_device *dsidev, int error)
 {
-        const int channel = dsi.update_channel;
-
-        dsi_unregister_isr_vc(channel, dsi_framedone_bta_callback,
-                        NULL, DSI_VC_IRQ_BTA);
-
-        cancel_delayed_work(&dsi.framedone_timeout_work);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 
         /* SIDLEMODE back to smart-idle */
         dispc_enable_sidle();
 
-        if (dsi.te_enabled) {
+        if (dsi->te_enabled) {
                 /* enable LP_RX_TO again after the TE */
-                REG_FLD_MOD(DSI_TIMING2, 1, 15, 15); /* LP_RX_TO */
+                REG_FLD_MOD(dsidev, DSI_TIMING2, 1, 15, 15); /* LP_RX_TO */
         }
 
-        /* RX_FIFO_NOT_EMPTY */
-        if (REG_GET(DSI_VC_CTRL(channel), 20, 20)) {
-                DSSERR("Received error during frame transfer:\n");
-                dsi_vc_flush_receive_data(channel);
-                if (!error)
-                        error = -EIO;
-        }
-
-        dsi.framedone_callback(error, dsi.framedone_data);
+        dsi->framedone_callback(error, dsi->framedone_data);
 
         if (!error)
-                dsi_perf_show("DISPC");
+                dsi_perf_show(dsidev, "DISPC");
 }
 
 static void dsi_framedone_timeout_work_callback(struct work_struct *work)
 {
+        struct dsi_data *dsi = container_of(work, struct dsi_data,
+                        framedone_timeout_work.work);
         /* XXX While extremely unlikely, we could get FRAMEDONE interrupt after
          * 250ms which would conflict with this timeout work. What should be
          * done is first cancel the transfer on the HW, and then cancel the
@@ -3137,70 +3906,34 @@ static void dsi_framedone_timeout_work_callback(struct work_struct *work)
 
         DSSERR("Framedone not received for 250ms!\n");
 
-        dsi_handle_framedone(-ETIMEDOUT);
-}
-
-static void dsi_framedone_bta_callback(void *data, u32 mask)
-{
-        dsi_handle_framedone(0);
-
-#ifdef CONFIG_OMAP2_DSS_FAKE_VSYNC
-        dispc_fake_vsync_irq();
-#endif
+        dsi_handle_framedone(dsi->pdev, -ETIMEDOUT);
 }
 
 static void dsi_framedone_irq_callback(void *data, u32 mask)
 {
-        const int channel = dsi.update_channel;
-        int r;
+        struct omap_dss_device *dssdev = (struct omap_dss_device *) data;
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 
         /* Note: We get FRAMEDONE when DISPC has finished sending pixels and
          * turns itself off. However, DSI still has the pixels in its buffers,
          * and is sending the data.
          */
 
-        if (dsi.te_enabled) {
-                /* enable LP_RX_TO again after the TE */
-                REG_FLD_MOD(DSI_TIMING2, 1, 15, 15); /* LP_RX_TO */
-        }
-
-        /* Send BTA after the frame. We need this for the TE to work, as TE
-         * trigger is only sent for BTAs without preceding packet. Thus we need
-         * to BTA after the pixel packets so that next BTA will cause TE
-         * trigger.
-         *
-         * This is not needed when TE is not in use, but we do it anyway to
-         * make sure that the transfer has been completed. It would be more
-         * optimal, but more complex, to wait only just before starting next
-         * transfer.
-         *
-         * Also, as there's no interrupt telling when the transfer has been
-         * done and the channel could be reconfigured, the only way is to
-         * busyloop until TE_SIZE is zero. With BTA we can do this
-         * asynchronously.
-         * */
-
-        r = dsi_register_isr_vc(channel, dsi_framedone_bta_callback,
-                        NULL, DSI_VC_IRQ_BTA);
-        if (r) {
-                DSSERR("Failed to register BTA ISR\n");
-                dsi_handle_framedone(-EIO);
-                return;
-        }
+        __cancel_delayed_work(&dsi->framedone_timeout_work);
 
-        r = dsi_vc_send_bta(channel);
-        if (r) {
-                DSSERR("BTA after framedone failed\n");
-                dsi_unregister_isr_vc(channel, dsi_framedone_bta_callback,
-                                NULL, DSI_VC_IRQ_BTA);
-                dsi_handle_framedone(-EIO);
-        }
+        dsi_handle_framedone(dsidev, 0);
+
+#ifdef CONFIG_OMAP2_DSS_FAKE_VSYNC
+        dispc_fake_vsync_irq();
+#endif
 }
 
 int omap_dsi_prepare_update(struct omap_dss_device *dssdev,
                                     u16 *x, u16 *y, u16 *w, u16 *h,
                                     bool enlarge_update_area)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         u16 dw, dh;
 
         dssdev->driver->get_resolution(dssdev, &dw, &dh);
@@ -3220,7 +3953,7 @@ int omap_dsi_prepare_update(struct omap_dss_device *dssdev,
         if (*w == 0 || *h == 0)
                 return -EINVAL;
 
-        dsi_perf_mark_setup();
+        dsi_perf_mark_setup(dsidev);
 
         if (dssdev->manager->caps & OMAP_DSS_OVL_MGR_CAP_DISPC) {
                 dss_setup_partial_planes(dssdev, x, y, w, h,
@@ -3237,7 +3970,10 @@ int omap_dsi_update(struct omap_dss_device *dssdev,
                 u16 x, u16 y, u16 w, u16 h,
                 void (*callback)(int, void *), void *data)
 {
-        dsi.update_channel = channel;
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        dsi->update_channel = channel;
 
         /* OMAP DSS cannot send updates of odd widths.
          * omap_dsi_prepare_update() makes the widths even, but add a BUG_ON
@@ -3246,14 +3982,14 @@ int omap_dsi_update(struct omap_dss_device *dssdev,
         BUG_ON(x % 2 == 1);
 
         if (dssdev->manager->caps & OMAP_DSS_OVL_MGR_CAP_DISPC) {
-                dsi.framedone_callback = callback;
-                dsi.framedone_data = data;
+                dsi->framedone_callback = callback;
+                dsi->framedone_data = data;
 
-                dsi.update_region.x = x;
-                dsi.update_region.y = y;
-                dsi.update_region.w = w;
-                dsi.update_region.h = h;
-                dsi.update_region.device = dssdev;
+                dsi->update_region.x = x;
+                dsi->update_region.y = y;
+                dsi->update_region.w = w;
+                dsi->update_region.h = h;
+                dsi->update_region.device = dssdev;
 
                 dsi_update_screen_dispc(dssdev, x, y, w, h);
         } else {
@@ -3263,7 +3999,7 @@ int omap_dsi_update(struct omap_dss_device *dssdev,
                 if (r)
                         return r;
 
-                dsi_perf_show("L4");
+                dsi_perf_show(dsidev, "L4");
                 callback(0, data);
         }
 
@@ -3276,9 +4012,13 @@ EXPORT_SYMBOL(omap_dsi_update);
 static int dsi_display_init_dispc(struct omap_dss_device *dssdev)
 {
         int r;
+        u32 irq;
+
+        irq = dssdev->manager->id == OMAP_DSS_CHANNEL_LCD ?
+                DISPC_IRQ_FRAMEDONE : DISPC_IRQ_FRAMEDONE2;
 
-        r = omap_dispc_register_isr(dsi_framedone_irq_callback, NULL,
-                        DISPC_IRQ_FRAMEDONE);
+        r = omap_dispc_register_isr(dsi_framedone_irq_callback, (void *) dssdev,
+                        irq);
         if (r) {
                 DSSERR("can't get FRAMEDONE irq\n");
                 return r;
@@ -3311,28 +4051,34 @@ static int dsi_display_init_dispc(struct omap_dss_device *dssdev)
 
 static void dsi_display_uninit_dispc(struct omap_dss_device *dssdev)
 {
-        omap_dispc_unregister_isr(dsi_framedone_irq_callback, NULL,
-                        DISPC_IRQ_FRAMEDONE);
+        u32 irq;
+
+        irq = dssdev->manager->id == OMAP_DSS_CHANNEL_LCD ?
+                DISPC_IRQ_FRAMEDONE : DISPC_IRQ_FRAMEDONE2;
+
+        omap_dispc_unregister_isr(dsi_framedone_irq_callback, (void *) dssdev,
+                        irq);
 }
 
 static int dsi_configure_dsi_clocks(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         struct dsi_clock_info cinfo;
         int r;
 
         /* we always use DSS_CLK_SYSCK as input clock */
         cinfo.use_sys_clk = true;
-        cinfo.regn  = dssdev->phy.dsi.div.regn;
-        cinfo.regm  = dssdev->phy.dsi.div.regm;
-        cinfo.regm_dispc = dssdev->phy.dsi.div.regm_dispc;
-        cinfo.regm_dsi = dssdev->phy.dsi.div.regm_dsi;
+        cinfo.regn  = dssdev->clocks.dsi.regn;
+        cinfo.regm  = dssdev->clocks.dsi.regm;
+        cinfo.regm_dispc = dssdev->clocks.dsi.regm_dispc;
+        cinfo.regm_dsi = dssdev->clocks.dsi.regm_dsi;
         r = dsi_calc_clock_rates(dssdev, &cinfo);
         if (r) {
                 DSSERR("Failed to calc dsi clocks\n");
                 return r;
         }
 
-        r = dsi_pll_set_clock_div(&cinfo);
+        r = dsi_pll_set_clock_div(dsidev, &cinfo);
         if (r) {
                 DSSERR("Failed to set dsi clocks\n");
                 return r;
@@ -3343,14 +4089,15 @@ static int dsi_configure_dsi_clocks(struct omap_dss_device *dssdev)
 
 static int dsi_configure_dispc_clocks(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
         struct dispc_clock_info dispc_cinfo;
         int r;
         unsigned long long fck;
 
-        fck = dsi_get_pll_hsdiv_dispc_rate();
+        fck = dsi_get_pll_hsdiv_dispc_rate(dsidev);
 
-        dispc_cinfo.lck_div = dssdev->phy.dsi.div.lck_div;
-        dispc_cinfo.pck_div = dssdev->phy.dsi.div.pck_div;
+        dispc_cinfo.lck_div = dssdev->clocks.dispc.channel.lck_div;
+        dispc_cinfo.pck_div = dssdev->clocks.dispc.channel.pck_div;
 
         r = dispc_calc_clock_rates(fck, &dispc_cinfo);
         if (r) {
@@ -3369,11 +4116,11 @@ static int dsi_configure_dispc_clocks(struct omap_dss_device *dssdev)
 
 static int dsi_display_init_dsi(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        int dsi_module = dsi_get_dsidev_id(dsidev);
         int r;
 
-        _dsi_print_reset_status();
-
-        r = dsi_pll_init(dssdev, true, true);
+        r = dsi_pll_init(dsidev, true, true);
         if (r)
                 goto err0;
 
@@ -3381,8 +4128,10 @@ static int dsi_display_init_dsi(struct omap_dss_device *dssdev)
         if (r)
                 goto err1;
 
-        dss_select_dispc_clk_source(DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC);
-        dss_select_dsi_clk_source(DSS_CLK_SRC_DSI_PLL_HSDIV_DSI);
+        dss_select_dispc_clk_source(dssdev->clocks.dispc.dispc_fclk_src);
+        dss_select_dsi_clk_source(dsi_module, dssdev->clocks.dsi.dsi_fclk_src);
+        dss_select_lcd_clk_source(dssdev->manager->id,
+                        dssdev->clocks.dispc.channel.lcd_clk_src);
 
         DSSDBG("PLL OK\n");
 
@@ -3390,82 +4139,92 @@ static int dsi_display_init_dsi(struct omap_dss_device *dssdev)
         if (r)
                 goto err2;
 
-        r = dsi_complexio_init(dssdev);
+        r = dsi_cio_init(dssdev);
         if (r)
                 goto err2;
 
-        _dsi_print_reset_status();
+        _dsi_print_reset_status(dsidev);
 
         dsi_proto_timings(dssdev);
         dsi_set_lp_clk_divisor(dssdev);
 
         if (1)
-                _dsi_print_reset_status();
+                _dsi_print_reset_status(dsidev);
 
         r = dsi_proto_config(dssdev);
         if (r)
                 goto err3;
 
         /* enable interface */
-        dsi_vc_enable(0, 1);
-        dsi_vc_enable(1, 1);
-        dsi_vc_enable(2, 1);
-        dsi_vc_enable(3, 1);
-        dsi_if_enable(1);
-        dsi_force_tx_stop_mode_io();
+        dsi_vc_enable(dsidev, 0, 1);
+        dsi_vc_enable(dsidev, 1, 1);
+        dsi_vc_enable(dsidev, 2, 1);
+        dsi_vc_enable(dsidev, 3, 1);
+        dsi_if_enable(dsidev, 1);
+        dsi_force_tx_stop_mode_io(dsidev);
 
         return 0;
 err3:
-        dsi_complexio_uninit();
+        dsi_cio_uninit(dsidev);
 err2:
-        dss_select_dispc_clk_source(DSS_CLK_SRC_FCK);
-        dss_select_dsi_clk_source(DSS_CLK_SRC_FCK);
+        dss_select_dispc_clk_source(OMAP_DSS_CLK_SRC_FCK);
+        dss_select_dsi_clk_source(dsi_module, OMAP_DSS_CLK_SRC_FCK);
 err1:
-        dsi_pll_uninit();
+        dsi_pll_uninit(dsidev, true);
 err0:
         return r;
 }
 
-static void dsi_display_uninit_dsi(struct omap_dss_device *dssdev)
+static void dsi_display_uninit_dsi(struct omap_dss_device *dssdev,
+                bool disconnect_lanes, bool enter_ulps)
 {
-        /* disable interface */
-        dsi_if_enable(0);
-        dsi_vc_enable(0, 0);
-        dsi_vc_enable(1, 0);
-        dsi_vc_enable(2, 0);
-        dsi_vc_enable(3, 0);
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        int dsi_module = dsi_get_dsidev_id(dsidev);
 
-        dss_select_dispc_clk_source(DSS_CLK_SRC_FCK);
-        dss_select_dsi_clk_source(DSS_CLK_SRC_FCK);
-        dsi_complexio_uninit();
-        dsi_pll_uninit();
+        if (enter_ulps && !dsi->ulps_enabled)
+                dsi_enter_ulps(dsidev);
+
+        /* disable interface */
+        dsi_if_enable(dsidev, 0);
+        dsi_vc_enable(dsidev, 0, 0);
+        dsi_vc_enable(dsidev, 1, 0);
+        dsi_vc_enable(dsidev, 2, 0);
+        dsi_vc_enable(dsidev, 3, 0);
+
+        dss_select_dispc_clk_source(OMAP_DSS_CLK_SRC_FCK);
+        dss_select_dsi_clk_source(dsi_module, OMAP_DSS_CLK_SRC_FCK);
+        dsi_cio_uninit(dsidev);
+        dsi_pll_uninit(dsidev, disconnect_lanes);
 }
 
-static int dsi_core_init(void)
+static int dsi_core_init(struct platform_device *dsidev)
 {
         /* Autoidle */
-        REG_FLD_MOD(DSI_SYSCONFIG, 1, 0, 0);
+        REG_FLD_MOD(dsidev, DSI_SYSCONFIG, 1, 0, 0);
 
         /* ENWAKEUP */
-        REG_FLD_MOD(DSI_SYSCONFIG, 1, 2, 2);
+        REG_FLD_MOD(dsidev, DSI_SYSCONFIG, 1, 2, 2);
 
         /* SIDLEMODE smart-idle */
-        REG_FLD_MOD(DSI_SYSCONFIG, 2, 4, 3);
+        REG_FLD_MOD(dsidev, DSI_SYSCONFIG, 2, 4, 3);
 
-        _dsi_initialize_irq();
+        _dsi_initialize_irq(dsidev);
 
         return 0;
 }
 
 int omapdss_dsi_display_enable(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int r = 0;
 
         DSSDBG("dsi_display_enable\n");
 
-        WARN_ON(!dsi_bus_is_locked());
+        WARN_ON(!dsi_bus_is_locked(dsidev));
 
-        mutex_lock(&dsi.lock);
+        mutex_lock(&dsi->lock);
 
         r = omap_dss_start_device(dssdev);
         if (r) {
@@ -3474,13 +4233,13 @@ int omapdss_dsi_display_enable(struct omap_dss_device *dssdev)
         }
 
         enable_clocks(1);
-        dsi_enable_pll_clock(1);
+        dsi_enable_pll_clock(dsidev, 1);
 
-        r = _dsi_reset();
+        r = _dsi_reset(dsidev);
         if (r)
                 goto err1;
 
-        dsi_core_init();
+        dsi_core_init(dsidev);
 
         r = dsi_display_init_dispc(dssdev);
         if (r)
@@ -3490,7 +4249,7 @@ int omapdss_dsi_display_enable(struct omap_dss_device *dssdev)
         if (r)
                 goto err2;
 
-        mutex_unlock(&dsi.lock);
+        mutex_unlock(&dsi->lock);
 
         return 0;
 
@@ -3498,39 +4257,46 @@ err2:
         dsi_display_uninit_dispc(dssdev);
 err1:
         enable_clocks(0);
-        dsi_enable_pll_clock(0);
+        dsi_enable_pll_clock(dsidev, 0);
         omap_dss_stop_device(dssdev);
 err0:
-        mutex_unlock(&dsi.lock);
+        mutex_unlock(&dsi->lock);
         DSSDBG("dsi_display_enable FAILED\n");
         return r;
 }
 EXPORT_SYMBOL(omapdss_dsi_display_enable);
 
-void omapdss_dsi_display_disable(struct omap_dss_device *dssdev)
+void omapdss_dsi_display_disable(struct omap_dss_device *dssdev,
+                bool disconnect_lanes, bool enter_ulps)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
         DSSDBG("dsi_display_disable\n");
 
-        WARN_ON(!dsi_bus_is_locked());
+        WARN_ON(!dsi_bus_is_locked(dsidev));
 
-        mutex_lock(&dsi.lock);
+        mutex_lock(&dsi->lock);
 
         dsi_display_uninit_dispc(dssdev);
 
-        dsi_display_uninit_dsi(dssdev);
+        dsi_display_uninit_dsi(dssdev, disconnect_lanes, enter_ulps);
 
         enable_clocks(0);
-        dsi_enable_pll_clock(0);
+        dsi_enable_pll_clock(dsidev, 0);
 
         omap_dss_stop_device(dssdev);
 
-        mutex_unlock(&dsi.lock);
+        mutex_unlock(&dsi->lock);
 }
 EXPORT_SYMBOL(omapdss_dsi_display_disable);
 
 int omapdss_dsi_enable_te(struct omap_dss_device *dssdev, bool enable)
 {
-        dsi.te_enabled = enable;
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        dsi->te_enabled = enable;
         return 0;
 }
 EXPORT_SYMBOL(omapdss_dsi_enable_te);
@@ -3550,23 +4316,33 @@ void dsi_get_overlay_fifo_thresholds(enum omap_plane plane,
 
 int dsi_init_display(struct omap_dss_device *dssdev)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+        int dsi_module = dsi_get_dsidev_id(dsidev);
+
         DSSDBG("DSI init\n");
 
         /* XXX these should be figured out dynamically */
         dssdev->caps = OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE |
                 OMAP_DSS_DISPLAY_CAP_TEAR_ELIM;
 
-        if (dsi.vdds_dsi_reg == NULL) {
+        if (dsi->vdds_dsi_reg == NULL) {
                 struct regulator *vdds_dsi;
 
-                vdds_dsi = regulator_get(&dsi.pdev->dev, "vdds_dsi");
+                vdds_dsi = regulator_get(&dsi->pdev->dev, "vdds_dsi");
 
                 if (IS_ERR(vdds_dsi)) {
                         DSSERR("can't get VDDS_DSI regulator\n");
                         return PTR_ERR(vdds_dsi);
                 }
 
-                dsi.vdds_dsi_reg = vdds_dsi;
+                dsi->vdds_dsi_reg = vdds_dsi;
+        }
+
+        if (dsi_get_num_data_lanes_dssdev(dssdev) > dsi->num_data_lanes) {
+                DSSERR("DSI%d can't support more than %d data lanes\n",
+                        dsi_module + 1, dsi->num_data_lanes);
+                return -EINVAL;
         }
 
         return 0;
@@ -3574,11 +4350,13 @@ int dsi_init_display(struct omap_dss_device *dssdev)
 
 int omap_dsi_request_vc(struct omap_dss_device *dssdev, int *channel)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
         int i;
 
-        for (i = 0; i < ARRAY_SIZE(dsi.vc); i++) {
-                if (!dsi.vc[i].dssdev) {
-                        dsi.vc[i].dssdev = dssdev;
+        for (i = 0; i < ARRAY_SIZE(dsi->vc); i++) {
+                if (!dsi->vc[i].dssdev) {
+                        dsi->vc[i].dssdev = dssdev;
                         *channel = i;
                         return 0;
                 }
@@ -3591,6 +4369,9 @@ EXPORT_SYMBOL(omap_dsi_request_vc);
 
 int omap_dsi_set_vc_id(struct omap_dss_device *dssdev, int channel, int vc_id)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
         if (vc_id < 0 || vc_id > 3) {
                 DSSERR("VC ID out of range\n");
                 return -EINVAL;
@@ -3601,13 +4382,13 @@ int omap_dsi_set_vc_id(struct omap_dss_device *dssdev, int channel, int vc_id)
                 return -EINVAL;
         }
 
-        if (dsi.vc[channel].dssdev != dssdev) {
+        if (dsi->vc[channel].dssdev != dssdev) {
                 DSSERR("Virtual Channel not allocated to display %s\n",
                         dssdev->name);
                 return -EINVAL;
         }
 
-        dsi.vc[channel].vc_id = vc_id;
+        dsi->vc[channel].vc_id = vc_id;
 
         return 0;
 }
@@ -3615,143 +4396,172 @@ EXPORT_SYMBOL(omap_dsi_set_vc_id);
 
 void omap_dsi_release_vc(struct omap_dss_device *dssdev, int channel)
 {
+        struct platform_device *dsidev = dsi_get_dsidev_from_dssdev(dssdev);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
         if ((channel >= 0 && channel <= 3) &&
-                dsi.vc[channel].dssdev == dssdev) {
-                dsi.vc[channel].dssdev = NULL;
-                dsi.vc[channel].vc_id = 0;
+                dsi->vc[channel].dssdev == dssdev) {
+                dsi->vc[channel].dssdev = NULL;
+                dsi->vc[channel].vc_id = 0;
         }
 }
 EXPORT_SYMBOL(omap_dsi_release_vc);
 
-void dsi_wait_pll_hsdiv_dispc_active(void)
+void dsi_wait_pll_hsdiv_dispc_active(struct platform_device *dsidev)
 {
-        if (wait_for_bit_change(DSI_PLL_STATUS, 7, 1) != 1)
+        if (wait_for_bit_change(dsidev, DSI_PLL_STATUS, 7, 1) != 1)
                 DSSERR("%s (%s) not active\n",
-                        dss_get_generic_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC),
-                        dss_feat_get_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC));
+                        dss_get_generic_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC),
+                        dss_feat_get_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC));
 }
 
-void dsi_wait_pll_hsdiv_dsi_active(void)
+void dsi_wait_pll_hsdiv_dsi_active(struct platform_device *dsidev)
 {
-        if (wait_for_bit_change(DSI_PLL_STATUS, 8, 1) != 1)
+        if (wait_for_bit_change(dsidev, DSI_PLL_STATUS, 8, 1) != 1)
                 DSSERR("%s (%s) not active\n",
-                        dss_get_generic_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DSI),
-                        dss_feat_get_clk_source_name(DSS_CLK_SRC_DSI_PLL_HSDIV_DSI));
+                        dss_get_generic_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI),
+                        dss_feat_get_clk_source_name(OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI));
 }
 
-static void dsi_calc_clock_param_ranges(void)
+static void dsi_calc_clock_param_ranges(struct platform_device *dsidev)
 {
-        dsi.regn_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGN);
-        dsi.regm_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGM);
-        dsi.regm_dispc_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGM_DISPC);
-        dsi.regm_dsi_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGM_DSI);
-        dsi.fint_min = dss_feat_get_param_min(FEAT_PARAM_DSIPLL_FINT);
-        dsi.fint_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_FINT);
-        dsi.lpdiv_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_LPDIV);
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        dsi->regn_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGN);
+        dsi->regm_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGM);
+        dsi->regm_dispc_max =
+                dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGM_DISPC);
+        dsi->regm_dsi_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_REGM_DSI);
+        dsi->fint_min = dss_feat_get_param_min(FEAT_PARAM_DSIPLL_FINT);
+        dsi->fint_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_FINT);
+        dsi->lpdiv_max = dss_feat_get_param_max(FEAT_PARAM_DSIPLL_LPDIV);
 }
 
-static int dsi_init(struct platform_device *pdev)
+static int dsi_init(struct platform_device *dsidev)
 {
+        struct omap_display_platform_data *dss_plat_data;
+        struct omap_dss_board_info *board_info;
         u32 rev;
-        int r, i;
+        int r, i, dsi_module = dsi_get_dsidev_id(dsidev);
         struct resource *dsi_mem;
+        struct dsi_data *dsi;
+
+        dsi = kzalloc(sizeof(*dsi), GFP_KERNEL);
+        if (!dsi) {
+                r = -ENOMEM;
+                goto err0;
+        }
+
+        dsi->pdev = dsidev;
+        dsi_pdev_map[dsi_module] = dsidev;
+        dev_set_drvdata(&dsidev->dev, dsi);
+
+        dss_plat_data = dsidev->dev.platform_data;
+        board_info = dss_plat_data->board_data;
+        dsi->dsi_mux_pads = board_info->dsi_mux_pads;
 
-        spin_lock_init(&dsi.irq_lock);
-        spin_lock_init(&dsi.errors_lock);
-        dsi.errors = 0;
+        spin_lock_init(&dsi->irq_lock);
+        spin_lock_init(&dsi->errors_lock);
+        dsi->errors = 0;
 
 #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS
-        spin_lock_init(&dsi.irq_stats_lock);
-        dsi.irq_stats.last_reset = jiffies;
+        spin_lock_init(&dsi->irq_stats_lock);
+        dsi->irq_stats.last_reset = jiffies;
 #endif
 
-        mutex_init(&dsi.lock);
-        sema_init(&dsi.bus_lock, 1);
+        mutex_init(&dsi->lock);
+        sema_init(&dsi->bus_lock, 1);
 
-        dsi.workqueue = create_singlethread_workqueue("dsi");
-        if (dsi.workqueue == NULL)
-                return -ENOMEM;
-
-        INIT_DELAYED_WORK_DEFERRABLE(&dsi.framedone_timeout_work,
+        INIT_DELAYED_WORK_DEFERRABLE(&dsi->framedone_timeout_work,
                         dsi_framedone_timeout_work_callback);
 
 #ifdef DSI_CATCH_MISSING_TE
-        init_timer(&dsi.te_timer);
-        dsi.te_timer.function = dsi_te_timeout;
-        dsi.te_timer.data = 0;
+        init_timer(&dsi->te_timer);
+        dsi->te_timer.function = dsi_te_timeout;
+        dsi->te_timer.data = 0;
 #endif
-        dsi_mem = platform_get_resource(dsi.pdev, IORESOURCE_MEM, 0);
+        dsi_mem = platform_get_resource(dsi->pdev, IORESOURCE_MEM, 0);
         if (!dsi_mem) {
                 DSSERR("can't get IORESOURCE_MEM DSI\n");
                 r = -EINVAL;
                 goto err1;
         }
-        dsi.base = ioremap(dsi_mem->start, resource_size(dsi_mem));
-        if (!dsi.base) {
+        dsi->base = ioremap(dsi_mem->start, resource_size(dsi_mem));
+        if (!dsi->base) {
                 DSSERR("can't ioremap DSI\n");
                 r = -ENOMEM;
                 goto err1;
         }
-        dsi.irq = platform_get_irq(dsi.pdev, 0);
-        if (dsi.irq < 0) {
+        dsi->irq = platform_get_irq(dsi->pdev, 0);
+        if (dsi->irq < 0) {
                 DSSERR("platform_get_irq failed\n");
                 r = -ENODEV;
                 goto err2;
         }
 
-        r = request_irq(dsi.irq, omap_dsi_irq_handler, IRQF_SHARED,
-                "OMAP DSI1", dsi.pdev);
+        r = request_irq(dsi->irq, omap_dsi_irq_handler, IRQF_SHARED,
+                dev_name(&dsidev->dev), dsi->pdev);
         if (r < 0) {
                 DSSERR("request_irq failed\n");
                 goto err2;
         }
 
         /* DSI VCs initialization */
-        for (i = 0; i < ARRAY_SIZE(dsi.vc); i++) {
-                dsi.vc[i].mode = DSI_VC_MODE_L4;
-                dsi.vc[i].dssdev = NULL;
-                dsi.vc[i].vc_id = 0;
+        for (i = 0; i < ARRAY_SIZE(dsi->vc); i++) {
+                dsi->vc[i].mode = DSI_VC_MODE_L4;
+                dsi->vc[i].dssdev = NULL;
+                dsi->vc[i].vc_id = 0;
         }
 
-        dsi_calc_clock_param_ranges();
+        dsi_calc_clock_param_ranges(dsidev);
 
         enable_clocks(1);
 
-        rev = dsi_read_reg(DSI_REVISION);
-        dev_dbg(&pdev->dev, "OMAP DSI rev %d.%d\n",
+        rev = dsi_read_reg(dsidev, DSI_REVISION);
+        dev_dbg(&dsidev->dev, "OMAP DSI rev %d.%d\n",
                FLD_GET(rev, 7, 4), FLD_GET(rev, 3, 0));
 
+        dsi->num_data_lanes = dsi_get_num_data_lanes(dsidev);
+
         enable_clocks(0);
 
         return 0;
 err2:
-        iounmap(dsi.base);
+        iounmap(dsi->base);
 err1:
-        destroy_workqueue(dsi.workqueue);
+        kfree(dsi);
+err0:
         return r;
 }
 
-static void dsi_exit(void)
+static void dsi_exit(struct platform_device *dsidev)
 {
-        if (dsi.vdds_dsi_reg != NULL) {
-                regulator_put(dsi.vdds_dsi_reg);
-                dsi.vdds_dsi_reg = NULL;
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        if (dsi->vdds_dsi_reg != NULL) {
+                if (dsi->vdds_dsi_enabled) {
+                        regulator_disable(dsi->vdds_dsi_reg);
+                        dsi->vdds_dsi_enabled = false;
+                }
+
+                regulator_put(dsi->vdds_dsi_reg);
+                dsi->vdds_dsi_reg = NULL;
         }
 
-        free_irq(dsi.irq, dsi.pdev);
-        iounmap(dsi.base);
+        free_irq(dsi->irq, dsi->pdev);
+        iounmap(dsi->base);
 
-        destroy_workqueue(dsi.workqueue);
+        kfree(dsi);
 
         DSSDBG("omap_dsi_exit\n");
 }
 
 /* DSI1 HW IP initialisation */
-static int omap_dsi1hw_probe(struct platform_device *pdev)
+static int omap_dsi1hw_probe(struct platform_device *dsidev)
 {
         int r;
-        dsi.pdev = pdev;
-        r = dsi_init(pdev);
+
+        r = dsi_init(dsidev);
         if (r) {
                 DSSERR("Failed to initialize DSI\n");
                 goto err_dsi;
@@ -3760,9 +4570,12 @@ err_dsi:
         return r;
 }
 
-static int omap_dsi1hw_remove(struct platform_device *pdev)
+static int omap_dsi1hw_remove(struct platform_device *dsidev)
 {
-        dsi_exit();
+        struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
+
+        dsi_exit(dsidev);
+        WARN_ON(dsi->scp_clk_refcount > 0);
         return 0;
 }
 
diff --git a/drivers/video/omap2/dss/dss.c b/drivers/video/omap2/dss/dss.c
index 3f1fee63c678..d9489d5c4f08 100644
--- a/drivers/video/omap2/dss/dss.c
+++ b/drivers/video/omap2/dss/dss.c
@@ -29,7 +29,7 @@
 #include <linux/seq_file.h>
 #include <linux/clk.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/clock.h>
 #include "dss.h"
 #include "dss_features.h"
@@ -45,7 +45,6 @@ struct dss_reg {
 #define DSS_REVISION                    DSS_REG(0x0000)
 #define DSS_SYSCONFIG                   DSS_REG(0x0010)
 #define DSS_SYSSTATUS                   DSS_REG(0x0014)
-#define DSS_IRQSTATUS                   DSS_REG(0x0018)
 #define DSS_CONTROL                     DSS_REG(0x0040)
 #define DSS_SDI_CONTROL                 DSS_REG(0x0044)
 #define DSS_PLL_CONTROL                 DSS_REG(0x0048)
@@ -75,17 +74,17 @@ static struct {
         struct dss_clock_info cache_dss_cinfo;
         struct dispc_clock_info cache_dispc_cinfo;
 
-        enum dss_clk_source dsi_clk_source;
-        enum dss_clk_source dispc_clk_source;
-        enum dss_clk_source lcd_clk_source[MAX_DSS_LCD_MANAGERS];
+        enum omap_dss_clk_source dsi_clk_source[MAX_NUM_DSI];
+        enum omap_dss_clk_source dispc_clk_source;
+        enum omap_dss_clk_source lcd_clk_source[MAX_DSS_LCD_MANAGERS];
 
         u32             ctx[DSS_SZ_REGS / sizeof(u32)];
 } dss;
 
 static const char * const dss_generic_clk_source_names[] = {
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]       = "DSI_PLL_HSDIV_DISPC",
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]         = "DSI_PLL_HSDIV_DSI",
-        [DSS_CLK_SRC_FCK]                       = "DSS_FCK",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]  = "DSI_PLL_HSDIV_DISPC",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]    = "DSI_PLL_HSDIV_DSI",
+        [OMAP_DSS_CLK_SRC_FCK]                  = "DSS_FCK",
 };
 
 static void dss_clk_enable_all_no_ctx(void);
@@ -230,7 +229,7 @@ void dss_sdi_disable(void)
         REG_FLD_MOD(DSS_PLL_CONTROL, 0, 18, 18); /* SDI_PLL_SYSRESET */
 }
 
-const char *dss_get_generic_clk_source_name(enum dss_clk_source clk_src)
+const char *dss_get_generic_clk_source_name(enum omap_dss_clk_source clk_src)
 {
         return dss_generic_clk_source_names[clk_src];
 }
@@ -246,8 +245,8 @@ void dss_dump_clocks(struct seq_file *s)
 
         seq_printf(s, "- DSS -\n");
 
-        fclk_name = dss_get_generic_clk_source_name(DSS_CLK_SRC_FCK);
-        fclk_real_name = dss_feat_get_clk_source_name(DSS_CLK_SRC_FCK);
+        fclk_name = dss_get_generic_clk_source_name(OMAP_DSS_CLK_SRC_FCK);
+        fclk_real_name = dss_feat_get_clk_source_name(OMAP_DSS_CLK_SRC_FCK);
         fclk_rate = dss_clk_get_rate(DSS_CLK_FCK);
 
         if (dss.dpll4_m4_ck) {
@@ -286,7 +285,6 @@ void dss_dump_regs(struct seq_file *s)
         DUMPREG(DSS_REVISION);
         DUMPREG(DSS_SYSCONFIG);
         DUMPREG(DSS_SYSSTATUS);
-        DUMPREG(DSS_IRQSTATUS);
         DUMPREG(DSS_CONTROL);
 
         if (dss_feat_get_supported_displays(OMAP_DSS_CHANNEL_LCD) &
@@ -300,18 +298,25 @@ void dss_dump_regs(struct seq_file *s)
 #undef DUMPREG
 }
 
-void dss_select_dispc_clk_source(enum dss_clk_source clk_src)
+void dss_select_dispc_clk_source(enum omap_dss_clk_source clk_src)
 {
+        struct platform_device *dsidev;
         int b;
         u8 start, end;
 
         switch (clk_src) {
-        case DSS_CLK_SRC_FCK:
+        case OMAP_DSS_CLK_SRC_FCK:
                 b = 0;
                 break;
-        case DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
+        case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
                 b = 1;
-                dsi_wait_pll_hsdiv_dispc_active();
+                dsidev = dsi_get_dsidev_from_id(0);
+                dsi_wait_pll_hsdiv_dispc_active(dsidev);
+                break;
+        case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
+                b = 2;
+                dsidev = dsi_get_dsidev_from_id(1);
+                dsi_wait_pll_hsdiv_dispc_active(dsidev);
                 break;
         default:
                 BUG();
@@ -324,17 +329,27 @@ void dss_select_dispc_clk_source(enum dss_clk_source clk_src)
         dss.dispc_clk_source = clk_src;
 }
 
-void dss_select_dsi_clk_source(enum dss_clk_source clk_src)
+void dss_select_dsi_clk_source(int dsi_module,
+                enum omap_dss_clk_source clk_src)
 {
+        struct platform_device *dsidev;
         int b;
 
         switch (clk_src) {
-        case DSS_CLK_SRC_FCK:
+        case OMAP_DSS_CLK_SRC_FCK:
                 b = 0;
                 break;
-        case DSS_CLK_SRC_DSI_PLL_HSDIV_DSI:
+        case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI:
+                BUG_ON(dsi_module != 0);
+                b = 1;
+                dsidev = dsi_get_dsidev_from_id(0);
+                dsi_wait_pll_hsdiv_dsi_active(dsidev);
+                break;
+        case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI:
+                BUG_ON(dsi_module != 1);
                 b = 1;
-                dsi_wait_pll_hsdiv_dsi_active();
+                dsidev = dsi_get_dsidev_from_id(1);
+                dsi_wait_pll_hsdiv_dsi_active(dsidev);
                 break;
         default:
                 BUG();
@@ -342,25 +357,33 @@ void dss_select_dsi_clk_source(enum dss_clk_source clk_src)
 
         REG_FLD_MOD(DSS_CONTROL, b, 1, 1);      /* DSI_CLK_SWITCH */
 
-        dss.dsi_clk_source = clk_src;
+        dss.dsi_clk_source[dsi_module] = clk_src;
 }
 
 void dss_select_lcd_clk_source(enum omap_channel channel,
-                enum dss_clk_source clk_src)
+                enum omap_dss_clk_source clk_src)
 {
+        struct platform_device *dsidev;
         int b, ix, pos;
 
         if (!dss_has_feature(FEAT_LCD_CLK_SRC))
                 return;
 
         switch (clk_src) {
-        case DSS_CLK_SRC_FCK:
+        case OMAP_DSS_CLK_SRC_FCK:
                 b = 0;
                 break;
-        case DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
+        case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
                 BUG_ON(channel != OMAP_DSS_CHANNEL_LCD);
                 b = 1;
-                dsi_wait_pll_hsdiv_dispc_active();
+                dsidev = dsi_get_dsidev_from_id(0);
+                dsi_wait_pll_hsdiv_dispc_active(dsidev);
+                break;
+        case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
+                BUG_ON(channel != OMAP_DSS_CHANNEL_LCD2);
+                b = 1;
+                dsidev = dsi_get_dsidev_from_id(1);
+                dsi_wait_pll_hsdiv_dispc_active(dsidev);
                 break;
         default:
                 BUG();
@@ -373,20 +396,26 @@ void dss_select_lcd_clk_source(enum omap_channel channel,
         dss.lcd_clk_source[ix] = clk_src;
 }
 
-enum dss_clk_source dss_get_dispc_clk_source(void)
+enum omap_dss_clk_source dss_get_dispc_clk_source(void)
 {
         return dss.dispc_clk_source;
 }
 
-enum dss_clk_source dss_get_dsi_clk_source(void)
+enum omap_dss_clk_source dss_get_dsi_clk_source(int dsi_module)
 {
-        return dss.dsi_clk_source;
+        return dss.dsi_clk_source[dsi_module];
 }
 
-enum dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel)
+enum omap_dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel)
 {
-        int ix = channel == OMAP_DSS_CHANNEL_LCD ? 0 : 1;
-        return dss.lcd_clk_source[ix];
+        if (dss_has_feature(FEAT_LCD_CLK_SRC)) {
+                int ix = channel == OMAP_DSS_CHANNEL_LCD ? 0 : 1;
+                return dss.lcd_clk_source[ix];
+        } else {
+                /* LCD_CLK source is the same as DISPC_FCLK source for
+                 * OMAP2 and OMAP3 */
+                return dss.dispc_clk_source;
+        }
 }
 
 /* calculate clock rates using dividers in cinfo */
@@ -659,13 +688,18 @@ static int dss_init(void)
          * the kernel resets it */
         omap_writel(omap_readl(0x48050440) & ~0x3, 0x48050440);
 
+#ifdef CONFIG_OMAP2_DSS_SLEEP_BEFORE_RESET
         /* We need to wait here a bit, otherwise we sometimes start to
          * get synclost errors, and after that only power cycle will
          * restore DSS functionality. I have no idea why this happens.
          * And we have to wait _before_ resetting the DSS, but after
          * enabling clocks.
+         *
+         * This bug was at least present on OMAP3430. It's unknown
+         * if it happens on OMAP2 or OMAP3630.
          */
         msleep(50);
+#endif
 
         _omap_dss_reset();
 
@@ -700,10 +734,11 @@ static int dss_init(void)
 
         dss.dpll4_m4_ck = dpll4_m4_ck;
 
-        dss.dsi_clk_source = DSS_CLK_SRC_FCK;
-        dss.dispc_clk_source = DSS_CLK_SRC_FCK;
-        dss.lcd_clk_source[0] = DSS_CLK_SRC_FCK;
-        dss.lcd_clk_source[1] = DSS_CLK_SRC_FCK;
+        dss.dsi_clk_source[0] = OMAP_DSS_CLK_SRC_FCK;
+        dss.dsi_clk_source[1] = OMAP_DSS_CLK_SRC_FCK;
+        dss.dispc_clk_source = OMAP_DSS_CLK_SRC_FCK;
+        dss.lcd_clk_source[0] = OMAP_DSS_CLK_SRC_FCK;
+        dss.lcd_clk_source[1] = OMAP_DSS_CLK_SRC_FCK;
 
         dss_save_context();
 
@@ -1015,6 +1050,14 @@ static void core_dump_clocks(struct seq_file *s)
                 dss.dss_video_fck
         };
 
+        const char *names[5] = {
+                "ick",
+                "fck",
+                "sys_clk",
+                "tv_fck",
+                "video_fck"
+        };
+
         seq_printf(s, "- CORE -\n");
 
         seq_printf(s, "internal clk count\t\t%u\n", dss.num_clks_enabled);
@@ -1022,8 +1065,11 @@ static void core_dump_clocks(struct seq_file *s)
         for (i = 0; i < 5; i++) {
                 if (!clocks[i])
                         continue;
-                seq_printf(s, "%-15s\t%lu\t%d\n",
+                seq_printf(s, "%s (%s)%*s\t%lu\t%d\n",
+                                names[i],
                                 clocks[i]->name,
+                                24 - strlen(names[i]) - strlen(clocks[i]->name),
+                                "",
                                 clk_get_rate(clocks[i]),
                                 clocks[i]->usecount);
         }
diff --git a/drivers/video/omap2/dss/dss.h b/drivers/video/omap2/dss/dss.h
index c2f582bb19c0..8ab6d43329bb 100644
--- a/drivers/video/omap2/dss/dss.h
+++ b/drivers/video/omap2/dss/dss.h
@@ -117,15 +117,6 @@ enum dss_clock {
         DSS_CLK_VIDFCK  = 1 << 4,       /* DSS_96M_FCLK*/
 };
 
-enum dss_clk_source {
-        DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC,        /* OMAP3: DSI1_PLL_FCLK
-                                                 * OMAP4: PLL1_CLK1 */
-        DSS_CLK_SRC_DSI_PLL_HSDIV_DSI,          /* OMAP3: DSI2_PLL_FCLK
-                                                 * OMAP4: PLL1_CLK2 */
-        DSS_CLK_SRC_FCK,                        /* OMAP2/3: DSS1_ALWON_FCLK
-                                                 * OMAP4: DSS_FCLK */
-};
-
 enum dss_hdmi_venc_clk_source_select {
         DSS_VENC_TV_CLK = 0,
         DSS_HDMI_M_PCLK = 1,
@@ -236,7 +227,7 @@ void dss_clk_enable(enum dss_clock clks);
 void dss_clk_disable(enum dss_clock clks);
 unsigned long dss_clk_get_rate(enum dss_clock clk);
 int dss_need_ctx_restore(void);
-const char *dss_get_generic_clk_source_name(enum dss_clk_source clk_src);
+const char *dss_get_generic_clk_source_name(enum omap_dss_clk_source clk_src);
 void dss_dump_clocks(struct seq_file *s);
 
 void dss_dump_regs(struct seq_file *s);
@@ -248,13 +239,14 @@ void dss_sdi_init(u8 datapairs);
 int dss_sdi_enable(void);
 void dss_sdi_disable(void);
 
-void dss_select_dispc_clk_source(enum dss_clk_source clk_src);
-void dss_select_dsi_clk_source(enum dss_clk_source clk_src);
+void dss_select_dispc_clk_source(enum omap_dss_clk_source clk_src);
+void dss_select_dsi_clk_source(int dsi_module,
+                enum omap_dss_clk_source clk_src);
 void dss_select_lcd_clk_source(enum omap_channel channel,
-                enum dss_clk_source clk_src);
-enum dss_clk_source dss_get_dispc_clk_source(void);
-enum dss_clk_source dss_get_dsi_clk_source(void);
-enum dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel);
+                enum omap_dss_clk_source clk_src);
+enum omap_dss_clk_source dss_get_dispc_clk_source(void);
+enum omap_dss_clk_source dss_get_dsi_clk_source(int dsi_module);
+enum omap_dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel);
 
 void dss_set_venc_output(enum omap_dss_venc_type type);
 void dss_set_dac_pwrdn_bgz(bool enable);
@@ -284,31 +276,39 @@ static inline void sdi_exit(void)
 
 /* DSI */
 #ifdef CONFIG_OMAP2_DSS_DSI
+
+struct dentry;
+struct file_operations;
+
 int dsi_init_platform_driver(void);
 void dsi_uninit_platform_driver(void);
 
 void dsi_dump_clocks(struct seq_file *s);
-void dsi_dump_irqs(struct seq_file *s);
-void dsi_dump_regs(struct seq_file *s);
+void dsi_create_debugfs_files_irq(struct dentry *debugfs_dir,
+                const struct file_operations *debug_fops);
+void dsi_create_debugfs_files_reg(struct dentry *debugfs_dir,
+                const struct file_operations *debug_fops);
 
 void dsi_save_context(void);
 void dsi_restore_context(void);
 
 int dsi_init_display(struct omap_dss_device *display);
 void dsi_irq_handler(void);
-unsigned long dsi_get_pll_hsdiv_dispc_rate(void);
-int dsi_pll_set_clock_div(struct dsi_clock_info *cinfo);
-int dsi_pll_calc_clock_div_pck(bool is_tft, unsigned long req_pck,
-                struct dsi_clock_info *cinfo,
+unsigned long dsi_get_pll_hsdiv_dispc_rate(struct platform_device *dsidev);
+int dsi_pll_set_clock_div(struct platform_device *dsidev,
+                struct dsi_clock_info *cinfo);
+int dsi_pll_calc_clock_div_pck(struct platform_device *dsidev, bool is_tft,
+                unsigned long req_pck, struct dsi_clock_info *cinfo,
                 struct dispc_clock_info *dispc_cinfo);
-int dsi_pll_init(struct omap_dss_device *dssdev, bool enable_hsclk,
+int dsi_pll_init(struct platform_device *dsidev, bool enable_hsclk,
                 bool enable_hsdiv);
-void dsi_pll_uninit(void);
+void dsi_pll_uninit(struct platform_device *dsidev, bool disconnect_lanes);
 void dsi_get_overlay_fifo_thresholds(enum omap_plane plane,
                 u32 fifo_size, enum omap_burst_size *burst_size,
                 u32 *fifo_low, u32 *fifo_high);
-void dsi_wait_pll_hsdiv_dispc_active(void);
-void dsi_wait_pll_hsdiv_dsi_active(void);
+void dsi_wait_pll_hsdiv_dispc_active(struct platform_device *dsidev);
+void dsi_wait_pll_hsdiv_dsi_active(struct platform_device *dsidev);
+struct platform_device *dsi_get_dsidev_from_id(int module);
 #else
 static inline int dsi_init_platform_driver(void)
 {
@@ -317,17 +317,47 @@ static inline int dsi_init_platform_driver(void)
 static inline void dsi_uninit_platform_driver(void)
 {
 }
-static inline unsigned long dsi_get_pll_hsdiv_dispc_rate(void)
+static inline unsigned long dsi_get_pll_hsdiv_dispc_rate(struct platform_device *dsidev)
 {
         WARN("%s: DSI not compiled in, returning rate as 0\n", __func__);
         return 0;
 }
-static inline void dsi_wait_pll_hsdiv_dispc_active(void)
+static inline int dsi_pll_set_clock_div(struct platform_device *dsidev,
+                struct dsi_clock_info *cinfo)
+{
+        WARN("%s: DSI not compiled in\n", __func__);
+        return -ENODEV;
+}
+static inline int dsi_pll_calc_clock_div_pck(struct platform_device *dsidev,
+                bool is_tft, unsigned long req_pck,
+                struct dsi_clock_info *dsi_cinfo,
+                struct dispc_clock_info *dispc_cinfo)
+{
+        WARN("%s: DSI not compiled in\n", __func__);
+        return -ENODEV;
+}
+static inline int dsi_pll_init(struct platform_device *dsidev,
+                bool enable_hsclk, bool enable_hsdiv)
 {
+        WARN("%s: DSI not compiled in\n", __func__);
+        return -ENODEV;
 }
-static inline void dsi_wait_pll_hsdiv_dsi_active(void)
+static inline void dsi_pll_uninit(struct platform_device *dsidev,
+                bool disconnect_lanes)
 {
 }
+static inline void dsi_wait_pll_hsdiv_dispc_active(struct platform_device *dsidev)
+{
+}
+static inline void dsi_wait_pll_hsdiv_dsi_active(struct platform_device *dsidev)
+{
+}
+static inline struct platform_device *dsi_get_dsidev_from_id(int module)
+{
+        WARN("%s: DSI not compiled in, returning platform device as NULL\n",
+                        __func__);
+        return NULL;
+}
 #endif
 
 /* DPI */
@@ -391,7 +421,8 @@ int dispc_setup_plane(enum omap_plane plane,
                       enum omap_dss_rotation_type rotation_type,
                       u8 rotation, bool mirror,
                       u8 global_alpha, u8 pre_mult_alpha,
-                      enum omap_channel channel);
+                      enum omap_channel channel,
+                      u32 puv_addr);
 
 bool dispc_go_busy(enum omap_channel channel);
 void dispc_go(enum omap_channel channel);
@@ -485,13 +516,6 @@ void hdmi_panel_exit(void);
 int rfbi_init_platform_driver(void);
 void rfbi_uninit_platform_driver(void);
 void rfbi_dump_regs(struct seq_file *s);
-
-int rfbi_configure(int rfbi_module, int bpp, int lines);
-void rfbi_enable_rfbi(bool enable);
-void rfbi_transfer_area(struct omap_dss_device *dssdev, u16 width,
-                u16 height, void (callback)(void *data), void *data);
-void rfbi_set_timings(int rfbi_module, struct rfbi_timings *t);
-unsigned long rfbi_get_max_tx_rate(void);
 int rfbi_init_display(struct omap_dss_device *display);
 #else
 static inline int rfbi_init_platform_driver(void)
diff --git a/drivers/video/omap2/dss/dss_features.c b/drivers/video/omap2/dss/dss_features.c
index aa1622241d0d..1c18888e5df3 100644
--- a/drivers/video/omap2/dss/dss_features.c
+++ b/drivers/video/omap2/dss/dss_features.c
@@ -22,7 +22,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/cpu.h>
 
 #include "dss.h"
@@ -52,7 +52,7 @@ struct omap_dss_features {
 };
 
 /* This struct is assigned to one of the below during initialization */
-static struct omap_dss_features *omap_current_dss_features;
+static const struct omap_dss_features *omap_current_dss_features;
 
 static const struct dss_reg_field omap2_dss_reg_fields[] = {
         [FEAT_REG_FIRHINC]                      = { 11, 0 },
@@ -177,22 +177,55 @@ static const enum omap_color_mode omap3_dss_supported_color_modes[] = {
         OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_RGBX32,
 };
 
+static const enum omap_color_mode omap4_dss_supported_color_modes[] = {
+        /* OMAP_DSS_GFX */
+        OMAP_DSS_COLOR_CLUT1 | OMAP_DSS_COLOR_CLUT2 |
+        OMAP_DSS_COLOR_CLUT4 | OMAP_DSS_COLOR_CLUT8 |
+        OMAP_DSS_COLOR_RGB12U | OMAP_DSS_COLOR_ARGB16 |
+        OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB24U |
+        OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_ARGB32 |
+        OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_RGBX32 |
+        OMAP_DSS_COLOR_ARGB16_1555,
+
+        /* OMAP_DSS_VIDEO1 */
+        OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB12U |
+        OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_ARGB16_1555 |
+        OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_NV12 |
+        OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_RGB24U |
+        OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_UYVY |
+        OMAP_DSS_COLOR_ARGB16 | OMAP_DSS_COLOR_XRGB16_1555 |
+        OMAP_DSS_COLOR_ARGB32 | OMAP_DSS_COLOR_RGBX16 |
+        OMAP_DSS_COLOR_RGBX32,
+
+       /* OMAP_DSS_VIDEO2 */
+        OMAP_DSS_COLOR_RGB16 | OMAP_DSS_COLOR_RGB12U |
+        OMAP_DSS_COLOR_YUV2 | OMAP_DSS_COLOR_ARGB16_1555 |
+        OMAP_DSS_COLOR_RGBA32 | OMAP_DSS_COLOR_NV12 |
+        OMAP_DSS_COLOR_RGBA16 | OMAP_DSS_COLOR_RGB24U |
+        OMAP_DSS_COLOR_RGB24P | OMAP_DSS_COLOR_UYVY |
+        OMAP_DSS_COLOR_ARGB16 | OMAP_DSS_COLOR_XRGB16_1555 |
+        OMAP_DSS_COLOR_ARGB32 | OMAP_DSS_COLOR_RGBX16 |
+        OMAP_DSS_COLOR_RGBX32,
+};
+
 static const char * const omap2_dss_clk_source_names[] = {
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]       = "N/A",
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]         = "N/A",
-        [DSS_CLK_SRC_FCK]                       = "DSS_FCLK1",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]  = "N/A",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]    = "N/A",
+        [OMAP_DSS_CLK_SRC_FCK]                  = "DSS_FCLK1",
 };
 
 static const char * const omap3_dss_clk_source_names[] = {
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]       = "DSI1_PLL_FCLK",
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]         = "DSI2_PLL_FCLK",
-        [DSS_CLK_SRC_FCK]                       = "DSS1_ALWON_FCLK",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]  = "DSI1_PLL_FCLK",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]    = "DSI2_PLL_FCLK",
+        [OMAP_DSS_CLK_SRC_FCK]                  = "DSS1_ALWON_FCLK",
 };
 
 static const char * const omap4_dss_clk_source_names[] = {
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]       = "PLL1_CLK1",
-        [DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]         = "PLL1_CLK2",
-        [DSS_CLK_SRC_FCK]                       = "DSS_FCLK",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]  = "PLL1_CLK1",
+        [OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]    = "PLL1_CLK2",
+        [OMAP_DSS_CLK_SRC_FCK]                  = "DSS_FCLK",
+        [OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC] = "PLL2_CLK1",
+        [OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI]   = "PLL2_CLK2",
 };
 
 static const struct dss_param_range omap2_dss_param_range[] = {
@@ -226,7 +259,7 @@ static const struct dss_param_range omap4_dss_param_range[] = {
 };
 
 /* OMAP2 DSS Features */
-static struct omap_dss_features omap2_dss_features = {
+static const struct omap_dss_features omap2_dss_features = {
         .reg_fields = omap2_dss_reg_fields,
         .num_reg_fields = ARRAY_SIZE(omap2_dss_reg_fields),
 
@@ -244,7 +277,7 @@ static struct omap_dss_features omap2_dss_features = {
 };
 
 /* OMAP3 DSS Features */
-static struct omap_dss_features omap3430_dss_features = {
+static const struct omap_dss_features omap3430_dss_features = {
         .reg_fields = omap3_dss_reg_fields,
         .num_reg_fields = ARRAY_SIZE(omap3_dss_reg_fields),
 
@@ -252,7 +285,8 @@ static struct omap_dss_features omap3430_dss_features = {
                 FEAT_GLOBAL_ALPHA | FEAT_LCDENABLEPOL |
                 FEAT_LCDENABLESIGNAL | FEAT_PCKFREEENABLE |
                 FEAT_FUNCGATED | FEAT_ROWREPEATENABLE |
-                FEAT_LINEBUFFERSPLIT | FEAT_RESIZECONF,
+                FEAT_LINEBUFFERSPLIT | FEAT_RESIZECONF |
+                FEAT_DSI_PLL_FREQSEL | FEAT_DSI_REVERSE_TXCLKESC,
 
         .num_mgrs = 2,
         .num_ovls = 3,
@@ -262,7 +296,7 @@ static struct omap_dss_features omap3430_dss_features = {
         .dss_params = omap3_dss_param_range,
 };
 
-static struct omap_dss_features omap3630_dss_features = {
+static const struct omap_dss_features omap3630_dss_features = {
         .reg_fields = omap3_dss_reg_fields,
         .num_reg_fields = ARRAY_SIZE(omap3_dss_reg_fields),
 
@@ -271,7 +305,8 @@ static struct omap_dss_features omap3630_dss_features = {
                 FEAT_LCDENABLESIGNAL | FEAT_PCKFREEENABLE |
                 FEAT_PRE_MULT_ALPHA | FEAT_FUNCGATED |
                 FEAT_ROWREPEATENABLE | FEAT_LINEBUFFERSPLIT |
-                FEAT_RESIZECONF,
+                FEAT_RESIZECONF | FEAT_DSI_PLL_PWR_BUG |
+                FEAT_DSI_PLL_FREQSEL,
 
         .num_mgrs = 2,
         .num_ovls = 3,
@@ -282,19 +317,43 @@ static struct omap_dss_features omap3630_dss_features = {
 };
 
 /* OMAP4 DSS Features */
-static struct omap_dss_features omap4_dss_features = {
+/* For OMAP4430 ES 1.0 revision */
+static const struct omap_dss_features omap4430_es1_0_dss_features  = {
         .reg_fields = omap4_dss_reg_fields,
         .num_reg_fields = ARRAY_SIZE(omap4_dss_reg_fields),
 
         .has_feature    =
                 FEAT_GLOBAL_ALPHA | FEAT_PRE_MULT_ALPHA |
                 FEAT_MGR_LCD2 | FEAT_GLOBAL_ALPHA_VID1 |
-                FEAT_CORE_CLK_DIV | FEAT_LCD_CLK_SRC,
+                FEAT_CORE_CLK_DIV | FEAT_LCD_CLK_SRC |
+                FEAT_DSI_DCS_CMD_CONFIG_VC | FEAT_DSI_VC_OCP_WIDTH |
+                FEAT_DSI_GNQ | FEAT_HANDLE_UV_SEPARATE | FEAT_ATTR2,
 
         .num_mgrs = 3,
         .num_ovls = 3,
         .supported_displays = omap4_dss_supported_displays,
-        .supported_color_modes = omap3_dss_supported_color_modes,
+        .supported_color_modes = omap4_dss_supported_color_modes,
+        .clksrc_names = omap4_dss_clk_source_names,
+        .dss_params = omap4_dss_param_range,
+};
+
+/* For all the other OMAP4 versions */
+static const struct omap_dss_features omap4_dss_features = {
+        .reg_fields = omap4_dss_reg_fields,
+        .num_reg_fields = ARRAY_SIZE(omap4_dss_reg_fields),
+
+        .has_feature    =
+                FEAT_GLOBAL_ALPHA | FEAT_PRE_MULT_ALPHA |
+                FEAT_MGR_LCD2 | FEAT_GLOBAL_ALPHA_VID1 |
+                FEAT_CORE_CLK_DIV | FEAT_LCD_CLK_SRC |
+                FEAT_DSI_DCS_CMD_CONFIG_VC | FEAT_DSI_VC_OCP_WIDTH |
+                FEAT_DSI_GNQ | FEAT_HDMI_CTS_SWMODE |
+                FEAT_HANDLE_UV_SEPARATE | FEAT_ATTR2,
+
+        .num_mgrs = 3,
+        .num_ovls = 3,
+        .supported_displays = omap4_dss_supported_displays,
+        .supported_color_modes = omap4_dss_supported_color_modes,
         .clksrc_names = omap4_dss_clk_source_names,
         .dss_params = omap4_dss_param_range,
 };
@@ -337,7 +396,7 @@ bool dss_feat_color_mode_supported(enum omap_plane plane,
                         color_mode;
 }
 
-const char *dss_feat_get_clk_source_name(enum dss_clk_source id)
+const char *dss_feat_get_clk_source_name(enum omap_dss_clk_source id)
 {
         return omap_current_dss_features->clksrc_names[id];
 }
@@ -365,6 +424,10 @@ void dss_features_init(void)
                 omap_current_dss_features = &omap3630_dss_features;
         else if (cpu_is_omap34xx())
                 omap_current_dss_features = &omap3430_dss_features;
-        else
+        else if (omap_rev() == OMAP4430_REV_ES1_0)
+                omap_current_dss_features = &omap4430_es1_0_dss_features;
+        else if (cpu_is_omap44xx())
                 omap_current_dss_features = &omap4_dss_features;
+        else
+                DSSWARN("Unsupported OMAP version");
 }
diff --git a/drivers/video/omap2/dss/dss_features.h b/drivers/video/omap2/dss/dss_features.h
index 12e9c4ef0dec..07b346f7d916 100644
--- a/drivers/video/omap2/dss/dss_features.h
+++ b/drivers/video/omap2/dss/dss_features.h
@@ -23,23 +23,34 @@
 #define MAX_DSS_MANAGERS        3
 #define MAX_DSS_OVERLAYS        3
 #define MAX_DSS_LCD_MANAGERS    2
+#define MAX_NUM_DSI             2
 
 /* DSS has feature id */
 enum dss_feat_id {
-        FEAT_GLOBAL_ALPHA       = 1 << 0,
-        FEAT_GLOBAL_ALPHA_VID1  = 1 << 1,
-        FEAT_PRE_MULT_ALPHA     = 1 << 2,
-        FEAT_LCDENABLEPOL       = 1 << 3,
-        FEAT_LCDENABLESIGNAL    = 1 << 4,
-        FEAT_PCKFREEENABLE      = 1 << 5,
-        FEAT_FUNCGATED          = 1 << 6,
-        FEAT_MGR_LCD2           = 1 << 7,
-        FEAT_LINEBUFFERSPLIT    = 1 << 8,
-        FEAT_ROWREPEATENABLE    = 1 << 9,
-        FEAT_RESIZECONF         = 1 << 10,
+        FEAT_GLOBAL_ALPHA               = 1 << 0,
+        FEAT_GLOBAL_ALPHA_VID1          = 1 << 1,
+        FEAT_PRE_MULT_ALPHA             = 1 << 2,
+        FEAT_LCDENABLEPOL               = 1 << 3,
+        FEAT_LCDENABLESIGNAL            = 1 << 4,
+        FEAT_PCKFREEENABLE              = 1 << 5,
+        FEAT_FUNCGATED                  = 1 << 6,
+        FEAT_MGR_LCD2                   = 1 << 7,
+        FEAT_LINEBUFFERSPLIT            = 1 << 8,
+        FEAT_ROWREPEATENABLE            = 1 << 9,
+        FEAT_RESIZECONF                 = 1 << 10,
         /* Independent core clk divider */
-        FEAT_CORE_CLK_DIV       = 1 << 11,
-        FEAT_LCD_CLK_SRC        = 1 << 12,
+        FEAT_CORE_CLK_DIV               = 1 << 11,
+        FEAT_LCD_CLK_SRC                = 1 << 12,
+        /* DSI-PLL power command 0x3 is not working */
+        FEAT_DSI_PLL_PWR_BUG            = 1 << 13,
+        FEAT_DSI_PLL_FREQSEL            = 1 << 14,
+        FEAT_DSI_DCS_CMD_CONFIG_VC      = 1 << 15,
+        FEAT_DSI_VC_OCP_WIDTH           = 1 << 16,
+        FEAT_DSI_REVERSE_TXCLKESC       = 1 << 17,
+        FEAT_DSI_GNQ                    = 1 << 18,
+        FEAT_HDMI_CTS_SWMODE            = 1 << 19,
+        FEAT_HANDLE_UV_SEPARATE         = 1 << 20,
+        FEAT_ATTR2                      = 1 << 21,
 };
 
 /* DSS register field id */
@@ -77,7 +88,7 @@ enum omap_display_type dss_feat_get_supported_displays(enum omap_channel channel
 enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane);
 bool dss_feat_color_mode_supported(enum omap_plane plane,
                 enum omap_color_mode color_mode);
-const char *dss_feat_get_clk_source_name(enum dss_clk_source id);
+const char *dss_feat_get_clk_source_name(enum omap_dss_clk_source id);
 
 bool dss_has_feature(enum dss_feat_id id);
 void dss_feat_get_reg_field(enum dss_feat_reg_field id, u8 *start, u8 *end);
diff --git a/drivers/video/omap2/dss/hdmi.c b/drivers/video/omap2/dss/hdmi.c
index a981def8099a..b0555f4f0a78 100644
--- a/drivers/video/omap2/dss/hdmi.c
+++ b/drivers/video/omap2/dss/hdmi.c
@@ -29,10 +29,16 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/string.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
+#if defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI) || \
+        defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI_MODULE)
+#include <sound/soc.h>
+#include <sound/pcm_params.h>
+#endif
 
 #include "dss.h"
 #include "hdmi.h"
+#include "dss_features.h"
 
 static struct {
         struct mutex lock;
@@ -1052,25 +1058,26 @@ static void update_hdmi_timings(struct hdmi_config *cfg,
         cfg->timings.hsync_pol = cea_vesa_timings[code].hsync_pol;
 }
 
-static void hdmi_compute_pll(unsigned long clkin, int phy,
-        int n, struct hdmi_pll_info *pi)
+static void hdmi_compute_pll(struct omap_dss_device *dssdev, int phy,
+                struct hdmi_pll_info *pi)
 {
-        unsigned long refclk;
+        unsigned long clkin, refclk;
         u32 mf;
 
+        clkin = dss_clk_get_rate(DSS_CLK_SYSCK) / 10000;
         /*
          * Input clock is predivided by N + 1
          * out put of which is reference clk
          */
-        refclk = clkin / (n + 1);
-        pi->regn = n;
+        pi->regn = dssdev->clocks.hdmi.regn;
+        refclk = clkin / (pi->regn + 1);
 
         /*
          * multiplier is pixel_clk/ref_clk
          * Multiplying by 100 to avoid fractional part removal
          */
-        pi->regm = (phy * 100/(refclk))/100;
-        pi->regm2 = 1;
+        pi->regm = (phy * 100 / (refclk)) / 100;
+        pi->regm2 = dssdev->clocks.hdmi.regm2;
 
         /*
          * fractional multiplier is remainder of the difference between
@@ -1078,14 +1085,14 @@ static void hdmi_compute_pll(unsigned long clkin, int phy,
          * multiplied by 2^18(262144) divided by the reference clock
          */
         mf = (phy - pi->regm * refclk) * 262144;
-        pi->regmf = mf/(refclk);
+        pi->regmf = mf / (refclk);
 
         /*
          * Dcofreq should be set to 1 if required pixel clock
          * is greater than 1000MHz
          */
         pi->dcofreq = phy > 1000 * 100;
-        pi->regsd = ((pi->regm * clkin / 10) / ((n + 1) * 250) + 5) / 10;
+        pi->regsd = ((pi->regm * clkin / 10) / ((pi->regn + 1) * 250) + 5) / 10;
 
         DSSDBG("M = %d Mf = %d\n", pi->regm, pi->regmf);
         DSSDBG("range = %d sd = %d\n", pi->dcofreq, pi->regsd);
@@ -1106,7 +1113,7 @@ static int hdmi_power_on(struct omap_dss_device *dssdev)
         int r, code = 0;
         struct hdmi_pll_info pll_data;
         struct omap_video_timings *p;
-        int clkin, n, phy;
+        unsigned long phy;
 
         hdmi_enable_clocks(1);
 
@@ -1126,11 +1133,9 @@ static int hdmi_power_on(struct omap_dss_device *dssdev)
         dssdev->panel.timings = cea_vesa_timings[code].timings;
         update_hdmi_timings(&hdmi.cfg, p, code);
 
-        clkin = 3840; /* 38.4 MHz */
-        n = 15; /* this is a constant for our math */
         phy = p->pixel_clock;
 
-        hdmi_compute_pll(clkin, phy, n, &pll_data);
+        hdmi_compute_pll(dssdev, phy, &pll_data);
 
         hdmi_wp_video_start(0);
 
@@ -1160,7 +1165,7 @@ static int hdmi_power_on(struct omap_dss_device *dssdev)
          * dynamically by user. This can be moved to single location , say
          * Boardfile.
          */
-        dss_select_dispc_clk_source(DSS_CLK_SRC_FCK);
+        dss_select_dispc_clk_source(dssdev->clocks.dispc.dispc_fclk_src);
 
         /* bypass TV gamma table */
         dispc_enable_gamma_table(0);
@@ -1275,10 +1280,420 @@ void omapdss_hdmi_display_disable(struct omap_dss_device *dssdev)
         mutex_unlock(&hdmi.lock);
 }
 
+#if defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI) || \
+        defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI_MODULE)
+static void hdmi_wp_audio_config_format(
+                struct hdmi_audio_format *aud_fmt)
+{
+        u32 r;
+
+        DSSDBG("Enter hdmi_wp_audio_config_format\n");
+
+        r = hdmi_read_reg(HDMI_WP_AUDIO_CFG);
+        r = FLD_MOD(r, aud_fmt->stereo_channels, 26, 24);
+        r = FLD_MOD(r, aud_fmt->active_chnnls_msk, 23, 16);
+        r = FLD_MOD(r, aud_fmt->en_sig_blk_strt_end, 5, 5);
+        r = FLD_MOD(r, aud_fmt->type, 4, 4);
+        r = FLD_MOD(r, aud_fmt->justification, 3, 3);
+        r = FLD_MOD(r, aud_fmt->sample_order, 2, 2);
+        r = FLD_MOD(r, aud_fmt->samples_per_word, 1, 1);
+        r = FLD_MOD(r, aud_fmt->sample_size, 0, 0);
+        hdmi_write_reg(HDMI_WP_AUDIO_CFG, r);
+}
+
+static void hdmi_wp_audio_config_dma(struct hdmi_audio_dma *aud_dma)
+{
+        u32 r;
+
+        DSSDBG("Enter hdmi_wp_audio_config_dma\n");
+
+        r = hdmi_read_reg(HDMI_WP_AUDIO_CFG2);
+        r = FLD_MOD(r, aud_dma->transfer_size, 15, 8);
+        r = FLD_MOD(r, aud_dma->block_size, 7, 0);
+        hdmi_write_reg(HDMI_WP_AUDIO_CFG2, r);
+
+        r = hdmi_read_reg(HDMI_WP_AUDIO_CTRL);
+        r = FLD_MOD(r, aud_dma->mode, 9, 9);
+        r = FLD_MOD(r, aud_dma->fifo_threshold, 8, 0);
+        hdmi_write_reg(HDMI_WP_AUDIO_CTRL, r);
+}
+
+static void hdmi_core_audio_config(struct hdmi_core_audio_config *cfg)
+{
+        u32 r;
+
+        /* audio clock recovery parameters */
+        r = hdmi_read_reg(HDMI_CORE_AV_ACR_CTRL);
+        r = FLD_MOD(r, cfg->use_mclk, 2, 2);
+        r = FLD_MOD(r, cfg->en_acr_pkt, 1, 1);
+        r = FLD_MOD(r, cfg->cts_mode, 0, 0);
+        hdmi_write_reg(HDMI_CORE_AV_ACR_CTRL, r);
+
+        REG_FLD_MOD(HDMI_CORE_AV_N_SVAL1, cfg->n, 7, 0);
+        REG_FLD_MOD(HDMI_CORE_AV_N_SVAL2, cfg->n >> 8, 7, 0);
+        REG_FLD_MOD(HDMI_CORE_AV_N_SVAL3, cfg->n >> 16, 7, 0);
+
+        if (cfg->cts_mode == HDMI_AUDIO_CTS_MODE_SW) {
+                REG_FLD_MOD(HDMI_CORE_AV_CTS_SVAL1, cfg->cts, 7, 0);
+                REG_FLD_MOD(HDMI_CORE_AV_CTS_SVAL2, cfg->cts >> 8, 7, 0);
+                REG_FLD_MOD(HDMI_CORE_AV_CTS_SVAL3, cfg->cts >> 16, 7, 0);
+        } else {
+                /*
+                 * HDMI IP uses this configuration to divide the MCLK to
+                 * update CTS value.
+                 */
+                REG_FLD_MOD(HDMI_CORE_AV_FREQ_SVAL, cfg->mclk_mode, 2, 0);
+
+                /* Configure clock for audio packets */
+                REG_FLD_MOD(HDMI_CORE_AV_AUD_PAR_BUSCLK_1,
+                        cfg->aud_par_busclk, 7, 0);
+                REG_FLD_MOD(HDMI_CORE_AV_AUD_PAR_BUSCLK_2,
+                        (cfg->aud_par_busclk >> 8), 7, 0);
+                REG_FLD_MOD(HDMI_CORE_AV_AUD_PAR_BUSCLK_3,
+                        (cfg->aud_par_busclk >> 16), 7, 0);
+        }
+
+        /* Override of SPDIF sample frequency with value in I2S_CHST4 */
+        REG_FLD_MOD(HDMI_CORE_AV_SPDIF_CTRL, cfg->fs_override, 1, 1);
+
+        /* I2S parameters */
+        REG_FLD_MOD(HDMI_CORE_AV_I2S_CHST4, cfg->freq_sample, 3, 0);
+
+        r = hdmi_read_reg(HDMI_CORE_AV_I2S_IN_CTRL);
+        r = FLD_MOD(r, cfg->i2s_cfg.en_high_bitrate_aud, 7, 7);
+        r = FLD_MOD(r, cfg->i2s_cfg.sck_edge_mode, 6, 6);
+        r = FLD_MOD(r, cfg->i2s_cfg.cbit_order, 5, 5);
+        r = FLD_MOD(r, cfg->i2s_cfg.vbit, 4, 4);
+        r = FLD_MOD(r, cfg->i2s_cfg.ws_polarity, 3, 3);
+        r = FLD_MOD(r, cfg->i2s_cfg.justification, 2, 2);
+        r = FLD_MOD(r, cfg->i2s_cfg.direction, 1, 1);
+        r = FLD_MOD(r, cfg->i2s_cfg.shift, 0, 0);
+        hdmi_write_reg(HDMI_CORE_AV_I2S_IN_CTRL, r);
+
+        r = hdmi_read_reg(HDMI_CORE_AV_I2S_CHST5);
+        r = FLD_MOD(r, cfg->freq_sample, 7, 4);
+        r = FLD_MOD(r, cfg->i2s_cfg.word_length, 3, 1);
+        r = FLD_MOD(r, cfg->i2s_cfg.word_max_length, 0, 0);
+        hdmi_write_reg(HDMI_CORE_AV_I2S_CHST5, r);
+
+        REG_FLD_MOD(HDMI_CORE_AV_I2S_IN_LEN, cfg->i2s_cfg.in_length_bits, 3, 0);
+
+        /* Audio channels and mode parameters */
+        REG_FLD_MOD(HDMI_CORE_AV_HDMI_CTRL, cfg->layout, 2, 1);
+        r = hdmi_read_reg(HDMI_CORE_AV_AUD_MODE);
+        r = FLD_MOD(r, cfg->i2s_cfg.active_sds, 7, 4);
+        r = FLD_MOD(r, cfg->en_dsd_audio, 3, 3);
+        r = FLD_MOD(r, cfg->en_parallel_aud_input, 2, 2);
+        r = FLD_MOD(r, cfg->en_spdif, 1, 1);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_MODE, r);
+}
+
+static void hdmi_core_audio_infoframe_config(
+                struct hdmi_core_infoframe_audio *info_aud)
+{
+        u8 val;
+        u8 sum = 0, checksum = 0;
+
+        /*
+         * Set audio info frame type, version and length as
+         * described in HDMI 1.4a Section 8.2.2 specification.
+         * Checksum calculation is defined in Section 5.3.5.
+         */
+        hdmi_write_reg(HDMI_CORE_AV_AUDIO_TYPE, 0x84);
+        hdmi_write_reg(HDMI_CORE_AV_AUDIO_VERS, 0x01);
+        hdmi_write_reg(HDMI_CORE_AV_AUDIO_LEN, 0x0a);
+        sum += 0x84 + 0x001 + 0x00a;
+
+        val = (info_aud->db1_coding_type << 4)
+                        | (info_aud->db1_channel_count - 1);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(0), val);
+        sum += val;
+
+        val = (info_aud->db2_sample_freq << 2) | info_aud->db2_sample_size;
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(1), val);
+        sum += val;
+
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(2), 0x00);
+
+        val = info_aud->db4_channel_alloc;
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(3), val);
+        sum += val;
+
+        val = (info_aud->db5_downmix_inh << 7) | (info_aud->db5_lsv << 3);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(4), val);
+        sum += val;
+
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(5), 0x00);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(6), 0x00);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(7), 0x00);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(8), 0x00);
+        hdmi_write_reg(HDMI_CORE_AV_AUD_DBYTE(9), 0x00);
+
+        checksum = 0x100 - sum;
+        hdmi_write_reg(HDMI_CORE_AV_AUDIO_CHSUM, checksum);
+
+        /*
+         * TODO: Add MPEG and SPD enable and repeat cfg when EDID parsing
+         * is available.
+         */
+}
+
+static int hdmi_config_audio_acr(u32 sample_freq, u32 *n, u32 *cts)
+{
+        u32 r;
+        u32 deep_color = 0;
+        u32 pclk = hdmi.cfg.timings.timings.pixel_clock;
+
+        if (n == NULL || cts == NULL)
+                return -EINVAL;
+        /*
+         * Obtain current deep color configuration. This needed
+         * to calculate the TMDS clock based on the pixel clock.
+         */
+        r = REG_GET(HDMI_WP_VIDEO_CFG, 1, 0);
+        switch (r) {
+        case 1: /* No deep color selected */
+                deep_color = 100;
+                break;
+        case 2: /* 10-bit deep color selected */
+                deep_color = 125;
+                break;
+        case 3: /* 12-bit deep color selected */
+                deep_color = 150;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        switch (sample_freq) {
+        case 32000:
+                if ((deep_color == 125) && ((pclk == 54054)
+                                || (pclk == 74250)))
+                        *n = 8192;
+                else
+                        *n = 4096;
+                break;
+        case 44100:
+                *n = 6272;
+                break;
+        case 48000:
+                if ((deep_color == 125) && ((pclk == 54054)
+                                || (pclk == 74250)))
+                        *n = 8192;
+                else
+                        *n = 6144;
+                break;
+        default:
+                *n = 0;
+                return -EINVAL;
+        }
+
+        /* Calculate CTS. See HDMI 1.3a or 1.4a specifications */
+        *cts = pclk * (*n / 128) * deep_color / (sample_freq / 10);
+
+        return 0;
+}
+
+static int hdmi_audio_hw_params(struct snd_pcm_substream *substream,
+                                    struct snd_pcm_hw_params *params,
+                                    struct snd_soc_dai *dai)
+{
+        struct hdmi_audio_format audio_format;
+        struct hdmi_audio_dma audio_dma;
+        struct hdmi_core_audio_config core_cfg;
+        struct hdmi_core_infoframe_audio aud_if_cfg;
+        int err, n, cts;
+        enum hdmi_core_audio_sample_freq sample_freq;
+
+        switch (params_format(params)) {
+        case SNDRV_PCM_FORMAT_S16_LE:
+                core_cfg.i2s_cfg.word_max_length =
+                        HDMI_AUDIO_I2S_MAX_WORD_20BITS;
+                core_cfg.i2s_cfg.word_length = HDMI_AUDIO_I2S_CHST_WORD_16_BITS;
+                core_cfg.i2s_cfg.in_length_bits =
+                        HDMI_AUDIO_I2S_INPUT_LENGTH_16;
+                core_cfg.i2s_cfg.justification = HDMI_AUDIO_JUSTIFY_LEFT;
+                audio_format.samples_per_word = HDMI_AUDIO_ONEWORD_TWOSAMPLES;
+                audio_format.sample_size = HDMI_AUDIO_SAMPLE_16BITS;
+                audio_format.justification = HDMI_AUDIO_JUSTIFY_LEFT;
+                audio_dma.transfer_size = 0x10;
+                break;
+        case SNDRV_PCM_FORMAT_S24_LE:
+                core_cfg.i2s_cfg.word_max_length =
+                        HDMI_AUDIO_I2S_MAX_WORD_24BITS;
+                core_cfg.i2s_cfg.word_length = HDMI_AUDIO_I2S_CHST_WORD_24_BITS;
+                core_cfg.i2s_cfg.in_length_bits =
+                        HDMI_AUDIO_I2S_INPUT_LENGTH_24;
+                audio_format.samples_per_word = HDMI_AUDIO_ONEWORD_ONESAMPLE;
+                audio_format.sample_size = HDMI_AUDIO_SAMPLE_24BITS;
+                audio_format.justification = HDMI_AUDIO_JUSTIFY_RIGHT;
+                core_cfg.i2s_cfg.justification = HDMI_AUDIO_JUSTIFY_RIGHT;
+                audio_dma.transfer_size = 0x20;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        switch (params_rate(params)) {
+        case 32000:
+                sample_freq = HDMI_AUDIO_FS_32000;
+                break;
+        case 44100:
+                sample_freq = HDMI_AUDIO_FS_44100;
+                break;
+        case 48000:
+                sample_freq = HDMI_AUDIO_FS_48000;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        err = hdmi_config_audio_acr(params_rate(params), &n, &cts);
+        if (err < 0)
+                return err;
+
+        /* Audio wrapper config */
+        audio_format.stereo_channels = HDMI_AUDIO_STEREO_ONECHANNEL;
+        audio_format.active_chnnls_msk = 0x03;
+        audio_format.type = HDMI_AUDIO_TYPE_LPCM;
+        audio_format.sample_order = HDMI_AUDIO_SAMPLE_LEFT_FIRST;
+        /* Disable start/stop signals of IEC 60958 blocks */
+        audio_format.en_sig_blk_strt_end = HDMI_AUDIO_BLOCK_SIG_STARTEND_OFF;
+
+        audio_dma.block_size = 0xC0;
+        audio_dma.mode = HDMI_AUDIO_TRANSF_DMA;
+        audio_dma.fifo_threshold = 0x20; /* in number of samples */
+
+        hdmi_wp_audio_config_dma(&audio_dma);
+        hdmi_wp_audio_config_format(&audio_format);
+
+        /*
+         * I2S config
+         */
+        core_cfg.i2s_cfg.en_high_bitrate_aud = false;
+        /* Only used with high bitrate audio */
+        core_cfg.i2s_cfg.cbit_order = false;
+        /* Serial data and word select should change on sck rising edge */
+        core_cfg.i2s_cfg.sck_edge_mode = HDMI_AUDIO_I2S_SCK_EDGE_RISING;
+        core_cfg.i2s_cfg.vbit = HDMI_AUDIO_I2S_VBIT_FOR_PCM;
+        /* Set I2S word select polarity */
+        core_cfg.i2s_cfg.ws_polarity = HDMI_AUDIO_I2S_WS_POLARITY_LOW_IS_LEFT;
+        core_cfg.i2s_cfg.direction = HDMI_AUDIO_I2S_MSB_SHIFTED_FIRST;
+        /* Set serial data to word select shift. See Phillips spec. */
+        core_cfg.i2s_cfg.shift = HDMI_AUDIO_I2S_FIRST_BIT_SHIFT;
+        /* Enable one of the four available serial data channels */
+        core_cfg.i2s_cfg.active_sds = HDMI_AUDIO_I2S_SD0_EN;
+
+        /* Core audio config */
+        core_cfg.freq_sample = sample_freq;
+        core_cfg.n = n;
+        core_cfg.cts = cts;
+        if (dss_has_feature(FEAT_HDMI_CTS_SWMODE)) {
+                core_cfg.aud_par_busclk = 0;
+                core_cfg.cts_mode = HDMI_AUDIO_CTS_MODE_SW;
+                core_cfg.use_mclk = false;
+        } else {
+                core_cfg.aud_par_busclk = (((128 * 31) - 1) << 8);
+                core_cfg.cts_mode = HDMI_AUDIO_CTS_MODE_HW;
+                core_cfg.use_mclk = true;
+                core_cfg.mclk_mode = HDMI_AUDIO_MCLK_128FS;
+        }
+        core_cfg.layout = HDMI_AUDIO_LAYOUT_2CH;
+        core_cfg.en_spdif = false;
+        /* Use sample frequency from channel status word */
+        core_cfg.fs_override = true;
+        /* Enable ACR packets */
+        core_cfg.en_acr_pkt = true;
+        /* Disable direct streaming digital audio */
+        core_cfg.en_dsd_audio = false;
+        /* Use parallel audio interface */
+        core_cfg.en_parallel_aud_input = true;
+
+        hdmi_core_audio_config(&core_cfg);
+
+        /*
+         * Configure packet
+         * info frame audio see doc CEA861-D page 74
+         */
+        aud_if_cfg.db1_coding_type = HDMI_INFOFRAME_AUDIO_DB1CT_FROM_STREAM;
+        aud_if_cfg.db1_channel_count = 2;
+        aud_if_cfg.db2_sample_freq = HDMI_INFOFRAME_AUDIO_DB2SF_FROM_STREAM;
+        aud_if_cfg.db2_sample_size = HDMI_INFOFRAME_AUDIO_DB2SS_FROM_STREAM;
+        aud_if_cfg.db4_channel_alloc = 0x00;
+        aud_if_cfg.db5_downmix_inh = false;
+        aud_if_cfg.db5_lsv = 0;
+
+        hdmi_core_audio_infoframe_config(&aud_if_cfg);
+        return 0;
+}
+
+static int hdmi_audio_trigger(struct snd_pcm_substream *substream, int cmd,
+                                  struct snd_soc_dai *dai)
+{
+        int err = 0;
+        switch (cmd) {
+        case SNDRV_PCM_TRIGGER_START:
+        case SNDRV_PCM_TRIGGER_RESUME:
+        case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+                REG_FLD_MOD(HDMI_CORE_AV_AUD_MODE, 1, 0, 0);
+                REG_FLD_MOD(HDMI_WP_AUDIO_CTRL, 1, 31, 31);
+                REG_FLD_MOD(HDMI_WP_AUDIO_CTRL, 1, 30, 30);
+                break;
+
+        case SNDRV_PCM_TRIGGER_STOP:
+        case SNDRV_PCM_TRIGGER_SUSPEND:
+        case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+                REG_FLD_MOD(HDMI_CORE_AV_AUD_MODE, 0, 0, 0);
+                REG_FLD_MOD(HDMI_WP_AUDIO_CTRL, 0, 30, 30);
+                REG_FLD_MOD(HDMI_WP_AUDIO_CTRL, 0, 31, 31);
+                break;
+        default:
+                err = -EINVAL;
+        }
+        return err;
+}
+
+static int hdmi_audio_startup(struct snd_pcm_substream *substream,
+                                  struct snd_soc_dai *dai)
+{
+        if (!hdmi.mode) {
+                pr_err("Current video settings do not support audio.\n");
+                return -EIO;
+        }
+        return 0;
+}
+
+static struct snd_soc_codec_driver hdmi_audio_codec_drv = {
+};
+
+static struct snd_soc_dai_ops hdmi_audio_codec_ops = {
+        .hw_params = hdmi_audio_hw_params,
+        .trigger = hdmi_audio_trigger,
+        .startup = hdmi_audio_startup,
+};
+
+static struct snd_soc_dai_driver hdmi_codec_dai_drv = {
+                .name = "hdmi-audio-codec",
+                .playback = {
+                        .channels_min = 2,
+                        .channels_max = 2,
+                        .rates = SNDRV_PCM_RATE_32000 |
+                                SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000,
+                        .formats = SNDRV_PCM_FMTBIT_S16_LE |
+                                SNDRV_PCM_FMTBIT_S24_LE,
+                },
+                .ops = &hdmi_audio_codec_ops,
+};
+#endif
+
 /* HDMI HW IP initialisation */
 static int omapdss_hdmihw_probe(struct platform_device *pdev)
 {
         struct resource *hdmi_mem;
+#if defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI) || \
+        defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI_MODULE)
+        int ret;
+#endif
 
         hdmi.pdata = pdev->dev.platform_data;
         hdmi.pdev = pdev;
@@ -1300,6 +1715,17 @@ static int omapdss_hdmihw_probe(struct platform_device *pdev)
 
         hdmi_panel_init();
 
+#if defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI) || \
+        defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI_MODULE)
+
+        /* Register ASoC codec DAI */
+        ret = snd_soc_register_codec(&pdev->dev, &hdmi_audio_codec_drv,
+                                        &hdmi_codec_dai_drv, 1);
+        if (ret) {
+                DSSERR("can't register ASoC HDMI audio codec\n");
+                return ret;
+        }
+#endif
         return 0;
 }
 
@@ -1307,6 +1733,11 @@ static int omapdss_hdmihw_remove(struct platform_device *pdev)
 {
         hdmi_panel_exit();
 
+#if defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI) || \
+        defined(CONFIG_SND_OMAP_SOC_OMAP4_HDMI_MODULE)
+        snd_soc_unregister_codec(&pdev->dev);
+#endif
+
         iounmap(hdmi.base_wp);
 
         return 0;
diff --git a/drivers/video/omap2/dss/hdmi.h b/drivers/video/omap2/dss/hdmi.h
index 9887ab96da3c..c885f9cb0659 100644
--- a/drivers/video/omap2/dss/hdmi.h
+++ b/drivers/video/omap2/dss/hdmi.h
@@ -22,7 +22,7 @@
 #define _OMAP4_DSS_HDMI_H_
 
 #include <linux/string.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #define HDMI_WP         0x0
 #define HDMI_CORE_SYS           0x400
@@ -48,6 +48,10 @@ struct hdmi_reg { u16 idx; };
 #define HDMI_WP_VIDEO_TIMING_H                  HDMI_WP_REG(0x68)
 #define HDMI_WP_VIDEO_TIMING_V                  HDMI_WP_REG(0x6C)
 #define HDMI_WP_WP_CLK                          HDMI_WP_REG(0x70)
+#define HDMI_WP_AUDIO_CFG                       HDMI_WP_REG(0x80)
+#define HDMI_WP_AUDIO_CFG2                      HDMI_WP_REG(0x84)
+#define HDMI_WP_AUDIO_CTRL                      HDMI_WP_REG(0x88)
+#define HDMI_WP_AUDIO_DATA                      HDMI_WP_REG(0x8C)
 
 /* HDMI IP Core System */
 #define HDMI_CORE_SYS_REG(idx)                  HDMI_REG(HDMI_CORE_SYS + idx)
@@ -105,6 +109,8 @@ struct hdmi_reg { u16 idx; };
 #define HDMI_CORE_AV_AVI_DBYTE_NELEMS           HDMI_CORE_AV_REG(15)
 #define HDMI_CORE_AV_SPD_DBYTE                  HDMI_CORE_AV_REG(0x190)
 #define HDMI_CORE_AV_SPD_DBYTE_NELEMS           HDMI_CORE_AV_REG(27)
+#define HDMI_CORE_AV_AUD_DBYTE(n)               HDMI_CORE_AV_REG(n * 4 + 0x210)
+#define HDMI_CORE_AV_AUD_DBYTE_NELEMS           HDMI_CORE_AV_REG(10)
 #define HDMI_CORE_AV_MPEG_DBYTE         HDMI_CORE_AV_REG(0x290)
 #define HDMI_CORE_AV_MPEG_DBYTE_NELEMS          HDMI_CORE_AV_REG(27)
 #define HDMI_CORE_AV_GEN_DBYTE                  HDMI_CORE_AV_REG(0x300)
@@ -153,6 +159,10 @@ struct hdmi_reg { u16 idx; };
 #define HDMI_CORE_AV_SPD_VERS                   HDMI_CORE_AV_REG(0x184)
 #define HDMI_CORE_AV_SPD_LEN                    HDMI_CORE_AV_REG(0x188)
 #define HDMI_CORE_AV_SPD_CHSUM                  HDMI_CORE_AV_REG(0x18C)
+#define HDMI_CORE_AV_AUDIO_TYPE         HDMI_CORE_AV_REG(0x200)
+#define HDMI_CORE_AV_AUDIO_VERS         HDMI_CORE_AV_REG(0x204)
+#define HDMI_CORE_AV_AUDIO_LEN                  HDMI_CORE_AV_REG(0x208)
+#define HDMI_CORE_AV_AUDIO_CHSUM                HDMI_CORE_AV_REG(0x20C)
 #define HDMI_CORE_AV_MPEG_TYPE                  HDMI_CORE_AV_REG(0x280)
 #define HDMI_CORE_AV_MPEG_VERS                  HDMI_CORE_AV_REG(0x284)
 #define HDMI_CORE_AV_MPEG_LEN                   HDMI_CORE_AV_REG(0x288)
@@ -272,7 +282,7 @@ enum hdmi_core_packet_ctrl {
         HDMI_PACKETREPEATOFF = 0
 };
 
-/* INFOFRAME_AVI_ definitions */
+/* INFOFRAME_AVI_ and INFOFRAME_AUDIO_ definitions */
 enum hdmi_core_infoframe {
         HDMI_INFOFRAME_AVI_DB1Y_RGB = 0,
         HDMI_INFOFRAME_AVI_DB1Y_YUV422 = 1,
@@ -317,7 +327,36 @@ enum hdmi_core_infoframe {
         HDMI_INFOFRAME_AVI_DB5PR_7 = 6,
         HDMI_INFOFRAME_AVI_DB5PR_8 = 7,
         HDMI_INFOFRAME_AVI_DB5PR_9 = 8,
-        HDMI_INFOFRAME_AVI_DB5PR_10 = 9
+        HDMI_INFOFRAME_AVI_DB5PR_10 = 9,
+        HDMI_INFOFRAME_AUDIO_DB1CT_FROM_STREAM = 0,
+        HDMI_INFOFRAME_AUDIO_DB1CT_IEC60958 = 1,
+        HDMI_INFOFRAME_AUDIO_DB1CT_AC3 = 2,
+        HDMI_INFOFRAME_AUDIO_DB1CT_MPEG1 = 3,
+        HDMI_INFOFRAME_AUDIO_DB1CT_MP3 = 4,
+        HDMI_INFOFRAME_AUDIO_DB1CT_MPEG2_MULTICH = 5,
+        HDMI_INFOFRAME_AUDIO_DB1CT_AAC = 6,
+        HDMI_INFOFRAME_AUDIO_DB1CT_DTS = 7,
+        HDMI_INFOFRAME_AUDIO_DB1CT_ATRAC = 8,
+        HDMI_INFOFRAME_AUDIO_DB1CT_ONEBIT = 9,
+        HDMI_INFOFRAME_AUDIO_DB1CT_DOLBY_DIGITAL_PLUS = 10,
+        HDMI_INFOFRAME_AUDIO_DB1CT_DTS_HD = 11,
+        HDMI_INFOFRAME_AUDIO_DB1CT_MAT = 12,
+        HDMI_INFOFRAME_AUDIO_DB1CT_DST = 13,
+        HDMI_INFOFRAME_AUDIO_DB1CT_WMA_PRO = 14,
+        HDMI_INFOFRAME_AUDIO_DB2SF_FROM_STREAM = 0,
+        HDMI_INFOFRAME_AUDIO_DB2SF_32000 = 1,
+        HDMI_INFOFRAME_AUDIO_DB2SF_44100 = 2,
+        HDMI_INFOFRAME_AUDIO_DB2SF_48000 = 3,
+        HDMI_INFOFRAME_AUDIO_DB2SF_88200 = 4,
+        HDMI_INFOFRAME_AUDIO_DB2SF_96000 = 5,
+        HDMI_INFOFRAME_AUDIO_DB2SF_176400 = 6,
+        HDMI_INFOFRAME_AUDIO_DB2SF_192000 = 7,
+        HDMI_INFOFRAME_AUDIO_DB2SS_FROM_STREAM = 0,
+        HDMI_INFOFRAME_AUDIO_DB2SS_16BIT = 1,
+        HDMI_INFOFRAME_AUDIO_DB2SS_20BIT = 2,
+        HDMI_INFOFRAME_AUDIO_DB2SS_24BIT = 3,
+        HDMI_INFOFRAME_AUDIO_DB5_DM_INH_PERMITTED = 0,
+        HDMI_INFOFRAME_AUDIO_DB5_DM_INH_PROHIBITED = 1
 };
 
 enum hdmi_packing_mode {
@@ -327,6 +366,121 @@ enum hdmi_packing_mode {
         HDMI_PACK_ALREADYPACKED = 7
 };
 
+enum hdmi_core_audio_sample_freq {
+        HDMI_AUDIO_FS_32000 = 0x3,
+        HDMI_AUDIO_FS_44100 = 0x0,
+        HDMI_AUDIO_FS_48000 = 0x2,
+        HDMI_AUDIO_FS_88200 = 0x8,
+        HDMI_AUDIO_FS_96000 = 0xA,
+        HDMI_AUDIO_FS_176400 = 0xC,
+        HDMI_AUDIO_FS_192000 = 0xE,
+        HDMI_AUDIO_FS_NOT_INDICATED = 0x1
+};
+
+enum hdmi_core_audio_layout {
+        HDMI_AUDIO_LAYOUT_2CH = 0,
+        HDMI_AUDIO_LAYOUT_8CH = 1
+};
+
+enum hdmi_core_cts_mode {
+        HDMI_AUDIO_CTS_MODE_HW = 0,
+        HDMI_AUDIO_CTS_MODE_SW = 1
+};
+
+enum hdmi_stereo_channels {
+        HDMI_AUDIO_STEREO_NOCHANNELS = 0,
+        HDMI_AUDIO_STEREO_ONECHANNEL = 1,
+        HDMI_AUDIO_STEREO_TWOCHANNELS = 2,
+        HDMI_AUDIO_STEREO_THREECHANNELS = 3,
+        HDMI_AUDIO_STEREO_FOURCHANNELS = 4
+};
+
+enum hdmi_audio_type {
+        HDMI_AUDIO_TYPE_LPCM = 0,
+        HDMI_AUDIO_TYPE_IEC = 1
+};
+
+enum hdmi_audio_justify {
+        HDMI_AUDIO_JUSTIFY_LEFT = 0,
+        HDMI_AUDIO_JUSTIFY_RIGHT = 1
+};
+
+enum hdmi_audio_sample_order {
+        HDMI_AUDIO_SAMPLE_RIGHT_FIRST = 0,
+        HDMI_AUDIO_SAMPLE_LEFT_FIRST = 1
+};
+
+enum hdmi_audio_samples_perword {
+        HDMI_AUDIO_ONEWORD_ONESAMPLE = 0,
+        HDMI_AUDIO_ONEWORD_TWOSAMPLES = 1
+};
+
+enum hdmi_audio_sample_size {
+        HDMI_AUDIO_SAMPLE_16BITS = 0,
+        HDMI_AUDIO_SAMPLE_24BITS = 1
+};
+
+enum hdmi_audio_transf_mode {
+        HDMI_AUDIO_TRANSF_DMA = 0,
+        HDMI_AUDIO_TRANSF_IRQ = 1
+};
+
+enum hdmi_audio_blk_strt_end_sig {
+        HDMI_AUDIO_BLOCK_SIG_STARTEND_ON = 0,
+        HDMI_AUDIO_BLOCK_SIG_STARTEND_OFF = 1
+};
+
+enum hdmi_audio_i2s_config {
+        HDMI_AUDIO_I2S_WS_POLARITY_LOW_IS_LEFT = 0,
+        HDMI_AUDIO_I2S_WS_POLARIT_YLOW_IS_RIGHT = 1,
+        HDMI_AUDIO_I2S_MSB_SHIFTED_FIRST = 0,
+        HDMI_AUDIO_I2S_LSB_SHIFTED_FIRST = 1,
+        HDMI_AUDIO_I2S_MAX_WORD_20BITS = 0,
+        HDMI_AUDIO_I2S_MAX_WORD_24BITS = 1,
+        HDMI_AUDIO_I2S_CHST_WORD_NOT_SPECIFIED = 0,
+        HDMI_AUDIO_I2S_CHST_WORD_16_BITS = 1,
+        HDMI_AUDIO_I2S_CHST_WORD_17_BITS = 6,
+        HDMI_AUDIO_I2S_CHST_WORD_18_BITS = 2,
+        HDMI_AUDIO_I2S_CHST_WORD_19_BITS = 4,
+        HDMI_AUDIO_I2S_CHST_WORD_20_BITS_20MAX = 5,
+        HDMI_AUDIO_I2S_CHST_WORD_20_BITS_24MAX = 1,
+        HDMI_AUDIO_I2S_CHST_WORD_21_BITS = 6,
+        HDMI_AUDIO_I2S_CHST_WORD_22_BITS = 2,
+        HDMI_AUDIO_I2S_CHST_WORD_23_BITS = 4,
+        HDMI_AUDIO_I2S_CHST_WORD_24_BITS = 5,
+        HDMI_AUDIO_I2S_SCK_EDGE_FALLING = 0,
+        HDMI_AUDIO_I2S_SCK_EDGE_RISING = 1,
+        HDMI_AUDIO_I2S_VBIT_FOR_PCM = 0,
+        HDMI_AUDIO_I2S_VBIT_FOR_COMPRESSED = 1,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_NA = 0,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_16 = 2,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_17 = 12,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_18 = 4,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_19 = 8,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_20 = 10,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_21 = 13,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_22 = 5,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_23 = 9,
+        HDMI_AUDIO_I2S_INPUT_LENGTH_24 = 11,
+        HDMI_AUDIO_I2S_FIRST_BIT_SHIFT = 0,
+        HDMI_AUDIO_I2S_FIRST_BIT_NO_SHIFT = 1,
+        HDMI_AUDIO_I2S_SD0_EN = 1,
+        HDMI_AUDIO_I2S_SD1_EN = 1 << 1,
+        HDMI_AUDIO_I2S_SD2_EN = 1 << 2,
+        HDMI_AUDIO_I2S_SD3_EN = 1 << 3,
+};
+
+enum hdmi_audio_mclk_mode {
+        HDMI_AUDIO_MCLK_128FS = 0,
+        HDMI_AUDIO_MCLK_256FS = 1,
+        HDMI_AUDIO_MCLK_384FS = 2,
+        HDMI_AUDIO_MCLK_512FS = 3,
+        HDMI_AUDIO_MCLK_768FS = 4,
+        HDMI_AUDIO_MCLK_1024FS = 5,
+        HDMI_AUDIO_MCLK_1152FS = 6,
+        HDMI_AUDIO_MCLK_192FS = 7
+};
+
 struct hdmi_core_video_config {
         enum hdmi_core_inputbus_width   ip_bus_width;
         enum hdmi_core_dither_trunc     op_dither_truc;
@@ -376,6 +530,19 @@ struct hdmi_core_infoframe_avi {
         u16     db12_13_pixel_sofright;
                 /* Pixel number start of right bar */
 };
+/*
+ * Refer to section 8.2 in HDMI 1.3 specification for
+ * details about infoframe databytes
+ */
+struct hdmi_core_infoframe_audio {
+        u8 db1_coding_type;
+        u8 db1_channel_count;
+        u8 db2_sample_freq;
+        u8 db2_sample_size;
+        u8 db4_channel_alloc;
+        bool db5_downmix_inh;
+        u8 db5_lsv;     /* Level shift values for downmix */
+};
 
 struct hdmi_core_packet_enable_repeat {
         u32     audio_pkt;
@@ -412,4 +579,53 @@ struct hdmi_config {
         struct hdmi_cm cm;
 };
 
+struct hdmi_audio_format {
+        enum hdmi_stereo_channels               stereo_channels;
+        u8                                      active_chnnls_msk;
+        enum hdmi_audio_type                    type;
+        enum hdmi_audio_justify                 justification;
+        enum hdmi_audio_sample_order            sample_order;
+        enum hdmi_audio_samples_perword         samples_per_word;
+        enum hdmi_audio_sample_size             sample_size;
+        enum hdmi_audio_blk_strt_end_sig        en_sig_blk_strt_end;
+};
+
+struct hdmi_audio_dma {
+        u8                              transfer_size;
+        u8                              block_size;
+        enum hdmi_audio_transf_mode     mode;
+        u16                             fifo_threshold;
+};
+
+struct hdmi_core_audio_i2s_config {
+        u8 word_max_length;
+        u8 word_length;
+        u8 in_length_bits;
+        u8 justification;
+        u8 en_high_bitrate_aud;
+        u8 sck_edge_mode;
+        u8 cbit_order;
+        u8 vbit;
+        u8 ws_polarity;
+        u8 direction;
+        u8 shift;
+        u8 active_sds;
+};
+
+struct hdmi_core_audio_config {
+        struct hdmi_core_audio_i2s_config       i2s_cfg;
+        enum hdmi_core_audio_sample_freq        freq_sample;
+        bool                                    fs_override;
+        u32                                     n;
+        u32                                     cts;
+        u32                                     aud_par_busclk;
+        enum hdmi_core_audio_layout             layout;
+        enum hdmi_core_cts_mode                 cts_mode;
+        bool                                    use_mclk;
+        enum hdmi_audio_mclk_mode               mclk_mode;
+        bool                                    en_acr_pkt;
+        bool                                    en_dsd_audio;
+        bool                                    en_parallel_aud_input;
+        bool                                    en_spdif;
+};
 #endif
diff --git a/drivers/video/omap2/dss/hdmi_omap4_panel.c b/drivers/video/omap2/dss/hdmi_omap4_panel.c
index ffb5de94131f..7d4f2bd7c506 100644
--- a/drivers/video/omap2/dss/hdmi_omap4_panel.c
+++ b/drivers/video/omap2/dss/hdmi_omap4_panel.c
@@ -24,7 +24,7 @@
 #include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #include "dss.h"
 
diff --git a/drivers/video/omap2/dss/manager.c b/drivers/video/omap2/dss/manager.c
index bcd37ec86952..9aeea50e33ff 100644
--- a/drivers/video/omap2/dss/manager.c
+++ b/drivers/video/omap2/dss/manager.c
@@ -29,7 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/cpu.h>
 
 #include "dss.h"
@@ -393,6 +393,7 @@ struct overlay_cache_data {
 
         u32 paddr;
         void __iomem *vaddr;
+        u32 p_uv_addr; /* relevant for NV12 format only */
         u16 screen_width;
         u16 width;
         u16 height;
@@ -775,10 +776,17 @@ static int configure_overlay(enum omap_plane plane)
                 }
 
                 switch (c->color_mode) {
+                case OMAP_DSS_COLOR_NV12:
+                        bpp = 8;
+                        break;
                 case OMAP_DSS_COLOR_RGB16:
                 case OMAP_DSS_COLOR_ARGB16:
                 case OMAP_DSS_COLOR_YUV2:
                 case OMAP_DSS_COLOR_UYVY:
+                case OMAP_DSS_COLOR_RGBA16:
+                case OMAP_DSS_COLOR_RGBX16:
+                case OMAP_DSS_COLOR_ARGB16_1555:
+                case OMAP_DSS_COLOR_XRGB16_1555:
                         bpp = 16;
                         break;
 
@@ -854,7 +862,8 @@ static int configure_overlay(enum omap_plane plane)
                         c->mirror,
                         c->global_alpha,
                         c->pre_mult_alpha,
-                        c->channel);
+                        c->channel,
+                        c->p_uv_addr);
 
         if (r) {
                 /* this shouldn't happen */
@@ -1269,6 +1278,7 @@ static int omap_dss_mgr_apply(struct omap_overlay_manager *mgr)
 
                 oc->paddr = ovl->info.paddr;
                 oc->vaddr = ovl->info.vaddr;
+                oc->p_uv_addr = ovl->info.p_uv_addr;
                 oc->screen_width = ovl->info.screen_width;
                 oc->width = ovl->info.width;
                 oc->height = ovl->info.height;
diff --git a/drivers/video/omap2/dss/overlay.c b/drivers/video/omap2/dss/overlay.c
index f1aca6d04011..0f08025b1f0e 100644
--- a/drivers/video/omap2/dss/overlay.c
+++ b/drivers/video/omap2/dss/overlay.c
@@ -31,7 +31,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/cpu.h>
 
 #include "dss.h"
@@ -201,12 +201,16 @@ static ssize_t overlay_enabled_show(struct omap_overlay *ovl, char *buf)
 static ssize_t overlay_enabled_store(struct omap_overlay *ovl, const char *buf,
                 size_t size)
 {
-        int r;
+        int r, enable;
         struct omap_overlay_info info;
 
         ovl->get_overlay_info(ovl, &info);
 
-        info.enabled = simple_strtoul(buf, NULL, 10);
+        r = kstrtoint(buf, 0, &enable);
+        if (r)
+                return r;
+
+        info.enabled = !!enable;
 
         r = ovl->set_overlay_info(ovl, &info);
         if (r)
@@ -231,8 +235,13 @@ static ssize_t overlay_global_alpha_store(struct omap_overlay *ovl,
                 const char *buf, size_t size)
 {
         int r;
+        u8 alpha;
         struct omap_overlay_info info;
 
+        r = kstrtou8(buf, 0, &alpha);
+        if (r)
+                return r;
+
         ovl->get_overlay_info(ovl, &info);
 
         /* Video1 plane does not support global alpha
@@ -242,7 +251,7 @@ static ssize_t overlay_global_alpha_store(struct omap_overlay *ovl,
                         ovl->id == OMAP_DSS_VIDEO1)
                 info.global_alpha = 255;
         else
-                info.global_alpha = simple_strtoul(buf, NULL, 10);
+                info.global_alpha = alpha;
 
         r = ovl->set_overlay_info(ovl, &info);
         if (r)
@@ -268,8 +277,13 @@ static ssize_t overlay_pre_mult_alpha_store(struct omap_overlay *ovl,
                 const char *buf, size_t size)
 {
         int r;
+        u8 alpha;
         struct omap_overlay_info info;
 
+        r = kstrtou8(buf, 0, &alpha);
+        if (r)
+                return r;
+
         ovl->get_overlay_info(ovl, &info);
 
         /* only GFX and Video2 plane support pre alpha multiplied
@@ -279,7 +293,7 @@ static ssize_t overlay_pre_mult_alpha_store(struct omap_overlay *ovl,
                 ovl->id == OMAP_DSS_VIDEO1)
                 info.pre_mult_alpha = 0;
         else
-                info.pre_mult_alpha = simple_strtoul(buf, NULL, 10);
+                info.pre_mult_alpha = alpha;
 
         r = ovl->set_overlay_info(ovl, &info);
         if (r)
@@ -491,13 +505,18 @@ static int omap_dss_set_manager(struct omap_overlay *ovl,
         ovl->manager = mgr;
 
         dss_clk_enable(DSS_CLK_ICK | DSS_CLK_FCK);
-        /* XXX: on manual update display, in auto update mode, a bug happens
-         * here. When an overlay is first enabled on LCD, then it's disabled,
-         * and the manager is changed to TV, we sometimes get SYNC_LOST_DIGIT
-         * errors. Waiting before changing the channel_out fixes it. I'm
-         * guessing that the overlay is still somehow being used for the LCD,
-         * but I don't understand how or why. */
-        msleep(40);
+        /* XXX: When there is an overlay on a DSI manual update display, and
+         * the overlay is first disabled, then moved to tv, and enabled, we
+         * seem to get SYNC_LOST_DIGIT error.
+         *
+         * Waiting doesn't seem to help, but updating the manual update display
+         * after disabling the overlay seems to fix this. This hints that the
+         * overlay is perhaps somehow tied to the LCD output until the output
+         * is updated.
+         *
+         * Userspace workaround for this is to update the LCD after disabling
+         * the overlay, but before moving the overlay to TV.
+         */
         dispc_set_channel_out(ovl->id, mgr->id);
         dss_clk_disable(DSS_CLK_ICK | DSS_CLK_FCK);
 
diff --git a/drivers/video/omap2/dss/rfbi.c b/drivers/video/omap2/dss/rfbi.c
index 5ea17f49c611..c06fbe0bc678 100644
--- a/drivers/video/omap2/dss/rfbi.c
+++ b/drivers/video/omap2/dss/rfbi.c
@@ -32,8 +32,9 @@
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
 #include <linux/seq_file.h>
+#include <linux/semaphore.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include "dss.h"
 
 struct rfbi_reg { u16 idx; };
@@ -65,9 +66,6 @@ struct rfbi_reg { u16 idx; };
 #define REG_FLD_MOD(idx, val, start, end) \
         rfbi_write_reg(idx, FLD_MOD(rfbi_read_reg(idx), val, start, end))
 
-/* To work around an RFBI transfer rate limitation */
-#define OMAP_RFBI_RATE_LIMIT    1
-
 enum omap_rfbi_cycleformat {
         OMAP_DSS_RFBI_CYCLEFORMAT_1_1 = 0,
         OMAP_DSS_RFBI_CYCLEFORMAT_2_1 = 1,
@@ -89,11 +87,6 @@ enum omap_rfbi_parallelmode {
         OMAP_DSS_RFBI_PARALLELMODE_16 = 3,
 };
 
-enum update_cmd {
-        RFBI_CMD_UPDATE = 0,
-        RFBI_CMD_SYNC   = 1,
-};
-
 static int rfbi_convert_timings(struct rfbi_timings *t);
 static void rfbi_get_clk_info(u32 *clk_period, u32 *max_clk_div);
 
@@ -114,20 +107,9 @@ static struct {
 
         struct omap_dss_device *dssdev[2];
 
-        struct kfifo      cmd_fifo;
-        spinlock_t        cmd_lock;
-        struct completion cmd_done;
-        atomic_t          cmd_fifo_full;
-        atomic_t          cmd_pending;
+        struct semaphore bus_lock;
 } rfbi;
 
-struct update_region {
-        u16     x;
-        u16     y;
-        u16     w;
-        u16     h;
-};
-
 static inline void rfbi_write_reg(const struct rfbi_reg idx, u32 val)
 {
         __raw_writel(val, rfbi.base + idx.idx);
@@ -146,9 +128,20 @@ static void rfbi_enable_clocks(bool enable)
                 dss_clk_disable(DSS_CLK_ICK | DSS_CLK_FCK);
 }
 
+void rfbi_bus_lock(void)
+{
+        down(&rfbi.bus_lock);
+}
+EXPORT_SYMBOL(rfbi_bus_lock);
+
+void rfbi_bus_unlock(void)
+{
+        up(&rfbi.bus_lock);
+}
+EXPORT_SYMBOL(rfbi_bus_unlock);
+
 void omap_rfbi_write_command(const void *buf, u32 len)
 {
-        rfbi_enable_clocks(1);
         switch (rfbi.parallelmode) {
         case OMAP_DSS_RFBI_PARALLELMODE_8:
         {
@@ -172,13 +165,11 @@ void omap_rfbi_write_command(const void *buf, u32 len)
         default:
                 BUG();
         }
-        rfbi_enable_clocks(0);
 }
 EXPORT_SYMBOL(omap_rfbi_write_command);
 
 void omap_rfbi_read_data(void *buf, u32 len)
 {
-        rfbi_enable_clocks(1);
         switch (rfbi.parallelmode) {
         case OMAP_DSS_RFBI_PARALLELMODE_8:
         {
@@ -206,13 +197,11 @@ void omap_rfbi_read_data(void *buf, u32 len)
         default:
                 BUG();
         }
-        rfbi_enable_clocks(0);
 }
 EXPORT_SYMBOL(omap_rfbi_read_data);
 
 void omap_rfbi_write_data(const void *buf, u32 len)
 {
-        rfbi_enable_clocks(1);
         switch (rfbi.parallelmode) {
         case OMAP_DSS_RFBI_PARALLELMODE_8:
         {
@@ -237,7 +226,6 @@ void omap_rfbi_write_data(const void *buf, u32 len)
                 BUG();
 
         }
-        rfbi_enable_clocks(0);
 }
 EXPORT_SYMBOL(omap_rfbi_write_data);
 
@@ -249,8 +237,6 @@ void omap_rfbi_write_pixels(const void __iomem *buf, int scr_width,
         int horiz_offset = scr_width - w;
         int i;
 
-        rfbi_enable_clocks(1);
-
         if (rfbi.datatype == OMAP_DSS_RFBI_DATATYPE_16 &&
            rfbi.parallelmode == OMAP_DSS_RFBI_PARALLELMODE_8) {
                 const u16 __iomem *pd = buf;
@@ -295,12 +281,10 @@ void omap_rfbi_write_pixels(const void __iomem *buf, int scr_width,
         } else {
                 BUG();
         }
-
-        rfbi_enable_clocks(0);
 }
 EXPORT_SYMBOL(omap_rfbi_write_pixels);
 
-void rfbi_transfer_area(struct omap_dss_device *dssdev, u16 width,
+static void rfbi_transfer_area(struct omap_dss_device *dssdev, u16 width,
                 u16 height, void (*callback)(void *data), void *data)
 {
         u32 l;
@@ -317,8 +301,6 @@ void rfbi_transfer_area(struct omap_dss_device *dssdev, u16 width,
         rfbi.framedone_callback = callback;
         rfbi.framedone_callback_data = data;
 
-        rfbi_enable_clocks(1);
-
         rfbi_write_reg(RFBI_PIXEL_CNT, width * height);
 
         l = rfbi_read_reg(RFBI_CONTROL);
@@ -337,15 +319,11 @@ static void framedone_callback(void *data, u32 mask)
 
         REG_FLD_MOD(RFBI_CONTROL, 0, 0, 0);
 
-        rfbi_enable_clocks(0);
-
         callback = rfbi.framedone_callback;
         rfbi.framedone_callback = NULL;
 
         if (callback != NULL)
                 callback(rfbi.framedone_callback_data);
-
-        atomic_set(&rfbi.cmd_pending, 0);
 }
 
 #if 1 /* VERBOSE */
@@ -435,7 +413,7 @@ static int calc_extif_timings(struct rfbi_timings *t)
 }
 
 
-void rfbi_set_timings(int rfbi_module, struct rfbi_timings *t)
+static void rfbi_set_timings(int rfbi_module, struct rfbi_timings *t)
 {
         int r;
 
@@ -447,7 +425,6 @@ void rfbi_set_timings(int rfbi_module, struct rfbi_timings *t)
 
         BUG_ON(!t->converted);
 
-        rfbi_enable_clocks(1);
         rfbi_write_reg(RFBI_ONOFF_TIME(rfbi_module), t->tim[0]);
         rfbi_write_reg(RFBI_CYCLE_TIME(rfbi_module), t->tim[1]);
 
@@ -456,7 +433,6 @@ void rfbi_set_timings(int rfbi_module, struct rfbi_timings *t)
                     (t->tim[2] ? 1 : 0), 4, 4);
 
         rfbi_print_timings();
-        rfbi_enable_clocks(0);
 }
 
 static int ps_to_rfbi_ticks(int time, int div)
@@ -472,59 +448,6 @@ static int ps_to_rfbi_ticks(int time, int div)
         return ret;
 }
 
-#ifdef OMAP_RFBI_RATE_LIMIT
-unsigned long rfbi_get_max_tx_rate(void)
-{
-        unsigned long   l4_rate, dss1_rate;
-        int             min_l4_ticks = 0;
-        int             i;
-
-        /* According to TI this can't be calculated so make the
-         * adjustments for a couple of known frequencies and warn for
-         * others.
-         */
-        static const struct {
-                unsigned long l4_clk;           /* HZ */
-                unsigned long dss1_clk;         /* HZ */
-                unsigned long min_l4_ticks;
-        } ftab[] = {
-                { 55,   132,    7, },           /* 7.86 MPix/s */
-                { 110,  110,    12, },          /* 9.16 MPix/s */
-                { 110,  132,    10, },          /* 11   Mpix/s */
-                { 120,  120,    10, },          /* 12   Mpix/s */
-                { 133,  133,    10, },          /* 13.3 Mpix/s */
-        };
-
-        l4_rate = rfbi.l4_khz / 1000;
-        dss1_rate = dss_clk_get_rate(DSS_CLK_FCK) / 1000000;
-
-        for (i = 0; i < ARRAY_SIZE(ftab); i++) {
-                /* Use a window instead of an exact match, to account
-                 * for different DPLL multiplier / divider pairs.
-                 */
-                if (abs(ftab[i].l4_clk - l4_rate) < 3 &&
-                    abs(ftab[i].dss1_clk - dss1_rate) < 3) {
-                        min_l4_ticks = ftab[i].min_l4_ticks;
-                        break;
-                }
-        }
-        if (i == ARRAY_SIZE(ftab)) {
-                /* Can't be sure, return anyway the maximum not
-                 * rate-limited. This might cause a problem only for the
-                 * tearing synchronisation.
-                 */
-                DSSERR("can't determine maximum RFBI transfer rate\n");
-                return rfbi.l4_khz * 1000;
-        }
-        return rfbi.l4_khz * 1000 / min_l4_ticks;
-}
-#else
-int rfbi_get_max_tx_rate(void)
-{
-        return rfbi.l4_khz * 1000;
-}
-#endif
-
 static void rfbi_get_clk_info(u32 *clk_period, u32 *max_clk_div)
 {
         *clk_period = 1000000000 / rfbi.l4_khz;
@@ -644,7 +567,6 @@ int omap_rfbi_setup_te(enum omap_rfbi_te_mode mode,
         DSSDBG("setup_te: mode %d hs %d vs %d hs_inv %d vs_inv %d\n",
                 mode, hs, vs, hs_pol_inv, vs_pol_inv);
 
-        rfbi_enable_clocks(1);
         rfbi_write_reg(RFBI_HSYNC_WIDTH, hs);
         rfbi_write_reg(RFBI_VSYNC_WIDTH, vs);
 
@@ -657,7 +579,6 @@ int omap_rfbi_setup_te(enum omap_rfbi_te_mode mode,
                 l &= ~(1 << 20);
         else
                 l |= 1 << 20;
-        rfbi_enable_clocks(0);
 
         return 0;
 }
@@ -672,7 +593,6 @@ int omap_rfbi_enable_te(bool enable, unsigned line)
         if (line > (1 << 11) - 1)
                 return -EINVAL;
 
-        rfbi_enable_clocks(1);
         l = rfbi_read_reg(RFBI_CONFIG(0));
         l &= ~(0x3 << 2);
         if (enable) {
@@ -682,50 +602,12 @@ int omap_rfbi_enable_te(bool enable, unsigned line)
                 rfbi.te_enabled = 0;
         rfbi_write_reg(RFBI_CONFIG(0), l);
         rfbi_write_reg(RFBI_LINE_NUMBER, line);
-        rfbi_enable_clocks(0);
 
         return 0;
 }
 EXPORT_SYMBOL(omap_rfbi_enable_te);
 
-#if 0
-static void rfbi_enable_config(int enable1, int enable2)
-{
-        u32 l;
-        int cs = 0;
-
-        if (enable1)
-                cs |= 1<<0;
-        if (enable2)
-                cs |= 1<<1;
-
-        rfbi_enable_clocks(1);
-
-        l = rfbi_read_reg(RFBI_CONTROL);
-
-        l = FLD_MOD(l, cs, 3, 2);
-        l = FLD_MOD(l, 0, 1, 1);
-
-        rfbi_write_reg(RFBI_CONTROL, l);
-
-
-        l = rfbi_read_reg(RFBI_CONFIG(0));
-        l = FLD_MOD(l, 0, 3, 2); /* TRIGGERMODE: ITE */
-        /*l |= FLD_VAL(2, 8, 7); */ /* L4FORMAT, 2pix/L4 */
-        /*l |= FLD_VAL(0, 8, 7); */ /* L4FORMAT, 1pix/L4 */
-
-        l = FLD_MOD(l, 0, 16, 16); /* A0POLARITY */
-        l = FLD_MOD(l, 1, 20, 20); /* TE_VSYNC_POLARITY */
-        l = FLD_MOD(l, 1, 21, 21); /* HSYNCPOLARITY */
-
-        l = FLD_MOD(l, OMAP_DSS_RFBI_PARALLELMODE_8, 1, 0);
-        rfbi_write_reg(RFBI_CONFIG(0), l);
-
-        rfbi_enable_clocks(0);
-}
-#endif
-
-int rfbi_configure(int rfbi_module, int bpp, int lines)
+static int rfbi_configure(int rfbi_module, int bpp, int lines)
 {
         u32 l;
         int cycle1 = 0, cycle2 = 0, cycle3 = 0;
@@ -821,8 +703,6 @@ int rfbi_configure(int rfbi_module, int bpp, int lines)
                 break;
         }
 
-        rfbi_enable_clocks(1);
-
         REG_FLD_MOD(RFBI_CONTROL, 0, 3, 2); /* clear CS */
 
         l = 0;
@@ -856,11 +736,15 @@ int rfbi_configure(int rfbi_module, int bpp, int lines)
         DSSDBG("RFBI config: bpp %d, lines %d, cycles: 0x%x 0x%x 0x%x\n",
                bpp, lines, cycle1, cycle2, cycle3);
 
-        rfbi_enable_clocks(0);
-
         return 0;
 }
-EXPORT_SYMBOL(rfbi_configure);
+
+int omap_rfbi_configure(struct omap_dss_device *dssdev, int pixel_size,
+                int data_lines)
+{
+        return rfbi_configure(dssdev->phy.rfbi.channel, pixel_size, data_lines);
+}
+EXPORT_SYMBOL(omap_rfbi_configure);
 
 int omap_rfbi_prepare_update(struct omap_dss_device *dssdev,
                 u16 *x, u16 *y, u16 *w, u16 *h)
@@ -960,6 +844,8 @@ int omapdss_rfbi_display_enable(struct omap_dss_device *dssdev)
 {
         int r;
 
+        rfbi_enable_clocks(1);
+
         r = omap_dss_start_device(dssdev);
         if (r) {
                 DSSERR("failed to start device\n");
@@ -1002,6 +888,8 @@ void omapdss_rfbi_display_disable(struct omap_dss_device *dssdev)
         omap_dispc_unregister_isr(framedone_callback, NULL,
                         DISPC_IRQ_FRAMEDONE);
         omap_dss_stop_device(dssdev);
+
+        rfbi_enable_clocks(0);
 }
 EXPORT_SYMBOL(omapdss_rfbi_display_disable);
 
@@ -1021,11 +909,7 @@ static int omap_rfbihw_probe(struct platform_device *pdev)
 
         rfbi.pdev = pdev;
 
-        spin_lock_init(&rfbi.cmd_lock);
-
-        init_completion(&rfbi.cmd_done);
-        atomic_set(&rfbi.cmd_fifo_full, 0);
-        atomic_set(&rfbi.cmd_pending, 0);
+        sema_init(&rfbi.bus_lock, 1);
 
         rfbi_mem = platform_get_resource(rfbi.pdev, IORESOURCE_MEM, 0);
         if (!rfbi_mem) {
diff --git a/drivers/video/omap2/dss/sdi.c b/drivers/video/omap2/dss/sdi.c
index 54a53e648180..0bd4b0350f80 100644
--- a/drivers/video/omap2/dss/sdi.c
+++ b/drivers/video/omap2/dss/sdi.c
@@ -25,7 +25,7 @@
 #include <linux/err.h>
 #include <linux/regulator/consumer.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/cpu.h>
 #include "dss.h"
 
diff --git a/drivers/video/omap2/dss/venc.c b/drivers/video/omap2/dss/venc.c
index 8e35a5bae429..980f919ed987 100644
--- a/drivers/video/omap2/dss/venc.c
+++ b/drivers/video/omap2/dss/venc.c
@@ -34,7 +34,7 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/cpu.h>
 
 #include "dss.h"
@@ -373,8 +373,11 @@ static void venc_reset(void)
                 }
         }
 
+#ifdef CONFIG_OMAP2_DSS_SLEEP_AFTER_VENC_RESET
         /* the magical sleep that makes things work */
+        /* XXX more info? What bug this circumvents? */
         msleep(20);
+#endif
 }
 
 static void venc_enable_clocks(int enable)
@@ -473,6 +476,12 @@ static int venc_panel_enable(struct omap_dss_device *dssdev)
 
         mutex_lock(&venc.venc_lock);
 
+        r = omap_dss_start_device(dssdev);
+        if (r) {
+                DSSERR("failed to start device\n");
+                goto err0;
+        }
+
         if (dssdev->state != OMAP_DSS_DISPLAY_DISABLED) {
                 r = -EINVAL;
                 goto err1;
@@ -484,10 +493,11 @@ static int venc_panel_enable(struct omap_dss_device *dssdev)
 
         dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
 
-        /* wait couple of vsyncs until enabling the LCD */
-        msleep(50);
-
+        mutex_unlock(&venc.venc_lock);
+        return 0;
 err1:
+        omap_dss_stop_device(dssdev);
+err0:
         mutex_unlock(&venc.venc_lock);
 
         return r;
@@ -510,10 +520,9 @@ static void venc_panel_disable(struct omap_dss_device *dssdev)
 
         venc_power_off(dssdev);
 
-        /* wait at least 5 vsyncs after disabling the LCD */
-        msleep(100);
-
         dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
+
+        omap_dss_stop_device(dssdev);
 end:
         mutex_unlock(&venc.venc_lock);
 }
diff --git a/drivers/video/omap2/omapfb/omapfb-ioctl.c b/drivers/video/omap2/omapfb/omapfb-ioctl.c
index 6f435450987e..cff450392b79 100644
--- a/drivers/video/omap2/omapfb/omapfb-ioctl.c
+++ b/drivers/video/omap2/omapfb/omapfb-ioctl.c
@@ -28,7 +28,7 @@
 #include <linux/omapfb.h>
 #include <linux/vmalloc.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/vrfb.h>
 #include <plat/vram.h>
 
@@ -895,8 +895,16 @@ int omapfb_ioctl(struct fb_info *fbi, unsigned int cmd, unsigned long arg)
 
                 p.display_info.xres = xres;
                 p.display_info.yres = yres;
-                p.display_info.width = 0;
-                p.display_info.height = 0;
+
+                if (display->driver->get_dimensions) {
+                        u32 w, h;
+                        display->driver->get_dimensions(display, &w, &h);
+                        p.display_info.width = w;
+                        p.display_info.height = h;
+                } else {
+                        p.display_info.width = 0;
+                        p.display_info.height = 0;
+                }
 
                 if (copy_to_user((void __user *)arg, &p.display_info,
                                         sizeof(p.display_info)))
diff --git a/drivers/video/omap2/omapfb/omapfb-main.c b/drivers/video/omap2/omapfb/omapfb-main.c
index 505ec6672049..505bc12a3031 100644
--- a/drivers/video/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/omap2/omapfb/omapfb-main.c
@@ -30,7 +30,7 @@
 #include <linux/platform_device.h>
 #include <linux/omapfb.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/vram.h>
 #include <plat/vrfb.h>
 
@@ -702,8 +702,16 @@ int check_fb_var(struct fb_info *fbi, struct fb_var_screeninfo *var)
                         var->xres, var->yres,
                         var->xres_virtual, var->yres_virtual);
 
-        var->height             = -1;
-        var->width              = -1;
+        if (display && display->driver->get_dimensions) {
+                u32 w, h;
+                display->driver->get_dimensions(display, &w, &h);
+                var->width = DIV_ROUND_CLOSEST(w, 1000);
+                var->height = DIV_ROUND_CLOSEST(h, 1000);
+        } else {
+                var->height = -1;
+                var->width = -1;
+        }
+
         var->grayscale          = 0;
 
         if (display && display->driver->get_timings) {
@@ -749,35 +757,6 @@ static int omapfb_open(struct fb_info *fbi, int user)
 
 static int omapfb_release(struct fb_info *fbi, int user)
 {
-#if 0
-        struct omapfb_info *ofbi = FB2OFB(fbi);
-        struct omapfb2_device *fbdev = ofbi->fbdev;
-        struct omap_dss_device *display = fb2display(fbi);
-
-        DBG("Closing fb with plane index %d\n", ofbi->id);
-
-        omapfb_lock(fbdev);
-
-        if (display && display->get_update_mode && display->update) {
-                /* XXX this update should be removed, I think. But it's
-                 * good for debugging */
-                if (display->get_update_mode(display) ==
-                                OMAP_DSS_UPDATE_MANUAL) {
-                        u16 w, h;
-
-                        if (display->sync)
-                                display->sync(display);
-
-                        display->get_resolution(display, &w, &h);
-                        display->update(display, 0, 0, w, h);
-                }
-        }
-
-        if (display && display->sync)
-                display->sync(display);
-
-        omapfb_unlock(fbdev);
-#endif
         return 0;
 }
 
@@ -1263,7 +1242,6 @@ static int omapfb_blank(int blank, struct fb_info *fbi)
         struct omapfb_info *ofbi = FB2OFB(fbi);
         struct omapfb2_device *fbdev = ofbi->fbdev;
         struct omap_dss_device *display = fb2display(fbi);
-        int do_update = 0;
         int r = 0;
 
         if (!display)
@@ -1279,11 +1257,6 @@ static int omapfb_blank(int blank, struct fb_info *fbi)
                 if (display->driver->resume)
                         r = display->driver->resume(display);
 
-                if (r == 0 && display->driver->get_update_mode &&
-                                display->driver->get_update_mode(display) ==
-                                OMAP_DSS_UPDATE_MANUAL)
-                        do_update = 1;
-
                 break;
 
         case FB_BLANK_NORMAL:
@@ -1307,13 +1280,6 @@ static int omapfb_blank(int blank, struct fb_info *fbi)
 exit:
         omapfb_unlock(fbdev);
 
-        if (r == 0 && do_update && display->driver->update) {
-                u16 w, h;
-                display->driver->get_resolution(display, &w, &h);
-
-                r = display->driver->update(display, 0, 0, w, h);
-        }
-
         return r;
 }
 
@@ -2030,9 +1996,9 @@ static int omapfb_create_framebuffers(struct omapfb2_device *fbdev)
 static int omapfb_mode_to_timings(const char *mode_str,
                 struct omap_video_timings *timings, u8 *bpp)
 {
-        struct fb_info fbi;
-        struct fb_var_screeninfo var;
-        struct fb_ops fbops;
+        struct fb_info *fbi;
+        struct fb_var_screeninfo *var;
+        struct fb_ops *fbops;
         int r;
 
 #ifdef CONFIG_OMAP2_DSS_VENC
@@ -2050,39 +2016,66 @@ static int omapfb_mode_to_timings(const char *mode_str,
         /* this is quite a hack, but I wanted to use the modedb and for
          * that we need fb_info and var, so we create dummy ones */
 
-        memset(&fbi, 0, sizeof(fbi));
-        memset(&var, 0, sizeof(var));
-        memset(&fbops, 0, sizeof(fbops));
-        fbi.fbops = &fbops;
-
-        r = fb_find_mode(&var, &fbi, mode_str, NULL, 0, NULL, 24);
-
-        if (r != 0) {
-                timings->pixel_clock = PICOS2KHZ(var.pixclock);
-                timings->hbp = var.left_margin;
-                timings->hfp = var.right_margin;
-                timings->vbp = var.upper_margin;
-                timings->vfp = var.lower_margin;
-                timings->hsw = var.hsync_len;
-                timings->vsw = var.vsync_len;
-                timings->x_res = var.xres;
-                timings->y_res = var.yres;
-
-                switch (var.bits_per_pixel) {
-                case 16:
-                        *bpp = 16;
-                        break;
-                case 24:
-                case 32:
-                default:
-                        *bpp = 24;
-                        break;
-                }
+        *bpp = 0;
+        fbi = NULL;
+        var = NULL;
+        fbops = NULL;
 
-                return 0;
-        } else {
-                return -EINVAL;
+        fbi = kzalloc(sizeof(*fbi), GFP_KERNEL);
+        if (fbi == NULL) {
+                r = -ENOMEM;
+                goto err;
+        }
+
+        var = kzalloc(sizeof(*var), GFP_KERNEL);
+        if (var == NULL) {
+                r = -ENOMEM;
+                goto err;
+        }
+
+        fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
+        if (fbops == NULL) {
+                r = -ENOMEM;
+                goto err;
+        }
+
+        fbi->fbops = fbops;
+
+        r = fb_find_mode(var, fbi, mode_str, NULL, 0, NULL, 24);
+        if (r == 0) {
+                r = -EINVAL;
+                goto err;
+        }
+
+        timings->pixel_clock = PICOS2KHZ(var->pixclock);
+        timings->hbp = var->left_margin;
+        timings->hfp = var->right_margin;
+        timings->vbp = var->upper_margin;
+        timings->vfp = var->lower_margin;
+        timings->hsw = var->hsync_len;
+        timings->vsw = var->vsync_len;
+        timings->x_res = var->xres;
+        timings->y_res = var->yres;
+
+        switch (var->bits_per_pixel) {
+        case 16:
+                *bpp = 16;
+                break;
+        case 24:
+        case 32:
+        default:
+                *bpp = 24;
+                break;
         }
+
+        r = 0;
+
+err:
+        kfree(fbi);
+        kfree(var);
+        kfree(fbops);
+
+        return r;
 }
 
 static int omapfb_set_def_mode(struct omapfb2_device *fbdev,
@@ -2185,6 +2178,61 @@ static int omapfb_parse_def_modes(struct omapfb2_device *fbdev)
         return r;
 }
 
+static int omapfb_init_display(struct omapfb2_device *fbdev,
+                struct omap_dss_device *dssdev)
+{
+        struct omap_dss_driver *dssdrv = dssdev->driver;
+        int r;
+
+        r = dssdrv->enable(dssdev);
+        if (r) {
+                dev_warn(fbdev->dev, "Failed to enable display '%s'\n",
+                                dssdev->name);
+                return r;
+        }
+
+        if (dssdev->caps & OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE) {
+                u16 w, h;
+                if (dssdrv->enable_te) {
+                        r = dssdrv->enable_te(dssdev, 1);
+                        if (r) {
+                                dev_err(fbdev->dev, "Failed to set TE\n");
+                                return r;
+                        }
+                }
+
+                if (dssdrv->set_update_mode) {
+                        r = dssdrv->set_update_mode(dssdev,
+                                        OMAP_DSS_UPDATE_MANUAL);
+                        if (r) {
+                                dev_err(fbdev->dev,
+                                                "Failed to set update mode\n");
+                                return r;
+                        }
+                }
+
+                dssdrv->get_resolution(dssdev, &w, &h);
+                r = dssdrv->update(dssdev, 0, 0, w, h);
+                if (r) {
+                        dev_err(fbdev->dev,
+                                        "Failed to update display\n");
+                        return r;
+                }
+        } else {
+                if (dssdrv->set_update_mode) {
+                        r = dssdrv->set_update_mode(dssdev,
+                                        OMAP_DSS_UPDATE_AUTO);
+                        if (r) {
+                                dev_err(fbdev->dev,
+                                                "Failed to set update mode\n");
+                                return r;
+                        }
+                }
+        }
+
+        return 0;
+}
+
 static int omapfb_probe(struct platform_device *pdev)
 {
         struct omapfb2_device *fbdev = NULL;
@@ -2284,30 +2332,13 @@ static int omapfb_probe(struct platform_device *pdev)
         }
 
         if (def_display) {
-                struct omap_dss_driver *dssdrv = def_display->driver;
-
-                r = def_display->driver->enable(def_display);
+                r = omapfb_init_display(fbdev, def_display);
                 if (r) {
-                        dev_warn(fbdev->dev, "Failed to enable display '%s'\n",
-                                        def_display->name);
+                        dev_err(fbdev->dev,
+                                        "failed to initialize default "
+                                        "display\n");
                         goto cleanup;
                 }
-
-                if (def_display->caps & OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE) {
-                        u16 w, h;
-                        if (dssdrv->enable_te)
-                                dssdrv->enable_te(def_display, 1);
-                        if (dssdrv->set_update_mode)
-                                dssdrv->set_update_mode(def_display,
-                                                OMAP_DSS_UPDATE_MANUAL);
-
-                        dssdrv->get_resolution(def_display, &w, &h);
-                        def_display->driver->update(def_display, 0, 0, w, h);
-                } else {
-                        if (dssdrv->set_update_mode)
-                                dssdrv->set_update_mode(def_display,
-                                                OMAP_DSS_UPDATE_AUTO);
-                }
         }
 
         DBG("create sysfs for fbs\n");
diff --git a/drivers/video/omap2/omapfb/omapfb-sysfs.c b/drivers/video/omap2/omapfb/omapfb-sysfs.c
index 6f9c72cd6bb0..2f5e817b2a9a 100644
--- a/drivers/video/omap2/omapfb/omapfb-sysfs.c
+++ b/drivers/video/omap2/omapfb/omapfb-sysfs.c
@@ -29,7 +29,7 @@
 #include <linux/mm.h>
 #include <linux/omapfb.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 #include <plat/vrfb.h>
 
 #include "omapfb.h"
@@ -50,10 +50,12 @@ static ssize_t store_rotate_type(struct device *dev,
         struct fb_info *fbi = dev_get_drvdata(dev);
         struct omapfb_info *ofbi = FB2OFB(fbi);
         struct omapfb2_mem_region *rg;
-        enum omap_dss_rotation_type rot_type;
+        int rot_type;
         int r;
 
-        rot_type = simple_strtoul(buf, NULL, 0);
+        r = kstrtoint(buf, 0, &rot_type);
+        if (r)
+                return r;
 
         if (rot_type != OMAP_DSS_ROT_DMA && rot_type != OMAP_DSS_ROT_VRFB)
                 return -EINVAL;
@@ -102,14 +104,15 @@ static ssize_t store_mirror(struct device *dev,
 {
         struct fb_info *fbi = dev_get_drvdata(dev);
         struct omapfb_info *ofbi = FB2OFB(fbi);
-        unsigned long mirror;
+        int mirror;
         int r;
         struct fb_var_screeninfo new_var;
 
-        mirror = simple_strtoul(buf, NULL, 0);
+        r = kstrtoint(buf, 0, &mirror);
+        if (r)
+                return r;
 
-        if (mirror != 0 && mirror != 1)
-                return -EINVAL;
+        mirror = !!mirror;
 
         if (!lock_fb_info(fbi))
                 return -ENODEV;
@@ -445,7 +448,11 @@ static ssize_t store_size(struct device *dev, struct device_attribute *attr,
         int r;
         int i;
 
-        size = PAGE_ALIGN(simple_strtoul(buf, NULL, 0));
+        r = kstrtoul(buf, 0, &size);
+        if (r)
+                return r;
+
+        size = PAGE_ALIGN(size);
 
         if (!lock_fb_info(fbi))
                 return -ENODEV;
diff --git a/drivers/video/omap2/omapfb/omapfb.h b/drivers/video/omap2/omapfb/omapfb.h
index 1305fc9880ba..aa1b1d974276 100644
--- a/drivers/video/omap2/omapfb/omapfb.h
+++ b/drivers/video/omap2/omapfb/omapfb.h
@@ -29,13 +29,15 @@
 
 #include <linux/rwsem.h>
 
-#include <plat/display.h>
+#include <video/omapdss.h>
 
 #ifdef DEBUG
 extern unsigned int omapfb_debug;
 #define DBG(format, ...) \
-        if (omapfb_debug) \
-                printk(KERN_DEBUG "OMAPFB: " format, ## __VA_ARGS__)
+        do { \
+                if (omapfb_debug) \
+                        printk(KERN_DEBUG "OMAPFB: " format, ## __VA_ARGS__); \
+        } while (0)
 #else
 #define DBG(format, ...)
 #endif
diff --git a/drivers/video/s3c-fb.c b/drivers/video/s3c-fb.c
index 3b6cdcac8f1a..0352afa49a39 100644
--- a/drivers/video/s3c-fb.c
+++ b/drivers/video/s3c-fb.c
@@ -182,6 +182,7 @@ struct s3c_fb_vsync {
 
 /**
  * struct s3c_fb - overall hardware state of the hardware
+ * @slock: The spinlock protection for this data sturcture.
  * @dev: The device that we bound to, for printing, etc.
  * @regs_res: The resource we claimed for the IO registers.
  * @bus_clk: The clk (hclk) feeding our interface and possibly pixclk.
@@ -195,6 +196,7 @@ struct s3c_fb_vsync {
  * @vsync_info: VSYNC-related information (count, queues...)
  */
 struct s3c_fb {
+        spinlock_t              slock;
         struct device           *dev;
         struct resource         *regs_res;
         struct clk              *bus_clk;
@@ -300,6 +302,7 @@ static int s3c_fb_check_var(struct fb_var_screeninfo *var,
                 var->blue.length        = 5;
                 break;
 
+        case 32:
         case 28:
         case 25:
                 var->transp.length      = var->bits_per_pixel - 24;
@@ -308,7 +311,6 @@ static int s3c_fb_check_var(struct fb_var_screeninfo *var,
         case 24:
                 /* our 24bpp is unpacked, so 32bpp */
                 var->bits_per_pixel     = 32;
-        case 32:
                 var->red.offset         = 16;
                 var->red.length         = 8;
                 var->green.offset       = 8;
@@ -947,6 +949,8 @@ static irqreturn_t s3c_fb_irq(int irq, void *dev_id)
         void __iomem  *regs = sfb->regs;
         u32 irq_sts_reg;
 
+        spin_lock(&sfb->slock);
+
         irq_sts_reg = readl(regs + VIDINTCON1);
 
         if (irq_sts_reg & VIDINTCON1_INT_FRAME) {
@@ -963,6 +967,7 @@ static irqreturn_t s3c_fb_irq(int irq, void *dev_id)
          */
         s3c_fb_disable_irq(sfb);
 
+        spin_unlock(&sfb->slock);
         return IRQ_HANDLED;
 }
 
@@ -1339,6 +1344,8 @@ static int __devinit s3c_fb_probe(struct platform_device *pdev)
         sfb->pdata = pd;
         sfb->variant = fbdrv->variant;
 
+        spin_lock_init(&sfb->slock);
+
         sfb->bus_clk = clk_get(dev, "lcd");
         if (IS_ERR(sfb->bus_clk)) {
                 dev_err(dev, "failed to get bus clock\n");
@@ -1442,8 +1449,7 @@ err_ioremap:
         iounmap(sfb->regs);
 
 err_req_region:
-        release_resource(sfb->regs_res);
-        kfree(sfb->regs_res);
+        release_mem_region(sfb->regs_res->start, resource_size(sfb->regs_res));
 
 err_clk:
         clk_disable(sfb->bus_clk);
@@ -1479,8 +1485,7 @@ static int __devexit s3c_fb_remove(struct platform_device *pdev)
         clk_disable(sfb->bus_clk);
         clk_put(sfb->bus_clk);
 
-        release_resource(sfb->regs_res);
-        kfree(sfb->regs_res);
+        release_mem_region(sfb->regs_res->start, resource_size(sfb->regs_res));
 
         kfree(sfb);
 
@@ -1521,7 +1526,8 @@ static int s3c_fb_resume(struct device *dev)
 
         clk_enable(sfb->bus_clk);
 
-        /* setup registers */
+        /* setup gpio and output polarity controls */
+        pd->setup_gpio();
         writel(pd->vidcon1, sfb->regs + VIDCON1);
 
         /* zero all windows before we do anything */
@@ -1549,7 +1555,7 @@ static int s3c_fb_resume(struct device *dev)
         return 0;
 }
 
-int s3c_fb_runtime_suspend(struct device *dev)
+static int s3c_fb_runtime_suspend(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
         struct s3c_fb *sfb = platform_get_drvdata(pdev);
@@ -1569,7 +1575,7 @@ int s3c_fb_runtime_suspend(struct device *dev)
         return 0;
 }
 
-int s3c_fb_runtime_resume(struct device *dev)
+static int s3c_fb_runtime_resume(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
         struct s3c_fb *sfb = platform_get_drvdata(pdev);
@@ -1579,7 +1585,8 @@ int s3c_fb_runtime_resume(struct device *dev)
 
         clk_enable(sfb->bus_clk);
 
-        /* setup registers */
+        /* setup gpio and output polarity controls */
+        pd->setup_gpio();
         writel(pd->vidcon1, sfb->regs + VIDCON1);
 
         /* zero all windows before we do anything */
@@ -1623,28 +1630,31 @@ static struct s3c_fb_win_variant s3c_fb_data_64xx_wins[] = {
                 .has_osd_c      = 1,
                 .osd_size_off   = 0x8,
                 .palette_sz     = 256,
-                .valid_bpp      = VALID_BPP1248 | VALID_BPP(16) | VALID_BPP(24),
+                .valid_bpp      = (VALID_BPP1248 | VALID_BPP(16) |
+                                   VALID_BPP(18) | VALID_BPP(24)),
         },
         [1] = {
                 .has_osd_c      = 1,
                 .has_osd_d      = 1,
-                .osd_size_off   = 0x12,
+                .osd_size_off   = 0xc,
                 .has_osd_alpha  = 1,
                 .palette_sz     = 256,
                 .valid_bpp      = (VALID_BPP1248 | VALID_BPP(16) |
                                    VALID_BPP(18) | VALID_BPP(19) |
-                                   VALID_BPP(24) | VALID_BPP(25)),
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(28)),
         },
         [2] = {
                 .has_osd_c      = 1,
                 .has_osd_d      = 1,
-                .osd_size_off   = 0x12,
+                .osd_size_off   = 0xc,
                 .has_osd_alpha  = 1,
                 .palette_sz     = 16,
                 .palette_16bpp  = 1,
                 .valid_bpp      = (VALID_BPP1248 | VALID_BPP(16) |
                                    VALID_BPP(18) | VALID_BPP(19) |
-                                   VALID_BPP(24) | VALID_BPP(25)),
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(28)),
         },
         [3] = {
                 .has_osd_c      = 1,
@@ -1653,7 +1663,8 @@ static struct s3c_fb_win_variant s3c_fb_data_64xx_wins[] = {
                 .palette_16bpp  = 1,
                 .valid_bpp      = (VALID_BPP124  | VALID_BPP(16) |
                                    VALID_BPP(18) | VALID_BPP(19) |
-                                   VALID_BPP(24) | VALID_BPP(25)),
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(28)),
         },
         [4] = {
                 .has_osd_c      = 1,
@@ -1662,7 +1673,65 @@ static struct s3c_fb_win_variant s3c_fb_data_64xx_wins[] = {
                 .palette_16bpp  = 1,
                 .valid_bpp      = (VALID_BPP(1) | VALID_BPP(2) |
                                    VALID_BPP(16) | VALID_BPP(18) |
-                                   VALID_BPP(24) | VALID_BPP(25)),
+                                   VALID_BPP(19) | VALID_BPP(24) |
+                                   VALID_BPP(25) | VALID_BPP(28)),
+        },
+};
+
+static struct s3c_fb_win_variant s3c_fb_data_s5p_wins[] = {
+        [0] = {
+                .has_osd_c      = 1,
+                .osd_size_off   = 0x8,
+                .palette_sz     = 256,
+                .valid_bpp      = (VALID_BPP1248 | VALID_BPP(13) |
+                                   VALID_BPP(15) | VALID_BPP(16) |
+                                   VALID_BPP(18) | VALID_BPP(19) |
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(32)),
+        },
+        [1] = {
+                .has_osd_c      = 1,
+                .has_osd_d      = 1,
+                .osd_size_off   = 0xc,
+                .has_osd_alpha  = 1,
+                .palette_sz     = 256,
+                .valid_bpp      = (VALID_BPP1248 | VALID_BPP(13) |
+                                   VALID_BPP(15) | VALID_BPP(16) |
+                                   VALID_BPP(18) | VALID_BPP(19) |
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(32)),
+        },
+        [2] = {
+                .has_osd_c      = 1,
+                .has_osd_d      = 1,
+                .osd_size_off   = 0xc,
+                .has_osd_alpha  = 1,
+                .palette_sz     = 256,
+                .valid_bpp      = (VALID_BPP1248 | VALID_BPP(13) |
+                                   VALID_BPP(15) | VALID_BPP(16) |
+                                   VALID_BPP(18) | VALID_BPP(19) |
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(32)),
+        },
+        [3] = {
+                .has_osd_c      = 1,
+                .has_osd_alpha  = 1,
+                .palette_sz     = 256,
+                .valid_bpp      = (VALID_BPP1248 | VALID_BPP(13) |
+                                   VALID_BPP(15) | VALID_BPP(16) |
+                                   VALID_BPP(18) | VALID_BPP(19) |
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(32)),
+        },
+        [4] = {
+                .has_osd_c      = 1,
+                .has_osd_alpha  = 1,
+                .palette_sz     = 256,
+                .valid_bpp      = (VALID_BPP1248 | VALID_BPP(13) |
+                                   VALID_BPP(15) | VALID_BPP(16) |
+                                   VALID_BPP(18) | VALID_BPP(19) |
+                                   VALID_BPP(24) | VALID_BPP(25) |
+                                   VALID_BPP(32)),
         },
 };
 
@@ -1719,11 +1788,11 @@ static struct s3c_fb_driverdata s3c_fb_data_s5pc100 = {
 
                 .has_prtcon     = 1,
         },
-        .win[0] = &s3c_fb_data_64xx_wins[0],
-        .win[1] = &s3c_fb_data_64xx_wins[1],
-        .win[2] = &s3c_fb_data_64xx_wins[2],
-        .win[3] = &s3c_fb_data_64xx_wins[3],
-        .win[4] = &s3c_fb_data_64xx_wins[4],
+        .win[0] = &s3c_fb_data_s5p_wins[0],
+        .win[1] = &s3c_fb_data_s5p_wins[1],
+        .win[2] = &s3c_fb_data_s5p_wins[2],
+        .win[3] = &s3c_fb_data_s5p_wins[3],
+        .win[4] = &s3c_fb_data_s5p_wins[4],
 };
 
 static struct s3c_fb_driverdata s3c_fb_data_s5pv210 = {
@@ -1749,11 +1818,11 @@ static struct s3c_fb_driverdata s3c_fb_data_s5pv210 = {
 
                 .has_shadowcon  = 1,
         },
-        .win[0] = &s3c_fb_data_64xx_wins[0],
-        .win[1] = &s3c_fb_data_64xx_wins[1],
-        .win[2] = &s3c_fb_data_64xx_wins[2],
-        .win[3] = &s3c_fb_data_64xx_wins[3],
-        .win[4] = &s3c_fb_data_64xx_wins[4],
+        .win[0] = &s3c_fb_data_s5p_wins[0],
+        .win[1] = &s3c_fb_data_s5p_wins[1],
+        .win[2] = &s3c_fb_data_s5p_wins[2],
+        .win[3] = &s3c_fb_data_s5p_wins[3],
+        .win[4] = &s3c_fb_data_s5p_wins[4],
 };
 
 /* S3C2443/S3C2416 style hardware */
diff --git a/drivers/video/s3c2410fb.c b/drivers/video/s3c2410fb.c
index 61c819e35f7f..0aa13761de6e 100644
--- a/drivers/video/s3c2410fb.c
+++ b/drivers/video/s3c2410fb.c
@@ -867,7 +867,7 @@ static int __devinit s3c24xxfb_probe(struct platform_device *pdev,
                 goto dealloc_fb;
         }
 
-        size = (res->end - res->start) + 1;
+        size = resource_size(res);
         info->mem = request_mem_region(res->start, size, pdev->name);
         if (info->mem == NULL) {
                 dev_err(&pdev->dev, "failed to get memory region\n");
@@ -997,8 +997,7 @@ release_irq:
 release_regs:
         iounmap(info->io);
 release_mem:
-        release_resource(info->mem);
-        kfree(info->mem);
+        release_mem_region(res->start, size);
 dealloc_fb:
         platform_set_drvdata(pdev, NULL);
         framebuffer_release(fbinfo);
@@ -1044,8 +1043,7 @@ static int __devexit s3c2410fb_remove(struct platform_device *pdev)
 
         iounmap(info->io);
 
-        release_resource(info->mem);
-        kfree(info->mem);
+        release_mem_region(info->mem->start, resource_size(info->mem));
 
         platform_set_drvdata(pdev, NULL);
         framebuffer_release(fbinfo);
diff --git a/drivers/video/s3fb.c b/drivers/video/s3fb.c
index c4482f2e5799..4ca5d0c8fe84 100644
--- a/drivers/video/s3fb.c
+++ b/drivers/video/s3fb.c
@@ -25,6 +25,9 @@
 #include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
 #include <video/vga.h>
 
+#include <linux/i2c.h>
+#include <linux/i2c-algo-bit.h>
+
 #ifdef CONFIG_MTRR
 #include <asm/mtrr.h>
 #endif
@@ -36,6 +39,12 @@ struct s3fb_info {
         struct mutex open_lock;
         unsigned int ref_count;
         u32 pseudo_palette[16];
+#ifdef CONFIG_FB_S3_DDC
+        u8 __iomem *mmio;
+        bool ddc_registered;
+        struct i2c_adapter ddc_adapter;
+        struct i2c_algo_bit_data ddc_algo;
+#endif
 };
 
 
@@ -105,6 +114,9 @@ static const char * const s3_names[] = {"S3 Unknown", "S3 Trio32", "S3 Trio64",
 #define CHIP_UNDECIDED_FLAG     0x80
 #define CHIP_MASK               0xFF
 
+#define MMIO_OFFSET             0x1000000
+#define MMIO_SIZE               0x10000
+
 /* CRT timing register sets */
 
 static const struct vga_regset s3_h_total_regs[]        = {{0x00, 0, 7}, {0x5D, 0, 0}, VGA_REGSET_END};
@@ -140,7 +152,7 @@ static const struct svga_timing_regs s3_timing_regs     = {
 /* Module parameters */
 
 
-static char *mode_option __devinitdata = "640x480-8@60";
+static char *mode_option __devinitdata;
 
 #ifdef CONFIG_MTRR
 static int mtrr __devinitdata = 1;
@@ -169,6 +181,119 @@ MODULE_PARM_DESC(fasttext, "Enable S3 fast text mode (1=enable, 0=disable, defau
 
 /* ------------------------------------------------------------------------- */
 
+#ifdef CONFIG_FB_S3_DDC
+
+#define DDC_REG         0xaa            /* Trio 3D/1X/2X */
+#define DDC_MMIO_REG    0xff20          /* all other chips */
+#define DDC_SCL_OUT     (1 << 0)
+#define DDC_SDA_OUT     (1 << 1)
+#define DDC_SCL_IN      (1 << 2)
+#define DDC_SDA_IN      (1 << 3)
+#define DDC_DRIVE_EN    (1 << 4)
+
+static bool s3fb_ddc_needs_mmio(int chip)
+{
+        return !(chip == CHIP_360_TRIO3D_1X  ||
+                 chip == CHIP_362_TRIO3D_2X  ||
+                 chip == CHIP_368_TRIO3D_2X);
+}
+
+static u8 s3fb_ddc_read(struct s3fb_info *par)
+{
+        if (s3fb_ddc_needs_mmio(par->chip))
+                return readb(par->mmio + DDC_MMIO_REG);
+        else
+                return vga_rcrt(par->state.vgabase, DDC_REG);
+}
+
+static void s3fb_ddc_write(struct s3fb_info *par, u8 val)
+{
+        if (s3fb_ddc_needs_mmio(par->chip))
+                writeb(val, par->mmio + DDC_MMIO_REG);
+        else
+                vga_wcrt(par->state.vgabase, DDC_REG, val);
+}
+
+static void s3fb_ddc_setscl(void *data, int val)
+{
+        struct s3fb_info *par = data;
+        unsigned char reg;
+
+        reg = s3fb_ddc_read(par) | DDC_DRIVE_EN;
+        if (val)
+                reg |= DDC_SCL_OUT;
+        else
+                reg &= ~DDC_SCL_OUT;
+        s3fb_ddc_write(par, reg);
+}
+
+static void s3fb_ddc_setsda(void *data, int val)
+{
+        struct s3fb_info *par = data;
+        unsigned char reg;
+
+        reg = s3fb_ddc_read(par) | DDC_DRIVE_EN;
+        if (val)
+                reg |= DDC_SDA_OUT;
+        else
+                reg &= ~DDC_SDA_OUT;
+        s3fb_ddc_write(par, reg);
+}
+
+static int s3fb_ddc_getscl(void *data)
+{
+        struct s3fb_info *par = data;
+
+        return !!(s3fb_ddc_read(par) & DDC_SCL_IN);
+}
+
+static int s3fb_ddc_getsda(void *data)
+{
+        struct s3fb_info *par = data;
+
+        return !!(s3fb_ddc_read(par) & DDC_SDA_IN);
+}
+
+static int __devinit s3fb_setup_ddc_bus(struct fb_info *info)
+{
+        struct s3fb_info *par = info->par;
+
+        strlcpy(par->ddc_adapter.name, info->fix.id,
+                sizeof(par->ddc_adapter.name));
+        par->ddc_adapter.owner          = THIS_MODULE;
+        par->ddc_adapter.class          = I2C_CLASS_DDC;
+        par->ddc_adapter.algo_data      = &par->ddc_algo;
+        par->ddc_adapter.dev.parent     = info->device;
+        par->ddc_algo.setsda            = s3fb_ddc_setsda;
+        par->ddc_algo.setscl            = s3fb_ddc_setscl;
+        par->ddc_algo.getsda            = s3fb_ddc_getsda;
+        par->ddc_algo.getscl            = s3fb_ddc_getscl;
+        par->ddc_algo.udelay            = 10;
+        par->ddc_algo.timeout           = 20;
+        par->ddc_algo.data              = par;
+
+        i2c_set_adapdata(&par->ddc_adapter, par);
+
+        /*
+         * some Virge cards have external MUX to switch chip I2C bus between
+         * DDC and extension pins - switch it do DDC
+         */
+/*      vga_wseq(par->state.vgabase, 0x08, 0x06); - not needed, already unlocked */
+        if (par->chip == CHIP_357_VIRGE_GX2 ||
+            par->chip == CHIP_359_VIRGE_GX2P)
+                svga_wseq_mask(par->state.vgabase, 0x0d, 0x01, 0x03);
+        else
+                svga_wseq_mask(par->state.vgabase, 0x0d, 0x00, 0x03);
+        /* some Virge need this or the DDC is ignored */
+        svga_wcrt_mask(par->state.vgabase, 0x5c, 0x03, 0x03);
+
+        return i2c_bit_add_bus(&par->ddc_adapter);
+}
+#endif /* CONFIG_FB_S3_DDC */
+
+
+/* ------------------------------------------------------------------------- */
+
 /* Set font in S3 fast text mode */
 
 static void s3fb_settile_fast(struct fb_info *info, struct fb_tilemap *map)
@@ -994,6 +1119,7 @@ static int __devinit s3_pci_probe(struct pci_dev *dev, const struct pci_device_i
         struct s3fb_info *par;
         int rc;
         u8 regval, cr38, cr39;
+        bool found = false;
 
         /* Ignore secondary VGA device because there is no VGA arbitration */
         if (! svga_primary_device(dev)) {
@@ -1110,12 +1236,69 @@ static int __devinit s3_pci_probe(struct pci_dev *dev, const struct pci_device_i
         info->fix.ypanstep = 0;
         info->fix.accel = FB_ACCEL_NONE;
         info->pseudo_palette = (void*) (par->pseudo_palette);
+        info->var.bits_per_pixel = 8;
+
+#ifdef CONFIG_FB_S3_DDC
+        /* Enable MMIO if needed */
+        if (s3fb_ddc_needs_mmio(par->chip)) {
+                par->mmio = ioremap(info->fix.smem_start + MMIO_OFFSET, MMIO_SIZE);
+                if (par->mmio)
+                        svga_wcrt_mask(par->state.vgabase, 0x53, 0x08, 0x08);   /* enable MMIO */
+                else
+                        dev_err(info->device, "unable to map MMIO at 0x%lx, disabling DDC",
+                                info->fix.smem_start + MMIO_OFFSET);
+        }
+        if (!s3fb_ddc_needs_mmio(par->chip) || par->mmio)
+                if (s3fb_setup_ddc_bus(info) == 0) {
+                        u8 *edid = fb_ddc_read(&par->ddc_adapter);
+                        par->ddc_registered = true;
+                        if (edid) {
+                                fb_edid_to_monspecs(edid, &info->monspecs);
+                                kfree(edid);
+                                if (!info->monspecs.modedb)
+                                        dev_err(info->device, "error getting mode database\n");
+                                else {
+                                        const struct fb_videomode *m;
+
+                                        fb_videomode_to_modelist(info->monspecs.modedb,
+                                                                 info->monspecs.modedb_len,
+                                                                 &info->modelist);
+                                        m = fb_find_best_display(&info->monspecs, &info->modelist);
+                                        if (m) {
+                                                fb_videomode_to_var(&info->var, m);
+                                                /* fill all other info->var's fields */
+                                                if (s3fb_check_var(&info->var, info) == 0)
+                                                        found = true;
+                                        }
+                                }
+                        }
+                }
+#endif
+        if (!mode_option && !found)
+                mode_option = "640x480-8@60";
 
         /* Prepare startup mode */
-        rc = fb_find_mode(&(info->var), info, mode_option, NULL, 0, NULL, 8);
-        if (! ((rc == 1) || (rc == 2))) {
-                rc = -EINVAL;
-                dev_err(info->device, "mode %s not found\n", mode_option);
+        if (mode_option) {
+                rc = fb_find_mode(&info->var, info, mode_option,
+                                   info->monspecs.modedb, info->monspecs.modedb_len,
+                                   NULL, info->var.bits_per_pixel);
+                if (!rc || rc == 4) {
+                        rc = -EINVAL;
+                        dev_err(info->device, "mode %s not found\n", mode_option);
+                        fb_destroy_modedb(info->monspecs.modedb);
+                        info->monspecs.modedb = NULL;
+                        goto err_find_mode;
+                }
+        }
+
+        fb_destroy_modedb(info->monspecs.modedb);
+        info->monspecs.modedb = NULL;
+
+        /* maximize virtual vertical size for fast scrolling */
+        info->var.yres_virtual = info->fix.smem_len * 8 /
+                        (info->var.bits_per_pixel * info->var.xres_virtual);
+        if (info->var.yres_virtual < info->var.yres) {
+                dev_err(info->device, "virtual vertical size smaller than real\n");
                 goto err_find_mode;
         }
 
@@ -1164,6 +1347,12 @@ err_reg_fb:
         fb_dealloc_cmap(&info->cmap);
 err_alloc_cmap:
 err_find_mode:
+#ifdef CONFIG_FB_S3_DDC
+        if (par->ddc_registered)
+                i2c_del_adapter(&par->ddc_adapter);
+        if (par->mmio)
+                iounmap(par->mmio);
+#endif
         pci_iounmap(dev, info->screen_base);
 err_iomap:
         pci_release_regions(dev);
@@ -1180,12 +1369,11 @@ err_enable_device:
 static void __devexit s3_pci_remove(struct pci_dev *dev)
 {
         struct fb_info *info = pci_get_drvdata(dev);
+        struct s3fb_info __maybe_unused *par = info->par;
 
         if (info) {
 
 #ifdef CONFIG_MTRR
-                struct s3fb_info *par = info->par;
-
                 if (par->mtrr_reg >= 0) {
                         mtrr_del(par->mtrr_reg, 0, 0);
                         par->mtrr_reg = -1;
@@ -1195,6 +1383,13 @@ static void __devexit s3_pci_remove(struct pci_dev *dev)
                 unregister_framebuffer(info);
                 fb_dealloc_cmap(&info->cmap);
 
+#ifdef CONFIG_FB_S3_DDC
+                if (par->ddc_registered)
+                        i2c_del_adapter(&par->ddc_adapter);
+                if (par->mmio)
+                        iounmap(par->mmio);
+#endif
+
                 pci_iounmap(dev, info->screen_base);
                 pci_release_regions(dev);
 /*              pci_disable_device(dev); */
diff --git a/drivers/video/savage/savagefb-i2c.c b/drivers/video/savage/savagefb-i2c.c
index bb71fea07284..80fa87e2ae2f 100644
--- a/drivers/video/savage/savagefb-i2c.c
+++ b/drivers/video/savage/savagefb-i2c.c
@@ -171,6 +171,8 @@ void savagefb_create_i2c_busses(struct fb_info *info)
 
         switch (par->chip) {
         case S3_PROSAVAGE:
+        case S3_PROSAVAGEDDR:
+        case S3_TWISTER:
                 par->chan.reg         = CR_SERIAL2;
                 par->chan.ioaddr      = par->mmio.vbase;
                 par->chan.algo.setsda = prosavage_gpio_setsda;
diff --git a/drivers/video/savage/savagefb.h b/drivers/video/savage/savagefb.h
index 4e9490c19d7d..32549d177b19 100644
--- a/drivers/video/savage/savagefb.h
+++ b/drivers/video/savage/savagefb.h
@@ -36,7 +36,6 @@
 #define PCI_CHIP_SAVAGE_IX    0x8c13
 #define PCI_CHIP_PROSAVAGE_PM 0x8a25
 #define PCI_CHIP_PROSAVAGE_KM 0x8a26
- /* Twister is a code name; hope I get the real name soon. */
 #define PCI_CHIP_S3TWISTER_P  0x8d01
 #define PCI_CHIP_S3TWISTER_K  0x8d02
 #define PCI_CHIP_PROSAVAGE_DDR          0x8d03
@@ -52,14 +51,15 @@
 #define PCI_CHIP_SUPSAV_IXCDDR          0x8c2f
 
 
+#define S3_SAVAGE_SERIES(chip)    ((chip>=S3_SAVAGE3D) && (chip<=S3_SAVAGE2000))
 
 #define S3_SAVAGE3D_SERIES(chip)  ((chip>=S3_SAVAGE3D) && (chip<=S3_SAVAGE_MX))
 
-#define S3_SAVAGE4_SERIES(chip)   ((chip==S3_SAVAGE4) || (chip==S3_PROSAVAGE))
+#define S3_SAVAGE4_SERIES(chip)   ((chip>=S3_SAVAGE4) || (chip<=S3_PROSAVAGEDDR))
 
 #define S3_SAVAGE_MOBILE_SERIES(chip)  ((chip==S3_SAVAGE_MX) || (chip==S3_SUPERSAVAGE))
 
-#define S3_SAVAGE_SERIES(chip)    ((chip>=S3_SAVAGE3D) && (chip<=S3_SAVAGE2000))
+#define S3_MOBILE_TWISTER_SERIES(chip) ((chip==S3_TWISTER) || (chip==S3_PROSAVAGEDDR))
 
 /* Chip tags.  These are used to group the adapters into
  * related families.
@@ -71,6 +71,8 @@ typedef enum {
   S3_SAVAGE_MX,
   S3_SAVAGE4,
   S3_PROSAVAGE,
+  S3_TWISTER,
+  S3_PROSAVAGEDDR,
   S3_SUPERSAVAGE,
   S3_SAVAGE2000,
   S3_LAST
diff --git a/drivers/video/savage/savagefb_driver.c b/drivers/video/savage/savagefb_driver.c
index a2dc1a7ec758..3b7f2f5bae71 100644
--- a/drivers/video/savage/savagefb_driver.c
+++ b/drivers/video/savage/savagefb_driver.c
@@ -328,7 +328,9 @@ SavageSetup2DEngine(struct savagefb_par  *par)
                 savage_out32(0x48C18, savage_in32(0x48C18, par) | 0x0C, par);
                 break;
         case S3_SAVAGE4:
+        case S3_TWISTER:
         case S3_PROSAVAGE:
+        case S3_PROSAVAGEDDR:
         case S3_SUPERSAVAGE:
                 /* Disable BCI */
                 savage_out32(0x48C18, savage_in32(0x48C18, par) & 0x3FF0, par);
@@ -1886,6 +1888,8 @@ static int savage_init_hw(struct savagefb_par *par)
                 break;
 
         case S3_PROSAVAGE:
+        case S3_PROSAVAGEDDR:
+        case S3_TWISTER:
                 videoRam = RamSavageNB[(config1 & 0xE0) >> 5] * 1024;
                 break;
 
@@ -1963,7 +1967,8 @@ static int savage_init_hw(struct savagefb_par *par)
                 }
         }
 
-        if (S3_SAVAGE_MOBILE_SERIES(par->chip) && !par->crtonly)
+        if ((S3_SAVAGE_MOBILE_SERIES(par->chip) ||
+             S3_MOBILE_TWISTER_SERIES(par->chip)) && !par->crtonly)
                 par->display_type = DISP_LCD;
         else if (dvi || (par->chip == S3_SAVAGE4 && par->dvi))
                 par->display_type = DISP_DFP;
@@ -2111,19 +2116,19 @@ static int __devinit savage_init_fb_info(struct fb_info *info,
                 snprintf(info->fix.id, 16, "ProSavageKM");
                 break;
         case FB_ACCEL_S3TWISTER_P:
-                par->chip = S3_PROSAVAGE;
+                par->chip = S3_TWISTER;
                 snprintf(info->fix.id, 16, "TwisterP");
                 break;
         case FB_ACCEL_S3TWISTER_K:
-                par->chip = S3_PROSAVAGE;
+                par->chip = S3_TWISTER;
                 snprintf(info->fix.id, 16, "TwisterK");
                 break;
         case FB_ACCEL_PROSAVAGE_DDR:
-                par->chip = S3_PROSAVAGE;
+                par->chip = S3_PROSAVAGEDDR;
                 snprintf(info->fix.id, 16, "ProSavageDDR");
                 break;
         case FB_ACCEL_PROSAVAGE_DDRK:
-                par->chip = S3_PROSAVAGE;
+                par->chip = S3_PROSAVAGEDDR;
                 snprintf(info->fix.id, 16, "ProSavage8");
                 break;
         }
diff --git a/drivers/video/sh7760fb.c b/drivers/video/sh7760fb.c
index 8fe19582c460..45e47d847163 100644
--- a/drivers/video/sh7760fb.c
+++ b/drivers/video/sh7760fb.c
@@ -551,8 +551,7 @@ out_unmap:
                 free_irq(par->irq, &par->vsync);
         iounmap(par->base);
 out_res:
-        release_resource(par->ioarea);
-        kfree(par->ioarea);
+        release_mem_region(res->start, resource_size(res));
 out_fb:
         framebuffer_release(info);
         return ret;
@@ -570,8 +569,7 @@ static int __devexit sh7760fb_remove(struct platform_device *dev)
         if (par->irq >= 0)
                 free_irq(par->irq, par);
         iounmap(par->base);
-        release_resource(par->ioarea);
-        kfree(par->ioarea);
+        release_mem_region(par->ioarea->start, resource_size(par->ioarea));
         framebuffer_release(info);
         platform_set_drvdata(dev, NULL);
 
diff --git a/drivers/video/sh_mobile_hdmi.c b/drivers/video/sh_mobile_hdmi.c
index 2b9e56a6bde4..6ae40b630dc9 100644
--- a/drivers/video/sh_mobile_hdmi.c
+++ b/drivers/video/sh_mobile_hdmi.c
@@ -1131,15 +1131,19 @@ static void sh_hdmi_edid_work_fn(struct work_struct *work)
                 pm_runtime_get_sync(hdmi->dev);
 
                 ret = sh_hdmi_read_edid(hdmi, &hdmi_rate, &parent_rate);
-                if (ret < 0)
+                if (ret < 0) {
+                        pm_runtime_put(hdmi->dev);
                         goto out;
+                }
 
                 hdmi->hp_state = HDMI_HOTPLUG_EDID_DONE;
 
                 /* Reconfigure the clock */
                 ret = sh_hdmi_clk_configure(hdmi, hdmi_rate, parent_rate);
-                if (ret < 0)
+                if (ret < 0) {
+                        pm_runtime_put(hdmi->dev);
                         goto out;
+                }
 
                 msleep(10);
                 sh_hdmi_configure(hdmi);
@@ -1336,6 +1340,7 @@ static int __init sh_hdmi_probe(struct platform_device *pdev)
 ecodec:
         free_irq(irq, hdmi);
 ereqirq:
+        pm_runtime_suspend(&pdev->dev);
         pm_runtime_disable(&pdev->dev);
         iounmap(hdmi->base);
 emap:
@@ -1372,6 +1377,7 @@ static int __exit sh_hdmi_remove(struct platform_device *pdev)
         free_irq(irq, hdmi);
         /* Wait for already scheduled work */
         cancel_delayed_work_sync(&hdmi->edid_work);
+        pm_runtime_suspend(&pdev->dev);
         pm_runtime_disable(&pdev->dev);
         clk_disable(hdmi->hdmi_clk);
         clk_put(hdmi->hdmi_clk);
diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index 9bcc61b4ef14..404c03b4b7c7 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -27,6 +27,7 @@
 #include <asm/atomic.h>
 
 #include "sh_mobile_lcdcfb.h"
+#include "sh_mobile_meram.h"
 
 #define SIDE_B_OFFSET 0x1000
 #define MIRROR_OFFSET 0x2000
@@ -143,6 +144,7 @@ struct sh_mobile_lcdc_priv {
         unsigned long saved_shared_regs[NR_SHARED_REGS];
         int started;
         int forced_bpp; /* 2 channel LCDC must share bpp setting */
+        struct sh_mobile_meram_info *meram_dev;
 };
 
 static bool banked(int reg_nr)
@@ -469,7 +471,6 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
         int bpp = 0;
         unsigned long ldddsr;
         int k, m;
-        int ret = 0;
 
         /* enable clocks before accessing the hardware */
         for (k = 0; k < ARRAY_SIZE(priv->ch); k++) {
@@ -538,11 +539,12 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
                 lcdc_write_chan(ch, LDPMR, 0);
 
                 board_cfg = &ch->cfg.board_cfg;
-                if (board_cfg->setup_sys)
-                        ret = board_cfg->setup_sys(board_cfg->board_data, ch,
-                                                   &sh_mobile_lcdc_sys_bus_ops);
-                if (ret)
-                        return ret;
+                if (board_cfg->setup_sys) {
+                        int ret = board_cfg->setup_sys(board_cfg->board_data,
+                                                ch, &sh_mobile_lcdc_sys_bus_ops);
+                        if (ret)
+                                return ret;
+                }
         }
 
         /* word and long word swap */
@@ -564,6 +566,9 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
         }
 
         for (k = 0; k < ARRAY_SIZE(priv->ch); k++) {
+                unsigned long base_addr_y;
+                unsigned long base_addr_c = 0;
+                int pitch;
                 ch = &priv->ch[k];
 
                 if (!priv->ch[k].enabled)
@@ -598,16 +603,68 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
                 }
                 lcdc_write_chan(ch, LDDFR, tmp);
 
+                base_addr_y = ch->info->fix.smem_start;
+                base_addr_c = base_addr_y +
+                                ch->info->var.xres *
+                                ch->info->var.yres_virtual;
+                pitch = ch->info->fix.line_length;
+
+                /* test if we can enable meram */
+                if (ch->cfg.meram_cfg && priv->meram_dev &&
+                                priv->meram_dev->ops) {
+                        struct sh_mobile_meram_cfg *cfg;
+                        struct sh_mobile_meram_info *mdev;
+                        unsigned long icb_addr_y, icb_addr_c;
+                        int icb_pitch;
+                        int pf;
+
+                        cfg = ch->cfg.meram_cfg;
+                        mdev = priv->meram_dev;
+                        /* we need to de-init configured ICBs before we
+                         * we can re-initialize them.
+                         */
+                        if (ch->meram_enabled)
+                                mdev->ops->meram_unregister(mdev, cfg);
+
+                        ch->meram_enabled = 0;
+
+                        if (ch->info->var.nonstd) {
+                                if (ch->info->var.bits_per_pixel == 24)
+                                        pf = SH_MOBILE_MERAM_PF_NV24;
+                                else
+                                        pf = SH_MOBILE_MERAM_PF_NV;
+                        } else {
+                                pf = SH_MOBILE_MERAM_PF_RGB;
+                        }
+
+                        ret = mdev->ops->meram_register(mdev, cfg, pitch,
+                                                ch->info->var.yres,
+                                                pf,
+                                                base_addr_y,
+                                                base_addr_c,
+                                                &icb_addr_y,
+                                                &icb_addr_c,
+                                                &icb_pitch);
+                        if (!ret)  {
+                                /* set LDSA1R value */
+                                base_addr_y = icb_addr_y;
+                                pitch = icb_pitch;
+
+                                /* set LDSA2R value if required */
+                                if (base_addr_c)
+                                        base_addr_c = icb_addr_c;
+
+                                ch->meram_enabled = 1;
+                        }
+                }
+
                 /* point out our frame buffer */
-                lcdc_write_chan(ch, LDSA1R, ch->info->fix.smem_start);
+                lcdc_write_chan(ch, LDSA1R, base_addr_y);
                 if (ch->info->var.nonstd)
-                        lcdc_write_chan(ch, LDSA2R,
-                                ch->info->fix.smem_start +
-                                ch->info->var.xres *
-                                ch->info->var.yres_virtual);
+                        lcdc_write_chan(ch, LDSA2R, base_addr_c);
 
                 /* set line size */
-                lcdc_write_chan(ch, LDMLSR, ch->info->fix.line_length);
+                lcdc_write_chan(ch, LDMLSR, pitch);
 
                 /* setup deferred io if SYS bus */
                 tmp = ch->cfg.sys_bus_cfg.deferred_io_msec;
@@ -692,6 +749,17 @@ static void sh_mobile_lcdc_stop(struct sh_mobile_lcdc_priv *priv)
                         board_cfg->display_off(board_cfg->board_data);
                         module_put(board_cfg->owner);
                 }
+
+                /* disable the meram */
+                if (ch->meram_enabled) {
+                        struct sh_mobile_meram_cfg *cfg;
+                        struct sh_mobile_meram_info *mdev;
+                        cfg = ch->cfg.meram_cfg;
+                        mdev = priv->meram_dev;
+                        mdev->ops->meram_unregister(mdev, cfg);
+                        ch->meram_enabled = 0;
+                }
+
         }
 
         /* stop the lcdc */
@@ -875,9 +943,29 @@ static int sh_mobile_fb_pan_display(struct fb_var_screeninfo *var,
         } else
                 base_addr_c = 0;
 
-        lcdc_write_chan_mirror(ch, LDSA1R, base_addr_y);
-        if (base_addr_c)
-                lcdc_write_chan_mirror(ch, LDSA2R, base_addr_c);
+        if (!ch->meram_enabled) {
+                lcdc_write_chan_mirror(ch, LDSA1R, base_addr_y);
+                if (base_addr_c)
+                        lcdc_write_chan_mirror(ch, LDSA2R, base_addr_c);
+        } else {
+                struct sh_mobile_meram_cfg *cfg;
+                struct sh_mobile_meram_info *mdev;
+                unsigned long icb_addr_y, icb_addr_c;
+                int ret;
+
+                cfg = ch->cfg.meram_cfg;
+                mdev = priv->meram_dev;
+                ret = mdev->ops->meram_update(mdev, cfg,
+                                        base_addr_y, base_addr_c,
+                                        &icb_addr_y, &icb_addr_c);
+                if (ret)
+                        return ret;
+
+                lcdc_write_chan_mirror(ch, LDSA1R, icb_addr_y);
+                if (icb_addr_c)
+                        lcdc_write_chan_mirror(ch, LDSA2R, icb_addr_c);
+
+        }
 
         if (lcdc_chan_is_sublcd(ch))
                 lcdc_write(ch->lcdc, _LDRCNTR, ldrcntr ^ LDRCNTR_SRS);
@@ -1288,7 +1376,6 @@ static int sh_mobile_lcdc_notify(struct notifier_block *nb,
         struct fb_info *info = event->info;
         struct sh_mobile_lcdc_chan *ch = info->par;
         struct sh_mobile_lcdc_board_cfg *board_cfg = &ch->cfg.board_cfg;
-        int ret;
 
         if (&ch->lcdc->notifier != nb)
                 return NOTIFY_DONE;
@@ -1302,7 +1389,6 @@ static int sh_mobile_lcdc_notify(struct notifier_block *nb,
                         board_cfg->display_off(board_cfg->board_data);
                         module_put(board_cfg->owner);
                 }
-                pm_runtime_put(info->device);
                 sh_mobile_lcdc_stop(ch->lcdc);
                 break;
         case FB_EVENT_RESUME:
@@ -1316,9 +1402,7 @@ static int sh_mobile_lcdc_notify(struct notifier_block *nb,
                         module_put(board_cfg->owner);
                 }
 
-                ret = sh_mobile_lcdc_start(ch->lcdc);
-                if (!ret)
-                        pm_runtime_get_sync(info->device);
+                sh_mobile_lcdc_start(ch->lcdc);
         }
 
         return NOTIFY_OK;
@@ -1420,6 +1504,8 @@ static int __devinit sh_mobile_lcdc_probe(struct platform_device *pdev)
                 goto err1;
         }
 
+        priv->meram_dev = pdata->meram_dev;
+
         for (i = 0; i < j; i++) {
                 struct fb_var_screeninfo *var;
                 const struct fb_videomode *lcd_cfg, *max_cfg = NULL;
diff --git a/drivers/video/sh_mobile_lcdcfb.h b/drivers/video/sh_mobile_lcdcfb.h
index f16cb5645a13..aeed6687e6a7 100644
--- a/drivers/video/sh_mobile_lcdcfb.h
+++ b/drivers/video/sh_mobile_lcdcfb.h
@@ -39,6 +39,7 @@ struct sh_mobile_lcdc_chan {
         int use_count;
         int blank_status;
         struct mutex open_lock;         /* protects the use counter */
+        int meram_enabled;
 };
 
 #endif
diff --git a/drivers/video/sh_mobile_meram.c b/drivers/video/sh_mobile_meram.c
new file mode 100644
index 000000000000..9170c82b495c
--- /dev/null
+++ b/drivers/video/sh_mobile_meram.c
@@ -0,0 +1,567 @@
+/*
+ * SuperH Mobile MERAM Driver for SuperH Mobile LCDC Driver
+ *
+ * Copyright (c) 2011   Damian Hobson-Garcia <dhobsong@igel.co.jp>
+ *                      Takanari Hayama <taki@igel.co.jp>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+
+#include "sh_mobile_meram.h"
+
+/* meram registers */
+#define MExxCTL 0x0
+#define MExxBSIZE 0x4
+#define MExxMNCF 0x8
+#define MExxSARA 0x10
+#define MExxSARB 0x14
+#define MExxSBSIZE 0x18
+
+#define MERAM_MExxCTL_VAL(ctl, next_icb, addr)  \
+        ((ctl) | (((next_icb) & 0x1f) << 11) | (((addr) & 0x7ff) << 16))
+#define MERAM_MExxBSIZE_VAL(a, b, c) \
+        (((a) << 28) | ((b) << 16) | (c))
+
+#define MEVCR1 0x4
+#define MEACTS 0x10
+#define MEQSEL1 0x40
+#define MEQSEL2 0x44
+
+/* settings */
+#define MERAM_SEC_LINE 15
+#define MERAM_LINE_WIDTH 2048
+
+/*
+ * MERAM/ICB access functions
+ */
+
+#define MERAM_ICB_OFFSET(base, idx, off)        \
+        ((base) + (0x400 + ((idx) * 0x20) + (off)))
+
+static inline void meram_write_icb(void __iomem *base, int idx, int off,
+        unsigned long val)
+{
+        iowrite32(val, MERAM_ICB_OFFSET(base, idx, off));
+}
+
+static inline unsigned long meram_read_icb(void __iomem *base, int idx, int off)
+{
+        return ioread32(MERAM_ICB_OFFSET(base, idx, off));
+}
+
+static inline void meram_write_reg(void __iomem *base, int off,
+                unsigned long val)
+{
+        iowrite32(val, base + off);
+}
+
+static inline unsigned long meram_read_reg(void __iomem *base, int off)
+{
+        return ioread32(base + off);
+}
+
+/*
+ * register ICB
+ */
+
+#define MERAM_CACHE_START(p)     ((p) >> 16)
+#define MERAM_CACHE_END(p)       ((p) & 0xffff)
+#define MERAM_CACHE_SET(o, s)    ((((o) & 0xffff) << 16) | \
+                                  (((o) + (s) - 1) & 0xffff))
+
+/*
+ * check if there's no overlaps in MERAM allocation.
+ */
+
+static inline int meram_check_overlap(struct sh_mobile_meram_priv *priv,
+                                      struct sh_mobile_meram_icb *new)
+{
+        int i;
+        int used_start, used_end, meram_start, meram_end;
+
+        /* valid ICB? */
+        if (new->marker_icb & ~0x1f || new->cache_icb & ~0x1f)
+                return 1;
+
+        if (test_bit(new->marker_icb, &priv->used_icb) ||
+                        test_bit(new->cache_icb,  &priv->used_icb))
+                return  1;
+
+        for (i = 0; i < priv->used_meram_cache_regions; i++) {
+                used_start = MERAM_CACHE_START(priv->used_meram_cache[i]);
+                used_end   = MERAM_CACHE_END(priv->used_meram_cache[i]);
+                meram_start = new->meram_offset;
+                meram_end   = new->meram_offset + new->meram_size;
+
+                if ((meram_start >= used_start && meram_start < used_end) ||
+                        (meram_end > used_start && meram_end < used_end))
+                        return 1;
+        }
+
+        return 0;
+}
+
+/*
+ * mark the specified ICB as used
+ */
+
+static inline void meram_mark(struct sh_mobile_meram_priv *priv,
+                              struct sh_mobile_meram_icb *new)
+{
+        int n;
+
+        if (new->marker_icb < 0 || new->cache_icb < 0)
+                return;
+
+        __set_bit(new->marker_icb, &priv->used_icb);
+        __set_bit(new->cache_icb, &priv->used_icb);
+
+        n = priv->used_meram_cache_regions;
+
+        priv->used_meram_cache[n] = MERAM_CACHE_SET(new->meram_offset,
+                                                    new->meram_size);
+
+        priv->used_meram_cache_regions++;
+}
+
+/*
+ * unmark the specified ICB as used
+ */
+
+static inline void meram_unmark(struct sh_mobile_meram_priv *priv,
+                                struct sh_mobile_meram_icb *icb)
+{
+        int i;
+        unsigned long pattern;
+
+        if (icb->marker_icb < 0 || icb->cache_icb < 0)
+                return;
+
+        __clear_bit(icb->marker_icb, &priv->used_icb);
+        __clear_bit(icb->cache_icb, &priv->used_icb);
+
+        pattern = MERAM_CACHE_SET(icb->meram_offset, icb->meram_size);
+        for (i = 0; i < priv->used_meram_cache_regions; i++) {
+                if (priv->used_meram_cache[i] == pattern) {
+                        while (i < priv->used_meram_cache_regions - 1) {
+                                priv->used_meram_cache[i] =
+                                        priv->used_meram_cache[i + 1] ;
+                                i++;
+                        }
+                        priv->used_meram_cache[i] = 0;
+                        priv->used_meram_cache_regions--;
+                        break;
+                }
+        }
+}
+
+/*
+ * is this a YCbCr(NV12, NV16 or NV24) colorspace
+ */
+static inline int is_nvcolor(int cspace)
+{
+        if (cspace == SH_MOBILE_MERAM_PF_NV ||
+                        cspace == SH_MOBILE_MERAM_PF_NV24)
+                return 1;
+        return 0;
+}
+
+/*
+ * set the next address to fetch
+ */
+static inline void meram_set_next_addr(struct sh_mobile_meram_priv *priv,
+                                       struct sh_mobile_meram_cfg *cfg,
+                                       unsigned long base_addr_y,
+                                       unsigned long base_addr_c)
+{
+        unsigned long target;
+
+        target = (cfg->current_reg) ? MExxSARA : MExxSARB;
+        cfg->current_reg ^= 1;
+
+        /* set the next address to fetch */
+        meram_write_icb(priv->base, cfg->icb[0].cache_icb,  target,
+                        base_addr_y);
+        meram_write_icb(priv->base, cfg->icb[0].marker_icb, target,
+                        base_addr_y + cfg->icb[0].cache_unit);
+
+        if (is_nvcolor(cfg->pixelformat)) {
+                meram_write_icb(priv->base, cfg->icb[1].cache_icb,  target,
+                                base_addr_c);
+                meram_write_icb(priv->base, cfg->icb[1].marker_icb, target,
+                                base_addr_c + cfg->icb[1].cache_unit);
+        }
+}
+
+/*
+ * get the next ICB address
+ */
+static inline void meram_get_next_icb_addr(struct sh_mobile_meram_info *pdata,
+                                           struct sh_mobile_meram_cfg *cfg,
+                                           unsigned long *icb_addr_y,
+                                           unsigned long *icb_addr_c)
+{
+        unsigned long icb_offset;
+
+        if (pdata->addr_mode == SH_MOBILE_MERAM_MODE0)
+                icb_offset = 0x80000000 | (cfg->current_reg << 29);
+        else
+                icb_offset = 0xc0000000 | (cfg->current_reg << 23);
+
+        *icb_addr_y = icb_offset | (cfg->icb[0].marker_icb << 24);
+        if ((*icb_addr_c) && is_nvcolor(cfg->pixelformat))
+                *icb_addr_c = icb_offset | (cfg->icb[1].marker_icb << 24);
+}
+
+#define MERAM_CALC_BYTECOUNT(x, y) \
+        (((x) * (y) + (MERAM_LINE_WIDTH - 1)) & ~(MERAM_LINE_WIDTH - 1))
+
+/*
+ * initialize MERAM
+ */
+
+static int meram_init(struct sh_mobile_meram_priv *priv,
+                      struct sh_mobile_meram_icb *icb,
+                      int xres, int yres, int *out_pitch)
+{
+        unsigned long total_byte_count = MERAM_CALC_BYTECOUNT(xres, yres);
+        unsigned long bnm;
+        int lcdc_pitch, xpitch, line_cnt;
+        int save_lines;
+
+        /* adjust pitch to 1024, 2048, 4096 or 8192 */
+        lcdc_pitch = (xres - 1) | 1023;
+        lcdc_pitch = lcdc_pitch | (lcdc_pitch >> 1);
+        lcdc_pitch = lcdc_pitch | (lcdc_pitch >> 2);
+        lcdc_pitch += 1;
+
+        /* derive settings */
+        if (lcdc_pitch == 8192 && yres >= 1024) {
+                lcdc_pitch = xpitch = MERAM_LINE_WIDTH;
+                line_cnt = total_byte_count >> 11;
+                *out_pitch = xres;
+                save_lines = (icb->meram_size / 16 / MERAM_SEC_LINE);
+                save_lines *= MERAM_SEC_LINE;
+        } else {
+                xpitch = xres;
+                line_cnt = yres;
+                *out_pitch = lcdc_pitch;
+                save_lines = icb->meram_size / (lcdc_pitch >> 10) / 2;
+                save_lines &= 0xff;
+        }
+        bnm = (save_lines - 1) << 16;
+
+        /* TODO: we better to check if we have enough MERAM buffer size */
+
+        /* set up ICB */
+        meram_write_icb(priv->base, icb->cache_icb,  MExxBSIZE,
+                        MERAM_MExxBSIZE_VAL(0x0, line_cnt - 1, xpitch - 1));
+        meram_write_icb(priv->base, icb->marker_icb, MExxBSIZE,
+                        MERAM_MExxBSIZE_VAL(0xf, line_cnt - 1, xpitch - 1));
+
+        meram_write_icb(priv->base, icb->cache_icb,  MExxMNCF, bnm);
+        meram_write_icb(priv->base, icb->marker_icb, MExxMNCF, bnm);
+
+        meram_write_icb(priv->base, icb->cache_icb,  MExxSBSIZE, xpitch);
+        meram_write_icb(priv->base, icb->marker_icb, MExxSBSIZE, xpitch);
+
+        /* save a cache unit size */
+        icb->cache_unit = xres * save_lines;
+
+        /*
+         * Set MERAM for framebuffer
+         *
+         * 0x70f:  WD = 0x3, WS=0x1, CM=0x1, MD=FB mode
+         * we also chain the cache_icb and the marker_icb.
+         * we also split the allocated MERAM buffer between two ICBs.
+         */
+        meram_write_icb(priv->base, icb->cache_icb, MExxCTL,
+                        MERAM_MExxCTL_VAL(0x70f, icb->marker_icb,
+                                          icb->meram_offset));
+        meram_write_icb(priv->base, icb->marker_icb, MExxCTL,
+                        MERAM_MExxCTL_VAL(0x70f, icb->cache_icb,
+                                          icb->meram_offset +
+                                          icb->meram_size / 2));
+
+        return 0;
+}
+
+static void meram_deinit(struct sh_mobile_meram_priv *priv,
+                        struct sh_mobile_meram_icb *icb)
+{
+        /* disable ICB */
+        meram_write_icb(priv->base, icb->cache_icb,  MExxCTL, 0);
+        meram_write_icb(priv->base, icb->marker_icb, MExxCTL, 0);
+        icb->cache_unit = 0;
+}
+
+/*
+ * register the ICB
+ */
+
+static int sh_mobile_meram_register(struct sh_mobile_meram_info *pdata,
+                                    struct sh_mobile_meram_cfg *cfg,
+                                    int xres, int yres, int pixelformat,
+                                    unsigned long base_addr_y,
+                                    unsigned long base_addr_c,
+                                    unsigned long *icb_addr_y,
+                                    unsigned long *icb_addr_c,
+                                    int *pitch)
+{
+        struct platform_device *pdev;
+        struct sh_mobile_meram_priv *priv;
+        int n, out_pitch;
+        int error = 0;
+
+        if (!pdata || !pdata->priv || !pdata->pdev || !cfg)
+                return -EINVAL;
+
+        if (pixelformat != SH_MOBILE_MERAM_PF_NV &&
+            pixelformat != SH_MOBILE_MERAM_PF_NV24 &&
+            pixelformat != SH_MOBILE_MERAM_PF_RGB)
+                return -EINVAL;
+
+        priv = pdata->priv;
+        pdev = pdata->pdev;
+
+        dev_dbg(&pdev->dev, "registering %dx%d (%s) (y=%08lx, c=%08lx)",
+                xres, yres, (!pixelformat) ? "yuv" : "rgb",
+                base_addr_y, base_addr_c);
+
+        mutex_lock(&priv->lock);
+
+        /* we can't handle wider than 8192px */
+        if (xres > 8192) {
+                dev_err(&pdev->dev, "width exceeding the limit (> 8192).");
+                error = -EINVAL;
+                goto err;
+        }
+
+        if (priv->used_meram_cache_regions + 2 > SH_MOBILE_MERAM_ICB_NUM) {
+                dev_err(&pdev->dev, "no more ICB available.");
+                error = -EINVAL;
+                goto err;
+        }
+
+        /* do we have at least one ICB config? */
+        if (cfg->icb[0].marker_icb < 0 || cfg->icb[0].cache_icb < 0) {
+                dev_err(&pdev->dev, "at least one ICB is required.");
+                error = -EINVAL;
+                goto err;
+        }
+
+        /* make sure that there's no overlaps */
+        if (meram_check_overlap(priv, &cfg->icb[0])) {
+                dev_err(&pdev->dev, "conflicting config detected.");
+                error = -EINVAL;
+                goto err;
+        }
+        n = 1;
+
+        /* do the same if we have the second ICB set */
+        if (cfg->icb[1].marker_icb >= 0 && cfg->icb[1].cache_icb >= 0) {
+                if (meram_check_overlap(priv, &cfg->icb[1])) {
+                        dev_err(&pdev->dev, "conflicting config detected.");
+                        error = -EINVAL;
+                        goto err;
+                }
+                n = 2;
+        }
+
+        if (is_nvcolor(pixelformat) && n != 2) {
+                dev_err(&pdev->dev, "requires two ICB sets for planar Y/C.");
+                error =  -EINVAL;
+                goto err;
+        }
+
+        /* we now register the ICB */
+        cfg->pixelformat = pixelformat;
+        meram_mark(priv, &cfg->icb[0]);
+        if (is_nvcolor(pixelformat))
+                meram_mark(priv, &cfg->icb[1]);
+
+        /* initialize MERAM */
+        meram_init(priv, &cfg->icb[0], xres, yres, &out_pitch);
+        *pitch = out_pitch;
+        if (pixelformat == SH_MOBILE_MERAM_PF_NV)
+                meram_init(priv, &cfg->icb[1], xres, (yres + 1) / 2,
+                        &out_pitch);
+        else if (pixelformat == SH_MOBILE_MERAM_PF_NV24)
+                meram_init(priv, &cfg->icb[1], 2 * xres, (yres + 1) / 2,
+                        &out_pitch);
+
+        cfg->current_reg = 1;
+        meram_set_next_addr(priv, cfg, base_addr_y, base_addr_c);
+        meram_get_next_icb_addr(pdata, cfg, icb_addr_y, icb_addr_c);
+
+        dev_dbg(&pdev->dev, "registered - can access via y=%08lx, c=%08lx",
+                *icb_addr_y, *icb_addr_c);
+
+err:
+        mutex_unlock(&priv->lock);
+        return error;
+}
+
+static int sh_mobile_meram_unregister(struct sh_mobile_meram_info *pdata,
+                                      struct sh_mobile_meram_cfg *cfg)
+{
+        struct sh_mobile_meram_priv *priv;
+
+        if (!pdata || !pdata->priv || !cfg)
+                return -EINVAL;
+
+        priv = pdata->priv;
+
+        mutex_lock(&priv->lock);
+
+        /* deinit & unmark */
+        if (is_nvcolor(cfg->pixelformat)) {
+                meram_deinit(priv, &cfg->icb[1]);
+                meram_unmark(priv, &cfg->icb[1]);
+        }
+        meram_deinit(priv, &cfg->icb[0]);
+        meram_unmark(priv, &cfg->icb[0]);
+
+        mutex_unlock(&priv->lock);
+
+        return 0;
+}
+
+static int sh_mobile_meram_update(struct sh_mobile_meram_info *pdata,
+                                  struct sh_mobile_meram_cfg *cfg,
+                                  unsigned long base_addr_y,
+                                  unsigned long base_addr_c,
+                                  unsigned long *icb_addr_y,
+                                  unsigned long *icb_addr_c)
+{
+        struct sh_mobile_meram_priv *priv;
+
+        if (!pdata || !pdata->priv || !cfg)
+                return -EINVAL;
+
+        priv = pdata->priv;
+
+        mutex_lock(&priv->lock);
+
+        meram_set_next_addr(priv, cfg, base_addr_y, base_addr_c);
+        meram_get_next_icb_addr(pdata, cfg, icb_addr_y, icb_addr_c);
+
+        mutex_unlock(&priv->lock);
+
+        return 0;
+}
+
+static struct sh_mobile_meram_ops sh_mobile_meram_ops = {
+        .module                 = THIS_MODULE,
+        .meram_register         = sh_mobile_meram_register,
+        .meram_unregister       = sh_mobile_meram_unregister,
+        .meram_update           = sh_mobile_meram_update,
+};
+
+/*
+ * initialize MERAM
+ */
+
+static int sh_mobile_meram_remove(struct platform_device *pdev);
+
+static int __devinit sh_mobile_meram_probe(struct platform_device *pdev)
+{
+        struct sh_mobile_meram_priv *priv;
+        struct sh_mobile_meram_info *pdata = pdev->dev.platform_data;
+        struct resource *res;
+        int error;
+
+        if (!pdata) {
+                dev_err(&pdev->dev, "no platform data defined\n");
+                return -EINVAL;
+        }
+
+        res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+        if (!res) {
+                dev_err(&pdev->dev, "cannot get platform resources\n");
+                return -ENOENT;
+        }
+
+        priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+        if (!priv) {
+                dev_err(&pdev->dev, "cannot allocate device data\n");
+                return -ENOMEM;
+        }
+
+        platform_set_drvdata(pdev, priv);
+
+        /* initialize private data */
+        mutex_init(&priv->lock);
+        priv->base = ioremap_nocache(res->start, resource_size(res));
+        if (!priv->base) {
+                dev_err(&pdev->dev, "ioremap failed\n");
+                error = -EFAULT;
+                goto err;
+        }
+        pdata->ops = &sh_mobile_meram_ops;
+        pdata->priv = priv;
+        pdata->pdev = pdev;
+
+        /* initialize ICB addressing mode */
+        if (pdata->addr_mode == SH_MOBILE_MERAM_MODE1)
+                meram_write_reg(priv->base, MEVCR1, 1 << 29);
+
+        dev_info(&pdev->dev, "sh_mobile_meram initialized.");
+
+        return 0;
+
+err:
+        sh_mobile_meram_remove(pdev);
+
+        return error;
+}
+
+
+static int sh_mobile_meram_remove(struct platform_device *pdev)
+{
+        struct sh_mobile_meram_priv *priv = platform_get_drvdata(pdev);
+
+        if (priv->base)
+                iounmap(priv->base);
+
+        mutex_destroy(&priv->lock);
+
+        kfree(priv);
+
+        return 0;
+}
+
+static struct platform_driver sh_mobile_meram_driver = {
+        .driver = {
+                .name           = "sh_mobile_meram",
+                .owner          = THIS_MODULE,
+        },
+        .probe          = sh_mobile_meram_probe,
+        .remove         = sh_mobile_meram_remove,
+};
+
+static int __init sh_mobile_meram_init(void)
+{
+        return platform_driver_register(&sh_mobile_meram_driver);
+}
+
+static void __exit sh_mobile_meram_exit(void)
+{
+        platform_driver_unregister(&sh_mobile_meram_driver);
+}
+
+module_init(sh_mobile_meram_init);
+module_exit(sh_mobile_meram_exit);
+
+MODULE_DESCRIPTION("SuperH Mobile MERAM driver");
+MODULE_AUTHOR("Damian Hobson-Garcia / Takanari Hayama");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/sh_mobile_meram.h b/drivers/video/sh_mobile_meram.h
new file mode 100644
index 000000000000..82c54fbce8bd
--- /dev/null
+++ b/drivers/video/sh_mobile_meram.h
@@ -0,0 +1,41 @@
+#ifndef __sh_mobile_meram_h__
+#define __sh_mobile_meram_h__
+
+#include <linux/mutex.h>
+#include <video/sh_mobile_meram.h>
+
+/*
+ * MERAM private
+ */
+
+#define MERAM_ICB_Y 0x1
+#define MERAM_ICB_C 0x2
+
+/* MERAM cache size */
+#define SH_MOBILE_MERAM_ICB_NUM         32
+
+#define SH_MOBILE_MERAM_CACHE_OFFSET(p) ((p) >> 16)
+#define SH_MOBILE_MERAM_CACHE_SIZE(p)   ((p) & 0xffff)
+
+struct sh_mobile_meram_priv {
+        void __iomem    *base;
+        struct mutex    lock;
+        unsigned long   used_icb;
+        int             used_meram_cache_regions;
+        unsigned long   used_meram_cache[SH_MOBILE_MERAM_ICB_NUM];
+};
+
+int sh_mobile_meram_alloc_icb(const struct sh_mobile_meram_cfg *cfg,
+                   int xres,
+                   int yres,
+                   unsigned int base_addr,
+                   int yuv_mode,
+                   int *marker_icb,
+                   int *out_pitch);
+
+void sh_mobile_meram_free_icb(int marker_icb);
+
+#define SH_MOBILE_MERAM_START(ind, ab) \
+        (0xC0000000 | ((ab & 0x1) << 23) | ((ind & 0x1F) << 24))
+
+#endif /* !__sh_mobile_meram_h__ */
diff --git a/drivers/video/sm501fb.c b/drivers/video/sm501fb.c
index 56ef6b3a9851..87f0be1e78b5 100644
--- a/drivers/video/sm501fb.c
+++ b/drivers/video/sm501fb.c
@@ -1625,22 +1625,22 @@ static int sm501fb_start(struct sm501fb_info *info,
         return 0; /* everything is setup */
 
  err_mem_res:
-        release_resource(info->fbmem_res);
-        kfree(info->fbmem_res);
+        release_mem_region(info->fbmem_res->start,
+                           resource_size(info->fbmem_res));
 
  err_regs2d_map:
         iounmap(info->regs2d);
 
  err_regs2d_res:
-        release_resource(info->regs2d_res);
-        kfree(info->regs2d_res);
+        release_mem_region(info->regs2d_res->start,
+                           resource_size(info->regs2d_res));
 
  err_regs_map:
         iounmap(info->regs);
 
  err_regs_res:
-        release_resource(info->regs_res);
-        kfree(info->regs_res);
+        release_mem_region(info->regs_res->start,
+                           resource_size(info->regs_res));
 
  err_release:
         return ret;
@@ -1652,16 +1652,16 @@ static void sm501fb_stop(struct sm501fb_info *info)
         sm501_unit_power(info->dev->parent, SM501_GATE_DISPLAY, 0);
 
         iounmap(info->fbmem);
-        release_resource(info->fbmem_res);
-        kfree(info->fbmem_res);
+        release_mem_region(info->fbmem_res->start,
+                           resource_size(info->fbmem_res));
 
         iounmap(info->regs2d);
-        release_resource(info->regs2d_res);
-        kfree(info->regs2d_res);
+        release_mem_region(info->regs2d_res->start,
+                           resource_size(info->regs2d_res));
 
         iounmap(info->regs);
-        release_resource(info->regs_res);
-        kfree(info->regs_res);
+        release_mem_region(info->regs_res->start,
+                           resource_size(info->regs_res));
 }
 
 static int sm501fb_init_fb(struct fb_info *fb,
diff --git a/drivers/video/udlfb.c b/drivers/video/udlfb.c
index 695066b5b2e6..52b0f3e8ccac 100644
--- a/drivers/video/udlfb.c
+++ b/drivers/video/udlfb.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/prefetch.h>
 #include <linux/delay.h>
+#include <linux/prefetch.h>
 #include <video/udlfb.h>
 #include "edid.h"
 
@@ -1587,10 +1588,19 @@ static int dlfb_usb_probe(struct usb_interface *interface,
                 goto error;
         }
 
-        for (i = 0; i < ARRAY_SIZE(fb_device_attrs); i++)
-                device_create_file(info->dev, &fb_device_attrs[i]);
+        for (i = 0; i < ARRAY_SIZE(fb_device_attrs); i++) {
+                retval = device_create_file(info->dev, &fb_device_attrs[i]);
+                if (retval) {
+                        pr_err("device_create_file failed %d\n", retval);
+                        goto err_del_attrs;
+                }
+        }
 
-        device_create_bin_file(info->dev, &edid_attr);
+        retval = device_create_bin_file(info->dev, &edid_attr);
+        if (retval) {
+                pr_err("device_create_bin_file failed %d\n", retval);
+                goto err_del_attrs;
+        }
 
         pr_info("DisplayLink USB device /dev/fb%d attached. %dx%d resolution."
                         " Using %dK framebuffer memory\n", info->node,
@@ -1599,6 +1609,10 @@ static int dlfb_usb_probe(struct usb_interface *interface,
                         info->fix.smem_len * 2 : info->fix.smem_len) >> 10);
         return 0;
 
+err_del_attrs:
+        for (i -= 1; i >= 0; i--)
+                device_remove_file(info->dev, &fb_device_attrs[i]);
+
 error:
         if (dev) {
 
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig
index 814ac4e213a8..0a93dc1cb4ac 100644
--- a/fs/9p/Kconfig
+++ b/fs/9p/Kconfig
@@ -1,6 +1,6 @@
 config 9P_FS
-        tristate "Plan 9 Resource Sharing Support (9P2000) (Experimental)"
-        depends on INET && NET_9P && EXPERIMENTAL
+        tristate "Plan 9 Resource Sharing Support (9P2000)"
+        depends on INET && NET_9P
         help
           If you say Y here, you will get experimental support for
           Plan 9 resource sharing via the 9P2000 protocol.
@@ -10,7 +10,6 @@ config 9P_FS
           If unsure, say N.
 
 if 9P_FS
-
 config 9P_FSCACHE
         bool "Enable 9P client caching support (EXPERIMENTAL)"
         depends on EXPERIMENTAL
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 82a7c38ddad0..691c78f58bef 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -259,7 +259,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
                 if (IS_ERR(inode_fid)) {
                         err = PTR_ERR(inode_fid);
                         mutex_unlock(&v9inode->v_mutex);
-                        goto error;
+                        goto err_clunk_old_fid;
                 }
                 v9inode->writeback_fid = (void *) inode_fid;
         }
@@ -267,8 +267,8 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
         /* Since we are opening a file, assign the open fid to the file */
         filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
         if (IS_ERR(filp)) {
-                p9_client_clunk(ofid);
-                return PTR_ERR(filp);
+                err = PTR_ERR(filp);
+                goto err_clunk_old_fid;
         }
         filp->private_data = ofid;
 #ifdef CONFIG_9P_FSCACHE
@@ -278,10 +278,11 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
         return 0;
 
 error:
-        if (ofid)
-                p9_client_clunk(ofid);
         if (fid)
                 p9_client_clunk(fid);
+err_clunk_old_fid:
+        if (ofid)
+                p9_client_clunk(ofid);
         return err;
 }
 
diff --git a/fs/Kconfig b/fs/Kconfig
index f3aa9b08b228..979992dcb386 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -121,9 +121,25 @@ config TMPFS
 
           See <file:Documentation/filesystems/tmpfs.txt> for details.
 
+config TMPFS_XATTR
+        bool "Tmpfs extended attributes"
+        depends on TMPFS
+        default n
+        help
+          Extended attributes are name:value pairs associated with inodes by
+          the kernel or by users (see the attr(5) manual page, or visit
+          <http://acl.bestbits.at/> for details).
+
+          Currently this enables support for the trusted.* and
+          security.* namespaces.
+
+          If unsure, say N.
+
+          You need this for POSIX ACL support on tmpfs.
+
 config TMPFS_POSIX_ACL
         bool "Tmpfs POSIX Access Control Lists"
-        depends on TMPFS
+        depends on TMPFS_XATTR
         select GENERIC_ACL
         help
           POSIX Access Control Lists (ACLs) support permissions for users and
diff --git a/fs/block_dev.c b/fs/block_dev.c
index bf9c7a720371..1f2b19978333 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1238,6 +1238,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
         res = __blkdev_get(bdev, mode, 0);
 
         if (whole) {
+                struct gendisk *disk = whole->bd_disk;
+
                 /* finish claiming */
                 mutex_lock(&bdev->bd_mutex);
                 spin_lock(&bdev_lock);
@@ -1264,15 +1266,16 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
                 spin_unlock(&bdev_lock);
 
                 /*
-                 * Block event polling for write claims.  Any write
-                 * holder makes the write_holder state stick until all
-                 * are released.  This is good enough and tracking
-                 * individual writeable reference is too fragile given
-                 * the way @mode is used in blkdev_get/put().
+                 * Block event polling for write claims if requested.  Any
+                 * write holder makes the write_holder state stick until
+                 * all are released.  This is good enough and tracking
+                 * individual writeable reference is too fragile given the
+                 * way @mode is used in blkdev_get/put().
                  */
-                if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+                if ((disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE) &&
+                    !res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
                         bdev->bd_write_holder = true;
-                        disk_block_events(bdev->bd_disk);
+                        disk_block_events(disk);
                 }
 
                 mutex_unlock(&bdev->bd_mutex);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 38b8ab554924..33da49dc3cc6 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -848,7 +848,8 @@ get_more_pages:
                 op->payload_len = cpu_to_le32(len);
                 req->r_request->hdr.data_len = cpu_to_le32(len);
 
-                ceph_osdc_start_request(&fsc->client->osdc, req, true);
+                rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
+                BUG_ON(rc);
                 req = NULL;
 
                 /* continue? */
@@ -880,8 +881,6 @@ release_pvec_pages:
 out:
         if (req)
                 ceph_osdc_put_request(req);
-        if (rc > 0)
-                rc = 0;  /* vfs expects us to return 0 */
         ceph_put_snap_context(snapc);
         dout("writepages done, rc = %d\n", rc);
         return rc;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 2a5404c1c42f..1f72b00447c4 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -569,7 +569,8 @@ retry:
                 list_add_tail(&cap->session_caps, &session->s_caps);
                 session->s_nr_caps++;
                 spin_unlock(&session->s_cap_lock);
-        }
+        } else if (new_cap)
+                ceph_put_cap(mdsc, new_cap);
 
         if (!ci->i_snap_realm) {
                 /*
@@ -2634,6 +2635,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
                               struct ceph_mds_session *session,
                               int *open_target_sessions)
 {
+        struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
         struct ceph_inode_info *ci = ceph_inode(inode);
         int mds = session->s_mds;
         unsigned mseq = le32_to_cpu(ex->migrate_seq);
@@ -2670,6 +2672,19 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
                          * export targets, so that we get the matching IMPORT
                          */
                         *open_target_sessions = 1;
+
+                        /*
+                         * we can't flush dirty caps that we've seen the
+                         * EXPORT but no IMPORT for
+                         */
+                        spin_lock(&mdsc->cap_dirty_lock);
+                        if (!list_empty(&ci->i_dirty_item)) {
+                                dout(" moving %p to cap_dirty_migrating\n",
+                                     inode);
+                                list_move(&ci->i_dirty_item,
+                                          &mdsc->cap_dirty_migrating);
+                        }
+                        spin_unlock(&mdsc->cap_dirty_lock);
                 }
                 __ceph_remove_cap(cap);
         }
@@ -2707,6 +2722,13 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
                 ci->i_cap_exporting_issued = 0;
                 ci->i_cap_exporting_mseq = 0;
                 ci->i_cap_exporting_mds = -1;
+
+                spin_lock(&mdsc->cap_dirty_lock);
+                if (!list_empty(&ci->i_dirty_item)) {
+                        dout(" moving %p back to cap_dirty\n", inode);
+                        list_move(&ci->i_dirty_item, &mdsc->cap_dirty);
+                }
+                spin_unlock(&mdsc->cap_dirty_lock);
         } else {
                 dout("handle_cap_import inode %p ci %p mds%d mseq %d\n",
                      inode, ci, mds, mseq);
@@ -2910,38 +2932,16 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
  */
 void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
 {
-        struct ceph_inode_info *ci, *nci = NULL;
-        struct inode *inode, *ninode = NULL;
-        struct list_head *p, *n;
+        struct ceph_inode_info *ci;
+        struct inode *inode;
 
         dout("flush_dirty_caps\n");
         spin_lock(&mdsc->cap_dirty_lock);
-        list_for_each_safe(p, n, &mdsc->cap_dirty) {
-                if (nci) {
-                        ci = nci;
-                        inode = ninode;
-                        ci->i_ceph_flags &= ~CEPH_I_NOFLUSH;
-                        dout("flush_dirty_caps inode %p (was next inode)\n",
-                             inode);
-                } else {
-                        ci = list_entry(p, struct ceph_inode_info,
-                                        i_dirty_item);
-                        inode = igrab(&ci->vfs_inode);
-                        BUG_ON(!inode);
-                        dout("flush_dirty_caps inode %p\n", inode);
-                }
-                if (n != &mdsc->cap_dirty) {
-                        nci = list_entry(n, struct ceph_inode_info,
-                                         i_dirty_item);
-                        ninode = igrab(&nci->vfs_inode);
-                        BUG_ON(!ninode);
-                        nci->i_ceph_flags |= CEPH_I_NOFLUSH;
-                        dout("flush_dirty_caps next inode %p, noflush\n",
-                             ninode);
-                } else {
-                        nci = NULL;
-                        ninode = NULL;
-                }
+        while (!list_empty(&mdsc->cap_dirty)) {
+                ci = list_first_entry(&mdsc->cap_dirty, struct ceph_inode_info,
+                                      i_dirty_item);
+                inode = igrab(&ci->vfs_inode);
+                dout("flush_dirty_caps %p\n", inode);
                 spin_unlock(&mdsc->cap_dirty_lock);
                 if (inode) {
                         ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH,
@@ -2951,6 +2951,7 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
                 spin_lock(&mdsc->cap_dirty_lock);
         }
         spin_unlock(&mdsc->cap_dirty_lock);
+        dout("flush_dirty_caps done\n");
 }
 
 /*
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 1a867a3601ae..33729e822bb9 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -360,7 +360,7 @@ more:
         rinfo = &fi->last_readdir->r_reply_info;
         dout("readdir frag %x num %d off %d chunkoff %d\n", frag,
              rinfo->dir_nr, off, fi->offset);
-        while (off - fi->offset >= 0 && off - fi->offset < rinfo->dir_nr) {
+        while (off >= fi->offset && off - fi->offset < rinfo->dir_nr) {
                 u64 pos = ceph_make_fpos(frag, off);
                 struct ceph_mds_reply_inode *in =
                         rinfo->dir_in[off - fi->offset].in;
@@ -1066,16 +1066,17 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
         int left;
+        const int bufsize = 1024;
 
         if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
                 return -EISDIR;
 
         if (!cf->dir_info) {
-                cf->dir_info = kmalloc(1024, GFP_NOFS);
+                cf->dir_info = kmalloc(bufsize, GFP_NOFS);
                 if (!cf->dir_info)
                         return -ENOMEM;
                 cf->dir_info_len =
-                        sprintf(cf->dir_info,
+                        snprintf(cf->dir_info, bufsize,
                                 "entries:   %20lld\n"
                                 " files:    %20lld\n"
                                 " subdirs:  %20lld\n"
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index e41056174bf8..a610d3d67488 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -86,6 +86,7 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
 static struct dentry *__fh_to_dentry(struct super_block *sb,
                                      struct ceph_nfs_fh *fh)
 {
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
         struct inode *inode;
         struct dentry *dentry;
         struct ceph_vino vino;
@@ -95,8 +96,24 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
         vino.ino = fh->ino;
         vino.snap = CEPH_NOSNAP;
         inode = ceph_find_inode(sb, vino);
-        if (!inode)
-                return ERR_PTR(-ESTALE);
+        if (!inode) {
+                struct ceph_mds_request *req;
+
+                req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
+                                               USE_ANY_MDS);
+                if (IS_ERR(req))
+                        return ERR_CAST(req);
+
+                req->r_ino1 = vino;
+                req->r_num_caps = 1;
+                err = ceph_mdsc_do_request(mdsc, NULL, req);
+                inode = req->r_target_inode;
+                if (inode)
+                        igrab(inode);
+                ceph_mdsc_put_request(req);
+                if (!inode)
+                        return ERR_PTR(-ESTALE);
+        }
 
         dentry = d_obtain_alias(inode);
         if (IS_ERR(dentry)) {
@@ -148,8 +165,10 @@ static struct dentry *__cfh_to_dentry(struct super_block *sb,
                 snprintf(req->r_path2, 16, "%d", cfh->parent_name_hash);
                 req->r_num_caps = 1;
                 err = ceph_mdsc_do_request(mdsc, NULL, req);
+                inode = req->r_target_inode;
+                if (inode)
+                        igrab(inode);
                 ceph_mdsc_put_request(req);
-                inode = ceph_find_inode(sb, vino);
                 if (!inode)
                         return ERR_PTR(err ? err : -ESTALE);
         }
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d0fae4ce9ba5..79743d146be6 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -578,6 +578,7 @@ static void __register_request(struct ceph_mds_client *mdsc,
         if (dir) {
                 struct ceph_inode_info *ci = ceph_inode(dir);
 
+                ihold(dir);
                 spin_lock(&ci->i_unsafe_lock);
                 req->r_unsafe_dir = dir;
                 list_add_tail(&req->r_unsafe_dir_item, &ci->i_unsafe_dirops);
@@ -598,6 +599,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
                 spin_lock(&ci->i_unsafe_lock);
                 list_del_init(&req->r_unsafe_dir_item);
                 spin_unlock(&ci->i_unsafe_lock);
+
+                iput(req->r_unsafe_dir);
+                req->r_unsafe_dir = NULL;
         }
 
         ceph_mdsc_put_request(req);
@@ -2691,7 +2695,6 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 {
         struct super_block *sb = mdsc->fsc->sb;
         struct inode *inode;
-        struct ceph_inode_info *ci;
         struct dentry *parent, *dentry;
         struct ceph_dentry_info *di;
         int mds = session->s_mds;
@@ -2728,7 +2731,6 @@ static void handle_lease(struct ceph_mds_client *mdsc,
                 dout("handle_lease no inode %llx\n", vino.ino);
                 goto release;
         }
-        ci = ceph_inode(inode);
 
         /* dentry */
         parent = d_find_alias(inode);
@@ -3002,6 +3004,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
         spin_lock_init(&mdsc->snap_flush_lock);
         mdsc->cap_flush_seq = 0;
         INIT_LIST_HEAD(&mdsc->cap_dirty);
+        INIT_LIST_HEAD(&mdsc->cap_dirty_migrating);
         mdsc->num_cap_flushing = 0;
         spin_lock_init(&mdsc->cap_dirty_lock);
         init_waitqueue_head(&mdsc->cap_flushing_wq);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 4e3a9cc0bba6..7d8a0d662d56 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -278,6 +278,7 @@ struct ceph_mds_client {
 
         u64               cap_flush_seq;
         struct list_head  cap_dirty;        /* inodes with dirty caps */
+        struct list_head  cap_dirty_migrating; /* ...that are migration... */
         int               num_cap_flushing; /* # caps we are flushing */
         spinlock_t        cap_dirty_lock;   /* protects above items */
         wait_queue_head_t cap_flushing_wq;
diff --git a/fs/dcache.c b/fs/dcache.c
index 18b2a1f10ed8..37f72ee5bf7c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1220,7 +1220,7 @@ void shrink_dcache_parent(struct dentry * parent)
 EXPORT_SYMBOL(shrink_dcache_parent);
 
 /*
- * Scan `nr' dentries and return the number which remain.
+ * Scan `sc->nr_slab_to_reclaim' dentries and return the number which remain.
  *
  * We need to avoid reentering the filesystem if the caller is performing a
  * GFP_NOFS allocation attempt.  One example deadlock is:
@@ -1231,8 +1231,12 @@ EXPORT_SYMBOL(shrink_dcache_parent);
  *
  * In this case we return -1 to tell the caller that we baled.
  */
-static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int shrink_dcache_memory(struct shrinker *shrink,
+                                struct shrink_control *sc)
 {
+        int nr = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
+
         if (nr) {
                 if (!(gfp_mask & __GFP_FS))
                         return -1;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 98b77c89494c..c00e055b6282 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -40,9 +40,12 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 static void drop_slab(void)
 {
         int nr_objects;
+        struct shrink_control shrink = {
+                .gfp_mask = GFP_KERNEL,
+        };
 
         do {
-                nr_objects = shrink_slab(1000, GFP_KERNEL, 1000);
+                nr_objects = shrink_slab(&shrink, 1000, 1000);
         } while (nr_objects > 10);
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index c1cf372f17a7..936f5776655c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -200,7 +200,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 
 #ifdef CONFIG_STACK_GROWSUP
         if (write) {
-                ret = expand_stack_downwards(bprm->vma, pos);
+                ret = expand_downwards(bprm->vma, pos);
                 if (ret < 0)
                         return NULL;
         }
@@ -600,7 +600,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
         unsigned long length = old_end - old_start;
         unsigned long new_start = old_start - shift;
         unsigned long new_end = old_end - shift;
-        struct mmu_gather *tlb;
+        struct mmu_gather tlb;
 
         BUG_ON(new_start > new_end);
 
@@ -626,12 +626,12 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
                 return -ENOMEM;
 
         lru_add_drain();
-        tlb = tlb_gather_mmu(mm, 0);
+        tlb_gather_mmu(&tlb, mm, 0);
         if (new_end > old_start) {
                 /*
                  * when the old and new regions overlap clear from new_end.
                  */
-                free_pgd_range(tlb, new_end, old_end, new_end,
+                free_pgd_range(&tlb, new_end, old_end, new_end,
                         vma->vm_next ? vma->vm_next->vm_start : 0);
         } else {
                 /*
@@ -640,10 +640,10 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
                  * have constraints on va-space that make this illegal (IA64) -
                  * for the others its just a little faster.
                  */
-                free_pgd_range(tlb, old_start, old_end, new_end,
+                free_pgd_range(&tlb, old_start, old_end, new_end,
                         vma->vm_next ? vma->vm_next->vm_start : 0);
         }
-        tlb_finish_mmu(tlb, new_end, old_end);
+        tlb_finish_mmu(&tlb, new_end, old_end);
 
         /*
          * Shrink the vma to just the new range.  Always succeeds.
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 48a18f184d50..30afdfa7aec7 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -33,8 +33,6 @@ void fscache_enqueue_operation(struct fscache_operation *op)
         _enter("{OBJ%x OP%x,%u}",
                op->object->debug_id, op->debug_id, atomic_read(&op->usage));
 
-        fscache_set_op_state(op, "EnQ");
-
         ASSERT(list_empty(&op->pend_link));
         ASSERT(op->processor != NULL);
         ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
@@ -66,8 +64,6 @@ EXPORT_SYMBOL(fscache_enqueue_operation);
 static void fscache_run_op(struct fscache_object *object,
                            struct fscache_operation *op)
 {
-        fscache_set_op_state(op, "Run");
-
         object->n_in_progress++;
         if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
                 wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
@@ -88,8 +84,6 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 
         _enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
 
-        fscache_set_op_state(op, "SubmitX");
-
         spin_lock(&object->lock);
         ASSERTCMP(object->n_ops, >=, object->n_in_progress);
         ASSERTCMP(object->n_ops, >=, object->n_exclusive);
@@ -194,8 +188,6 @@ int fscache_submit_op(struct fscache_object *object,
 
         ASSERTCMP(atomic_read(&op->usage), >, 0);
 
-        fscache_set_op_state(op, "Submit");
-
         spin_lock(&object->lock);
         ASSERTCMP(object->n_ops, >=, object->n_in_progress);
         ASSERTCMP(object->n_ops, >=, object->n_exclusive);
@@ -335,8 +327,6 @@ void fscache_put_operation(struct fscache_operation *op)
         if (!atomic_dec_and_test(&op->usage))
                 return;
 
-        fscache_set_op_state(op, "Put");
-
         _debug("PUT OP");
         if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
                 BUG();
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 41c441c2058d..a2a5d19ece6a 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -155,11 +155,9 @@ static void fscache_attr_changed_op(struct fscache_operation *op)
         fscache_stat(&fscache_n_attr_changed_calls);
 
         if (fscache_object_is_active(object)) {
-                fscache_set_op_state(op, "CallFS");
                 fscache_stat(&fscache_n_cop_attr_changed);
                 ret = object->cache->ops->attr_changed(object);
                 fscache_stat_d(&fscache_n_cop_attr_changed);
-                fscache_set_op_state(op, "Done");
                 if (ret < 0)
                         fscache_abort_object(object);
         }
@@ -190,7 +188,6 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 
         fscache_operation_init(op, fscache_attr_changed_op, NULL);
         op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE);
-        fscache_set_op_name(op, "Attr");
 
         spin_lock(&cookie->lock);
 
@@ -257,7 +254,6 @@ static struct fscache_retrieval *fscache_alloc_retrieval(
         op->context     = context;
         op->start_time  = jiffies;
         INIT_LIST_HEAD(&op->to_do);
-        fscache_set_op_name(&op->op, "Retr");
         return op;
 }
 
@@ -368,7 +364,6 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
                 _leave(" = -ENOMEM");
                 return -ENOMEM;
         }
-        fscache_set_op_name(&op->op, "RetrRA1");
 
         spin_lock(&cookie->lock);
 
@@ -487,7 +482,6 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
         op = fscache_alloc_retrieval(mapping, end_io_func, context);
         if (!op)
                 return -ENOMEM;
-        fscache_set_op_name(&op->op, "RetrRAN");
 
         spin_lock(&cookie->lock);
 
@@ -589,7 +583,6 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
         op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
         if (!op)
                 return -ENOMEM;
-        fscache_set_op_name(&op->op, "RetrAL1");
 
         spin_lock(&cookie->lock);
 
@@ -662,8 +655,6 @@ static void fscache_write_op(struct fscache_operation *_op)
 
         _enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage));
 
-        fscache_set_op_state(&op->op, "GetPage");
-
         spin_lock(&object->lock);
         cookie = object->cookie;
 
@@ -698,15 +689,12 @@ static void fscache_write_op(struct fscache_operation *_op)
         spin_unlock(&cookie->stores_lock);
         spin_unlock(&object->lock);
 
-        fscache_set_op_state(&op->op, "Store");
         fscache_stat(&fscache_n_store_pages);
         fscache_stat(&fscache_n_cop_write_page);
         ret = object->cache->ops->write_page(op, page);
         fscache_stat_d(&fscache_n_cop_write_page);
-        fscache_set_op_state(&op->op, "EndWrite");
         fscache_end_page_write(object, page);
         if (ret < 0) {
-                fscache_set_op_state(&op->op, "Abort");
                 fscache_abort_object(object);
         } else {
                 fscache_enqueue_operation(&op->op);
@@ -778,7 +766,6 @@ int __fscache_write_page(struct fscache_cookie *cookie,
         fscache_operation_init(&op->op, fscache_write_op,
                                fscache_release_write_op);
         op->op.flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_WAITING);
-        fscache_set_op_name(&op->op, "Write1");
 
         ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
         if (ret < 0)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a2a6abbccc07..2792a790e50b 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1346,11 +1346,14 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 }
 
 
-static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int gfs2_shrink_glock_memory(struct shrinker *shrink,
+                                    struct shrink_control *sc)
 {
         struct gfs2_glock *gl;
         int may_demote;
         int nr_skipped = 0;
+        int nr = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
         LIST_HEAD(skipped);
 
         if (nr == 0)
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index e23d9864c418..42e8d23bc047 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -38,6 +38,7 @@
 
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
@@ -77,19 +78,20 @@ static LIST_HEAD(qd_lru_list);
 static atomic_t qd_lru_count = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(qd_lru_lock);
 
-int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
 {
         struct gfs2_quota_data *qd;
         struct gfs2_sbd *sdp;
+        int nr_to_scan = sc->nr_to_scan;
 
-        if (nr == 0)
+        if (nr_to_scan == 0)
                 goto out;
 
-        if (!(gfp_mask & __GFP_FS))
+        if (!(sc->gfp_mask & __GFP_FS))
                 return -1;
 
         spin_lock(&qd_lru_lock);
-        while (nr && !list_empty(&qd_lru_list)) {
+        while (nr_to_scan && !list_empty(&qd_lru_list)) {
                 qd = list_entry(qd_lru_list.next,
                                 struct gfs2_quota_data, qd_reclaim);
                 sdp = qd->qd_gl->gl_sbd;
@@ -110,7 +112,7 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
                 spin_unlock(&qd_lru_lock);
                 kmem_cache_free(gfs2_quotad_cachep, qd);
                 spin_lock(&qd_lru_lock);
-                nr--;
+                nr_to_scan--;
         }
         spin_unlock(&qd_lru_lock);
 
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index e7d236ca48bd..90bf1c302a98 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -12,6 +12,7 @@
 
 struct gfs2_inode;
 struct gfs2_sbd;
+struct shrink_control;
 
 #define NO_QUOTA_CHANGE ((u32)-1)
 
@@ -51,7 +52,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
         return ret;
 }
 
-extern int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask);
+extern int gfs2_shrink_qd_memory(struct shrinker *shrink,
+                                 struct shrink_control *sc);
 extern const struct quotactl_ops gfs2_quotactl_ops;
 
 #endif /* __QUOTA_DOT_H__ */
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b9eeb1cd03ff..e7a035781b7d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -412,10 +412,10 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
         pgoff = offset >> PAGE_SHIFT;
 
         i_size_write(inode, offset);
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         if (!prio_tree_empty(&mapping->i_mmap))
                 hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
         truncate_hugepages(inode, offset);
         return 0;
 }
diff --git a/fs/inode.c b/fs/inode.c
index 05f4fa521325..990d284877a1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -326,12 +326,11 @@ void address_space_init_once(struct address_space *mapping)
         memset(mapping, 0, sizeof(*mapping));
         INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
         spin_lock_init(&mapping->tree_lock);
-        spin_lock_init(&mapping->i_mmap_lock);
+        mutex_init(&mapping->i_mmap_mutex);
         INIT_LIST_HEAD(&mapping->private_list);
         spin_lock_init(&mapping->private_lock);
         INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
         INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
-        mutex_init(&mapping->unmap_mutex);
 }
 EXPORT_SYMBOL(address_space_init_once);
 
@@ -752,8 +751,12 @@ static void prune_icache(int nr_to_scan)
  * This function is passed the number of inodes to scan, and it returns the
  * total number of remaining possibly-reclaimable inodes.
  */
-static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int shrink_icache_memory(struct shrinker *shrink,
+                                struct shrink_control *sc)
 {
+        int nr = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
+
         if (nr) {
                 /*
                  * Nasty deadlock avoidance.  We may hold various FS locks,
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 2f174be06555..8c32ef3ba88e 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -90,7 +90,8 @@ static DEFINE_SPINLOCK(mb_cache_spinlock);
  * What the mbcache registers as to get shrunk dynamically.
  */
 
-static int mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask);
+static int mb_cache_shrink_fn(struct shrinker *shrink,
+                              struct shrink_control *sc);
 
 static struct shrinker mb_cache_shrinker = {
         .shrink = mb_cache_shrink_fn,
@@ -156,18 +157,19 @@ forget:
  * gets low.
  *
  * @shrink: (ignored)
- * @nr_to_scan: Number of objects to scan
- * @gfp_mask: (ignored)
+ * @sc: shrink_control passed from reclaim
  *
  * Returns the number of objects which are present in the cache.
  */
 static int
-mb_cache_shrink_fn(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+mb_cache_shrink_fn(struct shrinker *shrink, struct shrink_control *sc)
 {
         LIST_HEAD(free_list);
         struct mb_cache *cache;
         struct mb_cache_entry *entry, *tmp;
         int count = 0;
+        int nr_to_scan = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
 
         mb_debug("trying to free %d entries", nr_to_scan);
         spin_lock(&mb_cache_spinlock);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 0250e4ce4893..202f370526a7 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -461,7 +461,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 #endif
         struct ncp_entry_info finfo;
 
-        data.wdog_pid = NULL;
+        memset(&data, 0, sizeof(data));
         server = kzalloc(sizeof(struct ncp_server), GFP_KERNEL);
         if (!server)
                 return -ENOMEM;
@@ -496,7 +496,6 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
                                 struct ncp_mount_data_v4* md = (struct ncp_mount_data_v4*)raw_data;
 
                                 data.flags = md->flags;
-                                data.int_flags = 0;
                                 data.mounted_uid = md->mounted_uid;
                                 data.wdog_pid = find_get_pid(md->wdog_pid);
                                 data.ncp_fd = md->ncp_fd;
@@ -507,7 +506,6 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
                                 data.file_mode = md->file_mode;
                                 data.dir_mode = md->dir_mode;
                                 data.info_fd = -1;
-                                data.mounted_vol[0] = 0;
                         }
                         break;
                 default:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7237672216c8..424e47773a84 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2042,11 +2042,14 @@ static void nfs_access_free_list(struct list_head *head)
         }
 }
 
-int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+int nfs_access_cache_shrinker(struct shrinker *shrink,
+                              struct shrink_control *sc)
 {
         LIST_HEAD(head);
         struct nfs_inode *nfsi, *next;
         struct nfs_access_entry *cache;
+        int nr_to_scan = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
 
         if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
                 return (nr_to_scan == 0) ? 0 : -1;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index ce118ce885dd..2df6ca7b5898 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -234,7 +234,7 @@ extern int nfs_init_client(struct nfs_client *clp,
 
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
-                                        int nr_to_scan, gfp_t gfp_mask);
+                                        struct shrink_control *sc);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index d545e97d99c3..8ed4d3433199 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -255,7 +255,11 @@ ssize_t part_discard_alignment_show(struct device *dev,
                                    struct device_attribute *attr, char *buf)
 {
         struct hd_struct *p = dev_to_part(dev);
-        return sprintf(buf, "%u\n", p->discard_alignment);
+        struct gendisk *disk = dev_to_disk(dev);
+
+        return sprintf(buf, "%u\n",
+                        queue_limit_discard_alignment(&disk->queue->limits,
+                                                        p->start_sect));
 }
 
 ssize_t part_stat_show(struct device *dev,
@@ -449,8 +453,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
         p->start_sect = start;
         p->alignment_offset =
                 queue_limit_alignment_offset(&disk->queue->limits, start);
-        p->discard_alignment =
-                queue_limit_discard_alignment(&disk->queue->limits, start);
         p->nr_sects = len;
         p->partno = partno;
         p->policy = get_disk_ro(disk);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c03e8d3a3a5b..3763b436e69d 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -61,6 +61,14 @@ extern const struct file_operations proc_pagemap_operations;
 extern const struct file_operations proc_net_operations;
 extern const struct inode_operations proc_net_inode_operations;
 
+struct proc_maps_private {
+        struct pid *pid;
+        struct task_struct *task;
+#ifdef CONFIG_MMU
+        struct vm_area_struct *tail_vma;
+#endif
+};
+
 void proc_init_inodecache(void);
 
 static inline struct pid *proc_pid(struct inode *inode)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 318d8654989b..2c9db29ea358 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -858,7 +858,192 @@ const struct file_operations proc_pagemap_operations = {
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
 #ifdef CONFIG_NUMA
-extern int show_numa_map(struct seq_file *m, void *v);
+
+struct numa_maps {
+        struct vm_area_struct *vma;
+        unsigned long pages;
+        unsigned long anon;
+        unsigned long active;
+        unsigned long writeback;
+        unsigned long mapcount_max;
+        unsigned long dirty;
+        unsigned long swapcache;
+        unsigned long node[MAX_NUMNODES];
+};
+
+struct numa_maps_private {
+        struct proc_maps_private proc_maps;
+        struct numa_maps md;
+};
+
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty)
+{
+        int count = page_mapcount(page);
+
+        md->pages++;
+        if (pte_dirty || PageDirty(page))
+                md->dirty++;
+
+        if (PageSwapCache(page))
+                md->swapcache++;
+
+        if (PageActive(page) || PageUnevictable(page))
+                md->active++;
+
+        if (PageWriteback(page))
+                md->writeback++;
+
+        if (PageAnon(page))
+                md->anon++;
+
+        if (count > md->mapcount_max)
+                md->mapcount_max = count;
+
+        md->node[page_to_nid(page)]++;
+}
+
+static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
+                unsigned long end, struct mm_walk *walk)
+{
+        struct numa_maps *md;
+        spinlock_t *ptl;
+        pte_t *orig_pte;
+        pte_t *pte;
+
+        md = walk->private;
+        orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+        do {
+                struct page *page;
+                int nid;
+
+                if (!pte_present(*pte))
+                        continue;
+
+                page = vm_normal_page(md->vma, addr, *pte);
+                if (!page)
+                        continue;
+
+                if (PageReserved(page))
+                        continue;
+
+                nid = page_to_nid(page);
+                if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+                        continue;
+
+                gather_stats(page, md, pte_dirty(*pte));
+
+        } while (pte++, addr += PAGE_SIZE, addr != end);
+        pte_unmap_unlock(orig_pte, ptl);
+        return 0;
+}
+#ifdef CONFIG_HUGETLB_PAGE
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+                unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+        struct numa_maps *md;
+        struct page *page;
+
+        if (pte_none(*pte))
+                return 0;
+
+        page = pte_page(*pte);
+        if (!page)
+                return 0;
+
+        md = walk->private;
+        gather_stats(page, md, pte_dirty(*pte));
+        return 0;
+}
+
+#else
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+                unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+        return 0;
+}
+#endif
+
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
+static int show_numa_map(struct seq_file *m, void *v)
+{
+        struct numa_maps_private *numa_priv = m->private;
+        struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+        struct vm_area_struct *vma = v;
+        struct numa_maps *md = &numa_priv->md;
+        struct file *file = vma->vm_file;
+        struct mm_struct *mm = vma->vm_mm;
+        struct mm_walk walk = {};
+        struct mempolicy *pol;
+        int n;
+        char buffer[50];
+
+        if (!mm)
+                return 0;
+
+        /* Ensure we start with an empty set of numa_maps statistics. */
+        memset(md, 0, sizeof(*md));
+
+        md->vma = vma;
+
+        walk.hugetlb_entry = gather_hugetbl_stats;
+        walk.pmd_entry = gather_pte_stats;
+        walk.private = md;
+        walk.mm = mm;
+
+        pol = get_vma_policy(proc_priv->task, vma, vma->vm_start);
+        mpol_to_str(buffer, sizeof(buffer), pol, 0);
+        mpol_cond_put(pol);
+
+        seq_printf(m, "%08lx %s", vma->vm_start, buffer);
+
+        if (file) {
+                seq_printf(m, " file=");
+                seq_path(m, &file->f_path, "\n\t= ");
+        } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
+                seq_printf(m, " heap");
+        } else if (vma->vm_start <= mm->start_stack &&
+                        vma->vm_end >= mm->start_stack) {
+                seq_printf(m, " stack");
+        }
+
+        walk_page_range(vma->vm_start, vma->vm_end, &walk);
+
+        if (!md->pages)
+                goto out;
+
+        if (md->anon)
+                seq_printf(m, " anon=%lu", md->anon);
+
+        if (md->dirty)
+                seq_printf(m, " dirty=%lu", md->dirty);
+
+        if (md->pages != md->anon && md->pages != md->dirty)
+                seq_printf(m, " mapped=%lu", md->pages);
+
+        if (md->mapcount_max > 1)
+                seq_printf(m, " mapmax=%lu", md->mapcount_max);
+
+        if (md->swapcache)
+                seq_printf(m, " swapcache=%lu", md->swapcache);
+
+        if (md->active < md->pages && !is_vm_hugetlb_page(vma))
+                seq_printf(m, " active=%lu", md->active);
+
+        if (md->writeback)
+                seq_printf(m, " writeback=%lu", md->writeback);
+
+        for_each_node_state(n, N_HIGH_MEMORY)
+                if (md->node[n])
+                        seq_printf(m, " N%d=%lu", n, md->node[n]);
+out:
+        seq_putc(m, '\n');
+
+        if (m->count < m->size)
+                m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+        return 0;
+}
 
 static const struct seq_operations proc_pid_numa_maps_op = {
         .start  = m_start,
@@ -869,7 +1054,20 @@ static const struct seq_operations proc_pid_numa_maps_op = {
 
 static int numa_maps_open(struct inode *inode, struct file *file)
 {
-        return do_maps_open(inode, file, &proc_pid_numa_maps_op);
+        struct numa_maps_private *priv;
+        int ret = -ENOMEM;
+        priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+        if (priv) {
+                priv->proc_maps.pid = proc_pid(inode);
+                ret = seq_open(file, &proc_pid_numa_maps_op);
+                if (!ret) {
+                        struct seq_file *m = file->private_data;
+                        m->private = priv;
+                } else {
+                        kfree(priv);
+                }
+        }
+        return ret;
 }
 
 const struct file_operations proc_numa_maps_operations = {
@@ -878,4 +1076,4 @@ const struct file_operations proc_numa_maps_operations = {
         .llseek         = seq_lseek,
         .release        = seq_release_private,
 };
-#endif
+#endif /* CONFIG_NUMA */
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index d3c032f5fa0a..5b572c89e6c4 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -691,8 +691,11 @@ static void prune_dqcache(int count)
  * This is called from kswapd when we think we need some
  * more memory
  */
-static int shrink_dqcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int shrink_dqcache_memory(struct shrinker *shrink,
+                                 struct shrink_control *sc)
 {
+        int nr = sc->nr_to_scan;
+
         if (nr) {
                 spin_lock(&dq_list_lock);
                 prune_dqcache(nr);
diff --git a/fs/splice.c b/fs/splice.c
index 50a5d978da16..aa866d309695 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -162,6 +162,14 @@ static const struct pipe_buf_operations user_page_pipe_buf_ops = {
         .get = generic_pipe_buf_get,
 };
 
+static void wakeup_pipe_readers(struct pipe_inode_info *pipe)
+{
+        smp_mb();
+        if (waitqueue_active(&pipe->wait))
+                wake_up_interruptible(&pipe->wait);
+        kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+}
+
 /**
  * splice_to_pipe - fill passed data into a pipe
  * @pipe:       pipe to fill
@@ -247,12 +255,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 
         pipe_unlock(pipe);
 
-        if (do_wakeup) {
-                smp_mb();
-                if (waitqueue_active(&pipe->wait))
-                        wake_up_interruptible(&pipe->wait);
-                kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
-        }
+        if (do_wakeup)
+                wakeup_pipe_readers(pipe);
 
         while (page_nr < spd_pages)
                 spd->spd_release(spd, page_nr++);
@@ -1892,12 +1896,9 @@ retry:
         /*
          * If we put data in the output pipe, wakeup any potential readers.
          */
-        if (ret > 0) {
-                smp_mb();
-                if (waitqueue_active(&opipe->wait))
-                        wake_up_interruptible(&opipe->wait);
-                kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
-        }
+        if (ret > 0)
+                wakeup_pipe_readers(opipe);
+
         if (input_wakeup)
                 wakeup_pipe_writers(ipipe);
 
@@ -1976,12 +1977,8 @@ static int link_pipe(struct pipe_inode_info *ipipe,
         /*
          * If we put data in the output pipe, wakeup any potential readers.
          */
-        if (ret > 0) {
-                smp_mb();
-                if (waitqueue_active(&opipe->wait))
-                        wake_up_interruptible(&opipe->wait);
-                kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
-        }
+        if (ret > 0)
+                wakeup_pipe_readers(opipe);
 
         return ret;
 }
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 52b2b5da566e..5e68099db2a5 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1422,12 +1422,12 @@ restart:
 int
 xfs_buftarg_shrink(
         struct shrinker         *shrink,
-        int                     nr_to_scan,
-        gfp_t                   mask)
+        struct shrink_control   *sc)
 {
         struct xfs_buftarg      *btp = container_of(shrink,
                                         struct xfs_buftarg, bt_shrinker);
         struct xfs_buf          *bp;
+        int nr_to_scan = sc->nr_to_scan;
         LIST_HEAD(dispose);
 
         if (!nr_to_scan)
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index cb1bb2080e44..8ecad5ff9f9b 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -1032,13 +1032,14 @@ xfs_reclaim_inodes(
 static int
 xfs_reclaim_inode_shrink(
         struct shrinker *shrink,
-        int             nr_to_scan,
-        gfp_t           gfp_mask)
+        struct shrink_control *sc)
 {
         struct xfs_mount *mp;
         struct xfs_perag *pag;
         xfs_agnumber_t  ag;
         int             reclaimable;
+        int nr_to_scan = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
 
         mp = container_of(shrink, struct xfs_mount, m_inode_shrink);
         if (nr_to_scan) {
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 69228aa8605a..b94dace4e785 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -60,7 +60,7 @@ STATIC void	xfs_qm_list_destroy(xfs_dqlist_t *);
 
 STATIC int      xfs_qm_init_quotainos(xfs_mount_t *);
 STATIC int      xfs_qm_init_quotainfo(xfs_mount_t *);
-STATIC int      xfs_qm_shake(struct shrinker *, int, gfp_t);
+STATIC int      xfs_qm_shake(struct shrinker *, struct shrink_control *);
 
 static struct shrinker xfs_qm_shaker = {
         .shrink = xfs_qm_shake,
@@ -2009,10 +2009,10 @@ xfs_qm_shake_freelist(
 STATIC int
 xfs_qm_shake(
         struct shrinker *shrink,
-        int             nr_to_scan,
-        gfp_t           gfp_mask)
+        struct shrink_control *sc)
 {
         int     ndqused, nfree, n;
+        gfp_t gfp_mask = sc->gfp_mask;
 
         if (!kmem_shake_allow(gfp_mask))
                 return 0;
diff --git a/include/asm-generic/audit_change_attr.h b/include/asm-generic/audit_change_attr.h
index bcbab3e4a3be..89b73e5d0fd0 100644
--- a/include/asm-generic/audit_change_attr.h
+++ b/include/asm-generic/audit_change_attr.h
@@ -1,4 +1,6 @@
+#ifdef __NR_chmod
 __NR_chmod,
+#endif
 __NR_fchmod,
 #ifdef __NR_chown
 __NR_chown,
@@ -20,7 +22,9 @@ __NR_chown32,
 __NR_fchown32,
 __NR_lchown32,
 #endif
+#ifdef __NR_link
 __NR_link,
+#endif
 #ifdef __NR_linkat
 __NR_linkat,
 #endif
diff --git a/include/asm-generic/audit_dir_write.h b/include/asm-generic/audit_dir_write.h
index 6621bd82cbe8..7b61db4fe72b 100644
--- a/include/asm-generic/audit_dir_write.h
+++ b/include/asm-generic/audit_dir_write.h
@@ -1,13 +1,27 @@
+#ifdef __NR_rename
 __NR_rename,
+#endif
+#ifdef __NR_mkdir
 __NR_mkdir,
+#endif
+#ifdef __NR_rmdir
 __NR_rmdir,
+#endif
 #ifdef __NR_creat
 __NR_creat,
 #endif
+#ifdef __NR_link
 __NR_link,
+#endif
+#ifdef __NR_unlink
 __NR_unlink,
+#endif
+#ifdef __NR_symlink
 __NR_symlink,
+#endif
+#ifdef __NR_mknod
 __NR_mknod,
+#endif
 #ifdef __NR_mkdirat
 __NR_mkdirat,
 __NR_mknodat,
diff --git a/include/asm-generic/audit_read.h b/include/asm-generic/audit_read.h
index 0e87464d9847..3b249cb857dc 100644
--- a/include/asm-generic/audit_read.h
+++ b/include/asm-generic/audit_read.h
@@ -1,4 +1,6 @@
+#ifdef __NR_readlink
 __NR_readlink,
+#endif
 __NR_quotactl,
 __NR_listxattr,
 __NR_llistxattr,
@@ -6,3 +8,6 @@ __NR_flistxattr,
 __NR_getxattr,
 __NR_lgetxattr,
 __NR_fgetxattr,
+#ifdef __NR_readlinkat
+__NR_readlinkat,
+#endif
diff --git a/include/asm-generic/audit_write.h b/include/asm-generic/audit_write.h
index c5f1c2c920e2..e7020c57b13b 100644
--- a/include/asm-generic/audit_write.h
+++ b/include/asm-generic/audit_write.h
@@ -4,7 +4,9 @@ __NR_acct,
 __NR_swapon,
 #endif
 __NR_quotactl,
+#ifdef __NR_truncate
 __NR_truncate,
+#endif
 #ifdef __NR_truncate64
 __NR_truncate64,
 #endif
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 57b5c3c82e86..87bc536ccde3 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -24,7 +24,10 @@
 #define flush_cache_vunmap(start, end)          do { } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-        memcpy(dst, src, len)
+        do { \
+                memcpy(dst, src, len); \
+                flush_icache_user_range(vma, page, vaddr, len); \
+        } while (0)
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
         memcpy(dst, src, len)
 
diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
index 587566f95f6c..61fa862fe08d 100644
--- a/include/asm-generic/resource.h
+++ b/include/asm-generic/resource.h
@@ -78,7 +78,7 @@
         [RLIMIT_CORE]           = {              0,  RLIM_INFINITY },   \
         [RLIMIT_RSS]            = {  RLIM_INFINITY,  RLIM_INFINITY },   \
         [RLIMIT_NPROC]          = {              0,              0 },   \
-        [RLIMIT_NOFILE]         = {       INR_OPEN,       INR_OPEN },   \
+        [RLIMIT_NOFILE]         = {   INR_OPEN_CUR,   INR_OPEN_MAX },   \
         [RLIMIT_MEMLOCK]        = {    MLOCK_LIMIT,    MLOCK_LIMIT },   \
         [RLIMIT_AS]             = {  RLIM_INFINITY,  RLIM_INFINITY },   \
         [RLIMIT_LOCKS]          = {  RLIM_INFINITY,  RLIM_INFINITY },   \
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index e43f9766259f..e58fa777fa09 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -5,6 +5,8 @@
  * Copyright 2001 Red Hat, Inc.
  * Based on code from mm/memory.c Copyright Linus Torvalds and others.
  *
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
  * 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; either version
@@ -17,97 +19,111 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
- * For UP we don't need to worry about TLB flush
- * and page free order so much..
+ * Semi RCU freeing of the page directories.
+ *
+ * This is needed by some architectures to implement software pagetable walkers.
+ *
+ * gup_fast() and other software pagetable walkers do a lockless page-table
+ * walk and therefore needs some synchronization with the freeing of the page
+ * directories. The chosen means to accomplish that is by disabling IRQs over
+ * the walk.
+ *
+ * Architectures that use IPIs to flush TLBs will then automagically DTRT,
+ * since we unlink the page, flush TLBs, free the page. Since the disabling of
+ * IRQs delays the completion of the TLB flush we can never observe an already
+ * freed page.
+ *
+ * Architectures that do not have this (PPC) need to delay the freeing by some
+ * other means, this is that means.
+ *
+ * What we do is batch the freed directory pages (tables) and RCU free them.
+ * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
+ * holds off grace periods.
+ *
+ * However, in order to batch these pages we need to allocate storage, this
+ * allocation is deep inside the MM code and can thus easily fail on memory
+ * pressure. To guarantee progress we fall back to single table freeing, see
+ * the implementation of tlb_remove_table_one().
+ *
  */
-#ifdef CONFIG_SMP
-  #ifdef ARCH_FREE_PTR_NR
-    #define FREE_PTR_NR   ARCH_FREE_PTR_NR
-  #else
-    #define FREE_PTE_NR 506
-  #endif
-  #define tlb_fast_mode(tlb) ((tlb)->nr == ~0U)
-#else
-  #define FREE_PTE_NR   1
-  #define tlb_fast_mode(tlb) 1
+struct mmu_table_batch {
+        struct rcu_head         rcu;
+        unsigned int            nr;
+        void                    *tables[0];
+};
+
+#define MAX_TABLE_BATCH         \
+        ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
 #endif
 
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
+/*
+ * If we can't allocate a page to make a big batch of page pointers
+ * to work on, then just handle a few from the on-stack structure.
  */
-struct mmu_gather {
-        struct mm_struct        *mm;
-        unsigned int            nr;     /* set to ~0U means fast mode */
-        unsigned int            need_flush;/* Really unmapped some ptes? */
-        unsigned int            fullmm; /* non-zero means full mm flush */
-        struct page *           pages[FREE_PTE_NR];
+#define MMU_GATHER_BUNDLE       8
+
+struct mmu_gather_batch {
+        struct mmu_gather_batch *next;
+        unsigned int            nr;
+        unsigned int            max;
+        struct page             *pages[0];
 };
 
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
+#define MAX_GATHER_BATCH        \
+        ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
 
-/* tlb_gather_mmu
- *      Return a pointer to an initialized struct mmu_gather.
+/* struct mmu_gather is an opaque type used by the mm code for passing around
+ * any data needed by arch specific code for tlb_remove_page.
  */
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
-{
-        struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
-        tlb->mm = mm;
+struct mmu_gather {
+        struct mm_struct        *mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        struct mmu_table_batch  *batch;
+#endif
+        unsigned int            need_flush : 1, /* Did free PTEs */
+                                fast_mode  : 1; /* No batching   */
 
-        /* Use fast mode if only one CPU is online */
-        tlb->nr = num_online_cpus() > 1 ? 0U : ~0U;
+        unsigned int            fullmm;
 
-        tlb->fullmm = full_mm_flush;
+        struct mmu_gather_batch *active;
+        struct mmu_gather_batch local;
+        struct page             *__pages[MMU_GATHER_BUNDLE];
+};
 
-        return tlb;
-}
+#define HAVE_GENERIC_MMU_GATHER
 
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+static inline int tlb_fast_mode(struct mmu_gather *tlb)
 {
-        if (!tlb->need_flush)
-                return;
-        tlb->need_flush = 0;
-        tlb_flush(tlb);
-        if (!tlb_fast_mode(tlb)) {
-                free_pages_and_swap_cache(tlb->pages, tlb->nr);
-                tlb->nr = 0;
-        }
+#ifdef CONFIG_SMP
+        return tlb->fast_mode;
+#else
+        /*
+         * For UP we don't need to worry about TLB flush
+         * and page free order so much..
+         */
+        return 1;
+#endif
 }
 
-/* tlb_finish_mmu
- *      Called at the end of the shootdown operation to free up any resources
- *      that were required.
- */
-static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-        tlb_flush_mmu(tlb, start, end);
-
-        /* keep the page table cache within bounds */
-        check_pgt_cache();
-
-        put_cpu_var(mmu_gathers);
-}
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
+void tlb_flush_mmu(struct mmu_gather *tlb);
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end);
+int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
 
 /* tlb_remove_page
- *      Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- *      handling the additional races in SMP caused by other CPUs caching valid
- *      mappings in their TLBs.
+ *      Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
+ *      required.
  */
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-        tlb->need_flush = 1;
-        if (tlb_fast_mode(tlb)) {
-                free_page_and_swap_cache(page);
-                return;
-        }
-        tlb->pages[tlb->nr++] = page;
-        if (tlb->nr >= FREE_PTE_NR)
-                tlb_flush_mmu(tlb, 0, 0);
+        if (!__tlb_remove_page(tlb, page))
+                tlb_flush_mmu(tlb);
 }
 
 /**
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 07c40d5149de..33d524704883 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -24,16 +24,24 @@
 #define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
 #endif
 
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
 #define __NR_io_setup 0
-__SYSCALL(__NR_io_setup, sys_io_setup)
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
 #define __NR_io_destroy 1
 __SYSCALL(__NR_io_destroy, sys_io_destroy)
 #define __NR_io_submit 2
-__SYSCALL(__NR_io_submit, sys_io_submit)
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
 #define __NR_io_cancel 3
 __SYSCALL(__NR_io_cancel, sys_io_cancel)
 #define __NR_io_getevents 4
-__SYSCALL(__NR_io_getevents, sys_io_getevents)
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
 
 /* fs/xattr.c */
 #define __NR_setxattr 5
@@ -67,7 +75,7 @@ __SYSCALL(__NR_getcwd, sys_getcwd)
 
 /* fs/cookies.c */
 #define __NR_lookup_dcookie 18
-__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie)
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
 
 /* fs/eventfd.c */
 #define __NR_eventfd2 19
@@ -79,7 +87,7 @@ __SYSCALL(__NR_epoll_create1, sys_epoll_create1)
 #define __NR_epoll_ctl 21
 __SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
 #define __NR_epoll_pwait 22
-__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait)
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
 
 /* fs/fcntl.c */
 #define __NR_dup 23
@@ -87,7 +95,7 @@ __SYSCALL(__NR_dup, sys_dup)
 #define __NR_dup3 24
 __SYSCALL(__NR_dup3, sys_dup3)
 #define __NR3264_fcntl 25
-__SC_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl)
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
 
 /* fs/inotify_user.c */
 #define __NR_inotify_init1 26
@@ -99,7 +107,7 @@ __SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
 
 /* fs/ioctl.c */
 #define __NR_ioctl 29
-__SYSCALL(__NR_ioctl, sys_ioctl)
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
 
 /* fs/ioprio.c */
 #define __NR_ioprio_set 30
@@ -129,26 +137,30 @@ __SYSCALL(__NR_renameat, sys_renameat)
 #define __NR_umount2 39
 __SYSCALL(__NR_umount2, sys_umount)
 #define __NR_mount 40
-__SYSCALL(__NR_mount, sys_mount)
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
 #define __NR_pivot_root 41
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 
 /* fs/nfsctl.c */
 #define __NR_nfsservctl 42
-__SYSCALL(__NR_nfsservctl, sys_nfsservctl)
+__SC_COMP(__NR_nfsservctl, sys_nfsservctl, compat_sys_nfsservctl)
 
 /* fs/open.c */
 #define __NR3264_statfs 43
-__SC_3264(__NR3264_statfs, sys_statfs64, sys_statfs)
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+               compat_sys_statfs64)
 #define __NR3264_fstatfs 44
-__SC_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs)
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+               compat_sys_fstatfs64)
 #define __NR3264_truncate 45
-__SC_3264(__NR3264_truncate, sys_truncate64, sys_truncate)
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+               compat_sys_truncate64)
 #define __NR3264_ftruncate 46
-__SC_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate)
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+               compat_sys_ftruncate64)
 
 #define __NR_fallocate 47
-__SYSCALL(__NR_fallocate, sys_fallocate)
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
 #define __NR_faccessat 48
 __SYSCALL(__NR_faccessat, sys_faccessat)
 #define __NR_chdir 49
@@ -166,7 +178,7 @@ __SYSCALL(__NR_fchownat, sys_fchownat)
 #define __NR_fchown 55
 __SYSCALL(__NR_fchown, sys_fchown)
 #define __NR_openat 56
-__SYSCALL(__NR_openat, sys_openat)
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
 #define __NR_close 57
 __SYSCALL(__NR_close, sys_close)
 #define __NR_vhangup 58
@@ -182,7 +194,7 @@ __SYSCALL(__NR_quotactl, sys_quotactl)
 
 /* fs/readdir.c */
 #define __NR_getdents64 61
-__SYSCALL(__NR_getdents64, sys_getdents64)
+__SC_COMP(__NR_getdents64, sys_getdents64, compat_sys_getdents64)
 
 /* fs/read_write.c */
 #define __NR3264_lseek 62
@@ -192,17 +204,17 @@ __SYSCALL(__NR_read, sys_read)
 #define __NR_write 64
 __SYSCALL(__NR_write, sys_write)
 #define __NR_readv 65
-__SYSCALL(__NR_readv, sys_readv)
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
 #define __NR_writev 66
-__SYSCALL(__NR_writev, sys_writev)
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
 #define __NR_pread64 67
-__SYSCALL(__NR_pread64, sys_pread64)
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
 #define __NR_pwrite64 68
-__SYSCALL(__NR_pwrite64, sys_pwrite64)
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
 #define __NR_preadv 69
-__SYSCALL(__NR_preadv, sys_preadv)
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
 #define __NR_pwritev 70
-__SYSCALL(__NR_pwritev, sys_pwritev)
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
 
 /* fs/sendfile.c */
 #define __NR3264_sendfile 71
@@ -210,17 +222,17 @@ __SC_3264(__NR3264_sendfile, sys_sendfile64, sys_sendfile)
 
 /* fs/select.c */
 #define __NR_pselect6 72
-__SYSCALL(__NR_pselect6, sys_pselect6)
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
 #define __NR_ppoll 73
-__SYSCALL(__NR_ppoll, sys_ppoll)
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
 
 /* fs/signalfd.c */
 #define __NR_signalfd4 74
-__SYSCALL(__NR_signalfd4, sys_signalfd4)
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
 
 /* fs/splice.c */
 #define __NR_vmsplice 75
-__SYSCALL(__NR_vmsplice, sys_vmsplice)
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
 #define __NR_splice 76
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_tee 77
@@ -243,23 +255,27 @@ __SYSCALL(__NR_fsync, sys_fsync)
 __SYSCALL(__NR_fdatasync, sys_fdatasync)
 #ifdef __ARCH_WANT_SYNC_FILE_RANGE2
 #define __NR_sync_file_range2 84
-__SYSCALL(__NR_sync_file_range2, sys_sync_file_range2)
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+          compat_sys_sync_file_range2)
 #else
 #define __NR_sync_file_range 84
-__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+          compat_sys_sync_file_range)
 #endif
 
 /* fs/timerfd.c */
 #define __NR_timerfd_create 85
 __SYSCALL(__NR_timerfd_create, sys_timerfd_create)
 #define __NR_timerfd_settime 86
-__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+          compat_sys_timerfd_settime)
 #define __NR_timerfd_gettime 87
-__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+          compat_sys_timerfd_gettime)
 
 /* fs/utimes.c */
 #define __NR_utimensat 88
-__SYSCALL(__NR_utimensat, sys_utimensat)
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
 
 /* kernel/acct.c */
 #define __NR_acct 89
@@ -281,7 +297,7 @@ __SYSCALL(__NR_exit, sys_exit)
 #define __NR_exit_group 94
 __SYSCALL(__NR_exit_group, sys_exit_group)
 #define __NR_waitid 95
-__SYSCALL(__NR_waitid, sys_waitid)
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
 
 /* kernel/fork.c */
 #define __NR_set_tid_address 96
@@ -291,25 +307,27 @@ __SYSCALL(__NR_unshare, sys_unshare)
 
 /* kernel/futex.c */
 #define __NR_futex 98
-__SYSCALL(__NR_futex, sys_futex)
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
 #define __NR_set_robust_list 99
-__SYSCALL(__NR_set_robust_list, sys_set_robust_list)
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+          compat_sys_set_robust_list)
 #define __NR_get_robust_list 100
-__SYSCALL(__NR_get_robust_list, sys_get_robust_list)
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+          compat_sys_get_robust_list)
 
 /* kernel/hrtimer.c */
 #define __NR_nanosleep 101
-__SYSCALL(__NR_nanosleep, sys_nanosleep)
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
 
 /* kernel/itimer.c */
 #define __NR_getitimer 102
-__SYSCALL(__NR_getitimer, sys_getitimer)
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
 #define __NR_setitimer 103
-__SYSCALL(__NR_setitimer, sys_setitimer)
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
 
 /* kernel/kexec.c */
 #define __NR_kexec_load 104
-__SYSCALL(__NR_kexec_load, sys_kexec_load)
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
 
 /* kernel/module.c */
 #define __NR_init_module 105
@@ -319,23 +337,24 @@ __SYSCALL(__NR_delete_module, sys_delete_module)
 
 /* kernel/posix-timers.c */
 #define __NR_timer_create 107
-__SYSCALL(__NR_timer_create, sys_timer_create)
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
 #define __NR_timer_gettime 108
-__SYSCALL(__NR_timer_gettime, sys_timer_gettime)
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
 #define __NR_timer_getoverrun 109
 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
 #define __NR_timer_settime 110
-__SYSCALL(__NR_timer_settime, sys_timer_settime)
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
 #define __NR_timer_delete 111
 __SYSCALL(__NR_timer_delete, sys_timer_delete)
 #define __NR_clock_settime 112
-__SYSCALL(__NR_clock_settime, sys_clock_settime)
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
 #define __NR_clock_gettime 113
-__SYSCALL(__NR_clock_gettime, sys_clock_gettime)
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
 #define __NR_clock_getres 114
-__SYSCALL(__NR_clock_getres, sys_clock_getres)
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
 #define __NR_clock_nanosleep 115
-__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep)
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+          compat_sys_clock_nanosleep)
 
 /* kernel/printk.c */
 #define __NR_syslog 116
@@ -355,9 +374,11 @@ __SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
 #define __NR_sched_getparam 121
 __SYSCALL(__NR_sched_getparam, sys_sched_getparam)
 #define __NR_sched_setaffinity 122
-__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity)
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+          compat_sys_sched_setaffinity)
 #define __NR_sched_getaffinity 123
-__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity)
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+          compat_sys_sched_getaffinity)
 #define __NR_sched_yield 124
 __SYSCALL(__NR_sched_yield, sys_sched_yield)
 #define __NR_sched_get_priority_max 125
@@ -365,7 +386,8 @@ __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
 #define __NR_sched_get_priority_min 126
 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
 #define __NR_sched_rr_get_interval 127
-__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval)
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+          compat_sys_sched_rr_get_interval)
 
 /* kernel/signal.c */
 #define __NR_restart_syscall 128
@@ -377,21 +399,23 @@ __SYSCALL(__NR_tkill, sys_tkill)
 #define __NR_tgkill 131
 __SYSCALL(__NR_tgkill, sys_tgkill)
 #define __NR_sigaltstack 132
-__SYSCALL(__NR_sigaltstack, sys_sigaltstack)
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
 #define __NR_rt_sigsuspend 133
-__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend) /* __ARCH_WANT_SYS_RT_SIGSUSPEND */
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
 #define __NR_rt_sigaction 134
-__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction) /* __ARCH_WANT_SYS_RT_SIGACTION */
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
 #define __NR_rt_sigprocmask 135
 __SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask)
 #define __NR_rt_sigpending 136
 __SYSCALL(__NR_rt_sigpending, sys_rt_sigpending)
 #define __NR_rt_sigtimedwait 137
-__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+          compat_sys_rt_sigtimedwait)
 #define __NR_rt_sigqueueinfo 138
-__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+          compat_sys_rt_sigqueueinfo)
 #define __NR_rt_sigreturn 139
-__SYSCALL(__NR_rt_sigreturn, sys_rt_sigreturn) /* sys_rt_sigreturn_wrapper, */
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
 
 /* kernel/sys.c */
 #define __NR_setpriority 140
@@ -421,7 +445,7 @@ __SYSCALL(__NR_setfsuid, sys_setfsuid)
 #define __NR_setfsgid 152
 __SYSCALL(__NR_setfsgid, sys_setfsgid)
 #define __NR_times 153
-__SYSCALL(__NR_times, sys_times)
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
 #define __NR_setpgid 154
 __SYSCALL(__NR_setpgid, sys_setpgid)
 #define __NR_getpgid 155
@@ -441,11 +465,11 @@ __SYSCALL(__NR_sethostname, sys_sethostname)
 #define __NR_setdomainname 162
 __SYSCALL(__NR_setdomainname, sys_setdomainname)
 #define __NR_getrlimit 163
-__SYSCALL(__NR_getrlimit, sys_getrlimit)
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
 #define __NR_setrlimit 164
-__SYSCALL(__NR_setrlimit, sys_setrlimit)
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
 #define __NR_getrusage 165
-__SYSCALL(__NR_getrusage, sys_getrusage)
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
 #define __NR_umask 166
 __SYSCALL(__NR_umask, sys_umask)
 #define __NR_prctl 167
@@ -455,11 +479,11 @@ __SYSCALL(__NR_getcpu, sys_getcpu)
 
 /* kernel/time.c */
 #define __NR_gettimeofday 169
-__SYSCALL(__NR_gettimeofday, sys_gettimeofday)
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
 #define __NR_settimeofday 170
-__SYSCALL(__NR_settimeofday, sys_settimeofday)
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
 #define __NR_adjtimex 171
-__SYSCALL(__NR_adjtimex, sys_adjtimex)
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
 
 /* kernel/timer.c */
 #define __NR_getpid 172
@@ -477,39 +501,40 @@ __SYSCALL(__NR_getegid, sys_getegid)
 #define __NR_gettid 178
 __SYSCALL(__NR_gettid, sys_gettid)
 #define __NR_sysinfo 179
-__SYSCALL(__NR_sysinfo, sys_sysinfo)
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
 
 /* ipc/mqueue.c */
 #define __NR_mq_open 180
-__SYSCALL(__NR_mq_open, sys_mq_open)
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
 #define __NR_mq_unlink 181
 __SYSCALL(__NR_mq_unlink, sys_mq_unlink)
 #define __NR_mq_timedsend 182
-__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend)
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
 #define __NR_mq_timedreceive 183
-__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive)
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+          compat_sys_mq_timedreceive)
 #define __NR_mq_notify 184
-__SYSCALL(__NR_mq_notify, sys_mq_notify)
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
 #define __NR_mq_getsetattr 185
-__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr)
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
 
 /* ipc/msg.c */
 #define __NR_msgget 186
 __SYSCALL(__NR_msgget, sys_msgget)
 #define __NR_msgctl 187
-__SYSCALL(__NR_msgctl, sys_msgctl)
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
 #define __NR_msgrcv 188
-__SYSCALL(__NR_msgrcv, sys_msgrcv)
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
 #define __NR_msgsnd 189
-__SYSCALL(__NR_msgsnd, sys_msgsnd)
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
 
 /* ipc/sem.c */
 #define __NR_semget 190
 __SYSCALL(__NR_semget, sys_semget)
 #define __NR_semctl 191
-__SYSCALL(__NR_semctl, sys_semctl)
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
 #define __NR_semtimedop 192
-__SYSCALL(__NR_semtimedop, sys_semtimedop)
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
 #define __NR_semop 193
 __SYSCALL(__NR_semop, sys_semop)
 
@@ -517,9 +542,9 @@ __SYSCALL(__NR_semop, sys_semop)
 #define __NR_shmget 194
 __SYSCALL(__NR_shmget, sys_shmget)
 #define __NR_shmctl 195
-__SYSCALL(__NR_shmctl, sys_shmctl)
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
 #define __NR_shmat 196
-__SYSCALL(__NR_shmat, sys_shmat)
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
 #define __NR_shmdt 197
 __SYSCALL(__NR_shmdt, sys_shmdt)
 
@@ -543,21 +568,21 @@ __SYSCALL(__NR_getpeername, sys_getpeername)
 #define __NR_sendto 206
 __SYSCALL(__NR_sendto, sys_sendto)
 #define __NR_recvfrom 207
-__SYSCALL(__NR_recvfrom, sys_recvfrom)
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
 #define __NR_setsockopt 208
-__SYSCALL(__NR_setsockopt, sys_setsockopt)
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
 #define __NR_getsockopt 209
-__SYSCALL(__NR_getsockopt, sys_getsockopt)
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
 #define __NR_shutdown 210
 __SYSCALL(__NR_shutdown, sys_shutdown)
 #define __NR_sendmsg 211
-__SYSCALL(__NR_sendmsg, sys_sendmsg)
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
 #define __NR_recvmsg 212
-__SYSCALL(__NR_recvmsg, sys_recvmsg)
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
 
 /* mm/filemap.c */
 #define __NR_readahead 213
-__SYSCALL(__NR_readahead, sys_readahead)
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
 
 /* mm/nommu.c, also with MMU */
 #define __NR_brk 214
@@ -573,19 +598,19 @@ __SYSCALL(__NR_add_key, sys_add_key)
 #define __NR_request_key 218
 __SYSCALL(__NR_request_key, sys_request_key)
 #define __NR_keyctl 219
-__SYSCALL(__NR_keyctl, sys_keyctl)
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
 
 /* arch/example/kernel/sys_example.c */
 #define __NR_clone 220
-__SYSCALL(__NR_clone, sys_clone)        /* .long sys_clone_wrapper */
+__SYSCALL(__NR_clone, sys_clone)
 #define __NR_execve 221
-__SYSCALL(__NR_execve, sys_execve)      /* .long sys_execve_wrapper */
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
 
 #define __NR3264_mmap 222
 __SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
 /* mm/fadvise.c */
 #define __NR3264_fadvise64 223
-__SYSCALL(__NR3264_fadvise64, sys_fadvise64_64)
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
 
 /* mm/, CONFIG_MMU only */
 #ifndef __ARCH_NOMMU
@@ -612,25 +637,26 @@ __SYSCALL(__NR_madvise, sys_madvise)
 #define __NR_remap_file_pages 234
 __SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
 #define __NR_mbind 235
-__SYSCALL(__NR_mbind, sys_mbind)
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
 #define __NR_get_mempolicy 236
-__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
 #define __NR_set_mempolicy 237
-__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
 #define __NR_migrate_pages 238
-__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
 #define __NR_move_pages 239
-__SYSCALL(__NR_move_pages, sys_move_pages)
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
 #endif
 
 #define __NR_rt_tgsigqueueinfo 240
-__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+          compat_sys_rt_tgsigqueueinfo)
 #define __NR_perf_event_open 241
 __SYSCALL(__NR_perf_event_open, sys_perf_event_open)
 #define __NR_accept4 242
 __SYSCALL(__NR_accept4, sys_accept4)
 #define __NR_recvmmsg 243
-__SYSCALL(__NR_recvmmsg, sys_recvmmsg)
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
 
 /*
  * Architectures may provide up to 16 syscalls of their own
@@ -639,19 +665,20 @@ __SYSCALL(__NR_recvmmsg, sys_recvmmsg)
 #define __NR_arch_specific_syscall 244
 
 #define __NR_wait4 260
-__SYSCALL(__NR_wait4, sys_wait4)
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
 #define __NR_prlimit64 261
 __SYSCALL(__NR_prlimit64, sys_prlimit64)
 #define __NR_fanotify_init 262
 __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 #define __NR_fanotify_mark 263
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
-#define __NR_name_to_handle_at          264
+#define __NR_name_to_handle_at         264
 __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
-#define __NR_open_by_handle_at          265
-__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+#define __NR_open_by_handle_at         265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+          compat_sys_open_by_handle_at)
 #define __NR_clock_adjtime 266
-__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
 #define __NR_syncfs 267
 __SYSCALL(__NR_syncfs, sys_syncfs)
 
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index cb1ded2bd545..ccfedb4f3eb0 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -302,6 +302,7 @@ header-y += ppp-comp.h
 header-y += ppp_defs.h
 header-y += pps.h
 header-y += prctl.h
+header-y += ptp_clock.h
 header-y += ptrace.h
 header-y += qnx4_fs.h
 header-y += qnxtypes.h
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index daf8c480c786..dcafe0bf0005 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -55,7 +55,8 @@
  * bitmap_parse(buf, buflen, dst, nbits)        Parse bitmap dst from kernel buf
  * bitmap_parse_user(ubuf, ulen, dst, nbits)    Parse bitmap dst from user buf
  * bitmap_scnlistprintf(buf, len, src, nbits)   Print bitmap src as list to buf
- * bitmap_parselist(buf, dst, nbits)            Parse bitmap dst from list
+ * bitmap_parselist(buf, dst, nbits)            Parse bitmap dst from kernel buf
+ * bitmap_parselist_user(buf, dst, nbits)       Parse bitmap dst from user buf
  * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region
  * bitmap_release_region(bitmap, pos, order)    Free specified bit region
  * bitmap_allocate_region(bitmap, pos, order)   Allocate specified bit region
@@ -129,6 +130,8 @@ extern int bitmap_scnlistprintf(char *buf, unsigned int len,
                         const unsigned long *src, int nbits);
 extern int bitmap_parselist(const char *buf, unsigned long *maskp,
                         int nmaskbits);
+extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
+                        unsigned long *dst, int nbits);
 extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
                 const unsigned long *old, const unsigned long *new, int bits);
 extern int bitmap_bitremap(int oldbit,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index be50d9e70a7d..2a7cea53ca0d 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -151,7 +151,6 @@ enum rq_flag_bits {
         __REQ_IO_STAT,          /* account I/O stat */
         __REQ_MIXED_MERGE,      /* merge of different types, fail separately */
         __REQ_SECURE,           /* secure discard (used with __REQ_DISCARD) */
-        __REQ_ON_PLUG,          /* on plug list */
         __REQ_NR_BITS,          /* stops here */
 };
 
@@ -192,6 +191,5 @@ enum rq_flag_bits {
 #define REQ_IO_STAT             (1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE         (1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE              (1 << __REQ_SECURE)
-#define REQ_ON_PLUG             (1 << __REQ_ON_PLUG)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2ad95fa1d130..ae9091a68480 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -257,7 +257,7 @@ struct queue_limits {
         unsigned char           misaligned;
         unsigned char           discard_misaligned;
         unsigned char           cluster;
-        signed char             discard_zeroes_data;
+        unsigned char           discard_zeroes_data;
 };
 
 struct request_queue
@@ -364,6 +364,8 @@ struct request_queue
          * for flush operations
          */
         unsigned int            flush_flags;
+        unsigned int            flush_not_queueable:1;
+        unsigned int            flush_queue_delayed:1;
         unsigned int            flush_pending_idx:1;
         unsigned int            flush_running_idx:1;
         unsigned long           flush_pending_since;
@@ -843,6 +845,7 @@ extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
+extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
@@ -1066,13 +1069,16 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 {
         unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1);
 
+        if (!lim->max_discard_sectors)
+                return 0;
+
         return (lim->discard_granularity + lim->discard_alignment - alignment)
                 & (lim->discard_granularity - 1);
 }
 
 static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
 {
-        if (q->limits.discard_zeroes_data == 1)
+        if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)
                 return 1;
 
         return 0;
@@ -1111,6 +1117,11 @@ static inline unsigned int block_size(struct block_device *bdev)
         return bdev->bd_block_size;
 }
 
+static inline bool queue_flush_queueable(struct request_queue *q)
+{
+        return !q->flush_not_queueable;
+}
+
 typedef struct {struct page *v;} Sector;
 
 unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 01eca1794e14..ab344a521105 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -99,24 +99,31 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
                                       unsigned long align,
                                       unsigned long goal);
 
+#ifdef CONFIG_NO_BOOTMEM
+/* We are using top down, so it is safe to use 0 here */
+#define BOOTMEM_LOW_LIMIT 0
+#else
+#define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS)
+#endif
+
 #define alloc_bootmem(x) \
-        __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_align(x, align) \
-        __alloc_bootmem(x, align, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_nopanic(x) \
-        __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_pages(x) \
-        __alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_pages_nopanic(x) \
-        __alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem_nopanic(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_node(pgdat, x) \
-        __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_node_nopanic(pgdat, x) \
-        __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_pages_node(pgdat, x) \
-        __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
 #define alloc_bootmem_pages_node_nopanic(pgdat, x) \
-        __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+        __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT)
 
 #define alloc_bootmem_low(x) \
         __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
diff --git a/include/linux/c2port.h b/include/linux/c2port.h
index 2a5cd867c365..a2f7d7413f30 100644
--- a/include/linux/c2port.h
+++ b/include/linux/c2port.h
@@ -60,9 +60,6 @@ struct c2port_ops {
  * Exported functions
  */
 
-#define to_class_dev(obj) container_of((obj), struct class_device, kobj)
-#define to_c2port_device(obj) container_of((obj), struct c2port_device, class)
-
 extern struct c2port_device *c2port_device_register(char *name,
                                         struct c2port_ops *ops, void *devdata);
 extern void c2port_device_unregister(struct c2port_device *dev);
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index b8e995fbd867..b8c60694b2b0 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -313,6 +313,7 @@ enum {
         CEPH_MDS_OP_GETATTR    = 0x00101,
         CEPH_MDS_OP_LOOKUPHASH = 0x00102,
         CEPH_MDS_OP_LOOKUPPARENT = 0x00103,
+        CEPH_MDS_OP_LOOKUPINO  = 0x00104,
 
         CEPH_MDS_OP_SETXATTR   = 0x01105,
         CEPH_MDS_OP_RMXATTR    = 0x01106,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 5778b559d59c..ddcb7db38e67 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -12,6 +12,8 @@
 #include <linux/sem.h>
 #include <linux/socket.h>
 #include <linux/if.h>
+#include <linux/fs.h>
+#include <linux/aio_abi.h>      /* for aio_context_t */
 
 #include <asm/compat.h>
 #include <asm/siginfo.h>
@@ -26,7 +28,7 @@ typedef __compat_gid32_t	compat_gid_t;
 struct compat_sel_arg_struct;
 struct rusage;
 
-struct compat_itimerspec { 
+struct compat_itimerspec {
         struct compat_timespec it_interval;
         struct compat_timespec it_value;
 };
@@ -70,9 +72,9 @@ struct compat_timex {
         compat_long_t stbcnt;
         compat_int_t tai;
 
-        compat_int_t :32; compat_int_t :32; compat_int_t :32; compat_int_t :32;
-        compat_int_t :32; compat_int_t :32; compat_int_t :32; compat_int_t :32;
-        compat_int_t :32; compat_int_t :32; compat_int_t :32;
+        compat_int_t:32; compat_int_t:32; compat_int_t:32; compat_int_t:32;
+        compat_int_t:32; compat_int_t:32; compat_int_t:32; compat_int_t:32;
+        compat_int_t:32; compat_int_t:32; compat_int_t:32;
 };
 
 #define _COMPAT_NSIG_WORDS      (_COMPAT_NSIG / _COMPAT_NSIG_BPW)
@@ -81,8 +83,10 @@ typedef struct {
         compat_sigset_word      sig[_COMPAT_NSIG_WORDS];
 } compat_sigset_t;
 
-extern int get_compat_timespec(struct timespec *, const struct compat_timespec __user *);
-extern int put_compat_timespec(const struct timespec *, struct compat_timespec __user *);
+extern int get_compat_timespec(struct timespec *,
+                               const struct compat_timespec __user *);
+extern int put_compat_timespec(const struct timespec *,
+                               struct compat_timespec __user *);
 
 struct compat_iovec {
         compat_uptr_t   iov_base;
@@ -113,7 +117,8 @@ struct compat_rusage {
         compat_long_t   ru_nivcsw;
 };
 
-extern int put_compat_rusage(const struct rusage *, struct compat_rusage __user *);
+extern int put_compat_rusage(const struct rusage *,
+                             struct compat_rusage __user *);
 
 struct compat_siginfo;
 
@@ -166,8 +171,7 @@ struct compat_ifmap {
         unsigned char port;
 };
 
-struct compat_if_settings
-{
+struct compat_if_settings {
         unsigned int type;      /* Type of physical device or protocol */
         unsigned int size;      /* Size of the data allocated by the caller */
         compat_uptr_t ifs_ifsu; /* union of pointers */
@@ -195,8 +199,8 @@ struct compat_ifreq {
 };
 
 struct compat_ifconf {
-        compat_int_t    ifc_len;                        /* size of buffer       */
-        compat_caddr_t  ifcbuf;
+        compat_int_t    ifc_len;                /* size of buffer */
+        compat_caddr_t  ifcbuf;
 };
 
 struct compat_robust_list {
@@ -209,6 +213,18 @@ struct compat_robust_list_head {
         compat_uptr_t                   list_op_pending;
 };
 
+struct compat_statfs;
+struct compat_statfs64;
+struct compat_old_linux_dirent;
+struct compat_linux_dirent;
+struct linux_dirent64;
+struct compat_msghdr;
+struct compat_mmsghdr;
+struct compat_sysinfo;
+struct compat_sysctl_args;
+struct compat_kexec_segment;
+struct compat_mq_attr;
+
 extern void compat_exit_robust_list(struct task_struct *curr);
 
 asmlinkage long
@@ -243,8 +259,8 @@ asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
                 const struct compat_iovec __user *vec,
                 unsigned long vlen, u32 pos_low, u32 pos_high);
 
-int compat_do_execve(char * filename, compat_uptr_t __user *argv,
-                compat_uptr_t __user *envp, struct pt_regs * regs);
+int compat_do_execve(char *filename, compat_uptr_t __user *argv,
+                     compat_uptr_t __user *envp, struct pt_regs *regs);
 
 asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
                 compat_ulong_t __user *outp, compat_ulong_t __user *exp,
@@ -331,12 +347,18 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
                         const compat_sigset_t __user *sigmask,
                         compat_size_t sigsetsize);
 
-asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename,
-                                struct compat_timespec __user *t, int flags);
+asmlinkage long compat_sys_utime(const char __user *filename,
+                                 struct compat_utimbuf __user *t);
+asmlinkage long compat_sys_utimensat(unsigned int dfd,
+                                     const char __user *filename,
+                                     struct compat_timespec __user *t,
+                                     int flags);
 
+asmlinkage long compat_sys_time(compat_time_t __user *tloc);
+asmlinkage long compat_sys_stime(compat_time_t __user *tptr);
 asmlinkage long compat_sys_signalfd(int ufd,
-                                const compat_sigset_t __user *sigmask,
-                                compat_size_t sigsetsize);
+                                    const compat_sigset_t __user *sigmask,
+                                    compat_size_t sigsetsize);
 asmlinkage long compat_sys_timerfd_settime(int ufd, int flags,
                                    const struct compat_itimerspec __user *utmr,
                                    struct compat_itimerspec __user *otmr);
@@ -348,16 +370,190 @@ asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_page,
                                       const int __user *nodes,
                                       int __user *status,
                                       int flags);
-asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename,
+asmlinkage long compat_sys_futimesat(unsigned int dfd,
+                                     const char __user *filename,
                                      struct compat_timeval __user *t);
-asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user * filename,
+asmlinkage long compat_sys_utimes(const char __user *filename,
+                                  struct compat_timeval __user *t);
+asmlinkage long compat_sys_newstat(const char __user *filename,
+                                   struct compat_stat __user *statbuf);
+asmlinkage long compat_sys_newlstat(const char __user *filename,
+                                    struct compat_stat __user *statbuf);
+asmlinkage long compat_sys_newfstatat(unsigned int dfd,
+                                      const char __user *filename,
                                       struct compat_stat __user *statbuf,
                                       int flag);
+asmlinkage long compat_sys_newfstat(unsigned int fd,
+                                    struct compat_stat __user *statbuf);
+asmlinkage long compat_sys_statfs(const char __user *pathname,
+                                  struct compat_statfs __user *buf);
+asmlinkage long compat_sys_fstatfs(unsigned int fd,
+                                   struct compat_statfs __user *buf);
+asmlinkage long compat_sys_statfs64(const char __user *pathname,
+                                    compat_size_t sz,
+                                    struct compat_statfs64 __user *buf);
+asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz,
+                                     struct compat_statfs64 __user *buf);
+asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
+                                   unsigned long arg);
+asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
+                                 unsigned long arg);
+asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p);
+asmlinkage long compat_sys_io_getevents(aio_context_t ctx_id,
+                                        unsigned long min_nr,
+                                        unsigned long nr,
+                                        struct io_event __user *events,
+                                        struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_submit(aio_context_t ctx_id, int nr,
+                                     u32 __user *iocb);
+asmlinkage long compat_sys_mount(const char __user *dev_name,
+                                 const char __user *dir_name,
+                                 const char __user *type, unsigned long flags,
+                                 const void __user *data);
+asmlinkage long compat_sys_old_readdir(unsigned int fd,
+                                       struct compat_old_linux_dirent __user *,
+                                       unsigned int count);
+asmlinkage long compat_sys_getdents(unsigned int fd,
+                                    struct compat_linux_dirent __user *dirent,
+                                    unsigned int count);
+asmlinkage long compat_sys_getdents64(unsigned int fd,
+                                      struct linux_dirent64 __user *dirent,
+                                      unsigned int count);
+asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *,
+                                    unsigned int nr_segs, unsigned int flags);
+asmlinkage long compat_sys_open(const char __user *filename, int flags,
+                                int mode);
 asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename,
                                   int flags, int mode);
+asmlinkage long compat_sys_open_by_handle_at(int mountdirfd,
+                                             struct file_handle __user *handle,
+                                             int flags);
+asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp,
+                                    compat_ulong_t __user *outp,
+                                    compat_ulong_t __user *exp,
+                                    struct compat_timespec __user *tsp,
+                                    void __user *sig);
+asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
+                                 unsigned int nfds,
+                                 struct compat_timespec __user *tsp,
+                                 const compat_sigset_t __user *sigmask,
+                                 compat_size_t sigsetsize);
+#if (defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)) && \
+        !defined(CONFIG_NFSD_DEPRECATED)
+union compat_nfsctl_res;
+struct compat_nfsctl_arg;
+asmlinkage long compat_sys_nfsservctl(int cmd,
+                                      struct compat_nfsctl_arg __user *arg,
+                                      union compat_nfsctl_res __user *res);
+#else
+asmlinkage long compat_sys_nfsservctl(int cmd, void *notused, void *notused2);
+#endif
+asmlinkage long compat_sys_signalfd4(int ufd,
+                                     const compat_sigset_t __user *sigmask,
+                                     compat_size_t sigsetsize, int flags);
+asmlinkage long compat_sys_get_mempolicy(int __user *policy,
+                                         compat_ulong_t __user *nmask,
+                                         compat_ulong_t maxnode,
+                                         compat_ulong_t addr,
+                                         compat_ulong_t flags);
+asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
+                                         compat_ulong_t maxnode);
+asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
+                                 compat_ulong_t mode,
+                                 compat_ulong_t __user *nmask,
+                                 compat_ulong_t maxnode, compat_ulong_t flags);
+
+asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
+                                      char __user *optval, unsigned int optlen);
+asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg,
+                                   unsigned flags);
+asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg,
+                                   unsigned int flags);
+asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len,
+                                unsigned flags);
+asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len,
+                            unsigned flags, struct sockaddr __user *addr,
+                            int __user *addrlen);
+asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
+                                    unsigned vlen, unsigned int flags,
+                                    struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
+                                     struct compat_timespec __user *rmtp);
+asmlinkage long compat_sys_getitimer(int which,
+                                     struct compat_itimerval __user *it);
+asmlinkage long compat_sys_setitimer(int which,
+                                     struct compat_itimerval __user *in,
+                                     struct compat_itimerval __user *out);
+asmlinkage long compat_sys_times(struct compat_tms __user *tbuf);
+asmlinkage long compat_sys_setrlimit(unsigned int resource,
+                                     struct compat_rlimit __user *rlim);
+asmlinkage long compat_sys_getrlimit(unsigned int resource,
+                                     struct compat_rlimit __user *rlim);
+asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru);
+asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
+                                     unsigned int len,
+                                     compat_ulong_t __user *user_mask_ptr);
+asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid,
+                                     unsigned int len,
+                                     compat_ulong_t __user *user_mask_ptr);
+asmlinkage long compat_sys_timer_create(clockid_t which_clock,
+                        struct compat_sigevent __user *timer_event_spec,
+                        timer_t __user *created_timer_id);
+asmlinkage long compat_sys_timer_settime(timer_t timer_id, int flags,
+                                         struct compat_itimerspec __user *new,
+                                         struct compat_itimerspec __user *old);
+asmlinkage long compat_sys_timer_gettime(timer_t timer_id,
+                                 struct compat_itimerspec __user *setting);
+asmlinkage long compat_sys_clock_settime(clockid_t which_clock,
+                                         struct compat_timespec __user *tp);
+asmlinkage long compat_sys_clock_gettime(clockid_t which_clock,
+                                         struct compat_timespec __user *tp);
+asmlinkage long compat_sys_clock_adjtime(clockid_t which_clock,
+                                         struct compat_timex __user *tp);
+asmlinkage long compat_sys_clock_getres(clockid_t which_clock,
+                                        struct compat_timespec __user *tp);
+asmlinkage long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
+                                           struct compat_timespec __user *rqtp,
+                                           struct compat_timespec __user *rmtp);
+asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese,
+                struct compat_siginfo __user *uinfo,
+                struct compat_timespec __user *uts, compat_size_t sigsetsize);
+asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset,
+                                         compat_size_t sigsetsize);
+asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info);
+asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
+                                 unsigned long arg);
+asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
+                struct compat_timespec __user *utime, u32 __user *uaddr2,
+                u32 val3);
+asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
+                                      char __user *optval, int __user *optlen);
+asmlinkage long compat_sys_kexec_load(unsigned long entry,
+                                      unsigned long nr_segments,
+                                      struct compat_kexec_segment __user *,
+                                      unsigned long flags);
+asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes,
+                        const struct compat_mq_attr __user *u_mqstat,
+                        struct compat_mq_attr __user *u_omqstat);
+asmlinkage long compat_sys_mq_notify(mqd_t mqdes,
+                        const struct compat_sigevent __user *u_notification);
+asmlinkage long compat_sys_mq_open(const char __user *u_name,
+                        int oflag, compat_mode_t mode,
+                        struct compat_mq_attr __user *u_attr);
+asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
+                        const char __user *u_msg_ptr,
+                        size_t msg_len, unsigned int msg_prio,
+                        const struct compat_timespec __user *u_abs_timeout);
+asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes,
+                        char __user *u_msg_ptr,
+                        size_t msg_len, unsigned int __user *u_msg_prio,
+                        const struct compat_timespec __user *u_abs_timeout);
+asmlinkage long compat_sys_socketcall(int call, u32 __user *args);
+asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args);
 
 extern ssize_t compat_rw_copy_check_uvector(int type,
-                const struct compat_iovec __user *uvector, unsigned long nr_segs,
+                const struct compat_iovec __user *uvector,
+                unsigned long nr_segs,
                 unsigned long fast_segs, struct iovec *fast_pointer,
                 struct iovec **ret_pointer);
 
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index cb4c1eb7778e..59e4028e833d 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -34,8 +34,12 @@
     __asm__ ("" : "=r"(__ptr) : "0"(ptr));              \
     (typeof(ptr)) (__ptr + (off)); })
 
+#ifdef __CHECKER__
+#define __must_be_array(arr) 0
+#else
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+#endif
 
 /*
  * Force always-inline if the user requests it so via the .config,
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 64b7c003fd7a..dfadc96e9d63 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -51,7 +51,7 @@
 #if __GNUC_MINOR__ > 0
 #define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
 #endif
-#if __GNUC_MINOR__ >= 4
+#if __GNUC_MINOR__ >= 4 && !defined(__CHECKER__)
 #define __compiletime_warning(message) __attribute__((warning(message)))
 #define __compiletime_error(message) __attribute__((error(message)))
 #endif
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index bae6fe24d1f9..b24ac56477b4 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -547,6 +547,21 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
 }
 
 /**
+ * cpumask_parselist_user - extract a cpumask from a user string
+ * @buf: the buffer to extract from
+ * @len: the length of the buffer
+ * @dstp: the cpumask to set.
+ *
+ * Returns -errno, or 0 for success.
+ */
+static inline int cpumask_parselist_user(const char __user *buf, int len,
+                                     struct cpumask *dstp)
+{
+        return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
+                                                        nr_cpumask_bits);
+}
+
+/**
  * cpulist_scnprintf - print a cpumask into a string as comma-separated list
  * @buf: the buffer to sprintf into
  * @len: the length of the buffer
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index cec467f5d676..9e5f5607eba3 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -38,7 +38,7 @@
 
 /* Although the Linux source code makes a difference between
    generic endianness and the bitfields' endianness, there is no
-   architecture as of Linux-2.6.24-rc4 where the bitfileds' endianness
+   architecture as of Linux-2.6.24-rc4 where the bitfields' endianness
    does not match the generic endianness. */
 
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -53,7 +53,7 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.10"
+#define REL_VERSION "8.3.11"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 96
@@ -195,7 +195,7 @@ enum drbd_conns {
         C_WF_REPORT_PARAMS, /* we have a socket */
         C_CONNECTED,      /* we have introduced each other */
         C_STARTING_SYNC_S,  /* starting full sync by admin request. */
-        C_STARTING_SYNC_T,  /* stariing full sync by admin request. */
+        C_STARTING_SYNC_T,  /* starting full sync by admin request. */
         C_WF_BITMAP_S,
         C_WF_BITMAP_T,
         C_WF_SYNC_UUID,
@@ -236,7 +236,7 @@ union drbd_state {
  * pointed out by Maxim Uvarov q<muvarov@ru.mvista.com>
  * even though we transmit as "cpu_to_be32(state)",
  * the offsets of the bitfields still need to be swapped
- * on different endianess.
+ * on different endianness.
  */
         struct {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
@@ -266,7 +266,7 @@ union drbd_state {
                 unsigned peer:2 ;   /* 3/4       primary/secondary/unknown */
                 unsigned role:2 ;   /* 3/4       primary/secondary/unknown */
 #else
-# error "this endianess is not supported"
+# error "this endianness is not supported"
 #endif
         };
         unsigned int i;
diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h
index f14a165e82dc..069543190516 100644
--- a/include/linux/drbd_tag_magic.h
+++ b/include/linux/drbd_tag_magic.h
@@ -30,7 +30,7 @@ enum packet_types {
         int tag_and_len ## member;
 #include "linux/drbd_nl.h"
 
-/* declate tag-list-sizes */
+/* declare tag-list-sizes */
 static const int tag_list_sizes[] = {
 #define NL_PACKET(name, number, fields) 2 fields ,
 #define NL_INTEGER(pn, pr, member)      + 4 + 4
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cdf9495df204..3f9d3251790d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -23,7 +23,8 @@
 
 /* Fixed constants first: */
 #undef NR_OPEN
-#define INR_OPEN 1024           /* Initial setting for nfile rlimits */
+#define INR_OPEN_CUR 1024       /* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096       /* Hard limit for nfile rlimits */
 
 #define BLOCK_SIZE_BITS 10
 #define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
@@ -634,8 +635,7 @@ struct address_space {
         unsigned int            i_mmap_writable;/* count VM_SHARED mappings */
         struct prio_tree_root   i_mmap;         /* tree of private and shared mappings */
         struct list_head        i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-        spinlock_t              i_mmap_lock;    /* protect tree, count, list */
-        unsigned int            truncate_count; /* Cover race condition with truncate */
+        struct mutex            i_mmap_mutex;   /* protect tree, count, list */
         unsigned long           nrpages;        /* number of total pages */
         pgoff_t                 writeback_index;/* writeback starts here */
         const struct address_space_operations *a_ops;   /* methods */
@@ -644,7 +644,6 @@ struct address_space {
         spinlock_t              private_lock;   /* for use by the address_space */
         struct list_head        private_list;   /* ditto */
         struct address_space    *assoc_mapping; /* ditto */
-        struct mutex            unmap_mutex;    /* to protect unmapping */
 } __attribute__((aligned(sizeof(long))));
         /*
          * On most architectures that alignment is already the case; but
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 76427e688d15..af095b54502e 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -100,17 +100,6 @@ struct fscache_operation {
 
         /* operation releaser */
         fscache_operation_release_t release;
-
-#ifdef CONFIG_WORKQUEUE_DEBUGFS
-        struct work_struct put_work;    /* work to delay operation put */
-        const char *name;               /* operation name */
-        const char *state;              /* operation state */
-#define fscache_set_op_name(OP, N)      do { (OP)->name  = (N); } while(0)
-#define fscache_set_op_state(OP, S)     do { (OP)->state = (S); } while(0)
-#else
-#define fscache_set_op_name(OP, N)      do { } while(0)
-#define fscache_set_op_state(OP, S)     do { } while(0)
-#endif
 };
 
 extern atomic_t fscache_op_debug_id;
@@ -137,7 +126,6 @@ static inline void fscache_operation_init(struct fscache_operation *op,
         op->processor = processor;
         op->release = release;
         INIT_LIST_HEAD(&op->pend_link);
-        fscache_set_op_state(op, "Init");
 }
 
 /*
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 9869ef3674ac..5bbebda78b02 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -9,6 +9,8 @@
  */
 
 
+#ifndef __GENALLOC_H__
+#define __GENALLOC_H__
 /*
  *  General purpose special memory pool descriptor.
  */
@@ -24,13 +26,34 @@ struct gen_pool {
 struct gen_pool_chunk {
         spinlock_t lock;
         struct list_head next_chunk;    /* next chunk in pool */
+        phys_addr_t phys_addr;          /* physical starting address of memory chunk */
         unsigned long start_addr;       /* starting address of memory chunk */
         unsigned long end_addr;         /* ending address of memory chunk */
         unsigned long bits[0];          /* bitmap for allocating memory chunk */
 };
 
 extern struct gen_pool *gen_pool_create(int, int);
-extern int gen_pool_add(struct gen_pool *, unsigned long, size_t, int);
+extern phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long);
+extern int gen_pool_add_virt(struct gen_pool *, unsigned long, phys_addr_t,
+                             size_t, int);
+/**
+ * gen_pool_add - add a new chunk of special memory to the pool
+ * @pool: pool to add new memory chunk to
+ * @addr: starting address of memory chunk to add to pool
+ * @size: size in bytes of the memory chunk to add to pool
+ * @nid: node id of the node the chunk structure and bitmap should be
+ *       allocated on, or -1
+ *
+ * Add a new chunk of special memory to the specified pool.
+ *
+ * Returns 0 on success or a -ve errno on failure.
+ */
+static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr,
+                               size_t size, int nid)
+{
+        return gen_pool_add_virt(pool, addr, -1, size, nid);
+}
 extern void gen_pool_destroy(struct gen_pool *);
 extern unsigned long gen_pool_alloc(struct gen_pool *, size_t);
 extern void gen_pool_free(struct gen_pool *, unsigned long, size_t);
+#endif /* __GENALLOC_H__ */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index d764a426e9fd..b78956b3c2e7 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -100,7 +100,6 @@ struct hd_struct {
         sector_t start_sect;
         sector_t nr_sects;
         sector_t alignment_offset;
-        unsigned int discard_alignment;
         struct device __dev;
         struct kobject *holder_dir;
         int policy, partno;
@@ -127,6 +126,7 @@ struct hd_struct {
 #define GENHD_FL_SUPPRESS_PARTITION_INFO        32
 #define GENHD_FL_EXT_DEVT                       64 /* allow extended devt */
 #define GENHD_FL_NATIVE_CAPACITY                128
+#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE     256
 
 enum {
         DISK_EVENT_MEDIA_CHANGE                 = 1 << 0, /* media changed */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 56d8fc87fbbc..cb4089254f01 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -249,14 +249,7 @@ static inline enum zone_type gfp_zone(gfp_t flags)
 
         z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) &
                                          ((1 << ZONES_SHIFT) - 1);
-
-        if (__builtin_constant_p(bit))
-                BUILD_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
-        else {
-#ifdef CONFIG_DEBUG_VM
-                BUG_ON((GFP_ZONE_BAD >> bit) & 1);
-#endif
-        }
+        VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
         return z;
 }
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8847c8c29791..48c32ebf65a7 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -92,12 +92,8 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
 #define wait_split_huge_page(__anon_vma, __pmd)                         \
         do {                                                            \
                 pmd_t *____pmd = (__pmd);                               \
-                spin_unlock_wait(&(__anon_vma)->root->lock);            \
-                /*                                                      \
-                 * spin_unlock_wait() is just a loop in C and so the    \
-                 * CPU can reorder anything around it.                  \
-                 */                                                     \
-                smp_mb();                                               \
+                anon_vma_lock(__anon_vma);                              \
+                anon_vma_unlock(__anon_vma);                            \
                 BUG_ON(pmd_trans_splitting(*____pmd) ||                 \
                        pmd_trans_huge(*____pmd));                       \
         } while (0)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index f37ba716ef8b..fb0e7329fee1 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -248,6 +248,37 @@ int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
 int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
 int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
 
+int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
+int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
+int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res);
+int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res);
+int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res);
+int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res);
+int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res);
+int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
+int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
+int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
+
+static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
+{
+        return kstrtoull_from_user(s, count, base, res);
+}
+
+static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res)
+{
+        return kstrtoll_from_user(s, count, base, res);
+}
+
+static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res)
+{
+        return kstrtouint_from_user(s, count, base, res);
+}
+
+static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res)
+{
+        return kstrtoint_from_user(s, count, base, res);
+}
+
 extern unsigned long simple_strtoul(const char *,char **,unsigned int);
 extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
@@ -638,6 +669,13 @@ struct sysinfo {
         char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */
 };
 
+#ifdef __CHECKER__
+#define BUILD_BUG_ON_NOT_POWER_OF_2(n)
+#define BUILD_BUG_ON_ZERO(e)
+#define BUILD_BUG_ON_NULL(e)
+#define BUILD_BUG_ON(condition)
+#else /* __CHECKER__ */
+
 /* Force a compilation error if a constant expression is not a power of 2 */
 #define BUILD_BUG_ON_NOT_POWER_OF_2(n)                  \
         BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
@@ -674,6 +712,7 @@ extern int __build_bug_on_failed;
                 if (condition) __build_bug_on_failed = 1;       \
         } while(0)
 #endif
+#endif  /* __CHECKER__ */
 
 /* Trap pasters of __FUNCTION__ at compile-time */
 #define __FUNCTION__ (__func__)
diff --git a/include/linux/leds-pca9532.h b/include/linux/leds-pca9532.h
index f158eb1149aa..b8d6fffed4d8 100644
--- a/include/linux/leds-pca9532.h
+++ b/include/linux/leds-pca9532.h
@@ -25,7 +25,7 @@ enum pca9532_state {
 };
 
 enum pca9532_type { PCA9532_TYPE_NONE, PCA9532_TYPE_LED,
-        PCA9532_TYPE_N2100_BEEP };
+        PCA9532_TYPE_N2100_BEEP, PCA9532_TYPE_GPIO };
 
 struct pca9532_led {
         u8 id;
@@ -41,6 +41,7 @@ struct pca9532_platform_data {
         struct pca9532_led leds[16];
         u8 pwm[2];
         u8 psc[2];
+        int gpio_base;
 };
 
 #endif /* __LINUX_PCA9532_H */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 61e0340a4b77..5884def15a24 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -207,5 +207,7 @@ struct gpio_led_platform_data {
                                         unsigned long *delay_off);
 };
 
+struct platform_device *gpio_led_register_device(
+                int id, const struct gpio_led_platform_data *pdata);
 
 #endif          /* __LINUX_LEDS_H_INCLUDED */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 4aef1dda6406..ef820a3c378b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -487,12 +487,15 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define mutex_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define mutex_acquire_nest(l, s, t, n, i)     lock_acquire(l, s, t, 0, 2, n, i)
 # else
 #  define mutex_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define mutex_acquire_nest(l, s, t, n, i)     lock_acquire(l, s, t, 0, 1, n, i)
 # endif
 # define mutex_release(l, n, i)                 lock_release(l, n, i)
 #else
 # define mutex_acquire(l, s, t, i)              do { } while (0)
+# define mutex_acquire_nest(l, s, t, n, i)      do { } while (0)
 # define mutex_release(l, n, i)                 do { } while (0)
 #endif
 
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 6a4fab7c6e09..7a71ffad037c 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -139,9 +139,9 @@ write intent log information, three of which are mentioned here.
  * .list is on one of three lists:
  *  in_use: currently in use (refcnt > 0, lc_number != LC_FREE)
  *     lru: unused but ready to be reused or recycled
- *          (ts_refcnt == 0, lc_number != LC_FREE),
+ *          (lc_refcnt == 0, lc_number != LC_FREE),
  *    free: unused but ready to be recycled
- *          (ts_refcnt == 0, lc_number == LC_FREE),
+ *          (lc_refcnt == 0, lc_number == LC_FREE),
  *
  * an element is said to be "in the active set",
  * if either on "in_use" or "lru", i.e. lc_number != LC_FREE.
@@ -160,8 +160,8 @@ struct lc_element {
         struct hlist_node colision;
         struct list_head list;           /* LRU list or free list */
         unsigned refcnt;
-        /* back "pointer" into ts_cache->element[index],
-         * for paranoia, and for "ts_element_to_index" */
+        /* back "pointer" into lc_cache->element[index],
+         * for paranoia, and for "lc_element_to_index" */
         unsigned lc_index;
         /* if we want to track a larger set of objects,
          * it needs to become arch independend u64 */
@@ -190,8 +190,8 @@ struct lru_cache {
         /* Arbitrary limit on maximum tracked objects. Practical limit is much
          * lower due to allocation failures, probably. For typical use cases,
          * nr_elements should be a few thousand at most.
-         * This also limits the maximum value of ts_element.ts_index, allowing the
-         * 8 high bits of .ts_index to be overloaded with flags in the future. */
+         * This also limits the maximum value of lc_element.lc_index, allowing the
+         * 8 high bits of .lc_index to be overloaded with flags in the future. */
 #define LC_MAX_ACTIVE   (1<<24)
 
         /* statistics */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 62a10c2a11f2..7525e38c434d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,6 +2,8 @@
 #define _LINUX_MEMBLOCK_H
 #ifdef __KERNEL__
 
+#define MEMBLOCK_ERROR  0
+
 #ifdef CONFIG_HAVE_MEMBLOCK
 /*
  * Logical memory blocks.
@@ -20,7 +22,6 @@
 #include <asm/memblock.h>
 
 #define INIT_MEMBLOCK_REGIONS   128
-#define MEMBLOCK_ERROR          0
 
 struct memblock_region {
         phys_addr_t base;
@@ -160,6 +161,12 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 #define __initdata_memblock
 #endif
 
+#else
+static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
+{
+        return MEMBLOCK_ERROR;
+}
+
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 31ac26ca4acf..7978eec1b7d9 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -199,6 +199,9 @@ void mpol_free_shared_policy(struct shared_policy *p);
 struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
                                             unsigned long idx);
 
+struct mempolicy *get_vma_policy(struct task_struct *tsk,
+                struct vm_area_struct *vma, unsigned long addr);
+
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
 extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
@@ -228,10 +231,10 @@ int do_migrate_pages(struct mm_struct *mm,
 
 #ifdef CONFIG_TMPFS
 extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context);
+#endif
 
 extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
                         int no_context);
-#endif
 
 /* Check if a vma is migratable */
 static inline int vma_migratable(struct vm_area_struct *vma)
@@ -368,13 +371,13 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol,
 {
         return 1;       /* error */
 }
+#endif
 
 static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
                                 int no_context)
 {
         return 0;
 }
-#endif
 
 #endif /* CONFIG_NUMA */
 #endif /* __KERNEL__ */
diff --git a/include/linux/mfd/db5500-prcmu.h b/include/linux/mfd/db5500-prcmu.h
new file mode 100644
index 000000000000..f0977986402c
--- /dev/null
+++ b/include/linux/mfd/db5500-prcmu.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * U5500 PRCMU API.
+ */
+#ifndef __MACH_PRCMU_U5500_H
+#define __MACH_PRCMU_U5500_H
+
+#ifdef CONFIG_UX500_SOC_DB5500
+
+void db5500_prcmu_early_init(void);
+
+int db5500_prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
+int db5500_prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
+
+#else /* !CONFIG_UX500_SOC_DB5500 */
+
+static inline void db5500_prcmu_early_init(void)
+{
+}
+
+static inline int db5500_prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        return -ENOSYS;
+}
+
+static inline int db5500_prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        return -ENOSYS;
+}
+
+#endif /* CONFIG_UX500_SOC_DB5500 */
+
+static inline int db5500_prcmu_config_abb_event_readout(u32 abb_events)
+{
+#ifdef CONFIG_MACH_U5500_SIMULATOR
+        return 0;
+#else
+        return -1;
+#endif
+}
+
+#endif /* __MACH_PRCMU_U5500_H */
diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h
new file mode 100644
index 000000000000..917dbcab701c
--- /dev/null
+++ b/include/linux/mfd/db8500-prcmu.h
@@ -0,0 +1,978 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Kumar Sanghvi <kumar.sanghvi@stericsson.com>
+ *
+ * PRCMU f/w APIs
+ */
+#ifndef __MFD_DB8500_PRCMU_H
+#define __MFD_DB8500_PRCMU_H
+
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+
+/* This portion previously known as <mach/prcmu-fw-defs_v1.h> */
+
+/**
+ * enum state - ON/OFF state definition
+ * @OFF: State is ON
+ * @ON: State is OFF
+ *
+ */
+enum state {
+        OFF = 0x0,
+        ON  = 0x1,
+};
+
+/**
+ * enum ret_state - general purpose On/Off/Retention states
+ *
+ */
+enum ret_state {
+        OFFST = 0,
+        ONST  = 1,
+        RETST = 2
+};
+
+/**
+ * enum clk_arm - ARM Cortex A9 clock schemes
+ * @A9_OFF:
+ * @A9_BOOT:
+ * @A9_OPPT1:
+ * @A9_OPPT2:
+ * @A9_EXTCLK:
+ */
+enum clk_arm {
+        A9_OFF,
+        A9_BOOT,
+        A9_OPPT1,
+        A9_OPPT2,
+        A9_EXTCLK
+};
+
+/**
+ * enum clk_gen - GEN#0/GEN#1 clock schemes
+ * @GEN_OFF:
+ * @GEN_BOOT:
+ * @GEN_OPPT1:
+ */
+enum clk_gen {
+        GEN_OFF,
+        GEN_BOOT,
+        GEN_OPPT1,
+};
+
+/* some information between arm and xp70 */
+
+/**
+ * enum romcode_write - Romcode message written by A9 AND read by XP70
+ * @RDY_2_DS: Value set when ApDeepSleep state can be executed by XP70
+ * @RDY_2_XP70_RST: Value set when 0x0F has been successfully polled by the
+ *                 romcode. The xp70 will go into self-reset
+ */
+enum romcode_write {
+        RDY_2_DS = 0x09,
+        RDY_2_XP70_RST = 0x10
+};
+
+/**
+ * enum romcode_read - Romcode message written by XP70 and read by A9
+ * @INIT: Init value when romcode field is not used
+ * @FS_2_DS: Value set when power state is going from ApExecute to
+ *          ApDeepSleep
+ * @END_DS: Value set when ApDeepSleep power state is reached coming from
+ *         ApExecute state
+ * @DS_TO_FS: Value set when power state is going from ApDeepSleep to
+ *           ApExecute
+ * @END_FS: Value set when ApExecute power state is reached coming from
+ *         ApDeepSleep state
+ * @SWR: Value set when power state is going to ApReset
+ * @END_SWR: Value set when the xp70 finished executing ApReset actions and
+ *          waits for romcode acknowledgment to go to self-reset
+ */
+enum romcode_read {
+        INIT = 0x00,
+        FS_2_DS = 0x0A,
+        END_DS = 0x0B,
+        DS_TO_FS = 0x0C,
+        END_FS = 0x0D,
+        SWR = 0x0E,
+        END_SWR = 0x0F
+};
+
+/**
+ * enum ap_pwrst - current power states defined in PRCMU firmware
+ * @NO_PWRST: Current power state init
+ * @AP_BOOT: Current power state is apBoot
+ * @AP_EXECUTE: Current power state is apExecute
+ * @AP_DEEP_SLEEP: Current power state is apDeepSleep
+ * @AP_SLEEP: Current power state is apSleep
+ * @AP_IDLE: Current power state is apIdle
+ * @AP_RESET: Current power state is apReset
+ */
+enum ap_pwrst {
+        NO_PWRST = 0x00,
+        AP_BOOT = 0x01,
+        AP_EXECUTE = 0x02,
+        AP_DEEP_SLEEP = 0x03,
+        AP_SLEEP = 0x04,
+        AP_IDLE = 0x05,
+        AP_RESET = 0x06
+};
+
+/**
+ * enum ap_pwrst_trans - Transition states defined in PRCMU firmware
+ * @NO_TRANSITION: No power state transition
+ * @APEXECUTE_TO_APSLEEP: Power state transition from ApExecute to ApSleep
+ * @APIDLE_TO_APSLEEP: Power state transition from ApIdle to ApSleep
+ * @APBOOT_TO_APEXECUTE: Power state transition from ApBoot to ApExecute
+ * @APEXECUTE_TO_APDEEPSLEEP: Power state transition from ApExecute to
+ *                          ApDeepSleep
+ * @APEXECUTE_TO_APIDLE: Power state transition from ApExecute to ApIdle
+ */
+enum ap_pwrst_trans {
+        NO_TRANSITION                   = 0x00,
+        APEXECUTE_TO_APSLEEP            = 0x01,
+        APIDLE_TO_APSLEEP               = 0x02, /* To be removed */
+        PRCMU_AP_SLEEP                  = 0x01,
+        APBOOT_TO_APEXECUTE             = 0x03,
+        APEXECUTE_TO_APDEEPSLEEP        = 0x04, /* To be removed */
+        PRCMU_AP_DEEP_SLEEP             = 0x04,
+        APEXECUTE_TO_APIDLE             = 0x05, /* To be removed */
+        PRCMU_AP_IDLE                   = 0x05,
+        PRCMU_AP_DEEP_IDLE              = 0x07,
+};
+
+/**
+ * enum ddr_pwrst - DDR power states definition
+ * @DDR_PWR_STATE_UNCHANGED: SDRAM and DDR controller state is unchanged
+ * @DDR_PWR_STATE_ON:
+ * @DDR_PWR_STATE_OFFLOWLAT:
+ * @DDR_PWR_STATE_OFFHIGHLAT:
+ */
+enum ddr_pwrst {
+        DDR_PWR_STATE_UNCHANGED     = 0x00,
+        DDR_PWR_STATE_ON            = 0x01,
+        DDR_PWR_STATE_OFFLOWLAT     = 0x02,
+        DDR_PWR_STATE_OFFHIGHLAT    = 0x03
+};
+
+/**
+ * enum arm_opp - ARM OPP states definition
+ * @ARM_OPP_INIT:
+ * @ARM_NO_CHANGE: The ARM operating point is unchanged
+ * @ARM_100_OPP: The new ARM operating point is arm100opp
+ * @ARM_50_OPP: The new ARM operating point is arm50opp
+ * @ARM_MAX_OPP: Operating point is "max" (more than 100)
+ * @ARM_MAX_FREQ100OPP: Set max opp if available, else 100
+ * @ARM_EXTCLK: The new ARM operating point is armExtClk
+ */
+enum arm_opp {
+        ARM_OPP_INIT = 0x00,
+        ARM_NO_CHANGE = 0x01,
+        ARM_100_OPP = 0x02,
+        ARM_50_OPP = 0x03,
+        ARM_MAX_OPP = 0x04,
+        ARM_MAX_FREQ100OPP = 0x05,
+        ARM_EXTCLK = 0x07
+};
+
+/**
+ * enum ape_opp - APE OPP states definition
+ * @APE_OPP_INIT:
+ * @APE_NO_CHANGE: The APE operating point is unchanged
+ * @APE_100_OPP: The new APE operating point is ape100opp
+ * @APE_50_OPP: 50%
+ */
+enum ape_opp {
+        APE_OPP_INIT = 0x00,
+        APE_NO_CHANGE = 0x01,
+        APE_100_OPP = 0x02,
+        APE_50_OPP = 0x03
+};
+
+/**
+ * enum hw_acc_state - State definition for hardware accelerator
+ * @HW_NO_CHANGE: The hardware accelerator state must remain unchanged
+ * @HW_OFF: The hardware accelerator must be switched off
+ * @HW_OFF_RAMRET: The hardware accelerator must be switched off with its
+ *               internal RAM in retention
+ * @HW_ON: The hwa hardware accelerator hwa must be switched on
+ *
+ * NOTE! Deprecated, to be removed when all users switched over to use the
+ * regulator API.
+ */
+enum hw_acc_state {
+        HW_NO_CHANGE = 0x00,
+        HW_OFF = 0x01,
+        HW_OFF_RAMRET = 0x02,
+        HW_ON = 0x04
+};
+
+/**
+ * enum  mbox_2_arm_stat - Status messages definition for mbox_arm
+ * @BOOT_TO_EXECUTEOK: The apBoot to apExecute state transition has been
+ *                    completed
+ * @DEEPSLEEPOK: The apExecute to apDeepSleep state transition has been
+ *              completed
+ * @SLEEPOK: The apExecute to apSleep state transition has been completed
+ * @IDLEOK: The apExecute to apIdle state transition has been completed
+ * @SOFTRESETOK: The A9 watchdog/ SoftReset state has been completed
+ * @SOFTRESETGO : The A9 watchdog/SoftReset state is on going
+ * @BOOT_TO_EXECUTE: The apBoot to apExecute state transition is on going
+ * @EXECUTE_TO_DEEPSLEEP: The apExecute to apDeepSleep state transition is on
+ *                       going
+ * @DEEPSLEEP_TO_EXECUTE: The apDeepSleep to apExecute state transition is on
+ *                       going
+ * @DEEPSLEEP_TO_EXECUTEOK: The apDeepSleep to apExecute state transition has
+ *                         been completed
+ * @EXECUTE_TO_SLEEP: The apExecute to apSleep state transition is on going
+ * @SLEEP_TO_EXECUTE: The apSleep to apExecute state transition is on going
+ * @SLEEP_TO_EXECUTEOK: The apSleep to apExecute state transition has been
+ *                     completed
+ * @EXECUTE_TO_IDLE: The apExecute to apIdle state transition is on going
+ * @IDLE_TO_EXECUTE: The apIdle to apExecute state transition is on going
+ * @IDLE_TO_EXECUTEOK: The apIdle to apExecute state transition has been
+ *                    completed
+ * @INIT_STATUS: Status init
+ */
+enum ap_pwrsttr_status {
+        BOOT_TO_EXECUTEOK = 0xFF,
+        DEEPSLEEPOK = 0xFE,
+        SLEEPOK = 0xFD,
+        IDLEOK = 0xFC,
+        SOFTRESETOK = 0xFB,
+        SOFTRESETGO = 0xFA,
+        BOOT_TO_EXECUTE = 0xF9,
+        EXECUTE_TO_DEEPSLEEP = 0xF8,
+        DEEPSLEEP_TO_EXECUTE = 0xF7,
+        DEEPSLEEP_TO_EXECUTEOK = 0xF6,
+        EXECUTE_TO_SLEEP = 0xF5,
+        SLEEP_TO_EXECUTE = 0xF4,
+        SLEEP_TO_EXECUTEOK = 0xF3,
+        EXECUTE_TO_IDLE = 0xF2,
+        IDLE_TO_EXECUTE = 0xF1,
+        IDLE_TO_EXECUTEOK = 0xF0,
+        RDYTODS_RETURNTOEXE    = 0xEF,
+        NORDYTODS_RETURNTOEXE  = 0xEE,
+        EXETOSLEEP_RETURNTOEXE = 0xED,
+        EXETOIDLE_RETURNTOEXE  = 0xEC,
+        INIT_STATUS = 0xEB,
+
+        /*error messages */
+        INITERROR                     = 0x00,
+        PLLARMLOCKP_ER                = 0x01,
+        PLLDDRLOCKP_ER                = 0x02,
+        PLLSOCLOCKP_ER                = 0x03,
+        PLLSOCK1LOCKP_ER              = 0x04,
+        ARMWFI_ER                     = 0x05,
+        SYSCLKOK_ER                   = 0x06,
+        I2C_NACK_DATA_ER              = 0x07,
+        BOOT_ER                       = 0x08,
+        I2C_STATUS_ALWAYS_1           = 0x0A,
+        I2C_NACK_REG_ADDR_ER          = 0x0B,
+        I2C_NACK_DATA0123_ER          = 0x1B,
+        I2C_NACK_ADDR_ER              = 0x1F,
+        CURAPPWRSTISNOT_BOOT          = 0x20,
+        CURAPPWRSTISNOT_EXECUTE       = 0x21,
+        CURAPPWRSTISNOT_SLEEPMODE     = 0x22,
+        CURAPPWRSTISNOT_CORRECTFORIT10 = 0x23,
+        FIFO4500WUISNOT_WUPEVENT      = 0x24,
+        PLL32KLOCKP_ER                = 0x29,
+        DDRDEEPSLEEPOK_ER             = 0x2A,
+        ROMCODEREADY_ER               = 0x50,
+        WUPBEFOREDS                   = 0x51,
+        DDRCONFIG_ER                  = 0x52,
+        WUPBEFORESLEEP                = 0x53,
+        WUPBEFOREIDLE                 = 0x54
+};  /* earlier called as  mbox_2_arm_stat */
+
+/**
+ * enum dvfs_stat - DVFS status messages definition
+ * @DVFS_GO: A state transition DVFS is on going
+ * @DVFS_ARM100OPPOK: The state transition DVFS has been completed for 100OPP
+ * @DVFS_ARM50OPPOK: The state transition DVFS has been completed for 50OPP
+ * @DVFS_ARMEXTCLKOK: The state transition DVFS has been completed for EXTCLK
+ * @DVFS_NOCHGTCLKOK: The state transition DVFS has been completed for
+ *                   NOCHGCLK
+ * @DVFS_INITSTATUS: Value init
+ */
+enum dvfs_stat {
+        DVFS_GO = 0xFF,
+        DVFS_ARM100OPPOK = 0xFE,
+        DVFS_ARM50OPPOK = 0xFD,
+        DVFS_ARMEXTCLKOK = 0xFC,
+        DVFS_NOCHGTCLKOK = 0xFB,
+        DVFS_INITSTATUS = 0x00
+};
+
+/**
+ * enum sva_mmdsp_stat - SVA MMDSP status messages
+ * @SVA_MMDSP_GO: SVAMMDSP interrupt has happened
+ * @SVA_MMDSP_INIT: Status init
+ */
+enum sva_mmdsp_stat {
+        SVA_MMDSP_GO = 0xFF,
+        SVA_MMDSP_INIT = 0x00
+};
+
+/**
+ * enum sia_mmdsp_stat - SIA MMDSP status messages
+ * @SIA_MMDSP_GO: SIAMMDSP interrupt has happened
+ * @SIA_MMDSP_INIT: Status init
+ */
+enum sia_mmdsp_stat {
+        SIA_MMDSP_GO = 0xFF,
+        SIA_MMDSP_INIT = 0x00
+};
+
+/**
+ * enum  mbox_to_arm_err - Error messages definition
+ * @INIT_ERR: Init value
+ * @PLLARMLOCKP_ERR: PLLARM has not been correctly locked in given time
+ * @PLLDDRLOCKP_ERR: PLLDDR has not been correctly locked in the given time
+ * @PLLSOC0LOCKP_ERR: PLLSOC0 has not been correctly locked in the given time
+ * @PLLSOC1LOCKP_ERR: PLLSOC1 has not been correctly locked in the given time
+ * @ARMWFI_ERR: The ARM WFI has not been correctly executed in the given time
+ * @SYSCLKOK_ERR: The SYSCLK is not available in the given time
+ * @BOOT_ERR: Romcode has not validated the XP70 self reset in the given time
+ * @ROMCODESAVECONTEXT: The Romcode didn.t correctly save it secure context
+ * @VARMHIGHSPEEDVALTO_ERR: The ARM high speed supply value transfered
+ *          through I2C has not been correctly executed in the given time
+ * @VARMHIGHSPEEDACCESS_ERR: The command value of VarmHighSpeedVal transfered
+ *             through I2C has not been correctly executed in the given time
+ * @VARMLOWSPEEDVALTO_ERR:The ARM low speed supply value transfered through
+ *                     I2C has not been correctly executed in the given time
+ * @VARMLOWSPEEDACCESS_ERR: The command value of VarmLowSpeedVal transfered
+ *             through I2C has not been correctly executed in the given time
+ * @VARMRETENTIONVALTO_ERR: The ARM retention supply value transfered through
+ *                     I2C has not been correctly executed in the given time
+ * @VARMRETENTIONACCESS_ERR: The command value of VarmRetentionVal transfered
+ *             through I2C has not been correctly executed in the given time
+ * @VAPEHIGHSPEEDVALTO_ERR: The APE highspeed supply value transfered through
+ *                     I2C has not been correctly executed in the given time
+ * @VSAFEHPVALTO_ERR: The SAFE high power supply value transfered through I2C
+ *                         has not been correctly executed in the given time
+ * @VMODSEL1VALTO_ERR: The MODEM sel1 supply value transfered through I2C has
+ *                             not been correctly executed in the given time
+ * @VMODSEL2VALTO_ERR: The MODEM sel2 supply value transfered through I2C has
+ *                             not been correctly executed in the given time
+ * @VARMOFFACCESS_ERR: The command value of Varm ON/OFF transfered through
+ *                     I2C has not been correctly executed in the given time
+ * @VAPEOFFACCESS_ERR: The command value of Vape ON/OFF transfered through
+ *                     I2C has not been correctly executed in the given time
+ * @VARMRETACCES_ERR: The command value of Varm retention ON/OFF transfered
+ *             through I2C has not been correctly executed in the given time
+ * @CURAPPWRSTISNOTBOOT:Generated when Arm want to do power state transition
+ *             ApBoot to ApExecute but the power current state is not Apboot
+ * @CURAPPWRSTISNOTEXECUTE: Generated when Arm want to do power state
+ *              transition from ApExecute to others power state but the
+ *              power current state is not ApExecute
+ * @CURAPPWRSTISNOTSLEEPMODE: Generated when wake up events are transmitted
+ *             but the power current state is not ApDeepSleep/ApSleep/ApIdle
+ * @CURAPPWRSTISNOTCORRECTDBG:  Generated when wake up events are transmitted
+ *              but the power current state is not correct
+ * @ARMREGU1VALTO_ERR:The ArmRegu1 value transferred through I2C has not
+ *                    been correctly executed in the given time
+ * @ARMREGU2VALTO_ERR: The ArmRegu2 value transferred through I2C has not
+ *                    been correctly executed in the given time
+ * @VAPEREGUVALTO_ERR: The VApeRegu value transfered through I2C has not
+ *                    been correctly executed in the given time
+ * @VSMPS3REGUVALTO_ERR: The VSmps3Regu value transfered through I2C has not
+ *                      been correctly executed in the given time
+ * @VMODREGUVALTO_ERR: The VModemRegu value transfered through I2C has not
+ *                    been correctly executed in the given time
+ */
+enum mbox_to_arm_err {
+        INIT_ERR = 0x00,
+        PLLARMLOCKP_ERR = 0x01,
+        PLLDDRLOCKP_ERR = 0x02,
+        PLLSOC0LOCKP_ERR = 0x03,
+        PLLSOC1LOCKP_ERR = 0x04,
+        ARMWFI_ERR = 0x05,
+        SYSCLKOK_ERR = 0x06,
+        BOOT_ERR = 0x07,
+        ROMCODESAVECONTEXT = 0x08,
+        VARMHIGHSPEEDVALTO_ERR = 0x10,
+        VARMHIGHSPEEDACCESS_ERR = 0x11,
+        VARMLOWSPEEDVALTO_ERR = 0x12,
+        VARMLOWSPEEDACCESS_ERR = 0x13,
+        VARMRETENTIONVALTO_ERR = 0x14,
+        VARMRETENTIONACCESS_ERR = 0x15,
+        VAPEHIGHSPEEDVALTO_ERR = 0x16,
+        VSAFEHPVALTO_ERR = 0x17,
+        VMODSEL1VALTO_ERR = 0x18,
+        VMODSEL2VALTO_ERR = 0x19,
+        VARMOFFACCESS_ERR = 0x1A,
+        VAPEOFFACCESS_ERR = 0x1B,
+        VARMRETACCES_ERR = 0x1C,
+        CURAPPWRSTISNOTBOOT = 0x20,
+        CURAPPWRSTISNOTEXECUTE = 0x21,
+        CURAPPWRSTISNOTSLEEPMODE = 0x22,
+        CURAPPWRSTISNOTCORRECTDBG = 0x23,
+        ARMREGU1VALTO_ERR = 0x24,
+        ARMREGU2VALTO_ERR = 0x25,
+        VAPEREGUVALTO_ERR = 0x26,
+        VSMPS3REGUVALTO_ERR = 0x27,
+        VMODREGUVALTO_ERR = 0x28
+};
+
+enum hw_acc {
+        SVAMMDSP = 0,
+        SVAPIPE = 1,
+        SIAMMDSP = 2,
+        SIAPIPE = 3,
+        SGA = 4,
+        B2R2MCDE = 5,
+        ESRAM12 = 6,
+        ESRAM34 = 7,
+};
+
+enum cs_pwrmgt {
+        PWRDNCS0  = 0,
+        WKUPCS0   = 1,
+        PWRDNCS1  = 2,
+        WKUPCS1   = 3
+};
+
+/* Defs related to autonomous power management */
+
+/**
+ * enum sia_sva_pwr_policy - Power policy
+ * @NO_CHGT:    No change
+ * @DSPOFF_HWPOFF:
+ * @DSPOFFRAMRET_HWPOFF:
+ * @DSPCLKOFF_HWPOFF:
+ * @DSPCLKOFF_HWPCLKOFF:
+ *
+ */
+enum sia_sva_pwr_policy {
+        NO_CHGT                 = 0x0,
+        DSPOFF_HWPOFF           = 0x1,
+        DSPOFFRAMRET_HWPOFF     = 0x2,
+        DSPCLKOFF_HWPOFF        = 0x3,
+        DSPCLKOFF_HWPCLKOFF     = 0x4,
+};
+
+/**
+ * enum auto_enable - Auto Power enable
+ * @AUTO_OFF:
+ * @AUTO_ON:
+ *
+ */
+enum auto_enable {
+        AUTO_OFF        = 0x0,
+        AUTO_ON         = 0x1,
+};
+
+/* End of file previously known as prcmu-fw-defs_v1.h */
+
+/* PRCMU Wakeup defines */
+enum prcmu_wakeup_index {
+        PRCMU_WAKEUP_INDEX_RTC,
+        PRCMU_WAKEUP_INDEX_RTT0,
+        PRCMU_WAKEUP_INDEX_RTT1,
+        PRCMU_WAKEUP_INDEX_HSI0,
+        PRCMU_WAKEUP_INDEX_HSI1,
+        PRCMU_WAKEUP_INDEX_USB,
+        PRCMU_WAKEUP_INDEX_ABB,
+        PRCMU_WAKEUP_INDEX_ABB_FIFO,
+        PRCMU_WAKEUP_INDEX_ARM,
+        NUM_PRCMU_WAKEUP_INDICES
+};
+#define PRCMU_WAKEUP(_name) (BIT(PRCMU_WAKEUP_INDEX_##_name))
+
+/* PRCMU QoS APE OPP class */
+#define PRCMU_QOS_APE_OPP 1
+#define PRCMU_QOS_DDR_OPP 2
+#define PRCMU_QOS_DEFAULT_VALUE -1
+
+/**
+ * enum hw_acc_dev - enum for hw accelerators
+ * @HW_ACC_SVAMMDSP: for SVAMMDSP
+ * @HW_ACC_SVAPIPE:  for SVAPIPE
+ * @HW_ACC_SIAMMDSP: for SIAMMDSP
+ * @HW_ACC_SIAPIPE: for SIAPIPE
+ * @HW_ACC_SGA: for SGA
+ * @HW_ACC_B2R2: for B2R2
+ * @HW_ACC_MCDE: for MCDE
+ * @HW_ACC_ESRAM1: for ESRAM1
+ * @HW_ACC_ESRAM2: for ESRAM2
+ * @HW_ACC_ESRAM3: for ESRAM3
+ * @HW_ACC_ESRAM4: for ESRAM4
+ * @NUM_HW_ACC: number of hardware accelerators
+ *
+ * Different hw accelerators which can be turned ON/
+ * OFF or put into retention (MMDSPs and ESRAMs).
+ * Used with EPOD API.
+ *
+ * NOTE! Deprecated, to be removed when all users switched over to use the
+ * regulator API.
+ */
+enum hw_acc_dev {
+        HW_ACC_SVAMMDSP,
+        HW_ACC_SVAPIPE,
+        HW_ACC_SIAMMDSP,
+        HW_ACC_SIAPIPE,
+        HW_ACC_SGA,
+        HW_ACC_B2R2,
+        HW_ACC_MCDE,
+        HW_ACC_ESRAM1,
+        HW_ACC_ESRAM2,
+        HW_ACC_ESRAM3,
+        HW_ACC_ESRAM4,
+        NUM_HW_ACC
+};
+
+/*
+ * Ids for all EPODs (power domains)
+ * - EPOD_ID_SVAMMDSP: power domain for SVA MMDSP
+ * - EPOD_ID_SVAPIPE: power domain for SVA pipe
+ * - EPOD_ID_SIAMMDSP: power domain for SIA MMDSP
+ * - EPOD_ID_SIAPIPE: power domain for SIA pipe
+ * - EPOD_ID_SGA: power domain for SGA
+ * - EPOD_ID_B2R2_MCDE: power domain for B2R2 and MCDE
+ * - EPOD_ID_ESRAM12: power domain for ESRAM 1 and 2
+ * - EPOD_ID_ESRAM34: power domain for ESRAM 3 and 4
+ * - NUM_EPOD_ID: number of power domains
+ */
+#define EPOD_ID_SVAMMDSP        0
+#define EPOD_ID_SVAPIPE         1
+#define EPOD_ID_SIAMMDSP        2
+#define EPOD_ID_SIAPIPE         3
+#define EPOD_ID_SGA             4
+#define EPOD_ID_B2R2_MCDE       5
+#define EPOD_ID_ESRAM12         6
+#define EPOD_ID_ESRAM34         7
+#define NUM_EPOD_ID             8
+
+/*
+ * state definition for EPOD (power domain)
+ * - EPOD_STATE_NO_CHANGE: The EPOD should remain unchanged
+ * - EPOD_STATE_OFF: The EPOD is switched off
+ * - EPOD_STATE_RAMRET: The EPOD is switched off with its internal RAM in
+ *                         retention
+ * - EPOD_STATE_ON_CLK_OFF: The EPOD is switched on, clock is still off
+ * - EPOD_STATE_ON: Same as above, but with clock enabled
+ */
+#define EPOD_STATE_NO_CHANGE    0x00
+#define EPOD_STATE_OFF          0x01
+#define EPOD_STATE_RAMRET       0x02
+#define EPOD_STATE_ON_CLK_OFF   0x03
+#define EPOD_STATE_ON           0x04
+
+/*
+ * CLKOUT sources
+ */
+#define PRCMU_CLKSRC_CLK38M             0x00
+#define PRCMU_CLKSRC_ACLK               0x01
+#define PRCMU_CLKSRC_SYSCLK             0x02
+#define PRCMU_CLKSRC_LCDCLK             0x03
+#define PRCMU_CLKSRC_SDMMCCLK           0x04
+#define PRCMU_CLKSRC_TVCLK              0x05
+#define PRCMU_CLKSRC_TIMCLK             0x06
+#define PRCMU_CLKSRC_CLK009             0x07
+/* These are only valid for CLKOUT1: */
+#define PRCMU_CLKSRC_SIAMMDSPCLK        0x40
+#define PRCMU_CLKSRC_I2CCLK             0x41
+#define PRCMU_CLKSRC_MSP02CLK           0x42
+#define PRCMU_CLKSRC_ARMPLL_OBSCLK      0x43
+#define PRCMU_CLKSRC_HSIRXCLK           0x44
+#define PRCMU_CLKSRC_HSITXCLK           0x45
+#define PRCMU_CLKSRC_ARMCLKFIX          0x46
+#define PRCMU_CLKSRC_HDMICLK            0x47
+
+/*
+ * Definitions for autonomous power management configuration.
+ */
+
+#define PRCMU_AUTO_PM_OFF 0
+#define PRCMU_AUTO_PM_ON 1
+
+#define PRCMU_AUTO_PM_POWER_ON_HSEM BIT(0)
+#define PRCMU_AUTO_PM_POWER_ON_ABB_FIFO_IT BIT(1)
+
+enum prcmu_auto_pm_policy {
+        PRCMU_AUTO_PM_POLICY_NO_CHANGE,
+        PRCMU_AUTO_PM_POLICY_DSP_OFF_HWP_OFF,
+        PRCMU_AUTO_PM_POLICY_DSP_OFF_RAMRET_HWP_OFF,
+        PRCMU_AUTO_PM_POLICY_DSP_CLK_OFF_HWP_OFF,
+        PRCMU_AUTO_PM_POLICY_DSP_CLK_OFF_HWP_CLK_OFF,
+};
+
+/**
+ * struct prcmu_auto_pm_config - Autonomous power management configuration.
+ * @sia_auto_pm_enable: SIA autonomous pm enable. (PRCMU_AUTO_PM_{OFF,ON})
+ * @sia_power_on:       SIA power ON enable. (PRCMU_AUTO_PM_POWER_ON_* bitmask)
+ * @sia_policy:         SIA power policy. (enum prcmu_auto_pm_policy)
+ * @sva_auto_pm_enable: SVA autonomous pm enable. (PRCMU_AUTO_PM_{OFF,ON})
+ * @sva_power_on:       SVA power ON enable. (PRCMU_AUTO_PM_POWER_ON_* bitmask)
+ * @sva_policy:         SVA power policy. (enum prcmu_auto_pm_policy)
+ */
+struct prcmu_auto_pm_config {
+        u8 sia_auto_pm_enable;
+        u8 sia_power_on;
+        u8 sia_policy;
+        u8 sva_auto_pm_enable;
+        u8 sva_power_on;
+        u8 sva_policy;
+};
+
+/**
+ * enum ddr_opp - DDR OPP states definition
+ * @DDR_100_OPP: The new DDR operating point is ddr100opp
+ * @DDR_50_OPP: The new DDR operating point is ddr50opp
+ * @DDR_25_OPP: The new DDR operating point is ddr25opp
+ */
+enum ddr_opp {
+        DDR_100_OPP = 0x00,
+        DDR_50_OPP = 0x01,
+        DDR_25_OPP = 0x02,
+};
+
+/*
+ * Clock identifiers.
+ */
+enum prcmu_clock {
+        PRCMU_SGACLK,
+        PRCMU_UARTCLK,
+        PRCMU_MSP02CLK,
+        PRCMU_MSP1CLK,
+        PRCMU_I2CCLK,
+        PRCMU_SDMMCCLK,
+        PRCMU_SLIMCLK,
+        PRCMU_PER1CLK,
+        PRCMU_PER2CLK,
+        PRCMU_PER3CLK,
+        PRCMU_PER5CLK,
+        PRCMU_PER6CLK,
+        PRCMU_PER7CLK,
+        PRCMU_LCDCLK,
+        PRCMU_BMLCLK,
+        PRCMU_HSITXCLK,
+        PRCMU_HSIRXCLK,
+        PRCMU_HDMICLK,
+        PRCMU_APEATCLK,
+        PRCMU_APETRACECLK,
+        PRCMU_MCDECLK,
+        PRCMU_IPI2CCLK,
+        PRCMU_DSIALTCLK,
+        PRCMU_DMACLK,
+        PRCMU_B2R2CLK,
+        PRCMU_TVCLK,
+        PRCMU_SSPCLK,
+        PRCMU_RNGCLK,
+        PRCMU_UICCCLK,
+        PRCMU_NUM_REG_CLOCKS,
+        PRCMU_SYSCLK = PRCMU_NUM_REG_CLOCKS,
+        PRCMU_TIMCLK,
+};
+
+/*
+ * Definitions for controlling ESRAM0 in deep sleep.
+ */
+#define ESRAM0_DEEP_SLEEP_STATE_OFF 1
+#define ESRAM0_DEEP_SLEEP_STATE_RET 2
+
+#ifdef CONFIG_MFD_DB8500_PRCMU
+void __init prcmu_early_init(void);
+int prcmu_set_display_clocks(void);
+int prcmu_disable_dsipll(void);
+int prcmu_enable_dsipll(void);
+#else
+static inline void __init prcmu_early_init(void) {}
+#endif
+
+#ifdef CONFIG_MFD_DB8500_PRCMU
+
+int prcmu_set_rc_a2p(enum romcode_write);
+enum romcode_read prcmu_get_rc_p2a(void);
+enum ap_pwrst prcmu_get_xp70_current_state(void);
+int prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll);
+
+void prcmu_enable_wakeups(u32 wakeups);
+static inline void prcmu_disable_wakeups(void)
+{
+        prcmu_enable_wakeups(0);
+}
+
+void prcmu_config_abb_event_readout(u32 abb_events);
+void prcmu_get_abb_event_buffer(void __iomem **buf);
+int prcmu_set_arm_opp(u8 opp);
+int prcmu_get_arm_opp(void);
+bool prcmu_has_arm_maxopp(void);
+bool prcmu_is_u8400(void);
+int prcmu_set_ape_opp(u8 opp);
+int prcmu_get_ape_opp(void);
+int prcmu_request_ape_opp_100_voltage(bool enable);
+int prcmu_release_usb_wakeup_state(void);
+int prcmu_set_ddr_opp(u8 opp);
+int prcmu_get_ddr_opp(void);
+unsigned long prcmu_qos_get_cpufreq_opp_delay(void);
+void prcmu_qos_set_cpufreq_opp_delay(unsigned long);
+/* NOTE! Use regulator framework instead */
+int prcmu_set_hwacc(u16 hw_acc_dev, u8 state);
+int prcmu_set_epod(u16 epod_id, u8 epod_state);
+void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep,
+        struct prcmu_auto_pm_config *idle);
+bool prcmu_is_auto_pm_enabled(void);
+
+int prcmu_config_clkout(u8 clkout, u8 source, u8 div);
+int prcmu_request_clock(u8 clock, bool enable);
+int prcmu_set_clock_divider(u8 clock, u8 divider);
+int prcmu_config_esram0_deep_sleep(u8 state);
+int prcmu_config_hotdog(u8 threshold);
+int prcmu_config_hotmon(u8 low, u8 high);
+int prcmu_start_temp_sense(u16 cycles32k);
+int prcmu_stop_temp_sense(void);
+int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
+int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
+
+void prcmu_ac_wake_req(void);
+void prcmu_ac_sleep_req(void);
+void prcmu_system_reset(u16 reset_code);
+void prcmu_modem_reset(void);
+bool prcmu_is_ac_wake_requested(void);
+void prcmu_enable_spi2(void);
+void prcmu_disable_spi2(void);
+
+#else /* !CONFIG_MFD_DB8500_PRCMU */
+
+static inline int prcmu_set_rc_a2p(enum romcode_write code)
+{
+        return 0;
+}
+
+static inline enum romcode_read prcmu_get_rc_p2a(void)
+{
+        return INIT;
+}
+
+static inline enum ap_pwrst prcmu_get_xp70_current_state(void)
+{
+        return AP_EXECUTE;
+}
+
+static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
+        bool keep_ap_pll)
+{
+        return 0;
+}
+
+static inline void prcmu_enable_wakeups(u32 wakeups) {}
+
+static inline void prcmu_disable_wakeups(void) {}
+
+static inline void prcmu_config_abb_event_readout(u32 abb_events) {}
+
+static inline int prcmu_set_arm_opp(u8 opp)
+{
+        return 0;
+}
+
+static inline int prcmu_get_arm_opp(void)
+{
+        return ARM_100_OPP;
+}
+
+static bool prcmu_has_arm_maxopp(void)
+{
+        return false;
+}
+
+static bool prcmu_is_u8400(void)
+{
+        return false;
+}
+
+static inline int prcmu_set_ape_opp(u8 opp)
+{
+        return 0;
+}
+
+static inline int prcmu_get_ape_opp(void)
+{
+        return APE_100_OPP;
+}
+
+static inline int prcmu_request_ape_opp_100_voltage(bool enable)
+{
+        return 0;
+}
+
+static inline int prcmu_release_usb_wakeup_state(void)
+{
+        return 0;
+}
+
+static inline int prcmu_set_ddr_opp(u8 opp)
+{
+        return 0;
+}
+
+static inline int prcmu_get_ddr_opp(void)
+{
+        return DDR_100_OPP;
+}
+
+static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void)
+{
+        return 0;
+}
+
+static inline void prcmu_qos_set_cpufreq_opp_delay(unsigned long n) {}
+
+static inline int prcmu_set_hwacc(u16 hw_acc_dev, u8 state)
+{
+        return 0;
+}
+
+static inline void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep,
+        struct prcmu_auto_pm_config *idle)
+{
+}
+
+static inline bool prcmu_is_auto_pm_enabled(void)
+{
+        return false;
+}
+
+static inline int prcmu_config_clkout(u8 clkout, u8 source, u8 div)
+{
+        return 0;
+}
+
+static inline int prcmu_request_clock(u8 clock, bool enable)
+{
+        return 0;
+}
+
+static inline int prcmu_set_clock_divider(u8 clock, u8 divider)
+{
+        return 0;
+}
+
+int prcmu_config_esram0_deep_sleep(u8 state)
+{
+        return 0;
+}
+
+static inline int prcmu_config_hotdog(u8 threshold)
+{
+        return 0;
+}
+
+static inline int prcmu_config_hotmon(u8 low, u8 high)
+{
+        return 0;
+}
+
+static inline int prcmu_start_temp_sense(u16 cycles32k)
+{
+        return 0;
+}
+
+static inline int prcmu_stop_temp_sense(void)
+{
+        return 0;
+}
+
+static inline int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        return -ENOSYS;
+}
+
+static inline int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+        return -ENOSYS;
+}
+
+static inline void prcmu_ac_wake_req(void) {}
+
+static inline void prcmu_ac_sleep_req(void) {}
+
+static inline void prcmu_system_reset(u16 reset_code) {}
+
+static inline void prcmu_modem_reset(void) {}
+
+static inline bool prcmu_is_ac_wake_requested(void)
+{
+        return false;
+}
+
+#ifndef CONFIG_UX500_SOC_DB5500
+static inline int prcmu_set_display_clocks(void)
+{
+        return 0;
+}
+
+static inline int prcmu_disable_dsipll(void)
+{
+        return 0;
+}
+
+static inline int prcmu_enable_dsipll(void)
+{
+        return 0;
+}
+#endif
+
+static inline int prcmu_enable_spi2(void)
+{
+        return 0;
+}
+
+static inline int prcmu_disable_spi2(void)
+{
+        return 0;
+}
+
+#endif /* !CONFIG_MFD_DB8500_PRCMU */
+
+#ifdef CONFIG_UX500_PRCMU_QOS_POWER
+int prcmu_qos_requirement(int pm_qos_class);
+int prcmu_qos_add_requirement(int pm_qos_class, char *name, s32 value);
+int prcmu_qos_update_requirement(int pm_qos_class, char *name, s32 new_value);
+void prcmu_qos_remove_requirement(int pm_qos_class, char *name);
+int prcmu_qos_add_notifier(int prcmu_qos_class,
+                           struct notifier_block *notifier);
+int prcmu_qos_remove_notifier(int prcmu_qos_class,
+                              struct notifier_block *notifier);
+#else
+static inline int prcmu_qos_requirement(int prcmu_qos_class)
+{
+        return 0;
+}
+
+static inline int prcmu_qos_add_requirement(int prcmu_qos_class,
+                                            char *name, s32 value)
+{
+        return 0;
+}
+
+static inline int prcmu_qos_update_requirement(int prcmu_qos_class,
+                                               char *name, s32 new_value)
+{
+        return 0;
+}
+
+static inline void prcmu_qos_remove_requirement(int prcmu_qos_class, char *name)
+{
+}
+
+static inline int prcmu_qos_add_notifier(int prcmu_qos_class,
+                                         struct notifier_block *notifier)
+{
+        return 0;
+}
+static inline int prcmu_qos_remove_notifier(int prcmu_qos_class,
+                                            struct notifier_block *notifier)
+{
+        return 0;
+}
+
+#endif
+
+#endif /* __MFD_DB8500_PRCMU_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6507dde38b16..8eb969ebf904 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -153,6 +153,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_MKWRITE      0x04    /* Fault was mkwrite of existing pte */
 #define FAULT_FLAG_ALLOW_RETRY  0x08    /* Retry fault if blocking */
 #define FAULT_FLAG_RETRY_NOWAIT 0x10    /* Don't drop mmap_sem and wait when retrying */
+#define FAULT_FLAG_KILLABLE     0x20    /* The fault task is in SIGKILL killable region */
 
 /*
  * This interface is used by x86 PAT code to identify a pfn mapping that is
@@ -604,10 +605,6 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define NODE_NOT_IN_PAGE_FLAGS
 #endif
 
-#ifndef PFN_SECTION_SHIFT
-#define PFN_SECTION_SHIFT 0
-#endif
-
 /*
  * Define the bit shifts to access each section.  For non-existent
  * sections we define the shift as 0; that plus a 0 mask ensures
@@ -681,6 +678,12 @@ static inline struct zone *page_zone(struct page *page)
 }
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+static inline void set_page_section(struct page *page, unsigned long section)
+{
+        page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
+        page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
+}
+
 static inline unsigned long page_to_section(struct page *page)
 {
         return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
@@ -699,18 +702,14 @@ static inline void set_page_node(struct page *page, unsigned long node)
         page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
 }
 
-static inline void set_page_section(struct page *page, unsigned long section)
-{
-        page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
-        page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
-}
-
 static inline void set_page_links(struct page *page, enum zone_type zone,
         unsigned long node, unsigned long pfn)
 {
         set_page_zone(page, zone);
         set_page_node(page, node);
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
         set_page_section(page, pfn_to_section_nr(pfn));
+#endif
 }
 
 /*
@@ -862,26 +861,18 @@ extern void pagefault_out_of_memory(void);
 #define offset_in_page(p)       ((unsigned long)(p) & ~PAGE_MASK)
 
 /*
- * Flags passed to show_mem() and __show_free_areas() to suppress output in
+ * Flags passed to show_mem() and show_free_areas() to suppress output in
  * various contexts.
  */
 #define SHOW_MEM_FILTER_NODES   (0x0001u)       /* filter disallowed nodes */
 
-extern void show_free_areas(void);
-extern void __show_free_areas(unsigned int flags);
+extern void show_free_areas(unsigned int flags);
+extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_lock(struct file *file, int lock, struct user_struct *user);
 struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
 int shmem_zero_setup(struct vm_area_struct *);
 
-#ifndef CONFIG_MMU
-extern unsigned long shmem_get_unmapped_area(struct file *file,
-                                             unsigned long addr,
-                                             unsigned long len,
-                                             unsigned long pgoff,
-                                             unsigned long flags);
-#endif
-
 extern int can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
 extern void user_shm_unlock(size_t, struct user_struct *);
@@ -894,8 +885,6 @@ struct zap_details {
         struct address_space *check_mapping;    /* Check page->mapping if set */
         pgoff_t first_index;                    /* Lowest page->index to unmap */
         pgoff_t last_index;                     /* Highest page->index to unmap */
-        spinlock_t *i_mmap_lock;                /* For unmap_mapping_range: */
-        unsigned long truncate_count;           /* Compare vm_truncate_count */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -905,7 +894,7 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
                 unsigned long size);
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
                 unsigned long size, struct zap_details *);
-unsigned long unmap_vmas(struct mmu_gather **tlb,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
                 struct vm_area_struct *start_vma, unsigned long start_addr,
                 unsigned long end_addr, unsigned long *nr_accounted,
                 struct zap_details *);
@@ -1056,65 +1045,35 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 /*
  * per-process(per-mm_struct) statistics.
  */
-#if defined(SPLIT_RSS_COUNTING)
-/*
- * The mm counters are not protected by its page_table_lock,
- * so must be incremented atomically.
- */
 static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
 {
         atomic_long_set(&mm->rss_stat.count[member], value);
 }
 
+#if defined(SPLIT_RSS_COUNTING)
 unsigned long get_mm_counter(struct mm_struct *mm, int member);
-
-static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
-{
-        atomic_long_add(value, &mm->rss_stat.count[member]);
-}
-
-static inline void inc_mm_counter(struct mm_struct *mm, int member)
-{
-        atomic_long_inc(&mm->rss_stat.count[member]);
-}
-
-static inline void dec_mm_counter(struct mm_struct *mm, int member)
-{
-        atomic_long_dec(&mm->rss_stat.count[member]);
-}
-
-#else  /* !USE_SPLIT_PTLOCKS */
-/*
- * The mm counters are protected by its page_table_lock,
- * so can be incremented directly.
- */
-static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
-{
-        mm->rss_stat.count[member] = value;
-}
-
+#else
 static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 {
-        return mm->rss_stat.count[member];
+        return atomic_long_read(&mm->rss_stat.count[member]);
 }
+#endif
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
 {
-        mm->rss_stat.count[member] += value;
+        atomic_long_add(value, &mm->rss_stat.count[member]);
 }
 
 static inline void inc_mm_counter(struct mm_struct *mm, int member)
 {
-        mm->rss_stat.count[member]++;
+        atomic_long_inc(&mm->rss_stat.count[member]);
 }
 
 static inline void dec_mm_counter(struct mm_struct *mm, int member)
 {
-        mm->rss_stat.count[member]--;
+        atomic_long_dec(&mm->rss_stat.count[member]);
 }
 
-#endif /* !USE_SPLIT_PTLOCKS */
-
 static inline unsigned long get_mm_rss(struct mm_struct *mm)
 {
         return get_mm_counter(mm, MM_FILEPAGES) +
@@ -1163,13 +1122,24 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
 #endif
 
 /*
+ * This struct is used to pass information from page reclaim to the shrinkers.
+ * We consolidate the values for easier extention later.
+ */
+struct shrink_control {
+        gfp_t gfp_mask;
+
+        /* How many slab objects shrinker() should scan and try to reclaim */
+        unsigned long nr_to_scan;
+};
+
+/*
  * A callback you can register to apply pressure to ageable caches.
  *
- * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should
- * look through the least-recently-used 'nr_to_scan' entries and
- * attempt to free them up.  It should return the number of objects
- * which remain in the cache.  If it returns -1, it means it cannot do
- * any scanning at this time (eg. there is a risk of deadlock).
+ * 'sc' is passed shrink_control which includes a count 'nr_to_scan'
+ * and a 'gfpmask'.  It should look through the least-recently-used
+ * 'nr_to_scan' entries and attempt to free them up.  It should return
+ * the number of objects which remain in the cache.  If it returns -1, it means
+ * it cannot do any scanning at this time (eg. there is a risk of deadlock).
  *
  * The 'gfpmask' refers to the allocation we are currently trying to
  * fulfil.
@@ -1178,7 +1148,7 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
  * querying the cache size, so a fastpath for that case is appropriate.
  */
 struct shrinker {
-        int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask);
+        int (*shrink)(struct shrinker *, struct shrink_control *sc);
         int seeks;      /* seeks to recreate an obj */
 
         /* These are for internal use */
@@ -1380,7 +1350,7 @@ extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long,
                                 unsigned long, enum memmap_context);
 extern void setup_per_zone_wmarks(void);
-extern void calculate_zone_inactive_ratio(struct zone *zone);
+extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
 extern void show_mem(unsigned int flags);
@@ -1388,6 +1358,8 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern int after_bootmem;
 
+extern void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
+
 extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
@@ -1517,15 +1489,17 @@ unsigned long ra_submit(struct file_ra_state *ra,
                         struct address_space *mapping,
                         struct file *filp);
 
-/* Do stack extension */
+/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
+
+/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */
+extern int expand_downwards(struct vm_area_struct *vma,
+                unsigned long address);
 #if VM_GROWSUP
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #else
   #define expand_upwards(vma, address) do { } while (0)
 #endif
-extern int expand_stack_downwards(struct vm_area_struct *vma,
-                                  unsigned long address);
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
@@ -1627,8 +1601,9 @@ int in_gate_area_no_mm(unsigned long addr);
 
 int drop_caches_sysctl_handler(struct ctl_table *, int,
                                         void __user *, size_t *, loff_t *);
-unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
-                        unsigned long lru_pages);
+unsigned long shrink_slab(struct shrink_control *shrink,
+                          unsigned long nr_pages_scanned,
+                          unsigned long lru_pages);
 
 #ifndef CONFIG_MMU
 #define randomize_va_space 0
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 02aa5619709b..071d459e866b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -175,7 +175,6 @@ struct vm_area_struct {
                                            units, *not* PAGE_CACHE_SIZE */
         struct file * vm_file;          /* File we map to (can be NULL). */
         void * vm_private_data;         /* was vm_pte (shared mem) */
-        unsigned long vm_truncate_count;/* truncate_count or restart_addr */
 
 #ifndef CONFIG_MMU
         struct vm_region *vm_region;    /* NOMMU mapping region */
@@ -205,19 +204,16 @@ enum {
 
 #if USE_SPLIT_PTLOCKS && defined(CONFIG_MMU)
 #define SPLIT_RSS_COUNTING
-struct mm_rss_stat {
-        atomic_long_t count[NR_MM_COUNTERS];
-};
 /* per-thread cached information, */
 struct task_rss_stat {
         int events;     /* for synchronization threshold */
         int count[NR_MM_COUNTERS];
 };
-#else  /* !USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTLOCKS */
+
 struct mm_rss_stat {
-        unsigned long count[NR_MM_COUNTERS];
+        atomic_long_t count[NR_MM_COUNTERS];
 };
-#endif /* !USE_SPLIT_PTLOCKS */
 
 struct mm_struct {
         struct vm_area_struct * mmap;           /* list of VMAs */
@@ -266,8 +262,6 @@ struct mm_struct {
 
         struct linux_binfmt *binfmt;
 
-        cpumask_t cpu_vm_mask;
-
         /* Architecture-specific MM context */
         mm_context_t context;
 
@@ -317,9 +311,14 @@ struct mm_struct {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
         pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
+
+        cpumask_var_t cpu_vm_mask_var;
 };
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
-#define mm_cpumask(mm) (&(mm)->cpu_vm_mask)
+static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
+{
+        return mm->cpu_vm_mask_var;
+}
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index cc2e7dfea9d7..1d1b1e13f79f 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -150,7 +150,7 @@ struct mmu_notifier_ops {
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock).
+ * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->mutex).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e56f835274c9..217bcf6bca77 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -928,9 +928,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #define pfn_to_nid(pfn)         (0)
 #endif
 
-#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT)
-#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT)
-
 #ifdef CONFIG_SPARSEMEM
 
 /*
@@ -956,6 +953,12 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #error Allocator MAX_ORDER exceeds SECTION_SIZE
 #endif
 
+#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT)
+#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT)
+
+#define SECTION_ALIGN_UP(pfn)   (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
+#define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK)
+
 struct page;
 struct page_cgroup;
 struct mem_section {
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index c75471db576e..a940fe435aca 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -132,6 +132,7 @@ static inline int mutex_is_locked(struct mutex *lock)
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
+extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
 extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
                                         unsigned int subclass);
 extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
@@ -140,6 +141,13 @@ extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
 #define mutex_lock(lock) mutex_lock_nested(lock, 0)
 #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
 #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+
+#define mutex_lock_nest_lock(lock, nest_lock)                           \
+do {                                                                    \
+        typecheck(struct lockdep_map *, &(nest_lock)->dep_map);         \
+        _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);             \
+} while (0)
+
 #else
 extern void mutex_lock(struct mutex *lock);
 extern int __must_check mutex_lock_interruptible(struct mutex *lock);
@@ -148,6 +156,7 @@ extern int __must_check mutex_lock_killable(struct mutex *lock);
 # define mutex_lock_nested(lock, subclass) mutex_lock(lock)
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
+# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
 #endif
 
 /*
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 5e3aa8311c5e..4952fb874ad3 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -40,6 +40,8 @@ enum oom_constraint {
         CONSTRAINT_MEMCG,
 };
 
+extern int test_set_oom_score_adj(int new_val);
+
 extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
                         const nodemask_t *nodemask, unsigned long totalpages);
 extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c11950652646..716875e53520 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -219,6 +219,12 @@ static inline struct page *page_cache_alloc_cold(struct address_space *x)
         return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
 }
 
+static inline struct page *page_cache_alloc_readahead(struct address_space *x)
+{
+        return __page_cache_alloc(mapping_gfp_mask(x) |
+                                  __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN);
+}
+
 typedef int filler_t(void *, struct page *);
 
 extern struct page * find_get_page(struct address_space *mapping,
@@ -357,6 +363,15 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
  */
 extern void wait_on_page_bit(struct page *page, int bit_nr);
 
+extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
+
+static inline int wait_on_page_locked_killable(struct page *page)
+{
+        if (PageLocked(page))
+                return wait_on_page_bit_killable(page, PG_locked);
+        return 0;
+}
+
 /* 
  * Wait for a page to be unlocked.
  *
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 46f6ba56fa91..5edc9014263a 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -75,7 +75,7 @@ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc)
         barrier();              /* Prevent reloads of fbc->count */
         if (ret >= 0)
                 return ret;
-        return 1;
+        return 0;
 }
 
 static inline int percpu_counter_initialized(struct percpu_counter *fbc)
@@ -133,6 +133,10 @@ static inline s64 percpu_counter_read(struct percpu_counter *fbc)
         return fbc->count;
 }
 
+/*
+ * percpu_counter is intended to track positive numbers. In the UP case the
+ * number should never be negative.
+ */
 static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc)
 {
         return fbc->count;
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 808227d40a64..959c14132f46 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -82,6 +82,7 @@ struct k_itimer {
                         unsigned long expires;
                 } mmtimer;
                 struct alarm alarmtimer;
+                struct rcu_head rcu;
         } it;
 };
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index ee048e77e1ae..0101d55d9651 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -1,6 +1,8 @@
 #ifndef __KERNEL_PRINTK__
 #define __KERNEL_PRINTK__
 
+#include <linux/init.h>
+
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
@@ -113,6 +115,7 @@ extern int dmesg_restrict;
 extern int kptr_restrict;
 
 void log_buf_kexec_setup(void);
+void __init setup_log_buf(int early);
 #else
 static inline __attribute__ ((format (printf, 1, 0)))
 int vprintk(const char *s, va_list args)
@@ -137,6 +140,10 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 static inline void log_buf_kexec_setup(void)
 {
 }
+
+static inline void setup_log_buf(int early)
+{
+}
 #endif
 
 extern void dump_stack(void) __cold;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index eaf4350c0f90..3686cd6c9aca 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -288,12 +288,4 @@ static inline struct net *PDE_NET(struct proc_dir_entry *pde)
         return pde->parent->data;
 }
 
-struct proc_maps_private {
-        struct pid *pid;
-        struct task_struct *task;
-#ifdef CONFIG_MMU
-        struct vm_area_struct *tail_vma;
-#endif
-};
-
 #endif /* _LINUX_PROC_FS_H */
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 943a85ab0020..e07e2742a865 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -25,6 +25,7 @@
 
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
+#include <linux/ip.h>
 #include <linux/filter.h>
 #ifdef __KERNEL__
 #include <linux/in.h>
@@ -58,6 +59,12 @@
 #define OFF_NEXT        6
 #define OFF_UDP_DST     2
 
+#define OFF_PTP_SOURCE_UUID     22 /* PTPv1 only */
+#define OFF_PTP_SEQUENCE_ID     30
+#define OFF_PTP_CONTROL         32 /* PTPv1 only */
+
+#define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2)
+
 #define IP6_HLEN        40
 #define UDP_HLEN        8
 
diff --git a/include/linux/ptp_clock.h b/include/linux/ptp_clock.h
new file mode 100644
index 000000000000..94e981f810a2
--- /dev/null
+++ b/include/linux/ptp_clock.h
@@ -0,0 +1,84 @@
+/*
+ * PTP 1588 clock support - user space interface
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _PTP_CLOCK_H_
+#define _PTP_CLOCK_H_
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/* PTP_xxx bits, for the flags field within the request structures. */
+#define PTP_ENABLE_FEATURE (1<<0)
+#define PTP_RISING_EDGE    (1<<1)
+#define PTP_FALLING_EDGE   (1<<2)
+
+/*
+ * struct ptp_clock_time - represents a time value
+ *
+ * The sign of the seconds field applies to the whole value. The
+ * nanoseconds field is always unsigned. The reserved field is
+ * included for sub-nanosecond resolution, should the demand for
+ * this ever appear.
+ *
+ */
+struct ptp_clock_time {
+        __s64 sec;  /* seconds */
+        __u32 nsec; /* nanoseconds */
+        __u32 reserved;
+};
+
+struct ptp_clock_caps {
+        int max_adj;   /* Maximum frequency adjustment in parts per billon. */
+        int n_alarm;   /* Number of programmable alarms. */
+        int n_ext_ts;  /* Number of external time stamp channels. */
+        int n_per_out; /* Number of programmable periodic signals. */
+        int pps;       /* Whether the clock supports a PPS callback. */
+        int rsv[15];   /* Reserved for future use. */
+};
+
+struct ptp_extts_request {
+        unsigned int index;  /* Which channel to configure. */
+        unsigned int flags;  /* Bit field for PTP_xxx flags. */
+        unsigned int rsv[2]; /* Reserved for future use. */
+};
+
+struct ptp_perout_request {
+        struct ptp_clock_time start;  /* Absolute start time. */
+        struct ptp_clock_time period; /* Desired period, zero means disable. */
+        unsigned int index;           /* Which channel to configure. */
+        unsigned int flags;           /* Reserved for future use. */
+        unsigned int rsv[4];          /* Reserved for future use. */
+};
+
+#define PTP_CLK_MAGIC '='
+
+#define PTP_CLOCK_GETCAPS  _IOR(PTP_CLK_MAGIC, 1, struct ptp_clock_caps)
+#define PTP_EXTTS_REQUEST  _IOW(PTP_CLK_MAGIC, 2, struct ptp_extts_request)
+#define PTP_PEROUT_REQUEST _IOW(PTP_CLK_MAGIC, 3, struct ptp_perout_request)
+#define PTP_ENABLE_PPS     _IOW(PTP_CLK_MAGIC, 4, int)
+
+struct ptp_extts_event {
+        struct ptp_clock_time t; /* Time event occured. */
+        unsigned int index;      /* Which channel produced the event. */
+        unsigned int flags;      /* Reserved for future use. */
+        unsigned int rsv[2];     /* Reserved for future use. */
+};
+
+#endif
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
new file mode 100644
index 000000000000..dd2e44fba63e
--- /dev/null
+++ b/include/linux/ptp_clock_kernel.h
@@ -0,0 +1,139 @@
+/*
+ * PTP 1588 clock support
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _PTP_CLOCK_KERNEL_H_
+#define _PTP_CLOCK_KERNEL_H_
+
+#include <linux/ptp_clock.h>
+
+
+struct ptp_clock_request {
+        enum {
+                PTP_CLK_REQ_EXTTS,
+                PTP_CLK_REQ_PEROUT,
+                PTP_CLK_REQ_PPS,
+        } type;
+        union {
+                struct ptp_extts_request extts;
+                struct ptp_perout_request perout;
+        };
+};
+
+/**
+ * struct ptp_clock_info - decribes a PTP hardware clock
+ *
+ * @owner:     The clock driver should set to THIS_MODULE.
+ * @name:      A short name to identify the clock.
+ * @max_adj:   The maximum possible frequency adjustment, in parts per billon.
+ * @n_alarm:   The number of programmable alarms.
+ * @n_ext_ts:  The number of external time stamp channels.
+ * @n_per_out: The number of programmable periodic signals.
+ * @pps:       Indicates whether the clock supports a PPS callback.
+ *
+ * clock operations
+ *
+ * @adjfreq:  Adjusts the frequency of the hardware clock.
+ *            parameter delta: Desired period change in parts per billion.
+ *
+ * @adjtime:  Shifts the time of the hardware clock.
+ *            parameter delta: Desired change in nanoseconds.
+ *
+ * @gettime:  Reads the current time from the hardware clock.
+ *            parameter ts: Holds the result.
+ *
+ * @settime:  Set the current time on the hardware clock.
+ *            parameter ts: Time value to set.
+ *
+ * @enable:   Request driver to enable or disable an ancillary feature.
+ *            parameter request: Desired resource to enable or disable.
+ *            parameter on: Caller passes one to enable or zero to disable.
+ *
+ * Drivers should embed their ptp_clock_info within a private
+ * structure, obtaining a reference to it using container_of().
+ *
+ * The callbacks must all return zero on success, non-zero otherwise.
+ */
+
+struct ptp_clock_info {
+        struct module *owner;
+        char name[16];
+        s32 max_adj;
+        int n_alarm;
+        int n_ext_ts;
+        int n_per_out;
+        int pps;
+        int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
+        int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
+        int (*gettime)(struct ptp_clock_info *ptp, struct timespec *ts);
+        int (*settime)(struct ptp_clock_info *ptp, const struct timespec *ts);
+        int (*enable)(struct ptp_clock_info *ptp,
+                      struct ptp_clock_request *request, int on);
+};
+
+struct ptp_clock;
+
+/**
+ * ptp_clock_register() - register a PTP hardware clock driver
+ *
+ * @info:  Structure describing the new clock.
+ */
+
+extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info);
+
+/**
+ * ptp_clock_unregister() - unregister a PTP hardware clock driver
+ *
+ * @ptp:  The clock to remove from service.
+ */
+
+extern int ptp_clock_unregister(struct ptp_clock *ptp);
+
+
+enum ptp_clock_events {
+        PTP_CLOCK_ALARM,
+        PTP_CLOCK_EXTTS,
+        PTP_CLOCK_PPS,
+};
+
+/**
+ * struct ptp_clock_event - decribes a PTP hardware clock event
+ *
+ * @type:  One of the ptp_clock_events enumeration values.
+ * @index: Identifies the source of the event.
+ * @timestamp: When the event occured.
+ */
+
+struct ptp_clock_event {
+        int type;
+        int index;
+        u64 timestamp;
+};
+
+/**
+ * ptp_clock_event() - notify the PTP layer about an event
+ *
+ * @ptp:    The clock obtained from ptp_clock_register().
+ * @event:  Message structure describing the event.
+ */
+
+extern void ptp_clock_event(struct ptp_clock *ptp,
+                            struct ptp_clock_event *event);
+
+#endif
diff --git a/include/linux/regulator/db8500-prcmu.h b/include/linux/regulator/db8500-prcmu.h
new file mode 100644
index 000000000000..612062313b68
--- /dev/null
+++ b/include/linux/regulator/db8500-prcmu.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * Author: Bengt Jonsson <bengt.g.jonsson@stericsson.com> for ST-Ericsson
+ *
+ * Interface to power domain regulators on DB8500
+ */
+
+#ifndef __REGULATOR_H__
+#define __REGULATOR_H__
+
+/* Number of DB8500 regulators and regulator enumeration */
+enum db8500_regulator_id {
+        DB8500_REGULATOR_VAPE,
+        DB8500_REGULATOR_VARM,
+        DB8500_REGULATOR_VMODEM,
+        DB8500_REGULATOR_VPLL,
+        DB8500_REGULATOR_VSMPS1,
+        DB8500_REGULATOR_VSMPS2,
+        DB8500_REGULATOR_VSMPS3,
+        DB8500_REGULATOR_VRF1,
+        DB8500_REGULATOR_SWITCH_SVAMMDSP,
+        DB8500_REGULATOR_SWITCH_SVAMMDSPRET,
+        DB8500_REGULATOR_SWITCH_SVAPIPE,
+        DB8500_REGULATOR_SWITCH_SIAMMDSP,
+        DB8500_REGULATOR_SWITCH_SIAMMDSPRET,
+        DB8500_REGULATOR_SWITCH_SIAPIPE,
+        DB8500_REGULATOR_SWITCH_SGA,
+        DB8500_REGULATOR_SWITCH_B2R2_MCDE,
+        DB8500_REGULATOR_SWITCH_ESRAM12,
+        DB8500_REGULATOR_SWITCH_ESRAM12RET,
+        DB8500_REGULATOR_SWITCH_ESRAM34,
+        DB8500_REGULATOR_SWITCH_ESRAM34RET,
+        DB8500_NUM_REGULATORS
+};
+
+/*
+ * Exported interface for CPUIdle only. This function is called with all
+ * interrupts turned off.
+ */
+int power_state_active_is_enabled(void);
+
+#endif
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 830e65dc01ee..2148b122779b 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/memcontrol.h>
 
 /*
@@ -26,7 +26,7 @@
  */
 struct anon_vma {
         struct anon_vma *root;  /* Root of this anon_vma tree */
-        spinlock_t lock;        /* Serialize access to vma list */
+        struct mutex mutex;     /* Serialize access to vma list */
         /*
          * The refcount is taken on an anon_vma when there is no
          * guarantee that the vma of page tables will exist for
@@ -64,7 +64,7 @@ struct anon_vma_chain {
         struct vm_area_struct *vma;
         struct anon_vma *anon_vma;
         struct list_head same_vma;   /* locked by mmap_sem & page_table_lock */
-        struct list_head same_anon_vma; /* locked by anon_vma->lock */
+        struct list_head same_anon_vma; /* locked by anon_vma->mutex */
 };
 
 #ifdef CONFIG_MMU
@@ -93,24 +93,24 @@ static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
 {
         struct anon_vma *anon_vma = vma->anon_vma;
         if (anon_vma)
-                spin_lock(&anon_vma->root->lock);
+                mutex_lock(&anon_vma->root->mutex);
 }
 
 static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 {
         struct anon_vma *anon_vma = vma->anon_vma;
         if (anon_vma)
-                spin_unlock(&anon_vma->root->lock);
+                mutex_unlock(&anon_vma->root->mutex);
 }
 
 static inline void anon_vma_lock(struct anon_vma *anon_vma)
 {
-        spin_lock(&anon_vma->root->lock);
+        mutex_lock(&anon_vma->root->mutex);
 }
 
 static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 {
-        spin_unlock(&anon_vma->root->lock);
+        mutex_unlock(&anon_vma->root->mutex);
 }
 
 /*
@@ -218,20 +218,7 @@ int try_to_munlock(struct page *);
 /*
  * Called by memory-failure.c to kill processes.
  */
-struct anon_vma *__page_lock_anon_vma(struct page *page);
-
-static inline struct anon_vma *page_lock_anon_vma(struct page *page)
-{
-        struct anon_vma *anon_vma;
-
-        __cond_lock(RCU, anon_vma = __page_lock_anon_vma(page));
-
-        /* (void) is needed to make gcc happy */
-        (void) __cond_lock(&anon_vma->root->lock, anon_vma);
-
-        return anon_vma;
-}
-
+struct anon_vma *page_lock_anon_vma(struct page *page);
 void page_unlock_anon_vma(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index aaf71e08222c..f18300eddfcb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1753,7 +1753,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_FROZEN       0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS      0x00020000      /* inside a filesystem transaction */
 #define PF_KSWAPD       0x00040000      /* I am kswapd */
-#define PF_OOM_ORIGIN   0x00080000      /* Allocating much memory to others */
 #define PF_LESS_THROTTLE 0x00100000     /* Throttle me less: I clean memory */
 #define PF_KTHREAD      0x00200000      /* I am a kernel thread */
 #define PF_RANDOMIZE    0x00400000      /* randomize virtual address space */
@@ -2177,6 +2176,7 @@ static inline void mmdrop(struct mm_struct * mm)
         if (unlikely(atomic_dec_and_test(&mm->mm_count)))
                 __mmdrop(mm);
 }
+extern int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm);
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 399be5ad2f99..2b7fec840517 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -9,6 +9,8 @@
 
 #define SHMEM_NR_DIRECT 16
 
+#define SHMEM_SYMLINK_INLINE_LEN (SHMEM_NR_DIRECT * sizeof(swp_entry_t))
+
 struct shmem_inode_info {
         spinlock_t              lock;
         unsigned long           flags;
@@ -17,8 +19,12 @@ struct shmem_inode_info {
         unsigned long           next_index;     /* highest alloced index + 1 */
         struct shared_policy    policy;         /* NUMA memory alloc policy */
         struct page             *i_indirect;    /* top indirect blocks page */
-        swp_entry_t             i_direct[SHMEM_NR_DIRECT]; /* first blocks */
+        union {
+                swp_entry_t     i_direct[SHMEM_NR_DIRECT]; /* first blocks */
+                char            inline_symlink[SHMEM_SYMLINK_INLINE_LEN];
+        };
         struct list_head        swaplist;       /* chain of maybes on swap */
+        struct list_head        xattr_list;     /* list of shmem_xattr */
         struct inode            vfs_inode;
 };
 
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 2b3831b58aa4..51359837511a 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -261,6 +261,7 @@ extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
 void refresh_cpu_vm_stats(int);
+void refresh_zone_stat_thresholds(void);
 
 int calculate_pressure_threshold(struct zone *zone);
 int calculate_normal_threshold(struct zone *zone);
@@ -313,6 +314,10 @@ static inline void __dec_zone_page_state(struct page *page,
 #define set_pgdat_percpu_threshold(pgdat, callback) { }
 
 static inline void refresh_cpu_vm_stats(int cpu) { }
-#endif
+static inline void refresh_zone_stat_thresholds(void) { }
+
+#endif          /* CONFIG_SMP */
+
+extern const char * const vmstat_text[];
 
 #endif /* _LINUX_VMSTAT_H */
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 6050783005bd..aed54c50aa66 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -13,10 +13,6 @@
 #define XATTR_CREATE    0x1     /* set value, fail if attr already exists */
 #define XATTR_REPLACE   0x2     /* set value, fail if attr does not exist */
 
-#ifdef  __KERNEL__
-
-#include <linux/types.h>
-
 /* Namespaces */
 #define XATTR_OS2_PREFIX "os2."
 #define XATTR_OS2_PREFIX_LEN (sizeof (XATTR_OS2_PREFIX) - 1)
@@ -53,6 +49,10 @@
 #define XATTR_CAPS_SUFFIX "capability"
 #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX
 
+#ifdef  __KERNEL__
+
+#include <linux/types.h>
+
 struct inode;
 struct dentry;
 
diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index d2df55b0c213..008711e8e78f 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -241,10 +241,10 @@ enum p9_open_mode_t {
 
 /**
  * enum p9_perm_t - 9P permissions
- * @P9_DMDIR: mode bite for directories
+ * @P9_DMDIR: mode bit for directories
  * @P9_DMAPPEND: mode bit for is append-only
  * @P9_DMEXCL: mode bit for excluse use (only one open handle allowed)
- * @P9_DMMOUNT: mode bite for mount points
+ * @P9_DMMOUNT: mode bit for mount points
  * @P9_DMAUTH: mode bit for authentication file
  * @P9_DMTMP: mode bit for non-backed-up files
  * @P9_DMSYMLINK: mode bit for symbolic links (9P2000.u)
@@ -362,7 +362,7 @@ struct p9_qid {
 };
 
 /**
- * struct p9_stat - file system metadata information
+ * struct p9_wstat - file system metadata information
  * @size: length prefix for this stat structure instance
  * @type: the type of the server (equivalent to a major number)
  * @dev: the sub-type of the server (equivalent to a minor number)
@@ -687,10 +687,10 @@ struct p9_rwstat {
  * @size: prefixed length of the structure
  * @id: protocol operating identifier of type &p9_msg_t
  * @tag: transaction id of the request
- * @offset: used by marshalling routines to track currentposition in buffer
+ * @offset: used by marshalling routines to track current position in buffer
  * @capacity: used by marshalling routines to track total malloc'd capacity
  * @pubuf: Payload user buffer given by the caller
- * @pubuf: Payload kernel buffer given by the caller
+ * @pkbuf: Payload kernel buffer given by the caller
  * @pbuf_size: pubuf/pkbuf(only one will be !NULL) size to be read/write.
  * @private: For transport layer's use.
  * @sdata: payload
@@ -714,7 +714,7 @@ struct p9_fcall {
         size_t pbuf_size;
         void *private;
 
-        uint8_t *sdata;
+        u8 *sdata;
 };
 
 struct p9_idpool;
@@ -728,7 +728,6 @@ void p9_idpool_put(int id, struct p9_idpool *p);
 int p9_idpool_check(int id, struct p9_idpool *p);
 
 int p9_error_init(void);
-int p9_errstr2errno(char *, int);
 int p9_trans_fd_init(void);
 void p9_trans_fd_exit(void);
 #endif /* NET_9P_H */
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 051a99f79769..d26d5e98a173 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -60,7 +60,7 @@ enum p9_trans_status {
 };
 
 /**
- * enum p9_req_status_t - virtio request status
+ * enum p9_req_status_t - status of a request
  * @REQ_STATUS_IDLE: request slot unused
  * @REQ_STATUS_ALLOC: request has been allocated but not sent
  * @REQ_STATUS_UNSENT: request waiting to be sent
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 8f08c736c4c3..d8549fb9c742 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -41,6 +41,7 @@
  * @pref: Preferences of this transport
  * @def: set if this transport should be considered the default
  * @create: member function to create a new connection on this transport
+ * @close: member function to discard a connection on this transport
  * @request: member function to issue a request to the transport
  * @cancel: member function to cancel a request (if it hasn't been sent)
  *
@@ -48,7 +49,7 @@
  * transport module with the 9P core network module and used by the client
  * to instantiate a new connection on a transport.
  *
- * BUGS: the transport module list isn't protected.
+ * The transport module list is protected by v9fs_trans_lock.
  */
 
 struct p9_trans_module {
diff --git a/arch/arm/plat-omap/include/plat/panel-generic-dpi.h b/include/video/omap-panel-generic-dpi.h
index 790619734bcd..127e3f20328e 100644
--- a/arch/arm/plat-omap/include/plat/panel-generic-dpi.h
+++ b/include/video/omap-panel-generic-dpi.h
@@ -17,10 +17,10 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef __ARCH_ARM_PLAT_OMAP_PANEL_GENERIC_DPI_H
-#define __ARCH_ARM_PLAT_OMAP_PANEL_GENERIC_DPI_H
+#ifndef __OMAP_PANEL_GENERIC_DPI_H
+#define __OMAP_PANEL_GENERIC_DPI_H
 
-#include "display.h"
+struct omap_dss_device;
 
 /**
  * struct panel_generic_dpi_data - panel driver configuration data
@@ -34,4 +34,4 @@ struct panel_generic_dpi_data {
         void (*platform_disable)(struct omap_dss_device *dssdev);
 };
 
-#endif /* __ARCH_ARM_PLAT_OMAP_PANEL_GENERIC_DPI_H */
+#endif /* __OMAP_PANEL_GENERIC_DPI_H */
diff --git a/arch/arm/plat-omap/include/plat/nokia-dsi-panel.h b/include/video/omap-panel-nokia-dsi.h
index 01ab6572ccbb..921ae9327228 100644
--- a/arch/arm/plat-omap/include/plat/nokia-dsi-panel.h
+++ b/include/video/omap-panel-nokia-dsi.h
@@ -1,14 +1,15 @@
-#ifndef __ARCH_ARM_PLAT_OMAP_NOKIA_DSI_PANEL_H
-#define __ARCH_ARM_PLAT_OMAP_NOKIA_DSI_PANEL_H
+#ifndef __OMAP_NOKIA_DSI_PANEL_H
+#define __OMAP_NOKIA_DSI_PANEL_H
 
-#include "display.h"
+struct omap_dss_device;
 
 /**
  * struct nokia_dsi_panel_data - Nokia DSI panel driver configuration
  * @name: panel name
  * @use_ext_te: use external TE
  * @ext_te_gpio: external TE GPIO
- * @use_esd_check: perform ESD checks
+ * @esd_interval: interval of ESD checks, 0 = disabled (ms)
+ * @ulps_timeout: time to wait before entering ULPS, 0 = disabled (ms)
  * @max_backlight_level: maximum backlight level
  * @set_backlight: pointer to backlight set function
  * @get_backlight: pointer to backlight get function
@@ -21,11 +22,12 @@ struct nokia_dsi_panel_data {
         bool use_ext_te;
         int ext_te_gpio;
 
-        bool use_esd_check;
+        unsigned esd_interval;
+        unsigned ulps_timeout;
 
         int max_backlight_level;
         int (*set_backlight)(struct omap_dss_device *dssdev, int level);
         int (*get_backlight)(struct omap_dss_device *dssdev);
 };
 
-#endif /* __ARCH_ARM_PLAT_OMAP_NOKIA_DSI_PANEL_H */
+#endif /* __OMAP_NOKIA_DSI_PANEL_H */
diff --git a/arch/arm/plat-omap/include/plat/display.h b/include/video/omapdss.h
index 5e04ddc18fa8..892b97f8e157 100644
--- a/arch/arm/plat-omap/include/plat/display.h
+++ b/include/video/omapdss.h
@@ -1,6 +1,4 @@
 /*
- * linux/include/asm-arm/arch-omap/display.h
- *
  * Copyright (C) 2008 Nokia Corporation
  * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
  *
@@ -17,8 +15,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef __ASM_ARCH_OMAP_DISPLAY_H
-#define __ASM_ARCH_OMAP_DISPLAY_H
+#ifndef __OMAP_OMAPDSS_H
+#define __OMAP_OMAPDSS_H
 
 #include <linux/list.h>
 #include <linux/kobject.h>
@@ -88,6 +86,11 @@ enum omap_color_mode {
         OMAP_DSS_COLOR_ARGB32   = 1 << 11, /* ARGB32 */
         OMAP_DSS_COLOR_RGBA32   = 1 << 12, /* RGBA32 */
         OMAP_DSS_COLOR_RGBX32   = 1 << 13, /* RGBx32 */
+        OMAP_DSS_COLOR_NV12             = 1 << 14, /* NV12 format: YUV 4:2:0 */
+        OMAP_DSS_COLOR_RGBA16           = 1 << 15, /* RGBA16 - 4444 */
+        OMAP_DSS_COLOR_RGBX16           = 1 << 16, /* RGBx16 - 4444 */
+        OMAP_DSS_COLOR_ARGB16_1555      = 1 << 17, /* ARGB16 - 1555 */
+        OMAP_DSS_COLOR_XRGB16_1555      = 1 << 18, /* xRGB16 - 1555 */
 };
 
 enum omap_lcd_display_type {
@@ -174,6 +177,17 @@ enum omap_overlay_manager_caps {
         OMAP_DSS_OVL_MGR_CAP_DISPC = 1 << 0,
 };
 
+enum omap_dss_clk_source {
+        OMAP_DSS_CLK_SRC_FCK = 0,               /* OMAP2/3: DSS1_ALWON_FCLK
+                                                 * OMAP4: DSS_FCLK */
+        OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC,   /* OMAP3: DSI1_PLL_FCLK
+                                                 * OMAP4: PLL1_CLK1 */
+        OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI,     /* OMAP3: DSI2_PLL_FCLK
+                                                 * OMAP4: PLL1_CLK2 */
+        OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC,  /* OMAP4: PLL2_CLK1 */
+        OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI,    /* OMAP4: PLL2_CLK2 */
+};
+
 /* RFBI */
 
 struct rfbi_timings {
@@ -205,20 +219,30 @@ int omap_rfbi_enable_te(bool enable, unsigned line);
 int omap_rfbi_setup_te(enum omap_rfbi_te_mode mode,
                              unsigned hs_pulse_time, unsigned vs_pulse_time,
                              int hs_pol_inv, int vs_pol_inv, int extif_div);
+void rfbi_bus_lock(void);
+void rfbi_bus_unlock(void);
 
 /* DSI */
-void dsi_bus_lock(void);
-void dsi_bus_unlock(void);
-int dsi_vc_dcs_write(int channel, u8 *data, int len);
-int dsi_vc_dcs_write_0(int channel, u8 dcs_cmd);
-int dsi_vc_dcs_write_1(int channel, u8 dcs_cmd, u8 param);
-int dsi_vc_dcs_write_nosync(int channel, u8 *data, int len);
-int dsi_vc_dcs_read(int channel, u8 dcs_cmd, u8 *buf, int buflen);
-int dsi_vc_dcs_read_1(int channel, u8 dcs_cmd, u8 *data);
-int dsi_vc_dcs_read_2(int channel, u8 dcs_cmd, u8 *data1, u8 *data2);
-int dsi_vc_set_max_rx_packet_size(int channel, u16 len);
-int dsi_vc_send_null(int channel);
-int dsi_vc_send_bta_sync(int channel);
+void dsi_bus_lock(struct omap_dss_device *dssdev);
+void dsi_bus_unlock(struct omap_dss_device *dssdev);
+int dsi_vc_dcs_write(struct omap_dss_device *dssdev, int channel, u8 *data,
+                int len);
+int dsi_vc_dcs_write_0(struct omap_dss_device *dssdev, int channel,
+                u8 dcs_cmd);
+int dsi_vc_dcs_write_1(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 param);
+int dsi_vc_dcs_write_nosync(struct omap_dss_device *dssdev, int channel,
+                u8 *data, int len);
+int dsi_vc_dcs_read(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 *buf, int buflen);
+int dsi_vc_dcs_read_1(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 *data);
+int dsi_vc_dcs_read_2(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+                u8 *data1, u8 *data2);
+int dsi_vc_set_max_rx_packet_size(struct omap_dss_device *dssdev, int channel,
+                u16 len);
+int dsi_vc_send_null(struct omap_dss_device *dssdev, int channel);
+int dsi_vc_send_bta_sync(struct omap_dss_device *dssdev, int channel);
 
 /* Board specific data */
 struct omap_dss_board_info {
@@ -226,6 +250,7 @@ struct omap_dss_board_info {
         int num_devices;
         struct omap_dss_device **devices;
         struct omap_dss_device *default_device;
+        void (*dsi_mux_pads)(bool enable);
 };
 
 #if defined(CONFIG_OMAP2_DSS_MODULE) || defined(CONFIG_OMAP2_DSS)
@@ -280,6 +305,7 @@ struct omap_overlay_info {
 
         u32 paddr;
         void __iomem *vaddr;
+        u32 p_uv_addr;  /* for NV12 format */
         u16 screen_width;
         u16 width;
         u16 height;
@@ -400,18 +426,12 @@ struct omap_dss_device {
                         u8 data1_pol;
                         u8 data2_lane;
                         u8 data2_pol;
+                        u8 data3_lane;
+                        u8 data3_pol;
+                        u8 data4_lane;
+                        u8 data4_pol;
 
-                        struct {
-                                u16 regn;
-                                u16 regm;
-                                u16 regm_dispc;
-                                u16 regm_dsi;
-
-                                u16 lp_clk_div;
-
-                                u16 lck_div;
-                                u16 pck_div;
-                        } div;
+                        int module;
 
                         bool ext_te;
                         u8 ext_te_gpio;
@@ -424,6 +444,33 @@ struct omap_dss_device {
         } phy;
 
         struct {
+                struct {
+                        struct {
+                                u16 lck_div;
+                                u16 pck_div;
+                                enum omap_dss_clk_source lcd_clk_src;
+                        } channel;
+
+                        enum omap_dss_clk_source dispc_fclk_src;
+                } dispc;
+
+                struct {
+                        u16 regn;
+                        u16 regm;
+                        u16 regm_dispc;
+                        u16 regm_dsi;
+
+                        u16 lp_clk_div;
+                        enum omap_dss_clk_source dsi_fclk_src;
+                } dsi;
+
+                struct {
+                        u16 regn;
+                        u16 regm2;
+                } hdmi;
+        } clocks;
+
+        struct {
                 struct omap_video_timings timings;
 
                 int acbi;       /* ac-bias pin transitions per interrupt */
@@ -503,6 +550,8 @@ struct omap_dss_driver {
 
         void (*get_resolution)(struct omap_dss_device *dssdev,
                         u16 *xres, u16 *yres);
+        void (*get_dimensions)(struct omap_dss_device *dssdev,
+                        u32 *width, u32 *height);
         int (*get_recommended_bpp)(struct omap_dss_device *dssdev);
 
         int (*check_timings)(struct omap_dss_device *dssdev,
@@ -519,9 +568,6 @@ struct omap_dss_driver {
 int omap_dss_register_driver(struct omap_dss_driver *);
 void omap_dss_unregister_driver(struct omap_dss_driver *);
 
-int omap_dss_register_device(struct omap_dss_device *);
-void omap_dss_unregister_device(struct omap_dss_device *);
-
 void omap_dss_get_device(struct omap_dss_device *dssdev);
 void omap_dss_put_device(struct omap_dss_device *dssdev);
 #define for_each_dss_dev(d) while ((d = omap_dss_get_next_device(d)) != NULL)
@@ -553,7 +599,8 @@ int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,
 #define to_dss_driver(x) container_of((x), struct omap_dss_driver, driver)
 #define to_dss_device(x) container_of((x), struct omap_dss_device, dev)
 
-void omapdss_dsi_vc_enable_hs(int channel, bool enable);
+void omapdss_dsi_vc_enable_hs(struct omap_dss_device *dssdev, int channel,
+                bool enable);
 int omapdss_dsi_enable_te(struct omap_dss_device *dssdev, bool enable);
 
 int omap_dsi_prepare_update(struct omap_dss_device *dssdev,
@@ -568,7 +615,8 @@ int omap_dsi_set_vc_id(struct omap_dss_device *dssdev, int channel, int vc_id);
 void omap_dsi_release_vc(struct omap_dss_device *dssdev, int channel);
 
 int omapdss_dsi_display_enable(struct omap_dss_device *dssdev);
-void omapdss_dsi_display_disable(struct omap_dss_device *dssdev);
+void omapdss_dsi_display_disable(struct omap_dss_device *dssdev,
+                bool disconnect_lanes, bool enter_ulps);
 
 int omapdss_dpi_display_enable(struct omap_dss_device *dssdev);
 void omapdss_dpi_display_disable(struct omap_dss_device *dssdev);
@@ -587,5 +635,7 @@ int omap_rfbi_prepare_update(struct omap_dss_device *dssdev,
 int omap_rfbi_update(struct omap_dss_device *dssdev,
                 u16 x, u16 y, u16 w, u16 h,
                 void (*callback)(void *), void *data);
+int omap_rfbi_configure(struct omap_dss_device *dssdev, int pixel_size,
+                int data_lines);
 
 #endif
diff --git a/include/video/sh_mobile_lcdc.h b/include/video/sh_mobile_lcdc.h
index 2c8d369190b3..d964e68fc61d 100644
--- a/include/video/sh_mobile_lcdc.h
+++ b/include/video/sh_mobile_lcdc.h
@@ -2,6 +2,7 @@
 #define __ASM_SH_MOBILE_LCDC_H__
 
 #include <linux/fb.h>
+#include <video/sh_mobile_meram.h>
 
 enum {
         RGB8,   /* 24bpp, 8:8:8 */
@@ -87,11 +88,13 @@ struct sh_mobile_lcdc_chan_cfg {
         struct sh_mobile_lcdc_bl_info bl_info;
         struct sh_mobile_lcdc_sys_bus_cfg sys_bus_cfg; /* only for SYSn I/F */
         int nonstd;
+        struct sh_mobile_meram_cfg *meram_cfg;
 };
 
 struct sh_mobile_lcdc_info {
         int clock_source;
         struct sh_mobile_lcdc_chan_cfg ch[2];
+        struct sh_mobile_meram_info *meram_dev;
 };
 
 #endif /* __ASM_SH_MOBILE_LCDC_H__ */
diff --git a/include/video/sh_mobile_meram.h b/include/video/sh_mobile_meram.h
new file mode 100644
index 000000000000..af602d602b28
--- /dev/null
+++ b/include/video/sh_mobile_meram.h
@@ -0,0 +1,68 @@
+#ifndef __VIDEO_SH_MOBILE_MERAM_H__
+#define __VIDEO_SH_MOBILE_MERAM_H__
+
+/* For sh_mobile_meram_info.addr_mode */
+enum {
+        SH_MOBILE_MERAM_MODE0 = 0,
+        SH_MOBILE_MERAM_MODE1
+};
+
+enum {
+        SH_MOBILE_MERAM_PF_NV = 0,
+        SH_MOBILE_MERAM_PF_RGB,
+        SH_MOBILE_MERAM_PF_NV24
+};
+
+
+struct sh_mobile_meram_priv;
+struct sh_mobile_meram_ops;
+
+struct sh_mobile_meram_info {
+        int                             addr_mode;
+        struct sh_mobile_meram_ops      *ops;
+        struct sh_mobile_meram_priv     *priv;
+        struct platform_device          *pdev;
+};
+
+/* icb config */
+struct sh_mobile_meram_icb {
+        int marker_icb;         /* ICB # for Marker ICB */
+        int cache_icb;          /* ICB # for Cache ICB */
+        int meram_offset;       /* MERAM Buffer Offset to use */
+        int meram_size;         /* MERAM Buffer Size to use */
+
+        int cache_unit;         /* bytes to cache per ICB */
+};
+
+struct sh_mobile_meram_cfg {
+        struct sh_mobile_meram_icb      icb[2];
+        int                             pixelformat;
+        int                             current_reg;
+};
+
+struct module;
+struct sh_mobile_meram_ops {
+        struct module   *module;
+        /* register usage of meram */
+        int (*meram_register)(struct sh_mobile_meram_info *meram_dev,
+                              struct sh_mobile_meram_cfg *cfg,
+                              int xres, int yres, int pixelformat,
+                              unsigned long base_addr_y,
+                              unsigned long base_addr_c,
+                              unsigned long *icb_addr_y,
+                              unsigned long *icb_addr_c, int *pitch);
+
+        /* unregister usage of meram */
+        int (*meram_unregister)(struct sh_mobile_meram_info *meram_dev,
+                                struct sh_mobile_meram_cfg *cfg);
+
+        /* update meram settings */
+        int (*meram_update)(struct sh_mobile_meram_info *meram_dev,
+                            struct sh_mobile_meram_cfg *cfg,
+                            unsigned long base_addr_y,
+                            unsigned long base_addr_c,
+                            unsigned long *icb_addr_y,
+                            unsigned long *icb_addr_c);
+};
+
+#endif /* __VIDEO_SH_MOBILE_MERAM_H__  */
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index 61e523af3c46..3d5d6db864fe 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -45,6 +45,19 @@ typedef uint64_t blkif_sector_t;
 #define BLKIF_OP_WRITE_BARRIER     2
 
 /*
+ * Recognised if "feature-flush-cache" is present in backend xenbus
+ * info.  A flush will ask the underlying storage hardware to flush its
+ * non-volatile caches as appropriate.  The "feature-flush-cache" node
+ * contains a boolean indicating whether flush requests are likely to
+ * succeed or fail. Either way, a flush request may fail at any time
+ * with BLKIF_RSP_EOPNOTSUPP if it is unsupported by the underlying
+ * block-device hardware. The boolean simply indicates whether or not it
+ * is worthwhile for the frontend to attempt flushes.  If a backend does
+ * not recognise BLKIF_OP_WRITE_FLUSH_CACHE, it should *not* create the
+ * "feature-flush-cache" node!
+ */
+#define BLKIF_OP_FLUSH_DISKCACHE   3
+/*
  * Maximum scatter/gather segments per request.
  * This is carefully chosen so that sizeof(struct blkif_ring) <= PAGE_SIZE.
  * NB. This could be 12 if the ring indexes weren't stored in the same page.
diff --git a/init/calibrate.c b/init/calibrate.c
index 76ac9194cbc4..cfd7000c9d71 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -38,6 +38,9 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
         unsigned long timer_rate_min, timer_rate_max;
         unsigned long good_timer_sum = 0;
         unsigned long good_timer_count = 0;
+        unsigned long measured_times[MAX_DIRECT_CALIBRATION_RETRIES];
+        int max = -1; /* index of measured_times with max/min values or not set */
+        int min = -1;
         int i;
 
         if (read_current_timer(&pre_start) < 0 )
@@ -90,18 +93,78 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
                  * If the upper limit and lower limit of the timer_rate is
                  * >= 12.5% apart, redo calibration.
                  */
-                if (pre_start != 0 && pre_end != 0 &&
+                printk(KERN_DEBUG "calibrate_delay_direct() timer_rate_max=%lu "
+                            "timer_rate_min=%lu pre_start=%lu pre_end=%lu\n",
+                          timer_rate_max, timer_rate_min, pre_start, pre_end);
+                if (start >= post_end)
+                        printk(KERN_NOTICE "calibrate_delay_direct() ignoring "
+                                        "timer_rate as we had a TSC wrap around"
+                                        " start=%lu >=post_end=%lu\n",
+                                start, post_end);
+                if (start < post_end && pre_start != 0 && pre_end != 0 &&
                     (timer_rate_max - timer_rate_min) < (timer_rate_max >> 3)) {
                         good_timer_count++;
                         good_timer_sum += timer_rate_max;
-                }
+                        measured_times[i] = timer_rate_max;
+                        if (max < 0 || timer_rate_max > measured_times[max])
+                                max = i;
+                        if (min < 0 || timer_rate_max < measured_times[min])
+                                min = i;
+                } else
+                        measured_times[i] = 0;
+
         }
 
-        if (good_timer_count)
-                return (good_timer_sum/good_timer_count);
+        /*
+         * Find the maximum & minimum - if they differ too much throw out the
+         * one with the largest difference from the mean and try again...
+         */
+        while (good_timer_count > 1) {
+                unsigned long estimate;
+                unsigned long maxdiff;
+
+                /* compute the estimate */
+                estimate = (good_timer_sum/good_timer_count);
+                maxdiff = estimate >> 3;
+
+                /* if range is within 12% let's take it */
+                if ((measured_times[max] - measured_times[min]) < maxdiff)
+                        return estimate;
+
+                /* ok - drop the worse value and try again... */
+                good_timer_sum = 0;
+                good_timer_count = 0;
+                if ((measured_times[max] - estimate) <
+                                (estimate - measured_times[min])) {
+                        printk(KERN_NOTICE "calibrate_delay_direct() dropping "
+                                        "min bogoMips estimate %d = %lu\n",
+                                min, measured_times[min]);
+                        measured_times[min] = 0;
+                        min = max;
+                } else {
+                        printk(KERN_NOTICE "calibrate_delay_direct() dropping "
+                                        "max bogoMips estimate %d = %lu\n",
+                                max, measured_times[max]);
+                        measured_times[max] = 0;
+                        max = min;
+                }
+
+                for (i = 0; i < MAX_DIRECT_CALIBRATION_RETRIES; i++) {
+                        if (measured_times[i] == 0)
+                                continue;
+                        good_timer_count++;
+                        good_timer_sum += measured_times[i];
+                        if (measured_times[i] < measured_times[min])
+                                min = i;
+                        if (measured_times[i] > measured_times[max])
+                                max = i;
+                }
+
+        }
 
-        printk(KERN_WARNING "calibrate_delay_direct() failed to get a good "
-               "estimate for loops_per_jiffy.\nProbably due to long platform interrupts. Consider using \"lpj=\" boot option.\n");
+        printk(KERN_NOTICE "calibrate_delay_direct() failed to get a good "
+               "estimate for loops_per_jiffy.\nProbably due to long platform "
+                "interrupts. Consider using \"lpj=\" boot option.\n");
         return 0;
 }
 #else
diff --git a/init/main.c b/init/main.c
index 48df882d51d2..d2f1e086bf33 100644
--- a/init/main.c
+++ b/init/main.c
@@ -504,11 +504,14 @@ asmlinkage void __init start_kernel(void)
          * These use large bootmem allocations and must precede
          * kmem_cache_init()
          */
+        setup_log_buf(0);
         pidhash_init();
         vfs_caches_init_early();
         sort_main_extable();
         trap_init();
         mm_init();
+        BUG_ON(mm_init_cpumask(&init_mm, 0));
+
         /*
          * Set up the scheduler prior starting any interrupts (such as the
          * timer interrupt). Full topology setup happens at smp_init()
diff --git a/kernel/compat.c b/kernel/compat.c
index 9214dcd087b7..fc9eb093acd5 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -293,6 +293,8 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
         return compat_jiffies_to_clock_t(jiffies);
 }
 
+#ifdef __ARCH_WANT_SYS_SIGPENDING
+
 /*
  * Assumption: old_sigset_t and compat_old_sigset_t are both
  * types that can be passed to put_user()/get_user().
@@ -312,6 +314,10 @@ asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set)
         return ret;
 }
 
+#endif
+
+#ifdef __ARCH_WANT_SYS_SIGPROCMASK
+
 asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set,
                 compat_old_sigset_t __user *oset)
 {
@@ -333,6 +339,8 @@ asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set,
         return ret;
 }
 
+#endif
+
 asmlinkage long compat_sys_setrlimit(unsigned int resource,
                 struct compat_rlimit __user *rlim)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 2b44d82b8237..8e7e135d0817 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -383,15 +383,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
                         get_file(file);
                         if (tmp->vm_flags & VM_DENYWRITE)
                                 atomic_dec(&inode->i_writecount);
-                        spin_lock(&mapping->i_mmap_lock);
+                        mutex_lock(&mapping->i_mmap_mutex);
                         if (tmp->vm_flags & VM_SHARED)
                                 mapping->i_mmap_writable++;
-                        tmp->vm_truncate_count = mpnt->vm_truncate_count;
                         flush_dcache_mmap_lock(mapping);
                         /* insert tmp into the share list, just after mpnt */
                         vma_prio_tree_add(tmp, mpnt);
                         flush_dcache_mmap_unlock(mapping);
-                        spin_unlock(&mapping->i_mmap_lock);
+                        mutex_unlock(&mapping->i_mmap_mutex);
                 }
 
                 /*
@@ -486,6 +485,20 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
+int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+#ifdef CONFIG_CPUMASK_OFFSTACK
+        if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL))
+                return -ENOMEM;
+
+        if (oldmm)
+                cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm));
+        else
+                memset(mm_cpumask(mm), 0, cpumask_size());
+#endif
+        return 0;
+}
+
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
         atomic_set(&mm->mm_users, 1);
@@ -522,10 +535,20 @@ struct mm_struct * mm_alloc(void)
         struct mm_struct * mm;
 
         mm = allocate_mm();
-        if (mm) {
-                memset(mm, 0, sizeof(*mm));
-                mm = mm_init(mm, current);
+        if (!mm)
+                return NULL;
+
+        memset(mm, 0, sizeof(*mm));
+        mm = mm_init(mm, current);
+        if (!mm)
+                return NULL;
+
+        if (mm_init_cpumask(mm, NULL)) {
+                mm_free_pgd(mm);
+                free_mm(mm);
+                return NULL;
         }
+
         return mm;
 }
 
@@ -537,6 +560,7 @@ struct mm_struct * mm_alloc(void)
 void __mmdrop(struct mm_struct *mm)
 {
         BUG_ON(mm == &init_mm);
+        free_cpumask_var(mm->cpu_vm_mask_var);
         mm_free_pgd(mm);
         destroy_context(mm);
         mmu_notifier_mm_destroy(mm);
@@ -691,6 +715,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
         if (!mm_init(mm, tsk))
                 goto fail_nomem;
 
+        if (mm_init_cpumask(mm, oldmm))
+                goto fail_nocpumask;
+
         if (init_new_context(tsk, mm))
                 goto fail_nocontext;
 
@@ -717,6 +744,9 @@ fail_nomem:
         return NULL;
 
 fail_nocontext:
+        free_cpumask_var(mm->cpu_vm_mask_var);
+
+fail_nocpumask:
         /*
          * If init_new_context() failed, we cannot use mmput() to free the mm
          * because it calls destroy_context()
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index c541ee527ecb..a9205e32a059 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -748,7 +748,7 @@ static inline void retrigger_next_event(void *arg) { }
  */
 void clock_was_set(void)
 {
-#ifdef CONFIG_HIGHRES_TIMERS
+#ifdef CONFIG_HIGH_RES_TIMERS
         /* Retrigger the CPU local events everywhere */
         on_each_cpu(retrigger_next_event, NULL, 1);
 #endif
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 834899f2500f..64e3df6ab1ef 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -19,7 +19,7 @@ static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
 
-static int irq_affinity_proc_show(struct seq_file *m, void *v)
+static int show_irq_affinity(int type, struct seq_file *m, void *v)
 {
         struct irq_desc *desc = irq_to_desc((long)m->private);
         const struct cpumask *mask = desc->irq_data.affinity;
@@ -28,7 +28,10 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v)
         if (irqd_is_setaffinity_pending(&desc->irq_data))
                 mask = desc->pending_mask;
 #endif
-        seq_cpumask(m, mask);
+        if (type)
+                seq_cpumask_list(m, mask);
+        else
+                seq_cpumask(m, mask);
         seq_putc(m, '\n');
         return 0;
 }
@@ -59,7 +62,18 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v)
 #endif
 
 int no_irq_affinity;
-static ssize_t irq_affinity_proc_write(struct file *file,
+static int irq_affinity_proc_show(struct seq_file *m, void *v)
+{
+        return show_irq_affinity(0, m, v);
+}
+
+static int irq_affinity_list_proc_show(struct seq_file *m, void *v)
+{
+        return show_irq_affinity(1, m, v);
+}
+
+
+static ssize_t write_irq_affinity(int type, struct file *file,
                 const char __user *buffer, size_t count, loff_t *pos)
 {
         unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data;
@@ -72,7 +86,10 @@ static ssize_t irq_affinity_proc_write(struct file *file,
         if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
                 return -ENOMEM;
 
-        err = cpumask_parse_user(buffer, count, new_value);
+        if (type)
+                err = cpumask_parselist_user(buffer, count, new_value);
+        else
+                err = cpumask_parse_user(buffer, count, new_value);
         if (err)
                 goto free_cpumask;
 
@@ -100,11 +117,28 @@ free_cpumask:
         return err;
 }
 
+static ssize_t irq_affinity_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *pos)
+{
+        return write_irq_affinity(0, file, buffer, count, pos);
+}
+
+static ssize_t irq_affinity_list_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *pos)
+{
+        return write_irq_affinity(1, file, buffer, count, pos);
+}
+
 static int irq_affinity_proc_open(struct inode *inode, struct file *file)
 {
         return single_open(file, irq_affinity_proc_show, PDE(inode)->data);
 }
 
+static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, irq_affinity_list_proc_show, PDE(inode)->data);
+}
+
 static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file)
 {
         return single_open(file, irq_affinity_hint_proc_show, PDE(inode)->data);
@@ -125,6 +159,14 @@ static const struct file_operations irq_affinity_hint_proc_fops = {
         .release        = single_release,
 };
 
+static const struct file_operations irq_affinity_list_proc_fops = {
+        .open           = irq_affinity_list_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = irq_affinity_list_proc_write,
+};
+
 static int default_affinity_show(struct seq_file *m, void *v)
 {
         seq_cpumask(m, irq_default_affinity);
@@ -289,6 +331,10 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
         proc_create_data("affinity_hint", 0400, desc->dir,
                          &irq_affinity_hint_proc_fops, (void *)(long)irq);
 
+        /* create /proc/irq/<irq>/smp_affinity_list */
+        proc_create_data("smp_affinity_list", 0600, desc->dir,
+                         &irq_affinity_list_proc_fops, (void *)(long)irq);
+
         proc_create_data("node", 0444, desc->dir,
                          &irq_node_proc_fops, (void *)(long)irq);
 #endif
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 2c938e2337cd..d607ed5dd441 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -131,14 +131,14 @@ EXPORT_SYMBOL(mutex_unlock);
  */
 static inline int __sched
 __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
-                unsigned long ip)
+                    struct lockdep_map *nest_lock, unsigned long ip)
 {
         struct task_struct *task = current;
         struct mutex_waiter waiter;
         unsigned long flags;
 
         preempt_disable();
-        mutex_acquire(&lock->dep_map, subclass, 0, ip);
+        mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
         /*
@@ -269,16 +269,25 @@ void __sched
 mutex_lock_nested(struct mutex *lock, unsigned int subclass)
 {
         might_sleep();
-        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, _RET_IP_);
+        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_nested);
 
+void __sched
+_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
+{
+        might_sleep();
+        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_);
+}
+
+EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
+
 int __sched
 mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
 {
         might_sleep();
-        return __mutex_lock_common(lock, TASK_KILLABLE, subclass, _RET_IP_);
+        return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
 }
 EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
 
@@ -287,7 +296,7 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 {
         might_sleep();
         return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
-                                   subclass, _RET_IP_);
+                                   subclass, NULL, _RET_IP_);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
@@ -393,7 +402,7 @@ __mutex_lock_slowpath(atomic_t *lock_count)
 {
         struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, _RET_IP_);
+        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched
@@ -401,7 +410,7 @@ __mutex_lock_killable_slowpath(atomic_t *lock_count)
 {
         struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-        return __mutex_lock_common(lock, TASK_KILLABLE, 0, _RET_IP_);
+        return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched
@@ -409,7 +418,7 @@ __mutex_lock_interruptible_slowpath(atomic_t *lock_count)
 {
         struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-        return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, _RET_IP_);
+        return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
 }
 #endif
 
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index a1b5edf1bf92..4556182527f3 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -491,6 +491,13 @@ static struct k_itimer * alloc_posix_timer(void)
         return tmr;
 }
 
+static void k_itimer_rcu_free(struct rcu_head *head)
+{
+        struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);
+
+        kmem_cache_free(posix_timers_cache, tmr);
+}
+
 #define IT_ID_SET       1
 #define IT_ID_NOT_SET   0
 static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
@@ -503,7 +510,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
         }
         put_pid(tmr->it_pid);
         sigqueue_free(tmr->sigq);
-        kmem_cache_free(posix_timers_cache, tmr);
+        call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
 }
 
 static struct k_clock *clockid_to_kclock(const clockid_t id)
@@ -631,22 +638,18 @@ out:
 static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
 {
         struct k_itimer *timr;
-        /*
-         * Watch out here.  We do a irqsave on the idr_lock and pass the
-         * flags part over to the timer lock.  Must not let interrupts in
-         * while we are moving the lock.
-         */
-        spin_lock_irqsave(&idr_lock, *flags);
+
+        rcu_read_lock();
         timr = idr_find(&posix_timers_id, (int)timer_id);
         if (timr) {
-                spin_lock(&timr->it_lock);
+                spin_lock_irqsave(&timr->it_lock, *flags);
                 if (timr->it_signal == current->signal) {
-                        spin_unlock(&idr_lock);
+                        rcu_read_unlock();
                         return timr;
                 }
-                spin_unlock(&timr->it_lock);
+                spin_unlock_irqrestore(&timr->it_lock, *flags);
         }
-        spin_unlock_irqrestore(&idr_lock, *flags);
+        rcu_read_unlock();
 
         return NULL;
 }
diff --git a/kernel/printk.c b/kernel/printk.c
index da8ca817eae3..35185392173f 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -31,6 +31,7 @@
 #include <linux/smp.h>
 #include <linux/security.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/syscalls.h>
 #include <linux/kexec.h>
 #include <linux/kdb.h>
@@ -167,46 +168,74 @@ void log_buf_kexec_setup(void)
 }
 #endif
 
+/* requested log_buf_len from kernel cmdline */
+static unsigned long __initdata new_log_buf_len;
+
+/* save requested log_buf_len since it's too early to process it */
 static int __init log_buf_len_setup(char *str)
 {
         unsigned size = memparse(str, &str);
-        unsigned long flags;
 
         if (size)
                 size = roundup_pow_of_two(size);
-        if (size > log_buf_len) {
-                unsigned start, dest_idx, offset;
-                char *new_log_buf;
+        if (size > log_buf_len)
+                new_log_buf_len = size;
 
-                new_log_buf = alloc_bootmem(size);
-                if (!new_log_buf) {
-                        printk(KERN_WARNING "log_buf_len: allocation failed\n");
-                        goto out;
-                }
+        return 0;
+}
+early_param("log_buf_len", log_buf_len_setup);
 
-                spin_lock_irqsave(&logbuf_lock, flags);
-                log_buf_len = size;
-                log_buf = new_log_buf;
-
-                offset = start = min(con_start, log_start);
-                dest_idx = 0;
-                while (start != log_end) {
-                        log_buf[dest_idx] = __log_buf[start & (__LOG_BUF_LEN - 1)];
-                        start++;
-                        dest_idx++;
-                }
-                log_start -= offset;
-                con_start -= offset;
-                log_end -= offset;
-                spin_unlock_irqrestore(&logbuf_lock, flags);
+void __init setup_log_buf(int early)
+{
+        unsigned long flags;
+        unsigned start, dest_idx, offset;
+        char *new_log_buf;
+        int free;
+
+        if (!new_log_buf_len)
+                return;
+
+        if (early) {
+                unsigned long mem;
 
-                printk(KERN_NOTICE "log_buf_len: %d\n", log_buf_len);
+                mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
+                if (mem == MEMBLOCK_ERROR)
+                        return;
+                new_log_buf = __va(mem);
+        } else {
+                new_log_buf = alloc_bootmem_nopanic(new_log_buf_len);
         }
-out:
-        return 1;
-}
 
-__setup("log_buf_len=", log_buf_len_setup);
+        if (unlikely(!new_log_buf)) {
+                pr_err("log_buf_len: %ld bytes not available\n",
+                        new_log_buf_len);
+                return;
+        }
+
+        spin_lock_irqsave(&logbuf_lock, flags);
+        log_buf_len = new_log_buf_len;
+        log_buf = new_log_buf;
+        new_log_buf_len = 0;
+        free = __LOG_BUF_LEN - log_end;
+
+        offset = start = min(con_start, log_start);
+        dest_idx = 0;
+        while (start != log_end) {
+                unsigned log_idx_mask = start & (__LOG_BUF_LEN - 1);
+
+                log_buf[dest_idx] = __log_buf[log_idx_mask];
+                start++;
+                dest_idx++;
+        }
+        log_start -= offset;
+        con_start -= offset;
+        log_end -= offset;
+        spin_unlock_irqrestore(&logbuf_lock, flags);
+
+        pr_info("log_buf_len: %d\n", log_buf_len);
+        pr_info("early log buf free: %d(%d%%)\n",
+                free, (free * 100) / __LOG_BUF_LEN);
+}
 
 #ifdef CONFIG_BOOT_PRINTK_DELAY
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4bffd62c2f13..4fc92445a29c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1506,7 +1506,7 @@ static struct ctl_table fs_table[] = {
 
 static struct ctl_table debug_table[] = {
 #if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || \
-    defined(CONFIG_S390)
+    defined(CONFIG_S390) || defined(CONFIG_TILE)
         {
                 .procname       = "exception-trace",
                 .data           = &show_unhandled_signals,
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 0efcdca9751a..28afa4c5333c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -670,6 +670,15 @@ config STACKTRACE
         bool
         depends on STACKTRACE_SUPPORT
 
+config DEBUG_STACK_USAGE
+        bool "Stack utilization instrumentation"
+        depends on DEBUG_KERNEL
+        help
+          Enables the display of the minimum amount of free stack which each
+          task has ever had available in the sysrq-T and sysrq-P debug output.
+
+          This option will slow down process creation somewhat.
+
 config DEBUG_KOBJECT
         bool "kobject debugging"
         depends on DEBUG_KERNEL
@@ -983,6 +992,17 @@ config DEBUG_FORCE_WEAK_PER_CPU
           To ensure that generic code follows the above rules, this
           option forces all percpu variables to be defined as weak.
 
+config DEBUG_PER_CPU_MAPS
+        bool "Debug access to per_cpu maps"
+        depends on DEBUG_KERNEL
+        depends on SMP
+        help
+          Say Y to verify that the per_cpu map being accessed has
+          been set up. This adds a fair amount of code to kernel memory
+          and decreases performance.
+
+          Say N if unsure.
+
 config LKDTM
         tristate "Linux Kernel Dump Test Tool Module"
         depends on DEBUG_FS
diff --git a/lib/audit.c b/lib/audit.c
index 8e7dc1c63aa9..76bbed4a20e5 100644
--- a/lib/audit.c
+++ b/lib/audit.c
@@ -36,8 +36,10 @@ int audit_classify_arch(int arch)
 int audit_classify_syscall(int abi, unsigned syscall)
 {
         switch(syscall) {
+#ifdef __NR_open
         case __NR_open:
                 return 2;
+#endif
 #ifdef __NR_openat
         case __NR_openat:
                 return 3;
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 91e0ccfdb424..41baf02924e6 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -571,8 +571,11 @@ int bitmap_scnlistprintf(char *buf, unsigned int buflen,
 EXPORT_SYMBOL(bitmap_scnlistprintf);
 
 /**
- * bitmap_parselist - convert list format ASCII string to bitmap
+ * __bitmap_parselist - convert list format ASCII string to bitmap
  * @bp: read nul-terminated user string from this buffer
+ * @buflen: buffer size in bytes.  If string is smaller than this
+ *    then it must be terminated with a \0.
+ * @is_user: location of buffer, 0 indicates kernel space
  * @maskp: write resulting mask here
  * @nmaskbits: number of bits in mask to be written
  *
@@ -587,20 +590,63 @@ EXPORT_SYMBOL(bitmap_scnlistprintf);
  *    %-EINVAL: invalid character in string
  *    %-ERANGE: bit number specified too large for mask
  */
-int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
+static int __bitmap_parselist(const char *buf, unsigned int buflen,
+                int is_user, unsigned long *maskp,
+                int nmaskbits)
 {
         unsigned a, b;
+        int c, old_c, totaldigits;
+        const char __user *ubuf = buf;
+        int exp_digit, in_range;
 
+        totaldigits = c = 0;
         bitmap_zero(maskp, nmaskbits);
         do {
-                if (!isdigit(*bp))
-                        return -EINVAL;
-                b = a = simple_strtoul(bp, (char **)&bp, BASEDEC);
-                if (*bp == '-') {
-                        bp++;
-                        if (!isdigit(*bp))
+                exp_digit = 1;
+                in_range = 0;
+                a = b = 0;
+
+                /* Get the next cpu# or a range of cpu#'s */
+                while (buflen) {
+                        old_c = c;
+                        if (is_user) {
+                                if (__get_user(c, ubuf++))
+                                        return -EFAULT;
+                        } else
+                                c = *buf++;
+                        buflen--;
+                        if (isspace(c))
+                                continue;
+
+                        /*
+                         * If the last character was a space and the current
+                         * character isn't '\0', we've got embedded whitespace.
+                         * This is a no-no, so throw an error.
+                         */
+                        if (totaldigits && c && isspace(old_c))
+                                return -EINVAL;
+
+                        /* A '\0' or a ',' signal the end of a cpu# or range */
+                        if (c == '\0' || c == ',')
+                                break;
+
+                        if (c == '-') {
+                                if (exp_digit || in_range)
+                                        return -EINVAL;
+                                b = 0;
+                                in_range = 1;
+                                exp_digit = 1;
+                                continue;
+                        }
+
+                        if (!isdigit(c))
                                 return -EINVAL;
-                        b = simple_strtoul(bp, (char **)&bp, BASEDEC);
+
+                        b = b * 10 + (c - '0');
+                        if (!in_range)
+                                a = b;
+                        exp_digit = 0;
+                        totaldigits++;
                 }
                 if (!(a <= b))
                         return -EINVAL;
@@ -610,13 +656,52 @@ int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
                         set_bit(a, maskp);
                         a++;
                 }
-                if (*bp == ',')
-                        bp++;
-        } while (*bp != '\0' && *bp != '\n');
+        } while (buflen && c == ',');
         return 0;
 }
+
+int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
+{
+        char *nl  = strchr(bp, '\n');
+        int len;
+
+        if (nl)
+                len = nl - bp;
+        else
+                len = strlen(bp);
+
+        return __bitmap_parselist(bp, len, 0, maskp, nmaskbits);
+}
 EXPORT_SYMBOL(bitmap_parselist);
 
+
+/**
+ * bitmap_parselist_user()
+ *
+ * @ubuf: pointer to user buffer containing string.
+ * @ulen: buffer size in bytes.  If string is smaller than this
+ *    then it must be terminated with a \0.
+ * @maskp: pointer to bitmap array that will contain result.
+ * @nmaskbits: size of bitmap, in bits.
+ *
+ * Wrapper for bitmap_parselist(), providing it with user buffer.
+ *
+ * We cannot have this as an inline function in bitmap.h because it needs
+ * linux/uaccess.h to get the access_ok() declaration and this causes
+ * cyclic dependencies.
+ */
+int bitmap_parselist_user(const char __user *ubuf,
+                        unsigned int ulen, unsigned long *maskp,
+                        int nmaskbits)
+{
+        if (!access_ok(VERIFY_READ, ubuf, ulen))
+                return -EFAULT;
+        return __bitmap_parselist((const char *)ubuf,
+                                        ulen, 1, maskp, nmaskbits);
+}
+EXPORT_SYMBOL(bitmap_parselist_user);
+
+
 /**
  * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
  *      @buf: pointer to a bitmap
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 1923f1490e72..577ddf805975 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -39,17 +39,20 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
 EXPORT_SYMBOL(gen_pool_create);
 
 /**
- * gen_pool_add - add a new chunk of special memory to the pool
+ * gen_pool_add_virt - add a new chunk of special memory to the pool
  * @pool: pool to add new memory chunk to
- * @addr: starting address of memory chunk to add to pool
+ * @virt: virtual starting address of memory chunk to add to pool
+ * @phys: physical starting address of memory chunk to add to pool
  * @size: size in bytes of the memory chunk to add to pool
  * @nid: node id of the node the chunk structure and bitmap should be
  *       allocated on, or -1
  *
  * Add a new chunk of special memory to the specified pool.
+ *
+ * Returns 0 on success or a -ve errno on failure.
  */
-int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size,
-                 int nid)
+int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
+                 size_t size, int nid)
 {
         struct gen_pool_chunk *chunk;
         int nbits = size >> pool->min_alloc_order;
@@ -58,11 +61,12 @@ int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size,
 
         chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
         if (unlikely(chunk == NULL))
-                return -1;
+                return -ENOMEM;
 
         spin_lock_init(&chunk->lock);
-        chunk->start_addr = addr;
-        chunk->end_addr = addr + size;
+        chunk->phys_addr = phys;
+        chunk->start_addr = virt;
+        chunk->end_addr = virt + size;
 
         write_lock(&pool->lock);
         list_add(&chunk->next_chunk, &pool->chunks);
@@ -70,7 +74,32 @@ int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size,
 
         return 0;
 }
-EXPORT_SYMBOL(gen_pool_add);
+EXPORT_SYMBOL(gen_pool_add_virt);
+
+/**
+ * gen_pool_virt_to_phys - return the physical address of memory
+ * @pool: pool to allocate from
+ * @addr: starting address of memory
+ *
+ * Returns the physical address on success, or -1 on error.
+ */
+phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
+{
+        struct list_head *_chunk;
+        struct gen_pool_chunk *chunk;
+
+        read_lock(&pool->lock);
+        list_for_each(_chunk, &pool->chunks) {
+                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+
+                if (addr >= chunk->start_addr && addr < chunk->end_addr)
+                        return chunk->phys_addr + addr - chunk->start_addr;
+        }
+        read_unlock(&pool->lock);
+
+        return -1;
+}
+EXPORT_SYMBOL(gen_pool_virt_to_phys);
 
 /**
  * gen_pool_destroy - destroy a special memory pool
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index a235f3cc471c..2dbae88090ac 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -17,6 +17,7 @@
 #include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <asm/uaccess.h>
 
 static inline char _tolower(const char c)
 {
@@ -222,3 +223,28 @@ int kstrtos8(const char *s, unsigned int base, s8 *res)
         return 0;
 }
 EXPORT_SYMBOL(kstrtos8);
+
+#define kstrto_from_user(f, g, type)                                    \
+int f(const char __user *s, size_t count, unsigned int base, type *res) \
+{                                                                       \
+        /* sign, base 2 representation, newline, terminator */          \
+        char buf[1 + sizeof(type) * 8 + 1 + 1];                         \
+                                                                        \
+        count = min(count, sizeof(buf) - 1);                            \
+        if (copy_from_user(buf, s, count))                              \
+                return -EFAULT;                                         \
+        buf[count] = '\0';                                              \
+        return g(buf, base, res);                                       \
+}                                                                       \
+EXPORT_SYMBOL(f)
+
+kstrto_from_user(kstrtoull_from_user,   kstrtoull,      unsigned long long);
+kstrto_from_user(kstrtoll_from_user,    kstrtoll,       long long);
+kstrto_from_user(kstrtoul_from_user,    kstrtoul,       unsigned long);
+kstrto_from_user(kstrtol_from_user,     kstrtol,        long);
+kstrto_from_user(kstrtouint_from_user,  kstrtouint,     unsigned int);
+kstrto_from_user(kstrtoint_from_user,   kstrtoint,      int);
+kstrto_from_user(kstrtou16_from_user,   kstrtou16,      u16);
+kstrto_from_user(kstrtos16_from_user,   kstrtos16,      s16);
+kstrto_from_user(kstrtou8_from_user,    kstrtou8,       u8);
+kstrto_from_user(kstrtos8_from_user,    kstrtos8,       s8);
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
index 270de9d31b8c..a07e7268d7ed 100644
--- a/lib/lru_cache.c
+++ b/lib/lru_cache.c
@@ -84,7 +84,7 @@ struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
         if (e_count > LC_MAX_ACTIVE)
                 return NULL;
 
-        slot = kzalloc(e_count * sizeof(struct hlist_head*), GFP_KERNEL);
+        slot = kcalloc(e_count, sizeof(struct hlist_head), GFP_KERNEL);
         if (!slot)
                 goto out_fail;
         element = kzalloc(e_count * sizeof(struct lc_element *), GFP_KERNEL);
diff --git a/lib/show_mem.c b/lib/show_mem.c
index 90cbe4bb5960..4407f8c9b1f7 100644
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -16,7 +16,7 @@ void show_mem(unsigned int filter)
                 nonshared = 0, highmem = 0;
 
         printk("Mem-Info:\n");
-        __show_free_areas(filter);
+        show_free_areas(filter);
 
         for_each_online_pgdat(pgdat) {
                 unsigned long i, flags;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 1d659d7bb0f8..c11205688fb4 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -898,7 +898,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
         case 'U':
                 return uuid_string(buf, end, ptr, spec, fmt);
         case 'V':
-                return buf + vsnprintf(buf, end - buf,
+                return buf + vsnprintf(buf, end > buf ? end - buf : 0,
                                        ((struct va_format *)ptr)->fmt,
                                        *(((struct va_format *)ptr)->va));
         case 'K':
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index befc87531e4f..f032e6e1e09a 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -63,10 +63,10 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
         unsigned long background_thresh;
         unsigned long dirty_thresh;
         unsigned long bdi_thresh;
-        unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+        unsigned long nr_dirty, nr_io, nr_more_io;
         struct inode *inode;
 
-        nr_wb = nr_dirty = nr_io = nr_more_io = 0;
+        nr_dirty = nr_io = nr_more_io = 0;
         spin_lock(&inode_wb_list_lock);
         list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
                 nr_dirty++;
diff --git a/mm/filemap.c b/mm/filemap.c
index c641edf553a9..68e782b3d3de 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -58,16 +58,16 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_lock               (truncate_pagecache)
+ *  ->i_mmap_mutex              (truncate_pagecache)
  *    ->private_lock            (__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock             (exclusive_swap_page, others)
  *        ->mapping->tree_lock
  *
  *  ->i_mutex
- *    ->i_mmap_lock             (truncate->unmap_mapping_range)
+ *    ->i_mmap_mutex            (truncate->unmap_mapping_range)
  *
  *  ->mmap_sem
- *    ->i_mmap_lock
+ *    ->i_mmap_mutex
  *      ->page_table_lock or pte_lock   (various, mainly in memory.c)
  *        ->mapping->tree_lock  (arch-dependent flush_dcache_mmap_lock)
  *
@@ -84,7 +84,7 @@
  *    sb_lock                   (fs/fs-writeback.c)
  *    ->mapping->tree_lock      (__sync_single_inode)
  *
- *  ->i_mmap_lock
+ *  ->i_mmap_mutex
  *    ->anon_vma.lock           (vma_adjust)
  *
  *  ->anon_vma.lock
@@ -106,7 +106,7 @@
  *
  *  (code doesn't rely on that order, so you could switch it around)
  *  ->tasklist_lock             (memory_failure, collect_procs_ao)
- *    ->i_mmap_lock
+ *    ->i_mmap_mutex
  */
 
 /*
@@ -562,6 +562,17 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 
+int wait_on_page_bit_killable(struct page *page, int bit_nr)
+{
+        DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+
+        if (!test_bit(bit_nr, &page->flags))
+                return 0;
+
+        return __wait_on_bit(page_waitqueue(page), &wait,
+                             sleep_on_page_killable, TASK_KILLABLE);
+}
+
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest
@@ -643,15 +654,32 @@ EXPORT_SYMBOL_GPL(__lock_page_killable);
 int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
                          unsigned int flags)
 {
-        if (!(flags & FAULT_FLAG_ALLOW_RETRY)) {
-                __lock_page(page);
-                return 1;
-        } else {
-                if (!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
-                        up_read(&mm->mmap_sem);
+        if (flags & FAULT_FLAG_ALLOW_RETRY) {
+                /*
+                 * CAUTION! In this case, mmap_sem is not released
+                 * even though return 0.
+                 */
+                if (flags & FAULT_FLAG_RETRY_NOWAIT)
+                        return 0;
+
+                up_read(&mm->mmap_sem);
+                if (flags & FAULT_FLAG_KILLABLE)
+                        wait_on_page_locked_killable(page);
+                else
                         wait_on_page_locked(page);
-                }
                 return 0;
+        } else {
+                if (flags & FAULT_FLAG_KILLABLE) {
+                        int ret;
+
+                        ret = __lock_page_killable(page);
+                        if (ret) {
+                                up_read(&mm->mmap_sem);
+                                return 0;
+                        }
+                } else
+                        __lock_page(page);
+                return 1;
         }
 }
 
@@ -1528,15 +1556,17 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
         /* If we don't want any read-ahead, don't bother */
         if (VM_RandomReadHint(vma))
                 return;
+        if (!ra->ra_pages)
+                return;
 
-        if (VM_SequentialReadHint(vma) ||
-                        offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) {
+        if (VM_SequentialReadHint(vma)) {
                 page_cache_sync_readahead(mapping, ra, file, offset,
                                           ra->ra_pages);
                 return;
         }
 
-        if (ra->mmap_miss < INT_MAX)
+        /* Avoid banging the cache line if not needed */
+        if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
                 ra->mmap_miss++;
 
         /*
@@ -1550,12 +1580,10 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
          * mmap read-around
          */
         ra_pages = max_sane_readahead(ra->ra_pages);
-        if (ra_pages) {
-                ra->start = max_t(long, 0, offset - ra_pages/2);
-                ra->size = ra_pages;
-                ra->async_size = 0;
-                ra_submit(ra, mapping, file);
-        }
+        ra->start = max_t(long, 0, offset - ra_pages / 2);
+        ra->size = ra_pages;
+        ra->async_size = ra_pages / 4;
+        ra_submit(ra, mapping, file);
 }
 
 /*
@@ -1660,7 +1688,6 @@ retry_find:
                 return VM_FAULT_SIGBUS;
         }
 
-        ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT;
         vmf->page = page;
         return ret | VM_FAULT_LOCKED;
 
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 83364df74a33..93356cd12828 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -183,7 +183,7 @@ __xip_unmap (struct address_space * mapping,
                 return;
 
 retry:
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
                 mm = vma->vm_mm;
                 address = vma->vm_start +
@@ -201,7 +201,7 @@ retry:
                         page_cache_release(page);
                 }
         }
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
 
         if (locked) {
                 mutex_unlock(&xip_sparse_mutex);
diff --git a/mm/fremap.c b/mm/fremap.c
index ec520c7b28df..7f4123056e06 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -211,13 +211,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
                         }
                         goto out;
                 }
-                spin_lock(&mapping->i_mmap_lock);
+                mutex_lock(&mapping->i_mmap_mutex);
                 flush_dcache_mmap_lock(mapping);
                 vma->vm_flags |= VM_NONLINEAR;
                 vma_prio_tree_remove(vma, &mapping->i_mmap);
                 vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
                 flush_dcache_mmap_unlock(mapping);
-                spin_unlock(&mapping->i_mmap_lock);
+                mutex_unlock(&mapping->i_mmap_mutex);
         }
 
         if (vma->vm_flags & VM_LOCKED) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 83326ad66d9b..615d9743a3cb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1139,7 +1139,7 @@ static int __split_huge_page_splitting(struct page *page,
                  * We can't temporarily set the pmd to null in order
                  * to split it, the pmd must remain marked huge at all
                  * times or the VM won't take the pmd_trans_huge paths
-                 * and it won't wait on the anon_vma->root->lock to
+                 * and it won't wait on the anon_vma->root->mutex to
                  * serialize against split_huge_page*.
                  */
                 pmdp_splitting_flush_notify(vma, address, pmd);
@@ -1333,7 +1333,7 @@ static int __split_huge_page_map(struct page *page,
         return ret;
 }
 
-/* must be called with anon_vma->root->lock hold */
+/* must be called with anon_vma->root->mutex hold */
 static void __split_huge_page(struct page *page,
                               struct anon_vma *anon_vma)
 {
@@ -1771,12 +1771,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 
         VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 #ifndef CONFIG_NUMA
+        up_read(&mm->mmap_sem);
         VM_BUG_ON(!*hpage);
         new_page = *hpage;
-        if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
-                up_read(&mm->mmap_sem);
-                return;
-        }
 #else
         VM_BUG_ON(*hpage);
         /*
@@ -1791,22 +1788,26 @@ static void collapse_huge_page(struct mm_struct *mm,
          */
         new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
                                       node, __GFP_OTHER_NODE);
+
+        /*
+         * After allocating the hugepage, release the mmap_sem read lock in
+         * preparation for taking it in write mode.
+         */
+        up_read(&mm->mmap_sem);
         if (unlikely(!new_page)) {
-                up_read(&mm->mmap_sem);
                 count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
                 *hpage = ERR_PTR(-ENOMEM);
                 return;
         }
+#endif
+
         count_vm_event(THP_COLLAPSE_ALLOC);
         if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
-                up_read(&mm->mmap_sem);
+#ifdef CONFIG_NUMA
                 put_page(new_page);
+#endif
                 return;
         }
-#endif
-
-        /* after allocating the hugepage upgrade to mmap_sem write mode */
-        up_read(&mm->mmap_sem);
 
         /*
          * Prevent all access to pagetables with the exception of
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bbb4a5bbb958..5fd68b95c671 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2205,7 +2205,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
         unsigned long sz = huge_page_size(h);
 
         /*
-         * A page gathering list, protected by per file i_mmap_lock. The
+         * A page gathering list, protected by per file i_mmap_mutex. The
          * lock is used to avoid list corruption from multiple unmapping
          * of the same page since we are using page->lru.
          */
@@ -2274,9 +2274,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
                           unsigned long end, struct page *ref_page)
 {
-        spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+        mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
         __unmap_hugepage_range(vma, start, end, ref_page);
-        spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+        mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
 /*
@@ -2308,7 +2308,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
          * this mapping should be shared between all the VMAs,
          * __unmap_hugepage_range() is called as the lock is already held
          */
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
                 /* Do not unmap the current VMA */
                 if (iter_vma == vma)
@@ -2326,7 +2326,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
                                 address, address + huge_page_size(h),
                                 page);
         }
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
 
         return 1;
 }
@@ -2810,7 +2810,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
         BUG_ON(address >= end);
         flush_cache_range(vma, address, end);
 
-        spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+        mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
         spin_lock(&mm->page_table_lock);
         for (; address < end; address += huge_page_size(h)) {
                 ptep = huge_pte_offset(mm, address);
@@ -2825,7 +2825,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
                 }
         }
         spin_unlock(&mm->page_table_lock);
-        spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+        mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 
         flush_tlb_range(vma, start, end);
 }
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 1d29cdfe8ebb..4019979b2637 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -21,6 +21,5 @@ struct mm_struct init_mm = {
         .mmap_sem       = __RWSEM_INITIALIZER(init_mm.mmap_sem),
         .page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
         .mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
-        .cpu_vm_mask    = CPU_MASK_ALL,
         INIT_MM_CONTEXT(init_mm)
 };
diff --git a/mm/internal.h b/mm/internal.h
index 9d0ced8e505e..d071d380fb49 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -66,6 +66,10 @@ static inline unsigned long page_order(struct page *page)
         return page_private(page);
 }
 
+/* mm/util.c */
+void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
+                struct vm_area_struct *prev, struct rb_node *rb_parent);
+
 #ifdef CONFIG_MMU
 extern long mlock_vma_pages_range(struct vm_area_struct *vma,
                         unsigned long start, unsigned long end);
diff --git a/mm/ksm.c b/mm/ksm.c
index 942dfc73a2ff..d708b3ef2260 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -35,6 +35,7 @@
 #include <linux/ksm.h>
 #include <linux/hash.h>
 #include <linux/freezer.h>
+#include <linux/oom.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -1894,9 +1895,11 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
         if (ksm_run != flags) {
                 ksm_run = flags;
                 if (flags & KSM_RUN_UNMERGE) {
-                        current->flags |= PF_OOM_ORIGIN;
+                        int oom_score_adj;
+
+                        oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
                         err = unmerge_and_remove_all_rmap_items();
-                        current->flags &= ~PF_OOM_ORIGIN;
+                        test_set_oom_score_adj(oom_score_adj);
                         if (err) {
                                 ksm_run = KSM_RUN_STOP;
                                 count = err;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 010f9166fa6e..d5fd3dcd3f2e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5169,19 +5169,12 @@ struct cgroup_subsys mem_cgroup_subsys = {
 static int __init enable_swap_account(char *s)
 {
         /* consider enabled if no parameter or 1 is given */
-        if (!(*s) || !strcmp(s, "=1"))
+        if (!strcmp(s, "1"))
                 really_do_swap_account = 1;
-        else if (!strcmp(s, "=0"))
+        else if (!strcmp(s, "0"))
                 really_do_swap_account = 0;
         return 1;
 }
-__setup("swapaccount", enable_swap_account);
+__setup("swapaccount=", enable_swap_account);
 
-static int __init disable_swap_account(char *s)
-{
-        printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n");
-        enable_swap_account("=0");
-        return 1;
-}
-__setup("noswapaccount", disable_swap_account);
 #endif
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2b9a5eef39e0..5c8f7e08928d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -239,7 +239,11 @@ void shake_page(struct page *p, int access)
         if (access) {
                 int nr;
                 do {
-                        nr = shrink_slab(1000, GFP_KERNEL, 1000);
+                        struct shrink_control shrink = {
+                                .gfp_mask = GFP_KERNEL,
+                        };
+
+                        nr = shrink_slab(&shrink, 1000, 1000);
                         if (page_count(p) == 1)
                                 break;
                 } while (nr > 10);
@@ -429,7 +433,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
          */
 
         read_lock(&tasklist_lock);
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         for_each_process(tsk) {
                 pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
@@ -449,7 +453,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
                                 add_to_kill(tsk, page, vma, to_kill, tkc);
                 }
         }
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
         read_unlock(&tasklist_lock);
 }
 
@@ -1440,16 +1444,12 @@ int soft_offline_page(struct page *page, int flags)
          */
         ret = invalidate_inode_page(page);
         unlock_page(page);
-
         /*
-         * Drop count because page migration doesn't like raised
-         * counts. The page could get re-allocated, but if it becomes
-         * LRU the isolation will just fail.
          * RED-PEN would be better to keep it isolated here, but we
          * would need to fix isolation locking first.
          */
-        put_page(page);
         if (ret == 1) {
+                put_page(page);
                 ret = 0;
                 pr_info("soft_offline: %#lx: invalidated\n", pfn);
                 goto done;
@@ -1461,6 +1461,11 @@ int soft_offline_page(struct page *page, int flags)
          * handles a large number of cases for us.
          */
         ret = isolate_lru_page(page);
+        /*
+         * Drop page reference which is came from get_any_page()
+         * successful isolate_lru_page() already took another one.
+         */
+        put_page(page);
         if (!ret) {
                 LIST_HEAD(pagelist);
 
diff --git a/mm/memory.c b/mm/memory.c
index 61e66f026563..b73f677f0bb1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -182,7 +182,7 @@ void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
 {
         __sync_task_rss_stat(task, mm);
 }
-#else
+#else /* SPLIT_RSS_COUNTING */
 
 #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
 #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)
@@ -191,8 +191,205 @@ static void check_sync_rss_stat(struct task_struct *task)
 {
 }
 
+#endif /* SPLIT_RSS_COUNTING */
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+
+static int tlb_next_batch(struct mmu_gather *tlb)
+{
+        struct mmu_gather_batch *batch;
+
+        batch = tlb->active;
+        if (batch->next) {
+                tlb->active = batch->next;
+                return 1;
+        }
+
+        batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+        if (!batch)
+                return 0;
+
+        batch->next = NULL;
+        batch->nr   = 0;
+        batch->max  = MAX_GATHER_BATCH;
+
+        tlb->active->next = batch;
+        tlb->active = batch;
+
+        return 1;
+}
+
+/* tlb_gather_mmu
+ *      Called to initialize an (on-stack) mmu_gather structure for page-table
+ *      tear-down from @mm. The @fullmm argument is used when @mm is without
+ *      users and we're going to destroy the full address space (exit/execve).
+ */
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+{
+        tlb->mm = mm;
+
+        tlb->fullmm     = fullmm;
+        tlb->need_flush = 0;
+        tlb->fast_mode  = (num_possible_cpus() == 1);
+        tlb->local.next = NULL;
+        tlb->local.nr   = 0;
+        tlb->local.max  = ARRAY_SIZE(tlb->__pages);
+        tlb->active     = &tlb->local;
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb->batch = NULL;
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+        struct mmu_gather_batch *batch;
+
+        if (!tlb->need_flush)
+                return;
+        tlb->need_flush = 0;
+        tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb_table_flush(tlb);
 #endif
 
+        if (tlb_fast_mode(tlb))
+                return;
+
+        for (batch = &tlb->local; batch; batch = batch->next) {
+                free_pages_and_swap_cache(batch->pages, batch->nr);
+                batch->nr = 0;
+        }
+        tlb->active = &tlb->local;
+}
+
+/* tlb_finish_mmu
+ *      Called at the end of the shootdown operation to free up any resources
+ *      that were required.
+ */
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+        struct mmu_gather_batch *batch, *next;
+
+        tlb_flush_mmu(tlb);
+
+        /* keep the page table cache within bounds */
+        check_pgt_cache();
+
+        for (batch = tlb->local.next; batch; batch = next) {
+                next = batch->next;
+                free_pages((unsigned long)batch, 0);
+        }
+        tlb->local.next = NULL;
+}
+
+/* __tlb_remove_page
+ *      Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
+ *      handling the additional races in SMP caused by other CPUs caching valid
+ *      mappings in their TLBs. Returns the number of free page slots left.
+ *      When out of page slots we must call tlb_flush_mmu().
+ */
+int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        struct mmu_gather_batch *batch;
+
+        tlb->need_flush = 1;
+
+        if (tlb_fast_mode(tlb)) {
+                free_page_and_swap_cache(page);
+                return 1; /* avoid calling tlb_flush_mmu() */
+        }
+
+        batch = tlb->active;
+        batch->pages[batch->nr++] = page;
+        if (batch->nr == batch->max) {
+                if (!tlb_next_batch(tlb))
+                        return 0;
+        }
+        VM_BUG_ON(batch->nr > batch->max);
+
+        return batch->max - batch->nr;
+}
+
+#endif /* HAVE_GENERIC_MMU_GATHER */
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+/*
+ * See the comment near struct mmu_table_batch.
+ */
+
+static void tlb_remove_table_smp_sync(void *arg)
+{
+        /* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+        /*
+         * This isn't an RCU grace period and hence the page-tables cannot be
+         * assumed to be actually RCU-freed.
+         *
+         * It is however sufficient for software page-table walkers that rely on
+         * IRQ disabling. See the comment near struct mmu_table_batch.
+         */
+        smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+        __tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+        struct mmu_table_batch *batch;
+        int i;
+
+        batch = container_of(head, struct mmu_table_batch, rcu);
+
+        for (i = 0; i < batch->nr; i++)
+                __tlb_remove_table(batch->tables[i]);
+
+        free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+        struct mmu_table_batch **batch = &tlb->batch;
+
+        if (*batch) {
+                call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+                *batch = NULL;
+        }
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+        struct mmu_table_batch **batch = &tlb->batch;
+
+        tlb->need_flush = 1;
+
+        /*
+         * When there's less then two users of this mm there cannot be a
+         * concurrent page-table walk.
+         */
+        if (atomic_read(&tlb->mm->mm_users) < 2) {
+                __tlb_remove_table(table);
+                return;
+        }
+
+        if (*batch == NULL) {
+                *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+                if (*batch == NULL) {
+                        tlb_remove_table_one(table);
+                        return;
+                }
+                (*batch)->nr = 0;
+        }
+        (*batch)->tables[(*batch)->nr++] = table;
+        if ((*batch)->nr == MAX_TABLE_BATCH)
+                tlb_table_flush(tlb);
+}
+
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * If a p?d_bad entry is found while walking page tables, report
  * the error, before resetting entry to p?d_none.  Usually (but
@@ -909,26 +1106,24 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma, pmd_t *pmd,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         struct mm_struct *mm = tlb->mm;
-        pte_t *pte;
-        spinlock_t *ptl;
+        int force_flush = 0;
         int rss[NR_MM_COUNTERS];
+        spinlock_t *ptl;
+        pte_t *pte;
 
+again:
         init_rss_vec(rss);
-
         pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
         arch_enter_lazy_mmu_mode();
         do {
                 pte_t ptent = *pte;
                 if (pte_none(ptent)) {
-                        (*zap_work)--;
                         continue;
                 }
 
-                (*zap_work) -= PAGE_SIZE;
-
                 if (pte_present(ptent)) {
                         struct page *page;
 
@@ -974,7 +1169,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                         page_remove_rmap(page);
                         if (unlikely(page_mapcount(page) < 0))
                                 print_bad_pte(vma, addr, ptent, page);
-                        tlb_remove_page(tlb, page);
+                        force_flush = !__tlb_remove_page(tlb, page);
+                        if (force_flush)
+                                break;
                         continue;
                 }
                 /*
@@ -995,19 +1192,31 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                                 print_bad_pte(vma, addr, ptent, NULL);
                 }
                 pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
-        } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
+        } while (pte++, addr += PAGE_SIZE, addr != end);
 
         add_mm_rss_vec(mm, rss);
         arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
 
+        /*
+         * mmu_gather ran out of room to batch pages, we break out of
+         * the PTE lock to avoid doing the potential expensive TLB invalidate
+         * and page-free while holding it.
+         */
+        if (force_flush) {
+                force_flush = 0;
+                tlb_flush_mmu(tlb);
+                if (addr != end)
+                        goto again;
+        }
+
         return addr;
 }
 
 static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma, pud_t *pud,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         pmd_t *pmd;
         unsigned long next;
@@ -1019,19 +1228,15 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
                         if (next-addr != HPAGE_PMD_SIZE) {
                                 VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
                                 split_huge_page_pmd(vma->vm_mm, pmd);
-                        } else if (zap_huge_pmd(tlb, vma, pmd)) {
-                                (*zap_work)--;
+                        } else if (zap_huge_pmd(tlb, vma, pmd))
                                 continue;
-                        }
                         /* fall through */
                 }
-                if (pmd_none_or_clear_bad(pmd)) {
-                        (*zap_work)--;
+                if (pmd_none_or_clear_bad(pmd))
                         continue;
-                }
-                next = zap_pte_range(tlb, vma, pmd, addr, next,
-                                                zap_work, details);
-        } while (pmd++, addr = next, (addr != end && *zap_work > 0));
+                next = zap_pte_range(tlb, vma, pmd, addr, next, details);
+                cond_resched();
+        } while (pmd++, addr = next, addr != end);
 
         return addr;
 }
@@ -1039,7 +1244,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma, pgd_t *pgd,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         pud_t *pud;
         unsigned long next;
@@ -1047,13 +1252,10 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
         pud = pud_offset(pgd, addr);
         do {
                 next = pud_addr_end(addr, end);
-                if (pud_none_or_clear_bad(pud)) {
-                        (*zap_work)--;
+                if (pud_none_or_clear_bad(pud))
                         continue;
-                }
-                next = zap_pmd_range(tlb, vma, pud, addr, next,
-                                                zap_work, details);
-        } while (pud++, addr = next, (addr != end && *zap_work > 0));
+                next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+        } while (pud++, addr = next, addr != end);
 
         return addr;
 }
@@ -1061,7 +1263,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 static unsigned long unmap_page_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         pgd_t *pgd;
         unsigned long next;
@@ -1075,13 +1277,10 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
         pgd = pgd_offset(vma->vm_mm, addr);
         do {
                 next = pgd_addr_end(addr, end);
-                if (pgd_none_or_clear_bad(pgd)) {
-                        (*zap_work)--;
+                if (pgd_none_or_clear_bad(pgd))
                         continue;
-                }
-                next = zap_pud_range(tlb, vma, pgd, addr, next,
-                                                zap_work, details);
-        } while (pgd++, addr = next, (addr != end && *zap_work > 0));
+                next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+        } while (pgd++, addr = next, addr != end);
         tlb_end_vma(tlb, vma);
         mem_cgroup_uncharge_end();
 
@@ -1121,17 +1320,12 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
  * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
  * drops the lock and schedules.
  */
-unsigned long unmap_vmas(struct mmu_gather **tlbp,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
                 struct vm_area_struct *vma, unsigned long start_addr,
                 unsigned long end_addr, unsigned long *nr_accounted,
                 struct zap_details *details)
 {
-        long zap_work = ZAP_BLOCK_SIZE;
-        unsigned long tlb_start = 0;    /* For tlb_finish_mmu */
-        int tlb_start_valid = 0;
         unsigned long start = start_addr;
-        spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
-        int fullmm = (*tlbp)->fullmm;
         struct mm_struct *mm = vma->vm_mm;
 
         mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
@@ -1152,11 +1346,6 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                         untrack_pfn_vma(vma, 0, 0);
 
                 while (start != end) {
-                        if (!tlb_start_valid) {
-                                tlb_start = start;
-                                tlb_start_valid = 1;
-                        }
-
                         if (unlikely(is_vm_hugetlb_page(vma))) {
                                 /*
                                  * It is undesirable to test vma->vm_file as it
@@ -1169,39 +1358,15 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                                  * Since no pte has actually been setup, it is
                                  * safe to do nothing in this case.
                                  */
-                                if (vma->vm_file) {
+                                if (vma->vm_file)
                                         unmap_hugepage_range(vma, start, end, NULL);
-                                        zap_work -= (end - start) /
-                                        pages_per_huge_page(hstate_vma(vma));
-                                }
 
                                 start = end;
                         } else
-                                start = unmap_page_range(*tlbp, vma,
-                                                start, end, &zap_work, details);
-
-                        if (zap_work > 0) {
-                                BUG_ON(start != end);
-                                break;
-                        }
-
-                        tlb_finish_mmu(*tlbp, tlb_start, start);
-
-                        if (need_resched() ||
-                                (i_mmap_lock && spin_needbreak(i_mmap_lock))) {
-                                if (i_mmap_lock) {
-                                        *tlbp = NULL;
-                                        goto out;
-                                }
-                                cond_resched();
-                        }
-
-                        *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
-                        tlb_start_valid = 0;
-                        zap_work = ZAP_BLOCK_SIZE;
+                                start = unmap_page_range(tlb, vma, start, end, details);
                 }
         }
-out:
+
         mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
         return start;   /* which is now the end (or restart) address */
 }
@@ -1217,16 +1382,15 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
                 unsigned long size, struct zap_details *details)
 {
         struct mm_struct *mm = vma->vm_mm;
-        struct mmu_gather *tlb;
+        struct mmu_gather tlb;
         unsigned long end = address + size;
         unsigned long nr_accounted = 0;
 
         lru_add_drain();
-        tlb = tlb_gather_mmu(mm, 0);
+        tlb_gather_mmu(&tlb, mm, 0);
         update_hiwater_rss(mm);
         end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
-        if (tlb)
-                tlb_finish_mmu(tlb, address, end);
+        tlb_finish_mmu(&tlb, address, end);
         return end;
 }
 
@@ -2535,96 +2699,11 @@ unwritable_page:
         return ret;
 }
 
-/*
- * Helper functions for unmap_mapping_range().
- *
- * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
- *
- * We have to restart searching the prio_tree whenever we drop the lock,
- * since the iterator is only valid while the lock is held, and anyway
- * a later vma might be split and reinserted earlier while lock dropped.
- *
- * The list of nonlinear vmas could be handled more efficiently, using
- * a placeholder, but handle it in the same way until a need is shown.
- * It is important to search the prio_tree before nonlinear list: a vma
- * may become nonlinear and be shifted from prio_tree to nonlinear list
- * while the lock is dropped; but never shifted from list to prio_tree.
- *
- * In order to make forward progress despite restarting the search,
- * vm_truncate_count is used to mark a vma as now dealt with, so we can
- * quickly skip it next time around.  Since the prio_tree search only
- * shows us those vmas affected by unmapping the range in question, we
- * can't efficiently keep all vmas in step with mapping->truncate_count:
- * so instead reset them all whenever it wraps back to 0 (then go to 1).
- * mapping->truncate_count and vma->vm_truncate_count are protected by
- * i_mmap_lock.
- *
- * In order to make forward progress despite repeatedly restarting some
- * large vma, note the restart_addr from unmap_vmas when it breaks out:
- * and restart from that address when we reach that vma again.  It might
- * have been split or merged, shrunk or extended, but never shifted: so
- * restart_addr remains valid so long as it remains in the vma's range.
- * unmap_mapping_range forces truncate_count to leap over page-aligned
- * values so we can save vma's restart_addr in its truncate_count field.
- */
-#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
-
-static void reset_vma_truncate_counts(struct address_space *mapping)
-{
-        struct vm_area_struct *vma;
-        struct prio_tree_iter iter;
-
-        vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
-                vma->vm_truncate_count = 0;
-        list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
-                vma->vm_truncate_count = 0;
-}
-
-static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+static void unmap_mapping_range_vma(struct vm_area_struct *vma,
                 unsigned long start_addr, unsigned long end_addr,
                 struct zap_details *details)
 {
-        unsigned long restart_addr;
-        int need_break;
-
-        /*
-         * files that support invalidating or truncating portions of the
-         * file from under mmaped areas must have their ->fault function
-         * return a locked page (and set VM_FAULT_LOCKED in the return).
-         * This provides synchronisation against concurrent unmapping here.
-         */
-
-again:
-        restart_addr = vma->vm_truncate_count;
-        if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
-                start_addr = restart_addr;
-                if (start_addr >= end_addr) {
-                        /* Top of vma has been split off since last time */
-                        vma->vm_truncate_count = details->truncate_count;
-                        return 0;
-                }
-        }
-
-        restart_addr = zap_page_range(vma, start_addr,
-                                        end_addr - start_addr, details);
-        need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
-
-        if (restart_addr >= end_addr) {
-                /* We have now completed this vma: mark it so */
-                vma->vm_truncate_count = details->truncate_count;
-                if (!need_break)
-                        return 0;
-        } else {
-                /* Note restart_addr in vma's truncate_count field */
-                vma->vm_truncate_count = restart_addr;
-                if (!need_break)
-                        goto again;
-        }
-
-        spin_unlock(details->i_mmap_lock);
-        cond_resched();
-        spin_lock(details->i_mmap_lock);
-        return -EINTR;
+        zap_page_range(vma, start_addr, end_addr - start_addr, details);
 }
 
 static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
@@ -2634,12 +2713,8 @@ static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
         struct prio_tree_iter iter;
         pgoff_t vba, vea, zba, zea;
 
-restart:
         vma_prio_tree_foreach(vma, &iter, root,
                         details->first_index, details->last_index) {
-                /* Skip quickly over those we have already dealt with */
-                if (vma->vm_truncate_count == details->truncate_count)
-                        continue;
 
                 vba = vma->vm_pgoff;
                 vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
@@ -2651,11 +2726,10 @@ restart:
                 if (zea > vea)
                         zea = vea;
 
-                if (unmap_mapping_range_vma(vma,
+                unmap_mapping_range_vma(vma,
                         ((zba - vba) << PAGE_SHIFT) + vma->vm_start,
                         ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
-                                details) < 0)
-                        goto restart;
+                                details);
         }
 }
 
@@ -2670,15 +2744,9 @@ static inline void unmap_mapping_range_list(struct list_head *head,
          * across *all* the pages in each nonlinear VMA, not just the pages
          * whose virtual address lies outside the file truncation point.
          */
-restart:
         list_for_each_entry(vma, head, shared.vm_set.list) {
-                /* Skip quickly over those we have already dealt with */
-                if (vma->vm_truncate_count == details->truncate_count)
-                        continue;
                 details->nonlinear_vma = vma;
-                if (unmap_mapping_range_vma(vma, vma->vm_start,
-                                        vma->vm_end, details) < 0)
-                        goto restart;
+                unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
         }
 }
 
@@ -2717,26 +2785,14 @@ void unmap_mapping_range(struct address_space *mapping,
         details.last_index = hba + hlen - 1;
         if (details.last_index < details.first_index)
                 details.last_index = ULONG_MAX;
-        details.i_mmap_lock = &mapping->i_mmap_lock;
 
-        mutex_lock(&mapping->unmap_mutex);
-        spin_lock(&mapping->i_mmap_lock);
-
-        /* Protect against endless unmapping loops */
-        mapping->truncate_count++;
-        if (unlikely(is_restart_addr(mapping->truncate_count))) {
-                if (mapping->truncate_count == 0)
-                        reset_vma_truncate_counts(mapping);
-                mapping->truncate_count++;
-        }
-        details.truncate_count = mapping->truncate_count;
 
+        mutex_lock(&mapping->i_mmap_mutex);
         if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
                 unmap_mapping_range_tree(&mapping->i_mmap, &details);
         if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
                 unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
-        spin_unlock(&mapping->i_mmap_lock);
-        mutex_unlock(&mapping->unmap_mutex);
+        mutex_unlock(&mapping->i_mmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
@@ -2966,7 +3022,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
                 if (prev && prev->vm_end == address)
                         return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-                expand_stack(vma, address - PAGE_SIZE);
+                expand_downwards(vma, address - PAGE_SIZE);
         }
         if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
                 struct vm_area_struct *next = vma->vm_next;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9ca1d604f7cd..9f646374e32f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -374,10 +374,6 @@ void online_page(struct page *page)
                 totalhigh_pages++;
 #endif
 
-#ifdef CONFIG_FLATMEM
-        max_mapnr = max(pfn, max_mapnr);
-#endif
-
         ClearPageReserved(page);
         init_page_count(page);
         __free_page(page);
@@ -400,7 +396,7 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 }
 
 
-int online_pages(unsigned long pfn, unsigned long nr_pages)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 {
         unsigned long onlined_pages = 0;
         struct zone *zone;
@@ -459,8 +455,9 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
                 zone_pcp_update(zone);
 
         mutex_unlock(&zonelists_mutex);
-        setup_per_zone_wmarks();
-        calculate_zone_inactive_ratio(zone);
+
+        init_per_zone_wmark_min();
+
         if (onlined_pages) {
                 kswapd_run(zone_to_nid(zone));
                 node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
@@ -705,7 +702,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                 if (!pfn_valid(pfn))
                         continue;
                 page = pfn_to_page(pfn);
-                if (!page_count(page))
+                if (!get_page_unless_zero(page))
                         continue;
                 /*
                  * We can skip free pages. And we can only deal with pages on
@@ -713,6 +710,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                  */
                 ret = isolate_lru_page(page);
                 if (!ret) { /* Success */
+                        put_page(page);
                         list_add_tail(&page->lru, &source);
                         move_pages--;
                         inc_zone_page_state(page, NR_ISOLATED_ANON +
@@ -724,6 +722,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                                pfn);
                         dump_page(page);
 #endif
+                        put_page(page);
                         /* Because we don't have big zone->lock. we should
                            check this again here. */
                         if (page_count(page)) {
@@ -795,7 +794,7 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
         return offlined;
 }
 
-static int offline_pages(unsigned long start_pfn,
+static int __ref offline_pages(unsigned long start_pfn,
                   unsigned long end_pfn, unsigned long timeout)
 {
         unsigned long pfn, nr_pages, expire;
@@ -893,8 +892,8 @@ repeat:
         zone->zone_pgdat->node_present_pages -= offlined_pages;
         totalram_pages -= offlined_pages;
 
-        setup_per_zone_wmarks();
-        calculate_zone_inactive_ratio(zone);
+        init_per_zone_wmark_min();
+
         if (!node_present_pages(node)) {
                 node_clear_state(node, N_HIGH_MEMORY);
                 kswapd_stop(node);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 959a8b8c7350..e7fb9d25c54e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -99,7 +99,6 @@
 /* Internal flags */
 #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)    /* Skip checks for continuous vmas */
 #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)          /* Invert check for nodemask */
-#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2)           /* Gather statistics */
 
 static struct kmem_cache *policy_cache;
 static struct kmem_cache *sn_cache;
@@ -457,7 +456,6 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
         },
 };
 
-static void gather_stats(struct page *, void *, int pte_dirty);
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
                                 unsigned long flags);
 
@@ -492,9 +490,7 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
                         continue;
 
-                if (flags & MPOL_MF_STATS)
-                        gather_stats(page, private, pte_dirty(*pte));
-                else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+                if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
                         migrate_page_add(page, private, flags);
                 else
                         break;
@@ -1489,7 +1485,7 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
  * freeing by another task.  It is the caller's responsibility to free the
  * extra reference for shared policies.
  */
-static struct mempolicy *get_vma_policy(struct task_struct *task,
+struct mempolicy *get_vma_policy(struct task_struct *task,
                 struct vm_area_struct *vma, unsigned long addr)
 {
         struct mempolicy *pol = task->mempolicy;
@@ -2529,159 +2525,3 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
         }
         return p - buffer;
 }
-
-struct numa_maps {
-        unsigned long pages;
-        unsigned long anon;
-        unsigned long active;
-        unsigned long writeback;
-        unsigned long mapcount_max;
-        unsigned long dirty;
-        unsigned long swapcache;
-        unsigned long node[MAX_NUMNODES];
-};
-
-static void gather_stats(struct page *page, void *private, int pte_dirty)
-{
-        struct numa_maps *md = private;
-        int count = page_mapcount(page);
-
-        md->pages++;
-        if (pte_dirty || PageDirty(page))
-                md->dirty++;
-
-        if (PageSwapCache(page))
-                md->swapcache++;
-
-        if (PageActive(page) || PageUnevictable(page))
-                md->active++;
-
-        if (PageWriteback(page))
-                md->writeback++;
-
-        if (PageAnon(page))
-                md->anon++;
-
-        if (count > md->mapcount_max)
-                md->mapcount_max = count;
-
-        md->node[page_to_nid(page)]++;
-}
-
-#ifdef CONFIG_HUGETLB_PAGE
-static void check_huge_range(struct vm_area_struct *vma,
-                unsigned long start, unsigned long end,
-                struct numa_maps *md)
-{
-        unsigned long addr;
-        struct page *page;
-        struct hstate *h = hstate_vma(vma);
-        unsigned long sz = huge_page_size(h);
-
-        for (addr = start; addr < end; addr += sz) {
-                pte_t *ptep = huge_pte_offset(vma->vm_mm,
-                                                addr & huge_page_mask(h));
-                pte_t pte;
-
-                if (!ptep)
-                        continue;
-
-                pte = *ptep;
-                if (pte_none(pte))
-                        continue;
-
-                page = pte_page(pte);
-                if (!page)
-                        continue;
-
-                gather_stats(page, md, pte_dirty(*ptep));
-        }
-}
-#else
-static inline void check_huge_range(struct vm_area_struct *vma,
-                unsigned long start, unsigned long end,
-                struct numa_maps *md)
-{
-}
-#endif
-
-/*
- * Display pages allocated per node and memory policy via /proc.
- */
-int show_numa_map(struct seq_file *m, void *v)
-{
-        struct proc_maps_private *priv = m->private;
-        struct vm_area_struct *vma = v;
-        struct numa_maps *md;
-        struct file *file = vma->vm_file;
-        struct mm_struct *mm = vma->vm_mm;
-        struct mempolicy *pol;
-        int n;
-        char buffer[50];
-
-        if (!mm)
-                return 0;
-
-        md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
-        if (!md)
-                return 0;
-
-        pol = get_vma_policy(priv->task, vma, vma->vm_start);
-        mpol_to_str(buffer, sizeof(buffer), pol, 0);
-        mpol_cond_put(pol);
-
-        seq_printf(m, "%08lx %s", vma->vm_start, buffer);
-
-        if (file) {
-                seq_printf(m, " file=");
-                seq_path(m, &file->f_path, "\n\t= ");
-        } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
-                seq_printf(m, " heap");
-        } else if (vma->vm_start <= mm->start_stack &&
-                        vma->vm_end >= mm->start_stack) {
-                seq_printf(m, " stack");
-        }
-
-        if (is_vm_hugetlb_page(vma)) {
-                check_huge_range(vma, vma->vm_start, vma->vm_end, md);
-                seq_printf(m, " huge");
-        } else {
-                check_pgd_range(vma, vma->vm_start, vma->vm_end,
-                        &node_states[N_HIGH_MEMORY], MPOL_MF_STATS, md);
-        }
-
-        if (!md->pages)
-                goto out;
-
-        if (md->anon)
-                seq_printf(m," anon=%lu",md->anon);
-
-        if (md->dirty)
-                seq_printf(m," dirty=%lu",md->dirty);
-
-        if (md->pages != md->anon && md->pages != md->dirty)
-                seq_printf(m, " mapped=%lu", md->pages);
-
-        if (md->mapcount_max > 1)
-                seq_printf(m, " mapmax=%lu", md->mapcount_max);
-
-        if (md->swapcache)
-                seq_printf(m," swapcache=%lu", md->swapcache);
-
-        if (md->active < md->pages && !is_vm_hugetlb_page(vma))
-                seq_printf(m," active=%lu", md->active);
-
-        if (md->writeback)
-                seq_printf(m," writeback=%lu", md->writeback);
-
-        for_each_node_state(n, N_HIGH_MEMORY)
-                if (md->node[n])
-                        seq_printf(m, " N%d=%lu", n, md->node[n]);
-out:
-        seq_putc(m, '\n');
-        kfree(md);
-
-        if (m->count < m->size)
-                m->version = (vma != priv->tail_vma) ? vma->vm_start : 0;
-        return 0;
-}
diff --git a/mm/migrate.c b/mm/migrate.c
index 34132f8e9109..e4a5c912983d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -721,15 +721,11 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
                  * Only page_lock_anon_vma() understands the subtleties of
                  * getting a hold on an anon_vma from outside one of its mms.
                  */
-                anon_vma = page_lock_anon_vma(page);
+                anon_vma = page_get_anon_vma(page);
                 if (anon_vma) {
                         /*
-                         * Take a reference count on the anon_vma if the
-                         * page is mapped so that it is guaranteed to
-                         * exist when the page is remapped later
+                         * Anon page
                          */
-                        get_anon_vma(anon_vma);
-                        page_unlock_anon_vma(anon_vma);
                 } else if (PageSwapCache(page)) {
                         /*
                          * We cannot be sure that the anon_vma of an unmapped
@@ -857,13 +853,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
                 lock_page(hpage);
         }
 
-        if (PageAnon(hpage)) {
-                anon_vma = page_lock_anon_vma(hpage);
-                if (anon_vma) {
-                        get_anon_vma(anon_vma);
-                        page_unlock_anon_vma(anon_vma);
-                }
-        }
+        if (PageAnon(hpage))
+                anon_vma = page_get_anon_vma(hpage);
 
         try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 772140c53ab1..ac2631b7477f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -84,10 +84,14 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags)
 }
 EXPORT_SYMBOL(vm_get_page_prot);
 
-int sysctl_overcommit_memory = OVERCOMMIT_GUESS;  /* heuristic overcommit */
-int sysctl_overcommit_ratio = 50;       /* default is 50% */
+int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
+int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
-struct percpu_counter vm_committed_as;
+/*
+ * Make sure vm_committed_as in one cacheline and not cacheline shared with
+ * other variables. It can be updated by several CPUs frequently.
+ */
+struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
 
 /*
  * Check that a process has enough memory to allocate a new virtual
@@ -190,7 +194,7 @@ error:
 }
 
 /*
- * Requires inode->i_mapping->i_mmap_lock
+ * Requires inode->i_mapping->i_mmap_mutex
  */
 static void __remove_shared_vm_struct(struct vm_area_struct *vma,
                 struct file *file, struct address_space *mapping)
@@ -218,9 +222,9 @@ void unlink_file_vma(struct vm_area_struct *vma)
 
         if (file) {
                 struct address_space *mapping = file->f_mapping;
-                spin_lock(&mapping->i_mmap_lock);
+                mutex_lock(&mapping->i_mmap_mutex);
                 __remove_shared_vm_struct(vma, file, mapping);
-                spin_unlock(&mapping->i_mmap_lock);
+                mutex_unlock(&mapping->i_mmap_mutex);
         }
 }
 
@@ -394,29 +398,6 @@ find_vma_prepare(struct mm_struct *mm, unsigned long addr,
         return vma;
 }
 
-static inline void
-__vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
-                struct vm_area_struct *prev, struct rb_node *rb_parent)
-{
-        struct vm_area_struct *next;
-
-        vma->vm_prev = prev;
-        if (prev) {
-                next = prev->vm_next;
-                prev->vm_next = vma;
-        } else {
-                mm->mmap = vma;
-                if (rb_parent)
-                        next = rb_entry(rb_parent,
-                                        struct vm_area_struct, vm_rb);
-                else
-                        next = NULL;
-        }
-        vma->vm_next = next;
-        if (next)
-                next->vm_prev = vma;
-}
-
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
                 struct rb_node **rb_link, struct rb_node *rb_parent)
 {
@@ -464,16 +445,14 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
         if (vma->vm_file)
                 mapping = vma->vm_file->f_mapping;
 
-        if (mapping) {
-                spin_lock(&mapping->i_mmap_lock);
-                vma->vm_truncate_count = mapping->truncate_count;
-        }
+        if (mapping)
+                mutex_lock(&mapping->i_mmap_mutex);
 
         __vma_link(mm, vma, prev, rb_link, rb_parent);
         __vma_link_file(vma);
 
         if (mapping)
-                spin_unlock(&mapping->i_mmap_lock);
+                mutex_unlock(&mapping->i_mmap_mutex);
 
         mm->map_count++;
         validate_mm(mm);
@@ -576,17 +555,8 @@ again:			remove_next = 1 + (end > next->vm_end);
                 mapping = file->f_mapping;
                 if (!(vma->vm_flags & VM_NONLINEAR))
                         root = &mapping->i_mmap;
-                spin_lock(&mapping->i_mmap_lock);
-                if (importer &&
-                    vma->vm_truncate_count != next->vm_truncate_count) {
-                        /*
-                         * unmap_mapping_range might be in progress:
-                         * ensure that the expanding vma is rescanned.
-                         */
-                        importer->vm_truncate_count = 0;
-                }
+                mutex_lock(&mapping->i_mmap_mutex);
                 if (insert) {
-                        insert->vm_truncate_count = vma->vm_truncate_count;
                         /*
                          * Put into prio_tree now, so instantiated pages
                          * are visible to arm/parisc __flush_dcache_page
@@ -605,7 +575,7 @@ again:			remove_next = 1 + (end > next->vm_end);
          * lock may be shared between many sibling processes.  Skipping
          * the lock for brk adjustments makes a difference sometimes.
          */
-        if (vma->anon_vma && (insert || importer || start != vma->vm_start)) {
+        if (vma->anon_vma && (importer || start != vma->vm_start)) {
                 anon_vma = vma->anon_vma;
                 anon_vma_lock(anon_vma);
         }
@@ -652,7 +622,7 @@ again:			remove_next = 1 + (end > next->vm_end);
         if (anon_vma)
                 anon_vma_unlock(anon_vma);
         if (mapping)
-                spin_unlock(&mapping->i_mmap_lock);
+                mutex_unlock(&mapping->i_mmap_mutex);
 
         if (remove_next) {
                 if (file) {
@@ -699,9 +669,17 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
 }
 
 static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
-                                        struct anon_vma *anon_vma2)
+                                        struct anon_vma *anon_vma2,
+                                        struct vm_area_struct *vma)
 {
-        return !anon_vma1 || !anon_vma2 || (anon_vma1 == anon_vma2);
+        /*
+         * The list_is_singular() test is to avoid merging VMA cloned from
+         * parents. This can improve scalability caused by anon_vma lock.
+         */
+        if ((!anon_vma1 || !anon_vma2) && (!vma ||
+                list_is_singular(&vma->anon_vma_chain)))
+                return 1;
+        return anon_vma1 == anon_vma2;
 }
 
 /*
@@ -720,7 +698,7 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
         struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
 {
         if (is_mergeable_vma(vma, file, vm_flags) &&
-            is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
+            is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
                 if (vma->vm_pgoff == vm_pgoff)
                         return 1;
         }
@@ -739,7 +717,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
         struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
 {
         if (is_mergeable_vma(vma, file, vm_flags) &&
-            is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
+            is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
                 pgoff_t vm_pglen;
                 vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
                 if (vma->vm_pgoff + vm_pglen == vm_pgoff)
@@ -817,7 +795,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
                                 can_vma_merge_before(next, vm_flags,
                                         anon_vma, file, pgoff+pglen) &&
                                 is_mergeable_anon_vma(prev->anon_vma,
-                                                      next->anon_vma)) {
+                                                      next->anon_vma, NULL)) {
                                                         /* cases 1, 6 */
                         err = vma_adjust(prev, prev->vm_start,
                                 next->vm_end, prev->vm_pgoff, NULL);
@@ -1785,7 +1763,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 /*
  * vma is the first one with address < vma->vm_start.  Have to extend vma.
  */
-static int expand_downwards(struct vm_area_struct *vma,
+int expand_downwards(struct vm_area_struct *vma,
                                    unsigned long address)
 {
         int error;
@@ -1832,11 +1810,6 @@ static int expand_downwards(struct vm_area_struct *vma,
         return error;
 }
 
-int expand_stack_downwards(struct vm_area_struct *vma, unsigned long address)
-{
-        return expand_downwards(vma, address);
-}
-
 #ifdef CONFIG_STACK_GROWSUP
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
@@ -1919,17 +1892,17 @@ static void unmap_region(struct mm_struct *mm,
                 unsigned long start, unsigned long end)
 {
         struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
-        struct mmu_gather *tlb;
+        struct mmu_gather tlb;
         unsigned long nr_accounted = 0;
 
         lru_add_drain();
-        tlb = tlb_gather_mmu(mm, 0);
+        tlb_gather_mmu(&tlb, mm, 0);
         update_hiwater_rss(mm);
         unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
         vm_unacct_memory(nr_accounted);
-        free_pgtables(tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
-                                 next? next->vm_start: 0);
-        tlb_finish_mmu(tlb, start, end);
+        free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
+                                 next ? next->vm_start : 0);
+        tlb_finish_mmu(&tlb, start, end);
 }
 
 /*
@@ -2271,7 +2244,7 @@ EXPORT_SYMBOL(do_brk);
 /* Release all mmaps. */
 void exit_mmap(struct mm_struct *mm)
 {
-        struct mmu_gather *tlb;
+        struct mmu_gather tlb;
         struct vm_area_struct *vma;
         unsigned long nr_accounted = 0;
         unsigned long end;
@@ -2296,14 +2269,14 @@ void exit_mmap(struct mm_struct *mm)
 
         lru_add_drain();
         flush_cache_mm(mm);
-        tlb = tlb_gather_mmu(mm, 1);
+        tlb_gather_mmu(&tlb, mm, 1);
         /* update_hiwater_rss(mm) here? but nobody should be looking */
         /* Use -1 here to ensure all VMAs in the mm are unmapped */
         end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
         vm_unacct_memory(nr_accounted);
 
-        free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0);
-        tlb_finish_mmu(tlb, 0, end);
+        free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
+        tlb_finish_mmu(&tlb, 0, end);
 
         /*
          * Walk the list again, actually closing and freeing it,
@@ -2317,7 +2290,7 @@ void exit_mmap(struct mm_struct *mm)
 
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL
- * then i_mmap_lock is taken here.
+ * then i_mmap_mutex is taken here.
  */
 int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
 {
@@ -2529,15 +2502,15 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
                  * The LSB of head.next can't change from under us
                  * because we hold the mm_all_locks_mutex.
                  */
-                spin_lock_nest_lock(&anon_vma->root->lock, &mm->mmap_sem);
+                mutex_lock_nest_lock(&anon_vma->root->mutex, &mm->mmap_sem);
                 /*
                  * We can safely modify head.next after taking the
-                 * anon_vma->root->lock. If some other vma in this mm shares
+                 * anon_vma->root->mutex. If some other vma in this mm shares
                  * the same anon_vma we won't take it again.
                  *
                  * No need of atomic instructions here, head.next
                  * can't change from under us thanks to the
-                 * anon_vma->root->lock.
+                 * anon_vma->root->mutex.
                  */
                 if (__test_and_set_bit(0, (unsigned long *)
                                        &anon_vma->root->head.next))
@@ -2559,7 +2532,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
                  */
                 if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
                         BUG();
-                spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
+                mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem);
         }
 }
 
@@ -2586,7 +2559,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_lock or anon_vma->lock outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
@@ -2642,7 +2615,7 @@ static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
                  *
                  * No need of atomic instructions here, head.next
                  * can't change from under us until we release the
-                 * anon_vma->root->lock.
+                 * anon_vma->root->mutex.
                  */
                 if (!__test_and_clear_bit(0, (unsigned long *)
                                           &anon_vma->root->head.next))
@@ -2658,7 +2631,7 @@ static void vm_unlock_mapping(struct address_space *mapping)
                  * AS_MM_ALL_LOCKS can't change to 0 from under us
                  * because we hold the mm_all_locks_mutex.
                  */
-                spin_unlock(&mapping->i_mmap_lock);
+                mutex_unlock(&mapping->i_mmap_mutex);
                 if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
                                         &mapping->flags))
                         BUG();
diff --git a/mm/mremap.c b/mm/mremap.c
index a7c1f9f9b941..506fa44403df 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -93,8 +93,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
                  * and we propagate stale pages into the dst afterward.
                  */
                 mapping = vma->vm_file->f_mapping;
-                spin_lock(&mapping->i_mmap_lock);
-                new_vma->vm_truncate_count = 0;
+                mutex_lock(&mapping->i_mmap_mutex);
         }
 
         /*
@@ -123,7 +122,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
         pte_unmap(new_pte - 1);
         pte_unmap_unlock(old_pte - 1, old_ptl);
         if (mapping)
-                spin_unlock(&mapping->i_mmap_lock);
+                mutex_unlock(&mapping->i_mmap_mutex);
         mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
 }
 
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 9109049f0bbc..6e93dc7f2586 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -307,30 +307,7 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
                                    unsigned long align, unsigned long goal)
 {
-#ifdef MAX_DMA32_PFN
-        unsigned long end_pfn;
-
-        if (WARN_ON_ONCE(slab_is_available()))
-                return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
-
-        /* update goal according ...MAX_DMA32_PFN */
-        end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages;
-
-        if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
-            (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
-                void *ptr;
-                unsigned long new_goal;
-
-                new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
-                ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
-                                                 new_goal, -1ULL);
-                if (ptr)
-                        return ptr;
-        }
-#endif
-
         return __alloc_bootmem_node(pgdat, size, align, goal);
-
 }
 
 #ifdef CONFIG_SPARSEMEM
diff --git a/mm/nommu.c b/mm/nommu.c
index c4c542c736a9..1fd0c51b10a6 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -680,9 +680,9 @@ static void protect_vma(struct vm_area_struct *vma, unsigned long flags)
  */
 static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-        struct vm_area_struct *pvma, **pp, *next;
+        struct vm_area_struct *pvma, *prev;
         struct address_space *mapping;
-        struct rb_node **p, *parent;
+        struct rb_node **p, *parent, *rb_prev;
 
         kenter(",%p", vma);
 
@@ -703,7 +703,7 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
         }
 
         /* add the VMA to the tree */
-        parent = NULL;
+        parent = rb_prev = NULL;
         p = &mm->mm_rb.rb_node;
         while (*p) {
                 parent = *p;
@@ -713,17 +713,20 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
                  * (the latter is necessary as we may get identical VMAs) */
                 if (vma->vm_start < pvma->vm_start)
                         p = &(*p)->rb_left;
-                else if (vma->vm_start > pvma->vm_start)
+                else if (vma->vm_start > pvma->vm_start) {
+                        rb_prev = parent;
                         p = &(*p)->rb_right;
-                else if (vma->vm_end < pvma->vm_end)
+                } else if (vma->vm_end < pvma->vm_end)
                         p = &(*p)->rb_left;
-                else if (vma->vm_end > pvma->vm_end)
+                else if (vma->vm_end > pvma->vm_end) {
+                        rb_prev = parent;
                         p = &(*p)->rb_right;
-                else if (vma < pvma)
+                } else if (vma < pvma)
                         p = &(*p)->rb_left;
-                else if (vma > pvma)
+                else if (vma > pvma) {
+                        rb_prev = parent;
                         p = &(*p)->rb_right;
-                else
+                } else
                         BUG();
         }
 
@@ -731,20 +734,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
         rb_insert_color(&vma->vm_rb, &mm->mm_rb);
 
         /* add VMA to the VMA list also */
-        for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) {
-                if (pvma->vm_start > vma->vm_start)
-                        break;
-                if (pvma->vm_start < vma->vm_start)
-                        continue;
-                if (pvma->vm_end < vma->vm_end)
-                        break;
-        }
+        prev = NULL;
+        if (rb_prev)
+                prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
 
-        next = *pp;
-        *pp = vma;
-        vma->vm_next = next;
-        if (next)
-                next->vm_prev = vma;
+        __vma_link_list(mm, vma, prev, parent);
 }
 
 /*
@@ -752,7 +746,6 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
  */
 static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
-        struct vm_area_struct **pp;
         struct address_space *mapping;
         struct mm_struct *mm = vma->vm_mm;
 
@@ -775,12 +768,14 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 
         /* remove from the MM's tree and list */
         rb_erase(&vma->vm_rb, &mm->mm_rb);
-        for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) {
-                if (*pp == vma) {
-                        *pp = vma->vm_next;
-                        break;
-                }
-        }
+
+        if (vma->vm_prev)
+                vma->vm_prev->vm_next = vma->vm_next;
+        else
+                mm->mmap = vma->vm_next;
+
+        if (vma->vm_next)
+                vma->vm_next->vm_prev = vma->vm_prev;
 
         vma->vm_mm = NULL;
 }
@@ -809,17 +804,15 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
         struct vm_area_struct *vma;
-        struct rb_node *n = mm->mm_rb.rb_node;
 
         /* check the cache first */
         vma = mm->mmap_cache;
         if (vma && vma->vm_start <= addr && vma->vm_end > addr)
                 return vma;
 
-        /* trawl the tree (there may be multiple mappings in which addr
+        /* trawl the list (there may be multiple mappings in which addr
          * resides) */
-        for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
-                vma = rb_entry(n, struct vm_area_struct, vm_rb);
+        for (vma = mm->mmap; vma; vma = vma->vm_next) {
                 if (vma->vm_start > addr)
                         return NULL;
                 if (vma->vm_end > addr) {
@@ -859,7 +852,6 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
                                              unsigned long len)
 {
         struct vm_area_struct *vma;
-        struct rb_node *n = mm->mm_rb.rb_node;
         unsigned long end = addr + len;
 
         /* check the cache first */
@@ -867,10 +859,9 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
         if (vma && vma->vm_start == addr && vma->vm_end == end)
                 return vma;
 
-        /* trawl the tree (there may be multiple mappings in which addr
+        /* trawl the list (there may be multiple mappings in which addr
          * resides) */
-        for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
-                vma = rb_entry(n, struct vm_area_struct, vm_rb);
+        for (vma = mm->mmap; vma; vma = vma->vm_next) {
                 if (vma->vm_start < addr)
                         continue;
                 if (vma->vm_start > addr)
@@ -1133,7 +1124,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
                            unsigned long capabilities)
 {
         struct page *pages;
-        unsigned long total, point, n, rlen;
+        unsigned long total, point, n;
         void *base;
         int ret, order;
 
@@ -1157,13 +1148,12 @@ static int do_mmap_private(struct vm_area_struct *vma,
                  * make a private copy of the data and map that instead */
         }
 
-        rlen = PAGE_ALIGN(len);
 
         /* allocate some memory to hold the mapping
          * - note that this may not return a page-aligned address if the object
          *   we're allocating is smaller than a page
          */
-        order = get_order(rlen);
+        order = get_order(len);
         kdebug("alloc order %d for %lx", order, len);
 
         pages = alloc_pages(GFP_KERNEL, order);
@@ -1173,7 +1163,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
         total = 1 << order;
         atomic_long_add(total, &mmap_pages_allocated);
 
-        point = rlen >> PAGE_SHIFT;
+        point = len >> PAGE_SHIFT;
 
         /* we allocated a power-of-2 sized page set, so we may want to trim off
          * the excess */
@@ -1195,7 +1185,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
         base = page_address(pages);
         region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY;
         region->vm_start = (unsigned long) base;
-        region->vm_end   = region->vm_start + rlen;
+        region->vm_end   = region->vm_start + len;
         region->vm_top   = region->vm_start + (total << PAGE_SHIFT);
 
         vma->vm_start = region->vm_start;
@@ -1211,22 +1201,22 @@ static int do_mmap_private(struct vm_area_struct *vma,
 
                 old_fs = get_fs();
                 set_fs(KERNEL_DS);
-                ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos);
+                ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos);
                 set_fs(old_fs);
 
                 if (ret < 0)
                         goto error_free;
 
                 /* clear the last little bit */
-                if (ret < rlen)
-                        memset(base + ret, 0, rlen - ret);
+                if (ret < len)
+                        memset(base + ret, 0, len - ret);
 
         }
 
         return 0;
 
 error_free:
-        free_page_series(region->vm_start, region->vm_end);
+        free_page_series(region->vm_start, region->vm_top);
         region->vm_start = vma->vm_start = 0;
         region->vm_end   = vma->vm_end = 0;
         region->vm_top   = 0;
@@ -1235,7 +1225,7 @@ error_free:
 enomem:
         printk("Allocation of length %lu from process %d (%s) failed\n",
                len, current->pid, current->comm);
-        show_free_areas();
+        show_free_areas(0);
         return -ENOMEM;
 }
 
@@ -1268,6 +1258,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 
         /* we ignore the address hint */
         addr = 0;
+        len = PAGE_ALIGN(len);
 
         /* we've determined that we can make the mapping, now translate what we
          * now know into VMA flags */
@@ -1385,15 +1376,15 @@ unsigned long do_mmap_pgoff(struct file *file,
                 if (capabilities & BDI_CAP_MAP_DIRECT) {
                         addr = file->f_op->get_unmapped_area(file, addr, len,
                                                              pgoff, flags);
-                        if (IS_ERR((void *) addr)) {
+                        if (IS_ERR_VALUE(addr)) {
                                 ret = addr;
-                                if (ret != (unsigned long) -ENOSYS)
+                                if (ret != -ENOSYS)
                                         goto error_just_free;
 
                                 /* the driver refused to tell us where to site
                                  * the mapping so we'll have to attempt to copy
                                  * it */
-                                ret = (unsigned long) -ENODEV;
+                                ret = -ENODEV;
                                 if (!(capabilities & BDI_CAP_MAP_COPY))
                                         goto error_just_free;
 
@@ -1468,14 +1459,14 @@ error_getting_vma:
         printk(KERN_WARNING "Allocation of vma for %lu byte allocation"
                " from process %d failed\n",
                len, current->pid);
-        show_free_areas();
+        show_free_areas(0);
         return -ENOMEM;
 
 error_getting_region:
         printk(KERN_WARNING "Allocation of vm region for %lu byte allocation"
                " from process %d failed\n",
                len, current->pid);
-        show_free_areas();
+        show_free_areas(0);
         return -ENOMEM;
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
@@ -1644,15 +1635,17 @@ static int shrink_vma(struct mm_struct *mm,
 int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 {
         struct vm_area_struct *vma;
-        struct rb_node *rb;
-        unsigned long end = start + len;
+        unsigned long end;
         int ret;
 
         kenter(",%lx,%zx", start, len);
 
+        len = PAGE_ALIGN(len);
         if (len == 0)
                 return -EINVAL;
 
+        end = start + len;
+
         /* find the first potentially overlapping VMA */
         vma = find_vma(mm, start);
         if (!vma) {
@@ -1677,9 +1670,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
                         }
                         if (end == vma->vm_end)
                                 goto erase_whole_vma;
-                        rb = rb_next(&vma->vm_rb);
-                        vma = rb_entry(rb, struct vm_area_struct, vm_rb);
-                } while (rb);
+                        vma = vma->vm_next;
+                } while (vma);
                 kleave(" = -EINVAL [split file]");
                 return -EINVAL;
         } else {
@@ -1773,6 +1765,8 @@ unsigned long do_mremap(unsigned long addr,
         struct vm_area_struct *vma;
 
         /* insanity checks first */
+        old_len = PAGE_ALIGN(old_len);
+        new_len = PAGE_ALIGN(new_len);
         if (old_len == 0 || new_len == 0)
                 return (unsigned long) -EINVAL;
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f52e85c80e8d..e4b0991ca351 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -38,6 +38,33 @@ int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
 
+/**
+ * test_set_oom_score_adj() - set current's oom_score_adj and return old value
+ * @new_val: new oom_score_adj value
+ *
+ * Sets the oom_score_adj value for current to @new_val with proper
+ * synchronization and returns the old value.  Usually used to temporarily
+ * set a value, save the old value in the caller, and then reinstate it later.
+ */
+int test_set_oom_score_adj(int new_val)
+{
+        struct sighand_struct *sighand = current->sighand;
+        int old_val;
+
+        spin_lock_irq(&sighand->siglock);
+        old_val = current->signal->oom_score_adj;
+        if (new_val != old_val) {
+                if (new_val == OOM_SCORE_ADJ_MIN)
+                        atomic_inc(&current->mm->oom_disable_count);
+                else if (old_val == OOM_SCORE_ADJ_MIN)
+                        atomic_dec(&current->mm->oom_disable_count);
+                current->signal->oom_score_adj = new_val;
+        }
+        spin_unlock_irq(&sighand->siglock);
+
+        return old_val;
+}
+
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
@@ -155,15 +182,6 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
         }
 
         /*
-         * When the PF_OOM_ORIGIN bit is set, it indicates the task should have
-         * priority for oom killing.
-         */
-        if (p->flags & PF_OOM_ORIGIN) {
-                task_unlock(p);
-                return 1000;
-        }
-
-        /*
          * The memory controller may have a limit of 0 bytes, so avoid a divide
          * by zero, if necessary.
          */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9d5498e2d0f5..2a00f17c3bf4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -30,6 +30,7 @@
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
+#include <linux/ratelimit.h>
 #include <linux/oom.h>
 #include <linux/notifier.h>
 #include <linux/topology.h>
@@ -39,6 +40,7 @@
 #include <linux/memory_hotplug.h>
 #include <linux/nodemask.h>
 #include <linux/vmalloc.h>
+#include <linux/vmstat.h>
 #include <linux/mempolicy.h>
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
@@ -1735,6 +1737,45 @@ static inline bool should_suppress_show_mem(void)
         return ret;
 }
 
+static DEFINE_RATELIMIT_STATE(nopage_rs,
+                DEFAULT_RATELIMIT_INTERVAL,
+                DEFAULT_RATELIMIT_BURST);
+
+void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
+{
+        va_list args;
+        unsigned int filter = SHOW_MEM_FILTER_NODES;
+
+        if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+                return;
+
+        /*
+         * This documents exceptions given to allocations in certain
+         * contexts that are allowed to allocate outside current's set
+         * of allowed nodes.
+         */
+        if (!(gfp_mask & __GFP_NOMEMALLOC))
+                if (test_thread_flag(TIF_MEMDIE) ||
+                    (current->flags & (PF_MEMALLOC | PF_EXITING)))
+                        filter &= ~SHOW_MEM_FILTER_NODES;
+        if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+                filter &= ~SHOW_MEM_FILTER_NODES;
+
+        if (fmt) {
+                printk(KERN_WARNING);
+                va_start(args, fmt);
+                vprintk(fmt, args);
+                va_end(args);
+        }
+
+        pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n",
+                   current->comm, order, gfp_mask);
+
+        dump_stack();
+        if (!should_suppress_show_mem())
+                show_mem(filter);
+}
+
 static inline int
 should_alloc_retry(gfp_t gfp_mask, unsigned int order,
                                 unsigned long pages_reclaimed)
@@ -2065,6 +2106,7 @@ restart:
                 first_zones_zonelist(zonelist, high_zoneidx, NULL,
                                         &preferred_zone);
 
+rebalance:
         /* This is the last chance, in general, before the goto nopage. */
         page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
                         high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2072,7 +2114,6 @@ restart:
         if (page)
                 goto got_pg;
 
-rebalance:
         /* Allocate without watermarks if the context allows */
         if (alloc_flags & ALLOC_NO_WATERMARKS) {
                 page = __alloc_pages_high_priority(gfp_mask, order,
@@ -2106,7 +2147,7 @@ rebalance:
                                         sync_migration);
         if (page)
                 goto got_pg;
-        sync_migration = !(gfp_mask & __GFP_NO_KSWAPD);
+        sync_migration = true;
 
         /* Try direct reclaim and then allocating */
         page = __alloc_pages_direct_reclaim(gfp_mask, order,
@@ -2177,27 +2218,7 @@ rebalance:
         }
 
 nopage:
-        if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
-                unsigned int filter = SHOW_MEM_FILTER_NODES;
-
-                /*
-                 * This documents exceptions given to allocations in certain
-                 * contexts that are allowed to allocate outside current's set
-                 * of allowed nodes.
-                 */
-                if (!(gfp_mask & __GFP_NOMEMALLOC))
-                        if (test_thread_flag(TIF_MEMDIE) ||
-                            (current->flags & (PF_MEMALLOC | PF_EXITING)))
-                                filter &= ~SHOW_MEM_FILTER_NODES;
-                if (in_interrupt() || !wait)
-                        filter &= ~SHOW_MEM_FILTER_NODES;
-
-                pr_warning("%s: page allocation failure. order:%d, mode:0x%x\n",
-                        current->comm, order, gfp_mask);
-                dump_stack();
-                if (!should_suppress_show_mem())
-                        show_mem(filter);
-        }
+        warn_alloc_failed(gfp_mask, order, NULL);
         return page;
 got_pg:
         if (kmemcheck_enabled)
@@ -2226,6 +2247,10 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
         if (should_fail_alloc_page(gfp_mask, order))
                 return NULL;
+#ifndef CONFIG_ZONE_DMA
+        if (WARN_ON_ONCE(gfp_mask & __GFP_DMA))
+                return NULL;
+#endif
 
         /*
          * Check the zones suitable for the gfp_mask contain at least one
@@ -2473,10 +2498,10 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 #endif
 
 /*
- * Determine whether the zone's node should be displayed or not, depending on
- * whether SHOW_MEM_FILTER_NODES was passed to __show_free_areas().
+ * Determine whether the node should be displayed or not, depending on whether
+ * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
  */
-static bool skip_free_areas_zone(unsigned int flags, const struct zone *zone)
+bool skip_free_areas_node(unsigned int flags, int nid)
 {
         bool ret = false;
 
@@ -2484,8 +2509,7 @@ static bool skip_free_areas_zone(unsigned int flags, const struct zone *zone)
                 goto out;
 
         get_mems_allowed();
-        ret = !node_isset(zone->zone_pgdat->node_id,
-                                cpuset_current_mems_allowed);
+        ret = !node_isset(nid, cpuset_current_mems_allowed);
         put_mems_allowed();
 out:
         return ret;
@@ -2500,13 +2524,13 @@ out:
  * Suppresses nodes that are not allowed by current's cpuset if
  * SHOW_MEM_FILTER_NODES is passed.
  */
-void __show_free_areas(unsigned int filter)
+void show_free_areas(unsigned int filter)
 {
         int cpu;
         struct zone *zone;
 
         for_each_populated_zone(zone) {
-                if (skip_free_areas_zone(filter, zone))
+                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                         continue;
                 show_node(zone);
                 printk("%s per-cpu:\n", zone->name);
@@ -2549,7 +2573,7 @@ void __show_free_areas(unsigned int filter)
         for_each_populated_zone(zone) {
                 int i;
 
-                if (skip_free_areas_zone(filter, zone))
+                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                         continue;
                 show_node(zone);
                 printk("%s"
@@ -2618,7 +2642,7 @@ void __show_free_areas(unsigned int filter)
         for_each_populated_zone(zone) {
                 unsigned long nr[MAX_ORDER], flags, order, total = 0;
 
-                if (skip_free_areas_zone(filter, zone))
+                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                         continue;
                 show_node(zone);
                 printk("%s: ", zone->name);
@@ -2639,11 +2663,6 @@ void __show_free_areas(unsigned int filter)
         show_swap_cache_info();
 }
 
-void show_free_areas(void)
-{
-        __show_free_areas(0);
-}
-
 static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
 {
         zoneref->zone = zone;
@@ -3314,6 +3333,20 @@ static inline unsigned long wait_table_bits(unsigned long size)
 #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
 
 /*
+ * Check if a pageblock contains reserved pages
+ */
+static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn)
+{
+        unsigned long pfn;
+
+        for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+                if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn)))
+                        return 1;
+        }
+        return 0;
+}
+
+/*
  * Mark a number of pageblocks as MIGRATE_RESERVE. The number
  * of blocks reserved is based on min_wmark_pages(zone). The memory within
  * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
@@ -3322,7 +3355,7 @@ static inline unsigned long wait_table_bits(unsigned long size)
  */
 static void setup_zone_migrate_reserve(struct zone *zone)
 {
-        unsigned long start_pfn, pfn, end_pfn;
+        unsigned long start_pfn, pfn, end_pfn, block_end_pfn;
         struct page *page;
         unsigned long block_migratetype;
         int reserve;
@@ -3352,7 +3385,8 @@ static void setup_zone_migrate_reserve(struct zone *zone)
                         continue;
 
                 /* Blocks with reserved pages will never free, skip them. */
-                if (PageReserved(page))
+                block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+                if (pageblock_is_reserved(pfn, block_end_pfn))
                         continue;
 
                 block_migratetype = get_pageblock_migratetype(page);
@@ -5100,7 +5134,7 @@ void setup_per_zone_wmarks(void)
  *    1TB     101        10GB
  *   10TB     320        32GB
  */
-void calculate_zone_inactive_ratio(struct zone *zone)
+static void __meminit calculate_zone_inactive_ratio(struct zone *zone)
 {
         unsigned int gb, ratio;
 
@@ -5114,7 +5148,7 @@ void calculate_zone_inactive_ratio(struct zone *zone)
         zone->inactive_ratio = ratio;
 }
 
-static void __init setup_per_zone_inactive_ratio(void)
+static void __meminit setup_per_zone_inactive_ratio(void)
 {
         struct zone *zone;
 
@@ -5146,7 +5180,7 @@ static void __init setup_per_zone_inactive_ratio(void)
  * 8192MB:      11584k
  * 16384MB:     16384k
  */
-static int __init init_per_zone_wmark_min(void)
+int __meminit init_per_zone_wmark_min(void)
 {
         unsigned long lowmem_kbytes;
 
@@ -5158,6 +5192,7 @@ static int __init init_per_zone_wmark_min(void)
         if (min_free_kbytes > 65536)
                 min_free_kbytes = 65536;
         setup_per_zone_wmarks();
+        refresh_zone_stat_thresholds();
         setup_per_zone_lowmem_reserve();
         setup_per_zone_inactive_ratio();
         return 0;
@@ -5508,10 +5543,8 @@ int set_migratetype_isolate(struct page *page)
         struct memory_isolate_notify arg;
         int notifier_ret;
         int ret = -EBUSY;
-        int zone_idx;
 
         zone = page_zone(page);
-        zone_idx = zone_idx(zone);
 
         spin_lock_irqsave(&zone->lock, flags);
 
diff --git a/mm/readahead.c b/mm/readahead.c
index 2c0cc489e288..867f9dd82dcd 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -180,7 +180,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
                 if (page)
                         continue;
 
-                page = page_cache_alloc_cold(mapping);
+                page = page_cache_alloc_readahead(mapping);
                 if (!page)
                         break;
                 page->index = page_offset;
diff --git a/mm/rmap.c b/mm/rmap.c
index 522e4a93cadd..3a39b518a653 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -24,8 +24,8 @@
  *   inode->i_alloc_sem (vmtruncate_range)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_lock
- *         anon_vma->lock
+ *       mapping->i_mmap_mutex
+ *         anon_vma->mutex
  *           mm->page_table_lock or pte_lock
  *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
  *             swap_lock (in swap_duplicate, swap_info_get)
@@ -40,7 +40,7 @@
  *
  * (code doesn't rely on that order so it could be switched around)
  * ->tasklist_lock
- *   anon_vma->lock      (memory_failure, collect_procs_anon)
+ *   anon_vma->mutex      (memory_failure, collect_procs_anon)
  *     pte map lock
  */
 
@@ -86,6 +86,29 @@ static inline struct anon_vma *anon_vma_alloc(void)
 static inline void anon_vma_free(struct anon_vma *anon_vma)
 {
         VM_BUG_ON(atomic_read(&anon_vma->refcount));
+
+        /*
+         * Synchronize against page_lock_anon_vma() such that
+         * we can safely hold the lock without the anon_vma getting
+         * freed.
+         *
+         * Relies on the full mb implied by the atomic_dec_and_test() from
+         * put_anon_vma() against the acquire barrier implied by
+         * mutex_trylock() from page_lock_anon_vma(). This orders:
+         *
+         * page_lock_anon_vma()         VS      put_anon_vma()
+         *   mutex_trylock()                      atomic_dec_and_test()
+         *   LOCK                                 MB
+         *   atomic_read()                        mutex_is_locked()
+         *
+         * LOCK should suffice since the actual taking of the lock must
+         * happen _before_ what follows.
+         */
+        if (mutex_is_locked(&anon_vma->root->mutex)) {
+                anon_vma_lock(anon_vma);
+                anon_vma_unlock(anon_vma);
+        }
+
         kmem_cache_free(anon_vma_cachep, anon_vma);
 }
 
@@ -307,7 +330,7 @@ static void anon_vma_ctor(void *data)
 {
         struct anon_vma *anon_vma = data;
 
-        spin_lock_init(&anon_vma->lock);
+        mutex_init(&anon_vma->mutex);
         atomic_set(&anon_vma->refcount, 0);
         INIT_LIST_HEAD(&anon_vma->head);
 }
@@ -320,12 +343,26 @@ void __init anon_vma_init(void)
 }
 
 /*
- * Getting a lock on a stable anon_vma from a page off the LRU is
- * tricky: page_lock_anon_vma rely on RCU to guard against the races.
+ * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
+ *
+ * Since there is no serialization what so ever against page_remove_rmap()
+ * the best this function can do is return a locked anon_vma that might
+ * have been relevant to this page.
+ *
+ * The page might have been remapped to a different anon_vma or the anon_vma
+ * returned may already be freed (and even reused).
+ *
+ * All users of this function must be very careful when walking the anon_vma
+ * chain and verify that the page in question is indeed mapped in it
+ * [ something equivalent to page_mapped_in_vma() ].
+ *
+ * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap()
+ * that the anon_vma pointer from page->mapping is valid if there is a
+ * mapcount, we can dereference the anon_vma after observing those.
  */
-struct anon_vma *__page_lock_anon_vma(struct page *page)
+struct anon_vma *page_get_anon_vma(struct page *page)
 {
-        struct anon_vma *anon_vma, *root_anon_vma;
+        struct anon_vma *anon_vma = NULL;
         unsigned long anon_mapping;
 
         rcu_read_lock();
@@ -336,32 +373,97 @@ struct anon_vma *__page_lock_anon_vma(struct page *page)
                 goto out;
 
         anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-        root_anon_vma = ACCESS_ONCE(anon_vma->root);
-        spin_lock(&root_anon_vma->lock);
+        if (!atomic_inc_not_zero(&anon_vma->refcount)) {
+                anon_vma = NULL;
+                goto out;
+        }
 
         /*
          * If this page is still mapped, then its anon_vma cannot have been
-         * freed.  But if it has been unmapped, we have no security against
-         * the anon_vma structure being freed and reused (for another anon_vma:
-         * SLAB_DESTROY_BY_RCU guarantees that - so the spin_lock above cannot
-         * corrupt): with anon_vma_prepare() or anon_vma_fork() redirecting
-         * anon_vma->root before page_unlock_anon_vma() is called to unlock.
+         * freed.  But if it has been unmapped, we have no security against the
+         * anon_vma structure being freed and reused (for another anon_vma:
+         * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero()
+         * above cannot corrupt).
          */
-        if (page_mapped(page))
-                return anon_vma;
+        if (!page_mapped(page)) {
+                put_anon_vma(anon_vma);
+                anon_vma = NULL;
+        }
+out:
+        rcu_read_unlock();
+
+        return anon_vma;
+}
+
+/*
+ * Similar to page_get_anon_vma() except it locks the anon_vma.
+ *
+ * Its a little more complex as it tries to keep the fast path to a single
+ * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
+ * reference like with page_get_anon_vma() and then block on the mutex.
+ */
+struct anon_vma *page_lock_anon_vma(struct page *page)
+{
+        struct anon_vma *anon_vma = NULL;
+        unsigned long anon_mapping;
+
+        rcu_read_lock();
+        anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping);
+        if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
+                goto out;
+        if (!page_mapped(page))
+                goto out;
+
+        anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
+        if (mutex_trylock(&anon_vma->root->mutex)) {
+                /*
+                 * If we observe a !0 refcount, then holding the lock ensures
+                 * the anon_vma will not go away, see __put_anon_vma().
+                 */
+                if (!atomic_read(&anon_vma->refcount)) {
+                        anon_vma_unlock(anon_vma);
+                        anon_vma = NULL;
+                }
+                goto out;
+        }
+
+        /* trylock failed, we got to sleep */
+        if (!atomic_inc_not_zero(&anon_vma->refcount)) {
+                anon_vma = NULL;
+                goto out;
+        }
+
+        if (!page_mapped(page)) {
+                put_anon_vma(anon_vma);
+                anon_vma = NULL;
+                goto out;
+        }
+
+        /* we pinned the anon_vma, its safe to sleep */
+        rcu_read_unlock();
+        anon_vma_lock(anon_vma);
+
+        if (atomic_dec_and_test(&anon_vma->refcount)) {
+                /*
+                 * Oops, we held the last refcount, release the lock
+                 * and bail -- can't simply use put_anon_vma() because
+                 * we'll deadlock on the anon_vma_lock() recursion.
+                 */
+                anon_vma_unlock(anon_vma);
+                __put_anon_vma(anon_vma);
+                anon_vma = NULL;
+        }
+
+        return anon_vma;
 
-        spin_unlock(&root_anon_vma->lock);
 out:
         rcu_read_unlock();
-        return NULL;
+        return anon_vma;
 }
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
-        __releases(&anon_vma->root->lock)
-        __releases(RCU)
 {
         anon_vma_unlock(anon_vma);
-        rcu_read_unlock();
 }
 
 /*
@@ -646,14 +748,14 @@ static int page_referenced_file(struct page *page,
          * The page lock not only makes sure that page->mapping cannot
          * suddenly be NULLified by truncation, it makes sure that the
          * structure at mapping cannot be freed and reused yet,
-         * so we can safely take mapping->i_mmap_lock.
+         * so we can safely take mapping->i_mmap_mutex.
          */
         BUG_ON(!PageLocked(page));
 
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
 
         /*
-         * i_mmap_lock does not stabilize mapcount at all, but mapcount
+         * i_mmap_mutex does not stabilize mapcount at all, but mapcount
          * is more likely to be accurate if we note it after spinning.
          */
         mapcount = page_mapcount(page);
@@ -675,7 +777,7 @@ static int page_referenced_file(struct page *page,
                         break;
         }
 
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
         return referenced;
 }
 
@@ -762,7 +864,7 @@ static int page_mkclean_file(struct address_space *mapping, struct page *page)
 
         BUG_ON(PageAnon(page));
 
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
                 if (vma->vm_flags & VM_SHARED) {
                         unsigned long address = vma_address(page, vma);
@@ -771,7 +873,7 @@ static int page_mkclean_file(struct address_space *mapping, struct page *page)
                         ret += page_mkclean_one(page, vma, address);
                 }
         }
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
         return ret;
 }
 
@@ -1119,7 +1221,7 @@ out_mlock:
         /*
          * We need mmap_sem locking, Otherwise VM_LOCKED check makes
          * unstable result and race. Plus, We can't wait here because
-         * we now hold anon_vma->lock or mapping->i_mmap_lock.
+         * we now hold anon_vma->mutex or mapping->i_mmap_mutex.
          * if trylock failed, the page remain in evictable lru and later
          * vmscan could retry to move the page to unevictable lru if the
          * page is actually mlocked.
@@ -1345,7 +1447,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
         unsigned long max_nl_size = 0;
         unsigned int mapcount;
 
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
                 unsigned long address = vma_address(page, vma);
                 if (address == -EFAULT)
@@ -1391,7 +1493,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
         mapcount = page_mapcount(page);
         if (!mapcount)
                 goto out;
-        cond_resched_lock(&mapping->i_mmap_lock);
+        cond_resched();
 
         max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
         if (max_nl_cursor == 0)
@@ -1413,7 +1515,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
                         }
                         vma->vm_private_data = (void *) max_nl_cursor;
                 }
-                cond_resched_lock(&mapping->i_mmap_lock);
+                cond_resched();
                 max_nl_cursor += CLUSTER_SIZE;
         } while (max_nl_cursor <= max_nl_size);
 
@@ -1425,7 +1527,7 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
         list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
                 vma->vm_private_data = NULL;
 out:
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
         return ret;
 }
 
@@ -1544,7 +1646,7 @@ static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *,
 
         if (!mapping)
                 return ret;
-        spin_lock(&mapping->i_mmap_lock);
+        mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
                 unsigned long address = vma_address(page, vma);
                 if (address == -EFAULT)
@@ -1558,7 +1660,7 @@ static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *,
          * never contain migration ptes.  Decide what to do about this
          * limitation to linear when we need rmap_walk() on nonlinear.
          */
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
         return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index ba4ad28b7db6..69edb45a9f28 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -99,6 +99,13 @@ static struct vfsmount *shm_mnt;
 /* Pretend that each entry is of this size in directory's i_size */
 #define BOGO_DIRENT_SIZE 20
 
+struct shmem_xattr {
+        struct list_head list;  /* anchored by shmem_inode_info->xattr_list */
+        char *name;             /* xattr name */
+        size_t size;
+        char value[0];
+};
+
 /* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
 enum sgp_type {
         SGP_READ,       /* don't exceed i_size, don't allocate page */
@@ -822,6 +829,7 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 static void shmem_evict_inode(struct inode *inode)
 {
         struct shmem_inode_info *info = SHMEM_I(inode);
+        struct shmem_xattr *xattr, *nxattr;
 
         if (inode->i_mapping->a_ops == &shmem_aops) {
                 truncate_inode_pages(inode->i_mapping, 0);
@@ -834,6 +842,11 @@ static void shmem_evict_inode(struct inode *inode)
                         mutex_unlock(&shmem_swaplist_mutex);
                 }
         }
+
+        list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) {
+                kfree(xattr->name);
+                kfree(xattr);
+        }
         BUG_ON(inode->i_blocks);
         shmem_free_inode(inode->i_sb);
         end_writeback(inode);
@@ -1615,6 +1628,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
                 spin_lock_init(&info->lock);
                 info->flags = flags & VM_NORESERVE;
                 INIT_LIST_HEAD(&info->swaplist);
+                INIT_LIST_HEAD(&info->xattr_list);
                 cache_no_acl(inode);
 
                 switch (mode & S_IFMT) {
@@ -2014,9 +2028,9 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 
         info = SHMEM_I(inode);
         inode->i_size = len-1;
-        if (len <= (char *)inode - (char *)info) {
+        if (len <= SHMEM_SYMLINK_INLINE_LEN) {
                 /* do it inline */
-                memcpy(info, symname, len);
+                memcpy(info->inline_symlink, symname, len);
                 inode->i_op = &shmem_symlink_inline_operations;
         } else {
                 error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
@@ -2042,7 +2056,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 
 static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd)
 {
-        nd_set_link(nd, (char *)SHMEM_I(dentry->d_inode));
+        nd_set_link(nd, SHMEM_I(dentry->d_inode)->inline_symlink);
         return NULL;
 }
 
@@ -2066,63 +2080,253 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co
         }
 }
 
-static const struct inode_operations shmem_symlink_inline_operations = {
-        .readlink       = generic_readlink,
-        .follow_link    = shmem_follow_link_inline,
-};
-
-static const struct inode_operations shmem_symlink_inode_operations = {
-        .readlink       = generic_readlink,
-        .follow_link    = shmem_follow_link,
-        .put_link       = shmem_put_link,
-};
-
-#ifdef CONFIG_TMPFS_POSIX_ACL
+#ifdef CONFIG_TMPFS_XATTR
 /*
- * Superblocks without xattr inode operations will get security.* xattr
- * support from the VFS "for free". As soon as we have any other xattrs
+ * Superblocks without xattr inode operations may get some security.* xattr
+ * support from the LSM "for free". As soon as we have any other xattrs
  * like ACLs, we also need to implement the security.* handlers at
  * filesystem level, though.
  */
 
-static size_t shmem_xattr_security_list(struct dentry *dentry, char *list,
-                                        size_t list_len, const char *name,
-                                        size_t name_len, int handler_flags)
+static int shmem_xattr_get(struct dentry *dentry, const char *name,
+                           void *buffer, size_t size)
 {
-        return security_inode_listsecurity(dentry->d_inode, list, list_len);
-}
+        struct shmem_inode_info *info;
+        struct shmem_xattr *xattr;
+        int ret = -ENODATA;
 
-static int shmem_xattr_security_get(struct dentry *dentry, const char *name,
-                void *buffer, size_t size, int handler_flags)
-{
-        if (strcmp(name, "") == 0)
-                return -EINVAL;
-        return xattr_getsecurity(dentry->d_inode, name, buffer, size);
+        info = SHMEM_I(dentry->d_inode);
+
+        spin_lock(&info->lock);
+        list_for_each_entry(xattr, &info->xattr_list, list) {
+                if (strcmp(name, xattr->name))
+                        continue;
+
+                ret = xattr->size;
+                if (buffer) {
+                        if (size < xattr->size)
+                                ret = -ERANGE;
+                        else
+                                memcpy(buffer, xattr->value, xattr->size);
+                }
+                break;
+        }
+        spin_unlock(&info->lock);
+        return ret;
 }
 
-static int shmem_xattr_security_set(struct dentry *dentry, const char *name,
-                const void *value, size_t size, int flags, int handler_flags)
+static int shmem_xattr_set(struct dentry *dentry, const char *name,
+                           const void *value, size_t size, int flags)
 {
-        if (strcmp(name, "") == 0)
-                return -EINVAL;
-        return security_inode_setsecurity(dentry->d_inode, name, value,
-                                          size, flags);
+        struct inode *inode = dentry->d_inode;
+        struct shmem_inode_info *info = SHMEM_I(inode);
+        struct shmem_xattr *xattr;
+        struct shmem_xattr *new_xattr = NULL;
+        size_t len;
+        int err = 0;
+
+        /* value == NULL means remove */
+        if (value) {
+                /* wrap around? */
+                len = sizeof(*new_xattr) + size;
+                if (len <= sizeof(*new_xattr))
+                        return -ENOMEM;
+
+                new_xattr = kmalloc(len, GFP_KERNEL);
+                if (!new_xattr)
+                        return -ENOMEM;
+
+                new_xattr->name = kstrdup(name, GFP_KERNEL);
+                if (!new_xattr->name) {
+                        kfree(new_xattr);
+                        return -ENOMEM;
+                }
+
+                new_xattr->size = size;
+                memcpy(new_xattr->value, value, size);
+        }
+
+        spin_lock(&info->lock);
+        list_for_each_entry(xattr, &info->xattr_list, list) {
+                if (!strcmp(name, xattr->name)) {
+                        if (flags & XATTR_CREATE) {
+                                xattr = new_xattr;
+                                err = -EEXIST;
+                        } else if (new_xattr) {
+                                list_replace(&xattr->list, &new_xattr->list);
+                        } else {
+                                list_del(&xattr->list);
+                        }
+                        goto out;
+                }
+        }
+        if (flags & XATTR_REPLACE) {
+                xattr = new_xattr;
+                err = -ENODATA;
+        } else {
+                list_add(&new_xattr->list, &info->xattr_list);
+                xattr = NULL;
+        }
+out:
+        spin_unlock(&info->lock);
+        if (xattr)
+                kfree(xattr->name);
+        kfree(xattr);
+        return err;
 }
 
-static const struct xattr_handler shmem_xattr_security_handler = {
-        .prefix = XATTR_SECURITY_PREFIX,
-        .list   = shmem_xattr_security_list,
-        .get    = shmem_xattr_security_get,
-        .set    = shmem_xattr_security_set,
-};
 
 static const struct xattr_handler *shmem_xattr_handlers[] = {
+#ifdef CONFIG_TMPFS_POSIX_ACL
         &generic_acl_access_handler,
         &generic_acl_default_handler,
-        &shmem_xattr_security_handler,
+#endif
         NULL
 };
+
+static int shmem_xattr_validate(const char *name)
+{
+        struct { const char *prefix; size_t len; } arr[] = {
+                { XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN },
+                { XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN }
+        };
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(arr); i++) {
+                size_t preflen = arr[i].len;
+                if (strncmp(name, arr[i].prefix, preflen) == 0) {
+                        if (!name[preflen])
+                                return -EINVAL;
+                        return 0;
+                }
+        }
+        return -EOPNOTSUPP;
+}
+
+static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
+                              void *buffer, size_t size)
+{
+        int err;
+
+        /*
+         * If this is a request for a synthetic attribute in the system.*
+         * namespace use the generic infrastructure to resolve a handler
+         * for it via sb->s_xattr.
+         */
+        if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+                return generic_getxattr(dentry, name, buffer, size);
+
+        err = shmem_xattr_validate(name);
+        if (err)
+                return err;
+
+        return shmem_xattr_get(dentry, name, buffer, size);
+}
+
+static int shmem_setxattr(struct dentry *dentry, const char *name,
+                          const void *value, size_t size, int flags)
+{
+        int err;
+
+        /*
+         * If this is a request for a synthetic attribute in the system.*
+         * namespace use the generic infrastructure to resolve a handler
+         * for it via sb->s_xattr.
+         */
+        if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+                return generic_setxattr(dentry, name, value, size, flags);
+
+        err = shmem_xattr_validate(name);
+        if (err)
+                return err;
+
+        if (size == 0)
+                value = "";  /* empty EA, do not remove */
+
+        return shmem_xattr_set(dentry, name, value, size, flags);
+
+}
+
+static int shmem_removexattr(struct dentry *dentry, const char *name)
+{
+        int err;
+
+        /*
+         * If this is a request for a synthetic attribute in the system.*
+         * namespace use the generic infrastructure to resolve a handler
+         * for it via sb->s_xattr.
+         */
+        if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+                return generic_removexattr(dentry, name);
+
+        err = shmem_xattr_validate(name);
+        if (err)
+                return err;
+
+        return shmem_xattr_set(dentry, name, NULL, 0, XATTR_REPLACE);
+}
+
+static bool xattr_is_trusted(const char *name)
+{
+        return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
+}
+
+static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+        bool trusted = capable(CAP_SYS_ADMIN);
+        struct shmem_xattr *xattr;
+        struct shmem_inode_info *info;
+        size_t used = 0;
+
+        info = SHMEM_I(dentry->d_inode);
+
+        spin_lock(&info->lock);
+        list_for_each_entry(xattr, &info->xattr_list, list) {
+                size_t len;
+
+                /* skip "trusted." attributes for unprivileged callers */
+                if (!trusted && xattr_is_trusted(xattr->name))
+                        continue;
+
+                len = strlen(xattr->name) + 1;
+                used += len;
+                if (buffer) {
+                        if (size < used) {
+                                used = -ERANGE;
+                                break;
+                        }
+                        memcpy(buffer, xattr->name, len);
+                        buffer += len;
+                }
+        }
+        spin_unlock(&info->lock);
+
+        return used;
+}
+#endif /* CONFIG_TMPFS_XATTR */
+
+static const struct inode_operations shmem_symlink_inline_operations = {
+        .readlink       = generic_readlink,
+        .follow_link    = shmem_follow_link_inline,
+#ifdef CONFIG_TMPFS_XATTR
+        .setxattr       = shmem_setxattr,
+        .getxattr       = shmem_getxattr,
+        .listxattr      = shmem_listxattr,
+        .removexattr    = shmem_removexattr,
+#endif
+};
+
+static const struct inode_operations shmem_symlink_inode_operations = {
+        .readlink       = generic_readlink,
+        .follow_link    = shmem_follow_link,
+        .put_link       = shmem_put_link,
+#ifdef CONFIG_TMPFS_XATTR
+        .setxattr       = shmem_setxattr,
+        .getxattr       = shmem_getxattr,
+        .listxattr      = shmem_listxattr,
+        .removexattr    = shmem_removexattr,
 #endif
+};
 
 static struct dentry *shmem_get_parent(struct dentry *child)
 {
@@ -2402,8 +2606,10 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
         sb->s_magic = TMPFS_MAGIC;
         sb->s_op = &shmem_ops;
         sb->s_time_gran = 1;
-#ifdef CONFIG_TMPFS_POSIX_ACL
+#ifdef CONFIG_TMPFS_XATTR
         sb->s_xattr = shmem_xattr_handlers;
+#endif
+#ifdef CONFIG_TMPFS_POSIX_ACL
         sb->s_flags |= MS_POSIXACL;
 #endif
 
@@ -2501,11 +2707,13 @@ static const struct file_operations shmem_file_operations = {
 static const struct inode_operations shmem_inode_operations = {
         .setattr        = shmem_notify_change,
         .truncate_range = shmem_truncate_range,
+#ifdef CONFIG_TMPFS_XATTR
+        .setxattr       = shmem_setxattr,
+        .getxattr       = shmem_getxattr,
+        .listxattr      = shmem_listxattr,
+        .removexattr    = shmem_removexattr,
+#endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-        .setxattr       = generic_setxattr,
-        .getxattr       = generic_getxattr,
-        .listxattr      = generic_listxattr,
-        .removexattr    = generic_removexattr,
         .check_acl      = generic_check_acl,
 #endif
 
@@ -2523,23 +2731,27 @@ static const struct inode_operations shmem_dir_inode_operations = {
         .mknod          = shmem_mknod,
         .rename         = shmem_rename,
 #endif
+#ifdef CONFIG_TMPFS_XATTR
+        .setxattr       = shmem_setxattr,
+        .getxattr       = shmem_getxattr,
+        .listxattr      = shmem_listxattr,
+        .removexattr    = shmem_removexattr,
+#endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
         .setattr        = shmem_notify_change,
-        .setxattr       = generic_setxattr,
-        .getxattr       = generic_getxattr,
-        .listxattr      = generic_listxattr,
-        .removexattr    = generic_removexattr,
         .check_acl      = generic_check_acl,
 #endif
 };
 
 static const struct inode_operations shmem_special_inode_operations = {
+#ifdef CONFIG_TMPFS_XATTR
+        .setxattr       = shmem_setxattr,
+        .getxattr       = shmem_getxattr,
+        .listxattr      = shmem_listxattr,
+        .removexattr    = shmem_removexattr,
+#endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
         .setattr        = shmem_notify_change,
-        .setxattr       = generic_setxattr,
-        .getxattr       = generic_getxattr,
-        .listxattr      = generic_listxattr,
-        .removexattr    = generic_removexattr,
         .check_acl      = generic_check_acl,
 #endif
 };
diff --git a/mm/slub.c b/mm/slub.c
index 4ea7f1a22a94..4aad32d2e60d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1884,7 +1884,8 @@ debug:
         deactivate_slab(s, c);
         c->page = NULL;
         c->node = NUMA_NO_NODE;
-        goto unlock_out;
+        local_irq_restore(flags);
+        return object;
 }
 
 /*
diff --git a/mm/swap.c b/mm/swap.c
index 5602f1a1b1e7..3a442f18b0b3 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -272,14 +272,10 @@ static void update_page_reclaim_stat(struct zone *zone, struct page *page,
                 memcg_reclaim_stat->recent_rotated[file]++;
 }
 
-/*
- * FIXME: speed this up?
- */
-void activate_page(struct page *page)
+static void __activate_page(struct page *page, void *arg)
 {
         struct zone *zone = page_zone(page);
 
-        spin_lock_irq(&zone->lru_lock);
         if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
                 int file = page_is_file_cache(page);
                 int lru = page_lru_base_type(page);
@@ -292,8 +288,45 @@ void activate_page(struct page *page)
 
                 update_page_reclaim_stat(zone, page, file, 1);
         }
+}
+
+#ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
+
+static void activate_page_drain(int cpu)
+{
+        struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
+
+        if (pagevec_count(pvec))
+                pagevec_lru_move_fn(pvec, __activate_page, NULL);
+}
+
+void activate_page(struct page *page)
+{
+        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+                struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+
+                page_cache_get(page);
+                if (!pagevec_add(pvec, page))
+                        pagevec_lru_move_fn(pvec, __activate_page, NULL);
+                put_cpu_var(activate_page_pvecs);
+        }
+}
+
+#else
+static inline void activate_page_drain(int cpu)
+{
+}
+
+void activate_page(struct page *page)
+{
+        struct zone *zone = page_zone(page);
+
+        spin_lock_irq(&zone->lru_lock);
+        __activate_page(page, NULL);
         spin_unlock_irq(&zone->lru_lock);
 }
+#endif
 
 /*
  * Mark a page as having seen activity.
@@ -464,6 +497,8 @@ static void drain_cpu_pagevecs(int cpu)
         pvec = &per_cpu(lru_deactivate_pvecs, cpu);
         if (pagevec_count(pvec))
                 pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
+        activate_page_drain(cpu);
 }
 
 /**
@@ -476,6 +511,13 @@ static void drain_cpu_pagevecs(int cpu)
  */
 void deactivate_page(struct page *page)
 {
+        /*
+         * In a workload with many unevictable page such as mprotect, unevictable
+         * page deactivation for accelerating reclaim is pointless.
+         */
+        if (PageUnevictable(page))
+                return;
+
         if (likely(get_page_unless_zero(page))) {
                 struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8c6b3ce38f09..d537d29e9b7b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -31,6 +31,7 @@
 #include <linux/syscalls.h>
 #include <linux/memcontrol.h>
 #include <linux/poll.h>
+#include <linux/oom.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -1555,6 +1556,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
         struct address_space *mapping;
         struct inode *inode;
         char *pathname;
+        int oom_score_adj;
         int i, type, prev;
         int err;
 
@@ -1613,9 +1615,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
         p->flags &= ~SWP_WRITEOK;
         spin_unlock(&swap_lock);
 
-        current->flags |= PF_OOM_ORIGIN;
+        oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
         err = try_to_unuse(type);
-        current->flags &= ~PF_OOM_ORIGIN;
+        test_set_oom_score_adj(oom_score_adj);
 
         if (err) {
                 /*
diff --git a/mm/util.c b/mm/util.c
index e7b103a6fd21..88ea1bd661c0 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -6,6 +6,8 @@
 #include <linux/sched.h>
 #include <asm/uaccess.h>
 
+#include "internal.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/kmem.h>
 
@@ -215,6 +217,28 @@ char *strndup_user(const char __user *s, long n)
 }
 EXPORT_SYMBOL(strndup_user);
 
+void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
+                struct vm_area_struct *prev, struct rb_node *rb_parent)
+{
+        struct vm_area_struct *next;
+
+        vma->vm_prev = prev;
+        if (prev) {
+                next = prev->vm_next;
+                prev->vm_next = vma;
+        } else {
+                mm->mmap = vma;
+                if (rb_parent)
+                        next = rb_entry(rb_parent,
+                                        struct vm_area_struct, vm_rb);
+                else
+                        next = NULL;
+        }
+        vma->vm_next = next;
+        if (next)
+                next->vm_prev = vma;
+}
+
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5d6030235d7a..b5ccf3158d82 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -375,7 +375,7 @@ nocache:
         /* find starting point for our search */
         if (free_vmap_cache) {
                 first = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
-                addr = ALIGN(first->va_end + PAGE_SIZE, align);
+                addr = ALIGN(first->va_end, align);
                 if (addr < vstart)
                         goto nocache;
                 if (addr + size - 1 < addr)
@@ -406,10 +406,10 @@ nocache:
         }
 
         /* from the starting point, walk areas until a suitable hole is found */
-        while (addr + size >= first->va_start && addr + size <= vend) {
+        while (addr + size > first->va_start && addr + size <= vend) {
                 if (addr + cached_hole_size < first->va_start)
                         cached_hole_size = first->va_start - addr;
-                addr = ALIGN(first->va_end + PAGE_SIZE, align);
+                addr = ALIGN(first->va_end, align);
                 if (addr + size - 1 < addr)
                         goto overflow;
 
@@ -1534,6 +1534,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
                                  pgprot_t prot, int node, void *caller)
 {
+        const int order = 0;
         struct page **pages;
         unsigned int nr_pages, array_size, i;
         gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
@@ -1560,11 +1561,12 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
         for (i = 0; i < area->nr_pages; i++) {
                 struct page *page;
+                gfp_t tmp_mask = gfp_mask | __GFP_NOWARN;
 
                 if (node < 0)
-                        page = alloc_page(gfp_mask);
+                        page = alloc_page(tmp_mask);
                 else
-                        page = alloc_pages_node(node, gfp_mask, 0);
+                        page = alloc_pages_node(node, tmp_mask, order);
 
                 if (unlikely(!page)) {
                         /* Successfully allocated i pages, free them in __vunmap() */
@@ -1579,6 +1581,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
         return area->addr;
 
 fail:
+        warn_alloc_failed(gfp_mask, order, "vmalloc: allocation failure, "
+                          "allocated %ld of %ld bytes\n",
+                          (area->nr_pages*PAGE_SIZE), area->size);
         vfree(area->addr);
         return NULL;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c9177202c8ce..7e0116150dc7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -202,6 +202,14 @@ void unregister_shrinker(struct shrinker *shrinker)
 }
 EXPORT_SYMBOL(unregister_shrinker);
 
+static inline int do_shrinker_shrink(struct shrinker *shrinker,
+                                     struct shrink_control *sc,
+                                     unsigned long nr_to_scan)
+{
+        sc->nr_to_scan = nr_to_scan;
+        return (*shrinker->shrink)(shrinker, sc);
+}
+
 #define SHRINK_BATCH 128
 /*
  * Call the shrink functions to age shrinkable caches
@@ -222,25 +230,29 @@ EXPORT_SYMBOL(unregister_shrinker);
  *
  * Returns the number of slab objects which we shrunk.
  */
-unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
-                        unsigned long lru_pages)
+unsigned long shrink_slab(struct shrink_control *shrink,
+                          unsigned long nr_pages_scanned,
+                          unsigned long lru_pages)
 {
         struct shrinker *shrinker;
         unsigned long ret = 0;
 
-        if (scanned == 0)
-                scanned = SWAP_CLUSTER_MAX;
+        if (nr_pages_scanned == 0)
+                nr_pages_scanned = SWAP_CLUSTER_MAX;
 
-        if (!down_read_trylock(&shrinker_rwsem))
-                return 1;       /* Assume we'll be able to shrink next time */
+        if (!down_read_trylock(&shrinker_rwsem)) {
+                /* Assume we'll be able to shrink next time */
+                ret = 1;
+                goto out;
+        }
 
         list_for_each_entry(shrinker, &shrinker_list, list) {
                 unsigned long long delta;
                 unsigned long total_scan;
                 unsigned long max_pass;
 
-                max_pass = (*shrinker->shrink)(shrinker, 0, gfp_mask);
-                delta = (4 * scanned) / shrinker->seeks;
+                max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+                delta = (4 * nr_pages_scanned) / shrinker->seeks;
                 delta *= max_pass;
                 do_div(delta, lru_pages + 1);
                 shrinker->nr += delta;
@@ -267,9 +279,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
                         int shrink_ret;
                         int nr_before;
 
-                        nr_before = (*shrinker->shrink)(shrinker, 0, gfp_mask);
-                        shrink_ret = (*shrinker->shrink)(shrinker, this_scan,
-                                                                gfp_mask);
+                        nr_before = do_shrinker_shrink(shrinker, shrink, 0);
+                        shrink_ret = do_shrinker_shrink(shrinker, shrink,
+                                                        this_scan);
                         if (shrink_ret == -1)
                                 break;
                         if (shrink_ret < nr_before)
@@ -283,6 +295,8 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
                 shrinker->nr += total_scan;
         }
         up_read(&shrinker_rwsem);
+out:
+        cond_resched();
         return ret;
 }
 
@@ -1202,13 +1216,16 @@ int isolate_lru_page(struct page *page)
 {
         int ret = -EBUSY;
 
+        VM_BUG_ON(!page_count(page));
+
         if (PageLRU(page)) {
                 struct zone *zone = page_zone(page);
 
                 spin_lock_irq(&zone->lru_lock);
-                if (PageLRU(page) && get_page_unless_zero(page)) {
+                if (PageLRU(page)) {
                         int lru = page_lru(page);
                         ret = 0;
+                        get_page(page);
                         ClearPageLRU(page);
 
                         del_page_from_lru_list(zone, page, lru);
@@ -2027,7 +2044,8 @@ static bool all_unreclaimable(struct zonelist *zonelist,
  *              else, the number of pages reclaimed
  */
 static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
-                                        struct scan_control *sc)
+                                        struct scan_control *sc,
+                                        struct shrink_control *shrink)
 {
         int priority;
         unsigned long total_scanned = 0;
@@ -2061,7 +2079,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
                                 lru_pages += zone_reclaimable_pages(zone);
                         }
 
-                        shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
+                        shrink_slab(shrink, sc->nr_scanned, lru_pages);
                         if (reclaim_state) {
                                 sc->nr_reclaimed += reclaim_state->reclaimed_slab;
                                 reclaim_state->reclaimed_slab = 0;
@@ -2133,12 +2151,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
                 .mem_cgroup = NULL,
                 .nodemask = nodemask,
         };
+        struct shrink_control shrink = {
+                .gfp_mask = sc.gfp_mask,
+        };
 
         trace_mm_vmscan_direct_reclaim_begin(order,
                                 sc.may_writepage,
                                 gfp_mask);
 
-        nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+        nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
 
         trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
 
@@ -2198,17 +2219,20 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
                 .order = 0,
                 .mem_cgroup = mem_cont,
                 .nodemask = NULL, /* we don't care the placement */
+                .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+                                (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
+        };
+        struct shrink_control shrink = {
+                .gfp_mask = sc.gfp_mask,
         };
 
-        sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
-                        (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
         zonelist = NODE_DATA(numa_node_id())->node_zonelists;
 
         trace_mm_vmscan_memcg_reclaim_begin(0,
                                             sc.may_writepage,
                                             sc.gfp_mask);
 
-        nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+        nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
 
         trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -2287,7 +2311,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
          * must be balanced
          */
         if (order)
-                return pgdat_balanced(pgdat, balanced, classzone_idx);
+                return !pgdat_balanced(pgdat, balanced, classzone_idx);
         else
                 return !all_zones_ok;
 }
@@ -2336,6 +2360,9 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
                 .order = order,
                 .mem_cgroup = NULL,
         };
+        struct shrink_control shrink = {
+                .gfp_mask = sc.gfp_mask,
+        };
 loop_again:
         total_scanned = 0;
         sc.nr_reclaimed = 0;
@@ -2435,8 +2462,7 @@ loop_again:
                                         end_zone, 0))
                                 shrink_zone(priority, zone, &sc);
                         reclaim_state->reclaimed_slab = 0;
-                        nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
-                                                lru_pages);
+                        nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
                         sc.nr_reclaimed += reclaim_state->reclaimed_slab;
                         total_scanned += sc.nr_scanned;
 
@@ -2788,7 +2814,10 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
                 .swappiness = vm_swappiness,
                 .order = 0,
         };
-        struct zonelist * zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
+        struct shrink_control shrink = {
+                .gfp_mask = sc.gfp_mask,
+        };
+        struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
         struct task_struct *p = current;
         unsigned long nr_reclaimed;
 
@@ -2797,7 +2826,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
         reclaim_state.reclaimed_slab = 0;
         p->reclaim_state = &reclaim_state;
 
-        nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+        nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
 
         p->reclaim_state = NULL;
         lockdep_clear_current_reclaim_state();
@@ -2972,6 +3001,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                 .swappiness = vm_swappiness,
                 .order = order,
         };
+        struct shrink_control shrink = {
+                .gfp_mask = sc.gfp_mask,
+        };
         unsigned long nr_slab_pages0, nr_slab_pages1;
 
         cond_resched();
@@ -3013,7 +3045,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
                         unsigned long lru_pages = zone_reclaimable_pages(zone);
 
                         /* No reclaimable slab or very low memory pressure */
-                        if (!shrink_slab(sc.nr_scanned, gfp_mask, lru_pages))
+                        if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages))
                                 break;
 
                         /* Freed enough memory */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 897ea9e88238..20c18b7694b2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -157,7 +157,7 @@ int calculate_normal_threshold(struct zone *zone)
 /*
  * Refresh the thresholds for each zone.
  */
-static void refresh_zone_stat_thresholds(void)
+void refresh_zone_stat_thresholds(void)
 {
         struct zone *zone;
         int cpu;
@@ -659,6 +659,138 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 }
 #endif
 
+#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS)
+#ifdef CONFIG_ZONE_DMA
+#define TEXT_FOR_DMA(xx) xx "_dma",
+#else
+#define TEXT_FOR_DMA(xx)
+#endif
+
+#ifdef CONFIG_ZONE_DMA32
+#define TEXT_FOR_DMA32(xx) xx "_dma32",
+#else
+#define TEXT_FOR_DMA32(xx)
+#endif
+
+#ifdef CONFIG_HIGHMEM
+#define TEXT_FOR_HIGHMEM(xx) xx "_high",
+#else
+#define TEXT_FOR_HIGHMEM(xx)
+#endif
+
+#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
+                                        TEXT_FOR_HIGHMEM(xx) xx "_movable",
+
+const char * const vmstat_text[] = {
+        /* Zoned VM counters */
+        "nr_free_pages",
+        "nr_inactive_anon",
+        "nr_active_anon",
+        "nr_inactive_file",
+        "nr_active_file",
+        "nr_unevictable",
+        "nr_mlock",
+        "nr_anon_pages",
+        "nr_mapped",
+        "nr_file_pages",
+        "nr_dirty",
+        "nr_writeback",
+        "nr_slab_reclaimable",
+        "nr_slab_unreclaimable",
+        "nr_page_table_pages",
+        "nr_kernel_stack",
+        "nr_unstable",
+        "nr_bounce",
+        "nr_vmscan_write",
+        "nr_writeback_temp",
+        "nr_isolated_anon",
+        "nr_isolated_file",
+        "nr_shmem",
+        "nr_dirtied",
+        "nr_written",
+
+#ifdef CONFIG_NUMA
+        "numa_hit",
+        "numa_miss",
+        "numa_foreign",
+        "numa_interleave",
+        "numa_local",
+        "numa_other",
+#endif
+        "nr_anon_transparent_hugepages",
+        "nr_dirty_threshold",
+        "nr_dirty_background_threshold",
+
+#ifdef CONFIG_VM_EVENT_COUNTERS
+        "pgpgin",
+        "pgpgout",
+        "pswpin",
+        "pswpout",
+
+        TEXTS_FOR_ZONES("pgalloc")
+
+        "pgfree",
+        "pgactivate",
+        "pgdeactivate",
+
+        "pgfault",
+        "pgmajfault",
+
+        TEXTS_FOR_ZONES("pgrefill")
+        TEXTS_FOR_ZONES("pgsteal")
+        TEXTS_FOR_ZONES("pgscan_kswapd")
+        TEXTS_FOR_ZONES("pgscan_direct")
+
+#ifdef CONFIG_NUMA
+        "zone_reclaim_failed",
+#endif
+        "pginodesteal",
+        "slabs_scanned",
+        "kswapd_steal",
+        "kswapd_inodesteal",
+        "kswapd_low_wmark_hit_quickly",
+        "kswapd_high_wmark_hit_quickly",
+        "kswapd_skip_congestion_wait",
+        "pageoutrun",
+        "allocstall",
+
+        "pgrotated",
+
+#ifdef CONFIG_COMPACTION
+        "compact_blocks_moved",
+        "compact_pages_moved",
+        "compact_pagemigrate_failed",
+        "compact_stall",
+        "compact_fail",
+        "compact_success",
+#endif
+
+#ifdef CONFIG_HUGETLB_PAGE
+        "htlb_buddy_alloc_success",
+        "htlb_buddy_alloc_fail",
+#endif
+        "unevictable_pgs_culled",
+        "unevictable_pgs_scanned",
+        "unevictable_pgs_rescued",
+        "unevictable_pgs_mlocked",
+        "unevictable_pgs_munlocked",
+        "unevictable_pgs_cleared",
+        "unevictable_pgs_stranded",
+        "unevictable_pgs_mlockfreed",
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+        "thp_fault_alloc",
+        "thp_fault_fallback",
+        "thp_collapse_alloc",
+        "thp_collapse_alloc_failed",
+        "thp_split",
+#endif
+
+#endif /* CONFIG_VM_EVENTS_COUNTERS */
+};
+#endif /* CONFIG_PROC_FS || CONFIG_SYSFS */
+
+
 #ifdef CONFIG_PROC_FS
 static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
                                                 struct zone *zone)
@@ -831,135 +963,6 @@ static const struct file_operations pagetypeinfo_file_ops = {
         .release        = seq_release,
 };
 
-#ifdef CONFIG_ZONE_DMA
-#define TEXT_FOR_DMA(xx) xx "_dma",
-#else
-#define TEXT_FOR_DMA(xx)
-#endif
-
-#ifdef CONFIG_ZONE_DMA32
-#define TEXT_FOR_DMA32(xx) xx "_dma32",
-#else
-#define TEXT_FOR_DMA32(xx)
-#endif
-
-#ifdef CONFIG_HIGHMEM
-#define TEXT_FOR_HIGHMEM(xx) xx "_high",
-#else
-#define TEXT_FOR_HIGHMEM(xx)
-#endif
-
-#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
-                                        TEXT_FOR_HIGHMEM(xx) xx "_movable",
-
-static const char * const vmstat_text[] = {
-        /* Zoned VM counters */
-        "nr_free_pages",
-        "nr_inactive_anon",
-        "nr_active_anon",
-        "nr_inactive_file",
-        "nr_active_file",
-        "nr_unevictable",
-        "nr_mlock",
-        "nr_anon_pages",
-        "nr_mapped",
-        "nr_file_pages",
-        "nr_dirty",
-        "nr_writeback",
-        "nr_slab_reclaimable",
-        "nr_slab_unreclaimable",
-        "nr_page_table_pages",
-        "nr_kernel_stack",
-        "nr_unstable",
-        "nr_bounce",
-        "nr_vmscan_write",
-        "nr_writeback_temp",
-        "nr_isolated_anon",
-        "nr_isolated_file",
-        "nr_shmem",
-        "nr_dirtied",
-        "nr_written",
-
-#ifdef CONFIG_NUMA
-        "numa_hit",
-        "numa_miss",
-        "numa_foreign",
-        "numa_interleave",
-        "numa_local",
-        "numa_other",
-#endif
-        "nr_anon_transparent_hugepages",
-        "nr_dirty_threshold",
-        "nr_dirty_background_threshold",
-
-#ifdef CONFIG_VM_EVENT_COUNTERS
-        "pgpgin",
-        "pgpgout",
-        "pswpin",
-        "pswpout",
-
-        TEXTS_FOR_ZONES("pgalloc")
-
-        "pgfree",
-        "pgactivate",
-        "pgdeactivate",
-
-        "pgfault",
-        "pgmajfault",
-
-        TEXTS_FOR_ZONES("pgrefill")
-        TEXTS_FOR_ZONES("pgsteal")
-        TEXTS_FOR_ZONES("pgscan_kswapd")
-        TEXTS_FOR_ZONES("pgscan_direct")
-
-#ifdef CONFIG_NUMA
-        "zone_reclaim_failed",
-#endif
-        "pginodesteal",
-        "slabs_scanned",
-        "kswapd_steal",
-        "kswapd_inodesteal",
-        "kswapd_low_wmark_hit_quickly",
-        "kswapd_high_wmark_hit_quickly",
-        "kswapd_skip_congestion_wait",
-        "pageoutrun",
-        "allocstall",
-
-        "pgrotated",
-
-#ifdef CONFIG_COMPACTION
-        "compact_blocks_moved",
-        "compact_pages_moved",
-        "compact_pagemigrate_failed",
-        "compact_stall",
-        "compact_fail",
-        "compact_success",
-#endif
-
-#ifdef CONFIG_HUGETLB_PAGE
-        "htlb_buddy_alloc_success",
-        "htlb_buddy_alloc_fail",
-#endif
-        "unevictable_pgs_culled",
-        "unevictable_pgs_scanned",
-        "unevictable_pgs_rescued",
-        "unevictable_pgs_mlocked",
-        "unevictable_pgs_munlocked",
-        "unevictable_pgs_cleared",
-        "unevictable_pgs_stranded",
-        "unevictable_pgs_mlockfreed",
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-        "thp_fault_alloc",
-        "thp_fault_fallback",
-        "thp_collapse_alloc",
-        "thp_collapse_alloc_failed",
-        "thp_split",
-#endif
-
-#endif /* CONFIG_VM_EVENTS_COUNTERS */
-};
-
 static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
                                                         struct zone *zone)
 {
@@ -1198,7 +1201,6 @@ static int __init setup_vmstat(void)
 #ifdef CONFIG_SMP
         int cpu;
 
-        refresh_zone_stat_thresholds();
         register_cpu_notifier(&vmstat_notifier);
 
         for_each_online_cpu(cpu)
diff --git a/net/9p/Kconfig b/net/9p/Kconfig
index 7ed75c7bd5d1..d9ea09b11cf8 100644
--- a/net/9p/Kconfig
+++ b/net/9p/Kconfig
@@ -3,8 +3,8 @@
 #
 
 menuconfig NET_9P
-        depends on NET && EXPERIMENTAL
-        tristate "Plan 9 Resource Sharing Support (9P2000) (Experimental)"
+        depends on NET
+        tristate "Plan 9 Resource Sharing Support (9P2000)"
         help
           If you say Y here, you will get experimental support for
           Plan 9 resource sharing via the 9P2000 protocol.
@@ -16,8 +16,8 @@ menuconfig NET_9P
 if NET_9P
 
 config NET_9P_VIRTIO
-        depends on EXPERIMENTAL && VIRTIO
-        tristate "9P Virtio Transport (Experimental)"
+        depends on VIRTIO
+        tristate "9P Virtio Transport"
         help
           This builds support for a transports between
           guest partitions and a host partition.
diff --git a/net/9p/client.c b/net/9p/client.c
index ceab943dfc49..9e3b0e640da1 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -92,9 +92,6 @@ static int get_protocol_version(const substring_t *name)
         return version;
 }
 
-static struct p9_req_t *
-p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
-
 /**
  * parse_options - parse mount options into client structure
  * @opts: options string passed from mount
@@ -307,12 +304,13 @@ static int p9_tag_init(struct p9_client *c)
         c->tagpool = p9_idpool_create();
         if (IS_ERR(c->tagpool)) {
                 err = PTR_ERR(c->tagpool);
-                c->tagpool = NULL;
                 goto error;
         }
-
-        p9_idpool_get(c->tagpool); /* reserve tag 0 */
-
+        err = p9_idpool_get(c->tagpool); /* reserve tag 0 */
+        if (err < 0) {
+                p9_idpool_destroy(c->tagpool);
+                goto error;
+        }
         c->max_tag = 0;
 error:
         return err;
@@ -518,12 +516,15 @@ out_err:
         return err;
 }
 
+static struct p9_req_t *
+p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
+
 /**
  * p9_client_flush - flush (cancel) a request
  * @c: client state
  * @oldreq: request to cancel
  *
- * This sents a flush for a particular requests and links
+ * This sents a flush for a particular request and links
  * the flush request to the original request.  The current
  * code only supports a single flush request although the protocol
  * allows for multiple flush requests to be sent for a single request.
@@ -789,11 +790,13 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
         spin_lock_init(&clnt->lock);
         INIT_LIST_HEAD(&clnt->fidlist);
 
-        p9_tag_init(clnt);
+        err = p9_tag_init(clnt);
+        if (err < 0)
+                goto free_client;
 
         err = parse_opts(options, clnt);
         if (err < 0)
-                goto free_client;
+                goto destroy_tagpool;
 
         if (!clnt->trans_mod)
                 clnt->trans_mod = v9fs_get_default_trans();
@@ -802,13 +805,12 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
                 err = -EPROTONOSUPPORT;
                 P9_DPRINTK(P9_DEBUG_ERROR,
                                 "No transport defined or default transport\n");
-                goto free_client;
+                goto destroy_tagpool;
         }
 
         clnt->fidpool = p9_idpool_create();
         if (IS_ERR(clnt->fidpool)) {
                 err = PTR_ERR(clnt->fidpool);
-                clnt->fidpool = NULL;
                 goto put_trans;
         }
 
@@ -834,6 +836,8 @@ destroy_fidpool:
         p9_idpool_destroy(clnt->fidpool);
 put_trans:
         v9fs_put_trans(clnt->trans_mod);
+destroy_tagpool:
+        p9_idpool_destroy(clnt->tagpool);
 free_client:
         kfree(clnt);
         return ERR_PTR(err);
@@ -1298,7 +1302,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
         if (count < rsize)
                 rsize = count;
 
-        /* Don't bother zerocopy form small IO (< 1024) */
+        /* Don't bother zerocopy for small IO (< 1024) */
         if (((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) ==
                         P9_TRANS_PREF_PAYLOAD_SEP) && (rsize > 1024)) {
                 req = p9_client_rpc(clnt, P9_TREAD, "dqE", fid->fid, offset,
diff --git a/net/9p/mod.c b/net/9p/mod.c
index cf8a4128cd5c..72c398275051 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -139,7 +139,7 @@ void v9fs_put_trans(struct p9_trans_module *m)
 }
 
 /**
- * v9fs_init - Initialize module
+ * init_p9 - Initialize module
  *
  */
 static int __init init_p9(void)
@@ -154,7 +154,7 @@ static int __init init_p9(void)
 }
 
 /**
- * v9fs_init - shutdown module
+ * exit_p9 - shutdown module
  *
  */
 
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 4a9084395d35..fdfdb5747f63 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -916,8 +916,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
         sin_server.sin_family = AF_INET;
         sin_server.sin_addr.s_addr = in_aton(addr);
         sin_server.sin_port = htons(opts.port);
-        err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket);
-
+        err = __sock_create(read_pnet(&current->nsproxy->net_ns), PF_INET,
+                            SOCK_STREAM, IPPROTO_TCP, &csocket, 1);
         if (err) {
                 P9_EPRINTK(KERN_ERR, "p9_trans_tcp: problem creating socket\n");
                 return err;
@@ -954,7 +954,8 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
 
         sun_server.sun_family = PF_UNIX;
         strcpy(sun_server.sun_path, addr);
-        err = sock_create_kern(PF_UNIX, SOCK_STREAM, 0, &csocket);
+        err = __sock_create(read_pnet(&current->nsproxy->net_ns), PF_UNIX,
+                            SOCK_STREAM, 0, &csocket, 1);
         if (err < 0) {
                 P9_EPRINTK(KERN_ERR, "p9_trans_unix: problem creating socket\n");
                 return err;
diff --git a/net/9p/util.c b/net/9p/util.c
index da6af81e59d9..9c1c9348ac35 100644
--- a/net/9p/util.c
+++ b/net/9p/util.c
@@ -93,7 +93,7 @@ int p9_idpool_get(struct p9_idpool *p)
 
 retry:
         if (idr_pre_get(&p->pool, GFP_NOFS) == 0)
-                return 0;
+                return -1;
 
         spin_lock_irqsave(&p->lock, flags);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index e15a82ccc05f..78b55f49de7c 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -76,7 +76,8 @@ const char *ceph_pr_addr(const struct sockaddr_storage *ss)
                 break;
 
         default:
-                sprintf(s, "(unknown sockaddr family %d)", (int)ss->ss_family);
+                snprintf(s, MAX_ADDR_STR_LEN, "(unknown sockaddr family %d)",
+                         (int)ss->ss_family);
         }
 
         return s;
@@ -598,7 +599,7 @@ static void prepare_write_keepalive(struct ceph_connection *con)
  * Connection negotiation.
  */
 
-static void prepare_connect_authorizer(struct ceph_connection *con)
+static int prepare_connect_authorizer(struct ceph_connection *con)
 {
         void *auth_buf;
         int auth_len = 0;
@@ -612,13 +613,20 @@ static void prepare_connect_authorizer(struct ceph_connection *con)
                                          con->auth_retry);
         mutex_lock(&con->mutex);
 
+        if (test_bit(CLOSED, &con->state) ||
+            test_bit(OPENING, &con->state))
+                return -EAGAIN;
+
         con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
         con->out_connect.authorizer_len = cpu_to_le32(auth_len);
 
-        con->out_kvec[con->out_kvec_left].iov_base = auth_buf;
-        con->out_kvec[con->out_kvec_left].iov_len = auth_len;
-        con->out_kvec_left++;
-        con->out_kvec_bytes += auth_len;
+        if (auth_len) {
+                con->out_kvec[con->out_kvec_left].iov_base = auth_buf;
+                con->out_kvec[con->out_kvec_left].iov_len = auth_len;
+                con->out_kvec_left++;
+                con->out_kvec_bytes += auth_len;
+        }
+        return 0;
 }
 
 /*
@@ -640,9 +648,9 @@ static void prepare_write_banner(struct ceph_messenger *msgr,
         set_bit(WRITE_PENDING, &con->state);
 }
 
-static void prepare_write_connect(struct ceph_messenger *msgr,
-                                  struct ceph_connection *con,
-                                  int after_banner)
+static int prepare_write_connect(struct ceph_messenger *msgr,
+                                 struct ceph_connection *con,
+                                 int after_banner)
 {
         unsigned global_seq = get_global_seq(con->msgr, 0);
         int proto;
@@ -683,7 +691,7 @@ static void prepare_write_connect(struct ceph_messenger *msgr,
         con->out_more = 0;
         set_bit(WRITE_PENDING, &con->state);
 
-        prepare_connect_authorizer(con);
+        return prepare_connect_authorizer(con);
 }
 
 
@@ -1065,8 +1073,10 @@ static void addr_set_port(struct sockaddr_storage *ss, int p)
         switch (ss->ss_family) {
         case AF_INET:
                 ((struct sockaddr_in *)ss)->sin_port = htons(p);
+                break;
         case AF_INET6:
                 ((struct sockaddr_in6 *)ss)->sin6_port = htons(p);
+                break;
         }
 }
 
@@ -1216,6 +1226,7 @@ static int process_connect(struct ceph_connection *con)
         u64 sup_feat = con->msgr->supported_features;
         u64 req_feat = con->msgr->required_features;
         u64 server_feat = le64_to_cpu(con->in_reply.features);
+        int ret;
 
         dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
 
@@ -1250,7 +1261,9 @@ static int process_connect(struct ceph_connection *con)
                         return -1;
                 }
                 con->auth_retry = 1;
-                prepare_write_connect(con->msgr, con, 0);
+                ret = prepare_write_connect(con->msgr, con, 0);
+                if (ret < 0)
+                        return ret;
                 prepare_read_connect(con);
                 break;
 
@@ -1277,6 +1290,9 @@ static int process_connect(struct ceph_connection *con)
                 if (con->ops->peer_reset)
                         con->ops->peer_reset(con);
                 mutex_lock(&con->mutex);
+                if (test_bit(CLOSED, &con->state) ||
+                    test_bit(OPENING, &con->state))
+                        return -EAGAIN;
                 break;
 
         case CEPH_MSGR_TAG_RETRY_SESSION:
@@ -1341,7 +1357,9 @@ static int process_connect(struct ceph_connection *con)
                  * to WAIT.  This shouldn't happen if we are the
                  * client.
                  */
-                pr_err("process_connect peer connecting WAIT\n");
+                pr_err("process_connect got WAIT as client\n");
+                con->error_msg = "protocol error, got WAIT as client";
+                return -1;
 
         default:
                 pr_err("connect protocol error, will retry\n");
@@ -1810,6 +1828,17 @@ static int try_read(struct ceph_connection *con)
 more:
         dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
              con->in_base_pos);
+
+        /*
+         * process_connect and process_message drop and re-take
+         * con->mutex.  make sure we handle a racing close or reopen.
+         */
+        if (test_bit(CLOSED, &con->state) ||
+            test_bit(OPENING, &con->state)) {
+                ret = -EAGAIN;
+                goto out;
+        }
+
         if (test_bit(CONNECTING, &con->state)) {
                 if (!test_bit(NEGOTIATING, &con->state)) {
                         dout("try_read connecting\n");
@@ -1938,8 +1967,10 @@ static void con_work(struct work_struct *work)
 {
         struct ceph_connection *con = container_of(work, struct ceph_connection,
                                                    work.work);
+        int ret;
 
         mutex_lock(&con->mutex);
+restart:
         if (test_and_clear_bit(BACKOFF, &con->state)) {
                 dout("con_work %p backing off\n", con);
                 if (queue_delayed_work(ceph_msgr_wq, &con->work,
@@ -1969,18 +2000,31 @@ static void con_work(struct work_struct *work)
                 con_close_socket(con);
         }
 
-        if (test_and_clear_bit(SOCK_CLOSED, &con->state) ||
-            try_read(con) < 0 ||
-            try_write(con) < 0) {
-                mutex_unlock(&con->mutex);
-                ceph_fault(con);     /* error/fault path */
-                goto done_unlocked;
-        }
+        if (test_and_clear_bit(SOCK_CLOSED, &con->state))
+                goto fault;
+
+        ret = try_read(con);
+        if (ret == -EAGAIN)
+                goto restart;
+        if (ret < 0)
+                goto fault;
+
+        ret = try_write(con);
+        if (ret == -EAGAIN)
+                goto restart;
+        if (ret < 0)
+                goto fault;
 
 done:
         mutex_unlock(&con->mutex);
 done_unlocked:
         con->ops->put(con);
+        return;
+
+fault:
+        mutex_unlock(&con->mutex);
+        ceph_fault(con);     /* error/fault path */
+        goto done_unlocked;
 }
 
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6b5dda1cb5df..6ea2b892f44b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -124,7 +124,7 @@ static void calc_layout(struct ceph_osd_client *osdc,
         ceph_calc_raw_layout(osdc, layout, vino.snap, off,
                              plen, &bno, req, op);
 
-        sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno);
+        snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno);
         req->r_oid_len = strlen(req->r_oid);
 }
 
@@ -1421,6 +1421,15 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 done:
         downgrade_write(&osdc->map_sem);
         ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch);
+
+        /*
+         * subscribe to subsequent osdmap updates if full to ensure
+         * we find out when we are no longer full and stop returning
+         * ENOSPC.
+         */
+        if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
+                ceph_monc_request_next_osdmap(&osdc->client->monc);
+
         send_queued(osdc);
         up_read(&osdc->map_sem);
         wake_up_all(&osdc->client->auth_wq);
@@ -1677,8 +1686,14 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
          */
         if (req->r_sent == 0) {
                 rc = __map_request(osdc, req);
-                if (rc < 0)
+                if (rc < 0) {
+                        if (nofail) {
+                                dout("osdc_start_request failed map, "
+                                     " will retry %lld\n", req->r_tid);
+                                rc = 0;
+                        }
                         goto out_unlock;
+                }
                 if (req->r_osd == NULL) {
                         dout("send_request %p no up osds in pg\n", req);
                         ceph_monc_request_next_osdmap(&osdc->client->monc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 71603ac3dff5..e97c3588c3ec 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -765,7 +765,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
         }
 
         map->epoch++;
-        map->modified = map->modified;
+        map->modified = modified;
         if (newcrush) {
                 if (map->crush)
                         crush_destroy(map->crush);
@@ -830,15 +830,20 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
                 map->osd_addr[osd] = addr;
         }
 
-        /* new_down */
+        /* new_state */
         ceph_decode_32_safe(p, end, len, bad);
         while (len--) {
                 u32 osd;
+                u8 xorstate;
                 ceph_decode_32_safe(p, end, osd, bad);
+                xorstate = **(u8 **)p;
                 (*p)++;  /* clean flag */
-                pr_info("osd%d down\n", osd);
+                if (xorstate == 0)
+                        xorstate = CEPH_OSD_UP;
+                if (xorstate & CEPH_OSD_UP)
+                        pr_info("osd%d down\n", osd);
                 if (osd < map->max_osd)
-                        map->osd_state[osd] &= ~CEPH_OSD_UP;
+                        map->osd_state[osd] ^= xorstate;
         }
 
         /* new_weight */
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 67e31276682a..cd6e4aa19dbf 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -326,10 +326,12 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
  * Run memory cache shrinker.
  */
 static int
-rpcauth_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+rpcauth_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc)
 {
         LIST_HEAD(free);
         int res;
+        int nr_to_scan = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
 
         if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
                 return (nr_to_scan == 0) ? 0 : -1;
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index d8670810db65..8657f99bfb2b 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -210,10 +210,10 @@ our $typeTypedefs = qr{(?x:
 
 our $logFunctions = qr{(?x:
         printk|
-        pr_(debug|dbg|vdbg|devel|info|warning|err|notice|alert|crit|emerg|cont)|
-        (dev|netdev|netif)_(printk|dbg|vdbg|info|warn|err|notice|alert|crit|emerg|WARN)|
+        [a-z]+_(emerg|alert|crit|err|warning|warn|notice|info|debug|dbg|vdbg|devel|cont|WARN)|
         WARN|
-        panic
+        panic|
+        MODULE_[A-Z_]+
 )};
 
 our @typeList = (
@@ -1462,7 +1462,7 @@ sub process {
 #80 column limit
                 if ($line =~ /^\+/ && $prevrawline !~ /\/\*\*/ &&
                     $rawline !~ /^.\s*\*\s*\@$Ident\s/ &&
-                    !($line =~ /^\+\s*$logFunctions\s*\(\s*(?:(KERN_\S+\s*|[^"]*))?"[X\t]*"\s*(?:,|\)\s*;)\s*$/ ||
+                    !($line =~ /^\+\s*$logFunctions\s*\(\s*(?:(KERN_\S+\s*|[^"]*))?"[X\t]*"\s*(?:|,|\)\s*;)\s*$/ ||
                     $line =~ /^\+\s*"[^"]*"\s*(?:\s*|,|\)\s*;)\s*$/) &&
                     $length > 80)
                 {
@@ -2748,6 +2748,11 @@ sub process {
                         WARN("sizeof(& should be avoided\n" . $herecurr);
                 }
 
+# check for line continuations in quoted strings with odd counts of "
+                if ($rawline =~ /\\$/ && $rawline =~ tr/"/"/ % 2) {
+                        WARN("Avoid line continuations in quoted strings\n" . $herecurr);
+                }
+
 # check for new externs in .c files.
                 if ($realfile =~ /\.c$/ && defined $stat &&
                     $stat =~ /^.\s*(?:extern\s+)?$Type\s+($Ident)(\s*)\(/s)
diff --git a/scripts/checkversion.pl b/scripts/checkversion.pl
index b444e89a0095..5e490a8ceca5 100755
--- a/scripts/checkversion.pl
+++ b/scripts/checkversion.pl
@@ -12,6 +12,7 @@ $| = 1;
 my $debugging;
 
 foreach my $file (@ARGV) {
+    next if $file =~ "include/linux/version\.h";
     # Open this file.
     open( my $f, '<', $file )
       or die "Can't open $file: $!\n";
diff --git a/scripts/export_report.pl b/scripts/export_report.pl
index 04dce7c15f83..8f79b701de87 100644
--- a/scripts/export_report.pl
+++ b/scripts/export_report.pl
@@ -25,11 +25,12 @@ sub alphabetically {
 sub print_depends_on {
         my ($href) = @_;
         print "\n";
-        while (my ($mod, $list) = each %$href) {
+        for my $mod (sort keys %$href) {
+                my $list = $href->{$mod};
                 print "\t$mod:\n";
                 foreach my $sym (sort numerically @{$list}) {
                         my ($symbol, $no) = split /\s+/, $sym;
-                        printf("\t\t%-25s\t%-25d\n", $symbol, $no);
+                        printf("\t\t%-25s\n", $symbol);
                 }
                 print "\n";
         }
@@ -49,8 +50,14 @@ sub usage {
 }
 
 sub collectcfiles {
-    my @file
-        = `cat .tmp_versions/*.mod | grep '.*\.ko\$' | sed s/\.ko$/.mod.c/`;
+    my @file;
+    while (<.tmp_versions/*.mod>) {
+        open my $fh, '<', $_ or die "cannot open $_: $!\n";
+        push (@file,
+              grep s/\.ko/.mod.c/,      # change the suffix
+              grep m/.+\.ko/,           # find the .ko path
+              <$fh>);                   # lines in opened file
+    }
     chomp @file;
     return @file;
 }
@@ -95,6 +102,8 @@ close($module_symvers);
 #
 # collect the usage count of each symbol.
 #
+my $modversion_warnings = 0;
+
 foreach my $thismod (@allcfiles) {
         my $module;
 
@@ -125,7 +134,8 @@ foreach my $thismod (@allcfiles) {
                 }
         }
         if ($state != 2) {
-                print "WARNING:$thismod is not built with CONFIG_MODVERSION enabled\n";
+                warn "WARNING:$thismod is not built with CONFIG_MODVERSIONS enabled\n";
+                $modversion_warnings++;
         }
         close($module);
 }
@@ -159,8 +169,12 @@ printf("SECTION 2:\n\tThis section reports export-symbol-usage of in-kernel
 modules. Each module lists the modules, and the symbols from that module that
 it uses.  Each listed symbol reports the number of modules using it\n");
 
+print "\nNOTE: Got $modversion_warnings CONFIG_MODVERSIONS warnings\n\n"
+    if $modversion_warnings;
+
 print "~"x80 , "\n";
-while (my ($thismod, $list) = each %MODULE) {
+for my $thismod (sort keys %MODULE) {
+        my $list = $MODULE{$thismod};
         my %depends;
         $thismod =~ s/\.mod\.c/.ko/;
         print "\t\t\t$thismod\n";
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index a834b935f536..006960ebbce9 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -26,9 +26,9 @@ RPM := $(shell if [ -x "/usr/bin/rpmbuild" ]; then echo rpmbuild; \
                    else echo rpm; fi)
 
 # Remove hyphens since they have special meaning in RPM filenames
-KERNELPATH := kernel-$(subst -,,$(KERNELRELEASE))
+KERNELPATH := kernel-$(subst -,_,$(KERNELRELEASE))
 MKSPEC     := $(srctree)/scripts/package/mkspec
-PREV       := set -e; cd ..;
+PREV       := set -e; cd -P ..;
 
 # rpm-pkg
 # ---------------------------------------------------------------------------
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index e1c1d5b8ca70..4bf17ddf7c7f 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -22,7 +22,7 @@ if [ "`grep CONFIG_DRM=y .config | cut -f2 -d\=`" = "y" ]; then
 fi
 
 PROVIDES="$PROVIDES kernel-$KERNELRELEASE"
-__KERNELRELEASE=`echo $KERNELRELEASE | sed -e "s/-//g"`
+__KERNELRELEASE=`echo $KERNELRELEASE | sed -e "s/-/_/g"`
 
 echo "Name: kernel"
 echo "Summary: The Linux Kernel"
@@ -47,6 +47,18 @@ echo ""
 echo "%description"
 echo "The Linux Kernel, the operating system core itself"
 echo ""
+echo "%package headers"
+echo "Summary: Header files for the Linux kernel for use by glibc"
+echo "Group: Development/System"
+echo "Obsoletes: kernel-headers"
+echo "Provides: kernel-headers = %{version}"
+echo "%description headers"
+echo "Kernel-headers includes the C header files that specify the interface"
+echo "between the Linux kernel and userspace libraries and programs.  The"
+echo "header files define structures and constants that are needed for"
+echo "building most standard programs and are also needed for rebuilding the"
+echo "glibc package."
+echo ""
 
 if ! $PREBUILT; then
 echo "%prep"
@@ -83,6 +95,7 @@ echo 'cp $KBUILD_IMAGE $RPM_BUILD_ROOT'"/boot/vmlinuz-$KERNELRELEASE"
 echo "%endif"
 echo "%endif"
 
+echo 'make %{?_smp_mflags} INSTALL_HDR_PATH=$RPM_BUILD_ROOT/usr headers_install'
 echo 'cp System.map $RPM_BUILD_ROOT'"/boot/System.map-$KERNELRELEASE"
 
 echo 'cp .config $RPM_BUILD_ROOT'"/boot/config-$KERNELRELEASE"
@@ -105,3 +118,7 @@ echo "/lib/modules/$KERNELRELEASE"
 echo "/lib/firmware"
 echo "/boot/*"
 echo ""
+echo "%files headers"
+echo '%defattr (-, root, root)'
+echo "/usr/include"
+echo ""
diff --git a/scripts/patch-kernel b/scripts/patch-kernel
index 46a59cae3a0a..20fb25c23382 100755
--- a/scripts/patch-kernel
+++ b/scripts/patch-kernel
@@ -250,7 +250,7 @@ while :				# incrementing SUBLEVEL (s in v.p.s)
 do
     CURRENTFULLVERSION="$VERSION.$PATCHLEVEL.$SUBLEVEL"
     EXTRAVER=
-    if [ $STOPFULLVERSION = $CURRENTFULLVERSION ]; then
+    if [ x$STOPFULLVERSION = x$CURRENTFULLVERSION ]; then
         echo "Stopping at $CURRENTFULLVERSION base as requested."
         break
     fi