Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	drivers/ata/libata-scsi.c
	include/linux/libata.h

Futher merge of Linus's head and compilation fixups.

Signed-Off-By: David Howells <dhowells@redhat.com>

588 files changed, 32298 insertions, 9297 deletions

diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index 4ac2d641fcb6..b3bd36668db3 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -6,6 +6,8 @@
     IBM Corp.
 (c) 2005 Becky Bruce <becky.bruce at freescale.com>,
     Freescale Semiconductor, FSL SOC and 32-bit additions
+(c) 2006 MontaVista Software, Inc.
+    Flash chip node definition
 
    May 18, 2005: Rev 0.1 - Initial draft, no chapter III yet.
 
@@ -1693,6 +1695,43 @@ platforms are moved over to use the flattened-device-tree model.
 		};
 	};
 
+    g) Flash chip nodes
+
+    Flash chips (Memory Technology Devices) are often used for solid state
+    file systems on embedded devices.
+
+    Required properties:
+
+     - device_type : has to be "rom"
+     - compatible : Should specify what this ROM device is compatible with
+       (i.e. "onenand"). Currently, this is most likely to be "direct-mapped"
+       (which corresponds to the MTD physmap mapping driver).
+     - regs : Offset and length of the register set (or memory mapping) for
+       the device.
+
+    Recommended properties :
+
+     - bank-width : Width of the flash data bus in bytes. Required
+       for the NOR flashes (compatible == "direct-mapped" and others) ONLY.
+     - partitions : Several pairs of 32-bit values where the first value is
+       partition's offset from the start of the device and the second one is
+       partition size in bytes with LSB used to signify a read only
+       partititon (so, the parition size should always be an even number).
+     - partition-names : The list of concatenated zero terminated strings
+       representing the partition names.
+
+   Example:
+
+ 	flash@ff000000 {
+ 		device_type = "rom";
+ 		compatible = "direct-mapped";
+ 		regs = <ff000000 01000000>;
+ 		bank-width = <4>;
+ 		partitions = <00000000 00f80000
+ 			      00f80000 00080001>;
+ 		partition-names = "fs\0firmware";
+ 	};
+
    More devices will be defined as this spec matures.
 
 
diff --git a/Documentation/powerpc/mpc52xx-device-tree-bindings.txt b/Documentation/powerpc/mpc52xx-device-tree-bindings.txt
new file mode 100644
index 000000000000..d077d764f82b
--- /dev/null
+++ b/Documentation/powerpc/mpc52xx-device-tree-bindings.txt
@@ -0,0 +1,189 @@
+MPC52xx Device Tree Bindings
+----------------------------
+
+(c) 2006 Secret Lab Technologies Ltd
+Grant Likely <grant.likely at secretlab.ca>
+
+I - Introduction
+================
+Boards supported by the arch/powerpc architecture require device tree be
+passed by the boot loader to the kernel at boot time.  The device tree
+describes what devices are present on the board and how they are
+connected.  The device tree can either be passed as a binary blob (as
+described in Documentation/powerpc/booting-without-of.txt), or passed
+by Open Firmare (IEEE 1275) compatible firmware using an OF compatible
+client interface API.
+
+This document specifies the requirements on the device-tree for mpc52xx
+based boards.  These requirements are above and beyond the details
+specified in either the OpenFirmware spec or booting-without-of.txt
+
+All new mpc52xx-based boards are expected to match this document.  In
+cases where this document is not sufficient to support a new board port,
+this document should be updated as part of adding the new board support.
+
+II - Philosophy
+===============
+The core of this document is naming convention.  The whole point of
+defining this convention is to reduce or eliminate the number of
+special cases required to support a 52xx board.  If all 52xx boards
+follow the same convention, then generic 52xx support code will work
+rather than coding special cases for each new board.
+
+This section tries to capture the thought process behind why the naming
+convention is what it is.
+
+1. Node names
+-------------
+There is strong convention/requirements already established for children
+of the root node.  'cpus' describes the processor cores, 'memory'
+describes memory, and 'chosen' provides boot configuration.  Other nodes
+are added to describe devices attached to the processor local bus.
+Following convention already established with other system-on-chip
+processors, MPC52xx boards must have an 'soc5200' node as a child of the
+root node.
+
+The soc5200 node holds child nodes for all on chip devices.  Child nodes
+are typically named after the configured function.  ie. the FEC node is
+named 'ethernet', and a PSC in uart mode is named 'serial'.
+
+2. device_type property
+-----------------------
+similar to the node name convention above; the device_type reflects the
+configured function of a device.  ie. 'serial' for a uart and 'spi' for
+an spi controller.  However, while node names *should* reflect the
+configured function, device_type *must* match the configured function
+exactly.
+
+3. compatible property
+----------------------
+Since device_type isn't enough to match devices to drivers, there also
+needs to be a naming convention for the compatible property.  Compatible
+is an list of device descriptions sorted from specific to generic.  For
+the mpc52xx, the required format for each compatible value is
+<chip>-<device>[-<mode>].  At the minimum, the list shall contain two
+items; the first specifying the exact chip, and the second specifying
+mpc52xx for the chip.
+
+ie. ethernet on mpc5200b: compatible = "mpc5200b-ethernet\0mpc52xx-ethernet"
+
+The idea here is that most drivers will match to the most generic field
+in the compatible list (mpc52xx-*), but can also test the more specific
+field for enabling bug fixes or extra features.
+
+Modal devices, like PSCs, also append the configured function to the
+end of the compatible field.  ie. A PSC in i2s mode would specify
+"mpc52xx-psc-i2s", not "mpc52xx-i2s".  This convention is chosen to
+avoid naming conflicts with non-psc devices providing the same
+function.  For example, "mpc52xx-spi" and "mpc52xx-psc-spi" describe
+the mpc5200 simple spi device and a PSC spi mode respectively.
+
+If the soc device is more generic and present on other SOCs, the
+compatible property can specify the more generic device type also.
+
+ie. mscan: compatible = "mpc5200-mscan\0mpc52xx-mscan\0fsl,mscan";
+
+At the time of writing, exact chip may be either 'mpc5200' or
+'mpc5200b'.
+
+Device drivers should always try to match as generically as possible.
+
+III - Structure
+===============
+The device tree for an mpc52xx board follows the structure defined in
+booting-without-of.txt with the following additional notes:
+
+0) the root node
+----------------
+Typical root description node; see booting-without-of
+
+1) The cpus node
+----------------
+The cpus node follows the basic layout described in booting-without-of.
+The bus-frequency property holds the XLB bus frequency
+The clock-frequency property holds the core frequency
+
+2) The memory node
+------------------
+Typical memory description node; see booting-without-of.
+
+3) The soc5200 node
+-------------------
+This node describes the on chip SOC peripherals.  Every mpc52xx based
+board will have this node, and as such there is a common naming
+convention for SOC devices.
+
+Required properties:
+name			type		description
+----			----		-----------
+device_type		string		must be "soc"
+ranges			int		should be <0 baseaddr baseaddr+10000>
+reg			int		must be <baseaddr 10000>
+
+Recommended properties:
+name			type		description
+----			----		-----------
+compatible		string		should be "<chip>-soc\0mpc52xx-soc"
+					ie. "mpc5200b-soc\0mpc52xx-soc"
+#interrupt-cells	int		must be <3>.  If it is not defined
+					here then it must be defined in every
+					soc device node.
+bus-frequency		int		IPB bus frequency in HZ.  Clock rate
+					used by most of the soc devices.
+					Defining it here avoids needing it
+					added to every device node.
+
+4) soc5200 child nodes
+----------------------
+Any on chip SOC devices available to Linux must appear as soc5200 child nodes.
+
+Note: in the tables below, '*' matches all <chip> values.  ie.
+*-pic would translate to "mpc5200-pic\0mpc52xx-pic"
+
+Required soc5200 child nodes:
+name		device_type		compatible	Description
+----		-----------		----------	-----------
+cdm@<addr>	cdm			*-cmd		Clock Distribution
+pic@<addr>	interrupt-controller	*-pic		need an interrupt
+							controller to boot
+bestcomm@<addr>	dma-controller		*-bestcomm	52xx pic also requires
+							the bestcomm device
+
+Recommended soc5200 child nodes; populate as needed for your board
+name		device_type	compatible	Description
+----		-----------	----------	-----------
+gpt@<addr>	gpt		*-gpt		General purpose timers
+rtc@<addr>	rtc		*-rtc		Real time clock
+mscan@<addr>	mscan		*-mscan		CAN bus controller
+pci@<addr>	pci		*-pci		PCI bridge
+serial@<addr>	serial		*-psc-uart	PSC in serial mode
+i2s@<addr>	i2s		*-psc-i2s	PSC in i2s mode
+ac97@<addr>	ac97		*-psc-ac97	PSC in ac97 mode
+spi@<addr>	spi		*-psc-spi	PSC in spi mode
+irda@<addr>	irda		*-psc-irda	PSC in IrDA mode
+spi@<addr>	spi		*-spi		MPC52xx spi device
+ethernet@<addr>	network		*-fec		MPC52xx ethernet device
+ata@<addr>	ata		*-ata		IDE ATA interface
+i2c@<addr>	i2c		*-i2c		I2C controller
+usb@<addr>	usb-ohci-be	*-ohci,ohci-be	USB controller
+xlb@<addr>	xlb		*-xlb		XLB arbritrator
+
+IV - Extra Notes
+================
+
+1. Interrupt mapping
+--------------------
+The mpc52xx pic driver splits hardware IRQ numbers into two levels.  The
+split reflects the layout of the PIC hardware itself, which groups
+interrupts into one of three groups; CRIT, MAIN or PERP.  Also, the
+Bestcomm dma engine has it's own set of interrupt sources which are
+cascaded off of peripheral interrupt 0, which the driver interprets as a
+fourth group, SDMA.
+
+The interrupts property for device nodes using the mpc52xx pic consists
+of three cells; <L1 L2 level>
+
+    L1 := [CRIT=0, MAIN=1, PERP=2, SDMA=3]
+    L2 := interrupt number; directly mapped from the value in the
+          "ICTL PerStat, MainStat, CritStat Encoded Register"
+    level := [LEVEL_HIGH=0, EDGE_RISING=1, EDGE_FALLING=2, LEVEL_LOW=3]
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index d684a6ac69a8..22f82f21bc60 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -74,7 +74,7 @@ Command line parameters
 
   Note: While already known devices can be added to the list of devices to be
         ignored, there will be no effect on then. However, if such a device
-        disappears and then reappeares, it will then be ignored.
+	disappears and then reappears, it will then be ignored.
 
   For example,
 	"echo add 0.0.a000-0.0.accc, 0.0.af00-0.0.afff > /proc/cio_ignore"
@@ -82,7 +82,7 @@ Command line parameters
   devices.
 
   The devices can be specified either by bus id (0.0.abcd) or, for 2.4 backward
-  compatibilty, by the device number in hexadecimal (0xabcd or abcd).
+  compatibility, by the device number in hexadecimal (0xabcd or abcd).
 
 
 * /proc/s390dbf/cio_*/ (S/390 debug feature)
diff --git a/Documentation/s390/Debugging390.txt b/Documentation/s390/Debugging390.txt
index 4dd25ee549e9..3f9ddbc23b27 100644
--- a/Documentation/s390/Debugging390.txt
+++ b/Documentation/s390/Debugging390.txt
@@ -7,7 +7,7 @@
 
 Overview of Document:
 =====================
-This document is intended to give an good overview of how to debug 
+This document is intended to give a good overview of how to debug
 Linux for s/390 & z/Architecture. It isn't intended as a complete reference & not a
 tutorial on the fundamentals of C & assembly. It doesn't go into
 390 IO in any detail. It is intended to complement the documents in the
@@ -300,7 +300,7 @@ On z/Architecture our page indexes are now 2k in size
 but only mess with 2 segment indices each time we mess with
 a PMD.
 
-3) As z/Architecture supports upto a massive 5-level page table lookup we 
+3) As z/Architecture supports up to a massive 5-level page table lookup we
 can only use 3 currently on Linux ( as this is all the generic kernel
 currently supports ) however this may change in future
 this allows us to access ( according to my sums )
@@ -502,7 +502,7 @@ Notes:
 ------
 1) The only requirement is that registers which are used
 by the callee are saved, e.g. the compiler is perfectly
-capible of using r11 for purposes other than a frame a
+capable of using r11 for purposes other than a frame a
 frame pointer if a frame pointer is not needed.
 2) In functions with variable arguments e.g. printf the calling procedure 
 is identical to one without variable arguments & the same number of 
@@ -846,7 +846,7 @@ of time searching for debugging info. The following self explanatory line should
 instead if the code isn't compiled -g, as it is much faster:
 objdump --disassemble-all --syms vmlinux > vmlinux.lst  
 
-As hard drive space is valuble most of us use the following approach.
+As hard drive space is valuable most of us use the following approach.
 1) Look at the emitted psw on the console to find the crash address in the kernel.
 2) Look at the file System.map ( in the linux directory ) produced when building 
 the kernel to find the closest address less than the current PSW to find the
@@ -902,7 +902,7 @@ A. It is a tool for intercepting calls to the kernel & logging them
 to a file & on the screen.
 
 Q. What use is it ?
-A. You can used it to find out what files a particular program opens.
+A. You can use it to find out what files a particular program opens.
 
 
 
@@ -911,7 +911,7 @@ Example 1
 If you wanted to know does ping work but didn't have the source 
 strace ping -c 1 127.0.0.1  
 & then look at the man pages for each of the syscalls below,
-( In fact this is sometimes easier than looking at some spagetti
+( In fact this is sometimes easier than looking at some spaghetti
 source which conditionally compiles for several architectures ).
 Not everything that it throws out needs to make sense immediately.
 
@@ -1037,7 +1037,7 @@ e.g. man strace, man alarm, man socket.
 
 Performance Debugging
 =====================
-gcc is capible of compiling in profiling code just add the -p option
+gcc is capable of compiling in profiling code just add the -p option
 to the CFLAGS, this obviously affects program size & performance.
 This can be used by the gprof gnu profiling tool or the
 gcov the gnu code coverage tool ( code coverage is a means of testing
@@ -1419,7 +1419,7 @@ On a SMP guest issue a command to all CPUs try prefixing the command with cpu al
 To issue a command to a particular cpu try cpu <cpu number> e.g.
 CPU 01 TR I R 2000.3000
 If you are running on a guest with several cpus & you have a IO related problem
-& cannot follow the flow of code but you know it isnt smp related.
+& cannot follow the flow of code but you know it isn't smp related.
 from the bash prompt issue
 shutdown -h now or halt.
 do a Q CPUS to find out how many cpus you have
@@ -1602,7 +1602,7 @@ V000FFFD0  00010400 80010802 8001085A 000FFFA0
 our 3rd return address is 8001085A
 
 as the 04B52002 looks suspiciously like rubbish it is fair to assume that the kernel entry routines
-for the sake of optimisation dont set up a backchain.
+for the sake of optimisation don't set up a backchain.
 
 now look at System.map to see if the addresses make any sense.
 
@@ -1638,11 +1638,11 @@ more useful information.
 
 Unlike other bus architectures modern 390 systems do their IO using mostly
 fibre optics & devices such as tapes & disks can be shared between several mainframes,
-also S390 can support upto 65536 devices while a high end PC based system might be choking 
+also S390 can support up to 65536 devices while a high end PC based system might be choking
 with around 64. Here is some of the common IO terminology
 
 Subchannel:
-This is the logical number most IO commands use to talk to an IO device there can be upto
+This is the logical number most IO commands use to talk to an IO device there can be up to
 0x10000 (65536) of these in a configuration typically there is a few hundred. Under VM
 for simplicity they are allocated contiguously, however on the native hardware they are not
 they typically stay consistent between boots provided no new hardware is inserted or removed.
@@ -1651,7 +1651,7 @@ HALT SUBCHANNEL,MODIFY SUBCHANNEL,RESUME SUBCHANNEL,START SUBCHANNEL,STORE SUBCH
 TEST SUBCHANNEL ) we use this as the ID of the device we wish to talk to, the most
 important of these instructions are START SUBCHANNEL ( to start IO ), TEST SUBCHANNEL ( to check
 whether the IO completed successfully ), & HALT SUBCHANNEL ( to kill IO ), a subchannel
-can have up to 8 channel paths to a device this offers redunancy if one is not available.
+can have up to 8 channel paths to a device this offers redundancy if one is not available.
 
 
 Device Number:
@@ -1659,7 +1659,7 @@ This number remains static & Is closely tied to the hardware, there are 65536 of
 also they are made up of a CHPID ( Channel Path ID, the most significant 8 bits ) 
 & another lsb 8 bits. These remain static even if more devices are inserted or removed
 from the hardware, there is a 1 to 1 mapping between Subchannels & Device Numbers provided
-devices arent inserted or removed.
+devices aren't inserted or removed.
 
 Channel Control Words:
 CCWS are linked lists of instructions initially pointed to by an operation request block (ORB),
@@ -1674,7 +1674,7 @@ concurrently, you check how the IO went on by issuing a TEST SUBCHANNEL at each
 from which you receive an Interruption response block (IRB). If you get channel & device end 
 status in the IRB without channel checks etc. your IO probably went okay. If you didn't you
 probably need a doctor to examine the IRB & extended status word etc.
-If an error occurs, more sophistocated control units have a facitity known as
+If an error occurs, more sophisticated control units have a facility known as
 concurrent sense this means that if an error occurs Extended sense information will
 be presented in the Extended status word in the IRB if not you have to issue a
 subsequent SENSE CCW command after the test subchannel. 
@@ -1749,7 +1749,7 @@ Interface (OEMI).
 This byte wide Parallel channel path/bus has parity & data on the "Bus" cable 
 & control lines on the "Tag" cable. These can operate in byte multiplex mode for
 sharing between several slow devices or burst mode & monopolize the channel for the
-whole burst. Upto 256 devices can be addressed  on one of these cables. These cables are
+whole burst. Up to 256 devices can be addressed  on one of these cables. These cables are
 about one inch in diameter. The maximum unextended length supported by these cables is
 125 Meters but this can be extended up to 2km with a fibre optic channel extended 
 such as a 3044. The maximum burst speed supported is 4.5 megabytes per second however
@@ -1759,7 +1759,7 @@ One of these paths can be daisy chained to up to 8 control units.
 
 ESCON if fibre optic it is also called FICON 
 Was introduced by IBM in 1990. Has 2 fibre optic cables & uses either leds or lasers
-for communication at a signaling rate of upto 200 megabits/sec. As 10bits are transferred
+for communication at a signaling rate of up to 200 megabits/sec. As 10bits are transferred
 for every 8 bits info this drops to 160 megabits/sec & to 18.6 Megabytes/sec once
 control info & CRC are added. ESCON only operates in burst mode.
  
@@ -1767,7 +1767,7 @@ ESCONs typical max cable length is 3km for the led version & 20km for the laser
 known as XDF ( extended distance facility ). This can be further extended by using an
 ESCON director which triples the above mentioned ranges. Unlike Bus & Tag as ESCON is
 serial it uses a packet switching architecture the standard Bus & Tag control protocol
-is however present within the packets. Upto 256 devices can be attached to each control 
+is however present within the packets. Up to 256 devices can be attached to each control
 unit that uses one of these interfaces.
 
 Common 390 Devices include:
@@ -2050,7 +2050,7 @@ list test.c:1,10
 
 directory:
 Adds directories to be searched for source if gdb cannot find the source.
-(note it is a bit sensititive about slashes) 
+(note it is a bit sensitive about slashes)
 e.g. To add the root of the filesystem to the searchpath do
 directory //
 
@@ -2152,7 +2152,7 @@ program as if it just crashed on your system, it is usually called core & create
 current working directory.
 This is very useful in that a customer can mail a core dump to a technical support department
 & the technical support department can reconstruct what happened.
-Provided the have an identical copy of this program with debugging symbols compiled in & 
+Provided they have an identical copy of this program with debugging symbols compiled in &
 the source base of this build is available.
 In short it is far more useful than something like a crash log could ever hope to be.
 
diff --git a/Documentation/s390/cds.txt b/Documentation/s390/cds.txt
index 32a96cc39215..05a2b4f7e38f 100644
--- a/Documentation/s390/cds.txt
+++ b/Documentation/s390/cds.txt
@@ -98,7 +98,7 @@ The following chapters describe the I/O related interface routines the
 Linux/390 common device support (CDS) provides to allow for device specific
 driver implementations on the IBM ESA/390 hardware platform. Those interfaces
 intend to provide the functionality required by every device driver
-implementaion to allow to drive a specific hardware device on the ESA/390
+implementation to allow to drive a specific hardware device on the ESA/390
 platform. Some of the interface routines are specific to Linux/390 and some
 of them can be found on other Linux platforms implementations too.
 Miscellaneous function prototypes, data declarations, and macro definitions
@@ -114,7 +114,7 @@ the ESA/390 architecture has implemented a so called channel subsystem, that
 provides a unified view of the devices physically attached to the systems.
 Though the ESA/390 hardware platform knows about a huge variety of different
 peripheral attachments like disk devices (aka. DASDs), tapes, communication
-controllers, etc. they can all by accessed by a well defined access method and
+controllers, etc. they can all be accessed by a well defined access method and
 they are presenting I/O completion a unified way : I/O interruptions. Every
 single device is uniquely identified to the system by a so called subchannel,
 where the ESA/390 architecture allows for 64k devices be attached.
@@ -338,7 +338,7 @@ DOIO_REPORT_ALL          - report all interrupt conditions
 The ccw_device_start() function returns :
 
       0 - successful completion or request successfully initiated
--EBUSY  - The device is currently processing a previous I/O request, or ther is
+-EBUSY	- The device is currently processing a previous I/O request, or there is
           a status pending at the device.
 -ENODEV - cdev is invalid, the device is not operational or the ccw_device is
           not online.
@@ -361,7 +361,7 @@ first:
 -EIO:       the common I/O layer terminated the request due to an error state
 
 If the concurrent sense flag in the extended status word in the irb is set, the
-field irb->scsw.count describes the numer of device specific sense bytes
+field irb->scsw.count describes the number of device specific sense bytes
 available in the extended control word irb->scsw.ecw[0]. No device sensing by
 the device driver itself is required.
 
@@ -410,7 +410,7 @@ ccw_device_start() must be called disabled and with the ccw device lock held.
 
 The device driver is allowed to issue the next ccw_device_start() call from
 within its interrupt handler already. It is not required to schedule a
-bottom-half, unless an non deterministically long running error recovery procedure
+bottom-half, unless a non deterministically long running error recovery procedure
 or similar needs to be scheduled. During I/O processing the Linux/390 generic
 I/O device driver support has already obtained the IRQ lock, i.e. the handler
 must not try to obtain it again when calling ccw_device_start() or we end in a
@@ -431,7 +431,7 @@ information prior to device-end the device driver urgently relies on. In this
 case all I/O interruptions are presented to the device driver until final
 status is recognized.
 
-If a device is able to recover from asynchronosly presented I/O errors, it can
+If a device is able to recover from asynchronously presented I/O errors, it can
 perform overlapping I/O using the DOIO_EARLY_NOTIFICATION flag. While some
 devices always report channel-end and device-end together, with a single
 interrupt, others present primary status (channel-end) when the channel is
diff --git a/Documentation/s390/crypto/crypto-API.txt b/Documentation/s390/crypto/crypto-API.txt
index 41a8b07da05a..71ae6ca9f2c2 100644
--- a/Documentation/s390/crypto/crypto-API.txt
+++ b/Documentation/s390/crypto/crypto-API.txt
@@ -17,8 +17,8 @@ arch/s390/crypto directory.
 2. Probing for availability of MSA
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 It should be possible to use Kernels with the z990 crypto implementations both
-on machines with MSA available an on those without MSA (pre z990 or z990
-without MSA). Therefore a simple probing mechanisms has been implemented:
+on machines with MSA available and on those without MSA (pre z990 or z990
+without MSA). Therefore a simple probing mechanism has been implemented:
 In the init function of each crypto module the availability of MSA and of the
 respective crypto algorithm in particular will be tested. If the algorithm is
 available the module will load and register its algorithm with the crypto API.
@@ -26,7 +26,7 @@ available the module will load and register its algorithm with the crypto API.
 If the respective crypto algorithm is not available, the init function will
 return -ENOSYS. In that case a fallback to the standard software implementation
 of the crypto algorithm must be taken ( -> the standard crypto modules are
-also build when compiling the kernel).
+also built when compiling the kernel).
 
 
 3. Ensuring z990 crypto module preference
diff --git a/Documentation/s390/s390dbf.txt b/Documentation/s390/s390dbf.txt
index 000230cd26db..0eb7c58916de 100644
--- a/Documentation/s390/s390dbf.txt
+++ b/Documentation/s390/s390dbf.txt
@@ -36,7 +36,7 @@ switches to the next debug area. This is done in order to be sure
 that the records which describe the origin of the exception are not
 overwritten when a wrap around for the current area occurs.
 
-The debug areas itselve are also ordered in form of a ring buffer. 
+The debug areas themselves are also ordered in form of a ring buffer.
 When an exception is thrown in the last debug area, the following debug 
 entries are then written again in the very first area.
 
@@ -55,7 +55,7 @@ The debug logs can be inspected in a live system through entries in
 the debugfs-filesystem. Under the toplevel directory "s390dbf" there is
 a directory for each registered component, which is named like the
 corresponding component. The debugfs normally should be mounted to
-/sys/kernel/debug therefore the debug feature can be accessed unter
+/sys/kernel/debug therefore the debug feature can be accessed under
 /sys/kernel/debug/s390dbf.
 
 The content of the directories are files which represent different views
@@ -87,11 +87,11 @@ There are currently 2 possible triggers, which stop the debug feature
 globally. The first possibility is to use the "debug_active" sysctl. If
 set to 1 the debug feature is running. If "debug_active" is set to 0 the
 debug feature is turned off.
-The second trigger which stops the debug feature is an kernel oops.
+The second trigger which stops the debug feature is a kernel oops.
 That prevents the debug feature from overwriting debug information that
 happened before the oops. After an oops you can reactivate the debug feature
 by piping 1 to /proc/sys/s390dbf/debug_active. Nevertheless, its not
-suggested to use an oopsed kernel in an production environment.
+suggested to use an oopsed kernel in a production environment.
 If you want to disallow the deactivation of the debug feature, you can use
 the "debug_stoppable" sysctl. If you set "debug_stoppable" to 0 the debug
 feature cannot be stopped. If the debug feature is already stopped, it
diff --git a/MAINTAINERS b/MAINTAINERS
index 8385a69138a8..5dff26814a06 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2438,6 +2438,13 @@ M:	promise@pnd-pc.demon.co.uk
 W:	http://www.pnd-pc.demon.co.uk/promise/
 S:	Maintained
 
+PS3 PLATFORM SUPPORT
+P:	Geoff Levand
+M:	geoffrey.levand@am.sony.com
+L:	linuxppc-dev@ozlabs.org
+L:	cbe-oss-dev@ozlabs.org
+S:	Supported
+
 PVRUSB2 VIDEO4LINUX DRIVER
 P:	Mike Isely
 M:	isely@pobox.com
diff --git a/arch/i386/kernel/acpi/cstate.c b/arch/i386/kernel/acpi/cstate.c
index 20563e52c622..4664b55f623e 100644
--- a/arch/i386/kernel/acpi/cstate.c
+++ b/arch/i386/kernel/acpi/cstate.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/cpu.h>
+#include <linux/sched.h>
 
 #include <acpi/processor.h>
 #include <asm/acpi.h>
diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
index 583c238e17fb..535f9794fba1 100644
--- a/arch/i386/kernel/alternative.c
+++ b/arch/i386/kernel/alternative.c
@@ -1,4 +1,5 @@
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <asm/alternative.h>
diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c
index 2d8703b7ce65..bad8b4420709 100644
--- a/arch/i386/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c
@@ -20,6 +20,7 @@
 #include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <linux/notifier.h>
+#include <linux/jiffies.h>
 #include <asm/therm_throt.h>
 
 /* How long to wait between reporting thermal events */
diff --git a/arch/m68knommu/Kconfig b/arch/m68knommu/Kconfig
index c1bc22c6d0d8..aa70dde54228 100644
--- a/arch/m68knommu/Kconfig
+++ b/arch/m68knommu/Kconfig
@@ -173,7 +173,7 @@ config CLOCK_DIV
 	  On many SoC style CPUs the master CPU clock is also used to drive 
 	  on-chip peripherals. The clock that is distributed to these
 	  peripherals is sometimes a fixed ratio of the master clock
-	  frequency. If so then set this to the divider ration of the
+	  frequency. If so then set this to the divider ratio of the
 	  master clock to the peripheral clock. If not sure then select 1.
 
 config OLDMASK
@@ -192,7 +192,7 @@ config PILOT3
 	  Support for the Palm Pilot 1000/5000, Personal/Pro and PalmIII.
 
 config XCOPILOT_BUGS
-	bool "  (X)Copilot support"
+	bool "(X)Copilot support"
 	depends on PILOT3
 	help
 	  Support the bugs of Xcopilot.
@@ -216,20 +216,20 @@ config DRAGEN2
 	  Support for the DragenEngine II board.
 
 config DIRECT_IO_ACCESS
-	bool "  Allow user to access IO directly"
+	bool "Allow user to access IO directly"
 	depends on (UCSIMM || UCDIMM || DRAGEN2)
 	help
 	  Disable the CPU internal registers protection in user mode,
           to allow a user application to read/write them.
 
 config INIT_LCD
-	bool "  Initialize LCD"
+	bool "Initialize LCD"
 	depends on (UCSIMM || UCDIMM || DRAGEN2)
 	help
 	  Initialize the LCD controller of the 68x328 processor.
 
 config MEMORY_RESERVE
-	int "  Memory reservation (MiB)"
+	int "Memory reservation (MiB)"
 	depends on (UCSIMM || UCDIMM)
 	help
 	  Reserve certain memory regions on 68x328 based boards.
@@ -409,7 +409,7 @@ config MOD5272
 	  Support for the Netburner MOD-5272 board.
 
 config ROMFS_FROM_ROM
-	bool "  ROMFS image not RAM resident"
+	bool "ROMFS image not RAM resident"
 	depends on (NETtel || SNAPGEAR)
 	help
 	  The ROMfs filesystem will stay resident in the FLASH/ROM, not be
diff --git a/arch/m68knommu/kernel/process.c b/arch/m68knommu/kernel/process.c
index c18a83306953..941955dc3b7c 100644
--- a/arch/m68knommu/kernel/process.c
+++ b/arch/m68knommu/kernel/process.c
@@ -290,7 +290,7 @@ void dump(struct pt_regs *fp)
 	unsigned char	*tp;
 	int		i;
 
-	printk(KERN_EMERG "\nCURRENT PROCESS:\n\n");
+	printk(KERN_EMERG "\n" KERN_EMERG "CURRENT PROCESS:\n" KERN_EMERG "\n");
 	printk(KERN_EMERG "COMM=%s PID=%d\n", current->comm, current->pid);
 
 	if (current->mm) {
@@ -301,7 +301,8 @@ void dump(struct pt_regs *fp)
 			(int) current->mm->end_data,
 			(int) current->mm->end_data,
 			(int) current->mm->brk);
-		printk(KERN_EMERG "USER-STACK=%08x  KERNEL-STACK=%08x\n\n",
+		printk(KERN_EMERG "USER-STACK=%08x KERNEL-STACK=%08x\n"
+			KERN_EMERG "\n",
 			(int) current->mm->start_stack,
 			(int)(((unsigned long) current) + THREAD_SIZE));
 	}
@@ -312,36 +313,35 @@ void dump(struct pt_regs *fp)
 		fp->d0, fp->d1, fp->d2, fp->d3);
 	printk(KERN_EMERG "d4: %08lx    d5: %08lx    a0: %08lx    a1: %08lx\n",
 		fp->d4, fp->d5, fp->a0, fp->a1);
-	printk(KERN_EMERG "\nUSP: %08x   TRAPFRAME: %08x\n", (unsigned int) rdusp(),
-		(unsigned int) fp);
+	printk(KERN_EMERG "\n" KERN_EMERG "USP: %08x   TRAPFRAME: %08x\n",
+		(unsigned int) rdusp(), (unsigned int) fp);
 
-	printk(KERN_EMERG "\nCODE:");
+	printk(KERN_EMERG "\n" KERN_EMERG "CODE:");
 	tp = ((unsigned char *) fp->pc) - 0x20;
 	for (sp = (unsigned long *) tp, i = 0; (i < 0x40);  i += 4) {
 		if ((i % 0x10) == 0)
-			printk(KERN_EMERG "\n%08x: ", (int) (tp + i));
-		printk(KERN_EMERG "%08x ", (int) *sp++);
+			printk("\n" KERN_EMERG "%08x: ", (int) (tp + i));
+		printk("%08x ", (int) *sp++);
 	}
-	printk(KERN_EMERG "\n");
+	printk("\n" KERN_EMERG "\n");
 
-	printk(KERN_EMERG "\nKERNEL STACK:");
+	printk(KERN_EMERG "KERNEL STACK:");
 	tp = ((unsigned char *) fp) - 0x40;
 	for (sp = (unsigned long *) tp, i = 0; (i < 0xc0); i += 4) {
 		if ((i % 0x10) == 0)
-			printk(KERN_EMERG "\n%08x: ", (int) (tp + i));
-		printk(KERN_EMERG "%08x ", (int) *sp++);
+			printk("\n" KERN_EMERG "%08x: ", (int) (tp + i));
+		printk("%08x ", (int) *sp++);
 	}
-	printk(KERN_EMERG "\n");
-	printk(KERN_EMERG "\n");
+	printk("\n" KERN_EMERG "\n");
 
-	printk(KERN_EMERG "\nUSER STACK:");
+	printk(KERN_EMERG "USER STACK:");
 	tp = (unsigned char *) (rdusp() - 0x10);
 	for (sp = (unsigned long *) tp, i = 0; (i < 0x80); i += 4) {
 		if ((i % 0x10) == 0)
-			printk(KERN_EMERG "\n%08x: ", (int) (tp + i));
-		printk(KERN_EMERG "%08x ", (int) *sp++);
+			printk("\n" KERN_EMERG "%08x: ", (int) (tp + i));
+		printk("%08x ", (int) *sp++);
 	}
-	printk(KERN_EMERG "\n\n");
+	printk("\n" KERN_EMERG "\n");
 }
 
 /*
diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c
index 7b21959eaeae..9cf2e4d1fc77 100644
--- a/arch/m68knommu/kernel/setup.c
+++ b/arch/m68knommu/kernel/setup.c
@@ -36,10 +36,7 @@
 #include <asm/setup.h>
 #include <asm/irq.h>
 #include <asm/machdep.h>
-
-#ifdef CONFIG_BLK_DEV_INITRD
 #include <asm/pgtable.h>
-#endif
 
 unsigned long memory_start;
 unsigned long memory_end;
diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c
index c3494b8447d1..3265b2d734db 100644
--- a/arch/m68knommu/kernel/sys_m68k.c
+++ b/arch/m68knommu/kernel/sys_m68k.c
@@ -137,7 +137,7 @@ asmlinkage int old_select(struct sel_arg_struct *arg)
 asmlinkage int sys_ipc (uint call, int first, int second,
 			int third, void *ptr, long fifth)
 {
-	int version;
+	int version, ret;
 
 	version = call >> 16; /* hack for backward compatibility */
 	call &= 0xffff;
@@ -190,6 +190,27 @@ asmlinkage int sys_ipc (uint call, int first, int second,
 		default:
 			return -EINVAL;
 		}
+	if (call <= SHMCTL)
+		switch (call) {
+		case SHMAT:
+			switch (version) {
+			default: {
+				ulong raddr;
+				ret = do_shmat (first, ptr, second, &raddr);
+				if (ret)
+					return ret;
+				return put_user (raddr, (ulong __user *) third);
+			}
+			}
+		case SHMDT:
+			return sys_shmdt (ptr);
+		case SHMGET:
+			return sys_shmget (first, second, third);
+		case SHMCTL:
+			return sys_shmctl (first, second, ptr);
+		default:
+			return -ENOSYS;
+		}
 
 	return -EINVAL;
 }
diff --git a/arch/m68knommu/kernel/traps.c b/arch/m68knommu/kernel/traps.c
index 17649d2543ef..9129b3a5258b 100644
--- a/arch/m68knommu/kernel/traps.c
+++ b/arch/m68knommu/kernel/traps.c
@@ -127,11 +127,12 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 		if (stack + 1 > endstack)
 			break;
 		if (i % 8 == 0)
-			printk(KERN_EMERG "\n       ");
-		printk(KERN_EMERG " %08lx", *stack++);
+			printk("\n" KERN_EMERG "       ");
+		printk(" %08lx", *stack++);
 	}
+	printk("\n");
 
-	printk(KERN_EMERG "\nCall Trace:");
+	printk(KERN_EMERG "Call Trace:");
 	i = 0;
 	while (stack + 1 <= endstack) {
 		addr = *stack++;
@@ -146,12 +147,12 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 		if (((addr >= (unsigned long) &_start) &&
 		     (addr <= (unsigned long) &_etext))) {
 			if (i % 4 == 0)
-				printk(KERN_EMERG "\n       ");
-			printk(KERN_EMERG " [<%08lx>]", addr);
+				printk("\n" KERN_EMERG "       ");
+			printk(" [<%08lx>]", addr);
 			i++;
 		}
 	}
-	printk(KERN_EMERG "\n");
+	printk("\n");
 }
 
 void bad_super_trap(struct frame *fp)
diff --git a/arch/m68knommu/platform/5307/head.S b/arch/m68knommu/platform/5307/head.S
index f2edb6498cd9..b9aa0ca29bfb 100644
--- a/arch/m68knommu/platform/5307/head.S
+++ b/arch/m68knommu/platform/5307/head.S
@@ -64,6 +64,26 @@
 	negl	%d0			/* negate bits */
 .endm
 
+#elif defined(CONFIG_M520x)
+.macro GET_MEM_SIZE
+	clrl	%d0
+	movel	MCF_MBAR+MCFSIM_SDCS0, %d2 /* Get SDRAM chip select 0 config */
+	andl	#0x1f, %d2		/* Get only the chip select size */
+	beq	3f			/* Check if it is enabled */
+	addql	#1, %d2			/* Form exponent */
+	moveql	#1, %d0
+	lsll	%d2, %d0		/* 2 ^ exponent */
+3:
+	movel	MCF_MBAR+MCFSIM_SDCS1, %d2 /* Get SDRAM chip select 1 config */
+	andl	#0x1f, %d2		/* Get only the chip select size */
+	beq	4f			/* Check if it is enabled */
+	addql	#1, %d2			/* Form exponent */
+	moveql	#1, %d1
+	lsll	%d2, %d1		/* 2 ^ exponent */
+	addl	%d1, %d0		/* Total size of SDRAM in d0 */
+4:
+.endm
+
 #else
 #error "ERROR: I don't know how to probe your boards memory size?"
 #endif
diff --git a/arch/m68knommu/platform/68360/head-ram.S b/arch/m68knommu/platform/68360/head-ram.S
index 2ea51479f13a..2ef06242398b 100644
--- a/arch/m68knommu/platform/68360/head-ram.S
+++ b/arch/m68knommu/platform/68360/head-ram.S
@@ -25,6 +25,7 @@
 .global _periph_base
 
 #define	RAMEND                      (CONFIG_RAMBASE + CONFIG_RAMSIZE)
+#define	ROMEND                      (CONFIG_ROMBASE + CONFIG_ROMSIZE)
 
 #define REGB                        0x1000
 #define PEPAR                       (_dprbase + REGB + 0x0016)
@@ -175,7 +176,7 @@ configure_chip_select_0:
 	move.l	%d0, BR0
 
 configure_chip_select_1:
-	move.l	#__rom_end, %d0
+	move.l	#ROMEND, %d0
 	subi.l	#__rom_start, %d0
 	subq.l	#0x01, %d0
 	eori.l	#SIM_OR_MASK, %d0
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 27f83e642968..4d64960be035 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -16,6 +16,7 @@ config MIPS_MTX1
 	bool "4G Systems MTX-1 board"
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
+	select RESOURCES_64BIT if PCI
 	select SOC_AU1500
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -32,6 +33,7 @@ config MIPS_PB1000
 	select SOC_AU1000
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
+	select RESOURCES_64BIT if PCI
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -41,6 +43,7 @@ config MIPS_PB1100
 	select SOC_AU1100
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
+	select RESOURCES_64BIT if PCI
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -50,6 +53,7 @@ config MIPS_PB1500
 	select SOC_AU1500
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
+	select RESOURCES_64BIT if PCI
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
@@ -59,6 +63,7 @@ config MIPS_PB1550
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
 	select MIPS_DISABLE_OBSOLETE_IDE
+	select RESOURCES_64BIT if PCI
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
@@ -67,6 +72,7 @@ config MIPS_PB1200
 	select SOC_AU1200
 	select DMA_NONCOHERENT
 	select MIPS_DISABLE_OBSOLETE_IDE
+	select RESOURCES_64BIT if PCI
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
@@ -75,6 +81,7 @@ config MIPS_DB1000
 	select SOC_AU1000
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
+	select RESOURCES_64BIT if PCI
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
@@ -91,6 +98,7 @@ config MIPS_DB1500
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
 	select MIPS_DISABLE_OBSOLETE_IDE
+	select RESOURCES_64BIT if PCI
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -101,6 +109,7 @@ config MIPS_DB1550
 	select HW_HAS_PCI
 	select DMA_NONCOHERENT
 	select MIPS_DISABLE_OBSOLETE_IDE
+	select RESOURCES_64BIT if PCI
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
@@ -1268,6 +1277,7 @@ config CPU_RM9000
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
+	select WEAK_ORDERING
 
 config CPU_SB1
 	bool "SB1"
@@ -1276,6 +1286,7 @@ config CPU_SB1
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
+	select WEAK_ORDERING
 
 endchoice
 
@@ -1336,6 +1347,8 @@ config SYS_HAS_CPU_RM9000
 config SYS_HAS_CPU_SB1
 	bool
 
+config WEAK_ORDERING
+	bool
 endmenu
 
 #
@@ -1940,6 +1953,11 @@ config COMPAT
 	depends on MIPS32_COMPAT
 	default y
 
+config SYSVIPC_COMPAT
+	bool
+	depends on COMPAT && SYSVIPC
+	default y
+
 config MIPS32_O32
 	bool "Kernel support for o32 binaries"
 	depends on MIPS32_COMPAT
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 7a3ebbeba1f3..b061c9aa6302 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -382,531 +382,6 @@ asmlinkage int sys32_sched_rr_get_interval(compat_pid_t pid,
 	return ret;
 }
 
-struct msgbuf32 { s32 mtype; char mtext[1]; };
-
-struct ipc_perm32
-{
-	key_t    	  key;
-        __compat_uid_t  uid;
-        __compat_gid_t  gid;
-        __compat_uid_t  cuid;
-        __compat_gid_t  cgid;
-        compat_mode_t	mode;
-        unsigned short  seq;
-};
-
-struct ipc64_perm32 {
-	key_t key;
-	__compat_uid_t uid;
-	__compat_gid_t gid;
-	__compat_uid_t cuid;
-	__compat_gid_t cgid;
-	compat_mode_t	mode;
-	unsigned short	seq;
-	unsigned short __pad1;
-	unsigned int __unused1;
-	unsigned int __unused2;
-};
-
-struct semid_ds32 {
-        struct ipc_perm32 sem_perm;               /* permissions .. see ipc.h */
-        compat_time_t   sem_otime;              /* last semop time */
-        compat_time_t   sem_ctime;              /* last change time */
-        u32 sem_base;              /* ptr to first semaphore in array */
-        u32 sem_pending;          /* pending operations to be processed */
-        u32 sem_pending_last;    /* last pending operation */
-        u32 undo;                  /* undo requests on this array */
-        unsigned short  sem_nsems;              /* no. of semaphores in array */
-};
-
-struct semid64_ds32 {
-	struct ipc64_perm32	sem_perm;
-	compat_time_t	sem_otime;
-	compat_time_t	sem_ctime;
-	unsigned int		sem_nsems;
-	unsigned int		__unused1;
-	unsigned int		__unused2;
-};
-
-struct msqid_ds32
-{
-        struct ipc_perm32 msg_perm;
-        u32 msg_first;
-        u32 msg_last;
-        compat_time_t   msg_stime;
-        compat_time_t   msg_rtime;
-        compat_time_t   msg_ctime;
-        u32 wwait;
-        u32 rwait;
-        unsigned short msg_cbytes;
-        unsigned short msg_qnum;
-        unsigned short msg_qbytes;
-        compat_ipc_pid_t msg_lspid;
-        compat_ipc_pid_t msg_lrpid;
-};
-
-struct msqid64_ds32 {
-	struct ipc64_perm32 msg_perm;
-	compat_time_t msg_stime;
-	unsigned int __unused1;
-	compat_time_t msg_rtime;
-	unsigned int __unused2;
-	compat_time_t msg_ctime;
-	unsigned int __unused3;
-	unsigned int msg_cbytes;
-	unsigned int msg_qnum;
-	unsigned int msg_qbytes;
-	compat_pid_t msg_lspid;
-	compat_pid_t msg_lrpid;
-	unsigned int __unused4;
-	unsigned int __unused5;
-};
-
-struct shmid_ds32 {
-        struct ipc_perm32       shm_perm;
-        int                     shm_segsz;
-        compat_time_t		shm_atime;
-        compat_time_t		shm_dtime;
-        compat_time_t		shm_ctime;
-        compat_ipc_pid_t    shm_cpid;
-        compat_ipc_pid_t    shm_lpid;
-        unsigned short          shm_nattch;
-};
-
-struct shmid64_ds32 {
-	struct ipc64_perm32	shm_perm;
-	compat_size_t		shm_segsz;
-	compat_time_t		shm_atime;
-	compat_time_t		shm_dtime;
-	compat_time_t shm_ctime;
-	compat_pid_t shm_cpid;
-	compat_pid_t shm_lpid;
-	unsigned int shm_nattch;
-	unsigned int __unused1;
-	unsigned int __unused2;
-};
-
-struct ipc_kludge32 {
-	u32 msgp;
-	s32 msgtyp;
-};
-
-static int
-do_sys32_semctl(int first, int second, int third, void __user *uptr)
-{
-	union semun fourth;
-	u32 pad;
-	int err, err2;
-	struct semid64_ds s;
-	mm_segment_t old_fs;
-
-	if (!uptr)
-		return -EINVAL;
-	err = -EFAULT;
-	if (get_user (pad, (u32 __user *)uptr))
-		return err;
-	if ((third & ~IPC_64) == SETVAL)
-		fourth.val = (int)pad;
-	else
-		fourth.__pad = (void __user *)A(pad);
-	switch (third & ~IPC_64) {
-	case IPC_INFO:
-	case IPC_RMID:
-	case IPC_SET:
-	case SEM_INFO:
-	case GETVAL:
-	case GETPID:
-	case GETNCNT:
-	case GETZCNT:
-	case GETALL:
-	case SETVAL:
-	case SETALL:
-		err = sys_semctl (first, second, third, fourth);
-		break;
-
-	case IPC_STAT:
-	case SEM_STAT:
-		fourth.__pad = (struct semid64_ds __user *)&s;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = sys_semctl(first, second, third | IPC_64, fourth);
-		set_fs(old_fs);
-
-		if (third & IPC_64) {
-			struct semid64_ds32 __user *usp64 = (struct semid64_ds32 __user *) A(pad);
-
-			if (!access_ok(VERIFY_WRITE, usp64, sizeof(*usp64))) {
-				err = -EFAULT;
-				break;
-			}
-			err2 = __put_user(s.sem_perm.key, &usp64->sem_perm.key);
-			err2 |= __put_user(s.sem_perm.uid, &usp64->sem_perm.uid);
-			err2 |= __put_user(s.sem_perm.gid, &usp64->sem_perm.gid);
-			err2 |= __put_user(s.sem_perm.cuid, &usp64->sem_perm.cuid);
-			err2 |= __put_user(s.sem_perm.cgid, &usp64->sem_perm.cgid);
-			err2 |= __put_user(s.sem_perm.mode, &usp64->sem_perm.mode);
-			err2 |= __put_user(s.sem_perm.seq, &usp64->sem_perm.seq);
-			err2 |= __put_user(s.sem_otime, &usp64->sem_otime);
-			err2 |= __put_user(s.sem_ctime, &usp64->sem_ctime);
-			err2 |= __put_user(s.sem_nsems, &usp64->sem_nsems);
-		} else {
-			struct semid_ds32 __user *usp32 = (struct semid_ds32 __user *) A(pad);
-
-			if (!access_ok(VERIFY_WRITE, usp32, sizeof(*usp32))) {
-				err = -EFAULT;
-				break;
-			}
-			err2 = __put_user(s.sem_perm.key, &usp32->sem_perm.key);
-			err2 |= __put_user(s.sem_perm.uid, &usp32->sem_perm.uid);
-			err2 |= __put_user(s.sem_perm.gid, &usp32->sem_perm.gid);
-			err2 |= __put_user(s.sem_perm.cuid, &usp32->sem_perm.cuid);
-			err2 |= __put_user(s.sem_perm.cgid, &usp32->sem_perm.cgid);
-			err2 |= __put_user(s.sem_perm.mode, &usp32->sem_perm.mode);
-			err2 |= __put_user(s.sem_perm.seq, &usp32->sem_perm.seq);
-			err2 |= __put_user(s.sem_otime, &usp32->sem_otime);
-			err2 |= __put_user(s.sem_ctime, &usp32->sem_ctime);
-			err2 |= __put_user(s.sem_nsems, &usp32->sem_nsems);
-		}
-		if (err2)
-			err = -EFAULT;
-		break;
-
-	default:
-		err = - EINVAL;
-		break;
-	}
-
-	return err;
-}
-
-static int
-do_sys32_msgsnd (int first, int second, int third, void __user *uptr)
-{
-	struct msgbuf32 __user *up = (struct msgbuf32 __user *)uptr;
-	struct msgbuf *p;
-	mm_segment_t old_fs;
-	int err;
-
-	if (second < 0)
-		return -EINVAL;
-	p = kmalloc (second + sizeof (struct msgbuf)
-				    + 4, GFP_USER);
-	if (!p)
-		return -ENOMEM;
-	err = get_user (p->mtype, &up->mtype);
-	if (err)
-		goto out;
-	err |= __copy_from_user (p->mtext, &up->mtext, second);
-	if (err)
-		goto out;
-	old_fs = get_fs ();
-	set_fs (KERNEL_DS);
-	err = sys_msgsnd (first, (struct msgbuf __user *)p, second, third);
-	set_fs (old_fs);
-out:
-	kfree (p);
-
-	return err;
-}
-
-static int
-do_sys32_msgrcv (int first, int second, int msgtyp, int third,
-		 int version, void __user *uptr)
-{
-	struct msgbuf32 __user *up;
-	struct msgbuf *p;
-	mm_segment_t old_fs;
-	int err;
-
-	if (!version) {
-		struct ipc_kludge32 __user *uipck = (struct ipc_kludge32 __user *)uptr;
-		struct ipc_kludge32 ipck;
-
-		err = -EINVAL;
-		if (!uptr)
-			goto out;
-		err = -EFAULT;
-		if (copy_from_user (&ipck, uipck, sizeof (struct ipc_kludge32)))
-			goto out;
-		uptr = (void __user *)AA(ipck.msgp);
-		msgtyp = ipck.msgtyp;
-	}
-
-	if (second < 0)
-		return -EINVAL;
-	err = -ENOMEM;
-	p = kmalloc (second + sizeof (struct msgbuf) + 4, GFP_USER);
-	if (!p)
-		goto out;
-	old_fs = get_fs ();
-	set_fs (KERNEL_DS);
-	err = sys_msgrcv (first, (struct msgbuf __user *)p, second + 4, msgtyp, third);
-	set_fs (old_fs);
-	if (err < 0)
-		goto free_then_out;
-	up = (struct msgbuf32 __user *)uptr;
-	if (put_user (p->mtype, &up->mtype) ||
-	    __copy_to_user (&up->mtext, p->mtext, err))
-		err = -EFAULT;
-free_then_out:
-	kfree (p);
-out:
-	return err;
-}
-
-static int
-do_sys32_msgctl (int first, int second, void __user *uptr)
-{
-	int err = -EINVAL, err2;
-	struct msqid64_ds m;
-	struct msqid_ds32 __user *up32 = (struct msqid_ds32 __user *)uptr;
-	struct msqid64_ds32 __user *up64 = (struct msqid64_ds32 __user *)uptr;
-	mm_segment_t old_fs;
-
-	switch (second & ~IPC_64) {
-	case IPC_INFO:
-	case IPC_RMID:
-	case MSG_INFO:
-		err = sys_msgctl (first, second, (struct msqid_ds __user *)uptr);
-		break;
-
-	case IPC_SET:
-		if (second & IPC_64) {
-			if (!access_ok(VERIFY_READ, up64, sizeof(*up64))) {
-				err = -EFAULT;
-				break;
-			}
-			err = __get_user(m.msg_perm.uid, &up64->msg_perm.uid);
-			err |= __get_user(m.msg_perm.gid, &up64->msg_perm.gid);
-			err |= __get_user(m.msg_perm.mode, &up64->msg_perm.mode);
-			err |= __get_user(m.msg_qbytes, &up64->msg_qbytes);
-		} else {
-			if (!access_ok(VERIFY_READ, up32, sizeof(*up32))) {
-				err = -EFAULT;
-				break;
-			}
-			err = __get_user(m.msg_perm.uid, &up32->msg_perm.uid);
-			err |= __get_user(m.msg_perm.gid, &up32->msg_perm.gid);
-			err |= __get_user(m.msg_perm.mode, &up32->msg_perm.mode);
-			err |= __get_user(m.msg_qbytes, &up32->msg_qbytes);
-		}
-		if (err)
-			break;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = sys_msgctl(first, second | IPC_64, (struct msqid_ds __user *)&m);
-		set_fs(old_fs);
-		break;
-
-	case IPC_STAT:
-	case MSG_STAT:
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = sys_msgctl(first, second | IPC_64, (struct msqid_ds __user *)&m);
-		set_fs(old_fs);
-		if (second & IPC_64) {
-			if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64))) {
-				err = -EFAULT;
-				break;
-			}
-			err2 = __put_user(m.msg_perm.key, &up64->msg_perm.key);
-			err2 |= __put_user(m.msg_perm.uid, &up64->msg_perm.uid);
-			err2 |= __put_user(m.msg_perm.gid, &up64->msg_perm.gid);
-			err2 |= __put_user(m.msg_perm.cuid, &up64->msg_perm.cuid);
-			err2 |= __put_user(m.msg_perm.cgid, &up64->msg_perm.cgid);
-			err2 |= __put_user(m.msg_perm.mode, &up64->msg_perm.mode);
-			err2 |= __put_user(m.msg_perm.seq, &up64->msg_perm.seq);
-			err2 |= __put_user(m.msg_stime, &up64->msg_stime);
-			err2 |= __put_user(m.msg_rtime, &up64->msg_rtime);
-			err2 |= __put_user(m.msg_ctime, &up64->msg_ctime);
-			err2 |= __put_user(m.msg_cbytes, &up64->msg_cbytes);
-			err2 |= __put_user(m.msg_qnum, &up64->msg_qnum);
-			err2 |= __put_user(m.msg_qbytes, &up64->msg_qbytes);
-			err2 |= __put_user(m.msg_lspid, &up64->msg_lspid);
-			err2 |= __put_user(m.msg_lrpid, &up64->msg_lrpid);
-			if (err2)
-				err = -EFAULT;
-		} else {
-			if (!access_ok(VERIFY_WRITE, up32, sizeof(*up32))) {
-				err = -EFAULT;
-				break;
-			}
-			err2 = __put_user(m.msg_perm.key, &up32->msg_perm.key);
-			err2 |= __put_user(m.msg_perm.uid, &up32->msg_perm.uid);
-			err2 |= __put_user(m.msg_perm.gid, &up32->msg_perm.gid);
-			err2 |= __put_user(m.msg_perm.cuid, &up32->msg_perm.cuid);
-			err2 |= __put_user(m.msg_perm.cgid, &up32->msg_perm.cgid);
-			err2 |= __put_user(m.msg_perm.mode, &up32->msg_perm.mode);
-			err2 |= __put_user(m.msg_perm.seq, &up32->msg_perm.seq);
-			err2 |= __put_user(m.msg_stime, &up32->msg_stime);
-			err2 |= __put_user(m.msg_rtime, &up32->msg_rtime);
-			err2 |= __put_user(m.msg_ctime, &up32->msg_ctime);
-			err2 |= __put_user(m.msg_cbytes, &up32->msg_cbytes);
-			err2 |= __put_user(m.msg_qnum, &up32->msg_qnum);
-			err2 |= __put_user(m.msg_qbytes, &up32->msg_qbytes);
-			err2 |= __put_user(m.msg_lspid, &up32->msg_lspid);
-			err2 |= __put_user(m.msg_lrpid, &up32->msg_lrpid);
-			if (err2)
-				err = -EFAULT;
-		}
-		break;
-	}
-
-	return err;
-}
-
-static int
-do_sys32_shmat (int first, int second, int third, int version, void __user *uptr)
-{
-	unsigned long raddr;
-	u32 __user *uaddr = (u32 __user *)A((u32)third);
-	int err = -EINVAL;
-
-	if (version == 1)
-		return err;
-	err = do_shmat (first, uptr, second, &raddr);
-	if (err)
-		return err;
-	err = put_user (raddr, uaddr);
-	return err;
-}
-
-struct shm_info32 {
-	int used_ids;
-	u32 shm_tot, shm_rss, shm_swp;
-	u32 swap_attempts, swap_successes;
-};
-
-static int
-do_sys32_shmctl (int first, int second, void __user *uptr)
-{
-	struct shmid64_ds32 __user *up64 = (struct shmid64_ds32 __user *)uptr;
-	struct shmid_ds32 __user *up32 = (struct shmid_ds32 __user *)uptr;
-	struct shm_info32 __user *uip = (struct shm_info32 __user *)uptr;
-	int err = -EFAULT, err2;
-	struct shmid64_ds s64;
-	mm_segment_t old_fs;
-	struct shm_info si;
-	struct shmid_ds s;
-
-	switch (second & ~IPC_64) {
-	case IPC_INFO:
-		second = IPC_INFO; /* So that we don't have to translate it */
-	case IPC_RMID:
-	case SHM_LOCK:
-	case SHM_UNLOCK:
-		err = sys_shmctl(first, second, (struct shmid_ds __user *)uptr);
-		break;
-	case IPC_SET:
-		if (second & IPC_64) {
-			err = get_user(s.shm_perm.uid, &up64->shm_perm.uid);
-			err |= get_user(s.shm_perm.gid, &up64->shm_perm.gid);
-			err |= get_user(s.shm_perm.mode, &up64->shm_perm.mode);
-		} else {
-			err = get_user(s.shm_perm.uid, &up32->shm_perm.uid);
-			err |= get_user(s.shm_perm.gid, &up32->shm_perm.gid);
-			err |= get_user(s.shm_perm.mode, &up32->shm_perm.mode);
-		}
-		if (err)
-			break;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = sys_shmctl(first, second & ~IPC_64, (struct shmid_ds __user *)&s);
-		set_fs(old_fs);
-		break;
-
-	case IPC_STAT:
-	case SHM_STAT:
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = sys_shmctl(first, second | IPC_64, (void __user *) &s64);
-		set_fs(old_fs);
-		if (err < 0)
-			break;
-		if (second & IPC_64) {
-			if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64))) {
-				err = -EFAULT;
-				break;
-			}
-			err2 = __put_user(s64.shm_perm.key, &up64->shm_perm.key);
-			err2 |= __put_user(s64.shm_perm.uid, &up64->shm_perm.uid);
-			err2 |= __put_user(s64.shm_perm.gid, &up64->shm_perm.gid);
-			err2 |= __put_user(s64.shm_perm.cuid, &up64->shm_perm.cuid);
-			err2 |= __put_user(s64.shm_perm.cgid, &up64->shm_perm.cgid);
-			err2 |= __put_user(s64.shm_perm.mode, &up64->shm_perm.mode);
-			err2 |= __put_user(s64.shm_perm.seq, &up64->shm_perm.seq);
-			err2 |= __put_user(s64.shm_atime, &up64->shm_atime);
-			err2 |= __put_user(s64.shm_dtime, &up64->shm_dtime);
-			err2 |= __put_user(s64.shm_ctime, &up64->shm_ctime);
-			err2 |= __put_user(s64.shm_segsz, &up64->shm_segsz);
-			err2 |= __put_user(s64.shm_nattch, &up64->shm_nattch);
-			err2 |= __put_user(s64.shm_cpid, &up64->shm_cpid);
-			err2 |= __put_user(s64.shm_lpid, &up64->shm_lpid);
-		} else {
-			if (!access_ok(VERIFY_WRITE, up32, sizeof(*up32))) {
-				err = -EFAULT;
-				break;
-			}
-			err2 = __put_user(s64.shm_perm.key, &up32->shm_perm.key);
-			err2 |= __put_user(s64.shm_perm.uid, &up32->shm_perm.uid);
-			err2 |= __put_user(s64.shm_perm.gid, &up32->shm_perm.gid);
-			err2 |= __put_user(s64.shm_perm.cuid, &up32->shm_perm.cuid);
-			err2 |= __put_user(s64.shm_perm.cgid, &up32->shm_perm.cgid);
-			err2 |= __put_user(s64.shm_perm.mode, &up32->shm_perm.mode);
-			err2 |= __put_user(s64.shm_perm.seq, &up32->shm_perm.seq);
-			err2 |= __put_user(s64.shm_atime, &up32->shm_atime);
-			err2 |= __put_user(s64.shm_dtime, &up32->shm_dtime);
-			err2 |= __put_user(s64.shm_ctime, &up32->shm_ctime);
-			err2 |= __put_user(s64.shm_segsz, &up32->shm_segsz);
-			err2 |= __put_user(s64.shm_nattch, &up32->shm_nattch);
-			err2 |= __put_user(s64.shm_cpid, &up32->shm_cpid);
-			err2 |= __put_user(s64.shm_lpid, &up32->shm_lpid);
-		}
-		if (err2)
-			err = -EFAULT;
-		break;
-
-	case SHM_INFO:
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = sys_shmctl(first, second, (void __user *)&si);
-		set_fs(old_fs);
-		if (err < 0)
-			break;
-		err2 = put_user(si.used_ids, &uip->used_ids);
-		err2 |= __put_user(si.shm_tot, &uip->shm_tot);
-		err2 |= __put_user(si.shm_rss, &uip->shm_rss);
-		err2 |= __put_user(si.shm_swp, &uip->shm_swp);
-		err2 |= __put_user(si.swap_attempts, &uip->swap_attempts);
-		err2 |= __put_user (si.swap_successes, &uip->swap_successes);
-		if (err2)
-			err = -EFAULT;
-		break;
-
-	default:
-		err = -EINVAL;
-		break;
-	}
-
-	return err;
-}
-
-static int sys32_semtimedop(int semid, struct sembuf __user *tsems, int nsems,
-                            const struct compat_timespec __user *timeout32)
-{
-	struct compat_timespec t32;
-	struct timespec __user *t64 = compat_alloc_user_space(sizeof(*t64));
-
-	if (copy_from_user(&t32, timeout32, sizeof(t32)))
-		return -EFAULT;
-
-	if (put_user(t32.tv_sec, &t64->tv_sec) ||
-	    put_user(t32.tv_nsec, &t64->tv_nsec))
-		return -EFAULT;
-
-	return sys_semtimedop(semid, tsems, nsems, t64);
-}
-
 asmlinkage long
 sys32_ipc (u32 call, int first, int second, int third, u32 ptr, u32 fifth)
 {
@@ -918,48 +393,43 @@ sys32_ipc (u32 call, int first, int second, int third, u32 ptr, u32 fifth)
 	switch (call) {
 	case SEMOP:
 		/* struct sembuf is the same on 32 and 64bit :)) */
-		err = sys_semtimedop (first, (struct sembuf __user *)AA(ptr), second,
-		                      NULL);
+		err = sys_semtimedop(first, compat_ptr(ptr), second, NULL);
 		break;
 	case SEMTIMEDOP:
-		err = sys32_semtimedop (first, (struct sembuf __user *)AA(ptr), second,
-		                      (const struct compat_timespec __user *)AA(fifth));
+		err = compat_sys_semtimedop(first, compat_ptr(ptr), second,
+					    compat_ptr(fifth));
 		break;
 	case SEMGET:
-		err = sys_semget (first, second, third);
+		err = sys_semget(first, second, third);
 		break;
 	case SEMCTL:
-		err = do_sys32_semctl (first, second, third,
-				       (void __user *)AA(ptr));
+		err = compat_sys_semctl(first, second, third, compat_ptr(ptr));
 		break;
-
 	case MSGSND:
-		err = do_sys32_msgsnd (first, second, third,
-				       (void __user *)AA(ptr));
+		err = compat_sys_msgsnd(first, second, third, compat_ptr(ptr));
 		break;
 	case MSGRCV:
-		err = do_sys32_msgrcv (first, second, fifth, third,
-				       version, (void __user *)AA(ptr));
+		err = compat_sys_msgrcv(first, second, fifth, third,
+					version, compat_ptr(ptr));
 		break;
 	case MSGGET:
-		err = sys_msgget ((key_t) first, second);
+		err = sys_msgget((key_t) first, second);
 		break;
 	case MSGCTL:
-		err = do_sys32_msgctl (first, second, (void __user *)AA(ptr));
+		err = compat_sys_msgctl(first, second, compat_ptr(ptr));
 		break;
-
 	case SHMAT:
-		err = do_sys32_shmat (first, second, third,
-				      version, (void __user *)AA(ptr));
+		err = compat_sys_shmat(first, second, third, version,
+				       compat_ptr(ptr));
 		break;
 	case SHMDT:
-		err = sys_shmdt ((char __user *)A(ptr));
+		err = sys_shmdt(compat_ptr(ptr));
 		break;
 	case SHMGET:
-		err = sys_shmget (first, (unsigned)second, third);
+		err = sys_shmget(first, (unsigned)second, third);
 		break;
 	case SHMCTL:
-		err = do_sys32_shmctl (first, second, (void __user *)AA(ptr));
+		err = compat_sys_shmctl(first, second, compat_ptr(ptr));
 		break;
 	default:
 		err = -EINVAL;
@@ -969,18 +439,16 @@ sys32_ipc (u32 call, int first, int second, int third, u32 ptr, u32 fifth)
 	return err;
 }
 
-asmlinkage long sys32_shmat(int shmid, char __user *shmaddr,
-			  int shmflg, int32_t __user *addr)
+#ifdef CONFIG_MIPS32_N32
+asmlinkage long sysn32_semctl(int semid, int semnum, int cmd, union semun arg)
 {
-	unsigned long raddr;
-	int err;
-
-	err = do_shmat(shmid, shmaddr, shmflg, &raddr);
-	if (err)
-		return err;
-
-	return put_user(raddr, addr);
+	/* compat_sys_semctl expects a pointer to union semun */
+	u32 __user *uptr = compat_alloc_user_space(sizeof(u32));
+	if (put_user(ptr_to_compat(arg.__pad), uptr))
+		return -EFAULT;
+	return compat_sys_semctl(semid, semnum, cmd, uptr);
 }
+#endif
 
 struct sysctl_args32
 {
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 5b18f265d75b..34567d81f940 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -149,8 +149,8 @@ EXPORT(sysn32_call_table)
 	PTR	sys_mincore
 	PTR	sys_madvise
 	PTR	sys_shmget
-	PTR	sys32_shmat
-	PTR	sys_shmctl			/* 6030 */
+	PTR	sys_shmat
+	PTR	compat_sys_shmctl			/* 6030 */
 	PTR	sys_dup
 	PTR	sys_dup2
 	PTR	sys_pause
@@ -184,12 +184,12 @@ EXPORT(sysn32_call_table)
 	PTR	sys32_newuname
 	PTR	sys_semget
 	PTR	sys_semop
-	PTR	sys_semctl
+	PTR	sysn32_semctl
 	PTR	sys_shmdt			/* 6065 */
 	PTR	sys_msgget
-	PTR	sys_msgsnd
-	PTR	sys_msgrcv
-	PTR	sys_msgctl
+	PTR	compat_sys_msgsnd
+	PTR	compat_sys_msgrcv
+	PTR	compat_sys_msgctl
 	PTR	compat_sys_fcntl		/* 6070 */
 	PTR	sys_flock
 	PTR	sys_fsync
@@ -335,7 +335,7 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_fcntl64
 	PTR	sys_set_tid_address
 	PTR	sys_restart_syscall
-	PTR	sys_semtimedop			/* 6215 */
+	PTR	compat_sys_semtimedop			/* 6215 */
 	PTR	sys_fadvise64_64
 	PTR	compat_sys_statfs64
 	PTR	compat_sys_fstatfs64
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 49db516789e0..f2a8701e414d 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -172,7 +172,7 @@ int smp_call_function (void (*func) (void *info), void *info, int retry,
 
 	spin_lock(&smp_call_lock);
 	call_data = &data;
-	mb();
+	smp_mb();
 
 	/* Send a message to all other CPUs and wait for them to respond */
 	for_each_online_cpu(i)
@@ -204,7 +204,7 @@ void smp_call_function_interrupt(void)
 	 * Notify initiating CPU that I've grabbed the data and am
 	 * about to execute the function.
 	 */
-	mb();
+	smp_mb();
 	atomic_inc(&call_data->started);
 
 	/*
@@ -215,7 +215,7 @@ void smp_call_function_interrupt(void)
 	irq_exit();
 
 	if (wait) {
-		mb();
+		smp_mb();
 		atomic_inc(&call_data->finished);
 	}
 }
diff --git a/arch/mips/lib-32/Makefile b/arch/mips/lib-32/Makefile
index ad285786e74b..dcd4d2ed2ac4 100644
--- a/arch/mips/lib-32/Makefile
+++ b/arch/mips/lib-32/Makefile
@@ -2,7 +2,7 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o memset.o watch.o
+lib-y	+= memset.o watch.o
 
 obj-$(CONFIG_CPU_MIPS32)	+= dump_tlb.o
 obj-$(CONFIG_CPU_MIPS64)	+= dump_tlb.o
diff --git a/arch/mips/lib-32/csum_partial.S b/arch/mips/lib-32/csum_partial.S
deleted file mode 100644
index ea257dbdcc40..000000000000
--- a/arch/mips/lib-32/csum_partial.S
+++ /dev/null
@@ -1,240 +0,0 @@
-/*
- * 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) 1998 Ralf Baechle
- */
-#include <asm/asm.h>
-#include <asm/regdef.h>
-
-#define ADDC(sum,reg)			\
-	addu	sum, reg;		\
-	sltu	v1, sum, reg;		\
-	addu	sum, v1
-
-#define CSUM_BIGCHUNK(src, offset, sum, t0, t1, t2, t3) \
-	lw	t0, (offset + 0x00)(src); \
-	lw	t1, (offset + 0x04)(src); \
-	lw	t2, (offset + 0x08)(src); \
-	lw	t3, (offset + 0x0c)(src); \
-	ADDC(sum, t0);                    \
-	ADDC(sum, t1);                    \
-	ADDC(sum, t2);                    \
-	ADDC(sum, t3);                    \
-	lw	t0, (offset + 0x10)(src); \
-	lw	t1, (offset + 0x14)(src); \
-	lw	t2, (offset + 0x18)(src); \
-	lw	t3, (offset + 0x1c)(src); \
-	ADDC(sum, t0);                    \
-	ADDC(sum, t1);                    \
-	ADDC(sum, t2);                    \
-	ADDC(sum, t3);                    \
-
-/*
- * a0: source address
- * a1: length of the area to checksum
- * a2: partial checksum
- */
-
-#define src a0
-#define dest a1
-#define sum v0
-
-	.text
-	.set	noreorder
-
-/* unknown src alignment and < 8 bytes to go  */
-small_csumcpy:
-	move	a1, t2
-
-	andi	t0, a1, 4
-	beqz	t0, 1f
-	 andi	t0, a1, 2
-
-	/* Still a full word to go  */
-	ulw	t1, (src)
-	addiu	src, 4
-	ADDC(sum, t1)
-
-1:	move	t1, zero
-	beqz	t0, 1f
-	 andi	t0, a1, 1
-
-	/* Still a halfword to go  */
-	ulhu	t1, (src)
-	addiu	src, 2
-
-1:	beqz	t0, 1f
-	 sll	t1, t1, 16
-
-	lbu	t2, (src)
-	 nop
-
-#ifdef __MIPSEB__
-	sll	t2, t2, 8
-#endif
-	or	t1, t2
-
-1:	ADDC(sum, t1)
-
-	/* fold checksum */
-	sll	v1, sum, 16
-	addu	sum, v1
-	sltu	v1, sum, v1
-	srl	sum, sum, 16
-	addu	sum, v1
-
-	/* odd buffer alignment? */
-	beqz	t7, 1f
-	 nop
-	sll	v1, sum, 8
-	srl	sum, sum, 8
-	or	sum, v1
-	andi	sum, 0xffff
-1:
-	.set	reorder
-	/* Add the passed partial csum.  */
-	ADDC(sum, a2)
-	jr	ra
-	.set	noreorder
-
-/* ------------------------------------------------------------------------- */
-
-	.align	5
-LEAF(csum_partial)
-	move	sum, zero
-	move	t7, zero
-
-	sltiu	t8, a1, 0x8
-	bnez	t8, small_csumcpy		/* < 8 bytes to copy */
-	 move	t2, a1
-
-	beqz	a1, out
-	 andi	t7, src, 0x1			/* odd buffer? */
-
-hword_align:
-	beqz	t7, word_align
-	 andi	t8, src, 0x2
-
-	lbu	t0, (src)
-	subu	a1, a1, 0x1
-#ifdef __MIPSEL__
-	sll	t0, t0, 8
-#endif
-	ADDC(sum, t0)
-	addu	src, src, 0x1
-	andi	t8, src, 0x2
-
-word_align:
-	beqz	t8, dword_align
-	 sltiu	t8, a1, 56
-
-	lhu	t0, (src)
-	subu	a1, a1, 0x2
-	ADDC(sum, t0)
-	sltiu	t8, a1, 56
-	addu	src, src, 0x2
-
-dword_align:
-	bnez	t8, do_end_words
-	 move	t8, a1
-
-	andi	t8, src, 0x4
-	beqz	t8, qword_align
-	 andi	t8, src, 0x8
-
-	lw	t0, 0x00(src)
-	subu	a1, a1, 0x4
-	ADDC(sum, t0)
-	addu	src, src, 0x4
-	andi	t8, src, 0x8
-
-qword_align:
-	beqz	t8, oword_align
-	 andi	t8, src, 0x10
-
-	lw	t0, 0x00(src)
-	lw	t1, 0x04(src)
-	subu	a1, a1, 0x8
-	ADDC(sum, t0)
-	ADDC(sum, t1)
-	addu	src, src, 0x8
-	andi	t8, src, 0x10
-
-oword_align:
-	beqz	t8, begin_movement
-	 srl	t8, a1, 0x7
-
-	lw	t3, 0x08(src)
-	lw	t4, 0x0c(src)
-	lw	t0, 0x00(src)
-	lw	t1, 0x04(src)
-	ADDC(sum, t3)
-	ADDC(sum, t4)
-	ADDC(sum, t0)
-	ADDC(sum, t1)
-	subu	a1, a1, 0x10
-	addu	src, src, 0x10
-	srl	t8, a1, 0x7
-
-begin_movement:
-	beqz	t8, 1f
-	 andi	t2, a1, 0x40
-
-move_128bytes:
-	CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4)
-	CSUM_BIGCHUNK(src, 0x20, sum, t0, t1, t3, t4)
-	CSUM_BIGCHUNK(src, 0x40, sum, t0, t1, t3, t4)
-	CSUM_BIGCHUNK(src, 0x60, sum, t0, t1, t3, t4)
-	subu	t8, t8, 0x01
-	bnez	t8, move_128bytes
-	 addu	src, src, 0x80
-
-1:
-	beqz	t2, 1f
-	 andi	t2, a1, 0x20
-
-move_64bytes:
-	CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4)
-	CSUM_BIGCHUNK(src, 0x20, sum, t0, t1, t3, t4)
-	addu	src, src, 0x40
-
-1:
-	beqz	t2, do_end_words
-	 andi	t8, a1, 0x1c
-
-move_32bytes:
-	CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4)
-	andi	t8, a1, 0x1c
-	addu	src, src, 0x20
-
-do_end_words:
-	beqz	t8, maybe_end_cruft
-	 srl	t8, t8, 0x2
-
-end_words:
-	lw	t0, (src)
-	subu	t8, t8, 0x1
-	ADDC(sum, t0)
-	bnez	t8, end_words
-	 addu	src, src, 0x4
-
-maybe_end_cruft:
-	andi	t2, a1, 0x3
-
-small_memcpy:
- j small_csumcpy; move a1, t2
-	beqz	t2, out
-	 move	a1, t2
-
-end_bytes:
-	lb	t0, (src)
-	subu	a1, a1, 0x1
-	bnez	a2, end_bytes
-	 addu	src, src, 0x1
-
-out:
-	jr	ra
-	 move	v0, sum
-	END(csum_partial)
diff --git a/arch/mips/lib-64/Makefile b/arch/mips/lib-64/Makefile
index ad285786e74b..dcd4d2ed2ac4 100644
--- a/arch/mips/lib-64/Makefile
+++ b/arch/mips/lib-64/Makefile
@@ -2,7 +2,7 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o memset.o watch.o
+lib-y	+= memset.o watch.o
 
 obj-$(CONFIG_CPU_MIPS32)	+= dump_tlb.o
 obj-$(CONFIG_CPU_MIPS64)	+= dump_tlb.o
diff --git a/arch/mips/lib-64/csum_partial.S b/arch/mips/lib-64/csum_partial.S
deleted file mode 100644
index 25aba660cc9c..000000000000
--- a/arch/mips/lib-64/csum_partial.S
+++ /dev/null
@@ -1,242 +0,0 @@
-/*
- * 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.
- *
- * Quick'n'dirty IP checksum ...
- *
- * Copyright (C) 1998, 1999 Ralf Baechle
- * Copyright (C) 1999 Silicon Graphics, Inc.
- */
-#include <asm/asm.h>
-#include <asm/regdef.h>
-
-#define ADDC(sum,reg)						\
-	addu	sum, reg;					\
-	sltu	v1, sum, reg;					\
-	addu	sum, v1
-
-#define CSUM_BIGCHUNK(src, offset, sum, t0, t1, t2, t3)		\
-	lw	t0, (offset + 0x00)(src);			\
-	lw	t1, (offset + 0x04)(src);			\
-	lw	t2, (offset + 0x08)(src); 			\
-	lw	t3, (offset + 0x0c)(src); 			\
-	ADDC(sum, t0);						\
-	ADDC(sum, t1);						\
-	ADDC(sum, t2);						\
-	ADDC(sum, t3);						\
-	lw	t0, (offset + 0x10)(src);			\
-	lw	t1, (offset + 0x14)(src);			\
-	lw	t2, (offset + 0x18)(src);			\
-	lw	t3, (offset + 0x1c)(src);			\
-	ADDC(sum, t0);						\
-	ADDC(sum, t1);						\
-	ADDC(sum, t2);						\
-	ADDC(sum, t3);						\
-
-/*
- * a0: source address
- * a1: length of the area to checksum
- * a2: partial checksum
- */
-
-#define src a0
-#define sum v0
-
-	.text
-	.set	noreorder
-
-/* unknown src alignment and < 8 bytes to go  */
-small_csumcpy:
-	move	a1, ta2
-
-	andi	ta0, a1, 4
-	beqz	ta0, 1f
-	 andi	ta0, a1, 2
-
-	/* Still a full word to go  */
-	ulw	ta1, (src)
-	daddiu	src, 4
-	ADDC(sum, ta1)
-
-1:	move	ta1, zero
-	beqz	ta0, 1f
-	 andi	ta0, a1, 1
-
-	/* Still a halfword to go  */
-	ulhu	ta1, (src)
-	daddiu	src, 2
-
-1:	beqz	ta0, 1f
-	 sll	ta1, ta1, 16
-
-	lbu	ta2, (src)
-	 nop
-
-#ifdef __MIPSEB__
-	sll	ta2, ta2, 8
-#endif
-	or	ta1, ta2
-
-1:	ADDC(sum, ta1)
-
-	/* fold checksum */
-	sll	v1, sum, 16
-	addu	sum, v1
-	sltu	v1, sum, v1
-	srl	sum, sum, 16
-	addu	sum, v1
-
-	/* odd buffer alignment? */
-	beqz	t3, 1f
-	 nop
-	sll	v1, sum, 8
-	srl	sum, sum, 8
-	or	sum, v1
-	andi	sum, 0xffff
-1:
-	.set	reorder
-	/* Add the passed partial csum.  */
-	ADDC(sum, a2)
-	jr	ra
-	.set	noreorder
-
-/* ------------------------------------------------------------------------- */
-
-	.align	5
-LEAF(csum_partial)
-	move	sum, zero
-	move	t3, zero
-
-	sltiu	t8, a1, 0x8
-	bnez	t8, small_csumcpy		/* < 8 bytes to copy */
-	 move	ta2, a1
-
-	beqz	a1, out
-	 andi	t3, src, 0x1			/* odd buffer? */
-
-hword_align:
-	beqz	t3, word_align
-	 andi	t8, src, 0x2
-
-	lbu	ta0, (src)
-	dsubu	a1, a1, 0x1
-#ifdef __MIPSEL__
-	sll	ta0, ta0, 8
-#endif
-	ADDC(sum, ta0)
-	daddu	src, src, 0x1
-	andi	t8, src, 0x2
-
-word_align:
-	beqz	t8, dword_align
-	 sltiu	t8, a1, 56
-
-	lhu	ta0, (src)
-	dsubu	a1, a1, 0x2
-	ADDC(sum, ta0)
-	sltiu	t8, a1, 56
-	daddu	src, src, 0x2
-
-dword_align:
-	bnez	t8, do_end_words
-	 move	t8, a1
-
-	andi	t8, src, 0x4
-	beqz	t8, qword_align
-	 andi	t8, src, 0x8
-
-	lw	ta0, 0x00(src)
-	dsubu	a1, a1, 0x4
-	ADDC(sum, ta0)
-	daddu	src, src, 0x4
-	andi	t8, src, 0x8
-
-qword_align:
-	beqz	t8, oword_align
-	 andi	t8, src, 0x10
-
-	lw	ta0, 0x00(src)
-	lw	ta1, 0x04(src)
-	dsubu	a1, a1, 0x8
-	ADDC(sum, ta0)
-	ADDC(sum, ta1)
-	daddu	src, src, 0x8
-	andi	t8, src, 0x10
-
-oword_align:
-	beqz	t8, begin_movement
-	 dsrl	t8, a1, 0x7
-
-	lw	ta3, 0x08(src)
-	lw	t0, 0x0c(src)
-	lw	ta0, 0x00(src)
-	lw	ta1, 0x04(src)
-	ADDC(sum, ta3)
-	ADDC(sum, t0)
-	ADDC(sum, ta0)
-	ADDC(sum, ta1)
-	dsubu	a1, a1, 0x10
-	daddu	src, src, 0x10
-	dsrl	t8, a1, 0x7
-
-begin_movement:
-	beqz	t8, 1f
-	 andi	ta2, a1, 0x40
-
-move_128bytes:
-	CSUM_BIGCHUNK(src, 0x00, sum, ta0, ta1, ta3, t0)
-	CSUM_BIGCHUNK(src, 0x20, sum, ta0, ta1, ta3, t0)
-	CSUM_BIGCHUNK(src, 0x40, sum, ta0, ta1, ta3, t0)
-	CSUM_BIGCHUNK(src, 0x60, sum, ta0, ta1, ta3, t0)
-	dsubu	t8, t8, 0x01
-	bnez	t8, move_128bytes
-	 daddu	src, src, 0x80
-
-1:
-	beqz	ta2, 1f
-	 andi	ta2, a1, 0x20
-
-move_64bytes:
-	CSUM_BIGCHUNK(src, 0x00, sum, ta0, ta1, ta3, t0)
-	CSUM_BIGCHUNK(src, 0x20, sum, ta0, ta1, ta3, t0)
-	daddu	src, src, 0x40
-
-1:
-	beqz	ta2, do_end_words
-	 andi	t8, a1, 0x1c
-
-move_32bytes:
-	CSUM_BIGCHUNK(src, 0x00, sum, ta0, ta1, ta3, t0)
-	andi	t8, a1, 0x1c
-	daddu	src, src, 0x20
-
-do_end_words:
-	beqz	t8, maybe_end_cruft
-	 dsrl	t8, t8, 0x2
-
-end_words:
-	lw	ta0, (src)
-	dsubu	t8, t8, 0x1
-	ADDC(sum, ta0)
-	bnez	t8, end_words
-	 daddu	src, src, 0x4
-
-maybe_end_cruft:
-	andi	ta2, a1, 0x3
-
-small_memcpy:
- j small_csumcpy; move a1, ta2		/* XXX ??? */
-	beqz	t2, out
-	 move	a1, ta2
-
-end_bytes:
-	lb	ta0, (src)
-	dsubu	a1, a1, 0x1
-	bnez	a2, end_bytes
-	 daddu	src, src, 0x1
-
-out:
-	jr	ra
-	 move	v0, sum
-	END(csum_partial)
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index b225543f5302..888b61ea12fe 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -2,8 +2,8 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial_copy.o memcpy.o promlib.o strlen_user.o strncpy_user.o \
-	   strnlen_user.o uncached.o
+lib-y	+= csum_partial.o csum_partial_copy.o memcpy.o promlib.o \
+	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
 
 obj-y	+= iomap.o
 
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
new file mode 100644
index 000000000000..15611d9df7ac
--- /dev/null
+++ b/arch/mips/lib/csum_partial.S
@@ -0,0 +1,258 @@
+/*
+ * 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.
+ *
+ * Quick'n'dirty IP checksum ...
+ *
+ * Copyright (C) 1998, 1999 Ralf Baechle
+ * Copyright (C) 1999 Silicon Graphics, Inc.
+ */
+#include <asm/asm.h>
+#include <asm/regdef.h>
+
+#ifdef CONFIG_64BIT
+#define T0	ta0
+#define T1	ta1
+#define T2	ta2
+#define T3	ta3
+#define T4	t0
+#define T7	t3
+#else
+#define T0	t0
+#define T1	t1
+#define T2	t2
+#define T3	t3
+#define T4	t4
+#define T7	t7
+#endif
+
+#define ADDC(sum,reg)						\
+	addu	sum, reg;					\
+	sltu	v1, sum, reg;					\
+	addu	sum, v1
+
+#define CSUM_BIGCHUNK(src, offset, sum, _t0, _t1, _t2, _t3)	\
+	lw	_t0, (offset + 0x00)(src);			\
+	lw	_t1, (offset + 0x04)(src);			\
+	lw	_t2, (offset + 0x08)(src); 			\
+	lw	_t3, (offset + 0x0c)(src); 			\
+	ADDC(sum, _t0);						\
+	ADDC(sum, _t1);						\
+	ADDC(sum, _t2);						\
+	ADDC(sum, _t3);						\
+	lw	_t0, (offset + 0x10)(src);			\
+	lw	_t1, (offset + 0x14)(src);			\
+	lw	_t2, (offset + 0x18)(src);			\
+	lw	_t3, (offset + 0x1c)(src);			\
+	ADDC(sum, _t0);						\
+	ADDC(sum, _t1);						\
+	ADDC(sum, _t2);						\
+	ADDC(sum, _t3);						\
+
+/*
+ * a0: source address
+ * a1: length of the area to checksum
+ * a2: partial checksum
+ */
+
+#define src a0
+#define sum v0
+
+	.text
+	.set	noreorder
+
+/* unknown src alignment and < 8 bytes to go  */
+small_csumcpy:
+	move	a1, T2
+
+	andi	T0, a1, 4
+	beqz	T0, 1f
+	 andi	T0, a1, 2
+
+	/* Still a full word to go  */
+	ulw	T1, (src)
+	PTR_ADDIU	src, 4
+	ADDC(sum, T1)
+
+1:	move	T1, zero
+	beqz	T0, 1f
+	 andi	T0, a1, 1
+
+	/* Still a halfword to go  */
+	ulhu	T1, (src)
+	PTR_ADDIU	src, 2
+
+1:	beqz	T0, 1f
+	 sll	T1, T1, 16
+
+	lbu	T2, (src)
+	 nop
+
+#ifdef __MIPSEB__
+	sll	T2, T2, 8
+#endif
+	or	T1, T2
+
+1:	ADDC(sum, T1)
+
+	/* fold checksum */
+	sll	v1, sum, 16
+	addu	sum, v1
+	sltu	v1, sum, v1
+	srl	sum, sum, 16
+	addu	sum, v1
+
+	/* odd buffer alignment? */
+	beqz	T7, 1f
+	 nop
+	sll	v1, sum, 8
+	srl	sum, sum, 8
+	or	sum, v1
+	andi	sum, 0xffff
+1:
+	.set	reorder
+	/* Add the passed partial csum.  */
+	ADDC(sum, a2)
+	jr	ra
+	.set	noreorder
+
+/* ------------------------------------------------------------------------- */
+
+	.align	5
+LEAF(csum_partial)
+	move	sum, zero
+	move	T7, zero
+
+	sltiu	t8, a1, 0x8
+	bnez	t8, small_csumcpy		/* < 8 bytes to copy */
+	 move	T2, a1
+
+	beqz	a1, out
+	 andi	T7, src, 0x1			/* odd buffer? */
+
+hword_align:
+	beqz	T7, word_align
+	 andi	t8, src, 0x2
+
+	lbu	T0, (src)
+	LONG_SUBU	a1, a1, 0x1
+#ifdef __MIPSEL__
+	sll	T0, T0, 8
+#endif
+	ADDC(sum, T0)
+	PTR_ADDU	src, src, 0x1
+	andi	t8, src, 0x2
+
+word_align:
+	beqz	t8, dword_align
+	 sltiu	t8, a1, 56
+
+	lhu	T0, (src)
+	LONG_SUBU	a1, a1, 0x2
+	ADDC(sum, T0)
+	sltiu	t8, a1, 56
+	PTR_ADDU	src, src, 0x2
+
+dword_align:
+	bnez	t8, do_end_words
+	 move	t8, a1
+
+	andi	t8, src, 0x4
+	beqz	t8, qword_align
+	 andi	t8, src, 0x8
+
+	lw	T0, 0x00(src)
+	LONG_SUBU	a1, a1, 0x4
+	ADDC(sum, T0)
+	PTR_ADDU	src, src, 0x4
+	andi	t8, src, 0x8
+
+qword_align:
+	beqz	t8, oword_align
+	 andi	t8, src, 0x10
+
+	lw	T0, 0x00(src)
+	lw	T1, 0x04(src)
+	LONG_SUBU	a1, a1, 0x8
+	ADDC(sum, T0)
+	ADDC(sum, T1)
+	PTR_ADDU	src, src, 0x8
+	andi	t8, src, 0x10
+
+oword_align:
+	beqz	t8, begin_movement
+	 LONG_SRL	t8, a1, 0x7
+
+	lw	T3, 0x08(src)
+	lw	T4, 0x0c(src)
+	lw	T0, 0x00(src)
+	lw	T1, 0x04(src)
+	ADDC(sum, T3)
+	ADDC(sum, T4)
+	ADDC(sum, T0)
+	ADDC(sum, T1)
+	LONG_SUBU	a1, a1, 0x10
+	PTR_ADDU	src, src, 0x10
+	LONG_SRL	t8, a1, 0x7
+
+begin_movement:
+	beqz	t8, 1f
+	 andi	T2, a1, 0x40
+
+move_128bytes:
+	CSUM_BIGCHUNK(src, 0x00, sum, T0, T1, T3, T4)
+	CSUM_BIGCHUNK(src, 0x20, sum, T0, T1, T3, T4)
+	CSUM_BIGCHUNK(src, 0x40, sum, T0, T1, T3, T4)
+	CSUM_BIGCHUNK(src, 0x60, sum, T0, T1, T3, T4)
+	LONG_SUBU	t8, t8, 0x01
+	bnez	t8, move_128bytes
+	 PTR_ADDU	src, src, 0x80
+
+1:
+	beqz	T2, 1f
+	 andi	T2, a1, 0x20
+
+move_64bytes:
+	CSUM_BIGCHUNK(src, 0x00, sum, T0, T1, T3, T4)
+	CSUM_BIGCHUNK(src, 0x20, sum, T0, T1, T3, T4)
+	PTR_ADDU	src, src, 0x40
+
+1:
+	beqz	T2, do_end_words
+	 andi	t8, a1, 0x1c
+
+move_32bytes:
+	CSUM_BIGCHUNK(src, 0x00, sum, T0, T1, T3, T4)
+	andi	t8, a1, 0x1c
+	PTR_ADDU	src, src, 0x20
+
+do_end_words:
+	beqz	t8, maybe_end_cruft
+	 LONG_SRL	t8, t8, 0x2
+
+end_words:
+	lw	T0, (src)
+	LONG_SUBU	t8, t8, 0x1
+	ADDC(sum, T0)
+	bnez	t8, end_words
+	 PTR_ADDU	src, src, 0x4
+
+maybe_end_cruft:
+	andi	T2, a1, 0x3
+
+small_memcpy:
+ j small_csumcpy; move a1, T2		/* XXX ??? */
+	beqz	t2, out
+	 move	a1, T2
+
+end_bytes:
+	lb	T0, (src)
+	LONG_SUBU	a1, a1, 0x1
+	bnez	a2, end_bytes
+	 PTR_ADDU	src, src, 0x1
+
+out:
+	jr	ra
+	 move	v0, sum
+	END(csum_partial)
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index ac342f5643c9..defa1f1452ad 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -43,7 +43,7 @@
 #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X)
 #include <asm/sibyte/sb1250_regs.h>
 #else
-#error invalid SiByte board configuation
+#error invalid SiByte board configuration
 #endif
 #include <asm/sibyte/sb1250_genbus.h>
 #include <asm/sibyte/board.h>
@@ -53,7 +53,7 @@ extern void bcm1480_setup(void);
 #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X)
 extern void sb1250_setup(void);
 #else
-#error invalid SiByte board configuation
+#error invalid SiByte board configuration
 #endif
 
 extern int xicor_probe(void);
@@ -90,7 +90,7 @@ void __init plat_timer_setup(struct irqaction *irq)
 #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X)
 	sb1250_time_init();
 #else
-#error invalid SiByte board configuation
+#error invalid SiByte board configuration
 #endif
 }
 
@@ -111,7 +111,7 @@ void __init plat_mem_setup(void)
 #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X)
 	sb1250_setup();
 #else
-#error invalid SiByte board configuation
+#error invalid SiByte board configuration
 #endif
 
 	panic_timeout = 5;  /* For debug.  */
diff --git a/arch/powerpc/.gitignore b/arch/powerpc/.gitignore
new file mode 100644
index 000000000000..a1a869c8c840
--- /dev/null
+++ b/arch/powerpc/.gitignore
@@ -0,0 +1 @@
+include
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 116d7d3683ed..291c95ac4b31 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -112,7 +112,7 @@ choice
 	default 6xx
 
 config CLASSIC32
-	bool "6xx/7xx/74xx"
+	bool "52xx/6xx/7xx/74xx"
 	select PPC_FPU
 	select 6xx
 	help
@@ -121,16 +121,18 @@ config CLASSIC32
 	  versions (821, 823, 850, 855, 860, 52xx, 82xx, 83xx), the AMCC
 	  embedded versions (403 and 405) and the high end 64 bit Power
 	  processors (POWER 3, POWER4, and IBM PPC970 also known as G5).
+
+	  This option is the catch-all for 6xx types, including some of the
+	  embedded versions.  Unless there is see an option for the specific
+	  chip family you are using, you want this option.
+	  
+	  You do not want this if you are building a kernel for a 64 bit
+	  IBM RS/6000 or an Apple G5, choose 6xx.
+	  
+	  If unsure, select this option
 	  
-	  Unless you are building a kernel for one of the embedded processor
-	  systems, 64 bit IBM RS/6000 or an Apple G5, choose 6xx.
 	  Note that the kernel runs in 32-bit mode even on 64-bit chips.
 
-config PPC_52xx
-	bool "Freescale 52xx"
-	select 6xx
-	select PPC_FPU
-	
 config PPC_82xx
 	bool "Freescale 82xx"
 	select 6xx
@@ -160,9 +162,11 @@ config PPC_86xx
 
 config 40x
 	bool "AMCC 40x"
+	select PPC_DCR_NATIVE
 
 config 44x
 	bool "AMCC 44x"
+	select PPC_DCR_NATIVE
 
 config 8xx
 	bool "Freescale 8xx"
@@ -208,6 +212,24 @@ config PPC_FPU
 	bool
 	default y if PPC64
 
+config PPC_DCR_NATIVE
+	bool
+	default n
+
+config PPC_DCR_MMIO
+	bool
+	default n
+
+config PPC_DCR
+	bool
+	depends on PPC_DCR_NATIVE || PPC_DCR_MMIO
+	default y
+
+config PPC_OF_PLATFORM_PCI
+	bool
+	depends on PPC64 # not supported on 32 bits yet
+	default n
+
 config BOOKE
 	bool
 	depends on E200 || E500
@@ -227,6 +249,7 @@ config PTE_64BIT
 config PHYS_64BIT
 	bool 'Large physical address support' if E500
 	depends on 44x || E500
+	select RESOURCES_64BIT
 	default y if 44x
 	---help---
 	  This option enables kernel support for larger than 32-bit physical
@@ -369,11 +392,13 @@ config PPC_PSERIES
 	select PPC_RTAS
 	select RTAS_ERROR_LOGGING
 	select PPC_UDBG_16550
+	select PPC_NATIVE
 	default y
 
 config PPC_ISERIES
 	bool "IBM Legacy iSeries"
 	depends on PPC_MULTIPLATFORM && PPC64
+	select PPC_INDIRECT_IO
 
 config PPC_CHRP
 	bool "Common Hardware Reference Platform (CHRP) based machines"
@@ -384,14 +409,35 @@ config PPC_CHRP
 	select PPC_RTAS
 	select PPC_MPC106
 	select PPC_UDBG_16550
+	select PPC_NATIVE
+	default y
+
+config PPC_MPC52xx
+	bool
+	default n
+
+config PPC_EFIKA
+	bool "bPlan Efika 5k2. MPC5200B based computer"
+	depends on PPC_MULTIPLATFORM && PPC32
+	select PPC_RTAS
+	select RTAS_PROC
+	select PPC_MPC52xx
+	select PPC_NATIVE
 	default y
 
+config PPC_LITE5200
+	bool "Freescale Lite5200 Eval Board"
+	depends on PPC_MULTIPLATFORM && PPC32
+	select PPC_MPC52xx
+	default n
+
 config PPC_PMAC
 	bool "Apple PowerMac based machines"
 	depends on PPC_MULTIPLATFORM
 	select MPIC
 	select PPC_INDIRECT_PCI if PPC32
 	select PPC_MPC106 if PPC32
+	select PPC_NATIVE
 	default y
 
 config PPC_PMAC64
@@ -411,6 +457,7 @@ config PPC_PREP
 	select PPC_I8259
 	select PPC_INDIRECT_PCI
 	select PPC_UDBG_16550
+	select PPC_NATIVE
 	default y
 
 config PPC_MAPLE
@@ -422,6 +469,7 @@ config PPC_MAPLE
 	select GENERIC_TBSYNC
 	select PPC_UDBG_16550
 	select PPC_970_NAP
+	select PPC_NATIVE
 	default n
 	help
           This option enables support for the Maple 970FX Evaluation Board.
@@ -434,6 +482,7 @@ config PPC_PASEMI
 	select MPIC
 	select PPC_UDBG_16550
 	select GENERIC_TBSYNC
+	select PPC_NATIVE
 	help
 	  This option enables support for PA Semi's PWRficient line
 	  of SoC processors, including PA6T-1682M
@@ -445,6 +494,11 @@ config PPC_CELL
 config PPC_CELL_NATIVE
 	bool
 	select PPC_CELL
+	select PPC_DCR_MMIO
+	select PPC_OF_PLATFORM_PCI
+	select PPC_INDIRECT_IO
+	select PPC_NATIVE
+	select MPIC
 	default n
 
 config PPC_IBM_CELL_BLADE
@@ -456,6 +510,22 @@ config PPC_IBM_CELL_BLADE
 	select PPC_UDBG_16550
 	select UDBG_RTAS_CONSOLE
 
+config PPC_PS3
+	bool "Sony PS3"
+	depends on PPC_MULTIPLATFORM && PPC64
+	select PPC_CELL
+	help
+	  This option enables support for the Sony PS3 game console
+	  and other platforms using the PS3 hypervisor.
+
+config PPC_NATIVE
+	bool
+	depends on PPC_MULTIPLATFORM
+	help
+	  Support for running natively on the hardware, i.e. without
+	  a hypervisor. This option is not user-selectable but should
+	  be selected by all platforms that need it.
+
 config UDBG_RTAS_CONSOLE
 	bool "RTAS based debug console"
 	depends on PPC_RTAS
@@ -517,6 +587,15 @@ config PPC_970_NAP
 	bool
 	default n
 
+config PPC_INDIRECT_IO
+	bool
+	select GENERIC_IOMAP
+	default n
+
+config GENERIC_IOMAP
+	bool
+	default n
+
 source "drivers/cpufreq/Kconfig"
 
 config CPU_FREQ_PMAC
@@ -594,12 +673,6 @@ config TAU_AVERAGE
 
 	  If in doubt, say N here.
 
-config PPC_TODC
-	depends on EMBEDDED6xx
-	bool "Generic Time-of-day Clock (TODC) support"
-	---help---
-	  This adds support for many TODC/RTC chips.
-
 endmenu
 
 source arch/powerpc/platforms/embedded6xx/Kconfig
@@ -610,6 +683,7 @@ source arch/powerpc/platforms/85xx/Kconfig
 source arch/powerpc/platforms/86xx/Kconfig
 source arch/powerpc/platforms/8xx/Kconfig
 source arch/powerpc/platforms/cell/Kconfig
+source arch/powerpc/platforms/ps3/Kconfig
 
 menu "Kernel options"
 
@@ -790,7 +864,6 @@ source "arch/powerpc/platforms/prep/Kconfig"
 
 config CMDLINE_BOOL
 	bool "Default bootloader kernel arguments"
-	depends on !PPC_ISERIES
 
 config CMDLINE
 	string "Initial kernel command string"
@@ -880,7 +953,7 @@ config MCA
 
 config PCI
 	bool "PCI support" if 40x || CPM2 || PPC_83xx || PPC_85xx || PPC_86xx \
-		|| PPC_MPC52xx || (EMBEDDED && PPC_ISERIES) || MPC7448HPC2
+		|| PPC_MPC52xx || (EMBEDDED && PPC_ISERIES) || MPC7448HPC2 || PPC_PS3
 	default y if !40x && !CPM2 && !8xx && !APUS && !PPC_83xx \
 		&& !PPC_85xx && !PPC_86xx
 	default PCI_PERMEDIA if !4xx && !CPM2 && !8xx && APUS
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 5ad149b47e34..f0e51edde022 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -77,7 +77,7 @@ config KGDB_CONSOLE
 
 config XMON
 	bool "Include xmon kernel debugger"
-	depends on DEBUGGER && !PPC_ISERIES
+	depends on DEBUGGER
 	help
 	  Include in-kernel hooks for the xmon kernel monitor/debugger.
 	  Unless you are intending to debug the kernel, say N here.
@@ -98,6 +98,15 @@ config XMON_DEFAULT
 	  xmon is normally disabled unless booted with 'xmon=on'.
 	  Use 'xmon=off' to disable xmon init during runtime.
 
+config XMON_DISASSEMBLY
+	bool "Include disassembly support in xmon"
+	depends on XMON
+	default y
+	help
+	  Include support for disassembling in xmon. You probably want
+	  to say Y here, unless you're building for a memory-constrained
+	  system.
+
 config IRQSTACKS
 	bool "Use separate kernel stacks when processing interrupts"
 	depends on PPC64
@@ -116,7 +125,7 @@ config BDI_SWITCH
 
 config BOOTX_TEXT
 	bool "Support for early boot text console (BootX or OpenFirmware only)"
-	depends PPC_OF && !PPC_ISERIES
+	depends PPC_OF
 	help
 	  Say Y here to see progress messages from the boot firmware in text
 	  mode. Requires either BootX or Open Firmware.
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 45c9ad23526e..0734b2fc1d95 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -1,19 +1,32 @@
 addnote
+empty.c
+hack-coff
 infblock.c
 infblock.h
 infcodes.c
 infcodes.h
 inffast.c
 inffast.h
+inffixed.h
 inflate.c
+inflate.h
 inftrees.c
 inftrees.h
 infutil.c
 infutil.h
 kernel-vmlinux.strip.c
 kernel-vmlinux.strip.gz
+mktree
 uImage
 zImage
+zImage.chrp
+zImage.coff
+zImage.coff.lds
+zImage.lds
+zImage.miboot
+zImage.pmac
+zImage.pseries
+zImage.sandpoint
 zImage.vmode
 zconf.h
 zlib.h
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 4b2be611f77f..343dbcfdf08a 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -40,7 +40,8 @@ zliblinuxheader := zlib.h zconf.h zutil.h
 $(addprefix $(obj)/,$(zlib) main.o): $(addprefix $(obj)/,$(zliblinuxheader)) \
 		$(addprefix $(obj)/,$(zlibheader))
 
-src-wlib := string.S stdio.c main.c div64.S $(zlib)
+src-wlib := string.S stdio.c main.c flatdevtree.c flatdevtree_misc.c \
+		ns16550.c serial.c simple_alloc.c div64.S util.S $(zlib)
 src-plat := of.c
 src-boot := crt0.S $(src-wlib) $(src-plat) empty.c
 
@@ -74,7 +75,7 @@ $(obj)/zImage.lds $(obj)/zImage.coff.lds: $(obj)/%: $(srctree)/$(src)/%.S
 	@cp $< $@
 
 clean-files := $(zlib) $(zlibheader) $(zliblinuxheader) \
-		$(obj)/empty.c
+		empty.c zImage zImage.coff.lds zImage.lds zImage.sandpoint
 
 quiet_cmd_bootcc = BOOTCC  $@
       cmd_bootcc = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
@@ -93,13 +94,13 @@ $(patsubst %.S,%.o, $(filter %.S, $(src-boot))): %.o: %.S
 $(obj)/wrapper.a: $(obj-wlib)
 	$(call cmd,bootar)
 
-hostprogs-y	:= addnote addRamDisk hack-coff
+hostprogs-y	:= addnote addRamDisk hack-coff mktree
 
 extra-y		:= $(obj)/crt0.o $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
 		   $(obj)/zImage.lds $(obj)/zImage.coff.lds
 
 wrapper		:=$(srctree)/$(src)/wrapper
-wrapperbits	:= $(extra-y) $(addprefix $(obj)/,addnote hack-coff)
+wrapperbits	:= $(extra-y) $(addprefix $(obj)/,addnote hack-coff mktree)
 
 #############
 # Bits for building various flavours of zImage
@@ -148,13 +149,18 @@ $(obj)/zImage.miboot: vmlinux $(wrapperbits)
 $(obj)/zImage.initrd.miboot: vmlinux $(wrapperbits)
 	$(call cmd,wrap_initrd,miboot)
 
+$(obj)/zImage.ps3: vmlinux
+	$(STRIP) -s -R .comment $< -o $@
+
 $(obj)/uImage: vmlinux $(wrapperbits)
 	$(call cmd,wrap,uboot)
 
 image-$(CONFIG_PPC_PSERIES)		+= zImage.pseries
 image-$(CONFIG_PPC_MAPLE)		+= zImage.pseries
 image-$(CONFIG_PPC_IBM_CELL_BLADE)	+= zImage.pseries
+image-$(CONFIG_PPC_PS3)			+= zImage.ps3
 image-$(CONFIG_PPC_CHRP)		+= zImage.chrp
+image-$(CONFIG_PPC_EFIKA)		+= zImage.chrp
 image-$(CONFIG_PPC_PMAC)		+= zImage.pmac
 image-$(CONFIG_DEFAULT_UIMAGE)		+= uImage
 
@@ -176,3 +182,4 @@ install: $(CONFIGURE) $(image-y)
 
 clean-files += $(addprefix $(objtree)/, $(obj-boot) vmlinux.strip.gz)
 clean-files += $(addprefix $(objtree)/, $(obj-boot) vmlinux.bin.gz)
+clean-files += $(image-)
diff --git a/arch/powerpc/boot/dts/kuroboxHG.dts b/arch/powerpc/boot/dts/kuroboxHG.dts
new file mode 100644
index 000000000000..d06b0b018899
--- /dev/null
+++ b/arch/powerpc/boot/dts/kuroboxHG.dts
@@ -0,0 +1,148 @@
+/*
+ * Device Tree Souce for Buffalo KuroboxHG
+ *
+ * Choose CONFIG_LINKSTATION to build a kernel for KuroboxHG, or use
+ * the default configuration linkstation_defconfig.
+ *
+ * Based on sandpoint.dts
+ *
+ * 2006 (c) G. Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This file is licensed under
+ * the terms of the GNU General Public License version 2.  This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+
+XXXX add flash parts, rtc, ??
+
+build with: "dtc -f -I dts -O dtb -o kuroboxHG.dtb -V 16 kuroboxHG.dts"
+
+
+ */
+
+/ {
+	linux,phandle = <1000>;
+	model = "KuroboxHG";
+	compatible = "linkstation";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpus {
+		linux,phandle = <2000>;
+		#cpus = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,603e { /* Really 8241 */
+			linux,phandle = <2100>;
+			linux,boot-cpu;
+			device_type = "cpu";
+			reg = <0>;
+			clock-frequency = <fdad680>;	/* Fixed by bootwrapper */
+			timebase-frequency = <1F04000>; /* Fixed by bootwrapper */
+			bus-frequency = <0>;		/* From bootloader */
+			/* Following required by dtc but not used */
+			i-cache-line-size = <0>;
+			d-cache-line-size = <0>;
+			i-cache-size = <4000>;
+			d-cache-size = <4000>;
+		};
+	};
+
+	memory {
+		linux,phandle = <3000>;
+		device_type = "memory";
+		reg = <00000000 08000000>;
+	};
+
+	soc10x { /* AFAICT need to make soc for 8245's uarts to be defined */
+		linux,phandle = <4000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		#interrupt-cells = <2>;
+		device_type = "soc";
+		compatible = "mpc10x";
+		store-gathering = <0>; /* 0 == off, !0 == on */
+		reg = <80000000 00100000>;
+		ranges = <80000000 80000000 70000000	/* pci mem space */
+			  fc000000 fc000000 00100000	/* EUMB */
+			  fe000000 fe000000 00c00000	/* pci i/o space */
+			  fec00000 fec00000 00300000	/* pci cfg regs */
+			  fef00000 fef00000 00100000>;	/* pci iack */
+
+		i2c@80003000 {
+			linux,phandle = <4300>;
+			device_type = "i2c";
+			compatible = "fsl-i2c";
+			reg = <80003000 1000>;
+			interrupts = <5 2>;
+			interrupt-parent = <4400>;
+		};
+
+		serial@80004500 {
+			linux,phandle = <4511>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <80004500 8>;
+			clock-frequency = <7c044a8>;
+			current-speed = <2580>;
+			interrupts = <9 2>;
+			interrupt-parent = <4400>;
+		};
+
+		serial@80004600 {
+			linux,phandle = <4512>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <80004600 8>;
+			clock-frequency = <7c044a8>;
+			current-speed = <e100>;
+			interrupts = <a 0>;
+			interrupt-parent = <4400>;
+		};
+
+		pic@80040000 {
+			linux,phandle = <4400>;
+			#interrupt-cells = <2>;
+			#address-cells = <0>;
+			device_type = "open-pic";
+			compatible = "chrp,open-pic";
+			interrupt-controller;
+			reg = <80040000 40000>;
+			built-in;
+		};
+
+		pci@fec00000 {
+			linux,phandle = <4500>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+			device_type = "pci";
+			compatible = "mpc10x-pci";
+			reg = <fec00000 400000>;
+			ranges = <01000000 0        0 fe000000 0 00c00000
+				  02000000 0 80000000 80000000 0 70000000>;
+			bus-range = <0 ff>;
+			clock-frequency = <7f28155>;
+			interrupt-parent = <4400>;
+			interrupt-map-mask = <f800 0 0 7>;
+			interrupt-map = <
+				/* IDSEL 0x11 - IRQ0 ETH */
+				5800 0 0 1 4400 0 1
+				5800 0 0 2 4400 1 1
+				5800 0 0 3 4400 2 1
+				5800 0 0 4 4400 3 1
+				/* IDSEL 0x12 - IRQ1 IDE0 */
+				6000 0 0 1 4400 1 1
+				6000 0 0 2 4400 2 1
+				6000 0 0 3 4400 3 1
+				6000 0 0 4 4400 0 1
+				/* IDSEL 0x14 - IRQ3 USB2.0 */
+				7000 0 0 1 4400 3 1
+				7000 0 0 2 4400 3 1
+				7000 0 0 3 4400 3 1
+				7000 0 0 4 4400 3 1
+			>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/lite5200.dts b/arch/powerpc/boot/dts/lite5200.dts
new file mode 100644
index 000000000000..8bc0d259796d
--- /dev/null
+++ b/arch/powerpc/boot/dts/lite5200.dts
@@ -0,0 +1,313 @@
+/*
+ * Lite5200 board Device Tree Source
+ *
+ * Copyright 2006 Secret Lab Technologies Ltd.
+ * Grant Likely <grant.likely@secretlab.ca>
+ *
+ * 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.
+ */
+
+/ {
+	model = "Lite5200";
+	compatible = "lite5200\0lite52xx\0mpc5200\0mpc52xx";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpus {
+		#cpus = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,5200@0 {
+			device_type = "cpu";
+			reg = <0>;
+			d-cache-line-size = <20>;
+			i-cache-line-size = <20>;
+			d-cache-size = <4000>;		// L1, 16K
+			i-cache-size = <4000>;		// L1, 16K
+			timebase-frequency = <0>;	// from bootloader
+			bus-frequency = <0>;		// from bootloader
+			clock-frequency = <0>;		// from bootloader
+			32-bit;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <00000000 04000000>;	// 64MB
+	};
+
+	soc5200@f0000000 {
+		#interrupt-cells = <3>;
+		device_type = "soc";
+		ranges = <0 f0000000 f0010000>;
+		reg = <f0000000 00010000>;
+		bus-frequency = <0>;		// from bootloader
+
+		cdm@200 {
+			compatible = "mpc5200-cdm\0mpc52xx-cdm";
+			reg = <200 38>;
+		};
+
+		pic@500 {
+			// 5200 interrupts are encoded into two levels;
+			linux,phandle = <500>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			device_type = "interrupt-controller";
+			compatible = "mpc5200-pic\0mpc52xx-pic";
+			reg = <500 80>;
+			built-in;
+		};
+
+		gpt@600 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <600 10>;
+			interrupts = <1 9 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@610 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <610 10>;
+			interrupts = <1 a 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@620 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <620 10>;
+			interrupts = <1 b 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@630 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <630 10>;
+			interrupts = <1 c 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@640 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <640 10>;
+			interrupts = <1 d 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@650 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <650 10>;
+			interrupts = <1 e 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@660 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <660 10>;
+			interrupts = <1 f 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@670 {	// General Purpose Timer
+			compatible = "mpc5200-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <670 10>;
+			interrupts = <1 10 0>;
+			interrupt-parent = <500>;
+		};
+
+		rtc@800 {	// Real time clock
+			compatible = "mpc5200-rtc\0mpc52xx-rtc";
+			device_type = "rtc";
+			reg = <800 100>;
+			interrupts = <1 5 0 1 6 0>;
+			interrupt-parent = <500>;
+		};
+
+		mscan@900 {
+			device_type = "mscan";
+			compatible = "mpc5200-mscan\0mpc52xx-mscan";
+			interrupts = <2 11 0>;
+			interrupt-parent = <500>;
+			reg = <900 80>;
+		};
+
+		mscan@980 {
+			device_type = "mscan";
+			compatible = "mpc5200-mscan\0mpc52xx-mscan";
+			interrupts = <1 12 0>;
+			interrupt-parent = <500>;
+			reg = <980 80>;
+		};
+
+		gpio@b00 {
+			compatible = "mpc5200-gpio\0mpc52xx-gpio";
+			reg = <b00 40>;
+			interrupts = <1 7 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpio-wkup@b00 {
+			compatible = "mpc5200-gpio-wkup\0mpc52xx-gpio-wkup";
+			reg = <c00 40>;
+			interrupts = <1 8 0 0 3 0>;
+			interrupt-parent = <500>;
+		};
+
+		pci@0d00 {
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			compatible = "mpc5200-pci\0mpc52xx-pci";
+			reg = <d00 100>;
+			interrupt-map-mask = <f800 0 0 7>;
+			interrupt-map = <c000 0 0 1 500 0 0 3
+			                 c000 0 0 2 500 0 0 3
+			                 c000 0 0 3 500 0 0 3
+			                 c000 0 0 4 500 0 0 3>;
+			clock-frequency = <0>; // From boot loader
+			interrupts = <2 8 0 2 9 0 2 a 0>;
+			interrupt-parent = <500>;
+			bus-range = <0 0>;
+			ranges = <42000000 0 80000000 80000000 0 20000000
+			          02000000 0 a0000000 a0000000 0 10000000
+			          01000000 0 00000000 b0000000 0 01000000>;
+		};
+
+		spi@f00 {
+			device_type = "spi";
+			compatible = "mpc5200-spi\0mpc52xx-spi";
+			reg = <f00 20>;
+			interrupts = <2 d 0 2 e 0>;
+			interrupt-parent = <500>;
+		};
+
+		usb@1000 {
+			device_type = "usb-ohci-be";
+			compatible = "mpc5200-ohci\0mpc52xx-ohci\0ohci-be";
+			reg = <1000 ff>;
+			interrupts = <2 6 0>;
+			interrupt-parent = <500>;
+		};
+
+		bestcomm@1200 {
+			device_type = "dma-controller";
+			compatible = "mpc5200-bestcomm\0mpc52xx-bestcomm";
+			reg = <1200 80>;
+			interrupts = <3 0 0  3 1 0  3 2 0  3 3 0
+			              3 4 0  3 5 0  3 6 0  3 7 0
+			              3 8 0  3 9 0  3 a 0  3 b 0
+			              3 c 0  3 d 0  3 e 0  3 f 0>;
+			interrupt-parent = <500>;
+		};
+
+		xlb@1f00 {
+			compatible = "mpc5200-xlb\0mpc52xx-xlb";
+			reg = <1f00 100>;
+		};
+
+		serial@2000 {		// PSC1
+			device_type = "serial";
+			compatible = "mpc5200-psc-uart\0mpc52xx-psc-uart";
+			port-number = <0>;  // Logical port assignment
+			reg = <2000 100>;
+			interrupts = <2 1 0>;
+			interrupt-parent = <500>;
+		};
+
+		// PSC2 in spi mode example
+		spi@2200 {		// PSC2
+			device_type = "spi";
+			compatible = "mpc5200-psc-spi\0mpc52xx-psc-spi";
+			reg = <2200 100>;
+			interrupts = <2 2 0>;
+			interrupt-parent = <500>;
+		};
+
+		// PSC3 in CODEC mode example
+		i2s@2400 {		// PSC3
+			device_type = "i2s";
+			compatible = "mpc5200-psc-i2s\0mpc52xx-psc-i2s";
+			reg = <2400 100>;
+			interrupts = <2 3 0>;
+			interrupt-parent = <500>;
+		};
+
+		// PSC4 unconfigured
+		//serial@2600 {		// PSC4
+		//	device_type = "serial";
+		//	compatible = "mpc5200-psc-uart\0mpc52xx-psc-uart";
+		//	reg = <2600 100>;
+		//	interrupts = <2 b 0>;
+		//	interrupt-parent = <500>;
+		//};
+
+		// PSC5 unconfigured
+		//serial@2800 {		// PSC5
+		//	device_type = "serial";
+		//	compatible = "mpc5200-psc-uart\0mpc52xx-psc-uart";
+		//	reg = <2800 100>;
+		//	interrupts = <2 c 0>;
+		//	interrupt-parent = <500>;
+		//};
+
+		// PSC6 in AC97 mode example
+		ac97@2c00 {		// PSC6
+			device_type = "ac97";
+			compatible = "mpc5200-psc-ac97\0mpc52xx-psc-ac97";
+			reg = <2c00 100>;
+			interrupts = <2 4 0>;
+			interrupt-parent = <500>;
+		};
+
+		ethernet@3000 {
+			device_type = "network";
+			compatible = "mpc5200-fec\0mpc52xx-fec";
+			reg = <3000 800>;
+			mac-address = [ 02 03 04 05 06 07 ]; // Bad!
+			interrupts = <2 5 0>;
+			interrupt-parent = <500>;
+		};
+
+		ata@3a00 {
+			device_type = "ata";
+			compatible = "mpc5200-ata\0mpc52xx-ata";
+			reg = <3a00 100>;
+			interrupts = <2 7 0>;
+			interrupt-parent = <500>;
+		};
+
+		i2c@3d00 {
+			device_type = "i2c";
+			compatible = "mpc5200-i2c\0mpc52xx-i2c";
+			reg = <3d00 40>;
+			interrupts = <2 f 0>;
+			interrupt-parent = <500>;
+		};
+
+		i2c@3d40 {
+			device_type = "i2c";
+			compatible = "mpc5200-i2c\0mpc52xx-i2c";
+			reg = <3d40 40>;
+			interrupts = <2 10 0>;
+			interrupt-parent = <500>;
+		};
+		sram@8000 {
+			device_type = "sram";
+			compatible = "mpc5200-sram\0mpc52xx-sram\0sram";
+			reg = <8000 4000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/lite5200b.dts b/arch/powerpc/boot/dts/lite5200b.dts
new file mode 100644
index 000000000000..81cb76418a78
--- /dev/null
+++ b/arch/powerpc/boot/dts/lite5200b.dts
@@ -0,0 +1,318 @@
+/*
+ * Lite5200B board Device Tree Source
+ *
+ * Copyright 2006 Secret Lab Technologies Ltd.
+ * Grant Likely <grant.likely@secretlab.ca>
+ *
+ * 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.
+ */
+
+/ {
+	model = "Lite5200b";
+	compatible = "lite5200b\0lite52xx\0mpc5200b\0mpc52xx";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	cpus {
+		#cpus = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,5200@0 {
+			device_type = "cpu";
+			reg = <0>;
+			d-cache-line-size = <20>;
+			i-cache-line-size = <20>;
+			d-cache-size = <4000>;		// L1, 16K
+			i-cache-size = <4000>;		// L1, 16K
+			timebase-frequency = <0>;	// from bootloader
+			bus-frequency = <0>;		// from bootloader
+			clock-frequency = <0>;		// from bootloader
+			32-bit;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <00000000 10000000>;	// 256MB
+	};
+
+	soc5200@f0000000 {
+		#interrupt-cells = <3>;
+		device_type = "soc";
+		ranges = <0 f0000000 f0010000>;
+		reg = <f0000000 00010000>;
+		bus-frequency = <0>;		// from bootloader
+
+		cdm@200 {
+			compatible = "mpc5200b-cdm\0mpc52xx-cdm";
+			reg = <200 38>;
+		};
+
+		pic@500 {
+			// 5200 interrupts are encoded into two levels;
+			linux,phandle = <500>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			device_type = "interrupt-controller";
+			compatible = "mpc5200b-pic\0mpc52xx-pic";
+			reg = <500 80>;
+			built-in;
+		};
+
+		gpt@600 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <600 10>;
+			interrupts = <1 9 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@610 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <610 10>;
+			interrupts = <1 a 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@620 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <620 10>;
+			interrupts = <1 b 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@630 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <630 10>;
+			interrupts = <1 c 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@640 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <640 10>;
+			interrupts = <1 d 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@650 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <650 10>;
+			interrupts = <1 e 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@660 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <660 10>;
+			interrupts = <1 f 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpt@670 {	// General Purpose Timer
+			compatible = "mpc5200b-gpt\0mpc52xx-gpt";
+			device_type = "gpt";
+			reg = <670 10>;
+			interrupts = <1 10 0>;
+			interrupt-parent = <500>;
+		};
+
+		rtc@800 {	// Real time clock
+			compatible = "mpc5200b-rtc\0mpc52xx-rtc";
+			device_type = "rtc";
+			reg = <800 100>;
+			interrupts = <1 5 0 1 6 0>;
+			interrupt-parent = <500>;
+		};
+
+		mscan@900 {
+			device_type = "mscan";
+			compatible = "mpc5200b-mscan\0mpc52xx-mscan";
+			interrupts = <2 11 0>;
+			interrupt-parent = <500>;
+			reg = <900 80>;
+		};
+
+		mscan@980 {
+			device_type = "mscan";
+			compatible = "mpc5200b-mscan\0mpc52xx-mscan";
+			interrupts = <1 12 0>;
+			interrupt-parent = <500>;
+			reg = <980 80>;
+		};
+
+		gpio@b00 {
+			compatible = "mpc5200b-gpio\0mpc52xx-gpio";
+			reg = <b00 40>;
+			interrupts = <1 7 0>;
+			interrupt-parent = <500>;
+		};
+
+		gpio-wkup@b00 {
+			compatible = "mpc5200b-gpio-wkup\0mpc52xx-gpio-wkup";
+			reg = <c00 40>;
+			interrupts = <1 8 0 0 3 0>;
+			interrupt-parent = <500>;
+		};
+
+		pci@0d00 {
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			compatible = "mpc5200b-pci\0mpc52xx-pci";
+			reg = <d00 100>;
+			interrupt-map-mask = <f800 0 0 7>;
+			interrupt-map = <c000 0 0 1 500 0 0 3 // 1st slot
+			                 c000 0 0 2 500 1 1 3
+			                 c000 0 0 3 500 1 2 3
+			                 c000 0 0 4 500 1 3 3
+
+			                 c800 0 0 1 500 1 1 3 // 2nd slot
+			                 c800 0 0 2 500 1 2 3
+			                 c800 0 0 3 500 1 3 3
+			                 c800 0 0 4 500 0 0 3>;
+			clock-frequency = <0>; // From boot loader
+			interrupts = <2 8 0 2 9 0 2 a 0>;
+			interrupt-parent = <500>;
+			bus-range = <0 0>;
+			ranges = <42000000 0 80000000 80000000 0 20000000
+			          02000000 0 a0000000 a0000000 0 10000000
+			          01000000 0 00000000 b0000000 0 01000000>;
+		};
+
+		spi@f00 {
+			device_type = "spi";
+			compatible = "mpc5200b-spi\0mpc52xx-spi";
+			reg = <f00 20>;
+			interrupts = <2 d 0 2 e 0>;
+			interrupt-parent = <500>;
+		};
+
+		usb@1000 {
+			device_type = "usb-ohci-be";
+			compatible = "mpc5200b-ohci\0mpc52xx-ohci\0ohci-be";
+			reg = <1000 ff>;
+			interrupts = <2 6 0>;
+			interrupt-parent = <500>;
+		};
+
+		bestcomm@1200 {
+			device_type = "dma-controller";
+			compatible = "mpc5200b-bestcomm\0mpc52xx-bestcomm";
+			reg = <1200 80>;
+			interrupts = <3 0 0  3 1 0  3 2 0  3 3 0
+			              3 4 0  3 5 0  3 6 0  3 7 0
+			              3 8 0  3 9 0  3 a 0  3 b 0
+			              3 c 0  3 d 0  3 e 0  3 f 0>;
+			interrupt-parent = <500>;
+		};
+
+		xlb@1f00 {
+			compatible = "mpc5200b-xlb\0mpc52xx-xlb";
+			reg = <1f00 100>;
+		};
+
+		serial@2000 {		// PSC1
+			device_type = "serial";
+			compatible = "mpc5200b-psc-uart\0mpc52xx-psc-uart";
+			port-number = <0>;  // Logical port assignment
+			reg = <2000 100>;
+			interrupts = <2 1 0>;
+			interrupt-parent = <500>;
+		};
+
+		// PSC2 in spi mode example
+		spi@2200 {		// PSC2
+			device_type = "spi";
+			compatible = "mpc5200b-psc-spi\0mpc52xx-psc-spi";
+			reg = <2200 100>;
+			interrupts = <2 2 0>;
+			interrupt-parent = <500>;
+		};
+
+		// PSC3 in CODEC mode example
+		i2s@2400 {		// PSC3
+			device_type = "i2s";
+			compatible = "mpc5200b-psc-i2s\0mpc52xx-psc-i2s";
+			reg = <2400 100>;
+			interrupts = <2 3 0>;
+			interrupt-parent = <500>;
+		};
+
+		// PSC4 unconfigured
+		//serial@2600 {		// PSC4
+		//	device_type = "serial";
+		//	compatible = "mpc5200b-psc-uart\0mpc52xx-psc-uart";
+		//	reg = <2600 100>;
+		//	interrupts = <2 b 0>;
+		//	interrupt-parent = <500>;
+		//};
+
+		// PSC5 unconfigured
+		//serial@2800 {		// PSC5
+		//	device_type = "serial";
+		//	compatible = "mpc5200b-psc-uart\0mpc52xx-psc-uart";
+		//	reg = <2800 100>;
+		//	interrupts = <2 c 0>;
+		//	interrupt-parent = <500>;
+		//};
+
+		// PSC6 in AC97 mode example
+		ac97@2c00 {		// PSC6
+			device_type = "ac97";
+			compatible = "mpc5200b-psc-ac97\0mpc52xx-psc-ac97";
+			reg = <2c00 100>;
+			interrupts = <2 4 0>;
+			interrupt-parent = <500>;
+		};
+
+		ethernet@3000 {
+			device_type = "network";
+			compatible = "mpc5200b-fec\0mpc52xx-fec";
+			reg = <3000 800>;
+			mac-address = [ 02 03 04 05 06 07 ]; // Bad!
+			interrupts = <2 5 0>;
+			interrupt-parent = <500>;
+		};
+
+		ata@3a00 {
+			device_type = "ata";
+			compatible = "mpc5200b-ata\0mpc52xx-ata";
+			reg = <3a00 100>;
+			interrupts = <2 7 0>;
+			interrupt-parent = <500>;
+		};
+
+		i2c@3d00 {
+			device_type = "i2c";
+			compatible = "mpc5200b-i2c\0mpc52xx-i2c";
+			reg = <3d00 40>;
+			interrupts = <2 f 0>;
+			interrupt-parent = <500>;
+		};
+
+		i2c@3d40 {
+			device_type = "i2c";
+			compatible = "mpc5200b-i2c\0mpc52xx-i2c";
+			reg = <3d40 40>;
+			interrupts = <2 10 0>;
+			interrupt-parent = <500>;
+		};
+		sram@8000 {
+			device_type = "sram";
+			compatible = "mpc5200b-sram\0mpc52xx-sram\0sram";
+			reg = <8000 4000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/mpc7448hpc2.dts b/arch/powerpc/boot/dts/mpc7448hpc2.dts
index d7b985e6bd2f..c4d9562cbaad 100644
--- a/arch/powerpc/boot/dts/mpc7448hpc2.dts
+++ b/arch/powerpc/boot/dts/mpc7448hpc2.dts
@@ -161,29 +161,41 @@
 			interrupt-map = <
 
 				/* IDSEL 0x11 */
-				0800 0 0 1 7400 24 0
-				0800 0 0 2 7400 25 0
-				0800 0 0 3 7400 26 0
-				0800 0 0 4 7400 27 0
+				0800 0 0 1 1180 24 0
+				0800 0 0 2 1180 25 0
+				0800 0 0 3 1180 26 0
+				0800 0 0 4 1180 27 0
 
 				/* IDSEL 0x12 */
-				1000 0 0 1 7400 25 0
-				1000 0 0 2 7400 26 0
-				1000 0 0 3 7400 27 0
-				1000 0 0 4 7400 24 0
+				1000 0 0 1 1180 25 0
+				1000 0 0 2 1180 26 0
+				1000 0 0 3 1180 27 0
+				1000 0 0 4 1180 24 0
 
 				/* IDSEL 0x13 */
-				1800 0 0 1 7400 26 0
-				1800 0 0 2 7400 27 0
-				1800 0 0 3 7400 24 0
-				1800 0 0 4 7400 25 0
+				1800 0 0 1 1180 26 0
+				1800 0 0 2 1180 27 0
+				1800 0 0 3 1180 24 0
+				1800 0 0 4 1180 25 0
 
 				/* IDSEL 0x14 */
-				2000 0 0 1 7400 27 0
-				2000 0 0 2 7400 24 0
-				2000 0 0 3 7400 25 0
-				2000 0 0 4 7400 26 0
+				2000 0 0 1 1180 27 0
+				2000 0 0 2 1180 24 0
+				2000 0 0 3 1180 25 0
+				2000 0 0 4 1180 26 0
 				>;
+			router@1180 {
+				linux,phandle = <1180>;
+				clock-frequency = <0>;
+				interrupt-controller;
+				device_type = "pic-router";
+				#address-cells = <0>;
+				#interrupt-cells = <2>;
+				built-in;
+				big-endian;
+				interrupts = <17 2>;
+				interrupt-parent = <7400>;
+			};
 		};
 	};
 
diff --git a/arch/powerpc/boot/flatdevtree.c b/arch/powerpc/boot/flatdevtree.c
new file mode 100644
index 000000000000..c76c194715b2
--- /dev/null
+++ b/arch/powerpc/boot/flatdevtree.c
@@ -0,0 +1,880 @@
+/*
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright Pantelis Antoniou 2006
+ * Copyright (C) IBM Corporation 2006
+ *
+ * Authors: Pantelis Antoniou <pantelis@embeddedalley.com>
+ *	    Hollis Blanchard <hollisb@us.ibm.com>
+ *	    Mark A. Greer <mgreer@mvista.com>
+ *	    Paul Mackerras <paulus@samba.org>
+ */
+
+#include <string.h>
+#include <stddef.h>
+#include "flatdevtree.h"
+#include "flatdevtree_env.h"
+
+#define _ALIGN(x, al)	(((x) + (al) - 1) & ~((al) - 1))
+
+/* Routines for keeping node ptrs returned by ft_find_device current */
+/* First entry not used b/c it would return 0 and be taken as NULL/error */
+static void *ft_node_add(struct ft_cxt *cxt, char *node)
+{
+	unsigned int i;
+
+	for (i = 1; i < cxt->nodes_used; i++)	/* already there? */
+		if (cxt->node_tbl[i] == node)
+			return (void *)i;
+
+	if (cxt->nodes_used < cxt->node_max) {
+		cxt->node_tbl[cxt->nodes_used] = node;
+		return (void *)cxt->nodes_used++;
+	}
+
+	return NULL;
+}
+
+static char *ft_node_ph2node(struct ft_cxt *cxt, const void *phandle)
+{
+	unsigned int i = (unsigned int)phandle;
+
+	if (i < cxt->nodes_used)
+		return cxt->node_tbl[i];
+	return NULL;
+}
+
+static void ft_node_update_before(struct ft_cxt *cxt, char *addr, int shift)
+{
+	unsigned int i;
+
+	if (shift == 0)
+		return;
+
+	for (i = 1; i < cxt->nodes_used; i++)
+		if (cxt->node_tbl[i] < addr)
+			cxt->node_tbl[i] += shift;
+}
+
+static void ft_node_update_after(struct ft_cxt *cxt, char *addr, int shift)
+{
+	unsigned int i;
+
+	if (shift == 0)
+		return;
+
+	for (i = 1; i < cxt->nodes_used; i++)
+		if (cxt->node_tbl[i] >= addr)
+			cxt->node_tbl[i] += shift;
+}
+
+/* Struct used to return info from ft_next() */
+struct ft_atom {
+	u32 tag;
+	const char *name;
+	void *data;
+	u32 size;
+};
+
+/* Set ptrs to current one's info; return addr of next one */
+static char *ft_next(struct ft_cxt *cxt, char *p, struct ft_atom *ret)
+{
+	u32 sz;
+
+	if (p >= cxt->rgn[FT_STRUCT].start + cxt->rgn[FT_STRUCT].size)
+		return NULL;
+
+	ret->tag = be32_to_cpu(*(u32 *) p);
+	p += 4;
+
+	switch (ret->tag) {	/* Tag */
+	case OF_DT_BEGIN_NODE:
+		ret->name = p;
+		ret->data = (void *)(p - 4);	/* start of node */
+		p += _ALIGN(strlen(p) + 1, 4);
+		break;
+	case OF_DT_PROP:
+		ret->size = sz = be32_to_cpu(*(u32 *) p);
+		ret->name = cxt->str_anchor + be32_to_cpu(*(u32 *) (p + 4));
+		ret->data = (void *)(p + 8);
+		p += 8 + _ALIGN(sz, 4);
+		break;
+	case OF_DT_END_NODE:
+	case OF_DT_NOP:
+		break;
+	case OF_DT_END:
+	default:
+		p = NULL;
+		break;
+	}
+
+	return p;
+}
+
+#define HDR_SIZE	_ALIGN(sizeof(struct boot_param_header), 8)
+#define EXPAND_INCR	1024	/* alloc this much extra when expanding */
+
+/* See if the regions are in the standard order and non-overlapping */
+static int ft_ordered(struct ft_cxt *cxt)
+{
+	char *p = (char *)cxt->bph + HDR_SIZE;
+	enum ft_rgn_id r;
+
+	for (r = FT_RSVMAP; r <= FT_STRINGS; ++r) {
+		if (p > cxt->rgn[r].start)
+			return 0;
+		p = cxt->rgn[r].start + cxt->rgn[r].size;
+	}
+	return p <= (char *)cxt->bph + cxt->max_size;
+}
+
+/* Copy the tree to a newly-allocated region and put things in order */
+static int ft_reorder(struct ft_cxt *cxt, int nextra)
+{
+	unsigned long tot;
+	enum ft_rgn_id r;
+	char *p, *pend;
+	int stroff;
+
+	tot = HDR_SIZE + EXPAND_INCR;
+	for (r = FT_RSVMAP; r <= FT_STRINGS; ++r)
+		tot += cxt->rgn[r].size;
+	if (nextra > 0)
+		tot += nextra;
+	tot = _ALIGN(tot, 8);
+
+	if (!cxt->realloc)
+		return 0;
+	p = cxt->realloc(NULL, tot);
+	if (!p)
+		return 0;
+
+	memcpy(p, cxt->bph, sizeof(struct boot_param_header));
+	/* offsets get fixed up later */
+
+	cxt->bph = (struct boot_param_header *)p;
+	cxt->max_size = tot;
+	pend = p + tot;
+	p += HDR_SIZE;
+
+	memcpy(p, cxt->rgn[FT_RSVMAP].start, cxt->rgn[FT_RSVMAP].size);
+	cxt->rgn[FT_RSVMAP].start = p;
+	p += cxt->rgn[FT_RSVMAP].size;
+
+	memcpy(p, cxt->rgn[FT_STRUCT].start, cxt->rgn[FT_STRUCT].size);
+	ft_node_update_after(cxt, cxt->rgn[FT_STRUCT].start,
+			p - cxt->rgn[FT_STRUCT].start);
+	cxt->p += p - cxt->rgn[FT_STRUCT].start;
+	cxt->rgn[FT_STRUCT].start = p;
+
+	p = pend - cxt->rgn[FT_STRINGS].size;
+	memcpy(p, cxt->rgn[FT_STRINGS].start, cxt->rgn[FT_STRINGS].size);
+	stroff = cxt->str_anchor - cxt->rgn[FT_STRINGS].start;
+	cxt->rgn[FT_STRINGS].start = p;
+	cxt->str_anchor = p + stroff;
+
+	cxt->isordered = 1;
+	return 1;
+}
+
+static inline char *prev_end(struct ft_cxt *cxt, enum ft_rgn_id r)
+{
+	if (r > FT_RSVMAP)
+		return cxt->rgn[r - 1].start + cxt->rgn[r - 1].size;
+	return (char *)cxt->bph + HDR_SIZE;
+}
+
+static inline char *next_start(struct ft_cxt *cxt, enum ft_rgn_id r)
+{
+	if (r < FT_STRINGS)
+		return cxt->rgn[r + 1].start;
+	return (char *)cxt->bph + cxt->max_size;
+}
+
+/*
+ * See if we can expand region rgn by nextra bytes by using up
+ * free space after or before the region.
+ */
+static int ft_shuffle(struct ft_cxt *cxt, char **pp, enum ft_rgn_id rgn,
+		int nextra)
+{
+	char *p = *pp;
+	char *rgn_start, *rgn_end;
+
+	rgn_start = cxt->rgn[rgn].start;
+	rgn_end = rgn_start + cxt->rgn[rgn].size;
+	if (nextra <= 0 || rgn_end + nextra <= next_start(cxt, rgn)) {
+		/* move following stuff */
+		if (p < rgn_end) {
+			if (nextra < 0)
+				memmove(p, p - nextra, rgn_end - p + nextra);
+			else
+				memmove(p + nextra, p, rgn_end - p);
+			if (rgn == FT_STRUCT)
+				ft_node_update_after(cxt, p, nextra);
+		}
+		cxt->rgn[rgn].size += nextra;
+		if (rgn == FT_STRINGS)
+			/* assumes strings only added at beginning */
+			cxt->str_anchor += nextra;
+		return 1;
+	}
+	if (prev_end(cxt, rgn) <= rgn_start - nextra) {
+		/* move preceding stuff */
+		if (p > rgn_start) {
+			memmove(rgn_start - nextra, rgn_start, p - rgn_start);
+			if (rgn == FT_STRUCT)
+				ft_node_update_before(cxt, p, -nextra);
+		}
+		*p -= nextra;
+		cxt->rgn[rgn].start -= nextra;
+		cxt->rgn[rgn].size += nextra;
+		return 1;
+	}
+	return 0;
+}
+
+static int ft_make_space(struct ft_cxt *cxt, char **pp, enum ft_rgn_id rgn,
+			 int nextra)
+{
+	unsigned long size, ssize, tot;
+	char *str, *next;
+	enum ft_rgn_id r;
+
+	if (!cxt->isordered && !ft_reorder(cxt, nextra))
+		return 0;
+	if (ft_shuffle(cxt, pp, rgn, nextra))
+		return 1;
+
+	/* See if there is space after the strings section */
+	ssize = cxt->rgn[FT_STRINGS].size;
+	if (cxt->rgn[FT_STRINGS].start + ssize
+			< (char *)cxt->bph + cxt->max_size) {
+		/* move strings up as far as possible */
+		str = (char *)cxt->bph + cxt->max_size - ssize;
+		cxt->str_anchor += str - cxt->rgn[FT_STRINGS].start;
+		memmove(str, cxt->rgn[FT_STRINGS].start, ssize);
+		cxt->rgn[FT_STRINGS].start = str;
+		/* enough space now? */
+		if (rgn >= FT_STRUCT && ft_shuffle(cxt, pp, rgn, nextra))
+			return 1;
+	}
+
+	/* how much total free space is there following this region? */
+	tot = 0;
+	for (r = rgn; r < FT_STRINGS; ++r) {
+		char *r_end = cxt->rgn[r].start + cxt->rgn[r].size;
+		tot += next_start(cxt, rgn) - r_end;
+	}
+
+	/* cast is to shut gcc up; we know nextra >= 0 */
+	if (tot < (unsigned int)nextra) {
+		/* have to reallocate */
+		char *newp, *new_start;
+		int shift;
+
+		if (!cxt->realloc)
+			return 0;
+		size = _ALIGN(cxt->max_size + (nextra - tot) + EXPAND_INCR, 8);
+		newp = cxt->realloc(cxt->bph, size);
+		if (!newp)
+			return 0;
+		cxt->max_size = size;
+		shift = newp - (char *)cxt->bph;
+
+		if (shift) { /* realloc can return same addr */
+			cxt->bph = (struct boot_param_header *)newp;
+			ft_node_update_after(cxt, cxt->rgn[FT_STRUCT].start,
+					shift);
+			for (r = FT_RSVMAP; r <= FT_STRINGS; ++r) {
+				new_start = cxt->rgn[r].start + shift;
+				cxt->rgn[r].start = new_start;
+			}
+			*pp += shift;
+			cxt->str_anchor += shift;
+		}
+
+		/* move strings up to the end */
+		str = newp + size - ssize;
+		cxt->str_anchor += str - cxt->rgn[FT_STRINGS].start;
+		memmove(str, cxt->rgn[FT_STRINGS].start, ssize);
+		cxt->rgn[FT_STRINGS].start = str;
+
+		if (ft_shuffle(cxt, pp, rgn, nextra))
+			return 1;
+	}
+
+	/* must be FT_RSVMAP and we need to move FT_STRUCT up */
+	if (rgn == FT_RSVMAP) {
+		next = cxt->rgn[FT_RSVMAP].start + cxt->rgn[FT_RSVMAP].size
+			+ nextra;
+		ssize = cxt->rgn[FT_STRUCT].size;
+		if (next + ssize >= cxt->rgn[FT_STRINGS].start)
+			return 0;	/* "can't happen" */
+		memmove(next, cxt->rgn[FT_STRUCT].start, ssize);
+		ft_node_update_after(cxt, cxt->rgn[FT_STRUCT].start, nextra);
+		cxt->rgn[FT_STRUCT].start = next;
+
+		if (ft_shuffle(cxt, pp, rgn, nextra))
+			return 1;
+	}
+
+	return 0;		/* "can't happen" */
+}
+
+static void ft_put_word(struct ft_cxt *cxt, u32 v)
+{
+	*(u32 *) cxt->p = cpu_to_be32(v);
+	cxt->p += 4;
+}
+
+static void ft_put_bin(struct ft_cxt *cxt, const void *data, unsigned int sz)
+{
+	unsigned long sza = _ALIGN(sz, 4);
+
+	/* zero out the alignment gap if necessary */
+	if (sz < sza)
+		*(u32 *) (cxt->p + sza - 4) = 0;
+
+	/* copy in the data */
+	memcpy(cxt->p, data, sz);
+
+	cxt->p += sza;
+}
+
+int ft_begin_node(struct ft_cxt *cxt, const char *name)
+{
+	unsigned long nlen = strlen(name) + 1;
+	unsigned long len = 8 + _ALIGN(nlen, 4);
+
+	if (!ft_make_space(cxt, &cxt->p, FT_STRUCT, len))
+		return -1;
+	ft_put_word(cxt, OF_DT_BEGIN_NODE);
+	ft_put_bin(cxt, name, strlen(name) + 1);
+	return 0;
+}
+
+void ft_end_node(struct ft_cxt *cxt)
+{
+	ft_put_word(cxt, OF_DT_END_NODE);
+}
+
+void ft_nop(struct ft_cxt *cxt)
+{
+	if (ft_make_space(cxt, &cxt->p, FT_STRUCT, 4))
+		ft_put_word(cxt, OF_DT_NOP);
+}
+
+#define NO_STRING	0x7fffffff
+
+static int lookup_string(struct ft_cxt *cxt, const char *name)
+{
+	char *p, *end;
+
+	p = cxt->rgn[FT_STRINGS].start;
+	end = p + cxt->rgn[FT_STRINGS].size;
+	while (p < end) {
+		if (strcmp(p, (char *)name) == 0)
+			return p - cxt->str_anchor;
+		p += strlen(p) + 1;
+	}
+
+	return NO_STRING;
+}
+
+/* lookup string and insert if not found */
+static int map_string(struct ft_cxt *cxt, const char *name)
+{
+	int off;
+	char *p;
+
+	off = lookup_string(cxt, name);
+	if (off != NO_STRING)
+		return off;
+	p = cxt->rgn[FT_STRINGS].start;
+	if (!ft_make_space(cxt, &p, FT_STRINGS, strlen(name) + 1))
+		return NO_STRING;
+	strcpy(p, name);
+	return p - cxt->str_anchor;
+}
+
+int ft_prop(struct ft_cxt *cxt, const char *name, const void *data,
+		unsigned int sz)
+{
+	int off, len;
+
+	off = lookup_string(cxt, name);
+	if (off == NO_STRING)
+		return -1;
+
+	len = 12 + _ALIGN(sz, 4);
+	if (!ft_make_space(cxt, &cxt->p, FT_STRUCT, len))
+		return -1;
+
+	ft_put_word(cxt, OF_DT_PROP);
+	ft_put_word(cxt, sz);
+	ft_put_word(cxt, off);
+	ft_put_bin(cxt, data, sz);
+	return 0;
+}
+
+int ft_prop_str(struct ft_cxt *cxt, const char *name, const char *str)
+{
+	return ft_prop(cxt, name, str, strlen(str) + 1);
+}
+
+int ft_prop_int(struct ft_cxt *cxt, const char *name, unsigned int val)
+{
+	u32 v = cpu_to_be32((u32) val);
+
+	return ft_prop(cxt, name, &v, 4);
+}
+
+/* Calculate the size of the reserved map */
+static unsigned long rsvmap_size(struct ft_cxt *cxt)
+{
+	struct ft_reserve *res;
+
+	res = (struct ft_reserve *)cxt->rgn[FT_RSVMAP].start;
+	while (res->start || res->len)
+		++res;
+	return (char *)(res + 1) - cxt->rgn[FT_RSVMAP].start;
+}
+
+/* Calculate the size of the struct region by stepping through it */
+static unsigned long struct_size(struct ft_cxt *cxt)
+{
+	char *p = cxt->rgn[FT_STRUCT].start;
+	char *next;
+	struct ft_atom atom;
+
+	/* make check in ft_next happy */
+	if (cxt->rgn[FT_STRUCT].size == 0)
+		cxt->rgn[FT_STRUCT].size = 0xfffffffful - (unsigned long)p;
+
+	while ((next = ft_next(cxt, p, &atom)) != NULL)
+		p = next;
+	return p + 4 - cxt->rgn[FT_STRUCT].start;
+}
+
+/* add `adj' on to all string offset values in the struct area */
+static void adjust_string_offsets(struct ft_cxt *cxt, int adj)
+{
+	char *p = cxt->rgn[FT_STRUCT].start;
+	char *next;
+	struct ft_atom atom;
+	int off;
+
+	while ((next = ft_next(cxt, p, &atom)) != NULL) {
+		if (atom.tag == OF_DT_PROP) {
+			off = be32_to_cpu(*(u32 *) (p + 8));
+			*(u32 *) (p + 8) = cpu_to_be32(off + adj);
+		}
+		p = next;
+	}
+}
+
+/* start construction of the flat OF tree from scratch */
+void ft_begin(struct ft_cxt *cxt, void *blob, unsigned int max_size,
+		void *(*realloc_fn) (void *, unsigned long))
+{
+	struct boot_param_header *bph = blob;
+	char *p;
+	struct ft_reserve *pres;
+
+	/* clear the cxt */
+	memset(cxt, 0, sizeof(*cxt));
+
+	cxt->bph = bph;
+	cxt->max_size = max_size;
+	cxt->realloc = realloc_fn;
+	cxt->isordered = 1;
+
+	/* zero everything in the header area */
+	memset(bph, 0, sizeof(*bph));
+
+	bph->magic = cpu_to_be32(OF_DT_HEADER);
+	bph->version = cpu_to_be32(0x10);
+	bph->last_comp_version = cpu_to_be32(0x10);
+
+	/* start pointers */
+	cxt->rgn[FT_RSVMAP].start = p = blob + HDR_SIZE;
+	cxt->rgn[FT_RSVMAP].size = sizeof(struct ft_reserve);
+	pres = (struct ft_reserve *)p;
+	cxt->rgn[FT_STRUCT].start = p += sizeof(struct ft_reserve);
+	cxt->rgn[FT_STRUCT].size = 4;
+	cxt->rgn[FT_STRINGS].start = blob + max_size;
+	cxt->rgn[FT_STRINGS].size = 0;
+
+	/* init rsvmap and struct */
+	pres->start = 0;
+	pres->len = 0;
+	*(u32 *) p = cpu_to_be32(OF_DT_END);
+
+	cxt->str_anchor = blob;
+}
+
+/* open up an existing blob to be examined or modified */
+int ft_open(struct ft_cxt *cxt, void *blob, unsigned int max_size,
+		unsigned int max_find_device,
+		void *(*realloc_fn) (void *, unsigned long))
+{
+	struct boot_param_header *bph = blob;
+
+	/* can't cope with version < 16 */
+	if (be32_to_cpu(bph->version) < 16)
+		return -1;
+
+	/* clear the cxt */
+	memset(cxt, 0, sizeof(*cxt));
+
+	/* alloc node_tbl to track node ptrs returned by ft_find_device */
+	++max_find_device;
+	cxt->node_tbl = realloc_fn(NULL, max_find_device * sizeof(char *));
+	if (!cxt->node_tbl)
+		return -1;
+	memset(cxt->node_tbl, 0, max_find_device * sizeof(char *));
+	cxt->node_max = max_find_device;
+	cxt->nodes_used = 1;	/* don't use idx 0 b/c looks like NULL */
+
+	cxt->bph = bph;
+	cxt->max_size = max_size;
+	cxt->realloc = realloc_fn;
+
+	cxt->rgn[FT_RSVMAP].start = blob + be32_to_cpu(bph->off_mem_rsvmap);
+	cxt->rgn[FT_RSVMAP].size = rsvmap_size(cxt);
+	cxt->rgn[FT_STRUCT].start = blob + be32_to_cpu(bph->off_dt_struct);
+	cxt->rgn[FT_STRUCT].size = struct_size(cxt);
+	cxt->rgn[FT_STRINGS].start = blob + be32_to_cpu(bph->off_dt_strings);
+	cxt->rgn[FT_STRINGS].size = be32_to_cpu(bph->dt_strings_size);
+	/* Leave as '0' to force first ft_make_space call to do a ft_reorder
+	 * and move dt to an area allocated by realloc.
+	cxt->isordered = ft_ordered(cxt);
+	*/
+
+	cxt->p = cxt->rgn[FT_STRUCT].start;
+	cxt->str_anchor = cxt->rgn[FT_STRINGS].start;
+
+	return 0;
+}
+
+/* add a reserver physical area to the rsvmap */
+int ft_add_rsvmap(struct ft_cxt *cxt, u64 physaddr, u64 size)
+{
+	char *p;
+	struct ft_reserve *pres;
+
+	p = cxt->rgn[FT_RSVMAP].start + cxt->rgn[FT_RSVMAP].size
+		- sizeof(struct ft_reserve);
+	if (!ft_make_space(cxt, &p, FT_RSVMAP, sizeof(struct ft_reserve)))
+		return -1;
+
+	pres = (struct ft_reserve *)p;
+	pres->start = cpu_to_be64(physaddr);
+	pres->len = cpu_to_be64(size);
+
+	return 0;
+}
+
+void ft_begin_tree(struct ft_cxt *cxt)
+{
+	cxt->p = cxt->rgn[FT_STRUCT].start;
+}
+
+void ft_end_tree(struct ft_cxt *cxt)
+{
+	struct boot_param_header *bph = cxt->bph;
+	char *p, *oldstr, *str, *endp;
+	unsigned long ssize;
+	int adj;
+
+	if (!cxt->isordered)
+		return;		/* we haven't touched anything */
+
+	/* adjust string offsets */
+	oldstr = cxt->rgn[FT_STRINGS].start;
+	adj = cxt->str_anchor - oldstr;
+	if (adj)
+		adjust_string_offsets(cxt, adj);
+
+	/* make strings end on 8-byte boundary */
+	ssize = cxt->rgn[FT_STRINGS].size;
+	endp = (char *)_ALIGN((unsigned long)cxt->rgn[FT_STRUCT].start
+			+ cxt->rgn[FT_STRUCT].size + ssize, 8);
+	str = endp - ssize;
+
+	/* move strings down to end of structs */
+	memmove(str, oldstr, ssize);
+	cxt->str_anchor = str;
+	cxt->rgn[FT_STRINGS].start = str;
+
+	/* fill in header fields */
+	p = (char *)bph;
+	bph->totalsize = cpu_to_be32(endp - p);
+	bph->off_mem_rsvmap = cpu_to_be32(cxt->rgn[FT_RSVMAP].start - p);
+	bph->off_dt_struct = cpu_to_be32(cxt->rgn[FT_STRUCT].start - p);
+	bph->off_dt_strings = cpu_to_be32(cxt->rgn[FT_STRINGS].start - p);
+	bph->dt_strings_size = cpu_to_be32(ssize);
+}
+
+void *ft_find_device(struct ft_cxt *cxt, const char *srch_path)
+{
+	char *node;
+
+	/* require absolute path */
+	if (srch_path[0] != '/')
+		return NULL;
+	node = ft_find_descendent(cxt, cxt->rgn[FT_STRUCT].start, srch_path);
+	return ft_node_add(cxt, node);
+}
+
+void *ft_find_descendent(struct ft_cxt *cxt, void *top, const char *srch_path)
+{
+	struct ft_atom atom;
+	char *p;
+	const char *cp, *q;
+	int cl;
+	int depth = -1;
+	int dmatch = 0;
+	const char *path_comp[FT_MAX_DEPTH];
+
+	cp = srch_path;
+	cl = 0;
+	p = top;
+
+	while ((p = ft_next(cxt, p, &atom)) != NULL) {
+		switch (atom.tag) {
+		case OF_DT_BEGIN_NODE:
+			++depth;
+			if (depth != dmatch)
+				break;
+			cxt->genealogy[depth] = atom.data;
+			cxt->genealogy[depth + 1] = NULL;
+			if (depth && !(strncmp(atom.name, cp, cl) == 0
+					&& (atom.name[cl] == '/'
+						|| atom.name[cl] == '\0'
+						|| atom.name[cl] == '@')))
+				break;
+			path_comp[dmatch] = cp;
+			/* it matches so far, advance to next path component */
+			cp += cl;
+			/* skip slashes */
+			while (*cp == '/')
+				++cp;
+			/* we're done if this is the end of the string */
+			if (*cp == 0)
+				return atom.data;
+			/* look for end of this component */
+			q = strchr(cp, '/');
+			if (q)
+				cl = q - cp;
+			else
+				cl = strlen(cp);
+			++dmatch;
+			break;
+		case OF_DT_END_NODE:
+			if (depth == 0)
+				return NULL;
+			if (dmatch > depth) {
+				--dmatch;
+				cl = cp - path_comp[dmatch] - 1;
+				cp = path_comp[dmatch];
+				while (cl > 0 && cp[cl - 1] == '/')
+					--cl;
+			}
+			--depth;
+			break;
+		}
+	}
+	return NULL;
+}
+
+void *ft_get_parent(struct ft_cxt *cxt, const void *phandle)
+{
+	void *node;
+	int d;
+	struct ft_atom atom;
+	char *p;
+
+	node = ft_node_ph2node(cxt, phandle);
+	if (node == NULL)
+		return NULL;
+
+	for (d = 0; cxt->genealogy[d] != NULL; ++d)
+		if (cxt->genealogy[d] == node)
+			return cxt->genealogy[d > 0 ? d - 1 : 0];
+
+	/* have to do it the hard way... */
+	p = cxt->rgn[FT_STRUCT].start;
+	d = 0;
+	while ((p = ft_next(cxt, p, &atom)) != NULL) {
+		switch (atom.tag) {
+		case OF_DT_BEGIN_NODE:
+			cxt->genealogy[d] = atom.data;
+			if (node == atom.data) {
+				/* found it */
+				cxt->genealogy[d + 1] = NULL;
+				return d > 0 ? cxt->genealogy[d - 1] : node;
+			}
+			++d;
+			break;
+		case OF_DT_END_NODE:
+			--d;
+			break;
+		}
+	}
+	return NULL;
+}
+
+int ft_get_prop(struct ft_cxt *cxt, const void *phandle, const char *propname,
+		void *buf, const unsigned int buflen)
+{
+	struct ft_atom atom;
+	void *node;
+	char *p;
+	int depth;
+	unsigned int size;
+
+	node = ft_node_ph2node(cxt, phandle);
+	if (node == NULL)
+		return -1;
+
+	depth = 0;
+	p = (char *)node;
+
+	while ((p = ft_next(cxt, p, &atom)) != NULL) {
+		switch (atom.tag) {
+		case OF_DT_BEGIN_NODE:
+			++depth;
+			break;
+		case OF_DT_PROP:
+			if ((depth != 1) || strcmp(atom.name, propname))
+				break;
+			size = min(atom.size, buflen);
+			memcpy(buf, atom.data, size);
+			return atom.size;
+		case OF_DT_END_NODE:
+			if (--depth <= 0)
+				return -1;
+		}
+	}
+	return -1;
+}
+
+int ft_set_prop(struct ft_cxt *cxt, const void *phandle, const char *propname,
+		const void *buf, const unsigned int buflen)
+{
+	struct ft_atom atom;
+	void *node;
+	char *p, *next;
+	int nextra, depth;
+
+	node = ft_node_ph2node(cxt, phandle);
+	if (node == NULL)
+		return -1;
+
+	depth = 0;
+	p = node;
+
+	while ((next = ft_next(cxt, p, &atom)) != NULL) {
+		switch (atom.tag) {
+		case OF_DT_BEGIN_NODE:
+			++depth;
+			break;
+		case OF_DT_END_NODE:
+			if (--depth > 0)
+				break;
+			/* haven't found the property, insert here */
+			cxt->p = p;
+			return ft_prop(cxt, propname, buf, buflen);
+		case OF_DT_PROP:
+			if ((depth != 1) || strcmp(atom.name, propname))
+				break;
+			/* found an existing property, overwrite it */
+			nextra = _ALIGN(buflen, 4) - _ALIGN(atom.size, 4);
+			cxt->p = atom.data;
+			if (nextra && !ft_make_space(cxt, &cxt->p, FT_STRUCT,
+						nextra))
+				return -1;
+			*(u32 *) (cxt->p - 8) = cpu_to_be32(buflen);
+			ft_put_bin(cxt, buf, buflen);
+			return 0;
+		}
+		p = next;
+	}
+	return -1;
+}
+
+int ft_del_prop(struct ft_cxt *cxt, const void *phandle, const char *propname)
+{
+	struct ft_atom atom;
+	void *node;
+	char *p, *next;
+	int size;
+
+	node = ft_node_ph2node(cxt, phandle);
+	if (node == NULL)
+		return -1;
+
+	p = node;
+	while ((next = ft_next(cxt, p, &atom)) != NULL) {
+		switch (atom.tag) {
+		case OF_DT_BEGIN_NODE:
+		case OF_DT_END_NODE:
+			return -1;
+		case OF_DT_PROP:
+			if (strcmp(atom.name, propname))
+				break;
+			/* found the property, remove it */
+			size = 12 + -_ALIGN(atom.size, 4);
+			cxt->p = p;
+			if (!ft_make_space(cxt, &cxt->p, FT_STRUCT, -size))
+				return -1;
+			return 0;
+		}
+		p = next;
+	}
+	return -1;
+}
+
+void *ft_create_node(struct ft_cxt *cxt, const void *parent, const char *path)
+{
+	struct ft_atom atom;
+	char *p, *next;
+	int depth = 0;
+
+	p = cxt->rgn[FT_STRUCT].start;
+	while ((next = ft_next(cxt, p, &atom)) != NULL) {
+		switch (atom.tag) {
+		case OF_DT_BEGIN_NODE:
+			++depth;
+			if (depth == 1 && strcmp(atom.name, path) == 0)
+				/* duplicate node path, return error */
+				return NULL;
+			break;
+		case OF_DT_END_NODE:
+			--depth;
+			if (depth > 0)
+				break;
+			/* end of node, insert here */
+			cxt->p = p;
+			ft_begin_node(cxt, path);
+			ft_end_node(cxt);
+			return p;
+		}
+		p = next;
+	}
+	return NULL;
+}
diff --git a/arch/powerpc/boot/flatdevtree.h b/arch/powerpc/boot/flatdevtree.h
index 761c8dc84008..b9cd9f61f351 100644
--- a/arch/powerpc/boot/flatdevtree.h
+++ b/arch/powerpc/boot/flatdevtree.h
@@ -17,7 +17,7 @@
 #ifndef FLATDEVTREE_H
 #define FLATDEVTREE_H
 
-#include "types.h"
+#include "flatdevtree_env.h"
 
 /* Definitions used by the flattened device tree */
 #define OF_DT_HEADER            0xd00dfeed      /* marker */
@@ -43,4 +43,64 @@ struct boot_param_header {
 	u32 dt_strings_size;    /* size of the DT strings block */
 };
 
+struct ft_reserve {
+	u64 start;
+	u64 len;
+};
+
+struct ft_region {
+	char *start;
+	unsigned long size;
+};
+
+enum ft_rgn_id {
+	FT_RSVMAP,
+	FT_STRUCT,
+	FT_STRINGS,
+	FT_N_REGION
+};
+
+#define FT_MAX_DEPTH	50
+
+struct ft_cxt {
+	struct boot_param_header *bph;
+	int max_size;           /* maximum size of tree */
+	int isordered;		/* everything in standard order */
+	void *(*realloc)(void *, unsigned long);
+	char *str_anchor;
+	char *p;		/* current insertion point in structs */
+	struct ft_region rgn[FT_N_REGION];
+	void *genealogy[FT_MAX_DEPTH+1];
+	char **node_tbl;
+	unsigned int node_max;
+	unsigned int nodes_used;
+};
+
+int ft_begin_node(struct ft_cxt *cxt, const char *name);
+void ft_end_node(struct ft_cxt *cxt);
+
+void ft_begin_tree(struct ft_cxt *cxt);
+void ft_end_tree(struct ft_cxt *cxt);
+
+void ft_nop(struct ft_cxt *cxt);
+int ft_prop(struct ft_cxt *cxt, const char *name,
+	    const void *data, unsigned int sz);
+int ft_prop_str(struct ft_cxt *cxt, const char *name, const char *str);
+int ft_prop_int(struct ft_cxt *cxt, const char *name, unsigned int val);
+void ft_begin(struct ft_cxt *cxt, void *blob, unsigned int max_size,
+	      void *(*realloc_fn)(void *, unsigned long));
+int ft_open(struct ft_cxt *cxt, void *blob, unsigned int max_size,
+		unsigned int max_find_device,
+		void *(*realloc_fn)(void *, unsigned long));
+int ft_add_rsvmap(struct ft_cxt *cxt, u64 physaddr, u64 size);
+
+void ft_dump_blob(const void *bphp);
+void ft_merge_blob(struct ft_cxt *cxt, void *blob);
+void *ft_find_device(struct ft_cxt *cxt, const char *srch_path);
+void *ft_find_descendent(struct ft_cxt *cxt, void *top, const char *srch_path);
+int ft_get_prop(struct ft_cxt *cxt, const void *phandle, const char *propname,
+		void *buf, const unsigned int buflen);
+int ft_set_prop(struct ft_cxt *cxt, const void *phandle, const char *propname,
+		const void *buf, const unsigned int buflen);
+
 #endif /* FLATDEVTREE_H */
diff --git a/arch/powerpc/boot/flatdevtree_env.h b/arch/powerpc/boot/flatdevtree_env.h
new file mode 100644
index 000000000000..83bc1c718836
--- /dev/null
+++ b/arch/powerpc/boot/flatdevtree_env.h
@@ -0,0 +1,47 @@
+/*
+ * This file adds the header file glue so that the shared files
+ * flatdevicetree.[ch] can compile and work in the powerpc bootwrapper.
+ *
+ * strncmp & strchr copied from <file:lib/strings.c>
+ * Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * Maintained by: Mark A. Greer <mgreer@mvista.com>
+ */
+#ifndef _PPC_BOOT_FLATDEVTREE_ENV_H_
+#define _PPC_BOOT_FLATDEVTREE_ENV_H_
+
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "string.h"
+#include "stdio.h"
+#include "ops.h"
+
+#define be16_to_cpu(x)		(x)
+#define cpu_to_be16(x)		(x)
+#define be32_to_cpu(x)		(x)
+#define cpu_to_be32(x)		(x)
+#define be64_to_cpu(x)		(x)
+#define cpu_to_be64(x)		(x)
+
+static inline int strncmp(const char *cs, const char *ct, size_t count)
+{
+	signed char __res = 0;
+
+	while (count) {
+		if ((__res = *cs - *ct++) != 0 || !*cs++)
+			break;
+		count--;
+	}
+	return __res;
+}
+
+static inline char *strchr(const char *s, int c)
+{
+	for (; *s != (char)c; ++s)
+		if (*s == '\0')
+			return NULL;
+	return (char *)s;
+}
+
+#endif /* _PPC_BOOT_FLATDEVTREE_ENV_H_ */
diff --git a/arch/powerpc/boot/flatdevtree_misc.c b/arch/powerpc/boot/flatdevtree_misc.c
new file mode 100644
index 000000000000..04da38fa477f
--- /dev/null
+++ b/arch/powerpc/boot/flatdevtree_misc.c
@@ -0,0 +1,51 @@
+/*
+ * This file does the necessary interface mapping between the bootwrapper
+ * device tree operations and the interface provided by shared source
+ * files flatdevicetree.[ch].
+ *
+ * Author: Mark A. Greer <mgreer@mvista.com>
+ *
+ * 2006 (c) MontaVista Software, Inc.  This file is licensed under
+ * the terms of the GNU General Public License version 2.  This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+ */
+#include <stddef.h>
+#include "flatdevtree.h"
+#include "ops.h"
+
+static struct ft_cxt cxt;
+
+static void *ft_finddevice(const char *name)
+{
+	return ft_find_device(&cxt, name);
+}
+
+static int ft_getprop(const void *phandle, const char *propname, void *buf,
+		const int buflen)
+{
+	return ft_get_prop(&cxt, phandle, propname, buf, buflen);
+}
+
+static int ft_setprop(const void *phandle, const char *propname,
+		const void *buf, const int buflen)
+{
+	return ft_set_prop(&cxt, phandle, propname, buf, buflen);
+}
+
+static unsigned long ft_finalize(void)
+{
+	ft_end_tree(&cxt);
+	return (unsigned long)cxt.bph;
+}
+
+int ft_init(void *dt_blob, unsigned int max_size, unsigned int max_find_device)
+{
+	dt_ops.finddevice = ft_finddevice;
+	dt_ops.getprop = ft_getprop;
+	dt_ops.setprop = ft_setprop;
+	dt_ops.finalize = ft_finalize;
+
+	return ft_open(&cxt, dt_blob, max_size, max_find_device,
+			platform_ops.realloc);
+}
diff --git a/arch/powerpc/boot/io.h b/arch/powerpc/boot/io.h
new file mode 100644
index 000000000000..32974ed49e02
--- /dev/null
+++ b/arch/powerpc/boot/io.h
@@ -0,0 +1,53 @@
+#ifndef _IO_H
+#define __IO_H
+/*
+ * Low-level I/O routines.
+ *
+ * Copied from <file:include/asm-powerpc/io.h> (which has no copyright)
+ */
+static inline int in_8(const volatile unsigned char *addr)
+{
+	int ret;
+
+	__asm__ __volatile__("lbz%U1%X1 %0,%1; twi 0,%0,0; isync"
+			     : "=r" (ret) : "m" (*addr));
+	return ret;
+}
+
+static inline void out_8(volatile unsigned char *addr, int val)
+{
+	__asm__ __volatile__("stb%U0%X0 %1,%0; sync"
+			     : "=m" (*addr) : "r" (val));
+}
+
+static inline unsigned in_le32(const volatile unsigned *addr)
+{
+	unsigned ret;
+
+	__asm__ __volatile__("lwbrx %0,0,%1; twi 0,%0,0; isync"
+			     : "=r" (ret) : "r" (addr), "m" (*addr));
+	return ret;
+}
+
+static inline unsigned in_be32(const volatile unsigned *addr)
+{
+	unsigned ret;
+
+	__asm__ __volatile__("lwz%U1%X1 %0,%1; twi 0,%0,0; isync"
+			     : "=r" (ret) : "m" (*addr));
+	return ret;
+}
+
+static inline void out_le32(volatile unsigned *addr, int val)
+{
+	__asm__ __volatile__("stwbrx %1,0,%2; sync" : "=m" (*addr)
+			     : "r" (val), "r" (addr));
+}
+
+static inline void out_be32(volatile unsigned *addr, int val)
+{
+	__asm__ __volatile__("stw%U0%X0 %1,%0; sync"
+			     : "=m" (*addr) : "r" (val));
+}
+
+#endif /* _IO_H */
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index d719bb9333d1..6f6b50d238b6 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -27,6 +27,8 @@ extern char _vmlinux_start[];
 extern char _vmlinux_end[];
 extern char _initrd_start[];
 extern char _initrd_end[];
+extern char _dtb_start[];
+extern char _dtb_end[];
 
 struct addr_range {
 	unsigned long addr;
@@ -167,7 +169,7 @@ static int is_elf32(void *hdr)
 	return 1;
 }
 
-static void prep_kernel(unsigned long *a1, unsigned long *a2)
+static void prep_kernel(unsigned long a1, unsigned long a2)
 {
 	int len;
 
@@ -203,11 +205,14 @@ static void prep_kernel(unsigned long *a1, unsigned long *a2)
 	}
 
 	/*
-	 * Now we try to alloc memory for the initrd (and copy it there)
+	 * Now find the initrd
+	 *
+	 * First see if we have an image attached to us.  If so
+	 * allocate memory for it and copy it there.
 	 */
 	initrd.size = (unsigned long)(_initrd_end - _initrd_start);
 	initrd.memsize = initrd.size;
-	if ( initrd.size > 0 ) {
+	if (initrd.size > 0) {
 		printf("Allocating 0x%lx bytes for initrd ...\n\r",
 		       initrd.size);
 		initrd.addr = (unsigned long)malloc((u32)initrd.size);
@@ -216,8 +221,6 @@ static void prep_kernel(unsigned long *a1, unsigned long *a2)
 					"ramdisk !\n\r");
 			exit();
 		}
-		*a1 = initrd.addr;
-		*a2 = initrd.size;
 		printf("initial ramdisk moving 0x%lx <- 0x%lx "
 			"(0x%lx bytes)\n\r", initrd.addr,
 			(unsigned long)_initrd_start, initrd.size);
@@ -225,6 +228,12 @@ static void prep_kernel(unsigned long *a1, unsigned long *a2)
 			initrd.size);
 		printf("initrd head: 0x%lx\n\r",
 				*((unsigned long *)initrd.addr));
+	} else if (a2 != 0) {
+		/* Otherwise, see if yaboot or another loader gave us an initrd */
+		initrd.addr = a1;
+		initrd.memsize = initrd.size = a2;
+		printf("Using loader supplied initrd at 0x%lx (0x%lx bytes)\n\r",
+		       initrd.addr, initrd.size);
 	}
 
 	/* Eventually gunzip the kernel */
@@ -250,10 +259,6 @@ static void prep_kernel(unsigned long *a1, unsigned long *a2)
 	flush_cache((void *)vmlinux.addr, vmlinux.size);
 }
 
-void __attribute__ ((weak)) ft_init(void *dt_blob)
-{
-}
-
 /* A buffer that may be edited by tools operating on a zImage binary so as to
  * edit the command line passed to vmlinux (by setting /chosen/bootargs).
  * The buffer is put in it's own section so that tools may locate it easier.
@@ -285,36 +290,22 @@ static void set_cmdline(char *buf)
 		setprop(devp, "bootargs", buf, strlen(buf) + 1);
 }
 
-/* Section where ft can be tacked on after zImage is built */
-union blobspace {
-	struct boot_param_header hdr;
-	char space[8*1024];
-} dt_blob __attribute__((__section__("__builtin_ft")));
-
 struct platform_ops platform_ops;
 struct dt_ops dt_ops;
 struct console_ops console_ops;
 
 void start(unsigned long a1, unsigned long a2, void *promptr, void *sp)
 {
-	int have_dt = 0;
 	kernel_entry_t kentry;
 	char cmdline[COMMAND_LINE_SIZE];
+	unsigned long ft_addr = 0;
 
 	memset(__bss_start, 0, _end - __bss_start);
 	memset(&platform_ops, 0, sizeof(platform_ops));
 	memset(&dt_ops, 0, sizeof(dt_ops));
 	memset(&console_ops, 0, sizeof(console_ops));
 
-	/* Override the dt_ops and device tree if there was an flat dev
-	 * tree attached to the zImage.
-	 */
-	if (dt_blob.hdr.magic == OF_DT_HEADER) {
-		have_dt = 1;
-		ft_init(&dt_blob);
-	}
-
-	if (platform_init(promptr))
+	if (platform_init(promptr, _dtb_start, _dtb_end))
 		exit();
 	if (console_ops.open && (console_ops.open() < 0))
 		exit();
@@ -324,7 +315,7 @@ void start(unsigned long a1, unsigned long a2, void *promptr, void *sp)
 	printf("\n\rzImage starting: loaded at 0x%p (sp: 0x%p)\n\r",
 	       _start, sp);
 
-	prep_kernel(&a1, &a2);
+	prep_kernel(a1, a2);
 
 	/* If cmdline came from zimage wrapper or if we can edit the one
 	 * in the dt, print it out and edit it, if possible.
@@ -338,15 +329,23 @@ void start(unsigned long a1, unsigned long a2, void *promptr, void *sp)
 		set_cmdline(cmdline);
 	}
 
+	printf("Finalizing device tree...");
+	if (dt_ops.finalize)
+		ft_addr = dt_ops.finalize();
+	if (ft_addr)
+		printf(" flat tree at 0x%lx\n\r", ft_addr);
+	else
+		printf(" using OF tree (promptr=%p)\n\r", promptr);
+
 	if (console_ops.close)
 		console_ops.close();
 
 	kentry = (kernel_entry_t) vmlinux.addr;
-	if (have_dt)
-		kentry(dt_ops.ft_addr(), 0, NULL);
+	if (ft_addr)
+		kentry(ft_addr, 0, NULL);
 	else
 		/* XXX initrd addr/size should be passed in properties */
-		kentry(a1, a2, promptr);
+		kentry(initrd.addr, initrd.size, promptr);
 
 	/* console closed so printf below may not work */
 	printf("Error: Linux kernel returned to zImage boot wrapper!\n\r");
diff --git a/arch/powerpc/boot/mktree.c b/arch/powerpc/boot/mktree.c
new file mode 100644
index 000000000000..4cb892993651
--- /dev/null
+++ b/arch/powerpc/boot/mktree.c
@@ -0,0 +1,152 @@
+/*
+ * Makes a tree bootable image for IBM Evaluation boards.
+ * Basically, just take a zImage, skip the ELF header, and stuff
+ * a 32 byte header on the front.
+ *
+ * We use htonl, which is a network macro, to make sure we're doing
+ * The Right Thing on an LE machine.  It's non-obvious, but it should
+ * work on anything BSD'ish.
+ */
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <netinet/in.h>
+#ifdef __sun__
+#include <inttypes.h>
+#else
+#include <stdint.h>
+#endif
+
+/* This gets tacked on the front of the image.  There are also a few
+ * bytes allocated after the _start label used by the boot rom (see
+ * head.S for details).
+ */
+typedef struct boot_block {
+	uint32_t bb_magic;		/* 0x0052504F */
+	uint32_t bb_dest;		/* Target address of the image */
+	uint32_t bb_num_512blocks;	/* Size, rounded-up, in 512 byte blks */
+	uint32_t bb_debug_flag;	/* Run debugger or image after load */
+	uint32_t bb_entry_point;	/* The image address to start */
+	uint32_t bb_checksum;	/* 32 bit checksum including header */
+	uint32_t reserved[2];
+} boot_block_t;
+
+#define IMGBLK	512
+char	tmpbuf[IMGBLK];
+
+int main(int argc, char *argv[])
+{
+	int	in_fd, out_fd;
+	int	nblks, i;
+	uint	cksum, *cp;
+	struct	stat	st;
+	boot_block_t	bt;
+
+	if (argc < 3) {
+		fprintf(stderr, "usage: %s <zImage-file> <boot-image> [entry-point]\n",argv[0]);
+		exit(1);
+	}
+
+	if (stat(argv[1], &st) < 0) {
+		perror("stat");
+		exit(2);
+	}
+
+	nblks = (st.st_size + IMGBLK) / IMGBLK;
+
+	bt.bb_magic = htonl(0x0052504F);
+
+	/* If we have the optional entry point parameter, use it */
+	if (argc == 4)
+		bt.bb_dest = bt.bb_entry_point = htonl(strtoul(argv[3], NULL, 0));
+	else
+		bt.bb_dest = bt.bb_entry_point = htonl(0x500000);
+
+	/* We know these from the linker command.
+	 * ...and then move it up into memory a little more so the
+	 * relocation can happen.
+	 */
+	bt.bb_num_512blocks = htonl(nblks);
+	bt.bb_debug_flag = 0;
+
+	bt.bb_checksum = 0;
+
+	/* To be neat and tidy :-).
+	*/
+	bt.reserved[0] = 0;
+	bt.reserved[1] = 0;
+
+	if ((in_fd = open(argv[1], O_RDONLY)) < 0) {
+		perror("zImage open");
+		exit(3);
+	}
+
+	if ((out_fd = open(argv[2], (O_RDWR | O_CREAT | O_TRUNC), 0666)) < 0) {
+		perror("bootfile open");
+		exit(3);
+	}
+
+	cksum = 0;
+	cp = (void *)&bt;
+	for (i=0; i<sizeof(bt)/sizeof(uint); i++)
+		cksum += *cp++;
+
+	/* Assume zImage is an ELF file, and skip the 64K header.
+	*/
+	if (read(in_fd, tmpbuf, IMGBLK) != IMGBLK) {
+		fprintf(stderr, "%s is too small to be an ELF image\n",
+				argv[1]);
+		exit(4);
+	}
+
+	if ((*(uint *)tmpbuf) != htonl(0x7f454c46)) {
+		fprintf(stderr, "%s is not an ELF image\n", argv[1]);
+		exit(4);
+	}
+
+	if (lseek(in_fd, (64 * 1024), SEEK_SET) < 0) {
+		fprintf(stderr, "%s failed to seek in ELF image\n", argv[1]);
+		exit(4);
+	}
+
+	nblks -= (64 * 1024) / IMGBLK;
+
+	/* And away we go......
+	*/
+	if (write(out_fd, &bt, sizeof(bt)) != sizeof(bt)) {
+		perror("boot-image write");
+		exit(5);
+	}
+
+	while (nblks-- > 0) {
+		if (read(in_fd, tmpbuf, IMGBLK) < 0) {
+			perror("zImage read");
+			exit(5);
+		}
+		cp = (uint *)tmpbuf;
+		for (i=0; i<sizeof(tmpbuf)/sizeof(uint); i++)
+			cksum += *cp++;
+		if (write(out_fd, tmpbuf, sizeof(tmpbuf)) != sizeof(tmpbuf)) {
+			perror("boot-image write");
+			exit(5);
+		}
+	}
+
+	/* rewrite the header with the computed checksum.
+	*/
+	bt.bb_checksum = htonl(cksum);
+	if (lseek(out_fd, 0, SEEK_SET) < 0) {
+		perror("rewrite seek");
+		exit(1);
+	}
+	if (write(out_fd, &bt, sizeof(bt)) != sizeof(bt)) {
+		perror("boot-image rewrite");
+		exit(1);
+	}
+
+	exit(0);
+}
diff --git a/arch/powerpc/boot/ns16550.c b/arch/powerpc/boot/ns16550.c
new file mode 100644
index 000000000000..1ffe72e35cdc
--- /dev/null
+++ b/arch/powerpc/boot/ns16550.c
@@ -0,0 +1,74 @@
+/*
+ * 16550 serial console support.
+ *
+ * Original copied from <file:arch/ppc/boot/common/ns16550.c>
+ * (which had no copyright)
+ * Modifications: 2006 (c) MontaVista Software, Inc.
+ *
+ * Modified by: Mark A. Greer <mgreer@mvista.com>
+ */
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "string.h"
+#include "stdio.h"
+#include "io.h"
+#include "ops.h"
+
+#define UART_DLL	0	/* Out: Divisor Latch Low */
+#define UART_DLM	1	/* Out: Divisor Latch High */
+#define UART_FCR	2	/* Out: FIFO Control Register */
+#define UART_LCR	3	/* Out: Line Control Register */
+#define UART_MCR	4	/* Out: Modem Control Register */
+#define UART_LSR	5	/* In:  Line Status Register */
+#define UART_LSR_THRE	0x20	/* Transmit-hold-register empty */
+#define UART_LSR_DR	0x01	/* Receiver data ready */
+#define UART_MSR	6	/* In:  Modem Status Register */
+#define UART_SCR	7	/* I/O: Scratch Register */
+
+static unsigned char *reg_base;
+static u32 reg_shift;
+
+static int ns16550_open(void)
+{
+	out_8(reg_base + (UART_FCR << reg_shift), 0x06);
+	return 0;
+}
+
+static void ns16550_putc(unsigned char c)
+{
+	while ((in_8(reg_base + (UART_LSR << reg_shift)) & UART_LSR_THRE) == 0);
+	out_8(reg_base, c);
+}
+
+static unsigned char ns16550_getc(void)
+{
+	while ((in_8(reg_base + (UART_LSR << reg_shift)) & UART_LSR_DR) == 0);
+	return in_8(reg_base);
+}
+
+static u8 ns16550_tstc(void)
+{
+	return ((in_8(reg_base + (UART_LSR << reg_shift)) & UART_LSR_DR) != 0);
+}
+
+int ns16550_console_init(void *devp, struct serial_console_data *scdp)
+{
+	int n;
+
+	n = getprop(devp, "virtual-reg", &reg_base, sizeof(reg_base));
+	if (n != sizeof(reg_base))
+		return -1;
+
+	n = getprop(devp, "reg-shift", &reg_shift, sizeof(reg_shift));
+	if (n != sizeof(reg_shift))
+		reg_shift = 0;
+
+	scdp->open = ns16550_open;
+	scdp->putc = ns16550_putc;
+	scdp->getc = ns16550_getc;
+	scdp->tstc = ns16550_tstc;
+	scdp->close = NULL;
+
+	return 0;
+}
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 3a71845afc6c..0182f384f3e6 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -256,24 +256,18 @@ static void of_console_write(char *buf, int len)
 	call_prom("write", 3, 1, of_stdout_handle, buf, len);
 }
 
-int platform_init(void *promptr)
+int platform_init(void *promptr, char *dt_blob_start, char *dt_blob_end)
 {
-	platform_ops.fixups = NULL;
 	platform_ops.image_hdr = of_image_hdr;
 	platform_ops.malloc = of_try_claim;
-	platform_ops.free = NULL;
 	platform_ops.exit = of_exit;
 
 	dt_ops.finddevice = of_finddevice;
 	dt_ops.getprop = of_getprop;
 	dt_ops.setprop = of_setprop;
-	dt_ops.translate_addr = NULL;
 
 	console_ops.open = of_console_open;
 	console_ops.write = of_console_write;
-	console_ops.edit_cmdline = NULL;
-	console_ops.close = NULL;
-	console_ops.data = NULL;
 
 	prom = (int (*)(void *))promptr;
 	return 0;
diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
index 135eb4bb03b4..8abb6516bb7c 100644
--- a/arch/powerpc/boot/ops.h
+++ b/arch/powerpc/boot/ops.h
@@ -22,7 +22,8 @@ struct platform_ops {
 	void	(*fixups)(void);
 	void	(*image_hdr)(const void *);
 	void *	(*malloc)(u32 size);
-	void	(*free)(void *ptr, u32 size);
+	void	(*free)(void *ptr);
+	void *	(*realloc)(void *ptr, unsigned long size);
 	void	(*exit)(void);
 };
 extern struct platform_ops platform_ops;
@@ -30,13 +31,11 @@ extern struct platform_ops platform_ops;
 /* Device Tree operations */
 struct dt_ops {
 	void *	(*finddevice)(const char *name);
-	int	(*getprop)(const void *node, const char *name, void *buf,
+	int	(*getprop)(const void *phandle, const char *name, void *buf,
 			const int buflen);
-	int	(*setprop)(const void *node, const char *name,
+	int	(*setprop)(const void *phandle, const char *name,
 			const void *buf, const int buflen);
-	u64	(*translate_addr)(const char *path, const u32 *in_addr,
-			const u32 addr_len);
-	unsigned long (*ft_addr)(void);
+	unsigned long (*finalize)(void);
 };
 extern struct dt_ops dt_ops;
 
@@ -59,10 +58,13 @@ struct serial_console_data {
 	void		(*close)(void);
 };
 
-extern int platform_init(void *promptr);
-extern void simple_alloc_init(void);
-extern void ft_init(void *dt_blob);
-extern int serial_console_init(void);
+int platform_init(void *promptr, char *dt_blob_start, char *dt_blob_end);
+int ft_init(void *dt_blob, unsigned int max_size, unsigned int max_find_device);
+int serial_console_init(void);
+int ns16550_console_init(void *devp, struct serial_console_data *scdp);
+void *simple_alloc_init(char *base, u32 heap_size, u32 granularity,
+		u32 max_allocs);
+
 
 static inline void *finddevice(const char *name)
 {
@@ -84,10 +86,10 @@ static inline void *malloc(u32 size)
 	return (platform_ops.malloc) ? platform_ops.malloc(size) : NULL;
 }
 
-static inline void free(void *ptr, u32 size)
+static inline void free(void *ptr)
 {
 	if (platform_ops.free)
-		platform_ops.free(ptr, size);
+		platform_ops.free(ptr);
 }
 
 static inline void exit(void)
diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c
new file mode 100644
index 000000000000..e8de4cf59be7
--- /dev/null
+++ b/arch/powerpc/boot/serial.c
@@ -0,0 +1,142 @@
+/*
+ * Generic serial console support
+ *
+ * Author: Mark A. Greer <mgreer@mvista.com>
+ *
+ * Code in serial_edit_cmdline() copied from <file:arch/ppc/boot/simple/misc.c>
+ * and was written by Matt Porter <mporter@kernel.crashing.org>.
+ *
+ * 2001,2006 (c) MontaVista Software, Inc.  This file is licensed under
+ * the terms of the GNU General Public License version 2.  This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "string.h"
+#include "stdio.h"
+#include "io.h"
+#include "ops.h"
+
+extern void udelay(long delay);
+
+static int serial_open(void)
+{
+	struct serial_console_data *scdp = console_ops.data;
+	return scdp->open();
+}
+
+static void serial_write(char *buf, int len)
+{
+	struct serial_console_data *scdp = console_ops.data;
+
+	while (*buf != '\0')
+		scdp->putc(*buf++);
+}
+
+static void serial_edit_cmdline(char *buf, int len)
+{
+	int timer = 0, count;
+	char ch, *cp;
+	struct serial_console_data *scdp = console_ops.data;
+
+	cp = buf;
+	count = strlen(buf);
+	cp = &buf[count];
+	count++;
+
+	while (timer++ < 5*1000) {
+		if (scdp->tstc()) {
+			while (((ch = scdp->getc()) != '\n') && (ch != '\r')) {
+				/* Test for backspace/delete */
+				if ((ch == '\b') || (ch == '\177')) {
+					if (cp != buf) {
+						cp--;
+						count--;
+						printf("\b \b");
+					}
+				/* Test for ^x/^u (and wipe the line) */
+				} else if ((ch == '\030') || (ch == '\025')) {
+					while (cp != buf) {
+						cp--;
+						count--;
+						printf("\b \b");
+					}
+				} else if (count < len) {
+						*cp++ = ch;
+						count++;
+						scdp->putc(ch);
+				}
+			}
+			break;  /* Exit 'timer' loop */
+		}
+		udelay(1000);  /* 1 msec */
+	}
+	*cp = 0;
+}
+
+static void serial_close(void)
+{
+	struct serial_console_data *scdp = console_ops.data;
+
+	if (scdp->close)
+		scdp->close();
+}
+
+static void *serial_get_stdout_devp(void)
+{
+	void *devp;
+	char devtype[MAX_PROP_LEN];
+	char path[MAX_PATH_LEN];
+
+	devp = finddevice("/chosen");
+	if (devp == NULL)
+		goto err_out;
+
+	if (getprop(devp, "linux,stdout-path", path, MAX_PATH_LEN) > 0) {
+		devp = finddevice(path);
+		if (devp == NULL)
+			goto err_out;
+
+		if ((getprop(devp, "device_type", devtype, sizeof(devtype)) > 0)
+				&& !strcmp(devtype, "serial"))
+			return devp;
+	}
+err_out:
+	return NULL;
+}
+
+static struct serial_console_data serial_cd;
+
+/* Node's "compatible" property determines which serial driver to use */
+int serial_console_init(void)
+{
+	void *devp;
+	int rc = -1;
+	char compat[MAX_PROP_LEN];
+
+	devp = serial_get_stdout_devp();
+	if (devp == NULL)
+		goto err_out;
+
+	if (getprop(devp, "compatible", compat, sizeof(compat)) < 0)
+		goto err_out;
+
+	if (!strcmp(compat, "ns16550"))
+		rc = ns16550_console_init(devp, &serial_cd);
+
+	/* Add other serial console driver calls here */
+
+	if (!rc) {
+		console_ops.open = serial_open;
+		console_ops.write = serial_write;
+		console_ops.edit_cmdline = serial_edit_cmdline;
+		console_ops.close = serial_close;
+		console_ops.data = &serial_cd;
+
+		return 0;
+	}
+err_out:
+	return -1;
+}
diff --git a/arch/powerpc/boot/simple_alloc.c b/arch/powerpc/boot/simple_alloc.c
new file mode 100644
index 000000000000..cfe3a7505ba0
--- /dev/null
+++ b/arch/powerpc/boot/simple_alloc.c
@@ -0,0 +1,149 @@
+/*
+ * Implement primitive realloc(3) functionality.
+ *
+ * Author: Mark A. Greer <mgreer@mvista.com>
+ *
+ * 2006 (c) MontaVista, Software, Inc.  This file is licensed under
+ * the terms of the GNU General Public License version 2.  This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+ */
+
+#include <stddef.h>
+#include "types.h"
+#include "page.h"
+#include "string.h"
+#include "ops.h"
+
+#define	ENTRY_BEEN_USED	0x01
+#define	ENTRY_IN_USE	0x02
+
+static struct alloc_info {
+	u32	flags;
+	u32	base;
+	u32	size;
+} *alloc_tbl;
+
+static u32 tbl_entries;
+static u32 alloc_min;
+static u32 next_base;
+static u32 space_left;
+
+/*
+ * First time an entry is used, its base and size are set.
+ * An entry can be freed and re-malloc'd but its base & size don't change.
+ * Should be smart enough for needs of bootwrapper.
+ */
+static void *simple_malloc(u32 size)
+{
+	u32 i;
+	struct alloc_info *p = alloc_tbl;
+
+	if (size == 0)
+		goto err_out;
+
+	size = _ALIGN_UP(size, alloc_min);
+
+	for (i=0; i<tbl_entries; i++, p++)
+		if (!(p->flags & ENTRY_BEEN_USED)) { /* never been used */
+			if (size <= space_left) {
+				p->base = next_base;
+				p->size = size;
+				p->flags = ENTRY_BEEN_USED | ENTRY_IN_USE;
+				next_base += size;
+				space_left -= size;
+				return (void *)p->base;
+			}
+			goto err_out; /* not enough space left */
+		}
+		/* reuse an entry keeping same base & size */
+		else if (!(p->flags & ENTRY_IN_USE) && (size <= p->size)) {
+			p->flags |= ENTRY_IN_USE;
+			return (void *)p->base;
+		}
+err_out:
+	return NULL;
+}
+
+static struct alloc_info *simple_find_entry(void *ptr)
+{
+	u32 i;
+	struct alloc_info *p = alloc_tbl;
+
+	for (i=0; i<tbl_entries; i++,p++) {
+		if (!(p->flags & ENTRY_BEEN_USED))
+			break;
+		if ((p->flags & ENTRY_IN_USE) && (p->base == (u32)ptr))
+			return p;
+	}
+	return NULL;
+}
+
+static void simple_free(void *ptr)
+{
+	struct alloc_info *p = simple_find_entry(ptr);
+
+	if (p != NULL)
+		p->flags &= ~ENTRY_IN_USE;
+}
+
+/*
+ * Change size of area pointed to by 'ptr' to 'size'.
+ * If 'ptr' is NULL, then its a malloc().  If 'size' is 0, then its a free().
+ * 'ptr' must be NULL or a pointer to a non-freed area previously returned by
+ * simple_realloc() or simple_malloc().
+ */
+static void *simple_realloc(void *ptr, unsigned long size)
+{
+	struct alloc_info *p;
+	void *new;
+
+	if (size == 0) {
+		simple_free(ptr);
+		return NULL;
+	}
+
+	if (ptr == NULL)
+		return simple_malloc(size);
+
+	p = simple_find_entry(ptr);
+	if (p == NULL) /* ptr not from simple_malloc/simple_realloc */
+		return NULL;
+	if (size <= p->size) /* fits in current block */
+		return ptr;
+
+	new = simple_malloc(size);
+	memcpy(new, ptr, p->size);
+	simple_free(ptr);
+	return new;
+}
+
+/*
+ * Returns addr of first byte after heap so caller can see if it took
+ * too much space.  If so, change args & try again.
+ */
+void *simple_alloc_init(char *base, u32 heap_size, u32 granularity,
+		u32 max_allocs)
+{
+	u32 heap_base, tbl_size;
+
+	heap_size = _ALIGN_UP(heap_size, granularity);
+	alloc_min = granularity;
+	tbl_entries = max_allocs;
+
+	tbl_size = tbl_entries * sizeof(struct alloc_info);
+
+	alloc_tbl = (struct alloc_info *)_ALIGN_UP((unsigned long)base, 8);
+	memset(alloc_tbl, 0, tbl_size);
+
+	heap_base = _ALIGN_UP((u32)alloc_tbl + tbl_size, alloc_min);
+
+	next_base = heap_base;
+	space_left = heap_size;
+
+	platform_ops.malloc = simple_malloc;
+	platform_ops.free = simple_free;
+	platform_ops.realloc = simple_realloc;
+
+	return (void *)(heap_base + heap_size);
+}
diff --git a/arch/powerpc/boot/stdio.c b/arch/powerpc/boot/stdio.c
index 6d5f6382e1ce..0a9feeb98342 100644
--- a/arch/powerpc/boot/stdio.c
+++ b/arch/powerpc/boot/stdio.c
@@ -320,6 +320,7 @@ printf(const char *fmt, ...)
 	va_start(args, fmt);
 	n = vsprintf(sprint_buf, fmt, args);
 	va_end(args);
-	console_ops.write(sprint_buf, n);
+	if (console_ops.write)
+		console_ops.write(sprint_buf, n);
 	return n;
 }
diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S
new file mode 100644
index 000000000000..427ddfc11991
--- /dev/null
+++ b/arch/powerpc/boot/util.S
@@ -0,0 +1,88 @@
+/*
+ * Copied from <file:arch/powerpc/kernel/misc_32.S>
+ *
+ * This file contains miscellaneous low-level functions.
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ * kexec bits:
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ *
+ * 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.
+ *
+ */
+#include "ppc_asm.h"
+
+#define SPRN_PVR        0x11F   /* Processor Version Register */
+
+	.text
+
+/* udelay (on non-601 processors) needs to know the period of the
+ * timebase in nanoseconds.  This used to be hardcoded to be 60ns
+ * (period of 66MHz/4).  Now a variable is used that is initialized to
+ * 60 for backward compatibility, but it can be overridden as necessary
+ * with code something like this:
+ *    extern unsigned long timebase_period_ns;
+ *    timebase_period_ns = 1000000000 / bd->bi_tbfreq;
+ */
+	.data
+	.globl timebase_period_ns
+timebase_period_ns:
+	.long	60
+
+	.text
+/*
+ * Delay for a number of microseconds
+ */
+	.globl	udelay
+udelay:
+	mfspr	r4,SPRN_PVR
+	srwi	r4,r4,16
+	cmpwi	0,r4,1		/* 601 ? */
+	bne	.udelay_not_601
+00:	li	r0,86	/* Instructions / microsecond? */
+	mtctr	r0
+10:	addi	r0,r0,0 /* NOP */
+	bdnz	10b
+	subic.	r3,r3,1
+	bne	00b
+	blr
+
+.udelay_not_601:
+	mulli	r4,r3,1000	/* nanoseconds */
+	/*  Change r4 to be the number of ticks using:
+	 *	(nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns
+	 *  timebase_period_ns defaults to 60 (16.6MHz) */
+	mflr	r5
+	bl	0f
+0:	mflr	r6
+	mtlr	r5
+	lis	r5,0b@ha
+	addi	r5,r5,0b@l
+	subf	r5,r5,r6	/* In case we're relocated */
+	addis	r5,r5,timebase_period_ns@ha
+	lwz	r5,timebase_period_ns@l(r5)
+	add	r4,r4,r5
+	addi	r4,r4,-1
+	divw	r4,r4,r5	/* BUS ticks */
+1:	mftbu	r5
+	mftb	r6
+	mftbu	r7
+	cmpw	0,r5,r7
+	bne	1b		/* Get [synced] base time */
+	addc	r9,r6,r4	/* Compute end time */
+	addze	r8,r5
+2:	mftbu	r5
+	cmpw	0,r5,r8
+	blt	2b
+	bgt	3f
+	mftb	r6
+	cmpw	0,r6,r9
+	blt	2b
+3:	blr
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index b5fb1fee76f8..024e4d425c59 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -184,6 +184,9 @@ fi
 
 if [ -n "$dtb" ]; then
     addsec $tmp "$dtb" .kernel:dtb
+    if [ -n "$dts" ]; then
+	rm $dtb
+    fi
 fi
 
 if [ "$platform" != "miboot" ]; then
diff --git a/arch/powerpc/boot/zImage.coff.lds.S b/arch/powerpc/boot/zImage.coff.lds.S
index 05f32388b953..a360905e5428 100644
--- a/arch/powerpc/boot/zImage.coff.lds.S
+++ b/arch/powerpc/boot/zImage.coff.lds.S
@@ -21,6 +21,10 @@ SECTIONS
     *(.got2)
     __got2_end = .;
 
+    _dtb_start = .;
+    *(.kernel:dtb)
+    _dtb_end = .;
+
     _vmlinux_start =  .;
     *(.kernel:vmlinux.strip)
     _vmlinux_end =  .;
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 0aba06d7d2ec..a98c982c73ad 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.18
-# Wed Oct  4 15:30:50 2006
+# Linux kernel version: 2.6.19-rc6
+# Wed Nov 22 15:33:04 2006
 #
 CONFIG_PPC64=y
 CONFIG_64BIT=y
@@ -32,6 +32,10 @@ CONFIG_AUDIT_ARCH=y
 CONFIG_POWER3=y
 CONFIG_POWER4=y
 CONFIG_PPC_FPU=y
+# CONFIG_PPC_DCR_NATIVE is not set
+CONFIG_PPC_DCR_MMIO=y
+CONFIG_PPC_DCR=y
+CONFIG_PPC_OF_PLATFORM_PCI=y
 CONFIG_ALTIVEC=y
 CONFIG_PPC_STD_MMU=y
 CONFIG_VIRT_CPU_ACCOUNTING=y
@@ -67,7 +71,7 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
-# CONFIG_SYSCTL_SYSCALL is not set
+CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -131,6 +135,7 @@ CONFIG_PPC_CELL=y
 CONFIG_PPC_CELL_NATIVE=y
 CONFIG_PPC_IBM_CELL_BLADE=y
 CONFIG_UDBG_RTAS_CONSOLE=y
+CONFIG_PPC_PS3=y
 # CONFIG_U3_DART is not set
 CONFIG_PPC_RTAS=y
 # CONFIG_RTAS_ERROR_LOGGING is not set
@@ -139,9 +144,23 @@ CONFIG_RTAS_FLASH=y
 CONFIG_MMIO_NVRAM=y
 # CONFIG_PPC_MPC106 is not set
 # CONFIG_PPC_970_NAP is not set
-# CONFIG_CPU_FREQ is not set
+CONFIG_PPC_INDIRECT_IO=y
+CONFIG_GENERIC_IOMAP=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_TABLE=y
+CONFIG_CPU_FREQ_DEBUG=y
+CONFIG_CPU_FREQ_STAT=y
+# CONFIG_CPU_FREQ_STAT_DETAILS is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+# CONFIG_CPU_FREQ_PMAC64 is not set
 # CONFIG_WANT_EARLY_SERIAL is not set
-# CONFIG_MPIC is not set
+CONFIG_MPIC=y
 
 #
 # Cell Broadband Engine options
@@ -149,6 +168,15 @@ CONFIG_MMIO_NVRAM=y
 CONFIG_SPU_FS=m
 CONFIG_SPU_BASE=y
 CONFIG_CBE_RAS=y
+CONFIG_CBE_THERM=m
+CONFIG_CBE_CPUFREQ=m
+
+#
+# PS3 Platform Options
+#
+CONFIG_PS3_HTAB_SIZE=20
+# CONFIG_PS3_DYNAMIC_DMA is not set
+CONFIG_PS3_USE_LPAR_ADDR=y
 
 #
 # Kernel options
@@ -166,13 +194,14 @@ CONFIG_BINFMT_MISC=m
 CONFIG_FORCE_MAX_ZONEORDER=9
 # CONFIG_IOMMU_VMERGE is not set
 CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
-CONFIG_KEXEC=y
+# CONFIG_KEXEC is not set
 # CONFIG_CRASH_DUMP is not set
 CONFIG_IRQ_ALL_CPUS=y
 CONFIG_NUMA=y
 CONFIG_NODES_SHIFT=4
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_SELECT_MEMORY_MODEL=y
 # CONFIG_FLATMEM_MANUAL is not set
@@ -189,6 +218,7 @@ CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_MIGRATION=y
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ARCH_MEMORY_PROBE=y
+CONFIG_NODES_SPAN_OTHER_NODES=y
 CONFIG_PPC_64K_PAGES=y
 CONFIG_SCHED_SMT=y
 CONFIG_PROC_DEVICETREE=y
@@ -207,7 +237,6 @@ CONFIG_GENERIC_ISA_DMA=y
 CONFIG_PCI=y
 CONFIG_PCI_DOMAINS=y
 CONFIG_PCIEPORTBUS=y
-# CONFIG_PCI_MULTITHREAD_PROBE is not set
 # CONFIG_PCI_DEBUG is not set
 
 #
@@ -280,7 +309,6 @@ CONFIG_INET6_XFRM_MODE_TUNNEL=y
 # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 # CONFIG_IPV6_SIT is not set
 CONFIG_IPV6_TUNNEL=m
-# CONFIG_IPV6_SUBTREES is not set
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
 # CONFIG_NETWORK_SECMARK is not set
 CONFIG_NETFILTER=y
@@ -1107,7 +1135,8 @@ CONFIG_PLIST=y
 #
 # Instrumentation Support
 #
-# CONFIG_PROFILING is not set
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
 # CONFIG_KPROBES is not set
 
 #
@@ -1142,6 +1171,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUGGER=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
+CONFIG_XMON_DISASSEMBLY=y
 CONFIG_IRQSTACKS=y
 # CONFIG_BOOTX_TEXT is not set
 # CONFIG_PPC_EARLY_DEBUG is not set
@@ -1159,7 +1189,7 @@ CONFIG_CRYPTO=y
 CONFIG_CRYPTO_ALGAPI=y
 CONFIG_CRYPTO_BLKCIPHER=m
 CONFIG_CRYPTO_HASH=y
-# CONFIG_CRYPTO_MANAGER is not set
+CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_HMAC=y
 # CONFIG_CRYPTO_NULL is not set
 # CONFIG_CRYPTO_MD4 is not set
diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig
new file mode 100644
index 000000000000..23fd210eb56a
--- /dev/null
+++ b/arch/powerpc/configs/linkstation_defconfig
@@ -0,0 +1,1583 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.19-rc4
+# Wed Nov 15 20:36:30 2006
+#
+# CONFIG_PPC64 is not set
+CONFIG_PPC32=y
+CONFIG_PPC_MERGE=y
+CONFIG_MMU=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_IRQ_PER_CPU=y
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_PPC=y
+CONFIG_EARLY_PRINTK=y
+CONFIG_GENERIC_NVRAM=y
+CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_PPC_OF=y
+CONFIG_PPC_UDBG_16550=y
+# CONFIG_GENERIC_TBSYNC is not set
+CONFIG_AUDIT_ARCH=y
+# CONFIG_DEFAULT_UIMAGE is not set
+
+#
+# Processor support
+#
+CONFIG_CLASSIC32=y
+# CONFIG_PPC_52xx is not set
+# CONFIG_PPC_82xx is not set
+# CONFIG_PPC_83xx is not set
+# CONFIG_PPC_85xx is not set
+# CONFIG_PPC_86xx is not set
+# CONFIG_40x is not set
+# CONFIG_44x is not set
+# CONFIG_8xx is not set
+# CONFIG_E200 is not set
+CONFIG_6xx=y
+CONFIG_PPC_FPU=y
+# CONFIG_PPC_DCR_NATIVE is not set
+# CONFIG_PPC_DCR_MMIO is not set
+# CONFIG_ALTIVEC is not set
+CONFIG_PPC_STD_MMU=y
+CONFIG_PPC_STD_MMU_32=y
+# CONFIG_SMP is not set
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION="-kuroboxHG"
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+# CONFIG_IPC_NS is not set
+CONFIG_POSIX_MQUEUE=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_UTS_NS is not set
+# CONFIG_AUDIT is not set
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_RELAY is not set
+CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SYSCTL=y
+# CONFIG_EMBEDDED is not set
+# CONFIG_SYSCTL_SYSCALL is not set
+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_SHMEM=y
+CONFIG_SLAB=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_RT_MUTEXES=y
+# CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
+# CONFIG_SLOB is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=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_KMOD=y
+
+#
+# Block layer
+#
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+
+#
+# Platform support
+#
+# CONFIG_PPC_MULTIPLATFORM is not set
+CONFIG_EMBEDDED6xx=y
+# CONFIG_APUS is not set
+# CONFIG_PPC_CELL is not set
+# CONFIG_PPC_CELL_NATIVE is not set
+# CONFIG_PPC_RTAS is not set
+# CONFIG_MMIO_NVRAM is not set
+# CONFIG_PPC_MPC106 is not set
+# CONFIG_PPC_970_NAP is not set
+# CONFIG_PPC_INDIRECT_IO is not set
+# CONFIG_GENERIC_IOMAP is not set
+# CONFIG_CPU_FREQ is not set
+# CONFIG_TAU is not set
+# CONFIG_KATANA is not set
+# CONFIG_WILLOW is not set
+# CONFIG_CPCI690 is not set
+# CONFIG_POWERPMC250 is not set
+# CONFIG_CHESTNUT is not set
+# CONFIG_SPRUCE is not set
+# CONFIG_HDPU is not set
+# CONFIG_EV64260 is not set
+# CONFIG_LOPEC is not set
+# CONFIG_MVME5100 is not set
+# CONFIG_PPLUS is not set
+# CONFIG_PRPMC750 is not set
+# CONFIG_PRPMC800 is not set
+# CONFIG_SANDPOINT is not set
+CONFIG_LINKSTATION=y
+# CONFIG_MPC7448HPC2 is not set
+# CONFIG_RADSTONE_PPC7D is not set
+# CONFIG_PAL4 is not set
+# CONFIG_GEMINI is not set
+# CONFIG_EST8260 is not set
+# CONFIG_SBC82xx is not set
+# CONFIG_SBS8260 is not set
+# CONFIG_RPX8260 is not set
+# CONFIG_TQM8260 is not set
+# CONFIG_ADS8272 is not set
+# CONFIG_PQ2FADS is not set
+# CONFIG_LITE5200 is not set
+# CONFIG_EV64360 is not set
+CONFIG_PPC_GEN550=y
+CONFIG_MPC10X_BRIDGE=y
+CONFIG_MPC10X_OPENPIC=y
+# CONFIG_MPC10X_STORE_GATHERING is not set
+# CONFIG_WANT_EARLY_SERIAL is not set
+CONFIG_MPIC=y
+
+#
+# Kernel options
+#
+# CONFIG_HIGHMEM is not set
+CONFIG_HZ_100=y
+# CONFIG_HZ_250 is not set
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=100
+CONFIG_PREEMPT_NONE=y
+# CONFIG_PREEMPT_VOLUNTARY is not set
+# CONFIG_PREEMPT is not set
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_MISC is not set
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_RESOURCES_64BIT is not set
+CONFIG_PROC_DEVICETREE=y
+# CONFIG_CMDLINE_BOOL is not set
+# CONFIG_PM is not set
+# CONFIG_SECCOMP is not set
+CONFIG_ISA_DMA_API=y
+
+#
+# Bus options
+#
+CONFIG_GENERIC_ISA_DMA=y
+# CONFIG_MPIC_WEIRD is not set
+# CONFIG_PPC_I8259 is not set
+CONFIG_PPC_INDIRECT_PCI=y
+CONFIG_FSL_SOC=y
+CONFIG_PCI=y
+CONFIG_PCI_DOMAINS=y
+# CONFIG_PCIEPORTBUS is not set
+# CONFIG_PCI_MULTITHREAD_PROBE is not set
+# CONFIG_PCI_DEBUG is not set
+
+#
+# PCCARD (PCMCIA/CardBus) support
+#
+# CONFIG_PCCARD is not set
+
+#
+# PCI Hotplug Support
+#
+# CONFIG_HOTPLUG_PCI is not set
+
+#
+# Advanced setup
+#
+# CONFIG_ADVANCED_OPTIONS is not set
+
+#
+# Default settings for advanced configuration options are used
+#
+CONFIG_HIGHMEM_START=0xfe000000
+CONFIG_LOWMEM_SIZE=0x30000000
+CONFIG_KERNEL_START=0xc0000000
+CONFIG_TASK_SIZE=0x80000000
+CONFIG_BOOT_LOAD=0x00800000
+
+#
+# Networking
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+# CONFIG_NETDEBUG is not set
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+CONFIG_UNIX=y
+CONFIG_XFRM=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY 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_FIB_HASH=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE 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 is not set
+CONFIG_INET_XFRM_MODE_TRANSPORT=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_INET_XFRM_MODE_BEET=y
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+
+#
+# IP: Virtual Server Configuration
+#
+# CONFIG_IP_VS is not set
+# CONFIG_IPV6 is not set
+# CONFIG_INET6_XFRM_TUNNEL is not set
+# CONFIG_INET6_TUNNEL is not set
+# CONFIG_NETWORK_SECMARK is not set
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_DEBUG is not set
+
+#
+# Core Netfilter Configuration
+#
+# CONFIG_NETFILTER_NETLINK is not set
+CONFIG_NETFILTER_XTABLES=m
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
+# CONFIG_NETFILTER_XT_TARGET_DSCP is not set
+CONFIG_NETFILTER_XT_TARGET_MARK=m
+# CONFIG_NETFILTER_XT_TARGET_NFQUEUE is not set
+# CONFIG_NETFILTER_XT_TARGET_NOTRACK is not set
+# CONFIG_NETFILTER_XT_MATCH_COMMENT is not set
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+# CONFIG_NETFILTER_XT_MATCH_DCCP is not set
+# CONFIG_NETFILTER_XT_MATCH_DSCP is not set
+CONFIG_NETFILTER_XT_MATCH_ESP=m
+# CONFIG_NETFILTER_XT_MATCH_HELPER is not set
+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_POLICY is not set
+CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
+# CONFIG_NETFILTER_XT_MATCH_QUOTA is not set
+# CONFIG_NETFILTER_XT_MATCH_REALM is not set
+# CONFIG_NETFILTER_XT_MATCH_SCTP is not set
+CONFIG_NETFILTER_XT_MATCH_STATE=m
+# CONFIG_NETFILTER_XT_MATCH_STATISTIC is not set
+# CONFIG_NETFILTER_XT_MATCH_STRING is not set
+# CONFIG_NETFILTER_XT_MATCH_TCPMSS is not set
+
+#
+# IP: Netfilter Configuration
+#
+CONFIG_IP_NF_CONNTRACK=m
+# CONFIG_IP_NF_CT_ACCT is not set
+# CONFIG_IP_NF_CONNTRACK_MARK is not set
+# CONFIG_IP_NF_CONNTRACK_EVENTS is not set
+# CONFIG_IP_NF_CT_PROTO_SCTP is not set
+CONFIG_IP_NF_FTP=m
+CONFIG_IP_NF_IRC=m
+# CONFIG_IP_NF_NETBIOS_NS is not set
+CONFIG_IP_NF_TFTP=m
+# CONFIG_IP_NF_AMANDA is not set
+# CONFIG_IP_NF_PPTP is not set
+# CONFIG_IP_NF_H323 is not set
+# CONFIG_IP_NF_SIP is not set
+# CONFIG_IP_NF_QUEUE is not set
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_MATCH_IPRANGE=m
+# CONFIG_IP_NF_MATCH_TOS is not set
+# CONFIG_IP_NF_MATCH_RECENT is not set
+# CONFIG_IP_NF_MATCH_ECN is not set
+# CONFIG_IP_NF_MATCH_AH is not set
+# CONFIG_IP_NF_MATCH_TTL is not set
+# CONFIG_IP_NF_MATCH_OWNER is not set
+# CONFIG_IP_NF_MATCH_ADDRTYPE is not set
+# CONFIG_IP_NF_MATCH_HASHLIMIT is not set
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+# CONFIG_IP_NF_TARGET_LOG is not set
+# CONFIG_IP_NF_TARGET_ULOG is not set
+# CONFIG_IP_NF_TARGET_TCPMSS is not set
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_NAT_NEEDED=y
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
+CONFIG_IP_NF_TARGET_NETMAP=m
+CONFIG_IP_NF_TARGET_SAME=m
+# CONFIG_IP_NF_NAT_SNMP_BASIC is not set
+CONFIG_IP_NF_NAT_IRC=m
+CONFIG_IP_NF_NAT_FTP=m
+CONFIG_IP_NF_NAT_TFTP=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_TARGET_TOS=m
+CONFIG_IP_NF_TARGET_ECN=m
+CONFIG_IP_NF_TARGET_TTL=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_ARPTABLES=m
+CONFIG_IP_NF_ARPFILTER=m
+CONFIG_IP_NF_ARP_MANGLE=m
+
+#
+# DCCP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_DCCP is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+
+#
+# TIPC Configuration (EXPERIMENTAL)
+#
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE 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
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+CONFIG_IEEE80211=m
+CONFIG_IEEE80211_DEBUG=y
+CONFIG_IEEE80211_CRYPT_WEP=m
+CONFIG_IEEE80211_CRYPT_CCMP=m
+CONFIG_IEEE80211_CRYPT_TKIP=m
+CONFIG_IEEE80211_SOFTMAC=m
+CONFIG_IEEE80211_SOFTMAC_DEBUG=y
+CONFIG_WIRELESS_EXT=y
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=m
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_SYS_HYPERVISOR is not set
+
+#
+# Connector - unified userspace <-> kernelspace linker
+#
+# CONFIG_CONNECTOR is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+CONFIG_MTD=y
+# CONFIG_MTD_DEBUG is not set
+CONFIG_MTD_CONCAT=y
+CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_REDBOOT_PARTS is not set
+# CONFIG_MTD_CMDLINE_PARTS is not set
+
+#
+# User Modules And Translation Layers
+#
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+# CONFIG_FTL is not set
+# CONFIG_NFTL is not set
+# CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+
+#
+# RAM/ROM/Flash chip drivers
+#
+CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
+CONFIG_MTD_GEN_PROBE=y
+CONFIG_MTD_CFI_ADV_OPTIONS=y
+CONFIG_MTD_CFI_NOSWAP=y
+# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set
+# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set
+CONFIG_MTD_CFI_GEOMETRY=y
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+# CONFIG_MTD_MAP_BANK_WIDTH_2 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
+CONFIG_MTD_CFI_I1=y
+# CONFIG_MTD_CFI_I2 is not set
+# CONFIG_MTD_CFI_I4 is not set
+# CONFIG_MTD_CFI_I8 is not set
+# CONFIG_MTD_OTP is not set
+# CONFIG_MTD_CFI_INTELEXT is not set
+CONFIG_MTD_CFI_AMDSTD=y
+# CONFIG_MTD_CFI_STAA is not set
+CONFIG_MTD_CFI_UTIL=y
+# CONFIG_MTD_RAM is not set
+# CONFIG_MTD_ROM is not set
+# CONFIG_MTD_ABSENT is not set
+# CONFIG_MTD_OBSOLETE_CHIPS is not set
+
+#
+# Mapping drivers for chip access
+#
+# CONFIG_MTD_COMPLEX_MAPPINGS is not set
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_START=0xffc00000
+CONFIG_MTD_PHYSMAP_LEN=0x400000
+CONFIG_MTD_PHYSMAP_BANKWIDTH=1
+# CONFIG_MTD_PLATRAM is not set
+
+#
+# Self-contained MTD device drivers
+#
+# CONFIG_MTD_PMC551 is not set
+# CONFIG_MTD_SLRAM is not set
+# CONFIG_MTD_PHRAM is not set
+# CONFIG_MTD_MTDRAM is not set
+# CONFIG_MTD_BLOCK2MTD is not set
+
+#
+# Disk-On-Chip Device Drivers
+#
+# CONFIG_MTD_DOC2000 is not set
+# CONFIG_MTD_DOC2001 is not set
+# CONFIG_MTD_DOC2001PLUS is not set
+
+#
+# NAND Flash Device Drivers
+#
+# CONFIG_MTD_NAND is not set
+
+#
+# OneNAND Flash Device Drivers
+#
+# CONFIG_MTD_ONENAND is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play support
+#
+
+#
+# Block devices
+#
+# CONFIG_BLK_DEV_FD is not set
+# 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 is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_SX8 is not set
+# CONFIG_BLK_DEV_UB is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=2
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+
+#
+# Misc devices
+#
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+
+#
+# ATA/ATAPI/MFM/RLL support
+#
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+# 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=y
+# CONFIG_CHR_DEV_SCH is not set
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+CONFIG_SCSI_MULTI_LUN=y
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# 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
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_3W_9XXX 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_DPT_I2O 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_HPTIOP is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH 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_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Serial ATA (prod) and Parallel ATA (experimental) drivers
+#
+CONFIG_ATA=y
+# CONFIG_SATA_AHCI is not set
+# CONFIG_SATA_SVW is not set
+# CONFIG_ATA_PIIX is not set
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SX4 is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIL24 is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_ATA_GENERIC 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_IT821X is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_TRIFLEX is not set
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_PDC2027X is not set
+CONFIG_PATA_SIL680=y
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+# CONFIG_FUSION_SPI is not set
+# CONFIG_FUSION_FC is not set
+# CONFIG_FUSION_SAS is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+
+#
+# Macintosh device drivers
+#
+# CONFIG_WINDFARM is not set
+
+#
+# Network device support
+#
+CONFIG_NETDEVICES=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+CONFIG_TUN=m
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+
+#
+# PHY device support
+#
+
+#
+# Ethernet (10 or 100Mbit)
+#
+# CONFIG_NET_ETHERNET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 is not set
+# CONFIG_NS83820 is not set
+# CONFIG_HAMACHI is not set
+# CONFIG_YELLOWFIN is not set
+CONFIG_R8169=y
+# CONFIG_R8169_NAPI is not set
+# CONFIG_SIS190 is not set
+# CONFIG_SKGE is not set
+# CONFIG_SKY2 is not set
+# CONFIG_SK98LIN is not set
+# CONFIG_TIGON3 is not set
+# CONFIG_BNX2 is not set
+# CONFIG_QLA3XXX is not set
+
+#
+# Ethernet (10000 Mbit)
+#
+# CONFIG_CHELSIO_T1 is not set
+# CONFIG_IXGB is not set
+# CONFIG_S2IO is not set
+# CONFIG_MYRI10GE is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+CONFIG_NET_RADIO=y
+# CONFIG_NET_WIRELESS_RTNETLINK is not set
+
+#
+# Obsolete Wireless cards support (pre-802.11)
+#
+# CONFIG_STRIP is not set
+
+#
+# Wireless 802.11b ISA/PCI cards support
+#
+# CONFIG_IPW2100 is not set
+# CONFIG_IPW2200 is not set
+# CONFIG_AIRO is not set
+# CONFIG_HERMES is not set
+# CONFIG_ATMEL is not set
+
+#
+# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support
+#
+# CONFIG_PRISM54 is not set
+# CONFIG_USB_ZD1201 is not set
+# CONFIG_HOSTAP is not set
+# CONFIG_BCM43XX is not set
+# CONFIG_ZD1211RW is not set
+CONFIG_NET_WIRELESS=y
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN 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_SHAPER is not set
+CONFIG_NETCONSOLE=y
+CONFIG_NETPOLL=y
+# CONFIG_NETPOLL_RX is not set
+# CONFIG_NETPOLL_TRAP is not set
+CONFIG_NET_POLL_CONTROLLER=y
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_TSDEV is not set
+CONFIG_INPUT_EVDEV=m
+# 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_TOUCHSCREEN is not set
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=m
+
+#
+# Hardware I/O ports
+#
+CONFIG_SERIO=y
+# CONFIG_SERIO_I8042 is not set
+CONFIG_SERIO_SERPORT=y
+# CONFIG_SERIO_PCIPS2 is not set
+# CONFIG_SERIO_RAW is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+# CONFIG_VT_HW_CONSOLE_BINDING is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_PCI=y
+CONFIG_SERIAL_8250_NR_UARTS=4
+CONFIG_SERIAL_8250_RUNTIME_UARTS=4
+# CONFIG_SERIAL_8250_EXTENDED is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_SERIAL_JSM is not set
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+CONFIG_HW_RANDOM=y
+# CONFIG_NVRAM is not set
+# CONFIG_GEN_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_AGP is not set
+# CONFIG_DRM is not set
+# CONFIG_RAW_DRIVER is not set
+
+#
+# TPM devices
+#
+# CONFIG_TCG_TPM is not set
+
+#
+# I2C support
+#
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+
+#
+# I2C Algorithms
+#
+# CONFIG_I2C_ALGOBIT is not set
+# CONFIG_I2C_ALGOPCF is not set
+# CONFIG_I2C_ALGOPCA is not set
+
+#
+# I2C Hardware Bus support
+#
+# 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_I810 is not set
+# CONFIG_I2C_PIIX4 is not set
+CONFIG_I2C_MPC=y
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_PROSAVAGE is not set
+# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_ISA is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_SENSORS_DS1337 is not set
+# CONFIG_SENSORS_DS1374 is not set
+CONFIG_SENSORS_EEPROM=m
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_M41T00 is not set
+# CONFIG_SENSORS_MAX6875 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_I2C_DEBUG_CHIP is not set
+
+#
+# SPI support
+#
+# CONFIG_SPI is not set
+# CONFIG_SPI_MASTER is not set
+
+#
+# Dallas's 1-wire bus
+#
+# CONFIG_W1 is not set
+
+#
+# Hardware Monitoring support
+#
+CONFIG_HWMON=y
+# CONFIG_HWMON_VID is not set
+# CONFIG_SENSORS_ABITUGURU is not set
+# CONFIG_SENSORS_ADM1021 is not set
+# CONFIG_SENSORS_ADM1025 is not set
+# CONFIG_SENSORS_ADM1026 is not set
+# CONFIG_SENSORS_ADM1031 is not set
+# CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATXP1 is not set
+# CONFIG_SENSORS_DS1621 is not set
+# CONFIG_SENSORS_F71805F is not set
+# CONFIG_SENSORS_FSCHER is not set
+# CONFIG_SENSORS_FSCPOS is not set
+# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_GL520SM is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_LM63 is not set
+# CONFIG_SENSORS_LM75 is not set
+# CONFIG_SENSORS_LM77 is not set
+# CONFIG_SENSORS_LM78 is not set
+# CONFIG_SENSORS_LM80 is not set
+# CONFIG_SENSORS_LM83 is not set
+# CONFIG_SENSORS_LM85 is not set
+# CONFIG_SENSORS_LM87 is not set
+# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_LM92 is not set
+# CONFIG_SENSORS_MAX1619 is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_SIS5595 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47M192 is not set
+# CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_VT1211 is not set
+# CONFIG_SENSORS_VT8231 is not set
+# CONFIG_SENSORS_W83781D is not set
+# CONFIG_SENSORS_W83791D is not set
+# CONFIG_SENSORS_W83792D is not set
+# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83627HF is not set
+# CONFIG_SENSORS_W83627EHF is not set
+# CONFIG_HWMON_DEBUG_CHIP is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# Digital Video Broadcasting Devices
+#
+# CONFIG_DVB is not set
+# CONFIG_USB_DABUSB is not set
+
+#
+# Graphics support
+#
+CONFIG_FIRMWARE_EDID=y
+# CONFIG_FB is not set
+
+#
+# Console display driver support
+#
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+CONFIG_USB_ARCH_HAS_EHCI=y
+CONFIG_USB=y
+# CONFIG_USB_DEBUG is not set
+
+#
+# Miscellaneous USB options
+#
+CONFIG_USB_DEVICEFS=y
+# CONFIG_USB_BANDWIDTH is not set
+# CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_OTG is not set
+
+#
+# USB Host Controller Drivers
+#
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_SPLIT_ISO is not set
+# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+# CONFIG_USB_ISP116X_HCD is not set
+CONFIG_USB_OHCI_HCD=y
+# CONFIG_USB_OHCI_BIG_ENDIAN is not set
+CONFIG_USB_OHCI_LITTLE_ENDIAN=y
+# CONFIG_USB_UHCI_HCD is not set
+# CONFIG_USB_SL811_HCD is not set
+
+#
+# USB Device Class drivers
+#
+# CONFIG_USB_ACM is not set
+# CONFIG_USB_PRINTER is not set
+
+#
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# may also be needed; see USB_STORAGE Help for more information
+#
+CONFIG_USB_STORAGE=m
+# CONFIG_USB_STORAGE_DEBUG is not set
+# CONFIG_USB_STORAGE_DATAFAB is not set
+# CONFIG_USB_STORAGE_FREECOM is not set
+# CONFIG_USB_STORAGE_DPCM is not set
+# CONFIG_USB_STORAGE_USBAT is not set
+# CONFIG_USB_STORAGE_SDDR09 is not set
+# CONFIG_USB_STORAGE_SDDR55 is not set
+# CONFIG_USB_STORAGE_JUMPSHOT is not set
+# CONFIG_USB_STORAGE_ALAUDA is not set
+# CONFIG_USB_STORAGE_ONETOUCH is not set
+# CONFIG_USB_STORAGE_KARMA is not set
+# CONFIG_USB_LIBUSUAL is not set
+
+#
+# USB Input Devices
+#
+# CONFIG_USB_HID is not set
+
+#
+# USB HID Boot Protocol drivers
+#
+# CONFIG_USB_KBD is not set
+# CONFIG_USB_MOUSE is not set
+# CONFIG_USB_AIPTEK is not set
+# CONFIG_USB_WACOM is not set
+# CONFIG_USB_ACECAD is not set
+# CONFIG_USB_KBTAB is not set
+# CONFIG_USB_POWERMATE is not set
+# CONFIG_USB_TOUCHSCREEN is not set
+# CONFIG_USB_YEALINK is not set
+# CONFIG_USB_XPAD is not set
+# CONFIG_USB_ATI_REMOTE is not set
+# CONFIG_USB_ATI_REMOTE2 is not set
+# CONFIG_USB_KEYSPAN_REMOTE is not set
+# CONFIG_USB_APPLETOUCH is not set
+
+#
+# USB Imaging devices
+#
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_MICROTEK is not set
+
+#
+# USB Network Adapters
+#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET is not set
+CONFIG_USB_MON=y
+
+#
+# USB port drivers
+#
+
+#
+# USB Serial Converter support
+#
+CONFIG_USB_SERIAL=y
+CONFIG_USB_SERIAL_CONSOLE=y
+# CONFIG_USB_SERIAL_GENERIC is not set
+# CONFIG_USB_SERIAL_AIRCABLE is not set
+# CONFIG_USB_SERIAL_AIRPRIME is not set
+# CONFIG_USB_SERIAL_ARK3116 is not set
+# CONFIG_USB_SERIAL_BELKIN is not set
+# CONFIG_USB_SERIAL_WHITEHEAT is not set
+# CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set
+# CONFIG_USB_SERIAL_CP2101 is not set
+# CONFIG_USB_SERIAL_CYPRESS_M8 is not set
+# CONFIG_USB_SERIAL_EMPEG is not set
+CONFIG_USB_SERIAL_FTDI_SIO=y
+# CONFIG_USB_SERIAL_FUNSOFT is not set
+# CONFIG_USB_SERIAL_VISOR is not set
+# CONFIG_USB_SERIAL_IPAQ is not set
+# CONFIG_USB_SERIAL_IR is not set
+# CONFIG_USB_SERIAL_EDGEPORT is not set
+# CONFIG_USB_SERIAL_EDGEPORT_TI is not set
+# CONFIG_USB_SERIAL_GARMIN is not set
+# CONFIG_USB_SERIAL_IPW is not set
+# CONFIG_USB_SERIAL_KEYSPAN_PDA is not set
+# CONFIG_USB_SERIAL_KEYSPAN is not set
+# CONFIG_USB_SERIAL_KLSI is not set
+# CONFIG_USB_SERIAL_KOBIL_SCT is not set
+# CONFIG_USB_SERIAL_MCT_U232 is not set
+# CONFIG_USB_SERIAL_MOS7720 is not set
+# CONFIG_USB_SERIAL_MOS7840 is not set
+# CONFIG_USB_SERIAL_NAVMAN is not set
+# CONFIG_USB_SERIAL_PL2303 is not set
+# CONFIG_USB_SERIAL_HP4X is not set
+# CONFIG_USB_SERIAL_SAFE is not set
+# CONFIG_USB_SERIAL_SIERRAWIRELESS is not set
+# CONFIG_USB_SERIAL_TI is not set
+# CONFIG_USB_SERIAL_CYBERJACK is not set
+# CONFIG_USB_SERIAL_XIRCOM is not set
+# CONFIG_USB_SERIAL_OPTION is not set
+# CONFIG_USB_SERIAL_OMNINET is not set
+
+#
+# USB Miscellaneous drivers
+#
+# CONFIG_USB_EMI62 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_ADUTUX is not set
+# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_LEGOTOWER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_LED is not set
+# CONFIG_USB_CYPRESS_CY7C63 is not set
+# CONFIG_USB_CYTHERM is not set
+# CONFIG_USB_PHIDGET is not set
+# CONFIG_USB_IDMOUSE is not set
+# CONFIG_USB_FTDI_ELAN is not set
+# CONFIG_USB_APPLEDISPLAY is not set
+# CONFIG_USB_SISUSBVGA is not set
+# CONFIG_USB_LD is not set
+# CONFIG_USB_TRANCEVIBRATOR is not set
+# CONFIG_USB_TEST is not set
+
+#
+# USB DSL modem support
+#
+
+#
+# USB Gadget Support
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# MMC/SD Card support
+#
+# CONFIG_MMC is not set
+
+#
+# LED devices
+#
+# CONFIG_NEW_LEDS is not set
+
+#
+# LED drivers
+#
+
+#
+# LED Triggers
+#
+
+#
+# InfiniBand support
+#
+# CONFIG_INFINIBAND is not set
+
+#
+# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
+#
+
+#
+# Real Time Clock
+#
+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
+
+#
+# RTC drivers
+#
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+CONFIG_RTC_DRV_RS5C372=y
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_TEST is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# DMA Engine support
+#
+# CONFIG_DMA_ENGINE is not set
+
+#
+# DMA Clients
+#
+
+#
+# DMA Devices
+#
+
+#
+# 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_FS_XATTR=y
+# CONFIG_EXT3_FS_POSIX_ACL is not set
+# CONFIG_EXT3_FS_SECURITY is not set
+# CONFIG_EXT4DEV_FS is not set
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+CONFIG_FS_POSIX_ACL=y
+# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
+# CONFIG_OCFS2_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_ROMFS_FS is not set
+CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_QUOTA is not set
+CONFIG_DNOTIFY=y
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+CONFIG_ISO9660_FS=m
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_ZISOFS_FS=m
+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="iso8859-1"
+CONFIG_NTFS_FS=m
+# CONFIG_NTFS_DEBUG is not set
+# CONFIG_NTFS_RW is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+# CONFIG_CONFIGFS_FS is not set
+
+#
+# Miscellaneous filesystems
+#
+# 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_JFFS_FS is not set
+# CONFIG_JFFS2_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+# CONFIG_NFS_DIRECTIO is not set
+CONFIG_NFSD=m
+CONFIG_NFSD_V3=y
+# CONFIG_NFSD_V3_ACL is not set
+# CONFIG_NFSD_V4 is not set
+CONFIG_NFSD_TCP=y
+CONFIG_ROOT_NFS=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+CONFIG_EXPORTFS=m
+CONFIG_NFS_ACL_SUPPORT=y
+CONFIG_NFS_COMMON=y
+CONFIG_SUNRPC=y
+CONFIG_SUNRPC_GSS=y
+CONFIG_RPCSEC_GSS_KRB5=y
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_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
+# CONFIG_9P_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+
+#
+# Native Language Support
+#
+CONFIG_NLS=m
+CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_CODEPAGE_437=m
+# 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=m
+# 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=m
+
+#
+# Library routines
+#
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+CONFIG_CRC32=y
+CONFIG_LIBCRC32C=m
+CONFIG_ZLIB_INFLATE=m
+CONFIG_ZLIB_DEFLATE=m
+CONFIG_PLIST=y
+
+#
+# Instrumentation Support
+#
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=m
+
+#
+# Kernel hacking
+#
+# CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_KERNEL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_DEBUG_SLAB 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_RWSEMS is not set
+# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_INFO is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_LIST is not set
+CONFIG_FORCED_INLINING=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_DEBUGGER is not set
+# CONFIG_BDI_SWITCH is not set
+# CONFIG_BOOTX_TEXT is not set
+# CONFIG_SERIAL_TEXT_DEBUG is not set
+# CONFIG_PPC_EARLY_DEBUG is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+
+#
+# Cryptographic options
+#
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_MANAGER=y
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_SHA1=m
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_WP512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_DES=y
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_TWOFISH_COMMON=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_AES=m
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_TEA is not set
+CONFIG_CRYPTO_ARC4=m
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_DEFLATE=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_CRC32C=m
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Hardware crypto devices
+#
diff --git a/arch/powerpc/configs/lite5200_defconfig b/arch/powerpc/configs/lite5200_defconfig
new file mode 100644
index 000000000000..ee7655776d45
--- /dev/null
+++ b/arch/powerpc/configs/lite5200_defconfig
@@ -0,0 +1,931 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.19-rc6
+# Mon Nov 27 11:08:20 2006
+#
+# CONFIG_PPC64 is not set
+CONFIG_PPC32=y
+CONFIG_PPC_MERGE=y
+CONFIG_MMU=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_IRQ_PER_CPU=y
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_PPC=y
+CONFIG_EARLY_PRINTK=y
+CONFIG_GENERIC_NVRAM=y
+CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_PPC_OF=y
+# CONFIG_PPC_UDBG_16550 is not set
+# CONFIG_GENERIC_TBSYNC is not set
+CONFIG_AUDIT_ARCH=y
+# CONFIG_DEFAULT_UIMAGE is not set
+
+#
+# Processor support
+#
+CONFIG_CLASSIC32=y
+# CONFIG_PPC_52xx is not set
+# CONFIG_PPC_82xx is not set
+# CONFIG_PPC_83xx is not set
+# CONFIG_PPC_85xx is not set
+# CONFIG_PPC_86xx is not set
+# CONFIG_40x is not set
+# CONFIG_44x is not set
+# CONFIG_8xx is not set
+# CONFIG_E200 is not set
+CONFIG_6xx=y
+CONFIG_PPC_FPU=y
+# CONFIG_PPC_DCR_NATIVE is not set
+# CONFIG_PPC_DCR_MMIO is not set
+# CONFIG_ALTIVEC is not set
+CONFIG_PPC_STD_MMU=y
+CONFIG_PPC_STD_MMU_32=y
+# CONFIG_SMP is not set
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+# CONFIG_IPC_NS is not set
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_UTS_NS is not set
+# CONFIG_AUDIT is not set
+# CONFIG_IKCONFIG is not set
+# CONFIG_RELAY is not set
+CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SYSCTL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SYSCTL_SYSCALL is not set
+# CONFIG_KALLSYMS 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 is not set
+CONFIG_SHMEM=y
+CONFIG_SLAB=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_RT_MUTEXES=y
+# CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
+# CONFIG_SLOB is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=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_KMOD is not set
+
+#
+# Block layer
+#
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+
+#
+# Platform support
+#
+CONFIG_PPC_MULTIPLATFORM=y
+# CONFIG_EMBEDDED6xx is not set
+# CONFIG_APUS is not set
+# CONFIG_PPC_CHRP is not set
+CONFIG_PPC_MPC52xx=y
+# CONFIG_PPC_EFIKA is not set
+CONFIG_PPC_LITE5200=y
+# CONFIG_PPC_PMAC is not set
+# CONFIG_PPC_CELL is not set
+# CONFIG_PPC_CELL_NATIVE is not set
+# CONFIG_PPC_RTAS is not set
+# CONFIG_MMIO_NVRAM is not set
+# CONFIG_PPC_MPC106 is not set
+# CONFIG_PPC_970_NAP is not set
+# CONFIG_PPC_INDIRECT_IO is not set
+# CONFIG_GENERIC_IOMAP is not set
+# CONFIG_CPU_FREQ is not set
+# CONFIG_TAU is not set
+# CONFIG_WANT_EARLY_SERIAL is not set
+# CONFIG_MPIC is not set
+
+#
+# Kernel options
+#
+# CONFIG_HIGHMEM is not set
+# CONFIG_HZ_100 is not set
+CONFIG_HZ_250=y
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=250
+CONFIG_PREEMPT_NONE=y
+# CONFIG_PREEMPT_VOLUNTARY is not set
+# CONFIG_PREEMPT is not set
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_MISC is not set
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+# CONFIG_KEXEC is not set
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_RESOURCES_64BIT is not set
+CONFIG_PROC_DEVICETREE=y
+# CONFIG_CMDLINE_BOOL is not set
+CONFIG_PM=y
+# CONFIG_PM_LEGACY is not set
+# CONFIG_PM_DEBUG is not set
+# CONFIG_PM_SYSFS_DEPRECATED is not set
+# CONFIG_SOFTWARE_SUSPEND is not set
+CONFIG_SECCOMP=y
+CONFIG_ISA_DMA_API=y
+
+#
+# Bus options
+#
+CONFIG_GENERIC_ISA_DMA=y
+# CONFIG_MPIC_WEIRD is not set
+# CONFIG_PPC_I8259 is not set
+# CONFIG_PPC_INDIRECT_PCI is not set
+CONFIG_PCI=y
+CONFIG_PCI_DOMAINS=y
+# CONFIG_PCIEPORTBUS is not set
+# CONFIG_PCI_DEBUG is not set
+
+#
+# PCCARD (PCMCIA/CardBus) support
+#
+# CONFIG_PCCARD is not set
+
+#
+# PCI Hotplug Support
+#
+# CONFIG_HOTPLUG_PCI is not set
+
+#
+# Advanced setup
+#
+# CONFIG_ADVANCED_OPTIONS is not set
+
+#
+# Default settings for advanced configuration options are used
+#
+CONFIG_HIGHMEM_START=0xfe000000
+CONFIG_LOWMEM_SIZE=0x30000000
+CONFIG_KERNEL_START=0xc0000000
+CONFIG_TASK_SIZE=0x80000000
+CONFIG_BOOT_LOAD=0x00800000
+
+#
+# Networking
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+# CONFIG_NETDEBUG is not set
+CONFIG_PACKET=y
+# CONFIG_PACKET_MMAP is not set
+CONFIG_UNIX=y
+CONFIG_XFRM=y
+CONFIG_XFRM_USER=m
+# CONFIG_XFRM_SUB_POLICY 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_FIB_HASH=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_IP_MROUTE is not set
+# CONFIG_ARPD is not set
+CONFIG_SYN_COOKIES=y
+# 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 is not set
+CONFIG_INET_XFRM_MODE_TRANSPORT=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_INET_XFRM_MODE_BEET=y
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_IPV6 is not set
+# CONFIG_INET6_XFRM_TUNNEL is not set
+# CONFIG_INET6_TUNNEL is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETFILTER is not set
+
+#
+# DCCP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_DCCP is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+
+#
+# TIPC Configuration (EXPERIMENTAL)
+#
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE 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
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_IEEE80211 is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_SYS_HYPERVISOR is not set
+
+#
+# Connector - unified userspace <-> kernelspace linker
+#
+# CONFIG_CONNECTOR is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play support
+#
+
+#
+# Block devices
+#
+# CONFIG_BLK_DEV_FD is not set
+# 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 is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_SX8 is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=32768
+CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+
+#
+# Misc devices
+#
+# CONFIG_SGI_IOC4 is not set
+# CONFIG_TIFM_CORE is not set
+
+#
+# ATA/ATAPI/MFM/RLL support
+#
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_SCSI_PROC_FS is not set
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+# CONFIG_BLK_DEV_SD is not set
+# 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
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# 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
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
+# CONFIG_SCSI_3W_9XXX 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_DPT_I2O 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_HPTIOP is not set
+# CONFIG_SCSI_BUSLOGIC is not set
+# CONFIG_SCSI_DMX3191D is not set
+# CONFIG_SCSI_EATA is not set
+# CONFIG_SCSI_FUTURE_DOMAIN is not set
+# CONFIG_SCSI_GDTH 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_NSP32 is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Serial ATA (prod) and Parallel ATA (experimental) drivers
+#
+CONFIG_ATA=y
+# CONFIG_SATA_AHCI is not set
+# CONFIG_SATA_SVW is not set
+# CONFIG_ATA_PIIX is not set
+# CONFIG_SATA_MV is not set
+# CONFIG_SATA_NV is not set
+# CONFIG_PDC_ADMA is not set
+# CONFIG_SATA_QSTOR is not set
+# CONFIG_SATA_PROMISE is not set
+# CONFIG_SATA_SX4 is not set
+# CONFIG_SATA_SIL is not set
+# CONFIG_SATA_SIL24 is not set
+# CONFIG_SATA_SIS is not set
+# CONFIG_SATA_ULI is not set
+# CONFIG_SATA_VIA is not set
+# CONFIG_SATA_VITESSE is not set
+# CONFIG_PATA_ALI is not set
+# CONFIG_PATA_AMD is not set
+# CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATIIXP is not set
+# CONFIG_PATA_CMD64X is not set
+# CONFIG_PATA_CS5520 is not set
+# CONFIG_PATA_CS5530 is not set
+# CONFIG_PATA_CYPRESS is not set
+# CONFIG_PATA_EFAR is not set
+# CONFIG_ATA_GENERIC 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_IT821X is not set
+# CONFIG_PATA_JMICRON is not set
+# CONFIG_PATA_TRIFLEX is not set
+CONFIG_PATA_MPC52xx=y
+# CONFIG_PATA_MPIIX is not set
+# CONFIG_PATA_OLDPIIX is not set
+# CONFIG_PATA_NETCELL is not set
+# CONFIG_PATA_NS87410 is not set
+# CONFIG_PATA_OPTI is not set
+# CONFIG_PATA_OPTIDMA is not set
+# CONFIG_PATA_PDC_OLD is not set
+# CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RZ1000 is not set
+# CONFIG_PATA_SC1200 is not set
+# CONFIG_PATA_SERVERWORKS is not set
+# CONFIG_PATA_PDC2027X is not set
+# CONFIG_PATA_SIL680 is not set
+# CONFIG_PATA_SIS is not set
+# CONFIG_PATA_VIA is not set
+# CONFIG_PATA_WINBOND is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+# CONFIG_FUSION_SPI is not set
+# CONFIG_FUSION_FC is not set
+# CONFIG_FUSION_SAS is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+# CONFIG_IEEE1394 is not set
+
+#
+# I2O device support
+#
+# CONFIG_I2O is not set
+
+#
+# Macintosh device drivers
+#
+# CONFIG_WINDFARM is not set
+
+#
+# Network device support
+#
+CONFIG_NETDEVICES=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+# CONFIG_TUN is not set
+
+#
+# ARCnet devices
+#
+# CONFIG_ARCNET is not set
+
+#
+# PHY device support
+#
+
+#
+# Ethernet (10 or 100Mbit)
+#
+# CONFIG_NET_ETHERNET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+# CONFIG_ACENIC is not set
+# CONFIG_DL2K is not set
+# CONFIG_E1000 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_SK98LIN is not set
+# CONFIG_TIGON3 is not set
+# CONFIG_BNX2 is not set
+# CONFIG_MV643XX_ETH is not set
+# CONFIG_QLA3XXX is not set
+
+#
+# Ethernet (10000 Mbit)
+#
+# CONFIG_CHELSIO_T1 is not set
+# CONFIG_IXGB is not set
+# CONFIG_S2IO is not set
+# CONFIG_MYRI10GE is not set
+
+#
+# Token Ring devices
+#
+# CONFIG_TR is not set
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN 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_SHAPER is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+# CONFIG_INPUT 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_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+CONFIG_SERIAL_MPC52xx=y
+CONFIG_SERIAL_MPC52xx_CONSOLE=y
+CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=9600
+# CONFIG_SERIAL_JSM is not set
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_NVRAM is not set
+# CONFIG_GEN_RTC is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+# CONFIG_APPLICOM is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_AGP is not set
+# CONFIG_DRM is not set
+# CONFIG_RAW_DRIVER is not set
+
+#
+# TPM devices
+#
+# CONFIG_TCG_TPM is not set
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# SPI support
+#
+# CONFIG_SPI is not set
+# CONFIG_SPI_MASTER is not set
+
+#
+# Dallas's 1-wire bus
+#
+# CONFIG_W1 is not set
+
+#
+# Hardware Monitoring support
+#
+# CONFIG_HWMON is not set
+# CONFIG_HWMON_VID is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# Digital Video Broadcasting Devices
+#
+# CONFIG_DVB is not set
+
+#
+# Graphics support
+#
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+CONFIG_USB_ARCH_HAS_EHCI=y
+# CONFIG_USB is not set
+
+#
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# USB Gadget Support
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# MMC/SD Card support
+#
+# CONFIG_MMC is not set
+
+#
+# LED devices
+#
+# CONFIG_NEW_LEDS is not set
+
+#
+# LED drivers
+#
+
+#
+# LED Triggers
+#
+
+#
+# InfiniBand support
+#
+# CONFIG_INFINIBAND is not set
+
+#
+# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
+#
+
+#
+# Real Time Clock
+#
+# CONFIG_RTC_CLASS is not set
+
+#
+# DMA Engine support
+#
+# CONFIG_DMA_ENGINE is not set
+
+#
+# DMA Clients
+#
+
+#
+# DMA Devices
+#
+
+#
+# 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_FS_XATTR=y
+# CONFIG_EXT3_FS_POSIX_ACL is not set
+# CONFIG_EXT3_FS_SECURITY is not set
+# CONFIG_EXT4DEV_FS is not set
+CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
+# CONFIG_OCFS2_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_ROMFS_FS is not set
+CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_QUOTA is not set
+CONFIG_DNOTIFY=y
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+# CONFIG_CONFIGFS_FS is not set
+
+#
+# Miscellaneous filesystems
+#
+# 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_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+# CONFIG_NFS_FS is not set
+# CONFIG_NFSD is not set
+# CONFIG_SMB_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
+# CONFIG_9P_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+
+#
+# Native Language Support
+#
+# CONFIG_NLS is not set
+
+#
+# Library routines
+#
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC32 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_PLIST=y
+
+#
+# Instrumentation Support
+#
+# CONFIG_PROFILING is not set
+
+#
+# Kernel hacking
+#
+CONFIG_PRINTK_TIME=y
+CONFIG_ENABLE_MUST_CHECK=y
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_KERNEL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_DEBUG_SLAB 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_RWSEMS is not set
+# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_KOBJECT is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_LIST is not set
+CONFIG_FORCED_INLINING=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_DEBUGGER is not set
+# CONFIG_BDI_SWITCH is not set
+# CONFIG_BOOTX_TEXT is not set
+# CONFIG_SERIAL_TEXT_DEBUG is not set
+# CONFIG_PPC_EARLY_DEBUG is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+
+#
+# Cryptographic options
+#
+# CONFIG_CRYPTO is not set
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index be11df7c11aa..1c009651f925 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -1386,8 +1386,8 @@ CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
 CONFIG_DNOTIFY=y
-CONFIG_AUTOFS_FS=y
-# CONFIG_AUTOFS4_FS is not set
+# CONFIG_AUTOFS_FS is not set
+CONFIG_AUTOFS4_FS=m
 # CONFIG_FUSE_FS is not set
 
 #
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
new file mode 100644
index 000000000000..f2d888e014a9
--- /dev/null
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -0,0 +1,837 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.19-rc6
+# Tue Nov 21 19:38:53 2006
+#
+CONFIG_PPC64=y
+CONFIG_64BIT=y
+CONFIG_PPC_MERGE=y
+CONFIG_MMU=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_IRQ_PER_CPU=y
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_PPC=y
+CONFIG_EARLY_PRINTK=y
+CONFIG_COMPAT=y
+CONFIG_SYSVIPC_COMPAT=y
+CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_PPC_OF=y
+# CONFIG_PPC_UDBG_16550 is not set
+# CONFIG_GENERIC_TBSYNC is not set
+CONFIG_AUDIT_ARCH=y
+# CONFIG_DEFAULT_UIMAGE is not set
+
+#
+# Processor support
+#
+# CONFIG_POWER4_ONLY is not set
+CONFIG_POWER3=y
+CONFIG_POWER4=y
+CONFIG_PPC_FPU=y
+# CONFIG_PPC_DCR_NATIVE is not set
+# CONFIG_PPC_DCR_MMIO is not set
+# CONFIG_PPC_OF_PLATFORM_PCI is not set
+CONFIG_ALTIVEC=y
+CONFIG_PPC_STD_MMU=y
+CONFIG_VIRT_CPU_ACCOUNTING=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# Code maturity level options
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_LOCK_KERNEL=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+
+#
+# General setup
+#
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+# CONFIG_IPC_NS is not set
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_UTS_NS is not set
+# CONFIG_AUDIT is not set
+# CONFIG_IKCONFIG is not set
+# CONFIG_CPUSETS is not set
+# CONFIG_RELAY is not set
+CONFIG_INITRAMFS_SOURCE=""
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SYSCTL=y
+CONFIG_EMBEDDED=y
+# CONFIG_SYSCTL_SYSCALL is not set
+CONFIG_KALLSYMS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KALLSYMS_EXTRA_PASS=y
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SHMEM=y
+CONFIG_SLAB=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_RT_MUTEXES=y
+# CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
+# CONFIG_SLOB is not set
+
+#
+# Loadable module support
+#
+CONFIG_MODULES=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_KMOD=y
+CONFIG_STOP_MACHINE=y
+
+#
+# Block layer
+#
+CONFIG_BLOCK=y
+# CONFIG_BLK_DEV_IO_TRACE is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+
+#
+# Platform support
+#
+CONFIG_PPC_MULTIPLATFORM=y
+# CONFIG_EMBEDDED6xx is not set
+# CONFIG_APUS is not set
+# CONFIG_PPC_PSERIES is not set
+# CONFIG_PPC_ISERIES is not set
+# CONFIG_PPC_PMAC is not set
+# CONFIG_PPC_MAPLE is not set
+# CONFIG_PPC_PASEMI is not set
+CONFIG_PPC_CELL=y
+# CONFIG_PPC_CELL_NATIVE is not set
+# CONFIG_PPC_IBM_CELL_BLADE is not set
+CONFIG_PPC_PS3=y
+# CONFIG_U3_DART is not set
+# CONFIG_PPC_RTAS is not set
+# CONFIG_MMIO_NVRAM is not set
+# CONFIG_PPC_MPC106 is not set
+# CONFIG_PPC_970_NAP is not set
+# CONFIG_PPC_INDIRECT_IO is not set
+# CONFIG_GENERIC_IOMAP is not set
+# CONFIG_CPU_FREQ is not set
+# CONFIG_WANT_EARLY_SERIAL is not set
+# CONFIG_MPIC is not set
+
+#
+# Cell Broadband Engine options
+#
+CONFIG_SPU_FS=y
+CONFIG_SPU_BASE=y
+# CONFIG_CBE_RAS is not set
+
+#
+# PS3 Platform Options
+#
+CONFIG_PS3_HTAB_SIZE=20
+CONFIG_PS3_DYNAMIC_DMA=y
+CONFIG_PS3_USE_LPAR_ADDR=y
+
+#
+# Kernel options
+#
+# CONFIG_HZ_100 is not set
+CONFIG_HZ_250=y
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=250
+CONFIG_PREEMPT_NONE=y
+# CONFIG_PREEMPT_VOLUNTARY is not set
+# CONFIG_PREEMPT is not set
+# CONFIG_PREEMPT_BKL is not set
+CONFIG_BINFMT_ELF=y
+CONFIG_BINFMT_MISC=y
+CONFIG_FORCE_MAX_ZONEORDER=9
+# CONFIG_IOMMU_VMERGE is not set
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+# CONFIG_KEXEC is not set
+# CONFIG_CRASH_DUMP is not set
+# CONFIG_IRQ_ALL_CPUS is not set
+# CONFIG_NUMA is not set
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_SELECT_MEMORY_MODEL=y
+# CONFIG_FLATMEM_MANUAL is not set
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
+CONFIG_HAVE_MEMORY_PRESENT=y
+# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_SPARSEMEM_EXTREME=y
+CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTPLUG_SPARSE=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_RESOURCES_64BIT=y
+CONFIG_ARCH_MEMORY_PROBE=y
+CONFIG_PPC_64K_PAGES=y
+# CONFIG_SCHED_SMT is not set
+CONFIG_PROC_DEVICETREE=y
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="root=/dev/nfs rw ip=dhcp"
+# CONFIG_PM is not set
+# CONFIG_SECCOMP is not set
+CONFIG_ISA_DMA_API=y
+
+#
+# Bus options
+#
+CONFIG_GENERIC_ISA_DMA=y
+# CONFIG_MPIC_WEIRD is not set
+# CONFIG_PPC_I8259 is not set
+# CONFIG_PCI is not set
+# CONFIG_PCI_DOMAINS is not set
+
+#
+# PCCARD (PCMCIA/CardBus) support
+#
+# CONFIG_PCCARD is not set
+
+#
+# PCI Hotplug Support
+#
+CONFIG_KERNEL_START=0xc000000000000000
+
+#
+# Networking
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+# CONFIG_NETDEBUG is not set
+# CONFIG_PACKET is not set
+CONFIG_UNIX=y
+# CONFIG_NET_KEY is not set
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_FIB_HASH=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE 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 is not set
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET 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_IPV6 is not set
+# CONFIG_INET6_XFRM_TUNNEL is not set
+# CONFIG_INET6_TUNNEL is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETFILTER is not set
+
+#
+# DCCP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_DCCP is not set
+
+#
+# SCTP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_SCTP is not set
+
+#
+# TIPC Configuration (EXPERIMENTAL)
+#
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE 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
+
+#
+# QoS and/or fair queueing
+#
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_IEEE80211 is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_SYS_HYPERVISOR is not set
+
+#
+# Connector - unified userspace <-> kernelspace linker
+#
+# CONFIG_CONNECTOR is not set
+
+#
+# Memory Technology Devices (MTD)
+#
+# CONFIG_MTD is not set
+
+#
+# Parallel port support
+#
+# CONFIG_PARPORT is not set
+
+#
+# Plug and Play support
+#
+
+#
+# Block devices
+#
+# CONFIG_BLK_DEV_FD is not set
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_BLK_DEV_INITRD is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+
+#
+# Misc devices
+#
+# CONFIG_TIFM_CORE is not set
+
+#
+# ATA/ATAPI/MFM/RLL support
+#
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+# CONFIG_BLK_DEV_SD is not set
+# 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
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+
+#
+# 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
+
+#
+# SCSI low-level drivers
+#
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_SCSI_DEBUG is not set
+
+#
+# Serial ATA (prod) and Parallel ATA (experimental) drivers
+#
+# CONFIG_ATA is not set
+
+#
+# Multi-device support (RAID and LVM)
+#
+# CONFIG_MD is not set
+
+#
+# Fusion MPT device support
+#
+# CONFIG_FUSION is not set
+
+#
+# IEEE 1394 (FireWire) support
+#
+
+#
+# I2O device support
+#
+
+#
+# Macintosh device drivers
+#
+# CONFIG_WINDFARM is not set
+
+#
+# Network device support
+#
+CONFIG_NETDEVICES=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_EQUALIZER is not set
+# CONFIG_TUN is not set
+
+#
+# PHY device support
+#
+
+#
+# Ethernet (10 or 100Mbit)
+#
+# CONFIG_NET_ETHERNET is not set
+
+#
+# Ethernet (1000 Mbit)
+#
+
+#
+# Ethernet (10000 Mbit)
+#
+
+#
+# Token Ring devices
+#
+
+#
+# Wireless LAN (non-hamradio)
+#
+# CONFIG_NET_RADIO is not set
+
+#
+# Wan interfaces
+#
+# CONFIG_WAN is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+# CONFIG_SHAPER is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+
+#
+# ISDN subsystem
+#
+# CONFIG_ISDN is not set
+
+#
+# Telephony Support
+#
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+
+#
+# Userland interfaces
+#
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_TSDEV is not set
+CONFIG_INPUT_EVDEV=y
+# 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_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=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+# CONFIG_VT_HW_CONSOLE_BINDING is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_UNIX98_PTYS=y
+# CONFIG_LEGACY_PTYS is not set
+
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
+#
+# Watchdog Cards
+#
+# CONFIG_WATCHDOG is not set
+# CONFIG_HW_RANDOM is not set
+CONFIG_GEN_RTC=y
+# CONFIG_GEN_RTC_X is not set
+# CONFIG_DTLK is not set
+# CONFIG_R3964 is not set
+
+#
+# Ftape, the floppy tape device driver
+#
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_HANGCHECK_TIMER is not set
+
+#
+# TPM devices
+#
+# CONFIG_TCG_TPM is not set
+
+#
+# I2C support
+#
+# CONFIG_I2C is not set
+
+#
+# SPI support
+#
+# CONFIG_SPI is not set
+# CONFIG_SPI_MASTER is not set
+
+#
+# Dallas's 1-wire bus
+#
+# CONFIG_W1 is not set
+
+#
+# Hardware Monitoring support
+#
+# CONFIG_HWMON is not set
+# CONFIG_HWMON_VID is not set
+
+#
+# Multimedia devices
+#
+# CONFIG_VIDEO_DEV is not set
+
+#
+# Digital Video Broadcasting Devices
+#
+# CONFIG_DVB is not set
+
+#
+# Graphics support
+#
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB is not set
+
+#
+# Console display driver support
+#
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Sound
+#
+# CONFIG_SOUND is not set
+
+#
+# USB support
+#
+# CONFIG_USB_ARCH_HAS_HCD is not set
+# CONFIG_USB_ARCH_HAS_OHCI is not set
+# CONFIG_USB_ARCH_HAS_EHCI is not set
+
+#
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# USB Gadget Support
+#
+# CONFIG_USB_GADGET is not set
+
+#
+# MMC/SD Card support
+#
+# CONFIG_MMC is not set
+
+#
+# LED devices
+#
+# CONFIG_NEW_LEDS is not set
+
+#
+# LED drivers
+#
+
+#
+# LED Triggers
+#
+
+#
+# InfiniBand support
+#
+
+#
+# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
+#
+
+#
+# Real Time Clock
+#
+# CONFIG_RTC_CLASS is not set
+
+#
+# DMA Engine support
+#
+# CONFIG_DMA_ENGINE is not set
+
+#
+# DMA Clients
+#
+
+#
+# DMA Devices
+#
+
+#
+# File systems
+#
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4DEV_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
+# CONFIG_OCFS2_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_ROMFS_FS is not set
+CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_QUOTA is not set
+CONFIG_DNOTIFY=y
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+CONFIG_RAMFS=y
+# CONFIG_CONFIGFS_FS is not set
+
+#
+# Miscellaneous filesystems
+#
+# 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_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Network File Systems
+#
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+# CONFIG_NFS_V3_ACL is not set
+# CONFIG_NFS_V4 is not set
+# CONFIG_NFS_DIRECTIO is not set
+# CONFIG_NFSD is not set
+CONFIG_ROOT_NFS=y
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+CONFIG_NFS_COMMON=y
+CONFIG_SUNRPC=y
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_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
+# CONFIG_9P_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+
+#
+# Native Language Support
+#
+# CONFIG_NLS is not set
+
+#
+# Library routines
+#
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC32 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_PLIST=y
+
+#
+# Instrumentation Support
+#
+# CONFIG_PROFILING is not set
+# CONFIG_KPROBES is not set
+
+#
+# Kernel hacking
+#
+# CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_MUST_CHECK=y
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_KERNEL=y
+CONFIG_LOG_BUF_SHIFT=17
+CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+CONFIG_DEBUG_SPINLOCK=y
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_RWSEMS is not set
+CONFIG_DEBUG_SPINLOCK_SLEEP=y
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_KOBJECT is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
+CONFIG_DEBUG_LIST=y
+CONFIG_FORCED_INLINING=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_DEBUG_STACKOVERFLOW is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_DEBUGGER is not set
+CONFIG_IRQSTACKS=y
+# CONFIG_BOOTX_TEXT is not set
+CONFIG_PPC_EARLY_DEBUG=y
+# CONFIG_PPC_EARLY_DEBUG_LPAR is not set
+# CONFIG_PPC_EARLY_DEBUG_G5 is not set
+# CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL is not set
+# CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE is not set
+# CONFIG_PPC_EARLY_DEBUG_MAPLE is not set
+# CONFIG_PPC_EARLY_DEBUG_ISERIES is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+
+#
+# Cryptographic options
+#
+# CONFIG_CRYPTO is not set
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 7af23c43fd4b..4fe53d08ab81 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -17,11 +17,11 @@ obj-y				+= vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o cpu_setup_ppc970.o \
-				   firmware.o sysfs.o
+				   firmware.o sysfs.o nvram_64.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
-obj-$(CONFIG_PPC_OF)		+= of_device.o prom_parse.o
+obj-$(CONFIG_PPC_OF)		+= of_device.o of_platform.o prom_parse.o
 procfs-$(CONFIG_PPC64)		:= proc_ppc64.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)		:= rtas_pci.o
@@ -32,7 +32,6 @@ obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
-obj64-$(CONFIG_PPC_MULTIPLATFORM) += nvram_64.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_6xx)		+= idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
 obj-$(CONFIG_TAU)		+= tau_6xx.o
@@ -59,11 +58,11 @@ obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
+
 module-$(CONFIG_PPC64)		+= module_64.o
 obj-$(CONFIG_MODULES)		+= $(module-y)
 
-pci64-$(CONFIG_PPC64)		+= pci_64.o pci_dn.o pci_iommu.o \
-				   pci_direct_iommu.o iomap.o
+pci64-$(CONFIG_PPC64)		+= pci_64.o pci_dn.o
 pci32-$(CONFIG_PPC32)		:= pci_32.o
 obj-$(CONFIG_PCI)		+= $(pci64-y) $(pci32-y)
 kexec-$(CONFIG_PPC64)		:= machine_kexec_64.o
@@ -72,8 +71,12 @@ obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o $(kexec-y)
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
+ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
+obj-y				+= iomap.o
+endif
+
 ifeq ($(CONFIG_PPC_ISERIES),y)
-$(obj)/head_64.o: $(obj)/lparmap.s
+extra-y += lparmap.s
 AFLAGS_head_64.o += -I$(obj)
 endif
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d06f378597bb..e96521530d21 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -118,7 +118,8 @@ int main(void)
 	DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
 	DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
 	DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
-	DEFINE(PACAPROCENABLED, offsetof(struct paca_struct, proc_enabled));
+	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
+	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
 	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
 	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S
index 652594891d58..bf118c385752 100644
--- a/arch/powerpc/kernel/cpu_setup_ppc970.S
+++ b/arch/powerpc/kernel/cpu_setup_ppc970.S
@@ -83,6 +83,22 @@ _GLOBAL(__setup_cpu_ppc970)
 	rldimi	r0,r11,52,8		/* set NAP and DPM */
 	li	r11,0
 	rldimi	r0,r11,32,31		/* clear EN_ATTN */
+	b	load_hids		/* Jump to shared code */
+
+
+_GLOBAL(__setup_cpu_ppc970MP)
+	/* Do nothing if not running in HV mode */
+	mfmsr	r0
+	rldicl.	r0,r0,4,63
+	beqlr
+
+	mfspr	r0,SPRN_HID0
+	li	r11,0x15		/* clear DOZE and SLEEP */
+	rldimi	r0,r11,52,6		/* set DEEPNAP, NAP and DPM */
+	li	r11,0
+	rldimi	r0,r11,32,31		/* clear EN_ATTN */
+
+load_hids:
 	mtspr	SPRN_HID0,r0
 	mfspr	r0,SPRN_HID0
 	mfspr	r0,SPRN_HID0
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index bfd499ee3753..9d1614c3ce67 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -42,6 +42,7 @@ extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec);
 #endif /* CONFIG_PPC32 */
 #ifdef CONFIG_PPC64
 extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_ppc970(void);
 #endif /* CONFIG_PPC64 */
 
@@ -222,9 +223,9 @@ static struct cpu_spec cpu_specs[] = {
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
-		.cpu_setup		= __setup_cpu_ppc970,
+		.cpu_setup		= __setup_cpu_ppc970MP,
 		.cpu_restore		= __restore_cpu_ppc970,
-		.oprofile_cpu_type	= "ppc64/970",
+		.oprofile_cpu_type	= "ppc64/970MP",
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.platform		= "ppc970",
 	},
@@ -276,10 +277,45 @@ static struct cpu_spec cpu_specs[] = {
 		.oprofile_mmcra_sipr	= MMCRA_SIPR,
 		.platform		= "power5+",
 	},
+	{	/* POWER6 in P5+ mode; 2.04-compliant processor */
+		.pvr_mask		= 0xffffffff,
+		.pvr_value		= 0x0f000001,
+		.cpu_name		= "POWER5+",
+		.cpu_features		= CPU_FTRS_POWER5,
+		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.oprofile_cpu_type	= "ppc64/power6",
+		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.oprofile_mmcra_sihv	= POWER6_MMCRA_SIHV,
+		.oprofile_mmcra_sipr	= POWER6_MMCRA_SIPR,
+		.oprofile_mmcra_clear	= POWER6_MMCRA_THRM |
+			POWER6_MMCRA_OTHER,
+		.platform		= "power5+",
+	},
 	{	/* Power6 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x003e0000,
-		.cpu_name		= "POWER6",
+		.cpu_name		= "POWER6 (raw)",
+		.cpu_features		= CPU_FTRS_POWER6,
+		.cpu_user_features	= COMMON_USER_POWER6 |
+			PPC_FEATURE_POWER6_EXT,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.oprofile_cpu_type	= "ppc64/power6",
+		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.oprofile_mmcra_sihv	= POWER6_MMCRA_SIHV,
+		.oprofile_mmcra_sipr	= POWER6_MMCRA_SIPR,
+		.oprofile_mmcra_clear	= POWER6_MMCRA_THRM |
+			POWER6_MMCRA_OTHER,
+		.platform		= "power6x",
+	},
+	{	/* 2.05-compliant processor, i.e. Power6 "architected" mode */
+		.pvr_mask		= 0xffffffff,
+		.pvr_value		= 0x0f000002,
+		.cpu_name		= "POWER6 (architected)",
 		.cpu_features		= CPU_FTRS_POWER6,
 		.cpu_user_features	= COMMON_USER_POWER6,
 		.icache_bsize		= 128,
@@ -303,6 +339,9 @@ static struct cpu_spec cpu_specs[] = {
 			PPC_FEATURE_SMT,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
+		.num_pmcs		= 4,
+		.oprofile_cpu_type	= "ppc64/cell-be",
+		.oprofile_type		= PPC_OPROFILE_CELL,
 		.platform		= "ppc-cell-be",
 	},
 	{	/* PA Semi PA6T */
@@ -801,6 +840,17 @@ static struct cpu_spec cpu_specs[] = {
 		.cpu_setup		= __setup_cpu_603,
 		.platform		= "ppc603",
 	},
+	{	/* e300c3 on 83xx  */
+		.pvr_mask		= 0x7fff0000,
+		.pvr_value		= 0x00850000,
+		.cpu_name		= "e300c3",
+		.cpu_features		= CPU_FTRS_E300,
+		.cpu_user_features	= COMMON_USER,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.cpu_setup		= __setup_cpu_603,
+		.platform		= "ppc603",
+	},
 	{	/* default match, we assume split I/D cache & TB (non-601)... */
 		.pvr_mask		= 0x00000000,
 		.pvr_value		= 0x00000000,
@@ -1169,19 +1219,15 @@ static struct cpu_spec cpu_specs[] = {
 #endif /* CONFIG_PPC32 */
 };
 
-struct cpu_spec *identify_cpu(unsigned long offset)
+struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr)
 {
 	struct cpu_spec *s = cpu_specs;
 	struct cpu_spec **cur = &cur_cpu_spec;
-	unsigned int pvr = mfspr(SPRN_PVR);
 	int i;
 
 	s = PTRRELOC(s);
 	cur = PTRRELOC(cur);
 
-	if (*cur != NULL)
-		return PTRRELOC(*cur);
-
 	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++)
 		if ((pvr & s->pvr_mask) == s->pvr_value) {
 			*cur = cpu_specs + i;
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 1af41f7616dc..89b03c8da9d2 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -111,7 +111,7 @@ void crash_ipi_callback(struct pt_regs *regs)
 	if (!cpu_online(cpu))
 		return;
 
-	local_irq_disable();
+	hard_irq_disable();
 	if (!cpu_isset(cpu, cpus_in_crash))
 		crash_save_this_cpu(regs, cpu);
 	cpu_set(cpu, cpus_in_crash);
@@ -289,7 +289,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	 * an SMP system.
 	 * The kernel is broken so disable interrupts.
 	 */
-	local_irq_disable();
+	hard_irq_disable();
 
 	for_each_irq(irq) {
 		struct irq_desc *desc = irq_desc + irq;
diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c
index 6c168f6ea142..7b0e754383cf 100644
--- a/arch/powerpc/kernel/dma_64.c
+++ b/arch/powerpc/kernel/dma_64.c
@@ -1,151 +1,194 @@
 /*
- * Copyright (C) 2004 IBM Corporation
+ * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
  *
- * Implements the generic device dma API for ppc64. Handles
- * the pci and vio busses
+ * Provide default implementations of the DMA mapping callbacks for
+ * directly mapped busses and busses using the iommu infrastructure
  */
 
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
-/* Include the busses we support */
-#include <linux/pci.h>
-#include <asm/vio.h>
-#include <asm/ibmebus.h>
-#include <asm/scatterlist.h>
 #include <asm/bug.h>
+#include <asm/iommu.h>
+#include <asm/abs_addr.h>
 
-static struct dma_mapping_ops *get_dma_ops(struct device *dev)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return &pci_dma_ops;
-#endif
-#ifdef CONFIG_IBMVIO
-	if (dev->bus == &vio_bus_type)
-		return &vio_dma_ops;
-#endif
-#ifdef CONFIG_IBMEBUS
-	if (dev->bus == &ibmebus_bus_type)
-		return &ibmebus_dma_ops;
-#endif
-	return NULL;
-}
+/*
+ * Generic iommu implementation
+ */
 
-int dma_supported(struct device *dev, u64 mask)
+static inline unsigned long device_to_mask(struct device *dev)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	if (dev->dma_mask && *dev->dma_mask)
+		return *dev->dma_mask;
+	/* Assume devices without mask can take 32 bit addresses */
+	return 0xfffffffful;
+}
 
-	BUG_ON(!dma_ops);
 
-	return dma_ops->dma_supported(dev, mask);
+/* Allocates a contiguous real buffer and creates mappings over it.
+ * Returns the virtual address of the buffer and sets dma_handle
+ * to the dma address (mapping) of the first page.
+ */
+static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
+				      dma_addr_t *dma_handle, gfp_t flag)
+{
+	return iommu_alloc_coherent(dev->archdata.dma_data, size, dma_handle,
+				    device_to_mask(dev), flag,
+				    dev->archdata.numa_node);
 }
-EXPORT_SYMBOL(dma_supported);
 
-int dma_set_mask(struct device *dev, u64 dma_mask)
+static void dma_iommu_free_coherent(struct device *dev, size_t size,
+				    void *vaddr, dma_addr_t dma_handle)
 {
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
-#endif
-#ifdef CONFIG_IBMVIO
-	if (dev->bus == &vio_bus_type)
-		return -EIO;
-#endif /* CONFIG_IBMVIO */
-#ifdef CONFIG_IBMEBUS
-	if (dev->bus == &ibmebus_bus_type)
-		return -EIO;
-#endif
-	BUG();
-	return 0;
+	iommu_free_coherent(dev->archdata.dma_data, size, vaddr, dma_handle);
 }
-EXPORT_SYMBOL(dma_set_mask);
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag)
+/* Creates TCEs for a user provided buffer.  The user buffer must be
+ * contiguous real kernel storage (not vmalloc).  The address of the buffer
+ * passed here is the kernel (virtual) address of the buffer.  The buffer
+ * need not be page aligned, the dma_addr_t returned will point to the same
+ * byte within the page as vaddr.
+ */
+static dma_addr_t dma_iommu_map_single(struct device *dev, void *vaddr,
+				       size_t size,
+				       enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+	return iommu_map_single(dev->archdata.dma_data, vaddr, size,
+			        device_to_mask(dev), direction);
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_handle)
+
+static void dma_iommu_unmap_single(struct device *dev, dma_addr_t dma_handle,
+				   size_t size,
+				   enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	iommu_unmap_single(dev->archdata.dma_data, dma_handle, size, direction);
+}
 
-	BUG_ON(!dma_ops);
 
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
+			    int nelems, enum dma_data_direction direction)
+{
+	return iommu_map_sg(dev->archdata.dma_data, sglist, nelems,
+			    device_to_mask(dev), direction);
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
-dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-		enum dma_data_direction direction)
+static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		int nelems, enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	return dma_ops->map_single(dev, cpu_addr, size, direction);
+	iommu_unmap_sg(dev->archdata.dma_data, sglist, nelems, direction);
 }
-EXPORT_SYMBOL(dma_map_single);
 
-void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction direction)
+/* We support DMA to/from any memory page via the iommu */
+static int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
-
-	dma_ops->unmap_single(dev, dma_addr, size, direction);
+	struct iommu_table *tbl = dev->archdata.dma_data;
+
+	if (!tbl || tbl->it_offset > mask) {
+		printk(KERN_INFO
+		       "Warning: IOMMU offset too big for device mask\n");
+		if (tbl)
+			printk(KERN_INFO
+			       "mask: 0x%08lx, table offset: 0x%08lx\n",
+				mask, tbl->it_offset);
+		else
+			printk(KERN_INFO "mask: 0x%08lx, table unavailable\n",
+				mask);
+		return 0;
+	} else
+		return 1;
 }
-EXPORT_SYMBOL(dma_unmap_single);
 
-dma_addr_t dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+struct dma_mapping_ops dma_iommu_ops = {
+	.alloc_coherent	= dma_iommu_alloc_coherent,
+	.free_coherent	= dma_iommu_free_coherent,
+	.map_single	= dma_iommu_map_single,
+	.unmap_single	= dma_iommu_unmap_single,
+	.map_sg		= dma_iommu_map_sg,
+	.unmap_sg	= dma_iommu_unmap_sg,
+	.dma_supported	= dma_iommu_dma_supported,
+};
+EXPORT_SYMBOL(dma_iommu_ops);
 
-	BUG_ON(!dma_ops);
+/*
+ * Generic direct DMA implementation
+ *
+ * This implementation supports a global offset that can be applied if
+ * the address at which memory is visible to devices is not 0.
+ */
+unsigned long dma_direct_offset;
 
-	return dma_ops->map_single(dev, page_address(page) + offset, size,
-			direction);
+static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
+{
+	struct page *page;
+	void *ret;
+	int node = dev->archdata.numa_node;
+
+	/* TODO: Maybe use the numa node here too ? */
+	page = alloc_pages_node(node, flag, get_order(size));
+	if (page == NULL)
+		return NULL;
+	ret = page_address(page);
+	memset(ret, 0, size);
+	*dma_handle = virt_to_abs(ret) | dma_direct_offset;
+
+	return ret;
 }
-EXPORT_SYMBOL(dma_map_page);
 
-void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-		enum dma_data_direction direction)
+static void dma_direct_free_coherent(struct device *dev, size_t size,
+				     void *vaddr, dma_addr_t dma_handle)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	free_pages((unsigned long)vaddr, get_order(size));
+}
 
-	BUG_ON(!dma_ops);
+static dma_addr_t dma_direct_map_single(struct device *dev, void *ptr,
+					size_t size,
+					enum dma_data_direction direction)
+{
+	return virt_to_abs(ptr) | dma_direct_offset;
+}
 
-	dma_ops->unmap_single(dev, dma_address, size, direction);
+static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr,
+				    size_t size,
+				    enum dma_data_direction direction)
+{
 }
-EXPORT_SYMBOL(dma_unmap_page);
 
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction direction)
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+	int i;
 
-	BUG_ON(!dma_ops);
+	for (i = 0; i < nents; i++, sg++) {
+		sg->dma_address = (page_to_phys(sg->page) + sg->offset) |
+			dma_direct_offset;
+		sg->dma_length = sg->length;
+	}
 
-	return dma_ops->map_sg(dev, sg, nents, direction);
+	return nents;
 }
-EXPORT_SYMBOL(dma_map_sg);
 
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-		enum dma_data_direction direction)
+static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction direction)
 {
-	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
-
-	BUG_ON(!dma_ops);
+}
 
-	dma_ops->unmap_sg(dev, sg, nhwentries, direction);
+static int dma_direct_dma_supported(struct device *dev, u64 mask)
+{
+	/* Could be improved to check for memory though it better be
+	 * done via some global so platforms can set the limit in case
+	 * they have limited DMA windows
+	 */
+	return mask >= DMA_32BIT_MASK;
 }
-EXPORT_SYMBOL(dma_unmap_sg);
+
+struct dma_mapping_ops dma_direct_ops = {
+	.alloc_coherent	= dma_direct_alloc_coherent,
+	.free_coherent	= dma_direct_free_coherent,
+	.map_single	= dma_direct_map_single,
+	.unmap_single	= dma_direct_unmap_single,
+	.map_sg		= dma_direct_map_sg,
+	.unmap_sg	= dma_direct_unmap_sg,
+	.dma_supported	= dma_direct_dma_supported,
+};
+EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 748e74fcf541..1a3d4de197d2 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -87,15 +87,19 @@ system_call_common:
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r9)		/* "regshere" marker */
+	li	r10,1
+	stb	r10,PACASOFTIRQEN(r13)
+	stb	r10,PACAHARDIRQEN(r13)
+	std	r10,SOFTE(r1)
 #ifdef CONFIG_PPC_ISERIES
 BEGIN_FW_FTR_SECTION
 	/* Hack for handling interrupts when soft-enabling on iSeries */
 	cmpdi	cr1,r0,0x5555		/* syscall 0x5555 */
 	andi.	r10,r12,MSR_PR		/* from kernel */
 	crand	4*cr0+eq,4*cr1+eq,4*cr0+eq
-	beq	hardware_interrupt_entry
-	lbz	r10,PACAPROCENABLED(r13)
-	std	r10,SOFTE(r1)
+	bne	2f
+	b	hardware_interrupt_entry
+2:
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif
 	mfmsr	r11
@@ -460,9 +464,9 @@ _GLOBAL(ret_from_except_lite)
 #endif
 
 restore:
+	ld	r5,SOFTE(r1)
 #ifdef CONFIG_PPC_ISERIES
 BEGIN_FW_FTR_SECTION
-	ld	r5,SOFTE(r1)
 	cmpdi	0,r5,0
 	beq	4f
 	/* Check for pending interrupts (iSeries) */
@@ -472,21 +476,25 @@ BEGIN_FW_FTR_SECTION
 	beq+	4f			/* skip do_IRQ if no interrupts */
 
 	li	r3,0
-	stb	r3,PACAPROCENABLED(r13)	/* ensure we are soft-disabled */
+	stb	r3,PACASOFTIRQEN(r13)	/* ensure we are soft-disabled */
 	ori	r10,r10,MSR_EE
 	mtmsrd	r10			/* hard-enable again */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_IRQ
 	b	.ret_from_except_lite		/* loop back and handle more */
-
-4:	stb	r5,PACAPROCENABLED(r13)
+4:
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif
+	stb	r5,PACASOFTIRQEN(r13)
 
 	ld	r3,_MSR(r1)
 	andi.	r0,r3,MSR_RI
 	beq-	unrecov_restore
 
+	/* extract EE bit and use it to restore paca->hard_enabled */
+	rldicl	r4,r3,49,63		/* r0 = (r3 >> 15) & 1 */
+	stb	r4,PACAHARDIRQEN(r13)
+
 	andi.	r0,r3,MSR_PR
 
 	/*
@@ -538,25 +546,15 @@ do_work:
 	/* Check that preempt_count() == 0 and interrupts are enabled */
 	lwz	r8,TI_PREEMPT(r9)
 	cmpwi	cr1,r8,0
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
 	ld	r0,SOFTE(r1)
 	cmpdi	r0,0
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
-BEGIN_FW_FTR_SECTION
-	andi.	r0,r3,MSR_EE
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 	crandc	eq,cr1*4+eq,eq
 	bne	restore
 	/* here we are preempting the current task */
 1:
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
 	li	r0,1
-	stb	r0,PACAPROCENABLED(r13)
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
+	stb	r0,PACASOFTIRQEN(r13)
+	stb	r0,PACAHARDIRQEN(r13)
 	ori	r10,r10,MSR_EE
 	mtmsrd	r10,1		/* reenable interrupts */
 	bl	.preempt_schedule
@@ -639,8 +637,7 @@ _GLOBAL(enter_rtas)
 	/* There is no way it is acceptable to get here with interrupts enabled,
 	 * check it with the asm equivalent of WARN_ON
 	 */
-	mfmsr	r6
-	andi.	r0,r6,MSR_EE
+	lbz	r0,PACASOFTIRQEN(r13)
 1:	tdnei	r0,0
 .section __bug_table,"a"
 	.llong	1b,__LINE__ + 0x1000000, 1f, 2f
@@ -649,7 +646,13 @@ _GLOBAL(enter_rtas)
 1:	.asciz	__FILE__
 2:	.asciz "enter_rtas"
 .previous
-	
+
+	/* Hard-disable interrupts */
+	mfmsr	r6
+	rldicl	r7,r6,48,1
+	rotldi	r7,r7,16
+	mtmsrd	r7,1
+
 	/* Unfortunately, the stack pointer and the MSR are also clobbered,
 	 * so they are saved in the PACA which allows us to restore
 	 * our original state after RTAS returns.
@@ -735,8 +738,6 @@ _STATIC(rtas_restore_regs)
 
 #endif /* CONFIG_PPC_RTAS */
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
-
 _GLOBAL(enter_prom)
 	mflr	r0
 	std	r0,16(r1)
@@ -821,5 +822,3 @@ _GLOBAL(enter_prom)
 	ld	r0,16(r1)
 	mtlr    r0
         blr
-	
-#endif	/* CONFIG_PPC_MULTIPLATFORM */
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index e720729f3e55..71b1fe58e9e4 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -35,9 +35,7 @@
 #include <asm/thread_info.h>
 #include <asm/firmware.h>
 
-#ifdef CONFIG_PPC_ISERIES
 #define DO_SOFT_DISABLE
-#endif
 
 /*
  * We layout physical memory as follows:
@@ -74,13 +72,11 @@
 	.text
 	.globl  _stext
 _stext:
-#ifdef CONFIG_PPC_MULTIPLATFORM
 _GLOBAL(__start)
 	/* NOP this out unconditionally */
 BEGIN_FTR_SECTION
 	b	.__start_initialization_multiplatform
 END_FTR_SECTION(0, 1)
-#endif /* CONFIG_PPC_MULTIPLATFORM */
 
 	/* Catch branch to 0 in real mode */
 	trap
@@ -308,7 +304,9 @@ exception_marker:
 	std	r9,_LINK(r1);						   \
 	mfctr	r10;			/* save CTR in stackframe	*/ \
 	std	r10,_CTR(r1);						   \
+	lbz	r10,PACASOFTIRQEN(r13);				   \
 	mfspr	r11,SPRN_XER;		/* save XER in stackframe	*/ \
+	std	r10,SOFTE(r1);						   \
 	std	r11,_XER(r1);						   \
 	li	r9,(n)+1;						   \
 	std	r9,_TRAP(r1);		/* set trap number		*/ \
@@ -343,6 +341,34 @@ label##_pSeries:					\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
 
 
+#define MASKABLE_EXCEPTION_PSERIES(n, label)				\
+	. = n;								\
+	.globl label##_pSeries;						\
+label##_pSeries:							\
+	HMT_MEDIUM;							\
+	mtspr	SPRN_SPRG1,r13;		/* save r13 */			\
+	mfspr	r13,SPRN_SPRG3;		/* get paca address into r13 */	\
+	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
+	std	r10,PACA_EXGEN+EX_R10(r13);				\
+	lbz	r10,PACASOFTIRQEN(r13);					\
+	mfcr	r9;							\
+	cmpwi	r10,0;							\
+	beq	masked_interrupt;					\
+	mfspr	r10,SPRN_SPRG1;						\
+	std	r10,PACA_EXGEN+EX_R13(r13);				\
+	std	r11,PACA_EXGEN+EX_R11(r13);				\
+	std	r12,PACA_EXGEN+EX_R12(r13);				\
+	clrrdi	r12,r13,32;		/* get high part of &label */	\
+	mfmsr	r10;							\
+	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
+	LOAD_HANDLER(r12,label##_common)				\
+	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI;				\
+	mtspr	SPRN_SRR0,r12;						\
+	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
+	mtspr	SPRN_SRR1,r10;						\
+	rfid;								\
+	b	.	/* prevent speculative execution */
+
 #define STD_EXCEPTION_ISERIES(n, label, area)		\
 	.globl label##_iSeries;				\
 label##_iSeries:					\
@@ -358,40 +384,32 @@ label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG1,r13;		/* save r13 */			\
 	EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN);				\
-	lbz	r10,PACAPROCENABLED(r13);				\
+	lbz	r10,PACASOFTIRQEN(r13);					\
 	cmpwi	0,r10,0;						\
 	beq-	label##_iSeries_masked;					\
 	EXCEPTION_PROLOG_ISERIES_2;					\
 	b	label##_common;						\
 
-#ifdef DO_SOFT_DISABLE
+#ifdef CONFIG_PPC_ISERIES
 #define DISABLE_INTS				\
-BEGIN_FW_FTR_SECTION;				\
-	lbz	r10,PACAPROCENABLED(r13);	\
 	li	r11,0;				\
-	std	r10,SOFTE(r1);			\
+	stb	r11,PACASOFTIRQEN(r13);		\
+BEGIN_FW_FTR_SECTION;				\
+	stb	r11,PACAHARDIRQEN(r13);		\
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES);	\
+BEGIN_FW_FTR_SECTION;				\
 	mfmsr	r10;				\
-	stb	r11,PACAPROCENABLED(r13);	\
 	ori	r10,r10,MSR_EE;			\
 	mtmsrd	r10,1;				\
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 
-#define ENABLE_INTS				\
-BEGIN_FW_FTR_SECTION;				\
-	lbz	r10,PACAPROCENABLED(r13);	\
-	mfmsr	r11;				\
-	std	r10,SOFTE(r1);			\
-	ori	r11,r11,MSR_EE;			\
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES);	\
-BEGIN_FW_FTR_SECTION;				\
-	ld	r12,_MSR(r1);			\
-	mfmsr	r11;				\
-	rlwimi	r11,r12,0,MSR_EE;		\
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES);	\
-	mtmsrd	r11,1
+#else
+#define DISABLE_INTS				\
+	li	r11,0;				\
+	stb	r11,PACASOFTIRQEN(r13);		\
+	stb	r11,PACAHARDIRQEN(r13)
 
-#else	/* hard enable/disable interrupts */
-#define DISABLE_INTS
+#endif /* CONFIG_PPC_ISERIES */
 
 #define ENABLE_INTS				\
 	ld	r12,_MSR(r1);			\
@@ -399,8 +417,6 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES);	\
 	rlwimi	r11,r12,0,MSR_EE;		\
 	mtmsrd	r11,1
 
-#endif
-
 #define STD_EXCEPTION_COMMON(trap, label, hdlr)		\
 	.align	7;					\
 	.globl label##_common;				\
@@ -541,11 +557,11 @@ instruction_access_slb_pSeries:
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
 	b	.slb_miss_realmode	/* Rel. branch works in real mode */
 
-	STD_EXCEPTION_PSERIES(0x500, hardware_interrupt)
+	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt)
 	STD_EXCEPTION_PSERIES(0x600, alignment)
 	STD_EXCEPTION_PSERIES(0x700, program_check)
 	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
-	STD_EXCEPTION_PSERIES(0x900, decrementer)
+	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer)
 	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
 	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
 
@@ -597,7 +613,24 @@ system_call_pSeries:
 /*** pSeries interrupt support ***/
 
 	/* moved from 0xf00 */
-	STD_EXCEPTION_PSERIES(., performance_monitor)
+	MASKABLE_EXCEPTION_PSERIES(., performance_monitor)
+
+/*
+ * An interrupt came in while soft-disabled; clear EE in SRR1,
+ * clear paca->hard_enabled and return.
+ */
+masked_interrupt:
+	stb	r10,PACAHARDIRQEN(r13)
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	mfspr	r10,SPRN_SRR1
+	rldicl	r10,r10,48,1		/* clear MSR_EE */
+	rotldi	r10,r10,16
+	mtspr	SPRN_SRR1,r10
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	mfspr	r13,SPRN_SPRG1
+	rfid
+	b	.
 
 	.align	7
 do_stab_bolted_pSeries:
@@ -792,7 +825,7 @@ system_reset_iSeries:
 
 	cmpwi	0,r23,0
 	beq	iSeries_secondary_smp_loop	/* Loop until told to go */
-	bne	.__secondary_start		/* Loop until told to go */
+	bne	__secondary_start		/* Loop until told to go */
 iSeries_secondary_smp_loop:
 	/* Let the Hypervisor know we are alive */
 	/* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */
@@ -813,7 +846,6 @@ iSeries_secondary_smp_loop:
 	b	1b			/* If SMP not configured, secondaries
 					 * loop forever */
 
-	.globl decrementer_iSeries_masked
 decrementer_iSeries_masked:
 	/* We may not have a valid TOC pointer in here. */
 	li	r11,1
@@ -824,7 +856,6 @@ decrementer_iSeries_masked:
 	mtspr	SPRN_DEC,r12
 	/* fall through */
 
-	.globl hardware_interrupt_iSeries_masked
 hardware_interrupt_iSeries_masked:
 	mtcrf	0x80,r9		/* Restore regs */
 	ld	r12,PACALPPACAPTR(r13)
@@ -926,10 +957,18 @@ bad_stack:
  * any task or sent any task a signal, you should use
  * ret_from_except or ret_from_except_lite instead of this.
  */
+fast_exc_return_irq:			/* restores irq state too */
+	ld	r3,SOFTE(r1)
+	ld	r12,_MSR(r1)
+	stb	r3,PACASOFTIRQEN(r13)	/* restore paca->soft_enabled */
+	rldicl	r4,r12,49,63		/* get MSR_EE to LSB */
+	stb	r4,PACAHARDIRQEN(r13)	/* restore paca->hard_enabled */
+	b	1f
+
 	.globl	fast_exception_return
 fast_exception_return:
 	ld	r12,_MSR(r1)
-	ld	r11,_NIP(r1)
+1:	ld	r11,_NIP(r1)
 	andi.	r3,r12,MSR_RI		/* check if RI is set */
 	beq-	unrecov_fer
 
@@ -952,7 +991,8 @@ fast_exception_return:
 	REST_8GPRS(2, r1)
 
 	mfmsr	r10
-	clrrdi	r10,r10,2		/* clear RI (LE is 0 already) */
+	rldicl	r10,r10,48,1		/* clear EE */
+	rldicr	r10,r10,16,61		/* clear RI (LE is 0 already) */
 	mtmsrd	r10,1
 
 	mtspr	SPRN_SRR1,r12
@@ -1326,6 +1366,16 @@ BEGIN_FW_FTR_SECTION
 	 * interrupts if necessary.
 	 */
 	beq	13f
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
+#endif
+BEGIN_FW_FTR_SECTION
+	/*
+	 * Here we have interrupts hard-disabled, so it is sufficient
+	 * to restore paca->{soft,hard}_enable and get out.
+	 */
+	beq	fast_exc_return_irq	/* Return from exception on success */
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
+
 	/* For a hash failure, we don't bother re-enabling interrupts */
 	ble-	12f
 
@@ -1337,14 +1387,6 @@ BEGIN_FW_FTR_SECTION
 	ld	r3,SOFTE(r1)
 	bl	.local_irq_restore
 	b	11f
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
-BEGIN_FW_FTR_SECTION
-	beq	fast_exception_return   /* Return from exception on success */
-	ble-	12f			/* Failure return from hash_page */
-
-	/* fall through */
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
@@ -1362,6 +1404,8 @@ handle_page_fault:
 	bl	.bad_page_fault
 	b	.ret_from_except
 
+13:	b	.ret_from_except_lite
+
 /* We have a page fault that hash_page could handle but HV refused
  * the PTE insertion
  */
@@ -1371,8 +1415,6 @@ handle_page_fault:
 	bl	.low_hash_fault
 	b	.ret_from_except
 
-13:	b	.ret_from_except_lite
-
 	/* here we have a segment miss */
 do_ste_alloc:
 	bl	.ste_allocate		/* try to insert stab entry */
@@ -1560,7 +1602,7 @@ _GLOBAL(generic_secondary_smp_init)
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,STACK_FRAME_OVERHEAD
 
-	b	.__secondary_start
+	b	__secondary_start
 #endif
 
 #ifdef CONFIG_PPC_ISERIES
@@ -1595,7 +1637,6 @@ _STATIC(__start_initialization_iSeries)
 	b	.start_here_common
 #endif /* CONFIG_PPC_ISERIES */
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 
 _STATIC(__mmu_off)
 	mfmsr	r3
@@ -1621,13 +1662,11 @@ _STATIC(__mmu_off)
  *
  */
 _GLOBAL(__start_initialization_multiplatform)
-#ifdef CONFIG_PPC_MULTIPLATFORM
 	/*
 	 * Are we booted from a PROM Of-type client-interface ?
 	 */
 	cmpldi	cr0,r5,0
 	bne	.__boot_from_prom		/* yes -> prom */
-#endif
 
 	/* Save parameters */
 	mr	r31,r3
@@ -1656,7 +1695,6 @@ _GLOBAL(__start_initialization_multiplatform)
 	bl	.__mmu_off
 	b	.__after_prom_start
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 _STATIC(__boot_from_prom)
 	/* Save parameters */
 	mr	r31,r3
@@ -1696,7 +1734,6 @@ _STATIC(__boot_from_prom)
 	bl	.prom_init
 	/* We never return */
 	trap
-#endif
 
 /*
  * At this point, r3 contains the physical address we are running at,
@@ -1752,8 +1789,6 @@ _STATIC(__after_prom_start)
 	bl	.copy_and_flush		/* copy the rest */
 	b	.start_here_multiplatform
 
-#endif /* CONFIG_PPC_MULTIPLATFORM */
-
 /*
  * Copy routine used to copy the kernel to start at physical address 0
  * and flush and invalidate the caches as needed.
@@ -1836,7 +1871,7 @@ _GLOBAL(pmac_secondary_start)
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,STACK_FRAME_OVERHEAD
 
-	b	.__secondary_start
+	b	__secondary_start
 
 #endif /* CONFIG_PPC_PMAC */
 
@@ -1853,7 +1888,7 @@ _GLOBAL(pmac_secondary_start)
  *   r13   = paca virtual address
  *   SPRG3 = paca virtual address
  */
-_GLOBAL(__secondary_start)
+__secondary_start:
 	/* Set thread priority to MEDIUM */
 	HMT_MEDIUM
 
@@ -1877,11 +1912,16 @@ _GLOBAL(__secondary_start)
 	/* enable MMU and jump to start_secondary */
 	LOAD_REG_ADDR(r3, .start_secondary_prolog)
 	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
-#ifdef DO_SOFT_DISABLE
+#ifdef CONFIG_PPC_ISERIES
 BEGIN_FW_FTR_SECTION
 	ori	r4,r4,MSR_EE
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif
+BEGIN_FW_FTR_SECTION
+	stb	r7,PACASOFTIRQEN(r13)
+	stb	r7,PACAHARDIRQEN(r13)
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
+
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
 	rfid
@@ -1913,7 +1953,6 @@ _GLOBAL(enable_64b_mode)
 	isync
 	blr
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 /*
  * This is where the main kernel code starts.
  */
@@ -1977,7 +2016,6 @@ _STATIC(start_here_multiplatform)
 	mtspr	SPRN_SRR1,r4
 	rfid
 	b	.	/* prevent speculative execution */
-#endif /* CONFIG_PPC_MULTIPLATFORM */
 	
 	/* This is where all platforms converge execution */
 _STATIC(start_here_common)
@@ -2005,15 +2043,18 @@ _STATIC(start_here_common)
 
 	/* Load up the kernel context */
 5:
-#ifdef DO_SOFT_DISABLE
-BEGIN_FW_FTR_SECTION
 	li	r5,0
-	stb	r5,PACAPROCENABLED(r13)	/* Soft Disabled */
+	stb	r5,PACASOFTIRQEN(r13)	/* Soft Disabled */
+#ifdef CONFIG_PPC_ISERIES
+BEGIN_FW_FTR_SECTION
 	mfmsr	r5
 	ori	r5,r5,MSR_EE		/* Hard Enabled */
 	mtmsrd	r5
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif
+BEGIN_FW_FTR_SECTION
+	stb	r5,PACAHARDIRQEN(r13)
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
 	bl .start_kernel
 
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 39db7a3affe1..82bd2f10770f 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -112,7 +112,7 @@ static int ibmebus_dma_supported(struct device *dev, u64 mask)
 	return 1;
 }
 
-struct dma_mapping_ops ibmebus_dma_ops = {
+static struct dma_mapping_ops ibmebus_dma_ops = {
 	.alloc_coherent = ibmebus_alloc_coherent,
 	.free_coherent  = ibmebus_free_coherent,
 	.map_single     = ibmebus_map_single,
@@ -176,6 +176,10 @@ static struct ibmebus_dev* __devinit ibmebus_register_device_common(
 	dev->ofdev.dev.bus     = &ibmebus_bus_type;
 	dev->ofdev.dev.release = ibmebus_dev_release;
 
+	dev->ofdev.dev.archdata.of_node = dev->ofdev.node;
+	dev->ofdev.dev.archdata.dma_ops = &ibmebus_dma_ops;
+	dev->ofdev.dev.archdata.numa_node = of_node_to_nid(dev->ofdev.node);
+
 	/* An ibmebusdev is based on a of_device. We have to change the
 	 * bus type to use our own DMA mapping operations. 
 	 */       
@@ -210,11 +214,10 @@ static struct ibmebus_dev* __devinit ibmebus_register_device_node(
 		return NULL;
 	}
 
-	dev = kmalloc(sizeof(struct ibmebus_dev), GFP_KERNEL);
+	dev = kzalloc(sizeof(struct ibmebus_dev), GFP_KERNEL);
 	if (!dev) {
 		return NULL;
 	}
-	memset(dev, 0, sizeof(struct ibmebus_dev));
 
 	dev->ofdev.node = of_node_get(dn);
        
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 4180c3998b39..8994af327b47 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -39,6 +39,13 @@
 #define cpu_should_die()	0
 #endif
 
+static int __init powersave_off(char *arg)
+{
+	ppc_md.power_save = NULL;
+	return 0;
+}
+__setup("powersave=off", powersave_off);
+
 /*
  * The body of the idle task.
  */
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index 30de81da7b40..ba3195478600 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -30,6 +30,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
 	beqlr
 
 	/* Go to NAP now */
+	mfmsr	r7
+	rldicl	r0,r7,48,1
+	rotldi	r0,r0,16
+	mtmsrd	r0,1			/* hard-disable interrupts */
+	li	r0,1
+	stb	r0,PACASOFTIRQEN(r13)	/* we'll hard-enable shortly */
+	stb	r0,PACAHARDIRQEN(r13)
 BEGIN_FTR_SECTION
 	DSSALL
 	sync
@@ -38,7 +45,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	ld	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
 	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
 	std	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
-	mfmsr	r7
 	ori	r7,r7,MSR_EE
 	oris	r7,r7,MSR_POW@h
 1:	sync
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index e98180686b35..34ae11494ddc 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -25,13 +25,11 @@
 #include <asm/firmware.h>
 #include <asm/bug.h>
 
-void _insb(volatile u8 __iomem *port, void *buf, long count)
+void _insb(const volatile u8 __iomem *port, void *buf, long count)
 {
 	u8 *tbuf = buf;
 	u8 tmp;
 
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
 	if (unlikely(count <= 0))
 		return;
 	asm volatile("sync");
@@ -48,8 +46,6 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count)
 {
 	const u8 *tbuf = buf;
 
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
 	if (unlikely(count <= 0))
 		return;
 	asm volatile("sync");
@@ -60,13 +56,11 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count)
 }
 EXPORT_SYMBOL(_outsb);
 
-void _insw_ns(volatile u16 __iomem *port, void *buf, long count)
+void _insw_ns(const volatile u16 __iomem *port, void *buf, long count)
 {
 	u16 *tbuf = buf;
 	u16 tmp;
 
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
 	if (unlikely(count <= 0))
 		return;
 	asm volatile("sync");
@@ -83,8 +77,6 @@ void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count)
 {
 	const u16 *tbuf = buf;
 
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
 	if (unlikely(count <= 0))
 		return;
 	asm volatile("sync");
@@ -95,13 +87,11 @@ void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count)
 }
 EXPORT_SYMBOL(_outsw_ns);
 
-void _insl_ns(volatile u32 __iomem *port, void *buf, long count)
+void _insl_ns(const volatile u32 __iomem *port, void *buf, long count)
 {
 	u32 *tbuf = buf;
 	u32 tmp;
 
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
 	if (unlikely(count <= 0))
 		return;
 	asm volatile("sync");
@@ -118,8 +108,6 @@ void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count)
 {
 	const u32 *tbuf = buf;
 
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
 	if (unlikely(count <= 0))
 		return;
 	asm volatile("sync");
@@ -129,3 +117,90 @@ void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count)
 	asm volatile("sync");
 }
 EXPORT_SYMBOL(_outsl_ns);
+
+#define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
+
+void _memset_io(volatile void __iomem *addr, int c, unsigned long n)
+{
+	void *p = (void __force *)addr;
+	u32 lc = c;
+	lc |= lc << 8;
+	lc |= lc << 16;
+
+	__asm__ __volatile__ ("sync" : : : "memory");
+	while(n && !IO_CHECK_ALIGN(p, 4)) {
+		*((volatile u8 *)p) = c;
+		p++;
+		n--;
+	}
+	while(n >= 4) {
+		*((volatile u32 *)p) = lc;
+		p += 4;
+		n -= 4;
+	}
+	while(n) {
+		*((volatile u8 *)p) = c;
+		p++;
+		n--;
+	}
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+EXPORT_SYMBOL(_memset_io);
+
+void _memcpy_fromio(void *dest, const volatile void __iomem *src,
+		    unsigned long n)
+{
+	void *vsrc = (void __force *) src;
+
+	__asm__ __volatile__ ("sync" : : : "memory");
+	while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) {
+		*((u8 *)dest) = *((volatile u8 *)vsrc);
+		__asm__ __volatile__ ("eieio" : : : "memory");
+		vsrc++;
+		dest++;
+		n--;
+	}
+	while(n > 4) {
+		*((u32 *)dest) = *((volatile u32 *)vsrc);
+		__asm__ __volatile__ ("eieio" : : : "memory");
+		vsrc += 4;
+		dest += 4;
+		n -= 4;
+	}
+	while(n) {
+		*((u8 *)dest) = *((volatile u8 *)vsrc);
+		__asm__ __volatile__ ("eieio" : : : "memory");
+		vsrc++;
+		dest++;
+		n--;
+	}
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+EXPORT_SYMBOL(_memcpy_fromio);
+
+void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
+{
+	void *vdest = (void __force *) dest;
+
+	__asm__ __volatile__ ("sync" : : : "memory");
+	while(n && (!IO_CHECK_ALIGN(vdest, 4) || !IO_CHECK_ALIGN(src, 4))) {
+		*((volatile u8 *)vdest) = *((u8 *)src);
+		src++;
+		vdest++;
+		n--;
+	}
+	while(n > 4) {
+		*((volatile u32 *)vdest) = *((volatile u32 *)src);
+		src += 4;
+		vdest += 4;
+		n-=4;
+	}
+	while(n) {
+		*((volatile u8 *)vdest) = *((u8 *)src);
+		src++;
+		vdest++;
+		n--;
+	}
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+EXPORT_SYMBOL(_memcpy_toio);
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index a13a93dfc655..c68113371050 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -106,7 +106,7 @@ EXPORT_SYMBOL(iowrite32_rep);
 
 void __iomem *ioport_map(unsigned long port, unsigned int len)
 {
-	return (void __iomem *) (port+pci_io_base);
+	return (void __iomem *) (port + _IO_BASE);
 }
 
 void ioport_unmap(void __iomem *addr)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ba6b7256084b..95edad4faf26 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -258,9 +258,9 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 }
 
-int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
-		struct scatterlist *sglist, int nelems,
-		unsigned long mask, enum dma_data_direction direction)
+int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
+		 int nelems, unsigned long mask,
+		 enum dma_data_direction direction)
 {
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5e37bf14ef2d..0bd8c7665834 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -64,8 +64,9 @@
 #include <asm/ptrace.h>
 #include <asm/machdep.h>
 #include <asm/udbg.h>
-#ifdef CONFIG_PPC_ISERIES
+#ifdef CONFIG_PPC64
 #include <asm/paca.h>
+#include <asm/firmware.h>
 #endif
 
 int __irq_offset_value;
@@ -95,6 +96,74 @@ extern atomic_t ipi_sent;
 EXPORT_SYMBOL(irq_desc);
 
 int distribute_irqs = 1;
+
+static inline unsigned long get_hard_enabled(void)
+{
+	unsigned long enabled;
+
+	__asm__ __volatile__("lbz %0,%1(13)"
+	: "=r" (enabled) : "i" (offsetof(struct paca_struct, hard_enabled)));
+
+	return enabled;
+}
+
+static inline void set_soft_enabled(unsigned long enable)
+{
+	__asm__ __volatile__("stb %0,%1(13)"
+	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
+}
+
+void local_irq_restore(unsigned long en)
+{
+	/*
+	 * get_paca()->soft_enabled = en;
+	 * Is it ever valid to use local_irq_restore(0) when soft_enabled is 1?
+	 * That was allowed before, and in such a case we do need to take care
+	 * that gcc will set soft_enabled directly via r13, not choose to use
+	 * an intermediate register, lest we're preempted to a different cpu.
+	 */
+	set_soft_enabled(en);
+	if (!en)
+		return;
+
+	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
+		/*
+		 * Do we need to disable preemption here?  Not really: in the
+		 * unlikely event that we're preempted to a different cpu in
+		 * between getting r13, loading its lppaca_ptr, and loading
+		 * its any_int, we might call iseries_handle_interrupts without
+		 * an interrupt pending on the new cpu, but that's no disaster,
+		 * is it?  And the business of preempting us off the old cpu
+		 * would itself involve a local_irq_restore which handles the
+		 * interrupt to that cpu.
+		 *
+		 * But use "local_paca->lppaca_ptr" instead of "get_lppaca()"
+		 * to avoid any preemption checking added into get_paca().
+		 */
+		if (local_paca->lppaca_ptr->int_dword.any_int)
+			iseries_handle_interrupts();
+		return;
+	}
+
+	/*
+	 * if (get_paca()->hard_enabled) return;
+	 * But again we need to take care that gcc gets hard_enabled directly
+	 * via r13, not choose to use an intermediate register, lest we're
+	 * preempted to a different cpu in between the two instructions.
+	 */
+	if (get_hard_enabled())
+		return;
+
+	/*
+	 * Need to hard-enable interrupts here.  Since currently disabled,
+	 * no need to take further asm precautions against preemption; but
+	 * use local_paca instead of get_paca() to avoid preemption checking.
+	 */
+	local_paca->hard_enabled = en;
+	if ((int)mfspr(SPRN_DEC) < 0)
+		mtspr(SPRN_DEC, 1);
+	hard_irq_enable();
+}
 #endif /* CONFIG_PPC64 */
 
 int show_interrupts(struct seq_file *p, void *v)
@@ -246,7 +315,8 @@ void do_IRQ(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 
 #ifdef CONFIG_PPC_ISERIES
-	if (get_lppaca()->int_dword.fields.decr_int) {
+	if (firmware_has_feature(FW_FEATURE_ISERIES) &&
+			get_lppaca()->int_dword.fields.decr_int) {
 		get_lppaca()->int_dword.fields.decr_int = 0;
 		/* Signal a fake decrementer interrupt */
 		timer_interrupt(regs);
@@ -626,10 +696,14 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
 
 void irq_dispose_mapping(unsigned int virq)
 {
-	struct irq_host *host = irq_map[virq].host;
+	struct irq_host *host;
 	irq_hw_number_t hwirq;
 	unsigned long flags;
 
+	if (virq == NO_IRQ)
+		return;
+
+	host = irq_map[virq].host;
 	WARN_ON (host == NULL);
 	if (host == NULL)
 		return;
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index 397c83eda20e..8a06724e029e 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -9,30 +9,26 @@
 #include <asm/of_device.h>
 
 /**
- * of_match_device - Tell if an of_device structure has a matching
- * of_match structure
+ * of_match_node - Tell if an device_node has a matching of_match structure
  * @ids: array of of device match structures to search in
- * @dev: the of device structure to match against
+ * @node: the of device structure to match against
  *
- * Used by a driver to check whether an of_device present in the
- * system is in its list of supported devices.
+ * Low level utility function used by device matching.
  */
-const struct of_device_id *of_match_device(const struct of_device_id *matches,
-					const struct of_device *dev)
+const struct of_device_id *of_match_node(const struct of_device_id *matches,
+					 const struct device_node *node)
 {
-	if (!dev->node)
-		return NULL;
 	while (matches->name[0] || matches->type[0] || matches->compatible[0]) {
 		int match = 1;
 		if (matches->name[0])
-			match &= dev->node->name
-				&& !strcmp(matches->name, dev->node->name);
+			match &= node->name
+				&& !strcmp(matches->name, node->name);
 		if (matches->type[0])
-			match &= dev->node->type
-				&& !strcmp(matches->type, dev->node->type);
+			match &= node->type
+				&& !strcmp(matches->type, node->type);
 		if (matches->compatible[0])
-			match &= device_is_compatible(dev->node,
-				matches->compatible);
+			match &= device_is_compatible(node,
+						      matches->compatible);
 		if (match)
 			return matches;
 		matches++;
@@ -40,16 +36,21 @@ const struct of_device_id *of_match_device(const struct of_device_id *matches,
 	return NULL;
 }
 
-static int of_platform_bus_match(struct device *dev, struct device_driver *drv)
+/**
+ * of_match_device - Tell if an of_device structure has a matching
+ * of_match structure
+ * @ids: array of of device match structures to search in
+ * @dev: the of device structure to match against
+ *
+ * Used by a driver to check whether an of_device present in the
+ * system is in its list of supported devices.
+ */
+const struct of_device_id *of_match_device(const struct of_device_id *matches,
+					const struct of_device *dev)
 {
-	struct of_device * of_dev = to_of_device(dev);
-	struct of_platform_driver * of_drv = to_of_platform_driver(drv);
-	const struct of_device_id * matches = of_drv->match_table;
-
-	if (!matches)
-		return 0;
-
-	return of_match_device(matches, of_dev) != NULL;
+	if (!dev->node)
+		return NULL;
+	return of_match_node(matches, dev->node);
 }
 
 struct of_device *of_dev_get(struct of_device *dev)
@@ -71,96 +72,8 @@ void of_dev_put(struct of_device *dev)
 		put_device(&dev->dev);
 }
 
-
-static int of_device_probe(struct device *dev)
-{
-	int error = -ENODEV;
-	struct of_platform_driver *drv;
-	struct of_device *of_dev;
-	const struct of_device_id *match;
-
-	drv = to_of_platform_driver(dev->driver);
-	of_dev = to_of_device(dev);
-
-	if (!drv->probe)
-		return error;
-
-	of_dev_get(of_dev);
-
-	match = of_match_device(drv->match_table, of_dev);
-	if (match)
-		error = drv->probe(of_dev, match);
-	if (error)
-		of_dev_put(of_dev);
-
-	return error;
-}
-
-static int of_device_remove(struct device *dev)
-{
-	struct of_device * of_dev = to_of_device(dev);
-	struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-
-	if (dev->driver && drv->remove)
-		drv->remove(of_dev);
-	return 0;
-}
-
-static int of_device_suspend(struct device *dev, pm_message_t state)
-{
-	struct of_device * of_dev = to_of_device(dev);
-	struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-	int error = 0;
-
-	if (dev->driver && drv->suspend)
-		error = drv->suspend(of_dev, state);
-	return error;
-}
-
-static int of_device_resume(struct device * dev)
-{
-	struct of_device * of_dev = to_of_device(dev);
-	struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
-	int error = 0;
-
-	if (dev->driver && drv->resume)
-		error = drv->resume(of_dev);
-	return error;
-}
-
-struct bus_type of_platform_bus_type = {
-       .name	= "of_platform",
-       .match	= of_platform_bus_match,
-       .probe	= of_device_probe,
-       .remove	= of_device_remove,
-       .suspend	= of_device_suspend,
-       .resume	= of_device_resume,
-};
-
-static int __init of_bus_driver_init(void)
-{
-	return bus_register(&of_platform_bus_type);
-}
-
-postcore_initcall(of_bus_driver_init);
-
-int of_register_driver(struct of_platform_driver *drv)
-{
-	/* initialize common driver fields */
-	drv->driver.name = drv->name;
-	drv->driver.bus = &of_platform_bus_type;
-
-	/* register with core */
-	return driver_register(&drv->driver);
-}
-
-void of_unregister_driver(struct of_platform_driver *drv)
-{
-	driver_unregister(&drv->driver);
-}
-
-
-static ssize_t dev_show_devspec(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t dev_show_devspec(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct of_device *ofdev;
 
@@ -208,41 +121,11 @@ void of_device_unregister(struct of_device *ofdev)
 	device_unregister(&ofdev->dev);
 }
 
-struct of_device* of_platform_device_create(struct device_node *np,
-					    const char *bus_id,
-					    struct device *parent)
-{
-	struct of_device *dev;
-
-	dev = kmalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return NULL;
-	memset(dev, 0, sizeof(*dev));
-
-	dev->node = of_node_get(np);
-	dev->dma_mask = 0xffffffffUL;
-	dev->dev.dma_mask = &dev->dma_mask;
-	dev->dev.parent = parent;
-	dev->dev.bus = &of_platform_bus_type;
-	dev->dev.release = of_release_dev;
-
-	strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE);
-
-	if (of_device_register(dev) != 0) {
-		kfree(dev);
-		return NULL;
-	}
-
-	return dev;
-}
 
+EXPORT_SYMBOL(of_match_node);
 EXPORT_SYMBOL(of_match_device);
-EXPORT_SYMBOL(of_platform_bus_type);
-EXPORT_SYMBOL(of_register_driver);
-EXPORT_SYMBOL(of_unregister_driver);
 EXPORT_SYMBOL(of_device_register);
 EXPORT_SYMBOL(of_device_unregister);
 EXPORT_SYMBOL(of_dev_get);
 EXPORT_SYMBOL(of_dev_put);
-EXPORT_SYMBOL(of_platform_device_create);
 EXPORT_SYMBOL(of_release_dev);
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
new file mode 100644
index 000000000000..b3189d0161b8
--- /dev/null
+++ b/arch/powerpc/kernel/of_platform.c
@@ -0,0 +1,489 @@
+/*
+ *    Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
+ *			 <benh@kernel.crashing.org>
+ *    and		 Arnd Bergmann, IBM Corp.
+ *
+ *  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.
+ *
+ */
+
+#undef DEBUG
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+
+#include <asm/errno.h>
+#include <asm/dcr.h>
+#include <asm/of_device.h>
+#include <asm/of_platform.h>
+#include <asm/topology.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/atomic.h>
+
+
+/*
+ * The list of OF IDs below is used for matching bus types in the
+ * system whose devices are to be exposed as of_platform_devices.
+ *
+ * This is the default list valid for most platforms. This file provides
+ * functions who can take an explicit list if necessary though
+ *
+ * The search is always performed recursively looking for children of
+ * the provided device_node and recursively if such a children matches
+ * a bus type in the list
+ */
+
+static struct of_device_id of_default_bus_ids[] = {
+	{ .type = "soc", },
+	{ .compatible = "soc", },
+	{ .type = "spider", },
+	{ .type = "axon", },
+	{ .type = "plb5", },
+	{ .type = "plb4", },
+	{ .type = "opb", },
+	{},
+};
+
+static atomic_t bus_no_reg_magic;
+
+/*
+ *
+ * OF platform device type definition & base infrastructure
+ *
+ */
+
+static int of_platform_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct of_device * of_dev = to_of_device(dev);
+	struct of_platform_driver * of_drv = to_of_platform_driver(drv);
+	const struct of_device_id * matches = of_drv->match_table;
+
+	if (!matches)
+		return 0;
+
+	return of_match_device(matches, of_dev) != NULL;
+}
+
+static int of_platform_device_probe(struct device *dev)
+{
+	int error = -ENODEV;
+	struct of_platform_driver *drv;
+	struct of_device *of_dev;
+	const struct of_device_id *match;
+
+	drv = to_of_platform_driver(dev->driver);
+	of_dev = to_of_device(dev);
+
+	if (!drv->probe)
+		return error;
+
+	of_dev_get(of_dev);
+
+	match = of_match_device(drv->match_table, of_dev);
+	if (match)
+		error = drv->probe(of_dev, match);
+	if (error)
+		of_dev_put(of_dev);
+
+	return error;
+}
+
+static int of_platform_device_remove(struct device *dev)
+{
+	struct of_device * of_dev = to_of_device(dev);
+	struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
+
+	if (dev->driver && drv->remove)
+		drv->remove(of_dev);
+	return 0;
+}
+
+static int of_platform_device_suspend(struct device *dev, pm_message_t state)
+{
+	struct of_device * of_dev = to_of_device(dev);
+	struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
+	int error = 0;
+
+	if (dev->driver && drv->suspend)
+		error = drv->suspend(of_dev, state);
+	return error;
+}
+
+static int of_platform_device_resume(struct device * dev)
+{
+	struct of_device * of_dev = to_of_device(dev);
+	struct of_platform_driver * drv = to_of_platform_driver(dev->driver);
+	int error = 0;
+
+	if (dev->driver && drv->resume)
+		error = drv->resume(of_dev);
+	return error;
+}
+
+struct bus_type of_platform_bus_type = {
+       .name	= "of_platform",
+       .match	= of_platform_bus_match,
+       .probe	= of_platform_device_probe,
+       .remove	= of_platform_device_remove,
+       .suspend	= of_platform_device_suspend,
+       .resume	= of_platform_device_resume,
+};
+EXPORT_SYMBOL(of_platform_bus_type);
+
+static int __init of_bus_driver_init(void)
+{
+	return bus_register(&of_platform_bus_type);
+}
+
+postcore_initcall(of_bus_driver_init);
+
+int of_register_platform_driver(struct of_platform_driver *drv)
+{
+	/* initialize common driver fields */
+	drv->driver.name = drv->name;
+	drv->driver.bus = &of_platform_bus_type;
+
+	/* register with core */
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL(of_register_platform_driver);
+
+void of_unregister_platform_driver(struct of_platform_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL(of_unregister_platform_driver);
+
+static void of_platform_make_bus_id(struct of_device *dev)
+{
+	struct device_node *node = dev->node;
+	char *name = dev->dev.bus_id;
+	const u32 *reg;
+	u64 addr;
+	long magic;
+
+	/*
+	 * If it's a DCR based device, use 'd' for native DCRs
+	 * and 'D' for MMIO DCRs.
+	 */
+#ifdef CONFIG_PPC_DCR
+	reg = get_property(node, "dcr-reg", NULL);
+	if (reg) {
+#ifdef CONFIG_PPC_DCR_NATIVE
+		snprintf(name, BUS_ID_SIZE, "d%x.%s",
+			 *reg, node->name);
+#else /* CONFIG_PPC_DCR_NATIVE */
+		addr = of_translate_dcr_address(node, *reg, NULL);
+		if (addr != OF_BAD_ADDR) {
+			snprintf(name, BUS_ID_SIZE,
+				 "D%llx.%s", (unsigned long long)addr,
+				 node->name);
+			return;
+		}
+#endif /* !CONFIG_PPC_DCR_NATIVE */
+	}
+#endif /* CONFIG_PPC_DCR */
+
+	/*
+	 * For MMIO, get the physical address
+	 */
+	reg = get_property(node, "reg", NULL);
+	if (reg) {
+		addr = of_translate_address(node, reg);
+		if (addr != OF_BAD_ADDR) {
+			snprintf(name, BUS_ID_SIZE,
+				 "%llx.%s", (unsigned long long)addr,
+				 node->name);
+			return;
+		}
+	}
+
+	/*
+	 * No BusID, use the node name and add a globally incremented
+	 * counter (and pray...)
+	 */
+	magic = atomic_add_return(1, &bus_no_reg_magic);
+	snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1);
+}
+
+struct of_device* of_platform_device_create(struct device_node *np,
+					    const char *bus_id,
+					    struct device *parent)
+{
+	struct of_device *dev;
+
+	dev = kmalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+	memset(dev, 0, sizeof(*dev));
+
+	dev->node = of_node_get(np);
+	dev->dma_mask = 0xffffffffUL;
+	dev->dev.dma_mask = &dev->dma_mask;
+	dev->dev.parent = parent;
+	dev->dev.bus = &of_platform_bus_type;
+	dev->dev.release = of_release_dev;
+	dev->dev.archdata.of_node = np;
+	dev->dev.archdata.numa_node = of_node_to_nid(np);
+
+	/* We do not fill the DMA ops for platform devices by default.
+	 * This is currently the responsibility of the platform code
+	 * to do such, possibly using a device notifier
+	 */
+
+	if (bus_id)
+		strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE);
+	else
+		of_platform_make_bus_id(dev);
+
+	if (of_device_register(dev) != 0) {
+		kfree(dev);
+		return NULL;
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL(of_platform_device_create);
+
+
+
+/**
+ * of_platform_bus_create - Create an OF device for a bus node and all its
+ * children. Optionally recursively instanciate matching busses.
+ * @bus: device node of the bus to instanciate
+ * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to
+ * disallow recursive creation of child busses
+ */
+static int of_platform_bus_create(struct device_node *bus,
+				  struct of_device_id *matches,
+				  struct device *parent)
+{
+	struct device_node *child;
+	struct of_device *dev;
+	int rc = 0;
+
+	for (child = NULL; (child = of_get_next_child(bus, child)); ) {
+		pr_debug("   create child: %s\n", child->full_name);
+		dev = of_platform_device_create(child, NULL, parent);
+		if (dev == NULL)
+			rc = -ENOMEM;
+		else if (!of_match_node(matches, child))
+			continue;
+		if (rc == 0) {
+			pr_debug("   and sub busses\n");
+			rc = of_platform_bus_create(child, matches, &dev->dev);
+		} if (rc) {
+			of_node_put(child);
+			break;
+		}
+	}
+	return rc;
+}
+
+/**
+ * of_platform_bus_probe - Probe the device-tree for platform busses
+ * @root: parent of the first level to probe or NULL for the root of the tree
+ * @matches: match table, NULL to use the default
+ * @parent: parent to hook devices from, NULL for toplevel
+ *
+ * Note that children of the provided root are not instanciated as devices
+ * unless the specified root itself matches the bus list and is not NULL.
+ */
+
+int of_platform_bus_probe(struct device_node *root,
+			  struct of_device_id *matches,
+			  struct device *parent)
+{
+	struct device_node *child;
+	struct of_device *dev;
+	int rc = 0;
+
+	if (matches == NULL)
+		matches = of_default_bus_ids;
+	if (matches == OF_NO_DEEP_PROBE)
+		return -EINVAL;
+	if (root == NULL)
+		root = of_find_node_by_path("/");
+	else
+		of_node_get(root);
+
+	pr_debug("of_platform_bus_probe()\n");
+	pr_debug(" starting at: %s\n", root->full_name);
+
+	/* Do a self check of bus type, if there's a match, create
+	 * children
+	 */
+	if (of_match_node(matches, root)) {
+		pr_debug(" root match, create all sub devices\n");
+		dev = of_platform_device_create(root, NULL, parent);
+		if (dev == NULL) {
+			rc = -ENOMEM;
+			goto bail;
+		}
+		pr_debug(" create all sub busses\n");
+		rc = of_platform_bus_create(root, matches, &dev->dev);
+		goto bail;
+	}
+	for (child = NULL; (child = of_get_next_child(root, child)); ) {
+		if (!of_match_node(matches, child))
+			continue;
+
+		pr_debug("  match: %s\n", child->full_name);
+		dev = of_platform_device_create(child, NULL, parent);
+		if (dev == NULL)
+			rc = -ENOMEM;
+		else
+			rc = of_platform_bus_create(child, matches, &dev->dev);
+		if (rc) {
+			of_node_put(child);
+			break;
+		}
+	}
+ bail:
+	of_node_put(root);
+	return rc;
+}
+EXPORT_SYMBOL(of_platform_bus_probe);
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+	return to_of_device(dev)->node == data;
+}
+
+struct of_device *of_find_device_by_node(struct device_node *np)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&of_platform_bus_type,
+			      NULL, np, of_dev_node_match);
+	if (dev)
+		return to_of_device(dev);
+	return NULL;
+}
+EXPORT_SYMBOL(of_find_device_by_node);
+
+static int of_dev_phandle_match(struct device *dev, void *data)
+{
+	phandle *ph = data;
+	return to_of_device(dev)->node->linux_phandle == *ph;
+}
+
+struct of_device *of_find_device_by_phandle(phandle ph)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&of_platform_bus_type,
+			      NULL, &ph, of_dev_phandle_match);
+	if (dev)
+		return to_of_device(dev);
+	return NULL;
+}
+EXPORT_SYMBOL(of_find_device_by_phandle);
+
+
+#ifdef CONFIG_PPC_OF_PLATFORM_PCI
+
+/* The probing of PCI controllers from of_platform is currently
+ * 64 bits only, mostly due to gratuitous differences between
+ * the 32 and 64 bits PCI code on PowerPC and the 32 bits one
+ * lacking some bits needed here.
+ */
+
+static int __devinit of_pci_phb_probe(struct of_device *dev,
+				      const struct of_device_id *match)
+{
+	struct pci_controller *phb;
+
+	/* Check if we can do that ... */
+	if (ppc_md.pci_setup_phb == NULL)
+		return -ENODEV;
+
+	printk(KERN_INFO "Setting up PCI bus %s\n", dev->node->full_name);
+
+	/* Alloc and setup PHB data structure */
+	phb = pcibios_alloc_controller(dev->node);
+	if (!phb)
+		return -ENODEV;
+
+	/* Setup parent in sysfs */
+	phb->parent = &dev->dev;
+
+	/* Setup the PHB using arch provided callback */
+	if (ppc_md.pci_setup_phb(phb)) {
+		pcibios_free_controller(phb);
+		return -ENODEV;
+	}
+
+	/* Process "ranges" property */
+	pci_process_bridge_OF_ranges(phb, dev->node, 0);
+
+	/* Setup IO space.
+	 * This will not work properly for ISA IOs, something needs to be done
+	 * about it if we ever generalize that way of probing PCI brigdes
+	 */
+	pci_setup_phb_io_dynamic(phb, 0);
+
+	/* Init pci_dn data structures */
+	pci_devs_phb_init_dynamic(phb);
+
+	/* Register devices with EEH */
+#ifdef CONFIG_EEH
+	if (dev->node->child)
+		eeh_add_device_tree_early(dev->node);
+#endif /* CONFIG_EEH */
+
+	/* Scan the bus */
+	scan_phb(phb);
+
+	/* Claim resources. This might need some rework as well depending
+	 * wether we are doing probe-only or not, like assigning unassigned
+	 * resources etc...
+	 */
+	pcibios_claim_one_bus(phb->bus);
+
+	/* Finish EEH setup */
+#ifdef CONFIG_EEH
+	eeh_add_device_tree_late(phb->bus);
+#endif
+
+	/* Add probed PCI devices to the device model */
+	pci_bus_add_devices(phb->bus);
+
+	return 0;
+}
+
+static struct of_device_id of_pci_phb_ids[] = {
+	{ .type = "pci", },
+	{ .type = "pcix", },
+	{ .type = "pcie", },
+	{ .type = "pciex", },
+	{ .type = "ht", },
+	{}
+};
+
+static struct of_platform_driver of_pci_phb_driver = {
+       .name = "of-pci",
+       .match_table = of_pci_phb_ids,
+       .probe = of_pci_phb_probe,
+       .driver = {
+	       .multithread_probe = 1,
+       },
+};
+
+static __init int of_pci_phb_init(void)
+{
+	return of_register_platform_driver(&of_pci_phb_driver);
+}
+
+device_initcall(of_pci_phb_init);
+
+#endif /* CONFIG_PPC_OF_PLATFORM_PCI */
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 0d9ff72e2852..2f54cd81dea5 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/bootmem.h>
 #include <linux/irq.h>
+#include <linux/list.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -99,7 +100,7 @@ pcibios_fixup_resources(struct pci_dev *dev)
 			continue;
 		if (res->end == 0xffffffff) {
 			DBG("PCI:%s Resource %d [%016llx-%016llx] is unassigned\n",
-			    pci_name(dev), i, res->start, res->end);
+			    pci_name(dev), i, (u64)res->start, (u64)res->end);
 			res->end -= res->start;
 			res->start = 0;
 			res->flags |= IORESOURCE_UNSET;
@@ -115,11 +116,9 @@ pcibios_fixup_resources(struct pci_dev *dev)
 		if (offset != 0) {
 			res->start += offset;
 			res->end += offset;
-#ifdef DEBUG
-			printk("Fixup res %d (%lx) of dev %s: %llx -> %llx\n",
-			       i, res->flags, pci_name(dev),
-			       res->start - offset, res->start);
-#endif
+			DBG("Fixup res %d (%lx) of dev %s: %llx -> %llx\n",
+			    i, res->flags, pci_name(dev),
+			    (u64)res->start - offset, (u64)res->start);
 		}
 	}
 
@@ -255,7 +254,7 @@ pcibios_allocate_bus_resources(struct list_head *bus_list)
 			}
 
 			DBG("PCI: bridge rsrc %llx..%llx (%lx), parent %p\n",
-				res->start, res->end, res->flags, pr);
+			    (u64)res->start, (u64)res->end, res->flags, pr);
 			if (pr) {
 				if (request_resource(pr, res) == 0)
 					continue;
@@ -306,7 +305,7 @@ reparent_resources(struct resource *parent, struct resource *res)
 	for (p = res->child; p != NULL; p = p->sibling) {
 		p->parent = res;
 		DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n",
-		    p->name, p->start, p->end, res->name);
+		    p->name, (u64)p->start, (u64)p->end, res->name);
 	}
 	return 0;
 }
@@ -362,7 +361,7 @@ pci_relocate_bridge_resource(struct pci_bus *bus, int i)
 	}
 	if (request_resource(pr, res)) {
 		DBG(KERN_ERR "PCI: huh? couldn't move to %llx..%llx\n",
-		    res->start, res->end);
+		    (u64)res->start, (u64)res->end);
 		return -1;		/* "can't happen" */
 	}
 	update_bridge_base(bus, i);
@@ -480,14 +479,14 @@ static inline void alloc_resource(struct pci_dev *dev, int idx)
 	struct resource *pr, *r = &dev->resource[idx];
 
 	DBG("PCI:%s: Resource %d: %016llx-%016llx (f=%lx)\n",
-	    pci_name(dev), idx, r->start, r->end, r->flags);
+	    pci_name(dev), idx, (u64)r->start, (u64)r->end, r->flags);
 	pr = pci_find_parent_resource(dev, r);
 	if (!pr || request_resource(pr, r) < 0) {
 		printk(KERN_ERR "PCI: Cannot allocate resource region %d"
 		       " of device %s\n", idx, pci_name(dev));
 		if (pr)
 			DBG("PCI:  parent is %p: %016llx-%016llx (f=%lx)\n",
-			    pr, pr->start, pr->end, pr->flags);
+			    pr, (u64)pr->start, (u64)pr->end, pr->flags);
 		/* We'll assign a new address later */
 		r->flags |= IORESOURCE_UNSET;
 		r->end -= r->start;
@@ -960,7 +959,7 @@ pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			res->flags = IORESOURCE_IO;
 			res->start = ranges[2];
 			DBG("PCI: IO 0x%llx -> 0x%llx\n",
-				    res->start, res->start + size - 1);
+			    (u64)res->start, (u64)res->start + size - 1);
 			break;
 		case 2:		/* memory space */
 			memno = 0;
@@ -982,7 +981,7 @@ pci_process_bridge_OF_ranges(struct pci_controller *hose,
 					res->flags |= IORESOURCE_PREFETCH;
 				res->start = ranges[na+2];
 				DBG("PCI: MEM[%d] 0x%llx -> 0x%llx\n", memno,
-					    res->start, res->start + size - 1);
+				    (u64)res->start, (u64)res->start + size - 1);
 			}
 			break;
 		}
@@ -1268,7 +1267,10 @@ pcibios_init(void)
 		if (pci_assign_all_buses)
 			hose->first_busno = next_busno;
 		hose->last_busno = 0xff;
-		bus = pci_scan_bus(hose->first_busno, hose->ops, hose);
+		bus = pci_scan_bus_parented(hose->parent, hose->first_busno,
+					    hose->ops, hose);
+		if (bus)
+			pci_bus_add_devices(bus);
 		hose->last_busno = bus->subordinate;
 		if (pci_assign_all_buses || next_busno <= hose->last_busno)
 			next_busno = hose->last_busno + pcibios_assign_bus_offset;
@@ -1282,10 +1284,6 @@ pcibios_init(void)
 	if (pci_assign_all_buses && have_of)
 		pcibios_make_OF_bus_map();
 
-	/* Do machine dependent PCI interrupt routing */
-	if (ppc_md.pci_swizzle && ppc_md.pci_map_irq)
-		pci_fixup_irqs(ppc_md.pci_swizzle, ppc_md.pci_map_irq);
-
 	/* Call machine dependent fixup */
 	if (ppc_md.pcibios_fixup)
 		ppc_md.pcibios_fixup();
@@ -1308,25 +1306,6 @@ pcibios_init(void)
 
 subsys_initcall(pcibios_init);
 
-unsigned char __init
-common_swizzle(struct pci_dev *dev, unsigned char *pinp)
-{
-	struct pci_controller *hose = dev->sysdata;
-
-	if (dev->bus->number != hose->first_busno) {
-		u8 pin = *pinp;
-		do {
-			pin = bridge_swizzle(pin, PCI_SLOT(dev->devfn));
-			/* Move up the chain of bridges. */
-			dev = dev->bus->self;
-		} while (dev->bus->self);
-		*pinp = pin;
-
-		/* The slot is the idsel of the last bridge. */
-	}
-	return PCI_SLOT(dev->devfn);
-}
-
 unsigned long resource_fixup(struct pci_dev * dev, struct resource * res,
 			     unsigned long start, unsigned long size)
 {
@@ -1338,6 +1317,7 @@ void __init pcibios_fixup_bus(struct pci_bus *bus)
 	struct pci_controller *hose = (struct pci_controller *) bus->sysdata;
 	unsigned long io_offset;
 	struct resource *res;
+	struct pci_dev *dev;
 	int i;
 
 	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
@@ -1390,8 +1370,16 @@ void __init pcibios_fixup_bus(struct pci_bus *bus)
 		}
 	}
 
+	/* Platform specific bus fixups */
 	if (ppc_md.pcibios_fixup_bus)
 		ppc_md.pcibios_fixup_bus(bus);
+
+	/* Read default IRQs and fixup if necessary */
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		pci_read_irq_line(dev);
+		if (ppc_md.pci_irq_fixup)
+			ppc_md.pci_irq_fixup(dev);
+	}
 }
 
 char __init *pcibios_setup(char *str)
@@ -1571,7 +1559,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 		*offset += hose->pci_mem_offset;
 		res_bit = IORESOURCE_MEM;
 	} else {
-		io_offset = hose->io_base_virt - ___IO_BASE;
+		io_offset = hose->io_base_virt - (void __iomem *)_IO_BASE;
 		*offset += io_offset;
 		res_bit = IORESOURCE_IO;
 	}
@@ -1826,7 +1814,8 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 		return;
 
 	if (rsrc->flags & IORESOURCE_IO)
-		offset = ___IO_BASE - hose->io_base_virt + hose->io_base_phys;
+		offset = (void __iomem *)_IO_BASE - hose->io_base_virt
+			+ hose->io_base_phys;
 
 	*start = rsrc->start + offset;
 	*end = rsrc->end + offset;
@@ -1845,35 +1834,6 @@ pci_init_resource(struct resource *res, unsigned long start, unsigned long end,
 	res->child = NULL;
 }
 
-void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max)
-{
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
-	unsigned long flags = pci_resource_flags(dev, bar);
-
-	if (!len)
-		return NULL;
-	if (max && len > max)
-		len = max;
-	if (flags & IORESOURCE_IO)
-		return ioport_map(start, len);
-	if (flags & IORESOURCE_MEM)
-		/* Not checking IORESOURCE_CACHEABLE because PPC does
-		 * not currently distinguish between ioremap and
-		 * ioremap_nocache.
-		 */
-		return ioremap(start, len);
-	/* What? */
-	return NULL;
-}
-
-void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
-{
-	/* Nothing to do */
-}
-EXPORT_SYMBOL(pci_iomap);
-EXPORT_SYMBOL(pci_iounmap);
-
 unsigned long pci_address_to_pio(phys_addr_t address)
 {
 	struct pci_controller* hose = hose_head;
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 9bae8a5bf671..6fa9a0a5c8db 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -42,11 +42,9 @@
 unsigned long pci_probe_only = 1;
 int pci_assign_all_buses = 0;
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 static void fixup_resource(struct resource *res, struct pci_dev *dev);
 static void do_bus_setup(struct pci_bus *bus);
 static void phbs_remap_io(void);
-#endif
 
 /* pci_io_base -- the base address from which io bars are offsets.
  * This is the lowest I/O base address (so bar values are always positive),
@@ -63,7 +61,7 @@ void iSeries_pcibios_init(void);
 
 LIST_HEAD(hose_list);
 
-struct dma_mapping_ops pci_dma_ops;
+struct dma_mapping_ops *pci_dma_ops;
 EXPORT_SYMBOL(pci_dma_ops);
 
 int global_phb_number;		/* Global phb counter */
@@ -212,6 +210,10 @@ struct pci_controller * pcibios_alloc_controller(struct device_node *dev)
 
 void pcibios_free_controller(struct pci_controller *phb)
 {
+	spin_lock(&hose_spinlock);
+	list_del(&phb->list_node);
+	spin_unlock(&hose_spinlock);
+
 	if (phb->is_dynamic)
 		kfree(phb);
 }
@@ -251,7 +253,6 @@ static void __init pcibios_claim_of_setup(void)
 		pcibios_claim_one_bus(b);
 }
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
 {
 	const u32 *prop;
@@ -329,7 +330,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	struct pci_dev *dev;
 	const char *type;
 
-	dev = kmalloc(sizeof(struct pci_dev), GFP_KERNEL);
+	dev = kzalloc(sizeof(struct pci_dev), GFP_KERNEL);
 	if (!dev)
 		return NULL;
 	type = get_property(node, "device_type", NULL);
@@ -338,7 +339,6 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
 	DBG("    create device, devfn: %x, type: %s\n", devfn, type);
 
-	memset(dev, 0, sizeof(struct pci_dev));
 	dev->bus = bus;
 	dev->sysdata = node;
 	dev->dev.parent = bus->bridge;
@@ -506,7 +506,6 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
 		pci_scan_child_bus(bus);
 }
 EXPORT_SYMBOL(of_scan_pci_bridge);
-#endif /* CONFIG_PPC_MULTIPLATFORM */
 
 void __devinit scan_phb(struct pci_controller *hose)
 {
@@ -517,7 +516,7 @@ void __devinit scan_phb(struct pci_controller *hose)
 
 	DBG("Scanning PHB %s\n", node ? node->full_name : "<NO NAME>");
 
-	bus = pci_create_bus(NULL, hose->first_busno, hose->ops, node);
+	bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, node);
 	if (bus == NULL) {
 		printk(KERN_ERR "Failed to create bus for PCI domain %04x\n",
 		       hose->global_number);
@@ -540,7 +539,7 @@ void __devinit scan_phb(struct pci_controller *hose)
 	}
 
 	mode = PCI_PROBE_NORMAL;
-#ifdef CONFIG_PPC_MULTIPLATFORM
+
 	if (node && ppc_md.pci_probe_mode)
 		mode = ppc_md.pci_probe_mode(bus);
 	DBG("    probe mode: %d\n", mode);
@@ -548,7 +547,7 @@ void __devinit scan_phb(struct pci_controller *hose)
 		bus->subordinate = hose->last_busno;
 		of_scan_bus(node, bus);
 	}
-#endif /* CONFIG_PPC_MULTIPLATFORM */
+
 	if (mode == PCI_PROBE_NORMAL)
 		hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
 }
@@ -592,11 +591,9 @@ static int __init pcibios_init(void)
 	if (ppc64_isabridge_dev != NULL)
 		printk(KERN_DEBUG "ISA bridge at %s\n", pci_name(ppc64_isabridge_dev));
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
 	if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		/* map in PCI I/O space */
 		phbs_remap_io();
-#endif
 
 	printk(KERN_DEBUG "PCI: Probing PCI hardware done\n");
 
@@ -873,8 +870,6 @@ void pcibios_add_platform_entries(struct pci_dev *pdev)
 	device_create_file(&pdev->dev, &dev_attr_devspec);
 }
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
-
 #define ISA_SPACE_MASK 0x1
 #define ISA_SPACE_IO 0x1
 
@@ -975,11 +970,7 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
 		res = NULL;
 		pci_space = ranges[0];
 		pci_addr = ((unsigned long)ranges[1] << 32) | ranges[2];
-
-		cpu_phys_addr = ranges[3];
-		if (na >= 2)
-			cpu_phys_addr = (cpu_phys_addr << 32) | ranges[4];
-
+		cpu_phys_addr = of_translate_address(dev, &ranges[3]);
 		size = ((unsigned long)ranges[na+3] << 32) | ranges[na+4];
 		ranges += np;
 		if (size == 0)
@@ -1145,7 +1136,7 @@ int unmap_bus_range(struct pci_bus *bus)
 	
 	if (get_bus_io_range(bus, &start_phys, &start_virt, &size))
 		return 1;
-	if (iounmap_explicit((void __iomem *) start_virt, size))
+	if (__iounmap_explicit((void __iomem *) start_virt, size))
 		return 1;
 
 	return 0;
@@ -1213,23 +1204,52 @@ void __devinit pcibios_fixup_device_resources(struct pci_dev *dev,
 }
 EXPORT_SYMBOL(pcibios_fixup_device_resources);
 
+void __devinit pcibios_setup_new_device(struct pci_dev *dev)
+{
+	struct dev_archdata *sd = &dev->dev.archdata;
+
+	sd->of_node = pci_device_to_OF_node(dev);
+
+	DBG("PCI device %s OF node: %s\n", pci_name(dev),
+	    sd->of_node ? sd->of_node->full_name : "<none>");
+
+	sd->dma_ops = pci_dma_ops;
+#ifdef CONFIG_NUMA
+	sd->numa_node = pcibus_to_node(dev->bus);
+#else
+	sd->numa_node = -1;
+#endif
+	if (ppc_md.pci_dma_dev_setup)
+		ppc_md.pci_dma_dev_setup(dev);
+}
+EXPORT_SYMBOL(pcibios_setup_new_device);
 
 static void __devinit do_bus_setup(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
-	ppc_md.iommu_bus_setup(bus);
+	if (ppc_md.pci_dma_bus_setup)
+		ppc_md.pci_dma_bus_setup(bus);
 
 	list_for_each_entry(dev, &bus->devices, bus_list)
-		ppc_md.iommu_dev_setup(dev);
+		pcibios_setup_new_device(dev);
 
-	if (ppc_md.irq_bus_setup)
-		ppc_md.irq_bus_setup(bus);
+	/* Read default IRQs and fixup if necessary */
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		pci_read_irq_line(dev);
+		if (ppc_md.pci_irq_fixup)
+			ppc_md.pci_irq_fixup(dev);
+	}
 }
 
 void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
 	struct pci_dev *dev = bus->self;
+	struct device_node *np;
+
+	np = pci_bus_to_OF_node(bus);
+
+	DBG("pcibios_fixup_bus(%s)\n", np ? np->full_name : "<???>");
 
 	if (dev && pci_probe_only &&
 	    (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
@@ -1343,8 +1363,6 @@ struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
 	return NULL;
 }
 
-#endif /* CONFIG_PPC_MULTIPLATFORM */
-
 unsigned long pci_address_to_pio(phys_addr_t address)
 {
 	struct pci_controller *hose, *tmp;
diff --git a/arch/powerpc/kernel/pci_direct_iommu.c b/arch/powerpc/kernel/pci_direct_iommu.c
deleted file mode 100644
index 72ce082ce738..000000000000
--- a/arch/powerpc/kernel/pci_direct_iommu.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Support for DMA from PCI devices to main memory on
- * machines without an iommu or with directly addressable
- * RAM (typically a pmac with 2Gb of RAM or less)
- *
- * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *
- * 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.
- */
-
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/dma-mapping.h>
-
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/prom.h>
-#include <asm/pci-bridge.h>
-#include <asm/machdep.h>
-#include <asm/pmac_feature.h>
-#include <asm/abs_addr.h>
-#include <asm/ppc-pci.h>
-
-static void *pci_direct_alloc_coherent(struct device *hwdev, size_t size,
-				   dma_addr_t *dma_handle, gfp_t flag)
-{
-	void *ret;
-
-	ret = (void *)__get_free_pages(flag, get_order(size));
-	if (ret != NULL) {
-		memset(ret, 0, size);
-		*dma_handle = virt_to_abs(ret);
-	}
-	return ret;
-}
-
-static void pci_direct_free_coherent(struct device *hwdev, size_t size,
-				 void *vaddr, dma_addr_t dma_handle)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static dma_addr_t pci_direct_map_single(struct device *hwdev, void *ptr,
-		size_t size, enum dma_data_direction direction)
-{
-	return virt_to_abs(ptr);
-}
-
-static void pci_direct_unmap_single(struct device *hwdev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction direction)
-{
-}
-
-static int pci_direct_map_sg(struct device *hwdev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction)
-{
-	int i;
-
-	for (i = 0; i < nents; i++, sg++) {
-		sg->dma_address = page_to_phys(sg->page) + sg->offset;
-		sg->dma_length = sg->length;
-	}
-
-	return nents;
-}
-
-static void pci_direct_unmap_sg(struct device *hwdev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction)
-{
-}
-
-static int pci_direct_dma_supported(struct device *dev, u64 mask)
-{
-	return mask < 0x100000000ull;
-}
-
-static struct dma_mapping_ops pci_direct_ops = {
-	.alloc_coherent = pci_direct_alloc_coherent,
-	.free_coherent = pci_direct_free_coherent,
-	.map_single = pci_direct_map_single,
-	.unmap_single = pci_direct_unmap_single,
-	.map_sg = pci_direct_map_sg,
-	.unmap_sg = pci_direct_unmap_sg,
-	.dma_supported = pci_direct_dma_supported,
-};
-
-void __init pci_direct_iommu_init(void)
-{
-	pci_dma_ops = pci_direct_ops;
-}
diff --git a/arch/powerpc/kernel/pci_iommu.c b/arch/powerpc/kernel/pci_iommu.c
deleted file mode 100644
index 0688b2534acb..000000000000
--- a/arch/powerpc/kernel/pci_iommu.c
+++ /dev/null
@@ -1,164 +0,0 @@
-/*
- * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
- *
- * Rewrite, cleanup, new allocation schemes:
- * Copyright (C) 2004 Olof Johansson, IBM Corporation
- *
- * Dynamic DMA mapping support, platform-independent parts.
- *
- * 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/init.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/pci.h>
-#include <linux/dma-mapping.h>
-#include <asm/io.h>
-#include <asm/prom.h>
-#include <asm/iommu.h>
-#include <asm/pci-bridge.h>
-#include <asm/machdep.h>
-#include <asm/ppc-pci.h>
-
-/*
- * We can use ->sysdata directly and avoid the extra work in
- * pci_device_to_OF_node since ->sysdata will have been initialised
- * in the iommu init code for all devices.
- */
-#define PCI_GET_DN(dev) ((struct device_node *)((dev)->sysdata))
-
-static inline struct iommu_table *device_to_table(struct device *hwdev)
-{
-	struct pci_dev *pdev;
-
-	if (!hwdev) {
-		pdev = ppc64_isabridge_dev;
-		if (!pdev)
-			return NULL;
-	} else
-		pdev = to_pci_dev(hwdev);
-
-	return PCI_DN(PCI_GET_DN(pdev))->iommu_table;
-}
-
-
-static inline unsigned long device_to_mask(struct device *hwdev)
-{
-	struct pci_dev *pdev;
-
-	if (!hwdev) {
-		pdev = ppc64_isabridge_dev;
-		if (!pdev) /* This is the best guess we can do */
-			return 0xfffffffful;
-	} else
-		pdev = to_pci_dev(hwdev);
-
-	if (pdev->dma_mask)
-		return pdev->dma_mask;
-
-	/* Assume devices without mask can take 32 bit addresses */
-	return 0xfffffffful;
-}
-
-
-/* Allocates a contiguous real buffer and creates mappings over it.
- * Returns the virtual address of the buffer and sets dma_handle
- * to the dma address (mapping) of the first page.
- */
-static void *pci_iommu_alloc_coherent(struct device *hwdev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag)
-{
-	return iommu_alloc_coherent(device_to_table(hwdev), size, dma_handle,
-			device_to_mask(hwdev), flag,
-			pcibus_to_node(to_pci_dev(hwdev)->bus));
-}
-
-static void pci_iommu_free_coherent(struct device *hwdev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle)
-{
-	iommu_free_coherent(device_to_table(hwdev), size, vaddr, dma_handle);
-}
-
-/* Creates TCEs for a user provided buffer.  The user buffer must be 
- * contiguous real kernel storage (not vmalloc).  The address of the buffer
- * passed here is the kernel (virtual) address of the buffer.  The buffer
- * need not be page aligned, the dma_addr_t returned will point to the same
- * byte within the page as vaddr.
- */
-static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr,
-		size_t size, enum dma_data_direction direction)
-{
-	return iommu_map_single(device_to_table(hwdev), vaddr, size,
-			        device_to_mask(hwdev), direction);
-}
-
-
-static void pci_iommu_unmap_single(struct device *hwdev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction direction)
-{
-	iommu_unmap_single(device_to_table(hwdev), dma_handle, size, direction);
-}
-
-
-static int pci_iommu_map_sg(struct device *pdev, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction)
-{
-	return iommu_map_sg(pdev, device_to_table(pdev), sglist,
-			nelems, device_to_mask(pdev), direction);
-}
-
-static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction)
-{
-	iommu_unmap_sg(device_to_table(pdev), sglist, nelems, direction);
-}
-
-/* We support DMA to/from any memory page via the iommu */
-static int pci_iommu_dma_supported(struct device *dev, u64 mask)
-{
-	struct iommu_table *tbl = device_to_table(dev);
-
-	if (!tbl || tbl->it_offset > mask) {
-		printk(KERN_INFO "Warning: IOMMU table offset too big for device mask\n");
-		if (tbl)
-			printk(KERN_INFO "mask: 0x%08lx, table offset: 0x%08lx\n",
-				mask, tbl->it_offset);
-		else
-			printk(KERN_INFO "mask: 0x%08lx, table unavailable\n",
-				mask);
-		return 0;
-	} else
-		return 1;
-}
-
-struct dma_mapping_ops pci_iommu_ops = {
-	.alloc_coherent = pci_iommu_alloc_coherent,
-	.free_coherent = pci_iommu_free_coherent,
-	.map_single = pci_iommu_map_single,
-	.unmap_single = pci_iommu_unmap_single,
-	.map_sg = pci_iommu_map_sg,
-	.unmap_sg = pci_iommu_unmap_sg,
-	.dma_supported = pci_iommu_dma_supported,
-};
-
-void pci_iommu_init(void)
-{
-	pci_dma_ops = pci_iommu_ops;
-}
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 807193a3c784..9179f0739ea2 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -49,6 +49,10 @@
 #include <asm/commproc.h>
 #endif
 
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(local_irq_restore);
+#endif
+
 #ifdef CONFIG_PPC32
 extern void transfer_to_handler(void);
 extern void do_IRQ(struct pt_regs *regs);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index bdb412d4b748..c18dbe77fdc2 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -538,35 +538,31 @@ static struct ibm_pa_feature {
 	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
 };
 
-static void __init check_cpu_pa_features(unsigned long node)
+static void __init scan_features(unsigned long node, unsigned char *ftrs,
+				 unsigned long tablelen,
+				 struct ibm_pa_feature *fp,
+				 unsigned long ft_size)
 {
-	unsigned char *pa_ftrs;
-	unsigned long len, tablelen, i, bit;
-
-	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
-	if (pa_ftrs == NULL)
-		return;
+	unsigned long i, len, bit;
 
 	/* find descriptor with type == 0 */
 	for (;;) {
 		if (tablelen < 3)
 			return;
-		len = 2 + pa_ftrs[0];
+		len = 2 + ftrs[0];
 		if (tablelen < len)
 			return;		/* descriptor 0 not found */
-		if (pa_ftrs[1] == 0)
+		if (ftrs[1] == 0)
 			break;
 		tablelen -= len;
-		pa_ftrs += len;
+		ftrs += len;
 	}
 
 	/* loop over bits we know about */
-	for (i = 0; i < ARRAY_SIZE(ibm_pa_features); ++i) {
-		struct ibm_pa_feature *fp = &ibm_pa_features[i];
-
-		if (fp->pabyte >= pa_ftrs[0])
+	for (i = 0; i < ft_size; ++i, ++fp) {
+		if (fp->pabyte >= ftrs[0])
 			continue;
-		bit = (pa_ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
+		bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
 		if (bit ^ fp->invert) {
 			cur_cpu_spec->cpu_features |= fp->cpu_features;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
@@ -577,16 +573,59 @@ static void __init check_cpu_pa_features(unsigned long node)
 	}
 }
 
+static void __init check_cpu_pa_features(unsigned long node)
+{
+	unsigned char *pa_ftrs;
+	unsigned long tablelen;
+
+	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
+	if (pa_ftrs == NULL)
+		return;
+
+	scan_features(node, pa_ftrs, tablelen,
+		      ibm_pa_features, ARRAY_SIZE(ibm_pa_features));
+}
+
+static struct feature_property {
+	const char *name;
+	u32 min_value;
+	unsigned long cpu_feature;
+	unsigned long cpu_user_ftr;
+} feature_properties[] __initdata = {
+#ifdef CONFIG_ALTIVEC
+	{"altivec", 0, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
+	{"ibm,vmx", 1, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_PPC64
+	{"ibm,dfp", 1, 0, PPC_FEATURE_HAS_DFP},
+	{"ibm,purr", 1, CPU_FTR_PURR, 0},
+	{"ibm,spurr", 1, CPU_FTR_SPURR, 0},
+#endif /* CONFIG_PPC64 */
+};
+
+static void __init check_cpu_feature_properties(unsigned long node)
+{
+	unsigned long i;
+	struct feature_property *fp = feature_properties;
+	const u32 *prop;
+
+	for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) {
+		prop = of_get_flat_dt_prop(node, fp->name, NULL);
+		if (prop && *prop >= fp->min_value) {
+			cur_cpu_spec->cpu_features |= fp->cpu_feature;
+			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
+		}
+	}
+}
+
 static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
 	static int logical_cpuid = 0;
 	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-#ifdef CONFIG_ALTIVEC
-	u32 *prop;
-#endif
-	u32 *intserv;
+	const u32 *prop;
+	const u32 *intserv;
 	int i, nthreads;
 	unsigned long len;
 	int found = 0;
@@ -643,24 +682,27 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 			intserv[i]);
 		boot_cpuid = logical_cpuid;
 		set_hard_smp_processor_id(boot_cpuid, intserv[i]);
-	}
 
-#ifdef CONFIG_ALTIVEC
-	/* Check if we have a VMX and eventually update CPU features */
-	prop = (u32 *)of_get_flat_dt_prop(node, "ibm,vmx", NULL);
-	if (prop && (*prop) > 0) {
-		cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
-		cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
-	}
-
-	/* Same goes for Apple's "altivec" property */
-	prop = (u32 *)of_get_flat_dt_prop(node, "altivec", NULL);
-	if (prop) {
-		cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
-		cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
+		/*
+		 * PAPR defines "logical" PVR values for cpus that
+		 * meet various levels of the architecture:
+		 * 0x0f000001	Architecture version 2.04
+		 * 0x0f000002	Architecture version 2.05
+		 * If the cpu-version property in the cpu node contains
+		 * such a value, we call identify_cpu again with the
+		 * logical PVR value in order to use the cpu feature
+		 * bits appropriate for the architecture level.
+		 *
+		 * A POWER6 partition in "POWER6 architected" mode
+		 * uses the 0x0f000002 PVR value; in POWER5+ mode
+		 * it uses 0x0f000001.
+		 */
+		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
+		if (prop && (*prop & 0xff000000) == 0x0f000000)
+			identify_cpu(0, *prop);
 	}
-#endif /* CONFIG_ALTIVEC */
 
+	check_cpu_feature_properties(node);
 	check_cpu_pa_features(node);
 
 #ifdef CONFIG_PPC_PSERIES
@@ -1674,6 +1716,7 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(of_get_cpu_node);
 
 #ifdef DEBUG
 static struct debugfs_blob_wrapper flat_dt_blob;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index b91761639d96..46cf32670ddb 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -173,8 +173,8 @@ static unsigned long __initdata dt_string_start, dt_string_end;
 static unsigned long __initdata prom_initrd_start, prom_initrd_end;
 
 #ifdef CONFIG_PPC64
-static int __initdata iommu_force_on;
-static int __initdata ppc64_iommu_off;
+static int __initdata prom_iommu_force_on;
+static int __initdata prom_iommu_off;
 static unsigned long __initdata prom_tce_alloc_start;
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
@@ -582,9 +582,9 @@ static void __init early_cmdline_parse(void)
 		while (*opt && *opt == ' ')
 			opt++;
 		if (!strncmp(opt, RELOC("off"), 3))
-			RELOC(ppc64_iommu_off) = 1;
+			RELOC(prom_iommu_off) = 1;
 		else if (!strncmp(opt, RELOC("force"), 5))
-			RELOC(iommu_force_on) = 1;
+			RELOC(prom_iommu_force_on) = 1;
 	}
 #endif
 }
@@ -627,6 +627,7 @@ static void __init early_cmdline_parse(void)
 /* Option vector 3: processor options supported */
 #define OV3_FP			0x80	/* floating point */
 #define OV3_VMX			0x40	/* VMX/Altivec */
+#define OV3_DFP			0x20	/* decimal FP */
 
 /* Option vector 5: PAPR/OF options supported */
 #define OV5_LPAR		0x80	/* logical partitioning supported */
@@ -642,6 +643,7 @@ static void __init early_cmdline_parse(void)
 static unsigned char ibm_architecture_vec[] = {
 	W(0xfffe0000), W(0x003a0000),	/* POWER5/POWER5+ */
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
+	W(0xffffffff), W(0x0f000002),	/* all 2.05-compliant */
 	W(0xfffffffe), W(0x0f000001),	/* all 2.04-compliant and earlier */
 	5 - 1,				/* 5 option vectors */
 
@@ -668,7 +670,7 @@ static unsigned char ibm_architecture_vec[] = {
 	/* option vector 3: processor options supported */
 	3 - 2,				/* length */
 	0,				/* don't ignore, don't halt */
-	OV3_FP | OV3_VMX,
+	OV3_FP | OV3_VMX | OV3_DFP,
 
 	/* option vector 4: IBM PAPR implementation */
 	2 - 2,				/* length */
@@ -1167,7 +1169,7 @@ static void __init prom_initialize_tce_table(void)
 	u64 local_alloc_top, local_alloc_bottom;
 	u64 i;
 
-	if (RELOC(ppc64_iommu_off))
+	if (RELOC(prom_iommu_off))
 		return;
 
 	prom_debug("starting prom_initialize_tce_table\n");
@@ -2283,11 +2285,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * Fill in some infos for use by the kernel later on
 	 */
 #ifdef CONFIG_PPC64
-	if (RELOC(ppc64_iommu_off))
+	if (RELOC(prom_iommu_off))
 		prom_setprop(_prom->chosen, "/chosen", "linux,iommu-off",
 			     NULL, 0);
 
-	if (RELOC(iommu_force_on))
+	if (RELOC(prom_iommu_force_on))
 		prom_setprop(_prom->chosen, "/chosen", "linux,iommu-force-on",
 			     NULL, 0);
 
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 603dff3ad62a..0dfbe1cd28eb 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -25,6 +25,12 @@
 #define OF_CHECK_COUNTS(na, ns)	((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \
 			(ns) > 0)
 
+static struct of_bus *of_match_bus(struct device_node *np);
+static int __of_address_to_resource(struct device_node *dev,
+		const u32 *addrp, u64 size, unsigned int flags,
+		struct resource *r);
+
+
 /* Debug utility */
 #ifdef DEBUG
 static void of_dump_addr(const char *s, const u32 *addr, int na)
@@ -101,6 +107,7 @@ static unsigned int of_bus_default_get_flags(const u32 *addr)
 }
 
 
+#ifdef CONFIG_PCI
 /*
  * PCI bus specific translator
  */
@@ -153,15 +160,156 @@ static unsigned int of_bus_pci_get_flags(const u32 *addr)
 	switch((w >> 24) & 0x03) {
 	case 0x01:
 		flags |= IORESOURCE_IO;
+		break;
 	case 0x02: /* 32 bits */
 	case 0x03: /* 64 bits */
 		flags |= IORESOURCE_MEM;
+		break;
 	}
 	if (w & 0x40000000)
 		flags |= IORESOURCE_PREFETCH;
 	return flags;
 }
 
+const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size,
+			unsigned int *flags)
+{
+	const u32 *prop;
+	unsigned int psize;
+	struct device_node *parent;
+	struct of_bus *bus;
+	int onesize, i, na, ns;
+
+	/* Get parent & match bus type */
+	parent = of_get_parent(dev);
+	if (parent == NULL)
+		return NULL;
+	bus = of_match_bus(parent);
+	if (strcmp(bus->name, "pci")) {
+		of_node_put(parent);
+		return NULL;
+	}
+	bus->count_cells(dev, &na, &ns);
+	of_node_put(parent);
+	if (!OF_CHECK_COUNTS(na, ns))
+		return NULL;
+
+	/* Get "reg" or "assigned-addresses" property */
+	prop = get_property(dev, bus->addresses, &psize);
+	if (prop == NULL)
+		return NULL;
+	psize /= 4;
+
+	onesize = na + ns;
+	for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++)
+		if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) {
+			if (size)
+				*size = of_read_number(prop + na, ns);
+			if (flags)
+				*flags = bus->get_flags(prop);
+			return prop;
+		}
+	return NULL;
+}
+EXPORT_SYMBOL(of_get_pci_address);
+
+int of_pci_address_to_resource(struct device_node *dev, int bar,
+			       struct resource *r)
+{
+	const u32	*addrp;
+	u64		size;
+	unsigned int	flags;
+
+	addrp = of_get_pci_address(dev, bar, &size, &flags);
+	if (addrp == NULL)
+		return -EINVAL;
+	return __of_address_to_resource(dev, addrp, size, flags, r);
+}
+EXPORT_SYMBOL_GPL(of_pci_address_to_resource);
+
+static u8 of_irq_pci_swizzle(u8 slot, u8 pin)
+{
+	return (((pin - 1) + slot) % 4) + 1;
+}
+
+int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
+{
+	struct device_node *dn, *ppnode;
+	struct pci_dev *ppdev;
+	u32 lspec;
+	u32 laddr[3];
+	u8 pin;
+	int rc;
+
+	/* Check if we have a device node, if yes, fallback to standard OF
+	 * parsing
+	 */
+	dn = pci_device_to_OF_node(pdev);
+	if (dn)
+		return of_irq_map_one(dn, 0, out_irq);
+
+	/* Ok, we don't, time to have fun. Let's start by building up an
+	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
+	 * for PCI. If you do different, then don't use that routine.
+	 */
+	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
+	if (rc != 0)
+		return rc;
+	/* No pin, exit */
+	if (pin == 0)
+		return -ENODEV;
+
+	/* Now we walk up the PCI tree */
+	lspec = pin;
+	for (;;) {
+		/* Get the pci_dev of our parent */
+		ppdev = pdev->bus->self;
+
+		/* Ouch, it's a host bridge... */
+		if (ppdev == NULL) {
+#ifdef CONFIG_PPC64
+			ppnode = pci_bus_to_OF_node(pdev->bus);
+#else
+			struct pci_controller *host;
+			host = pci_bus_to_host(pdev->bus);
+			ppnode = host ? host->arch_data : NULL;
+#endif
+			/* No node for host bridge ? give up */
+			if (ppnode == NULL)
+				return -EINVAL;
+		} else
+			/* We found a P2P bridge, check if it has a node */
+			ppnode = pci_device_to_OF_node(ppdev);
+
+		/* Ok, we have found a parent with a device-node, hand over to
+		 * the OF parsing code.
+		 * We build a unit address from the linux device to be used for
+		 * resolution. Note that we use the linux bus number which may
+		 * not match your firmware bus numbering.
+		 * Fortunately, in most cases, interrupt-map-mask doesn't include
+		 * the bus number as part of the matching.
+		 * You should still be careful about that though if you intend
+		 * to rely on this function (you ship  a firmware that doesn't
+		 * create device nodes for all PCI devices).
+		 */
+		if (ppnode)
+			break;
+
+		/* We can only get here if we hit a P2P bridge with no node,
+		 * let's do standard swizzling and try again
+		 */
+		lspec = of_irq_pci_swizzle(PCI_SLOT(pdev->devfn), lspec);
+		pdev = ppdev;
+	}
+
+	laddr[0] = (pdev->bus->number << 16)
+		| (pdev->devfn << 8);
+	laddr[1]  = laddr[2] = 0;
+	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
+}
+EXPORT_SYMBOL_GPL(of_irq_map_pci);
+#endif /* CONFIG_PCI */
+
 /*
  * ISA bus specific translator
  */
@@ -223,6 +371,7 @@ static unsigned int of_bus_isa_get_flags(const u32 *addr)
  */
 
 static struct of_bus of_busses[] = {
+#ifdef CONFIG_PCI
 	/* PCI */
 	{
 		.name = "pci",
@@ -233,6 +382,7 @@ static struct of_bus of_busses[] = {
 		.translate = of_bus_pci_translate,
 		.get_flags = of_bus_pci_get_flags,
 	},
+#endif /* CONFIG_PCI */
 	/* ISA */
 	{
 		.name = "isa",
@@ -445,48 +595,6 @@ const u32 *of_get_address(struct device_node *dev, int index, u64 *size,
 }
 EXPORT_SYMBOL(of_get_address);
 
-const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size,
-			unsigned int *flags)
-{
-	const u32 *prop;
-	unsigned int psize;
-	struct device_node *parent;
-	struct of_bus *bus;
-	int onesize, i, na, ns;
-
-	/* Get parent & match bus type */
-	parent = of_get_parent(dev);
-	if (parent == NULL)
-		return NULL;
-	bus = of_match_bus(parent);
-	if (strcmp(bus->name, "pci")) {
-		of_node_put(parent);
-		return NULL;
-	}
-	bus->count_cells(dev, &na, &ns);
-	of_node_put(parent);
-	if (!OF_CHECK_COUNTS(na, ns))
-		return NULL;
-
-	/* Get "reg" or "assigned-addresses" property */
-	prop = get_property(dev, bus->addresses, &psize);
-	if (prop == NULL)
-		return NULL;
-	psize /= 4;
-
-	onesize = na + ns;
-	for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++)
-		if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) {
-			if (size)
-				*size = of_read_number(prop + na, ns);
-			if (flags)
-				*flags = bus->get_flags(prop);
-			return prop;
-		}
-	return NULL;
-}
-EXPORT_SYMBOL(of_get_pci_address);
-
 static int __of_address_to_resource(struct device_node *dev, const u32 *addrp,
 				    u64 size, unsigned int flags,
 				    struct resource *r)
@@ -529,20 +637,6 @@ int of_address_to_resource(struct device_node *dev, int index,
 }
 EXPORT_SYMBOL_GPL(of_address_to_resource);
 
-int of_pci_address_to_resource(struct device_node *dev, int bar,
-			       struct resource *r)
-{
-	const u32	*addrp;
-	u64		size;
-	unsigned int	flags;
-
-	addrp = of_get_pci_address(dev, bar, &size, &flags);
-	if (addrp == NULL)
-		return -EINVAL;
-	return __of_address_to_resource(dev, addrp, size, flags, r);
-}
-EXPORT_SYMBOL_GPL(of_pci_address_to_resource);
-
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
 {
@@ -898,87 +992,3 @@ int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq
 	return res;
 }
 EXPORT_SYMBOL_GPL(of_irq_map_one);
-
-#ifdef CONFIG_PCI
-static u8 of_irq_pci_swizzle(u8 slot, u8 pin)
-{
-	return (((pin - 1) + slot) % 4) + 1;
-}
-
-int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
-{
-	struct device_node *dn, *ppnode;
-	struct pci_dev *ppdev;
-	u32 lspec;
-	u32 laddr[3];
-	u8 pin;
-	int rc;
-
-	/* Check if we have a device node, if yes, fallback to standard OF
-	 * parsing
-	 */
-	dn = pci_device_to_OF_node(pdev);
-	if (dn)
-		return of_irq_map_one(dn, 0, out_irq);
-
-	/* Ok, we don't, time to have fun. Let's start by building up an
-	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
-	 * for PCI. If you do different, then don't use that routine.
-	 */
-	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
-	if (rc != 0)
-		return rc;
-	/* No pin, exit */
-	if (pin == 0)
-		return -ENODEV;
-
-	/* Now we walk up the PCI tree */
-	lspec = pin;
-	for (;;) {
-		/* Get the pci_dev of our parent */
-		ppdev = pdev->bus->self;
-
-		/* Ouch, it's a host bridge... */
-		if (ppdev == NULL) {
-#ifdef CONFIG_PPC64
-			ppnode = pci_bus_to_OF_node(pdev->bus);
-#else
-			struct pci_controller *host;
-			host = pci_bus_to_host(pdev->bus);
-			ppnode = host ? host->arch_data : NULL;
-#endif
-			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
-		} else
-			/* We found a P2P bridge, check if it has a node */
-			ppnode = pci_device_to_OF_node(ppdev);
-
-		/* Ok, we have found a parent with a device-node, hand over to
-		 * the OF parsing code.
-		 * We build a unit address from the linux device to be used for
-		 * resolution. Note that we use the linux bus number which may
-		 * not match your firmware bus numbering.
-		 * Fortunately, in most cases, interrupt-map-mask doesn't include
-		 * the bus number as part of the matching.
-		 * You should still be careful about that though if you intend
-		 * to rely on this function (you ship  a firmware that doesn't
-		 * create device nodes for all PCI devices).
-		 */
-		if (ppnode)
-			break;
-
-		/* We can only get here if we hit a P2P bridge with no node,
-		 * let's do standard swizzling and try again
-		 */
-		lspec = of_irq_pci_swizzle(PCI_SLOT(pdev->devfn), lspec);
-		pdev = ppdev;
-	}
-
-	laddr[0] = (pdev->bus->number << 16)
-		| (pdev->devfn << 8);
-	laddr[1]  = laddr[2] = 0;
-	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
-}
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
-#endif /* CONFIG_PCI */
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 6ef80d4e38d3..387ed0d9ad61 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -810,9 +810,9 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /* This version can't take the spinlock, because it never returns */
-
-struct rtas_args rtas_stop_self_args = {
+static struct rtas_args rtas_stop_self_args = {
 	/* The token is initialized for real in setup_system() */
 	.token = RTAS_UNKNOWN_SERVICE,
 	.nargs = 0,
@@ -834,6 +834,7 @@ void rtas_stop_self(void)
 
 	panic("Alas, I survived.\n");
 }
+#endif
 
 /*
  * Call early during boot, before mem init or bootmem, to retrieve the RTAS
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 6f6fc977cb39..b9561d300516 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -681,14 +681,12 @@ static int initialize_flash_pde_data(const char *rtas_call_name,
 	int *status;
 	int token;
 
-	dp->data = kmalloc(buf_size, GFP_KERNEL);
+	dp->data = kzalloc(buf_size, GFP_KERNEL);
 	if (dp->data == NULL) {
 		remove_flash_pde(dp);
 		return -ENOMEM;
 	}
 
-	memset(dp->data, 0, buf_size);
-
 	/*
 	 * This code assumes that the status int is the first member of the
 	 * struct 
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index b4a0de79c060..ace9f4c86e67 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -38,6 +38,7 @@
 #include <asm/rtas.h>
 #include <asm/mpic.h>
 #include <asm/ppc-pci.h>
+#include <asm/eeh.h>
 
 /* RTAS tokens */
 static int read_pci_config;
@@ -231,32 +232,13 @@ void __init init_pci_config_tokens (void)
 
 unsigned long __devinit get_phb_buid (struct device_node *phb)
 {
-	int addr_cells;
-	const unsigned int *buid_vals;
-	unsigned int len;
-	unsigned long buid;
-
-	if (ibm_read_pci_config == -1) return 0;
+	struct resource r;
 
-	/* PHB's will always be children of the root node,
-	 * or so it is promised by the current firmware. */
-	if (phb->parent == NULL)
+	if (ibm_read_pci_config == -1)
 		return 0;
-	if (phb->parent->parent)
-		return 0;
-
-	buid_vals = get_property(phb, "reg", &len);
-	if (buid_vals == NULL)
+	if (of_address_to_resource(phb, 0, &r))
 		return 0;
-
-	addr_cells = prom_n_addr_cells(phb);
-	if (addr_cells == 1) {
-		buid = (unsigned long) buid_vals[0];
-	} else {
-		buid = (((unsigned long)buid_vals[0]) << 32UL) |
-			(((unsigned long)buid_vals[1]) & 0xffffffff);
-	}
-	return buid;
+	return r.start;
 }
 
 static int phb_set_bus_ranges(struct device_node *dev,
@@ -276,8 +258,10 @@ static int phb_set_bus_ranges(struct device_node *dev,
 	return 0;
 }
 
-int __devinit setup_phb(struct device_node *dev, struct pci_controller *phb)
+int __devinit rtas_setup_phb(struct pci_controller *phb)
 {
+	struct device_node *dev = phb->arch_data;
+
 	if (is_python(dev))
 		python_countermeasures(dev);
 
@@ -309,7 +293,7 @@ unsigned long __init find_and_init_phbs(void)
 		phb = pcibios_alloc_controller(node);
 		if (!phb)
 			continue;
-		setup_phb(node, phb);
+		rtas_setup_phb(phb);
 		pci_process_bridge_OF_ranges(phb, node, 0);
 		pci_setup_phb_io(phb, index == 0);
 		index++;
@@ -381,7 +365,6 @@ int pcibios_remove_root_bus(struct pci_controller *phb)
 		}
 	}
 
-	list_del(&phb->list_node);
 	pcibios_free_controller(phb);
 
 	return 0;
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index a4c2964a3ca6..61c65d19ef06 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -63,10 +63,6 @@ unsigned int DMA_MODE_WRITE;
 
 int have_of = 1;
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
-dev_t boot_dev;
-#endif /* CONFIG_PPC_MULTIPLATFORM */
-
 #ifdef CONFIG_VGA_CONSOLE
 unsigned long vgacon_remap_base;
 #endif
@@ -101,7 +97,7 @@ unsigned long __init early_init(unsigned long dt_ptr)
 	 * Identify the CPU type and fix up code sections
 	 * that depend on which cpu we have.
 	 */
-	spec = identify_cpu(offset);
+	spec = identify_cpu(offset, mfspr(SPRN_PVR));
 
 	do_feature_fixups(spec->cpu_features,
 			  PTRRELOC(&__start___ftr_fixup),
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 16278968dab6..3733de30e84d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -33,6 +33,7 @@
 #include <linux/serial.h>
 #include <linux/serial_8250.h>
 #include <linux/bootmem.h>
+#include <linux/pci.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -71,7 +72,6 @@
 
 int have_of = 1;
 int boot_cpuid = 0;
-dev_t boot_dev;
 u64 ppc64_pft_size;
 
 /* Pick defaults since we might want to patch instructions
@@ -171,7 +171,7 @@ void __init setup_paca(int cpu)
 void __init early_setup(unsigned long dt_ptr)
 {
 	/* Identify CPU type */
-	identify_cpu(0);
+	identify_cpu(0, mfspr(SPRN_PVR));
 
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
 	setup_paca(0);
@@ -226,8 +226,8 @@ void early_setup_secondary(void)
 {
 	struct paca_struct *lpaca = get_paca();
 
-	/* Mark enabled in PACA */
-	lpaca->proc_enabled = 0;
+	/* Mark interrupts enabled in PACA */
+	lpaca->soft_enabled = 0;
 
 	/* Initialize hash table for that CPU */
 	htab_initialize_secondary();
@@ -392,7 +392,8 @@ void __init setup_system(void)
 	 * setting up the hash table pointers. It also sets up some interrupt-mapping
 	 * related options that will be used by finish_device_tree()
 	 */
-	ppc_md.init_early();
+	if (ppc_md.init_early)
+		ppc_md.init_early();
 
  	/*
 	 * We can discover serial ports now since the above did setup the
@@ -598,3 +599,10 @@ void __init setup_per_cpu_areas(void)
 	}
 }
 #endif
+
+
+#ifdef CONFIG_PPC_INDIRECT_IO
+struct ppc_pci_io ppc_pci_io;
+EXPORT_SYMBOL(ppc_pci_io);
+#endif /* CONFIG_PPC_INDIRECT_IO */
+
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
index de59c6c31a5b..bc892e69b4f7 100644
--- a/arch/powerpc/kernel/smp-tbsync.c
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -78,7 +78,7 @@ static int __devinit start_contest(int cmd, long offset, int num)
 {
 	int i, score=0;
 	u64 tb;
-	long mark;
+	u64 mark;
 
 	tbsync->cmd = cmd;
 
@@ -116,8 +116,7 @@ void __devinit smp_generic_give_timebase(void)
 	printk("Synchronizing timebase\n");
 
 	/* if this fails then this kernel won't work anyway... */
-	tbsync = kmalloc( sizeof(*tbsync), GFP_KERNEL );
-	memset( tbsync, 0, sizeof(*tbsync) );
+	tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL );
 	mb();
 	running = 1;
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 35c6309bdb76..9b28c238b6c0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -65,6 +65,7 @@ cpumask_t cpu_sibling_map[NR_CPUS] = { [0 ... NR_CPUS-1] = CPU_MASK_NONE };
 
 EXPORT_SYMBOL(cpu_online_map);
 EXPORT_SYMBOL(cpu_possible_map);
+EXPORT_SYMBOL(cpu_sibling_map);
 
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index d15c33e95959..03a2a2f30d66 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -51,6 +51,7 @@
 #include <asm/time.h>
 #include <asm/mmu_context.h>
 #include <asm/ppc-pci.h>
+#include <asm/syscalls.h>
 
 /* readdir & getdents */
 #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index d45a168bdaca..22123a0d5416 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -200,10 +200,9 @@ static void register_cpu_online(unsigned int cpu)
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
 	struct sys_device *s = &c->sysdev;
 
-#ifndef CONFIG_PPC_ISERIES
-	if (cpu_has_feature(CPU_FTR_SMT))
+	if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
+			cpu_has_feature(CPU_FTR_SMT))
 		sysdev_create_file(s, &attr_smt_snooze_delay);
-#endif
 
 	/* PMC stuff */
 
@@ -242,10 +241,9 @@ static void unregister_cpu_online(unsigned int cpu)
 
 	BUG_ON(c->no_control);
 
-#ifndef CONFIG_PPC_ISERIES
-	if (cpu_has_feature(CPU_FTR_SMT))
+	if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
+			cpu_has_feature(CPU_FTR_SMT))
 		sysdev_remove_file(s, &attr_smt_snooze_delay);
-#endif
 
 	/* PMC stuff */
 
@@ -299,6 +297,72 @@ static struct notifier_block __cpuinitdata sysfs_cpu_nb = {
 	.notifier_call	= sysfs_cpu_notify,
 };
 
+static DEFINE_MUTEX(cpu_mutex);
+
+int cpu_add_sysdev_attr(struct sysdev_attribute *attr)
+{
+	int cpu;
+
+	mutex_lock(&cpu_mutex);
+
+	for_each_possible_cpu(cpu) {
+		sysdev_create_file(get_cpu_sysdev(cpu), attr);
+	}
+
+	mutex_unlock(&cpu_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpu_add_sysdev_attr);
+
+int cpu_add_sysdev_attr_group(struct attribute_group *attrs)
+{
+	int cpu;
+	struct sys_device *sysdev;
+
+	mutex_lock(&cpu_mutex);
+
+	for_each_possible_cpu(cpu) {
+		sysdev = get_cpu_sysdev(cpu);
+		sysfs_create_group(&sysdev->kobj, attrs);
+	}
+
+	mutex_unlock(&cpu_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpu_add_sysdev_attr_group);
+
+
+void cpu_remove_sysdev_attr(struct sysdev_attribute *attr)
+{
+	int cpu;
+
+	mutex_lock(&cpu_mutex);
+
+	for_each_possible_cpu(cpu) {
+		sysdev_remove_file(get_cpu_sysdev(cpu), attr);
+	}
+
+	mutex_unlock(&cpu_mutex);
+}
+EXPORT_SYMBOL_GPL(cpu_remove_sysdev_attr);
+
+void cpu_remove_sysdev_attr_group(struct attribute_group *attrs)
+{
+	int cpu;
+	struct sys_device *sysdev;
+
+	mutex_lock(&cpu_mutex);
+
+	for_each_possible_cpu(cpu) {
+		sysdev = get_cpu_sysdev(cpu);
+		sysfs_remove_group(&sysdev->kobj, attrs);
+	}
+
+	mutex_unlock(&cpu_mutex);
+}
+EXPORT_SYMBOL_GPL(cpu_remove_sysdev_attr_group);
+
+
 /* NUMA stuff */
 
 #ifdef CONFIG_NUMA
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 46a24de36fec..f6f0c6b07c4c 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -631,7 +631,8 @@ void timer_interrupt(struct pt_regs * regs)
 	calculate_steal_time();
 
 #ifdef CONFIG_PPC_ISERIES
-	get_lppaca()->int_dword.fields.decr_int = 0;
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		get_lppaca()->int_dword.fields.decr_int = 0;
 #endif
 
 	while ((ticks = tb_ticks_since(per_cpu(last_jiffy, cpu)))
@@ -674,7 +675,7 @@ void timer_interrupt(struct pt_regs * regs)
 	set_dec(next_dec);
 
 #ifdef CONFIG_PPC_ISERIES
-	if (hvlpevent_is_pending())
+	if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
 		process_hvlpevents();
 #endif
 
@@ -774,7 +775,7 @@ int do_settimeofday(struct timespec *tv)
 	 * settimeofday to perform this operation.
 	 */
 #ifdef CONFIG_PPC_ISERIES
-	if (first_settimeofday) {
+	if (firmware_has_feature(FW_FEATURE_ISERIES) && first_settimeofday) {
 		iSeries_tb_recal();
 		first_settimeofday = 0;
 	}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c66b4771ef44..0d4e203fa7a0 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -53,10 +53,6 @@
 #endif
 #include <asm/kexec.h>
 
-#ifdef CONFIG_PPC64	/* XXX */
-#define _IO_BASE	pci_io_base
-#endif
-
 #ifdef CONFIG_DEBUGGER
 int (*__debugger)(struct pt_regs *regs);
 int (*__debugger_ipi)(struct pt_regs *regs);
@@ -241,7 +237,7 @@ void system_reset_exception(struct pt_regs *regs)
  */
 static inline int check_io_access(struct pt_regs *regs)
 {
-#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)
+#ifdef CONFIG_PPC32
 	unsigned long msr = regs->msr;
 	const struct exception_table_entry *entry;
 	unsigned int *nip = (unsigned int *)regs->nip;
@@ -274,7 +270,7 @@ static inline int check_io_access(struct pt_regs *regs)
 			return 1;
 		}
 	}
-#endif /* CONFIG_PPC_PMAC && CONFIG_PPC32 */
+#endif /* CONFIG_PPC32 */
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index ed007878d1bf..a80f8f1d2e5d 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -81,15 +81,15 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 		struct iommu_table *tbl;
 		unsigned long offset, size;
 
-		dma_window = get_property(dev->dev.platform_data,
-				"ibm,my-dma-window", NULL);
+		dma_window = get_property(dev->dev.archdata.of_node,
+					  "ibm,my-dma-window", NULL);
 		if (!dma_window)
 			return NULL;
 
 		tbl = kmalloc(sizeof(*tbl), GFP_KERNEL);
 
-		of_parse_dma_window(dev->dev.platform_data, dma_window,
-				&tbl->it_index, &offset, &size);
+		of_parse_dma_window(dev->dev.archdata.of_node, dma_window,
+				    &tbl->it_index, &offset, &size);
 
 		/* TCE table size - measured in tce entries */
 		tbl->it_size = size >> IOMMU_PAGE_SHIFT;
@@ -117,7 +117,8 @@ static const struct vio_device_id *vio_match_device(
 {
 	while (ids->type[0] != '\0') {
 		if ((strncmp(dev->type, ids->type, strlen(ids->type)) == 0) &&
-		    device_is_compatible(dev->dev.platform_data, ids->compat))
+		    device_is_compatible(dev->dev.archdata.of_node,
+					 ids->compat))
 			return ids;
 		ids++;
 	}
@@ -198,9 +199,9 @@ EXPORT_SYMBOL(vio_unregister_driver);
 /* vio_dev refcount hit 0 */
 static void __devinit vio_dev_release(struct device *dev)
 {
-	if (dev->platform_data) {
-		/* XXX free TCE table */
-		of_node_put(dev->platform_data);
+	if (dev->archdata.of_node) {
+		/* XXX should free TCE table */
+		of_node_put(dev->archdata.of_node);
 	}
 	kfree(to_vio_dev(dev));
 }
@@ -210,7 +211,7 @@ static void __devinit vio_dev_release(struct device *dev)
  * @of_node:	The OF node for this device.
  *
  * Creates and initializes a vio_dev structure from the data in
- * of_node (dev.platform_data) and adds it to the list of virtual devices.
+ * of_node and adds it to the list of virtual devices.
  * Returns a pointer to the created vio_dev or NULL if node has
  * NULL device_type or compatible fields.
  */
@@ -240,8 +241,6 @@ struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node)
 	if (viodev == NULL)
 		return NULL;
 
-	viodev->dev.platform_data = of_node_get(of_node);
-
 	viodev->irq = irq_of_parse_and_map(of_node, 0);
 
 	snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address);
@@ -254,7 +253,10 @@ struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node)
 		if (unit_address != NULL)
 			viodev->unit_address = *unit_address;
 	}
-	viodev->iommu_table = vio_build_iommu_table(viodev);
+	viodev->dev.archdata.of_node = of_node_get(of_node);
+	viodev->dev.archdata.dma_ops = &dma_iommu_ops;
+	viodev->dev.archdata.dma_data = vio_build_iommu_table(viodev);
+	viodev->dev.archdata.numa_node = of_node_to_nid(of_node);
 
 	/* init generic 'struct device' fields: */
 	viodev->dev.parent = &vio_bus_device.dev;
@@ -285,10 +287,11 @@ static int __init vio_bus_init(void)
 #ifdef CONFIG_PPC_ISERIES
 	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
 		iommu_vio_init();
-		vio_bus_device.iommu_table = &vio_iommu_table;
+		vio_bus_device.dev.archdata.dma_ops = &dma_iommu_ops;
+		vio_bus_device.dev.archdata.dma_data = &vio_iommu_table;
 		iSeries_vio_dev = &vio_bus_device.dev;
 	}
-#endif
+#endif /* CONFIG_PPC_ISERIES */
 
 	err = bus_register(&vio_bus_type);
 	if (err) {
@@ -336,7 +339,7 @@ static ssize_t name_show(struct device *dev,
 static ssize_t devspec_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct device_node *of_node = dev->platform_data;
+	struct device_node *of_node = dev->archdata.of_node;
 
 	return sprintf(buf, "%s\n", of_node ? of_node->full_name : "none");
 }
@@ -353,62 +356,6 @@ void __devinit vio_unregister_device(struct vio_dev *viodev)
 }
 EXPORT_SYMBOL(vio_unregister_device);
 
-static dma_addr_t vio_map_single(struct device *dev, void *vaddr,
-			  size_t size, enum dma_data_direction direction)
-{
-	return iommu_map_single(to_vio_dev(dev)->iommu_table, vaddr, size,
-			~0ul, direction);
-}
-
-static void vio_unmap_single(struct device *dev, dma_addr_t dma_handle,
-		      size_t size, enum dma_data_direction direction)
-{
-	iommu_unmap_single(to_vio_dev(dev)->iommu_table, dma_handle, size,
-			direction);
-}
-
-static int vio_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction)
-{
-	return iommu_map_sg(dev, to_vio_dev(dev)->iommu_table, sglist,
-			nelems, ~0ul, direction);
-}
-
-static void vio_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction)
-{
-	iommu_unmap_sg(to_vio_dev(dev)->iommu_table, sglist, nelems, direction);
-}
-
-static void *vio_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag)
-{
-	return iommu_alloc_coherent(to_vio_dev(dev)->iommu_table, size,
-			dma_handle, ~0ul, flag, -1);
-}
-
-static void vio_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle)
-{
-	iommu_free_coherent(to_vio_dev(dev)->iommu_table, size, vaddr,
-			dma_handle);
-}
-
-static int vio_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-struct dma_mapping_ops vio_dma_ops = {
-	.alloc_coherent = vio_alloc_coherent,
-	.free_coherent = vio_free_coherent,
-	.map_single = vio_map_single,
-	.unmap_single = vio_unmap_single,
-	.map_sg = vio_map_sg,
-	.unmap_sg = vio_unmap_sg,
-	.dma_supported = vio_dma_supported,
-};
-
 static int vio_bus_match(struct device *dev, struct device_driver *drv)
 {
 	const struct vio_dev *vio_dev = to_vio_dev(dev);
@@ -422,13 +369,14 @@ static int vio_hotplug(struct device *dev, char **envp, int num_envp,
 			char *buffer, int buffer_size)
 {
 	const struct vio_dev *vio_dev = to_vio_dev(dev);
-	struct device_node *dn = dev->platform_data;
+	struct device_node *dn;
 	const char *cp;
 	int length;
 
 	if (!num_envp)
 		return -ENOMEM;
 
+	dn = dev->archdata.of_node;
 	if (!dn)
 		return -ENODEV;
 	cp = get_property(dn, "compatible", &length);
@@ -465,7 +413,7 @@ struct bus_type vio_bus_type = {
 */
 const void *vio_get_attribute(struct vio_dev *vdev, char *which, int *length)
 {
-	return get_property(vdev->dev.platform_data, which, length);
+	return get_property(vdev->dev.archdata.of_node, which, length);
 }
 EXPORT_SYMBOL(vio_get_attribute);
 
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 93441e7a2921..38a81967ca07 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -8,7 +8,7 @@ endif
 
 obj-y				:= fault.o mem.o lmb.o
 obj-$(CONFIG_PPC32)		+= init_32.o pgtable_32.o mmu_context_32.o
-hash-$(CONFIG_PPC_MULTIPLATFORM) := hash_native_64.o
+hash-$(CONFIG_PPC_NATIVE)	:= hash_native_64.o
 obj-$(CONFIG_PPC64)		+= init_64.o pgtable_64.o mmu_context_64.o \
 				   hash_utils_64.o hash_low_64.o tlb_64.o \
 				   slb_low.o slb.o stab.o mmap.o imalloc.o \
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index e8fa50624b70..03aeb3a46077 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -426,18 +426,21 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 
 	/* kernel has accessed a bad area */
 
-	printk(KERN_ALERT "Unable to handle kernel paging request for ");
 	switch (regs->trap) {
-		case 0x300:
-		case 0x380:
-			printk("data at address 0x%08lx\n", regs->dar);
-			break;
-		case 0x400:
-		case 0x480:
-			printk("instruction fetch\n");
-			break;
-		default:
-			printk("unknown fault\n");
+	case 0x300:
+	case 0x380:
+		printk(KERN_ALERT "Unable to handle kernel paging request for "
+			"data at address 0x%08lx\n", regs->dar);
+		break;
+	case 0x400:
+	case 0x480:
+		printk(KERN_ALERT "Unable to handle kernel paging request for "
+			"instruction fetch\n");
+		break;
+	default:
+		printk(KERN_ALERT "Unable to handle kernel paging request for "
+			"unknown fault\n");
+		break;
 	}
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
 		regs->nip);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index c90f124f3c71..6f1016acdbf6 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -123,7 +123,7 @@ static inline void native_unlock_hpte(hpte_t *hptep)
 	clear_bit(HPTE_LOCK_BIT, word);
 }
 
-long native_hpte_insert(unsigned long hpte_group, unsigned long va,
+static long native_hpte_insert(unsigned long hpte_group, unsigned long va,
 			unsigned long pa, unsigned long rflags,
 			unsigned long vflags, int psize)
 {
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 1915661c2c81..c0d2a694fa30 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -277,7 +277,7 @@ static void __init htab_init_page_sizes(void)
 	 * Not in the device-tree, let's fallback on known size
 	 * list for 16M capable GP & GR
 	 */
-	if (cpu_has_feature(CPU_FTR_16M_PAGE) && !machine_is(iseries))
+	if (cpu_has_feature(CPU_FTR_16M_PAGE))
 		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
 		       sizeof(mmu_psize_defaults_gp));
  found:
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 3ff374697e34..9a178549cbcf 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -130,7 +130,7 @@ static int __init setup_kcore(void)
 		/* GFP_ATOMIC to avoid might_sleep warnings during boot */
 		kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC);
 		if (!kcore_mem)
-			panic("mem_init: kmalloc failed\n");
+			panic("%s: kmalloc failed\n", __FUNCTION__);
 
 		kclist_add(kcore_mem, __va(base), size);
 	}
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 8fcacb0239da..1891dbeeb8e9 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -141,29 +141,19 @@ void pte_free(struct page *ptepage)
 	__free_page(ptepage);
 }
 
-#ifndef CONFIG_PHYS_64BIT
 void __iomem *
 ioremap(phys_addr_t addr, unsigned long size)
 {
 	return __ioremap(addr, size, _PAGE_NO_CACHE);
 }
-#else /* CONFIG_PHYS_64BIT */
-void __iomem *
-ioremap64(unsigned long long addr, unsigned long size)
-{
-	return __ioremap(addr, size, _PAGE_NO_CACHE);
-}
-EXPORT_SYMBOL(ioremap64);
+EXPORT_SYMBOL(ioremap);
 
 void __iomem *
-ioremap(phys_addr_t addr, unsigned long size)
+ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
 {
-	phys_addr_t addr64 = fixup_bigphys_addr(addr, size);
-
-	return ioremap64(addr64, size);
+	return __ioremap(addr, size, flags);
 }
-#endif /* CONFIG_PHYS_64BIT */
-EXPORT_SYMBOL(ioremap);
+EXPORT_SYMBOL(ioremap_flags);
 
 void __iomem *
 __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
@@ -264,20 +254,7 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
-void __iomem *ioport_map(unsigned long port, unsigned int len)
-{
-	return (void __iomem *) (port + _IO_BASE);
-}
-
-void ioport_unmap(void __iomem *addr)
-{
-	/* Nothing to do */
-}
-EXPORT_SYMBOL(ioport_map);
-EXPORT_SYMBOL(ioport_unmap);
-
-int
-map_page(unsigned long va, phys_addr_t pa, int flags)
+int map_page(unsigned long va, phys_addr_t pa, int flags)
 {
 	pmd_t *pd;
 	pte_t *pg;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index ac64f4aaa509..16e4ee1c2318 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -113,7 +113,7 @@ static int map_io_page(unsigned long ea, unsigned long pa, int flags)
 }
 
 
-static void __iomem * __ioremap_com(unsigned long addr, unsigned long pa,
+static void __iomem * __ioremap_com(phys_addr_t addr, unsigned long pa,
 			    unsigned long ea, unsigned long size,
 			    unsigned long flags)
 {
@@ -129,22 +129,12 @@ static void __iomem * __ioremap_com(unsigned long addr, unsigned long pa,
 	return (void __iomem *) (ea + (addr & ~PAGE_MASK));
 }
 
-
-void __iomem *
-ioremap(unsigned long addr, unsigned long size)
-{
-	return __ioremap(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED);
-}
-
-void __iomem * __ioremap(unsigned long addr, unsigned long size,
+void __iomem * __ioremap(phys_addr_t addr, unsigned long size,
 			 unsigned long flags)
 {
 	unsigned long pa, ea;
 	void __iomem *ret;
 
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		return (void __iomem *)addr;
-
 	/*
 	 * Choose an address to map it to.
 	 * Once the imalloc system is running, we use it.
@@ -178,9 +168,28 @@ void __iomem * __ioremap(unsigned long addr, unsigned long size,
 	return ret;
 }
 
+
+void __iomem * ioremap(phys_addr_t addr, unsigned long size)
+{
+	unsigned long flags = _PAGE_NO_CACHE | _PAGE_GUARDED;
+
+	if (ppc_md.ioremap)
+		return ppc_md.ioremap(addr, size, flags);
+	return __ioremap(addr, size, flags);
+}
+
+void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size,
+			     unsigned long flags)
+{
+	if (ppc_md.ioremap)
+		return ppc_md.ioremap(addr, size, flags);
+	return __ioremap(addr, size, flags);
+}
+
+
 #define IS_PAGE_ALIGNED(_val) ((_val) == ((_val) & PAGE_MASK))
 
-int __ioremap_explicit(unsigned long pa, unsigned long ea,
+int __ioremap_explicit(phys_addr_t pa, unsigned long ea,
 		       unsigned long size, unsigned long flags)
 {
 	struct vm_struct *area;
@@ -235,13 +244,10 @@ int __ioremap_explicit(unsigned long pa, unsigned long ea,
  *
  * XXX	what about calls before mem_init_done (ie python_countermeasures())
  */
-void iounmap(volatile void __iomem *token)
+void __iounmap(volatile void __iomem *token)
 {
 	void *addr;
 
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		return;
-
 	if (!mem_init_done)
 		return;
 	
@@ -250,6 +256,14 @@ void iounmap(volatile void __iomem *token)
 	im_free(addr);
 }
 
+void iounmap(volatile void __iomem *token)
+{
+	if (ppc_md.iounmap)
+		ppc_md.iounmap(token);
+	else
+		__iounmap(token);
+}
+
 static int iounmap_subset_regions(unsigned long addr, unsigned long size)
 {
 	struct vm_struct *area;
@@ -268,7 +282,7 @@ static int iounmap_subset_regions(unsigned long addr, unsigned long size)
 	return 0;
 }
 
-int iounmap_explicit(volatile void __iomem *start, unsigned long size)
+int __iounmap_explicit(volatile void __iomem *start, unsigned long size)
 {
 	struct vm_struct *area;
 	unsigned long addr;
@@ -303,8 +317,10 @@ int iounmap_explicit(volatile void __iomem *start, unsigned long size)
 }
 
 EXPORT_SYMBOL(ioremap);
+EXPORT_SYMBOL(ioremap_flags);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(iounmap);
+EXPORT_SYMBOL(__iounmap);
 
 void __iomem * reserve_phb_iospace(unsigned long size)
 {
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index d3733912adb4..224e960650a0 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -23,6 +23,7 @@
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
+#include <asm/firmware.h>
 #include <linux/compiler.h>
 
 #ifdef DEBUG
@@ -193,6 +194,7 @@ static inline void patch_slb_encoding(unsigned int *insn_addr,
 void slb_initialize(void)
 {
 	unsigned long linear_llp, vmalloc_llp, io_llp;
+	unsigned long lflags, vflags;
 	static int slb_encoding_inited;
 	extern unsigned int *slb_miss_kernel_load_linear;
 	extern unsigned int *slb_miss_kernel_load_io;
@@ -225,11 +227,12 @@ void slb_initialize(void)
 #endif
 	}
 
+	get_paca()->stab_rr = SLB_NUM_BOLTED;
+
 	/* On iSeries the bolted entries have already been set up by
 	 * the hypervisor from the lparMap data in head.S */
-#ifndef CONFIG_PPC_ISERIES
- {
-	unsigned long lflags, vflags;
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		return;
 
 	lflags = SLB_VSID_KERNEL | linear_llp;
 	vflags = SLB_VSID_KERNEL | vmalloc_llp;
@@ -247,8 +250,4 @@ void slb_initialize(void)
 	 * elsewhere, we'll call _switch() which will bolt in the new
 	 * one. */
 	asm volatile("isync":::"memory");
- }
-#endif /* CONFIG_PPC_ISERIES */
-
-	get_paca()->stab_rr = SLB_NUM_BOLTED;
 }
diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile
index 0b5df9c96ae0..4ccef2d5530c 100644
--- a/arch/powerpc/oprofile/Makefile
+++ b/arch/powerpc/oprofile/Makefile
@@ -11,6 +11,7 @@ DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
 		timer_int.o )
 
 oprofile-y := $(DRIVER_OBJS) common.o backtrace.o
+oprofile-$(CONFIG_PPC_CELL_NATIVE) += op_model_cell.o
 oprofile-$(CONFIG_PPC64) += op_model_rs64.o op_model_power4.o
 oprofile-$(CONFIG_FSL_BOOKE) += op_model_fsl_booke.o
 oprofile-$(CONFIG_6xx) += op_model_7450.o
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index 63bbef3b63f1..b6d82390b6a6 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -69,7 +69,10 @@ static void op_powerpc_cpu_start(void *dummy)
 
 static int op_powerpc_start(void)
 {
-	on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
+	if (model->global_start)
+		model->global_start(ctr);
+	if (model->start)
+		on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
 	return 0;
 }
 
@@ -80,7 +83,10 @@ static inline void op_powerpc_cpu_stop(void *dummy)
 
 static void op_powerpc_stop(void)
 {
-	on_each_cpu(op_powerpc_cpu_stop, NULL, 0, 1);
+	if (model->stop)
+		on_each_cpu(op_powerpc_cpu_stop, NULL, 0, 1);
+        if (model->global_stop)
+                model->global_stop();
 }
 
 static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
@@ -141,6 +147,11 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 
 	switch (cur_cpu_spec->oprofile_type) {
 #ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_CELL_NATIVE
+		case PPC_OPROFILE_CELL:
+			model = &op_model_cell;
+			break;
+#endif
 		case PPC_OPROFILE_RS64:
 			model = &op_model_rs64;
 			break;
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
new file mode 100644
index 000000000000..2eb15f388103
--- /dev/null
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -0,0 +1,724 @@
+/*
+ * Cell Broadband Engine OProfile Support
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author: David Erb (djerb@us.ibm.com)
+ * Modifications:
+ *         Carl Love <carll@us.ibm.com>
+ *         Maynard Johnson <maynardj@us.ibm.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.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kthread.h>
+#include <linux/oprofile.h>
+#include <linux/percpu.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/timer.h>
+#include <asm/cell-pmu.h>
+#include <asm/cputable.h>
+#include <asm/firmware.h>
+#include <asm/io.h>
+#include <asm/oprofile_impl.h>
+#include <asm/processor.h>
+#include <asm/prom.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+#include <asm/rtas.h>
+#include <asm/system.h>
+
+#include "../platforms/cell/interrupt.h"
+
+#define PPU_CYCLES_EVENT_NUM 1	/*  event number for CYCLES */
+#define CBE_COUNT_ALL_CYCLES 0x42800000	/* PPU cycle event specifier */
+
+#define NUM_THREADS 2
+#define VIRT_CNTR_SW_TIME_NS 100000000	// 0.5 seconds
+
+struct pmc_cntrl_data {
+	unsigned long vcntr;
+	unsigned long evnts;
+	unsigned long masks;
+	unsigned long enabled;
+};
+
+/*
+ * ibm,cbe-perftools rtas parameters
+ */
+
+struct pm_signal {
+	u16 cpu;		/* Processor to modify */
+	u16 sub_unit;		/* hw subunit this applies to (if applicable) */
+	u16 signal_group;	/* Signal Group to Enable/Disable */
+	u8 bus_word;		/* Enable/Disable on this Trace/Trigger/Event
+				 * Bus Word(s) (bitmask)
+				 */
+	u8 bit;			/* Trigger/Event bit (if applicable) */
+};
+
+/*
+ * rtas call arguments
+ */
+enum {
+	SUBFUNC_RESET = 1,
+	SUBFUNC_ACTIVATE = 2,
+	SUBFUNC_DEACTIVATE = 3,
+
+	PASSTHRU_IGNORE = 0,
+	PASSTHRU_ENABLE = 1,
+	PASSTHRU_DISABLE = 2,
+};
+
+struct pm_cntrl {
+	u16 enable;
+	u16 stop_at_max;
+	u16 trace_mode;
+	u16 freeze;
+	u16 count_mode;
+};
+
+static struct {
+	u32 group_control;
+	u32 debug_bus_control;
+	struct pm_cntrl pm_cntrl;
+	u32 pm07_cntrl[NR_PHYS_CTRS];
+} pm_regs;
+
+
+#define GET_SUB_UNIT(x) ((x & 0x0000f000) >> 12)
+#define GET_BUS_WORD(x) ((x & 0x000000f0) >> 4)
+#define GET_BUS_TYPE(x) ((x & 0x00000300) >> 8)
+#define GET_POLARITY(x) ((x & 0x00000002) >> 1)
+#define GET_COUNT_CYCLES(x) (x & 0x00000001)
+#define GET_INPUT_CONTROL(x) ((x & 0x00000004) >> 2)
+
+
+static DEFINE_PER_CPU(unsigned long[NR_PHYS_CTRS], pmc_values);
+
+static struct pmc_cntrl_data pmc_cntrl[NUM_THREADS][NR_PHYS_CTRS];
+
+/* Interpetation of hdw_thread:
+ * 0 - even virtual cpus 0, 2, 4,...
+ * 1 - odd virtual cpus 1, 3, 5, ...
+ */
+static u32 hdw_thread;
+
+static u32 virt_cntr_inter_mask;
+static struct timer_list timer_virt_cntr;
+
+/* pm_signal needs to be global since it is initialized in
+ * cell_reg_setup at the time when the necessary information
+ * is available.
+ */
+static struct pm_signal pm_signal[NR_PHYS_CTRS];
+static int pm_rtas_token;
+
+static u32 reset_value[NR_PHYS_CTRS];
+static int num_counters;
+static int oprofile_running;
+static spinlock_t virt_cntr_lock = SPIN_LOCK_UNLOCKED;
+
+static u32 ctr_enabled;
+
+static unsigned char trace_bus[4];
+static unsigned char input_bus[2];
+
+/*
+ * Firmware interface functions
+ */
+static int
+rtas_ibm_cbe_perftools(int subfunc, int passthru,
+		       void *address, unsigned long length)
+{
+	u64 paddr = __pa(address);
+
+	return rtas_call(pm_rtas_token, 5, 1, NULL, subfunc, passthru,
+			 paddr >> 32, paddr & 0xffffffff, length);
+}
+
+static void pm_rtas_reset_signals(u32 node)
+{
+	int ret;
+	struct pm_signal pm_signal_local;
+
+	/*  The debug bus is being set to the passthru disable state.
+	 *  However, the FW still expects atleast one legal signal routing
+	 *  entry or it will return an error on the arguments.  If we don't
+	 *  supply a valid entry, we must ignore all return values.  Ignoring
+	 *  all return values means we might miss an error we should be
+	 *  concerned about.
+	 */
+
+	/*  fw expects physical cpu #. */
+	pm_signal_local.cpu = node;
+	pm_signal_local.signal_group = 21;
+	pm_signal_local.bus_word = 1;
+	pm_signal_local.sub_unit = 0;
+	pm_signal_local.bit = 0;
+
+	ret = rtas_ibm_cbe_perftools(SUBFUNC_RESET, PASSTHRU_DISABLE,
+				     &pm_signal_local,
+				     sizeof(struct pm_signal));
+
+	if (ret)
+		printk(KERN_WARNING "%s: rtas returned: %d\n",
+		       __FUNCTION__, ret);
+}
+
+static void pm_rtas_activate_signals(u32 node, u32 count)
+{
+	int ret;
+	int j;
+	struct pm_signal pm_signal_local[NR_PHYS_CTRS];
+
+	for (j = 0; j < count; j++) {
+		/* fw expects physical cpu # */
+		pm_signal_local[j].cpu = node;
+		pm_signal_local[j].signal_group = pm_signal[j].signal_group;
+		pm_signal_local[j].bus_word = pm_signal[j].bus_word;
+		pm_signal_local[j].sub_unit = pm_signal[j].sub_unit;
+		pm_signal_local[j].bit = pm_signal[j].bit;
+	}
+
+	ret = rtas_ibm_cbe_perftools(SUBFUNC_ACTIVATE, PASSTHRU_ENABLE,
+				     pm_signal_local,
+				     count * sizeof(struct pm_signal));
+
+	if (ret)
+		printk(KERN_WARNING "%s: rtas returned: %d\n",
+		       __FUNCTION__, ret);
+}
+
+/*
+ * PM Signal functions
+ */
+static void set_pm_event(u32 ctr, int event, u32 unit_mask)
+{
+	struct pm_signal *p;
+	u32 signal_bit;
+	u32 bus_word, bus_type, count_cycles, polarity, input_control;
+	int j, i;
+
+	if (event == PPU_CYCLES_EVENT_NUM) {
+		/* Special Event: Count all cpu cycles */
+		pm_regs.pm07_cntrl[ctr] = CBE_COUNT_ALL_CYCLES;
+		p = &(pm_signal[ctr]);
+		p->signal_group = 21;
+		p->bus_word = 1;
+		p->sub_unit = 0;
+		p->bit = 0;
+		goto out;
+	} else {
+		pm_regs.pm07_cntrl[ctr] = 0;
+	}
+
+	bus_word = GET_BUS_WORD(unit_mask);
+	bus_type = GET_BUS_TYPE(unit_mask);
+	count_cycles = GET_COUNT_CYCLES(unit_mask);
+	polarity = GET_POLARITY(unit_mask);
+	input_control = GET_INPUT_CONTROL(unit_mask);
+	signal_bit = (event % 100);
+
+	p = &(pm_signal[ctr]);
+
+	p->signal_group = event / 100;
+	p->bus_word = bus_word;
+	p->sub_unit = unit_mask & 0x0000f000;
+
+	pm_regs.pm07_cntrl[ctr] = 0;
+	pm_regs.pm07_cntrl[ctr] |= PM07_CTR_COUNT_CYCLES(count_cycles);
+	pm_regs.pm07_cntrl[ctr] |= PM07_CTR_POLARITY(polarity);
+	pm_regs.pm07_cntrl[ctr] |= PM07_CTR_INPUT_CONTROL(input_control);
+
+	if (input_control == 0) {
+		if (signal_bit > 31) {
+			signal_bit -= 32;
+			if (bus_word == 0x3)
+				bus_word = 0x2;
+			else if (bus_word == 0xc)
+				bus_word = 0x8;
+		}
+
+		if ((bus_type == 0) && p->signal_group >= 60)
+			bus_type = 2;
+		if ((bus_type == 1) && p->signal_group >= 50)
+			bus_type = 0;
+
+		pm_regs.pm07_cntrl[ctr] |= PM07_CTR_INPUT_MUX(signal_bit);
+	} else {
+		pm_regs.pm07_cntrl[ctr] = 0;
+		p->bit = signal_bit;
+	}
+
+	for (i = 0; i < 4; i++) {
+		if (bus_word & (1 << i)) {
+			pm_regs.debug_bus_control |=
+			    (bus_type << (31 - (2 * i) + 1));
+
+			for (j = 0; j < 2; j++) {
+				if (input_bus[j] == 0xff) {
+					input_bus[j] = i;
+					pm_regs.group_control |=
+					    (i << (31 - i));
+					break;
+				}
+			}
+		}
+	}
+out:
+	;
+}
+
+static void write_pm_cntrl(int cpu, struct pm_cntrl *pm_cntrl)
+{
+	/* Oprofile will use 32 bit counters, set bits 7:10 to 0 */
+	u32 val = 0;
+	if (pm_cntrl->enable == 1)
+		val |= CBE_PM_ENABLE_PERF_MON;
+
+	if (pm_cntrl->stop_at_max == 1)
+		val |= CBE_PM_STOP_AT_MAX;
+
+	if (pm_cntrl->trace_mode == 1)
+		val |= CBE_PM_TRACE_MODE_SET(pm_cntrl->trace_mode);
+
+	if (pm_cntrl->freeze == 1)
+		val |= CBE_PM_FREEZE_ALL_CTRS;
+
+	/* Routine set_count_mode must be called previously to set
+	 * the count mode based on the user selection of user and kernel.
+	 */
+	val |= CBE_PM_COUNT_MODE_SET(pm_cntrl->count_mode);
+	cbe_write_pm(cpu, pm_control, val);
+}
+
+static inline void
+set_count_mode(u32 kernel, u32 user, struct pm_cntrl *pm_cntrl)
+{
+	/* The user must specify user and kernel if they want them. If
+	 *  neither is specified, OProfile will count in hypervisor mode
+	 */
+	if (kernel) {
+		if (user)
+			pm_cntrl->count_mode = CBE_COUNT_ALL_MODES;
+		else
+			pm_cntrl->count_mode = CBE_COUNT_SUPERVISOR_MODE;
+	} else {
+		if (user)
+			pm_cntrl->count_mode = CBE_COUNT_PROBLEM_MODE;
+		else
+			pm_cntrl->count_mode = CBE_COUNT_HYPERVISOR_MODE;
+	}
+}
+
+static inline void enable_ctr(u32 cpu, u32 ctr, u32 * pm07_cntrl)
+{
+
+	pm07_cntrl[ctr] |= PM07_CTR_ENABLE(1);
+	cbe_write_pm07_control(cpu, ctr, pm07_cntrl[ctr]);
+}
+
+/*
+ * Oprofile is expected to collect data on all CPUs simultaneously.
+ * However, there is one set of performance counters per node.  There are
+ * two hardware threads or virtual CPUs on each node.  Hence, OProfile must
+ * multiplex in time the performance counter collection on the two virtual
+ * CPUs.  The multiplexing of the performance counters is done by this
+ * virtual counter routine.
+ *
+ * The pmc_values used below is defined as 'per-cpu' but its use is
+ * more akin to 'per-node'.  We need to store two sets of counter
+ * values per node -- one for the previous run and one for the next.
+ * The per-cpu[NR_PHYS_CTRS] gives us the storage we need.  Each odd/even
+ * pair of per-cpu arrays is used for storing the previous and next
+ * pmc values for a given node.
+ * NOTE: We use the per-cpu variable to improve cache performance.
+ */
+static void cell_virtual_cntr(unsigned long data)
+{
+	/* This routine will alternate loading the virtual counters for
+	 * virtual CPUs
+	 */
+	int i, prev_hdw_thread, next_hdw_thread;
+	u32 cpu;
+	unsigned long flags;
+
+	/* Make sure that the interrupt_hander and
+	 * the virt counter are not both playing with
+	 * the counters on the same node.
+	 */
+
+	spin_lock_irqsave(&virt_cntr_lock, flags);
+
+	prev_hdw_thread = hdw_thread;
+
+	/* switch the cpu handling the interrupts */
+	hdw_thread = 1 ^ hdw_thread;
+	next_hdw_thread = hdw_thread;
+
+	/* The following is done only once per each node, but
+	 * we need cpu #, not node #, to pass to the cbe_xxx functions.
+	 */
+	for_each_online_cpu(cpu) {
+		if (cbe_get_hw_thread_id(cpu))
+			continue;
+
+		/* stop counters, save counter values, restore counts
+		 * for previous thread
+		 */
+		cbe_disable_pm(cpu);
+		cbe_disable_pm_interrupts(cpu);
+		for (i = 0; i < num_counters; i++) {
+			per_cpu(pmc_values, cpu + prev_hdw_thread)[i]
+			    = cbe_read_ctr(cpu, i);
+
+			if (per_cpu(pmc_values, cpu + next_hdw_thread)[i]
+			    == 0xFFFFFFFF)
+				/* If the cntr value is 0xffffffff, we must
+				 * reset that to 0xfffffff0 when the current
+				 * thread is restarted.  This will generate a new
+				 * interrupt and make sure that we never restore
+				 * the counters to the max value.  If the counters
+				 * were restored to the max value, they do not
+				 * increment and no interrupts are generated.  Hence
+				 * no more samples will be collected on that cpu.
+				 */
+				cbe_write_ctr(cpu, i, 0xFFFFFFF0);
+			else
+				cbe_write_ctr(cpu, i,
+					      per_cpu(pmc_values,
+						      cpu +
+						      next_hdw_thread)[i]);
+		}
+
+		/* Switch to the other thread. Change the interrupt
+		 * and control regs to be scheduled on the CPU
+		 * corresponding to the thread to execute.
+		 */
+		for (i = 0; i < num_counters; i++) {
+			if (pmc_cntrl[next_hdw_thread][i].enabled) {
+				/* There are some per thread events.
+				 * Must do the set event, enable_cntr
+				 * for each cpu.
+				 */
+				set_pm_event(i,
+				     pmc_cntrl[next_hdw_thread][i].evnts,
+				     pmc_cntrl[next_hdw_thread][i].masks);
+				enable_ctr(cpu, i,
+					   pm_regs.pm07_cntrl);
+			} else {
+				cbe_write_pm07_control(cpu, i, 0);
+			}
+		}
+
+		/* Enable interrupts on the CPU thread that is starting */
+		cbe_enable_pm_interrupts(cpu, next_hdw_thread,
+					 virt_cntr_inter_mask);
+		cbe_enable_pm(cpu);
+	}
+
+	spin_unlock_irqrestore(&virt_cntr_lock, flags);
+
+	mod_timer(&timer_virt_cntr, jiffies + HZ / 10);
+}
+
+static void start_virt_cntrs(void)
+{
+	init_timer(&timer_virt_cntr);
+	timer_virt_cntr.function = cell_virtual_cntr;
+	timer_virt_cntr.data = 0UL;
+	timer_virt_cntr.expires = jiffies + HZ / 10;
+	add_timer(&timer_virt_cntr);
+}
+
+/* This function is called once for all cpus combined */
+static void
+cell_reg_setup(struct op_counter_config *ctr,
+	       struct op_system_config *sys, int num_ctrs)
+{
+	int i, j, cpu;
+
+	pm_rtas_token = rtas_token("ibm,cbe-perftools");
+	if (pm_rtas_token == RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_WARNING "%s: RTAS_UNKNOWN_SERVICE\n",
+		       __FUNCTION__);
+		goto out;
+	}
+
+	num_counters = num_ctrs;
+
+	pm_regs.group_control = 0;
+	pm_regs.debug_bus_control = 0;
+
+	/* setup the pm_control register */
+	memset(&pm_regs.pm_cntrl, 0, sizeof(struct pm_cntrl));
+	pm_regs.pm_cntrl.stop_at_max = 1;
+	pm_regs.pm_cntrl.trace_mode = 0;
+	pm_regs.pm_cntrl.freeze = 1;
+
+	set_count_mode(sys->enable_kernel, sys->enable_user,
+		       &pm_regs.pm_cntrl);
+
+	/* Setup the thread 0 events */
+	for (i = 0; i < num_ctrs; ++i) {
+
+		pmc_cntrl[0][i].evnts = ctr[i].event;
+		pmc_cntrl[0][i].masks = ctr[i].unit_mask;
+		pmc_cntrl[0][i].enabled = ctr[i].enabled;
+		pmc_cntrl[0][i].vcntr = i;
+
+		for_each_possible_cpu(j)
+			per_cpu(pmc_values, j)[i] = 0;
+	}
+
+	/* Setup the thread 1 events, map the thread 0 event to the
+	 * equivalent thread 1 event.
+	 */
+	for (i = 0; i < num_ctrs; ++i) {
+		if ((ctr[i].event >= 2100) && (ctr[i].event <= 2111))
+			pmc_cntrl[1][i].evnts = ctr[i].event + 19;
+		else if (ctr[i].event == 2203)
+			pmc_cntrl[1][i].evnts = ctr[i].event;
+		else if ((ctr[i].event >= 2200) && (ctr[i].event <= 2215))
+			pmc_cntrl[1][i].evnts = ctr[i].event + 16;
+		else
+			pmc_cntrl[1][i].evnts = ctr[i].event;
+
+		pmc_cntrl[1][i].masks = ctr[i].unit_mask;
+		pmc_cntrl[1][i].enabled = ctr[i].enabled;
+		pmc_cntrl[1][i].vcntr = i;
+	}
+
+	for (i = 0; i < 4; i++)
+		trace_bus[i] = 0xff;
+
+	for (i = 0; i < 2; i++)
+		input_bus[i] = 0xff;
+
+	/* Our counters count up, and "count" refers to
+	 * how much before the next interrupt, and we interrupt
+	 * on overflow.  So we calculate the starting value
+	 * which will give us "count" until overflow.
+	 * Then we set the events on the enabled counters.
+	 */
+	for (i = 0; i < num_counters; ++i) {
+		/* start with virtual counter set 0 */
+		if (pmc_cntrl[0][i].enabled) {
+			/* Using 32bit counters, reset max - count */
+			reset_value[i] = 0xFFFFFFFF - ctr[i].count;
+			set_pm_event(i,
+				     pmc_cntrl[0][i].evnts,
+				     pmc_cntrl[0][i].masks);
+
+			/* global, used by cell_cpu_setup */
+			ctr_enabled |= (1 << i);
+		}
+	}
+
+	/* initialize the previous counts for the virtual cntrs */
+	for_each_online_cpu(cpu)
+		for (i = 0; i < num_counters; ++i) {
+			per_cpu(pmc_values, cpu)[i] = reset_value[i];
+		}
+out:
+	;
+}
+
+/* This function is called once for each cpu */
+static void cell_cpu_setup(struct op_counter_config *cntr)
+{
+	u32 cpu = smp_processor_id();
+	u32 num_enabled = 0;
+	int i;
+
+	/* There is one performance monitor per processor chip (i.e. node),
+	 * so we only need to perform this function once per node.
+	 */
+	if (cbe_get_hw_thread_id(cpu))
+		goto out;
+
+	if (pm_rtas_token == RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_WARNING "%s: RTAS_UNKNOWN_SERVICE\n",
+		       __FUNCTION__);
+		goto out;
+	}
+
+	/* Stop all counters */
+	cbe_disable_pm(cpu);
+	cbe_disable_pm_interrupts(cpu);
+
+	cbe_write_pm(cpu, pm_interval, 0);
+	cbe_write_pm(cpu, pm_start_stop, 0);
+	cbe_write_pm(cpu, group_control, pm_regs.group_control);
+	cbe_write_pm(cpu, debug_bus_control, pm_regs.debug_bus_control);
+	write_pm_cntrl(cpu, &pm_regs.pm_cntrl);
+
+	for (i = 0; i < num_counters; ++i) {
+		if (ctr_enabled & (1 << i)) {
+			pm_signal[num_enabled].cpu = cbe_cpu_to_node(cpu);
+			num_enabled++;
+		}
+	}
+
+	pm_rtas_activate_signals(cbe_cpu_to_node(cpu), num_enabled);
+out:
+	;
+}
+
+static void cell_global_start(struct op_counter_config *ctr)
+{
+	u32 cpu;
+	u32 interrupt_mask = 0;
+	u32 i;
+
+	/* This routine gets called once for the system.
+	 * There is one performance monitor per node, so we
+	 * only need to perform this function once per node.
+	 */
+	for_each_online_cpu(cpu) {
+		if (cbe_get_hw_thread_id(cpu))
+			continue;
+
+		interrupt_mask = 0;
+
+		for (i = 0; i < num_counters; ++i) {
+			if (ctr_enabled & (1 << i)) {
+				cbe_write_ctr(cpu, i, reset_value[i]);
+				enable_ctr(cpu, i, pm_regs.pm07_cntrl);
+				interrupt_mask |=
+				    CBE_PM_CTR_OVERFLOW_INTR(i);
+			} else {
+				/* Disable counter */
+				cbe_write_pm07_control(cpu, i, 0);
+			}
+		}
+
+		cbe_clear_pm_interrupts(cpu);
+		cbe_enable_pm_interrupts(cpu, hdw_thread, interrupt_mask);
+		cbe_enable_pm(cpu);
+	}
+
+	virt_cntr_inter_mask = interrupt_mask;
+	oprofile_running = 1;
+	smp_wmb();
+
+	/* NOTE: start_virt_cntrs will result in cell_virtual_cntr() being
+	 * executed which manipulates the PMU.  We start the "virtual counter"
+	 * here so that we do not need to synchronize access to the PMU in
+	 * the above for-loop.
+	 */
+	start_virt_cntrs();
+}
+
+static void cell_global_stop(void)
+{
+	int cpu;
+
+	/* This routine will be called once for the system.
+	 * There is one performance monitor per node, so we
+	 * only need to perform this function once per node.
+	 */
+	del_timer_sync(&timer_virt_cntr);
+	oprofile_running = 0;
+	smp_wmb();
+
+	for_each_online_cpu(cpu) {
+		if (cbe_get_hw_thread_id(cpu))
+			continue;
+
+		cbe_sync_irq(cbe_cpu_to_node(cpu));
+		/* Stop the counters */
+		cbe_disable_pm(cpu);
+
+		/* Deactivate the signals */
+		pm_rtas_reset_signals(cbe_cpu_to_node(cpu));
+
+		/* Deactivate interrupts */
+		cbe_disable_pm_interrupts(cpu);
+	}
+}
+
+static void
+cell_handle_interrupt(struct pt_regs *regs, struct op_counter_config *ctr)
+{
+	u32 cpu;
+	u64 pc;
+	int is_kernel;
+	unsigned long flags = 0;
+	u32 interrupt_mask;
+	int i;
+
+	cpu = smp_processor_id();
+
+	/* Need to make sure the interrupt handler and the virt counter
+	 * routine are not running at the same time. See the
+	 * cell_virtual_cntr() routine for additional comments.
+	 */
+	spin_lock_irqsave(&virt_cntr_lock, flags);
+
+	/* Need to disable and reenable the performance counters
+	 * to get the desired behavior from the hardware.  This
+	 * is hardware specific.
+	 */
+
+	cbe_disable_pm(cpu);
+
+	interrupt_mask = cbe_clear_pm_interrupts(cpu);
+
+	/* If the interrupt mask has been cleared, then the virt cntr
+	 * has cleared the interrupt.  When the thread that generated
+	 * the interrupt is restored, the data count will be restored to
+	 * 0xffffff0 to cause the interrupt to be regenerated.
+	 */
+
+	if ((oprofile_running == 1) && (interrupt_mask != 0)) {
+		pc = regs->nip;
+		is_kernel = is_kernel_addr(pc);
+
+		for (i = 0; i < num_counters; ++i) {
+			if ((interrupt_mask & CBE_PM_CTR_OVERFLOW_INTR(i))
+			    && ctr[i].enabled) {
+				oprofile_add_pc(pc, is_kernel, i);
+				cbe_write_ctr(cpu, i, reset_value[i]);
+			}
+		}
+
+		/* The counters were frozen by the interrupt.
+		 * Reenable the interrupt and restart the counters.
+		 * If there was a race between the interrupt handler and
+		 * the virtual counter routine.  The virutal counter
+		 * routine may have cleared the interrupts.  Hence must
+		 * use the virt_cntr_inter_mask to re-enable the interrupts.
+		 */
+		cbe_enable_pm_interrupts(cpu, hdw_thread,
+					 virt_cntr_inter_mask);
+
+		/* The writes to the various performance counters only writes
+		 * to a latch.  The new values (interrupt setting bits, reset
+		 * counter value etc.) are not copied to the actual registers
+		 * until the performance monitor is enabled.  In order to get
+		 * this to work as desired, the permormance monitor needs to
+		 * be disabled while writting to the latches.  This is a
+		 * HW design issue.
+		 */
+		cbe_enable_pm(cpu);
+	}
+	spin_unlock_irqrestore(&virt_cntr_lock, flags);
+}
+
+struct op_powerpc_model op_model_cell = {
+	.reg_setup = cell_reg_setup,
+	.cpu_setup = cell_cpu_setup,
+	.global_start = cell_global_start,
+	.global_stop = cell_global_stop,
+	.handle_interrupt = cell_handle_interrupt,
+};
diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile
new file mode 100644
index 000000000000..a46184a0c750
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for 52xx based boards
+#
+ifeq ($(CONFIG_PPC_MERGE),y)
+obj-y				+= mpc52xx_pic.o mpc52xx_common.o
+endif
+
+obj-$(CONFIG_PPC_EFIKA)		+= efika-setup.o efika-pci.o
+obj-$(CONFIG_PPC_LITE5200)	+= lite5200.o
diff --git a/arch/powerpc/platforms/52xx/efika-pci.c b/arch/powerpc/platforms/52xx/efika-pci.c
new file mode 100644
index 000000000000..62e05b2a9227
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/efika-pci.c
@@ -0,0 +1,119 @@
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/sections.h>
+#include <asm/pci-bridge.h>
+#include <asm/rtas.h>
+
+#include "efika.h"
+
+#ifdef CONFIG_PCI
+/*
+ * Access functions for PCI config space using RTAS calls.
+ */
+static int rtas_read_config(struct pci_bus *bus, unsigned int devfn, int offset,
+			    int len, u32 * val)
+{
+	struct pci_controller *hose = bus->sysdata;
+	unsigned long addr = (offset & 0xff) | ((devfn & 0xff) << 8)
+	    | (((bus->number - hose->first_busno) & 0xff) << 16)
+	    | (hose->index << 24);
+	int ret = -1;
+	int rval;
+
+	rval = rtas_call(rtas_token("read-pci-config"), 2, 2, &ret, addr, len);
+	*val = ret;
+	return rval ? PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL;
+}
+
+static int rtas_write_config(struct pci_bus *bus, unsigned int devfn,
+			     int offset, int len, u32 val)
+{
+	struct pci_controller *hose = bus->sysdata;
+	unsigned long addr = (offset & 0xff) | ((devfn & 0xff) << 8)
+	    | (((bus->number - hose->first_busno) & 0xff) << 16)
+	    | (hose->index << 24);
+	int rval;
+
+	rval = rtas_call(rtas_token("write-pci-config"), 3, 1, NULL,
+			 addr, len, val);
+	return rval ? PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops rtas_pci_ops = {
+	rtas_read_config,
+	rtas_write_config
+};
+
+void __init efika_pcisetup(void)
+{
+	const int *bus_range;
+	int len;
+	struct pci_controller *hose;
+	struct device_node *root;
+	struct device_node *pcictrl;
+
+	root = of_find_node_by_path("/");
+	if (root == NULL) {
+		printk(KERN_WARNING EFIKA_PLATFORM_NAME
+		       ": Unable to find the root node\n");
+		return;
+	}
+
+	for (pcictrl = NULL;;) {
+		pcictrl = of_get_next_child(root, pcictrl);
+		if ((pcictrl == NULL) || (strcmp(pcictrl->name, "pci") == 0))
+			break;
+	}
+
+	of_node_put(root);
+
+	if (pcictrl == NULL) {
+		printk(KERN_WARNING EFIKA_PLATFORM_NAME
+		       ": Unable to find the PCI bridge node\n");
+		return;
+	}
+
+	bus_range = get_property(pcictrl, "bus-range", &len);
+	if (bus_range == NULL || len < 2 * sizeof(int)) {
+		printk(KERN_WARNING EFIKA_PLATFORM_NAME
+		       ": Can't get bus-range for %s\n", pcictrl->full_name);
+		return;
+	}
+
+	if (bus_range[1] == bus_range[0])
+		printk(KERN_INFO EFIKA_PLATFORM_NAME ": PCI bus %d",
+		       bus_range[0]);
+	else
+		printk(KERN_INFO EFIKA_PLATFORM_NAME ": PCI buses %d..%d",
+		       bus_range[0], bus_range[1]);
+	printk(" controlled by %s\n", pcictrl->full_name);
+	printk("\n");
+
+	hose = pcibios_alloc_controller();
+	if (!hose) {
+		printk(KERN_WARNING EFIKA_PLATFORM_NAME
+		       ": Can't allocate PCI controller structure for %s\n",
+		       pcictrl->full_name);
+		return;
+	}
+
+	hose->arch_data = of_node_get(pcictrl);
+	hose->first_busno = bus_range[0];
+	hose->last_busno = bus_range[1];
+	hose->ops = &rtas_pci_ops;
+
+	pci_process_bridge_OF_ranges(hose, pcictrl, 0);
+}
+
+#else
+void __init efika_pcisetup(void)
+{}
+#endif
diff --git a/arch/powerpc/platforms/52xx/efika-setup.c b/arch/powerpc/platforms/52xx/efika-setup.c
new file mode 100644
index 000000000000..110c980ed1e0
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/efika-setup.c
@@ -0,0 +1,150 @@
+/*
+ *
+ * Efika 5K2 platform setup
+ * Some code really inspired from the lite5200b platform.
+ * 
+ * Copyright (C) 2006 bplan GmbH
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/utsrelease.h>
+#include <linux/seq_file.h>
+#include <linux/root_dev.h>
+#include <linux/initrd.h>
+#include <linux/timer.h>
+#include <linux/pci.h>
+
+#include <asm/pgtable.h>
+#include <asm/prom.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/rtas.h>
+#include <asm/of_device.h>
+#include <asm/of_platform.h>
+#include <asm/mpc52xx.h>
+
+#include "efika.h"
+
+static void efika_show_cpuinfo(struct seq_file *m)
+{
+	struct device_node *root;
+	const char *revision = NULL;
+	const char *codegendescription = NULL;
+	const char *codegenvendor = NULL;
+
+	root = of_find_node_by_path("/");
+	if (root) {
+		revision = get_property(root, "revision", NULL);
+		codegendescription =
+		    get_property(root, "CODEGEN,description", NULL);
+		codegenvendor = get_property(root, "CODEGEN,vendor", NULL);
+
+		of_node_put(root);
+	}
+
+	if (codegendescription)
+		seq_printf(m, "machine\t\t: %s\n", codegendescription);
+	else
+		seq_printf(m, "machine\t\t: Efika\n");
+
+	if (revision)
+		seq_printf(m, "revision\t: %s\n", revision);
+
+	if (codegenvendor)
+		seq_printf(m, "vendor\t\t: %s\n", codegenvendor);
+
+	of_node_put(root);
+}
+
+static void __init efika_setup_arch(void)
+{
+	rtas_initialize();
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	initrd_below_start_ok = 1;
+
+	if (initrd_start)
+		ROOT_DEV = Root_RAM0;
+	else
+#endif
+		ROOT_DEV = Root_SDA2;	/* sda2 (sda1 is for the kernel) */
+
+	efika_pcisetup();
+
+	if (ppc_md.progress)
+		ppc_md.progress("Linux/PPC " UTS_RELEASE " runnung on Efika ;-)\n", 0x0);
+}
+
+static void __init efika_init(void)
+{
+	struct device_node *np;
+	struct device_node *cnp = NULL;
+	const u32 *base;
+
+	/* Find every child of the SOC node and add it to of_platform */
+	np = of_find_node_by_name(NULL, "builtin");
+	if (np) {
+		char name[BUS_ID_SIZE];
+		while ((cnp = of_get_next_child(np, cnp))) {
+			strcpy(name, cnp->name);
+
+			base = get_property(cnp, "reg", NULL);
+			if (base == NULL)
+				continue;
+
+			snprintf(name+strlen(name), BUS_ID_SIZE, "@%x", *base);
+			of_platform_device_create(cnp, name, NULL);
+
+			printk(KERN_INFO EFIKA_PLATFORM_NAME" : Added %s (type '%s' at '%s') to the known devices\n", name, cnp->type, cnp->full_name);
+		}
+	}
+
+	if (ppc_md.progress)
+		ppc_md.progress("  Have fun with your Efika!    ", 0x7777);
+}
+
+static int __init efika_probe(void)
+{
+	char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
+					  "model", NULL);
+
+	if (model == NULL)
+		return 0;
+	if (strcmp(model, "EFIKA5K2"))
+		return 0;
+
+	ISA_DMA_THRESHOLD = ~0L;
+	DMA_MODE_READ = 0x44;
+	DMA_MODE_WRITE = 0x48;
+
+	return 1;
+}
+
+define_machine(efika)
+{
+	.name = EFIKA_PLATFORM_NAME,
+	.probe = efika_probe,
+	.setup_arch = efika_setup_arch,
+	.init = efika_init,
+	.show_cpuinfo = efika_show_cpuinfo,
+	.init_IRQ = mpc52xx_init_irq,
+	.get_irq = mpc52xx_get_irq,
+	.restart = rtas_restart,
+	.power_off = rtas_power_off,
+	.halt = rtas_halt,
+	.set_rtc_time = rtas_set_rtc_time,
+	.get_rtc_time = rtas_get_rtc_time,
+	.progress = rtas_progress,
+	.get_boot_time = rtas_get_boot_time,
+	.calibrate_decr = generic_calibrate_decr,
+	.phys_mem_access_prot = pci_phys_mem_access_prot,
+};
diff --git a/arch/powerpc/platforms/52xx/efika.h b/arch/powerpc/platforms/52xx/efika.h
new file mode 100644
index 000000000000..2f060fd097d7
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/efika.h
@@ -0,0 +1,19 @@
+/*
+ * Efika 5K2 platform setup - Header file
+ *
+ * Copyright (C) 2006 bplan GmbH
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ */
+
+#ifndef __ARCH_POWERPC_EFIKA__
+#define __ARCH_POWERPC_EFIKA__
+
+#define EFIKA_PLATFORM_NAME "Efika"
+
+extern void __init efika_pcisetup(void);
+
+#endif
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
new file mode 100644
index 000000000000..a375c15b4315
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -0,0 +1,162 @@
+/*
+ * Freescale Lite5200 board support
+ *
+ * Written by: Grant Likely <grant.likely@secretlab.ca>
+ *
+ * Copyright (C) Secret Lab Technologies Ltd. 2006. All rights reserved.
+ * Copyright (C) Freescale Semicondutor, Inc. 2006. All rights reserved.
+ *
+ * Description:
+ * 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.
+ */
+
+#undef DEBUG
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/reboot.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/major.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/root_dev.h>
+#include <linux/initrd.h>
+
+#include <asm/system.h>
+#include <asm/atomic.h>
+#include <asm/time.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/ipic.h>
+#include <asm/bootinfo.h>
+#include <asm/irq.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <sysdev/fsl_soc.h>
+#include <asm/qe.h>
+#include <asm/qe_ic.h>
+#include <asm/of_platform.h>
+
+#include <asm/mpc52xx.h>
+
+/* ************************************************************************
+ *
+ * Setup the architecture
+ *
+ */
+
+static void __init
+lite52xx_setup_cpu(void)
+{
+	struct mpc52xx_gpio __iomem *gpio;
+	u32 port_config;
+
+	/* Map zones */
+	gpio = mpc52xx_find_and_map("mpc52xx-gpio");
+	if (!gpio) {
+		printk(KERN_ERR __FILE__ ": "
+			"Error while mapping GPIO register for port config. "
+			"Expect some abnormal behavior\n");
+		goto error;
+	}
+
+	/* Set port config */
+	port_config = in_be32(&gpio->port_config);
+
+	port_config &= ~0x00800000;	/* 48Mhz internal, pin is GPIO	*/
+
+	port_config &= ~0x00007000;	/* USB port : Differential mode	*/
+	port_config |=  0x00001000;	/*            USB 1 only	*/
+
+	port_config &= ~0x03000000;	/* ATA CS is on csb_4/5		*/
+	port_config |=  0x01000000;
+
+	pr_debug("port_config: old:%x new:%x\n",
+	         in_be32(&gpio->port_config), port_config);
+	out_be32(&gpio->port_config, port_config);
+
+	/* Unmap zone */
+error:
+	iounmap(gpio);
+}
+
+static void __init lite52xx_setup_arch(void)
+{
+	struct device_node *np;
+
+	if (ppc_md.progress)
+		ppc_md.progress("lite52xx_setup_arch()", 0);
+
+	np = of_find_node_by_type(NULL, "cpu");
+	if (np) {
+		unsigned int *fp =
+		    (int *)get_property(np, "clock-frequency", NULL);
+		if (fp != 0)
+			loops_per_jiffy = *fp / HZ;
+		else
+			loops_per_jiffy = 50000000 / HZ;
+		of_node_put(np);
+	}
+
+	/* CPU & Port mux setup */
+	mpc52xx_setup_cpu();	/* Generic */
+	lite52xx_setup_cpu();	/* Platorm specific */
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (initrd_start)
+		ROOT_DEV = Root_RAM0;
+	else
+#endif
+#ifdef  CONFIG_ROOT_NFS
+		ROOT_DEV = Root_NFS;
+#else
+		ROOT_DEV = Root_HDA1;
+#endif
+
+}
+
+void lite52xx_show_cpuinfo(struct seq_file *m)
+{
+	struct device_node* np = of_find_all_nodes(NULL);
+	const char *model = NULL;
+
+	if (np)
+		model = get_property(np, "model", NULL);
+
+	seq_printf(m, "vendor\t\t:	Freescale Semiconductor\n");
+	seq_printf(m, "machine\t\t:	%s\n", model ? model : "unknown");
+
+	of_node_put(np);
+}
+
+/*
+ * Called very early, MMU is off, device-tree isn't unflattened
+ */
+static int __init lite52xx_probe(void)
+{
+	unsigned long node = of_get_flat_dt_root();
+	const char *model = of_get_flat_dt_prop(node, "model", NULL);
+
+	if (!of_flat_dt_is_compatible(node, "lite52xx"))
+		return 0;
+	pr_debug("%s board w/ mpc52xx found\n", model ? model : "unknown");
+
+	return 1;
+}
+
+define_machine(lite52xx) {
+	.name 		= "lite52xx",
+	.probe 		= lite52xx_probe,
+	.setup_arch 	= lite52xx_setup_arch,
+	.init_IRQ 	= mpc52xx_init_irq,
+	.get_irq 	= mpc52xx_get_irq,
+	.show_cpuinfo	= lite52xx_show_cpuinfo,
+	.calibrate_decr	= generic_calibrate_decr,
+};
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
new file mode 100644
index 000000000000..8331ff457770
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -0,0 +1,126 @@
+/*
+ *
+ * Utility functions for the Freescale MPC52xx.
+ *
+ * Copyright (C) 2006 Sylvain Munaut <tnt@246tNt.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/of_platform.h>
+#include <asm/mpc52xx.h>
+
+
+void __iomem *
+mpc52xx_find_and_map(const char *compatible)
+{
+	struct device_node *ofn;
+	const u32 *regaddr_p;
+	u64 regaddr64, size64;
+
+	ofn = of_find_compatible_node(NULL, NULL, compatible);
+	if (!ofn)
+		return NULL;
+
+	regaddr_p = of_get_address(ofn, 0, &size64, NULL);
+	if (!regaddr_p) {
+		of_node_put(ofn);
+		return NULL;
+	}
+
+	regaddr64 = of_translate_address(ofn, regaddr_p);
+
+	of_node_put(ofn);
+
+	return ioremap((u32)regaddr64, (u32)size64);
+}
+EXPORT_SYMBOL(mpc52xx_find_and_map);
+
+
+/**
+ * 	mpc52xx_find_ipb_freq - Find the IPB bus frequency for a device
+ * 	@node:	device node
+ *
+ * 	Returns IPB bus frequency, or 0 if the bus frequency cannot be found.
+ */
+unsigned int
+mpc52xx_find_ipb_freq(struct device_node *node)
+{
+	struct device_node *np;
+	const unsigned int *p_ipb_freq = NULL;
+
+	of_node_get(node);
+	while (node) {
+		p_ipb_freq = get_property(node, "bus-frequency", NULL);
+		if (p_ipb_freq)
+			break;
+
+		np = of_get_parent(node);
+		of_node_put(node);
+		node = np;
+	}
+	if (node)
+		of_node_put(node);
+
+	return p_ipb_freq ? *p_ipb_freq : 0;
+}
+EXPORT_SYMBOL(mpc52xx_find_ipb_freq);
+
+
+void __init
+mpc52xx_setup_cpu(void)
+{
+	struct mpc52xx_cdm  __iomem *cdm;
+	struct mpc52xx_xlb  __iomem *xlb;
+
+	/* Map zones */
+	cdm = mpc52xx_find_and_map("mpc52xx-cdm");
+	xlb = mpc52xx_find_and_map("mpc52xx-xlb");
+
+	if (!cdm || !xlb) {
+		printk(KERN_ERR __FILE__ ": "
+			"Error while mapping CDM/XLB during mpc52xx_setup_cpu. "
+			"Expect some abnormal behavior\n");
+		goto unmap_regs;
+	}
+
+	/* Use internal 48 Mhz */
+	out_8(&cdm->ext_48mhz_en, 0x00);
+	out_8(&cdm->fd_enable, 0x01);
+	if (in_be32(&cdm->rstcfg) & 0x40)	/* Assumes 33Mhz clock */
+		out_be16(&cdm->fd_counters, 0x0001);
+	else
+		out_be16(&cdm->fd_counters, 0x5555);
+
+	/* Configure the XLB Arbiter priorities */
+	out_be32(&xlb->master_pri_enable, 0xff);
+	out_be32(&xlb->master_priority, 0x11111111);
+
+	/* Disable XLB pipelining */
+	/* (cfr errate 292. We could do this only just before ATA PIO
+	    transaction and re-enable it afterwards ...) */
+	out_be32(&xlb->config, in_be32(&xlb->config) | MPC52xx_XLB_CFG_PLDIS);
+
+	/* Unmap zones */
+unmap_regs:
+	if (cdm) iounmap(cdm);
+	if (xlb) iounmap(xlb);
+}
+
+static int __init
+mpc52xx_declare_of_platform_devices(void)
+{
+	/* Find every child of the SOC node and add it to of_platform */
+	return of_platform_bus_probe(NULL, NULL, NULL);
+}
+
+device_initcall(mpc52xx_declare_of_platform_devices);
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
new file mode 100644
index 000000000000..cd91a6c3aafa
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -0,0 +1,473 @@
+/*
+ *
+ * Programmable Interrupt Controller functions for the Freescale MPC52xx.
+ *
+ * Copyright (C) 2006 bplan GmbH
+ *
+ * Based on the code from the 2.4 kernel by
+ * Dale Farnsworth <dfarnsworth@mvista.com> and Kent Borg.
+ *
+ * Copyright (C) 2004 Sylvain Munaut <tnt@246tNt.com>
+ * Copyright (C) 2003 Montavista Software, Inc
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ */
+
+#undef DEBUG
+
+#include <linux/stddef.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/signal.h>
+#include <linux/stddef.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/hardirq.h>
+
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/irq.h>
+#include <asm/prom.h>
+#include <asm/mpc52xx.h>
+#include "mpc52xx_pic.h"
+
+/*
+ *
+*/
+
+static struct mpc52xx_intr __iomem *intr;
+static struct mpc52xx_sdma __iomem *sdma;
+static struct irq_host *mpc52xx_irqhost = NULL;
+
+static unsigned char mpc52xx_map_senses[4] = {
+	IRQ_TYPE_LEVEL_HIGH,
+	IRQ_TYPE_EDGE_RISING,
+	IRQ_TYPE_EDGE_FALLING,
+	IRQ_TYPE_LEVEL_LOW,
+};
+
+/*
+ *
+*/
+
+static inline void io_be_setbit(u32 __iomem *addr, int bitno)
+{
+	out_be32(addr, in_be32(addr) | (1 << bitno));
+}
+
+static inline void io_be_clrbit(u32 __iomem *addr, int bitno)
+{
+	out_be32(addr, in_be32(addr) & ~(1 << bitno));
+}
+
+/*
+ * IRQ[0-3] interrupt irq_chip
+*/
+
+static void mpc52xx_extirq_mask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_clrbit(&intr->ctrl, 11 - l2irq);
+}
+
+static void mpc52xx_extirq_unmask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_setbit(&intr->ctrl, 11 - l2irq);
+}
+
+static void mpc52xx_extirq_ack(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_setbit(&intr->ctrl, 27-l2irq);
+}
+
+static struct irq_chip mpc52xx_extirq_irqchip = {
+	.typename = " MPC52xx IRQ[0-3] ",
+	.mask = mpc52xx_extirq_mask,
+	.unmask = mpc52xx_extirq_unmask,
+	.ack = mpc52xx_extirq_ack,
+};
+
+/*
+ * Main interrupt irq_chip
+*/
+
+static void mpc52xx_main_mask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_setbit(&intr->main_mask, 15 - l2irq);
+}
+
+static void mpc52xx_main_unmask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_clrbit(&intr->main_mask, 15 - l2irq);
+}
+
+static struct irq_chip mpc52xx_main_irqchip = {
+	.typename = "MPC52xx Main",
+	.mask = mpc52xx_main_mask,
+	.mask_ack = mpc52xx_main_mask,
+	.unmask = mpc52xx_main_unmask,
+};
+
+/*
+ * Peripherals interrupt irq_chip
+*/
+
+static void mpc52xx_periph_mask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_setbit(&intr->per_mask, 31 - l2irq);
+}
+
+static void mpc52xx_periph_unmask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_clrbit(&intr->per_mask, 31 - l2irq);
+}
+
+static struct irq_chip mpc52xx_periph_irqchip = {
+	.typename = "MPC52xx Peripherals",
+	.mask = mpc52xx_periph_mask,
+	.mask_ack = mpc52xx_periph_mask,
+	.unmask = mpc52xx_periph_unmask,
+};
+
+/*
+ * SDMA interrupt irq_chip
+*/
+
+static void mpc52xx_sdma_mask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_setbit(&sdma->IntMask, l2irq);
+}
+
+static void mpc52xx_sdma_unmask(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	io_be_clrbit(&sdma->IntMask, l2irq);
+}
+
+static void mpc52xx_sdma_ack(unsigned int virq)
+{
+	int irq;
+	int l2irq;
+
+	irq = irq_map[virq].hwirq;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	pr_debug("%s: irq=%x. l2=%d\n", __func__, irq, l2irq);
+
+	out_be32(&sdma->IntPend, 1 << l2irq);
+}
+
+static struct irq_chip mpc52xx_sdma_irqchip = {
+	.typename = "MPC52xx SDMA",
+	.mask = mpc52xx_sdma_mask,
+	.unmask = mpc52xx_sdma_unmask,
+	.ack = mpc52xx_sdma_ack,
+};
+
+/*
+ * irq_host
+*/
+
+static int mpc52xx_irqhost_match(struct irq_host *h, struct device_node *node)
+{
+	pr_debug("%s: node=%p\n", __func__, node);
+	return mpc52xx_irqhost->host_data == node;
+}
+
+static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
+				 u32 * intspec, unsigned int intsize,
+				 irq_hw_number_t * out_hwirq,
+				 unsigned int *out_flags)
+{
+	int intrvect_l1;
+	int intrvect_l2;
+	int intrvect_type;
+	int intrvect_linux;
+
+	if (intsize != 3)
+		return -1;
+
+	intrvect_l1 = (int)intspec[0];
+	intrvect_l2 = (int)intspec[1];
+	intrvect_type = (int)intspec[2];
+
+	intrvect_linux =
+	    (intrvect_l1 << MPC52xx_IRQ_L1_OFFSET) & MPC52xx_IRQ_L1_MASK;
+	intrvect_linux |=
+	    (intrvect_l2 << MPC52xx_IRQ_L2_OFFSET) & MPC52xx_IRQ_L2_MASK;
+
+	pr_debug("return %x, l1=%d, l2=%d\n", intrvect_linux, intrvect_l1,
+		 intrvect_l2);
+
+	*out_hwirq = intrvect_linux;
+	*out_flags = mpc52xx_map_senses[intrvect_type];
+
+	return 0;
+}
+
+/*
+ * this function retrieves the correct IRQ type out
+ * of the MPC regs
+ * Only externals IRQs needs this
+*/
+static int mpc52xx_irqx_gettype(int irq)
+{
+	int type;
+	u32 ctrl_reg;
+
+	ctrl_reg = in_be32(&intr->ctrl);
+	type = (ctrl_reg >> (22 - irq * 2)) & 0x3;
+
+	return mpc52xx_map_senses[type];
+}
+
+static int mpc52xx_irqhost_map(struct irq_host *h, unsigned int virq,
+			       irq_hw_number_t irq)
+{
+	int l1irq;
+	int l2irq;
+	struct irq_chip *good_irqchip;
+	void *good_handle;
+	int type;
+
+	l1irq = (irq & MPC52xx_IRQ_L1_MASK) >> MPC52xx_IRQ_L1_OFFSET;
+	l2irq = (irq & MPC52xx_IRQ_L2_MASK) >> MPC52xx_IRQ_L2_OFFSET;
+
+	/*
+	 * Most of ours IRQs will be level low
+	 * Only external IRQs on some platform may be others
+	 */
+	type = IRQ_TYPE_LEVEL_LOW;
+
+	switch (l1irq) {
+	case MPC52xx_IRQ_L1_CRIT:
+		pr_debug("%s: Critical. l2=%x\n", __func__, l2irq);
+
+		BUG_ON(l2irq != 0);
+
+		type = mpc52xx_irqx_gettype(l2irq);
+		good_irqchip = &mpc52xx_extirq_irqchip;
+		break;
+
+	case MPC52xx_IRQ_L1_MAIN:
+		pr_debug("%s: Main IRQ[1-3] l2=%x\n", __func__, l2irq);
+
+		if ((l2irq >= 1) && (l2irq <= 3)) {
+			type = mpc52xx_irqx_gettype(l2irq);
+			good_irqchip = &mpc52xx_extirq_irqchip;
+		} else {
+			good_irqchip = &mpc52xx_main_irqchip;
+		}
+		break;
+
+	case MPC52xx_IRQ_L1_PERP:
+		pr_debug("%s: Peripherals. l2=%x\n", __func__, l2irq);
+		good_irqchip = &mpc52xx_periph_irqchip;
+		break;
+
+	case MPC52xx_IRQ_L1_SDMA:
+		pr_debug("%s: SDMA. l2=%x\n", __func__, l2irq);
+		good_irqchip = &mpc52xx_sdma_irqchip;
+		break;
+
+	default:
+		pr_debug("%s: Error, unknown L1 IRQ (0x%x)\n", __func__, l1irq);
+		printk(KERN_ERR "Unknow IRQ!\n");
+		return -EINVAL;
+	}
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_FALLING:
+	case IRQ_TYPE_EDGE_RISING:
+		good_handle = handle_edge_irq;
+		break;
+	default:
+		good_handle = handle_level_irq;
+	}
+
+	set_irq_chip_and_handler(virq, good_irqchip, good_handle);
+
+	pr_debug("%s: virq=%x, hw=%x. type=%x\n", __func__, virq,
+		 (int)irq, type);
+
+	return 0;
+}
+
+static struct irq_host_ops mpc52xx_irqhost_ops = {
+	.match = mpc52xx_irqhost_match,
+	.xlate = mpc52xx_irqhost_xlate,
+	.map = mpc52xx_irqhost_map,
+};
+
+/*
+ * init (public)
+*/
+
+void __init mpc52xx_init_irq(void)
+{
+	u32 intr_ctrl;
+	struct device_node *picnode;
+
+	/* Remap the necessary zones */
+	picnode = of_find_compatible_node(NULL, NULL, "mpc52xx-pic");
+
+	intr = mpc52xx_find_and_map("mpc52xx-pic");
+	if (!intr)
+		panic(__FILE__	": find_and_map failed on 'mpc52xx-pic'. "
+				"Check node !");
+
+	sdma = mpc52xx_find_and_map("mpc52xx-bestcomm");
+	if (!sdma)
+		panic(__FILE__	": find_and_map failed on 'mpc52xx-bestcomm'. "
+				"Check node !");
+
+	/* Disable all interrupt sources. */
+	out_be32(&sdma->IntPend, 0xffffffff);	/* 1 means clear pending */
+	out_be32(&sdma->IntMask, 0xffffffff);	/* 1 means disabled */
+	out_be32(&intr->per_mask, 0x7ffffc00);	/* 1 means disabled */
+	out_be32(&intr->main_mask, 0x00010fff);	/* 1 means disabled */
+	intr_ctrl = in_be32(&intr->ctrl);
+	intr_ctrl &= 0x00ff0000;	/* Keeps IRQ[0-3] config */
+	intr_ctrl |=	0x0f000000 |	/* clear IRQ 0-3 */
+			0x00001000 |	/* MEE master external enable */
+			0x00000000 |	/* 0 means disable IRQ 0-3 */
+			0x00000001;	/* CEb route critical normally */
+	out_be32(&intr->ctrl, intr_ctrl);
+
+	/* Zero a bunch of the priority settings. */
+	out_be32(&intr->per_pri1, 0);
+	out_be32(&intr->per_pri2, 0);
+	out_be32(&intr->per_pri3, 0);
+	out_be32(&intr->main_pri1, 0);
+	out_be32(&intr->main_pri2, 0);
+
+	/*
+	 * As last step, add an irq host to translate the real
+	 * hw irq information provided by the ofw to linux virq
+	 */
+
+	mpc52xx_irqhost = irq_alloc_host(IRQ_HOST_MAP_LINEAR,
+	                                 MPC52xx_IRQ_HIGHTESTHWIRQ,
+	                                 &mpc52xx_irqhost_ops, -1);
+
+	if (!mpc52xx_irqhost)
+		panic(__FILE__ ": Cannot allocate the IRQ host\n");
+
+	mpc52xx_irqhost->host_data = picnode;
+	printk(KERN_INFO "MPC52xx PIC is up and running!\n");
+}
+
+/*
+ * get_irq (public)
+*/
+unsigned int mpc52xx_get_irq(void)
+{
+	u32 status;
+	int irq = NO_IRQ_IGNORE;
+
+	status = in_be32(&intr->enc_status);
+	if (status & 0x00000400) {	/* critical */
+		irq = (status >> 8) & 0x3;
+		if (irq == 2)	/* high priority peripheral */
+			goto peripheral;
+		irq |=	(MPC52xx_IRQ_L1_CRIT << MPC52xx_IRQ_L1_OFFSET) &
+			MPC52xx_IRQ_L1_MASK;
+	} else if (status & 0x00200000) {	/* main */
+		irq = (status >> 16) & 0x1f;
+		if (irq == 4)	/* low priority peripheral */
+			goto peripheral;
+		irq |=	(MPC52xx_IRQ_L1_MAIN << MPC52xx_IRQ_L1_OFFSET) &
+			MPC52xx_IRQ_L1_MASK;
+	} else if (status & 0x20000000) {	/* peripheral */
+	      peripheral:
+		irq = (status >> 24) & 0x1f;
+		if (irq == 0) {	/* bestcomm */
+			status = in_be32(&sdma->IntPend);
+			irq = ffs(status) - 1;
+			irq |=	(MPC52xx_IRQ_L1_SDMA << MPC52xx_IRQ_L1_OFFSET) &
+				MPC52xx_IRQ_L1_MASK;
+		} else {
+			irq |=	(MPC52xx_IRQ_L1_PERP << MPC52xx_IRQ_L1_OFFSET) &
+				MPC52xx_IRQ_L1_MASK;
+		}
+	}
+
+	pr_debug("%s: irq=%x. virq=%d\n", __func__, irq,
+		 irq_linear_revmap(mpc52xx_irqhost, irq));
+
+	return irq_linear_revmap(mpc52xx_irqhost, irq);
+}
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.h b/arch/powerpc/platforms/52xx/mpc52xx_pic.h
new file mode 100644
index 000000000000..1a26bcdb3049
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.h
@@ -0,0 +1,53 @@
+/*
+ * Header file for Freescale MPC52xx Interrupt controller
+ *
+ * Copyright (C) 2004-2005 Sylvain Munaut <tnt@246tNt.com>
+ * Copyright (C) 2003 MontaVista, Software, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __POWERPC_SYSDEV_MPC52xx_PIC_H__
+#define __POWERPC_SYSDEV_MPC52xx_PIC_H__
+
+#include <asm/types.h>
+
+
+/* HW IRQ mapping */
+#define MPC52xx_IRQ_L1_CRIT	(0)
+#define MPC52xx_IRQ_L1_MAIN	(1)
+#define MPC52xx_IRQ_L1_PERP	(2)
+#define MPC52xx_IRQ_L1_SDMA	(3)
+
+#define MPC52xx_IRQ_L1_OFFSET   (6)
+#define MPC52xx_IRQ_L1_MASK     (0x00c0)
+
+#define MPC52xx_IRQ_L2_OFFSET   (0)
+#define MPC52xx_IRQ_L2_MASK     (0x003f)
+
+#define MPC52xx_IRQ_HIGHTESTHWIRQ (0xd0)
+
+
+/* Interrupt controller Register set */
+struct mpc52xx_intr {
+	u32 per_mask;		/* INTR + 0x00 */
+	u32 per_pri1;		/* INTR + 0x04 */
+	u32 per_pri2;		/* INTR + 0x08 */
+	u32 per_pri3;		/* INTR + 0x0c */
+	u32 ctrl;		/* INTR + 0x10 */
+	u32 main_mask;		/* INTR + 0x14 */
+	u32 main_pri1;		/* INTR + 0x18 */
+	u32 main_pri2;		/* INTR + 0x1c */
+	u32 reserved1;		/* INTR + 0x20 */
+	u32 enc_status;		/* INTR + 0x24 */
+	u32 crit_status;	/* INTR + 0x28 */
+	u32 main_status;	/* INTR + 0x2c */
+	u32 per_status;		/* INTR + 0x30 */
+	u32 reserved2;		/* INTR + 0x34 */
+	u32 per_error;		/* INTR + 0x38 */
+};
+
+#endif /* __POWERPC_SYSDEV_MPC52xx_PIC_H__ */
+
diff --git a/arch/powerpc/platforms/82xx/mpc82xx_ads.c b/arch/powerpc/platforms/82xx/mpc82xx_ads.c
index bb9acbb98176..ea880f1f0dcd 100644
--- a/arch/powerpc/platforms/82xx/mpc82xx_ads.c
+++ b/arch/powerpc/platforms/82xx/mpc82xx_ads.c
@@ -515,16 +515,6 @@ static int m82xx_pci_exclude_device(u_char bus, u_char devfn)
 		return PCIBIOS_SUCCESSFUL;
 }
 
-static void
-__init mpc82xx_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-
-	for_each_pci_dev(dev) {
-		pci_read_irq_line(dev);
-	}
-}
-
 void __init add_bridge(struct device_node *np)
 {
 	int len;
@@ -597,9 +587,6 @@ static void __init mpc82xx_ads_setup_arch(void)
 		add_bridge(np);
 
 	of_node_put(np);
-	ppc_md.pci_map_irq = NULL;
-	ppc_md.pcibios_fixup = mpc82xx_pcibios_fixup;
-	ppc_md.pcibios_fixup_bus = NULL;
 #endif
 
 #ifdef  CONFIG_ROOT_NFS
diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c
index a43ac71ab740..f58c9780b66f 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c
@@ -97,8 +97,6 @@ static void __init mpc832x_sys_setup_arch(void)
 #ifdef CONFIG_PCI
 	for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;)
 		add_bridge(np);
-
-	ppc_md.pci_swizzle = common_swizzle;
 	ppc_md.pci_exclude_device = mpc83xx_exclude_device;
 #endif
 
diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c
index e2bcaaf6b329..314c42ac6048 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_itx.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c
@@ -118,7 +118,4 @@ define_machine(mpc834x_itx) {
 	.time_init		= mpc83xx_time_init,
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,
-#ifdef CONFIG_PCI
-	.pcibios_fixup		= mpc83xx_pcibios_fixup,
-#endif
 };
diff --git a/arch/powerpc/platforms/83xx/mpc834x_sys.c b/arch/powerpc/platforms/83xx/mpc834x_sys.c
index 677196187a4e..80b735a414d9 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_sys.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_sys.c
@@ -137,7 +137,4 @@ define_machine(mpc834x_sys) {
 	.time_init		= mpc83xx_time_init,
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,
-#ifdef CONFIG_PCI
-	.pcibios_fixup		= mpc83xx_pcibios_fixup,
-#endif
 };
diff --git a/arch/powerpc/platforms/83xx/mpc8360e_pb.c b/arch/powerpc/platforms/83xx/mpc8360e_pb.c
index 1a523c81c06e..7bfd47ad7233 100644
--- a/arch/powerpc/platforms/83xx/mpc8360e_pb.c
+++ b/arch/powerpc/platforms/83xx/mpc8360e_pb.c
@@ -102,8 +102,6 @@ static void __init mpc8360_sys_setup_arch(void)
 #ifdef CONFIG_PCI
 	for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;)
 		add_bridge(np);
-
-	ppc_md.pci_swizzle = common_swizzle;
 	ppc_md.pci_exclude_device = mpc83xx_exclude_device;
 #endif
 
diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h
index 2c82bca9bfbb..01cae106912b 100644
--- a/arch/powerpc/platforms/83xx/mpc83xx.h
+++ b/arch/powerpc/platforms/83xx/mpc83xx.h
@@ -11,7 +11,6 @@
 
 extern int add_bridge(struct device_node *dev);
 extern int mpc83xx_exclude_device(u_char bus, u_char devfn);
-extern void mpc83xx_pcibios_fixup(void);
 extern void mpc83xx_restart(char *cmd);
 extern long mpc83xx_time_init(void);
 
diff --git a/arch/powerpc/platforms/83xx/pci.c b/arch/powerpc/platforms/83xx/pci.c
index 4557ac5255c1..9c3650555144 100644
--- a/arch/powerpc/platforms/83xx/pci.c
+++ b/arch/powerpc/platforms/83xx/pci.c
@@ -45,15 +45,6 @@ int mpc83xx_exclude_device(u_char bus, u_char devfn)
 	return PCIBIOS_SUCCESSFUL;
 }
 
-void __init mpc83xx_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-
-	/* map all the PCI irqs */
-	for_each_pci_dev(dev)
-		pci_read_irq_line(dev);
-}
-
 int __init add_bridge(struct device_node *dev)
 {
 	int len;
diff --git a/arch/powerpc/platforms/85xx/misc.c b/arch/powerpc/platforms/85xx/misc.c
index 26c5e822c7c8..3e62fcb04c1c 100644
--- a/arch/powerpc/platforms/85xx/misc.c
+++ b/arch/powerpc/platforms/85xx/misc.c
@@ -21,11 +21,3 @@ void mpc85xx_restart(char *cmd)
 	local_irq_disable();
 	abort();
 }
-
-/* For now this is a pass through */
-phys_addr_t fixup_bigphys_addr(phys_addr_t addr, phys_addr_t size)
-{
-	return addr;
-};
-
-EXPORT_SYMBOL(fixup_bigphys_addr);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index d3e669d69c73..bda2e55e6c4c 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -53,15 +53,6 @@ mpc85xx_exclude_device(u_char bus, u_char devfn)
 	else
 		return PCIBIOS_SUCCESSFUL;
 }
-
-void __init
-mpc85xx_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-
-	for_each_pci_dev(dev)
-		pci_read_irq_line(dev);
-}
 #endif /* CONFIG_PCI */
 
 #ifdef CONFIG_CPM2
@@ -253,8 +244,6 @@ static void __init mpc85xx_ads_setup_arch(void)
 #ifdef CONFIG_PCI
 	for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;)
 		add_bridge(np);
-
-	ppc_md.pcibios_fixup = mpc85xx_pcibios_fixup;
 	ppc_md.pci_exclude_device = mpc85xx_exclude_device;
 #endif
 
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 1a1c226ad4d9..f4dd5f2f8a28 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -398,15 +398,6 @@ mpc86xx_hpcn_show_cpuinfo(struct seq_file *m)
 }
 
 
-void __init mpc86xx_hpcn_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-
-	for_each_pci_dev(dev)
-		pci_read_irq_line(dev);
-}
-
-
 /*
  * Called very early, device-tree isn't unflattened
  */
@@ -461,7 +452,6 @@ define_machine(mpc86xx_hpcn) {
 	.setup_arch		= mpc86xx_hpcn_setup_arch,
 	.init_IRQ		= mpc86xx_hpcn_init_irq,
 	.show_cpuinfo		= mpc86xx_hpcn_show_cpuinfo,
-	.pcibios_fixup		= mpc86xx_hpcn_pcibios_fixup,
 	.get_irq		= mpic_get_irq,
 	.restart		= mpc86xx_restart,
 	.time_init		= mpc86xx_time_init,
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index e58fa953a50b..44d95eaf22e6 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -7,12 +7,14 @@ endif
 endif
 obj-$(CONFIG_PPC_CHRP)		+= chrp/
 obj-$(CONFIG_4xx)		+= 4xx/
+obj-$(CONFIG_PPC_MPC52xx)	+= 52xx/
 obj-$(CONFIG_PPC_83xx)		+= 83xx/
 obj-$(CONFIG_PPC_85xx)		+= 85xx/
 obj-$(CONFIG_PPC_86xx)		+= 86xx/
 obj-$(CONFIG_PPC_PSERIES)	+= pseries/
 obj-$(CONFIG_PPC_ISERIES)	+= iseries/
 obj-$(CONFIG_PPC_MAPLE)		+= maple/
-obj-$(CONFIG_PPC_PASEMI)		+= pasemi/
+obj-$(CONFIG_PPC_PASEMI)	+= pasemi/
 obj-$(CONFIG_PPC_CELL)		+= cell/
+obj-$(CONFIG_PPC_PS3)		+= ps3/
 obj-$(CONFIG_EMBEDDED6xx)	+= embedded6xx/
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 3e430b489bb7..06a85b704331 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -20,4 +20,18 @@ config CBE_RAS
 	bool "RAS features for bare metal Cell BE"
 	default y
 
+config CBE_THERM
+	tristate "CBE thermal support"
+	default m
+	depends on CBE_RAS
+
+config CBE_CPUFREQ
+	tristate "CBE frequency scaling"
+	depends on CBE_RAS && CPU_FREQ
+	default m
+	help
+	  This adds the cpufreq driver for Cell BE processors.
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+	  If you don't have such processor, say N
+
 endmenu
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index c89cdd67383b..f90e8337796c 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -1,7 +1,11 @@
 obj-$(CONFIG_PPC_CELL_NATIVE)		+= interrupt.o iommu.o setup.o \
-					   cbe_regs.o spider-pic.o pervasive.o
+					   cbe_regs.o spider-pic.o \
+					   pervasive.o pmu.o io-workarounds.o
 obj-$(CONFIG_CBE_RAS)			+= ras.o
 
+obj-$(CONFIG_CBE_THERM)			+= cbe_thermal.o
+obj-$(CONFIG_CBE_CPUFREQ)		+= cbe_cpufreq.o
+
 ifeq ($(CONFIG_SMP),y)
 obj-$(CONFIG_PPC_CELL_NATIVE)		+= smp.o
 endif
@@ -11,5 +15,6 @@ spufs-modular-$(CONFIG_SPU_FS)		+= spu_syscalls.o
 spu-priv1-$(CONFIG_PPC_CELL_NATIVE)	+= spu_priv1_mmio.o
 
 obj-$(CONFIG_SPU_BASE)			+= spu_callbacks.o spu_base.o \
+					   spu_coredump.o \
 					   $(spufs-modular-m) \
 					   $(spu-priv1-y) spufs/
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c
new file mode 100644
index 000000000000..a3850fd1e94c
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq.c
@@ -0,0 +1,248 @@
+/*
+ * cpufreq driver for the cell processor
+ *
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
+ *
+ * Author: Christian Krafft <krafft@de.ibm.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, 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/cpufreq.h>
+#include <linux/timer.h>
+
+#include <asm/hw_irq.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/prom.h>
+#include <asm/time.h>
+
+#include "cbe_regs.h"
+
+static DEFINE_MUTEX(cbe_switch_mutex);
+
+
+/* the CBE supports an 8 step frequency scaling */
+static struct cpufreq_frequency_table cbe_freqs[] = {
+	{1,	0},
+	{2,	0},
+	{3,	0},
+	{4,	0},
+	{5,	0},
+	{6,	0},
+	{8,	0},
+	{10,	0},
+	{0,	CPUFREQ_TABLE_END},
+};
+
+/* to write to MIC register */
+static u64 MIC_Slow_Fast_Timer_table[] = {
+	[0 ... 7] = 0x007fc00000000000ull,
+};
+
+/* more values for the MIC */
+static u64 MIC_Slow_Next_Timer_table[] = {
+	0x0000240000000000ull,
+	0x0000268000000000ull,
+	0x000029C000000000ull,
+	0x00002D0000000000ull,
+	0x0000300000000000ull,
+	0x0000334000000000ull,
+	0x000039C000000000ull,
+	0x00003FC000000000ull,
+};
+
+/*
+ * hardware specific functions
+ */
+
+static int get_pmode(int cpu)
+{
+	int ret;
+	struct cbe_pmd_regs __iomem *pmd_regs;
+
+	pmd_regs = cbe_get_cpu_pmd_regs(cpu);
+	ret = in_be64(&pmd_regs->pmsr) & 0x07;
+
+	return ret;
+}
+
+static int set_pmode(int cpu, unsigned int pmode)
+{
+	struct cbe_pmd_regs __iomem *pmd_regs;
+	struct cbe_mic_tm_regs __iomem *mic_tm_regs;
+	u64 flags;
+	u64 value;
+
+	local_irq_save(flags);
+
+	mic_tm_regs = cbe_get_cpu_mic_tm_regs(cpu);
+	pmd_regs = cbe_get_cpu_pmd_regs(cpu);
+
+	pr_debug("pm register is mapped at %p\n", &pmd_regs->pmcr);
+	pr_debug("mic register is mapped at %p\n", &mic_tm_regs->slow_fast_timer_0);
+
+	out_be64(&mic_tm_regs->slow_fast_timer_0, MIC_Slow_Fast_Timer_table[pmode]);
+	out_be64(&mic_tm_regs->slow_fast_timer_1, MIC_Slow_Fast_Timer_table[pmode]);
+
+	out_be64(&mic_tm_regs->slow_next_timer_0, MIC_Slow_Next_Timer_table[pmode]);
+	out_be64(&mic_tm_regs->slow_next_timer_1, MIC_Slow_Next_Timer_table[pmode]);
+
+	value = in_be64(&pmd_regs->pmcr);
+	/* set bits to zero */
+	value &= 0xFFFFFFFFFFFFFFF8ull;
+	/* set bits to next pmode */
+	value |= pmode;
+
+	out_be64(&pmd_regs->pmcr, value);
+
+	/* wait until new pmode appears in status register */
+	value = in_be64(&pmd_regs->pmsr) & 0x07;
+	while(value != pmode) {
+		cpu_relax();
+		value = in_be64(&pmd_regs->pmsr) & 0x07;
+	}
+
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+/*
+ * cpufreq functions
+ */
+
+static int cbe_cpufreq_cpu_init (struct cpufreq_policy *policy)
+{
+	u32 *max_freq;
+	int i, cur_pmode;
+	struct device_node *cpu;
+
+	cpu = of_get_cpu_node(policy->cpu, NULL);
+
+	if(!cpu)
+		return -ENODEV;
+
+	pr_debug("init cpufreq on CPU %d\n", policy->cpu);
+
+	max_freq = (u32*) get_property(cpu, "clock-frequency", NULL);
+
+	if(!max_freq)
+		return -EINVAL;
+
+	// we need the freq in kHz
+	*max_freq /= 1000;
+
+	pr_debug("max clock-frequency is at %u kHz\n", *max_freq);
+	pr_debug("initializing frequency table\n");
+
+	// initialize frequency table
+	for (i=0; cbe_freqs[i].frequency!=CPUFREQ_TABLE_END; i++) {
+		cbe_freqs[i].frequency = *max_freq / cbe_freqs[i].index;
+		pr_debug("%d: %d\n", i, cbe_freqs[i].frequency);
+	}
+
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+	/* if DEBUG is enabled set_pmode() measures the correct latency of a transition */
+	policy->cpuinfo.transition_latency = 25000;
+
+	cur_pmode = get_pmode(policy->cpu);
+	pr_debug("current pmode is at %d\n",cur_pmode);
+
+	policy->cur = cbe_freqs[cur_pmode].frequency;
+
+#ifdef CONFIG_SMP
+	policy->cpus = cpu_sibling_map[policy->cpu];
+#endif
+
+	cpufreq_frequency_table_get_attr (cbe_freqs, policy->cpu);
+
+	/* this ensures that policy->cpuinfo_min and policy->cpuinfo_max are set correctly */
+	return cpufreq_frequency_table_cpuinfo (policy, cbe_freqs);
+}
+
+static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
+static int cbe_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, cbe_freqs);
+}
+
+
+static int cbe_cpufreq_target(struct cpufreq_policy *policy, unsigned int target_freq,
+			    unsigned int relation)
+{
+	int rc;
+	struct cpufreq_freqs freqs;
+	int cbe_pmode_new;
+
+	cpufreq_frequency_table_target(policy,
+				       cbe_freqs,
+				       target_freq,
+				       relation,
+				       &cbe_pmode_new);
+
+	freqs.old = policy->cur;
+	freqs.new = cbe_freqs[cbe_pmode_new].frequency;
+	freqs.cpu = policy->cpu;
+
+	mutex_lock (&cbe_switch_mutex);
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	pr_debug("setting frequency for cpu %d to %d kHz, 1/%d of max frequency\n",
+		 policy->cpu,
+		 cbe_freqs[cbe_pmode_new].frequency,
+		 cbe_freqs[cbe_pmode_new].index);
+
+	rc = set_pmode(policy->cpu, cbe_pmode_new);
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	mutex_unlock(&cbe_switch_mutex);
+
+	return rc;
+}
+
+static struct cpufreq_driver cbe_cpufreq_driver = {
+	.verify		= cbe_cpufreq_verify,
+	.target		= cbe_cpufreq_target,
+	.init		= cbe_cpufreq_cpu_init,
+	.exit		= cbe_cpufreq_cpu_exit,
+	.name		= "cbe-cpufreq",
+	.owner		= THIS_MODULE,
+	.flags		= CPUFREQ_CONST_LOOPS,
+};
+
+/*
+ * module init and destoy
+ */
+
+static int __init cbe_cpufreq_init(void)
+{
+	return cpufreq_register_driver(&cbe_cpufreq_driver);
+}
+
+static void __exit cbe_cpufreq_exit(void)
+{
+	cpufreq_unregister_driver(&cbe_cpufreq_driver);
+}
+
+module_init(cbe_cpufreq_init);
+module_exit(cbe_cpufreq_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
index 2f194ba29899..9a0ee62691d5 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ b/arch/powerpc/platforms/cell/cbe_regs.c
@@ -8,6 +8,7 @@
 
 #include <linux/percpu.h>
 #include <linux/types.h>
+#include <linux/module.h>
 
 #include <asm/io.h>
 #include <asm/pgtable.h>
@@ -16,8 +17,6 @@
 
 #include "cbe_regs.h"
 
-#define MAX_CBE		2
-
 /*
  * Current implementation uses "cpu" nodes. We build our own mapping
  * array of cpu numbers to cpu nodes locally for now to allow interrupt
@@ -30,6 +29,8 @@ static struct cbe_regs_map
 	struct device_node *cpu_node;
 	struct cbe_pmd_regs __iomem *pmd_regs;
 	struct cbe_iic_regs __iomem *iic_regs;
+	struct cbe_mic_tm_regs __iomem *mic_tm_regs;
+	struct cbe_pmd_shadow_regs pmd_shadow_regs;
 } cbe_regs_maps[MAX_CBE];
 static int cbe_regs_map_count;
 
@@ -42,6 +43,19 @@ static struct cbe_thread_map
 static struct cbe_regs_map *cbe_find_map(struct device_node *np)
 {
 	int i;
+	struct device_node *tmp_np;
+
+	if (strcasecmp(np->type, "spe") == 0) {
+		if (np->data == NULL) {
+			/* walk up path until cpu node was found */
+			tmp_np = np->parent;
+			while (tmp_np != NULL && strcasecmp(tmp_np->type, "cpu") != 0)
+				tmp_np = tmp_np->parent;
+
+			np->data = cbe_find_map(tmp_np);
+		}
+		return np->data;
+	}
 
 	for (i = 0; i < cbe_regs_map_count; i++)
 		if (cbe_regs_maps[i].cpu_node == np)
@@ -56,6 +70,7 @@ struct cbe_pmd_regs __iomem *cbe_get_pmd_regs(struct device_node *np)
 		return NULL;
 	return map->pmd_regs;
 }
+EXPORT_SYMBOL_GPL(cbe_get_pmd_regs);
 
 struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu)
 {
@@ -64,7 +79,23 @@ struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu)
 		return NULL;
 	return map->pmd_regs;
 }
+EXPORT_SYMBOL_GPL(cbe_get_cpu_pmd_regs);
 
+struct cbe_pmd_shadow_regs *cbe_get_pmd_shadow_regs(struct device_node *np)
+{
+	struct cbe_regs_map *map = cbe_find_map(np);
+	if (map == NULL)
+		return NULL;
+	return &map->pmd_shadow_regs;
+}
+
+struct cbe_pmd_shadow_regs *cbe_get_cpu_pmd_shadow_regs(int cpu)
+{
+	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
+	if (map == NULL)
+		return NULL;
+	return &map->pmd_shadow_regs;
+}
 
 struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np)
 {
@@ -73,6 +104,7 @@ struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np)
 		return NULL;
 	return map->iic_regs;
 }
+
 struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu)
 {
 	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
@@ -81,6 +113,36 @@ struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu)
 	return map->iic_regs;
 }
 
+struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np)
+{
+	struct cbe_regs_map *map = cbe_find_map(np);
+	if (map == NULL)
+		return NULL;
+	return map->mic_tm_regs;
+}
+
+struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu)
+{
+	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
+	if (map == NULL)
+		return NULL;
+	return map->mic_tm_regs;
+}
+EXPORT_SYMBOL_GPL(cbe_get_cpu_mic_tm_regs);
+
+/* FIXME
+ * This is little more than a stub at the moment.  It should be
+ * fleshed out so that it works for both SMT and non-SMT, no
+ * matter if the passed cpu is odd or even.
+ * For SMT enabled, returns 0 for even-numbered cpu; otherwise 1.
+ * For SMT disabled, returns 0 for all cpus.
+ */
+u32 cbe_get_hw_thread_id(int cpu)
+{
+	return (cpu & 1);
+}
+EXPORT_SYMBOL_GPL(cbe_get_hw_thread_id);
+
 void __init cbe_regs_init(void)
 {
 	int i;
@@ -119,6 +181,11 @@ void __init cbe_regs_init(void)
 		prop = get_property(cpu, "iic", NULL);
 		if (prop != NULL)
 			map->iic_regs = ioremap(prop->address, prop->len);
+
+		prop = (struct address_prop *)get_property(cpu, "mic-tm",
+							   NULL);
+		if (prop != NULL)
+			map->mic_tm_regs = ioremap(prop->address, prop->len);
 	}
 }
 
diff --git a/arch/powerpc/platforms/cell/cbe_regs.h b/arch/powerpc/platforms/cell/cbe_regs.h
index e76e4a6af5bc..440a7ecc66ea 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.h
+++ b/arch/powerpc/platforms/cell/cbe_regs.h
@@ -4,12 +4,19 @@
  * This file is intended to hold the various register definitions for CBE
  * on-chip system devices (memory controller, IO controller, etc...)
  *
+ * (C) Copyright IBM Corporation 2001,2006
+ *
+ * Authors: Maximino Aguilar (maguilar@us.ibm.com)
+ *          David J. Erb (djerb@us.ibm.com)
+ *
  * (c) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp.
  */
 
 #ifndef CBE_REGS_H
 #define CBE_REGS_H
 
+#include <asm/cell-pmu.h>
+
 /*
  *
  * Some HID register definitions
@@ -22,6 +29,7 @@
 #define HID0_CBE_THERM_INT_EN	0x0000000400000000ul
 #define HID0_CBE_SYSERR_INT_EN	0x0000000200000000ul
 
+#define MAX_CBE		2
 
 /*
  *
@@ -29,51 +37,124 @@
  *
  */
 
+union spe_reg {
+	u64 val;
+	u8 spe[8];
+};
+
+union ppe_spe_reg {
+	u64 val;
+	struct {
+		u32 ppe;
+		u32 spe;
+	};
+};
+
+
 struct cbe_pmd_regs {
-	u8 pad_0x0000_0x0800[0x0800 - 0x0000];			/* 0x0000 */
+	/* Debug Bus Control */
+	u64	pad_0x0000;					/* 0x0000 */
+
+	u64	group_control;					/* 0x0008 */
+
+	u8	pad_0x0010_0x00a8 [0x00a8 - 0x0010];		/* 0x0010 */
+
+	u64	debug_bus_control;				/* 0x00a8 */
+
+	u8	pad_0x00b0_0x0100 [0x0100 - 0x00b0];		/* 0x00b0 */
+
+	u64	trace_aux_data;					/* 0x0100 */
+	u64	trace_buffer_0_63;				/* 0x0108 */
+	u64	trace_buffer_64_127;				/* 0x0110 */
+	u64	trace_address;					/* 0x0118 */
+	u64	ext_tr_timer;					/* 0x0120 */
+
+	u8	pad_0x0128_0x0400 [0x0400 - 0x0128];		/* 0x0128 */
+
+	/* Performance Monitor */
+	u64	pm_status;					/* 0x0400 */
+	u64	pm_control;					/* 0x0408 */
+	u64	pm_interval;					/* 0x0410 */
+	u64	pm_ctr[4];					/* 0x0418 */
+	u64	pm_start_stop;					/* 0x0438 */
+	u64	pm07_control[8];				/* 0x0440 */
+
+	u8	pad_0x0480_0x0800 [0x0800 - 0x0480];		/* 0x0480 */
 
 	/* Thermal Sensor Registers */
-	u64  ts_ctsr1;						/* 0x0800 */
-	u64  ts_ctsr2;						/* 0x0808 */
-	u64  ts_mtsr1;						/* 0x0810 */
-	u64  ts_mtsr2;						/* 0x0818 */
-	u64  ts_itr1;						/* 0x0820 */
-	u64  ts_itr2;						/* 0x0828 */
-	u64  ts_gitr;						/* 0x0830 */
-	u64  ts_isr;						/* 0x0838 */
-	u64  ts_imr;						/* 0x0840 */
-	u64  tm_cr1;						/* 0x0848 */
-	u64  tm_cr2;						/* 0x0850 */
-	u64  tm_simr;						/* 0x0858 */
-	u64  tm_tpr;						/* 0x0860 */
-	u64  tm_str1;						/* 0x0868 */
-	u64  tm_str2;						/* 0x0870 */
-	u64  tm_tsr;						/* 0x0878 */
+	union	spe_reg	ts_ctsr1;				/* 0x0800 */
+	u64	ts_ctsr2;					/* 0x0808 */
+	union	spe_reg	ts_mtsr1;				/* 0x0810 */
+	u64	ts_mtsr2;					/* 0x0818 */
+	union	spe_reg	ts_itr1;				/* 0x0820 */
+	u64	ts_itr2;					/* 0x0828 */
+	u64	ts_gitr;					/* 0x0830 */
+	u64	ts_isr;						/* 0x0838 */
+	u64	ts_imr;						/* 0x0840 */
+	union	spe_reg	tm_cr1;					/* 0x0848 */
+	u64	tm_cr2;						/* 0x0850 */
+	u64	tm_simr;					/* 0x0858 */
+	union	ppe_spe_reg tm_tpr;				/* 0x0860 */
+	union	spe_reg	tm_str1;				/* 0x0868 */
+	u64	tm_str2;					/* 0x0870 */
+	union	ppe_spe_reg tm_tsr;				/* 0x0878 */
 
 	/* Power Management */
-	u64  pm_control;					/* 0x0880 */
-#define CBE_PMD_PAUSE_ZERO_CONTROL		0x10000
-	u64  pm_status;						/* 0x0888 */
+	u64	pmcr;						/* 0x0880 */
+#define CBE_PMD_PAUSE_ZERO_CONTROL	0x10000
+	u64	pmsr;						/* 0x0888 */
 
 	/* Time Base Register */
-	u64  tbr;						/* 0x0890 */
+	u64	tbr;						/* 0x0890 */
 
-	u8   pad_0x0898_0x0c00 [0x0c00 - 0x0898];		/* 0x0898 */
+	u8	pad_0x0898_0x0c00 [0x0c00 - 0x0898];		/* 0x0898 */
 
 	/* Fault Isolation Registers */
-	u64  checkstop_fir;					/* 0x0c00 */
-	u64  recoverable_fir;
-	u64  spec_att_mchk_fir;
-	u64  fir_mode_reg;
-	u64  fir_enable_mask;
+	u64	checkstop_fir;					/* 0x0c00 */
+	u64	recoverable_fir;				/* 0x0c08 */
+	u64	spec_att_mchk_fir;				/* 0x0c10 */
+	u64	fir_mode_reg;					/* 0x0c18 */
+	u64	fir_enable_mask;				/* 0x0c20 */
 
-	u8   pad_0x0c28_0x1000 [0x1000 - 0x0c28];		/* 0x0c28 */
+	u8	pad_0x0c28_0x1000 [0x1000 - 0x0c28];		/* 0x0c28 */
 };
 
 extern struct cbe_pmd_regs __iomem *cbe_get_pmd_regs(struct device_node *np);
 extern struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu);
 
 /*
+ * PMU shadow registers
+ *
+ * Many of the registers in the performance monitoring unit are write-only,
+ * so we need to save a copy of what we write to those registers.
+ *
+ * The actual data counters are read/write. However, writing to the counters
+ * only takes effect if the PMU is enabled. Otherwise the value is stored in
+ * a hardware latch until the next time the PMU is enabled. So we save a copy
+ * of the counter values if we need to read them back while the PMU is
+ * disabled. The counter_value_in_latch field is a bitmap indicating which
+ * counters currently have a value waiting to be written.
+ */
+
+struct cbe_pmd_shadow_regs {
+	u32 group_control;
+	u32 debug_bus_control;
+	u32 trace_address;
+	u32 ext_tr_timer;
+	u32 pm_status;
+	u32 pm_control;
+	u32 pm_interval;
+	u32 pm_start_stop;
+	u32 pm07_control[NR_CTRS];
+
+	u32 pm_ctr[NR_PHYS_CTRS];
+	u32 counter_value_in_latch;
+};
+
+extern struct cbe_pmd_shadow_regs *cbe_get_pmd_shadow_regs(struct device_node *np);
+extern struct cbe_pmd_shadow_regs *cbe_get_cpu_pmd_shadow_regs(int cpu);
+
+/*
  *
  * IIC unit register definitions
  *
@@ -102,18 +183,28 @@ struct cbe_iic_regs {
 
 	/* IIC interrupt registers */
 	struct	cbe_iic_thread_regs thread[2];			/* 0x0400 */
-	u64     iic_ir;						/* 0x0440 */
-	u64     iic_is;						/* 0x0448 */
+
+	u64	iic_ir;						/* 0x0440 */
+#define CBE_IIC_IR_PRIO(x)      (((x) & 0xf) << 12)
+#define CBE_IIC_IR_DEST_NODE(x) (((x) & 0xf) << 4)
+#define CBE_IIC_IR_DEST_UNIT(x) ((x) & 0xf)
+#define CBE_IIC_IR_IOC_0        0x0
+#define CBE_IIC_IR_IOC_1S       0xb
+#define CBE_IIC_IR_PT_0         0xe
+#define CBE_IIC_IR_PT_1         0xf
+
+	u64	iic_is;						/* 0x0448 */
+#define CBE_IIC_IS_PMI		0x2
 
 	u8	pad_0x0450_0x0500[0x0500 - 0x0450];		/* 0x0450 */
 
 	/* IOC FIR */
 	u64	ioc_fir_reset;					/* 0x0500 */
-	u64	ioc_fir_set;
-	u64	ioc_checkstop_enable;
-	u64	ioc_fir_error_mask;
-	u64	ioc_syserr_enable;
-	u64	ioc_fir;
+	u64	ioc_fir_set;					/* 0x0508 */
+	u64	ioc_checkstop_enable;				/* 0x0510 */
+	u64	ioc_fir_error_mask;				/* 0x0518 */
+	u64	ioc_syserr_enable;				/* 0x0520 */
+	u64	ioc_fir;					/* 0x0528 */
 
 	u8	pad_0x0530_0x1000[0x1000 - 0x0530];		/* 0x0530 */
 };
@@ -122,6 +213,48 @@ extern struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np);
 extern struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu);
 
 
+struct cbe_mic_tm_regs {
+	u8	pad_0x0000_0x0040[0x0040 - 0x0000];		/* 0x0000 */
+
+	u64	mic_ctl_cnfg2;					/* 0x0040 */
+#define CBE_MIC_ENABLE_AUX_TRC		0x8000000000000000LL
+#define CBE_MIC_DISABLE_PWR_SAV_2	0x0200000000000000LL
+#define CBE_MIC_DISABLE_AUX_TRC_WRAP	0x0100000000000000LL
+#define CBE_MIC_ENABLE_AUX_TRC_INT	0x0080000000000000LL
+
+	u64	pad_0x0048;					/* 0x0048 */
+
+	u64	mic_aux_trc_base;				/* 0x0050 */
+	u64	mic_aux_trc_max_addr;				/* 0x0058 */
+	u64	mic_aux_trc_cur_addr;				/* 0x0060 */
+	u64	mic_aux_trc_grf_addr;				/* 0x0068 */
+	u64	mic_aux_trc_grf_data;				/* 0x0070 */
+
+	u64	pad_0x0078;					/* 0x0078 */
+
+	u64	mic_ctl_cnfg_0;					/* 0x0080 */
+#define CBE_MIC_DISABLE_PWR_SAV_0	0x8000000000000000LL
+
+	u64	pad_0x0088;					/* 0x0088 */
+
+	u64	slow_fast_timer_0;				/* 0x0090 */
+	u64	slow_next_timer_0;				/* 0x0098 */
+
+	u8	pad_0x00a0_0x01c0[0x01c0 - 0x0a0];		/* 0x00a0 */
+
+	u64	mic_ctl_cnfg_1;					/* 0x01c0 */
+#define CBE_MIC_DISABLE_PWR_SAV_1	0x8000000000000000LL
+	u64	pad_0x01c8;					/* 0x01c8 */
+
+	u64	slow_fast_timer_1;				/* 0x01d0 */
+	u64	slow_next_timer_1;				/* 0x01d8 */
+
+	u8	pad_0x01e0_0x1000[0x1000 - 0x01e0];		/* 0x01e0 */
+};
+
+extern struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np);
+extern struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu);
+
 /* Init this module early */
 extern void cbe_regs_init(void);
 
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
new file mode 100644
index 000000000000..616a0a3fd0e2
--- /dev/null
+++ b/arch/powerpc/platforms/cell/cbe_thermal.c
@@ -0,0 +1,226 @@
+/*
+ * thermal support for the cell processor
+ *
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
+ *
+ * Author: Christian Krafft <krafft@de.ibm.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, 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/sysdev.h>
+#include <linux/kernel.h>
+#include <linux/cpu.h>
+#include <asm/spu.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+
+#include "cbe_regs.h"
+#include "spu_priv1_mmio.h"
+
+static struct cbe_pmd_regs __iomem *get_pmd_regs(struct sys_device *sysdev)
+{
+	struct spu *spu;
+
+	spu = container_of(sysdev, struct spu, sysdev);
+
+	return cbe_get_pmd_regs(spu_devnode(spu));
+}
+
+/* returns the value for a given spu in a given register */
+static u8 spu_read_register_value(struct sys_device *sysdev, union spe_reg __iomem *reg)
+{
+	unsigned int *id;
+	union spe_reg value;
+	struct spu *spu;
+
+	/* getting the id from the reg attribute will not work on future device-tree layouts
+	 * in future we should store the id to the spu struct and use it here */
+	spu = container_of(sysdev, struct spu, sysdev);
+	id = (unsigned int *)get_property(spu_devnode(spu), "reg", NULL);
+	value.val = in_be64(&reg->val);
+
+	return value.spe[*id];
+}
+
+static ssize_t spu_show_temp(struct sys_device *sysdev, char *buf)
+{
+	int value;
+	struct cbe_pmd_regs __iomem *pmd_regs;
+
+	pmd_regs = get_pmd_regs(sysdev);
+
+	value = spu_read_register_value(sysdev, &pmd_regs->ts_ctsr1);
+	/* clear all other bits */
+	value &= 0x3F;
+	/* temp is stored in steps of 2 degrees */
+	value *= 2;
+	/* base temp is 65 degrees */
+	value += 65;
+
+	return sprintf(buf, "%d\n", (int) value);
+}
+
+static ssize_t ppe_show_temp(struct sys_device *sysdev, char *buf, int pos)
+{
+	struct cbe_pmd_regs __iomem *pmd_regs;
+	u64 value;
+
+	pmd_regs = cbe_get_cpu_pmd_regs(sysdev->id);
+	value = in_be64(&pmd_regs->ts_ctsr2);
+
+	/* access the corresponding byte */
+	value >>= pos;
+	/* clear all other bits */
+	value &= 0x3F;
+	/* temp is stored in steps of 2 degrees */
+	value *= 2;
+	/* base temp is 65 degrees */
+	value += 65;
+
+	return sprintf(buf, "%d\n", (int) value);
+}
+
+
+/* shows the temperature of the DTS on the PPE,
+ * located near the linear thermal sensor */
+static ssize_t ppe_show_temp0(struct sys_device *sysdev, char *buf)
+{
+	return ppe_show_temp(sysdev, buf, 32);
+}
+
+/* shows the temperature of the second DTS on the PPE */
+static ssize_t ppe_show_temp1(struct sys_device *sysdev, char *buf)
+{
+	return ppe_show_temp(sysdev, buf, 0);
+}
+
+static struct sysdev_attribute attr_spu_temperature = {
+	.attr = {.name = "temperature", .mode = 0400 },
+	.show = spu_show_temp,
+};
+
+static struct attribute *spu_attributes[] = {
+	&attr_spu_temperature.attr,
+};
+
+static struct attribute_group spu_attribute_group = {
+	.name	= "thermal",
+	.attrs	= spu_attributes,
+};
+
+static struct sysdev_attribute attr_ppe_temperature0 = {
+	.attr = {.name = "temperature0", .mode = 0400 },
+	.show = ppe_show_temp0,
+};
+
+static struct sysdev_attribute attr_ppe_temperature1 = {
+	.attr = {.name = "temperature1", .mode = 0400 },
+	.show = ppe_show_temp1,
+};
+
+static struct attribute *ppe_attributes[] = {
+	&attr_ppe_temperature0.attr,
+	&attr_ppe_temperature1.attr,
+};
+
+static struct attribute_group ppe_attribute_group = {
+	.name	= "thermal",
+	.attrs	= ppe_attributes,
+};
+
+/*
+ * initialize throttling with default values
+ */
+static void __init init_default_values(void)
+{
+	int cpu;
+	struct cbe_pmd_regs __iomem *pmd_regs;
+	struct sys_device *sysdev;
+	union ppe_spe_reg tpr;
+	union spe_reg str1;
+	u64 str2;
+	union spe_reg cr1;
+	u64 cr2;
+
+	/* TPR defaults */
+	/* ppe
+	 *	1F - no full stop
+	 *	08 - dynamic throttling starts if over 80 degrees
+	 *	03 - dynamic throttling ceases if below 70 degrees */
+	tpr.ppe = 0x1F0803;
+	/* spe
+	 *	10 - full stopped when over 96 degrees
+	 *	08 - dynamic throttling starts if over 80 degrees
+	 *	03 - dynamic throttling ceases if below 70 degrees
+	 */
+	tpr.spe = 0x100803;
+
+	/* STR defaults */
+	/* str1
+	 *	10 - stop 16 of 32 cycles
+	 */
+	str1.val = 0x1010101010101010ull;
+	/* str2
+	 *	10 - stop 16 of 32 cycles
+	 */
+	str2 = 0x10;
+
+	/* CR defaults */
+	/* cr1
+	 *	4 - normal operation
+	 */
+	cr1.val = 0x0404040404040404ull;
+	/* cr2
+	 *	4 - normal operation
+	 */
+	cr2 = 0x04;
+
+	for_each_possible_cpu (cpu) {
+		pr_debug("processing cpu %d\n", cpu);
+		sysdev = get_cpu_sysdev(cpu);
+		pmd_regs = cbe_get_cpu_pmd_regs(sysdev->id);
+
+		out_be64(&pmd_regs->tm_str2, str2);
+		out_be64(&pmd_regs->tm_str1.val, str1.val);
+		out_be64(&pmd_regs->tm_tpr.val, tpr.val);
+		out_be64(&pmd_regs->tm_cr1.val, cr1.val);
+		out_be64(&pmd_regs->tm_cr2, cr2);
+	}
+}
+
+
+static int __init thermal_init(void)
+{
+	init_default_values();
+
+	spu_add_sysdev_attr_group(&spu_attribute_group);
+	cpu_add_sysdev_attr_group(&ppe_attribute_group);
+
+	return 0;
+}
+module_init(thermal_init);
+
+static void __exit thermal_exit(void)
+{
+	spu_remove_sysdev_attr_group(&spu_attribute_group);
+	cpu_remove_sysdev_attr_group(&ppe_attribute_group);
+}
+module_exit(thermal_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
+
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index a914c12b4060..6666d037eb44 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -396,3 +396,19 @@ void __init iic_init_IRQ(void)
 	/* Enable on current CPU */
 	iic_setup_cpu();
 }
+
+void iic_set_interrupt_routing(int cpu, int thread, int priority)
+{
+	struct cbe_iic_regs __iomem *iic_regs = cbe_get_cpu_iic_regs(cpu);
+	u64 iic_ir = 0;
+	int node = cpu >> 1;
+
+	/* Set which node and thread will handle the next interrupt */
+	iic_ir |= CBE_IIC_IR_PRIO(priority) |
+		  CBE_IIC_IR_DEST_NODE(node);
+	if (thread == 0)
+		iic_ir |= CBE_IIC_IR_DEST_UNIT(CBE_IIC_IR_PT_0);
+	else
+		iic_ir |= CBE_IIC_IR_DEST_UNIT(CBE_IIC_IR_PT_1);
+	out_be64(&iic_regs->iic_ir, iic_ir);
+}
diff --git a/arch/powerpc/platforms/cell/interrupt.h b/arch/powerpc/platforms/cell/interrupt.h
index 9ba1d3c17b4b..942dc39d6045 100644
--- a/arch/powerpc/platforms/cell/interrupt.h
+++ b/arch/powerpc/platforms/cell/interrupt.h
@@ -83,5 +83,7 @@ extern u8 iic_get_target_id(int cpu);
 
 extern void spider_init_IRQ(void);
 
+extern void iic_set_interrupt_routing(int cpu, int thread, int priority);
+
 #endif
 #endif /* ASM_CELL_PIC_H */
diff --git a/arch/powerpc/platforms/cell/io-workarounds.c b/arch/powerpc/platforms/cell/io-workarounds.c
new file mode 100644
index 000000000000..580d42595912
--- /dev/null
+++ b/arch/powerpc/platforms/cell/io-workarounds.c
@@ -0,0 +1,346 @@
+/*
+ *  Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ *		       IBM, Corp.
+ *
+ * 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.
+ */
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+
+#define SPIDER_PCI_REG_BASE		0xd000
+#define SPIDER_PCI_VCI_CNTL_STAT	0x0110
+#define SPIDER_PCI_DUMMY_READ		0x0810
+#define SPIDER_PCI_DUMMY_READ_BASE	0x0814
+
+/* Undefine that to re-enable bogus prefetch
+ *
+ * Without that workaround, the chip will do bogus prefetch past
+ * page boundary from system memory. This setting will disable that,
+ * though the documentation is unclear as to the consequences of doing
+ * so, either purely performances, or possible misbehaviour... It's not
+ * clear wether the chip can handle unaligned accesses at all without
+ * prefetching enabled.
+ *
+ * For now, things appear to be behaving properly with that prefetching
+ * disabled and IDE, possibly because IDE isn't doing any unaligned
+ * access.
+ */
+#define SPIDER_DISABLE_PREFETCH
+
+#define MAX_SPIDERS	2
+
+static struct spider_pci_bus {
+	void __iomem	*regs;
+	unsigned long	mmio_start;
+	unsigned long	mmio_end;
+	unsigned long	pio_vstart;
+	unsigned long	pio_vend;
+} spider_pci_busses[MAX_SPIDERS];
+static int spider_pci_count;
+
+static struct spider_pci_bus *spider_pci_find(unsigned long vaddr,
+					      unsigned long paddr)
+{
+	int i;
+
+	for (i = 0; i < spider_pci_count; i++) {
+		struct spider_pci_bus *bus = &spider_pci_busses[i];
+		if (paddr && paddr >= bus->mmio_start && paddr < bus->mmio_end)
+			return bus;
+		if (vaddr && vaddr >= bus->pio_vstart && vaddr < bus->pio_vend)
+			return bus;
+	}
+	return NULL;
+}
+
+static void spider_io_flush(const volatile void __iomem *addr)
+{
+	struct spider_pci_bus *bus;
+	int token;
+
+	/* Get platform token (set by ioremap) from address */
+	token = PCI_GET_ADDR_TOKEN(addr);
+
+	/* Fast path if we have a non-0 token, it indicates which bus we
+	 * are on.
+	 *
+	 * If the token is 0, that means either the the ioremap was done
+	 * before we initialized this layer, or it's a PIO operation. We
+	 * fallback to a low path in this case. Hopefully, internal devices
+	 * which are ioremap'ed early should use in_XX/out_XX functions
+	 * instead of the PCI ones and thus not suffer from the slowdown.
+	 *
+	 * Also note that currently, the workaround will not work for areas
+	 * that are not mapped with PTEs (bolted in the hash table). This
+	 * is the case for ioremaps done very early at boot (before
+	 * mem_init_done) and includes the mapping of the ISA IO space.
+	 *
+	 * Fortunately, none of the affected devices is expected to do DMA
+	 * and thus there should be no problem in practice.
+	 *
+	 * In order to improve performances, we only do the PTE search for
+	 * addresses falling in the PHB IO space area. That means it will
+	 * not work for hotplug'ed PHBs but those don't exist with Spider.
+	 */
+	if (token && token <= spider_pci_count)
+		bus = &spider_pci_busses[token - 1];
+	else {
+		unsigned long vaddr, paddr;
+		pte_t *ptep;
+
+		/* Fixup physical address */
+		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
+
+		/* Check if it's in allowed range for  PIO */
+		if (vaddr < PHBS_IO_BASE || vaddr >= IMALLOC_BASE)
+			return;
+
+		/* Try to find a PTE. If not, clear the paddr, we'll do
+		 * a vaddr only lookup (PIO only)
+		 */
+		ptep = find_linux_pte(init_mm.pgd, vaddr);
+		if (ptep == NULL)
+			paddr = 0;
+		else
+			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
+
+		bus = spider_pci_find(vaddr, paddr);
+		if (bus == NULL)
+			return;
+	}
+
+	/* Now do the workaround
+	 */
+	(void)in_be32(bus->regs + SPIDER_PCI_DUMMY_READ);
+}
+
+static u8 spider_readb(const volatile void __iomem *addr)
+{
+	u8 val = __do_readb(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static u16 spider_readw(const volatile void __iomem *addr)
+{
+	u16 val = __do_readw(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static u32 spider_readl(const volatile void __iomem *addr)
+{
+	u32 val = __do_readl(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static u64 spider_readq(const volatile void __iomem *addr)
+{
+	u64 val = __do_readq(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static u16 spider_readw_be(const volatile void __iomem *addr)
+{
+	u16 val = __do_readw_be(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static u32 spider_readl_be(const volatile void __iomem *addr)
+{
+	u32 val = __do_readl_be(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static u64 spider_readq_be(const volatile void __iomem *addr)
+{
+	u64 val = __do_readq_be(addr);
+	spider_io_flush(addr);
+	return val;
+}
+
+static void spider_readsb(const volatile void __iomem *addr, void *buf,
+			  unsigned long count)
+{
+	__do_readsb(addr, buf, count);
+	spider_io_flush(addr);
+}
+
+static void spider_readsw(const volatile void __iomem *addr, void *buf,
+			  unsigned long count)
+{
+	__do_readsw(addr, buf, count);
+	spider_io_flush(addr);
+}
+
+static void spider_readsl(const volatile void __iomem *addr, void *buf,
+			  unsigned long count)
+{
+	__do_readsl(addr, buf, count);
+	spider_io_flush(addr);
+}
+
+static void spider_memcpy_fromio(void *dest, const volatile void __iomem *src,
+				 unsigned long n)
+{
+	__do_memcpy_fromio(dest, src, n);
+	spider_io_flush(src);
+}
+
+
+static void __iomem * spider_ioremap(unsigned long addr, unsigned long size,
+				     unsigned long flags)
+{
+	struct spider_pci_bus *bus;
+	void __iomem *res = __ioremap(addr, size, flags);
+	int busno;
+
+	pr_debug("spider_ioremap(0x%lx, 0x%lx, 0x%lx) -> 0x%p\n",
+		 addr, size, flags, res);
+
+	bus = spider_pci_find(0, addr);
+	if (bus != NULL) {
+		busno = bus - spider_pci_busses;
+		pr_debug(" found bus %d, setting token\n", busno);
+		PCI_SET_ADDR_TOKEN(res, busno + 1);
+	}
+	pr_debug(" result=0x%p\n", res);
+
+	return res;
+}
+
+static void __init spider_pci_setup_chip(struct spider_pci_bus *bus)
+{
+#ifdef SPIDER_DISABLE_PREFETCH
+	u32 val = in_be32(bus->regs + SPIDER_PCI_VCI_CNTL_STAT);
+	pr_debug(" PVCI_Control_Status was 0x%08x\n", val);
+	out_be32(bus->regs + SPIDER_PCI_VCI_CNTL_STAT, val | 0x8);
+#endif
+
+	/* Configure the dummy address for the workaround */
+	out_be32(bus->regs + SPIDER_PCI_DUMMY_READ_BASE, 0x80000000);
+}
+
+static void __init spider_pci_add_one(struct pci_controller *phb)
+{
+	struct spider_pci_bus *bus = &spider_pci_busses[spider_pci_count];
+	struct device_node *np = phb->arch_data;
+	struct resource rsrc;
+	void __iomem *regs;
+
+	if (spider_pci_count >= MAX_SPIDERS) {
+		printk(KERN_ERR "Too many spider bridges, workarounds"
+		       " disabled for %s\n", np->full_name);
+		return;
+	}
+
+	/* Get the registers for the beast */
+	if (of_address_to_resource(np, 0, &rsrc)) {
+		printk(KERN_ERR "Failed to get registers for spider %s"
+		       " workarounds disabled\n", np->full_name);
+		return;
+	}
+
+	/* Mask out some useless bits in there to get to the base of the
+	 * spider chip
+	 */
+	rsrc.start &= ~0xfffffffful;
+
+	/* Map them */
+	regs = ioremap(rsrc.start + SPIDER_PCI_REG_BASE, 0x1000);
+	if (regs == NULL) {
+		printk(KERN_ERR "Failed to map registers for spider %s"
+		       " workarounds disabled\n", np->full_name);
+		return;
+	}
+
+	spider_pci_count++;
+
+	/* We assume spiders only have one MMIO resource */
+	bus->mmio_start = phb->mem_resources[0].start;
+	bus->mmio_end = phb->mem_resources[0].end + 1;
+
+	bus->pio_vstart = (unsigned long)phb->io_base_virt;
+	bus->pio_vend = bus->pio_vstart + phb->pci_io_size;
+
+	bus->regs = regs;
+
+	printk(KERN_INFO "PCI: Spider MMIO workaround for %s\n",np->full_name);
+
+	pr_debug(" mmio (P) = 0x%016lx..0x%016lx\n",
+		 bus->mmio_start, bus->mmio_end);
+	pr_debug("  pio (V) = 0x%016lx..0x%016lx\n",
+		 bus->pio_vstart, bus->pio_vend);
+	pr_debug(" regs (P) = 0x%016lx (V) = 0x%p\n",
+		 rsrc.start + SPIDER_PCI_REG_BASE, bus->regs);
+
+	spider_pci_setup_chip(bus);
+}
+
+static struct ppc_pci_io __initdata spider_pci_io = {
+	.readb = spider_readb,
+	.readw = spider_readw,
+	.readl = spider_readl,
+	.readq = spider_readq,
+	.readw_be = spider_readw_be,
+	.readl_be = spider_readl_be,
+	.readq_be = spider_readq_be,
+	.readsb = spider_readsb,
+	.readsw = spider_readsw,
+	.readsl = spider_readsl,
+	.memcpy_fromio = spider_memcpy_fromio,
+};
+
+static int __init spider_pci_workaround_init(void)
+{
+	struct pci_controller *phb;
+
+	if (!machine_is(cell))
+		return 0;
+
+	/* Find spider bridges. We assume they have been all probed
+	 * in setup_arch(). If that was to change, we would need to
+	 * update this code to cope with dynamically added busses
+	 */
+	list_for_each_entry(phb, &hose_list, list_node) {
+		struct device_node *np = phb->arch_data;
+		const char *model = get_property(np, "model", NULL);
+
+		/* If no model property or name isn't exactly "pci", skip */
+		if (model == NULL || strcmp(np->name, "pci"))
+			continue;
+		/* If model is not "Spider", skip */
+		if (strcmp(model, "Spider"))
+			continue;
+		spider_pci_add_one(phb);
+	}
+
+	/* No Spider PCI found, exit */
+	if (spider_pci_count == 0)
+		return 0;
+
+	/* Setup IO callbacks. We only setup MMIO reads. PIO reads will
+	 * fallback to MMIO reads (though without a token, thus slower)
+	 */
+	ppc_pci_io = spider_pci_io;
+
+	/* Setup ioremap callback */
+	ppc_md.ioremap = spider_ioremap;
+
+	return 0;
+}
+arch_initcall(spider_pci_workaround_init);
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index aca4c3db0dde..b43466ba8096 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -1,514 +1,747 @@
 /*
  * IOMMU implementation for Cell Broadband Processor Architecture
- * We just establish a linear mapping at boot by setting all the
- * IOPT cache entries in the CPU.
- * The mapping functions should be identical to pci_direct_iommu, 
- * except for the handling of the high order bit that is required
- * by the Spider bridge. These should be split into a separate
- * file at the point where we get a different bridge chip.
  *
- * Copyright (C) 2005 IBM Deutschland Entwicklung GmbH,
- *			 Arnd Bergmann <arndb@de.ibm.com>
+ * (C) Copyright IBM Corporation 2006
  *
- * Based on linear mapping
- * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ * Author: Jeremy Kerr <jk@ozlabs.org>
  *
- * 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 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, 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.
  */
 
 #undef DEBUG
 
 #include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/dma-mapping.h>
-#include <linux/kernel.h>
-#include <linux/compiler.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
 
-#include <asm/sections.h>
-#include <asm/iommu.h>
-#include <asm/io.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
+#include <asm/iommu.h>
 #include <asm/machdep.h>
-#include <asm/pmac_feature.h>
-#include <asm/abs_addr.h>
-#include <asm/system.h>
-#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
 #include <asm/udbg.h>
+#include <asm/of_platform.h>
+#include <asm/lmb.h>
 
-#include "iommu.h"
+#include "cbe_regs.h"
+#include "interrupt.h"
 
-static inline unsigned long 
-get_iopt_entry(unsigned long real_address, unsigned long ioid,
-			 unsigned long prot)
-{
-	return (prot & IOPT_PROT_MASK)
-	     | (IOPT_COHERENT)
-	     | (IOPT_ORDER_VC)
-	     | (real_address & IOPT_RPN_MASK)
-	     | (ioid & IOPT_IOID_MASK);
-}
+/* Define CELL_IOMMU_REAL_UNMAP to actually unmap non-used pages
+ * instead of leaving them mapped to some dummy page. This can be
+ * enabled once the appropriate workarounds for spider bugs have
+ * been enabled
+ */
+#define CELL_IOMMU_REAL_UNMAP
 
-typedef struct {
-	unsigned long val;
-} ioste;
+/* Define CELL_IOMMU_STRICT_PROTECTION to enforce protection of
+ * IO PTEs based on the transfer direction. That can be enabled
+ * once spider-net has been fixed to pass the correct direction
+ * to the DMA mapping functions
+ */
+#define CELL_IOMMU_STRICT_PROTECTION
+
+
+#define NR_IOMMUS			2
+
+/* IOC mmap registers */
+#define IOC_Reg_Size			0x2000
+
+#define IOC_IOPT_CacheInvd		0x908
+#define IOC_IOPT_CacheInvd_NE_Mask	0xffe0000000000000ul
+#define IOC_IOPT_CacheInvd_IOPTE_Mask	0x000003fffffffff8ul
+#define IOC_IOPT_CacheInvd_Busy		0x0000000000000001ul
+
+#define IOC_IOST_Origin			0x918
+#define IOC_IOST_Origin_E		0x8000000000000000ul
+#define IOC_IOST_Origin_HW		0x0000000000000800ul
+#define IOC_IOST_Origin_HL		0x0000000000000400ul
+
+#define IOC_IO_ExcpStat			0x920
+#define IOC_IO_ExcpStat_V		0x8000000000000000ul
+#define IOC_IO_ExcpStat_SPF_Mask	0x6000000000000000ul
+#define IOC_IO_ExcpStat_SPF_S		0x6000000000000000ul
+#define IOC_IO_ExcpStat_SPF_P		0x4000000000000000ul
+#define IOC_IO_ExcpStat_ADDR_Mask	0x00000007fffff000ul
+#define IOC_IO_ExcpStat_RW_Mask		0x0000000000000800ul
+#define IOC_IO_ExcpStat_IOID_Mask	0x00000000000007fful
+
+#define IOC_IO_ExcpMask			0x928
+#define IOC_IO_ExcpMask_SFE		0x4000000000000000ul
+#define IOC_IO_ExcpMask_PFE		0x2000000000000000ul
+
+#define IOC_IOCmd_Offset		0x1000
+
+#define IOC_IOCmd_Cfg			0xc00
+#define IOC_IOCmd_Cfg_TE		0x0000800000000000ul
+
+
+/* Segment table entries */
+#define IOSTE_V			0x8000000000000000ul /* valid */
+#define IOSTE_H			0x4000000000000000ul /* cache hint */
+#define IOSTE_PT_Base_RPN_Mask  0x3ffffffffffff000ul /* base RPN of IOPT */
+#define IOSTE_NPPT_Mask		0x0000000000000fe0ul /* no. pages in IOPT */
+#define IOSTE_PS_Mask		0x0000000000000007ul /* page size */
+#define IOSTE_PS_4K		0x0000000000000001ul /*   - 4kB  */
+#define IOSTE_PS_64K		0x0000000000000003ul /*   - 64kB */
+#define IOSTE_PS_1M		0x0000000000000005ul /*   - 1MB  */
+#define IOSTE_PS_16M		0x0000000000000007ul /*   - 16MB */
+
+/* Page table entries */
+#define IOPTE_PP_W		0x8000000000000000ul /* protection: write */
+#define IOPTE_PP_R		0x4000000000000000ul /* protection: read */
+#define IOPTE_M			0x2000000000000000ul /* coherency required */
+#define IOPTE_SO_R		0x1000000000000000ul /* ordering: writes */
+#define IOPTE_SO_RW             0x1800000000000000ul /* ordering: r & w */
+#define IOPTE_RPN_Mask		0x07fffffffffff000ul /* RPN */
+#define IOPTE_H			0x0000000000000800ul /* cache hint */
+#define IOPTE_IOID_Mask		0x00000000000007fful /* ioid */
+
+
+/* IOMMU sizing */
+#define IO_SEGMENT_SHIFT	28
+#define IO_PAGENO_BITS		(IO_SEGMENT_SHIFT - IOMMU_PAGE_SHIFT)
+
+/* The high bit needs to be set on every DMA address */
+#define SPIDER_DMA_OFFSET	0x80000000ul
+
+struct iommu_window {
+	struct list_head list;
+	struct cbe_iommu *iommu;
+	unsigned long offset;
+	unsigned long size;
+	unsigned long pte_offset;
+	unsigned int ioid;
+	struct iommu_table table;
+};
 
-static inline ioste
-mk_ioste(unsigned long val)
-{
-	ioste ioste = { .val = val, };
-	return ioste;
-}
+#define NAMESIZE 8
+struct cbe_iommu {
+	int nid;
+	char name[NAMESIZE];
+	void __iomem *xlate_regs;
+	void __iomem *cmd_regs;
+	unsigned long *stab;
+	unsigned long *ptab;
+	void *pad_page;
+	struct list_head windows;
+};
+
+/* Static array of iommus, one per node
+ *   each contains a list of windows, keyed from dma_window property
+ *   - on bus setup, look for a matching window, or create one
+ *   - on dev setup, assign iommu_table ptr
+ */
+static struct cbe_iommu iommus[NR_IOMMUS];
+static int cbe_nr_iommus;
 
-static inline ioste
-get_iost_entry(unsigned long iopt_base, unsigned long io_address, unsigned page_size)
+static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte,
+		long n_ptes)
 {
-	unsigned long ps;
-	unsigned long iostep;
-	unsigned long nnpt;
-	unsigned long shift;
-
-	switch (page_size) {
-	case 0x1000000:
-		ps = IOST_PS_16M;
-		nnpt = 0;  /* one page per segment */
-		shift = 5; /* segment has 16 iopt entries */
-		break;
-
-	case 0x100000:
-		ps = IOST_PS_1M;
-		nnpt = 0;  /* one page per segment */
-		shift = 1; /* segment has 256 iopt entries */
-		break;
-
-	case 0x10000:
-		ps = IOST_PS_64K;
-		nnpt = 0x07; /* 8 pages per io page table */
-		shift = 0;   /* all entries are used */
-		break;
-
-	case 0x1000:
-		ps = IOST_PS_4K;
-		nnpt = 0x7f; /* 128 pages per io page table */
-		shift = 0;   /* all entries are used */
-		break;
-
-	default: /* not a known compile time constant */
-		{
-			/* BUILD_BUG_ON() is not usable here */
-			extern void __get_iost_entry_bad_page_size(void);
-			__get_iost_entry_bad_page_size();
-		}
-		break;
-	}
+	unsigned long *reg, val;
+	long n;
 
-	iostep = iopt_base +
-			 /* need 8 bytes per iopte */
-			(((io_address / page_size * 8)
-			 /* align io page tables on 4k page boundaries */
-				 << shift) 
-			 /* nnpt+1 pages go into each iopt */
-				 & ~(nnpt << 12));
-
-	nnpt++; /* this seems to work, but the documentation is not clear
-		   about wether we put nnpt or nnpt-1 into the ioste bits.
-		   In theory, this can't work for 4k pages. */
-	return mk_ioste(IOST_VALID_MASK
-			| (iostep & IOST_PT_BASE_MASK)
-			| ((nnpt << 5) & IOST_NNPT_MASK)
-			| (ps & IOST_PS_MASK));
-}
+	reg = iommu->xlate_regs + IOC_IOPT_CacheInvd;
 
-/* compute the address of an io pte */
-static inline unsigned long
-get_ioptep(ioste iost_entry, unsigned long io_address)
-{
-	unsigned long iopt_base;
-	unsigned long page_size;
-	unsigned long page_number;
-	unsigned long iopt_offset;
-
-	iopt_base = iost_entry.val & IOST_PT_BASE_MASK;
-	page_size = iost_entry.val & IOST_PS_MASK;
-
-	/* decode page size to compute page number */
-	page_number = (io_address & 0x0fffffff) >> (10 + 2 * page_size);
-	/* page number is an offset into the io page table */
-	iopt_offset = (page_number << 3) & 0x7fff8ul;
-	return iopt_base + iopt_offset;
-}
+	while (n_ptes > 0) {
+		/* we can invalidate up to 1 << 11 PTEs at once */
+		n = min(n_ptes, 1l << 11);
+		val = (((n /*- 1*/) << 53) & IOC_IOPT_CacheInvd_NE_Mask)
+			| (__pa(pte) & IOC_IOPT_CacheInvd_IOPTE_Mask)
+		        | IOC_IOPT_CacheInvd_Busy;
 
-/* compute the tag field of the iopt cache entry */
-static inline unsigned long
-get_ioc_tag(ioste iost_entry, unsigned long io_address)
-{
-	unsigned long iopte = get_ioptep(iost_entry, io_address);
+		out_be64(reg, val);
+		while (in_be64(reg) & IOC_IOPT_CacheInvd_Busy)
+			;
 
-	return IOPT_VALID_MASK
-	     | ((iopte & 0x00000000000000ff8ul) >> 3)
-	     | ((iopte & 0x0000003fffffc0000ul) >> 9);
+		n_ptes -= n;
+		pte += n;
+	}
 }
 
-/* compute the hashed 6 bit index for the 4-way associative pte cache */
-static inline unsigned long
-get_ioc_hash(ioste iost_entry, unsigned long io_address)
+static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
+		unsigned long uaddr, enum dma_data_direction direction)
 {
-	unsigned long iopte = get_ioptep(iost_entry, io_address);
-
-	return ((iopte & 0x000000000000001f8ul) >> 3)
-	     ^ ((iopte & 0x00000000000020000ul) >> 17)
-	     ^ ((iopte & 0x00000000000010000ul) >> 15)
-	     ^ ((iopte & 0x00000000000008000ul) >> 13)
-	     ^ ((iopte & 0x00000000000004000ul) >> 11)
-	     ^ ((iopte & 0x00000000000002000ul) >> 9)
-	     ^ ((iopte & 0x00000000000001000ul) >> 7);
+	int i;
+	unsigned long *io_pte, base_pte;
+	struct iommu_window *window =
+		container_of(tbl, struct iommu_window, table);
+
+	/* implementing proper protection causes problems with the spidernet
+	 * driver - check mapping directions later, but allow read & write by
+	 * default for now.*/
+#ifdef CELL_IOMMU_STRICT_PROTECTION
+	/* to avoid referencing a global, we use a trick here to setup the
+	 * protection bit. "prot" is setup to be 3 fields of 4 bits apprended
+	 * together for each of the 3 supported direction values. It is then
+	 * shifted left so that the fields matching the desired direction
+	 * lands on the appropriate bits, and other bits are masked out.
+	 */
+	const unsigned long prot = 0xc48;
+	base_pte =
+		((prot << (52 + 4 * direction)) & (IOPTE_PP_W | IOPTE_PP_R))
+		| IOPTE_M | IOPTE_SO_RW | (window->ioid & IOPTE_IOID_Mask);
+#else
+	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW |
+		(window->ioid & IOPTE_IOID_Mask);
+#endif
+
+	io_pte = (unsigned long *)tbl->it_base + (index - window->pte_offset);
+
+	for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE)
+		io_pte[i] = base_pte | (__pa(uaddr) & IOPTE_RPN_Mask);
+
+	mb();
+
+	invalidate_tce_cache(window->iommu, io_pte, npages);
+
+	pr_debug("tce_build_cell(index=%lx,n=%lx,dir=%d,base_pte=%lx)\n",
+		 index, npages, direction, base_pte);
 }
 
-/* same as above, but pretend that we have a simpler 1-way associative
-   pte cache with an 8 bit index */
-static inline unsigned long
-get_ioc_hash_1way(ioste iost_entry, unsigned long io_address)
+static void tce_free_cell(struct iommu_table *tbl, long index, long npages)
 {
-	unsigned long iopte = get_ioptep(iost_entry, io_address);
-
-	return ((iopte & 0x000000000000001f8ul) >> 3)
-	     ^ ((iopte & 0x00000000000020000ul) >> 17)
-	     ^ ((iopte & 0x00000000000010000ul) >> 15)
-	     ^ ((iopte & 0x00000000000008000ul) >> 13)
-	     ^ ((iopte & 0x00000000000004000ul) >> 11)
-	     ^ ((iopte & 0x00000000000002000ul) >> 9)
-	     ^ ((iopte & 0x00000000000001000ul) >> 7)
-	     ^ ((iopte & 0x0000000000000c000ul) >> 8);
-}
 
-static inline ioste
-get_iost_cache(void __iomem *base, unsigned long index)
-{
-	unsigned long __iomem *p = (base + IOC_ST_CACHE_DIR);
-	return mk_ioste(in_be64(&p[index]));
-}
+	int i;
+	unsigned long *io_pte, pte;
+	struct iommu_window *window =
+		container_of(tbl, struct iommu_window, table);
 
-static inline void
-set_iost_cache(void __iomem *base, unsigned long index, ioste ste)
-{
-	unsigned long __iomem *p = (base + IOC_ST_CACHE_DIR);
-	pr_debug("ioste %02lx was %016lx, store %016lx", index,
-			get_iost_cache(base, index).val, ste.val);
-	out_be64(&p[index], ste.val);
-	pr_debug(" now %016lx\n", get_iost_cache(base, index).val);
-}
+	pr_debug("tce_free_cell(index=%lx,n=%lx)\n", index, npages);
 
-static inline unsigned long
-get_iopt_cache(void __iomem *base, unsigned long index, unsigned long *tag)
-{
-	unsigned long __iomem *tags = (void *)(base + IOC_PT_CACHE_DIR);
-	unsigned long __iomem *p = (void *)(base + IOC_PT_CACHE_REG);	
+#ifdef CELL_IOMMU_REAL_UNMAP
+	pte = 0;
+#else
+	/* spider bridge does PCI reads after freeing - insert a mapping
+	 * to a scratch page instead of an invalid entry */
+	pte = IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW | __pa(window->iommu->pad_page)
+		| (window->ioid & IOPTE_IOID_Mask);
+#endif
 
-	*tag = tags[index];
-	rmb();
-	return *p;
-}
+	io_pte = (unsigned long *)tbl->it_base + (index - window->pte_offset);
 
-static inline void
-set_iopt_cache(void __iomem *base, unsigned long index,
-		 unsigned long tag, unsigned long val)
-{
-	unsigned long __iomem *tags = base + IOC_PT_CACHE_DIR;
-	unsigned long __iomem *p = base + IOC_PT_CACHE_REG;
+	for (i = 0; i < npages; i++)
+		io_pte[i] = pte;
+
+	mb();
 
-	out_be64(p, val);
-	out_be64(&tags[index], tag);
+	invalidate_tce_cache(window->iommu, io_pte, npages);
 }
 
-static inline void
-set_iost_origin(void __iomem *base)
+static irqreturn_t ioc_interrupt(int irq, void *data)
 {
-	unsigned long __iomem *p = base + IOC_ST_ORIGIN;
-	unsigned long origin = IOSTO_ENABLE | IOSTO_SW;
-
-	pr_debug("iost_origin %016lx, now %016lx\n", in_be64(p), origin);
-	out_be64(p, origin);
+	unsigned long stat;
+	struct cbe_iommu *iommu = data;
+
+	stat = in_be64(iommu->xlate_regs + IOC_IO_ExcpStat);
+
+	/* Might want to rate limit it */
+	printk(KERN_ERR "iommu: DMA exception 0x%016lx\n", stat);
+	printk(KERN_ERR "  V=%d, SPF=[%c%c], RW=%s, IOID=0x%04x\n",
+	       !!(stat & IOC_IO_ExcpStat_V),
+	       (stat & IOC_IO_ExcpStat_SPF_S) ? 'S' : ' ',
+	       (stat & IOC_IO_ExcpStat_SPF_P) ? 'P' : ' ',
+	       (stat & IOC_IO_ExcpStat_RW_Mask) ? "Read" : "Write",
+	       (unsigned int)(stat & IOC_IO_ExcpStat_IOID_Mask));
+	printk(KERN_ERR "  page=0x%016lx\n",
+	       stat & IOC_IO_ExcpStat_ADDR_Mask);
+
+	/* clear interrupt */
+	stat &= ~IOC_IO_ExcpStat_V;
+	out_be64(iommu->xlate_regs + IOC_IO_ExcpStat, stat);
+
+	return IRQ_HANDLED;
 }
 
-static inline void
-set_iocmd_config(void __iomem *base)
+static int cell_iommu_find_ioc(int nid, unsigned long *base)
 {
-	unsigned long __iomem *p = base + 0xc00;
-	unsigned long conf;
+	struct device_node *np;
+	struct resource r;
+
+	*base = 0;
+
+	/* First look for new style /be nodes */
+	for_each_node_by_name(np, "ioc") {
+		if (of_node_to_nid(np) != nid)
+			continue;
+		if (of_address_to_resource(np, 0, &r)) {
+			printk(KERN_ERR "iommu: can't get address for %s\n",
+			       np->full_name);
+			continue;
+		}
+		*base = r.start;
+		of_node_put(np);
+		return 0;
+	}
 
-	conf = in_be64(p);
-	pr_debug("iost_conf %016lx, now %016lx\n", conf, conf | IOCMD_CONF_TE);
-	out_be64(p, conf | IOCMD_CONF_TE);
+	/* Ok, let's try the old way */
+	for_each_node_by_type(np, "cpu") {
+		const unsigned int *nidp;
+		const unsigned long *tmp;
+
+		nidp = get_property(np, "node-id", NULL);
+		if (nidp && *nidp == nid) {
+			tmp = get_property(np, "ioc-translation", NULL);
+			if (tmp) {
+				*base = *tmp;
+				of_node_put(np);
+				return 0;
+			}
+		}
+	}
+
+	return -ENODEV;
 }
 
-static void enable_mapping(void __iomem *base, void __iomem *mmio_base)
+static void cell_iommu_setup_hardware(struct cbe_iommu *iommu, unsigned long size)
 {
-	set_iocmd_config(base);
-	set_iost_origin(mmio_base);
-}
+	struct page *page;
+	int ret, i;
+	unsigned long reg, segments, pages_per_segment, ptab_size, n_pte_pages;
+	unsigned long xlate_base;
+	unsigned int virq;
+
+	if (cell_iommu_find_ioc(iommu->nid, &xlate_base))
+		panic("%s: missing IOC register mappings for node %d\n",
+		      __FUNCTION__, iommu->nid);
+
+	iommu->xlate_regs = ioremap(xlate_base, IOC_Reg_Size);
+	iommu->cmd_regs = iommu->xlate_regs + IOC_IOCmd_Offset;
+
+	segments = size >> IO_SEGMENT_SHIFT;
+	pages_per_segment = 1ull << IO_PAGENO_BITS;
+
+	pr_debug("%s: iommu[%d]: segments: %lu, pages per segment: %lu\n",
+			__FUNCTION__, iommu->nid, segments, pages_per_segment);
+
+	/* set up the segment table */
+	page = alloc_pages_node(iommu->nid, GFP_KERNEL, 0);
+	BUG_ON(!page);
+	iommu->stab = page_address(page);
+	clear_page(iommu->stab);
+
+	/* ... and the page tables. Since these are contiguous, we can treat
+	 * the page tables as one array of ptes, like pSeries does.
+	 */
+	ptab_size = segments * pages_per_segment * sizeof(unsigned long);
+	pr_debug("%s: iommu[%d]: ptab_size: %lu, order: %d\n", __FUNCTION__,
+			iommu->nid, ptab_size, get_order(ptab_size));
+	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(ptab_size));
+	BUG_ON(!page);
+
+	iommu->ptab = page_address(page);
+	memset(iommu->ptab, 0, ptab_size);
+
+	/* allocate a bogus page for the end of each mapping */
+	page = alloc_pages_node(iommu->nid, GFP_KERNEL, 0);
+	BUG_ON(!page);
+	iommu->pad_page = page_address(page);
+	clear_page(iommu->pad_page);
+
+	/* number of pages needed for a page table */
+	n_pte_pages = (pages_per_segment *
+		       sizeof(unsigned long)) >> IOMMU_PAGE_SHIFT;
+
+	pr_debug("%s: iommu[%d]: stab at %p, ptab at %p, n_pte_pages: %lu\n",
+			__FUNCTION__, iommu->nid, iommu->stab, iommu->ptab,
+			n_pte_pages);
+
+	/* initialise the STEs */
+	reg = IOSTE_V | ((n_pte_pages - 1) << 5);
+
+	if (IOMMU_PAGE_SIZE == 0x1000)
+		reg |= IOSTE_PS_4K;
+	else if (IOMMU_PAGE_SIZE == 0x10000)
+		reg |= IOSTE_PS_64K;
+	else {
+		extern void __unknown_page_size_error(void);
+		__unknown_page_size_error();
+	}
+
+	pr_debug("Setting up IOMMU stab:\n");
+	for (i = 0; i * (1ul << IO_SEGMENT_SHIFT) < size; i++) {
+		iommu->stab[i] = reg |
+			(__pa(iommu->ptab) + n_pte_pages * IOMMU_PAGE_SIZE * i);
+		pr_debug("\t[%d] 0x%016lx\n", i, iommu->stab[i]);
+	}
 
-static void iommu_dev_setup_null(struct pci_dev *d) { }
-static void iommu_bus_setup_null(struct pci_bus *b) { }
+	/* ensure that the STEs have updated */
+	mb();
 
-struct cell_iommu {
-	unsigned long base;
-	unsigned long mmio_base;
-	void __iomem *mapped_base;
-	void __iomem *mapped_mmio_base;
-};
+	/* setup interrupts for the iommu. */
+	reg = in_be64(iommu->xlate_regs + IOC_IO_ExcpStat);
+	out_be64(iommu->xlate_regs + IOC_IO_ExcpStat,
+			reg & ~IOC_IO_ExcpStat_V);
+	out_be64(iommu->xlate_regs + IOC_IO_ExcpMask,
+			IOC_IO_ExcpMask_PFE | IOC_IO_ExcpMask_SFE);
 
-static struct cell_iommu cell_iommus[NR_CPUS];
+	virq = irq_create_mapping(NULL,
+			IIC_IRQ_IOEX_ATI | (iommu->nid << IIC_IRQ_NODE_SHIFT));
+	BUG_ON(virq == NO_IRQ);
 
-/* initialize the iommu to support a simple linear mapping
- * for each DMA window used by any device. For now, we
- * happen to know that there is only one DMA window in use,
- * starting at iopt_phys_offset. */
-static void cell_do_map_iommu(struct cell_iommu *iommu,
-			      unsigned int ioid,
-			      unsigned long map_start,
-			      unsigned long map_size)
-{
-	unsigned long io_address, real_address;
-	void __iomem *ioc_base, *ioc_mmio_base;
-	ioste ioste;
-	unsigned long index;
+	ret = request_irq(virq, ioc_interrupt, IRQF_DISABLED,
+			iommu->name, iommu);
+	BUG_ON(ret);
 
-	/* we pretend the io page table was at a very high address */
-	const unsigned long fake_iopt = 0x10000000000ul;
-	const unsigned long io_page_size = 0x1000000; /* use 16M pages */
-	const unsigned long io_segment_size = 0x10000000; /* 256M */
-
-	ioc_base = iommu->mapped_base;
-	ioc_mmio_base = iommu->mapped_mmio_base;
-
-	for (real_address = 0, io_address = map_start;
-	     io_address <= map_start + map_size;
-	     real_address += io_page_size, io_address += io_page_size) {
-		ioste = get_iost_entry(fake_iopt, io_address, io_page_size);
-		if ((real_address % io_segment_size) == 0) /* segment start */
-			set_iost_cache(ioc_mmio_base,
-				       io_address >> 28, ioste);
-		index = get_ioc_hash_1way(ioste, io_address);
-		pr_debug("addr %08lx, index %02lx, ioste %016lx\n",
-					 io_address, index, ioste.val);
-		set_iopt_cache(ioc_mmio_base,
-			get_ioc_hash_1way(ioste, io_address),
-			get_ioc_tag(ioste, io_address),
-			get_iopt_entry(real_address, ioid, IOPT_PROT_RW));
-	}
+	/* set the IOC segment table origin register (and turn on the iommu) */
+	reg = IOC_IOST_Origin_E | __pa(iommu->stab) | IOC_IOST_Origin_HW;
+	out_be64(iommu->xlate_regs + IOC_IOST_Origin, reg);
+	in_be64(iommu->xlate_regs + IOC_IOST_Origin);
+
+	/* turn on IO translation */
+	reg = in_be64(iommu->cmd_regs + IOC_IOCmd_Cfg) | IOC_IOCmd_Cfg_TE;
+	out_be64(iommu->cmd_regs + IOC_IOCmd_Cfg, reg);
 }
 
-static void iommu_devnode_setup(struct device_node *d)
+#if 0/* Unused for now */
+static struct iommu_window *find_window(struct cbe_iommu *iommu,
+		unsigned long offset, unsigned long size)
 {
-	const unsigned int *ioid;
-	unsigned long map_start, map_size, token;
-	const unsigned long *dma_window;
-	struct cell_iommu *iommu;
+	struct iommu_window *window;
 
-	ioid = get_property(d, "ioid", NULL);
-	if (!ioid)
-		pr_debug("No ioid entry found !\n");
+	/* todo: check for overlapping (but not equal) windows) */
 
-	dma_window = get_property(d, "ibm,dma-window", NULL);
-	if (!dma_window)
-		pr_debug("No ibm,dma-window entry found !\n");
+	list_for_each_entry(window, &(iommu->windows), list) {
+		if (window->offset == offset && window->size == size)
+			return window;
+	}
 
-	map_start = dma_window[1];
-	map_size = dma_window[2];
-	token = dma_window[0] >> 32;
+	return NULL;
+}
+#endif
 
-	iommu = &cell_iommus[token];
+static struct iommu_window * __init
+cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
+			unsigned long offset, unsigned long size,
+			unsigned long pte_offset)
+{
+	struct iommu_window *window;
+	const unsigned int *ioid;
 
-	cell_do_map_iommu(iommu, *ioid, map_start, map_size);
+	ioid = get_property(np, "ioid", NULL);
+	if (ioid == NULL)
+		printk(KERN_WARNING "iommu: missing ioid for %s using 0\n",
+		       np->full_name);
+
+	window = kmalloc_node(sizeof(*window), GFP_KERNEL, iommu->nid);
+	BUG_ON(window == NULL);
+
+	window->offset = offset;
+	window->size = size;
+	window->ioid = ioid ? *ioid : 0;
+	window->iommu = iommu;
+	window->pte_offset = pte_offset;
+
+	window->table.it_blocksize = 16;
+	window->table.it_base = (unsigned long)iommu->ptab;
+	window->table.it_index = iommu->nid;
+	window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) +
+		window->pte_offset;
+	window->table.it_size = size >> IOMMU_PAGE_SHIFT;
+
+	iommu_init_table(&window->table, iommu->nid);
+
+	pr_debug("\tioid      %d\n", window->ioid);
+	pr_debug("\tblocksize %ld\n", window->table.it_blocksize);
+	pr_debug("\tbase      0x%016lx\n", window->table.it_base);
+	pr_debug("\toffset    0x%lx\n", window->table.it_offset);
+	pr_debug("\tsize      %ld\n", window->table.it_size);
+
+	list_add(&window->list, &iommu->windows);
+
+	if (offset != 0)
+		return window;
+
+	/* We need to map and reserve the first IOMMU page since it's used
+	 * by the spider workaround. In theory, we only need to do that when
+	 * running on spider but it doesn't really matter.
+	 *
+	 * This code also assumes that we have a window that starts at 0,
+	 * which is the case on all spider based blades.
+	 */
+	__set_bit(0, window->table.it_map);
+	tce_build_cell(&window->table, window->table.it_offset, 1,
+		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE);
+	window->table.it_hint = window->table.it_blocksize;
+
+	return window;
 }
 
-static void iommu_bus_setup(struct pci_bus *b)
+static struct cbe_iommu *cell_iommu_for_node(int nid)
 {
-	struct device_node *d = (struct device_node *)b->sysdata;
-	iommu_devnode_setup(d);
-}
+	int i;
 
+	for (i = 0; i < cbe_nr_iommus; i++)
+		if (iommus[i].nid == nid)
+			return &iommus[i];
+	return NULL;
+}
 
-static int cell_map_iommu_hardcoded(int num_nodes)
+static void cell_dma_dev_setup(struct device *dev)
 {
-	struct cell_iommu *iommu = NULL;
-
-	pr_debug("%s(%d): Using hardcoded defaults\n", __FUNCTION__, __LINE__);
+	struct iommu_window *window;
+	struct cbe_iommu *iommu;
+	struct dev_archdata *archdata = &dev->archdata;
+
+	/* If we run without iommu, no need to do anything */
+	if (pci_dma_ops == &dma_direct_ops)
+		return;
+
+	/* Current implementation uses the first window available in that
+	 * node's iommu. We -might- do something smarter later though it may
+	 * never be necessary
+	 */
+	iommu = cell_iommu_for_node(archdata->numa_node);
+	if (iommu == NULL || list_empty(&iommu->windows)) {
+		printk(KERN_ERR "iommu: missing iommu for %s (node %d)\n",
+		       archdata->of_node ? archdata->of_node->full_name : "?",
+		       archdata->numa_node);
+		return;
+	}
+	window = list_entry(iommu->windows.next, struct iommu_window, list);
 
-	/* node 0 */
-	iommu = &cell_iommus[0];
-	iommu->mapped_base = ioremap(0x20000511000ul, 0x1000);
-	iommu->mapped_mmio_base = ioremap(0x20000510000ul, 0x1000);
+	archdata->dma_data = &window->table;
+}
 
-	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
+static void cell_pci_dma_dev_setup(struct pci_dev *dev)
+{
+	cell_dma_dev_setup(&dev->dev);
+}
 
-	cell_do_map_iommu(iommu, 0x048a,
-			  0x20000000ul,0x20000000ul);
+static int cell_of_bus_notify(struct notifier_block *nb, unsigned long action,
+			      void *data)
+{
+	struct device *dev = data;
 
-	if (num_nodes < 2)
+	/* We are only intereted in device addition */
+	if (action != BUS_NOTIFY_ADD_DEVICE)
 		return 0;
 
-	/* node 1 */
-	iommu = &cell_iommus[1];
-	iommu->mapped_base = ioremap(0x30000511000ul, 0x1000);
-	iommu->mapped_mmio_base = ioremap(0x30000510000ul, 0x1000);
-
-	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
+	/* We use the PCI DMA ops */
+	dev->archdata.dma_ops = pci_dma_ops;
 
-	cell_do_map_iommu(iommu, 0x048a,
-			  0x20000000,0x20000000ul);
+	cell_dma_dev_setup(dev);
 
 	return 0;
 }
 
+static struct notifier_block cell_of_bus_notifier = {
+	.notifier_call = cell_of_bus_notify
+};
 
-static int cell_map_iommu(void)
+static int __init cell_iommu_get_window(struct device_node *np,
+					 unsigned long *base,
+					 unsigned long *size)
 {
-	unsigned int num_nodes = 0;
-	const unsigned int *node_id;
-	const unsigned long *base, *mmio_base;
-	struct device_node *dn;
-	struct cell_iommu *iommu = NULL;
-
-	/* determine number of nodes (=iommus) */
-	pr_debug("%s(%d): determining number of nodes...", __FUNCTION__, __LINE__);
-	for(dn = of_find_node_by_type(NULL, "cpu");
-	    dn;
-	    dn = of_find_node_by_type(dn, "cpu")) {
-		node_id = get_property(dn, "node-id", NULL);
-
-		if (num_nodes < *node_id)
-			num_nodes = *node_id;
-		}
-
-	num_nodes++;
-	pr_debug("%i found.\n", num_nodes);
+	const void *dma_window;
+	unsigned long index;
 
-	/* map the iommu registers for each node */
-	pr_debug("%s(%d): Looping through nodes\n", __FUNCTION__, __LINE__);
-	for(dn = of_find_node_by_type(NULL, "cpu");
-	    dn;
-	    dn = of_find_node_by_type(dn, "cpu")) {
+	/* Use ibm,dma-window if available, else, hard code ! */
+	dma_window = get_property(np, "ibm,dma-window", NULL);
+	if (dma_window == NULL) {
+		*base = 0;
+		*size = 0x80000000u;
+		return -ENODEV;
+	}
 
-		node_id = get_property(dn, "node-id", NULL);
-		base = get_property(dn, "ioc-cache", NULL);
-		mmio_base = get_property(dn, "ioc-translation", NULL);
+	of_parse_dma_window(np, dma_window, &index, base, size);
+	return 0;
+}
 
-		if (!base || !mmio_base || !node_id)
-			return cell_map_iommu_hardcoded(num_nodes);
+static void __init cell_iommu_init_one(struct device_node *np, unsigned long offset)
+{
+	struct cbe_iommu *iommu;
+	unsigned long base, size;
+	int nid, i;
+
+	/* Get node ID */
+	nid = of_node_to_nid(np);
+	if (nid < 0) {
+		printk(KERN_ERR "iommu: failed to get node for %s\n",
+		       np->full_name);
+		return;
+	}
+	pr_debug("iommu: setting up iommu for node %d (%s)\n",
+		 nid, np->full_name);
+
+	/* XXX todo: If we can have multiple windows on the same IOMMU, which
+	 * isn't the case today, we probably want here to check wether the
+	 * iommu for that node is already setup.
+	 * However, there might be issue with getting the size right so let's
+	 * ignore that for now. We might want to completely get rid of the
+	 * multiple window support since the cell iommu supports per-page ioids
+	 */
+
+	if (cbe_nr_iommus >= NR_IOMMUS) {
+		printk(KERN_ERR "iommu: too many IOMMUs detected ! (%s)\n",
+		       np->full_name);
+		return;
+	}
 
-		iommu = &cell_iommus[*node_id];
-		iommu->base = *base;
-		iommu->mmio_base = *mmio_base;
+	/* Init base fields */
+	i = cbe_nr_iommus++;
+	iommu = &iommus[i];
+	iommu->stab = 0;
+	iommu->nid = nid;
+	snprintf(iommu->name, sizeof(iommu->name), "iommu%d", i);
+	INIT_LIST_HEAD(&iommu->windows);
 
-		iommu->mapped_base = ioremap(*base, 0x1000);
-		iommu->mapped_mmio_base = ioremap(*mmio_base, 0x1000);
+	/* Obtain a window for it */
+	cell_iommu_get_window(np, &base, &size);
 
-		enable_mapping(iommu->mapped_base,
-			       iommu->mapped_mmio_base);
+	pr_debug("\ttranslating window 0x%lx...0x%lx\n",
+		 base, base + size - 1);
 
-		/* everything else will be done in iommu_bus_setup */
-	}
+	/* Initialize the hardware */
+	cell_iommu_setup_hardware(iommu, size);
 
-	return 1;
+	/* Setup the iommu_table */
+	cell_iommu_setup_window(iommu, np, base, size,
+				offset >> IOMMU_PAGE_SHIFT);
 }
 
-static void *cell_alloc_coherent(struct device *hwdev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag)
+static void __init cell_disable_iommus(void)
 {
-	void *ret;
-
-	ret = (void *)__get_free_pages(flag, get_order(size));
-	if (ret != NULL) {
-		memset(ret, 0, size);
-		*dma_handle = virt_to_abs(ret) | CELL_DMA_VALID;
+	int node;
+	unsigned long base, val;
+	void __iomem *xregs, *cregs;
+
+	/* Make sure IOC translation is disabled on all nodes */
+	for_each_online_node(node) {
+		if (cell_iommu_find_ioc(node, &base))
+			continue;
+		xregs = ioremap(base, IOC_Reg_Size);
+		if (xregs == NULL)
+			continue;
+		cregs = xregs + IOC_IOCmd_Offset;
+
+		pr_debug("iommu: cleaning up iommu on node %d\n", node);
+
+		out_be64(xregs + IOC_IOST_Origin, 0);
+		(void)in_be64(xregs + IOC_IOST_Origin);
+		val = in_be64(cregs + IOC_IOCmd_Cfg);
+		val &= ~IOC_IOCmd_Cfg_TE;
+		out_be64(cregs + IOC_IOCmd_Cfg, val);
+		(void)in_be64(cregs + IOC_IOCmd_Cfg);
+
+		iounmap(xregs);
 	}
-	return ret;
 }
 
-static void cell_free_coherent(struct device *hwdev, size_t size,
-				 void *vaddr, dma_addr_t dma_handle)
+static int __init cell_iommu_init_disabled(void)
 {
-	free_pages((unsigned long)vaddr, get_order(size));
-}
+	struct device_node *np = NULL;
+	unsigned long base = 0, size;
+
+	/* When no iommu is present, we use direct DMA ops */
+	pci_dma_ops = &dma_direct_ops;
+
+	/* First make sure all IOC translation is turned off */
+	cell_disable_iommus();
+
+	/* If we have no Axon, we set up the spider DMA magic offset */
+	if (of_find_node_by_name(NULL, "axon") == NULL)
+		dma_direct_offset = SPIDER_DMA_OFFSET;
+
+	/* Now we need to check to see where the memory is mapped
+	 * in PCI space. We assume that all busses use the same dma
+	 * window which is always the case so far on Cell, thus we
+	 * pick up the first pci-internal node we can find and check
+	 * the DMA window from there.
+	 */
+	for_each_node_by_name(np, "axon") {
+		if (np->parent == NULL || np->parent->parent != NULL)
+			continue;
+		if (cell_iommu_get_window(np, &base, &size) == 0)
+			break;
+	}
+	if (np == NULL) {
+		for_each_node_by_name(np, "pci-internal") {
+			if (np->parent == NULL || np->parent->parent != NULL)
+				continue;
+			if (cell_iommu_get_window(np, &base, &size) == 0)
+				break;
+		}
+	}
+	of_node_put(np);
+
+	/* If we found a DMA window, we check if it's big enough to enclose
+	 * all of physical memory. If not, we force enable IOMMU
+	 */
+	if (np && size < lmb_end_of_DRAM()) {
+		printk(KERN_WARNING "iommu: force-enabled, dma window"
+		       " (%ldMB) smaller than total memory (%ldMB)\n",
+		       size >> 20, lmb_end_of_DRAM() >> 20);
+		return -ENODEV;
+	}
 
-static dma_addr_t cell_map_single(struct device *hwdev, void *ptr,
-		size_t size, enum dma_data_direction direction)
-{
-	return virt_to_abs(ptr) | CELL_DMA_VALID;
-}
+	dma_direct_offset += base;
 
-static void cell_unmap_single(struct device *hwdev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction direction)
-{
+	printk("iommu: disabled, direct DMA offset is 0x%lx\n",
+	       dma_direct_offset);
+
+	return 0;
 }
 
-static int cell_map_sg(struct device *hwdev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction)
+static int __init cell_iommu_init(void)
 {
-	int i;
+	struct device_node *np;
+
+	if (!machine_is(cell))
+		return -ENODEV;
+
+	/* If IOMMU is disabled or we have little enough RAM to not need
+	 * to enable it, we setup a direct mapping.
+	 *
+	 * Note: should we make sure we have the IOMMU actually disabled ?
+	 */
+	if (iommu_is_off ||
+	    (!iommu_force_on && lmb_end_of_DRAM() <= 0x80000000ull))
+		if (cell_iommu_init_disabled() == 0)
+			goto bail;
+
+	/* Setup various ppc_md. callbacks */
+	ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup;
+	ppc_md.tce_build = tce_build_cell;
+	ppc_md.tce_free = tce_free_cell;
+
+	/* Create an iommu for each /axon node.  */
+	for_each_node_by_name(np, "axon") {
+		if (np->parent == NULL || np->parent->parent != NULL)
+			continue;
+		cell_iommu_init_one(np, 0);
+	}
 
-	for (i = 0; i < nents; i++, sg++) {
-		sg->dma_address = (page_to_phys(sg->page) + sg->offset)
-					| CELL_DMA_VALID;
-		sg->dma_length = sg->length;
+	/* Create an iommu for each toplevel /pci-internal node for
+	 * old hardware/firmware
+	 */
+	for_each_node_by_name(np, "pci-internal") {
+		if (np->parent == NULL || np->parent->parent != NULL)
+			continue;
+		cell_iommu_init_one(np, SPIDER_DMA_OFFSET);
 	}
 
-	return nents;
-}
+	/* Setup default PCI iommu ops */
+	pci_dma_ops = &dma_iommu_ops;
 
-static void cell_unmap_sg(struct device *hwdev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction)
-{
-}
+ bail:
+	/* Register callbacks on OF platform device addition/removal
+	 * to handle linking them to the right DMA operations
+	 */
+	bus_register_notifier(&of_platform_bus_type, &cell_of_bus_notifier);
 
-static int cell_dma_supported(struct device *dev, u64 mask)
-{
-	return mask < 0x100000000ull;
+	return 0;
 }
+arch_initcall(cell_iommu_init);
 
-static struct dma_mapping_ops cell_iommu_ops = {
-	.alloc_coherent = cell_alloc_coherent,
-	.free_coherent = cell_free_coherent,
-	.map_single = cell_map_single,
-	.unmap_single = cell_unmap_single,
-	.map_sg = cell_map_sg,
-	.unmap_sg = cell_unmap_sg,
-	.dma_supported = cell_dma_supported,
-};
-
-void cell_init_iommu(void)
-{
-	int setup_bus = 0;
-
-	if (of_find_node_by_path("/mambo")) {
-		pr_info("Not using iommu on systemsim\n");
-	} else {
-
-		if (!(of_chosen &&
-		      get_property(of_chosen, "linux,iommu-off", NULL)))
-			setup_bus = cell_map_iommu();
-
-		if (setup_bus) {
-			pr_debug("%s: IOMMU mapping activated\n", __FUNCTION__);
-			ppc_md.iommu_dev_setup = iommu_dev_setup_null;
-			ppc_md.iommu_bus_setup = iommu_bus_setup;
-		} else {
-			pr_debug("%s: IOMMU mapping activated, "
-				 "no device action necessary\n", __FUNCTION__);
-			/* Direct I/O, IOMMU off */
-			ppc_md.iommu_dev_setup = iommu_dev_setup_null;
-			ppc_md.iommu_bus_setup = iommu_bus_setup_null;
-		}
-	}
-
-	pci_dma_ops = cell_iommu_ops;
-}
diff --git a/arch/powerpc/platforms/cell/iommu.h b/arch/powerpc/platforms/cell/iommu.h
deleted file mode 100644
index 490d77abfe85..000000000000
--- a/arch/powerpc/platforms/cell/iommu.h
+++ /dev/null
@@ -1,65 +0,0 @@
-#ifndef CELL_IOMMU_H
-#define CELL_IOMMU_H
-
-/* some constants */
-enum {
-	/* segment table entries */
-	IOST_VALID_MASK	  = 0x8000000000000000ul,
-	IOST_TAG_MASK     = 0x3000000000000000ul,
-	IOST_PT_BASE_MASK = 0x000003fffffff000ul,
-	IOST_NNPT_MASK	  = 0x0000000000000fe0ul,
-	IOST_PS_MASK	  = 0x000000000000000ful,
-
-	IOST_PS_4K	  = 0x1,
-	IOST_PS_64K	  = 0x3,
-	IOST_PS_1M	  = 0x5,
-	IOST_PS_16M	  = 0x7,
-
-	/* iopt tag register */
-	IOPT_VALID_MASK   = 0x0000000200000000ul,
-	IOPT_TAG_MASK	  = 0x00000001fffffffful,
-
-	/* iopt cache register */
-	IOPT_PROT_MASK	  = 0xc000000000000000ul,
-	IOPT_PROT_NONE	  = 0x0000000000000000ul,
-	IOPT_PROT_READ	  = 0x4000000000000000ul,
-	IOPT_PROT_WRITE	  = 0x8000000000000000ul,
-	IOPT_PROT_RW	  = 0xc000000000000000ul,
-	IOPT_COHERENT	  = 0x2000000000000000ul,
-	
-	IOPT_ORDER_MASK	  = 0x1800000000000000ul,
-	/* order access to same IOID/VC on same address */
-	IOPT_ORDER_ADDR	  = 0x0800000000000000ul,
-	/* similar, but only after a write access */
-	IOPT_ORDER_WRITES = 0x1000000000000000ul,
-	/* Order all accesses to same IOID/VC */
-	IOPT_ORDER_VC	  = 0x1800000000000000ul,
-	
-	IOPT_RPN_MASK	  = 0x000003fffffff000ul,
-	IOPT_HINT_MASK	  = 0x0000000000000800ul,
-	IOPT_IOID_MASK	  = 0x00000000000007fful,
-
-	IOSTO_ENABLE	  = 0x8000000000000000ul,
-	IOSTO_ORIGIN	  = 0x000003fffffff000ul,
-	IOSTO_HW	  = 0x0000000000000800ul,
-	IOSTO_SW	  = 0x0000000000000400ul,
-
-	IOCMD_CONF_TE	  = 0x0000800000000000ul,
-
-	/* memory mapped registers */
-	IOC_PT_CACHE_DIR  = 0x000,
-	IOC_ST_CACHE_DIR  = 0x800,
-	IOC_PT_CACHE_REG  = 0x910,
-	IOC_ST_ORIGIN     = 0x918,
-	IOC_CONF	  = 0x930,
-
-	/* The high bit needs to be set on every DMA address,
-	   only 2GB are addressable */
-	CELL_DMA_VALID	  = 0x80000000,
-	CELL_DMA_MASK	  = 0x7fffffff,
-};
-
-
-void cell_init_iommu(void);
-
-#endif
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index 9f2e4ed20a57..8c20f0fb8651 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -38,32 +38,25 @@
 #include "pervasive.h"
 #include "cbe_regs.h"
 
-static DEFINE_SPINLOCK(cbe_pervasive_lock);
-
-static void __init cbe_enable_pause_zero(void)
+static void cbe_power_save(void)
 {
-	unsigned long thread_switch_control;
-	unsigned long temp_register;
-	struct cbe_pmd_regs __iomem *pregs;
-
-	spin_lock_irq(&cbe_pervasive_lock);
-	pregs = cbe_get_cpu_pmd_regs(smp_processor_id());
-	if (pregs == NULL)
-		goto out;
+	unsigned long ctrl, thread_switch_control;
 
-	pr_debug("Power Management: CPU %d\n", smp_processor_id());
-
-	 /* Enable Pause(0) control bit */
-	temp_register = in_be64(&pregs->pm_control);
+	/*
+	 * We need to hard disable interrupts, but we also need to mark them
+	 * hard disabled in the PACA so that the local_irq_enable() done by
+	 * our caller upon return propertly hard enables.
+	 */
+	hard_irq_disable();
+	get_paca()->hard_enabled = 0;
 
-	out_be64(&pregs->pm_control,
-		 temp_register | CBE_PMD_PAUSE_ZERO_CONTROL);
+	ctrl = mfspr(SPRN_CTRLF);
 
 	/* Enable DEC and EE interrupt request */
 	thread_switch_control  = mfspr(SPRN_TSC_CELL);
 	thread_switch_control |= TSC_CELL_EE_ENABLE | TSC_CELL_EE_BOOST;
 
-	switch ((mfspr(SPRN_CTRLF) & CTRL_CT)) {
+	switch (ctrl & CTRL_CT) {
 	case CTRL_CT0:
 		thread_switch_control |= TSC_CELL_DEC_ENABLE_0;
 		break;
@@ -75,58 +68,21 @@ static void __init cbe_enable_pause_zero(void)
 			__FUNCTION__);
 		break;
 	}
-
 	mtspr(SPRN_TSC_CELL, thread_switch_control);
 
-out:
-	spin_unlock_irq(&cbe_pervasive_lock);
-}
-
-static void cbe_idle(void)
-{
-	unsigned long ctrl;
+	/*
+	 * go into low thread priority, medium priority will be
+	 * restored for us after wake-up.
+	 */
+	HMT_low();
 
-	/* Why do we do that on every idle ? Couldn't that be done once for
-	 * all or do we lose the state some way ? Also, the pm_control
-	 * register setting, that can't be set once at boot ? We really want
-	 * to move that away in order to implement a simple powersave
+	/*
+	 * atomically disable thread execution and runlatch.
+	 * External and Decrementer exceptions are still handled when the
+	 * thread is disabled but now enter in cbe_system_reset_exception()
 	 */
-	cbe_enable_pause_zero();
-
-	while (1) {
-		if (!need_resched()) {
-			local_irq_disable();
-			while (!need_resched()) {
-				/* go into low thread priority */
-				HMT_low();
-
-				/*
-				 * atomically disable thread execution
-				 * and runlatch.
-				 * External and Decrementer exceptions
-				 * are still handled when the thread
-				 * is disabled but now enter in
-				 * cbe_system_reset_exception()
-				 */
-				ctrl = mfspr(SPRN_CTRLF);
-				ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
-				mtspr(SPRN_CTRLT, ctrl);
-			}
-			/* restore thread prio */
-			HMT_medium();
-			local_irq_enable();
-		}
-
-		/*
-		 * turn runlatch on again before scheduling the
-		 * process we just woke up
-		 */
-		ppc64_runlatch_on();
-
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
-	}
+	ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
+	mtspr(SPRN_CTRLT, ctrl);
 }
 
 static int cbe_system_reset_exception(struct pt_regs *regs)
@@ -158,9 +114,20 @@ static int cbe_system_reset_exception(struct pt_regs *regs)
 
 void __init cbe_pervasive_init(void)
 {
+	int cpu;
 	if (!cpu_has_feature(CPU_FTR_PAUSE_ZERO))
 		return;
 
-	ppc_md.idle_loop = cbe_idle;
+	for_each_possible_cpu(cpu) {
+		struct cbe_pmd_regs __iomem *regs = cbe_get_cpu_pmd_regs(cpu);
+		if (!regs)
+			continue;
+
+		 /* Enable Pause(0) control bit */
+		out_be64(&regs->pmcr, in_be64(&regs->pmcr) |
+					    CBE_PMD_PAUSE_ZERO_CONTROL);
+	}
+
+	ppc_md.power_save = cbe_power_save;
 	ppc_md.system_reset_exception = cbe_system_reset_exception;
 }
diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
new file mode 100644
index 000000000000..99c612025e8f
--- /dev/null
+++ b/arch/powerpc/platforms/cell/pmu.c
@@ -0,0 +1,429 @@
+/*
+ * Cell Broadband Engine Performance Monitor
+ *
+ * (C) Copyright IBM Corporation 2001,2006
+ *
+ * Author:
+ *    David Erb (djerb@us.ibm.com)
+ *    Kevin Corry (kevcorry@us.ibm.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, 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/interrupt.h>
+#include <linux/types.h>
+#include <asm/io.h>
+#include <asm/irq_regs.h>
+#include <asm/machdep.h>
+#include <asm/pmc.h>
+#include <asm/reg.h>
+#include <asm/spu.h>
+
+#include "cbe_regs.h"
+#include "interrupt.h"
+
+/*
+ * When writing to write-only mmio addresses, save a shadow copy. All of the
+ * registers are 32-bit, but stored in the upper-half of a 64-bit field in
+ * pmd_regs.
+ */
+
+#define WRITE_WO_MMIO(reg, x)					\
+	do {							\
+		u32 _x = (x);					\
+		struct cbe_pmd_regs __iomem *pmd_regs;		\
+		struct cbe_pmd_shadow_regs *shadow_regs;	\
+		pmd_regs = cbe_get_cpu_pmd_regs(cpu);		\
+		shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);	\
+		out_be64(&(pmd_regs->reg), (((u64)_x) << 32));	\
+		shadow_regs->reg = _x;				\
+	} while (0)
+
+#define READ_SHADOW_REG(val, reg)				\
+	do {							\
+		struct cbe_pmd_shadow_regs *shadow_regs;	\
+		shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);	\
+		(val) = shadow_regs->reg;			\
+	} while (0)
+
+#define READ_MMIO_UPPER32(val, reg)				\
+	do {							\
+		struct cbe_pmd_regs __iomem *pmd_regs;		\
+		pmd_regs = cbe_get_cpu_pmd_regs(cpu);		\
+		(val) = (u32)(in_be64(&pmd_regs->reg) >> 32);	\
+	} while (0)
+
+/*
+ * Physical counter registers.
+ * Each physical counter can act as one 32-bit counter or two 16-bit counters.
+ */
+
+u32 cbe_read_phys_ctr(u32 cpu, u32 phys_ctr)
+{
+	u32 val_in_latch, val = 0;
+
+	if (phys_ctr < NR_PHYS_CTRS) {
+		READ_SHADOW_REG(val_in_latch, counter_value_in_latch);
+
+		/* Read the latch or the actual counter, whichever is newer. */
+		if (val_in_latch & (1 << phys_ctr)) {
+			READ_SHADOW_REG(val, pm_ctr[phys_ctr]);
+		} else {
+			READ_MMIO_UPPER32(val, pm_ctr[phys_ctr]);
+		}
+	}
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(cbe_read_phys_ctr);
+
+void cbe_write_phys_ctr(u32 cpu, u32 phys_ctr, u32 val)
+{
+	struct cbe_pmd_shadow_regs *shadow_regs;
+	u32 pm_ctrl;
+
+	if (phys_ctr < NR_PHYS_CTRS) {
+		/* Writing to a counter only writes to a hardware latch.
+		 * The new value is not propagated to the actual counter
+		 * until the performance monitor is enabled.
+		 */
+		WRITE_WO_MMIO(pm_ctr[phys_ctr], val);
+
+		pm_ctrl = cbe_read_pm(cpu, pm_control);
+		if (pm_ctrl & CBE_PM_ENABLE_PERF_MON) {
+			/* The counters are already active, so we need to
+			 * rewrite the pm_control register to "re-enable"
+			 * the PMU.
+			 */
+			cbe_write_pm(cpu, pm_control, pm_ctrl);
+		} else {
+			shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);
+			shadow_regs->counter_value_in_latch |= (1 << phys_ctr);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(cbe_write_phys_ctr);
+
+/*
+ * "Logical" counter registers.
+ * These will read/write 16-bits or 32-bits depending on the
+ * current size of the counter. Counters 4 - 7 are always 16-bit.
+ */
+
+u32 cbe_read_ctr(u32 cpu, u32 ctr)
+{
+	u32 val;
+	u32 phys_ctr = ctr & (NR_PHYS_CTRS - 1);
+
+	val = cbe_read_phys_ctr(cpu, phys_ctr);
+
+	if (cbe_get_ctr_size(cpu, phys_ctr) == 16)
+		val = (ctr < NR_PHYS_CTRS) ? (val >> 16) : (val & 0xffff);
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(cbe_read_ctr);
+
+void cbe_write_ctr(u32 cpu, u32 ctr, u32 val)
+{
+	u32 phys_ctr;
+	u32 phys_val;
+
+	phys_ctr = ctr & (NR_PHYS_CTRS - 1);
+
+	if (cbe_get_ctr_size(cpu, phys_ctr) == 16) {
+		phys_val = cbe_read_phys_ctr(cpu, phys_ctr);
+
+		if (ctr < NR_PHYS_CTRS)
+			val = (val << 16) | (phys_val & 0xffff);
+		else
+			val = (val & 0xffff) | (phys_val & 0xffff0000);
+	}
+
+	cbe_write_phys_ctr(cpu, phys_ctr, val);
+}
+EXPORT_SYMBOL_GPL(cbe_write_ctr);
+
+/*
+ * Counter-control registers.
+ * Each "logical" counter has a corresponding control register.
+ */
+
+u32 cbe_read_pm07_control(u32 cpu, u32 ctr)
+{
+	u32 pm07_control = 0;
+
+	if (ctr < NR_CTRS)
+		READ_SHADOW_REG(pm07_control, pm07_control[ctr]);
+
+	return pm07_control;
+}
+EXPORT_SYMBOL_GPL(cbe_read_pm07_control);
+
+void cbe_write_pm07_control(u32 cpu, u32 ctr, u32 val)
+{
+	if (ctr < NR_CTRS)
+		WRITE_WO_MMIO(pm07_control[ctr], val);
+}
+EXPORT_SYMBOL_GPL(cbe_write_pm07_control);
+
+/*
+ * Other PMU control registers. Most of these are write-only.
+ */
+
+u32 cbe_read_pm(u32 cpu, enum pm_reg_name reg)
+{
+	u32 val = 0;
+
+	switch (reg) {
+	case group_control:
+		READ_SHADOW_REG(val, group_control);
+		break;
+
+	case debug_bus_control:
+		READ_SHADOW_REG(val, debug_bus_control);
+		break;
+
+	case trace_address:
+		READ_MMIO_UPPER32(val, trace_address);
+		break;
+
+	case ext_tr_timer:
+		READ_SHADOW_REG(val, ext_tr_timer);
+		break;
+
+	case pm_status:
+		READ_MMIO_UPPER32(val, pm_status);
+		break;
+
+	case pm_control:
+		READ_SHADOW_REG(val, pm_control);
+		break;
+
+	case pm_interval:
+		READ_SHADOW_REG(val, pm_interval);
+		break;
+
+	case pm_start_stop:
+		READ_SHADOW_REG(val, pm_start_stop);
+		break;
+	}
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(cbe_read_pm);
+
+void cbe_write_pm(u32 cpu, enum pm_reg_name reg, u32 val)
+{
+	switch (reg) {
+	case group_control:
+		WRITE_WO_MMIO(group_control, val);
+		break;
+
+	case debug_bus_control:
+		WRITE_WO_MMIO(debug_bus_control, val);
+		break;
+
+	case trace_address:
+		WRITE_WO_MMIO(trace_address, val);
+		break;
+
+	case ext_tr_timer:
+		WRITE_WO_MMIO(ext_tr_timer, val);
+		break;
+
+	case pm_status:
+		WRITE_WO_MMIO(pm_status, val);
+		break;
+
+	case pm_control:
+		WRITE_WO_MMIO(pm_control, val);
+		break;
+
+	case pm_interval:
+		WRITE_WO_MMIO(pm_interval, val);
+		break;
+
+	case pm_start_stop:
+		WRITE_WO_MMIO(pm_start_stop, val);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(cbe_write_pm);
+
+/*
+ * Get/set the size of a physical counter to either 16 or 32 bits.
+ */
+
+u32 cbe_get_ctr_size(u32 cpu, u32 phys_ctr)
+{
+	u32 pm_ctrl, size = 0;
+
+	if (phys_ctr < NR_PHYS_CTRS) {
+		pm_ctrl = cbe_read_pm(cpu, pm_control);
+		size = (pm_ctrl & CBE_PM_16BIT_CTR(phys_ctr)) ? 16 : 32;
+	}
+
+	return size;
+}
+EXPORT_SYMBOL_GPL(cbe_get_ctr_size);
+
+void cbe_set_ctr_size(u32 cpu, u32 phys_ctr, u32 ctr_size)
+{
+	u32 pm_ctrl;
+
+	if (phys_ctr < NR_PHYS_CTRS) {
+		pm_ctrl = cbe_read_pm(cpu, pm_control);
+		switch (ctr_size) {
+		case 16:
+			pm_ctrl |= CBE_PM_16BIT_CTR(phys_ctr);
+			break;
+
+		case 32:
+			pm_ctrl &= ~CBE_PM_16BIT_CTR(phys_ctr);
+			break;
+		}
+		cbe_write_pm(cpu, pm_control, pm_ctrl);
+	}
+}
+EXPORT_SYMBOL_GPL(cbe_set_ctr_size);
+
+/*
+ * Enable/disable the entire performance monitoring unit.
+ * When we enable the PMU, all pending writes to counters get committed.
+ */
+
+void cbe_enable_pm(u32 cpu)
+{
+	struct cbe_pmd_shadow_regs *shadow_regs;
+	u32 pm_ctrl;
+
+	shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);
+	shadow_regs->counter_value_in_latch = 0;
+
+	pm_ctrl = cbe_read_pm(cpu, pm_control) | CBE_PM_ENABLE_PERF_MON;
+	cbe_write_pm(cpu, pm_control, pm_ctrl);
+}
+EXPORT_SYMBOL_GPL(cbe_enable_pm);
+
+void cbe_disable_pm(u32 cpu)
+{
+	u32 pm_ctrl;
+	pm_ctrl = cbe_read_pm(cpu, pm_control) & ~CBE_PM_ENABLE_PERF_MON;
+	cbe_write_pm(cpu, pm_control, pm_ctrl);
+}
+EXPORT_SYMBOL_GPL(cbe_disable_pm);
+
+/*
+ * Reading from the trace_buffer.
+ * The trace buffer is two 64-bit registers. Reading from
+ * the second half automatically increments the trace_address.
+ */
+
+void cbe_read_trace_buffer(u32 cpu, u64 *buf)
+{
+	struct cbe_pmd_regs __iomem *pmd_regs = cbe_get_cpu_pmd_regs(cpu);
+
+	*buf++ = in_be64(&pmd_regs->trace_buffer_0_63);
+	*buf++ = in_be64(&pmd_regs->trace_buffer_64_127);
+}
+EXPORT_SYMBOL_GPL(cbe_read_trace_buffer);
+
+/*
+ * Enabling/disabling interrupts for the entire performance monitoring unit.
+ */
+
+u32 cbe_query_pm_interrupts(u32 cpu)
+{
+	return cbe_read_pm(cpu, pm_status);
+}
+EXPORT_SYMBOL_GPL(cbe_query_pm_interrupts);
+
+u32 cbe_clear_pm_interrupts(u32 cpu)
+{
+	/* Reading pm_status clears the interrupt bits. */
+	return cbe_query_pm_interrupts(cpu);
+}
+EXPORT_SYMBOL_GPL(cbe_clear_pm_interrupts);
+
+void cbe_enable_pm_interrupts(u32 cpu, u32 thread, u32 mask)
+{
+	/* Set which node and thread will handle the next interrupt. */
+	iic_set_interrupt_routing(cpu, thread, 0);
+
+	/* Enable the interrupt bits in the pm_status register. */
+	if (mask)
+		cbe_write_pm(cpu, pm_status, mask);
+}
+EXPORT_SYMBOL_GPL(cbe_enable_pm_interrupts);
+
+void cbe_disable_pm_interrupts(u32 cpu)
+{
+	cbe_clear_pm_interrupts(cpu);
+	cbe_write_pm(cpu, pm_status, 0);
+}
+EXPORT_SYMBOL_GPL(cbe_disable_pm_interrupts);
+
+static irqreturn_t cbe_pm_irq(int irq, void *dev_id)
+{
+	perf_irq(get_irq_regs());
+	return IRQ_HANDLED;
+}
+
+int __init cbe_init_pm_irq(void)
+{
+	unsigned int irq;
+	int rc, node;
+
+	for_each_node(node) {
+		irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI |
+					       (node << IIC_IRQ_NODE_SHIFT));
+		if (irq == NO_IRQ) {
+			printk("ERROR: Unable to allocate irq for node %d\n",
+			       node);
+			return -EINVAL;
+		}
+
+		rc = request_irq(irq, cbe_pm_irq,
+				 IRQF_DISABLED, "cbe-pmu-0", NULL);
+		if (rc) {
+			printk("ERROR: Request for irq on node %d failed\n",
+			       node);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+arch_initcall(cbe_init_pm_irq);
+
+void cbe_sync_irq(int node)
+{
+	unsigned int irq;
+
+	irq = irq_find_mapping(NULL,
+			       IIC_IRQ_IOEX_PMI
+			       | (node << IIC_IRQ_NODE_SHIFT));
+
+	if (irq == NO_IRQ) {
+		printk(KERN_WARNING "ERROR, unable to get existing irq %d " \
+		"for node %d\n", irq, node);
+		return;
+	}
+
+	synchronize_irq(irq);
+}
+EXPORT_SYMBOL_GPL(cbe_sync_irq);
+
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 22c228a49c33..36989c2eee66 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -50,9 +50,10 @@
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
 #include <asm/udbg.h>
+#include <asm/mpic.h>
+#include <asm/of_platform.h>
 
 #include "interrupt.h"
-#include "iommu.h"
 #include "cbe_regs.h"
 #include "pervasive.h"
 #include "ras.h"
@@ -80,24 +81,72 @@ static void cell_progress(char *s, unsigned short hex)
 	printk("*** %04x : %s\n", hex, s ? s : "");
 }
 
-static void __init cell_pcibios_fixup(void)
+static int __init cell_publish_devices(void)
 {
-	struct pci_dev *dev = NULL;
+	if (!machine_is(cell))
+		return 0;
+
+	/* Publish OF platform devices for southbridge IOs */
+	of_platform_bus_probe(NULL, NULL, NULL);
+
+	return 0;
+}
+device_initcall(cell_publish_devices);
+
+static void cell_mpic_cascade(unsigned int irq, struct irq_desc *desc)
+{
+	struct mpic *mpic = desc->handler_data;
+	unsigned int virq;
+
+	virq = mpic_get_one_irq(mpic);
+	if (virq != NO_IRQ)
+		generic_handle_irq(virq);
+	desc->chip->eoi(irq);
+}
 
-	for_each_pci_dev(dev)
-		pci_read_irq_line(dev);
+static void __init mpic_init_IRQ(void)
+{
+	struct device_node *dn;
+	struct mpic *mpic;
+	unsigned int virq;
+
+	for (dn = NULL;
+	     (dn = of_find_node_by_name(dn, "interrupt-controller"));) {
+		if (!device_is_compatible(dn, "CBEA,platform-open-pic"))
+			continue;
+
+		/* The MPIC driver will get everything it needs from the
+		 * device-tree, just pass 0 to all arguments
+		 */
+		mpic = mpic_alloc(dn, 0, 0, 0, 0, " MPIC     ");
+		if (mpic == NULL)
+			continue;
+		mpic_init(mpic);
+
+		virq = irq_of_parse_and_map(dn, 0);
+		if (virq == NO_IRQ)
+			continue;
+
+		printk(KERN_INFO "%s : hooking up to IRQ %d\n",
+		       dn->full_name, virq);
+		set_irq_data(virq, mpic);
+		set_irq_chained_handler(virq, cell_mpic_cascade);
+	}
 }
 
+
 static void __init cell_init_irq(void)
 {
 	iic_init_IRQ();
 	spider_init_IRQ();
+	mpic_init_IRQ();
 }
 
 static void __init cell_setup_arch(void)
 {
 #ifdef CONFIG_SPU_BASE
-	spu_priv1_ops         = &spu_priv1_mmio_ops;
+	spu_priv1_ops = &spu_priv1_mmio_ops;
+	spu_management_ops = &spu_management_of_ops;
 #endif
 
 	cbe_regs_init();
@@ -109,7 +158,6 @@ static void __init cell_setup_arch(void)
 #ifdef CONFIG_SMP
 	smp_init_cell();
 #endif
-
 	/* init to some ~sane value until calibrate_delay() runs */
 	loops_per_jiffy = 50000000;
 
@@ -129,19 +177,6 @@ static void __init cell_setup_arch(void)
 	mmio_nvram_init();
 }
 
-/*
- * Early initialization.  Relocation is on but do not reference unbolted pages
- */
-static void __init cell_init_early(void)
-{
-	DBG(" -> cell_init_early()\n");
-
-	cell_init_iommu();
-
-	DBG(" <- cell_init_early()\n");
-}
-
-
 static int __init cell_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
@@ -168,7 +203,6 @@ define_machine(cell) {
 	.name			= "Cell",
 	.probe			= cell_probe,
 	.setup_arch		= cell_setup_arch,
-	.init_early		= cell_init_early,
 	.show_cpuinfo		= cell_show_cpuinfo,
 	.restart		= rtas_restart,
 	.power_off		= rtas_power_off,
@@ -180,7 +214,7 @@ define_machine(cell) {
 	.check_legacy_ioport	= cell_check_legacy_ioport,
 	.progress		= cell_progress,
 	.init_IRQ       	= cell_init_irq,
-	.pcibios_fixup		= cell_pcibios_fixup,
+	.pci_setup_phb		= rtas_setup_phb,
 #ifdef CONFIG_KEXEC
 	.machine_kexec		= default_machine_kexec,
 	.machine_kexec_prepare	= default_machine_kexec_prepare,
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 7aa809d5a244..bd7bffc3ddd0 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -25,22 +25,17 @@
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/poll.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
-
-#include <asm/firmware.h>
-#include <asm/io.h>
-#include <asm/prom.h>
+#include <linux/mm.h>
+#include <linux/io.h>
 #include <linux/mutex.h>
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
-#include <asm/mmu_context.h>
-
-#include "interrupt.h"
+#include <asm/xmon.h>
 
+const struct spu_management_ops *spu_management_ops;
 const struct spu_priv1_ops *spu_priv1_ops;
 
 EXPORT_SYMBOL_GPL(spu_priv1_ops);
@@ -89,7 +84,30 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
 		printk("%s: invalid access during switch!\n", __func__);
 		return 1;
 	}
-	if (!mm || (REGION_ID(ea) != USER_REGION_ID)) {
+	esid = (ea & ESID_MASK) | SLB_ESID_V;
+
+	switch(REGION_ID(ea)) {
+	case USER_REGION_ID:
+#ifdef CONFIG_HUGETLB_PAGE
+		if (in_hugepage_area(mm->context, ea))
+			llp = mmu_psize_defs[mmu_huge_psize].sllp;
+		else
+#endif
+			llp = mmu_psize_defs[mmu_virtual_psize].sllp;
+		vsid = (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT) |
+				SLB_VSID_USER | llp;
+		break;
+	case VMALLOC_REGION_ID:
+		llp = mmu_psize_defs[mmu_virtual_psize].sllp;
+		vsid = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) |
+			SLB_VSID_KERNEL | llp;
+		break;
+	case KERNEL_REGION_ID:
+		llp = mmu_psize_defs[mmu_linear_psize].sllp;
+		vsid = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) |
+			SLB_VSID_KERNEL | llp;
+		break;
+	default:
 		/* Future: support kernel segments so that drivers
 		 * can use SPUs.
 		 */
@@ -97,16 +115,6 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
 		return 1;
 	}
 
-	esid = (ea & ESID_MASK) | SLB_ESID_V;
-#ifdef CONFIG_HUGETLB_PAGE
-	if (in_hugepage_area(mm->context, ea))
-		llp = mmu_psize_defs[mmu_huge_psize].sllp;
-	else
-#endif
-		llp = mmu_psize_defs[mmu_virtual_psize].sllp;
-	vsid = (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT) |
-			SLB_VSID_USER | llp;
-
 	out_be64(&priv2->slb_index_W, spu->slb_replace);
 	out_be64(&priv2->slb_vsid_RW, vsid);
 	out_be64(&priv2->slb_esid_RW, esid);
@@ -320,6 +328,7 @@ static void spu_free_irqs(struct spu *spu)
 }
 
 static struct list_head spu_list[MAX_NUMNODES];
+static LIST_HEAD(spu_full_list);
 static DEFINE_MUTEX(spu_mutex);
 
 static void spu_init_channels(struct spu *spu)
@@ -364,8 +373,7 @@ struct spu *spu_alloc_node(int node)
 	if (!list_empty(&spu_list[node])) {
 		spu = list_entry(spu_list[node].next, struct spu, list);
 		list_del_init(&spu->list);
-		pr_debug("Got SPU %x %d %d\n",
-			 spu->isrc, spu->number, spu->node);
+		pr_debug("Got SPU %d %d\n", spu->number, spu->node);
 		spu_init_channels(spu);
 	}
 	mutex_unlock(&spu_mutex);
@@ -493,280 +501,65 @@ int spu_irq_class_1_bottom(struct spu *spu)
 	if (!error) {
 		spu_restart_dma(spu);
 	} else {
-		__spu_trap_invalid_dma(spu);
+		spu->dma_callback(spu, SPE_EVENT_SPE_DATA_STORAGE);
 	}
 	return ret;
 }
 
-static int __init find_spu_node_id(struct device_node *spe)
-{
-	const unsigned int *id;
-	struct device_node *cpu;
-	cpu = spe->parent->parent;
-	id = get_property(cpu, "node-id", NULL);
-	return id ? *id : 0;
-}
-
-static int __init cell_spuprop_present(struct spu *spu, struct device_node *spe,
-		const char *prop)
-{
-	static DEFINE_MUTEX(add_spumem_mutex);
-
-	const struct address_prop {
-		unsigned long address;
-		unsigned int len;
-	} __attribute__((packed)) *p;
-	int proplen;
-
-	unsigned long start_pfn, nr_pages;
-	struct pglist_data *pgdata;
-	struct zone *zone;
-	int ret;
-
-	p = get_property(spe, prop, &proplen);
-	WARN_ON(proplen != sizeof (*p));
-
-	start_pfn = p->address >> PAGE_SHIFT;
-	nr_pages = ((unsigned long)p->len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-
-	pgdata = NODE_DATA(spu->nid);
-	zone = pgdata->node_zones;
-
-	/* XXX rethink locking here */
-	mutex_lock(&add_spumem_mutex);
-	ret = __add_pages(zone, start_pfn, nr_pages);
-	mutex_unlock(&add_spumem_mutex);
-
-	return ret;
-}
+struct sysdev_class spu_sysdev_class = {
+	set_kset_name("spu")
+};
 
-static void __iomem * __init map_spe_prop(struct spu *spu,
-		struct device_node *n, const char *name)
+int spu_add_sysdev_attr(struct sysdev_attribute *attr)
 {
-	const struct address_prop {
-		unsigned long address;
-		unsigned int len;
-	} __attribute__((packed)) *prop;
-
-	const void *p;
-	int proplen;
-	void __iomem *ret = NULL;
-	int err = 0;
-
-	p = get_property(n, name, &proplen);
-	if (proplen != sizeof (struct address_prop))
-		return NULL;
-
-	prop = p;
-
-	err = cell_spuprop_present(spu, n, name);
-	if (err && (err != -EEXIST))
-		goto out;
-
-	ret = ioremap(prop->address, prop->len);
-
- out:
-	return ret;
-}
+	struct spu *spu;
+	mutex_lock(&spu_mutex);
 
-static void spu_unmap(struct spu *spu)
-{
-	iounmap(spu->priv2);
-	iounmap(spu->priv1);
-	iounmap(spu->problem);
-	iounmap((__force u8 __iomem *)spu->local_store);
-}
+	list_for_each_entry(spu, &spu_full_list, full_list)
+		sysdev_create_file(&spu->sysdev, attr);
 
-/* This function shall be abstracted for HV platforms */
-static int __init spu_map_interrupts_old(struct spu *spu, struct device_node *np)
-{
-	unsigned int isrc;
-	const u32 *tmp;
-
-	/* Get the interrupt source unit from the device-tree */
-	tmp = get_property(np, "isrc", NULL);
-	if (!tmp)
-		return -ENODEV;
-	isrc = tmp[0];
-
-	/* Add the node number */
-	isrc |= spu->node << IIC_IRQ_NODE_SHIFT;
-	spu->isrc = isrc;
-
-	/* Now map interrupts of all 3 classes */
-	spu->irqs[0] = irq_create_mapping(NULL, IIC_IRQ_CLASS_0 | isrc);
-	spu->irqs[1] = irq_create_mapping(NULL, IIC_IRQ_CLASS_1 | isrc);
-	spu->irqs[2] = irq_create_mapping(NULL, IIC_IRQ_CLASS_2 | isrc);
-
-	/* Right now, we only fail if class 2 failed */
-	return spu->irqs[2] == NO_IRQ ? -EINVAL : 0;
+	mutex_unlock(&spu_mutex);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(spu_add_sysdev_attr);
 
-static int __init spu_map_device_old(struct spu *spu, struct device_node *node)
+int spu_add_sysdev_attr_group(struct attribute_group *attrs)
 {
-	const char *prop;
-	int ret;
-
-	ret = -ENODEV;
-	spu->name = get_property(node, "name", NULL);
-	if (!spu->name)
-		goto out;
-
-	prop = get_property(node, "local-store", NULL);
-	if (!prop)
-		goto out;
-	spu->local_store_phys = *(unsigned long *)prop;
-
-	/* we use local store as ram, not io memory */
-	spu->local_store = (void __force *)
-		map_spe_prop(spu, node, "local-store");
-	if (!spu->local_store)
-		goto out;
-
-	prop = get_property(node, "problem", NULL);
-	if (!prop)
-		goto out_unmap;
-	spu->problem_phys = *(unsigned long *)prop;
-
-	spu->problem= map_spe_prop(spu, node, "problem");
-	if (!spu->problem)
-		goto out_unmap;
-
-	spu->priv1= map_spe_prop(spu, node, "priv1");
-	/* priv1 is not available on a hypervisor */
-
-	spu->priv2= map_spe_prop(spu, node, "priv2");
-	if (!spu->priv2)
-		goto out_unmap;
-	ret = 0;
-	goto out;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	return ret;
-}
+	struct spu *spu;
+	mutex_lock(&spu_mutex);
 
-static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
-{
-	struct of_irq oirq;
-	int ret;
-	int i;
+	list_for_each_entry(spu, &spu_full_list, full_list)
+		sysfs_create_group(&spu->sysdev.kobj, attrs);
 
-	for (i=0; i < 3; i++) {
-		ret = of_irq_map_one(np, i, &oirq);
-		if (ret) {
-			pr_debug("spu_new: failed to get irq %d\n", i);
-			goto err;
-		}
-		ret = -EINVAL;
-		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.specifier[0],
-			 oirq.controller->full_name);
-		spu->irqs[i] = irq_create_of_mapping(oirq.controller,
-					oirq.specifier, oirq.size);
-		if (spu->irqs[i] == NO_IRQ) {
-			pr_debug("spu_new: failed to map it !\n");
-			goto err;
-		}
-	}
+	mutex_unlock(&spu_mutex);
 	return 0;
-
-err:
-	pr_debug("failed to map irq %x for spu %s\n", *oirq.specifier, spu->name);
-	for (; i >= 0; i--) {
-		if (spu->irqs[i] != NO_IRQ)
-			irq_dispose_mapping(spu->irqs[i]);
-	}
-	return ret;
 }
+EXPORT_SYMBOL_GPL(spu_add_sysdev_attr_group);
 
-static int spu_map_resource(struct device_node *node, int nr,
-		void __iomem** virt, unsigned long *phys)
-{
-	struct resource resource = { };
-	int ret;
-
-	ret = of_address_to_resource(node, nr, &resource);
-	if (ret)
-		goto out;
 
-	if (phys)
-		*phys = resource.start;
-	*virt = ioremap(resource.start, resource.end - resource.start);
-	if (!*virt)
-		ret = -EINVAL;
-
-out:
-	return ret;
-}
-
-static int __init spu_map_device(struct spu *spu, struct device_node *node)
+void spu_remove_sysdev_attr(struct sysdev_attribute *attr)
 {
-	int ret = -ENODEV;
-	spu->name = get_property(node, "name", NULL);
-	if (!spu->name)
-		goto out;
-
-	ret = spu_map_resource(node, 0, (void __iomem**)&spu->local_store,
-					&spu->local_store_phys);
-	if (ret) {
-		pr_debug("spu_new: failed to map %s resource 0\n",
-			 node->full_name);
-		goto out;
-	}
-	ret = spu_map_resource(node, 1, (void __iomem**)&spu->problem,
-					&spu->problem_phys);
-	if (ret) {
-		pr_debug("spu_new: failed to map %s resource 1\n",
-			 node->full_name);
-		goto out_unmap;
-	}
-	ret = spu_map_resource(node, 2, (void __iomem**)&spu->priv2,
-					NULL);
-	if (ret) {
-		pr_debug("spu_new: failed to map %s resource 2\n",
-			 node->full_name);
-		goto out_unmap;
-	}
-
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
-		ret = spu_map_resource(node, 3, (void __iomem**)&spu->priv1,
-					NULL);
-	if (ret) {
-		pr_debug("spu_new: failed to map %s resource 3\n",
-			 node->full_name);
-		goto out_unmap;
-	}
-	pr_debug("spu_new: %s maps:\n", node->full_name);
-	pr_debug("  local store   : 0x%016lx -> 0x%p\n",
-		 spu->local_store_phys, spu->local_store);
-	pr_debug("  problem state : 0x%016lx -> 0x%p\n",
-		 spu->problem_phys, spu->problem);
-	pr_debug("  priv2         :                       0x%p\n", spu->priv2);
-	pr_debug("  priv1         :                       0x%p\n", spu->priv1);
+	struct spu *spu;
+	mutex_lock(&spu_mutex);
 
-	return 0;
+	list_for_each_entry(spu, &spu_full_list, full_list)
+		sysdev_remove_file(&spu->sysdev, attr);
 
-out_unmap:
-	spu_unmap(spu);
-out:
-	pr_debug("failed to map spe %s: %d\n", spu->name, ret);
-	return ret;
+	mutex_unlock(&spu_mutex);
 }
+EXPORT_SYMBOL_GPL(spu_remove_sysdev_attr);
 
-struct sysdev_class spu_sysdev_class = {
-	set_kset_name("spu")
-};
-
-static ssize_t spu_show_isrc(struct sys_device *sysdev, char *buf)
+void spu_remove_sysdev_attr_group(struct attribute_group *attrs)
 {
-	struct spu *spu = container_of(sysdev, struct spu, sysdev);
-	return sprintf(buf, "%d\n", spu->isrc);
+	struct spu *spu;
+	mutex_lock(&spu_mutex);
 
-}
-static SYSDEV_ATTR(isrc, 0400, spu_show_isrc, NULL);
+	list_for_each_entry(spu, &spu_full_list, full_list)
+		sysfs_remove_group(&spu->sysdev.kobj, attrs);
 
-extern int attach_sysdev_to_node(struct sys_device *dev, int nid);
+	mutex_unlock(&spu_mutex);
+}
+EXPORT_SYMBOL_GPL(spu_remove_sysdev_attr_group);
 
 static int spu_create_sysdev(struct spu *spu)
 {
@@ -781,21 +574,18 @@ static int spu_create_sysdev(struct spu *spu)
 		return ret;
 	}
 
-	if (spu->isrc != 0)
-		sysdev_create_file(&spu->sysdev, &attr_isrc);
-	sysfs_add_device_to_node(&spu->sysdev, spu->nid);
+	sysfs_add_device_to_node(&spu->sysdev, spu->node);
 
 	return 0;
 }
 
 static void spu_destroy_sysdev(struct spu *spu)
 {
-	sysdev_remove_file(&spu->sysdev, &attr_isrc);
-	sysfs_remove_device_from_node(&spu->sysdev, spu->nid);
+	sysfs_remove_device_from_node(&spu->sysdev, spu->node);
 	sysdev_unregister(&spu->sysdev);
 }
 
-static int __init create_spu(struct device_node *spe)
+static int __init create_spu(void *data)
 {
 	struct spu *spu;
 	int ret;
@@ -806,57 +596,37 @@ static int __init create_spu(struct device_node *spe)
 	if (!spu)
 		goto out;
 
-	spu->node = find_spu_node_id(spe);
-	if (spu->node >= MAX_NUMNODES) {
-		printk(KERN_WARNING "SPE %s on node %d ignored,"
-		       " node number too big\n", spe->full_name, spu->node);
-		printk(KERN_WARNING "Check if CONFIG_NUMA is enabled.\n");
-		return -ENODEV;
-	}
-	spu->nid = of_node_to_nid(spe);
-	if (spu->nid == -1)
-		spu->nid = 0;
+	spin_lock_init(&spu->register_lock);
+	mutex_lock(&spu_mutex);
+	spu->number = number++;
+	mutex_unlock(&spu_mutex);
+
+	ret = spu_create_spu(spu, data);
 
-	ret = spu_map_device(spu, spe);
-	/* try old method */
-	if (ret)
-		ret = spu_map_device_old(spu, spe);
 	if (ret)
 		goto out_free;
 
-	ret = spu_map_interrupts(spu, spe);
-	if (ret)
-		ret = spu_map_interrupts_old(spu, spe);
-	if (ret)
-		goto out_unmap;
-	spin_lock_init(&spu->register_lock);
-	spu_mfc_sdr_set(spu, mfspr(SPRN_SDR1));
+	spu_mfc_sdr_setup(spu);
 	spu_mfc_sr1_set(spu, 0x33);
-	mutex_lock(&spu_mutex);
-
-	spu->number = number++;
 	ret = spu_request_irqs(spu);
 	if (ret)
-		goto out_unlock;
+		goto out_destroy;
 
 	ret = spu_create_sysdev(spu);
 	if (ret)
 		goto out_free_irqs;
 
+	mutex_lock(&spu_mutex);
 	list_add(&spu->list, &spu_list[spu->node]);
+	list_add(&spu->full_list, &spu_full_list);
 	mutex_unlock(&spu_mutex);
 
-	pr_debug(KERN_DEBUG "Using SPE %s %02x %p %p %p %p %d\n",
-		spu->name, spu->isrc, spu->local_store,
-		spu->problem, spu->priv1, spu->priv2, spu->number);
 	goto out;
 
 out_free_irqs:
 	spu_free_irqs(spu);
-out_unlock:
-	mutex_unlock(&spu_mutex);
-out_unmap:
-	spu_unmap(spu);
+out_destroy:
+	spu_destroy_spu(spu);
 out_free:
 	kfree(spu);
 out:
@@ -866,10 +636,11 @@ out:
 static void destroy_spu(struct spu *spu)
 {
 	list_del_init(&spu->list);
+	list_del_init(&spu->full_list);
 
 	spu_destroy_sysdev(spu);
 	spu_free_irqs(spu);
-	spu_unmap(spu);
+	spu_destroy_spu(spu);
 	kfree(spu);
 }
 
@@ -890,9 +661,11 @@ module_exit(cleanup_spu_base);
 
 static int __init init_spu_base(void)
 {
-	struct device_node *node;
 	int i, ret;
 
+	if (!spu_management_ops)
+		return 0;
+
 	/* create sysdev class for spus */
 	ret = sysdev_class_register(&spu_sysdev_class);
 	if (ret)
@@ -901,17 +674,17 @@ static int __init init_spu_base(void)
 	for (i = 0; i < MAX_NUMNODES; i++)
 		INIT_LIST_HEAD(&spu_list[i]);
 
-	ret = -ENODEV;
-	for (node = of_find_node_by_type(NULL, "spe");
-			node; node = of_find_node_by_type(node, "spe")) {
-		ret = create_spu(node);
-		if (ret) {
-			printk(KERN_WARNING "%s: Error initializing %s\n",
-				__FUNCTION__, node->name);
-			cleanup_spu_base();
-			break;
-		}
+	ret = spu_enumerate_spus(create_spu);
+
+	if (ret) {
+		printk(KERN_WARNING "%s: Error initializing spus\n",
+			__FUNCTION__);
+		cleanup_spu_base();
+		return ret;
 	}
+
+	xmon_register_spus(&spu_full_list);
+
 	return ret;
 }
 module_init(init_spu_base);
diff --git a/arch/powerpc/platforms/cell/spu_coredump.c b/arch/powerpc/platforms/cell/spu_coredump.c
new file mode 100644
index 000000000000..6915b418ee73
--- /dev/null
+++ b/arch/powerpc/platforms/cell/spu_coredump.c
@@ -0,0 +1,81 @@
+/*
+ * SPU core dump code
+ *
+ * (C) Copyright 2006 IBM Corp.
+ *
+ * Author: Dwayne Grant McConnell <decimal@us.ibm.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, 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/file.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+
+#include <asm/spu.h>
+
+static struct spu_coredump_calls spu_coredump_calls;
+static DEFINE_MUTEX(spu_coredump_mutex);
+
+int arch_notes_size(void)
+{
+	long ret;
+	struct module *owner = spu_coredump_calls.owner;
+
+	ret = -ENOSYS;
+	mutex_lock(&spu_coredump_mutex);
+	if (owner && try_module_get(owner)) {
+		ret = spu_coredump_calls.arch_notes_size();
+		module_put(owner);
+	}
+	mutex_unlock(&spu_coredump_mutex);
+	return ret;
+}
+
+void arch_write_notes(struct file *file)
+{
+	struct module *owner = spu_coredump_calls.owner;
+
+	mutex_lock(&spu_coredump_mutex);
+	if (owner && try_module_get(owner)) {
+		spu_coredump_calls.arch_write_notes(file);
+		module_put(owner);
+	}
+	mutex_unlock(&spu_coredump_mutex);
+}
+
+int register_arch_coredump_calls(struct spu_coredump_calls *calls)
+{
+	if (spu_coredump_calls.owner)
+		return -EBUSY;
+
+	mutex_lock(&spu_coredump_mutex);
+	spu_coredump_calls.arch_notes_size = calls->arch_notes_size;
+	spu_coredump_calls.arch_write_notes = calls->arch_write_notes;
+	spu_coredump_calls.owner = calls->owner;
+	mutex_unlock(&spu_coredump_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_arch_coredump_calls);
+
+void unregister_arch_coredump_calls(struct spu_coredump_calls *calls)
+{
+	BUG_ON(spu_coredump_calls.owner != calls->owner);
+
+	mutex_lock(&spu_coredump_mutex);
+	spu_coredump_calls.owner = NULL;
+	mutex_unlock(&spu_coredump_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_arch_coredump_calls);
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.c b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
index 71b69f0a1a48..a5de0430c56d 100644
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.c
+++ b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
@@ -18,120 +18,498 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/interrupt.h>
+#include <linux/list.h>
 #include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+#include <linux/mutex.h>
+#include <linux/device.h>
 
-#include <asm/io.h>
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
+#include <asm/firmware.h>
+#include <asm/prom.h>
 
 #include "interrupt.h"
+#include "spu_priv1_mmio.h"
+
+struct spu_pdata {
+	int nid;
+	struct device_node *devnode;
+	struct spu_priv1 __iomem *priv1;
+};
+
+static struct spu_pdata *spu_get_pdata(struct spu *spu)
+{
+	BUG_ON(!spu->pdata);
+	return spu->pdata;
+}
+
+struct device_node *spu_devnode(struct spu *spu)
+{
+	return spu_get_pdata(spu)->devnode;
+}
+
+EXPORT_SYMBOL_GPL(spu_devnode);
+
+static int __init find_spu_node_id(struct device_node *spe)
+{
+	const unsigned int *id;
+	struct device_node *cpu;
+	cpu = spe->parent->parent;
+	id = get_property(cpu, "node-id", NULL);
+	return id ? *id : 0;
+}
+
+static int __init cell_spuprop_present(struct spu *spu, struct device_node *spe,
+		const char *prop)
+{
+	static DEFINE_MUTEX(add_spumem_mutex);
+
+	const struct address_prop {
+		unsigned long address;
+		unsigned int len;
+	} __attribute__((packed)) *p;
+	int proplen;
+
+	unsigned long start_pfn, nr_pages;
+	struct pglist_data *pgdata;
+	struct zone *zone;
+	int ret;
+
+	p = get_property(spe, prop, &proplen);
+	WARN_ON(proplen != sizeof (*p));
+
+	start_pfn = p->address >> PAGE_SHIFT;
+	nr_pages = ((unsigned long)p->len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	pgdata = NODE_DATA(spu_get_pdata(spu)->nid);
+	zone = pgdata->node_zones;
+
+	/* XXX rethink locking here */
+	mutex_lock(&add_spumem_mutex);
+	ret = __add_pages(zone, start_pfn, nr_pages);
+	mutex_unlock(&add_spumem_mutex);
+
+	return ret;
+}
+
+static void __iomem * __init map_spe_prop(struct spu *spu,
+		struct device_node *n, const char *name)
+{
+	const struct address_prop {
+		unsigned long address;
+		unsigned int len;
+	} __attribute__((packed)) *prop;
+
+	const void *p;
+	int proplen;
+	void __iomem *ret = NULL;
+	int err = 0;
+
+	p = get_property(n, name, &proplen);
+	if (proplen != sizeof (struct address_prop))
+		return NULL;
+
+	prop = p;
+
+	err = cell_spuprop_present(spu, n, name);
+	if (err && (err != -EEXIST))
+		goto out;
+
+	ret = ioremap(prop->address, prop->len);
+
+ out:
+	return ret;
+}
+
+static void spu_unmap(struct spu *spu)
+{
+	iounmap(spu->priv2);
+	iounmap(spu_get_pdata(spu)->priv1);
+	iounmap(spu->problem);
+	iounmap((__force u8 __iomem *)spu->local_store);
+}
+
+static int __init spu_map_interrupts_old(struct spu *spu,
+	struct device_node *np)
+{
+	unsigned int isrc;
+	const u32 *tmp;
+
+	/* Get the interrupt source unit from the device-tree */
+	tmp = get_property(np, "isrc", NULL);
+	if (!tmp)
+		return -ENODEV;
+	isrc = tmp[0];
+
+	/* Add the node number */
+	isrc |= spu->node << IIC_IRQ_NODE_SHIFT;
+
+	/* Now map interrupts of all 3 classes */
+	spu->irqs[0] = irq_create_mapping(NULL, IIC_IRQ_CLASS_0 | isrc);
+	spu->irqs[1] = irq_create_mapping(NULL, IIC_IRQ_CLASS_1 | isrc);
+	spu->irqs[2] = irq_create_mapping(NULL, IIC_IRQ_CLASS_2 | isrc);
+
+	/* Right now, we only fail if class 2 failed */
+	return spu->irqs[2] == NO_IRQ ? -EINVAL : 0;
+}
+
+static int __init spu_map_device_old(struct spu *spu, struct device_node *node)
+{
+	const char *prop;
+	int ret;
+
+	ret = -ENODEV;
+	spu->name = get_property(node, "name", NULL);
+	if (!spu->name)
+		goto out;
+
+	prop = get_property(node, "local-store", NULL);
+	if (!prop)
+		goto out;
+	spu->local_store_phys = *(unsigned long *)prop;
+
+	/* we use local store as ram, not io memory */
+	spu->local_store = (void __force *)
+		map_spe_prop(spu, node, "local-store");
+	if (!spu->local_store)
+		goto out;
+
+	prop = get_property(node, "problem", NULL);
+	if (!prop)
+		goto out_unmap;
+	spu->problem_phys = *(unsigned long *)prop;
+
+	spu->problem= map_spe_prop(spu, node, "problem");
+	if (!spu->problem)
+		goto out_unmap;
+
+	spu_get_pdata(spu)->priv1= map_spe_prop(spu, node, "priv1");
+
+	spu->priv2= map_spe_prop(spu, node, "priv2");
+	if (!spu->priv2)
+		goto out_unmap;
+	ret = 0;
+	goto out;
+
+out_unmap:
+	spu_unmap(spu);
+out:
+	return ret;
+}
+
+static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
+{
+	struct of_irq oirq;
+	int ret;
+	int i;
+
+	for (i=0; i < 3; i++) {
+		ret = of_irq_map_one(np, i, &oirq);
+		if (ret) {
+			pr_debug("spu_new: failed to get irq %d\n", i);
+			goto err;
+		}
+		ret = -EINVAL;
+		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.specifier[0],
+			 oirq.controller->full_name);
+		spu->irqs[i] = irq_create_of_mapping(oirq.controller,
+					oirq.specifier, oirq.size);
+		if (spu->irqs[i] == NO_IRQ) {
+			pr_debug("spu_new: failed to map it !\n");
+			goto err;
+		}
+	}
+	return 0;
+
+err:
+	pr_debug("failed to map irq %x for spu %s\n", *oirq.specifier,
+		spu->name);
+	for (; i >= 0; i--) {
+		if (spu->irqs[i] != NO_IRQ)
+			irq_dispose_mapping(spu->irqs[i]);
+	}
+	return ret;
+}
+
+static int spu_map_resource(struct device_node *node, int nr,
+		void __iomem** virt, unsigned long *phys)
+{
+	struct resource resource = { };
+	int ret;
+
+	ret = of_address_to_resource(node, nr, &resource);
+	if (ret)
+		goto out;
+
+	if (phys)
+		*phys = resource.start;
+	*virt = ioremap(resource.start, resource.end - resource.start);
+	if (!*virt)
+		ret = -EINVAL;
+
+out:
+	return ret;
+}
+
+static int __init spu_map_device(struct spu *spu, struct device_node *node)
+{
+	int ret = -ENODEV;
+	spu->name = get_property(node, "name", NULL);
+	if (!spu->name)
+		goto out;
+
+	ret = spu_map_resource(node, 0, (void __iomem**)&spu->local_store,
+					&spu->local_store_phys);
+	if (ret) {
+		pr_debug("spu_new: failed to map %s resource 0\n",
+			 node->full_name);
+		goto out;
+	}
+	ret = spu_map_resource(node, 1, (void __iomem**)&spu->problem,
+					&spu->problem_phys);
+	if (ret) {
+		pr_debug("spu_new: failed to map %s resource 1\n",
+			 node->full_name);
+		goto out_unmap;
+	}
+	ret = spu_map_resource(node, 2, (void __iomem**)&spu->priv2,
+					NULL);
+	if (ret) {
+		pr_debug("spu_new: failed to map %s resource 2\n",
+			 node->full_name);
+		goto out_unmap;
+	}
+	if (!firmware_has_feature(FW_FEATURE_LPAR))
+		ret = spu_map_resource(node, 3,
+			(void __iomem**)&spu_get_pdata(spu)->priv1, NULL);
+	if (ret) {
+		pr_debug("spu_new: failed to map %s resource 3\n",
+			 node->full_name);
+		goto out_unmap;
+	}
+	pr_debug("spu_new: %s maps:\n", node->full_name);
+	pr_debug("  local store   : 0x%016lx -> 0x%p\n",
+		 spu->local_store_phys, spu->local_store);
+	pr_debug("  problem state : 0x%016lx -> 0x%p\n",
+		 spu->problem_phys, spu->problem);
+	pr_debug("  priv2         :                       0x%p\n", spu->priv2);
+	pr_debug("  priv1         :                       0x%p\n",
+						spu_get_pdata(spu)->priv1);
+
+	return 0;
+
+out_unmap:
+	spu_unmap(spu);
+out:
+	pr_debug("failed to map spe %s: %d\n", spu->name, ret);
+	return ret;
+}
+
+static int __init of_enumerate_spus(int (*fn)(void *data))
+{
+	int ret;
+	struct device_node *node;
+
+	ret = -ENODEV;
+	for (node = of_find_node_by_type(NULL, "spe");
+			node; node = of_find_node_by_type(node, "spe")) {
+		ret = fn(node);
+		if (ret) {
+			printk(KERN_WARNING "%s: Error initializing %s\n",
+				__FUNCTION__, node->name);
+			break;
+		}
+	}
+	return ret;
+}
+
+static int __init of_create_spu(struct spu *spu, void *data)
+{
+	int ret;
+	struct device_node *spe = (struct device_node *)data;
+
+	spu->pdata = kzalloc(sizeof(struct spu_pdata),
+		GFP_KERNEL);
+	if (!spu->pdata) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	spu->node = find_spu_node_id(spe);
+	if (spu->node >= MAX_NUMNODES) {
+		printk(KERN_WARNING "SPE %s on node %d ignored,"
+		       " node number too big\n", spe->full_name, spu->node);
+		printk(KERN_WARNING "Check if CONFIG_NUMA is enabled.\n");
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	spu_get_pdata(spu)->nid = of_node_to_nid(spe);
+	if (spu_get_pdata(spu)->nid == -1)
+		spu_get_pdata(spu)->nid = 0;
+
+	ret = spu_map_device(spu, spe);
+	/* try old method */
+	if (ret)
+		ret = spu_map_device_old(spu, spe);
+	if (ret)
+		goto out_free;
+
+	ret = spu_map_interrupts(spu, spe);
+	if (ret)
+		ret = spu_map_interrupts_old(spu, spe);
+	if (ret)
+		goto out_unmap;
+
+	spu_get_pdata(spu)->devnode = of_node_get(spe);
+
+	pr_debug(KERN_DEBUG "Using SPE %s %p %p %p %p %d\n", spu->name,
+		spu->local_store, spu->problem, spu_get_pdata(spu)->priv1,
+		spu->priv2, spu->number);
+	goto out;
+
+out_unmap:
+	spu_unmap(spu);
+out_free:
+	kfree(spu->pdata);
+	spu->pdata = NULL;
+out:
+	return ret;
+}
+
+static int of_destroy_spu(struct spu *spu)
+{
+	spu_unmap(spu);
+	of_node_put(spu_get_pdata(spu)->devnode);
+	kfree(spu->pdata);
+	spu->pdata = NULL;
+	return 0;
+}
+
+const struct spu_management_ops spu_management_of_ops = {
+	.enumerate_spus = of_enumerate_spus,
+	.create_spu = of_create_spu,
+	.destroy_spu = of_destroy_spu,
+};
 
 static void int_mask_and(struct spu *spu, int class, u64 mask)
 {
 	u64 old_mask;
 
-	old_mask = in_be64(&spu->priv1->int_mask_RW[class]);
-	out_be64(&spu->priv1->int_mask_RW[class], old_mask & mask);
+	old_mask = in_be64(&spu_get_pdata(spu)->priv1->int_mask_RW[class]);
+	out_be64(&spu_get_pdata(spu)->priv1->int_mask_RW[class],
+		old_mask & mask);
 }
 
 static void int_mask_or(struct spu *spu, int class, u64 mask)
 {
 	u64 old_mask;
 
-	old_mask = in_be64(&spu->priv1->int_mask_RW[class]);
-	out_be64(&spu->priv1->int_mask_RW[class], old_mask | mask);
+	old_mask = in_be64(&spu_get_pdata(spu)->priv1->int_mask_RW[class]);
+	out_be64(&spu_get_pdata(spu)->priv1->int_mask_RW[class],
+		old_mask | mask);
 }
 
 static void int_mask_set(struct spu *spu, int class, u64 mask)
 {
-	out_be64(&spu->priv1->int_mask_RW[class], mask);
+	out_be64(&spu_get_pdata(spu)->priv1->int_mask_RW[class], mask);
 }
 
 static u64 int_mask_get(struct spu *spu, int class)
 {
-	return in_be64(&spu->priv1->int_mask_RW[class]);
+	return in_be64(&spu_get_pdata(spu)->priv1->int_mask_RW[class]);
 }
 
 static void int_stat_clear(struct spu *spu, int class, u64 stat)
 {
-	out_be64(&spu->priv1->int_stat_RW[class], stat);
+	out_be64(&spu_get_pdata(spu)->priv1->int_stat_RW[class], stat);
 }
 
 static u64 int_stat_get(struct spu *spu, int class)
 {
-	return in_be64(&spu->priv1->int_stat_RW[class]);
+	return in_be64(&spu_get_pdata(spu)->priv1->int_stat_RW[class]);
 }
 
 static void cpu_affinity_set(struct spu *spu, int cpu)
 {
 	u64 target = iic_get_target_id(cpu);
 	u64 route = target << 48 | target << 32 | target << 16;
-	out_be64(&spu->priv1->int_route_RW, route);
+	out_be64(&spu_get_pdata(spu)->priv1->int_route_RW, route);
 }
 
 static u64 mfc_dar_get(struct spu *spu)
 {
-	return in_be64(&spu->priv1->mfc_dar_RW);
+	return in_be64(&spu_get_pdata(spu)->priv1->mfc_dar_RW);
 }
 
 static u64 mfc_dsisr_get(struct spu *spu)
 {
-	return in_be64(&spu->priv1->mfc_dsisr_RW);
+	return in_be64(&spu_get_pdata(spu)->priv1->mfc_dsisr_RW);
 }
 
 static void mfc_dsisr_set(struct spu *spu, u64 dsisr)
 {
-	out_be64(&spu->priv1->mfc_dsisr_RW, dsisr);
+	out_be64(&spu_get_pdata(spu)->priv1->mfc_dsisr_RW, dsisr);
 }
 
-static void mfc_sdr_set(struct spu *spu, u64 sdr)
+static void mfc_sdr_setup(struct spu *spu)
 {
-	out_be64(&spu->priv1->mfc_sdr_RW, sdr);
+	out_be64(&spu_get_pdata(spu)->priv1->mfc_sdr_RW, mfspr(SPRN_SDR1));
 }
 
 static void mfc_sr1_set(struct spu *spu, u64 sr1)
 {
-	out_be64(&spu->priv1->mfc_sr1_RW, sr1);
+	out_be64(&spu_get_pdata(spu)->priv1->mfc_sr1_RW, sr1);
 }
 
 static u64 mfc_sr1_get(struct spu *spu)
 {
-	return in_be64(&spu->priv1->mfc_sr1_RW);
+	return in_be64(&spu_get_pdata(spu)->priv1->mfc_sr1_RW);
 }
 
 static void mfc_tclass_id_set(struct spu *spu, u64 tclass_id)
 {
-	out_be64(&spu->priv1->mfc_tclass_id_RW, tclass_id);
+	out_be64(&spu_get_pdata(spu)->priv1->mfc_tclass_id_RW, tclass_id);
 }
 
 static u64 mfc_tclass_id_get(struct spu *spu)
 {
-	return in_be64(&spu->priv1->mfc_tclass_id_RW);
+	return in_be64(&spu_get_pdata(spu)->priv1->mfc_tclass_id_RW);
 }
 
 static void tlb_invalidate(struct spu *spu)
 {
-	out_be64(&spu->priv1->tlb_invalidate_entry_W, 0ul);
+	out_be64(&spu_get_pdata(spu)->priv1->tlb_invalidate_entry_W, 0ul);
 }
 
 static void resource_allocation_groupID_set(struct spu *spu, u64 id)
 {
-	out_be64(&spu->priv1->resource_allocation_groupID_RW, id);
+	out_be64(&spu_get_pdata(spu)->priv1->resource_allocation_groupID_RW,
+		id);
 }
 
 static u64 resource_allocation_groupID_get(struct spu *spu)
 {
-	return in_be64(&spu->priv1->resource_allocation_groupID_RW);
+	return in_be64(
+		&spu_get_pdata(spu)->priv1->resource_allocation_groupID_RW);
 }
 
 static void resource_allocation_enable_set(struct spu *spu, u64 enable)
 {
-	out_be64(&spu->priv1->resource_allocation_enable_RW, enable);
+	out_be64(&spu_get_pdata(spu)->priv1->resource_allocation_enable_RW,
+		enable);
 }
 
 static u64 resource_allocation_enable_get(struct spu *spu)
 {
-	return in_be64(&spu->priv1->resource_allocation_enable_RW);
+	return in_be64(
+		&spu_get_pdata(spu)->priv1->resource_allocation_enable_RW);
 }
 
 const struct spu_priv1_ops spu_priv1_mmio_ops =
@@ -146,7 +524,7 @@ const struct spu_priv1_ops spu_priv1_mmio_ops =
 	.mfc_dar_get = mfc_dar_get,
 	.mfc_dsisr_get = mfc_dsisr_get,
 	.mfc_dsisr_set = mfc_dsisr_set,
-	.mfc_sdr_set = mfc_sdr_set,
+	.mfc_sdr_setup = mfc_sdr_setup,
 	.mfc_sr1_set = mfc_sr1_set,
 	.mfc_sr1_get = mfc_sr1_get,
 	.mfc_tclass_id_set = mfc_tclass_id_set,
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.h b/arch/powerpc/platforms/cell/spu_priv1_mmio.h
new file mode 100644
index 000000000000..7b62bd1cc256
--- /dev/null
+++ b/arch/powerpc/platforms/cell/spu_priv1_mmio.h
@@ -0,0 +1,26 @@
+/*
+ * spu hypervisor abstraction for direct hardware access.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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
+ */
+
+#ifndef SPU_PRIV1_MMIO_H
+#define SPU_PRIV1_MMIO_H
+
+struct device_node *spu_devnode(struct spu *spu);
+
+#endif /* SPU_PRIV1_MMIO_H */
diff --git a/arch/powerpc/platforms/cell/spufs/Makefile b/arch/powerpc/platforms/cell/spufs/Makefile
index ecdfbb35f82e..472217d19faf 100644
--- a/arch/powerpc/platforms/cell/spufs/Makefile
+++ b/arch/powerpc/platforms/cell/spufs/Makefile
@@ -1,7 +1,7 @@
 obj-y += switch.o
 
 obj-$(CONFIG_SPU_FS) += spufs.o
-spufs-y += inode.o file.o context.o syscalls.o
+spufs-y += inode.o file.o context.o syscalls.o coredump.o
 spufs-y += sched.o backing_ops.o hw_ops.o run.o gang.o
 
 # Rules to build switch.o with the help of SPU tool chain
diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c
index 2d22cd59d6fc..1898f0d3a8b8 100644
--- a/arch/powerpc/platforms/cell/spufs/backing_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c
@@ -36,6 +36,7 @@
 #include <asm/io.h>
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
+#include <asm/spu_info.h>
 #include <asm/mmu_context.h>
 #include "spufs.h"
 
@@ -267,6 +268,11 @@ static char *spu_backing_get_ls(struct spu_context *ctx)
 	return ctx->csa.lscsa->ls;
 }
 
+static u32 spu_backing_runcntl_read(struct spu_context *ctx)
+{
+	return ctx->csa.prob.spu_runcntl_RW;
+}
+
 static void spu_backing_runcntl_write(struct spu_context *ctx, u32 val)
 {
 	spin_lock(&ctx->csa.register_lock);
@@ -279,9 +285,26 @@ static void spu_backing_runcntl_write(struct spu_context *ctx, u32 val)
 	spin_unlock(&ctx->csa.register_lock);
 }
 
-static void spu_backing_runcntl_stop(struct spu_context *ctx)
+static void spu_backing_master_start(struct spu_context *ctx)
+{
+	struct spu_state *csa = &ctx->csa;
+	u64 sr1;
+
+	spin_lock(&csa->register_lock);
+	sr1 = csa->priv1.mfc_sr1_RW | MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+	csa->priv1.mfc_sr1_RW = sr1;
+	spin_unlock(&csa->register_lock);
+}
+
+static void spu_backing_master_stop(struct spu_context *ctx)
 {
-	spu_backing_runcntl_write(ctx, SPU_RUNCNTL_STOP);
+	struct spu_state *csa = &ctx->csa;
+	u64 sr1;
+
+	spin_lock(&csa->register_lock);
+	sr1 = csa->priv1.mfc_sr1_RW & ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+	csa->priv1.mfc_sr1_RW = sr1;
+	spin_unlock(&csa->register_lock);
 }
 
 static int spu_backing_set_mfc_query(struct spu_context * ctx, u32 mask,
@@ -345,8 +368,10 @@ struct spu_context_ops spu_backing_ops = {
 	.npc_write = spu_backing_npc_write,
 	.status_read = spu_backing_status_read,
 	.get_ls = spu_backing_get_ls,
+	.runcntl_read = spu_backing_runcntl_read,
 	.runcntl_write = spu_backing_runcntl_write,
-	.runcntl_stop = spu_backing_runcntl_stop,
+	.master_start = spu_backing_master_start,
+	.master_stop = spu_backing_master_stop,
 	.set_mfc_query = spu_backing_set_mfc_query,
 	.read_mfc_tagstatus = spu_backing_read_mfc_tagstatus,
 	.get_mfc_free_elements = spu_backing_get_mfc_free_elements,
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 034cf6af53a2..0870009f56db 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -120,6 +120,33 @@ void spu_unmap_mappings(struct spu_context *ctx)
 		unmap_mapping_range(ctx->signal2, 0, 0x4000, 1);
 }
 
+int spu_acquire_exclusive(struct spu_context *ctx)
+{
+	int ret = 0;
+
+	down_write(&ctx->state_sema);
+	/* ctx is about to be freed, can't acquire any more */
+	if (!ctx->owner) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (ctx->state == SPU_STATE_SAVED) {
+		ret = spu_activate(ctx, 0);
+		if (ret)
+			goto out;
+		ctx->state = SPU_STATE_RUNNABLE;
+	} else {
+		/* We need to exclude userspace access to the context. */
+		spu_unmap_mappings(ctx);
+	}
+
+out:
+	if (ret)
+		up_write(&ctx->state_sema);
+	return ret;
+}
+
 int spu_acquire_runnable(struct spu_context *ctx)
 {
 	int ret = 0;
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
new file mode 100644
index 000000000000..26945c491f6b
--- /dev/null
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -0,0 +1,238 @@
+/*
+ * SPU core dump code
+ *
+ * (C) Copyright 2006 IBM Corp.
+ *
+ * Author: Dwayne Grant McConnell <decimal@us.ibm.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, 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/elf.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+
+#include <asm/uaccess.h>
+
+#include "spufs.h"
+
+struct spufs_ctx_info {
+	struct list_head list;
+	int dfd;
+	int memsize; /* in bytes */
+	struct spu_context *ctx;
+};
+
+static LIST_HEAD(ctx_info_list);
+
+static ssize_t do_coredump_read(int num, struct spu_context *ctx, void __user *buffer,
+				size_t size, loff_t *off)
+{
+	u64 data;
+	int ret;
+
+	if (spufs_coredump_read[num].read)
+		return spufs_coredump_read[num].read(ctx, buffer, size, off);
+
+	data = spufs_coredump_read[num].get(ctx);
+	ret = copy_to_user(buffer, &data, 8);
+	return ret ? -EFAULT : 8;
+}
+
+/*
+ * These are the only things you should do on a core-file: use only these
+ * functions to write out all the necessary info.
+ */
+static int spufs_dump_write(struct file *file, const void *addr, int nr)
+{
+	return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
+}
+
+static int spufs_dump_seek(struct file *file, loff_t off)
+{
+	if (file->f_op->llseek) {
+		if (file->f_op->llseek(file, off, 0) != off)
+			return 0;
+	} else
+		file->f_pos = off;
+	return 1;
+}
+
+static void spufs_fill_memsize(struct spufs_ctx_info *ctx_info)
+{
+	struct spu_context *ctx;
+	unsigned long long lslr;
+
+	ctx = ctx_info->ctx;
+	lslr = ctx->csa.priv2.spu_lslr_RW;
+	ctx_info->memsize = lslr + 1;
+}
+
+static int spufs_ctx_note_size(struct spufs_ctx_info *ctx_info)
+{
+	int dfd, memsize, i, sz, total = 0;
+	char *name;
+	char fullname[80];
+
+	dfd = ctx_info->dfd;
+	memsize = ctx_info->memsize;
+
+	for (i = 0; spufs_coredump_read[i].name; i++) {
+		name = spufs_coredump_read[i].name;
+		sz = spufs_coredump_read[i].size;
+
+		sprintf(fullname, "SPU/%d/%s", dfd, name);
+
+		total += sizeof(struct elf_note);
+		total += roundup(strlen(fullname) + 1, 4);
+		if (!strcmp(name, "mem"))
+			total += roundup(memsize, 4);
+		else
+			total += roundup(sz, 4);
+	}
+
+	return total;
+}
+
+static int spufs_add_one_context(struct file *file, int dfd)
+{
+	struct spu_context *ctx;
+	struct spufs_ctx_info *ctx_info;
+	int size;
+
+	ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx;
+	if (ctx->flags & SPU_CREATE_NOSCHED)
+		return 0;
+
+	ctx_info = kzalloc(sizeof(*ctx_info), GFP_KERNEL);
+	if (unlikely(!ctx_info))
+		return -ENOMEM;
+
+	ctx_info->dfd = dfd;
+	ctx_info->ctx = ctx;
+
+	spufs_fill_memsize(ctx_info);
+
+	size = spufs_ctx_note_size(ctx_info);
+	list_add(&ctx_info->list, &ctx_info_list);
+	return size;
+}
+
+/*
+ * The additional architecture-specific notes for Cell are various
+ * context files in the spu context.
+ *
+ * This function iterates over all open file descriptors and sees
+ * if they are a directory in spufs.  In that case we use spufs
+ * internal functionality to dump them without needing to actually
+ * open the files.
+ */
+static int spufs_arch_notes_size(void)
+{
+	struct fdtable *fdt = files_fdtable(current->files);
+	int size = 0, fd;
+
+	for (fd = 0; fd < fdt->max_fdset && fd < fdt->max_fds; fd++) {
+		if (FD_ISSET(fd, fdt->open_fds)) {
+			struct file *file = fcheck(fd);
+
+			if (file && file->f_op == &spufs_context_fops) {
+				int rval = spufs_add_one_context(file, fd);
+				if (rval < 0)
+					break;
+				size += rval;
+			}
+		}
+	}
+
+	return size;
+}
+
+static void spufs_arch_write_note(struct spufs_ctx_info *ctx_info, int i,
+				struct file *file)
+{
+	struct spu_context *ctx;
+	loff_t pos = 0;
+	int sz, dfd, rc, total = 0;
+	const int bufsz = 4096;
+	char *name;
+	char fullname[80], *buf;
+	struct elf_note en;
+
+	buf = kmalloc(bufsz, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	dfd = ctx_info->dfd;
+	name = spufs_coredump_read[i].name;
+
+	if (!strcmp(name, "mem"))
+		sz = ctx_info->memsize;
+	else
+		sz = spufs_coredump_read[i].size;
+
+	ctx = ctx_info->ctx;
+	if (!ctx) {
+		return;
+	}
+
+	sprintf(fullname, "SPU/%d/%s", dfd, name);
+	en.n_namesz = strlen(fullname) + 1;
+	en.n_descsz = sz;
+	en.n_type = NT_SPU;
+
+	if (!spufs_dump_write(file, &en, sizeof(en)))
+		return;
+	if (!spufs_dump_write(file, fullname, en.n_namesz))
+		return;
+	if (!spufs_dump_seek(file, roundup((unsigned long)file->f_pos, 4)))
+		return;
+
+	do {
+		rc = do_coredump_read(i, ctx, buf, bufsz, &pos);
+		if (rc > 0) {
+			if (!spufs_dump_write(file, buf, rc))
+				return;
+			total += rc;
+		}
+	} while (rc == bufsz && total < sz);
+
+	spufs_dump_seek(file, roundup((unsigned long)file->f_pos
+						- total + sz, 4));
+}
+
+static void spufs_arch_write_notes(struct file *file)
+{
+	int j;
+	struct spufs_ctx_info *ctx_info, *next;
+
+	list_for_each_entry_safe(ctx_info, next, &ctx_info_list, list) {
+		spu_acquire_saved(ctx_info->ctx);
+		for (j = 0; j < spufs_coredump_num_notes; j++)
+			spufs_arch_write_note(ctx_info, j, file);
+		spu_release(ctx_info->ctx);
+		list_del(&ctx_info->list);
+		kfree(ctx_info);
+	}
+}
+
+struct spu_coredump_calls spufs_coredump_calls = {
+	.arch_notes_size = spufs_arch_notes_size,
+	.arch_write_notes = spufs_arch_write_notes,
+	.owner = THIS_MODULE,
+};
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 533e2723e184..347eff56fcbd 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -32,13 +32,13 @@
 #include <asm/io.h>
 #include <asm/semaphore.h>
 #include <asm/spu.h>
+#include <asm/spu_info.h>
 #include <asm/uaccess.h>
 
 #include "spufs.h"
 
 #define SPUFS_MMAP_4K (PAGE_SIZE == 0x1000)
 
-
 static int
 spufs_mem_open(struct inode *inode, struct file *file)
 {
@@ -51,18 +51,23 @@ spufs_mem_open(struct inode *inode, struct file *file)
 }
 
 static ssize_t
+__spufs_mem_read(struct spu_context *ctx, char __user *buffer,
+			size_t size, loff_t *pos)
+{
+	char *local_store = ctx->ops->get_ls(ctx);
+	return simple_read_from_buffer(buffer, size, pos, local_store,
+					LS_SIZE);
+}
+
+static ssize_t
 spufs_mem_read(struct file *file, char __user *buffer,
 				size_t size, loff_t *pos)
 {
-	struct spu_context *ctx = file->private_data;
-	char *local_store;
 	int ret;
+	struct spu_context *ctx = file->private_data;
 
 	spu_acquire(ctx);
-
-	local_store = ctx->ops->get_ls(ctx);
-	ret = simple_read_from_buffer(buffer, size, pos, local_store, LS_SIZE);
-
+	ret = __spufs_mem_read(ctx, buffer, size, pos);
 	spu_release(ctx);
 	return ret;
 }
@@ -104,11 +109,11 @@ spufs_mem_mmap_nopage(struct vm_area_struct *vma,
 
 	if (ctx->state == SPU_STATE_SAVED) {
 		vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-					& ~(_PAGE_NO_CACHE | _PAGE_GUARDED));
+							& ~_PAGE_NO_CACHE);
 		page = vmalloc_to_page(ctx->csa.lscsa->ls + offset);
 	} else {
 		vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
-					| _PAGE_NO_CACHE | _PAGE_GUARDED);
+							| _PAGE_NO_CACHE);
 		page = pfn_to_page((ctx->spu->local_store_phys + offset)
 				   >> PAGE_SHIFT);
 	}
@@ -131,7 +136,7 @@ spufs_mem_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	/* FIXME: */
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE);
 
@@ -200,7 +205,7 @@ static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
 
@@ -261,18 +266,23 @@ spufs_regs_open(struct inode *inode, struct file *file)
 }
 
 static ssize_t
+__spufs_regs_read(struct spu_context *ctx, char __user *buffer,
+			size_t size, loff_t *pos)
+{
+	struct spu_lscsa *lscsa = ctx->csa.lscsa;
+	return simple_read_from_buffer(buffer, size, pos,
+				      lscsa->gprs, sizeof lscsa->gprs);
+}
+
+static ssize_t
 spufs_regs_read(struct file *file, char __user *buffer,
 		size_t size, loff_t *pos)
 {
-	struct spu_context *ctx = file->private_data;
-	struct spu_lscsa *lscsa = ctx->csa.lscsa;
 	int ret;
+	struct spu_context *ctx = file->private_data;
 
 	spu_acquire_saved(ctx);
-
-	ret = simple_read_from_buffer(buffer, size, pos,
-				      lscsa->gprs, sizeof lscsa->gprs);
-
+	ret = __spufs_regs_read(ctx, buffer, size, pos);
 	spu_release(ctx);
 	return ret;
 }
@@ -307,18 +317,23 @@ static struct file_operations spufs_regs_fops = {
 };
 
 static ssize_t
+__spufs_fpcr_read(struct spu_context *ctx, char __user * buffer,
+			size_t size, loff_t * pos)
+{
+	struct spu_lscsa *lscsa = ctx->csa.lscsa;
+	return simple_read_from_buffer(buffer, size, pos,
+				      &lscsa->fpcr, sizeof(lscsa->fpcr));
+}
+
+static ssize_t
 spufs_fpcr_read(struct file *file, char __user * buffer,
 		size_t size, loff_t * pos)
 {
-	struct spu_context *ctx = file->private_data;
-	struct spu_lscsa *lscsa = ctx->csa.lscsa;
 	int ret;
+	struct spu_context *ctx = file->private_data;
 
 	spu_acquire_saved(ctx);
-
-	ret = simple_read_from_buffer(buffer, size, pos,
-				      &lscsa->fpcr, sizeof(lscsa->fpcr));
-
+	ret = __spufs_fpcr_read(ctx, buffer, size, pos);
 	spu_release(ctx);
 	return ret;
 }
@@ -718,23 +733,41 @@ static int spufs_signal1_open(struct inode *inode, struct file *file)
 	return nonseekable_open(inode, file);
 }
 
-static ssize_t spufs_signal1_read(struct file *file, char __user *buf,
+static ssize_t __spufs_signal1_read(struct spu_context *ctx, char __user *buf,
 			size_t len, loff_t *pos)
 {
-	struct spu_context *ctx = file->private_data;
+	int ret = 0;
 	u32 data;
 
 	if (len < 4)
 		return -EINVAL;
 
-	spu_acquire(ctx);
-	data = ctx->ops->signal1_read(ctx);
-	spu_release(ctx);
+	if (ctx->csa.spu_chnlcnt_RW[3]) {
+		data = ctx->csa.spu_chnldata_RW[3];
+		ret = 4;
+	}
+
+	if (!ret)
+		goto out;
 
 	if (copy_to_user(buf, &data, 4))
 		return -EFAULT;
 
-	return 4;
+out:
+	return ret;
+}
+
+static ssize_t spufs_signal1_read(struct file *file, char __user *buf,
+			size_t len, loff_t *pos)
+{
+	int ret;
+	struct spu_context *ctx = file->private_data;
+
+	spu_acquire_saved(ctx);
+	ret = __spufs_signal1_read(ctx, buf, len, pos);
+	spu_release(ctx);
+
+	return ret;
 }
 
 static ssize_t spufs_signal1_write(struct file *file, const char __user *buf,
@@ -782,7 +815,7 @@ static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
 
@@ -807,25 +840,41 @@ static int spufs_signal2_open(struct inode *inode, struct file *file)
 	return nonseekable_open(inode, file);
 }
 
-static ssize_t spufs_signal2_read(struct file *file, char __user *buf,
+static ssize_t __spufs_signal2_read(struct spu_context *ctx, char __user *buf,
 			size_t len, loff_t *pos)
 {
-	struct spu_context *ctx;
+	int ret = 0;
 	u32 data;
 
-	ctx = file->private_data;
-
 	if (len < 4)
 		return -EINVAL;
 
-	spu_acquire(ctx);
-	data = ctx->ops->signal2_read(ctx);
-	spu_release(ctx);
+	if (ctx->csa.spu_chnlcnt_RW[4]) {
+		data =  ctx->csa.spu_chnldata_RW[4];
+		ret = 4;
+	}
+
+	if (!ret)
+		goto out;
 
 	if (copy_to_user(buf, &data, 4))
 		return -EFAULT;
 
-	return 4;
+out:
+	return ret;
+}
+
+static ssize_t spufs_signal2_read(struct file *file, char __user *buf,
+			size_t len, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	spu_acquire_saved(ctx);
+	ret = __spufs_signal2_read(ctx, buf, len, pos);
+	spu_release(ctx);
+
+	return ret;
 }
 
 static ssize_t spufs_signal2_write(struct file *file, const char __user *buf,
@@ -874,8 +923,7 @@ static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	/* FIXME: */
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
 
@@ -902,13 +950,19 @@ static void spufs_signal1_type_set(void *data, u64 val)
 	spu_release(ctx);
 }
 
+static u64 __spufs_signal1_type_get(void *data)
+{
+	struct spu_context *ctx = data;
+	return ctx->ops->signal1_type_get(ctx);
+}
+
 static u64 spufs_signal1_type_get(void *data)
 {
 	struct spu_context *ctx = data;
 	u64 ret;
 
 	spu_acquire(ctx);
-	ret = ctx->ops->signal1_type_get(ctx);
+	ret = __spufs_signal1_type_get(data);
 	spu_release(ctx);
 
 	return ret;
@@ -925,13 +979,19 @@ static void spufs_signal2_type_set(void *data, u64 val)
 	spu_release(ctx);
 }
 
+static u64 __spufs_signal2_type_get(void *data)
+{
+	struct spu_context *ctx = data;
+	return ctx->ops->signal2_type_get(ctx);
+}
+
 static u64 spufs_signal2_type_get(void *data)
 {
 	struct spu_context *ctx = data;
 	u64 ret;
 
 	spu_acquire(ctx);
-	ret = ctx->ops->signal2_type_get(ctx);
+	ret = __spufs_signal2_type_get(data);
 	spu_release(ctx);
 
 	return ret;
@@ -958,7 +1018,7 @@ static int spufs_mss_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
 
@@ -1000,7 +1060,7 @@ static int spufs_psmap_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
 
@@ -1041,7 +1101,7 @@ static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
 
@@ -1265,6 +1325,7 @@ static ssize_t spufs_mfc_write(struct file *file, const char __user *buffer,
 		goto out;
 
 	ctx->tagwait |= 1 << cmd.tag;
+	ret = size;
 
 out:
 	return ret;
@@ -1360,7 +1421,8 @@ static u64 spufs_npc_get(void *data)
 	spu_release(ctx);
 	return ret;
 }
-DEFINE_SIMPLE_ATTRIBUTE(spufs_npc_ops, spufs_npc_get, spufs_npc_set, "%llx\n")
+DEFINE_SIMPLE_ATTRIBUTE(spufs_npc_ops, spufs_npc_get, spufs_npc_set,
+			"0x%llx\n")
 
 static void spufs_decr_set(void *data, u64 val)
 {
@@ -1371,18 +1433,24 @@ static void spufs_decr_set(void *data, u64 val)
 	spu_release(ctx);
 }
 
-static u64 spufs_decr_get(void *data)
+static u64 __spufs_decr_get(void *data)
 {
 	struct spu_context *ctx = data;
 	struct spu_lscsa *lscsa = ctx->csa.lscsa;
+	return lscsa->decr.slot[0];
+}
+
+static u64 spufs_decr_get(void *data)
+{
+	struct spu_context *ctx = data;
 	u64 ret;
 	spu_acquire_saved(ctx);
-	ret = lscsa->decr.slot[0];
+	ret = __spufs_decr_get(data);
 	spu_release(ctx);
 	return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_decr_ops, spufs_decr_get, spufs_decr_set,
-			"%llx\n")
+			"0x%llx\n")
 
 static void spufs_decr_status_set(void *data, u64 val)
 {
@@ -1393,62 +1461,76 @@ static void spufs_decr_status_set(void *data, u64 val)
 	spu_release(ctx);
 }
 
-static u64 spufs_decr_status_get(void *data)
+static u64 __spufs_decr_status_get(void *data)
 {
 	struct spu_context *ctx = data;
 	struct spu_lscsa *lscsa = ctx->csa.lscsa;
+	return lscsa->decr_status.slot[0];
+}
+
+static u64 spufs_decr_status_get(void *data)
+{
+	struct spu_context *ctx = data;
 	u64 ret;
 	spu_acquire_saved(ctx);
-	ret = lscsa->decr_status.slot[0];
+	ret = __spufs_decr_status_get(data);
 	spu_release(ctx);
 	return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_decr_status_ops, spufs_decr_status_get,
-			spufs_decr_status_set, "%llx\n")
+			spufs_decr_status_set, "0x%llx\n")
 
-static void spufs_spu_tag_mask_set(void *data, u64 val)
+static void spufs_event_mask_set(void *data, u64 val)
 {
 	struct spu_context *ctx = data;
 	struct spu_lscsa *lscsa = ctx->csa.lscsa;
 	spu_acquire_saved(ctx);
-	lscsa->tag_mask.slot[0] = (u32) val;
+	lscsa->event_mask.slot[0] = (u32) val;
 	spu_release(ctx);
 }
 
-static u64 spufs_spu_tag_mask_get(void *data)
+static u64 __spufs_event_mask_get(void *data)
 {
 	struct spu_context *ctx = data;
 	struct spu_lscsa *lscsa = ctx->csa.lscsa;
+	return lscsa->event_mask.slot[0];
+}
+
+static u64 spufs_event_mask_get(void *data)
+{
+	struct spu_context *ctx = data;
 	u64 ret;
 	spu_acquire_saved(ctx);
-	ret = lscsa->tag_mask.slot[0];
+	ret = __spufs_event_mask_get(data);
 	spu_release(ctx);
 	return ret;
 }
-DEFINE_SIMPLE_ATTRIBUTE(spufs_spu_tag_mask_ops, spufs_spu_tag_mask_get,
-			spufs_spu_tag_mask_set, "%llx\n")
+DEFINE_SIMPLE_ATTRIBUTE(spufs_event_mask_ops, spufs_event_mask_get,
+			spufs_event_mask_set, "0x%llx\n")
 
-static void spufs_event_mask_set(void *data, u64 val)
+static u64 __spufs_event_status_get(void *data)
 {
 	struct spu_context *ctx = data;
-	struct spu_lscsa *lscsa = ctx->csa.lscsa;
-	spu_acquire_saved(ctx);
-	lscsa->event_mask.slot[0] = (u32) val;
-	spu_release(ctx);
+	struct spu_state *state = &ctx->csa;
+	u64 stat;
+	stat = state->spu_chnlcnt_RW[0];
+	if (stat)
+		return state->spu_chnldata_RW[0];
+	return 0;
 }
 
-static u64 spufs_event_mask_get(void *data)
+static u64 spufs_event_status_get(void *data)
 {
 	struct spu_context *ctx = data;
-	struct spu_lscsa *lscsa = ctx->csa.lscsa;
-	u64 ret;
+	u64 ret = 0;
+
 	spu_acquire_saved(ctx);
-	ret = lscsa->event_mask.slot[0];
+	ret = __spufs_event_status_get(data);
 	spu_release(ctx);
 	return ret;
 }
-DEFINE_SIMPLE_ATTRIBUTE(spufs_event_mask_ops, spufs_event_mask_get,
-			spufs_event_mask_set, "%llx\n")
+DEFINE_SIMPLE_ATTRIBUTE(spufs_event_status_ops, spufs_event_status_get,
+			NULL, "0x%llx\n")
 
 static void spufs_srr0_set(void *data, u64 val)
 {
@@ -1470,7 +1552,7 @@ static u64 spufs_srr0_get(void *data)
 	return ret;
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_srr0_ops, spufs_srr0_get, spufs_srr0_set,
-			"%llx\n")
+			"0x%llx\n")
 
 static u64 spufs_id_get(void *data)
 {
@@ -1488,12 +1570,18 @@ static u64 spufs_id_get(void *data)
 }
 DEFINE_SIMPLE_ATTRIBUTE(spufs_id_ops, spufs_id_get, NULL, "0x%llx\n")
 
-static u64 spufs_object_id_get(void *data)
+static u64 __spufs_object_id_get(void *data)
 {
 	struct spu_context *ctx = data;
 	return ctx->object_id;
 }
 
+static u64 spufs_object_id_get(void *data)
+{
+	/* FIXME: Should there really be no locking here? */
+	return __spufs_object_id_get(data);
+}
+
 static void spufs_object_id_set(void *data, u64 id)
 {
 	struct spu_context *ctx = data;
@@ -1503,6 +1591,250 @@ static void spufs_object_id_set(void *data, u64 id)
 DEFINE_SIMPLE_ATTRIBUTE(spufs_object_id_ops, spufs_object_id_get,
 		spufs_object_id_set, "0x%llx\n");
 
+static u64 __spufs_lslr_get(void *data)
+{
+	struct spu_context *ctx = data;
+	return ctx->csa.priv2.spu_lslr_RW;
+}
+
+static u64 spufs_lslr_get(void *data)
+{
+	struct spu_context *ctx = data;
+	u64 ret;
+
+	spu_acquire_saved(ctx);
+	ret = __spufs_lslr_get(data);
+	spu_release(ctx);
+
+	return ret;
+}
+DEFINE_SIMPLE_ATTRIBUTE(spufs_lslr_ops, spufs_lslr_get, NULL, "0x%llx\n")
+
+static int spufs_info_open(struct inode *inode, struct file *file)
+{
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+	file->private_data = ctx;
+	return 0;
+}
+
+static ssize_t __spufs_mbox_info_read(struct spu_context *ctx,
+			char __user *buf, size_t len, loff_t *pos)
+{
+	u32 mbox_stat;
+	u32 data;
+
+	mbox_stat = ctx->csa.prob.mb_stat_R;
+	if (mbox_stat & 0x0000ff) {
+		data = ctx->csa.prob.pu_mb_R;
+	}
+
+	return simple_read_from_buffer(buf, len, pos, &data, sizeof data);
+}
+
+static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *pos)
+{
+	int ret;
+	struct spu_context *ctx = file->private_data;
+
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	spu_acquire_saved(ctx);
+	spin_lock(&ctx->csa.register_lock);
+	ret = __spufs_mbox_info_read(ctx, buf, len, pos);
+	spin_unlock(&ctx->csa.register_lock);
+	spu_release(ctx);
+
+	return ret;
+}
+
+static struct file_operations spufs_mbox_info_fops = {
+	.open = spufs_info_open,
+	.read = spufs_mbox_info_read,
+	.llseek  = generic_file_llseek,
+};
+
+static ssize_t __spufs_ibox_info_read(struct spu_context *ctx,
+				char __user *buf, size_t len, loff_t *pos)
+{
+	u32 ibox_stat;
+	u32 data;
+
+	ibox_stat = ctx->csa.prob.mb_stat_R;
+	if (ibox_stat & 0xff0000) {
+		data = ctx->csa.priv2.puint_mb_R;
+	}
+
+	return simple_read_from_buffer(buf, len, pos, &data, sizeof data);
+}
+
+static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	spu_acquire_saved(ctx);
+	spin_lock(&ctx->csa.register_lock);
+	ret = __spufs_ibox_info_read(ctx, buf, len, pos);
+	spin_unlock(&ctx->csa.register_lock);
+	spu_release(ctx);
+
+	return ret;
+}
+
+static struct file_operations spufs_ibox_info_fops = {
+	.open = spufs_info_open,
+	.read = spufs_ibox_info_read,
+	.llseek  = generic_file_llseek,
+};
+
+static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
+			char __user *buf, size_t len, loff_t *pos)
+{
+	int i, cnt;
+	u32 data[4];
+	u32 wbox_stat;
+
+	wbox_stat = ctx->csa.prob.mb_stat_R;
+	cnt = 4 - ((wbox_stat & 0x00ff00) >> 8);
+	for (i = 0; i < cnt; i++) {
+		data[i] = ctx->csa.spu_mailbox_data[i];
+	}
+
+	return simple_read_from_buffer(buf, len, pos, &data,
+				cnt * sizeof(u32));
+}
+
+static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	spu_acquire_saved(ctx);
+	spin_lock(&ctx->csa.register_lock);
+	ret = __spufs_wbox_info_read(ctx, buf, len, pos);
+	spin_unlock(&ctx->csa.register_lock);
+	spu_release(ctx);
+
+	return ret;
+}
+
+static struct file_operations spufs_wbox_info_fops = {
+	.open = spufs_info_open,
+	.read = spufs_wbox_info_read,
+	.llseek  = generic_file_llseek,
+};
+
+static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
+			char __user *buf, size_t len, loff_t *pos)
+{
+	struct spu_dma_info info;
+	struct mfc_cq_sr *qp, *spuqp;
+	int i;
+
+	info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
+	info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
+	info.dma_info_status = ctx->csa.spu_chnldata_RW[24];
+	info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
+	info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
+	for (i = 0; i < 16; i++) {
+		qp = &info.dma_info_command_data[i];
+		spuqp = &ctx->csa.priv2.spuq[i];
+
+		qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW;
+		qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW;
+		qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW;
+		qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW;
+	}
+
+	return simple_read_from_buffer(buf, len, pos, &info,
+				sizeof info);
+}
+
+static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
+			      size_t len, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	spu_acquire_saved(ctx);
+	spin_lock(&ctx->csa.register_lock);
+	ret = __spufs_dma_info_read(ctx, buf, len, pos);
+	spin_unlock(&ctx->csa.register_lock);
+	spu_release(ctx);
+
+	return ret;
+}
+
+static struct file_operations spufs_dma_info_fops = {
+	.open = spufs_info_open,
+	.read = spufs_dma_info_read,
+};
+
+static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
+			char __user *buf, size_t len, loff_t *pos)
+{
+	struct spu_proxydma_info info;
+	struct mfc_cq_sr *qp, *puqp;
+	int ret = sizeof info;
+	int i;
+
+	if (len < ret)
+		return -EINVAL;
+
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
+	info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
+	info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
+	for (i = 0; i < 8; i++) {
+		qp = &info.proxydma_info_command_data[i];
+		puqp = &ctx->csa.priv2.puq[i];
+
+		qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
+		qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
+		qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
+		qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
+	}
+
+	return simple_read_from_buffer(buf, len, pos, &info,
+				sizeof info);
+}
+
+static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *pos)
+{
+	struct spu_context *ctx = file->private_data;
+	int ret;
+
+	spu_acquire_saved(ctx);
+	spin_lock(&ctx->csa.register_lock);
+	ret = __spufs_proxydma_info_read(ctx, buf, len, pos);
+	spin_unlock(&ctx->csa.register_lock);
+	spu_release(ctx);
+
+	return ret;
+}
+
+static struct file_operations spufs_proxydma_info_fops = {
+	.open = spufs_info_open,
+	.read = spufs_proxydma_info_read,
+};
+
 struct tree_descr spufs_dir_contents[] = {
 	{ "mem",  &spufs_mem_fops,  0666, },
 	{ "regs", &spufs_regs_fops,  0666, },
@@ -1516,18 +1848,70 @@ struct tree_descr spufs_dir_contents[] = {
 	{ "signal2", &spufs_signal2_fops, 0666, },
 	{ "signal1_type", &spufs_signal1_type, 0666, },
 	{ "signal2_type", &spufs_signal2_type, 0666, },
-	{ "mss", &spufs_mss_fops, 0666, },
-	{ "mfc", &spufs_mfc_fops, 0666, },
 	{ "cntl", &spufs_cntl_fops,  0666, },
-	{ "npc", &spufs_npc_ops, 0666, },
 	{ "fpcr", &spufs_fpcr_fops, 0666, },
+	{ "lslr", &spufs_lslr_ops, 0444, },
+	{ "mfc", &spufs_mfc_fops, 0666, },
+	{ "mss", &spufs_mss_fops, 0666, },
+	{ "npc", &spufs_npc_ops, 0666, },
+	{ "srr0", &spufs_srr0_ops, 0666, },
 	{ "decr", &spufs_decr_ops, 0666, },
 	{ "decr_status", &spufs_decr_status_ops, 0666, },
-	{ "spu_tag_mask", &spufs_spu_tag_mask_ops, 0666, },
 	{ "event_mask", &spufs_event_mask_ops, 0666, },
-	{ "srr0", &spufs_srr0_ops, 0666, },
+	{ "event_status", &spufs_event_status_ops, 0444, },
+	{ "psmap", &spufs_psmap_fops, 0666, },
+	{ "phys-id", &spufs_id_ops, 0666, },
+	{ "object-id", &spufs_object_id_ops, 0666, },
+	{ "mbox_info", &spufs_mbox_info_fops, 0444, },
+	{ "ibox_info", &spufs_ibox_info_fops, 0444, },
+	{ "wbox_info", &spufs_wbox_info_fops, 0444, },
+	{ "dma_info", &spufs_dma_info_fops, 0444, },
+	{ "proxydma_info", &spufs_proxydma_info_fops, 0444, },
+	{},
+};
+
+struct tree_descr spufs_dir_nosched_contents[] = {
+	{ "mem",  &spufs_mem_fops,  0666, },
+	{ "mbox", &spufs_mbox_fops, 0444, },
+	{ "ibox", &spufs_ibox_fops, 0444, },
+	{ "wbox", &spufs_wbox_fops, 0222, },
+	{ "mbox_stat", &spufs_mbox_stat_fops, 0444, },
+	{ "ibox_stat", &spufs_ibox_stat_fops, 0444, },
+	{ "wbox_stat", &spufs_wbox_stat_fops, 0444, },
+	{ "signal1", &spufs_signal1_fops, 0666, },
+	{ "signal2", &spufs_signal2_fops, 0666, },
+	{ "signal1_type", &spufs_signal1_type, 0666, },
+	{ "signal2_type", &spufs_signal2_type, 0666, },
+	{ "mss", &spufs_mss_fops, 0666, },
+	{ "mfc", &spufs_mfc_fops, 0666, },
+	{ "cntl", &spufs_cntl_fops,  0666, },
+	{ "npc", &spufs_npc_ops, 0666, },
 	{ "psmap", &spufs_psmap_fops, 0666, },
 	{ "phys-id", &spufs_id_ops, 0666, },
 	{ "object-id", &spufs_object_id_ops, 0666, },
 	{},
 };
+
+struct spufs_coredump_reader spufs_coredump_read[] = {
+	{ "regs", __spufs_regs_read, NULL, 128 * 16 },
+	{ "fpcr", __spufs_fpcr_read, NULL, 16 },
+	{ "lslr", NULL, __spufs_lslr_get, 11 },
+	{ "decr", NULL, __spufs_decr_get, 11 },
+	{ "decr_status", NULL, __spufs_decr_status_get, 11 },
+	{ "mem", __spufs_mem_read, NULL, 256 * 1024, },
+	{ "signal1", __spufs_signal1_read, NULL, 4 },
+	{ "signal1_type", NULL, __spufs_signal1_type_get, 2 },
+	{ "signal2", __spufs_signal2_read, NULL, 4 },
+	{ "signal2_type", NULL, __spufs_signal2_type_get, 2 },
+	{ "event_mask", NULL, __spufs_event_mask_get, 8 },
+	{ "event_status", NULL, __spufs_event_status_get, 8 },
+	{ "mbox_info", __spufs_mbox_info_read, NULL, 4 },
+	{ "ibox_info", __spufs_ibox_info_read, NULL, 4 },
+	{ "wbox_info", __spufs_wbox_info_read, NULL, 16 },
+	{ "dma_info", __spufs_dma_info_read, NULL, 69 * 8 },
+	{ "proxydma_info", __spufs_proxydma_info_read, NULL, 35 * 8 },
+	{ "object-id", NULL, __spufs_object_id_get, 19 },
+	{ },
+};
+int spufs_coredump_num_notes = ARRAY_SIZE(spufs_coredump_read) - 1;
+
diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c
index d805ffed892d..ae42e03b8c86 100644
--- a/arch/powerpc/platforms/cell/spufs/hw_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c
@@ -135,21 +135,11 @@ static int spu_hw_wbox_write(struct spu_context *ctx, u32 data)
 	return ret;
 }
 
-static u32 spu_hw_signal1_read(struct spu_context *ctx)
-{
-	return in_be32(&ctx->spu->problem->signal_notify1);
-}
-
 static void spu_hw_signal1_write(struct spu_context *ctx, u32 data)
 {
 	out_be32(&ctx->spu->problem->signal_notify1, data);
 }
 
-static u32 spu_hw_signal2_read(struct spu_context *ctx)
-{
-	return in_be32(&ctx->spu->problem->signal_notify2);
-}
-
 static void spu_hw_signal2_write(struct spu_context *ctx, u32 data)
 {
 	out_be32(&ctx->spu->problem->signal_notify2, data);
@@ -217,21 +207,42 @@ static char *spu_hw_get_ls(struct spu_context *ctx)
 	return ctx->spu->local_store;
 }
 
-static void spu_hw_runcntl_write(struct spu_context *ctx, u32 val)
+static u32 spu_hw_runcntl_read(struct spu_context *ctx)
 {
-	eieio();
-	out_be32(&ctx->spu->problem->spu_runcntl_RW, val);
+	return in_be32(&ctx->spu->problem->spu_runcntl_RW);
 }
 
-static void spu_hw_runcntl_stop(struct spu_context *ctx)
+static void spu_hw_runcntl_write(struct spu_context *ctx, u32 val)
 {
 	spin_lock_irq(&ctx->spu->register_lock);
-	out_be32(&ctx->spu->problem->spu_runcntl_RW, SPU_RUNCNTL_STOP);
-	while (in_be32(&ctx->spu->problem->spu_status_R) & SPU_STATUS_RUNNING)
-		cpu_relax();
+	if (val & SPU_RUNCNTL_ISOLATE)
+		out_be64(&ctx->spu->priv2->spu_privcntl_RW, 4LL);
+	out_be32(&ctx->spu->problem->spu_runcntl_RW, val);
 	spin_unlock_irq(&ctx->spu->register_lock);
 }
 
+static void spu_hw_master_start(struct spu_context *ctx)
+{
+	struct spu *spu = ctx->spu;
+	u64 sr1;
+
+	spin_lock_irq(&spu->register_lock);
+	sr1 = spu_mfc_sr1_get(spu) | MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+	spu_mfc_sr1_set(spu, sr1);
+	spin_unlock_irq(&spu->register_lock);
+}
+
+static void spu_hw_master_stop(struct spu_context *ctx)
+{
+	struct spu *spu = ctx->spu;
+	u64 sr1;
+
+	spin_lock_irq(&spu->register_lock);
+	sr1 = spu_mfc_sr1_get(spu) & ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+	spu_mfc_sr1_set(spu, sr1);
+	spin_unlock_irq(&spu->register_lock);
+}
+
 static int spu_hw_set_mfc_query(struct spu_context * ctx, u32 mask, u32 mode)
 {
 	struct spu_problem __iomem *prob = ctx->spu->problem;
@@ -291,9 +302,7 @@ struct spu_context_ops spu_hw_ops = {
 	.mbox_stat_poll = spu_hw_mbox_stat_poll,
 	.ibox_read = spu_hw_ibox_read,
 	.wbox_write = spu_hw_wbox_write,
-	.signal1_read = spu_hw_signal1_read,
 	.signal1_write = spu_hw_signal1_write,
-	.signal2_read = spu_hw_signal2_read,
 	.signal2_write = spu_hw_signal2_write,
 	.signal1_type_set = spu_hw_signal1_type_set,
 	.signal1_type_get = spu_hw_signal1_type_get,
@@ -303,8 +312,10 @@ struct spu_context_ops spu_hw_ops = {
 	.npc_write = spu_hw_npc_write,
 	.status_read = spu_hw_status_read,
 	.get_ls = spu_hw_get_ls,
+	.runcntl_read = spu_hw_runcntl_read,
 	.runcntl_write = spu_hw_runcntl_write,
-	.runcntl_stop = spu_hw_runcntl_stop,
+	.master_start = spu_hw_master_start,
+	.master_stop = spu_hw_master_stop,
 	.set_mfc_query = spu_hw_set_mfc_query,
 	.read_mfc_tagstatus = spu_hw_read_mfc_tagstatus,
 	.get_mfc_free_elements = spu_hw_get_mfc_free_elements,
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 427d00a4f6a0..c7d010749a18 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -33,7 +33,7 @@
 #include <linux/slab.h>
 #include <linux/parser.h>
 
-#include <asm/io.h>
+#include <asm/prom.h>
 #include <asm/semaphore.h>
 #include <asm/spu.h>
 #include <asm/uaccess.h>
@@ -41,6 +41,7 @@
 #include "spufs.h"
 
 static kmem_cache_t *spufs_inode_cache;
+char *isolated_loader;
 
 static struct inode *
 spufs_alloc_inode(struct super_block *sb)
@@ -231,6 +232,7 @@ struct file_operations spufs_context_fops = {
 	.readdir	= dcache_readdir,
 	.fsync		= simple_sync_file,
 };
+EXPORT_SYMBOL_GPL(spufs_context_fops);
 
 static int
 spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
@@ -255,10 +257,14 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 		goto out_iput;
 
 	ctx->flags = flags;
-
 	inode->i_op = &spufs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
-	ret = spufs_fill_dir(dentry, spufs_dir_contents, mode, ctx);
+	if (flags & SPU_CREATE_NOSCHED)
+		ret = spufs_fill_dir(dentry, spufs_dir_nosched_contents,
+					 mode, ctx);
+	else
+		ret = spufs_fill_dir(dentry, spufs_dir_contents, mode, ctx);
+
 	if (ret)
 		goto out_free_ctx;
 
@@ -307,6 +313,20 @@ static int spufs_create_context(struct inode *inode,
 {
 	int ret;
 
+	ret = -EPERM;
+	if ((flags & SPU_CREATE_NOSCHED) &&
+	    !capable(CAP_SYS_NICE))
+		goto out_unlock;
+
+	ret = -EINVAL;
+	if ((flags & (SPU_CREATE_NOSCHED | SPU_CREATE_ISOLATE))
+	    == SPU_CREATE_ISOLATE)
+		goto out_unlock;
+
+	ret = -ENODEV;
+	if ((flags & SPU_CREATE_ISOLATE) && !isolated_loader)
+		goto out_unlock;
+
 	ret = spufs_mkdir(inode, dentry, flags, mode & S_IRWXUGO);
 	if (ret)
 		goto out_unlock;
@@ -540,6 +560,30 @@ spufs_parse_options(char *options, struct inode *root)
 	return 1;
 }
 
+static void
+spufs_init_isolated_loader(void)
+{
+	struct device_node *dn;
+	const char *loader;
+	int size;
+
+	dn = of_find_node_by_path("/spu-isolation");
+	if (!dn)
+		return;
+
+	loader = get_property(dn, "loader", &size);
+	if (!loader)
+		return;
+
+	/* kmalloc should align on a 16 byte boundary..* */
+	isolated_loader = kmalloc(size, GFP_KERNEL);
+	if (!isolated_loader)
+		return;
+
+	memcpy(isolated_loader, loader, size);
+	printk(KERN_INFO "spufs: SPU isolation mode enabled\n");
+}
+
 static int
 spufs_create_root(struct super_block *sb, void *data)
 {
@@ -608,6 +652,7 @@ static struct file_system_type spufs_type = {
 static int __init spufs_init(void)
 {
 	int ret;
+
 	ret = -ENOMEM;
 	spufs_inode_cache = kmem_cache_create("spufs_inode_cache",
 			sizeof(struct spufs_inode_info), 0,
@@ -625,6 +670,12 @@ static int __init spufs_init(void)
 	ret = register_spu_syscalls(&spufs_calls);
 	if (ret)
 		goto out_fs;
+	ret = register_arch_coredump_calls(&spufs_coredump_calls);
+	if (ret)
+		goto out_fs;
+
+	spufs_init_isolated_loader();
+
 	return 0;
 out_fs:
 	unregister_filesystem(&spufs_type);
@@ -638,6 +689,7 @@ module_init(spufs_init);
 static void __exit spufs_exit(void)
 {
 	spu_sched_exit();
+	unregister_arch_coredump_calls(&spufs_coredump_calls);
 	unregister_spu_syscalls(&spufs_calls);
 	unregister_filesystem(&spufs_type);
 	kmem_cache_destroy(spufs_inode_cache);
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 63df8cf4ba16..1acc2ffef8c8 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -1,7 +1,11 @@
+#define DEBUG
+
 #include <linux/wait.h>
 #include <linux/ptrace.h>
 
 #include <asm/spu.h>
+#include <asm/spu_priv1.h>
+#include <asm/io.h>
 #include <asm/unistd.h>
 
 #include "spufs.h"
@@ -24,6 +28,7 @@ void spufs_dma_callback(struct spu *spu, int type)
 	} else {
 		switch (type) {
 		case SPE_EVENT_DMA_ALIGNMENT:
+		case SPE_EVENT_SPE_DATA_STORAGE:
 		case SPE_EVENT_INVALID_DMA:
 			force_sig(SIGBUS, /* info, */ current);
 			break;
@@ -48,15 +53,122 @@ static inline int spu_stopped(struct spu_context *ctx, u32 * stat)
 	return (!(*stat & 0x1) || pte_fault || spu->class_0_pending) ? 1 : 0;
 }
 
+static int spu_setup_isolated(struct spu_context *ctx)
+{
+	int ret;
+	u64 __iomem *mfc_cntl;
+	u64 sr1;
+	u32 status;
+	unsigned long timeout;
+	const u32 status_loading = SPU_STATUS_RUNNING
+		| SPU_STATUS_ISOLATED_STATE | SPU_STATUS_ISOLATED_LOAD_STATUS;
+
+	if (!isolated_loader)
+		return -ENODEV;
+
+	ret = spu_acquire_exclusive(ctx);
+	if (ret)
+		goto out;
+
+	mfc_cntl = &ctx->spu->priv2->mfc_control_RW;
+
+	/* purge the MFC DMA queue to ensure no spurious accesses before we
+	 * enter kernel mode */
+	timeout = jiffies + HZ;
+	out_be64(mfc_cntl, MFC_CNTL_PURGE_DMA_REQUEST);
+	while ((in_be64(mfc_cntl) & MFC_CNTL_PURGE_DMA_STATUS_MASK)
+			!= MFC_CNTL_PURGE_DMA_COMPLETE) {
+		if (time_after(jiffies, timeout)) {
+			printk(KERN_ERR "%s: timeout flushing MFC DMA queue\n",
+					__FUNCTION__);
+			ret = -EIO;
+			goto out_unlock;
+		}
+		cond_resched();
+	}
+
+	/* put the SPE in kernel mode to allow access to the loader */
+	sr1 = spu_mfc_sr1_get(ctx->spu);
+	sr1 &= ~MFC_STATE1_PROBLEM_STATE_MASK;
+	spu_mfc_sr1_set(ctx->spu, sr1);
+
+	/* start the loader */
+	ctx->ops->signal1_write(ctx, (unsigned long)isolated_loader >> 32);
+	ctx->ops->signal2_write(ctx,
+			(unsigned long)isolated_loader & 0xffffffff);
+
+	ctx->ops->runcntl_write(ctx,
+			SPU_RUNCNTL_RUNNABLE | SPU_RUNCNTL_ISOLATE);
+
+	ret = 0;
+	timeout = jiffies + HZ;
+	while (((status = ctx->ops->status_read(ctx)) & status_loading) ==
+				status_loading) {
+		if (time_after(jiffies, timeout)) {
+			printk(KERN_ERR "%s: timeout waiting for loader\n",
+					__FUNCTION__);
+			ret = -EIO;
+			goto out_drop_priv;
+		}
+		cond_resched();
+	}
+
+	if (!(status & SPU_STATUS_RUNNING)) {
+		/* If isolated LOAD has failed: run SPU, we will get a stop-and
+		 * signal later. */
+		pr_debug("%s: isolated LOAD failed\n", __FUNCTION__);
+		ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
+		ret = -EACCES;
+
+	} else if (!(status & SPU_STATUS_ISOLATED_STATE)) {
+		/* This isn't allowed by the CBEA, but check anyway */
+		pr_debug("%s: SPU fell out of isolated mode?\n", __FUNCTION__);
+		ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_STOP);
+		ret = -EINVAL;
+	}
+
+out_drop_priv:
+	/* Finished accessing the loader. Drop kernel mode */
+	sr1 |= MFC_STATE1_PROBLEM_STATE_MASK;
+	spu_mfc_sr1_set(ctx->spu, sr1);
+
+out_unlock:
+	spu_release_exclusive(ctx);
+out:
+	return ret;
+}
+
 static inline int spu_run_init(struct spu_context *ctx, u32 * npc)
 {
 	int ret;
+	unsigned long runcntl = SPU_RUNCNTL_RUNNABLE;
 
-	if ((ret = spu_acquire_runnable(ctx)) != 0)
+	ret = spu_acquire_runnable(ctx);
+	if (ret)
 		return ret;
-	ctx->ops->npc_write(ctx, *npc);
-	ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
-	return 0;
+
+	if (ctx->flags & SPU_CREATE_ISOLATE) {
+		if (!(ctx->ops->status_read(ctx) & SPU_STATUS_ISOLATED_STATE)) {
+			/* Need to release ctx, because spu_setup_isolated will
+			 * acquire it exclusively.
+			 */
+			spu_release(ctx);
+			ret = spu_setup_isolated(ctx);
+			if (!ret)
+				ret = spu_acquire_runnable(ctx);
+		}
+
+		/* if userspace has set the runcntrl register (eg, to issue an
+		 * isolated exit), we need to re-set it here */
+		runcntl = ctx->ops->runcntl_read(ctx) &
+			(SPU_RUNCNTL_RUNNABLE | SPU_RUNCNTL_ISOLATE);
+		if (runcntl == 0)
+			runcntl = SPU_RUNCNTL_RUNNABLE;
+	} else
+		ctx->ops->npc_write(ctx, *npc);
+
+	ctx->ops->runcntl_write(ctx, runcntl);
+	return ret;
 }
 
 static inline int spu_run_fini(struct spu_context *ctx, u32 * npc,
@@ -70,13 +182,7 @@ static inline int spu_run_fini(struct spu_context *ctx, u32 * npc,
 
 	if (signal_pending(current))
 		ret = -ERESTARTSYS;
-	if (unlikely(current->ptrace & PT_PTRACED)) {
-		if ((*status & SPU_STATUS_STOPPED_BY_STOP)
-		    && (*status >> SPU_STOP_STATUS_SHIFT) == 0x3fff) {
-			force_sig(SIGTRAP, current);
-			ret = -ERESTARTSYS;
-		}
-	}
+
 	return ret;
 }
 
@@ -204,6 +310,7 @@ long spufs_run_spu(struct file *file, struct spu_context *ctx,
 	if (down_interruptible(&ctx->run_sema))
 		return -ERESTARTSYS;
 
+	ctx->ops->master_start(ctx);
 	ctx->event_return = 0;
 	ret = spu_run_init(ctx, npc);
 	if (ret)
@@ -223,7 +330,7 @@ long spufs_run_spu(struct file *file, struct spu_context *ctx,
 		if (unlikely(ctx->state != SPU_STATE_RUNNABLE)) {
 			ret = spu_reacquire_runnable(ctx, npc, &status);
 			if (ret)
-				goto out;
+				goto out2;
 			continue;
 		}
 		ret = spu_process_events(ctx);
@@ -231,12 +338,24 @@ long spufs_run_spu(struct file *file, struct spu_context *ctx,
 	} while (!ret && !(status & (SPU_STATUS_STOPPED_BY_STOP |
 				      SPU_STATUS_STOPPED_BY_HALT)));
 
-	ctx->ops->runcntl_stop(ctx);
+	ctx->ops->master_stop(ctx);
 	ret = spu_run_fini(ctx, npc, &status);
-	if (!ret)
-		ret = status;
 	spu_yield(ctx);
 
+out2:
+	if ((ret == 0) ||
+	    ((ret == -ERESTARTSYS) &&
+	     ((status & SPU_STATUS_STOPPED_BY_HALT) ||
+	      ((status & SPU_STATUS_STOPPED_BY_STOP) &&
+	       (status >> SPU_STOP_STATUS_SHIFT != 0x2104)))))
+		ret = status;
+
+	if ((status & SPU_STATUS_STOPPED_BY_STOP)
+	    && (status >> SPU_STOP_STATUS_SHIFT) == 0x3fff) {
+		force_sig(SIGTRAP, current);
+		ret = -ERESTARTSYS;
+	}
+
 out:
 	*event = ctx->event_return;
 	up(&ctx->run_sema);
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index a0f55ca2d488..70fb13395c04 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -29,6 +29,7 @@
 
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
+#include <asm/spu_info.h>
 
 /* The magic number for our file system */
 enum {
@@ -114,13 +115,19 @@ struct spu_context_ops {
 	void (*npc_write) (struct spu_context * ctx, u32 data);
 	 u32(*status_read) (struct spu_context * ctx);
 	char*(*get_ls) (struct spu_context * ctx);
+	 u32 (*runcntl_read) (struct spu_context * ctx);
 	void (*runcntl_write) (struct spu_context * ctx, u32 data);
-	void (*runcntl_stop) (struct spu_context * ctx);
+	void (*master_start) (struct spu_context * ctx);
+	void (*master_stop) (struct spu_context * ctx);
 	int (*set_mfc_query)(struct spu_context * ctx, u32 mask, u32 mode);
 	u32 (*read_mfc_tagstatus)(struct spu_context * ctx);
 	u32 (*get_mfc_free_elements)(struct spu_context *ctx);
-	int (*send_mfc_command)(struct spu_context *ctx,
-					struct mfc_dma_command *cmd);
+	int (*send_mfc_command)(struct spu_context * ctx,
+				struct mfc_dma_command * cmd);
+	void (*dma_info_read) (struct spu_context * ctx,
+			       struct spu_dma_info * info);
+	void (*proxydma_info_read) (struct spu_context * ctx,
+				    struct spu_proxydma_info * info);
 };
 
 extern struct spu_context_ops spu_hw_ops;
@@ -135,6 +142,7 @@ struct spufs_inode_info {
 	container_of(inode, struct spufs_inode_info, vfs_inode)
 
 extern struct tree_descr spufs_dir_contents[];
+extern struct tree_descr spufs_dir_nosched_contents[];
 
 /* system call implementation */
 long spufs_run_spu(struct file *file,
@@ -162,6 +170,12 @@ void spu_acquire(struct spu_context *ctx);
 void spu_release(struct spu_context *ctx);
 int spu_acquire_runnable(struct spu_context *ctx);
 void spu_acquire_saved(struct spu_context *ctx);
+int spu_acquire_exclusive(struct spu_context *ctx);
+
+static inline void spu_release_exclusive(struct spu_context *ctx)
+{
+	up_write(&ctx->state_sema);
+}
 
 int spu_activate(struct spu_context *ctx, u64 flags);
 void spu_deactivate(struct spu_context *ctx);
@@ -169,6 +183,8 @@ void spu_yield(struct spu_context *ctx);
 int __init spu_sched_init(void);
 void __exit spu_sched_exit(void);
 
+extern char *isolated_loader;
+
 /*
  * spufs_wait
  * 	Same as wait_event_interruptible(), except that here
@@ -207,4 +223,15 @@ void spufs_stop_callback(struct spu *spu);
 void spufs_mfc_callback(struct spu *spu);
 void spufs_dma_callback(struct spu *spu, int type);
 
+extern struct spu_coredump_calls spufs_coredump_calls;
+struct spufs_coredump_reader {
+	char *name;
+	ssize_t (*read)(struct spu_context *ctx,
+			char __user *buffer, size_t size, loff_t *pos);
+	u64 (*get)(void *data);
+	size_t size;
+};
+extern struct spufs_coredump_reader spufs_coredump_read[];
+extern int spufs_coredump_num_notes;
+
 #endif
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 0f782ca662ba..c08981ff7fc6 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -102,7 +102,7 @@ static inline int check_spu_isolate(struct spu_state *csa, struct spu *spu)
 	 *     saved at this time.
 	 */
 	isolate_state = SPU_STATUS_ISOLATED_STATE |
-	    SPU_STATUS_ISOLATED_LOAD_STAUTUS | SPU_STATUS_ISOLATED_EXIT_STAUTUS;
+	    SPU_STATUS_ISOLATED_LOAD_STATUS | SPU_STATUS_ISOLATED_EXIT_STATUS;
 	return (in_be32(&prob->spu_status_R) & isolate_state) ? 1 : 0;
 }
 
@@ -1046,12 +1046,12 @@ static inline int suspend_spe(struct spu_state *csa, struct spu *spu)
 	 */
 	if (in_be32(&prob->spu_status_R) & SPU_STATUS_RUNNING) {
 		if (in_be32(&prob->spu_status_R) &
-		    SPU_STATUS_ISOLATED_EXIT_STAUTUS) {
+		    SPU_STATUS_ISOLATED_EXIT_STATUS) {
 			POLL_WHILE_TRUE(in_be32(&prob->spu_status_R) &
 					SPU_STATUS_RUNNING);
 		}
 		if ((in_be32(&prob->spu_status_R) &
-		     SPU_STATUS_ISOLATED_LOAD_STAUTUS)
+		     SPU_STATUS_ISOLATED_LOAD_STATUS)
 		    || (in_be32(&prob->spu_status_R) &
 			SPU_STATUS_ISOLATED_STATE)) {
 			out_be32(&prob->spu_runcntl_RW, SPU_RUNCNTL_STOP);
@@ -1085,7 +1085,7 @@ static inline void clear_spu_status(struct spu_state *csa, struct spu *spu)
 	 */
 	if (!(in_be32(&prob->spu_status_R) & SPU_STATUS_RUNNING)) {
 		if (in_be32(&prob->spu_status_R) &
-		    SPU_STATUS_ISOLATED_EXIT_STAUTUS) {
+		    SPU_STATUS_ISOLATED_EXIT_STATUS) {
 			spu_mfc_sr1_set(spu,
 					MFC_STATE1_MASTER_RUN_CONTROL_MASK);
 			eieio();
@@ -1095,7 +1095,7 @@ static inline void clear_spu_status(struct spu_state *csa, struct spu *spu)
 					SPU_STATUS_RUNNING);
 		}
 		if ((in_be32(&prob->spu_status_R) &
-		     SPU_STATUS_ISOLATED_LOAD_STAUTUS)
+		     SPU_STATUS_ISOLATED_LOAD_STATUS)
 		    || (in_be32(&prob->spu_status_R) &
 			SPU_STATUS_ISOLATED_STATE)) {
 			spu_mfc_sr1_set(spu,
@@ -1916,6 +1916,51 @@ static void save_lscsa(struct spu_state *prev, struct spu *spu)
 	wait_spu_stopped(prev, spu);	/* Step 57. */
 }
 
+static void force_spu_isolate_exit(struct spu *spu)
+{
+	struct spu_problem __iomem *prob = spu->problem;
+	struct spu_priv2 __iomem *priv2 = spu->priv2;
+
+	/* Stop SPE execution and wait for completion. */
+	out_be32(&prob->spu_runcntl_RW, SPU_RUNCNTL_STOP);
+	iobarrier_rw();
+	POLL_WHILE_TRUE(in_be32(&prob->spu_status_R) & SPU_STATUS_RUNNING);
+
+	/* Restart SPE master runcntl. */
+	spu_mfc_sr1_set(spu, MFC_STATE1_MASTER_RUN_CONTROL_MASK);
+	iobarrier_w();
+
+	/* Initiate isolate exit request and wait for completion. */
+	out_be64(&priv2->spu_privcntl_RW, 4LL);
+	iobarrier_w();
+	out_be32(&prob->spu_runcntl_RW, 2);
+	iobarrier_rw();
+	POLL_WHILE_FALSE((in_be32(&prob->spu_status_R)
+				& SPU_STATUS_STOPPED_BY_STOP));
+
+	/* Reset load request to normal. */
+	out_be64(&priv2->spu_privcntl_RW, SPU_PRIVCNT_LOAD_REQUEST_NORMAL);
+	iobarrier_w();
+}
+
+/**
+ * stop_spu_isolate
+ *	Check SPU run-control state and force isolated
+ *	exit function as necessary.
+ */
+static void stop_spu_isolate(struct spu *spu)
+{
+	struct spu_problem __iomem *prob = spu->problem;
+
+	if (in_be32(&prob->spu_status_R) & SPU_STATUS_ISOLATED_STATE) {
+		/* The SPU is in isolated state; the only way
+		 * to get it out is to perform an isolated
+		 * exit (clean) operation.
+		 */
+		force_spu_isolate_exit(spu);
+	}
+}
+
 static void harvest(struct spu_state *prev, struct spu *spu)
 {
 	/*
@@ -1928,6 +1973,7 @@ static void harvest(struct spu_state *prev, struct spu *spu)
 	inhibit_user_access(prev, spu);	        /* Step 3.  */
 	terminate_spu_app(prev, spu);	        /* Step 4.  */
 	set_switch_pending(prev, spu);	        /* Step 5.  */
+	stop_spu_isolate(spu);			/* NEW.     */
 	remove_other_spu_access(prev, spu);	/* Step 6.  */
 	suspend_mfc(prev, spu);	                /* Step 7.  */
 	wait_suspend_mfc_complete(prev, spu);	/* Step 8.  */
@@ -2096,11 +2142,11 @@ int spu_save(struct spu_state *prev, struct spu *spu)
 	acquire_spu_lock(spu);	        /* Step 1.     */
 	rc = __do_spu_save(prev, spu);	/* Steps 2-53. */
 	release_spu_lock(spu);
-	if (rc) {
+	if (rc != 0 && rc != 2 && rc != 6) {
 		panic("%s failed on SPU[%d], rc=%d.\n",
 		      __func__, spu->number, rc);
 	}
-	return rc;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(spu_save);
 
@@ -2165,9 +2211,6 @@ static void init_priv1(struct spu_state *csa)
 	    MFC_STATE1_PROBLEM_STATE_MASK |
 	    MFC_STATE1_RELOCATE_MASK | MFC_STATE1_BUS_TLBIE_MASK;
 
-	/* Set storage description.  */
-	csa->priv1.mfc_sdr_RW = mfspr(SPRN_SDR1);
-
 	/* Enable OS-specific set of interrupts. */
 	csa->priv1.int_mask_class0_RW = CLASS0_ENABLE_DMA_ALIGNMENT_INTR |
 	    CLASS0_ENABLE_INVALID_DMA_COMMAND_INTR |
diff --git a/arch/powerpc/platforms/chrp/chrp.h b/arch/powerpc/platforms/chrp/chrp.h
index 996c28744e96..63f0aee4c158 100644
--- a/arch/powerpc/platforms/chrp/chrp.h
+++ b/arch/powerpc/platforms/chrp/chrp.h
@@ -9,4 +9,3 @@ extern long chrp_time_init(void);
 
 extern void chrp_find_bridges(void);
 extern void chrp_event_scan(unsigned long);
-extern void chrp_pcibios_fixup(void);
diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c
index 0f4340506c75..ddb4a116ea89 100644
--- a/arch/powerpc/platforms/chrp/pci.c
+++ b/arch/powerpc/platforms/chrp/pci.c
@@ -156,15 +156,6 @@ hydra_init(void)
 	return 1;
 }
 
-void __init
-chrp_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-
-	for_each_pci_dev(dev)
-		pci_read_irq_line(dev);
-}
-
 #define PRG_CL_RESET_VALID 0x00010000
 
 static void __init
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 49b8dabcbc99..e1f51d455984 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -588,7 +588,6 @@ static int __init chrp_probe(void)
 	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
-	isa_io_base = CHRP_ISA_IO_BASE;		/* default value */
 
 	return 1;
 }
@@ -600,7 +599,6 @@ define_machine(chrp) {
 	.init			= chrp_init2,
 	.show_cpuinfo		= chrp_show_cpuinfo,
 	.init_IRQ		= chrp_init_IRQ,
-	.pcibios_fixup		= chrp_pcibios_fixup,
 	.restart		= rtas_restart,
 	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig
index 234a861870a8..ddbe398fbd48 100644
--- a/arch/powerpc/platforms/embedded6xx/Kconfig
+++ b/arch/powerpc/platforms/embedded6xx/Kconfig
@@ -74,6 +74,18 @@ config SANDPOINT
 	  Select SANDPOINT if configuring for a Motorola Sandpoint X3
 	  (any flavor).
 
+config LINKSTATION
+	bool "Linkstation / Kurobox(HG) from Buffalo"
+	select MPIC
+	select FSL_SOC
+	select PPC_UDBG_16550 if SERIAL_8250
+	help
+	  Select LINKSTATION if configuring for one of PPC- (MPC8241)
+	  based NAS systems from Buffalo Technology. So far only
+	  KuroboxHG has been tested. In the future classical Kurobox,
+	  Linkstation-I HD-HLAN and HD-HGLAN versions, and PPC-based
+	  Terastation systems should be supported too.
+
 config MPC7448HPC2
 	bool "Freescale MPC7448HPC2(Taiga)"
 	select TSI108_BRIDGE
@@ -146,15 +158,6 @@ config PQ2FADS
 	  Select PQ2FADS if you wish to configure for a Freescale
 	  PQ2FADS board (-VR or -ZU).
 
-config LITE5200
-	bool "Freescale LITE5200 / (IceCube)"
-	select PPC_MPC52xx
-	help
-	  Support for the LITE5200 dev board for the MPC5200 from Freescale.
-	  This is for the LITE5200 version 2.0 board. Don't know if it changes
-	  much but it's only been tested on this board version. I think this
-	  board is also known as IceCube.
-
 config EV64360
 	bool "Marvell-EV64360BP"
 	help
@@ -172,9 +175,6 @@ config TQM8xxL
 	depends on 8xx && (TQM823L || TQM850L || FPS850L || TQM855L || TQM860L)
 	default y
 
-config PPC_MPC52xx
-	bool
-
 config 8260
 	bool "CPM2 Support" if WILLOW
 	depends on 6xx
@@ -208,7 +208,7 @@ config PPC_GEN550
 	depends on SANDPOINT || SPRUCE || PPLUS || \
 		PRPMC750 || PRPMC800 || LOPEC || \
 		(EV64260 && !SERIAL_MPSC) || CHESTNUT || RADSTONE_PPC7D || \
-		83xx
+		83xx || LINKSTATION
 	default y
 
 config FORCE
@@ -282,13 +282,13 @@ config EPIC_SERIAL_MODE
 
 config MPC10X_BRIDGE
 	bool
-	depends on POWERPMC250 || LOPEC || SANDPOINT
+	depends on POWERPMC250 || LOPEC || SANDPOINT || LINKSTATION
 	select PPC_INDIRECT_PCI
 	default y
 
 config MPC10X_OPENPIC
 	bool
-	depends on POWERPMC250 || LOPEC || SANDPOINT
+	depends on POWERPMC250 || LOPEC || SANDPOINT || LINKSTATION
 	default y
 
 config MPC10X_STORE_GATHERING
diff --git a/arch/powerpc/platforms/embedded6xx/Makefile b/arch/powerpc/platforms/embedded6xx/Makefile
index fa499fe59291..d3d11a3cd656 100644
--- a/arch/powerpc/platforms/embedded6xx/Makefile
+++ b/arch/powerpc/platforms/embedded6xx/Makefile
@@ -2,3 +2,4 @@
 # Makefile for the 6xx/7xx/7xxxx linux kernel.
 #
 obj-$(CONFIG_MPC7448HPC2)	+= mpc7448_hpc2.o
+obj-$(CONFIG_LINKSTATION)	+= linkstation.o ls_uart.o
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
new file mode 100644
index 000000000000..61599d919ea8
--- /dev/null
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -0,0 +1,211 @@
+/*
+ * Board setup routines for the Buffalo Linkstation / Kurobox Platform.
+ *
+ * Copyright (C) 2006 G. Liakhovetski (g.liakhovetski@gmx.de)
+ *
+ * Based on sandpoint.c by Mark A. Greer
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of
+ * any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/initrd.h>
+#include <linux/root_dev.h>
+#include <linux/mtd/physmap.h>
+
+#include <asm/time.h>
+#include <asm/prom.h>
+#include <asm/mpic.h>
+#include <asm/mpc10x.h>
+#include <asm/pci-bridge.h>
+
+static struct mtd_partition linkstation_physmap_partitions[] = {
+	{
+		.name   = "mtd_firmimg",
+		.offset = 0x000000,
+		.size   = 0x300000,
+	},
+	{
+		.name   = "mtd_bootcode",
+		.offset = 0x300000,
+		.size   = 0x070000,
+	},
+	{
+		.name   = "mtd_status",
+		.offset = 0x370000,
+		.size   = 0x010000,
+	},
+	{
+		.name   = "mtd_conf",
+		.offset = 0x380000,
+		.size   = 0x080000,
+	},
+	{
+		.name   = "mtd_allflash",
+		.offset = 0x000000,
+		.size   = 0x400000,
+	},
+	{
+		.name   = "mtd_data",
+		.offset = 0x310000,
+		.size   = 0x0f0000,
+	},
+};
+
+static int __init add_bridge(struct device_node *dev)
+{
+	int len;
+	struct pci_controller *hose;
+	int *bus_range;
+
+	printk("Adding PCI host bridge %s\n", dev->full_name);
+
+	bus_range = (int *) get_property(dev, "bus-range", &len);
+	if (bus_range == NULL || len < 2 * sizeof(int))
+		printk(KERN_WARNING "Can't get bus-range for %s, assume"
+				" bus 0\n", dev->full_name);
+
+	hose = pcibios_alloc_controller();
+	if (hose == NULL)
+		return -ENOMEM;
+	hose->first_busno = bus_range ? bus_range[0] : 0;
+	hose->last_busno = bus_range ? bus_range[1] : 0xff;
+	hose->arch_data = dev;
+	setup_indirect_pci(hose, 0xfec00000, 0xfee00000);
+
+	/* Interpret the "ranges" property */
+	/* This also maps the I/O region and sets isa_io/mem_base */
+	pci_process_bridge_OF_ranges(hose, dev, 1);
+
+	return 0;
+}
+
+static void __init linkstation_setup_arch(void)
+{
+	struct device_node *np;
+#ifdef CONFIG_MTD_PHYSMAP
+	physmap_set_partitions(linkstation_physmap_partitions,
+			       ARRAY_SIZE(linkstation_physmap_partitions));
+#endif
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (initrd_start)
+		ROOT_DEV = Root_RAM0;
+	else
+#endif
+#ifdef	CONFIG_ROOT_NFS
+		ROOT_DEV = Root_NFS;
+#else
+		ROOT_DEV = Root_HDA1;
+#endif
+
+	/* Lookup PCI host bridges */
+	for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;)
+		add_bridge(np);
+
+	printk(KERN_INFO "BUFFALO Network Attached Storage Series\n");
+	printk(KERN_INFO "(C) 2002-2005 BUFFALO INC.\n");
+}
+
+/*
+ * Interrupt setup and service.  Interrrupts on the linkstation come
+ * from the four PCI slots plus onboard 8241 devices: I2C, DUART.
+ */
+static void __init linkstation_init_IRQ(void)
+{
+	struct mpic *mpic;
+	struct device_node *dnp;
+	void *prop;
+	int size;
+	phys_addr_t paddr;
+
+	dnp = of_find_node_by_type(NULL, "open-pic");
+	if (dnp == NULL)
+		return;
+
+	prop = (struct device_node *)get_property(dnp, "reg", &size);
+	paddr = (phys_addr_t)of_translate_address(dnp, prop);
+
+	mpic = mpic_alloc(dnp, paddr, MPIC_PRIMARY | MPIC_WANTS_RESET, 4, 32, " EPIC     ");
+	BUG_ON(mpic == NULL);
+
+	/* PCI IRQs */
+	mpic_assign_isu(mpic, 0, paddr + 0x10200);
+
+	/* I2C */
+	mpic_assign_isu(mpic, 1, paddr + 0x11000);
+
+	/* ttyS0, ttyS1 */
+	mpic_assign_isu(mpic, 2, paddr + 0x11100);
+
+	mpic_init(mpic);
+}
+
+extern void avr_uart_configure(void);
+extern void avr_uart_send(const char);
+
+static void linkstation_restart(char *cmd)
+{
+	local_irq_disable();
+
+	/* Reset system via AVR */
+	avr_uart_configure();
+	/* Send reboot command */
+	avr_uart_send('C');
+
+	for(;;)  /* Spin until reset happens */
+		avr_uart_send('G');	/* "kick" */
+}
+
+static void linkstation_power_off(void)
+{
+	local_irq_disable();
+
+	/* Power down system via AVR */
+	avr_uart_configure();
+	/* send shutdown command */
+	avr_uart_send('E');
+
+	for(;;)  /* Spin until power-off happens */
+		avr_uart_send('G');	/* "kick" */
+	/* NOTREACHED */
+}
+
+static void linkstation_halt(void)
+{
+	linkstation_power_off();
+	/* NOTREACHED */
+}
+
+static void linkstation_show_cpuinfo(struct seq_file *m)
+{
+	seq_printf(m, "vendor\t\t: Buffalo Technology\n");
+	seq_printf(m, "machine\t\t: Linkstation I/Kurobox(HG)\n");
+}
+
+static int __init linkstation_probe(void)
+{
+	unsigned long root;
+
+	root = of_get_flat_dt_root();
+
+	if (!of_flat_dt_is_compatible(root, "linkstation"))
+		return 0;
+	return 1;
+}
+
+define_machine(linkstation){
+	.name 			= "Buffalo Linkstation",
+	.probe 			= linkstation_probe,
+	.setup_arch 		= linkstation_setup_arch,
+	.init_IRQ 		= linkstation_init_IRQ,
+	.show_cpuinfo 		= linkstation_show_cpuinfo,
+	.get_irq 		= mpic_get_irq,
+	.restart 		= linkstation_restart,
+	.power_off 		= linkstation_power_off,
+	.halt	 		= linkstation_halt,
+	.calibrate_decr 	= generic_calibrate_decr,
+};
diff --git a/arch/powerpc/platforms/embedded6xx/ls_uart.c b/arch/powerpc/platforms/embedded6xx/ls_uart.c
new file mode 100644
index 000000000000..31bcdae84823
--- /dev/null
+++ b/arch/powerpc/platforms/embedded6xx/ls_uart.c
@@ -0,0 +1,131 @@
+#include <linux/workqueue.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/serial_reg.h>
+#include <linux/serial_8250.h>
+#include <asm/io.h>
+#include <asm/mpc10x.h>
+#include <asm/ppc_sys.h>
+#include <asm/prom.h>
+#include <asm/termbits.h>
+
+static void __iomem *avr_addr;
+static unsigned long avr_clock;
+
+static struct work_struct wd_work;
+
+static void wd_stop(void *unused)
+{
+	const char string[] = "AAAAFFFFJJJJ>>>>VVVV>>>>ZZZZVVVVKKKK";
+	int i = 0, rescue = 8;
+	int len = strlen(string);
+
+	while (rescue--) {
+		int j;
+		char lsr = in_8(avr_addr + UART_LSR);
+
+		if (lsr & (UART_LSR_THRE | UART_LSR_TEMT)) {
+			for (j = 0; j < 16 && i < len; j++, i++)
+				out_8(avr_addr + UART_TX, string[i]);
+			if (i == len) {
+				/* Read "OK" back: 4ms for the last "KKKK"
+				   plus a couple bytes back */
+				msleep(7);
+				printk("linkstation: disarming the AVR watchdog: ");
+				while (in_8(avr_addr + UART_LSR) & UART_LSR_DR)
+					printk("%c", in_8(avr_addr + UART_RX));
+				break;
+			}
+		}
+		msleep(17);
+	}
+	printk("\n");
+}
+
+#define AVR_QUOT(clock) ((clock) + 8 * 9600) / (16 * 9600)
+
+void avr_uart_configure(void)
+{
+	unsigned char cval = UART_LCR_WLEN8;
+	unsigned int quot = AVR_QUOT(avr_clock);
+
+	if (!avr_addr || !avr_clock)
+		return;
+
+	out_8(avr_addr + UART_LCR, cval);			/* initialise UART */
+	out_8(avr_addr + UART_MCR, 0);
+	out_8(avr_addr + UART_IER, 0);
+
+	cval |= UART_LCR_STOP | UART_LCR_PARITY | UART_LCR_EPAR;
+
+	out_8(avr_addr + UART_LCR, cval);			/* Set character format */
+
+	out_8(avr_addr + UART_LCR, cval | UART_LCR_DLAB);	/* set DLAB */
+	out_8(avr_addr + UART_DLL, quot & 0xff);		/* LS of divisor */
+	out_8(avr_addr + UART_DLM, quot >> 8);			/* MS of divisor */
+	out_8(avr_addr + UART_LCR, cval);			/* reset DLAB */
+	out_8(avr_addr + UART_FCR, UART_FCR_ENABLE_FIFO);	/* enable FIFO */
+}
+
+void avr_uart_send(const char c)
+{
+	if (!avr_addr || !avr_clock)
+		return;
+
+	out_8(avr_addr + UART_TX, c);
+	out_8(avr_addr + UART_TX, c);
+	out_8(avr_addr + UART_TX, c);
+	out_8(avr_addr + UART_TX, c);
+}
+
+static void __init ls_uart_init(void)
+{
+	local_irq_disable();
+
+#ifndef CONFIG_SERIAL_8250
+	out_8(avr_addr + UART_FCR, UART_FCR_ENABLE_FIFO);	/* enable FIFO */
+	out_8(avr_addr + UART_FCR, UART_FCR_ENABLE_FIFO |
+	      UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT);	/* clear FIFOs */
+	out_8(avr_addr + UART_FCR, 0);
+	out_8(avr_addr + UART_IER, 0);
+
+	/* Clear up interrupts */
+	(void) in_8(avr_addr + UART_LSR);
+	(void) in_8(avr_addr + UART_RX);
+	(void) in_8(avr_addr + UART_IIR);
+	(void) in_8(avr_addr + UART_MSR);
+#endif
+	avr_uart_configure();
+
+	local_irq_enable();
+}
+
+static int __init ls_uarts_init(void)
+{
+	struct device_node *avr;
+	phys_addr_t phys_addr;
+	int len;
+
+	avr = of_find_node_by_path("/soc10x/serial@80004500");
+	if (!avr)
+		return -EINVAL;
+
+	avr_clock = *(u32*)get_property(avr, "clock-frequency", &len);
+	phys_addr = ((u32*)get_property(avr, "reg", &len))[0];
+
+	if (!avr_clock || !phys_addr)
+		return -EINVAL;
+
+	avr_addr = ioremap(phys_addr, 32);
+	if (!avr_addr)
+		return -EFAULT;
+
+	ls_uart_init();
+
+	INIT_WORK(&wd_work, wd_stop, NULL);
+	schedule_work(&wd_work);
+
+	return 0;
+}
+
+late_initcall(ls_uarts_init);
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index bdb475c65cba..3fcc85f60fbf 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -60,7 +60,7 @@ pci_dram_offset = MPC7448_HPC2_PCI_MEM_OFFSET;
 
 extern int tsi108_setup_pci(struct device_node *dev);
 extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val);
-extern void tsi108_pci_int_init(void);
+extern void tsi108_pci_int_init(struct device_node *node);
 extern void tsi108_irq_cascade(unsigned int irq, struct irq_desc *desc);
 
 int mpc7448_hpc2_exclude_device(u_char bus, u_char devfn)
@@ -71,65 +71,6 @@ int mpc7448_hpc2_exclude_device(u_char bus, u_char devfn)
 		return PCIBIOS_SUCCESSFUL;
 }
 
-/*
- * find pci slot by devfn in interrupt map of OF tree
- */
-u8 find_slot_by_devfn(unsigned int *interrupt_map, unsigned int devfn)
-{
-	int i;
-	unsigned int tmp;
-	for (i = 0; i < 4; i++){
-		tmp = interrupt_map[i*4*7];
-		if ((tmp >> 11) == (devfn >> 3))
-			return i;
-	}
-	return i;
-}
-
-/*
- * Scans the interrupt map for pci device
- */
-void mpc7448_hpc2_fixup_irq(struct pci_dev *dev)
-{
-	struct pci_controller *hose;
-	struct device_node *node;
-	const unsigned int *interrupt;
-	int busnr;
-	int len;
-	u8 slot;
-	u8 pin;
-
-	/* Lookup the hose */
-	busnr = dev->bus->number;
-	hose = pci_bus_to_hose(busnr);
-	if (!hose)
-		printk(KERN_ERR "No pci hose found\n");
-
-	/* Check it has an OF node associated */
-	node = (struct device_node *) hose->arch_data;
-	if (!node)
-		printk(KERN_ERR "No pci node found\n");
-
-	interrupt = get_property(node, "interrupt-map", &len);
-	slot = find_slot_by_devfn(interrupt, dev->devfn);
-	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
-	if (pin == 0 || pin > 4)
-		pin = 1;
-	pin--;
-	dev->irq  = interrupt[slot*4*7 + pin*7 + 5];
-	DBG("TSI_PCI: dev->irq = 0x%x\n", dev->irq);
-}
-/* temporary pci irq map fixup*/
-
-void __init mpc7448_hpc2_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-	for_each_pci_dev(dev) {
-		mpc7448_hpc2_fixup_irq(dev);
-		pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
-	}
-}
-
 static void __init mpc7448_hpc2_setup_arch(void)
 {
 	struct device_node *cpu;
@@ -192,9 +133,12 @@ static void __init mpc7448_hpc2_init_IRQ(void)
 {
 	struct mpic *mpic;
 	phys_addr_t mpic_paddr = 0;
+	struct device_node *tsi_pic;
+#ifdef CONFIG_PCI
 	unsigned int cascade_pci_irq;
 	struct device_node *tsi_pci;
-	struct device_node *tsi_pic;
+	struct device_node *cascade_node = NULL;
+#endif
 
 	tsi_pic = of_find_node_by_type(NULL, "open-pic");
 	if (tsi_pic) {
@@ -208,31 +152,41 @@ static void __init mpc7448_hpc2_init_IRQ(void)
 		return;
 	}
 
-	DBG("%s: tsi108pic phys_addr = 0x%x\n", __FUNCTION__,
+	DBG("%s: tsi108 pic phys_addr = 0x%x\n", __FUNCTION__,
 	    (u32) mpic_paddr);
 
 	mpic = mpic_alloc(tsi_pic, mpic_paddr,
 			MPIC_PRIMARY | MPIC_BIG_ENDIAN | MPIC_WANTS_RESET |
 			MPIC_SPV_EOI | MPIC_NO_PTHROU_DIS | MPIC_REGSET_TSI108,
-			0, /* num_sources used */
-			0, /* num_sources used */
+			24,
+			NR_IRQS-4, /* num_sources used */
 			"Tsi108_PIC");
 
-	BUG_ON(mpic == NULL); /* XXXX */
+	BUG_ON(mpic == NULL);
+
+	mpic_assign_isu(mpic, 0, mpic_paddr + 0x100);
+
 	mpic_init(mpic);
 
+#ifdef CONFIG_PCI
 	tsi_pci = of_find_node_by_type(NULL, "pci");
-	if (tsi_pci == 0) {
+	if (tsi_pci == NULL) {
 		printk("%s: No tsi108 pci node found !\n", __FUNCTION__);
 		return;
 	}
+	cascade_node = of_find_node_by_type(NULL, "pic-router");
+	if (cascade_node == NULL) {
+		printk("%s: No tsi108 pci cascade node found !\n", __FUNCTION__);
+		return;
+	}
 
 	cascade_pci_irq = irq_of_parse_and_map(tsi_pci, 0);
+	DBG("%s: tsi108 cascade_pci_irq = 0x%x\n", __FUNCTION__,
+	    (u32) cascade_pci_irq);
+	tsi108_pci_int_init(cascade_node);
 	set_irq_data(cascade_pci_irq, mpic);
 	set_irq_chained_handler(cascade_pci_irq, tsi108_irq_cascade);
-
-	tsi108_pci_int_init();
-
+#endif
 	/* Configure MPIC outputs to CPU0 */
 	tsi108_write_reg(TSI108_MPIC_OFFSET + 0x30c, 0);
 	of_node_put(tsi_pic);
@@ -290,7 +244,6 @@ static int mpc7448_machine_check_exception(struct pt_regs *regs)
 		return 1;
 	}
 	return 0;
-
 }
 
 define_machine(mpc7448_hpc2){
@@ -300,7 +253,6 @@ define_machine(mpc7448_hpc2){
 	.init_IRQ 		= mpc7448_hpc2_init_IRQ,
 	.show_cpuinfo 		= mpc7448_hpc2_show_cpuinfo,
 	.get_irq 		= mpic_get_irq,
-	.pcibios_fixup 		= mpc7448_hpc2_pcibios_fixup,
 	.restart 		= mpc7448_hpc2_restart,
 	.calibrate_decr 	= generic_calibrate_decr,
 	.machine_check_exception= mpc7448_machine_check_exception,
diff --git a/arch/powerpc/platforms/iseries/Makefile b/arch/powerpc/platforms/iseries/Makefile
index dee4eb4d8bec..13ac3015d91c 100644
--- a/arch/powerpc/platforms/iseries/Makefile
+++ b/arch/powerpc/platforms/iseries/Makefile
@@ -1,5 +1,7 @@
 EXTRA_CFLAGS	+= -mno-minimal-toc
 
+extra-y += dt.o
+
 obj-y += hvlog.o hvlpconfig.o lpardata.o setup.o dt_mod.o mf.o lpevents.o \
 	hvcall.o proc.o htab.o iommu.o misc.o irq.o
 obj-$(CONFIG_PCI) += pci.o vpdinfo.o
@@ -7,5 +9,9 @@ obj-$(CONFIG_SMP) += smp.o
 obj-$(CONFIG_VIOPATH) += viopath.o
 obj-$(CONFIG_MODULES) += ksyms.o
 
+quiet_cmd_dt_strings = DT_STR  $@
+      cmd_dt_strings = $(OBJCOPY) --rename-section .rodata.str1.8=.dt_strings \
+				$< $@
+
 $(obj)/dt_mod.o:	$(obj)/dt.o
-	@$(OBJCOPY) --rename-section .rodata.str1.8=.dt_strings $(obj)/dt.o $(obj)/dt_mod.o
+	$(call if_changed,dt_strings)
diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c
index e305deee7f44..9e8a334a518a 100644
--- a/arch/powerpc/platforms/iseries/dt.c
+++ b/arch/powerpc/platforms/iseries/dt.c
@@ -41,6 +41,7 @@
 #include "call_pci.h"
 #include "pci.h"
 #include "it_exp_vpd_panel.h"
+#include "naca.h"
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -205,13 +206,11 @@ static void __init dt_prop_u32(struct iseries_flat_dt *dt, const char *name,
 	dt_prop(dt, name, &data, sizeof(u32));
 }
 
-#ifdef notyet
 static void __init dt_prop_u64(struct iseries_flat_dt *dt, const char *name,
 		u64 data)
 {
 	dt_prop(dt, name, &data, sizeof(u64));
 }
-#endif
 
 static void __init dt_prop_u64_list(struct iseries_flat_dt *dt,
 		const char *name, u64 *data, int n)
@@ -306,6 +305,17 @@ static void __init dt_model(struct iseries_flat_dt *dt)
 	dt_prop_u32(dt, "ibm,partition-no", HvLpConfig_getLpIndex());
 }
 
+static void __init dt_initrd(struct iseries_flat_dt *dt)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (naca.xRamDisk) {
+		dt_prop_u64(dt, "linux,initrd-start", (u64)naca.xRamDisk);
+		dt_prop_u64(dt, "linux,initrd-end",
+			(u64)naca.xRamDisk + naca.xRamDiskSize * HW_PAGE_SIZE);
+	}
+#endif
+}
+
 static void __init dt_do_vdevice(struct iseries_flat_dt *dt,
 		const char *name, u32 reg, int unit,
 		const char *type, const char *compat, int end)
@@ -641,6 +651,7 @@ void * __init build_flat_dt(unsigned long phys_mem_size)
 	/* /chosen */
 	dt_start_node(iseries_dt, "chosen");
 	dt_prop_str(iseries_dt, "bootargs", cmd_line);
+	dt_initrd(iseries_dt);
 	dt_end_node(iseries_dt);
 
 	dt_cpus(iseries_dt);
diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c
index 218817d13c5c..d7a756d5135c 100644
--- a/arch/powerpc/platforms/iseries/iommu.c
+++ b/arch/powerpc/platforms/iseries/iommu.c
@@ -27,6 +27,7 @@
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
+#include <linux/pci.h>
 
 #include <asm/iommu.h>
 #include <asm/tce.h>
@@ -114,12 +115,10 @@ void iommu_table_getparms_iSeries(unsigned long busno,
 {
 	struct iommu_table_cb *parms;
 
-	parms = kmalloc(sizeof(*parms), GFP_KERNEL);
+	parms = kzalloc(sizeof(*parms), GFP_KERNEL);
 	if (parms == NULL)
 		panic("PCI_DMA: TCE Table Allocation failed.");
 
-	memset(parms, 0, sizeof(*parms));
-
 	parms->itc_busno = busno;
 	parms->itc_slotno = slotno;
 	parms->itc_virtbus = virtbus;
@@ -168,7 +167,7 @@ static struct iommu_table *iommu_table_find(struct iommu_table * tbl)
 }
 
 
-void iommu_devnode_init_iSeries(struct device_node *dn)
+void iommu_devnode_init_iSeries(struct pci_dev *pdev, struct device_node *dn)
 {
 	struct iommu_table *tbl;
 	struct pci_dn *pdn = PCI_DN(dn);
@@ -186,19 +185,14 @@ void iommu_devnode_init_iSeries(struct device_node *dn)
 		pdn->iommu_table = iommu_init_table(tbl, -1);
 	else
 		kfree(tbl);
+	pdev->dev.archdata.dma_data = pdn->iommu_table;
 }
 #endif
 
-static void iommu_dev_setup_iSeries(struct pci_dev *dev) { }
-static void iommu_bus_setup_iSeries(struct pci_bus *bus) { }
-
 void iommu_init_early_iSeries(void)
 {
 	ppc_md.tce_build = tce_build_iSeries;
 	ppc_md.tce_free  = tce_free_iSeries;
 
-	ppc_md.iommu_dev_setup = iommu_dev_setup_iSeries;
-	ppc_md.iommu_bus_setup = iommu_bus_setup_iSeries;
-
-	pci_iommu_init();
+	pci_dma_ops = &dma_iommu_ops;
 }
diff --git a/arch/powerpc/platforms/iseries/ksyms.c b/arch/powerpc/platforms/iseries/ksyms.c
index a2200842f4e5..2430848b98e7 100644
--- a/arch/powerpc/platforms/iseries/ksyms.c
+++ b/arch/powerpc/platforms/iseries/ksyms.c
@@ -19,9 +19,3 @@ EXPORT_SYMBOL(HvCall4);
 EXPORT_SYMBOL(HvCall5);
 EXPORT_SYMBOL(HvCall6);
 EXPORT_SYMBOL(HvCall7);
-
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(local_get_flags);
-EXPORT_SYMBOL(local_irq_disable);
-EXPORT_SYMBOL(local_irq_restore);
-#endif
diff --git a/arch/powerpc/platforms/iseries/misc.S b/arch/powerpc/platforms/iseries/misc.S
index 7641fc7e550a..2c6ff0fdac98 100644
--- a/arch/powerpc/platforms/iseries/misc.S
+++ b/arch/powerpc/platforms/iseries/misc.S
@@ -19,39 +19,8 @@
 
 	.text
 
-/* unsigned long local_save_flags(void) */
-_GLOBAL(local_get_flags)
-	lbz	r3,PACAPROCENABLED(r13)
-	blr
-
-/* unsigned long local_irq_disable(void) */
-_GLOBAL(local_irq_disable)
-	lbz	r3,PACAPROCENABLED(r13)
-	li	r4,0
-	stb	r4,PACAPROCENABLED(r13)
-	blr			/* Done */
-
-/* void local_irq_restore(unsigned long flags) */
-_GLOBAL(local_irq_restore)
-	lbz	r5,PACAPROCENABLED(r13)
-	 /* Check if things are setup the way we want _already_. */
-	cmpw	0,r3,r5
-	beqlr
-	/* are we enabling interrupts? */
-	cmpdi	0,r3,0
-	stb	r3,PACAPROCENABLED(r13)
-	beqlr
-	/* Check pending interrupts */
-	/*   A decrementer, IPI or PMC interrupt may have occurred
-	 *   while we were in the hypervisor (which enables) */
-	ld	r4,PACALPPACAPTR(r13)
-	ld	r4,LPPACAANYINT(r4)
-	cmpdi	r4,0
-	beqlr
-
-	/*
-	 * Handle pending interrupts in interrupt context
-	 */
+/* Handle pending interrupts in interrupt context */
+_GLOBAL(iseries_handle_interrupts)
 	li	r0,0x5555
 	sc
 	blr
diff --git a/arch/powerpc/platforms/iseries/pci.c b/arch/powerpc/platforms/iseries/pci.c
index 4aa165e010d9..4a06d9c34986 100644
--- a/arch/powerpc/platforms/iseries/pci.c
+++ b/arch/powerpc/platforms/iseries/pci.c
@@ -156,53 +156,6 @@ static void pci_Log_Error(char *Error_Text, int Bus, int SubBus,
 }
 
 /*
- * iSeries_pcibios_init
- *
- * Description:
- *   This function checks for all possible system PCI host bridges that connect
- *   PCI buses.  The system hypervisor is queried as to the guest partition
- *   ownership status.  A pci_controller is built for any bus which is partially
- *   owned or fully owned by this guest partition.
- */
-void iSeries_pcibios_init(void)
-{
-	struct pci_controller *phb;
-	struct device_node *root = of_find_node_by_path("/");
-	struct device_node *node = NULL;
-
-	if (root == NULL) {
-		printk(KERN_CRIT "iSeries_pcibios_init: can't find root "
-				"of device tree\n");
-		return;
-	}
-	while ((node = of_get_next_child(root, node)) != NULL) {
-		HvBusNumber bus;
-		const u32 *busp;
-
-		if ((node->type == NULL) || (strcmp(node->type, "pci") != 0))
-			continue;
-
-		busp = get_property(node, "bus-range", NULL);
-		if (busp == NULL)
-			continue;
-		bus = *busp;
-		printk("bus %d appears to exist\n", bus);
-		phb = pcibios_alloc_controller(node);
-		if (phb == NULL)
-			continue;
-
-		phb->pci_mem_offset = phb->local_number = bus;
-		phb->first_busno = bus;
-		phb->last_busno = bus;
-		phb->ops = &iSeries_pci_ops;
-	}
-
-	of_node_put(root);
-
-	pci_devs_phb_init();
-}
-
-/*
  * iSeries_pci_final_fixup(void)
  */
 void __init iSeries_pci_final_fixup(void)
@@ -253,7 +206,7 @@ void __init iSeries_pci_final_fixup(void)
 			PCI_DN(node)->pcidev = pdev;
 			allocate_device_bars(pdev);
 			iSeries_Device_Information(pdev, DeviceCount);
-			iommu_devnode_init_iSeries(node);
+			iommu_devnode_init_iSeries(pdev, node);
 		} else
 			printk("PCI: Device Tree not found for 0x%016lX\n",
 					(unsigned long)pdev);
@@ -438,11 +391,7 @@ static inline struct device_node *xlate_iomm_address(
 /*
  * Read MM I/O Instructions for the iSeries
  * On MM I/O error, all ones are returned and iSeries_pci_IoError is cal
- * else, data is returned in big Endian format.
- *
- * iSeries_Read_Byte = Read Byte  ( 8 bit)
- * iSeries_Read_Word = Read Word  (16 bit)
- * iSeries_Read_Long = Read Long  (32 bit)
+ * else, data is returned in Big Endian format.
  */
 static u8 iSeries_Read_Byte(const volatile void __iomem *IoAddress)
 {
@@ -462,14 +411,15 @@ static u8 iSeries_Read_Byte(const volatile void __iomem *IoAddress)
 			num_printed = 0;
 		}
 		if (num_printed++ < 10)
-			printk(KERN_ERR "iSeries_Read_Byte: invalid access at IO address %p\n", IoAddress);
+			printk(KERN_ERR "iSeries_Read_Byte: invalid access at IO address %p\n",
+			       IoAddress);
 		return 0xff;
 	}
 	do {
 		HvCall3Ret16(HvCallPciBarLoad8, &ret, dsa, BarOffset, 0);
 	} while (CheckReturnCode("RDB", DevNode, &retry, ret.rc) != 0);
 
-	return (u8)ret.value;
+	return ret.value;
 }
 
 static u16 iSeries_Read_Word(const volatile void __iomem *IoAddress)
@@ -490,7 +440,8 @@ static u16 iSeries_Read_Word(const volatile void __iomem *IoAddress)
 			num_printed = 0;
 		}
 		if (num_printed++ < 10)
-			printk(KERN_ERR "iSeries_Read_Word: invalid access at IO address %p\n", IoAddress);
+			printk(KERN_ERR "iSeries_Read_Word: invalid access at IO address %p\n",
+			       IoAddress);
 		return 0xffff;
 	}
 	do {
@@ -498,7 +449,7 @@ static u16 iSeries_Read_Word(const volatile void __iomem *IoAddress)
 				BarOffset, 0);
 	} while (CheckReturnCode("RDW", DevNode, &retry, ret.rc) != 0);
 
-	return swab16((u16)ret.value);
+	return ret.value;
 }
 
 static u32 iSeries_Read_Long(const volatile void __iomem *IoAddress)
@@ -519,7 +470,8 @@ static u32 iSeries_Read_Long(const volatile void __iomem *IoAddress)
 			num_printed = 0;
 		}
 		if (num_printed++ < 10)
-			printk(KERN_ERR "iSeries_Read_Long: invalid access at IO address %p\n", IoAddress);
+			printk(KERN_ERR "iSeries_Read_Long: invalid access at IO address %p\n",
+			       IoAddress);
 		return 0xffffffff;
 	}
 	do {
@@ -527,15 +479,12 @@ static u32 iSeries_Read_Long(const volatile void __iomem *IoAddress)
 				BarOffset, 0);
 	} while (CheckReturnCode("RDL", DevNode, &retry, ret.rc) != 0);
 
-	return swab32((u32)ret.value);
+	return ret.value;
 }
 
 /*
  * Write MM I/O Instructions for the iSeries
  *
- * iSeries_Write_Byte = Write Byte (8 bit)
- * iSeries_Write_Word = Write Word(16 bit)
- * iSeries_Write_Long = Write Long(32 bit)
  */
 static void iSeries_Write_Byte(u8 data, volatile void __iomem *IoAddress)
 {
@@ -581,11 +530,12 @@ static void iSeries_Write_Word(u16 data, volatile void __iomem *IoAddress)
 			num_printed = 0;
 		}
 		if (num_printed++ < 10)
-			printk(KERN_ERR "iSeries_Write_Word: invalid access at IO address %p\n", IoAddress);
+			printk(KERN_ERR "iSeries_Write_Word: invalid access at IO address %p\n",
+			       IoAddress);
 		return;
 	}
 	do {
-		rc = HvCall4(HvCallPciBarStore16, dsa, BarOffset, swab16(data), 0);
+		rc = HvCall4(HvCallPciBarStore16, dsa, BarOffset, data, 0);
 	} while (CheckReturnCode("WWW", DevNode, &retry, rc) != 0);
 }
 
@@ -607,231 +557,221 @@ static void iSeries_Write_Long(u32 data, volatile void __iomem *IoAddress)
 			num_printed = 0;
 		}
 		if (num_printed++ < 10)
-			printk(KERN_ERR "iSeries_Write_Long: invalid access at IO address %p\n", IoAddress);
+			printk(KERN_ERR "iSeries_Write_Long: invalid access at IO address %p\n",
+			       IoAddress);
 		return;
 	}
 	do {
-		rc = HvCall4(HvCallPciBarStore32, dsa, BarOffset, swab32(data), 0);
+		rc = HvCall4(HvCallPciBarStore32, dsa, BarOffset, data, 0);
 	} while (CheckReturnCode("WWL", DevNode, &retry, rc) != 0);
 }
 
-extern unsigned char __raw_readb(const volatile void __iomem *addr)
+static u8 iseries_readb(const volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	return *(volatile unsigned char __force *)addr;
+	return iSeries_Read_Byte(addr);
 }
-EXPORT_SYMBOL(__raw_readb);
 
-extern unsigned short __raw_readw(const volatile void __iomem *addr)
+static u16 iseries_readw(const volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	return *(volatile unsigned short __force *)addr;
+	return le16_to_cpu(iSeries_Read_Word(addr));
 }
-EXPORT_SYMBOL(__raw_readw);
 
-extern unsigned int __raw_readl(const volatile void __iomem *addr)
+static u32 iseries_readl(const volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	return *(volatile unsigned int __force *)addr;
+	return le32_to_cpu(iSeries_Read_Long(addr));
 }
-EXPORT_SYMBOL(__raw_readl);
 
-extern unsigned long __raw_readq(const volatile void __iomem *addr)
+static u16 iseries_readw_be(const volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	return *(volatile unsigned long __force *)addr;
+	return iSeries_Read_Word(addr);
 }
-EXPORT_SYMBOL(__raw_readq);
 
-extern void __raw_writeb(unsigned char v, volatile void __iomem *addr)
+static u32 iseries_readl_be(const volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	*(volatile unsigned char __force *)addr = v;
+	return iSeries_Read_Long(addr);
 }
-EXPORT_SYMBOL(__raw_writeb);
 
-extern void __raw_writew(unsigned short v, volatile void __iomem *addr)
+static void iseries_writeb(u8 data, volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	*(volatile unsigned short __force *)addr = v;
+	iSeries_Write_Byte(data, addr);
 }
-EXPORT_SYMBOL(__raw_writew);
 
-extern void __raw_writel(unsigned int v, volatile void __iomem *addr)
+static void iseries_writew(u16 data, volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	*(volatile unsigned int __force *)addr = v;
+	iSeries_Write_Word(cpu_to_le16(data), addr);
 }
-EXPORT_SYMBOL(__raw_writel);
 
-extern void __raw_writeq(unsigned long v, volatile void __iomem *addr)
+static void iseries_writel(u32 data, volatile void __iomem *addr)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	*(volatile unsigned long __force *)addr = v;
+	iSeries_Write_Long(cpu_to_le32(data), addr);
 }
-EXPORT_SYMBOL(__raw_writeq);
 
-int in_8(const volatile unsigned char __iomem *addr)
+static void iseries_writew_be(u16 data, volatile void __iomem *addr)
 {
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		return iSeries_Read_Byte(addr);
-	return __in_8(addr);
+	iSeries_Write_Word(data, addr);
 }
-EXPORT_SYMBOL(in_8);
 
-void out_8(volatile unsigned char __iomem *addr, int val)
+static void iseries_writel_be(u32 data, volatile void __iomem *addr)
 {
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		iSeries_Write_Byte(val, addr);
-	else
-		__out_8(addr, val);
+	iSeries_Write_Long(data, addr);
 }
-EXPORT_SYMBOL(out_8);
 
-int in_le16(const volatile unsigned short __iomem *addr)
+static void iseries_readsb(const volatile void __iomem *addr, void *buf,
+			   unsigned long count)
 {
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		return iSeries_Read_Word(addr);
-	return __in_le16(addr);
+	u8 *dst = buf;
+	while(count-- > 0)
+		*(dst++) = iSeries_Read_Byte(addr);
 }
-EXPORT_SYMBOL(in_le16);
 
-int in_be16(const volatile unsigned short __iomem *addr)
+static void iseries_readsw(const volatile void __iomem *addr, void *buf,
+			   unsigned long count)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	return __in_be16(addr);
+	u16 *dst = buf;
+	while(count-- > 0)
+		*(dst++) = iSeries_Read_Word(addr);
 }
-EXPORT_SYMBOL(in_be16);
 
-void out_le16(volatile unsigned short __iomem *addr, int val)
+static void iseries_readsl(const volatile void __iomem *addr, void *buf,
+			   unsigned long count)
 {
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		iSeries_Write_Word(val, addr);
-	else
-		__out_le16(addr, val);
+	u32 *dst = buf;
+	while(count-- > 0)
+		*(dst++) = iSeries_Read_Long(addr);
 }
-EXPORT_SYMBOL(out_le16);
 
-void out_be16(volatile unsigned short __iomem *addr, int val)
+static void iseries_writesb(volatile void __iomem *addr, const void *buf,
+			    unsigned long count)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	__out_be16(addr, val);
+	const u8 *src = buf;
+	while(count-- > 0)
+		iSeries_Write_Byte(*(src++), addr);
 }
-EXPORT_SYMBOL(out_be16);
 
-unsigned in_le32(const volatile unsigned __iomem *addr)
+static void iseries_writesw(volatile void __iomem *addr, const void *buf,
+			    unsigned long count)
 {
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		return iSeries_Read_Long(addr);
-	return __in_le32(addr);
+	const u16 *src = buf;
+	while(count-- > 0)
+		iSeries_Write_Word(*(src++), addr);
 }
-EXPORT_SYMBOL(in_le32);
 
-unsigned in_be32(const volatile unsigned __iomem *addr)
+static void iseries_writesl(volatile void __iomem *addr, const void *buf,
+			    unsigned long count)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	return __in_be32(addr);
+	const u32 *src = buf;
+	while(count-- > 0)
+		iSeries_Write_Long(*(src++), addr);
 }
-EXPORT_SYMBOL(in_be32);
 
-void out_le32(volatile unsigned __iomem *addr, int val)
+static void iseries_memset_io(volatile void __iomem *addr, int c,
+			      unsigned long n)
 {
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		iSeries_Write_Long(val, addr);
-	else
-		__out_le32(addr, val);
-}
-EXPORT_SYMBOL(out_le32);
+	volatile char __iomem *d = addr;
 
-void out_be32(volatile unsigned __iomem *addr, int val)
-{
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
-
-	__out_be32(addr, val);
+	while (n-- > 0)
+		iSeries_Write_Byte(c, d++);
 }
-EXPORT_SYMBOL(out_be32);
 
-unsigned long in_le64(const volatile unsigned long __iomem *addr)
+static void iseries_memcpy_fromio(void *dest, const volatile void __iomem *src,
+				  unsigned long n)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
+	char *d = dest;
+	const volatile char __iomem *s = src;
 
-	return __in_le64(addr);
+	while (n-- > 0)
+		*d++ = iSeries_Read_Byte(s++);
 }
-EXPORT_SYMBOL(in_le64);
 
-unsigned long in_be64(const volatile unsigned long __iomem *addr)
+static void iseries_memcpy_toio(volatile void __iomem *dest, const void *src,
+				unsigned long n)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
+	const char *s = src;
+	volatile char __iomem *d = dest;
 
-	return __in_be64(addr);
+	while (n-- > 0)
+		iSeries_Write_Byte(*s++, d++);
 }
-EXPORT_SYMBOL(in_be64);
-
-void out_le64(volatile unsigned long __iomem *addr, unsigned long val)
-{
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
 
-	__out_le64(addr, val);
-}
-EXPORT_SYMBOL(out_le64);
+/* We only set MMIO ops. The default PIO ops will be default
+ * to the MMIO ops + pci_io_base which is 0 on iSeries as
+ * expected so both should work.
+ *
+ * Note that we don't implement the readq/writeq versions as
+ * I don't know of an HV call for doing so. Thus, the default
+ * operation will be used instead, which will fault a the value
+ * return by iSeries for MMIO addresses always hits a non mapped
+ * area. This is as good as the BUG() we used to have there.
+ */
+static struct ppc_pci_io __initdata iseries_pci_io = {
+	.readb = iseries_readb,
+	.readw = iseries_readw,
+	.readl = iseries_readl,
+	.readw_be = iseries_readw_be,
+	.readl_be = iseries_readl_be,
+	.writeb = iseries_writeb,
+	.writew = iseries_writew,
+	.writel = iseries_writel,
+	.writew_be = iseries_writew_be,
+	.writel_be = iseries_writel_be,
+	.readsb = iseries_readsb,
+	.readsw = iseries_readsw,
+	.readsl = iseries_readsl,
+	.writesb = iseries_writesb,
+	.writesw = iseries_writesw,
+	.writesl = iseries_writesl,
+	.memset_io = iseries_memset_io,
+	.memcpy_fromio = iseries_memcpy_fromio,
+	.memcpy_toio = iseries_memcpy_toio,
+};
 
-void out_be64(volatile unsigned long __iomem *addr, unsigned long val)
+/*
+ * iSeries_pcibios_init
+ *
+ * Description:
+ *   This function checks for all possible system PCI host bridges that connect
+ *   PCI buses.  The system hypervisor is queried as to the guest partition
+ *   ownership status.  A pci_controller is built for any bus which is partially
+ *   owned or fully owned by this guest partition.
+ */
+void __init iSeries_pcibios_init(void)
 {
-	BUG_ON(firmware_has_feature(FW_FEATURE_ISERIES));
+	struct pci_controller *phb;
+	struct device_node *root = of_find_node_by_path("/");
+	struct device_node *node = NULL;
 
-	__out_be64(addr, val);
-}
-EXPORT_SYMBOL(out_be64);
+	/* Install IO hooks */
+	ppc_pci_io = iseries_pci_io;
 
-void memset_io(volatile void __iomem *addr, int c, unsigned long n)
-{
-	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-		volatile char __iomem *d = addr;
+	if (root == NULL) {
+		printk(KERN_CRIT "iSeries_pcibios_init: can't find root "
+				"of device tree\n");
+		return;
+	}
+	while ((node = of_get_next_child(root, node)) != NULL) {
+		HvBusNumber bus;
+		const u32 *busp;
 
-		while (n-- > 0) {
-			iSeries_Write_Byte(c, d++);
-		}
-	} else
-		eeh_memset_io(addr, c, n);
-}
-EXPORT_SYMBOL(memset_io);
+		if ((node->type == NULL) || (strcmp(node->type, "pci") != 0))
+			continue;
 
-void memcpy_fromio(void *dest, const volatile void __iomem *src,
-                                 unsigned long n)
-{
-	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-		char *d = dest;
-		const volatile char __iomem *s = src;
+		busp = get_property(node, "bus-range", NULL);
+		if (busp == NULL)
+			continue;
+		bus = *busp;
+		printk("bus %d appears to exist\n", bus);
+		phb = pcibios_alloc_controller(node);
+		if (phb == NULL)
+			continue;
 
-		while (n-- > 0) {
-			*d++ = iSeries_Read_Byte(s++);
-		}
-	} else
-		eeh_memcpy_fromio(dest, src, n);
-}
-EXPORT_SYMBOL(memcpy_fromio);
+		phb->pci_mem_offset = phb->local_number = bus;
+		phb->first_busno = bus;
+		phb->last_busno = bus;
+		phb->ops = &iSeries_pci_ops;
+	}
 
-void memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
-{
-	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-		const char *s = src;
-		volatile char __iomem *d = dest;
+	of_node_put(root);
 
-		while (n-- > 0) {
-			iSeries_Write_Byte(*s++, d++);
-		}
-	} else
-		eeh_memcpy_toio(dest, src, n);
+	pci_devs_phb_init();
 }
-EXPORT_SYMBOL(memcpy_toio);
+
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index 6f73469fd3b0..bdf2afbb60c1 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -21,7 +21,6 @@
 #include <linux/smp.h>
 #include <linux/param.h>
 #include <linux/string.h>
-#include <linux/initrd.h>
 #include <linux/seq_file.h>
 #include <linux/kdev_t.h>
 #include <linux/major.h>
@@ -80,8 +79,6 @@ extern void iSeries_pci_final_fixup(void);
 static void iSeries_pci_final_fixup(void) { }
 #endif
 
-extern int rd_size;		/* Defined in drivers/block/rd.c */
-
 extern unsigned long iSeries_recal_tb;
 extern unsigned long iSeries_recal_titan;
 
@@ -295,24 +292,6 @@ static void __init iSeries_init_early(void)
 {
 	DBG(" -> iSeries_init_early()\n");
 
-#if defined(CONFIG_BLK_DEV_INITRD)
-	/*
-	 * If the init RAM disk has been configured and there is
-	 * a non-zero starting address for it, set it up
-	 */
-	if (naca.xRamDisk) {
-		initrd_start = (unsigned long)__va(naca.xRamDisk);
-		initrd_end = initrd_start + naca.xRamDiskSize * HW_PAGE_SIZE;
-		initrd_below_start_ok = 1;	// ramdisk in kernel space
-		ROOT_DEV = Root_RAM0;
-		if (((rd_size * 1024) / HW_PAGE_SIZE) < naca.xRamDiskSize)
-			rd_size = (naca.xRamDiskSize * HW_PAGE_SIZE) / 1024;
-	} else
-#endif /* CONFIG_BLK_DEV_INITRD */
-	{
-	    /* ROOT_DEV = MKDEV(VIODASD_MAJOR, 1); */
-	}
-
 	iSeries_recal_tb = get_tb();
 	iSeries_recal_titan = HvCallXm_loadTod();
 
@@ -331,17 +310,6 @@ static void __init iSeries_init_early(void)
 
 	mf_init();
 
-	/* If we were passed an initrd, set the ROOT_DEV properly if the values
-	 * look sensible. If not, clear initrd reference.
-	 */
-#ifdef CONFIG_BLK_DEV_INITRD
-	if (initrd_start >= KERNELBASE && initrd_end >= KERNELBASE &&
-	    initrd_end > initrd_start)
-		ROOT_DEV = Root_RAM0;
-	else
-		initrd_start = initrd_end = 0;
-#endif /* CONFIG_BLK_DEV_INITRD */
-
 	DBG(" <- iSeries_init_early()\n");
 }
 
@@ -649,6 +617,16 @@ static void iseries_dedicated_idle(void)
 void __init iSeries_init_IRQ(void) { }
 #endif
 
+static void __iomem *iseries_ioremap(phys_addr_t address, unsigned long size,
+				     unsigned long flags)
+{
+	return (void __iomem *)address;
+}
+
+static void iseries_iounmap(volatile void __iomem *token)
+{
+}
+
 /*
  * iSeries has no legacy IO, anything calling this function has to
  * fail or bad things will happen
@@ -665,6 +643,8 @@ static int __init iseries_probe(void)
 		return 0;
 
 	hpte_init_iSeries();
+	/* iSeries does not support 16M pages */
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_16M_PAGE;
 
 	return 1;
 }
@@ -687,6 +667,8 @@ define_machine(iseries) {
 	.progress	= iSeries_progress,
 	.probe		= iseries_probe,
 	.check_legacy_ioport	= iseries_check_legacy_ioport,
+	.ioremap	= iseries_ioremap,
+	.iounmap	= iseries_iounmap,
 	/* XXX Implement enable_pmcs for iSeries */
 };
 
@@ -697,7 +679,7 @@ void * __init iSeries_early_setup(void)
 	/* Identify CPU type. This is done again by the common code later
 	 * on but calling this function multiple times is fine.
 	 */
-	identify_cpu(0);
+	identify_cpu(0, mfspr(SPRN_PVR));
 
 	powerpc_firmware_features |= FW_FEATURE_ISERIES;
 	powerpc_firmware_features |= FW_FEATURE_LPAR;
diff --git a/arch/powerpc/platforms/iseries/viopath.c b/arch/powerpc/platforms/iseries/viopath.c
index 04e07e5da0c1..84e7ee2c086f 100644
--- a/arch/powerpc/platforms/iseries/viopath.c
+++ b/arch/powerpc/platforms/iseries/viopath.c
@@ -119,10 +119,9 @@ static int proc_viopath_show(struct seq_file *m, void *v)
 	struct device_node *node;
 	const char *sysid;
 
-	buf = kmalloc(HW_PAGE_SIZE, GFP_KERNEL);
+	buf = kzalloc(HW_PAGE_SIZE, GFP_KERNEL);
 	if (!buf)
 		return 0;
-	memset(buf, 0, HW_PAGE_SIZE);
 
 	handle = dma_map_single(iSeries_vio_dev, buf, HW_PAGE_SIZE,
 				DMA_FROM_DEVICE);
diff --git a/arch/powerpc/platforms/maple/maple.h b/arch/powerpc/platforms/maple/maple.h
index 0657c579b840..c6911ddc479f 100644
--- a/arch/powerpc/platforms/maple/maple.h
+++ b/arch/powerpc/platforms/maple/maple.h
@@ -8,5 +8,5 @@ extern void maple_get_rtc_time(struct rtc_time *tm);
 extern unsigned long maple_get_boot_time(void);
 extern void maple_calibrate_decr(void);
 extern void maple_pci_init(void);
-extern void maple_pcibios_fixup(void);
+extern void maple_pci_irq_fixup(struct pci_dev *dev);
 extern int maple_pci_get_legacy_ide_irq(struct pci_dev *dev, int channel);
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
index 63b4d1bff359..3a32deda765d 100644
--- a/arch/powerpc/platforms/maple/pci.c
+++ b/arch/powerpc/platforms/maple/pci.c
@@ -502,38 +502,29 @@ static int __init add_bridge(struct device_node *dev)
 }
 
 
-void __init maple_pcibios_fixup(void)
+void __devinit maple_pci_irq_fixup(struct pci_dev *dev)
 {
-	struct pci_dev *dev = NULL;
-
-	DBG(" -> maple_pcibios_fixup\n");
-
-	for_each_pci_dev(dev) {
-		/* Fixup IRQ for PCIe host */
-		if (u4_pcie != NULL && dev->bus->number == 0 &&
-		    pci_bus_to_host(dev->bus) == u4_pcie) {
-			printk(KERN_DEBUG "Fixup U4 PCIe IRQ\n");
-			dev->irq = irq_create_mapping(NULL, 1);
-			if (dev->irq != NO_IRQ)
-				set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW);
-			continue;
-		}
-
-		/* Hide AMD8111 IDE interrupt when in legacy mode so
-		 * the driver calls pci_get_legacy_ide_irq()
-		 */
-		if (dev->vendor == PCI_VENDOR_ID_AMD &&
-		    dev->device == PCI_DEVICE_ID_AMD_8111_IDE &&
-		    (dev->class & 5) != 5) {
-			dev->irq = NO_IRQ;
-			continue;
-		}
+	DBG(" -> maple_pci_irq_fixup\n");
+
+	/* Fixup IRQ for PCIe host */
+	if (u4_pcie != NULL && dev->bus->number == 0 &&
+	    pci_bus_to_host(dev->bus) == u4_pcie) {
+		printk(KERN_DEBUG "Fixup U4 PCIe IRQ\n");
+		dev->irq = irq_create_mapping(NULL, 1);
+		if (dev->irq != NO_IRQ)
+			set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW);
+	}
 
-		/* For all others, map the interrupt from the device-tree */
-		pci_read_irq_line(dev);
+	/* Hide AMD8111 IDE interrupt when in legacy mode so
+	 * the driver calls pci_get_legacy_ide_irq()
+	 */
+	if (dev->vendor == PCI_VENDOR_ID_AMD &&
+	    dev->device == PCI_DEVICE_ID_AMD_8111_IDE &&
+	    (dev->class & 5) != 5) {
+		dev->irq = NO_IRQ;
 	}
 
-	DBG(" <- maple_pcibios_fixup\n");
+	DBG(" <- maple_pci_irq_fixup\n");
 }
 
 static void __init maple_fixup_phb_resources(void)
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index fe6b9bff61b9..094989d50bab 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -312,7 +312,7 @@ define_machine(maple_md) {
 	.setup_arch		= maple_setup_arch,
 	.init_early		= maple_init_early,
 	.init_IRQ		= maple_init_IRQ,
-	.pcibios_fixup		= maple_pcibios_fixup,
+	.pci_irq_fixup		= maple_pci_irq_fixup,
 	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
 	.restart		= maple_restart,
 	.power_off		= maple_power_off,
diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h
index fd71d72736b2..51c2a2397ecf 100644
--- a/arch/powerpc/platforms/pasemi/pasemi.h
+++ b/arch/powerpc/platforms/pasemi/pasemi.h
@@ -3,6 +3,5 @@
 
 extern unsigned long pas_get_boot_time(void);
 extern void pas_pci_init(void);
-extern void pas_pcibios_fixup(void);
 
 #endif /* _PASEMI_PASEMI_H */
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
index 39020c1fa13d..faa618e04047 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -148,14 +148,6 @@ static int __init add_bridge(struct device_node *dev)
 }
 
 
-void __init pas_pcibios_fixup(void)
-{
-	struct pci_dev *dev = NULL;
-
-	for_each_pci_dev(dev)
-		pci_read_irq_line(dev);
-}
-
 static void __init pas_fixup_phb_resources(void)
 {
 	struct pci_controller *hose, *tmp;
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 106896c3b60a..89d6e295dbf7 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/console.h>
+#include <linux/pci.h>
 
 #include <asm/prom.h>
 #include <asm/system.h>
@@ -71,6 +72,9 @@ void __init pas_setup_arch(void)
 	/* Setup SMP callback */
 	smp_ops = &pas_smp_ops;
 #endif
+	/* no iommu yet */
+	pci_dma_ops = &dma_direct_ops;
+
 	/* Lookup PCI hosts */
 	pas_pci_init();
 
@@ -81,17 +85,6 @@ void __init pas_setup_arch(void)
 	printk(KERN_DEBUG "Using default idle loop\n");
 }
 
-static void iommu_dev_setup_null(struct pci_dev *dev) { }
-static void iommu_bus_setup_null(struct pci_bus *bus) { }
-
-static void __init pas_init_early(void)
-{
-	/* No iommu code yet */
-	ppc_md.iommu_dev_setup = iommu_dev_setup_null;
-	ppc_md.iommu_bus_setup = iommu_bus_setup_null;
-	pci_direct_iommu_init();
-}
-
 /* No legacy IO on our parts */
 static int pas_check_legacy_ioport(unsigned int baseport)
 {
@@ -173,10 +166,8 @@ define_machine(pas) {
 	.name			= "PA Semi PA6T-1682M",
 	.probe			= pas_probe,
 	.setup_arch		= pas_setup_arch,
-	.init_early		= pas_init_early,
 	.init_IRQ		= pas_init_IRQ,
 	.get_irq		= mpic_get_irq,
-	.pcibios_fixup		= pas_pcibios_fixup,
 	.restart		= pas_restart,
 	.power_off		= pas_power_off,
 	.halt			= pas_halt,
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index e49621be6640..c29a6a064d22 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -486,10 +486,6 @@ static long heathrow_sound_enable(struct device_node *node, long param,
 
 static u32 save_fcr[6];
 static u32 save_mbcr;
-static u32 save_gpio_levels[2];
-static u8 save_gpio_extint[KEYLARGO_GPIO_EXTINT_CNT];
-static u8 save_gpio_normal[KEYLARGO_GPIO_CNT];
-static u32 save_unin_clock_ctl;
 static struct dbdma_regs save_dbdma[13];
 static struct dbdma_regs save_alt_dbdma[13];
 
@@ -1548,6 +1544,10 @@ void g5_phy_disable_cpu1(void)
 
 
 #ifdef CONFIG_PM
+static u32 save_gpio_levels[2];
+static u8 save_gpio_extint[KEYLARGO_GPIO_EXTINT_CNT];
+static u8 save_gpio_normal[KEYLARGO_GPIO_CNT];
+static u32 save_unin_clock_ctl;
 
 static void keylargo_shutdown(struct macio_chip *macio, int sleep_mode)
 {
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 257dc9068468..f42475b27c15 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -984,30 +984,23 @@ static int __init add_bridge(struct device_node *dev)
 	return 0;
 }
 
-void __init pmac_pcibios_fixup(void)
+void __devinit pmac_pci_irq_fixup(struct pci_dev *dev)
 {
-	struct pci_dev* dev = NULL;
-
-	for_each_pci_dev(dev) {
-		/* Read interrupt from the device-tree */
-		pci_read_irq_line(dev);
-
 #ifdef CONFIG_PPC32
-		/* Fixup interrupt for the modem/ethernet combo controller.
-		 * on machines with a second ohare chip.
-		 * The number in the device tree (27) is bogus (correct for
-		 * the ethernet-only board but not the combo ethernet/modem
-		 * board). The real interrupt is 28 on the second controller
-		 * -> 28+32 = 60.
-		 */
-		if (has_second_ohare &&
-		    dev->vendor == PCI_VENDOR_ID_DEC &&
-		    dev->device == PCI_DEVICE_ID_DEC_TULIP_PLUS) {
-			dev->irq = irq_create_mapping(NULL, 60);
-			set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW);
-		}
-#endif /* CONFIG_PPC32 */
+	/* Fixup interrupt for the modem/ethernet combo controller.
+	 * on machines with a second ohare chip.
+	 * The number in the device tree (27) is bogus (correct for
+	 * the ethernet-only board but not the combo ethernet/modem
+	 * board). The real interrupt is 28 on the second controller
+	 * -> 28+32 = 60.
+	 */
+	if (has_second_ohare &&
+	    dev->vendor == PCI_VENDOR_ID_DEC &&
+	    dev->device == PCI_DEVICE_ID_DEC_TULIP_PLUS) {
+		dev->irq = irq_create_mapping(NULL, 60);
+		set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW);
 	}
+#endif /* CONFIG_PPC32 */
 }
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h
index 94e7b24b840b..6e090a7dea83 100644
--- a/arch/powerpc/platforms/powermac/pmac.h
+++ b/arch/powerpc/platforms/powermac/pmac.h
@@ -20,7 +20,7 @@ extern void pmac_get_rtc_time(struct rtc_time *);
 extern int pmac_set_rtc_time(struct rtc_time *);
 extern void pmac_read_rtc_time(void);
 extern void pmac_calibrate_decr(void);
-extern void pmac_pcibios_fixup(void);
+extern void pmac_pci_irq_fixup(struct pci_dev *);
 extern void pmac_pci_init(void);
 extern unsigned long pmac_ide_get_base(int index);
 extern void pmac_ide_init_hwif_ports(hw_regs_t *hw,
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 824a618396ab..d949e9df41ef 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -70,6 +70,7 @@
 #include <asm/pmac_feature.h>
 #include <asm/time.h>
 #include <asm/of_device.h>
+#include <asm/of_platform.h>
 #include <asm/mmu_context.h>
 #include <asm/iommu.h>
 #include <asm/smu.h>
@@ -361,7 +362,7 @@ char *bootdevice;
 void *boot_host;
 int boot_target;
 int boot_part;
-extern dev_t boot_dev;
+static dev_t boot_dev;
 
 #ifdef CONFIG_SCSI
 void __init note_scsi_host(struct device_node *node, void *host)
@@ -676,8 +677,6 @@ static int __init pmac_probe(void)
 
 #ifdef CONFIG_PPC32
 	/* isa_io_base gets set in pmac_pci_init */
-	isa_mem_base = PMAC_ISA_MEM_BASE;
-	pci_dram_offset = PMAC_PCI_DRAM_OFFSET;
 	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 1;
 	DMA_MODE_WRITE = 2;
@@ -727,7 +726,7 @@ define_machine(powermac) {
 	.show_cpuinfo		= pmac_show_cpuinfo,
 	.init_IRQ		= pmac_pic_init,
 	.get_irq		= NULL,	/* changed later */
-	.pcibios_fixup		= pmac_pcibios_fixup,
+	.pci_irq_fixup		= pmac_pci_irq_fixup,
 	.restart		= pmac_restart,
 	.power_off		= pmac_power_off,
 	.halt			= pmac_halt,
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
new file mode 100644
index 000000000000..451bfcd5502e
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -0,0 +1,43 @@
+menu "PS3 Platform Options"
+	depends on PPC_PS3
+
+config PS3_HTAB_SIZE
+	depends on PPC_PS3
+	int "PS3 Platform pagetable size"
+	range 18 20
+	default 20
+	help
+	  This option is only for experts who may have the desire to fine
+	  tune the pagetable size on their system.  The value here is
+	  expressed as the log2 of the page table size.  Valid values are
+	  18, 19, and 20, corresponding to 256KB, 512KB and 1MB respectively.
+
+	  If unsure, choose the default (20) with the confidence that your
+	  system will have optimal runtime performance.
+
+config PS3_DYNAMIC_DMA
+	depends on PPC_PS3 && EXPERIMENTAL
+	bool "PS3 Platform dynamic DMA page table management"
+	default n
+	help
+	  This option will enable kernel support to take advantage of the
+	  per device dynamic DMA page table management provided by the Cell
+	  processor's IO Controller.  This support incurs some runtime
+	  overhead and also slightly increases kernel memory usage.  The
+	  current implementation should be considered experimental.
+
+	  This support is mainly for Linux kernel development.  If unsure,
+	  say N.
+
+config PS3_USE_LPAR_ADDR
+	depends on PPC_PS3 && EXPERIMENTAL
+	bool "PS3 use lpar address space"
+	default y
+	help
+	  This option is solely for experimentation by experts.  Disables
+	  translation of lpar addresses.  SPE support currently won't work
+	  without this set to y.
+
+	  If you have any doubt, choose the default y.
+
+endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
new file mode 100644
index 000000000000..3757cfabc8ce
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -0,0 +1,4 @@
+obj-y += setup.o mm.o smp.o time.o hvcall.o htab.o repository.o
+obj-y += interrupt.o exports.o os-area.o
+
+obj-$(CONFIG_SPU_BASE) += spu.o
diff --git a/arch/powerpc/platforms/ps3/exports.c b/arch/powerpc/platforms/ps3/exports.c
new file mode 100644
index 000000000000..a7e8ffd24a65
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/exports.c
@@ -0,0 +1,27 @@
+/*
+ *  PS3 hvcall exports for modules.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/module.h>
+
+#define LV1_CALL(name, in, out, num)                          \
+  extern s64 _lv1_##name(LV1_##in##_IN_##out##_OUT_ARG_DECL); \
+  EXPORT_SYMBOL(_lv1_##name);
+
+#include <asm/lv1call.h>
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
new file mode 100644
index 000000000000..8fe1769655a3
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -0,0 +1,277 @@
+/*
+ *  PS3 pagetable management routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+
+#include <asm/machdep.h>
+#include <asm/lmb.h>
+#include <asm/udbg.h>
+#include <asm/ps3.h>
+#include <asm/lv1call.h>
+
+#include "platform.h"
+
+#if defined(DEBUG)
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...) do{if(0)printk(fmt);}while(0)
+#endif
+
+static hpte_t *htab;
+static unsigned long htab_addr;
+static unsigned char *bolttab;
+static unsigned char *inusetab;
+
+static spinlock_t ps3_bolttab_lock = SPIN_LOCK_UNLOCKED;
+
+#define debug_dump_hpte(_a, _b, _c, _d, _e, _f, _g) \
+	_debug_dump_hpte(_a, _b, _c, _d, _e, _f, _g, __func__, __LINE__)
+static void _debug_dump_hpte(unsigned long pa, unsigned long va,
+	unsigned long group, unsigned long bitmap, hpte_t lhpte, int psize,
+	unsigned long slot, const char* func, int line)
+{
+	DBG("%s:%d: pa     = %lxh\n", func, line, pa);
+	DBG("%s:%d: lpar   = %lxh\n", func, line,
+		ps3_mm_phys_to_lpar(pa));
+	DBG("%s:%d: va     = %lxh\n", func, line, va);
+	DBG("%s:%d: group  = %lxh\n", func, line, group);
+	DBG("%s:%d: bitmap = %lxh\n", func, line, bitmap);
+	DBG("%s:%d: hpte.v = %lxh\n", func, line, lhpte.v);
+	DBG("%s:%d: hpte.r = %lxh\n", func, line, lhpte.r);
+	DBG("%s:%d: psize  = %xh\n", func, line, psize);
+	DBG("%s:%d: slot   = %lxh\n", func, line, slot);
+}
+
+static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
+	unsigned long pa, unsigned long rflags, unsigned long vflags, int psize)
+{
+	unsigned long slot;
+	hpte_t lhpte;
+	int secondary = 0;
+	unsigned long result;
+	unsigned long bitmap;
+	unsigned long flags;
+	unsigned long p_pteg, s_pteg, b_index, b_mask, cb, ci;
+
+	vflags &= ~HPTE_V_SECONDARY; /* this bit is ignored */
+
+	lhpte.v = hpte_encode_v(va, psize) | vflags | HPTE_V_VALID;
+	lhpte.r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags;
+
+	p_pteg = hpte_group / HPTES_PER_GROUP;
+	s_pteg = ~p_pteg & htab_hash_mask;
+
+	spin_lock_irqsave(&ps3_bolttab_lock, flags);
+
+	BUG_ON(bolttab[p_pteg] == 0xff && bolttab[s_pteg] == 0xff);
+
+	bitmap = (inusetab[p_pteg] << 8) | inusetab[s_pteg];
+
+	if (bitmap == 0xffff) {
+		/*
+		 * PTEG is full. Search for victim.
+		 */
+		bitmap &= ~((bolttab[p_pteg] << 8) | bolttab[s_pteg]);
+		do {
+			ci = mftb() & 15;
+			cb = 0x8000UL >> ci;
+		} while ((cb & bitmap) == 0);
+	} else {
+		/*
+		 * search free slot in hardware order
+		 *	[primary]	0, 2, 4, 6, 1, 3, 5, 7
+		 *	[secondary]	0, 2, 4, 6, 1, 3, 5, 7
+		 */
+		for (ci = 0; ci < HPTES_PER_GROUP; ci += 2) {
+			cb = 0x8000UL >> ci;
+			if ((cb & bitmap) == 0)
+				goto found;
+		}
+		for (ci = 1; ci < HPTES_PER_GROUP; ci += 2) {
+			cb = 0x8000UL >> ci;
+			if ((cb & bitmap) == 0)
+				goto found;
+		}
+		for (ci = HPTES_PER_GROUP; ci < HPTES_PER_GROUP*2; ci += 2) {
+			cb = 0x8000UL >> ci;
+			if ((cb & bitmap) == 0)
+				goto found;
+		}
+		for (ci = HPTES_PER_GROUP+1; ci < HPTES_PER_GROUP*2; ci += 2) {
+			cb = 0x8000UL >> ci;
+			if ((cb & bitmap) == 0)
+				goto found;
+		}
+	}
+
+found:
+	if (ci < HPTES_PER_GROUP) {
+		slot = p_pteg * HPTES_PER_GROUP + ci;
+	} else {
+		slot = s_pteg * HPTES_PER_GROUP + (ci & 7);
+		/* lhpte.dw0.dw0.h = 1; */
+		vflags |= HPTE_V_SECONDARY;
+		lhpte.v |= HPTE_V_SECONDARY;
+	}
+
+	result = lv1_write_htab_entry(0, slot, lhpte.v, lhpte.r);
+
+	if (result) {
+		debug_dump_hpte(pa, va, hpte_group, bitmap, lhpte, psize, slot);
+		BUG();
+	}
+
+	/*
+	 * If used slot is not in primary HPTE group,
+	 * the slot should be in secondary HPTE group.
+	 */
+
+	if ((hpte_group ^ slot) & ~(HPTES_PER_GROUP - 1)) {
+		secondary = 1;
+		b_index = s_pteg;
+	} else {
+		secondary = 0;
+		b_index = p_pteg;
+	}
+
+	b_mask = (lhpte.v & HPTE_V_BOLTED) ? 1 << 7 : 0 << 7;
+	bolttab[b_index] |= b_mask >> (slot & 7);
+	b_mask = 1 << 7;
+	inusetab[b_index] |= b_mask >> (slot & 7);
+	spin_unlock_irqrestore(&ps3_bolttab_lock, flags);
+
+	return (slot & 7) | (secondary << 3);
+}
+
+static long ps3_hpte_remove(unsigned long hpte_group)
+{
+	panic("ps3_hpte_remove() not implemented");
+	return 0;
+}
+
+static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
+	unsigned long va, int psize, int local)
+{
+	unsigned long flags;
+	unsigned long result;
+	unsigned long pteg, bit;
+	unsigned long hpte_v, want_v;
+
+	want_v = hpte_encode_v(va, psize);
+
+	spin_lock_irqsave(&ps3_bolttab_lock, flags);
+
+	hpte_v = htab[slot].v;
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
+		spin_unlock_irqrestore(&ps3_bolttab_lock, flags);
+
+		/* ps3_hpte_insert() will be used to update PTE */
+		return -1;
+	}
+
+	result = lv1_write_htab_entry(0, slot, 0, 0);
+
+	if (result) {
+		DBG("%s: va=%lx slot=%lx psize=%d result = %ld (0x%lx)\n",
+		       __func__, va, slot, psize, result, result);
+		BUG();
+	}
+
+	pteg = slot / HPTES_PER_GROUP;
+	bit = slot % HPTES_PER_GROUP;
+	inusetab[pteg] &= ~(0x80 >> bit);
+
+	spin_unlock_irqrestore(&ps3_bolttab_lock, flags);
+
+	/* ps3_hpte_insert() will be used to update PTE */
+	return -1;
+}
+
+static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
+	int psize)
+{
+	panic("ps3_hpte_updateboltedpp() not implemented");
+}
+
+static void ps3_hpte_invalidate(unsigned long slot, unsigned long va,
+	int psize, int local)
+{
+	unsigned long flags;
+	unsigned long result;
+	unsigned long pteg, bit;
+
+	spin_lock_irqsave(&ps3_bolttab_lock, flags);
+	result = lv1_write_htab_entry(0, slot, 0, 0);
+
+	if (result) {
+		DBG("%s: va=%lx slot=%lx psize=%d result = %ld (0x%lx)\n",
+		       __func__, va, slot, psize, result, result);
+		BUG();
+	}
+
+	pteg = slot / HPTES_PER_GROUP;
+	bit = slot % HPTES_PER_GROUP;
+	inusetab[pteg] &= ~(0x80 >> bit);
+	spin_unlock_irqrestore(&ps3_bolttab_lock, flags);
+}
+
+static void ps3_hpte_clear(void)
+{
+	lv1_unmap_htab(htab_addr);
+}
+
+void __init ps3_hpte_init(unsigned long htab_size)
+{
+	long bitmap_size;
+
+	DBG(" -> %s:%d\n", __func__, __LINE__);
+
+	ppc_md.hpte_invalidate = ps3_hpte_invalidate;
+	ppc_md.hpte_updatepp = ps3_hpte_updatepp;
+	ppc_md.hpte_updateboltedpp = ps3_hpte_updateboltedpp;
+	ppc_md.hpte_insert = ps3_hpte_insert;
+	ppc_md.hpte_remove = ps3_hpte_remove;
+	ppc_md.hpte_clear_all = ps3_hpte_clear;
+
+	ppc64_pft_size = __ilog2(htab_size);
+
+	bitmap_size = htab_size / sizeof(hpte_t) / 8;
+
+	bolttab = __va(lmb_alloc(bitmap_size, 1));
+	inusetab = __va(lmb_alloc(bitmap_size, 1));
+
+	memset(bolttab, 0, bitmap_size);
+	memset(inusetab, 0, bitmap_size);
+
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+}
+
+void __init ps3_map_htab(void)
+{
+	long result;
+	unsigned long htab_size = (1UL << ppc64_pft_size);
+
+	result = lv1_map_htab(0, &htab_addr);
+
+	htab = (hpte_t *)__ioremap(htab_addr, htab_size, PAGE_READONLY_X);
+
+	DBG("%s:%d: lpar %016lxh, virt %016lxh\n", __func__, __LINE__,
+		htab_addr, (unsigned long)htab);
+}
diff --git a/arch/powerpc/platforms/ps3/hvcall.S b/arch/powerpc/platforms/ps3/hvcall.S
new file mode 100644
index 000000000000..54be6523a0e8
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/hvcall.S
@@ -0,0 +1,804 @@
+/*
+ *  PS3 hvcall interface.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *  Copyright 2003, 2004 (c) MontaVista Software, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  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 <asm/processor.h>
+#include <asm/ppc_asm.h>
+
+#define lv1call .long 0x44000022; extsw r3, r3
+
+#define LV1_N_IN_0_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_0_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_1_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_2_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_3_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_4_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_5_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_6_IN_0_OUT LV1_N_IN_0_OUT
+#define LV1_7_IN_0_OUT LV1_N_IN_0_OUT
+
+#define LV1_0_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu    r3, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_0_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r3, -8(r1);			\
+	stdu	r4, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_0_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r3, -8(r1);			\
+	std	r4, -16(r1);			\
+	stdu	r5, -24(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 24;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_0_IN_7_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r3, -8(r1);			\
+	std	r4, -16(r1);			\
+	std	r5, -24(r1);			\
+	std	r6, -32(r1);			\
+	std	r7, -40(r1);			\
+	std	r8, -48(r1);			\
+	stdu	r9, -56(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 56;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+	ld	r11, -40(r1);			\
+	std	r8, 0(r11);			\
+	ld	r11, -48(r1);			\
+	std	r9, 0(r11);			\
+	ld	r11, -56(r1);			\
+	std	r10, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu    r4, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r4, -8(r1);			\
+	stdu	r5, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r4, -8(r1);			\
+	std	r5, -16(r1);			\
+	stdu	r6, -24(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 24;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_4_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r4, -8(r1);			\
+	std	r5, -16(r1);			\
+	std	r6, -24(r1);			\
+	stdu	r7, -32(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 32;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_5_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r4, -8(r1);			\
+	std	r5, -16(r1);			\
+	std	r6, -24(r1);			\
+	std	r7, -32(r1);			\
+	stdu	r8, -40(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 40;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+	ld	r11, -40(r1);			\
+	std	r8, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_6_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r4, -8(r1);			\
+	std	r5, -16(r1);			\
+	std	r6, -24(r1);			\
+	std	r7, -32(r1);			\
+	std	r8, -40(r1);			\
+	stdu	r9, -48(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 48;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+	ld	r11, -40(r1);			\
+	std	r8, 0(r11);			\
+	ld	r11, -48(r1);			\
+	std	r9, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_1_IN_7_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r4, -8(r1);			\
+	std	r5, -16(r1);			\
+	std	r6, -24(r1);			\
+	std	r7, -32(r1);			\
+	std	r8, -40(r1);			\
+	std	r9, -48(r1);			\
+	stdu	r10, -56(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 56;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+	ld	r11, -40(r1);			\
+	std	r8, 0(r11);			\
+	ld	r11, -48(r1);			\
+	std	r9, 0(r11);			\
+	ld	r11, -56(r1);			\
+	std	r10, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_2_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu	r5, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_2_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r5, -8(r1);			\
+	stdu	r6, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_2_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r5, -8(r1);			\
+	std	r6, -16(r1);			\
+	stdu	r7, -24(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 24;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_2_IN_4_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r5, -8(r1);			\
+	std	r6, -16(r1);			\
+	std	r7, -24(r1);			\
+	stdu	r8, -32(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 32;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_2_IN_5_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r5, -8(r1);			\
+	std	r6, -16(r1);			\
+	std	r7, -24(r1);			\
+	std	r8, -32(r1);			\
+	stdu	r9, -40(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 40;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+	ld	r11, -32(r1);			\
+	std	r7, 0(r11);			\
+	ld	r11, -40(r1);			\
+	std	r8, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_3_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu	r6, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_3_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r6, -8(r1);			\
+	stdu	r7, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_3_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r6, -8(r1);			\
+	std	r7, -16(r1);			\
+	stdu	r8, -24(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 24;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_4_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu    r7, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_4_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r7, -8(r1);			\
+	stdu	r8, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_4_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r7, -8(r1);			\
+	std	r8, -16(r1);			\
+	stdu	r9, -24(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 24;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_5_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu    r8, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_5_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r8, -8(r1);			\
+	stdu	r9, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_5_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r8, -8(r1);			\
+	std	r9, -16(r1);			\
+	stdu	r10, -24(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 24;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, -24(r1);			\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_6_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu    r9, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_6_IN_2_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r9, -8(r1);			\
+	stdu    r10, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_6_IN_3_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std     r9, -8(r1);			\
+	stdu    r10, -16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 16;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+	ld	r11, -16(r1);			\
+	std	r5, 0(r11);			\
+	ld	r11, 48+8*8(r1);		\
+	std	r6, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_7_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	stdu    r10, -8(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	addi	r1, r1, 8;			\
+	ld	r11, -8(r1);			\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_7_IN_6_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	std	r10, 48+8*7(r1);		\
+						\
+	li	r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	ld	r11, 48+8*7(r1);		\
+	std	r4, 0(r11);			\
+	ld	r11, 48+8*8(r1);		\
+	std	r5, 0(r11);			\
+	ld	r11, 48+8*9(r1);		\
+	std	r6, 0(r11);			\
+	ld	r11, 48+8*10(r1);		\
+	std	r7, 0(r11);			\
+	ld	r11, 48+8*11(r1);		\
+	std	r8, 0(r11);			\
+	ld	r11, 48+8*12(r1);		\
+	std	r9, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+#define LV1_8_IN_1_OUT(API_NAME, API_NUMBER)	\
+_GLOBAL(_##API_NAME)				\
+						\
+	mflr	r0;				\
+	std	r0, 16(r1);			\
+						\
+	li      r11, API_NUMBER;		\
+	lv1call;				\
+						\
+	ld	r11, 48+8*8(r1);		\
+	std	r4, 0(r11);			\
+						\
+	ld	r0, 16(r1);			\
+	mtlr	r0;				\
+	blr
+
+	.text
+
+/* the lv1 underscored call definitions expand here */
+
+#define LV1_CALL(name, in, out, num) LV1_##in##_IN_##out##_OUT(lv1_##name, num)
+#include <asm/lv1call.h>
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
new file mode 100644
index 000000000000..056c1e4141ba
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -0,0 +1,575 @@
+/*
+ *  PS3 interrupt routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/ps3.h>
+#include <asm/lv1call.h>
+
+#include "platform.h"
+
+#if defined(DEBUG)
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...) do{if(0)printk(fmt);}while(0)
+#endif
+
+/**
+ * ps3_alloc_io_irq - Assign a virq to a system bus device.
+ * interrupt_id: The device interrupt id read from the system repository.
+ * @virq: The assigned Linux virq.
+ *
+ * An io irq represents a non-virtualized device interrupt.  interrupt_id
+ * coresponds to the interrupt number of the interrupt controller.
+ */
+
+int ps3_alloc_io_irq(unsigned int interrupt_id, unsigned int *virq)
+{
+	int result;
+	unsigned long outlet;
+
+	result = lv1_construct_io_irq_outlet(interrupt_id, &outlet);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_construct_io_irq_outlet failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		return result;
+	}
+
+	*virq = irq_create_mapping(NULL, outlet);
+
+	pr_debug("%s:%d: interrupt_id %u => outlet %lu, virq %u\n",
+		__func__, __LINE__, interrupt_id, outlet, *virq);
+
+	return 0;
+}
+
+int ps3_free_io_irq(unsigned int virq)
+{
+	int result;
+
+	result = lv1_destruct_io_irq_outlet(virq_to_hw(virq));
+
+	if (!result)
+		pr_debug("%s:%d: lv1_destruct_io_irq_outlet failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+
+	irq_dispose_mapping(virq);
+
+	return result;
+}
+
+/**
+ * ps3_alloc_event_irq - Allocate a virq for use with a system event.
+ * @virq: The assigned Linux virq.
+ *
+ * The virq can be used with lv1_connect_interrupt_event_receive_port() to
+ * arrange to receive events, or with ps3_send_event_locally() to signal
+ * events.
+ */
+
+int ps3_alloc_event_irq(unsigned int *virq)
+{
+	int result;
+	unsigned long outlet;
+
+	result = lv1_construct_event_receive_port(&outlet);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_construct_event_receive_port failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		*virq = NO_IRQ;
+		return result;
+	}
+
+	*virq = irq_create_mapping(NULL, outlet);
+
+	pr_debug("%s:%d: outlet %lu, virq %u\n", __func__, __LINE__, outlet,
+		*virq);
+
+	return 0;
+}
+
+int ps3_free_event_irq(unsigned int virq)
+{
+	int result;
+
+	pr_debug(" -> %s:%d\n", __func__, __LINE__);
+
+	result = lv1_destruct_event_receive_port(virq_to_hw(virq));
+
+	if (result)
+		pr_debug("%s:%d: lv1_destruct_event_receive_port failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+
+	irq_dispose_mapping(virq);
+
+	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+
+int ps3_send_event_locally(unsigned int virq)
+{
+	return lv1_send_event_locally(virq_to_hw(virq));
+}
+
+/**
+ * ps3_connect_event_irq - Assign a virq to a system bus device.
+ * @did: The HV device identifier read from the system repository.
+ * @interrupt_id: The device interrupt id read from the system repository.
+ * @virq: The assigned Linux virq.
+ *
+ * An event irq represents a virtual device interrupt.  The interrupt_id
+ * coresponds to the software interrupt number.
+ */
+
+int ps3_connect_event_irq(const struct ps3_device_id *did,
+	unsigned int interrupt_id, unsigned int *virq)
+{
+	int result;
+
+	result = ps3_alloc_event_irq(virq);
+
+	if (result)
+		return result;
+
+	result = lv1_connect_interrupt_event_receive_port(did->bus_id,
+		did->dev_id, virq_to_hw(*virq), interrupt_id);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_connect_interrupt_event_receive_port"
+			" failed: %s\n", __func__, __LINE__,
+			ps3_result(result));
+		ps3_free_event_irq(*virq);
+		*virq = NO_IRQ;
+		return result;
+	}
+
+	pr_debug("%s:%d: interrupt_id %u, virq %u\n", __func__, __LINE__,
+		interrupt_id, *virq);
+
+	return 0;
+}
+
+int ps3_disconnect_event_irq(const struct ps3_device_id *did,
+	unsigned int interrupt_id, unsigned int virq)
+{
+	int result;
+
+	pr_debug(" -> %s:%d: interrupt_id %u, virq %u\n", __func__, __LINE__,
+		interrupt_id, virq);
+
+	result = lv1_disconnect_interrupt_event_receive_port(did->bus_id,
+		did->dev_id, virq_to_hw(virq), interrupt_id);
+
+	if (result)
+		pr_debug("%s:%d: lv1_disconnect_interrupt_event_receive_port"
+			" failed: %s\n", __func__, __LINE__,
+			ps3_result(result));
+
+	ps3_free_event_irq(virq);
+
+	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+
+/**
+ * ps3_alloc_vuart_irq - Configure the system virtual uart virq.
+ * @virt_addr_bmp: The caller supplied virtual uart interrupt bitmap.
+ * @virq: The assigned Linux virq.
+ *
+ * The system supports only a single virtual uart, so multiple calls without
+ * freeing the interrupt will return a wrong state error.
+ */
+
+int ps3_alloc_vuart_irq(void* virt_addr_bmp, unsigned int *virq)
+{
+	int result;
+	unsigned long outlet;
+	unsigned long lpar_addr;
+
+	BUG_ON(!is_kernel_addr((unsigned long)virt_addr_bmp));
+
+	lpar_addr = ps3_mm_phys_to_lpar(__pa(virt_addr_bmp));
+
+	result = lv1_configure_virtual_uart_irq(lpar_addr, &outlet);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_configure_virtual_uart_irq failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		return result;
+	}
+
+	*virq = irq_create_mapping(NULL, outlet);
+
+	pr_debug("%s:%d: outlet %lu, virq %u\n", __func__, __LINE__,
+		outlet, *virq);
+
+	return 0;
+}
+
+int ps3_free_vuart_irq(unsigned int virq)
+{
+	int result;
+
+	result = lv1_deconfigure_virtual_uart_irq();
+
+	if (result) {
+		pr_debug("%s:%d: lv1_configure_virtual_uart_irq failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		return result;
+	}
+
+	irq_dispose_mapping(virq);
+
+	return result;
+}
+
+/**
+ * ps3_alloc_spe_irq - Configure an spe virq.
+ * @spe_id: The spe_id returned from lv1_construct_logical_spe().
+ * @class: The spe interrupt class {0,1,2}.
+ * @virq: The assigned Linux virq.
+ *
+ */
+
+int ps3_alloc_spe_irq(unsigned long spe_id, unsigned int class,
+	unsigned int *virq)
+{
+	int result;
+	unsigned long outlet;
+
+	BUG_ON(class > 2);
+
+	result = lv1_get_spe_irq_outlet(spe_id, class, &outlet);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_get_spe_irq_outlet failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		return result;
+	}
+
+	*virq = irq_create_mapping(NULL, outlet);
+
+	pr_debug("%s:%d: spe_id %lu, class %u, outlet %lu, virq %u\n",
+		__func__, __LINE__, spe_id, class, outlet, *virq);
+
+	return 0;
+}
+
+int ps3_free_spe_irq(unsigned int virq)
+{
+	irq_dispose_mapping(virq);
+	return 0;
+}
+
+#define PS3_INVALID_OUTLET ((irq_hw_number_t)-1)
+#define PS3_PLUG_MAX 63
+
+/**
+ * struct bmp - a per cpu irq status and mask bitmap structure
+ * @status: 256 bit status bitmap indexed by plug
+ * @unused_1:
+ * @mask: 256 bit mask bitmap indexed by plug
+ * @unused_2:
+ * @lock:
+ * @ipi_debug_brk_mask:
+ *
+ * The HV mantains per SMT thread mappings of HV outlet to HV plug on
+ * behalf of the guest.  These mappings are implemented as 256 bit guest
+ * supplied bitmaps indexed by plug number.  The address of the bitmaps are
+ * registered with the HV through lv1_configure_irq_state_bitmap().
+ *
+ * The HV supports 256 plugs per thread, assigned as {0..255}, for a total
+ * of 512 plugs supported on a processor.  To simplify the logic this
+ * implementation equates HV plug value to linux virq value, constrains each
+ * interrupt to have a system wide unique plug number, and limits the range
+ * of the plug values to map into the first dword of the bitmaps.  This
+ * gives a usable range of plug values of  {NUM_ISA_INTERRUPTS..63}.  Note
+ * that there is no constraint on how many in this set an individual thread
+ * can aquire.
+ */
+
+struct bmp {
+	struct {
+		unsigned long status;
+		unsigned long unused_1[3];
+		unsigned long mask;
+		unsigned long unused_2[3];
+	} __attribute__ ((packed));
+	spinlock_t lock;
+	unsigned long ipi_debug_brk_mask;
+};
+
+/**
+ * struct private - a per cpu data structure
+ * @node: HV node id
+ * @cpu: HV thread id
+ * @bmp: an HV bmp structure
+ */
+
+struct private {
+	unsigned long node;
+	unsigned int cpu;
+	struct bmp bmp;
+};
+
+#if defined(DEBUG)
+static void _dump_64_bmp(const char *header, const unsigned long *p, unsigned cpu,
+	const char* func, int line)
+{
+	pr_debug("%s:%d: %s %u {%04lx_%04lx_%04lx_%04lx}\n",
+		func, line, header, cpu,
+		*p >> 48, (*p >> 32) & 0xffff, (*p >> 16) & 0xffff,
+		*p & 0xffff);
+}
+
+static void __attribute__ ((unused)) _dump_256_bmp(const char *header,
+	const unsigned long *p, unsigned cpu, const char* func, int line)
+{
+	pr_debug("%s:%d: %s %u {%016lx:%016lx:%016lx:%016lx}\n",
+		func, line, header, cpu, p[0], p[1], p[2], p[3]);
+}
+
+#define dump_bmp(_x) _dump_bmp(_x, __func__, __LINE__)
+static void _dump_bmp(struct private* pd, const char* func, int line)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pd->bmp.lock, flags);
+	_dump_64_bmp("stat", &pd->bmp.status, pd->cpu, func, line);
+	_dump_64_bmp("mask", &pd->bmp.mask, pd->cpu, func, line);
+	spin_unlock_irqrestore(&pd->bmp.lock, flags);
+}
+
+#define dump_mask(_x) _dump_mask(_x, __func__, __LINE__)
+static void __attribute__ ((unused)) _dump_mask(struct private* pd,
+	const char* func, int line)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pd->bmp.lock, flags);
+	_dump_64_bmp("mask", &pd->bmp.mask, pd->cpu, func, line);
+	spin_unlock_irqrestore(&pd->bmp.lock, flags);
+}
+#else
+static void dump_bmp(struct private* pd) {};
+#endif /* defined(DEBUG) */
+
+static void chip_mask(unsigned int virq)
+{
+	unsigned long flags;
+	struct private *pd = get_irq_chip_data(virq);
+
+	pr_debug("%s:%d: cpu %u, virq %d\n", __func__, __LINE__, pd->cpu, virq);
+
+	BUG_ON(virq < NUM_ISA_INTERRUPTS);
+	BUG_ON(virq > PS3_PLUG_MAX);
+
+	spin_lock_irqsave(&pd->bmp.lock, flags);
+	pd->bmp.mask &= ~(0x8000000000000000UL >> virq);
+	spin_unlock_irqrestore(&pd->bmp.lock, flags);
+
+	lv1_did_update_interrupt_mask(pd->node, pd->cpu);
+}
+
+static void chip_unmask(unsigned int virq)
+{
+	unsigned long flags;
+	struct private *pd = get_irq_chip_data(virq);
+
+	pr_debug("%s:%d: cpu %u, virq %d\n", __func__, __LINE__, pd->cpu, virq);
+
+	BUG_ON(virq < NUM_ISA_INTERRUPTS);
+	BUG_ON(virq > PS3_PLUG_MAX);
+
+	spin_lock_irqsave(&pd->bmp.lock, flags);
+	pd->bmp.mask |= (0x8000000000000000UL >> virq);
+	spin_unlock_irqrestore(&pd->bmp.lock, flags);
+
+	lv1_did_update_interrupt_mask(pd->node, pd->cpu);
+}
+
+static void chip_eoi(unsigned int virq)
+{
+	lv1_end_of_interrupt(virq);
+}
+
+static struct irq_chip irq_chip = {
+	.typename = "ps3",
+	.mask = chip_mask,
+	.unmask = chip_unmask,
+	.eoi = chip_eoi,
+};
+
+static void host_unmap(struct irq_host *h, unsigned int virq)
+{
+	int result;
+
+	pr_debug("%s:%d: virq %d\n", __func__, __LINE__, virq);
+
+	lv1_disconnect_irq_plug(virq);
+
+	result = set_irq_chip_data(virq, NULL);
+	BUG_ON(result);
+}
+
+static DEFINE_PER_CPU(struct private, private);
+
+static int host_map(struct irq_host *h, unsigned int virq,
+	irq_hw_number_t hwirq)
+{
+	int result;
+	unsigned int cpu;
+
+	pr_debug(" -> %s:%d\n", __func__, __LINE__);
+	pr_debug("%s:%d: hwirq %lu => virq %u\n", __func__, __LINE__, hwirq,
+		virq);
+
+	/* bind this virq to a cpu */
+
+	preempt_disable();
+	cpu = smp_processor_id();
+	result = lv1_connect_irq_plug(virq, hwirq);
+	preempt_enable();
+
+	if (result) {
+		pr_info("%s:%d: lv1_connect_irq_plug failed:"
+			" %s\n", __func__, __LINE__, ps3_result(result));
+		return -EPERM;
+	}
+
+	result = set_irq_chip_data(virq, &per_cpu(private, cpu));
+	BUG_ON(result);
+
+	set_irq_chip_and_handler(virq, &irq_chip, handle_fasteoi_irq);
+
+	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+
+static struct irq_host_ops host_ops = {
+	.map = host_map,
+	.unmap = host_unmap,
+};
+
+void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq)
+{
+	struct private *pd = &per_cpu(private, cpu);
+
+	pd->bmp.ipi_debug_brk_mask = 0x8000000000000000UL >> virq;
+
+	pr_debug("%s:%d: cpu %u, virq %u, mask %lxh\n", __func__, __LINE__,
+		cpu, virq, pd->bmp.ipi_debug_brk_mask);
+}
+
+static int bmp_get_and_clear_status_bit(struct bmp *m)
+{
+	unsigned long flags;
+	unsigned int bit;
+	unsigned long x;
+
+	spin_lock_irqsave(&m->lock, flags);
+
+	/* check for ipi break first to stop this cpu ASAP */
+
+	if (m->status & m->ipi_debug_brk_mask) {
+		m->status &= ~m->ipi_debug_brk_mask;
+		spin_unlock_irqrestore(&m->lock, flags);
+		return __ilog2(m->ipi_debug_brk_mask);
+	}
+
+	x = (m->status & m->mask);
+
+	for (bit = NUM_ISA_INTERRUPTS, x <<= bit; x; bit++, x <<= 1)
+		if (x & 0x8000000000000000UL) {
+			m->status &= ~(0x8000000000000000UL >> bit);
+			spin_unlock_irqrestore(&m->lock, flags);
+			return bit;
+		}
+
+	spin_unlock_irqrestore(&m->lock, flags);
+
+	pr_debug("%s:%d: not found\n", __func__, __LINE__);
+	return -1;
+}
+
+unsigned int ps3_get_irq(void)
+{
+	int plug;
+
+	struct private *pd = &__get_cpu_var(private);
+
+	plug = bmp_get_and_clear_status_bit(&pd->bmp);
+
+	if (plug < 1) {
+		pr_debug("%s:%d: no plug found: cpu %u\n", __func__, __LINE__,
+			pd->cpu);
+		dump_bmp(&per_cpu(private, 0));
+		dump_bmp(&per_cpu(private, 1));
+		return NO_IRQ;
+	}
+
+#if defined(DEBUG)
+	if (plug < NUM_ISA_INTERRUPTS || plug > PS3_PLUG_MAX) {
+		dump_bmp(&per_cpu(private, 0));
+		dump_bmp(&per_cpu(private, 1));
+		BUG();
+	}
+#endif
+	return plug;
+}
+
+void __init ps3_init_IRQ(void)
+{
+	int result;
+	unsigned long node;
+	unsigned cpu;
+	struct irq_host *host;
+
+	lv1_get_logical_ppe_id(&node);
+
+	host = irq_alloc_host(IRQ_HOST_MAP_NOMAP, 0, &host_ops,
+		PS3_INVALID_OUTLET);
+	irq_set_default_host(host);
+	irq_set_virq_count(PS3_PLUG_MAX + 1);
+
+	for_each_possible_cpu(cpu) {
+		struct private *pd = &per_cpu(private, cpu);
+
+		pd->node = node;
+		pd->cpu = cpu;
+		spin_lock_init(&pd->bmp.lock);
+
+		result = lv1_configure_irq_state_bitmap(node, cpu,
+			ps3_mm_phys_to_lpar(__pa(&pd->bmp.status)));
+
+		if (result)
+			pr_debug("%s:%d: lv1_configure_irq_state_bitmap failed:"
+				" %s\n", __func__, __LINE__,
+				ps3_result(result));
+	}
+
+	ppc_md.get_irq = ps3_get_irq;
+}
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
new file mode 100644
index 000000000000..49c0d010d491
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -0,0 +1,831 @@
+/*
+ *  PS3 address space management.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/module.h>
+#include <linux/memory_hotplug.h>
+
+#include <asm/firmware.h>
+#include <asm/lmb.h>
+#include <asm/udbg.h>
+#include <asm/ps3.h>
+#include <asm/lv1call.h>
+
+#include "platform.h"
+
+#if defined(DEBUG)
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...) do{if(0)printk(fmt);}while(0)
+#endif
+
+enum {
+#if defined(CONFIG_PS3_USE_LPAR_ADDR)
+	USE_LPAR_ADDR = 1,
+#else
+	USE_LPAR_ADDR = 0,
+#endif
+#if defined(CONFIG_PS3_DYNAMIC_DMA)
+	USE_DYNAMIC_DMA = 1,
+#else
+	USE_DYNAMIC_DMA = 0,
+#endif
+};
+
+enum {
+	PAGE_SHIFT_4K = 12U,
+	PAGE_SHIFT_64K = 16U,
+	PAGE_SHIFT_16M = 24U,
+};
+
+static unsigned long make_page_sizes(unsigned long a, unsigned long b)
+{
+	return (a << 56) | (b << 48);
+}
+
+enum {
+	ALLOCATE_MEMORY_TRY_ALT_UNIT = 0X04,
+	ALLOCATE_MEMORY_ADDR_ZERO = 0X08,
+};
+
+/* valid htab sizes are {18,19,20} = 256K, 512K, 1M */
+
+enum {
+	HTAB_SIZE_MAX = 20U, /* HV limit of 1MB */
+	HTAB_SIZE_MIN = 18U, /* CPU limit of 256KB */
+};
+
+/*============================================================================*/
+/* virtual address space routines                                             */
+/*============================================================================*/
+
+/**
+ * struct mem_region - memory region structure
+ * @base: base address
+ * @size: size in bytes
+ * @offset: difference between base and rm.size
+ */
+
+struct mem_region {
+	unsigned long base;
+	unsigned long size;
+	unsigned long offset;
+};
+
+/**
+ * struct map - address space state variables holder
+ * @total: total memory available as reported by HV
+ * @vas_id - HV virtual address space id
+ * @htab_size: htab size in bytes
+ *
+ * The HV virtual address space (vas) allows for hotplug memory regions.
+ * Memory regions can be created and destroyed in the vas at runtime.
+ * @rm: real mode (bootmem) region
+ * @r1: hotplug memory region(s)
+ *
+ * ps3 addresses
+ * virt_addr: a cpu 'translated' effective address
+ * phys_addr: an address in what Linux thinks is the physical address space
+ * lpar_addr: an address in the HV virtual address space
+ * bus_addr: an io controller 'translated' address on a device bus
+ */
+
+struct map {
+	unsigned long total;
+	unsigned long vas_id;
+	unsigned long htab_size;
+	struct mem_region rm;
+	struct mem_region r1;
+};
+
+#define debug_dump_map(x) _debug_dump_map(x, __func__, __LINE__)
+static void _debug_dump_map(const struct map* m, const char* func, int line)
+{
+	DBG("%s:%d: map.total     = %lxh\n", func, line, m->total);
+	DBG("%s:%d: map.rm.size   = %lxh\n", func, line, m->rm.size);
+	DBG("%s:%d: map.vas_id    = %lu\n", func, line, m->vas_id);
+	DBG("%s:%d: map.htab_size = %lxh\n", func, line, m->htab_size);
+	DBG("%s:%d: map.r1.base   = %lxh\n", func, line, m->r1.base);
+	DBG("%s:%d: map.r1.offset = %lxh\n", func, line, m->r1.offset);
+	DBG("%s:%d: map.r1.size   = %lxh\n", func, line, m->r1.size);
+}
+
+static struct map map;
+
+/**
+ * ps3_mm_phys_to_lpar - translate a linux physical address to lpar address
+ * @phys_addr: linux physical address
+ */
+
+unsigned long ps3_mm_phys_to_lpar(unsigned long phys_addr)
+{
+	BUG_ON(is_kernel_addr(phys_addr));
+	if (USE_LPAR_ADDR)
+		return phys_addr;
+	else
+		return (phys_addr < map.rm.size || phys_addr >= map.total)
+			? phys_addr : phys_addr + map.r1.offset;
+}
+
+EXPORT_SYMBOL(ps3_mm_phys_to_lpar);
+
+/**
+ * ps3_mm_vas_create - create the virtual address space
+ */
+
+void __init ps3_mm_vas_create(unsigned long* htab_size)
+{
+	int result;
+	unsigned long start_address;
+	unsigned long size;
+	unsigned long access_right;
+	unsigned long max_page_size;
+	unsigned long flags;
+
+	result = lv1_query_logical_partition_address_region_info(0,
+		&start_address, &size, &access_right, &max_page_size,
+		&flags);
+
+	if (result) {
+		DBG("%s:%d: lv1_query_logical_partition_address_region_info "
+			"failed: %s\n", __func__, __LINE__,
+			ps3_result(result));
+		goto fail;
+	}
+
+	if (max_page_size < PAGE_SHIFT_16M) {
+		DBG("%s:%d: bad max_page_size %lxh\n", __func__, __LINE__,
+			max_page_size);
+		goto fail;
+	}
+
+	BUILD_BUG_ON(CONFIG_PS3_HTAB_SIZE > HTAB_SIZE_MAX);
+	BUILD_BUG_ON(CONFIG_PS3_HTAB_SIZE < HTAB_SIZE_MIN);
+
+	result = lv1_construct_virtual_address_space(CONFIG_PS3_HTAB_SIZE,
+			2, make_page_sizes(PAGE_SHIFT_16M, PAGE_SHIFT_64K),
+			&map.vas_id, &map.htab_size);
+
+	if (result) {
+		DBG("%s:%d: lv1_construct_virtual_address_space failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		goto fail;
+	}
+
+	result = lv1_select_virtual_address_space(map.vas_id);
+
+	if (result) {
+		DBG("%s:%d: lv1_select_virtual_address_space failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		goto fail;
+	}
+
+	*htab_size = map.htab_size;
+
+	debug_dump_map(&map);
+
+	return;
+
+fail:
+	panic("ps3_mm_vas_create failed");
+}
+
+/**
+ * ps3_mm_vas_destroy -
+ */
+
+void ps3_mm_vas_destroy(void)
+{
+	if (map.vas_id) {
+		lv1_select_virtual_address_space(0);
+		lv1_destruct_virtual_address_space(map.vas_id);
+		map.vas_id = 0;
+	}
+}
+
+/*============================================================================*/
+/* memory hotplug routines                                                    */
+/*============================================================================*/
+
+/**
+ * ps3_mm_region_create - create a memory region in the vas
+ * @r: pointer to a struct mem_region to accept initialized values
+ * @size: requested region size
+ *
+ * This implementation creates the region with the vas large page size.
+ * @size is rounded down to a multiple of the vas large page size.
+ */
+
+int ps3_mm_region_create(struct mem_region *r, unsigned long size)
+{
+	int result;
+	unsigned long muid;
+
+	r->size = _ALIGN_DOWN(size, 1 << PAGE_SHIFT_16M);
+
+	DBG("%s:%d requested  %lxh\n", __func__, __LINE__, size);
+	DBG("%s:%d actual     %lxh\n", __func__, __LINE__, r->size);
+	DBG("%s:%d difference %lxh (%luMB)\n", __func__, __LINE__,
+		(unsigned long)(size - r->size),
+		(size - r->size) / 1024 / 1024);
+
+	if (r->size == 0) {
+		DBG("%s:%d: size == 0\n", __func__, __LINE__);
+		result = -1;
+		goto zero_region;
+	}
+
+	result = lv1_allocate_memory(r->size, PAGE_SHIFT_16M, 0,
+		ALLOCATE_MEMORY_TRY_ALT_UNIT, &r->base, &muid);
+
+	if (result || r->base < map.rm.size) {
+		DBG("%s:%d: lv1_allocate_memory failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		goto zero_region;
+	}
+
+	r->offset = r->base - map.rm.size;
+	return result;
+
+zero_region:
+	r->size = r->base = r->offset = 0;
+	return result;
+}
+
+/**
+ * ps3_mm_region_destroy - destroy a memory region
+ * @r: pointer to struct mem_region
+ */
+
+void ps3_mm_region_destroy(struct mem_region *r)
+{
+	if (r->base) {
+		lv1_release_memory(r->base);
+		r->size = r->base = r->offset = 0;
+		map.total = map.rm.size;
+	}
+}
+
+/**
+ * ps3_mm_add_memory - hot add memory
+ */
+
+static int __init ps3_mm_add_memory(void)
+{
+	int result;
+	unsigned long start_addr;
+	unsigned long start_pfn;
+	unsigned long nr_pages;
+
+	if (!firmware_has_feature(FW_FEATURE_PS3_LV1))
+		return 0;
+
+	BUG_ON(!mem_init_done);
+
+	start_addr = USE_LPAR_ADDR ? map.r1.base : map.rm.size;
+	start_pfn = start_addr >> PAGE_SHIFT;
+	nr_pages = (map.r1.size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	DBG("%s:%d: start_addr %lxh, start_pfn %lxh, nr_pages %lxh\n",
+		__func__, __LINE__, start_addr, start_pfn, nr_pages);
+
+	result = add_memory(0, start_addr, map.r1.size);
+
+	if (result) {
+		DBG("%s:%d: add_memory failed: (%d)\n",
+			__func__, __LINE__, result);
+		return result;
+	}
+
+	result = online_pages(start_pfn, nr_pages);
+
+	if (result)
+		DBG("%s:%d: online_pages failed: (%d)\n",
+			__func__, __LINE__, result);
+
+	return result;
+}
+
+core_initcall(ps3_mm_add_memory);
+
+/*============================================================================*/
+/* dma routines                                                               */
+/*============================================================================*/
+
+/**
+ * dma_lpar_to_bus - Translate an lpar address to ioc mapped bus address.
+ * @r: pointer to dma region structure
+ * @lpar_addr: HV lpar address
+ */
+
+static unsigned long dma_lpar_to_bus(struct ps3_dma_region *r,
+	unsigned long lpar_addr)
+{
+	BUG_ON(lpar_addr >= map.r1.base + map.r1.size);
+	return r->bus_addr + (lpar_addr <= map.rm.size ? lpar_addr
+		: lpar_addr - map.r1.offset);
+}
+
+#define dma_dump_region(_a) _dma_dump_region(_a, __func__, __LINE__)
+static void _dma_dump_region(const struct ps3_dma_region *r, const char* func,
+	int line)
+{
+	DBG("%s:%d: dev        %u:%u\n", func, line, r->did.bus_id,
+		r->did.dev_id);
+	DBG("%s:%d: page_size  %u\n", func, line, r->page_size);
+	DBG("%s:%d: bus_addr   %lxh\n", func, line, r->bus_addr);
+	DBG("%s:%d: len        %lxh\n", func, line, r->len);
+}
+
+/**
+ * dma_chunk - A chunk of dma pages mapped by the io controller.
+ * @region - The dma region that owns this chunk.
+ * @lpar_addr: Starting lpar address of the area to map.
+ * @bus_addr: Starting ioc bus address of the area to map.
+ * @len: Length in bytes of the area to map.
+ * @link: A struct list_head used with struct ps3_dma_region.chunk_list, the
+ * list of all chuncks owned by the region.
+ *
+ * This implementation uses a very simple dma page manager
+ * based on the dma_chunk structure.  This scheme assumes
+ * that all drivers use very well behaved dma ops.
+ */
+
+struct dma_chunk {
+	struct ps3_dma_region *region;
+	unsigned long lpar_addr;
+	unsigned long bus_addr;
+	unsigned long len;
+	struct list_head link;
+	unsigned int usage_count;
+};
+
+#define dma_dump_chunk(_a) _dma_dump_chunk(_a, __func__, __LINE__)
+static void _dma_dump_chunk (const struct dma_chunk* c, const char* func,
+	int line)
+{
+	DBG("%s:%d: r.dev        %u:%u\n", func, line,
+		c->region->did.bus_id, c->region->did.dev_id);
+	DBG("%s:%d: r.bus_addr   %lxh\n", func, line, c->region->bus_addr);
+	DBG("%s:%d: r.page_size  %u\n", func, line, c->region->page_size);
+	DBG("%s:%d: r.len        %lxh\n", func, line, c->region->len);
+	DBG("%s:%d: c.lpar_addr  %lxh\n", func, line, c->lpar_addr);
+	DBG("%s:%d: c.bus_addr   %lxh\n", func, line, c->bus_addr);
+	DBG("%s:%d: c.len        %lxh\n", func, line, c->len);
+}
+
+static struct dma_chunk * dma_find_chunk(struct ps3_dma_region *r,
+	unsigned long bus_addr, unsigned long len)
+{
+	struct dma_chunk *c;
+	unsigned long aligned_bus = _ALIGN_DOWN(bus_addr, 1 << r->page_size);
+	unsigned long aligned_len = _ALIGN_UP(len, 1 << r->page_size);
+
+	list_for_each_entry(c, &r->chunk_list.head, link) {
+		/* intersection */
+		if (aligned_bus >= c->bus_addr
+			&& aligned_bus < c->bus_addr + c->len
+			&& aligned_bus + aligned_len <= c->bus_addr + c->len) {
+			return c;
+		}
+		/* below */
+		if (aligned_bus + aligned_len <= c->bus_addr) {
+			continue;
+		}
+		/* above */
+		if (aligned_bus >= c->bus_addr + c->len) {
+			continue;
+		}
+
+		/* we don't handle the multi-chunk case for now */
+
+		dma_dump_chunk(c);
+		BUG();
+	}
+	return NULL;
+}
+
+static int dma_free_chunk(struct dma_chunk *c)
+{
+	int result = 0;
+
+	if (c->bus_addr) {
+		result = lv1_unmap_device_dma_region(c->region->did.bus_id,
+			c->region->did.dev_id, c->bus_addr, c->len);
+		BUG_ON(result);
+	}
+
+	kfree(c);
+	return result;
+}
+
+/**
+ * dma_map_pages - Maps dma pages into the io controller bus address space.
+ * @r: Pointer to a struct ps3_dma_region.
+ * @phys_addr: Starting physical address of the area to map.
+ * @len: Length in bytes of the area to map.
+ * c_out: A pointer to receive an allocated struct dma_chunk for this area.
+ *
+ * This is the lowest level dma mapping routine, and is the one that will
+ * make the HV call to add the pages into the io controller address space.
+ */
+
+static int dma_map_pages(struct ps3_dma_region *r, unsigned long phys_addr,
+	unsigned long len, struct dma_chunk **c_out)
+{
+	int result;
+	struct dma_chunk *c;
+
+	c = kzalloc(sizeof(struct dma_chunk), GFP_ATOMIC);
+
+	if (!c) {
+		result = -ENOMEM;
+		goto fail_alloc;
+	}
+
+	c->region = r;
+	c->lpar_addr = ps3_mm_phys_to_lpar(phys_addr);
+	c->bus_addr = dma_lpar_to_bus(r, c->lpar_addr);
+	c->len = len;
+
+	result = lv1_map_device_dma_region(c->region->did.bus_id,
+		c->region->did.dev_id, c->lpar_addr, c->bus_addr, c->len,
+		0xf800000000000000UL);
+
+	if (result) {
+		DBG("%s:%d: lv1_map_device_dma_region failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		goto fail_map;
+	}
+
+	list_add(&c->link, &r->chunk_list.head);
+
+	*c_out = c;
+	return 0;
+
+fail_map:
+	kfree(c);
+fail_alloc:
+	*c_out = NULL;
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+
+/**
+ * dma_region_create - Create a device dma region.
+ * @r: Pointer to a struct ps3_dma_region.
+ *
+ * This is the lowest level dma region create routine, and is the one that
+ * will make the HV call to create the region.
+ */
+
+static int dma_region_create(struct ps3_dma_region* r)
+{
+	int result;
+
+	r->len = _ALIGN_UP(map.total, 1 << r->page_size);
+	INIT_LIST_HEAD(&r->chunk_list.head);
+	spin_lock_init(&r->chunk_list.lock);
+
+	result = lv1_allocate_device_dma_region(r->did.bus_id, r->did.dev_id,
+		r->len, r->page_size, r->region_type, &r->bus_addr);
+
+	dma_dump_region(r);
+
+	if (result) {
+		DBG("%s:%d: lv1_allocate_device_dma_region failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		r->len = r->bus_addr = 0;
+	}
+
+	return result;
+}
+
+/**
+ * dma_region_free - Free a device dma region.
+ * @r: Pointer to a struct ps3_dma_region.
+ *
+ * This is the lowest level dma region free routine, and is the one that
+ * will make the HV call to free the region.
+ */
+
+static int dma_region_free(struct ps3_dma_region* r)
+{
+	int result;
+	struct dma_chunk *c;
+	struct dma_chunk *tmp;
+
+	list_for_each_entry_safe(c, tmp, &r->chunk_list.head, link) {
+		list_del(&c->link);
+		dma_free_chunk(c);
+	}
+
+	result = lv1_free_device_dma_region(r->did.bus_id, r->did.dev_id,
+		r->bus_addr);
+
+	if (result)
+		DBG("%s:%d: lv1_free_device_dma_region failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+
+	r->len = r->bus_addr = 0;
+
+	return result;
+}
+
+/**
+ * dma_map_area - Map an area of memory into a device dma region.
+ * @r: Pointer to a struct ps3_dma_region.
+ * @virt_addr: Starting virtual address of the area to map.
+ * @len: Length in bytes of the area to map.
+ * @bus_addr: A pointer to return the starting ioc bus address of the area to
+ * map.
+ *
+ * This is the common dma mapping routine.
+ */
+
+static int dma_map_area(struct ps3_dma_region *r, unsigned long virt_addr,
+	unsigned long len, unsigned long *bus_addr)
+{
+	int result;
+	unsigned long flags;
+	struct dma_chunk *c;
+	unsigned long phys_addr = is_kernel_addr(virt_addr) ? __pa(virt_addr)
+		: virt_addr;
+
+	*bus_addr = dma_lpar_to_bus(r, ps3_mm_phys_to_lpar(phys_addr));
+
+	if (!USE_DYNAMIC_DMA) {
+		unsigned long lpar_addr = ps3_mm_phys_to_lpar(phys_addr);
+		DBG(" -> %s:%d\n", __func__, __LINE__);
+		DBG("%s:%d virt_addr %lxh\n", __func__, __LINE__,
+			virt_addr);
+		DBG("%s:%d phys_addr %lxh\n", __func__, __LINE__,
+			phys_addr);
+		DBG("%s:%d lpar_addr %lxh\n", __func__, __LINE__,
+			lpar_addr);
+		DBG("%s:%d len       %lxh\n", __func__, __LINE__, len);
+		DBG("%s:%d bus_addr  %lxh (%lxh)\n", __func__, __LINE__,
+		*bus_addr, len);
+	}
+
+	spin_lock_irqsave(&r->chunk_list.lock, flags);
+	c = dma_find_chunk(r, *bus_addr, len);
+
+	if (c) {
+		c->usage_count++;
+		spin_unlock_irqrestore(&r->chunk_list.lock, flags);
+		return 0;
+	}
+
+	result = dma_map_pages(r, _ALIGN_DOWN(phys_addr, 1 << r->page_size),
+		_ALIGN_UP(len, 1 << r->page_size), &c);
+
+	if (result) {
+		*bus_addr = 0;
+		DBG("%s:%d: dma_map_pages failed (%d)\n",
+			__func__, __LINE__, result);
+		spin_unlock_irqrestore(&r->chunk_list.lock, flags);
+		return result;
+	}
+
+	c->usage_count = 1;
+
+	spin_unlock_irqrestore(&r->chunk_list.lock, flags);
+	return result;
+}
+
+/**
+ * dma_unmap_area - Unmap an area of memory from a device dma region.
+ * @r: Pointer to a struct ps3_dma_region.
+ * @bus_addr: The starting ioc bus address of the area to unmap.
+ * @len: Length in bytes of the area to unmap.
+ *
+ * This is the common dma unmap routine.
+ */
+
+int dma_unmap_area(struct ps3_dma_region *r, unsigned long bus_addr,
+	unsigned long len)
+{
+	unsigned long flags;
+	struct dma_chunk *c;
+
+	spin_lock_irqsave(&r->chunk_list.lock, flags);
+	c = dma_find_chunk(r, bus_addr, len);
+
+	if (!c) {
+		unsigned long aligned_bus = _ALIGN_DOWN(bus_addr,
+			1 << r->page_size);
+		unsigned long aligned_len = _ALIGN_UP(len, 1 << r->page_size);
+		DBG("%s:%d: not found: bus_addr %lxh\n",
+			__func__, __LINE__, bus_addr);
+		DBG("%s:%d: not found: len %lxh\n",
+			__func__, __LINE__, len);
+		DBG("%s:%d: not found: aligned_bus %lxh\n",
+			__func__, __LINE__, aligned_bus);
+		DBG("%s:%d: not found: aligned_len %lxh\n",
+			__func__, __LINE__, aligned_len);
+		BUG();
+	}
+
+	c->usage_count--;
+
+	if (!c->usage_count) {
+		list_del(&c->link);
+		dma_free_chunk(c);
+	}
+
+	spin_unlock_irqrestore(&r->chunk_list.lock, flags);
+	return 0;
+}
+
+/**
+ * dma_region_create_linear - Setup a linear dma maping for a device.
+ * @r: Pointer to a struct ps3_dma_region.
+ *
+ * This routine creates an HV dma region for the device and maps all available
+ * ram into the io controller bus address space.
+ */
+
+static int dma_region_create_linear(struct ps3_dma_region *r)
+{
+	int result;
+	unsigned long tmp;
+
+	/* force 16M dma pages for linear mapping */
+
+	if (r->page_size != PS3_DMA_16M) {
+		pr_info("%s:%d: forcing 16M pages for linear map\n",
+			__func__, __LINE__);
+		r->page_size = PS3_DMA_16M;
+	}
+
+	result = dma_region_create(r);
+	BUG_ON(result);
+
+	result = dma_map_area(r, map.rm.base, map.rm.size, &tmp);
+	BUG_ON(result);
+
+	if (USE_LPAR_ADDR)
+		result = dma_map_area(r, map.r1.base, map.r1.size,
+			&tmp);
+	else
+		result = dma_map_area(r, map.rm.size, map.r1.size,
+			&tmp);
+
+	BUG_ON(result);
+
+	return result;
+}
+
+/**
+ * dma_region_free_linear - Free a linear dma mapping for a device.
+ * @r: Pointer to a struct ps3_dma_region.
+ *
+ * This routine will unmap all mapped areas and free the HV dma region.
+ */
+
+static int dma_region_free_linear(struct ps3_dma_region *r)
+{
+	int result;
+
+	result = dma_unmap_area(r, dma_lpar_to_bus(r, 0), map.rm.size);
+	BUG_ON(result);
+
+	result = dma_unmap_area(r, dma_lpar_to_bus(r, map.r1.base),
+		map.r1.size);
+	BUG_ON(result);
+
+	result = dma_region_free(r);
+	BUG_ON(result);
+
+	return result;
+}
+
+/**
+ * dma_map_area_linear - Map an area of memory into a device dma region.
+ * @r: Pointer to a struct ps3_dma_region.
+ * @virt_addr: Starting virtual address of the area to map.
+ * @len: Length in bytes of the area to map.
+ * @bus_addr: A pointer to return the starting ioc bus address of the area to
+ * map.
+ *
+ * This routine just returns the coresponding bus address.  Actual mapping
+ * occurs in dma_region_create_linear().
+ */
+
+static int dma_map_area_linear(struct ps3_dma_region *r,
+	unsigned long virt_addr, unsigned long len, unsigned long *bus_addr)
+{
+	unsigned long phys_addr = is_kernel_addr(virt_addr) ? __pa(virt_addr)
+		: virt_addr;
+	*bus_addr = dma_lpar_to_bus(r, ps3_mm_phys_to_lpar(phys_addr));
+	return 0;
+}
+
+/**
+ * dma_unmap_area_linear - Unmap an area of memory from a device dma region.
+ * @r: Pointer to a struct ps3_dma_region.
+ * @bus_addr: The starting ioc bus address of the area to unmap.
+ * @len: Length in bytes of the area to unmap.
+ *
+ * This routine does nothing.  Unmapping occurs in dma_region_free_linear().
+ */
+
+static int dma_unmap_area_linear(struct ps3_dma_region *r,
+	unsigned long bus_addr, unsigned long len)
+{
+	return 0;
+}
+
+int ps3_dma_region_create(struct ps3_dma_region *r)
+{
+	return (USE_DYNAMIC_DMA)
+		? dma_region_create(r)
+		: dma_region_create_linear(r);
+}
+
+int ps3_dma_region_free(struct ps3_dma_region *r)
+{
+	return (USE_DYNAMIC_DMA)
+		? dma_region_free(r)
+		: dma_region_free_linear(r);
+}
+
+int ps3_dma_map(struct ps3_dma_region *r, unsigned long virt_addr,
+	unsigned long len, unsigned long *bus_addr)
+{
+	return (USE_DYNAMIC_DMA)
+		? dma_map_area(r, virt_addr, len, bus_addr)
+		: dma_map_area_linear(r, virt_addr, len, bus_addr);
+}
+
+int ps3_dma_unmap(struct ps3_dma_region *r, unsigned long bus_addr,
+	unsigned long len)
+{
+	return (USE_DYNAMIC_DMA) ? dma_unmap_area(r, bus_addr, len)
+		: dma_unmap_area_linear(r, bus_addr, len);
+}
+
+/*============================================================================*/
+/* system startup routines                                                    */
+/*============================================================================*/
+
+/**
+ * ps3_mm_init - initialize the address space state variables
+ */
+
+void __init ps3_mm_init(void)
+{
+	int result;
+
+	DBG(" -> %s:%d\n", __func__, __LINE__);
+
+	result = ps3_repository_read_mm_info(&map.rm.base, &map.rm.size,
+		&map.total);
+
+	if (result)
+		panic("ps3_repository_read_mm_info() failed");
+
+	map.rm.offset = map.rm.base;
+	map.vas_id = map.htab_size = 0;
+
+	/* this implementation assumes map.rm.base is zero */
+
+	BUG_ON(map.rm.base);
+	BUG_ON(!map.rm.size);
+
+	lmb_add(map.rm.base, map.rm.size);
+	lmb_analyze();
+
+	/* arrange to do this in ps3_mm_add_memory */
+	ps3_mm_region_create(&map.r1, map.total - map.rm.size);
+
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+}
+
+/**
+ * ps3_mm_shutdown - final cleanup of address space
+ */
+
+void ps3_mm_shutdown(void)
+{
+	ps3_mm_region_destroy(&map.r1);
+	map.total = map.rm.size;
+}
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
new file mode 100644
index 000000000000..58358305dc10
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -0,0 +1,259 @@
+/*
+ *  PS3 'Other OS' area data.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/io.h>
+
+#include <asm/lmb.h>
+#include <asm/ps3.h>
+
+#include "platform.h"
+
+enum {
+	OS_AREA_SEGMENT_SIZE = 0X200,
+};
+
+enum {
+	HEADER_LDR_FORMAT_RAW = 0,
+	HEADER_LDR_FORMAT_GZIP = 1,
+};
+
+/**
+ * struct os_area_header - os area header segment.
+ * @magic_num: Always 'cell_ext_os_area'.
+ * @hdr_version: Header format version number.
+ * @os_area_offset: Starting segment number of os image area.
+ * @ldr_area_offset: Starting segment number of bootloader image area.
+ * @ldr_format: HEADER_LDR_FORMAT flag.
+ * @ldr_size: Size of bootloader image in bytes.
+ *
+ * Note that the docs refer to area offsets.  These are offsets in units of
+ * segments from the start of the os area (top of the header).  These are
+ * better thought of as segment numbers.  The os area of the os area is
+ * reserved for the os image.
+ */
+
+struct os_area_header {
+	s8 magic_num[16];
+	u32 hdr_version;
+	u32 os_area_offset;
+	u32 ldr_area_offset;
+	u32 _reserved_1;
+	u32 ldr_format;
+	u32 ldr_size;
+	u32 _reserved_2[6];
+} __attribute__ ((packed));
+
+enum {
+	PARAM_BOOT_FLAG_GAME_OS = 0,
+	PARAM_BOOT_FLAG_OTHER_OS = 1,
+};
+
+enum {
+	PARAM_AV_MULTI_OUT_NTSC = 0,
+	PARAM_AV_MULTI_OUT_PAL_RGB = 1,
+	PARAM_AV_MULTI_OUT_PAL_YCBCR = 2,
+	PARAM_AV_MULTI_OUT_SECAM = 3,
+};
+
+enum {
+	PARAM_CTRL_BUTTON_O_IS_YES = 0,
+	PARAM_CTRL_BUTTON_X_IS_YES = 1,
+};
+
+/**
+ * struct os_area_params - os area params segment.
+ * @boot_flag: User preference of operating system, PARAM_BOOT_FLAG flag.
+ * @num_params: Number of params in this (params) segment.
+ * @rtc_diff: Difference in seconds between 1970 and the ps3 rtc value.
+ * @av_multi_out: User preference of AV output, PARAM_AV_MULTI_OUT flag.
+ * @ctrl_button: User preference of controller button config, PARAM_CTRL_BUTTON
+ *	flag.
+ * @static_ip_addr: User preference of static IP address.
+ * @network_mask: User preference of static network mask.
+ * @default_gateway: User preference of static default gateway.
+ * @dns_primary: User preference of static primary dns server.
+ * @dns_secondary: User preference of static secondary dns server.
+ *
+ * User preference of zero for static_ip_addr means use dhcp.
+ */
+
+struct os_area_params {
+	u32 boot_flag;
+	u32 _reserved_1[3];
+	u32 num_params;
+	u32 _reserved_2[3];
+	/* param 0 */
+	s64 rtc_diff;
+	u8 av_multi_out;
+	u8 ctrl_button;
+	u8 _reserved_3[6];
+	/* param 1 */
+	u8 static_ip_addr[4];
+	u8 network_mask[4];
+	u8 default_gateway[4];
+	u8 _reserved_4[4];
+	/* param 2 */
+	u8 dns_primary[4];
+	u8 dns_secondary[4];
+	u8 _reserved_5[8];
+} __attribute__ ((packed));
+
+/**
+ * struct saved_params - Static working copies of data from the 'Other OS' area.
+ *
+ * For the convinience of the guest, the HV makes a copy of the 'Other OS' area
+ * in flash to a high address in the boot memory region and then puts that RAM
+ * address and the byte count into the repository for retreval by the guest.
+ * We copy the data we want into a static variable and allow the memory setup
+ * by the HV to be claimed by the lmb manager.
+ */
+
+struct saved_params {
+	/* param 0 */
+	s64 rtc_diff;
+	unsigned int av_multi_out;
+	unsigned int ctrl_button;
+	/* param 1 */
+	u8 static_ip_addr[4];
+	u8 network_mask[4];
+	u8 default_gateway[4];
+	/* param 2 */
+	u8 dns_primary[4];
+	u8 dns_secondary[4];
+} static saved_params;
+
+#define dump_header(_a) _dump_header(_a, __func__, __LINE__)
+static void _dump_header(const struct os_area_header __iomem *h, const char* func,
+	int line)
+{
+	pr_debug("%s:%d: h.magic_num:         '%s'\n", func, line,
+		h->magic_num);
+	pr_debug("%s:%d: h.hdr_version:       %u\n", func, line,
+		h->hdr_version);
+	pr_debug("%s:%d: h.os_area_offset:   %u\n", func, line,
+		h->os_area_offset);
+	pr_debug("%s:%d: h.ldr_area_offset: %u\n", func, line,
+		h->ldr_area_offset);
+	pr_debug("%s:%d: h.ldr_format:        %u\n", func, line,
+		h->ldr_format);
+	pr_debug("%s:%d: h.ldr_size:          %xh\n", func, line,
+		h->ldr_size);
+}
+
+#define dump_params(_a) _dump_params(_a, __func__, __LINE__)
+static void _dump_params(const struct os_area_params __iomem *p, const char* func,
+	int line)
+{
+	pr_debug("%s:%d: p.boot_flag:       %u\n", func, line, p->boot_flag);
+	pr_debug("%s:%d: p.num_params:      %u\n", func, line, p->num_params);
+	pr_debug("%s:%d: p.rtc_diff         %ld\n", func, line, p->rtc_diff);
+	pr_debug("%s:%d: p.av_multi_out     %u\n", func, line, p->av_multi_out);
+	pr_debug("%s:%d: p.ctrl_button:     %u\n", func, line, p->ctrl_button);
+	pr_debug("%s:%d: p.static_ip_addr:  %u.%u.%u.%u\n", func, line,
+		p->static_ip_addr[0], p->static_ip_addr[1],
+		p->static_ip_addr[2], p->static_ip_addr[3]);
+	pr_debug("%s:%d: p.network_mask:    %u.%u.%u.%u\n", func, line,
+		p->network_mask[0], p->network_mask[1],
+		p->network_mask[2], p->network_mask[3]);
+	pr_debug("%s:%d: p.default_gateway: %u.%u.%u.%u\n", func, line,
+		p->default_gateway[0], p->default_gateway[1],
+		p->default_gateway[2], p->default_gateway[3]);
+	pr_debug("%s:%d: p.dns_primary:     %u.%u.%u.%u\n", func, line,
+		p->dns_primary[0], p->dns_primary[1],
+		p->dns_primary[2], p->dns_primary[3]);
+	pr_debug("%s:%d: p.dns_secondary:   %u.%u.%u.%u\n", func, line,
+		p->dns_secondary[0], p->dns_secondary[1],
+		p->dns_secondary[2], p->dns_secondary[3]);
+}
+
+static int __init verify_header(const struct os_area_header *header)
+{
+	if (memcmp(header->magic_num, "cell_ext_os_area", 16)) {
+		pr_debug("%s:%d magic_num failed\n", __func__, __LINE__);
+		return -1;
+	}
+
+	if (header->hdr_version < 1) {
+		pr_debug("%s:%d hdr_version failed\n", __func__, __LINE__);
+		return -1;
+	}
+
+	if (header->os_area_offset > header->ldr_area_offset) {
+		pr_debug("%s:%d offsets failed\n", __func__, __LINE__);
+		return -1;
+	}
+
+	return 0;
+}
+
+int __init ps3_os_area_init(void)
+{
+	int result;
+	u64 lpar_addr;
+	unsigned int size;
+	struct os_area_header *header;
+	struct os_area_params *params;
+
+	result = ps3_repository_read_boot_dat_info(&lpar_addr, &size);
+
+	if (result) {
+		pr_debug("%s:%d ps3_repository_read_boot_dat_info failed\n",
+			__func__, __LINE__);
+		return result;
+	}
+
+	header = (struct os_area_header *)__va(lpar_addr);
+	params = (struct os_area_params *)__va(lpar_addr + OS_AREA_SEGMENT_SIZE);
+
+	result = verify_header(header);
+
+	if (result) {
+		pr_debug("%s:%d verify_header failed\n", __func__, __LINE__);
+		dump_header(header);
+		return -EIO;
+	}
+
+	dump_header(header);
+	dump_params(params);
+
+	saved_params.rtc_diff = params->rtc_diff;
+	saved_params.av_multi_out = params->av_multi_out;
+	saved_params.ctrl_button = params->ctrl_button;
+	memcpy(saved_params.static_ip_addr, params->static_ip_addr, 4);
+	memcpy(saved_params.network_mask, params->network_mask, 4);
+	memcpy(saved_params.default_gateway, params->default_gateway, 4);
+	memcpy(saved_params.dns_secondary, params->dns_secondary, 4);
+
+	return result;
+}
+
+/**
+ * ps3_os_area_rtc_diff - Returns the ps3 rtc diff value.
+ *
+ * The ps3 rtc maintains a value that approximates seconds since
+ * 2000-01-01 00:00:00 UTC.  Returns the exact number of seconds from 1970 to
+ * 2000 when saved_params.rtc_diff has not been properly set up.
+ */
+
+u64 ps3_os_area_rtc_diff(void)
+{
+	return saved_params.rtc_diff ? saved_params.rtc_diff : 946684800UL;
+}
diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h
new file mode 100644
index 000000000000..23b111bea9d0
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/platform.h
@@ -0,0 +1,68 @@
+/*
+ *  PS3 platform declarations.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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
+ */
+
+#if !defined(_PS3_PLATFORM_H)
+#define _PS3_PLATFORM_H
+
+#include <linux/rtc.h>
+
+/* htab */
+
+void __init ps3_hpte_init(unsigned long htab_size);
+void __init ps3_map_htab(void);
+
+/* mm */
+
+void __init ps3_mm_init(void);
+void __init ps3_mm_vas_create(unsigned long* htab_size);
+void ps3_mm_vas_destroy(void);
+void ps3_mm_shutdown(void);
+
+/* irq */
+
+void ps3_init_IRQ(void);
+void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq);
+
+/* smp */
+
+void smp_init_ps3(void);
+void ps3_smp_cleanup_cpu(int cpu);
+
+/* time */
+
+void __init ps3_calibrate_decr(void);
+unsigned long __init ps3_get_boot_time(void);
+void ps3_get_rtc_time(struct rtc_time *time);
+int ps3_set_rtc_time(struct rtc_time *time);
+
+/* os area */
+
+int __init ps3_os_area_init(void);
+u64 ps3_os_area_rtc_diff(void);
+
+/* spu */
+
+#if defined(CONFIG_SPU_BASE)
+void ps3_spu_set_platform (void);
+#else
+static inline void ps3_spu_set_platform (void) {}
+#endif
+
+#endif
diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
new file mode 100644
index 000000000000..273a0d621bdd
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/repository.c
@@ -0,0 +1,840 @@
+/*
+ *  PS3 repository routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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 <asm/ps3.h>
+#include <asm/lv1call.h>
+
+enum ps3_vendor_id {
+	PS3_VENDOR_ID_NONE = 0,
+	PS3_VENDOR_ID_SONY = 0x8000000000000000UL,
+};
+
+enum ps3_lpar_id {
+	PS3_LPAR_ID_CURRENT = 0,
+	PS3_LPAR_ID_PME = 1,
+};
+
+#define dump_field(_a, _b) _dump_field(_a, _b, __func__, __LINE__)
+static void _dump_field(const char *hdr, u64 n, const char* func, int line)
+{
+#if defined(DEBUG)
+	char s[16];
+	const char *const in = (const char *)&n;
+	unsigned int i;
+
+	for (i = 0; i < 8; i++)
+		s[i] = (in[i] <= 126 && in[i] >= 32) ? in[i] : '.';
+	s[i] = 0;
+
+	pr_debug("%s:%d: %s%016lx : %s\n", func, line, hdr, n, s);
+#endif
+}
+
+#define dump_node_name(_a, _b, _c, _d, _e) \
+	_dump_node_name(_a, _b, _c, _d, _e, __func__, __LINE__)
+static void _dump_node_name (unsigned int lpar_id, u64 n1, u64 n2, u64 n3,
+	u64 n4, const char* func, int line)
+{
+	pr_debug("%s:%d: lpar: %u\n", func, line, lpar_id);
+	_dump_field("n1: ", n1, func, line);
+	_dump_field("n2: ", n2, func, line);
+	_dump_field("n3: ", n3, func, line);
+	_dump_field("n4: ", n4, func, line);
+}
+
+#define dump_node(_a, _b, _c, _d, _e, _f, _g) \
+	_dump_node(_a, _b, _c, _d, _e, _f, _g, __func__, __LINE__)
+static void _dump_node(unsigned int lpar_id, u64 n1, u64 n2, u64 n3, u64 n4,
+	u64 v1, u64 v2, const char* func, int line)
+{
+	pr_debug("%s:%d: lpar: %u\n", func, line, lpar_id);
+	_dump_field("n1: ", n1, func, line);
+	_dump_field("n2: ", n2, func, line);
+	_dump_field("n3: ", n3, func, line);
+	_dump_field("n4: ", n4, func, line);
+	pr_debug("%s:%d: v1: %016lx\n", func, line, v1);
+	pr_debug("%s:%d: v2: %016lx\n", func, line, v2);
+}
+
+/**
+ * make_first_field - Make the first field of a repository node name.
+ * @text: Text portion of the field.
+ * @index: Numeric index portion of the field.  Use zero for 'don't care'.
+ *
+ * This routine sets the vendor id to zero (non-vendor specific).
+ * Returns field value.
+ */
+
+static u64 make_first_field(const char *text, u64 index)
+{
+	u64 n;
+
+	strncpy((char *)&n, text, 8);
+	return PS3_VENDOR_ID_NONE + (n >> 32) + index;
+}
+
+/**
+ * make_field - Make subsequent fields of a repository node name.
+ * @text: Text portion of the field.  Use "" for 'don't care'.
+ * @index: Numeric index portion of the field.  Use zero for 'don't care'.
+ *
+ * Returns field value.
+ */
+
+static u64 make_field(const char *text, u64 index)
+{
+	u64 n;
+
+	strncpy((char *)&n, text, 8);
+	return n + index;
+}
+
+/**
+ * read_node - Read a repository node from raw fields.
+ * @n1: First field of node name.
+ * @n2: Second field of node name.  Use zero for 'don't care'.
+ * @n3: Third field of node name.  Use zero for 'don't care'.
+ * @n4: Fourth field of node name.  Use zero for 'don't care'.
+ * @v1: First repository value (high word).
+ * @v2: Second repository value (low word).  Optional parameter, use zero
+ *      for 'don't care'.
+ */
+
+static int read_node(unsigned int lpar_id, u64 n1, u64 n2, u64 n3, u64 n4,
+	u64 *_v1, u64 *_v2)
+{
+	int result;
+	u64 v1;
+	u64 v2;
+
+	if (lpar_id == PS3_LPAR_ID_CURRENT) {
+		u64 id;
+		lv1_get_logical_partition_id(&id);
+		lpar_id = id;
+	}
+
+	result = lv1_get_repository_node_value(lpar_id, n1, n2, n3, n4, &v1,
+		&v2);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_get_repository_node_value failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		dump_node_name(lpar_id, n1, n2, n3, n4);
+		return result;
+	}
+
+	dump_node(lpar_id, n1, n2, n3, n4, v1, v2);
+
+	if (_v1)
+		*_v1 = v1;
+	if (_v2)
+		*_v2 = v2;
+
+	if (v1 && !_v1)
+		pr_debug("%s:%d: warning: discarding non-zero v1: %016lx\n",
+			__func__, __LINE__, v1);
+	if (v2 && !_v2)
+		pr_debug("%s:%d: warning: discarding non-zero v2: %016lx\n",
+			__func__, __LINE__, v2);
+
+	return result;
+}
+
+int ps3_repository_read_bus_str(unsigned int bus_index, const char *bus_str,
+	u64 *value)
+{
+	return read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field(bus_str, 0),
+		0, 0,
+		value, 0);
+}
+
+int ps3_repository_read_bus_id(unsigned int bus_index, unsigned int *bus_id)
+{
+	int result;
+	u64 v1;
+	u64 v2; /* unused */
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("id", 0),
+		0, 0,
+		&v1, &v2);
+	*bus_id = v1;
+	return result;
+}
+
+int ps3_repository_read_bus_type(unsigned int bus_index,
+	enum ps3_bus_type *bus_type)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("type", 0),
+		0, 0,
+		&v1, 0);
+	*bus_type = v1;
+	return result;
+}
+
+int ps3_repository_read_bus_num_dev(unsigned int bus_index,
+	unsigned int *num_dev)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("num_dev", 0),
+		0, 0,
+		&v1, 0);
+	*num_dev = v1;
+	return result;
+}
+
+int ps3_repository_read_dev_str(unsigned int bus_index,
+	unsigned int dev_index, const char *dev_str, u64 *value)
+{
+	return read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("dev", dev_index),
+		make_field(dev_str, 0),
+		0,
+		value, 0);
+}
+
+int ps3_repository_read_dev_id(unsigned int bus_index, unsigned int dev_index,
+	unsigned int *dev_id)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("dev", dev_index),
+		make_field("id", 0),
+		0,
+		&v1, 0);
+	*dev_id = v1;
+	return result;
+}
+
+int ps3_repository_read_dev_type(unsigned int bus_index,
+	unsigned int dev_index, enum ps3_dev_type *dev_type)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("dev", dev_index),
+		make_field("type", 0),
+		0,
+		&v1, 0);
+	*dev_type = v1;
+	return result;
+}
+
+int ps3_repository_read_dev_intr(unsigned int bus_index,
+	unsigned int dev_index, unsigned int intr_index,
+	unsigned int *intr_type, unsigned int* interrupt_id)
+{
+	int result;
+	u64 v1;
+	u64 v2;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("dev", dev_index),
+		make_field("intr", intr_index),
+		0,
+		&v1, &v2);
+	*intr_type = v1;
+	*interrupt_id = v2;
+	return result;
+}
+
+int ps3_repository_read_dev_reg_type(unsigned int bus_index,
+	unsigned int dev_index, unsigned int reg_index, unsigned int *reg_type)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("dev", dev_index),
+		make_field("reg", reg_index),
+		make_field("type", 0),
+		&v1, 0);
+	*reg_type = v1;
+	return result;
+}
+
+int ps3_repository_read_dev_reg_addr(unsigned int bus_index,
+	unsigned int dev_index, unsigned int reg_index, u64 *bus_addr, u64 *len)
+{
+	return read_node(PS3_LPAR_ID_PME,
+		make_first_field("bus", bus_index),
+		make_field("dev", dev_index),
+		make_field("reg", reg_index),
+		make_field("data", 0),
+		bus_addr, len);
+}
+
+int ps3_repository_read_dev_reg(unsigned int bus_index,
+	unsigned int dev_index, unsigned int reg_index, unsigned int *reg_type,
+	u64 *bus_addr, u64 *len)
+{
+	int result = ps3_repository_read_dev_reg_type(bus_index, dev_index,
+		reg_index, reg_type);
+	return result ? result
+		: ps3_repository_read_dev_reg_addr(bus_index, dev_index,
+		reg_index, bus_addr, len);
+}
+
+#if defined(DEBUG)
+int ps3_repository_dump_resource_info(unsigned int bus_index,
+	unsigned int dev_index)
+{
+	int result = 0;
+	unsigned int res_index;
+
+	pr_debug(" -> %s:%d: (%u:%u)\n", __func__, __LINE__,
+		bus_index, dev_index);
+
+	for (res_index = 0; res_index < 10; res_index++) {
+		enum ps3_interrupt_type intr_type;
+		unsigned int interrupt_id;
+
+		result = ps3_repository_read_dev_intr(bus_index, dev_index,
+			res_index, &intr_type, &interrupt_id);
+
+		if (result) {
+			if (result !=  LV1_NO_ENTRY)
+				pr_debug("%s:%d ps3_repository_read_dev_intr"
+					" (%u:%u) failed\n", __func__, __LINE__,
+					bus_index, dev_index);
+			break;
+		}
+
+		pr_debug("%s:%d (%u:%u) intr_type %u, interrupt_id %u\n",
+			__func__, __LINE__, bus_index, dev_index, intr_type,
+			interrupt_id);
+	}
+
+	for (res_index = 0; res_index < 10; res_index++) {
+		enum ps3_region_type reg_type;
+		u64 bus_addr;
+		u64 len;
+
+		result = ps3_repository_read_dev_reg(bus_index, dev_index,
+			res_index, &reg_type, &bus_addr, &len);
+
+		if (result) {
+			if (result !=  LV1_NO_ENTRY)
+				pr_debug("%s:%d ps3_repository_read_dev_reg"
+					" (%u:%u) failed\n", __func__, __LINE__,
+					bus_index, dev_index);
+			break;
+		}
+
+		pr_debug("%s:%d (%u:%u) reg_type %u, bus_addr %lxh, len %lxh\n",
+			__func__, __LINE__, bus_index, dev_index, reg_type,
+			bus_addr, len);
+	}
+
+	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+
+static int dump_device_info(unsigned int bus_index, unsigned int num_dev)
+{
+	int result = 0;
+	unsigned int dev_index;
+
+	pr_debug(" -> %s:%d: bus_%u\n", __func__, __LINE__, bus_index);
+
+	for (dev_index = 0; dev_index < num_dev; dev_index++) {
+		enum ps3_dev_type dev_type;
+		unsigned int dev_id;
+
+		result = ps3_repository_read_dev_type(bus_index, dev_index,
+			&dev_type);
+
+		if (result) {
+			pr_debug("%s:%d ps3_repository_read_dev_type"
+				" (%u:%u) failed\n", __func__, __LINE__,
+				bus_index, dev_index);
+			break;
+		}
+
+		result = ps3_repository_read_dev_id(bus_index, dev_index,
+			&dev_id);
+
+		if (result) {
+			pr_debug("%s:%d ps3_repository_read_dev_id"
+				" (%u:%u) failed\n", __func__, __LINE__,
+				bus_index, dev_index);
+			continue;
+		}
+
+		pr_debug("%s:%d  (%u:%u): dev_type %u, dev_id %u\n", __func__,
+			__LINE__, bus_index, dev_index, dev_type, dev_id);
+
+		ps3_repository_dump_resource_info(bus_index, dev_index);
+	}
+
+	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+
+int ps3_repository_dump_bus_info(void)
+{
+	int result = 0;
+	unsigned int bus_index;
+
+	pr_debug(" -> %s:%d\n", __func__, __LINE__);
+
+	for (bus_index = 0; bus_index < 10; bus_index++) {
+		enum ps3_bus_type bus_type;
+		unsigned int bus_id;
+		unsigned int num_dev;
+
+		result = ps3_repository_read_bus_type(bus_index, &bus_type);
+
+		if (result) {
+			pr_debug("%s:%d read_bus_type(%u) failed\n",
+				__func__, __LINE__, bus_index);
+			break;
+		}
+
+		result = ps3_repository_read_bus_id(bus_index, &bus_id);
+
+		if (result) {
+			pr_debug("%s:%d read_bus_id(%u) failed\n",
+				__func__, __LINE__, bus_index);
+			continue;
+		}
+
+		if (bus_index != bus_id)
+			pr_debug("%s:%d bus_index != bus_id\n",
+				__func__, __LINE__);
+
+		result = ps3_repository_read_bus_num_dev(bus_index, &num_dev);
+
+		if (result) {
+			pr_debug("%s:%d read_bus_num_dev(%u) failed\n",
+				__func__, __LINE__, bus_index);
+			continue;
+		}
+
+		pr_debug("%s:%d bus_%u: bus_type %u, bus_id %u, num_dev %u\n",
+			__func__, __LINE__, bus_index, bus_type, bus_id,
+			num_dev);
+
+		dump_device_info(bus_index, num_dev);
+	}
+
+	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return result;
+}
+#endif /* defined(DEBUG) */
+
+static int find_device(unsigned int bus_index, unsigned int num_dev,
+	unsigned int start_dev_index, enum ps3_dev_type dev_type,
+	struct ps3_repository_device *dev)
+{
+	int result = 0;
+	unsigned int dev_index;
+
+	pr_debug("%s:%d: find dev_type %u\n", __func__, __LINE__, dev_type);
+
+	dev->dev_index = UINT_MAX;
+
+	for (dev_index = start_dev_index; dev_index < num_dev; dev_index++) {
+		enum ps3_dev_type x;
+
+		result = ps3_repository_read_dev_type(bus_index, dev_index,
+			&x);
+
+		if (result) {
+			pr_debug("%s:%d read_dev_type failed\n",
+				__func__, __LINE__);
+			return result;
+		}
+
+		if (x == dev_type)
+			break;
+	}
+
+	BUG_ON(dev_index == num_dev);
+
+	pr_debug("%s:%d: found dev_type %u at dev_index %u\n",
+		__func__, __LINE__, dev_type, dev_index);
+
+	result = ps3_repository_read_dev_id(bus_index, dev_index,
+		&dev->did.dev_id);
+
+	if (result) {
+		pr_debug("%s:%d read_dev_id failed\n",
+			__func__, __LINE__);
+		return result;
+	}
+
+	dev->dev_index = dev_index;
+
+	pr_debug("%s:%d found: dev_id %u\n", __func__, __LINE__,
+		dev->did.dev_id);
+
+	return result;
+}
+
+int ps3_repository_find_device (enum ps3_bus_type bus_type,
+	enum ps3_dev_type dev_type,
+	const struct ps3_repository_device *start_dev,
+	struct ps3_repository_device *dev)
+{
+	int result = 0;
+	unsigned int bus_index;
+	unsigned int num_dev;
+
+	pr_debug("%s:%d: find bus_type %u, dev_type %u\n", __func__, __LINE__,
+		bus_type, dev_type);
+
+	dev->bus_index = UINT_MAX;
+
+	for (bus_index = start_dev ? start_dev->bus_index : 0; bus_index < 10;
+		bus_index++) {
+		enum ps3_bus_type x;
+
+		result = ps3_repository_read_bus_type(bus_index, &x);
+
+		if (result) {
+			pr_debug("%s:%d read_bus_type failed\n",
+				__func__, __LINE__);
+			return result;
+		}
+		if (x == bus_type)
+			break;
+	}
+
+	BUG_ON(bus_index == 10);
+
+	pr_debug("%s:%d: found bus_type %u at bus_index %u\n",
+		__func__, __LINE__, bus_type, bus_index);
+
+	result = ps3_repository_read_bus_num_dev(bus_index, &num_dev);
+
+	if (result) {
+		pr_debug("%s:%d read_bus_num_dev failed\n",
+			__func__, __LINE__);
+		return result;
+	}
+
+	result = find_device(bus_index, num_dev, start_dev
+		? start_dev->dev_index + 1 : 0, dev_type, dev);
+
+	if (result) {
+		pr_debug("%s:%d get_did failed\n", __func__, __LINE__);
+		return result;
+	}
+
+	result = ps3_repository_read_bus_id(bus_index, &dev->did.bus_id);
+
+	if (result) {
+		pr_debug("%s:%d read_bus_id failed\n",
+			__func__, __LINE__);
+		return result;
+	}
+
+	dev->bus_index = bus_index;
+
+	pr_debug("%s:%d found: bus_id %u, dev_id %u\n",
+		__func__, __LINE__, dev->did.bus_id, dev->did.dev_id);
+
+	return result;
+}
+
+int ps3_repository_find_interrupt(const struct ps3_repository_device *dev,
+	enum ps3_interrupt_type intr_type, unsigned int *interrupt_id)
+{
+	int result = 0;
+	unsigned int res_index;
+
+	pr_debug("%s:%d: find intr_type %u\n", __func__, __LINE__, intr_type);
+
+	*interrupt_id = UINT_MAX;
+
+	for (res_index = 0; res_index < 10; res_index++) {
+		enum ps3_interrupt_type t;
+		unsigned int id;
+
+		result = ps3_repository_read_dev_intr(dev->bus_index,
+			dev->dev_index, res_index, &t, &id);
+
+		if (result) {
+			pr_debug("%s:%d read_dev_intr failed\n",
+				__func__, __LINE__);
+			return result;
+		}
+
+		if (t == intr_type) {
+			*interrupt_id = id;
+			break;
+		}
+	}
+
+	BUG_ON(res_index == 10);
+
+	pr_debug("%s:%d: found intr_type %u at res_index %u\n",
+		__func__, __LINE__, intr_type, res_index);
+
+	return result;
+}
+
+int ps3_repository_find_region(const struct ps3_repository_device *dev,
+	enum ps3_region_type reg_type, u64 *bus_addr, u64 *len)
+{
+	int result = 0;
+	unsigned int res_index;
+
+	pr_debug("%s:%d: find reg_type %u\n", __func__, __LINE__, reg_type);
+
+	*bus_addr = *len = 0;
+
+	for (res_index = 0; res_index < 10; res_index++) {
+		enum ps3_region_type t;
+		u64 a;
+		u64 l;
+
+		result = ps3_repository_read_dev_reg(dev->bus_index,
+			dev->dev_index, res_index, &t, &a, &l);
+
+		if (result) {
+			pr_debug("%s:%d read_dev_reg failed\n",
+				__func__, __LINE__);
+			return result;
+		}
+
+		if (t == reg_type) {
+			*bus_addr = a;
+			*len = l;
+			break;
+		}
+	}
+
+	BUG_ON(res_index == 10);
+
+	pr_debug("%s:%d: found reg_type %u at res_index %u\n",
+		__func__, __LINE__, reg_type, res_index);
+
+	return result;
+}
+
+int ps3_repository_read_rm_size(unsigned int ppe_id, u64 *rm_size)
+{
+	return read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("pu", 0),
+		ppe_id,
+		make_field("rm_size", 0),
+		rm_size, 0);
+}
+
+int ps3_repository_read_region_total(u64 *region_total)
+{
+	return read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("rgntotal", 0),
+		0, 0,
+		region_total, 0);
+}
+
+/**
+ * ps3_repository_read_mm_info - Read mm info for single pu system.
+ * @rm_base: Real mode memory base address.
+ * @rm_size: Real mode memory size.
+ * @region_total: Maximum memory region size.
+ */
+
+int ps3_repository_read_mm_info(u64 *rm_base, u64 *rm_size, u64 *region_total)
+{
+	int result;
+	u64 ppe_id;
+
+	lv1_get_logical_ppe_id(&ppe_id);
+	*rm_base = 0;
+	result = ps3_repository_read_rm_size(ppe_id, rm_size);
+	return result ? result
+		: ps3_repository_read_region_total(region_total);
+}
+
+/**
+ * ps3_repository_read_num_spu_reserved - Number of physical spus reserved.
+ * @num_spu: Number of physical spus.
+ */
+
+int ps3_repository_read_num_spu_reserved(unsigned int *num_spu_reserved)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("spun", 0),
+		0, 0,
+		&v1, 0);
+	*num_spu_reserved = v1;
+	return result;
+}
+
+/**
+ * ps3_repository_read_num_spu_resource_id - Number of spu resource reservations.
+ * @num_resource_id: Number of spu resource ids.
+ */
+
+int ps3_repository_read_num_spu_resource_id(unsigned int *num_resource_id)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("spursvn", 0),
+		0, 0,
+		&v1, 0);
+	*num_resource_id = v1;
+	return result;
+}
+
+/**
+ * ps3_repository_read_spu_resource_id - spu resource reservation id value.
+ * @res_index: Resource reservation index.
+ * @resource_type: Resource reservation type.
+ * @resource_id: Resource reservation id.
+ */
+
+int ps3_repository_read_spu_resource_id(unsigned int res_index,
+	enum ps3_spu_resource_type* resource_type, unsigned int *resource_id)
+{
+	int result;
+	u64 v1;
+	u64 v2;
+
+	result = read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("spursv", 0),
+		res_index,
+		0,
+		&v1, &v2);
+	*resource_type = v1;
+	*resource_id = v2;
+	return result;
+}
+
+int ps3_repository_read_boot_dat_address(u64 *address)
+{
+	return read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("boot_dat", 0),
+		make_field("address", 0),
+		0,
+		address, 0);
+}
+
+int ps3_repository_read_boot_dat_size(unsigned int *size)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_CURRENT,
+		make_first_field("bi", 0),
+		make_field("boot_dat", 0),
+		make_field("size", 0),
+		0,
+		&v1, 0);
+	*size = v1;
+	return result;
+}
+
+/**
+  * ps3_repository_read_boot_dat_info - Get address and size of cell_ext_os_area.
+  * address: lpar address of cell_ext_os_area
+  * @size: size of cell_ext_os_area
+  */
+
+int ps3_repository_read_boot_dat_info(u64 *lpar_addr, unsigned int *size)
+{
+	int result;
+
+	*size = 0;
+	result = ps3_repository_read_boot_dat_address(lpar_addr);
+	return result ? result
+		: ps3_repository_read_boot_dat_size(size);
+}
+
+int ps3_repository_read_num_be(unsigned int *num_be)
+{
+	int result;
+	u64 v1;
+
+	result = read_node(PS3_LPAR_ID_PME,
+		make_first_field("ben", 0),
+		0,
+		0,
+		0,
+		&v1, 0);
+	*num_be = v1;
+	return result;
+}
+
+int ps3_repository_read_be_node_id(unsigned int be_index, u64 *node_id)
+{
+	return read_node(PS3_LPAR_ID_PME,
+		make_first_field("be", be_index),
+		0,
+		0,
+		0,
+		node_id, 0);
+}
+
+int ps3_repository_read_tb_freq(u64 node_id, u64 *tb_freq)
+{
+	return read_node(PS3_LPAR_ID_PME,
+		make_first_field("be", 0),
+		node_id,
+		make_field("clock", 0),
+		0,
+		tb_freq, 0);
+}
+
+int ps3_repository_read_be_tb_freq(unsigned int be_index, u64 *tb_freq)
+{
+	int result;
+	u64 node_id;
+
+	*tb_freq = 0;
+	result = ps3_repository_read_be_node_id(0, &node_id);
+	return result ? result
+		: ps3_repository_read_tb_freq(node_id, tb_freq);
+}
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
new file mode 100644
index 000000000000..d8b5cadbe80e
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -0,0 +1,173 @@
+/*
+ *  PS3 platform setup routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/root_dev.h>
+#include <linux/console.h>
+#include <linux/kexec.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/time.h>
+#include <asm/iommu.h>
+#include <asm/udbg.h>
+#include <asm/prom.h>
+#include <asm/lv1call.h>
+
+#include "platform.h"
+
+#if defined(DEBUG)
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...) do{if(0)printk(fmt);}while(0)
+#endif
+
+static void ps3_show_cpuinfo(struct seq_file *m)
+{
+	seq_printf(m, "machine\t\t: %s\n", ppc_md.name);
+}
+
+static void ps3_power_save(void)
+{
+	/*
+	 * lv1_pause() puts the PPE thread into inactive state until an
+	 * irq on an unmasked plug exists. MSR[EE] has no effect.
+	 * flags: 0 = wake on DEC interrupt, 1 = ignore DEC interrupt.
+	 */
+
+	lv1_pause(0);
+}
+
+static void ps3_panic(char *str)
+{
+	DBG("%s:%d %s\n", __func__, __LINE__, str);
+
+#ifdef CONFIG_SMP
+	smp_send_stop();
+#endif
+	printk("\n");
+	printk("   System does not reboot automatically.\n");
+	printk("   Please press POWER button.\n");
+	printk("\n");
+
+	for (;;) ;
+}
+
+static void __init ps3_setup_arch(void)
+{
+	DBG(" -> %s:%d\n", __func__, __LINE__);
+
+	ps3_spu_set_platform();
+	ps3_map_htab();
+
+#ifdef CONFIG_SMP
+	smp_init_ps3();
+#endif
+
+#ifdef CONFIG_DUMMY_CONSOLE
+	conswitchp = &dummy_con;
+#endif
+
+	ppc_md.power_save = ps3_power_save;
+
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+}
+
+static void __init ps3_progress(char *s, unsigned short hex)
+{
+	printk("*** %04x : %s\n", hex, s ? s : "");
+}
+
+static int __init ps3_probe(void)
+{
+	unsigned long htab_size;
+	unsigned long dt_root;
+
+	DBG(" -> %s:%d\n", __func__, __LINE__);
+
+	dt_root = of_get_flat_dt_root();
+	if (!of_flat_dt_is_compatible(dt_root, "PS3"))
+		return 0;
+
+	powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
+
+	ps3_os_area_init();
+	ps3_mm_init();
+	ps3_mm_vas_create(&htab_size);
+	ps3_hpte_init(htab_size);
+
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+	return 1;
+}
+
+#if defined(CONFIG_KEXEC)
+static void ps3_kexec_cpu_down(int crash_shutdown, int secondary)
+{
+	DBG(" -> %s:%d\n", __func__, __LINE__);
+
+	if (secondary) {
+		int cpu;
+		for_each_online_cpu(cpu)
+			if (cpu)
+				ps3_smp_cleanup_cpu(cpu);
+	} else
+		ps3_smp_cleanup_cpu(0);
+
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+}
+
+static void ps3_machine_kexec(struct kimage *image)
+{
+	unsigned long ppe_id;
+
+	DBG(" -> %s:%d\n", __func__, __LINE__);
+
+	lv1_get_logical_ppe_id(&ppe_id);
+	lv1_configure_irq_state_bitmap(ppe_id, 0, 0);
+	ps3_mm_shutdown();
+	ps3_mm_vas_destroy();
+
+	default_machine_kexec(image);
+
+	DBG(" <- %s:%d\n", __func__, __LINE__);
+}
+#endif
+
+define_machine(ps3) {
+	.name				= "PS3",
+	.probe				= ps3_probe,
+	.setup_arch			= ps3_setup_arch,
+	.show_cpuinfo			= ps3_show_cpuinfo,
+	.init_IRQ			= ps3_init_IRQ,
+	.panic				= ps3_panic,
+	.get_boot_time			= ps3_get_boot_time,
+	.set_rtc_time			= ps3_set_rtc_time,
+	.get_rtc_time			= ps3_get_rtc_time,
+	.calibrate_decr			= ps3_calibrate_decr,
+	.progress			= ps3_progress,
+#if defined(CONFIG_KEXEC)
+	.kexec_cpu_down			= ps3_kexec_cpu_down,
+	.machine_kexec			= ps3_machine_kexec,
+	.machine_kexec_prepare		= default_machine_kexec_prepare,
+	.machine_crash_shutdown		= default_machine_crash_shutdown,
+#endif
+};
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
new file mode 100644
index 000000000000..11d2080607ed
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -0,0 +1,158 @@
+/*
+ *  PS3 SMP routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/smp.h>
+
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/ps3.h>
+
+#include "platform.h"
+
+#if defined(DEBUG)
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...) do{if(0)printk(fmt);}while(0)
+#endif
+
+static irqreturn_t ipi_function_handler(int irq, void *msg)
+{
+	smp_message_recv((int)(long)msg);
+	return IRQ_HANDLED;
+}
+
+/**
+  * virqs - a per cpu array of virqs for ipi use
+  */
+
+#define MSG_COUNT 4
+static DEFINE_PER_CPU(unsigned int, virqs[MSG_COUNT]);
+
+static const char *names[MSG_COUNT] = {
+	"ipi call",
+	"ipi reschedule",
+	"ipi migrate",
+	"ipi debug brk"
+};
+
+static void do_message_pass(int target, int msg)
+{
+	int result;
+	unsigned int virq;
+
+	if (msg >= MSG_COUNT) {
+		DBG("%s:%d: bad msg: %d\n", __func__, __LINE__, msg);
+		return;
+	}
+
+	virq = per_cpu(virqs, target)[msg];
+	result = ps3_send_event_locally(virq);
+
+	if (result)
+		DBG("%s:%d: ps3_send_event_locally(%d, %d) failed"
+			" (%d)\n", __func__, __LINE__, target, msg, result);
+}
+
+static void ps3_smp_message_pass(int target, int msg)
+{
+	int cpu;
+
+	if (target < NR_CPUS)
+		do_message_pass(target, msg);
+	else if (target == MSG_ALL_BUT_SELF) {
+		for_each_online_cpu(cpu)
+			if (cpu != smp_processor_id())
+				do_message_pass(cpu, msg);
+	} else {
+		for_each_online_cpu(cpu)
+			do_message_pass(cpu, msg);
+	}
+}
+
+static int ps3_smp_probe(void)
+{
+	return 2;
+}
+
+static void __init ps3_smp_setup_cpu(int cpu)
+{
+	int result;
+	unsigned int *virqs = per_cpu(virqs, cpu);
+	int i;
+
+	DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
+
+	/*
+	 * Check assumptions on virqs[] indexing. If this
+	 * check fails, then a different mapping of PPC_MSG_
+	 * to index needs to be setup.
+	 */
+
+	BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION  != 0);
+	BUILD_BUG_ON(PPC_MSG_RESCHEDULE     != 1);
+	BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK != 3);
+
+	for (i = 0; i < MSG_COUNT; i++) {
+		result = ps3_alloc_event_irq(&virqs[i]);
+
+		if (result)
+			continue;
+
+		DBG("%s:%d: (%d, %d) => virq %u\n",
+			__func__, __LINE__, cpu, i, virqs[i]);
+
+
+		request_irq(virqs[i], ipi_function_handler, IRQF_DISABLED,
+			names[i], (void*)(long)i);
+	}
+
+	ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
+
+	DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+}
+
+void ps3_smp_cleanup_cpu(int cpu)
+{
+	unsigned int *virqs = per_cpu(virqs, cpu);
+	int i;
+
+	DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
+	for (i = 0; i < MSG_COUNT; i++) {
+		ps3_free_event_irq(virqs[i]);
+		free_irq(virqs[i], (void*)(long)i);
+		virqs[i] = NO_IRQ;
+	}
+	DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+}
+
+static struct smp_ops_t ps3_smp_ops = {
+	.probe		= ps3_smp_probe,
+	.message_pass	= ps3_smp_message_pass,
+	.kick_cpu	= smp_generic_kick_cpu,
+	.setup_cpu	= ps3_smp_setup_cpu,
+};
+
+void smp_init_ps3(void)
+{
+	DBG(" -> %s\n", __func__);
+	smp_ops = &ps3_smp_ops;
+	DBG(" <- %s\n", __func__);
+}
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
new file mode 100644
index 000000000000..644532c3b7c4
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -0,0 +1,613 @@
+/*
+ *  PS3 Platform spu routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/init.h>
+#include <linux/mmzone.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+
+#include <asm/spu.h>
+#include <asm/spu_priv1.h>
+#include <asm/ps3.h>
+#include <asm/lv1call.h>
+
+/* spu_management_ops */
+
+/**
+ * enum spe_type - Type of spe to create.
+ * @spe_type_logical: Standard logical spe.
+ *
+ * For use with lv1_construct_logical_spe().  The current HV does not support
+ * any types other than those listed.
+ */
+
+enum spe_type {
+	SPE_TYPE_LOGICAL = 0,
+};
+
+/**
+ * struct spe_shadow - logical spe shadow register area.
+ *
+ * Read-only shadow of spe registers.
+ */
+
+struct spe_shadow {
+	u8 padding_0000[0x0140];
+	u64 int_status_class0_RW;       /* 0x0140 */
+	u64 int_status_class1_RW;       /* 0x0148 */
+	u64 int_status_class2_RW;       /* 0x0150 */
+	u8 padding_0158[0x0610-0x0158];
+	u64 mfc_dsisr_RW;               /* 0x0610 */
+	u8 padding_0618[0x0620-0x0618];
+	u64 mfc_dar_RW;                 /* 0x0620 */
+	u8 padding_0628[0x0800-0x0628];
+	u64 mfc_dsipr_R;                /* 0x0800 */
+	u8 padding_0808[0x0810-0x0808];
+	u64 mfc_lscrr_R;                /* 0x0810 */
+	u8 padding_0818[0x0c00-0x0818];
+	u64 mfc_cer_R;                  /* 0x0c00 */
+	u8 padding_0c08[0x0f00-0x0c08];
+	u64 spe_execution_status;       /* 0x0f00 */
+	u8 padding_0f08[0x1000-0x0f08];
+} __attribute__ ((packed));
+
+
+/**
+ * enum spe_ex_state - Logical spe execution state.
+ * @spe_ex_state_unexecutable: Uninitialized.
+ * @spe_ex_state_executable: Enabled, not ready.
+ * @spe_ex_state_executed: Ready for use.
+ *
+ * The execution state (status) of the logical spe as reported in
+ * struct spe_shadow:spe_execution_status.
+ */
+
+enum spe_ex_state {
+	SPE_EX_STATE_UNEXECUTABLE = 0,
+	SPE_EX_STATE_EXECUTABLE = 2,
+	SPE_EX_STATE_EXECUTED = 3,
+};
+
+/**
+ * struct priv1_cache - Cached values of priv1 registers.
+ * @masks[]: Array of cached spe interrupt masks, indexed by class.
+ * @sr1: Cached mfc_sr1 register.
+ * @tclass_id: Cached mfc_tclass_id register.
+ */
+
+struct priv1_cache {
+	u64 masks[3];
+	u64 sr1;
+	u64 tclass_id;
+};
+
+/**
+ * struct spu_pdata - Platform state variables.
+ * @spe_id: HV spe id returned by lv1_construct_logical_spe().
+ * @resource_id: HV spe resource id returned by
+ * 	ps3_repository_read_spe_resource_id().
+ * @priv2_addr: lpar address of spe priv2 area returned by
+ * 	lv1_construct_logical_spe().
+ * @shadow_addr: lpar address of spe register shadow area returned by
+ * 	lv1_construct_logical_spe().
+ * @shadow: Virtual (ioremap) address of spe register shadow area.
+ * @cache: Cached values of priv1 registers.
+ */
+
+struct spu_pdata {
+	u64 spe_id;
+	u64 resource_id;
+	u64 priv2_addr;
+	u64 shadow_addr;
+	struct spe_shadow __iomem *shadow;
+	struct priv1_cache cache;
+};
+
+static struct spu_pdata *spu_pdata(struct spu *spu)
+{
+	return spu->pdata;
+}
+
+#define dump_areas(_a, _b, _c, _d, _e) \
+	_dump_areas(_a, _b, _c, _d, _e, __func__, __LINE__)
+static void _dump_areas(unsigned int spe_id, unsigned long priv2,
+	unsigned long problem, unsigned long ls, unsigned long shadow,
+	const char* func, int line)
+{
+	pr_debug("%s:%d: spe_id:  %xh (%u)\n", func, line, spe_id, spe_id);
+	pr_debug("%s:%d: priv2:   %lxh\n", func, line, priv2);
+	pr_debug("%s:%d: problem: %lxh\n", func, line, problem);
+	pr_debug("%s:%d: ls:      %lxh\n", func, line, ls);
+	pr_debug("%s:%d: shadow:  %lxh\n", func, line, shadow);
+}
+
+static unsigned long get_vas_id(void)
+{
+	unsigned long id;
+
+	lv1_get_logical_ppe_id(&id);
+	lv1_get_virtual_address_space_id_of_ppe(id, &id);
+
+	return id;
+}
+
+static int __init construct_spu(struct spu *spu)
+{
+	int result;
+	unsigned long unused;
+
+	result = lv1_construct_logical_spe(PAGE_SHIFT, PAGE_SHIFT, PAGE_SHIFT,
+		PAGE_SHIFT, PAGE_SHIFT, get_vas_id(), SPE_TYPE_LOGICAL,
+		&spu_pdata(spu)->priv2_addr, &spu->problem_phys,
+		&spu->local_store_phys, &unused,
+		&spu_pdata(spu)->shadow_addr,
+		&spu_pdata(spu)->spe_id);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_construct_logical_spe failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		return result;
+	}
+
+	return result;
+}
+
+static int __init add_spu_pages(unsigned long start_addr, unsigned long size)
+{
+	int result;
+	unsigned long start_pfn;
+	unsigned long nr_pages;
+	struct pglist_data *pgdata;
+	struct zone *zone;
+
+	BUG_ON(!mem_init_done);
+
+	start_pfn = start_addr >> PAGE_SHIFT;
+	nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	pgdata = NODE_DATA(0);
+	zone = pgdata->node_zones;
+
+	result = __add_pages(zone, start_pfn, nr_pages);
+
+	if (result)
+		pr_debug("%s:%d: __add_pages failed: (%d)\n",
+			__func__, __LINE__, result);
+
+	return result;
+}
+
+static void spu_unmap(struct spu *spu)
+{
+	iounmap(spu->priv2);
+	iounmap(spu->problem);
+	iounmap((__force u8 __iomem *)spu->local_store);
+	iounmap(spu_pdata(spu)->shadow);
+}
+
+static int __init setup_areas(struct spu *spu)
+{
+	struct table {char* name; unsigned long addr; unsigned long size;};
+	int result;
+
+	/* setup pages */
+
+	result = add_spu_pages(spu->local_store_phys, LS_SIZE);
+	if (result)
+		goto fail_add;
+
+	result = add_spu_pages(spu->problem_phys, sizeof(struct spu_problem));
+	if (result)
+		goto fail_add;
+
+	/* ioremap */
+
+	spu_pdata(spu)->shadow = __ioremap(
+		spu_pdata(spu)->shadow_addr, sizeof(struct spe_shadow),
+		PAGE_READONLY | _PAGE_NO_CACHE | _PAGE_GUARDED);
+	if (!spu_pdata(spu)->shadow) {
+		pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__);
+		goto fail_ioremap;
+	}
+
+	spu->local_store = ioremap(spu->local_store_phys, LS_SIZE);
+	if (!spu->local_store) {
+		pr_debug("%s:%d: ioremap local_store failed\n",
+			__func__, __LINE__);
+		goto fail_ioremap;
+	}
+
+	spu->problem = ioremap(spu->problem_phys,
+		sizeof(struct spu_problem));
+	if (!spu->problem) {
+		pr_debug("%s:%d: ioremap problem failed\n", __func__, __LINE__);
+		goto fail_ioremap;
+	}
+
+	spu->priv2 = ioremap(spu_pdata(spu)->priv2_addr,
+		sizeof(struct spu_priv2));
+	if (!spu->priv2) {
+		pr_debug("%s:%d: ioremap priv2 failed\n", __func__, __LINE__);
+		goto fail_ioremap;
+	}
+
+	dump_areas(spu_pdata(spu)->spe_id, spu_pdata(spu)->priv2_addr,
+		spu->problem_phys, spu->local_store_phys,
+		spu_pdata(spu)->shadow_addr);
+	dump_areas(spu_pdata(spu)->spe_id, (unsigned long)spu->priv2,
+		(unsigned long)spu->problem, (unsigned long)spu->local_store,
+		(unsigned long)spu_pdata(spu)->shadow);
+
+	return 0;
+
+fail_ioremap:
+	spu_unmap(spu);
+fail_add:
+	return result;
+}
+
+static int __init setup_interrupts(struct spu *spu)
+{
+	int result;
+
+	result = ps3_alloc_spe_irq(spu_pdata(spu)->spe_id, 0,
+		&spu->irqs[0]);
+
+	if (result)
+		goto fail_alloc_0;
+
+	result = ps3_alloc_spe_irq(spu_pdata(spu)->spe_id, 1,
+		&spu->irqs[1]);
+
+	if (result)
+		goto fail_alloc_1;
+
+	result = ps3_alloc_spe_irq(spu_pdata(spu)->spe_id, 2,
+		&spu->irqs[2]);
+
+	if (result)
+		goto fail_alloc_2;
+
+	return result;
+
+fail_alloc_2:
+	ps3_free_spe_irq(spu->irqs[1]);
+fail_alloc_1:
+	ps3_free_spe_irq(spu->irqs[0]);
+fail_alloc_0:
+	spu->irqs[0] = spu->irqs[1] = spu->irqs[2] = NO_IRQ;
+	return result;
+}
+
+static int __init enable_spu(struct spu *spu)
+{
+	int result;
+
+	result = lv1_enable_logical_spe(spu_pdata(spu)->spe_id,
+		spu_pdata(spu)->resource_id);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_enable_logical_spe failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		goto fail_enable;
+	}
+
+	result = setup_areas(spu);
+
+	if (result)
+		goto fail_areas;
+
+	result = setup_interrupts(spu);
+
+	if (result)
+		goto fail_interrupts;
+
+	return 0;
+
+fail_interrupts:
+	spu_unmap(spu);
+fail_areas:
+	lv1_disable_logical_spe(spu_pdata(spu)->spe_id, 0);
+fail_enable:
+	return result;
+}
+
+static int ps3_destroy_spu(struct spu *spu)
+{
+	int result;
+
+	pr_debug("%s:%d spu_%d\n", __func__, __LINE__, spu->number);
+
+	result = lv1_disable_logical_spe(spu_pdata(spu)->spe_id, 0);
+	BUG_ON(result);
+
+	ps3_free_spe_irq(spu->irqs[2]);
+	ps3_free_spe_irq(spu->irqs[1]);
+	ps3_free_spe_irq(spu->irqs[0]);
+
+	spu->irqs[0] = spu->irqs[1] = spu->irqs[2] = NO_IRQ;
+
+	spu_unmap(spu);
+
+	result = lv1_destruct_logical_spe(spu_pdata(spu)->spe_id);
+	BUG_ON(result);
+
+	kfree(spu->pdata);
+	spu->pdata = NULL;
+
+	return 0;
+}
+
+static int __init ps3_create_spu(struct spu *spu, void *data)
+{
+	int result;
+
+	pr_debug("%s:%d spu_%d\n", __func__, __LINE__, spu->number);
+
+	spu->pdata = kzalloc(sizeof(struct spu_pdata),
+		GFP_KERNEL);
+
+	if (!spu->pdata) {
+		result = -ENOMEM;
+		goto fail_malloc;
+	}
+
+	spu_pdata(spu)->resource_id = (unsigned long)data;
+
+	/* Init cached reg values to HV defaults. */
+
+	spu_pdata(spu)->cache.sr1 = 0x33;
+
+	result = construct_spu(spu);
+
+	if (result)
+		goto fail_construct;
+
+	/* For now, just go ahead and enable it. */
+
+	result = enable_spu(spu);
+
+	if (result)
+		goto fail_enable;
+
+	/* Make sure the spu is in SPE_EX_STATE_EXECUTED. */
+
+	/* need something better here!!! */
+	while (in_be64(&spu_pdata(spu)->shadow->spe_execution_status)
+		!= SPE_EX_STATE_EXECUTED)
+		(void)0;
+
+	return result;
+
+fail_enable:
+fail_construct:
+	ps3_destroy_spu(spu);
+fail_malloc:
+	return result;
+}
+
+static int __init ps3_enumerate_spus(int (*fn)(void *data))
+{
+	int result;
+	unsigned int num_resource_id;
+	unsigned int i;
+
+	result = ps3_repository_read_num_spu_resource_id(&num_resource_id);
+
+	pr_debug("%s:%d: num_resource_id %u\n", __func__, __LINE__,
+		num_resource_id);
+
+	/*
+	 * For now, just create logical spus equal to the number
+	 * of physical spus reserved for the partition.
+	 */
+
+	for (i = 0; i < num_resource_id; i++) {
+		enum ps3_spu_resource_type resource_type;
+		unsigned int resource_id;
+
+		result = ps3_repository_read_spu_resource_id(i,
+			&resource_type, &resource_id);
+
+		if (result)
+			break;
+
+		if (resource_type == PS3_SPU_RESOURCE_TYPE_EXCLUSIVE) {
+			result = fn((void*)(unsigned long)resource_id);
+
+			if (result)
+				break;
+		}
+	}
+
+	if (result)
+		printk(KERN_WARNING "%s:%d: Error initializing spus\n",
+			__func__, __LINE__);
+
+	return result;
+}
+
+const struct spu_management_ops spu_management_ps3_ops = {
+	.enumerate_spus = ps3_enumerate_spus,
+	.create_spu = ps3_create_spu,
+	.destroy_spu = ps3_destroy_spu,
+};
+
+/* spu_priv1_ops */
+
+static void int_mask_and(struct spu *spu, int class, u64 mask)
+{
+	u64 old_mask;
+
+	/* are these serialized by caller??? */
+	old_mask = spu_int_mask_get(spu, class);
+	spu_int_mask_set(spu, class, old_mask & mask);
+}
+
+static void int_mask_or(struct spu *spu, int class, u64 mask)
+{
+	u64 old_mask;
+
+	old_mask = spu_int_mask_get(spu, class);
+	spu_int_mask_set(spu, class, old_mask | mask);
+}
+
+static void int_mask_set(struct spu *spu, int class, u64 mask)
+{
+	spu_pdata(spu)->cache.masks[class] = mask;
+	lv1_set_spe_interrupt_mask(spu_pdata(spu)->spe_id, class,
+		spu_pdata(spu)->cache.masks[class]);
+}
+
+static u64 int_mask_get(struct spu *spu, int class)
+{
+	return spu_pdata(spu)->cache.masks[class];
+}
+
+static void int_stat_clear(struct spu *spu, int class, u64 stat)
+{
+	/* Note that MFC_DSISR will be cleared when class1[MF] is set. */
+
+	lv1_clear_spe_interrupt_status(spu_pdata(spu)->spe_id, class,
+		stat, 0);
+}
+
+static u64 int_stat_get(struct spu *spu, int class)
+{
+	u64 stat;
+
+	lv1_get_spe_interrupt_status(spu_pdata(spu)->spe_id, class, &stat);
+	return stat;
+}
+
+static void cpu_affinity_set(struct spu *spu, int cpu)
+{
+	/* No support. */
+}
+
+static u64 mfc_dar_get(struct spu *spu)
+{
+	return in_be64(&spu_pdata(spu)->shadow->mfc_dar_RW);
+}
+
+static void mfc_dsisr_set(struct spu *spu, u64 dsisr)
+{
+	/* Nothing to do, cleared in int_stat_clear(). */
+}
+
+static u64 mfc_dsisr_get(struct spu *spu)
+{
+	return in_be64(&spu_pdata(spu)->shadow->mfc_dsisr_RW);
+}
+
+static void mfc_sdr_setup(struct spu *spu)
+{
+	/* Nothing to do. */
+}
+
+static void mfc_sr1_set(struct spu *spu, u64 sr1)
+{
+	/* Check bits allowed by HV. */
+
+	static const u64 allowed = ~(MFC_STATE1_LOCAL_STORAGE_DECODE_MASK
+		| MFC_STATE1_PROBLEM_STATE_MASK);
+
+	BUG_ON((sr1 & allowed) != (spu_pdata(spu)->cache.sr1 & allowed));
+
+	spu_pdata(spu)->cache.sr1 = sr1;
+	lv1_set_spe_privilege_state_area_1_register(
+		spu_pdata(spu)->spe_id,
+		offsetof(struct spu_priv1, mfc_sr1_RW),
+		spu_pdata(spu)->cache.sr1);
+}
+
+static u64 mfc_sr1_get(struct spu *spu)
+{
+	return spu_pdata(spu)->cache.sr1;
+}
+
+static void mfc_tclass_id_set(struct spu *spu, u64 tclass_id)
+{
+	spu_pdata(spu)->cache.tclass_id = tclass_id;
+	lv1_set_spe_privilege_state_area_1_register(
+		spu_pdata(spu)->spe_id,
+		offsetof(struct spu_priv1, mfc_tclass_id_RW),
+		spu_pdata(spu)->cache.tclass_id);
+}
+
+static u64 mfc_tclass_id_get(struct spu *spu)
+{
+	return spu_pdata(spu)->cache.tclass_id;
+}
+
+static void tlb_invalidate(struct spu *spu)
+{
+	/* Nothing to do. */
+}
+
+static void resource_allocation_groupID_set(struct spu *spu, u64 id)
+{
+	/* No support. */
+}
+
+static u64 resource_allocation_groupID_get(struct spu *spu)
+{
+	return 0; /* No support. */
+}
+
+static void resource_allocation_enable_set(struct spu *spu, u64 enable)
+{
+	/* No support. */
+}
+
+static u64 resource_allocation_enable_get(struct spu *spu)
+{
+	return 0; /* No support. */
+}
+
+const struct spu_priv1_ops spu_priv1_ps3_ops = {
+	.int_mask_and = int_mask_and,
+	.int_mask_or = int_mask_or,
+	.int_mask_set = int_mask_set,
+	.int_mask_get = int_mask_get,
+	.int_stat_clear = int_stat_clear,
+	.int_stat_get = int_stat_get,
+	.cpu_affinity_set = cpu_affinity_set,
+	.mfc_dar_get = mfc_dar_get,
+	.mfc_dsisr_set = mfc_dsisr_set,
+	.mfc_dsisr_get = mfc_dsisr_get,
+	.mfc_sdr_setup = mfc_sdr_setup,
+	.mfc_sr1_set = mfc_sr1_set,
+	.mfc_sr1_get = mfc_sr1_get,
+	.mfc_tclass_id_set = mfc_tclass_id_set,
+	.mfc_tclass_id_get = mfc_tclass_id_get,
+	.tlb_invalidate = tlb_invalidate,
+	.resource_allocation_groupID_set = resource_allocation_groupID_set,
+	.resource_allocation_groupID_get = resource_allocation_groupID_get,
+	.resource_allocation_enable_set = resource_allocation_enable_set,
+	.resource_allocation_enable_get = resource_allocation_enable_get,
+};
+
+void ps3_spu_set_platform(void)
+{
+	spu_priv1_ops = &spu_priv1_ps3_ops;
+	spu_management_ops = &spu_management_ps3_ops;
+}
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
new file mode 100644
index 000000000000..1bae8b19b363
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -0,0 +1,104 @@
+/*
+ *  PS3 time and rtc routines.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+
+#include <asm/rtc.h>
+#include <asm/lv1call.h>
+#include <asm/ps3.h>
+
+#include "platform.h"
+
+#define dump_tm(_a) _dump_tm(_a, __func__, __LINE__)
+static void _dump_tm(const struct rtc_time *tm, const char* func, int line)
+{
+	pr_debug("%s:%d tm_sec  %d\n", func, line, tm->tm_sec);
+	pr_debug("%s:%d tm_min  %d\n", func, line, tm->tm_min);
+	pr_debug("%s:%d tm_hour %d\n", func, line, tm->tm_hour);
+	pr_debug("%s:%d tm_mday %d\n", func, line, tm->tm_mday);
+	pr_debug("%s:%d tm_mon  %d\n", func, line, tm->tm_mon);
+	pr_debug("%s:%d tm_year %d\n", func, line, tm->tm_year);
+	pr_debug("%s:%d tm_wday %d\n", func, line, tm->tm_wday);
+}
+
+#define dump_time(_a) _dump_time(_a, __func__, __LINE__)
+static void __attribute__ ((unused)) _dump_time(int time, const char* func,
+	int line)
+{
+	struct rtc_time tm;
+
+	to_tm(time, &tm);
+
+	pr_debug("%s:%d time    %d\n", func, line, time);
+	_dump_tm(&tm, func, line);
+}
+
+/**
+ * rtc_shift - Difference in seconds between 1970 and the ps3 rtc value.
+ */
+
+static s64 rtc_shift;
+
+void __init ps3_calibrate_decr(void)
+{
+	int result;
+	u64 tmp;
+
+	result = ps3_repository_read_be_tb_freq(0, &tmp);
+	BUG_ON(result);
+
+	ppc_tb_freq = tmp;
+	ppc_proc_freq = ppc_tb_freq * 40;
+
+	rtc_shift = ps3_os_area_rtc_diff();
+}
+
+static u64 read_rtc(void)
+{
+	int result;
+	u64 rtc_val;
+	u64 tb_val;
+
+	result = lv1_get_rtc(&rtc_val, &tb_val);
+	BUG_ON(result);
+
+	return rtc_val;
+}
+
+int ps3_set_rtc_time(struct rtc_time *tm)
+{
+	u64 now = mktime(tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday,
+		tm->tm_hour, tm->tm_min, tm->tm_sec);
+
+	rtc_shift = now - read_rtc();
+	return 0;
+}
+
+void ps3_get_rtc_time(struct rtc_time *tm)
+{
+	to_tm(read_rtc() + rtc_shift, tm);
+	tm->tm_year -= 1900;
+	tm->tm_mon -= 1;
+}
+
+unsigned long __init ps3_get_boot_time(void)
+{
+	return read_rtc() + rtc_shift;
+}
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 556c279a789d..3c95392f4f41 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -309,7 +309,7 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 	tbl->it_size = size >> IOMMU_PAGE_SHIFT;
 }
 
-static void iommu_bus_setup_pSeries(struct pci_bus *bus)
+static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 {
 	struct device_node *dn;
 	struct iommu_table *tbl;
@@ -318,10 +318,9 @@ static void iommu_bus_setup_pSeries(struct pci_bus *bus)
 	struct pci_dn *pci;
 	int children;
 
-	DBG("iommu_bus_setup_pSeries, bus %p, bus->self %p\n", bus, bus->self);
-
 	dn = pci_bus_to_OF_node(bus);
-	pci = PCI_DN(dn);
+
+	DBG("pci_dma_bus_setup_pSeries: setting up bus %s\n", dn->full_name);
 
 	if (bus->self) {
 		/* This is not a root bus, any setup will be done for the
@@ -329,6 +328,7 @@ static void iommu_bus_setup_pSeries(struct pci_bus *bus)
 		 */
 		return;
 	}
+	pci = PCI_DN(dn);
 
 	/* Check if the ISA bus on the system is under
 	 * this PHB.
@@ -390,17 +390,17 @@ static void iommu_bus_setup_pSeries(struct pci_bus *bus)
 }
 
 
-static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
+static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 {
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
 	const void *dma_window = NULL;
 
-	DBG("iommu_bus_setup_pSeriesLP, bus %p, bus->self %p\n", bus, bus->self);
-
 	dn = pci_bus_to_OF_node(bus);
 
+	DBG("pci_dma_bus_setup_pSeriesLP: setting up bus %s\n", dn->full_name);
+
 	/* Find nearest ibm,dma-window, walking up the device tree */
 	for (pdn = dn; pdn != NULL; pdn = pdn->parent) {
 		dma_window = get_property(pdn, "ibm,dma-window", NULL);
@@ -409,11 +409,15 @@ static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
 	}
 
 	if (dma_window == NULL) {
-		DBG("iommu_bus_setup_pSeriesLP: bus %s seems to have no ibm,dma-window property\n", dn->full_name);
+		DBG("  no ibm,dma-window property !\n");
 		return;
 	}
 
 	ppci = PCI_DN(pdn);
+
+	DBG("  parent is %s, iommu_table: 0x%p\n",
+	    pdn->full_name, ppci->iommu_table);
+
 	if (!ppci->iommu_table) {
 		/* Bussubno hasn't been copied yet.
 		 * Do it now because iommu_table_setparms_lpar needs it.
@@ -427,6 +431,7 @@ static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
 
 		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
+		DBG("  created table: %p\n", ppci->iommu_table);
 	}
 
 	if (pdn != dn)
@@ -434,27 +439,27 @@ static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
 }
 
 
-static void iommu_dev_setup_pSeries(struct pci_dev *dev)
+static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 {
-	struct device_node *dn, *mydn;
+	struct device_node *dn;
 	struct iommu_table *tbl;
 
-	DBG("iommu_dev_setup_pSeries, dev %p (%s)\n", dev, pci_name(dev));
+	DBG("pci_dma_dev_setup_pSeries: %s\n", pci_name(dev));
 
-	mydn = dn = pci_device_to_OF_node(dev);
+	dn = dev->dev.archdata.of_node;
 
 	/* If we're the direct child of a root bus, then we need to allocate
 	 * an iommu table ourselves. The bus setup code should have setup
 	 * the window sizes already.
 	 */
 	if (!dev->bus->self) {
+		struct pci_controller *phb = PCI_DN(dn)->phb;
+
 		DBG(" --> first child, no bridge. Allocating iommu table.\n");
 		tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   PCI_DN(dn)->phb->node);
-		iommu_table_setparms(PCI_DN(dn)->phb, dn, tbl);
-		PCI_DN(dn)->iommu_table = iommu_init_table(tbl,
-						PCI_DN(dn)->phb->node);
-
+				   phb->node);
+		iommu_table_setparms(phb, dn, tbl);
+		dev->dev.archdata.dma_data = iommu_init_table(tbl, phb->node);
 		return;
 	}
 
@@ -465,11 +470,11 @@ static void iommu_dev_setup_pSeries(struct pci_dev *dev)
 	while (dn && PCI_DN(dn) && PCI_DN(dn)->iommu_table == NULL)
 		dn = dn->parent;
 
-	if (dn && PCI_DN(dn)) {
-		PCI_DN(mydn)->iommu_table = PCI_DN(dn)->iommu_table;
-	} else {
-		DBG("iommu_dev_setup_pSeries, dev %p (%s) has no iommu table\n", dev, pci_name(dev));
-	}
+	if (dn && PCI_DN(dn))
+		dev->dev.archdata.dma_data = PCI_DN(dn)->iommu_table;
+	else
+		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
+		       pci_name(dev));
 }
 
 static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
@@ -495,13 +500,15 @@ static struct notifier_block iommu_reconfig_nb = {
 	.notifier_call = iommu_reconfig_notifier,
 };
 
-static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
+static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
 	const void *dma_window = NULL;
 	struct pci_dn *pci;
 
+	DBG("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
+
 	/* dev setup for LPAR is a little tricky, since the device tree might
 	 * contain the dma-window properties per-device and not neccesarily
 	 * for the bus. So we need to search upwards in the tree until we
@@ -509,9 +516,7 @@ static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
 	 * already allocated.
 	 */
 	dn = pci_device_to_OF_node(dev);
-
-	DBG("iommu_dev_setup_pSeriesLP, dev %p (%s) %s\n",
-	     dev, pci_name(dev), dn->full_name);
+	DBG("  node is %s\n", dn->full_name);
 
 	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
 	     pdn = pdn->parent) {
@@ -520,16 +525,17 @@ static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
 			break;
 	}
 
+	DBG("  parent is %s\n", pdn->full_name);
+
 	/* Check for parent == NULL so we don't try to setup the empty EADS
 	 * slots on POWER4 machines.
 	 */
 	if (dma_window == NULL || pdn->parent == NULL) {
-		DBG("No dma window for device, linking to parent\n");
-		PCI_DN(dn)->iommu_table = PCI_DN(pdn)->iommu_table;
+		DBG("  no dma window for device, linking to parent\n");
+		dev->dev.archdata.dma_data = PCI_DN(pdn)->iommu_table;
 		return;
-	} else {
-		DBG("Found DMA window, allocating table\n");
 	}
+	DBG("  found DMA window, table: %p\n", pci->iommu_table);
 
 	pci = PCI_DN(pdn);
 	if (!pci->iommu_table) {
@@ -542,24 +548,20 @@ static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
 
 		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+		DBG("  created table: %p\n", pci->iommu_table);
 	}
 
-	if (pdn != dn)
-		PCI_DN(dn)->iommu_table = pci->iommu_table;
+	dev->dev.archdata.dma_data = pci->iommu_table;
 }
 
-static void iommu_bus_setup_null(struct pci_bus *b) { }
-static void iommu_dev_setup_null(struct pci_dev *d) { }
-
 /* These are called very early. */
 void iommu_init_early_pSeries(void)
 {
 	if (of_chosen && get_property(of_chosen, "linux,iommu-off", NULL)) {
 		/* Direct I/O, IOMMU off */
-		ppc_md.iommu_dev_setup = iommu_dev_setup_null;
-		ppc_md.iommu_bus_setup = iommu_bus_setup_null;
-		pci_direct_iommu_init();
-
+		ppc_md.pci_dma_dev_setup = NULL;
+		ppc_md.pci_dma_bus_setup = NULL;
+		pci_dma_ops = &dma_direct_ops;
 		return;
 	}
 
@@ -572,19 +574,19 @@ void iommu_init_early_pSeries(void)
 			ppc_md.tce_free	 = tce_free_pSeriesLP;
 		}
 		ppc_md.tce_get   = tce_get_pSeriesLP;
-		ppc_md.iommu_bus_setup = iommu_bus_setup_pSeriesLP;
-		ppc_md.iommu_dev_setup = iommu_dev_setup_pSeriesLP;
+		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
 	} else {
 		ppc_md.tce_build = tce_build_pSeries;
 		ppc_md.tce_free  = tce_free_pSeries;
 		ppc_md.tce_get   = tce_get_pseries;
-		ppc_md.iommu_bus_setup = iommu_bus_setup_pSeries;
-		ppc_md.iommu_dev_setup = iommu_dev_setup_pSeries;
+		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeries;
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeries;
 	}
 
 
 	pSeries_reconfig_notifier_register(&iommu_reconfig_nb);
 
-	pci_iommu_init();
+	pci_dma_ops = &dma_iommu_ops;
 }
 
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 1820a0b0a8c6..721436db3ef0 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -282,7 +282,7 @@ void vpa_init(int cpu)
 	}
 }
 
-long pSeries_lpar_hpte_insert(unsigned long hpte_group,
+static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
  			      unsigned long va, unsigned long pa,
  			      unsigned long rflags, unsigned long vflags,
  			      int psize)
@@ -506,7 +506,7 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
  * lock.
  */
-void pSeries_lpar_flush_hash_range(unsigned long number, int local)
+static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 {
 	int i;
 	unsigned long flags = 0;
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 410a6bcc4ca0..715db5c89908 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -29,8 +29,6 @@
 #include <asm/prom.h>
 #include <asm/ppc-pci.h>
 
-static int __devinitdata s7a_workaround = -1;
-
 #if 0
 void pcibios_name_device(struct pci_dev *dev)
 {
@@ -57,39 +55,6 @@ void pcibios_name_device(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_name_device);
 #endif
 
-static void __devinit check_s7a(void)
-{
-	struct device_node *root;
-	const char *model;
-
-	s7a_workaround = 0;
-	root = of_find_node_by_path("/");
-	if (root) {
-		model = get_property(root, "model", NULL);
-		if (model && !strcmp(model, "IBM,7013-S7A"))
-			s7a_workaround = 1;
-		of_node_put(root);
-	}
-}
-
-void __devinit pSeries_irq_bus_setup(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	if (s7a_workaround < 0)
-		check_s7a();
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		pci_read_irq_line(dev);
-		if (s7a_workaround) {
-			if (dev->irq > 16) {
-				dev->irq -= 3;
-				pci_write_config_byte(dev, PCI_INTERRUPT_LINE,
-					dev->irq);
-			}
-		}
-	}
-}
-
 static void __init pSeries_request_regions(void)
 {
 	if (!isa_io_base)
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 6bfacc217085..ac56b868913a 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -93,8 +93,8 @@ pcibios_fixup_new_pci_devices(struct pci_bus *bus, int fix_bus)
 		if (list_empty(&dev->global_list)) {
 			int i;
 
-			/* Need to setup IOMMU tables */
-			ppc_md.iommu_dev_setup(dev);
+			/* Fill device archdata and setup iommu table */
+			pcibios_setup_new_device(dev);
 
 			if(fix_bus)
 				pcibios_fixup_device_resources(dev, bus);
@@ -195,7 +195,7 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
 	phb = pcibios_alloc_controller(dn);
 	if (!phb)
 		return NULL;
-	setup_phb(dn, phb);
+	rtas_setup_phb(phb);
 	pci_process_bridge_OF_ranges(phb, dn, 0);
 
 	pci_setup_phb_io_dynamic(phb, primary);
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 1773103354be..4ad33e41b008 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -268,11 +268,10 @@ static char * parse_next_property(char *buf, char *end, char **name, int *length
 static struct property *new_property(const char *name, const int length,
 				     const unsigned char *value, struct property *last)
 {
-	struct property *new = kmalloc(sizeof(*new), GFP_KERNEL);
+	struct property *new = kzalloc(sizeof(*new), GFP_KERNEL);
 
 	if (!new)
 		return NULL;
-	memset(new, 0, sizeof(*new));
 
 	if (!(new->name = kmalloc(strlen(name) + 1, GFP_KERNEL)))
 		goto cleanup;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 89a8119f988d..0dc2548ca9bc 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -347,6 +347,7 @@ static int __init pSeries_init_panel(void)
 }
 arch_initcall(pSeries_init_panel);
 
+#ifdef CONFIG_HOTPLUG_CPU
 static void pSeries_mach_cpu_die(void)
 {
 	local_irq_disable();
@@ -357,6 +358,9 @@ static void pSeries_mach_cpu_die(void)
 	BUG();
 	for(;;);
 }
+#else
+#define pSeries_mach_cpu_die NULL
+#endif
 
 static int pseries_set_dabr(unsigned long dabr)
 {
@@ -553,7 +557,6 @@ define_machine(pseries) {
 	.log_error		= pSeries_log_error,
 	.pcibios_fixup		= pSeries_final_fixup,
 	.pci_probe_mode		= pSeries_pci_probe_mode,
-	.irq_bus_setup		= pSeries_irq_bus_setup,
 	.restart		= rtas_restart,
 	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index d071abe78ab1..b5b2b1103de8 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -656,13 +656,38 @@ static void __init xics_setup_8259_cascade(void)
 	set_irq_chained_handler(cascade, pseries_8259_cascade);
 }
 
+static struct device_node *cpuid_to_of_node(int cpu)
+{
+	struct device_node *np;
+	u32 hcpuid = get_hard_smp_processor_id(cpu);
+
+	for_each_node_by_type(np, "cpu") {
+		int i, len;
+		const u32 *intserv;
+
+		intserv = get_property(np, "ibm,ppc-interrupt-server#s", &len);
+
+		if (!intserv)
+			intserv = get_property(np, "reg", &len);
+
+		i = len / sizeof(u32);
+
+		while (i--)
+			if (intserv[i] == hcpuid)
+				return np;
+	}
+
+	return NULL;
+}
+
 void __init xics_init_IRQ(void)
 {
-	int i;
+	int i, j;
 	struct device_node *np;
 	u32 ilen, indx = 0;
-	const u32 *ireg;
+	const u32 *ireg, *isize;
 	int found = 0;
+	u32 hcpuid;
 
 	ppc64_boot_msg(0x20, "XICS Init");
 
@@ -683,26 +708,31 @@ void __init xics_init_IRQ(void)
 	xics_init_host();
 
 	/* Find the server numbers for the boot cpu. */
-	for (np = of_find_node_by_type(NULL, "cpu");
-	     np;
-	     np = of_find_node_by_type(np, "cpu")) {
-		ireg = get_property(np, "reg", &ilen);
-		if (ireg && ireg[0] == get_hard_smp_processor_id(boot_cpuid)) {
-			ireg = get_property(np,
-					"ibm,ppc-interrupt-gserver#s", &ilen);
-			i = ilen / sizeof(int);
-			if (ireg && i > 0) {
-				default_server = ireg[0];
-				/* take last element */
-				default_distrib_server = ireg[i-1];
-			}
-			ireg = get_property(np,
+	np = cpuid_to_of_node(boot_cpuid);
+	BUG_ON(!np);
+	ireg = get_property(np, "ibm,ppc-interrupt-gserver#s", &ilen);
+	if (!ireg)
+		goto skip_gserver_check;
+	i = ilen / sizeof(int);
+	hcpuid = get_hard_smp_processor_id(boot_cpuid);
+
+	/* Global interrupt distribution server is specified in the last
+	 * entry of "ibm,ppc-interrupt-gserver#s" property. Get the last
+	 * entry fom this property for current boot cpu id and use it as
+	 * default distribution server
+	 */
+	for (j = 0; j < i; j += 2) {
+		if (ireg[j] == hcpuid) {
+			default_server = hcpuid;
+			default_distrib_server = ireg[j+1];
+
+			isize = get_property(np,
 					"ibm,interrupt-server#-size", NULL);
-			if (ireg)
-				interrupt_server_size = *ireg;
-			break;
+			if (isize)
+				interrupt_server_size = *isize;
 		}
 	}
+skip_gserver_check:
 	of_node_put(np);
 
 	if (firmware_has_feature(FW_FEATURE_LPAR))
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 91f052d8cce0..6cc34597a620 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -5,14 +5,13 @@ endif
 obj-$(CONFIG_MPIC)		+= mpic.o
 obj-$(CONFIG_PPC_INDIRECT_PCI)	+= indirect_pci.o
 obj-$(CONFIG_PPC_MPC106)	+= grackle.o
-obj-$(CONFIG_BOOKE)		+= dcr.o
-obj-$(CONFIG_40x)		+= dcr.o
+obj-$(CONFIG_PPC_DCR)		+= dcr.o dcr-low.o
 obj-$(CONFIG_U3_DART)		+= dart_iommu.o
 obj-$(CONFIG_MMIO_NVRAM)	+= mmio_nvram.o
 obj-$(CONFIG_FSL_SOC)		+= fsl_soc.o
-obj-$(CONFIG_PPC_TODC)		+= todc.o
 obj-$(CONFIG_TSI108_BRIDGE)	+= tsi108_pci.o tsi108_dev.o
 obj-$(CONFIG_QUICC_ENGINE)	+= qe_lib/
+obj-$(CONFIG_MTD)		+= rom.o
 
 ifeq ($(CONFIG_PPC_MERGE),y)
 obj-$(CONFIG_PPC_I8259)		+= i8259.o
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 572b7846cc77..1488535b0e13 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -48,9 +48,6 @@
 
 #include "dart.h"
 
-extern int iommu_is_off;
-extern int iommu_force_on;
-
 /* Physical base address and size of the DART table */
 unsigned long dart_tablebase; /* exported to htab_initialize */
 static unsigned long dart_tablesize;
@@ -289,24 +286,15 @@ static void iommu_table_dart_setup(void)
 	set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
 }
 
-static void iommu_dev_setup_dart(struct pci_dev *dev)
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
 {
-	struct device_node *dn;
-
 	/* We only have one iommu table on the mac for now, which makes
 	 * things simple. Setup all PCI devices to point to this table
-	 *
-	 * We must use pci_device_to_OF_node() to make sure that
-	 * we get the real "final" pointer to the device in the
-	 * pci_dev sysdata and not the temporary PHB one
 	 */
-	dn = pci_device_to_OF_node(dev);
-
-	if (dn)
-		PCI_DN(dn)->iommu_table = &iommu_table_dart;
+	dev->dev.archdata.dma_data = &iommu_table_dart;
 }
 
-static void iommu_bus_setup_dart(struct pci_bus *bus)
+static void pci_dma_bus_setup_dart(struct pci_bus *bus)
 {
 	struct device_node *dn;
 
@@ -321,9 +309,6 @@ static void iommu_bus_setup_dart(struct pci_bus *bus)
 		PCI_DN(dn)->iommu_table = &iommu_table_dart;
 }
 
-static void iommu_dev_setup_null(struct pci_dev *dev) { }
-static void iommu_bus_setup_null(struct pci_bus *bus) { }
-
 void iommu_init_early_dart(void)
 {
 	struct device_node *dn;
@@ -344,22 +329,21 @@ void iommu_init_early_dart(void)
 
 	/* Initialize the DART HW */
 	if (dart_init(dn) == 0) {
-		ppc_md.iommu_dev_setup = iommu_dev_setup_dart;
-		ppc_md.iommu_bus_setup = iommu_bus_setup_dart;
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_dart;
+		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_dart;
 
 		/* Setup pci_dma ops */
-		pci_iommu_init();
-
+		pci_dma_ops = &dma_iommu_ops;
 		return;
 	}
 
  bail:
 	/* If init failed, use direct iommu and null setup functions */
-	ppc_md.iommu_dev_setup = iommu_dev_setup_null;
-	ppc_md.iommu_bus_setup = iommu_bus_setup_null;
+	ppc_md.pci_dma_dev_setup = NULL;
+	ppc_md.pci_dma_bus_setup = NULL;
 
 	/* Setup pci_dma ops */
-	pci_direct_iommu_init();
+	pci_dma_ops = &dma_direct_ops;
 }
 
 
diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S
new file mode 100644
index 000000000000..2078f39e2f17
--- /dev/null
+++ b/arch/powerpc/sysdev/dcr-low.S
@@ -0,0 +1,39 @@
+/*
+ * "Indirect" DCR access
+ *
+ * Copyright (c) 2004 Eugene Surovegin <ebs@ebshome.net>
+ *
+ * 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.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/processor.h>
+
+#define DCR_ACCESS_PROLOG(table) \
+	rlwinm  r3,r3,4,18,27;   \
+	lis     r5,table@h;      \
+	ori     r5,r5,table@l;   \
+	add     r3,r3,r5;        \
+	mtctr   r3;              \
+	bctr
+
+_GLOBAL(__mfdcr)
+	DCR_ACCESS_PROLOG(__mfdcr_table)
+
+_GLOBAL(__mtdcr)
+	DCR_ACCESS_PROLOG(__mtdcr_table)
+
+__mfdcr_table:
+	mfdcr  r3,0; blr
+__mtdcr_table:
+	mtdcr  0,r4; blr
+
+dcr     = 1
+        .rept   1023
+	mfdcr   r3,dcr; blr
+	mtdcr   dcr,r4; blr
+	dcr     = dcr + 1
+	.endr
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
new file mode 100644
index 000000000000..dffeeaeca1d9
--- /dev/null
+++ b/arch/powerpc/sysdev/dcr.c
@@ -0,0 +1,137 @@
+/*
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ *
+ *   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
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <asm/prom.h>
+#include <asm/dcr.h>
+
+unsigned int dcr_resource_start(struct device_node *np, unsigned int index)
+{
+	unsigned int ds;
+	const u32 *dr = get_property(np, "dcr-reg", &ds);
+
+	if (dr == NULL || ds & 1 || index >= (ds / 8))
+		return 0;
+
+	return dr[index * 2];
+}
+
+unsigned int dcr_resource_len(struct device_node *np, unsigned int index)
+{
+	unsigned int ds;
+	const u32 *dr = get_property(np, "dcr-reg", &ds);
+
+	if (dr == NULL || ds & 1 || index >= (ds / 8))
+		return 0;
+
+	return dr[index * 2 + 1];
+}
+
+#ifndef CONFIG_PPC_DCR_NATIVE
+
+static struct device_node * find_dcr_parent(struct device_node * node)
+{
+	struct device_node *par, *tmp;
+	const u32 *p;
+
+	for (par = of_node_get(node); par;) {
+		if (get_property(par, "dcr-controller", NULL))
+			break;
+		p = get_property(par, "dcr-parent", NULL);
+		tmp = par;
+		if (p == NULL)
+			par = of_get_parent(par);
+		else
+			par = of_find_node_by_phandle(*p);
+		of_node_put(tmp);
+	}
+	return par;
+}
+
+u64 of_translate_dcr_address(struct device_node *dev,
+			     unsigned int dcr_n,
+			     unsigned int *out_stride)
+{
+	struct device_node *dp;
+	const u32 *p;
+	unsigned int stride;
+	u64 ret;
+
+	dp = find_dcr_parent(dev);
+	if (dp == NULL)
+		return OF_BAD_ADDR;
+
+	/* Stride is not properly defined yet, default to 0x10 for Axon */
+	p = get_property(dp, "dcr-mmio-stride", NULL);
+	stride = (p == NULL) ? 0x10 : *p;
+
+	/* XXX FIXME: Which property name is to use of the 2 following ? */
+	p = get_property(dp, "dcr-mmio-range", NULL);
+	if (p == NULL)
+		p = get_property(dp, "dcr-mmio-space", NULL);
+	if (p == NULL)
+		return OF_BAD_ADDR;
+
+	/* Maybe could do some better range checking here */
+	ret = of_translate_address(dp, p);
+	if (ret != OF_BAD_ADDR)
+		ret += (u64)(stride) * (u64)dcr_n;
+	if (out_stride)
+		*out_stride = stride;
+	return ret;
+}
+
+dcr_host_t dcr_map(struct device_node *dev, unsigned int dcr_n,
+		   unsigned int dcr_c)
+{
+	dcr_host_t ret = { .token = NULL, .stride = 0 };
+	u64 addr;
+
+	pr_debug("dcr_map(%s, 0x%x, 0x%x)\n",
+		 dev->full_name, dcr_n, dcr_c);
+
+	addr = of_translate_dcr_address(dev, dcr_n, &ret.stride);
+	pr_debug("translates to addr: 0x%lx, stride: 0x%x\n",
+		 addr, ret.stride);
+	if (addr == OF_BAD_ADDR)
+		return ret;
+	pr_debug("mapping 0x%x bytes\n", dcr_c * ret.stride);
+	ret.token = ioremap(addr, dcr_c * ret.stride);
+	if (ret.token == NULL)
+		return ret;
+	pr_debug("mapped at 0x%p -> base is 0x%p\n",
+		 ret.token, ret.token - dcr_n * ret.stride);
+	ret.token -= dcr_n * ret.stride;
+	return ret;
+}
+
+void dcr_unmap(dcr_host_t host, unsigned int dcr_n, unsigned int dcr_c)
+{
+	dcr_host_t h = host;
+
+	if (h.token == NULL)
+		return;
+	h.token -= dcr_n * h.stride;
+	iounmap(h.token);
+	h.token = NULL;
+}
+
+#endif /* !defined(CONFIG_PPC_DCR_NATIVE) */
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index dbe92ae20333..ad31e56e892b 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
+#include <linux/phy.h>
 #include <linux/fsl_devices.h>
 #include <linux/fs_enet_pd.h>
 #include <linux/fs_uart_pd.h>
@@ -146,7 +147,7 @@ static int __init gfar_mdio_of_init(void)
 		}
 
 		for (k = 0; k < 32; k++)
-			mdio_data.irq[k] = -1;
+			mdio_data.irq[k] = PHY_POLL;
 
 		while ((child = of_get_next_child(np, child)) != NULL) {
 			int irq = irq_of_parse_and_map(child, 0);
@@ -177,6 +178,7 @@ static const char *gfar_tx_intr = "tx";
 static const char *gfar_rx_intr = "rx";
 static const char *gfar_err_intr = "error";
 
+
 static int __init gfar_of_init(void)
 {
 	struct device_node *np;
@@ -204,8 +206,7 @@ static int __init gfar_of_init(void)
 		if (ret)
 			goto err;
 
-		r[1].start = r[1].end = irq_of_parse_and_map(np, 0);
-		r[1].flags = IORESOURCE_IRQ;
+		of_irq_to_resource(np, 0, &r[1]);
 
 		model = get_property(np, "model", NULL);
 
@@ -214,12 +215,10 @@ static int __init gfar_of_init(void)
 			r[1].name = gfar_tx_intr;
 
 			r[2].name = gfar_rx_intr;
-			r[2].start = r[2].end = irq_of_parse_and_map(np, 1);
-			r[2].flags = IORESOURCE_IRQ;
+			of_irq_to_resource(np, 1, &r[2]);
 
 			r[3].name = gfar_err_intr;
-			r[3].start = r[3].end = irq_of_parse_and_map(np, 2);
-			r[3].flags = IORESOURCE_IRQ;
+			of_irq_to_resource(np, 2, &r[3]);
 
 			n_res += 2;
 		}
@@ -323,8 +322,7 @@ static int __init fsl_i2c_of_init(void)
 		if (ret)
 			goto err;
 
-		r[1].start = r[1].end = irq_of_parse_and_map(np, 0);
-		r[1].flags = IORESOURCE_IRQ;
+		of_irq_to_resource(np, 0, &r[1]);
 
 		i2c_dev = platform_device_register_simple("fsl-i2c", i, r, 2);
 		if (IS_ERR(i2c_dev)) {
@@ -459,8 +457,7 @@ static int __init fsl_usb_of_init(void)
 		if (ret)
 			goto err;
 
-		r[1].start = r[1].end = irq_of_parse_and_map(np, 0);
-		r[1].flags = IORESOURCE_IRQ;
+		of_irq_to_resource(np, 0, &r[1]);
 
 		usb_dev_mph =
 		    platform_device_register_simple("fsl-ehci", i, r, 2);
@@ -507,8 +504,7 @@ static int __init fsl_usb_of_init(void)
 		if (ret)
 			goto unreg_mph;
 
-		r[1].start = r[1].end = irq_of_parse_and_map(np, 0);
-		r[1].flags = IORESOURCE_IRQ;
+		of_irq_to_resource(np, 0, &r[1]);
 
 		usb_dev_dr =
 		    platform_device_register_simple("fsl-ehci", i, r, 2);
@@ -591,8 +587,7 @@ static int __init fs_enet_of_init(void)
 		r[2].name = fcc_regs_c;
 		fs_enet_data.fcc_regs_c = r[2].start;
 
-		r[3].start = r[3].end = irq_of_parse_and_map(np, 0);
-		r[3].flags = IORESOURCE_IRQ;
+		of_irq_to_resource(np, 0, &r[3]);
 
 		fs_enet_dev =
 		    platform_device_register_simple("fsl-cpm-fcc", i, &r[0], 4);
@@ -754,8 +749,7 @@ static int __init cpm_uart_of_init(void)
 			goto err;
 		r[1].name = scc_pram;
 
-		r[2].start = r[2].end = irq_of_parse_and_map(np, 0);
-		r[2].flags = IORESOURCE_IRQ;
+		of_irq_to_resource(np, 0, &r[2]);
 
 		cpm_uart_dev =
 		    platform_device_register_simple("fsl-cpm-scc:uart", i, &r[0], 3);
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index ba4833f57d47..411480d5c626 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -147,33 +147,51 @@ static u32 mpic_infos[][MPIC_IDX_END] = {
  */
 
 
-static inline u32 _mpic_read(unsigned int be, volatile u32 __iomem *base,
-			    unsigned int reg)
+static inline u32 _mpic_read(enum mpic_reg_type type,
+			     struct mpic_reg_bank *rb,
+			     unsigned int reg)
 {
-	if (be)
-		return in_be32(base + (reg >> 2));
-	else
-		return in_le32(base + (reg >> 2));
+	switch(type) {
+#ifdef CONFIG_PPC_DCR
+	case mpic_access_dcr:
+		return dcr_read(rb->dhost,
+				rb->dbase + reg + rb->doff);
+#endif
+	case mpic_access_mmio_be:
+		return in_be32(rb->base + (reg >> 2));
+	case mpic_access_mmio_le:
+	default:
+		return in_le32(rb->base + (reg >> 2));
+	}
 }
 
-static inline void _mpic_write(unsigned int be, volatile u32 __iomem *base,
-			      unsigned int reg, u32 value)
+static inline void _mpic_write(enum mpic_reg_type type,
+			       struct mpic_reg_bank *rb,
+ 			       unsigned int reg, u32 value)
 {
-	if (be)
-		out_be32(base + (reg >> 2), value);
-	else
-		out_le32(base + (reg >> 2), value);
+	switch(type) {
+#ifdef CONFIG_PPC_DCR
+	case mpic_access_dcr:
+		return dcr_write(rb->dhost,
+				 rb->dbase + reg + rb->doff, value);
+#endif
+	case mpic_access_mmio_be:
+		return out_be32(rb->base + (reg >> 2), value);
+	case mpic_access_mmio_le:
+	default:
+		return out_le32(rb->base + (reg >> 2), value);
+	}
 }
 
 static inline u32 _mpic_ipi_read(struct mpic *mpic, unsigned int ipi)
 {
-	unsigned int be = (mpic->flags & MPIC_BIG_ENDIAN) != 0;
+	enum mpic_reg_type type = mpic->reg_type;
 	unsigned int offset = MPIC_INFO(GREG_IPI_VECTOR_PRI_0) +
 			      (ipi * MPIC_INFO(GREG_IPI_STRIDE));
 
-	if (mpic->flags & MPIC_BROKEN_IPI)
-		be = !be;
-	return _mpic_read(be, mpic->gregs, offset);
+	if ((mpic->flags & MPIC_BROKEN_IPI) && type == mpic_access_mmio_le)
+		type = mpic_access_mmio_be;
+	return _mpic_read(type, &mpic->gregs, offset);
 }
 
 static inline void _mpic_ipi_write(struct mpic *mpic, unsigned int ipi, u32 value)
@@ -181,7 +199,7 @@ static inline void _mpic_ipi_write(struct mpic *mpic, unsigned int ipi, u32 valu
 	unsigned int offset = MPIC_INFO(GREG_IPI_VECTOR_PRI_0) +
 			      (ipi * MPIC_INFO(GREG_IPI_STRIDE));
 
-	_mpic_write(mpic->flags & MPIC_BIG_ENDIAN, mpic->gregs, offset, value);
+	_mpic_write(mpic->reg_type, &mpic->gregs, offset, value);
 }
 
 static inline u32 _mpic_cpu_read(struct mpic *mpic, unsigned int reg)
@@ -190,8 +208,7 @@ static inline u32 _mpic_cpu_read(struct mpic *mpic, unsigned int reg)
 
 	if (mpic->flags & MPIC_PRIMARY)
 		cpu = hard_smp_processor_id();
-	return _mpic_read(mpic->flags & MPIC_BIG_ENDIAN,
-			  mpic->cpuregs[cpu], reg);
+	return _mpic_read(mpic->reg_type, &mpic->cpuregs[cpu], reg);
 }
 
 static inline void _mpic_cpu_write(struct mpic *mpic, unsigned int reg, u32 value)
@@ -201,7 +218,7 @@ static inline void _mpic_cpu_write(struct mpic *mpic, unsigned int reg, u32 valu
 	if (mpic->flags & MPIC_PRIMARY)
 		cpu = hard_smp_processor_id();
 
-	_mpic_write(mpic->flags & MPIC_BIG_ENDIAN, mpic->cpuregs[cpu], reg, value);
+	_mpic_write(mpic->reg_type, &mpic->cpuregs[cpu], reg, value);
 }
 
 static inline u32 _mpic_irq_read(struct mpic *mpic, unsigned int src_no, unsigned int reg)
@@ -209,7 +226,7 @@ static inline u32 _mpic_irq_read(struct mpic *mpic, unsigned int src_no, unsigne
 	unsigned int	isu = src_no >> mpic->isu_shift;
 	unsigned int	idx = src_no & mpic->isu_mask;
 
-	return _mpic_read(mpic->flags & MPIC_BIG_ENDIAN, mpic->isus[isu],
+	return _mpic_read(mpic->reg_type, &mpic->isus[isu],
 			  reg + (idx * MPIC_INFO(IRQ_STRIDE)));
 }
 
@@ -219,12 +236,12 @@ static inline void _mpic_irq_write(struct mpic *mpic, unsigned int src_no,
 	unsigned int	isu = src_no >> mpic->isu_shift;
 	unsigned int	idx = src_no & mpic->isu_mask;
 
-	_mpic_write(mpic->flags & MPIC_BIG_ENDIAN, mpic->isus[isu],
+	_mpic_write(mpic->reg_type, &mpic->isus[isu],
 		    reg + (idx * MPIC_INFO(IRQ_STRIDE)), value);
 }
 
-#define mpic_read(b,r)		_mpic_read(mpic->flags & MPIC_BIG_ENDIAN,(b),(r))
-#define mpic_write(b,r,v)	_mpic_write(mpic->flags & MPIC_BIG_ENDIAN,(b),(r),(v))
+#define mpic_read(b,r)		_mpic_read(mpic->reg_type,&(b),(r))
+#define mpic_write(b,r,v)	_mpic_write(mpic->reg_type,&(b),(r),(v))
 #define mpic_ipi_read(i)	_mpic_ipi_read(mpic,(i))
 #define mpic_ipi_write(i,v)	_mpic_ipi_write(mpic,(i),(v))
 #define mpic_cpu_read(i)	_mpic_cpu_read(mpic,(i))
@@ -238,6 +255,38 @@ static inline void _mpic_irq_write(struct mpic *mpic, unsigned int src_no,
  */
 
 
+static void _mpic_map_mmio(struct mpic *mpic, unsigned long phys_addr,
+			   struct mpic_reg_bank *rb, unsigned int offset,
+			   unsigned int size)
+{
+	rb->base = ioremap(phys_addr + offset, size);
+	BUG_ON(rb->base == NULL);
+}
+
+#ifdef CONFIG_PPC_DCR
+static void _mpic_map_dcr(struct mpic *mpic, struct mpic_reg_bank *rb,
+			  unsigned int offset, unsigned int size)
+{
+	rb->dbase = mpic->dcr_base;
+	rb->doff = offset;
+	rb->dhost = dcr_map(mpic->of_node, rb->dbase + rb->doff, size);
+	BUG_ON(!DCR_MAP_OK(rb->dhost));
+}
+
+static inline void mpic_map(struct mpic *mpic, unsigned long phys_addr,
+			    struct mpic_reg_bank *rb, unsigned int offset,
+			    unsigned int size)
+{
+	if (mpic->flags & MPIC_USES_DCR)
+		_mpic_map_dcr(mpic, rb, offset, size);
+	else
+		_mpic_map_mmio(mpic, phys_addr, rb, offset, size);
+}
+#else /* CONFIG_PPC_DCR */
+#define mpic_map(m,p,b,o,s)	_mpic_map_mmio(m,p,b,o,s)
+#endif /* !CONFIG_PPC_DCR */
+
+
 
 /* Check if we have one of those nice broken MPICs with a flipped endian on
  * reads from IPI registers
@@ -845,7 +894,7 @@ static struct irq_host_ops mpic_host_ops = {
  */
 
 struct mpic * __init mpic_alloc(struct device_node *node,
-				unsigned long phys_addr,
+				phys_addr_t phys_addr,
 				unsigned int flags,
 				unsigned int isu_size,
 				unsigned int irq_count,
@@ -855,6 +904,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	u32		reg;
 	const char	*vers;
 	int		i;
+	u64		paddr = phys_addr;
 
 	mpic = alloc_bootmem(sizeof(struct mpic));
 	if (mpic == NULL)
@@ -883,6 +933,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	if (flags & MPIC_PRIMARY)
 		mpic->hc_ht_irq.set_affinity = mpic_set_affinity;
 #endif /* CONFIG_MPIC_BROKEN_U3 */
+
 #ifdef CONFIG_SMP
 	mpic->hc_ipi = mpic_ipi_chip;
 	mpic->hc_ipi.typename = name;
@@ -893,15 +944,52 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	mpic->irq_count = irq_count;
 	mpic->num_sources = 0; /* so far */
 
+	/* Check for "big-endian" in device-tree */
+	if (node && get_property(node, "big-endian", NULL) != NULL)
+		mpic->flags |= MPIC_BIG_ENDIAN;
+
+
 #ifdef CONFIG_MPIC_WEIRD
 	mpic->hw_set = mpic_infos[MPIC_GET_REGSET(flags)];
 #endif
 
+	/* default register type */
+	mpic->reg_type = (flags & MPIC_BIG_ENDIAN) ?
+		mpic_access_mmio_be : mpic_access_mmio_le;
+
+	/* If no physical address is passed in, a device-node is mandatory */
+	BUG_ON(paddr == 0 && node == NULL);
+
+	/* If no physical address passed in, check if it's dcr based */
+	if (paddr == 0 && get_property(node, "dcr-reg", NULL) != NULL)
+		mpic->flags |= MPIC_USES_DCR;
+
+#ifdef CONFIG_PPC_DCR
+	if (mpic->flags & MPIC_USES_DCR) {
+		const u32 *dbasep;
+		dbasep = get_property(node, "dcr-reg", NULL);
+		BUG_ON(dbasep == NULL);
+		mpic->dcr_base = *dbasep;
+		mpic->reg_type = mpic_access_dcr;
+	}
+#else
+	BUG_ON (mpic->flags & MPIC_USES_DCR);
+#endif /* CONFIG_PPC_DCR */
+
+	/* If the MPIC is not DCR based, and no physical address was passed
+	 * in, try to obtain one
+	 */
+	if (paddr == 0 && !(mpic->flags & MPIC_USES_DCR)) {
+		const u32 *reg;
+		reg = get_property(node, "reg", NULL);
+		BUG_ON(reg == NULL);
+		paddr = of_translate_address(node, reg);
+		BUG_ON(paddr == OF_BAD_ADDR);
+	}
+
 	/* Map the global registers */
-	mpic->gregs = ioremap(phys_addr + MPIC_INFO(GREG_BASE), 0x1000);
-	mpic->tmregs = mpic->gregs +
-		       ((MPIC_INFO(TIMER_BASE) - MPIC_INFO(GREG_BASE)) >> 2);
-	BUG_ON(mpic->gregs == NULL);
+	mpic_map(mpic, paddr, &mpic->gregs, MPIC_INFO(GREG_BASE), 0x1000);
+	mpic_map(mpic, paddr, &mpic->tmregs, MPIC_INFO(TIMER_BASE), 0x1000);
 
 	/* Reset */
 	if (flags & MPIC_WANTS_RESET) {
@@ -926,17 +1014,16 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 
 	/* Map the per-CPU registers */
 	for (i = 0; i < mpic->num_cpus; i++) {
-		mpic->cpuregs[i] = ioremap(phys_addr + MPIC_INFO(CPU_BASE) +
-					   i * MPIC_INFO(CPU_STRIDE), 0x1000);
-		BUG_ON(mpic->cpuregs[i] == NULL);
+		mpic_map(mpic, paddr, &mpic->cpuregs[i],
+			 MPIC_INFO(CPU_BASE) + i * MPIC_INFO(CPU_STRIDE),
+			 0x1000);
 	}
 
 	/* Initialize main ISU if none provided */
 	if (mpic->isu_size == 0) {
 		mpic->isu_size = mpic->num_sources;
-		mpic->isus[0] = ioremap(phys_addr + MPIC_INFO(IRQ_BASE),
-					MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
-		BUG_ON(mpic->isus[0] == NULL);
+		mpic_map(mpic, paddr, &mpic->isus[0],
+			 MPIC_INFO(IRQ_BASE), MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
 	}
 	mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1);
 	mpic->isu_mask = (1 << mpic->isu_shift) - 1;
@@ -956,10 +1043,11 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 		vers = "<unknown>";
 		break;
 	}
-	printk(KERN_INFO "mpic: Setting up MPIC \"%s\" version %s at %lx, max %d CPUs\n",
-	       name, vers, phys_addr, mpic->num_cpus);
-	printk(KERN_INFO "mpic: ISU size: %d, shift: %d, mask: %x\n", mpic->isu_size,
-	       mpic->isu_shift, mpic->isu_mask);
+	printk(KERN_INFO "mpic: Setting up MPIC \"%s\" version %s at %llx,"
+	       " max %d CPUs\n",
+	       name, vers, (unsigned long long)paddr, mpic->num_cpus);
+	printk(KERN_INFO "mpic: ISU size: %d, shift: %d, mask: %x\n",
+	       mpic->isu_size, mpic->isu_shift, mpic->isu_mask);
 
 	mpic->next = mpics;
 	mpics = mpic;
@@ -973,14 +1061,14 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 }
 
 void __init mpic_assign_isu(struct mpic *mpic, unsigned int isu_num,
-			    unsigned long phys_addr)
+			    phys_addr_t paddr)
 {
 	unsigned int isu_first = isu_num * mpic->isu_size;
 
 	BUG_ON(isu_num >= MPIC_MAX_ISU);
 
-	mpic->isus[isu_num] = ioremap(phys_addr,
-				      MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
+	mpic_map(mpic, paddr, &mpic->isus[isu_num], 0,
+		 MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
 	if ((isu_first + mpic->isu_size) > mpic->num_sources)
 		mpic->num_sources = isu_first + mpic->isu_size;
 }
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index e4223226a7a8..e3d71e083f35 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -174,8 +174,7 @@ void qe_setbrg(u32 brg, u32 rate)
 	u32 divisor, tempval;
 	int div16 = 0;
 
-	bp = &qe_immr->brg.brgc1;
-	bp += brg;
+	bp = &qe_immr->brg.brgc[brg];
 
 	divisor = (get_brg_clk() / rate);
 	if (divisor > QE_BRGC_DIVISOR_MAX + 1) {
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_fast.c b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
index 75fa3104a43a..e657559bea93 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_fast.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
@@ -216,14 +216,12 @@ int ucc_fast_init(struct ucc_fast_info * uf_info, struct ucc_fast_private ** ucc
 		return -EINVAL;
 	}
 
-	uccf = (struct ucc_fast_private *)
-		 kmalloc(sizeof(struct ucc_fast_private), GFP_KERNEL);
+	uccf = kzalloc(sizeof(struct ucc_fast_private), GFP_KERNEL);
 	if (!uccf) {
 		uccf_err
 		    ("ucc_fast_init: No memory for UCC slow data structure!");
 		return -ENOMEM;
 	}
-	memset(uccf, 0, sizeof(struct ucc_fast_private));
 
 	/* Fill fast UCC structure */
 	uccf->uf_info = uf_info;
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_slow.c b/arch/powerpc/sysdev/qe_lib/ucc_slow.c
index a49da6b73ecf..47b56203f47e 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_slow.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_slow.c
@@ -168,14 +168,12 @@ int ucc_slow_init(struct ucc_slow_info * us_info, struct ucc_slow_private ** ucc
 		return -EINVAL;
 	}
 
-	uccs = (struct ucc_slow_private *)
-		kmalloc(sizeof(struct ucc_slow_private), GFP_KERNEL);
+	uccs = kzalloc(sizeof(struct ucc_slow_private), GFP_KERNEL);
 	if (!uccs) {
 		uccs_err
 		    ("ucc_slow_init: No memory for UCC slow data structure!");
 		return -ENOMEM;
 	}
-	memset(uccs, 0, sizeof(struct ucc_slow_private));
 
 	/* Fill slow UCC structure */
 	uccs->us_info = us_info;
diff --git a/arch/powerpc/sysdev/rom.c b/arch/powerpc/sysdev/rom.c
new file mode 100644
index 000000000000..bf5b3f10e6c6
--- /dev/null
+++ b/arch/powerpc/sysdev/rom.c
@@ -0,0 +1,31 @@
+/*
+ * ROM device registration
+ *
+ * (C) 2006 MontaVista Software, Inc. This file is licensed under
+ * the terms of the GNU General Public License version 2. This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+ */
+
+#include <linux/kernel.h>
+#include <asm/of_device.h>
+
+static int __init powerpc_flash_init(void)
+{
+	struct device_node *node = NULL;
+
+	/*
+	 * Register all the devices which type is "rom"
+	 */
+	while ((node = of_find_node_by_type(node, "rom")) != NULL) {
+		if (node->name == NULL) {
+			printk(KERN_WARNING "powerpc_flash_init: found 'rom' "
+				"device, but with no name, skipping...\n");
+			continue;
+		}
+		of_platform_device_create(node, node->name, NULL);
+	}
+	return 0;
+}
+
+arch_initcall(powerpc_flash_init);
diff --git a/arch/powerpc/sysdev/todc.c b/arch/powerpc/sysdev/todc.c
deleted file mode 100644
index 0a65980efb50..000000000000
--- a/arch/powerpc/sysdev/todc.c
+++ /dev/null
@@ -1,392 +0,0 @@
-/*
- * Time of Day Clock support for the M48T35, M48T37, M48T59, and MC146818
- * Real Time Clocks/Timekeepers.
- *
- * Author: Mark A. Greer <mgreer@mvista.com>
- *
- * 2001-2004 (c) MontaVista, Software, Inc.  This file is licensed under
- * the terms of the GNU General Public License version 2.  This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/timex.h>
-#include <linux/bcd.h>
-#include <linux/mc146818rtc.h>
-
-#include <asm/machdep.h>
-#include <asm/io.h>
-#include <asm/time.h>
-#include <asm/todc.h>
-
-/*
- * Depending on the hardware on your board and your board design, the
- * RTC/NVRAM may be accessed either directly (like normal memory) or via
- * address/data registers.  If your board uses the direct method, set
- * 'nvram_data' to the base address of your nvram and leave 'nvram_as0' and
- * 'nvram_as1' NULL.  If your board uses address/data regs to access nvram,
- * set 'nvram_as0' to the address of the lower byte, set 'nvram_as1' to the
- * address of the upper byte (leave NULL if using mc146818), and set
- * 'nvram_data' to the address of the 8-bit data register.
- *
- * Note: Even though the documentation for the various RTC chips say that it
- * 	 take up to a second before it starts updating once the 'R' bit is
- * 	 cleared, they always seem to update even though we bang on it many
- * 	 times a second.  This is true, except for the Dallas Semi 1746/1747
- * 	 (possibly others).  Those chips seem to have a real problem whenever
- * 	 we set the 'R' bit before reading them, they basically stop counting.
- * 	 					--MAG
- */
-
-/*
- * 'todc_info' should be initialized in your *_setup.c file to
- * point to a fully initialized 'todc_info_t' structure.
- * This structure holds all the register offsets for your particular
- * TODC/RTC chip.
- * TODC_ALLOC()/TODC_INIT() will allocate and initialize this table for you.
- */
-
-#ifdef	RTC_FREQ_SELECT
-#undef	RTC_FREQ_SELECT
-#define	RTC_FREQ_SELECT		control_b	/* Register A */
-#endif
-
-#ifdef	RTC_CONTROL
-#undef	RTC_CONTROL
-#define	RTC_CONTROL		control_a	/* Register B */
-#endif
-
-#ifdef	RTC_INTR_FLAGS
-#undef	RTC_INTR_FLAGS
-#define	RTC_INTR_FLAGS		watchdog	/* Register C */
-#endif
-
-#ifdef	RTC_VALID
-#undef	RTC_VALID
-#define	RTC_VALID		interrupts	/* Register D */
-#endif
-
-/* Access routines when RTC accessed directly (like normal memory) */
-u_char
-todc_direct_read_val(int addr)
-{
-	return readb((void __iomem *)(todc_info->nvram_data + addr));
-}
-
-void
-todc_direct_write_val(int addr, unsigned char val)
-{
-	writeb(val, (void __iomem *)(todc_info->nvram_data + addr));
-	return;
-}
-
-/* Access routines for accessing m48txx type chips via addr/data regs */
-u_char
-todc_m48txx_read_val(int addr)
-{
-	outb(addr, todc_info->nvram_as0);
-	outb(addr>>todc_info->as0_bits, todc_info->nvram_as1);
-	return inb(todc_info->nvram_data);
-}
-
-void
-todc_m48txx_write_val(int addr, unsigned char val)
-{
-	outb(addr, todc_info->nvram_as0);
-	outb(addr>>todc_info->as0_bits, todc_info->nvram_as1);
-	outb(val, todc_info->nvram_data);
-	return;
-}
-
-/* Access routines for accessing mc146818 type chips via addr/data regs */
-u_char
-todc_mc146818_read_val(int addr)
-{
-	outb_p(addr, todc_info->nvram_as0);
-	return inb_p(todc_info->nvram_data);
-}
-
-void
-todc_mc146818_write_val(int addr, unsigned char val)
-{
-	outb_p(addr, todc_info->nvram_as0);
-	outb_p(val, todc_info->nvram_data);
-}
-
-
-/*
- * Routines to make RTC chips with NVRAM buried behind an addr/data pair
- * have the NVRAM and clock regs appear at the same level.
- * The NVRAM will appear to start at addr 0 and the clock regs will appear
- * to start immediately after the NVRAM (actually, start at offset
- * todc_info->nvram_size).
- */
-static inline u_char
-todc_read_val(int addr)
-{
-	u_char	val;
-
-	if (todc_info->sw_flags & TODC_FLAG_2_LEVEL_NVRAM) {
-		if (addr < todc_info->nvram_size) { /* NVRAM */
-			ppc_md.rtc_write_val(todc_info->nvram_addr_reg, addr);
-			val = ppc_md.rtc_read_val(todc_info->nvram_data_reg);
-		} else { /* Clock Reg */
-			addr -= todc_info->nvram_size;
-			val = ppc_md.rtc_read_val(addr);
-		}
-	} else
-		val = ppc_md.rtc_read_val(addr);
-
-	return val;
-}
-
-static inline void
-todc_write_val(int addr, u_char val)
-{
-	if (todc_info->sw_flags & TODC_FLAG_2_LEVEL_NVRAM) {
-		if (addr < todc_info->nvram_size) { /* NVRAM */
-			ppc_md.rtc_write_val(todc_info->nvram_addr_reg, addr);
-			ppc_md.rtc_write_val(todc_info->nvram_data_reg, val);
-		} else { /* Clock Reg */
-			addr -= todc_info->nvram_size;
-			ppc_md.rtc_write_val(addr, val);
-		}
-	} else
-		ppc_md.rtc_write_val(addr, val);
-}
-
-/*
- * TODC routines
- *
- * There is some ugly stuff in that there are assumptions for the mc146818.
- *
- * Assumptions:
- *	- todc_info->control_a has the offset as mc146818 Register B reg
- *	- todc_info->control_b has the offset as mc146818 Register A reg
- *	- m48txx control reg's write enable or 'W' bit is same as
- *	  mc146818 Register B 'SET' bit (i.e., 0x80)
- *
- * These assumptions were made to make the code simpler.
- */
-long __init
-todc_time_init(void)
-{
-	u_char	cntl_b;
-
-	if (!ppc_md.rtc_read_val)
-		ppc_md.rtc_read_val = ppc_md.nvram_read_val;
-	if (!ppc_md.rtc_write_val)
-		ppc_md.rtc_write_val = ppc_md.nvram_write_val;
-
-	cntl_b = todc_read_val(todc_info->control_b);
-
-	if (todc_info->rtc_type == TODC_TYPE_MC146818) {
-		if ((cntl_b & 0x70) != 0x20) {
-			printk(KERN_INFO "TODC real-time-clock was stopped."
-				"  Now starting...");
-			cntl_b &= ~0x70;
-			cntl_b |= 0x20;
-		}
-
-		todc_write_val(todc_info->control_b, cntl_b);
-	} else if (todc_info->rtc_type == TODC_TYPE_DS17285) {
-		u_char mode;
-
-		mode = todc_read_val(TODC_TYPE_DS17285_CNTL_A);
-		/* Make sure countdown clear is not set */
-		mode &= ~0x40;
-		/* Enable oscillator, extended register set */
-		mode |= 0x30;
-		todc_write_val(TODC_TYPE_DS17285_CNTL_A, mode);
-
-	} else if (todc_info->rtc_type == TODC_TYPE_DS1501) {
-		u_char	month;
-
-		todc_info->enable_read = TODC_DS1501_CNTL_B_TE;
-		todc_info->enable_write = TODC_DS1501_CNTL_B_TE;
-
-		month = todc_read_val(todc_info->month);
-
-		if ((month & 0x80) == 0x80) {
-			printk(KERN_INFO "TODC %s %s\n",
-				"real-time-clock was stopped.",
-				"Now starting...");
-			month &= ~0x80;
-			todc_write_val(todc_info->month, month);
-		}
-
-		cntl_b &= ~TODC_DS1501_CNTL_B_TE;
-		todc_write_val(todc_info->control_b, cntl_b);
-	} else { /* must be a m48txx type */
-		u_char	cntl_a;
-
-		todc_info->enable_read = TODC_MK48TXX_CNTL_A_R;
-		todc_info->enable_write = TODC_MK48TXX_CNTL_A_W;
-
-		cntl_a = todc_read_val(todc_info->control_a);
-
-		/* Check & clear STOP bit in control B register */
-		if (cntl_b & TODC_MK48TXX_DAY_CB) {
-			printk(KERN_INFO "TODC %s %s\n",
-				"real-time-clock was stopped.",
-				"Now starting...");
-
-			cntl_a |= todc_info->enable_write;
-			cntl_b &= ~TODC_MK48TXX_DAY_CB;/* Start Oscil */
-
-			todc_write_val(todc_info->control_a, cntl_a);
-			todc_write_val(todc_info->control_b, cntl_b);
-		}
-
-		/* Make sure READ & WRITE bits are cleared. */
-		cntl_a &= ~(todc_info->enable_write | todc_info->enable_read);
-		todc_write_val(todc_info->control_a, cntl_a);
-	}
-
-	return 0;
-}
-
-/*
- * There is some ugly stuff in that there are assumptions that for a mc146818,
- * the todc_info->control_a has the offset of the mc146818 Register B reg and
- * that the register'ss 'SET' bit is the same as the m48txx's write enable
- * bit in the control register of the m48txx (i.e., 0x80).
- *
- * It was done to make the code look simpler.
- */
-void
-todc_get_rtc_time(struct rtc_time *tm)
-{
-	uint	year = 0, mon = 0, mday = 0, hour = 0, min = 0, sec = 0;
-	uint	limit, i;
-	u_char	save_control, uip = 0;
-	extern void GregorianDay(struct rtc_time *);
-
-	spin_lock(&rtc_lock);
-	save_control = todc_read_val(todc_info->control_a);
-
-	if (todc_info->rtc_type != TODC_TYPE_MC146818) {
-		limit = 1;
-
-		switch (todc_info->rtc_type) {
-		case TODC_TYPE_DS1553:
-		case TODC_TYPE_DS1557:
-		case TODC_TYPE_DS1743:
-		case TODC_TYPE_DS1746:	/* XXXX BAD HACK -> FIX */
-		case TODC_TYPE_DS1747:
-		case TODC_TYPE_DS17285:
-			break;
-		default:
-			todc_write_val(todc_info->control_a,
-				(save_control | todc_info->enable_read));
-		}
-	} else
-		limit = 100000000;
-
-	for (i=0; i<limit; i++) {
-		if (todc_info->rtc_type == TODC_TYPE_MC146818)
-			uip = todc_read_val(todc_info->RTC_FREQ_SELECT);
-
-		sec = todc_read_val(todc_info->seconds) & 0x7f;
-		min = todc_read_val(todc_info->minutes) & 0x7f;
-		hour = todc_read_val(todc_info->hours) & 0x3f;
-		mday = todc_read_val(todc_info->day_of_month) & 0x3f;
-		mon = todc_read_val(todc_info->month) & 0x1f;
-		year = todc_read_val(todc_info->year) & 0xff;
-
-		if (todc_info->rtc_type == TODC_TYPE_MC146818) {
-			uip |= todc_read_val(todc_info->RTC_FREQ_SELECT);
-			if ((uip & RTC_UIP) == 0)
-				break;
-		}
-	}
-
-	if (todc_info->rtc_type != TODC_TYPE_MC146818) {
-		switch (todc_info->rtc_type) {
-		case TODC_TYPE_DS1553:
-		case TODC_TYPE_DS1557:
-		case TODC_TYPE_DS1743:
-		case TODC_TYPE_DS1746:	/* XXXX BAD HACK -> FIX */
-		case TODC_TYPE_DS1747:
-		case TODC_TYPE_DS17285:
-			break;
-		default:
-			save_control &= ~(todc_info->enable_read);
-			todc_write_val(todc_info->control_a, save_control);
-		}
-	}
-	spin_unlock(&rtc_lock);
-
-	if ((todc_info->rtc_type != TODC_TYPE_MC146818)
-			|| ((save_control & RTC_DM_BINARY) == 0)
-			|| RTC_ALWAYS_BCD) {
-		BCD_TO_BIN(sec);
-		BCD_TO_BIN(min);
-		BCD_TO_BIN(hour);
-		BCD_TO_BIN(mday);
-		BCD_TO_BIN(mon);
-		BCD_TO_BIN(year);
-	}
-
-	if ((year + 1900) < 1970) {
-		year += 100;
-	}
-
-	tm->tm_sec = sec;
-	tm->tm_min = min;
-	tm->tm_hour = hour;
-	tm->tm_mday = mday;
-	tm->tm_mon = mon;
-	tm->tm_year = year;
-
-	GregorianDay(tm);
-}
-
-int
-todc_set_rtc_time(struct rtc_time *tm)
-{
-	u_char save_control, save_freq_select = 0;
-
-	spin_lock(&rtc_lock);
-	save_control = todc_read_val(todc_info->control_a);
-
-	/* Assuming MK48T59_RTC_CA_WRITE & RTC_SET are equal */
-	todc_write_val(todc_info->control_a,
-		(save_control | todc_info->enable_write));
-	save_control &= ~(todc_info->enable_write); /* in case it was set */
-
-	if (todc_info->rtc_type == TODC_TYPE_MC146818) {
-		save_freq_select = todc_read_val(todc_info->RTC_FREQ_SELECT);
-		todc_write_val(todc_info->RTC_FREQ_SELECT,
-			save_freq_select | RTC_DIV_RESET2);
-	}
-
-	if ((todc_info->rtc_type != TODC_TYPE_MC146818)
-			|| ((save_control & RTC_DM_BINARY) == 0)
-			|| RTC_ALWAYS_BCD) {
-		BIN_TO_BCD(tm->tm_sec);
-		BIN_TO_BCD(tm->tm_min);
-		BIN_TO_BCD(tm->tm_hour);
-		BIN_TO_BCD(tm->tm_mon);
-		BIN_TO_BCD(tm->tm_mday);
-		BIN_TO_BCD(tm->tm_year);
-	}
-
-	todc_write_val(todc_info->seconds, tm->tm_sec);
-	todc_write_val(todc_info->minutes, tm->tm_min);
-	todc_write_val(todc_info->hours, tm->tm_hour);
-	todc_write_val(todc_info->month, tm->tm_mon);
-	todc_write_val(todc_info->day_of_month, tm->tm_mday);
-	todc_write_val(todc_info->year, tm->tm_year);
-
-	todc_write_val(todc_info->control_a, save_control);
-
-	if (todc_info->rtc_type == TODC_TYPE_MC146818)
-		todc_write_val(todc_info->RTC_FREQ_SELECT, save_freq_select);
-
-	spin_unlock(&rtc_lock);
-	return 0;
-}
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 322f86e93de5..ae249c6bbbcf 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -3,6 +3,8 @@
  *
  * 2004-2005 (c) Tundra Semiconductor Corp.
  * Author: Alex Bounine (alexandreb@tundra.com)
+ * Author: Roy Zang (tie-fei.zang@freescale.com)
+ * 	   Add pci interrupt router host
  *
  * 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
@@ -48,6 +50,8 @@
 
 u32 tsi108_pci_cfg_base;
 u32 tsi108_csr_vir_base;
+static struct device_node *pci_irq_node;
+static struct irq_host *pci_irq_host;
 
 extern u32 get_vir_csrbase(void);
 extern u32 tsi108_read_reg(u32 reg_offset);
@@ -378,6 +382,38 @@ static struct irq_chip tsi108_pci_irq = {
 	.unmask = tsi108_pci_irq_enable,
 };
 
+static int pci_irq_host_xlate(struct irq_host *h, struct device_node *ct,
+			    u32 *intspec, unsigned int intsize,
+			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
+{
+	*out_hwirq = intspec[0];
+	*out_flags = IRQ_TYPE_LEVEL_HIGH;
+	return 0;
+}
+
+static int pci_irq_host_map(struct irq_host *h, unsigned int virq,
+			  irq_hw_number_t hw)
+{	unsigned int irq;
+	DBG("%s(%d, 0x%lx)\n", __FUNCTION__, virq, hw);
+	if ((virq >= 1) && (virq <= 4)){
+		irq = virq + IRQ_PCI_INTAD_BASE - 1;
+		get_irq_desc(irq)->status |= IRQ_LEVEL;
+		set_irq_chip(irq, &tsi108_pci_irq);
+	}
+	return 0;
+}
+
+static int pci_irq_host_match(struct irq_host *h, struct device_node *node)
+{
+	return pci_irq_node == node;
+}
+
+static struct irq_host_ops pci_irq_host_ops = {
+	.match = pci_irq_host_match,
+	.map = pci_irq_host_map,
+	.xlate = pci_irq_host_xlate,
+};
+
 /*
  * Exported functions
  */
@@ -391,15 +427,15 @@ static struct irq_chip tsi108_pci_irq = {
  * to the MPIC.
  */
 
-void __init tsi108_pci_int_init(void)
+void __init tsi108_pci_int_init(struct device_node *node)
 {
-	u_int i;
-
 	DBG("Tsi108_pci_int_init: initializing PCI interrupts\n");
 
-	for (i = 0; i < NUM_PCI_IRQS; i++) {
-		irq_desc[i + IRQ_PCI_INTAD_BASE].chip = &tsi108_pci_irq;
-		irq_desc[i + IRQ_PCI_INTAD_BASE].status |= IRQ_LEVEL;
+	pci_irq_node = of_node_get(node);
+	pci_irq_host = irq_alloc_host(IRQ_HOST_MAP_LEGACY, 0, &pci_irq_host_ops, 0);
+	if (pci_irq_host == NULL) {
+		printk(KERN_ERR "pci_irq_host: failed to allocate irq host !\n");
+		return;
 	}
 
 	init_pci_source();
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 109d874ecfbe..51d97588e762 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -3,5 +3,10 @@
 ifdef CONFIG_PPC64
 EXTRA_CFLAGS += -mno-minimal-toc
 endif
-obj-y			+= xmon.o ppc-dis.o ppc-opc.o setjmp.o start.o \
-			   nonstdio.o
+
+obj-y			+= xmon.o setjmp.o start.o nonstdio.o
+
+ifdef CONFIG_XMON_DISASSEMBLY
+obj-y			+= ppc-dis.o ppc-opc.o
+obj-$(CONFIG_SPU_BASE)	+= spu-dis.o spu-opc.o
+endif
diff --git a/arch/powerpc/xmon/dis-asm.h b/arch/powerpc/xmon/dis-asm.h
new file mode 100644
index 000000000000..be3533b93f30
--- /dev/null
+++ b/arch/powerpc/xmon/dis-asm.h
@@ -0,0 +1,31 @@
+#ifndef _POWERPC_XMON_DIS_ASM_H
+#define _POWERPC_XMON_DIS_ASM_H
+/*
+ * Copyright (C) 2006 Michael Ellerman, IBM Corporation.
+ *
+ * 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.
+ */
+
+extern void print_address (unsigned long memaddr);
+
+#ifdef CONFIG_XMON_DISASSEMBLY
+extern int print_insn_powerpc(unsigned long insn, unsigned long memaddr);
+extern int print_insn_spu(unsigned long insn, unsigned long memaddr);
+#else
+static inline int print_insn_powerpc(unsigned long insn, unsigned long memaddr)
+{
+	printf("%.8x", insn);
+	return 0;
+}
+
+static inline int print_insn_spu(unsigned long insn, unsigned long memaddr)
+{
+	printf("%.8x", insn);
+	return 0;
+}
+#endif
+
+#endif /* _POWERPC_XMON_DIS_ASM_H */
diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c
index ac0a9d2427e0..89098f320ad5 100644
--- a/arch/powerpc/xmon/ppc-dis.c
+++ b/arch/powerpc/xmon/ppc-dis.c
@@ -1,5 +1,6 @@
 /* ppc-dis.c -- Disassemble PowerPC instructions
-   Copyright 1994 Free Software Foundation, Inc.
+   Copyright 1994, 1995, 2000, 2001, 2002, 2003, 2004, 2005, 2006
+   Free Software Foundation, Inc.
    Written by Ian Lance Taylor, Cygnus Support
 
 This file is part of GDB, GAS, and the GNU binutils.
@@ -16,27 +17,36 @@ the GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License
 along with this file; see the file COPYING.  If not, write to the Free
-Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
+Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
 
+#include <asm/cputable.h>
 #include "nonstdio.h"
 #include "ansidecl.h"
 #include "ppc.h"
-
-extern void print_address (unsigned long memaddr);
+#include "dis-asm.h"
 
 /* Print a PowerPC or POWER instruction.  */
 
 int
-print_insn_powerpc (unsigned long insn, unsigned long memaddr, int dialect)
+print_insn_powerpc (unsigned long insn, unsigned long memaddr)
 {
   const struct powerpc_opcode *opcode;
   const struct powerpc_opcode *opcode_end;
   unsigned long op;
+  int dialect;
 
-  if (dialect == 0)
-    dialect = PPC_OPCODE_PPC | PPC_OPCODE_CLASSIC | PPC_OPCODE_COMMON
+  dialect = PPC_OPCODE_PPC | PPC_OPCODE_CLASSIC | PPC_OPCODE_COMMON
 	      | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC;
 
+  if (cpu_has_feature(CPU_FTRS_POWER5))
+    dialect |= PPC_OPCODE_POWER5;
+
+  if (cpu_has_feature(CPU_FTRS_CELL))
+    dialect |= PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC;
+
+  if (cpu_has_feature(CPU_FTRS_POWER6))
+    dialect |= PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC;
+
   /* Get the major opcode of the instruction.  */
   op = PPC_OP (insn);
 
@@ -121,7 +131,8 @@ print_insn_powerpc (unsigned long insn, unsigned long memaddr, int dialect)
 	    }
 
 	  /* Print the operand as directed by the flags.  */
-	  if ((operand->flags & PPC_OPERAND_GPR) != 0)
+	  if ((operand->flags & PPC_OPERAND_GPR) != 0
+	      || ((operand->flags & PPC_OPERAND_GPR_0) != 0 && value != 0))
 	    printf("r%ld", value);
 	  else if ((operand->flags & PPC_OPERAND_FPR) != 0)
 	    printf("f%ld", value);
@@ -137,7 +148,7 @@ print_insn_powerpc (unsigned long insn, unsigned long memaddr, int dialect)
 	  else
 	    {
 	      if (operand->bits == 3)
-		printf("cr%d", value);
+		printf("cr%ld", value);
 	      else
 		{
 		  static const char *cbnames[4] = { "lt", "gt", "eq", "so" };
diff --git a/arch/powerpc/xmon/ppc-opc.c b/arch/powerpc/xmon/ppc-opc.c
index 5ee8fc32f824..5d841f4b3530 100644
--- a/arch/powerpc/xmon/ppc-opc.c
+++ b/arch/powerpc/xmon/ppc-opc.c
@@ -1,6 +1,6 @@
 /* ppc-opc.c -- PowerPC opcode list
-   Copyright 1994, 1995, 1996, 1997, 1998, 2000, 2001, 2002, 2003
-   Free Software Foundation, Inc.
+   Copyright 1994, 1995, 1996, 1997, 1998, 2000, 2001, 2002, 2003, 2004,
+   2005 Free Software Foundation, Inc.
    Written by Ian Lance Taylor, Cygnus Support
 
    This file is part of GDB, GAS, and the GNU binutils.
@@ -17,8 +17,8 @@
 
    You should have received a copy of the GNU General Public License
    along with this file; see the file COPYING.  If not, write to the Free
-   Software Foundation, 59 Temple Place - Suite 330, Boston, MA
-   02111-1307, USA.  */
+   Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA
+   02110-1301, USA.  */
 
 #include <linux/stddef.h>
 #include "nonstdio.h"
@@ -86,6 +86,8 @@ static unsigned long insert_sh6 (unsigned long, long, int, const char **);
 static long extract_sh6 (unsigned long, int, int *);
 static unsigned long insert_spr (unsigned long, long, int, const char **);
 static long extract_spr (unsigned long, int, int *);
+static unsigned long insert_sprg (unsigned long, long, int, const char **);
+static long extract_sprg (unsigned long, int, int *);
 static unsigned long insert_tbr (unsigned long, long, int, const char **);
 static long extract_tbr (unsigned long, int, int *);
 static unsigned long insert_ev2 (unsigned long, long, int, const char **);
@@ -196,8 +198,11 @@ const struct powerpc_operand powerpc_operands[] =
 #define BOE BO + 1
   { 5, 21, insert_boe, extract_boe, 0 },
 
+#define BH BOE + 1
+  { 2, 11, NULL, NULL, PPC_OPERAND_OPTIONAL },
+
   /* The BT field in an X or XL form instruction.  */
-#define BT BOE + 1
+#define BT BH + 1
   { 5, 21, NULL, NULL, PPC_OPERAND_CR },
 
   /* The condition register number portion of the BI field in a B form
@@ -301,10 +306,14 @@ const struct powerpc_operand powerpc_operands[] =
 #define L FXM4 + 1
   { 1, 21, NULL, NULL, PPC_OPERAND_OPTIONAL },
 
-  /* The LEV field in a POWER SC form instruction.  */
-#define LEV L + 1
+  /* The LEV field in a POWER SVC form instruction.  */
+#define SVC_LEV L + 1
   { 7, 5, NULL, NULL, 0 },
 
+  /* The LEV field in an SC form instruction.  */
+#define LEV SVC_LEV + 1
+  { 7, 5, NULL, NULL, PPC_OPERAND_OPTIONAL },
+
   /* The LI field in an I form instruction.  The lower two bits are
      forced to zero.  */
 #define LI LEV + 1
@@ -346,7 +355,7 @@ const struct powerpc_operand powerpc_operands[] =
 
   /* The MO field in an mbar instruction.  */
 #define MO MB6 + 1
-  { 5, 21, NULL, NULL, 0 },
+  { 5, 21, NULL, NULL, PPC_OPERAND_OPTIONAL },
 
   /* The NB field in an X form instruction.  The value 32 is stored as
      0.  */
@@ -364,30 +373,38 @@ const struct powerpc_operand powerpc_operands[] =
 #define RA_MASK (0x1f << 16)
   { 5, 16, NULL, NULL, PPC_OPERAND_GPR },
 
+  /* As above, but 0 in the RA field means zero, not r0.  */
+#define RA0 RA + 1
+  { 5, 16, NULL, NULL, PPC_OPERAND_GPR_0 },
+
   /* The RA field in the DQ form lq instruction, which has special
      value restrictions.  */
-#define RAQ RA + 1
-  { 5, 16, insert_raq, NULL, PPC_OPERAND_GPR },
+#define RAQ RA0 + 1
+  { 5, 16, insert_raq, NULL, PPC_OPERAND_GPR_0 },
 
   /* The RA field in a D or X form instruction which is an updating
      load, which means that the RA field may not be zero and may not
      equal the RT field.  */
 #define RAL RAQ + 1
-  { 5, 16, insert_ral, NULL, PPC_OPERAND_GPR },
+  { 5, 16, insert_ral, NULL, PPC_OPERAND_GPR_0 },
 
   /* The RA field in an lmw instruction, which has special value
      restrictions.  */
 #define RAM RAL + 1
-  { 5, 16, insert_ram, NULL, PPC_OPERAND_GPR },
+  { 5, 16, insert_ram, NULL, PPC_OPERAND_GPR_0 },
 
   /* The RA field in a D or X form instruction which is an updating
      store or an updating floating point load, which means that the RA
      field may not be zero.  */
 #define RAS RAM + 1
-  { 5, 16, insert_ras, NULL, PPC_OPERAND_GPR },
+  { 5, 16, insert_ras, NULL, PPC_OPERAND_GPR_0 },
+
+  /* The RA field of the tlbwe instruction, which is optional.  */
+#define RAOPT RAS + 1
+  { 5, 16, NULL, NULL, PPC_OPERAND_GPR | PPC_OPERAND_OPTIONAL },
 
   /* The RB field in an X, XO, M, or MDS form instruction.  */
-#define RB RAS + 1
+#define RB RAOPT + 1
 #define RB_MASK (0x1f << 11)
   { 5, 11, NULL, NULL, PPC_OPERAND_GPR },
 
@@ -408,15 +425,20 @@ const struct powerpc_operand powerpc_operands[] =
   /* The RS field of the DS form stq instruction, which has special
      value restrictions.  */
 #define RSQ RS + 1
-  { 5, 21, insert_rsq, NULL, PPC_OPERAND_GPR },
+  { 5, 21, insert_rsq, NULL, PPC_OPERAND_GPR_0 },
 
   /* The RT field of the DQ form lq instruction, which has special
      value restrictions.  */
 #define RTQ RSQ + 1
-  { 5, 21, insert_rtq, NULL, PPC_OPERAND_GPR },
+  { 5, 21, insert_rtq, NULL, PPC_OPERAND_GPR_0 },
+
+  /* The RS field of the tlbwe instruction, which is optional.  */
+#define RSO RTQ + 1
+#define RTO RSO
+  { 5, 21, NULL, NULL, PPC_OPERAND_GPR | PPC_OPERAND_OPTIONAL },
 
   /* The SH field in an X or M form instruction.  */
-#define SH RTQ + 1
+#define SH RSO + 1
 #define SH_MASK (0x1f << 11)
   { 5, 11, NULL, NULL, 0 },
 
@@ -425,8 +447,12 @@ const struct powerpc_operand powerpc_operands[] =
 #define SH6_MASK ((0x1f << 11) | (1 << 1))
   { 6, 1, insert_sh6, extract_sh6, 0 },
 
+  /* The SH field of the tlbwe instruction, which is optional.  */
+#define SHO SH6 + 1
+  { 5, 11,NULL, NULL, PPC_OPERAND_OPTIONAL },
+
   /* The SI field in a D form instruction.  */
-#define SI SH6 + 1
+#define SI SHO + 1
   { 16, 0, NULL, NULL, PPC_OPERAND_SIGNED },
 
   /* The SI field in a D form instruction when we accept a wide range
@@ -448,8 +474,7 @@ const struct powerpc_operand powerpc_operands[] =
 
   /* The SPRG register number in an XFX form m[ft]sprg instruction.  */
 #define SPRG SPRBAT + 1
-#define SPRG_MASK (0x3 << 16)
-  { 2, 16, NULL, NULL, 0 },
+  { 5, 16, insert_sprg, extract_sprg, 0 },
 
   /* The SR field in an X form instruction.  */
 #define SR SPRG + 1
@@ -536,10 +561,45 @@ const struct powerpc_operand powerpc_operands[] =
 #define WS_MASK (0x7 << 11)
   { 3, 11, NULL, NULL, 0 },
 
-  /* The L field in an mtmsrd instruction */
+  /* The L field in an mtmsrd or A form instruction.  */
 #define MTMSRD_L WS + 1
+#define A_L MTMSRD_L
   { 1, 16, NULL, NULL, PPC_OPERAND_OPTIONAL },
 
+  /* The DCM field in a Z form instruction.  */
+#define DCM MTMSRD_L + 1
+  { 6, 16, NULL, NULL, 0 },
+
+  /* Likewise, the DGM field in a Z form instruction.  */
+#define DGM DCM + 1
+  { 6, 16, NULL, NULL, 0 },
+
+#define TE DGM + 1
+  { 5, 11, NULL, NULL, 0 },
+
+#define RMC TE + 1
+  { 2, 21, NULL, NULL, 0 },
+
+#define R RMC + 1
+  { 1, 15, NULL, NULL, 0 },
+
+#define SP R + 1
+  { 2, 11, NULL, NULL, 0 },
+
+#define S SP + 1
+  { 1, 11, NULL, NULL, 0 },
+
+  /* SH field starting at bit position 16.  */
+#define SH16 S + 1
+  { 6, 10, NULL, NULL, 0 },
+
+  /* The L field in an X form with the RT field fixed instruction.  */
+#define XRT_L SH16 + 1
+  { 2, 21, NULL, NULL, PPC_OPERAND_OPTIONAL },
+
+  /* The EH field in larx instruction.  */
+#define EH XRT_L + 1
+  { 1, 0, NULL, NULL, PPC_OPERAND_OPTIONAL },
 };
 
 /* The functions used to insert and extract complicated operands.  */
@@ -550,7 +610,6 @@ const struct powerpc_operand powerpc_operands[] =
    and the extraction function just checks that the fields are the
    same.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_bat (unsigned long insn,
 	    long value ATTRIBUTE_UNUSED,
@@ -576,7 +635,6 @@ extract_bat (unsigned long insn,
    and the extraction function just checks that the fields are the
    same.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_bba (unsigned long insn,
 	    long value ATTRIBUTE_UNUSED,
@@ -599,7 +657,6 @@ extract_bba (unsigned long insn,
 /* The BD field in a B form instruction.  The lower two bits are
    forced to zero.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_bd (unsigned long insn,
 	   long value,
@@ -609,7 +666,6 @@ insert_bd (unsigned long insn,
   return insn | (value & 0xfffc);
 }
 
-/*ARGSUSED*/
 static long
 extract_bd (unsigned long insn,
 	    int dialect ATTRIBUTE_UNUSED,
@@ -631,7 +687,6 @@ extract_bd (unsigned long insn,
    in BO field, the "a" bit is 00010 for branch on CR(BI) and 01000
    for branch on CTR.  We only handle the taken/not-taken hint here.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_bdm (unsigned long insn,
 	    long value,
@@ -677,7 +732,6 @@ extract_bdm (unsigned long insn,
    This is like BDM, above, except that the branch is expected to be
    taken.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_bdp (unsigned long insn,
 	    long value,
@@ -831,7 +885,6 @@ extract_boe (unsigned long insn,
 /* The DQ field in a DQ form instruction.  This is like D, but the
    lower four bits are forced to zero. */
 
-/*ARGSUSED*/
 static unsigned long
 insert_dq (unsigned long insn,
 	   long value,
@@ -843,7 +896,6 @@ insert_dq (unsigned long insn,
   return insn | (value & 0xfff0);
 }
 
-/*ARGSUSED*/
 static long
 extract_dq (unsigned long insn,
 	    int dialect ATTRIBUTE_UNUSED,
@@ -918,7 +970,6 @@ extract_ev8 (unsigned long insn,
 /* The DS field in a DS form instruction.  This is like D, but the
    lower two bits are forced to zero.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_ds (unsigned long insn,
 	   long value,
@@ -930,7 +981,6 @@ insert_ds (unsigned long insn,
   return insn | (value & 0xfffc);
 }
 
-/*ARGSUSED*/
 static long
 extract_ds (unsigned long insn,
 	    int dialect ATTRIBUTE_UNUSED,
@@ -941,7 +991,6 @@ extract_ds (unsigned long insn,
 
 /* The DE field in a DE form instruction.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_de (unsigned long insn,
 	   long value,
@@ -953,7 +1002,6 @@ insert_de (unsigned long insn,
   return insn | ((value << 4) & 0xfff0);
 }
 
-/*ARGSUSED*/
 static long
 extract_de (unsigned long insn,
 	    int dialect ATTRIBUTE_UNUSED,
@@ -964,7 +1012,6 @@ extract_de (unsigned long insn,
 
 /* The DES field in a DES form instruction.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_des (unsigned long insn,
 	    long value,
@@ -978,7 +1025,6 @@ insert_des (unsigned long insn,
   return insn | ((value << 2) & 0xfff0);
 }
 
-/*ARGSUSED*/
 static long
 extract_des (unsigned long insn,
 	     int dialect ATTRIBUTE_UNUSED,
@@ -995,17 +1041,33 @@ insert_fxm (unsigned long insn,
 	    int dialect,
 	    const char **errmsg)
 {
+  /* If we're handling the mfocrf and mtocrf insns ensure that exactly
+     one bit of the mask field is set.  */
+  if ((insn & (1 << 20)) != 0)
+    {
+      if (value == 0 || (value & -value) != value)
+	{
+	  *errmsg = _("invalid mask field");
+	  value = 0;
+	}
+    }
+
   /* If the optional field on mfcr is missing that means we want to use
      the old form of the instruction that moves the whole cr.  In that
      case we'll have VALUE zero.  There doesn't seem to be a way to
      distinguish this from the case where someone writes mfcr %r3,0.  */
-  if (value == 0)
+  else if (value == 0)
     ;
 
   /* If only one bit of the FXM field is set, we can use the new form
      of the instruction, which is faster.  Unlike the Power4 branch hint
-     encoding, this is not backward compatible.  */
-  else if ((dialect & PPC_OPCODE_POWER4) != 0 && (value & -value) == value)
+     encoding, this is not backward compatible.  Do not generate the
+     new form unless -mpower4 has been given, or -many and the two
+     operand form of mfcr was used.  */
+  else if ((value & -value) == value
+	   && ((dialect & PPC_OPCODE_POWER4) != 0
+	       || ((dialect & PPC_OPCODE_ANY) != 0
+		   && (insn & (0x3ff << 1)) == 19 << 1)))
     insn |= 1 << 20;
 
   /* Any other value on mfcr is an error.  */
@@ -1020,7 +1082,7 @@ insert_fxm (unsigned long insn,
 
 static long
 extract_fxm (unsigned long insn,
-	     int dialect,
+	     int dialect ATTRIBUTE_UNUSED,
 	     int *invalid)
 {
   long mask = (insn >> 12) & 0xff;
@@ -1028,14 +1090,9 @@ extract_fxm (unsigned long insn,
   /* Is this a Power4 insn?  */
   if ((insn & (1 << 20)) != 0)
     {
-      if ((dialect & PPC_OPCODE_POWER4) == 0)
+      /* Exactly one bit of MASK should be set.  */
+      if (mask == 0 || (mask & -mask) != mask)
 	*invalid = 1;
-      else
-	{
-	  /* Exactly one bit of MASK should be set.  */
-	  if (mask == 0 || (mask & -mask) != mask)
-	    *invalid = 1;
-	}
     }
 
   /* Check that non-power4 form of mfcr has a zero MASK.  */
@@ -1051,7 +1108,6 @@ extract_fxm (unsigned long insn,
 /* The LI field in an I form instruction.  The lower two bits are
    forced to zero.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_li (unsigned long insn,
 	   long value,
@@ -1063,7 +1119,6 @@ insert_li (unsigned long insn,
   return insn | (value & 0x3fffffc);
 }
 
-/*ARGSUSED*/
 static long
 extract_li (unsigned long insn,
 	    int dialect ATTRIBUTE_UNUSED,
@@ -1163,7 +1218,6 @@ extract_mbe (unsigned long insn,
 /* The MB or ME field in an MD or MDS form instruction.  The high bit
    is wrapped to the low end.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_mb6 (unsigned long insn,
 	    long value,
@@ -1173,7 +1227,6 @@ insert_mb6 (unsigned long insn,
   return insn | ((value & 0x1f) << 6) | (value & 0x20);
 }
 
-/*ARGSUSED*/
 static long
 extract_mb6 (unsigned long insn,
 	     int dialect ATTRIBUTE_UNUSED,
@@ -1198,7 +1251,6 @@ insert_nb (unsigned long insn,
   return insn | ((value & 0x1f) << 11);
 }
 
-/*ARGSUSED*/
 static long
 extract_nb (unsigned long insn,
 	    int dialect ATTRIBUTE_UNUSED,
@@ -1217,7 +1269,6 @@ extract_nb (unsigned long insn,
    invalid, since we never want to recognize an instruction which uses
    a field of this type.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_nsi (unsigned long insn,
 	    long value,
@@ -1269,7 +1320,6 @@ insert_ram (unsigned long insn,
 /* The RA field in the DQ form lq instruction, which has special
    value restrictions.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_raq (unsigned long insn,
 	    long value,
@@ -1304,7 +1354,6 @@ insert_ras (unsigned long insn,
    function just copies the BT field into the BA field, and the
    extraction function just checks that the fields are the same.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_rbs (unsigned long insn,
 	    long value ATTRIBUTE_UNUSED,
@@ -1327,7 +1376,6 @@ extract_rbs (unsigned long insn,
 /* The RT field of the DQ form lq instruction, which has special
    value restrictions.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_rtq (unsigned long insn,
 	    long value,
@@ -1342,7 +1390,6 @@ insert_rtq (unsigned long insn,
 /* The RS field of the DS form stq instruction, which has special
    value restrictions.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_rsq (unsigned long insn,
 	    long value ATTRIBUTE_UNUSED,
@@ -1356,7 +1403,6 @@ insert_rsq (unsigned long insn,
 
 /* The SH field in an MD form instruction.  This is split.  */
 
-/*ARGSUSED*/
 static unsigned long
 insert_sh6 (unsigned long insn,
 	    long value,
@@ -1366,7 +1412,6 @@ insert_sh6 (unsigned long insn,
   return insn | ((value & 0x1f) << 11) | ((value & 0x20) >> 4);
 }
 
-/*ARGSUSED*/
 static long
 extract_sh6 (unsigned long insn,
 	     int dialect ATTRIBUTE_UNUSED,
@@ -1395,6 +1440,47 @@ extract_spr (unsigned long insn,
   return ((insn >> 16) & 0x1f) | ((insn >> 6) & 0x3e0);
 }
 
+/* Some dialects have 8 SPRG registers instead of the standard 4.  */
+
+static unsigned long
+insert_sprg (unsigned long insn,
+	     long value,
+	     int dialect,
+	     const char **errmsg)
+{
+  /* This check uses PPC_OPCODE_403 because PPC405 is later defined
+     as a synonym.  If ever a 405 specific dialect is added this
+     check should use that instead.  */
+  if (value > 7
+      || (value > 3
+	  && (dialect & (PPC_OPCODE_BOOKE | PPC_OPCODE_403)) == 0))
+    *errmsg = _("invalid sprg number");
+
+  /* If this is mfsprg4..7 then use spr 260..263 which can be read in
+     user mode.  Anything else must use spr 272..279.  */
+  if (value <= 3 || (insn & 0x100) != 0)
+    value |= 0x10;
+
+  return insn | ((value & 0x17) << 16);
+}
+
+static long
+extract_sprg (unsigned long insn,
+	      int dialect,
+	      int *invalid)
+{
+  unsigned long val = (insn >> 16) & 0x1f;
+
+  /* mfsprg can use 260..263 and 272..279.  mtsprg only uses spr 272..279
+     If not BOOKE or 405, then both use only 272..275.  */
+  if (val <= 3
+      || (val < 0x10 && (insn & 0x100) != 0)
+      || (val - 0x10 > 3
+	  && (dialect & (PPC_OPCODE_BOOKE | PPC_OPCODE_403)) == 0))
+    *invalid = 1;
+  return val & 7;
+}
+
 /* The TBR field in an XFX instruction.  This is just like SPR, but it
    is optional.  When TBR is omitted, it must be inserted as 268 (the
    magic number of the TB register).  These functions treat 0
@@ -1460,6 +1546,9 @@ extract_tbr (unsigned long insn,
 /* An A_MASK with the FRA and FRC fields fixed.  */
 #define AFRAFRC_MASK (A_MASK | FRA_MASK | FRC_MASK)
 
+/* An AFRAFRC_MASK, but with L bit clear.  */
+#define AFRALFRC_MASK (AFRAFRC_MASK & ~((unsigned long) 1 << 16))
+
 /* A B form instruction.  */
 #define B(op, aa, lk) (OP (op) | ((((unsigned long)(aa)) & 1) << 1) | ((lk) & 1))
 #define B_MASK B (0x3f, 1, 1)
@@ -1494,11 +1583,11 @@ extract_tbr (unsigned long insn,
 
 /* An Context form instruction.  */
 #define CTX(op, xop)   (OP (op) | (((unsigned long)(xop)) & 0x7))
-#define CTX_MASK       CTX(0x3f, 0x7)
+#define CTX_MASK CTX(0x3f, 0x7)
 
 /* An User Context form instruction.  */
 #define UCTX(op, xop)  (OP (op) | (((unsigned long)(xop)) & 0x1f))
-#define UCTX_MASK      UCTX(0x3f, 0x1f)
+#define UCTX_MASK UCTX(0x3f, 0x1f)
 
 /* The main opcode mask with the RA field clear.  */
 #define DRA_MASK (OP_MASK | RA_MASK)
@@ -1570,12 +1659,21 @@ extract_tbr (unsigned long insn,
 /* An X form instruction.  */
 #define X(op, xop) (OP (op) | ((((unsigned long)(xop)) & 0x3ff) << 1))
 
+/* A Z form instruction.  */
+#define Z(op, xop) (OP (op) | ((((unsigned long)(xop)) & 0x1ff) << 1))
+
 /* An X form instruction with the RC bit specified.  */
 #define XRC(op, xop, rc) (X ((op), (xop)) | ((rc) & 1))
 
+/* A Z form instruction with the RC bit specified.  */
+#define ZRC(op, xop, rc) (Z ((op), (xop)) | ((rc) & 1))
+
 /* The mask for an X form instruction.  */
 #define X_MASK XRC (0x3f, 0x3ff, 1)
 
+/* The mask for a Z form instruction.  */
+#define Z_MASK ZRC (0x3f, 0x1ff, 1)
+
 /* An X_MASK with the RA field fixed.  */
 #define XRA_MASK (X_MASK | RA_MASK)
 
@@ -1585,6 +1683,9 @@ extract_tbr (unsigned long insn,
 /* An X_MASK with the RT field fixed.  */
 #define XRT_MASK (X_MASK | RT_MASK)
 
+/* An XRT_MASK mask with the L bits clear.  */
+#define XLRT_MASK (XRT_MASK & ~((unsigned long) 0x3 << 21))
+
 /* An X_MASK with the RA and RB fields fixed.  */
 #define XRARB_MASK (X_MASK | RA_MASK | RB_MASK)
 
@@ -1597,8 +1698,8 @@ extract_tbr (unsigned long insn,
 /* An XRTRA_MASK, but with L bit clear.  */
 #define XRTLRA_MASK (XRTRA_MASK & ~((unsigned long) 1 << 21))
 
-/* An X form comparison instruction.  */
-#define XCMPL(op, xop, l) (X ((op), (xop)) | ((((unsigned long)(l)) & 1) << 21))
+/* An X form instruction with the L bit specified.  */
+#define XOPL(op, xop, l) (X ((op), (xop)) | ((((unsigned long)(l)) & 1) << 21))
 
 /* The mask for an X form comparison instruction.  */
 #define XCMP_MASK (X_MASK | (((unsigned long)1) << 22))
@@ -1621,6 +1722,9 @@ extract_tbr (unsigned long insn,
 /* An X form sync instruction with everything filled in except the LS field.  */
 #define XSYNC_MASK (0xff9fffff)
 
+/* An X_MASK, but with the EH bit clear.  */
+#define XEH_MASK (X_MASK & ~((unsigned long )1))
+
 /* An X form AltiVec dss instruction.  */
 #define XDSS(op, xop, a) (X ((op), (xop)) | ((((unsigned long)(a)) & 1) << 25))
 #define XDSS_MASK XDSS(0x3f, 0x3ff, 1)
@@ -1663,6 +1767,9 @@ extract_tbr (unsigned long insn,
 #define XLYBB_MASK (XLYLK_MASK | BB_MASK)
 #define XLBOCBBB_MASK (XLOCB_MASK | BB_MASK)
 
+/* A mask for branch instructions using the BH field.  */
+#define XLBH_MASK (XL_MASK | (0x1c << 11))
+
 /* An XL_MASK with the BO and BB fields fixed.  */
 #define XLBOBB_MASK (XL_MASK | BO_MASK | BB_MASK)
 
@@ -1682,11 +1789,12 @@ extract_tbr (unsigned long insn,
 #define XS_MASK XS (0x3f, 0x1ff, 1)
 
 /* A mask for the FXM version of an XFX form instruction.  */
-#define XFXFXM_MASK (X_MASK | (1 << 11))
+#define XFXFXM_MASK (X_MASK | (1 << 11) | (1 << 20))
 
 /* An XFX form instruction with the FXM field filled in.  */
-#define XFXM(op, xop, fxm) \
-  (X ((op), (xop)) | ((((unsigned long)(fxm)) & 0xff) << 12))
+#define XFXM(op, xop, fxm, p4) \
+  (X ((op), (xop)) | ((((unsigned long)(fxm)) & 0xff) << 12) \
+   | ((unsigned long)(p4) << 20))
 
 /* An XFX form instruction with the SPR field filled in.  */
 #define XSPR(op, xop, spr) \
@@ -1699,7 +1807,7 @@ extract_tbr (unsigned long insn,
 
 /* An XFX form instruction with the SPR field filled in except for the
    SPRG field.  */
-#define XSPRG_MASK (XSPR_MASK &~ SPRG_MASK)
+#define XSPRG_MASK (XSPR_MASK & ~(0x17 << 16))
 
 /* An X form instruction with everything filled in except the E field.  */
 #define XE_MASK (0xffff7fff)
@@ -1769,6 +1877,9 @@ extract_tbr (unsigned long insn,
 #define PPCCOM	PPC_OPCODE_PPC | PPC_OPCODE_COMMON
 #define NOPOWER4 PPC_OPCODE_NOPOWER4 | PPCCOM
 #define POWER4	PPC_OPCODE_POWER4
+#define POWER5	PPC_OPCODE_POWER5
+#define POWER6	PPC_OPCODE_POWER6
+#define CELL	PPC_OPCODE_CELL
 #define PPC32   PPC_OPCODE_32 | PPC_OPCODE_PPC
 #define PPC64   PPC_OPCODE_64 | PPC_OPCODE_PPC
 #define PPC403	PPC_OPCODE_403
@@ -1776,7 +1887,7 @@ extract_tbr (unsigned long insn,
 #define PPC440	PPC_OPCODE_440
 #define PPC750	PPC
 #define PPC860	PPC
-#define PPCVEC	PPC_OPCODE_ALTIVEC | PPC_OPCODE_PPC
+#define PPCVEC	PPC_OPCODE_ALTIVEC
 #define	POWER   PPC_OPCODE_POWER
 #define	POWER2	PPC_OPCODE_POWER | PPC_OPCODE_POWER2
 #define PPCPWR2	PPC_OPCODE_PPC | PPC_OPCODE_POWER | PPC_OPCODE_POWER2
@@ -1790,6 +1901,7 @@ extract_tbr (unsigned long insn,
 #define BOOKE	PPC_OPCODE_BOOKE
 #define BOOKE64	PPC_OPCODE_BOOKE64
 #define CLASSIC	PPC_OPCODE_CLASSIC
+#define PPCE300 PPC_OPCODE_E300
 #define PPCSPE	PPC_OPCODE_SPE
 #define PPCISEL	PPC_OPCODE_ISEL
 #define PPCEFS	PPC_OPCODE_EFS
@@ -1952,6 +2064,41 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "nmaclhwso.",	XO(4,494,1,1), XO_MASK,	PPC405|PPC440,	{ RT, RA, RB } },
 { "mfvscr",  VX(4, 1540), VX_MASK,	PPCVEC,		{ VD } },
 { "mtvscr",  VX(4, 1604), VX_MASK,	PPCVEC,		{ VB } },
+
+  /* Double-precision opcodes.  */
+  /* Some of these conflict with AltiVec, so move them before, since
+     PPCVEC includes the PPC_OPCODE_PPC set.  */
+{ "efscfd",   VX(4, 719), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdabs",   VX(4, 740), VX_MASK,	PPCEFS,		{ RS, RA } },
+{ "efdnabs",  VX(4, 741), VX_MASK,	PPCEFS,		{ RS, RA } },
+{ "efdneg",   VX(4, 742), VX_MASK,	PPCEFS,		{ RS, RA } },
+{ "efdadd",   VX(4, 736), VX_MASK,	PPCEFS,		{ RS, RA, RB } },
+{ "efdsub",   VX(4, 737), VX_MASK,	PPCEFS,		{ RS, RA, RB } },
+{ "efdmul",   VX(4, 744), VX_MASK,	PPCEFS,		{ RS, RA, RB } },
+{ "efddiv",   VX(4, 745), VX_MASK,	PPCEFS,		{ RS, RA, RB } },
+{ "efdcmpgt", VX(4, 748), VX_MASK,	PPCEFS,		{ CRFD, RA, RB } },
+{ "efdcmplt", VX(4, 749), VX_MASK,	PPCEFS,		{ CRFD, RA, RB } },
+{ "efdcmpeq", VX(4, 750), VX_MASK,	PPCEFS,		{ CRFD, RA, RB } },
+{ "efdtstgt", VX(4, 764), VX_MASK,	PPCEFS,		{ CRFD, RA, RB } },
+{ "efdtstlt", VX(4, 765), VX_MASK,	PPCEFS,		{ CRFD, RA, RB } },
+{ "efdtsteq", VX(4, 766), VX_MASK,	PPCEFS,		{ CRFD, RA, RB } },
+{ "efdcfsi",  VX(4, 753), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdcfsid", VX(4, 739), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdcfui",  VX(4, 752), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdcfuid", VX(4, 738), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdcfsf",  VX(4, 755), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdcfuf",  VX(4, 754), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctsi",  VX(4, 757), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctsidz",VX(4, 747), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctsiz", VX(4, 762), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctui",  VX(4, 756), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctuidz",VX(4, 746), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctuiz", VX(4, 760), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctsf",  VX(4, 759), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdctuf",  VX(4, 758), VX_MASK,	PPCEFS,		{ RS, RB } },
+{ "efdcfs",   VX(4, 751), VX_MASK,	PPCEFS,		{ RS, RB } },
+  /* End of double-precision opcodes.  */
+
 { "vaddcuw", VX(4,  384), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
 { "vaddfp",  VX(4,   10), VX_MASK, 	PPCVEC,		{ VD, VA, VB } },
 { "vaddsbs", VX(4,  768), VX_MASK,	PPCVEC,		{ VD, VA, VB } },
@@ -2389,16 +2536,16 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "li",	     OP(14),	DRA_MASK,	PPCCOM,		{ RT, SI } },
 { "lil",     OP(14),	DRA_MASK,	PWRCOM,		{ RT, SI } },
-{ "addi",    OP(14),	OP_MASK,	PPCCOM,		{ RT, RA, SI } },
-{ "cal",     OP(14),	OP_MASK,	PWRCOM,		{ RT, D, RA } },
-{ "subi",    OP(14),	OP_MASK,	PPCCOM,		{ RT, RA, NSI } },
-{ "la",	     OP(14),	OP_MASK,	PPCCOM,		{ RT, D, RA } },
+{ "addi",    OP(14),	OP_MASK,	PPCCOM,		{ RT, RA0, SI } },
+{ "cal",     OP(14),	OP_MASK,	PWRCOM,		{ RT, D, RA0 } },
+{ "subi",    OP(14),	OP_MASK,	PPCCOM,		{ RT, RA0, NSI } },
+{ "la",	     OP(14),	OP_MASK,	PPCCOM,		{ RT, D, RA0 } },
 
 { "lis",     OP(15),	DRA_MASK,	PPCCOM,		{ RT, SISIGNOPT } },
 { "liu",     OP(15),	DRA_MASK,	PWRCOM,		{ RT, SISIGNOPT } },
-{ "addis",   OP(15),	OP_MASK,	PPCCOM,		{ RT,RA,SISIGNOPT } },
-{ "cau",     OP(15),	OP_MASK,	PWRCOM,		{ RT,RA,SISIGNOPT } },
-{ "subis",   OP(15),	OP_MASK,	PPCCOM,		{ RT, RA, NSI } },
+{ "addis",   OP(15),	OP_MASK,	PPCCOM,		{ RT,RA0,SISIGNOPT } },
+{ "cau",     OP(15),	OP_MASK,	PWRCOM,		{ RT,RA0,SISIGNOPT } },
+{ "subis",   OP(15),	OP_MASK,	PPCCOM,		{ RT, RA0, NSI } },
 
 { "bdnz-",   BBO(16,BODNZ,0,0),      BBOATBI_MASK, PPCCOM,	{ BDM } },
 { "bdnz+",   BBO(16,BODNZ,0,0),      BBOATBI_MASK, PPCCOM,	{ BDP } },
@@ -2665,9 +2812,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "bcla+",   B(16,1,1),	B_MASK,		PPCCOM,		{ BOE, BI, BDPA } },
 { "bcla",    B(16,1,1),	B_MASK,		COM,		{ BO, BI, BDA } },
 
-{ "sc",      SC(17,1,0), 0xffffffff,	PPC,		{ 0 } },
-{ "svc",     SC(17,0,0), SC_MASK,	POWER,		{ LEV, FL1, FL2 } },
-{ "svcl",    SC(17,0,1), SC_MASK,	POWER,		{ LEV, FL1, FL2 } },
+{ "sc",      SC(17,1,0), SC_MASK,	PPC,		{ LEV } },
+{ "svc",     SC(17,0,0), SC_MASK,	POWER,		{ SVC_LEV, FL1, FL2 } },
+{ "svcl",    SC(17,0,1), SC_MASK,	POWER,		{ SVC_LEV, FL1, FL2 } },
 { "svca",    SC(17,1,0), SC_MASK,	PWRCOM,		{ SV } },
 { "svcla",   SC(17,1,1), SC_MASK,	POWER,		{ SV } },
 
@@ -2890,12 +3037,12 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "bdzflrl", XLO(19,BODZF,16,1), XLBOBB_MASK, PPCCOM,	{ BI } },
 { "bdzflrl-",XLO(19,BODZF,16,1), XLBOBB_MASK, NOPOWER4,	{ BI } },
 { "bdzflrl+",XLO(19,BODZFP,16,1), XLBOBB_MASK, NOPOWER4, { BI } },
-{ "bclr",    XLLK(19,16,0), XLYBB_MASK,	PPCCOM,		{ BO, BI } },
-{ "bclrl",   XLLK(19,16,1), XLYBB_MASK,	PPCCOM,		{ BO, BI } },
 { "bclr+",   XLYLK(19,16,1,0), XLYBB_MASK, PPCCOM,	{ BOE, BI } },
 { "bclrl+",  XLYLK(19,16,1,1), XLYBB_MASK, PPCCOM,	{ BOE, BI } },
 { "bclr-",   XLYLK(19,16,0,0), XLYBB_MASK, PPCCOM,	{ BOE, BI } },
 { "bclrl-",  XLYLK(19,16,0,1), XLYBB_MASK, PPCCOM,	{ BOE, BI } },
+{ "bclr",    XLLK(19,16,0), XLBH_MASK,	PPCCOM,		{ BO, BI, BH } },
+{ "bclrl",   XLLK(19,16,1), XLBH_MASK,	PPCCOM,		{ BO, BI, BH } },
 { "bcr",     XLLK(19,16,0), XLBB_MASK,	PWRCOM,		{ BO, BI } },
 { "bcrl",    XLLK(19,16,1), XLBB_MASK,	PWRCOM,		{ BO, BI } },
 { "bclre",   XLLK(19,17,0), XLBB_MASK,	BOOKE64,	{ BO, BI } },
@@ -2924,14 +3071,23 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "crand",   XL(19,257), XL_MASK,	COM,		{ BT, BA, BB } },
 
+{ "hrfid",   XL(19,274), 0xffffffff,	POWER5 | CELL,	{ 0 } },
+
 { "crset",   XL(19,289), XL_MASK,	PPCCOM,		{ BT, BAT, BBA } },
 { "creqv",   XL(19,289), XL_MASK,	COM,		{ BT, BA, BB } },
 
+{ "doze",    XL(19,402), 0xffffffff,	POWER6,		{ 0 } },
+
 { "crorc",   XL(19,417), XL_MASK,	COM,		{ BT, BA, BB } },
 
+{ "nap",     XL(19,434), 0xffffffff,	POWER6,		{ 0 } },
+
 { "crmove",  XL(19,449), XL_MASK,	PPCCOM,		{ BT, BA, BBA } },
 { "cror",    XL(19,449), XL_MASK,	COM,		{ BT, BA, BB } },
 
+{ "sleep",   XL(19,466), 0xffffffff,	POWER6,		{ 0 } },
+{ "rvwinkle", XL(19,498), 0xffffffff,	POWER6,		{ 0 } },
+
 { "bctr",    XLO(19,BOU,528,0), XLBOBIBB_MASK, COM,	{ 0 } },
 { "bctrl",   XLO(19,BOU,528,1), XLBOBIBB_MASK, COM,	{ 0 } },
 { "bltctr",  XLOCB(19,BOT,CBLT,528,0),  XLBOCBBB_MASK, PPCCOM,	{ CR } },
@@ -3074,12 +3230,12 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "bfctrl-", XLO(19,BOFM4,528,1), XLBOBB_MASK, POWER4, { BI } },
 { "bfctrl+", XLO(19,BOFP,528,1), XLBOBB_MASK, NOPOWER4, { BI } },
 { "bfctrl+", XLO(19,BOFP4,528,1), XLBOBB_MASK, POWER4, { BI } },
-{ "bcctr",   XLLK(19,528,0),     XLYBB_MASK,  PPCCOM,	{ BO, BI } },
 { "bcctr-",  XLYLK(19,528,0,0),  XLYBB_MASK,  PPCCOM,	{ BOE, BI } },
 { "bcctr+",  XLYLK(19,528,1,0),  XLYBB_MASK,  PPCCOM,	{ BOE, BI } },
-{ "bcctrl",  XLLK(19,528,1),     XLYBB_MASK,  PPCCOM,	{ BO, BI } },
 { "bcctrl-", XLYLK(19,528,0,1),  XLYBB_MASK,  PPCCOM,	{ BOE, BI } },
 { "bcctrl+", XLYLK(19,528,1,1),  XLYBB_MASK,  PPCCOM,	{ BOE, BI } },
+{ "bcctr",   XLLK(19,528,0),     XLBH_MASK,   PPCCOM,	{ BO, BI, BH } },
+{ "bcctrl",  XLLK(19,528,1),     XLBH_MASK,   PPCCOM,	{ BO, BI, BH } },
 { "bcc",     XLLK(19,528,0),     XLBB_MASK,   PWRCOM,	{ BO, BI } },
 { "bccl",    XLLK(19,528,1),     XLBB_MASK,   PWRCOM,	{ BO, BI } },
 { "bcctre",  XLLK(19,529,0),     XLYBB_MASK,  BOOKE64,	{ BO, BI } },
@@ -3158,8 +3314,8 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "rldcr",   MDS(30,9,0), MDS_MASK,	PPC64,		{ RA, RS, RB, ME6 } },
 { "rldcr.",  MDS(30,9,1), MDS_MASK,	PPC64,		{ RA, RS, RB, ME6 } },
 
-{ "cmpw",    XCMPL(31,0,0), XCMPL_MASK, PPCCOM,		{ OBF, RA, RB } },
-{ "cmpd",    XCMPL(31,0,1), XCMPL_MASK, PPC64,		{ OBF, RA, RB } },
+{ "cmpw",    XOPL(31,0,0), XCMPL_MASK, PPCCOM,		{ OBF, RA, RB } },
+{ "cmpd",    XOPL(31,0,1), XCMPL_MASK, PPC64,		{ OBF, RA, RB } },
 { "cmp",     X(31,0),	XCMP_MASK,	PPC,		{ BF, L, RA, RB } },
 { "cmp",     X(31,0),	XCMPL_MASK,	PWRCOM,		{ BF, RA, RB } },
 
@@ -3228,17 +3384,18 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "iseleq",  X(31,79),      X_MASK,	PPCISEL,	{ RT, RA, RB } },
 { "isel",    XISEL(31,15),  XISEL_MASK,	PPCISEL,	{ RT, RA, RB, CRB } },
 
-{ "mfcr",    X(31,19),	XRARB_MASK,	NOPOWER4,	{ RT } },
+{ "mfocrf",  XFXM(31,19,0,1), XFXFXM_MASK, COM,		{ RT, FXM } },
+{ "mfcr",    X(31,19),	XRARB_MASK,	NOPOWER4 | COM,	{ RT } },
 { "mfcr",    X(31,19),	XFXFXM_MASK,	POWER4,		{ RT, FXM4 } },
 
-{ "lwarx",   X(31,20),	X_MASK,		PPC,		{ RT, RA, RB } },
+{ "lwarx",   X(31,20),	XEH_MASK,	PPC,		{ RT, RA0, RB, EH } },
 
-{ "ldx",     X(31,21),	X_MASK,		PPC64,		{ RT, RA, RB } },
+{ "ldx",     X(31,21),	X_MASK,		PPC64,		{ RT, RA0, RB } },
 
-{ "icbt",    X(31,22),	X_MASK,		BOOKE,		{ CT, RA, RB } },
+{ "icbt",    X(31,22),	X_MASK,		BOOKE|PPCE300,	{ CT, RA, RB } },
 { "icbt",    X(31,262),	XRT_MASK,	PPC403,		{ RA, RB } },
 
-{ "lwzx",    X(31,23),	X_MASK,		PPCCOM,		{ RT, RA, RB } },
+{ "lwzx",    X(31,23),	X_MASK,		PPCCOM,		{ RT, RA0, RB } },
 { "lx",      X(31,23),	X_MASK,		PWRCOM,		{ RT, RA, RB } },
 
 { "slw",     XRC(31,24,0), X_MASK,	PPCCOM,		{ RA, RS, RB } },
@@ -3262,10 +3419,10 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "icbte",   X(31,30),	X_MASK,		BOOKE64,	{ CT, RA, RB } },
 
-{ "lwzxe",   X(31,31),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lwzxe",   X(31,31),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
-{ "cmplw",   XCMPL(31,32,0), XCMPL_MASK, PPCCOM,	{ OBF, RA, RB } },
-{ "cmpld",   XCMPL(31,32,1), XCMPL_MASK, PPC64,		{ OBF, RA, RB } },
+{ "cmplw",   XOPL(31,32,0), XCMPL_MASK, PPCCOM,	{ OBF, RA, RB } },
+{ "cmpld",   XOPL(31,32,1), XCMPL_MASK, PPC64,		{ OBF, RA, RB } },
 { "cmpl",    X(31,32),	XCMP_MASK,	 PPC,		{ BF, L, RA, RB } },
 { "cmpl",    X(31,32),	XCMPL_MASK,	 PWRCOM,	{ BF, RA, RB } },
 
@@ -3324,15 +3481,16 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "mfmsr",   X(31,83),	XRARB_MASK,	COM,		{ RT } },
 
-{ "ldarx",   X(31,84),	X_MASK,		PPC64,		{ RT, RA, RB } },
+{ "ldarx",   X(31,84),	XEH_MASK,	PPC64,		{ RT, RA0, RB, EH } },
 
-{ "dcbf",    X(31,86),	XRT_MASK,	PPC,		{ RA, RB } },
+{ "dcbfl",   XOPL(31,86,1), XRT_MASK,	POWER5,		{ RA, RB } },
+{ "dcbf",    X(31,86),	XLRT_MASK,	PPC,		{ RA, RB, XRT_L } },
 
-{ "lbzx",    X(31,87),	X_MASK,		COM,		{ RT, RA, RB } },
+{ "lbzx",    X(31,87),	X_MASK,		COM,		{ RT, RA0, RB } },
 
 { "dcbfe",   X(31,94),	XRT_MASK,	BOOKE64,	{ RA, RB } },
 
-{ "lbzxe",   X(31,95),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lbzxe",   X(31,95),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
 { "neg",     XO(31,104,0,0), XORB_MASK,	COM,		{ RT, RA } },
 { "neg.",    XO(31,104,0,1), XORB_MASK,	COM,		{ RT, RA } },
@@ -3350,12 +3508,14 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "lbzux",   X(31,119),	X_MASK,		COM,		{ RT, RAL, RB } },
 
+{ "popcntb", X(31,122), XRB_MASK,	POWER5,		{ RA, RS } },
+
 { "not",     XRC(31,124,0), X_MASK,	COM,		{ RA, RS, RBS } },
 { "nor",     XRC(31,124,0), X_MASK,	COM,		{ RA, RS, RB } },
 { "not.",    XRC(31,124,1), X_MASK,	COM,		{ RA, RS, RBS } },
 { "nor.",    XRC(31,124,1), X_MASK,	COM,		{ RA, RS, RB } },
 
-{ "lwarxe",  X(31,126),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lwarxe",  X(31,126),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
 { "lbzuxe",  X(31,127),	X_MASK,		BOOKE64,	{ RT, RAL, RB } },
 
@@ -3383,21 +3543,22 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "dcbtstlse",X(31,142),X_MASK,		PPCCHLK64,	{ CT, RA, RB }},
 
-{ "mtcr",    XFXM(31,144,0xff), XRARB_MASK, COM,	{ RS }},
+{ "mtocrf",  XFXM(31,144,0,1), XFXFXM_MASK, COM,	{ FXM, RS } },
+{ "mtcr",    XFXM(31,144,0xff,0), XRARB_MASK, COM,	{ RS }},
 { "mtcrf",   X(31,144),	XFXFXM_MASK,	COM,		{ FXM, RS } },
 
 { "mtmsr",   X(31,146),	XRARB_MASK,	COM,		{ RS } },
 
-{ "stdx",    X(31,149), X_MASK,		PPC64,		{ RS, RA, RB } },
+{ "stdx",    X(31,149), X_MASK,		PPC64,		{ RS, RA0, RB } },
 
-{ "stwcx.",  XRC(31,150,1), X_MASK,	PPC,		{ RS, RA, RB } },
+{ "stwcx.",  XRC(31,150,1), X_MASK,	PPC,		{ RS, RA0, RB } },
 
-{ "stwx",    X(31,151), X_MASK,		PPCCOM,		{ RS, RA, RB } },
+{ "stwx",    X(31,151), X_MASK,		PPCCOM,		{ RS, RA0, RB } },
 { "stx",     X(31,151), X_MASK,		PWRCOM,		{ RS, RA, RB } },
 
-{ "stwcxe.", XRC(31,158,1), X_MASK,	BOOKE64,	{ RS, RA, RB } },
+{ "stwcxe.", XRC(31,158,1), X_MASK,	BOOKE64,	{ RS, RA0, RB } },
 
-{ "stwxe",   X(31,159), X_MASK,		BOOKE64,	{ RS, RA, RB } },
+{ "stwxe",   X(31,159), X_MASK,		BOOKE64,	{ RS, RA0, RB } },
 
 { "slq",     XRC(31,152,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "slq.",    XRC(31,152,1), X_MASK,	M601,		{ RA, RS, RB } },
@@ -3405,6 +3566,8 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "sle",     XRC(31,153,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "sle.",    XRC(31,153,1), X_MASK,	M601,		{ RA, RS, RB } },
 
+{ "prtyw",   X(31,154),	XRB_MASK,	POWER6,		{ RA, RS } },
+
 { "wrteei",  X(31,163),	XE_MASK,	PPC403 | BOOKE,	{ E } },
 
 { "dcbtls",  X(31,166),	X_MASK,		PPCCHLK,	{ CT, RA, RB }},
@@ -3415,11 +3578,13 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "stdux",   X(31,181),	X_MASK,		PPC64,		{ RS, RAS, RB } },
 
 { "stwux",   X(31,183),	X_MASK,		PPCCOM,		{ RS, RAS, RB } },
-{ "stux",    X(31,183),	X_MASK,		PWRCOM,		{ RS, RA, RB } },
+{ "stux",    X(31,183),	X_MASK,		PWRCOM,		{ RS, RA0, RB } },
 
 { "sliq",    XRC(31,184,0), X_MASK,	M601,		{ RA, RS, SH } },
 { "sliq.",   XRC(31,184,1), X_MASK,	M601,		{ RA, RS, SH } },
 
+{ "prtyd",   X(31,186),	XRB_MASK,	POWER6,		{ RA, RS } },
+
 { "stwuxe",  X(31,191),	X_MASK,		BOOKE64,	{ RS, RAS, RB } },
 
 { "subfze",  XO(31,200,0,0), XORB_MASK, PPCCOM,		{ RT, RA } },
@@ -3442,9 +3607,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "mtsr",    X(31,210),	XRB_MASK|(1<<20), COM32,	{ SR, RS } },
 
-{ "stdcx.",  XRC(31,214,1), X_MASK,	PPC64,		{ RS, RA, RB } },
+{ "stdcx.",  XRC(31,214,1), X_MASK,	PPC64,		{ RS, RA0, RB } },
 
-{ "stbx",    X(31,215),	X_MASK,		COM,		{ RS, RA, RB } },
+{ "stbx",    X(31,215),	X_MASK,		COM,		{ RS, RA0, RB } },
 
 { "sllq",    XRC(31,216,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "sllq.",   XRC(31,216,1), X_MASK,	M601,		{ RA, RS, RB } },
@@ -3452,7 +3617,7 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "sleq",    XRC(31,217,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "sleq.",   XRC(31,217,1), X_MASK,	M601,		{ RA, RS, RB } },
 
-{ "stbxe",   X(31,223),	X_MASK,		BOOKE64,	{ RS, RA, RB } },
+{ "stbxe",   X(31,223),	X_MASK,		BOOKE64,	{ RS, RA0, RB } },
 
 { "icblc",   X(31,230),	X_MASK,		PPCCHLK,	{ CT, RA, RB }},
 
@@ -3492,7 +3657,7 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mtsrin",  X(31,242),	XRA_MASK,	PPC32,		{ RS, RB } },
 { "mtsri",   X(31,242),	XRA_MASK,	POWER32,	{ RS, RB } },
 
-{ "dcbtst",  X(31,246),	XRT_MASK,	PPC,		{ CT, RA, RB } },
+{ "dcbtst",  X(31,246),	X_MASK,	PPC,			{ CT, RA, RB } },
 
 { "stbux",   X(31,247),	X_MASK,		COM,		{ RS, RAS, RB } },
 
@@ -3519,26 +3684,26 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "addo.",   XO(31,266,1,1), XO_MASK,	PPCCOM,		{ RT, RA, RB } },
 { "caxo.",   XO(31,266,1,1), XO_MASK,	PWRCOM,		{ RT, RA, RB } },
 
-{ "tlbiel",  X(31,274), XRTRA_MASK,	POWER4,		{ RB } },
+{ "tlbiel",  X(31,274), XRTLRA_MASK,	POWER4,		{ RB, L } },
 
 { "mfapidi", X(31,275), X_MASK,		BOOKE,		{ RT, RA } },
 
 { "lscbx",   XRC(31,277,0), X_MASK,	M601,		{ RT, RA, RB } },
 { "lscbx.",  XRC(31,277,1), X_MASK,	M601,		{ RT, RA, RB } },
 
-{ "dcbt",    X(31,278),	XRT_MASK,	PPC,		{ CT, RA, RB } },
+{ "dcbt",    X(31,278),	X_MASK,		PPC,		{ CT, RA, RB } },
 
-{ "lhzx",    X(31,279),	X_MASK,		COM,		{ RT, RA, RB } },
+{ "lhzx",    X(31,279),	X_MASK,		COM,		{ RT, RA0, RB } },
 
 { "eqv",     XRC(31,284,0), X_MASK,	COM,		{ RA, RS, RB } },
 { "eqv.",    XRC(31,284,1), X_MASK,	COM,		{ RA, RS, RB } },
 
 { "dcbte",   X(31,286),	X_MASK,		BOOKE64,	{ CT, RA, RB } },
 
-{ "lhzxe",   X(31,287),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lhzxe",   X(31,287),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
 { "tlbie",   X(31,306),	XRTLRA_MASK,	PPC,		{ RB, L } },
-{ "tlbi",    X(31,306),	XRT_MASK,	POWER,		{ RA, RB } },
+{ "tlbi",    X(31,306),	XRT_MASK,	POWER,		{ RA0, RB } },
 
 { "eciwx",   X(31,310), X_MASK,		PPC,		{ RT, RA, RB } },
 
@@ -3607,6 +3772,7 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mfsdr1",     XSPR(31,339,25),   XSPR_MASK, COM,	{ RT } },
 { "mfsrr0",     XSPR(31,339,26),   XSPR_MASK, COM,	{ RT } },
 { "mfsrr1",     XSPR(31,339,27),   XSPR_MASK, COM,	{ RT } },
+{ "mfcfar",     XSPR(31,339,28),   XSPR_MASK, POWER6,	{ RT } },
 { "mfpid",      XSPR(31,339,48),   XSPR_MASK, BOOKE,    { RT } },
 { "mfpid",      XSPR(31,339,945),  XSPR_MASK, PPC403,	{ RT } },
 { "mfcsrr0",    XSPR(31,339,58),   XSPR_MASK, BOOKE,    { RT } },
@@ -3634,21 +3800,21 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mfbar",      XSPR(31,339,159),  XSPR_MASK, PPC860,	{ RT } },
 { "mfvrsave",   XSPR(31,339,256),  XSPR_MASK, PPCVEC,	{ RT } },
 { "mfusprg0",   XSPR(31,339,256),  XSPR_MASK, BOOKE,    { RT } },
-{ "mfsprg4",    XSPR(31,339,260),  XSPR_MASK, PPC405,	{ RT } },
-{ "mfsprg5",    XSPR(31,339,261),  XSPR_MASK, PPC405,	{ RT } },
-{ "mfsprg6",    XSPR(31,339,262),  XSPR_MASK, PPC405,	{ RT } },
-{ "mfsprg7",    XSPR(31,339,263),  XSPR_MASK, PPC405,	{ RT } },
 { "mftb",       X(31,371),	   X_MASK,    CLASSIC,	{ RT, TBR } },
 { "mftb",       XSPR(31,339,268),  XSPR_MASK, BOOKE,    { RT } },
 { "mftbl",      XSPR(31,371,268),  XSPR_MASK, CLASSIC,	{ RT } },
 { "mftbl",      XSPR(31,339,268),  XSPR_MASK, BOOKE,    { RT } },
 { "mftbu",      XSPR(31,371,269),  XSPR_MASK, CLASSIC,	{ RT } },
 { "mftbu",      XSPR(31,339,269),  XSPR_MASK, BOOKE,    { RT } },
-{ "mfsprg",     XSPR(31,339,272),  XSPRG_MASK, PPC,	{ RT, SPRG } },
+{ "mfsprg",     XSPR(31,339,256),  XSPRG_MASK, PPC,	{ RT, SPRG } },
 { "mfsprg0",    XSPR(31,339,272),  XSPR_MASK, PPC,	{ RT } },
 { "mfsprg1",    XSPR(31,339,273),  XSPR_MASK, PPC,	{ RT } },
 { "mfsprg2",    XSPR(31,339,274),  XSPR_MASK, PPC,	{ RT } },
 { "mfsprg3",    XSPR(31,339,275),  XSPR_MASK, PPC,	{ RT } },
+{ "mfsprg4",    XSPR(31,339,260),  XSPR_MASK, PPC405 | BOOKE,	{ RT } },
+{ "mfsprg5",    XSPR(31,339,261),  XSPR_MASK, PPC405 | BOOKE,	{ RT } },
+{ "mfsprg6",    XSPR(31,339,262),  XSPR_MASK, PPC405 | BOOKE,	{ RT } },
+{ "mfsprg7",    XSPR(31,339,263),  XSPR_MASK, PPC405 | BOOKE,	{ RT } },
 { "mfasr",      XSPR(31,339,280),  XSPR_MASK, PPC64,	{ RT } },
 { "mfear",      XSPR(31,339,282),  XSPR_MASK, PPC,	{ RT } },
 { "mfpir",      XSPR(31,339,286),  XSPR_MASK, BOOKE,    { RT } },
@@ -3699,6 +3865,10 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mfspefscr",  XSPR(31,339,512),  XSPR_MASK, PPCSPE,	{ RT } },
 { "mfbbear",    XSPR(31,339,513),  XSPR_MASK, PPCBRLK,  { RT } },
 { "mfbbtar",    XSPR(31,339,514),  XSPR_MASK, PPCBRLK,  { RT } },
+{ "mfivor32",   XSPR(31,339,528),  XSPR_MASK, PPCSPE,	{ RT } },
+{ "mfivor33",   XSPR(31,339,529),  XSPR_MASK, PPCSPE,	{ RT } },
+{ "mfivor34",   XSPR(31,339,530),  XSPR_MASK, PPCSPE,	{ RT } },
+{ "mfivor35",   XSPR(31,339,531),  XSPR_MASK, PPCPMR,	{ RT } },
 { "mfibatu",    XSPR(31,339,528),  XSPRBAT_MASK, PPC,	{ RT, SPRBAT } },
 { "mfibatl",    XSPR(31,339,529),  XSPRBAT_MASK, PPC,	{ RT, SPRBAT } },
 { "mfdbatu",    XSPR(31,339,536),  XSPRBAT_MASK, PPC,	{ RT, SPRBAT } },
@@ -3708,10 +3878,11 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mfic_dat",   XSPR(31,339,562),  XSPR_MASK, PPC860,	{ RT } },
 { "mfdc_cst",   XSPR(31,339,568),  XSPR_MASK, PPC860,	{ RT } },
 { "mfdc_adr",   XSPR(31,339,569),  XSPR_MASK, PPC860,	{ RT } },
-{ "mfdc_dat",   XSPR(31,339,570),  XSPR_MASK, PPC860,	{ RT } },
 { "mfmcsrr0",   XSPR(31,339,570),  XSPR_MASK, PPCRFMCI, { RT } },
+{ "mfdc_dat",   XSPR(31,339,570),  XSPR_MASK, PPC860,	{ RT } },
 { "mfmcsrr1",   XSPR(31,339,571),  XSPR_MASK, PPCRFMCI, { RT } },
 { "mfmcsr",     XSPR(31,339,572),  XSPR_MASK, PPCRFMCI, { RT } },
+{ "mfmcar",     XSPR(31,339,573),  XSPR_MASK, PPCRFMCI, { RT } },
 { "mfdpdr",     XSPR(31,339,630),  XSPR_MASK, PPC860,	{ RT } },
 { "mfdpir",     XSPR(31,339,631),  XSPR_MASK, PPC860,	{ RT } },
 { "mfimmr",     XSPR(31,339,638),  XSPR_MASK, PPC860,	{ RT } },
@@ -3775,14 +3946,14 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mfpbu2",     XSPR(31,339,1023), XSPR_MASK, PPC403,	{ RT } },
 { "mfspr",      X(31,339),	   X_MASK,    COM,	{ RT, SPR } },
 
-{ "lwax",    X(31,341),	X_MASK,		PPC64,		{ RT, RA, RB } },
+{ "lwax",    X(31,341),	X_MASK,		PPC64,		{ RT, RA0, RB } },
 
 { "dst",     XDSS(31,342,0), XDSS_MASK,	PPCVEC,		{ RA, RB, STRM } },
 { "dstt",    XDSS(31,342,1), XDSS_MASK,	PPCVEC,		{ RA, RB, STRM } },
 
-{ "lhax",    X(31,343),	X_MASK,		COM,		{ RT, RA, RB } },
+{ "lhax",    X(31,343),	X_MASK,		COM,		{ RT, RA0, RB } },
 
-{ "lhaxe",   X(31,351),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lhaxe",   X(31,351),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
 { "dstst",   XDSS(31,374,0), XDSS_MASK,	PPCVEC,		{ RA, RB, STRM } },
 { "dststt",  XDSS(31,374,1), XDSS_MASK,	PPCVEC,		{ RA, RB, STRM } },
@@ -3821,14 +3992,20 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "slbmte",  X(31,402), XRA_MASK,	PPC64,		{ RS, RB } },
 
-{ "sthx",    X(31,407),	X_MASK,		COM,		{ RS, RA, RB } },
+{ "sthx",    X(31,407),	X_MASK,		COM,		{ RS, RA0, RB } },
+
+{ "cmpb",    X(31,508),	X_MASK,		POWER6,		{ RA, RS, RB } },
 
 { "lfqx",    X(31,791),	X_MASK,		POWER2,		{ FRT, RA, RB } },
 
+{ "lfdpx",   X(31,791),	X_MASK,		POWER6,		{ FRT, RA, RB } },
+
 { "lfqux",   X(31,823),	X_MASK,		POWER2,		{ FRT, RA, RB } },
 
 { "stfqx",   X(31,919),	X_MASK,		POWER2,		{ FRS, RA, RB } },
 
+{ "stfdpx",  X(31,919),	X_MASK,		POWER6,		{ FRS, RA, RB } },
+
 { "stfqux",  X(31,951),	X_MASK,		POWER2,		{ FRS, RA, RB } },
 
 { "orc",     XRC(31,412,0), X_MASK,	COM,		{ RA, RS, RB } },
@@ -3837,7 +4014,7 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "sradi",   XS(31,413,0), XS_MASK,	PPC64,		{ RA, RS, SH6 } },
 { "sradi.",  XS(31,413,1), XS_MASK,	PPC64,		{ RA, RS, SH6 } },
 
-{ "sthxe",   X(31,415),	X_MASK,		BOOKE64,	{ RS, RA, RB } },
+{ "sthxe",   X(31,415),	X_MASK,		BOOKE64,	{ RS, RA0, RB } },
 
 { "slbie",   X(31,434),	XRTRA_MASK,	PPC64,		{ RB } },
 
@@ -3918,6 +4095,7 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mtsdr1",    XSPR(31,467,25),   XSPR_MASK, COM,	{ RS } },
 { "mtsrr0",    XSPR(31,467,26),   XSPR_MASK, COM,	{ RS } },
 { "mtsrr1",    XSPR(31,467,27),   XSPR_MASK, COM,	{ RS } },
+{ "mtcfar",    XSPR(31,467,28),   XSPR_MASK, POWER6,	{ RS } },
 { "mtpid",     XSPR(31,467,48),   XSPR_MASK, BOOKE,     { RS } },
 { "mtpid",     XSPR(31,467,945),  XSPR_MASK, PPC403,	{ RS } },
 { "mtdecar",   XSPR(31,467,54),   XSPR_MASK, BOOKE,     { RS } },
@@ -3946,7 +4124,7 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mtbar",     XSPR(31,467,159),  XSPR_MASK, PPC860,	{ RS } },
 { "mtvrsave",  XSPR(31,467,256),  XSPR_MASK, PPCVEC,	{ RS } },
 { "mtusprg0",  XSPR(31,467,256),  XSPR_MASK, BOOKE,     { RS } },
-{ "mtsprg",    XSPR(31,467,272),  XSPRG_MASK,PPC,	{ SPRG, RS } },
+{ "mtsprg",    XSPR(31,467,256),  XSPRG_MASK,PPC,	{ SPRG, RS } },
 { "mtsprg0",   XSPR(31,467,272),  XSPR_MASK, PPC,	{ RS } },
 { "mtsprg1",   XSPR(31,467,273),  XSPR_MASK, PPC,	{ RS } },
 { "mtsprg2",   XSPR(31,467,274),  XSPR_MASK, PPC,	{ RS } },
@@ -4005,6 +4183,10 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "mtspefscr",  XSPR(31,467,512),  XSPR_MASK, PPCSPE,   { RS } },
 { "mtbbear",   XSPR(31,467,513),  XSPR_MASK, PPCBRLK,   { RS } },
 { "mtbbtar",   XSPR(31,467,514),  XSPR_MASK, PPCBRLK,  { RS } },
+{ "mtivor32",  XSPR(31,467,528),  XSPR_MASK, PPCSPE,	{ RS } },
+{ "mtivor33",  XSPR(31,467,529),  XSPR_MASK, PPCSPE,	{ RS } },
+{ "mtivor34",  XSPR(31,467,530),  XSPR_MASK, PPCSPE,	{ RS } },
+{ "mtivor35",  XSPR(31,467,531),  XSPR_MASK, PPCPMR,	{ RS } },
 { "mtibatu",   XSPR(31,467,528),  XSPRBAT_MASK, PPC,	{ SPRBAT, RS } },
 { "mtibatl",   XSPR(31,467,529),  XSPRBAT_MASK, PPC,	{ SPRBAT, RS } },
 { "mtdbatu",   XSPR(31,467,536),  XSPRBAT_MASK, PPC,	{ SPRBAT, RS } },
@@ -4101,13 +4283,15 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "clcs",    X(31,531), XRB_MASK,	M601,		{ RT, RA } },
 
-{ "lswx",    X(31,533),	X_MASK,		PPCCOM,		{ RT, RA, RB } },
+{ "ldbrx",   X(31,532),	X_MASK,		CELL,		{ RT, RA0, RB } },
+
+{ "lswx",    X(31,533),	X_MASK,		PPCCOM,		{ RT, RA0, RB } },
 { "lsx",     X(31,533),	X_MASK,		PWRCOM,		{ RT, RA, RB } },
 
-{ "lwbrx",   X(31,534),	X_MASK,		PPCCOM,		{ RT, RA, RB } },
+{ "lwbrx",   X(31,534),	X_MASK,		PPCCOM,		{ RT, RA0, RB } },
 { "lbrx",    X(31,534),	X_MASK,		PWRCOM,		{ RT, RA, RB } },
 
-{ "lfsx",    X(31,535),	X_MASK,		COM,		{ FRT, RA, RB } },
+{ "lfsx",    X(31,535),	X_MASK,		COM,		{ FRT, RA0, RB } },
 
 { "srw",     XRC(31,536,0), X_MASK,	PPCCOM,		{ RA, RS, RB } },
 { "sr",      XRC(31,536,0), X_MASK,	PWRCOM,		{ RA, RS, RB } },
@@ -4123,11 +4307,12 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "maskir",  XRC(31,541,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "maskir.", XRC(31,541,1), X_MASK,	M601,		{ RA, RS, RB } },
 
-{ "lwbrxe",  X(31,542),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lwbrxe",  X(31,542),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
-{ "lfsxe",   X(31,543),	X_MASK,		BOOKE64,	{ FRT, RA, RB } },
+{ "lfsxe",   X(31,543),	X_MASK,		BOOKE64,	{ FRT, RA0, RB } },
 
 { "bbelr",   X(31,550),	X_MASK,		PPCBRLK,	{ 0 }},
+
 { "tlbsync", X(31,566),	0xffffffff,	PPC,		{ 0 } },
 
 { "lfsux",   X(31,567),	X_MASK,		COM,		{ FRT, RAS, RB } },
@@ -4136,8 +4321,8 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "mfsr",    X(31,595),	XRB_MASK|(1<<20), COM32,	{ RT, SR } },
 
-{ "lswi",    X(31,597),	X_MASK,		PPCCOM,		{ RT, RA, NB } },
-{ "lsi",     X(31,597),	X_MASK,		PWRCOM,		{ RT, RA, NB } },
+{ "lswi",    X(31,597),	X_MASK,		PPCCOM,		{ RT, RA0, NB } },
+{ "lsi",     X(31,597),	X_MASK,		PWRCOM,		{ RT, RA0, NB } },
 
 { "lwsync",  XSYNC(31,598,1), 0xffffffff, PPC,		{ 0 } },
 { "ptesync", XSYNC(31,598,2), 0xffffffff, PPC64,	{ 0 } },
@@ -4145,9 +4330,11 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "sync",    X(31,598), XSYNC_MASK,	PPCCOM,		{ LS } },
 { "dcs",     X(31,598), 0xffffffff,	PWRCOM,		{ 0 } },
 
-{ "lfdx",    X(31,599), X_MASK,		COM,		{ FRT, RA, RB } },
+{ "lfdx",    X(31,599), X_MASK,		COM,		{ FRT, RA0, RB } },
+
+{ "lfdxe",   X(31,607), X_MASK,		BOOKE64,	{ FRT, RA0, RB } },
 
-{ "lfdxe",   X(31,607), X_MASK,		BOOKE64,	{ FRT, RA, RB } },
+{ "mffgpr",  XRC(31,607,0), XRA_MASK,	POWER6,		{ FRT, RB } },
 
 { "mfsri",   X(31,627), X_MASK,		PWRCOM,		{ RT, RA, RB } },
 
@@ -4159,13 +4346,15 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "mfsrin",  X(31,659), XRA_MASK,	PPC32,		{ RT, RB } },
 
-{ "stswx",   X(31,661), X_MASK,		PPCCOM,		{ RS, RA, RB } },
-{ "stsx",    X(31,661), X_MASK,		PWRCOM,		{ RS, RA, RB } },
+{ "stdbrx",  X(31,660), X_MASK,		CELL,		{ RS, RA0, RB } },
+
+{ "stswx",   X(31,661), X_MASK,		PPCCOM,		{ RS, RA0, RB } },
+{ "stsx",    X(31,661), X_MASK,		PWRCOM,		{ RS, RA0, RB } },
 
-{ "stwbrx",  X(31,662), X_MASK,		PPCCOM,		{ RS, RA, RB } },
-{ "stbrx",   X(31,662), X_MASK,		PWRCOM,		{ RS, RA, RB } },
+{ "stwbrx",  X(31,662), X_MASK,		PPCCOM,		{ RS, RA0, RB } },
+{ "stbrx",   X(31,662), X_MASK,		PWRCOM,		{ RS, RA0, RB } },
 
-{ "stfsx",   X(31,663), X_MASK,		COM,		{ FRS, RA, RB } },
+{ "stfsx",   X(31,663), X_MASK,		COM,		{ FRS, RA0, RB } },
 
 { "srq",     XRC(31,664,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "srq.",    XRC(31,664,1), X_MASK,	M601,		{ RA, RS, RB } },
@@ -4173,9 +4362,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "sre",     XRC(31,665,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "sre.",    XRC(31,665,1), X_MASK,	M601,		{ RA, RS, RB } },
 
-{ "stwbrxe", X(31,670), X_MASK,		BOOKE64,	{ RS, RA, RB } },
+{ "stwbrxe", X(31,670), X_MASK,		BOOKE64,	{ RS, RA0, RB } },
 
-{ "stfsxe",  X(31,671), X_MASK,		BOOKE64,	{ FRS, RA, RB } },
+{ "stfsxe",  X(31,671), X_MASK,		BOOKE64,	{ FRS, RA0, RB } },
 
 { "stfsux",  X(31,695),	X_MASK,		COM,		{ FRS, RAS, RB } },
 
@@ -4184,10 +4373,10 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "stfsuxe", X(31,703),	X_MASK,		BOOKE64,	{ FRS, RAS, RB } },
 
-{ "stswi",   X(31,725),	X_MASK,		PPCCOM,		{ RS, RA, NB } },
-{ "stsi",    X(31,725),	X_MASK,		PWRCOM,		{ RS, RA, NB } },
+{ "stswi",   X(31,725),	X_MASK,		PPCCOM,		{ RS, RA0, NB } },
+{ "stsi",    X(31,725),	X_MASK,		PWRCOM,		{ RS, RA0, NB } },
 
-{ "stfdx",   X(31,727),	X_MASK,		COM,		{ FRS, RA, RB } },
+{ "stfdx",   X(31,727),	X_MASK,		COM,		{ FRS, RA0, RB } },
 
 { "srlq",    XRC(31,728,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "srlq.",   XRC(31,728,1), X_MASK,	M601,		{ RA, RS, RB } },
@@ -4195,7 +4384,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "sreq",    XRC(31,729,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "sreq.",   XRC(31,729,1), X_MASK,	M601,		{ RA, RS, RB } },
 
-{ "stfdxe",  X(31,735),	X_MASK,		BOOKE64,	{ FRS, RA, RB } },
+{ "stfdxe",  X(31,735),	X_MASK,		BOOKE64,	{ FRS, RA0, RB } },
+
+{ "mftgpr",  XRC(31,735,0), XRA_MASK,	POWER6,		{ RT, FRB } },
 
 { "dcba",    X(31,758),	XRT_MASK,	PPC405 | BOOKE,	{ RA, RB } },
 
@@ -4211,7 +4402,9 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "tlbivax", X(31,786),	XRT_MASK,	BOOKE,		{ RA, RB } },
 { "tlbivaxe",X(31,787),	XRT_MASK,	BOOKE64,	{ RA, RB } },
 
-{ "lhbrx",   X(31,790),	X_MASK,		COM,		{ RT, RA, RB } },
+{ "lwzcix",  X(31,789),	X_MASK,		POWER6,		{ RT, RA0, RB } },
+
+{ "lhbrx",   X(31,790),	X_MASK,		COM,		{ RT, RA0, RB } },
 
 { "sraw",    XRC(31,792,0), X_MASK,	PPCCOM,		{ RA, RS, RB } },
 { "sra",     XRC(31,792,0), X_MASK,	PWRCOM,		{ RA, RS, RB } },
@@ -4221,13 +4414,15 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "srad",    XRC(31,794,0), X_MASK,	PPC64,		{ RA, RS, RB } },
 { "srad.",   XRC(31,794,1), X_MASK,	PPC64,		{ RA, RS, RB } },
 
-{ "lhbrxe",  X(31,798),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "lhbrxe",  X(31,798),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
-{ "ldxe",    X(31,799),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
-{ "lduxe",   X(31,831),	X_MASK,		BOOKE64,	{ RT, RA, RB } },
+{ "ldxe",    X(31,799),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
+{ "lduxe",   X(31,831),	X_MASK,		BOOKE64,	{ RT, RA0, RB } },
 
 { "rac",     X(31,818),	X_MASK,		PWRCOM,		{ RT, RA, RB } },
 
+{ "lhzcix",  X(31,821),	X_MASK,		POWER6,		{ RT, RA0, RB } },
+
 { "dss",     XDSS(31,822,0), XDSS_MASK,	PPCVEC,		{ STRM } },
 { "dssall",  XDSS(31,822,1), XDSS_MASK,	PPCVEC,		{ 0 } },
 
@@ -4238,19 +4433,25 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "slbmfev", X(31,851), XRA_MASK,	PPC64,		{ RT, RB } },
 
+{ "lbzcix",  X(31,853),	X_MASK,		POWER6,		{ RT, RA0, RB } },
+
 { "mbar",    X(31,854),	X_MASK,		BOOKE,		{ MO } },
 { "eieio",   X(31,854),	0xffffffff,	PPC,		{ 0 } },
 
-{ "tlbsx",   XRC(31,914,0), X_MASK,	BOOKE,		{ RA, RB } },
-{ "tlbsx",   XRC(31,914,0), X_MASK, 	PPC403,		{ RT, RA, RB } },
-{ "tlbsx.",  XRC(31,914,1), X_MASK,	BOOKE,		{ RA, RB } },
-{ "tlbsx.",  XRC(31,914,1), X_MASK, 	PPC403,		{ RT, RA, RB } },
+{ "lfiwax",  X(31,855),	X_MASK,		POWER6,		{ FRT, RA0, RB } },
+
+{ "ldcix",   X(31,885),	X_MASK,		POWER6,		{ RT, RA0, RB } },
+
+{ "tlbsx",   XRC(31,914,0), X_MASK, 	PPC403|BOOKE,	{ RTO, RA, RB } },
+{ "tlbsx.",  XRC(31,914,1), X_MASK, 	PPC403|BOOKE,	{ RTO, RA, RB } },
 { "tlbsxe",  XRC(31,915,0), X_MASK,	BOOKE64,	{ RA, RB } },
 { "tlbsxe.", XRC(31,915,1), X_MASK,	BOOKE64,	{ RA, RB } },
 
 { "slbmfee", X(31,915), XRA_MASK,	PPC64,		{ RT, RB } },
 
-{ "sthbrx",  X(31,918),	X_MASK,		COM,		{ RS, RA, RB } },
+{ "stwcix",  X(31,917),	X_MASK,		POWER6,		{ RS, RA0, RB } },
+
+{ "sthbrx",  X(31,918),	X_MASK,		COM,		{ RS, RA0, RB } },
 
 { "sraq",    XRC(31,920,0), X_MASK,	M601,		{ RA, RS, RB } },
 { "sraq.",   XRC(31,920,1), X_MASK,	M601,		{ RA, RS, RB } },
@@ -4263,14 +4464,15 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "extsh.",  XRC(31,922,1), XRB_MASK,	PPCCOM,		{ RA, RS } },
 { "exts.",   XRC(31,922,1), XRB_MASK,	PWRCOM,		{ RA, RS } },
 
-{ "sthbrxe", X(31,926),	X_MASK,		BOOKE64,	{ RS, RA, RB } },
+{ "sthbrxe", X(31,926),	X_MASK,		BOOKE64,	{ RS, RA0, RB } },
 
-{ "stdxe",   X(31,927), X_MASK,		BOOKE64,	{ RS, RA, RB } },
+{ "stdxe",   X(31,927), X_MASK,		BOOKE64,	{ RS, RA0, RB } },
 
 { "tlbrehi", XTLB(31,946,0), XTLB_MASK,	PPC403,		{ RT, RA } },
 { "tlbrelo", XTLB(31,946,1), XTLB_MASK,	PPC403,		{ RT, RA } },
-{ "tlbre",   X(31,946),	X_MASK,		BOOKE,		{ 0 } },
-{ "tlbre",   X(31,946),	X_MASK,		PPC403,		{ RS, RA, SH } },
+{ "tlbre",   X(31,946),	X_MASK,		PPC403|BOOKE,	{ RSO, RAOPT, SHO } },
+
+{ "sthcix",  X(31,949),	X_MASK,		POWER6,		{ RS, RA0, RB } },
 
 { "sraiq",   XRC(31,952,0), X_MASK,	M601,		{ RA, RS, SH } },
 { "sraiq.",  XRC(31,952,1), X_MASK,	M601,		{ RA, RS, SH } },
@@ -4284,13 +4486,14 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "tlbwehi", XTLB(31,978,0), XTLB_MASK,	PPC403,		{ RT, RA } },
 { "tlbwelo", XTLB(31,978,1), XTLB_MASK,	PPC403,		{ RT, RA } },
-{ "tlbwe",   X(31,978),	X_MASK,		BOOKE,		{ 0 } },
-{ "tlbwe",   X(31,978),	X_MASK,		PPC403,		{ RS, RA, SH } },
+{ "tlbwe",   X(31,978),	X_MASK,		PPC403|BOOKE,	{ RSO, RAOPT, SHO } },
 { "tlbld",   X(31,978),	XRTRA_MASK,	PPC,		{ RB } },
 
+{ "stbcix",  X(31,981),	X_MASK,		POWER6,		{ RS, RA0, RB } },
+
 { "icbi",    X(31,982),	XRT_MASK,	PPC,		{ RA, RB } },
 
-{ "stfiwx",  X(31,983),	X_MASK,		PPC,		{ FRS, RA, RB } },
+{ "stfiwx",  X(31,983),	X_MASK,		PPC,		{ FRS, RA0, RB } },
 
 { "extsw",   XRC(31,986,0), XRB_MASK,	PPC64 | BOOKE64,{ RA, RS } },
 { "extsw.",  XRC(31,986,1), XRB_MASK,	PPC64,		{ RA, RS } },
@@ -4298,10 +4501,13 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "icread",  X(31,998),	XRT_MASK,	PPC403|PPC440,	{ RA, RB } },
 
 { "icbie",   X(31,990),	XRT_MASK,	BOOKE64,	{ RA, RB } },
-{ "stfiwxe", X(31,991),	X_MASK,		BOOKE64,	{ FRS, RA, RB } },
+{ "stfiwxe", X(31,991),	X_MASK,		BOOKE64,	{ FRS, RA0, RB } },
 
 { "tlbli",   X(31,1010), XRTRA_MASK,	PPC,		{ RB } },
 
+{ "stdcix",  X(31,1013), X_MASK,	POWER6,		{ RS, RA0, RB } },
+
+{ "dcbzl",   XOPL(31,1014,1), XRT_MASK,POWER4,            { RA, RB } },
 { "dcbz",    X(31,1014), XRT_MASK,	PPC,		{ RA, RB } },
 { "dclz",    X(31,1014), XRT_MASK,	PPC,		{ RA, RB } },
 
@@ -4320,86 +4526,104 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "stvx",    X(31, 231), X_MASK,	PPCVEC,		{ VS, RA, RB } },
 { "stvxl",   X(31, 487), X_MASK,	PPCVEC,		{ VS, RA, RB } },
 
-{ "lwz",     OP(32),	OP_MASK,	PPCCOM,		{ RT, D, RA } },
-{ "l",	     OP(32),	OP_MASK,	PWRCOM,		{ RT, D, RA } },
+/* New load/store left/right index vector instructions that are in the Cell only.  */
+{ "lvlx",    X(31, 519), X_MASK,	CELL,		{ VD, RA0, RB } },
+{ "lvlxl",   X(31, 775), X_MASK,	CELL,		{ VD, RA0, RB } },
+{ "lvrx",    X(31, 551), X_MASK,	CELL,		{ VD, RA0, RB } },
+{ "lvrxl",   X(31, 807), X_MASK,	CELL,		{ VD, RA0, RB } },
+{ "stvlx",   X(31, 647), X_MASK,	CELL,		{ VS, RA0, RB } },
+{ "stvlxl",  X(31, 903), X_MASK,	CELL,		{ VS, RA0, RB } },
+{ "stvrx",   X(31, 679), X_MASK,	CELL,		{ VS, RA0, RB } },
+{ "stvrxl",  X(31, 935), X_MASK,	CELL,		{ VS, RA0, RB } },
+
+{ "lwz",     OP(32),	OP_MASK,	PPCCOM,		{ RT, D, RA0 } },
+{ "l",	     OP(32),	OP_MASK,	PWRCOM,		{ RT, D, RA0 } },
 
 { "lwzu",    OP(33),	OP_MASK,	PPCCOM,		{ RT, D, RAL } },
-{ "lu",      OP(33),	OP_MASK,	PWRCOM,		{ RT, D, RA } },
+{ "lu",      OP(33),	OP_MASK,	PWRCOM,		{ RT, D, RA0 } },
 
-{ "lbz",     OP(34),	OP_MASK,	COM,		{ RT, D, RA } },
+{ "lbz",     OP(34),	OP_MASK,	COM,		{ RT, D, RA0 } },
 
 { "lbzu",    OP(35),	OP_MASK,	COM,		{ RT, D, RAL } },
 
-{ "stw",     OP(36),	OP_MASK,	PPCCOM,		{ RS, D, RA } },
-{ "st",      OP(36),	OP_MASK,	PWRCOM,		{ RS, D, RA } },
+{ "stw",     OP(36),	OP_MASK,	PPCCOM,		{ RS, D, RA0 } },
+{ "st",      OP(36),	OP_MASK,	PWRCOM,		{ RS, D, RA0 } },
 
 { "stwu",    OP(37),	OP_MASK,	PPCCOM,		{ RS, D, RAS } },
-{ "stu",     OP(37),	OP_MASK,	PWRCOM,		{ RS, D, RA } },
+{ "stu",     OP(37),	OP_MASK,	PWRCOM,		{ RS, D, RA0 } },
 
-{ "stb",     OP(38),	OP_MASK,	COM,		{ RS, D, RA } },
+{ "stb",     OP(38),	OP_MASK,	COM,		{ RS, D, RA0 } },
 
 { "stbu",    OP(39),	OP_MASK,	COM,		{ RS, D, RAS } },
 
-{ "lhz",     OP(40),	OP_MASK,	COM,		{ RT, D, RA } },
+{ "lhz",     OP(40),	OP_MASK,	COM,		{ RT, D, RA0 } },
 
 { "lhzu",    OP(41),	OP_MASK,	COM,		{ RT, D, RAL } },
 
-{ "lha",     OP(42),	OP_MASK,	COM,		{ RT, D, RA } },
+{ "lha",     OP(42),	OP_MASK,	COM,		{ RT, D, RA0 } },
 
 { "lhau",    OP(43),	OP_MASK,	COM,		{ RT, D, RAL } },
 
-{ "sth",     OP(44),	OP_MASK,	COM,		{ RS, D, RA } },
+{ "sth",     OP(44),	OP_MASK,	COM,		{ RS, D, RA0 } },
 
 { "sthu",    OP(45),	OP_MASK,	COM,		{ RS, D, RAS } },
 
 { "lmw",     OP(46),	OP_MASK,	PPCCOM,		{ RT, D, RAM } },
-{ "lm",      OP(46),	OP_MASK,	PWRCOM,		{ RT, D, RA } },
+{ "lm",      OP(46),	OP_MASK,	PWRCOM,		{ RT, D, RA0 } },
 
-{ "stmw",    OP(47),	OP_MASK,	PPCCOM,		{ RS, D, RA } },
-{ "stm",     OP(47),	OP_MASK,	PWRCOM,		{ RS, D, RA } },
+{ "stmw",    OP(47),	OP_MASK,	PPCCOM,		{ RS, D, RA0 } },
+{ "stm",     OP(47),	OP_MASK,	PWRCOM,		{ RS, D, RA0 } },
 
-{ "lfs",     OP(48),	OP_MASK,	COM,		{ FRT, D, RA } },
+{ "lfs",     OP(48),	OP_MASK,	COM,		{ FRT, D, RA0 } },
 
 { "lfsu",    OP(49),	OP_MASK,	COM,		{ FRT, D, RAS } },
 
-{ "lfd",     OP(50),	OP_MASK,	COM,		{ FRT, D, RA } },
+{ "lfd",     OP(50),	OP_MASK,	COM,		{ FRT, D, RA0 } },
 
 { "lfdu",    OP(51),	OP_MASK,	COM,		{ FRT, D, RAS } },
 
-{ "stfs",    OP(52),	OP_MASK,	COM,		{ FRS, D, RA } },
+{ "stfs",    OP(52),	OP_MASK,	COM,		{ FRS, D, RA0 } },
 
 { "stfsu",   OP(53),	OP_MASK,	COM,		{ FRS, D, RAS } },
 
-{ "stfd",    OP(54),	OP_MASK,	COM,		{ FRS, D, RA } },
+{ "stfd",    OP(54),	OP_MASK,	COM,		{ FRS, D, RA0 } },
 
 { "stfdu",   OP(55),	OP_MASK,	COM,		{ FRS, D, RAS } },
 
 { "lq",      OP(56),	OP_MASK,	POWER4,		{ RTQ, DQ, RAQ } },
 
-{ "lfq",     OP(56),	OP_MASK,	POWER2,		{ FRT, D, RA } },
+{ "lfq",     OP(56),	OP_MASK,	POWER2,		{ FRT, D, RA0 } },
+
+{ "lfqu",    OP(57),	OP_MASK,	POWER2,		{ FRT, D, RA0 } },
 
-{ "lfqu",    OP(57),	OP_MASK,	POWER2,		{ FRT, D, RA } },
+{ "lfdp",    OP(57),	OP_MASK,	POWER6,		{ FRT, D, RA0 } },
 
-{ "lbze",    DEO(58,0), DE_MASK,	BOOKE64,	{ RT, DE, RA } },
+{ "lbze",    DEO(58,0), DE_MASK,	BOOKE64,	{ RT, DE, RA0 } },
 { "lbzue",   DEO(58,1), DE_MASK,	BOOKE64,	{ RT, DE, RAL } },
-{ "lhze",    DEO(58,2), DE_MASK,	BOOKE64,	{ RT, DE, RA } },
+{ "lhze",    DEO(58,2), DE_MASK,	BOOKE64,	{ RT, DE, RA0 } },
 { "lhzue",   DEO(58,3), DE_MASK,	BOOKE64,	{ RT, DE, RAL } },
-{ "lhae",    DEO(58,4), DE_MASK,	BOOKE64,	{ RT, DE, RA } },
+{ "lhae",    DEO(58,4), DE_MASK,	BOOKE64,	{ RT, DE, RA0 } },
 { "lhaue",   DEO(58,5), DE_MASK,	BOOKE64,	{ RT, DE, RAL } },
-{ "lwze",    DEO(58,6), DE_MASK,	BOOKE64,	{ RT, DE, RA } },
+{ "lwze",    DEO(58,6), DE_MASK,	BOOKE64,	{ RT, DE, RA0 } },
 { "lwzue",   DEO(58,7), DE_MASK,	BOOKE64,	{ RT, DE, RAL } },
-{ "stbe",    DEO(58,8), DE_MASK,	BOOKE64,	{ RS, DE, RA } },
+{ "stbe",    DEO(58,8), DE_MASK,	BOOKE64,	{ RS, DE, RA0 } },
 { "stbue",   DEO(58,9), DE_MASK,	BOOKE64,	{ RS, DE, RAS } },
-{ "sthe",    DEO(58,10), DE_MASK,	BOOKE64,	{ RS, DE, RA } },
+{ "sthe",    DEO(58,10), DE_MASK,	BOOKE64,	{ RS, DE, RA0 } },
 { "sthue",   DEO(58,11), DE_MASK,	BOOKE64,	{ RS, DE, RAS } },
-{ "stwe",    DEO(58,14), DE_MASK,	BOOKE64,	{ RS, DE, RA } },
+{ "stwe",    DEO(58,14), DE_MASK,	BOOKE64,	{ RS, DE, RA0 } },
 { "stwue",   DEO(58,15), DE_MASK,	BOOKE64,	{ RS, DE, RAS } },
 
-{ "ld",      DSO(58,0),	DS_MASK,	PPC64,		{ RT, DS, RA } },
+{ "ld",      DSO(58,0),	DS_MASK,	PPC64,		{ RT, DS, RA0 } },
 
 { "ldu",     DSO(58,1), DS_MASK,	PPC64,		{ RT, DS, RAL } },
 
-{ "lwa",     DSO(58,2), DS_MASK,	PPC64,		{ RT, DS, RA } },
+{ "lwa",     DSO(58,2), DS_MASK,	PPC64,		{ RT, DS, RA0 } },
+
+{ "dadd",    XRC(59,2,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "dadd.",   XRC(59,2,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "dqua",    ZRC(59,3,0), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+{ "dqua.",   ZRC(59,3,1), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
 
 { "fdivs",   A(59,18,0), AFRC_MASK,	PPC,		{ FRT, FRA, FRB } },
 { "fdivs.",  A(59,18,1), AFRC_MASK,	PPC,		{ FRT, FRA, FRB } },
@@ -4413,12 +4637,15 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "fsqrts",  A(59,22,0), AFRAFRC_MASK,	PPC,		{ FRT, FRB } },
 { "fsqrts.", A(59,22,1), AFRAFRC_MASK,	PPC,		{ FRT, FRB } },
 
-{ "fres",    A(59,24,0), AFRAFRC_MASK,	PPC,		{ FRT, FRB } },
-{ "fres.",   A(59,24,1), AFRAFRC_MASK,	PPC,		{ FRT, FRB } },
+{ "fres",    A(59,24,0), AFRALFRC_MASK,	PPC,		{ FRT, FRB, A_L } },
+{ "fres.",   A(59,24,1), AFRALFRC_MASK,	PPC,		{ FRT, FRB, A_L } },
 
 { "fmuls",   A(59,25,0), AFRB_MASK,	PPC,		{ FRT, FRA, FRC } },
 { "fmuls.",  A(59,25,1), AFRB_MASK,	PPC,		{ FRT, FRA, FRC } },
 
+{ "frsqrtes", A(59,26,0), AFRALFRC_MASK,POWER5,		{ FRT, FRB, A_L } },
+{ "frsqrtes.",A(59,26,1), AFRALFRC_MASK,POWER5,		{ FRT, FRB, A_L } },
+
 { "fmsubs",  A(59,28,0), A_MASK,	PPC,		{ FRT,FRA,FRC,FRB } },
 { "fmsubs.", A(59,28,1), A_MASK,	PPC,		{ FRT,FRA,FRC,FRB } },
 
@@ -4431,31 +4658,103 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "fnmadds", A(59,31,0), A_MASK,	PPC,		{ FRT,FRA,FRC,FRB } },
 { "fnmadds.",A(59,31,1), A_MASK,	PPC,		{ FRT,FRA,FRC,FRB } },
 
+{ "dmul",    XRC(59,34,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "dmul.",   XRC(59,34,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "drrnd",   ZRC(59,35,0), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+{ "drrnd.",  ZRC(59,35,1), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+
+{ "dscli",   ZRC(59,66,0), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+{ "dscli.",  ZRC(59,66,1), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+
+{ "dquai",   ZRC(59,67,0), Z_MASK,	POWER6,		{ TE,  FRT, FRB, RMC } },
+{ "dquai.",  ZRC(59,67,1), Z_MASK,	POWER6,		{ TE,  FRT, FRB, RMC } },
+
+{ "dscri",   ZRC(59,98,0), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+{ "dscri.",  ZRC(59,98,1), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+
+{ "drintx",  ZRC(59,99,0), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+{ "drintx.", ZRC(59,99,1), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+
+{ "dcmpo",   X(59,130),	   X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+
+{ "dtstex",  X(59,162),	   X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+{ "dtstdc",  Z(59,194),	   Z_MASK,	POWER6,		{ BF,  FRA, DCM } },
+{ "dtstdg",  Z(59,226),	   Z_MASK,	POWER6,		{ BF,  FRA, DGM } },
+
+{ "drintn",  ZRC(59,227,0), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+{ "drintn.", ZRC(59,227,1), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+
+{ "dctdp",   XRC(59,258,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dctdp.",  XRC(59,258,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "dctfix",  XRC(59,290,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dctfix.", XRC(59,290,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "ddedpd",  XRC(59,322,0), X_MASK,	POWER6,		{ SP, FRT, FRB } }, 
+{ "ddedpd.", XRC(59,322,1), X_MASK,	POWER6,		{ SP, FRT, FRB } }, 
+
+{ "dxex",    XRC(59,354,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dxex.",   XRC(59,354,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "dsub",    XRC(59,514,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "dsub.",   XRC(59,514,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "ddiv",    XRC(59,546,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "ddiv.",   XRC(59,546,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "dcmpu",   X(59,642),	    X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+
+{ "dtstsf",  X(59,674),	   X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+
+{ "drsp",    XRC(59,770,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "drsp.",   XRC(59,770,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "dcffix",  XRC(59,802,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dcffix.", XRC(59,802,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "denbcd",  XRC(59,834,0), X_MASK,	POWER6,		{ S, FRT, FRB } },
+{ "denbcd.", XRC(59,834,1), X_MASK,	POWER6,		{ S, FRT, FRB } },
+
+{ "diex",    XRC(59,866,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "diex.",   XRC(59,866,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
 { "stfq",    OP(60),	OP_MASK,	POWER2,		{ FRS, D, RA } },
 
 { "stfqu",   OP(61),	OP_MASK,	POWER2,		{ FRS, D, RA } },
 
-{ "lde",     DEO(62,0), DE_MASK,	BOOKE64,	{ RT, DES, RA } },
-{ "ldue",    DEO(62,1), DE_MASK,	BOOKE64,	{ RT, DES, RA } },
-{ "lfse",    DEO(62,4), DE_MASK,	BOOKE64,	{ FRT, DES, RA } },
+{ "stfdp",   OP(61),	OP_MASK,	POWER6,		{ FRT, D, RA0 } },
+
+{ "lde",     DEO(62,0), DE_MASK,	BOOKE64,	{ RT, DES, RA0 } },
+{ "ldue",    DEO(62,1), DE_MASK,	BOOKE64,	{ RT, DES, RA0 } },
+{ "lfse",    DEO(62,4), DE_MASK,	BOOKE64,	{ FRT, DES, RA0 } },
 { "lfsue",   DEO(62,5), DE_MASK,	BOOKE64,	{ FRT, DES, RAS } },
-{ "lfde",    DEO(62,6), DE_MASK,	BOOKE64,	{ FRT, DES, RA } },
+{ "lfde",    DEO(62,6), DE_MASK,	BOOKE64,	{ FRT, DES, RA0 } },
 { "lfdue",   DEO(62,7), DE_MASK,	BOOKE64,	{ FRT, DES, RAS } },
-{ "stde",    DEO(62,8), DE_MASK,	BOOKE64,	{ RS, DES, RA } },
+{ "stde",    DEO(62,8), DE_MASK,	BOOKE64,	{ RS, DES, RA0 } },
 { "stdue",   DEO(62,9), DE_MASK,	BOOKE64,	{ RS, DES, RAS } },
-{ "stfse",   DEO(62,12), DE_MASK,	BOOKE64,	{ FRS, DES, RA } },
+{ "stfse",   DEO(62,12), DE_MASK,	BOOKE64,	{ FRS, DES, RA0 } },
 { "stfsue",  DEO(62,13), DE_MASK,	BOOKE64,	{ FRS, DES, RAS } },
-{ "stfde",   DEO(62,14), DE_MASK,	BOOKE64,	{ FRS, DES, RA } },
+{ "stfde",   DEO(62,14), DE_MASK,	BOOKE64,	{ FRS, DES, RA0 } },
 { "stfdue",  DEO(62,15), DE_MASK,	BOOKE64,	{ FRS, DES, RAS } },
 
-{ "std",     DSO(62,0),	DS_MASK,	PPC64,		{ RS, DS, RA } },
+{ "std",     DSO(62,0),	DS_MASK,	PPC64,		{ RS, DS, RA0 } },
 
 { "stdu",    DSO(62,1),	DS_MASK,	PPC64,		{ RS, DS, RAS } },
 
-{ "stq",     DSO(62,2),	DS_MASK,	POWER4,		{ RSQ, DS, RA } },
+{ "stq",     DSO(62,2),	DS_MASK,	POWER4,		{ RSQ, DS, RA0 } },
 
 { "fcmpu",   X(63,0),	X_MASK|(3<<21),	COM,		{ BF, FRA, FRB } },
 
+{ "daddq",   XRC(63,2,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "daddq.",  XRC(63,2,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "dquaq",   ZRC(63,3,0), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+{ "dquaq.",  ZRC(63,3,1), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+
+{ "fcpsgn",  XRC(63,8,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "fcpsgn.", XRC(63,8,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
 { "frsp",    XRC(63,12,0), XRA_MASK,	COM,		{ FRT, FRB } },
 { "frsp.",   XRC(63,12,1), XRA_MASK,	COM,		{ FRT, FRB } },
 
@@ -4490,13 +4789,16 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 { "fsel",    A(63,23,0), A_MASK,	PPC,		{ FRT,FRA,FRC,FRB } },
 { "fsel.",   A(63,23,1), A_MASK,	PPC,		{ FRT,FRA,FRC,FRB } },
 
+{ "fre",     A(63,24,0), AFRALFRC_MASK,	POWER5,		{ FRT, FRB, A_L } },
+{ "fre.",    A(63,24,1), AFRALFRC_MASK,	POWER5,		{ FRT, FRB, A_L } },
+
 { "fmul",    A(63,25,0), AFRB_MASK,	PPCCOM,		{ FRT, FRA, FRC } },
 { "fm",      A(63,25,0), AFRB_MASK,	PWRCOM,		{ FRT, FRA, FRC } },
 { "fmul.",   A(63,25,1), AFRB_MASK,	PPCCOM,		{ FRT, FRA, FRC } },
 { "fm.",     A(63,25,1), AFRB_MASK,	PWRCOM,		{ FRT, FRA, FRC } },
 
-{ "frsqrte", A(63,26,0), AFRAFRC_MASK,	PPC,		{ FRT, FRB } },
-{ "frsqrte.",A(63,26,1), AFRAFRC_MASK,	PPC,		{ FRT, FRB } },
+{ "frsqrte", A(63,26,0), AFRALFRC_MASK,	PPC,		{ FRT, FRB, A_L } },
+{ "frsqrte.",A(63,26,1), AFRALFRC_MASK,	PPC,		{ FRT, FRB, A_L } },
 
 { "fmsub",   A(63,28,0), A_MASK,	PPCCOM,		{ FRT,FRA,FRC,FRB } },
 { "fms",     A(63,28,0), A_MASK,	PWRCOM,		{ FRT,FRA,FRC,FRB } },
@@ -4520,6 +4822,12 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "fcmpo",   X(63,32),	X_MASK|(3<<21),	COM,		{ BF, FRA, FRB } },
 
+{ "dmulq",   XRC(63,34,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "dmulq.",  XRC(63,34,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "drrndq",  ZRC(63,35,0), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+{ "drrndq.", ZRC(63,35,1), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+
 { "mtfsb1",  XRC(63,38,0), XRARB_MASK,	COM,		{ BT } },
 { "mtfsb1.", XRC(63,38,1), XRARB_MASK,	COM,		{ BT } },
 
@@ -4528,36 +4836,100 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 
 { "mcrfs",   X(63,64),	XRB_MASK|(3<<21)|(3<<16), COM,	{ BF, BFA } },
 
+{ "dscliq",  ZRC(63,66,0), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+{ "dscliq.", ZRC(63,66,1), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+
+{ "dquaiq",  ZRC(63,67,0), Z_MASK,	POWER6,		{ TE,  FRT, FRB, RMC } },
+{ "dquaiq.", ZRC(63,67,1), Z_MASK,	POWER6,		{ FRT, FRA, FRB, RMC } },
+
 { "mtfsb0",  XRC(63,70,0), XRARB_MASK,	COM,		{ BT } },
 { "mtfsb0.", XRC(63,70,1), XRARB_MASK,	COM,		{ BT } },
 
 { "fmr",     XRC(63,72,0), XRA_MASK,	COM,		{ FRT, FRB } },
 { "fmr.",    XRC(63,72,1), XRA_MASK,	COM,		{ FRT, FRB } },
 
+{ "dscriq",  ZRC(63,98,0), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+{ "dscriq.", ZRC(63,98,1), Z_MASK,	POWER6,		{ FRT, FRA, SH16 } },
+
+{ "drintxq", ZRC(63,99,0), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+{ "drintxq.",ZRC(63,99,1), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+
+{ "dcmpoq",  X(63,130),	   X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+
 { "mtfsfi",  XRC(63,134,0), XRA_MASK|(3<<21)|(1<<11), COM, { BF, U } },
 { "mtfsfi.", XRC(63,134,1), XRA_MASK|(3<<21)|(1<<11), COM, { BF, U } },
 
 { "fnabs",   XRC(63,136,0), XRA_MASK,	COM,		{ FRT, FRB } },
 { "fnabs.",  XRC(63,136,1), XRA_MASK,	COM,		{ FRT, FRB } },
 
+{ "dtstexq", X(63,162),	    X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+{ "dtstdcq", Z(63,194),	    Z_MASK,	POWER6,		{ BF,  FRA, DCM } },
+{ "dtstdgq", Z(63,226),	    Z_MASK,	POWER6,		{ BF,  FRA, DGM } },
+
+{ "drintnq", ZRC(63,227,0), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+{ "drintnq.",ZRC(63,227,1), Z_MASK,	POWER6,		{ R, FRT, FRB, RMC } },
+
+{ "dctqpq",  XRC(63,258,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dctqpq.", XRC(63,258,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
 { "fabs",    XRC(63,264,0), XRA_MASK,	COM,		{ FRT, FRB } },
 { "fabs.",   XRC(63,264,1), XRA_MASK,	COM,		{ FRT, FRB } },
 
+{ "dctfixq", XRC(63,290,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dctfixq.",XRC(63,290,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "ddedpdq", XRC(63,322,0), X_MASK,	POWER6,		{ SP, FRT, FRB } },
+{ "ddedpdq.",XRC(63,322,1), X_MASK,	POWER6,		{ SP, FRT, FRB } },
+
+{ "dxexq",   XRC(63,354,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dxexq.",  XRC(63,354,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "frin",    XRC(63,392,0), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "frin.",   XRC(63,392,1), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "friz",    XRC(63,424,0), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "friz.",   XRC(63,424,1), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "frip",    XRC(63,456,0), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "frip.",   XRC(63,456,1), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "frim",    XRC(63,488,0), XRA_MASK,	POWER5,		{ FRT, FRB } },
+{ "frim.",   XRC(63,488,1), XRA_MASK,	POWER5,		{ FRT, FRB } },
+
+{ "dsubq",   XRC(63,514,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "dsubq.",  XRC(63,514,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
+{ "ddivq",   XRC(63,546,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "ddivq.",  XRC(63,546,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
 { "mffs",    XRC(63,583,0), XRARB_MASK,	COM,		{ FRT } },
 { "mffs.",   XRC(63,583,1), XRARB_MASK,	COM,		{ FRT } },
 
+{ "dcmpuq",  X(63,642),	    X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+
+{ "dtstsfq", X(63,674),	    X_MASK,	POWER6,		{ BF,  FRA, FRB } },
+
 { "mtfsf",   XFL(63,711,0), XFL_MASK,	COM,		{ FLM, FRB } },
 { "mtfsf.",  XFL(63,711,1), XFL_MASK,	COM,		{ FLM, FRB } },
 
+{ "drdpq",   XRC(63,770,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "drdpq.",  XRC(63,770,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
+{ "dcffixq", XRC(63,802,0), X_MASK,	POWER6,		{ FRT, FRB } },
+{ "dcffixq.",XRC(63,802,1), X_MASK,	POWER6,		{ FRT, FRB } },
+
 { "fctid",   XRC(63,814,0), XRA_MASK,	PPC64,		{ FRT, FRB } },
 { "fctid.",  XRC(63,814,1), XRA_MASK,	PPC64,		{ FRT, FRB } },
 
 { "fctidz",  XRC(63,815,0), XRA_MASK,	PPC64,		{ FRT, FRB } },
 { "fctidz.", XRC(63,815,1), XRA_MASK,	PPC64,		{ FRT, FRB } },
 
+{ "denbcdq", XRC(63,834,0), X_MASK,	POWER6,		{ S, FRT, FRB } },
+{ "denbcdq.",XRC(63,834,1), X_MASK,	POWER6,		{ S, FRT, FRB } },
+
 { "fcfid",   XRC(63,846,0), XRA_MASK,	PPC64,		{ FRT, FRB } },
 { "fcfid.",  XRC(63,846,1), XRA_MASK,	PPC64,		{ FRT, FRB } },
 
+{ "diexq",   XRC(63,866,0), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+{ "diexq.",  XRC(63,866,1), X_MASK,	POWER6,		{ FRT, FRA, FRB } },
+
 };
 
 const int powerpc_num_opcodes =
diff --git a/arch/powerpc/xmon/ppc.h b/arch/powerpc/xmon/ppc.h
index 342237e8dd69..110df96354b4 100644
--- a/arch/powerpc/xmon/ppc.h
+++ b/arch/powerpc/xmon/ppc.h
@@ -1,5 +1,5 @@
 /* ppc.h -- Header file for PowerPC opcode table
-   Copyright 1994, 1995, 1999, 2000, 2001, 2002, 2003
+   Copyright 1994, 1995, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006
    Free Software Foundation, Inc.
    Written by Ian Lance Taylor, Cygnus Support
 
@@ -17,7 +17,7 @@ the GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License
 along with this file; see the file COPYING.  If not, write to the Free
-Software Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
+Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
 
 #ifndef PPC_H
 #define PPC_H
@@ -134,6 +134,18 @@ extern const int powerpc_num_opcodes;
 /* Opcode is supported by machine check APU.  */
 #define PPC_OPCODE_RFMCI	  0x800000
 
+/* Opcode is only supported by Power5 architecture.  */
+#define PPC_OPCODE_POWER5	 0x1000000
+
+/* Opcode is supported by PowerPC e300 family.  */
+#define PPC_OPCODE_E300          0x2000000
+
+/* Opcode is only supported by Power6 architecture.  */
+#define PPC_OPCODE_POWER6	 0x4000000
+
+/* Opcode is only supported by PowerPC Cell family.  */
+#define PPC_OPCODE_CELL		 0x8000000
+
 /* A macro to extract the major opcode from an instruction.  */
 #define PPC_OP(i) (((i) >> 26) & 0x3f)
 
@@ -233,25 +245,28 @@ extern const struct powerpc_operand powerpc_operands[];
    register names with a leading 'r'.  */
 #define PPC_OPERAND_GPR (040)
 
+/* Like PPC_OPERAND_GPR, but don't print a leading 'r' for r0.  */
+#define PPC_OPERAND_GPR_0 (0100)
+
 /* This operand names a floating point register.  The disassembler
    prints these with a leading 'f'.  */
-#define PPC_OPERAND_FPR (0100)
+#define PPC_OPERAND_FPR (0200)
 
 /* This operand is a relative branch displacement.  The disassembler
    prints these symbolically if possible.  */
-#define PPC_OPERAND_RELATIVE (0200)
+#define PPC_OPERAND_RELATIVE (0400)
 
 /* This operand is an absolute branch address.  The disassembler
    prints these symbolically if possible.  */
-#define PPC_OPERAND_ABSOLUTE (0400)
+#define PPC_OPERAND_ABSOLUTE (01000)
 
 /* This operand is optional, and is zero if omitted.  This is used for
-   the optional BF and L fields in the comparison instructions.  The
+   example, in the optional BF field in the comparison instructions.  The
    assembler must count the number of operands remaining on the line,
    and the number of operands remaining for the opcode, and decide
    whether this operand is present or not.  The disassembler should
    print this operand out only if it is not zero.  */
-#define PPC_OPERAND_OPTIONAL (01000)
+#define PPC_OPERAND_OPTIONAL (02000)
 
 /* This flag is only used with PPC_OPERAND_OPTIONAL.  If this operand
    is omitted, then for the next operand use this operand value plus
@@ -259,24 +274,24 @@ extern const struct powerpc_operand powerpc_operands[];
    hack is needed because the Power rotate instructions can take
    either 4 or 5 operands.  The disassembler should print this operand
    out regardless of the PPC_OPERAND_OPTIONAL field.  */
-#define PPC_OPERAND_NEXT (02000)
+#define PPC_OPERAND_NEXT (04000)
 
 /* This operand should be regarded as a negative number for the
    purposes of overflow checking (i.e., the normal most negative
    number is disallowed and one more than the normal most positive
    number is allowed).  This flag will only be set for a signed
    operand.  */
-#define PPC_OPERAND_NEGATIVE (04000)
+#define PPC_OPERAND_NEGATIVE (010000)
 
 /* This operand names a vector unit register.  The disassembler
    prints these with a leading 'v'.  */
-#define PPC_OPERAND_VR (010000)
+#define PPC_OPERAND_VR (020000)
 
 /* This operand is for the DS field in a DS form instruction.  */
-#define PPC_OPERAND_DS (020000)
+#define PPC_OPERAND_DS (040000)
 
 /* This operand is for the DQ field in a DQ form instruction.  */
-#define PPC_OPERAND_DQ (040000)
+#define PPC_OPERAND_DQ (0100000)
 
 /* The POWER and PowerPC assemblers use a few macros.  We keep them
    with the operands table for simplicity.  The macro table is an
diff --git a/arch/powerpc/xmon/spu-dis.c b/arch/powerpc/xmon/spu-dis.c
new file mode 100644
index 000000000000..ee929c641bf3
--- /dev/null
+++ b/arch/powerpc/xmon/spu-dis.c
@@ -0,0 +1,248 @@
+/* Disassemble SPU instructions
+
+   Copyright 2006 Free Software Foundation, Inc.
+
+   This file is part of GDB, GAS, and the GNU binutils.
+
+   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.,
+   51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+#include <linux/string.h>
+#include "nonstdio.h"
+#include "ansidecl.h"
+#include "spu.h"
+#include "dis-asm.h"
+
+/* This file provides a disassembler function which uses
+   the disassembler interface defined in dis-asm.h.   */
+
+extern const struct spu_opcode spu_opcodes[];
+extern const int spu_num_opcodes;
+
+#define SPU_DISASM_TBL_SIZE (1 << 11)
+static const struct spu_opcode *spu_disassemble_table[SPU_DISASM_TBL_SIZE];
+
+static void
+init_spu_disassemble (void)
+{
+  int i;
+
+  /* If two instructions have the same opcode then we prefer the first
+   * one.  In most cases it is just an alternate mnemonic. */
+  for (i = 0; i < spu_num_opcodes; i++)
+    {
+      int o = spu_opcodes[i].opcode;
+      if (o >= SPU_DISASM_TBL_SIZE)
+	continue; /* abort (); */
+      if (spu_disassemble_table[o] == 0)
+	spu_disassemble_table[o] = &spu_opcodes[i];
+    }
+}
+
+/* Determine the instruction from the 10 least significant bits. */
+static const struct spu_opcode *
+get_index_for_opcode (unsigned int insn)
+{
+  const struct spu_opcode *index;
+  unsigned int opcode = insn >> (32-11);
+
+  /* Init the table.  This assumes that element 0/opcode 0 (currently
+   * NOP) is always used */
+  if (spu_disassemble_table[0] == 0)
+    init_spu_disassemble ();
+
+  if ((index = spu_disassemble_table[opcode & 0x780]) != 0
+      && index->insn_type == RRR)
+    return index;
+
+  if ((index = spu_disassemble_table[opcode & 0x7f0]) != 0
+      && (index->insn_type == RI18 || index->insn_type == LBT))
+    return index;
+
+  if ((index = spu_disassemble_table[opcode & 0x7f8]) != 0
+      && index->insn_type == RI10)
+    return index;
+
+  if ((index = spu_disassemble_table[opcode & 0x7fc]) != 0
+      && (index->insn_type == RI16))
+    return index;
+
+  if ((index = spu_disassemble_table[opcode & 0x7fe]) != 0
+      && (index->insn_type == RI8))
+    return index;
+
+  if ((index = spu_disassemble_table[opcode & 0x7ff]) != 0)
+    return index;
+
+  return 0;
+}
+
+/* Print a Spu instruction.  */
+
+int
+print_insn_spu (unsigned long insn, unsigned long memaddr)
+{
+  int value;
+  int hex_value;
+  const struct spu_opcode *index;
+  enum spu_insns tag;
+
+  index = get_index_for_opcode (insn);
+
+  if (index == 0)
+    {
+      printf(".long 0x%x", insn);
+    }
+  else
+    {
+      int i;
+      int paren = 0;
+      tag = (enum spu_insns)(index - spu_opcodes);
+      printf("%s", index->mnemonic);
+      if (tag == M_BI || tag == M_BISL || tag == M_IRET || tag == M_BISLED
+	  || tag == M_BIHNZ || tag == M_BIHZ || tag == M_BINZ || tag == M_BIZ
+          || tag == M_SYNC || tag == M_HBR)
+	{
+	  int fb = (insn >> (32-18)) & 0x7f;
+	  if (fb & 0x40)
+	    printf(tag == M_SYNC ? "c" : "p");
+	  if (fb & 0x20)
+	    printf("d");
+	  if (fb & 0x10)
+	    printf("e");
+	}
+      if (index->arg[0] != 0)
+	printf("\t");
+      hex_value = 0;
+      for (i = 1;  i <= index->arg[0]; i++)
+	{
+	  int arg = index->arg[i];
+	  if (arg != A_P && !paren && i > 1)
+	    printf(",");
+
+	  switch (arg)
+	    {
+	    case A_T:
+	      printf("$%d",
+				     DECODE_INSN_RT (insn));
+	      break;
+	    case A_A:
+	      printf("$%d",
+				     DECODE_INSN_RA (insn));
+	      break;
+	    case A_B:
+	      printf("$%d",
+				     DECODE_INSN_RB (insn));
+	      break;
+	    case A_C:
+	      printf("$%d",
+				     DECODE_INSN_RC (insn));
+	      break;
+	    case A_S:
+	      printf("$sp%d",
+				     DECODE_INSN_RA (insn));
+	      break;
+	    case A_H:
+	      printf("$ch%d",
+				     DECODE_INSN_RA (insn));
+	      break;
+	    case A_P:
+	      paren++;
+	      printf("(");
+	      break;
+	    case A_U7A:
+	      printf("%d",
+				     173 - DECODE_INSN_U8 (insn));
+	      break;
+	    case A_U7B:
+	      printf("%d",
+				     155 - DECODE_INSN_U8 (insn));
+	      break;
+	    case A_S3:
+	    case A_S6:
+	    case A_S7:
+	    case A_S7N:
+	    case A_U3:
+	    case A_U5:
+	    case A_U6:
+	    case A_U7:
+	      hex_value = DECODE_INSN_I7 (insn);
+	      printf("%d", hex_value);
+	      break;
+	    case A_S11:
+	      print_address(memaddr + DECODE_INSN_I9a (insn) * 4);
+	      break;
+	    case A_S11I:
+	      print_address(memaddr + DECODE_INSN_I9b (insn) * 4);
+	      break;
+	    case A_S10:
+	    case A_S10B:
+	      hex_value = DECODE_INSN_I10 (insn);
+	      printf("%d", hex_value);
+	      break;
+	    case A_S14:
+	      hex_value = DECODE_INSN_I10 (insn) * 16;
+	      printf("%d", hex_value);
+	      break;
+	    case A_S16:
+	      hex_value = DECODE_INSN_I16 (insn);
+	      printf("%d", hex_value);
+	      break;
+	    case A_X16:
+	      hex_value = DECODE_INSN_U16 (insn);
+	      printf("%u", hex_value);
+	      break;
+	    case A_R18:
+	      value = DECODE_INSN_I16 (insn) * 4;
+	      if (value == 0)
+		printf("%d", value);
+	      else
+		{
+		  hex_value = memaddr + value;
+		  print_address(hex_value & 0x3ffff);
+		}
+	      break;
+	    case A_S18:
+	      value = DECODE_INSN_U16 (insn) * 4;
+	      if (value == 0)
+		printf("%d", value);
+	      else
+		print_address(value);
+	      break;
+	    case A_U18:
+	      value = DECODE_INSN_U18 (insn);
+	      if (value == 0 || 1)
+		{
+		  hex_value = value;
+		  printf("%u", value);
+		}
+	      else
+		print_address(value);
+	      break;
+	    case A_U14:
+	      hex_value = DECODE_INSN_U14 (insn);
+	      printf("%u", hex_value);
+	      break;
+	    }
+	  if (arg != A_P && paren)
+	    {
+	      printf(")");
+	      paren--;
+	    }
+	}
+      if (hex_value > 16)
+	printf("\t# %x", hex_value);
+    }
+  return 4;
+}
diff --git a/arch/powerpc/xmon/spu-insns.h b/arch/powerpc/xmon/spu-insns.h
new file mode 100644
index 000000000000..99dc452821ac
--- /dev/null
+++ b/arch/powerpc/xmon/spu-insns.h
@@ -0,0 +1,410 @@
+/* SPU ELF support for BFD.
+
+   Copyright 2006 Free Software Foundation, Inc.
+
+   This file is part of BFD, the Binary File Descriptor library.
+
+   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., 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+/* SPU Opcode Table
+
+-=-=-= FORMAT =-=-=-
+                                             		                                             
+       +----+-------+-------+-------+-------+  		       +------------+-------+-------+-------+
+RRR    | op |  RC   |  RB   |  RA   |  RT   |		RI7    | op         |  I7   |  RA   |  RT   |
+       +----+-------+-------+-------+-------+		       +------------+-------+-------+-------+
+        0  3       1       1       2       3		        0          1       1       2       3 
+                   0       7       4       1		                   0       7       4       1 
+
+       +-----------+--------+-------+-------+		       +---------+----------+-------+-------+
+RI8    | op        |   I8   |  RA   |  RT   |		RI10   | op      |   I10    |  RA   |  RT   |
+       +-----------+--------+-------+-------+		       +---------+----------+-------+-------+
+        0         9        1       2       3		        0       7          1       2       3 
+                           7       4       1		                           7       4       1 
+
+       +----------+-----------------+-------+		       +--------+-------------------+-------+
+RI16   | op       |       I16       |  RT   |		RI18   | op     |       I18         |  RT   |
+       +----------+-----------------+-------+		       +--------+-------------------+-------+
+        0        8                 2       3		        0      6                   2       3 
+                                   4       1		                                   4       1 
+
+       +------------+-------+-------+-------+		       +-------+--+-----------------+-------+
+RR     | op         |  RB   |  RA   |  RT   |		LBT    | op    |RO|       I16       |  RO   |
+       +------------+-------+-------+-------+		       +-------+--+-----------------+-------+
+        0          1       1       2       3		        0     6  8                 2       3 
+                   0       7       4       1		                                   4       1 
+
+							       +------------+----+--+-------+-------+
+							LBTI   | op         | // |RO|  RA   |  RO   |
+							       +------------+----+--+-------+-------+
+							        0          1    1  1       2       3
+							                   0    5  7       4       1
+
+-=-=-= OPCODE =-=-=-
+
+OPCODE field specifies the most significant 11bit of the instruction. Some formats don't have 11bits for opcode field, and in this
+case, bit field other than op are defined as 0s. For example, opcode of fma instruction which is RRR format is defined as 0x700,
+since 0x700 -> 11'b11100000000, this means opcode is 4'b1110, and other 7bits are defined as 7'b0000000.
+
+-=-=-= ASM_FORMAT =-=-=-
+
+RRR category						RI7 category                               
+	ASM_RRR		mnemonic RC, RA, RB, RT		        ASM_RI4         mnemonic RT, RA, I4
+							        ASM_RI7         mnemonic RT, RA, I7
+
+RI8 category						RI10 category                               
+	ASM_RUI8	mnemonic RT, RA, UI8		        ASM_AI10        mnemonic RA, I10    
+							        ASM_RI10        mnemonic RT, RA, R10
+							        ASM_RI10IDX     mnemonic RT, I10(RA)
+
+RI16 category						RI18 category                           
+	ASM_I16W	mnemonic I16W			        ASM_RI18        mnemonic RT, I18
+	ASM_RI16	mnemonic RT, I16
+	ASM_RI16W	mnemonic RT, I16W
+
+RR category						LBT category                                    
+	ASM_MFSPR	mnemonic RT, SA			        ASM_LBT         mnemonic brinst, brtarg 
+	ASM_MTSPR	mnemonic SA, RT			                                                
+	ASM_NOOP	mnemonic			LBTI category                                   
+	ASM_RA		mnemonic RA			        ASM_LBTI        mnemonic brinst, RA     
+	ASM_RAB		mnemonic RA, RB
+	ASM_RDCH	mnemonic RT, CA
+	ASM_RR		mnemonic RT, RA, RB
+	ASM_RT		mnemonic RT
+	ASM_RTA		mnemonic RT, RA
+	ASM_WRCH	mnemonic CA, RT
+
+Note that RRR instructions have the names for RC and RT reversed from
+what's in the ISA, in order to put RT in the same position it appears
+for other formats.
+
+-=-=-= DEPENDENCY =-=-=-
+
+DEPENDENCY filed consists of 5 digits. This represents which register is used as source and which register is used as target.
+The first(most significant) digit is always 0. Then it is followd by RC, RB, RA and RT digits.
+If the digit is 0, this means the corresponding register is not used in the instruction.
+If the digit is 1, this means the corresponding register is used as a source in the instruction.
+If the digit is 2, this means the corresponding register is used as a target in the instruction.
+If the digit is 3, this means the corresponding register is used as both source and target in the instruction.
+For example, fms instruction has 00113 as the DEPENDENCY field. This means RC is not used in this operation, RB and RA are
+used as sources and RT is the target.
+
+-=-=-= PIPE =-=-=-
+
+This field shows which execution pipe is used for the instruction
+
+pipe0 execution pipelines:
+	FP6	SP floating pipeline
+	FP7	integer operations executed in SP floating pipeline
+	FPD	DP floating pipeline
+	FX2	FXU pipeline
+	FX3	Rotate/Shift pipeline
+	FXB	Byte pipeline
+	NOP	No pipeline
+
+pipe1 execution pipelines:
+	BR	Branch pipeline
+	LNOP	No pipeline
+	LS	Load/Store pipeline
+	SHUF	Shuffle pipeline
+	SPR	SPR/CH pipeline
+
+*/
+
+#define _A0() {0}
+#define _A1(a) {1,a}
+#define _A2(a,b) {2,a,b}
+#define _A3(a,b,c) {3,a,b,c}
+#define _A4(a,b,c,d) {4,a,b,c,d}
+
+/*    TAG		FORMAT	OPCODE	MNEMONIC	ASM_FORMAT	DEPENDENCY	PIPE	COMMENT				*/
+/*									0[RC][RB][RA][RT]					*/
+/*									1:src, 2:target						*/
+
+APUOP(M_BR,		RI16,	0x190,	"br",		_A1(A_R18),	00000,	BR)	/* BRel          IP<-IP+I16 */
+APUOP(M_BRSL,		RI16,	0x198,	"brsl",		_A2(A_T,A_R18),	00002,	BR)	/* BRelSetLink   RT,IP<-IP,IP+I16 */
+APUOP(M_BRA,		RI16,	0x180,	"bra",		_A1(A_S18),	00000,	BR)	/* BRAbs         IP<-I16 */
+APUOP(M_BRASL,		RI16,	0x188,	"brasl",	_A2(A_T,A_S18),	00002,	BR)	/* BRAbsSetLink  RT,IP<-IP,I16 */
+APUOP(M_FSMBI,		RI16,	0x194,	"fsmbi",	_A2(A_T,A_X16),	00002,	SHUF)	/* FormSelMask%I RT<-fsm(I16) */
+APUOP(M_LQA,		RI16,	0x184,	"lqa",		_A2(A_T,A_S18),	00002,	LS)	/* LoadQAbs      RT<-M[I16] */
+APUOP(M_LQR,		RI16,	0x19C,	"lqr",		_A2(A_T,A_R18),	00002,	LS)	/* LoadQRel      RT<-M[IP+I16] */
+APUOP(M_STOP,		RR,	0x000,	"stop",		_A0(),		00000,	BR)	/* STOP          stop */
+APUOP(M_STOP2,		RR,	0x000,	"stop",		_A1(A_U14),	00000,	BR)	/* STOP          stop */
+APUOP(M_STOPD,		RR,	0x140,	"stopd",	_A3(A_T,A_A,A_B),         00111,	BR)	/* STOPD         stop (with register dependencies) */
+APUOP(M_LNOP,		RR,	0x001,	"lnop",		_A0(),		00000,	LNOP)	/* LNOP          no_operation */
+APUOP(M_SYNC,		RR,	0x002,	"sync",		_A0(),		00000,	BR)	/* SYNC          flush_pipe */
+APUOP(M_DSYNC,		RR,	0x003,	"dsync",	_A0(),		00000,	BR)	/* DSYNC         flush_store_queue */
+APUOP(M_MFSPR,		RR,	0x00c,	"mfspr",	_A2(A_T,A_S),	00002,	SPR)	/* MFSPR         RT<-SA */
+APUOP(M_RDCH,		RR,	0x00d,	"rdch",		_A2(A_T,A_H),	00002,	SPR)	/* ReaDCHannel   RT<-CA:data */
+APUOP(M_RCHCNT,		RR,	0x00f,	"rchcnt",	_A2(A_T,A_H),	00002,	SPR)	/* ReaDCHanCouNT RT<-CA:count */
+APUOP(M_HBRA,		LBT,	0x080,	"hbra",		_A2(A_S11,A_S18),	00000,	LS)	/* HBRA          BTB[B9]<-M[I16] */
+APUOP(M_HBRR,		LBT,	0x090,	"hbrr",		_A2(A_S11,A_R18),	00000,	LS)	/* HBRR          BTB[B9]<-M[IP+I16] */
+APUOP(M_BRZ,		RI16,	0x100,	"brz",		_A2(A_T,A_R18),	00001,	BR)	/* BRZ           IP<-IP+I16_if(RT) */
+APUOP(M_BRNZ,		RI16,	0x108,	"brnz",		_A2(A_T,A_R18),	00001,	BR)	/* BRNZ          IP<-IP+I16_if(RT) */
+APUOP(M_BRHZ,		RI16,	0x110,	"brhz",		_A2(A_T,A_R18),	00001,	BR)	/* BRHZ          IP<-IP+I16_if(RT) */
+APUOP(M_BRHNZ,		RI16,	0x118,	"brhnz",	_A2(A_T,A_R18),	00001,	BR)	/* BRHNZ         IP<-IP+I16_if(RT) */
+APUOP(M_STQA,		RI16,	0x104,	"stqa",		_A2(A_T,A_S18),	00001,	LS)	/* SToreQAbs     M[I16]<-RT */
+APUOP(M_STQR,		RI16,	0x11C,	"stqr",		_A2(A_T,A_R18),	00001,	LS)	/* SToreQRel     M[IP+I16]<-RT */
+APUOP(M_MTSPR,		RR,	0x10c,	"mtspr",	_A2(A_S,A_T),	00001,	SPR)	/* MTSPR         SA<-RT */
+APUOP(M_WRCH,		RR,	0x10d,	"wrch",		_A2(A_H,A_T),	00001,	SPR)	/* ChanWRite     CA<-RT */
+APUOP(M_LQD,		RI10,	0x1a0,	"lqd",		_A4(A_T,A_S14,A_P,A_A),	00012,	LS)	/* LoadQDisp     RT<-M[Ra+I10] */
+APUOP(M_BI,		RR,	0x1a8,	"bi",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
+APUOP(M_BISL,		RR,	0x1a9,	"bisl",		_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
+APUOP(M_IRET,  		RR,	0x1aa,	"iret",	        _A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
+APUOP(M_IRET2, 		RR,	0x1aa,	"iret",	        _A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
+APUOP(M_BISLED,		RR,	0x1ab,	"bisled",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
+APUOP(M_HBR,		LBTI,	0x1ac,	"hbr",		_A2(A_S11I,A_A),	00010,	LS)	/* HBR           BTB[B9]<-M[Ra] */
+APUOP(M_FREST,		RR,	0x1b8,	"frest",	_A2(A_T,A_A),	00012,	SHUF)	/* FREST         RT<-recip(RA) */
+APUOP(M_FRSQEST,	RR,	0x1b9,	"frsqest",	_A2(A_T,A_A),	00012,	SHUF)	/* FRSQEST       RT<-rsqrt(RA) */
+APUOP(M_FSM,		RR,	0x1b4,	"fsm",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
+APUOP(M_FSMH,		RR,	0x1b5,	"fsmh",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
+APUOP(M_FSMB,		RR,	0x1b6,	"fsmb",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
+APUOP(M_GB,		RR,	0x1b0,	"gb",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
+APUOP(M_GBH,		RR,	0x1b1,	"gbh",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
+APUOP(M_GBB,		RR,	0x1b2,	"gbb",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
+APUOP(M_CBD,		RI7,	0x1f4,	"cbd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
+APUOP(M_CHD,		RI7,	0x1f5,	"chd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
+APUOP(M_CWD,		RI7,	0x1f6,	"cwd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
+APUOP(M_CDD,		RI7,	0x1f7,	"cdd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
+APUOP(M_ROTQBII,	RI7,	0x1f8,	"rotqbii",	_A3(A_T,A_A,A_U3),	00012,	SHUF)	/* ROTQBII       RT<-RA<<<I7 */
+APUOP(M_ROTQBYI,	RI7,	0x1fc,	"rotqbyi",	_A3(A_T,A_A,A_S7N),	00012,	SHUF)	/* ROTQBYI       RT<-RA<<<(I7*8) */
+APUOP(M_ROTQMBII,	RI7,	0x1f9,	"rotqmbii",	_A3(A_T,A_A,A_S3),	00012,	SHUF)	/* ROTQMBII      RT<-RA<<I7 */
+APUOP(M_ROTQMBYI,	RI7,	0x1fd,	"rotqmbyi",	_A3(A_T,A_A,A_S6),	00012,	SHUF)	/* ROTQMBYI      RT<-RA<<I7 */
+APUOP(M_SHLQBII,	RI7,	0x1fb,	"shlqbii",	_A3(A_T,A_A,A_U3),	00012,	SHUF)	/* SHLQBII       RT<-RA<<I7 */
+APUOP(M_SHLQBYI,	RI7,	0x1ff,	"shlqbyi",	_A3(A_T,A_A,A_U5),	00012,	SHUF)	/* SHLQBYI       RT<-RA<<I7 */
+APUOP(M_STQD,		RI10,	0x120,	"stqd",		_A4(A_T,A_S14,A_P,A_A),	00011,	LS)	/* SToreQDisp    M[Ra+I10]<-RT */
+APUOP(M_BIHNZ,		RR,	0x12b,	"bihnz",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
+APUOP(M_BIHZ,		RR,	0x12a,	"bihz",		_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
+APUOP(M_BINZ,		RR,	0x129,	"binz",		_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
+APUOP(M_BIZ,		RR,	0x128,	"biz",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
+APUOP(M_CBX,		RR,	0x1d4,	"cbx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
+APUOP(M_CHX,		RR,	0x1d5,	"chx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
+APUOP(M_CWX,		RR,	0x1d6,	"cwx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
+APUOP(M_CDX,		RR,	0x1d7,	"cdx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
+APUOP(M_LQX,		RR,	0x1c4,	"lqx",		_A3(A_T,A_A,A_B),		00112,	LS)	/* LoadQindeX    RT<-M[Ra+Rb] */
+APUOP(M_ROTQBI,		RR,	0x1d8,	"rotqbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* ROTQBI        RT<-RA<<<Rb */
+APUOP(M_ROTQMBI,	RR,	0x1d9,	"rotqmbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* ROTQMBI       RT<-RA<<Rb */
+APUOP(M_SHLQBI,		RR,	0x1db,	"shlqbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBI        RT<-RA<<Rb */
+APUOP(M_ROTQBY,		RR,	0x1dc,	"rotqby",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQBY        RT<-RA<<<(Rb*8) */
+APUOP(M_ROTQMBY,	RR,	0x1dd,	"rotqmby",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQMBY       RT<-RA<<Rb */
+APUOP(M_SHLQBY,		RR,	0x1df,	"shlqby",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBY        RT<-RA<<Rb */
+APUOP(M_ROTQBYBI,	RR,	0x1cc,	"rotqbybi",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQBYBI      RT<-RA<<Rb */
+APUOP(M_ROTQMBYBI,	RR,	0x1cd,	"rotqmbybi",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQMBYBI     RT<-RA<<Rb */
+APUOP(M_SHLQBYBI,	RR,	0x1cf,	"shlqbybi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBYBI      RT<-RA<<Rb */
+APUOP(M_STQX,		RR,	0x144,	"stqx",		_A3(A_T,A_A,A_B),		00111,	LS)	/* SToreQindeX   M[Ra+Rb]<-RT */
+APUOP(M_SHUFB,		RRR,	0x580,	"shufb",	_A4(A_C,A_A,A_B,A_T),	02111,	SHUF)	/* SHUFfleBytes  RC<-f(RA,RB,RT) */
+APUOP(M_IL,		RI16,	0x204,	"il",		_A2(A_T,A_S16),	00002,	FX2)	/* ImmLoad       RT<-sxt(I16) */
+APUOP(M_ILH,		RI16,	0x20c,	"ilh",		_A2(A_T,A_X16),	00002,	FX2)	/* ImmLoadH      RT<-I16 */
+APUOP(M_ILHU,		RI16,	0x208,	"ilhu",		_A2(A_T,A_X16),	00002,	FX2)	/* ImmLoadHUpper RT<-I16<<16 */
+APUOP(M_ILA,		RI18,	0x210,	"ila",		_A2(A_T,A_U18),	00002,	FX2)	/* ImmLoadAddr   RT<-zxt(I18) */
+APUOP(M_NOP,		RR,	0x201,	"nop",		_A1(A_T),		00000,	NOP)	/* XNOP          no_operation */
+APUOP(M_NOP2,		RR,	0x201,	"nop",		_A0(),		00000,	NOP)	/* XNOP          no_operation */
+APUOP(M_IOHL,		RI16,	0x304,	"iohl",		_A2(A_T,A_X16),	00003,	FX2)	/* AddImmeXt     RT<-RT+sxt(I16) */
+APUOP(M_ANDBI,		RI10,	0x0b0,	"andbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
+APUOP(M_ANDHI,		RI10,	0x0a8,	"andhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
+APUOP(M_ANDI,		RI10,	0x0a0,	"andi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
+APUOP(M_ORBI,		RI10,	0x030,	"orbi",		_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
+APUOP(M_ORHI,		RI10,	0x028,	"orhi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
+APUOP(M_ORI,		RI10,	0x020,	"ori",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
+APUOP(M_ORX,		RR,	0x1f0,	"orx",		_A2(A_T,A_A),		00012,	BR)	/* ORX           RT<-RA.w0|RA.w1|RA.w2|RA.w3 */
+APUOP(M_XORBI,		RI10,	0x230,	"xorbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
+APUOP(M_XORHI,		RI10,	0x228,	"xorhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
+APUOP(M_XORI,		RI10,	0x220,	"xori",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
+APUOP(M_AHI,		RI10,	0x0e8,	"ahi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* Add%Immed     RT<-RA+I10 */
+APUOP(M_AI,		RI10,	0x0e0,	"ai",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* Add%Immed     RT<-RA+I10 */
+APUOP(M_SFHI,		RI10,	0x068,	"sfhi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* SubFrom%Imm   RT<-I10-RA */
+APUOP(M_SFI,		RI10,	0x060,	"sfi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* SubFrom%Imm   RT<-I10-RA */
+APUOP(M_CGTBI,		RI10,	0x270,	"cgtbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
+APUOP(M_CGTHI,		RI10,	0x268,	"cgthi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
+APUOP(M_CGTI,		RI10,	0x260,	"cgti",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
+APUOP(M_CLGTBI,		RI10,	0x2f0,	"clgtbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
+APUOP(M_CLGTHI,		RI10,	0x2e8,	"clgthi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
+APUOP(M_CLGTI,		RI10,	0x2e0,	"clgti",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
+APUOP(M_CEQBI,		RI10,	0x3f0,	"ceqbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
+APUOP(M_CEQHI,		RI10,	0x3e8,	"ceqhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
+APUOP(M_CEQI,		RI10,	0x3e0,	"ceqi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
+APUOP(M_HGTI,		RI10,	0x278,	"hgti",		_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltGTI       halt_if(RA>I10) */
+APUOP(M_HGTI2,		RI10,	0x278,	"hgti",		_A2(A_A,A_S10),	00010,	FX2)	/* HaltGTI       halt_if(RA>I10) */
+APUOP(M_HLGTI,		RI10,	0x2f8,	"hlgti",	_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltLGTI      halt_if(RA>I10) */
+APUOP(M_HLGTI2,		RI10,	0x2f8,	"hlgti",	_A2(A_A,A_S10),	00010,	FX2)	/* HaltLGTI      halt_if(RA>I10) */
+APUOP(M_HEQI,		RI10,	0x3f8,	"heqi",		_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltEQImm     halt_if(RA=I10) */
+APUOP(M_HEQI2,		RI10,	0x3f8,	"heqi",		_A2(A_A,A_S10),	00010,	FX2)	/* HaltEQImm     halt_if(RA=I10) */
+APUOP(M_MPYI,		RI10,	0x3a0,	"mpyi",		_A3(A_T,A_A,A_S10),	00012,	FP7)	/* MPYI          RT<-RA*I10 */
+APUOP(M_MPYUI,		RI10,	0x3a8,	"mpyui",	_A3(A_T,A_A,A_S10),	00012,	FP7)	/* MPYUI         RT<-RA*I10 */
+APUOP(M_CFLTS,		RI8,	0x3b0,	"cflts",	_A3(A_T,A_A,A_U7A),	00012,	FP7)	/* CFLTS         RT<-int(RA,I8) */
+APUOP(M_CFLTU,		RI8,	0x3b2,	"cfltu",	_A3(A_T,A_A,A_U7A),	00012,	FP7)	/* CFLTU         RT<-int(RA,I8) */
+APUOP(M_CSFLT,		RI8,	0x3b4,	"csflt",	_A3(A_T,A_A,A_U7B),	00012,	FP7)	/* CSFLT         RT<-flt(RA,I8) */
+APUOP(M_CUFLT,		RI8,	0x3b6,	"cuflt",	_A3(A_T,A_A,A_U7B),	00012,	FP7)	/* CUFLT         RT<-flt(RA,I8) */
+APUOP(M_FESD,		RR,	0x3b8,	"fesd",		_A2(A_T,A_A),	00012,	FPD)	/* FESD          RT<-double(RA) */
+APUOP(M_FRDS,		RR,	0x3b9,	"frds",		_A2(A_T,A_A),	00012,	FPD)	/* FRDS          RT<-single(RA) */
+APUOP(M_FSCRRD,		RR,	0x398,	"fscrrd",	_A1(A_T),		00002,	FPD)	/* FSCRRD        RT<-FP_status */
+APUOP(M_FSCRWR,		RR,	0x3ba,	"fscrwr",	_A2(A_T,A_A),	00010,	FP7)	/* FSCRWR        FP_status<-RA */
+APUOP(M_FSCRWR2,	RR,	0x3ba,	"fscrwr",	_A1(A_A),		00010,	FP7)	/* FSCRWR        FP_status<-RA */
+APUOP(M_CLZ,		RR,	0x2a5,	"clz",		_A2(A_T,A_A),	00012,	FX2)	/* CLZ           RT<-clz(RA) */
+APUOP(M_CNTB,		RR,	0x2b4,	"cntb",		_A2(A_T,A_A),	00012,	FXB)	/* CNT           RT<-pop(RA) */
+APUOP(M_XSBH,		RR,	0x2b6,	"xsbh",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignBtoH   RT<-sign_ext(RA) */
+APUOP(M_XSHW,		RR,	0x2ae,	"xshw",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignHtoW   RT<-sign_ext(RA) */
+APUOP(M_XSWD,		RR,	0x2a6,	"xswd",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignWtoD   RT<-sign_ext(RA) */
+APUOP(M_ROTI,		RI7,	0x078,	"roti",		_A3(A_T,A_A,A_S7N),	00012,	FX3)	/* ROT%I         RT<-RA<<<I7 */
+APUOP(M_ROTMI,		RI7,	0x079,	"rotmi",	_A3(A_T,A_A,A_S7),	00012,	FX3)	/* ROT%MI        RT<-RA<<I7 */
+APUOP(M_ROTMAI,		RI7,	0x07a,	"rotmai",	_A3(A_T,A_A,A_S7),	00012,	FX3)	/* ROTMA%I       RT<-RA<<I7 */
+APUOP(M_SHLI,		RI7,	0x07b,	"shli",		_A3(A_T,A_A,A_U6),	00012,	FX3)	/* SHL%I         RT<-RA<<I7 */
+APUOP(M_ROTHI,		RI7,	0x07c,	"rothi",	_A3(A_T,A_A,A_S7N),	00012,	FX3)	/* ROT%I         RT<-RA<<<I7 */
+APUOP(M_ROTHMI,		RI7,	0x07d,	"rothmi",	_A3(A_T,A_A,A_S6),	00012,	FX3)	/* ROT%MI        RT<-RA<<I7 */
+APUOP(M_ROTMAHI,	RI7,	0x07e,	"rotmahi",	_A3(A_T,A_A,A_S6),	00012,	FX3)	/* ROTMA%I       RT<-RA<<I7 */
+APUOP(M_SHLHI,		RI7,	0x07f,	"shlhi",	_A3(A_T,A_A,A_U5),	00012,	FX3)	/* SHL%I         RT<-RA<<I7 */
+APUOP(M_A,		RR,	0x0c0,	"a",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* Add%          RT<-RA+RB */
+APUOP(M_AH,		RR,	0x0c8,	"ah",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* Add%          RT<-RA+RB */
+APUOP(M_SF,		RR,	0x040,	"sf",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* SubFrom%      RT<-RB-RA */
+APUOP(M_SFH,		RR,	0x048,	"sfh",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* SubFrom%      RT<-RB-RA */
+APUOP(M_CGT,		RR,	0x240,	"cgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
+APUOP(M_CGTB,		RR,	0x250,	"cgtb",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
+APUOP(M_CGTH,		RR,	0x248,	"cgth",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
+APUOP(M_CLGT,		RR,	0x2c0,	"clgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
+APUOP(M_CLGTB,		RR,	0x2d0,	"clgtb",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
+APUOP(M_CLGTH,		RR,	0x2c8,	"clgth",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
+APUOP(M_CEQ,		RR,	0x3c0,	"ceq",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
+APUOP(M_CEQB,		RR,	0x3d0,	"ceqb",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
+APUOP(M_CEQH,		RR,	0x3c8,	"ceqh",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
+APUOP(M_HGT,		RR,	0x258,	"hgt",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltGT        halt_if(RA>RB) */
+APUOP(M_HGT2,		RR,	0x258,	"hgt",		_A2(A_A,A_B),	00110,	FX2)	/* HaltGT        halt_if(RA>RB) */
+APUOP(M_HLGT,		RR,	0x2d8,	"hlgt",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltLGT       halt_if(RA>RB) */
+APUOP(M_HLGT2,		RR,	0x2d8,	"hlgt",		_A2(A_A,A_B),	00110,	FX2)	/* HaltLGT       halt_if(RA>RB) */
+APUOP(M_HEQ,		RR,	0x3d8,	"heq",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltEQ        halt_if(RA=RB) */
+APUOP(M_HEQ2,		RR,	0x3d8,	"heq",		_A2(A_A,A_B),	00110,	FX2)	/* HaltEQ        halt_if(RA=RB) */
+APUOP(M_FCEQ,		RR,	0x3c2,	"fceq",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCEQ          RT<-(RA=RB) */
+APUOP(M_FCMEQ,		RR,	0x3ca,	"fcmeq",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCMEQ         RT<-(|RA|=|RB|) */
+APUOP(M_FCGT,		RR,	0x2c2,	"fcgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCGT          RT<-(RA<RB) */
+APUOP(M_FCMGT,		RR,	0x2ca,	"fcmgt",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCMGT         RT<-(|RA|<|RB|) */
+APUOP(M_AND,		RR,	0x0c1,	"and",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* AND           RT<-RA&RB */
+APUOP(M_NAND,		RR,	0x0c9,	"nand",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* NAND          RT<-!(RA&RB) */
+APUOP(M_OR,		RR,	0x041,	"or",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* OR            RT<-RA|RB */
+APUOP(M_NOR,		RR,	0x049,	"nor",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* NOR           RT<-!(RA&RB) */
+APUOP(M_XOR,		RR,	0x241,	"xor",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* XOR           RT<-RA^RB */
+APUOP(M_EQV,		RR,	0x249,	"eqv",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* EQuiValent    RT<-!(RA^RB) */
+APUOP(M_ANDC,		RR,	0x2c1,	"andc",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* ANDComplement RT<-RA&!RB */
+APUOP(M_ORC,		RR,	0x2c9,	"orc",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* ORComplement  RT<-RA|!RB */
+APUOP(M_ABSDB,		RR,	0x053,	"absdb",	_A3(A_T,A_A,A_B),		00112,	FXB)	/* ABSoluteDiff  RT<-|RA-RB| */
+APUOP(M_AVGB,		RR,	0x0d3,	"avgb",		_A3(A_T,A_A,A_B),		00112,	FXB)	/* AVG%          RT<-(RA+RB+1)/2 */
+APUOP(M_SUMB,		RR,	0x253,	"sumb",		_A3(A_T,A_A,A_B),		00112,	FXB)	/* SUM%          RT<-f(RA,RB) */
+APUOP(M_DFA,		RR,	0x2cc,	"dfa",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFAdd         RT<-RA+RB */
+APUOP(M_DFM,		RR,	0x2ce,	"dfm",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFMul         RT<-RA*RB */
+APUOP(M_DFS,		RR,	0x2cd,	"dfs",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFSub         RT<-RA-RB */
+APUOP(M_FA,		RR,	0x2c4,	"fa",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FAdd          RT<-RA+RB */
+APUOP(M_FM,		RR,	0x2c6,	"fm",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FMul          RT<-RA*RB */
+APUOP(M_FS,		RR,	0x2c5,	"fs",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FSub          RT<-RA-RB */
+APUOP(M_MPY,		RR,	0x3c4,	"mpy",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPY           RT<-RA*RB */
+APUOP(M_MPYH,		RR,	0x3c5,	"mpyh",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYH          RT<-(RAh*RB)<<16 */
+APUOP(M_MPYHH,		RR,	0x3c6,	"mpyhh",	_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYHH         RT<-RAh*RBh */
+APUOP(M_MPYHHU,		RR,	0x3ce,	"mpyhhu",	_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYHHU        RT<-RAh*RBh */
+APUOP(M_MPYS,		RR,	0x3c7,	"mpys",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYS          RT<-(RA*RB)>>16 */
+APUOP(M_MPYU,		RR,	0x3cc,	"mpyu",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYU          RT<-RA*RB */
+APUOP(M_FI,		RR,	0x3d4,	"fi",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* FInterpolate  RT<-f(RA,RB) */
+APUOP(M_ROT,		RR,	0x058,	"rot",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%          RT<-RA<<<RB */
+APUOP(M_ROTM,		RR,	0x059,	"rotm",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%M         RT<-RA<<Rb */
+APUOP(M_ROTMA,		RR,	0x05a,	"rotma",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROTMA%        RT<-RA<<Rb */
+APUOP(M_SHL,		RR,	0x05b,	"shl",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* SHL%          RT<-RA<<Rb */
+APUOP(M_ROTH,		RR,	0x05c,	"roth",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%          RT<-RA<<<RB */
+APUOP(M_ROTHM,		RR,	0x05d,	"rothm",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%M         RT<-RA<<Rb */
+APUOP(M_ROTMAH,		RR,	0x05e,	"rotmah",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROTMA%        RT<-RA<<Rb */
+APUOP(M_SHLH,		RR,	0x05f,	"shlh",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* SHL%          RT<-RA<<Rb */
+APUOP(M_MPYHHA,		RR,	0x346,	"mpyhha",	_A3(A_T,A_A,A_B),		00113,	FP7)	/* MPYHHA        RT<-RAh*RBh+RT */
+APUOP(M_MPYHHAU,	RR,	0x34e,	"mpyhhau",	_A3(A_T,A_A,A_B),		00113,	FP7)	/* MPYHHAU       RT<-RAh*RBh+RT */
+APUOP(M_DFMA,		RR,	0x35c,	"dfma",		_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFMAdd        RT<-RT+RA*RB */
+APUOP(M_DFMS,		RR,	0x35d,	"dfms",		_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFMSub        RT<-RA*RB-RT */
+APUOP(M_DFNMS,		RR,	0x35e,	"dfnms",	_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFNMSub       RT<-RT-RA*RB */
+APUOP(M_DFNMA,		RR,	0x35f,	"dfnma",	_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFNMAdd       RT<-(-RT)-RA*RB */
+APUOP(M_FMA,		RRR,	0x700,	"fma",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FMAdd         RC<-RT+RA*RB */
+APUOP(M_FMS,		RRR,	0x780,	"fms",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FMSub         RC<-RA*RB-RT */
+APUOP(M_FNMS,		RRR,	0x680,	"fnms",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FNMSub        RC<-RT-RA*RB */
+APUOP(M_MPYA,		RRR,	0x600,	"mpya",		_A4(A_C,A_A,A_B,A_T),	02111,	FP7)	/* MPYA          RC<-RA*RB+RT */
+APUOP(M_SELB,		RRR,	0x400,	"selb",		_A4(A_C,A_A,A_B,A_T),	02111,	FX2)	/* SELectBits    RC<-RA&RT|RB&!RT */
+/* for system function call, this uses op-code of mtspr */
+APUOP(M_SYSCALL,	RI7,    0x10c,	"syscall",      _A3(A_T,A_A,A_S7N),	00002,	SPR)        /* System Call */
+/*
+pseudo instruction:
+system call
+value of I9	operation
+0	halt
+1		rt[0] = open(MEM[ra[0]],	ra[1])
+2		rt[0] = close(ra[0])
+3		rt[0] = read(ra[0],	MEM[ra[1]],	ra[2])
+4		rt[0] = write(ra[0],	MEM[ra[1]],	ra[2])
+5		printf(MEM[ra[0]],	ra[1],	ra[2],	ra[3])
+42		rt[0] = clock()
+52		rt[0] = lseek(ra0,	ra1,	ra2)
+
+*/
+
+
+/* new multiprecision add/sub */
+APUOP(M_ADDX,		RR,	0x340,	"addx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* Add_eXtended  RT<-RA+RB+RT */
+APUOP(M_CG,		RR,	0x0c2,	"cg",		_A3(A_T,A_A,A_B),		00112,		FX2)	/* CarryGenerate RT<-cout(RA+RB) */
+APUOP(M_CGX,		RR,	0x342,	"cgx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* CarryGen_eXtd RT<-cout(RA+RB+RT) */
+APUOP(M_SFX,		RR,	0x341,	"sfx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* Add_eXtended  RT<-RA+RB+RT */
+APUOP(M_BG,		RR,	0x042,	"bg",		_A3(A_T,A_A,A_B),		00112,		FX2)	/* CarryGenerate RT<-cout(RA+RB) */
+APUOP(M_BGX,		RR,	0x343,	"bgx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* CarryGen_eXtd RT<-cout(RA+RB+RT) */
+
+/*
+
+The following ops are a subset of above except with feature bits set.
+Feature bits are bits 11-17 of the instruction:
+
+  11 - C & P feature bit
+  12 - disable interrupts
+  13 - enable interrupts
+
+*/
+APUOPFB(M_BID,		RR,	0x1a8,	0x20,	"bid",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
+APUOPFB(M_BIE,		RR,	0x1a8,	0x10,	"bie",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
+APUOPFB(M_BISLD,	RR,	0x1a9,	0x20,	"bisld",	_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
+APUOPFB(M_BISLE,	RR,	0x1a9,	0x10,	"bisle",	_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
+APUOPFB(M_IRETD,  	RR,	0x1aa,	0x20,	"iretd",	_A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
+APUOPFB(M_IRETD2,  	RR,	0x1aa,	0x20,	"iretd",	_A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
+APUOPFB(M_IRETE,  	RR,	0x1aa,	0x10,	"irete",	_A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
+APUOPFB(M_IRETE2,  	RR,	0x1aa,	0x10,	"irete",	_A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
+APUOPFB(M_BISLEDD,	RR,	0x1ab,	0x20,	"bisledd",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
+APUOPFB(M_BISLEDE,	RR,	0x1ab,	0x10,	"bislede",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
+APUOPFB(M_BIHNZD,	RR,	0x12b,	0x20,	"bihnzd",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
+APUOPFB(M_BIHNZE,	RR,	0x12b,	0x10,	"bihnze",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
+APUOPFB(M_BIHZD,	RR,	0x12a,	0x20,	"bihzd",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
+APUOPFB(M_BIHZE,	RR,	0x12a,	0x10,	"bihze",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
+APUOPFB(M_BINZD,	RR,	0x129,	0x20,	"binzd",	_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
+APUOPFB(M_BINZE,	RR,	0x129,	0x10,	"binze",	_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
+APUOPFB(M_BIZD,		RR,	0x128,	0x20,	"bizd",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
+APUOPFB(M_BIZE,		RR,	0x128,	0x10,	"bize",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
+APUOPFB(M_SYNCC,	RR,	0x002,	0x40,	"syncc",	_A0(),		00000,	BR)	/* SYNCC          flush_pipe */
+APUOPFB(M_HBRP,		LBTI,	0x1ac,	0x40,	"hbrp",		_A0(),	        00010,	LS)	/* HBR           BTB[B9]<-M[Ra] */
+
+/* Synonyms required by the AS manual. */
+APUOP(M_LR,		RI10,	0x020,	"lr",		_A2(A_T,A_A),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
+APUOP(M_BIHT,		RR,	0x12b,	"biht", 	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
+APUOP(M_BIHF,		RR,	0x12a,	"bihf",		_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
+APUOP(M_BIT,		RR,	0x129,	"bit",		_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
+APUOP(M_BIF,		RR,	0x128,	"bif",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
+APUOPFB(M_BIHTD,	RR,	0x12b,	0x20,	"bihtd",	_A2(A_T,A_A),	00011,	BR)	/* BIHNF         IP<-RA_if(RT) */
+APUOPFB(M_BIHTE,	RR,	0x12b,	0x10,	"bihte",	_A2(A_T,A_A),	00011,	BR)	/* BIHNF         IP<-RA_if(RT) */
+APUOPFB(M_BIHFD,	RR,	0x12a,	0x20,	"bihfd",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
+APUOPFB(M_BIHFE,	RR,	0x12a,	0x10,	"bihfe",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
+APUOPFB(M_BITD, 	RR,	0x129,	0x20,	"bitd", 	_A2(A_T,A_A),	00011,	BR)	/* BINF          IP<-RA_if(RT) */
+APUOPFB(M_BITE, 	RR,	0x129,	0x10,	"bite", 	_A2(A_T,A_A),	00011,	BR)	/* BINF          IP<-RA_if(RT) */
+APUOPFB(M_BIFD,		RR,	0x128,	0x20,	"bifd",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
+APUOPFB(M_BIFE,		RR,	0x128,	0x10,	"bife",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
+
+#undef _A0
+#undef _A1
+#undef _A2
+#undef _A3
+#undef _A4
diff --git a/arch/powerpc/xmon/spu-opc.c b/arch/powerpc/xmon/spu-opc.c
new file mode 100644
index 000000000000..efffde9edc6e
--- /dev/null
+++ b/arch/powerpc/xmon/spu-opc.c
@@ -0,0 +1,44 @@
+/* SPU opcode list
+
+   Copyright 2006 Free Software Foundation, Inc.
+
+   This file is part of GDB, GAS, and the GNU binutils.
+
+   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.,
+   51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+#include "spu.h"
+
+/* This file holds the Spu opcode table */
+
+
+/*
+   Example contents of spu-insn.h
+      id_tag	mode	mode	type	opcode	mnemonic	asmtype	    dependency		FPU	L/S?	branch?	instruction   
+                QUAD	WORD                                               (0,RC,RB,RA,RT)    latency  			              		
+   APUOP(M_LQD,	1,	0,	RI9,	0x1f8,	"lqd",		ASM_RI9IDX,	00012,		FXU,	1,	0)	Load Quadword d-form 
+ */
+
+const struct spu_opcode spu_opcodes[] = {
+#define APUOP(TAG,MACFORMAT,OPCODE,MNEMONIC,ASMFORMAT,DEP,PIPE) \
+	{ MACFORMAT, OPCODE, MNEMONIC, ASMFORMAT },
+#define APUOPFB(TAG,MACFORMAT,OPCODE,FB,MNEMONIC,ASMFORMAT,DEP,PIPE) \
+	{ MACFORMAT, OPCODE, MNEMONIC, ASMFORMAT },
+#include "spu-insns.h"
+#undef APUOP
+#undef APUOPFB
+};
+
+const int spu_num_opcodes =
+  sizeof (spu_opcodes) / sizeof (spu_opcodes[0]);
diff --git a/arch/powerpc/xmon/spu.h b/arch/powerpc/xmon/spu.h
new file mode 100644
index 000000000000..c761fc8f35d8
--- /dev/null
+++ b/arch/powerpc/xmon/spu.h
@@ -0,0 +1,126 @@
+/* SPU ELF support for BFD.
+
+   Copyright 2006 Free Software Foundation, Inc.
+
+   This file is part of GDB, GAS, and the GNU binutils.
+
+   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., 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+
+/* These two enums are from rel_apu/common/spu_asm_format.h */
+/* definition of instruction format */
+typedef enum {
+  RRR,
+  RI18,
+  RI16,
+  RI10,
+  RI8,
+  RI7,
+  RR,
+  LBT,
+  LBTI,
+  IDATA,
+  UNKNOWN_IFORMAT
+} spu_iformat;
+
+/* These values describe assembly instruction arguments.  They indicate
+ * how to encode, range checking and which relocation to use. */
+typedef enum {
+  A_T,  /* register at pos 0 */
+  A_A,  /* register at pos 7 */
+  A_B,  /* register at pos 14 */
+  A_C,  /* register at pos 21 */
+  A_S,  /* special purpose register at pos 7 */
+  A_H,  /* channel register at pos 7 */
+  A_P,  /* parenthesis, this has to separate regs from immediates */
+  A_S3,
+  A_S6,
+  A_S7N,
+  A_S7,
+  A_U7A,
+  A_U7B,
+  A_S10B,
+  A_S10,
+  A_S11,
+  A_S11I,
+  A_S14,
+  A_S16,
+  A_S18,
+  A_R18,
+  A_U3,
+  A_U5,
+  A_U6,
+  A_U7,
+  A_U14,
+  A_X16,
+  A_U18,
+  A_MAX
+} spu_aformat;
+
+enum spu_insns {
+#define APUOP(TAG,MACFORMAT,OPCODE,MNEMONIC,ASMFORMAT,DEP,PIPE) \
+	TAG,
+#define APUOPFB(TAG,MACFORMAT,OPCODE,FB,MNEMONIC,ASMFORMAT,DEP,PIPE) \
+	TAG,
+#include "spu-insns.h"
+#undef APUOP
+#undef APUOPFB
+        M_SPU_MAX
+};
+
+struct spu_opcode
+{
+   spu_iformat insn_type;
+   unsigned int opcode;
+   char *mnemonic;
+   int arg[5];
+};
+
+#define SIGNED_EXTRACT(insn,size,pos) (((int)((insn) << (32-size-pos))) >> (32-size))
+#define UNSIGNED_EXTRACT(insn,size,pos) (((insn) >> pos) & ((1 << size)-1))
+
+#define DECODE_INSN_RT(insn) (insn & 0x7f)
+#define DECODE_INSN_RA(insn) ((insn >> 7) & 0x7f)
+#define DECODE_INSN_RB(insn) ((insn >> 14) & 0x7f)
+#define DECODE_INSN_RC(insn) ((insn >> 21) & 0x7f)
+
+#define DECODE_INSN_I10(insn) SIGNED_EXTRACT(insn,10,14)
+#define DECODE_INSN_U10(insn) UNSIGNED_EXTRACT(insn,10,14)
+
+/* For branching, immediate loads, hbr and  lqa/stqa. */
+#define DECODE_INSN_I16(insn) SIGNED_EXTRACT(insn,16,7)
+#define DECODE_INSN_U16(insn) UNSIGNED_EXTRACT(insn,16,7)
+
+/* for stop */
+#define DECODE_INSN_U14(insn) UNSIGNED_EXTRACT(insn,14,0)
+
+/* For ila */
+#define DECODE_INSN_I18(insn) SIGNED_EXTRACT(insn,18,7)
+#define DECODE_INSN_U18(insn) UNSIGNED_EXTRACT(insn,18,7)
+
+/* For rotate and shift and generate control mask */
+#define DECODE_INSN_I7(insn) SIGNED_EXTRACT(insn,7,14)
+#define DECODE_INSN_U7(insn) UNSIGNED_EXTRACT(insn,7,14)
+
+/* For float <-> int conversion */
+#define DECODE_INSN_I8(insn)  SIGNED_EXTRACT(insn,8,14)
+#define DECODE_INSN_U8(insn) UNSIGNED_EXTRACT(insn,8,14)
+
+/* For hbr  */
+#define DECODE_INSN_I9a(insn) ((SIGNED_EXTRACT(insn,2,23) << 7) | UNSIGNED_EXTRACT(insn,7,0))
+#define DECODE_INSN_I9b(insn) ((SIGNED_EXTRACT(insn,2,14) << 7) | UNSIGNED_EXTRACT(insn,7,0))
+#define DECODE_INSN_U9a(insn) ((UNSIGNED_EXTRACT(insn,2,23) << 7) | UNSIGNED_EXTRACT(insn,7,0))
+#define DECODE_INSN_U9b(insn) ((UNSIGNED_EXTRACT(insn,2,14) << 7) | UNSIGNED_EXTRACT(insn,7,0))
+
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index f56ffef4defa..a34ed49e0356 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -37,13 +37,18 @@
 #include <asm/sstep.h>
 #include <asm/bug.h>
 #include <asm/irq_regs.h>
+#include <asm/spu.h>
+#include <asm/spu_priv1.h>
+#include <asm/firmware.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/hvcall.h>
 #include <asm/paca.h>
+#include <asm/iseries/it_lp_reg_save.h>
 #endif
 
 #include "nonstdio.h"
+#include "dis-asm.h"
 
 #define scanhex	xmon_scanhex
 #define skipbl	xmon_skipbl
@@ -107,7 +112,6 @@ static int bsesc(void);
 static void dump(void);
 static void prdump(unsigned long, long);
 static int ppc_inst_dump(unsigned long, long, int);
-void print_address(unsigned long);
 static void backtrace(struct pt_regs *);
 static void excprint(struct pt_regs *);
 static void prregs(struct pt_regs *);
@@ -147,9 +151,9 @@ static void xmon_print_symbol(unsigned long address, const char *mid,
 			      const char *after);
 static const char *getvecname(unsigned long vec);
 
-int xmon_no_auto_backtrace;
+static int do_spu_cmd(void);
 
-extern int print_insn_powerpc(unsigned long, unsigned long, int);
+int xmon_no_auto_backtrace;
 
 extern void xmon_enter(void);
 extern void xmon_leave(void);
@@ -209,8 +213,15 @@ Commands:\n\
   mi	show information about memory allocation\n\
   p 	call a procedure\n\
   r	print registers\n\
-  s	single step\n\
-  S	print special registers\n\
+  s	single step\n"
+#ifdef CONFIG_SPU_BASE
+"  ss	stop execution on all spus\n\
+  sr	restore execution on stopped spus\n\
+  sf  #	dump spu fields for spu # (in hex)\n\
+  sd  #	dump spu local store for spu # (in hex)\
+  sdi #	disassemble spu local store for spu # (in hex)\n"
+#endif
+"  S	print special registers\n\
   t	print backtrace\n\
   x	exit monitor and recover\n\
   X	exit monitor and dont recover\n"
@@ -518,6 +529,7 @@ int xmon(struct pt_regs *excp)
 		xmon_save_regs(&regs);
 		excp = &regs;
 	}
+
 	return xmon_core(excp, 0);
 }
 EXPORT_SYMBOL(xmon);
@@ -809,6 +821,8 @@ cmds(struct pt_regs *excp)
 			cacheflush();
 			break;
 		case 's':
+			if (do_spu_cmd() == 0)
+				break;
 			if (do_step(excp))
 				return cmd;
 			break;
@@ -1555,11 +1569,6 @@ void super_regs(void)
 {
 	int cmd;
 	unsigned long val;
-#ifdef CONFIG_PPC_ISERIES
-	struct paca_struct *ptrPaca = NULL;
-	struct lppaca *ptrLpPaca = NULL;
-	struct ItLpRegSave *ptrLpRegSave = NULL;
-#endif
 
 	cmd = skipbl();
 	if (cmd == '\n') {
@@ -1576,26 +1585,32 @@ void super_regs(void)
 		printf("sp   = "REG"  sprg3= "REG"\n", sp, mfspr(SPRN_SPRG3));
 		printf("toc  = "REG"  dar  = "REG"\n", toc, mfspr(SPRN_DAR));
 #ifdef CONFIG_PPC_ISERIES
-		// Dump out relevant Paca data areas.
-		printf("Paca: \n");
-		ptrPaca = get_paca();
-    
-		printf("  Local Processor Control Area (LpPaca): \n");
-		ptrLpPaca = ptrPaca->lppaca_ptr;
-		printf("    Saved Srr0=%.16lx  Saved Srr1=%.16lx \n",
-		       ptrLpPaca->saved_srr0, ptrLpPaca->saved_srr1);
-		printf("    Saved Gpr3=%.16lx  Saved Gpr4=%.16lx \n",
-		       ptrLpPaca->saved_gpr3, ptrLpPaca->saved_gpr4);
-		printf("    Saved Gpr5=%.16lx \n", ptrLpPaca->saved_gpr5);
-    
-		printf("  Local Processor Register Save Area (LpRegSave): \n");
-		ptrLpRegSave = ptrPaca->reg_save_ptr;
-		printf("    Saved Sprg0=%.16lx  Saved Sprg1=%.16lx \n",
-		       ptrLpRegSave->xSPRG0, ptrLpRegSave->xSPRG0);
-		printf("    Saved Sprg2=%.16lx  Saved Sprg3=%.16lx \n",
-		       ptrLpRegSave->xSPRG2, ptrLpRegSave->xSPRG3);
-		printf("    Saved Msr  =%.16lx  Saved Nia  =%.16lx \n",
-		       ptrLpRegSave->xMSR, ptrLpRegSave->xNIA);
+		if (firmware_has_feature(FW_FEATURE_ISERIES)) {
+			struct paca_struct *ptrPaca;
+			struct lppaca *ptrLpPaca;
+			struct ItLpRegSave *ptrLpRegSave;
+
+			/* Dump out relevant Paca data areas. */
+			printf("Paca: \n");
+			ptrPaca = get_paca();
+
+			printf("  Local Processor Control Area (LpPaca): \n");
+			ptrLpPaca = ptrPaca->lppaca_ptr;
+			printf("    Saved Srr0=%.16lx  Saved Srr1=%.16lx \n",
+			       ptrLpPaca->saved_srr0, ptrLpPaca->saved_srr1);
+			printf("    Saved Gpr3=%.16lx  Saved Gpr4=%.16lx \n",
+			       ptrLpPaca->saved_gpr3, ptrLpPaca->saved_gpr4);
+			printf("    Saved Gpr5=%.16lx \n", ptrLpPaca->saved_gpr5);
+
+			printf("  Local Processor Register Save Area (LpRegSave): \n");
+			ptrLpRegSave = ptrPaca->reg_save_ptr;
+			printf("    Saved Sprg0=%.16lx  Saved Sprg1=%.16lx \n",
+			       ptrLpRegSave->xSPRG0, ptrLpRegSave->xSPRG0);
+			printf("    Saved Sprg2=%.16lx  Saved Sprg3=%.16lx \n",
+			       ptrLpRegSave->xSPRG2, ptrLpRegSave->xSPRG3);
+			printf("    Saved Msr  =%.16lx  Saved Nia  =%.16lx \n",
+			       ptrLpRegSave->xMSR, ptrLpRegSave->xNIA);
+		}
 #endif
 
 		return;
@@ -2053,8 +2068,11 @@ prdump(unsigned long adrs, long ndump)
 	}
 }
 
+typedef int (*instruction_dump_func)(unsigned long inst, unsigned long addr);
+
 int
-ppc_inst_dump(unsigned long adr, long count, int praddr)
+generic_inst_dump(unsigned long adr, long count, int praddr,
+			instruction_dump_func dump_func)
 {
 	int nr, dotted;
 	unsigned long first_adr;
@@ -2084,12 +2102,18 @@ ppc_inst_dump(unsigned long adr, long count, int praddr)
 		if (praddr)
 			printf(REG"  %.8x", adr, inst);
 		printf("\t");
-		print_insn_powerpc(inst, adr, 0);	/* always returns 4 */
+		dump_func(inst, adr);
 		printf("\n");
 	}
 	return adr - first_adr;
 }
 
+int
+ppc_inst_dump(unsigned long adr, long count, int praddr)
+{
+	return generic_inst_dump(adr, count, praddr, print_insn_powerpc);
+}
+
 void
 print_address(unsigned long addr)
 {
@@ -2557,6 +2581,10 @@ void dump_segments(void)
 
 void xmon_init(int enable)
 {
+#ifdef CONFIG_PPC_ISERIES
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		return;
+#endif
 	if (enable) {
 		__debugger = xmon;
 		__debugger_ipi = xmon_ipi;
@@ -2594,6 +2622,10 @@ static struct sysrq_key_op sysrq_xmon_op =
 
 static int __init setup_xmon_sysrq(void)
 {
+#ifdef CONFIG_PPC_ISERIES
+	if (firmware_has_feature(FW_FEATURE_ISERIES))
+		return 0;
+#endif
 	register_sysrq_key('x', &sysrq_xmon_op);
 	return 0;
 }
@@ -2630,3 +2662,263 @@ void __init xmon_setup(void)
 	if (xmon_early)
 		debugger(NULL);
 }
+
+#ifdef CONFIG_SPU_BASE
+
+struct spu_info {
+	struct spu *spu;
+	u64 saved_mfc_sr1_RW;
+	u32 saved_spu_runcntl_RW;
+	unsigned long dump_addr;
+	u8 stopped_ok;
+};
+
+#define XMON_NUM_SPUS	16	/* Enough for current hardware */
+
+static struct spu_info spu_info[XMON_NUM_SPUS];
+
+void xmon_register_spus(struct list_head *list)
+{
+	struct spu *spu;
+
+	list_for_each_entry(spu, list, full_list) {
+		if (spu->number >= XMON_NUM_SPUS) {
+			WARN_ON(1);
+			continue;
+		}
+
+		spu_info[spu->number].spu = spu;
+		spu_info[spu->number].stopped_ok = 0;
+		spu_info[spu->number].dump_addr = (unsigned long)
+				spu_info[spu->number].spu->local_store;
+	}
+}
+
+static void stop_spus(void)
+{
+	struct spu *spu;
+	int i;
+	u64 tmp;
+
+	for (i = 0; i < XMON_NUM_SPUS; i++) {
+		if (!spu_info[i].spu)
+			continue;
+
+		if (setjmp(bus_error_jmp) == 0) {
+			catch_memory_errors = 1;
+			sync();
+
+			spu = spu_info[i].spu;
+
+			spu_info[i].saved_spu_runcntl_RW =
+				in_be32(&spu->problem->spu_runcntl_RW);
+
+			tmp = spu_mfc_sr1_get(spu);
+			spu_info[i].saved_mfc_sr1_RW = tmp;
+
+			tmp &= ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
+			spu_mfc_sr1_set(spu, tmp);
+
+			sync();
+			__delay(200);
+
+			spu_info[i].stopped_ok = 1;
+
+			printf("Stopped spu %.2d (was %s)\n", i,
+					spu_info[i].saved_spu_runcntl_RW ?
+					"running" : "stopped");
+		} else {
+			catch_memory_errors = 0;
+			printf("*** Error stopping spu %.2d\n", i);
+		}
+		catch_memory_errors = 0;
+	}
+}
+
+static void restart_spus(void)
+{
+	struct spu *spu;
+	int i;
+
+	for (i = 0; i < XMON_NUM_SPUS; i++) {
+		if (!spu_info[i].spu)
+			continue;
+
+		if (!spu_info[i].stopped_ok) {
+			printf("*** Error, spu %d was not successfully stopped"
+					", not restarting\n", i);
+			continue;
+		}
+
+		if (setjmp(bus_error_jmp) == 0) {
+			catch_memory_errors = 1;
+			sync();
+
+			spu = spu_info[i].spu;
+			spu_mfc_sr1_set(spu, spu_info[i].saved_mfc_sr1_RW);
+			out_be32(&spu->problem->spu_runcntl_RW,
+					spu_info[i].saved_spu_runcntl_RW);
+
+			sync();
+			__delay(200);
+
+			printf("Restarted spu %.2d\n", i);
+		} else {
+			catch_memory_errors = 0;
+			printf("*** Error restarting spu %.2d\n", i);
+		}
+		catch_memory_errors = 0;
+	}
+}
+
+#define DUMP_WIDTH	23
+#define DUMP_VALUE(format, field, value)				\
+do {									\
+	if (setjmp(bus_error_jmp) == 0) {				\
+		catch_memory_errors = 1;				\
+		sync();							\
+		printf("  %-*s = "format"\n", DUMP_WIDTH,		\
+				#field, value);				\
+		sync();							\
+		__delay(200);						\
+	} else {							\
+		catch_memory_errors = 0;				\
+		printf("  %-*s = *** Error reading field.\n",		\
+					DUMP_WIDTH, #field);		\
+	}								\
+	catch_memory_errors = 0;					\
+} while (0)
+
+#define DUMP_FIELD(obj, format, field)	\
+	DUMP_VALUE(format, field, obj->field)
+
+static void dump_spu_fields(struct spu *spu)
+{
+	printf("Dumping spu fields at address %p:\n", spu);
+
+	DUMP_FIELD(spu, "0x%x", number);
+	DUMP_FIELD(spu, "%s", name);
+	DUMP_FIELD(spu, "0x%lx", local_store_phys);
+	DUMP_FIELD(spu, "0x%p", local_store);
+	DUMP_FIELD(spu, "0x%lx", ls_size);
+	DUMP_FIELD(spu, "0x%x", node);
+	DUMP_FIELD(spu, "0x%lx", flags);
+	DUMP_FIELD(spu, "0x%lx", dar);
+	DUMP_FIELD(spu, "0x%lx", dsisr);
+	DUMP_FIELD(spu, "%d", class_0_pending);
+	DUMP_FIELD(spu, "0x%lx", irqs[0]);
+	DUMP_FIELD(spu, "0x%lx", irqs[1]);
+	DUMP_FIELD(spu, "0x%lx", irqs[2]);
+	DUMP_FIELD(spu, "0x%x", slb_replace);
+	DUMP_FIELD(spu, "%d", pid);
+	DUMP_FIELD(spu, "%d", prio);
+	DUMP_FIELD(spu, "0x%p", mm);
+	DUMP_FIELD(spu, "0x%p", ctx);
+	DUMP_FIELD(spu, "0x%p", rq);
+	DUMP_FIELD(spu, "0x%p", timestamp);
+	DUMP_FIELD(spu, "0x%lx", problem_phys);
+	DUMP_FIELD(spu, "0x%p", problem);
+	DUMP_VALUE("0x%x", problem->spu_runcntl_RW,
+			in_be32(&spu->problem->spu_runcntl_RW));
+	DUMP_VALUE("0x%x", problem->spu_status_R,
+			in_be32(&spu->problem->spu_status_R));
+	DUMP_VALUE("0x%x", problem->spu_npc_RW,
+			in_be32(&spu->problem->spu_npc_RW));
+	DUMP_FIELD(spu, "0x%p", priv2);
+	DUMP_FIELD(spu, "0x%p", pdata);
+}
+
+int
+spu_inst_dump(unsigned long adr, long count, int praddr)
+{
+	return generic_inst_dump(adr, count, praddr, print_insn_spu);
+}
+
+static void dump_spu_ls(unsigned long num, int subcmd)
+{
+	unsigned long offset, addr, ls_addr;
+
+	if (setjmp(bus_error_jmp) == 0) {
+		catch_memory_errors = 1;
+		sync();
+		ls_addr = (unsigned long)spu_info[num].spu->local_store;
+		sync();
+		__delay(200);
+	} else {
+		catch_memory_errors = 0;
+		printf("*** Error: accessing spu info for spu %d\n", num);
+		return;
+	}
+	catch_memory_errors = 0;
+
+	if (scanhex(&offset))
+		addr = ls_addr + offset;
+	else
+		addr = spu_info[num].dump_addr;
+
+	if (addr >= ls_addr + LS_SIZE) {
+		printf("*** Error: address outside of local store\n");
+		return;
+	}
+
+	switch (subcmd) {
+	case 'i':
+		addr += spu_inst_dump(addr, 16, 1);
+		last_cmd = "sdi\n";
+		break;
+	default:
+		prdump(addr, 64);
+		addr += 64;
+		last_cmd = "sd\n";
+		break;
+	}
+
+	spu_info[num].dump_addr = addr;
+}
+
+static int do_spu_cmd(void)
+{
+	static unsigned long num = 0;
+	int cmd, subcmd = 0;
+
+	cmd = inchar();
+	switch (cmd) {
+	case 's':
+		stop_spus();
+		break;
+	case 'r':
+		restart_spus();
+		break;
+	case 'd':
+		subcmd = inchar();
+		if (isxdigit(subcmd) || subcmd == '\n')
+			termch = subcmd;
+	case 'f':
+		scanhex(&num);
+		if (num >= XMON_NUM_SPUS || !spu_info[num].spu) {
+			printf("*** Error: invalid spu number\n");
+			return 0;
+		}
+
+		switch (cmd) {
+		case 'f':
+			dump_spu_fields(spu_info[num].spu);
+			break;
+		default:
+			dump_spu_ls(num, subcmd);
+			break;
+		}
+
+		break;
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+#else /* ! CONFIG_SPU_BASE */
+static int do_spu_cmd(void)
+{
+	return -1;
+}
+#endif
diff --git a/arch/ppc/.gitignore b/arch/ppc/.gitignore
new file mode 100644
index 000000000000..a1a869c8c840
--- /dev/null
+++ b/arch/ppc/.gitignore
@@ -0,0 +1 @@
+include
diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig
index ef018e25fb07..edf71a4ecc95 100644
--- a/arch/ppc/Kconfig
+++ b/arch/ppc/Kconfig
@@ -77,9 +77,11 @@ config 6xx
 
 config 40x
 	bool "40x"
+	select PPC_DCR_NATIVE
 
 config 44x
 	bool "44x"
+	select PPC_DCR_NATIVE
 
 config 8xx
 	bool "8xx"
@@ -95,6 +97,15 @@ endchoice
 config PPC_FPU
 	bool
 
+config PPC_DCR_NATIVE
+	bool
+	default n
+
+config PPC_DCR
+	bool
+	depends on PPC_DCR_NATIVE
+	default y
+
 config BOOKE
 	bool
 	depends on E200 || E500
diff --git a/arch/ppc/boot/images/.gitignore b/arch/ppc/boot/images/.gitignore
new file mode 100644
index 000000000000..21c2dc5b6b78
--- /dev/null
+++ b/arch/ppc/boot/images/.gitignore
@@ -0,0 +1,6 @@
+sImage
+vmapus
+vmlinux*
+miboot*
+zImage*
+uImage
diff --git a/arch/ppc/boot/lib/.gitignore b/arch/ppc/boot/lib/.gitignore
new file mode 100644
index 000000000000..1629a6167755
--- /dev/null
+++ b/arch/ppc/boot/lib/.gitignore
@@ -0,0 +1,3 @@
+inffast.c
+inflate.c
+inftrees.c
diff --git a/arch/ppc/boot/utils/.gitignore b/arch/ppc/boot/utils/.gitignore
new file mode 100644
index 000000000000..bbdfb3b9c532
--- /dev/null
+++ b/arch/ppc/boot/utils/.gitignore
@@ -0,0 +1,3 @@
+mkprep
+mkbugboot
+mktree
diff --git a/arch/ppc/kernel/setup.c b/arch/ppc/kernel/setup.c
index 27faeca2c7a2..3c506af19880 100644
--- a/arch/ppc/kernel/setup.c
+++ b/arch/ppc/kernel/setup.c
@@ -313,7 +313,7 @@ early_init(int r3, int r4, int r5)
 	 * Identify the CPU type and fix up code sections
 	 * that depend on which cpu we have.
 	 */
-	spec = identify_cpu(offset);
+	spec = identify_cpu(offset, mfspr(SPRN_PVR));
 	do_feature_fixups(spec->cpu_features,
 			  PTRRELOC(&__start___ftr_fixup),
 			  PTRRELOC(&__stop___ftr_fixup));
diff --git a/arch/ppc/kernel/traps.c b/arch/ppc/kernel/traps.c
index 9661a91183b3..2f835b9e95e4 100644
--- a/arch/ppc/kernel/traps.c
+++ b/arch/ppc/kernel/traps.c
@@ -316,7 +316,7 @@ void machine_check_exception(struct pt_regs *regs)
 	if (reason & MCSR_BUS_RBERR)
 		printk("Bus - Read Data Bus Error\n");
 	if (reason & MCSR_BUS_WBERR)
-		printk("Bus - Read Data Bus Error\n");
+		printk("Bus - Write Data Bus Error\n");
 	if (reason & MCSR_BUS_IPERR)
 		printk("Bus - Instruction Parity Error\n");
 	if (reason & MCSR_BUS_RPERR)
diff --git a/arch/ppc/platforms/4xx/bubinga.c b/arch/ppc/platforms/4xx/bubinga.c
index 4009f4983ca6..75857b38e894 100644
--- a/arch/ppc/platforms/4xx/bubinga.c
+++ b/arch/ppc/platforms/4xx/bubinga.c
@@ -116,6 +116,7 @@ bubinga_early_serial_map(void)
 void __init
 bios_fixup(struct pci_controller *hose, struct pcil0_regs *pcip)
 {
+#ifdef CONFIG_PCI
 
 	unsigned int bar_response, bar;
 	/*
@@ -212,6 +213,7 @@ bios_fixup(struct pci_controller *hose, struct pcil0_regs *pcip)
 	printk(" ptm2la\t0x%x\n", in_le32(&(pcip->ptm2la)));
 
 #endif
+#endif
 }
 
 void __init
diff --git a/arch/ppc/platforms/4xx/cpci405.c b/arch/ppc/platforms/4xx/cpci405.c
index 367430998fc5..8474b05b795a 100644
--- a/arch/ppc/platforms/4xx/cpci405.c
+++ b/arch/ppc/platforms/4xx/cpci405.c
@@ -126,6 +126,7 @@ cpci405_setup_arch(void)
 void __init
 bios_fixup(struct pci_controller *hose, struct pcil0_regs *pcip)
 {
+#ifdef CONFIG_PCI
 	unsigned int bar_response, bar;
 
 	/* Disable region first */
@@ -167,6 +168,7 @@ bios_fixup(struct pci_controller *hose, struct pcil0_regs *pcip)
 					PCI_FUNC(hose->first_busno), bar,
 					&bar_response);
 	}
+#endif
 }
 
 void __init
diff --git a/arch/ppc/platforms/4xx/ep405.c b/arch/ppc/platforms/4xx/ep405.c
index ae5c82081c95..e5adf9ba1fca 100644
--- a/arch/ppc/platforms/4xx/ep405.c
+++ b/arch/ppc/platforms/4xx/ep405.c
@@ -68,6 +68,7 @@ ep405_setup_arch(void)
 void __init
 bios_fixup(struct pci_controller *hose, struct pcil0_regs *pcip)
 {
+#ifdef CONFIG_PCI
 	unsigned int bar_response, bar;
 	/*
 	 * Expected PCI mapping:
@@ -130,6 +131,7 @@ bios_fixup(struct pci_controller *hose, struct pcil0_regs *pcip)
 		    PCI_FUNC(hose->first_busno), bar, bar_response);
 	}
 	/* end work arround */
+#endif
 }
 
 void __init
diff --git a/arch/ppc/platforms/83xx/mpc834x_sys.c b/arch/ppc/platforms/83xx/mpc834x_sys.c
index 3397f0de1592..b84f8df325c4 100644
--- a/arch/ppc/platforms/83xx/mpc834x_sys.c
+++ b/arch/ppc/platforms/83xx/mpc834x_sys.c
@@ -121,8 +121,8 @@ mpc834x_sys_setup_arch(void)
 
 	mdata->irq[0] = MPC83xx_IRQ_EXT1;
 	mdata->irq[1] = MPC83xx_IRQ_EXT2;
-	mdata->irq[2] = -1;
-	mdata->irq[31] = -1;
+	mdata->irq[2] = PHY_POLL;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC83xx_TSEC1);
diff --git a/arch/ppc/platforms/85xx/mpc8540_ads.c b/arch/ppc/platforms/85xx/mpc8540_ads.c
index 4f839da6782f..00a3ba57063f 100644
--- a/arch/ppc/platforms/85xx/mpc8540_ads.c
+++ b/arch/ppc/platforms/85xx/mpc8540_ads.c
@@ -92,9 +92,9 @@ mpc8540ads_setup_arch(void)
 
 	mdata->irq[0] = MPC85xx_IRQ_EXT5;
 	mdata->irq[1] = MPC85xx_IRQ_EXT5;
-	mdata->irq[2] = -1;
+	mdata->irq[2] = PHY_POLL;
 	mdata->irq[3] = MPC85xx_IRQ_EXT5;
-	mdata->irq[31] = -1;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1);
diff --git a/arch/ppc/platforms/85xx/mpc8560_ads.c b/arch/ppc/platforms/85xx/mpc8560_ads.c
index 14ecec7bbed7..3a060468dd95 100644
--- a/arch/ppc/platforms/85xx/mpc8560_ads.c
+++ b/arch/ppc/platforms/85xx/mpc8560_ads.c
@@ -156,9 +156,9 @@ mpc8560ads_setup_arch(void)
 
 	mdata->irq[0] = MPC85xx_IRQ_EXT5;
 	mdata->irq[1] = MPC85xx_IRQ_EXT5;
-	mdata->irq[2] = -1;
+	mdata->irq[2] = PHY_POLL;
 	mdata->irq[3] = MPC85xx_IRQ_EXT5;
-	mdata->irq[31] = -1;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1);
diff --git a/arch/ppc/platforms/85xx/mpc85xx_cds_common.c b/arch/ppc/platforms/85xx/mpc85xx_cds_common.c
index 5ce0f69c1db6..2d59eb776c95 100644
--- a/arch/ppc/platforms/85xx/mpc85xx_cds_common.c
+++ b/arch/ppc/platforms/85xx/mpc85xx_cds_common.c
@@ -451,9 +451,9 @@ mpc85xx_cds_setup_arch(void)
 
 	mdata->irq[0] = MPC85xx_IRQ_EXT5;
 	mdata->irq[1] = MPC85xx_IRQ_EXT5;
-	mdata->irq[2] = -1;
-	mdata->irq[3] = -1;
-	mdata->irq[31] = -1;
+	mdata->irq[2] = PHY_POLL;
+	mdata->irq[3] = PHY_POLL;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1);
diff --git a/arch/ppc/platforms/85xx/sbc8560.c b/arch/ppc/platforms/85xx/sbc8560.c
index 764d580ff535..1d10ab98f66d 100644
--- a/arch/ppc/platforms/85xx/sbc8560.c
+++ b/arch/ppc/platforms/85xx/sbc8560.c
@@ -129,7 +129,7 @@ sbc8560_setup_arch(void)
 
 	mdata->irq[25] = MPC85xx_IRQ_EXT6;
 	mdata->irq[26] = MPC85xx_IRQ_EXT7;
-	mdata->irq[31] = -1;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1);
diff --git a/arch/ppc/platforms/85xx/stx_gp3.c b/arch/ppc/platforms/85xx/stx_gp3.c
index 4bb18ab27672..b1f5b737c70d 100644
--- a/arch/ppc/platforms/85xx/stx_gp3.c
+++ b/arch/ppc/platforms/85xx/stx_gp3.c
@@ -123,7 +123,7 @@ gp3_setup_arch(void)
 
 	mdata->irq[2] = MPC85xx_IRQ_EXT5;
 	mdata->irq[4] = MPC85xx_IRQ_EXT5;
-	mdata->irq[31] = -1;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1);
diff --git a/arch/ppc/platforms/85xx/tqm85xx.c b/arch/ppc/platforms/85xx/tqm85xx.c
index dd45f2e18449..4ee2bd156dc5 100644
--- a/arch/ppc/platforms/85xx/tqm85xx.c
+++ b/arch/ppc/platforms/85xx/tqm85xx.c
@@ -137,9 +137,9 @@ tqm85xx_setup_arch(void)
 
 	mdata->irq[0] = MPC85xx_IRQ_EXT8;
 	mdata->irq[1] = MPC85xx_IRQ_EXT8;
-	mdata->irq[2] = -1;
+	mdata->irq[2] = PHY_POLL;
 	mdata->irq[3] = MPC85xx_IRQ_EXT8;
-	mdata->irq[31] = -1;
+	mdata->irq[31] = PHY_POLL;
 
 	/* setup the board related information for the enet controllers */
 	pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1);
diff --git a/arch/ppc/platforms/mpc8272ads_setup.c b/arch/ppc/platforms/mpc8272ads_setup.c
index 1f9ea36837b1..0bc06768cf24 100644
--- a/arch/ppc/platforms/mpc8272ads_setup.c
+++ b/arch/ppc/platforms/mpc8272ads_setup.c
@@ -266,10 +266,10 @@ static void __init mpc8272ads_fixup_mdio_pdata(struct platform_device *pdev,
 					      int idx)
 {
 	m82xx_mii_bb_pdata.irq[0] = PHY_INTERRUPT;
-	m82xx_mii_bb_pdata.irq[1] = -1;
-	m82xx_mii_bb_pdata.irq[2] = -1;
+	m82xx_mii_bb_pdata.irq[1] = PHY_POLL;
+	m82xx_mii_bb_pdata.irq[2] = PHY_POLL;
 	m82xx_mii_bb_pdata.irq[3] = PHY_INTERRUPT;
-	m82xx_mii_bb_pdata.irq[31] = -1;
+	m82xx_mii_bb_pdata.irq[31] = PHY_POLL;
 
 
 	m82xx_mii_bb_pdata.mdio_dat.offset =
diff --git a/arch/ppc/platforms/mpc866ads_setup.c b/arch/ppc/platforms/mpc866ads_setup.c
index e95d2c111747..8a0c07eb4449 100644
--- a/arch/ppc/platforms/mpc866ads_setup.c
+++ b/arch/ppc/platforms/mpc866ads_setup.c
@@ -361,7 +361,7 @@ int __init mpc866ads_init(void)
 
 	fmpi->mii_speed = ((((bd->bi_intfreq + 4999999) / 2500000) / 2) & 0x3F) << 1;
 	/* No PHY interrupt line here */
-	fmpi->irq[0xf] = -1;
+	fmpi->irq[0xf] = PHY_POLL;
 
 /* Since either of the uarts could be used as console, they need to ready */
 #ifdef CONFIG_SERIAL_CPM_SMC1
@@ -380,7 +380,7 @@ int __init mpc866ads_init(void)
 
 	fmpi->mii_speed = ((((bd->bi_intfreq + 4999999) / 2500000) / 2) & 0x3F) << 1;
 	/* No PHY interrupt line here */
-	fmpi->irq[0xf] = -1;
+	fmpi->irq[0xf] = PHY_POLL;
 
 	return 0;
 }
diff --git a/arch/ppc/syslib/mpc8xx_devices.c b/arch/ppc/syslib/mpc8xx_devices.c
index cf5ab47487a7..31fb56593d17 100644
--- a/arch/ppc/syslib/mpc8xx_devices.c
+++ b/arch/ppc/syslib/mpc8xx_devices.c
@@ -78,7 +78,7 @@ struct platform_device ppc_sys_platform_devices[] = {
 			{
 				.name 	= "pram",
 				.start 	= 0x3c00,
-				.end 	= 0x3c80,
+				.end 	= 0x3c7f,
 				.flags 	= IORESOURCE_MEM,
 			},
 			{
@@ -103,7 +103,7 @@ struct platform_device ppc_sys_platform_devices[] = {
 			{
 				.name 	= "pram",
 				.start 	= 0x3d00,
-				.end 	= 0x3d80,
+				.end 	= 0x3d7f,
 				.flags 	= IORESOURCE_MEM,
 			},
 
@@ -129,7 +129,7 @@ struct platform_device ppc_sys_platform_devices[] = {
 			{
 				.name 	= "pram",
 				.start 	= 0x3e00,
-				.end 	= 0x3e80,
+				.end 	= 0x3e7f,
 				.flags 	= IORESOURCE_MEM,
 			},
 
@@ -155,7 +155,7 @@ struct platform_device ppc_sys_platform_devices[] = {
 			{
 				.name 	= "pram",
 				.start 	= 0x3f00,
-				.end 	= 0x3f80,
+				.end 	= 0x3f7f,
 				.flags 	= IORESOURCE_MEM,
 			},
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 245b81bc7157..583d9ff0a571 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -33,9 +33,6 @@ config GENERIC_CALIBRATE_DELAY
 config GENERIC_TIME
 	def_bool y
 
-config GENERIC_BUST_SPINLOCK
-	bool
-
 mainmenu "Linux Kernel Configuration"
 
 config S390
@@ -181,7 +178,7 @@ config PACK_STACK
 
 config SMALL_STACK
 	bool "Use 4kb/8kb for kernel stack instead of 8kb/16kb"
-	depends on PACK_STACK
+	depends on PACK_STACK && !LOCKDEP
 	help
 	  If you say Y here and the compiler supports the -mkernel-backchain
 	  option the kernel will use a smaller kernel stack size. For 31 bit
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 5deb9f7544a1..6598e5268573 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -35,6 +35,9 @@ cflags-$(CONFIG_MARCH_Z900) += $(call cc-option,-march=z900)
 cflags-$(CONFIG_MARCH_Z990) += $(call cc-option,-march=z990)
 cflags-$(CONFIG_MARCH_Z9_109) += $(call cc-option,-march=z9-109)
 
+#KBUILD_IMAGE is necessary for make rpm
+KBUILD_IMAGE	:=arch/s390/boot/image
+
 #
 # Prevent tail-call optimizations, to get clearer backtraces:
 #
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index aa978978d3d1..a81881c9b297 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -4,7 +4,7 @@
 
 EXTRA_AFLAGS	:= -traditional
 
-obj-y	:=  bitmap.o traps.o time.o process.o \
+obj-y	:=  bitmap.o traps.o time.o process.o reset.o \
             setup.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
 	    semaphore.o s390_ext.o debug.o profile.o irq.o ipl.o
 
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index 1eae74e72f95..a5972f1541fe 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -21,14 +21,15 @@ static DEFINE_SPINLOCK(cpcmd_lock);
 static char cpcmd_buf[241];
 
 /*
- * the caller of __cpcmd has to ensure that the response buffer is below 2 GB
+ * __cpcmd has some restrictions over cpcmd
+ *  - the response buffer must reside below 2GB (if any)
+ *  - __cpcmd is unlocked and therefore not SMP-safe
  */
 int  __cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 {
-	unsigned long flags, cmdlen;
+	unsigned cmdlen;
 	int return_code, return_len;
 
-	spin_lock_irqsave(&cpcmd_lock, flags);
 	cmdlen = strlen(cmd);
 	BUG_ON(cmdlen > 240);
 	memcpy(cpcmd_buf, cmd, cmdlen);
@@ -74,7 +75,6 @@ int  __cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 			: "+d" (reg3) : "d" (reg2) : "cc");
 		return_code = (int) reg3;
         }
-	spin_unlock_irqrestore(&cpcmd_lock, flags);
 	if (response_code != NULL)
 		*response_code = return_code;
 	return return_len;
@@ -82,15 +82,18 @@ int  __cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 
 EXPORT_SYMBOL(__cpcmd);
 
-#ifdef CONFIG_64BIT
 int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 {
 	char *lowbuf;
 	int len;
+	unsigned long flags;
 
 	if ((rlen == 0) || (response == NULL)
-	    || !((unsigned long)response >> 31))
+	    || !((unsigned long)response >> 31)) {
+		spin_lock_irqsave(&cpcmd_lock, flags);
 		len = __cpcmd(cmd, response, rlen, response_code);
+		spin_unlock_irqrestore(&cpcmd_lock, flags);
+	}
 	else {
 		lowbuf = kmalloc(rlen, GFP_KERNEL | GFP_DMA);
 		if (!lowbuf) {
@@ -98,7 +101,9 @@ int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 				"cpcmd: could not allocate response buffer\n");
 			return -ENOMEM;
 		}
+		spin_lock_irqsave(&cpcmd_lock, flags);
 		len = __cpcmd(cmd, lowbuf, rlen, response_code);
+		spin_unlock_irqrestore(&cpcmd_lock, flags);
 		memcpy(response, lowbuf, rlen);
 		kfree(lowbuf);
 	}
@@ -106,4 +111,3 @@ int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 }
 
 EXPORT_SYMBOL(cpcmd);
-#endif		/* CONFIG_64BIT */
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 0cf59bb7a857..8f8c802f1bcf 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -418,24 +418,6 @@ start:
 .gotr:
 	l	%r10,.tbl		# EBCDIC to ASCII table
 	tr	0(240,%r8),0(%r10)
-	stidp	__LC_CPUID		# Are we running on VM maybe
-	cli	__LC_CPUID,0xff
-	bnz	.test
-	.long	0x83300060		# diag 3,0,x'0060' - storage size
-	b	.done
-.test:
-	mvc	0x68(8),.pgmnw		# set up pgm check handler
-	l	%r2,.fourmeg
-	lr	%r3,%r2
-	bctr	%r3,%r0			# 4M-1
-.loop:	iske	%r0,%r3
-	ar	%r3,%r2
-.pgmx:
-	sr	%r3,%r2
-	la	%r3,1(%r3)
-.done:
-	l	%r1,.memsize
-	st	%r3,ARCH_OFFSET(%r1)
 	slr	%r0,%r0
 	st	%r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11)
 	st	%r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11)
@@ -443,9 +425,6 @@ start:
 .tbl:	.long	_ebcasc			# translate table
 .cmd:	.long	COMMAND_LINE		# address of command line buffer
 .parm:	.long	PARMAREA
-.memsize: .long memory_size
-.fourmeg: .long 0x00400000      	# 4M
-.pgmnw:	.long	0x00080000,.pgmx
 .lowcase:
 	.byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07
 	.byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index 0a2c929486ab..4388b3309e0c 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -131,10 +131,11 @@ startup_continue:
 	.long	init_thread_union
 .Lpmask:
 	.byte	0
-.align 8
+	.align	8
 .Lpcext:.long	0x00080000,0x80000000
 .Lcr:
 	.long	0x00			# place holder for cr0
+	.align	8
 .Lwaitsclp:
 	.long 0x010a0000,0x80000000 + .Lsclph
 .Lrcp:
@@ -156,7 +157,7 @@ startup_continue:
 	slr	%r4,%r4			# set start of chunk to zero
 	slr	%r5,%r5			# set end of chunk to zero
 	slr	%r6,%r6			# set access code to zero
-	la	%r10, MEMORY_CHUNKS	# number of chunks
+	la	%r10,MEMORY_CHUNKS	# number of chunks
 .Lloop:
 	tprot	0(%r5),0		# test protection of first byte
 	ipm	%r7
@@ -176,8 +177,6 @@ startup_continue:
 	st	%r0,4(%r3)		# store size of chunk
 	st	%r6,8(%r3)		# store type of chunk
 	la	%r3,12(%r3)
-	l	%r4,.Lmemsize-.LPG1(%r13)	 # address of variable memory_size
-	st	%r5,0(%r4)		# store last end to memory size
 	ahi	%r10,-1			# update chunk number
 .Lchkloop:
 	lr	%r6,%r7			# set access code to last cc
@@ -292,7 +291,6 @@ startup_continue:
 .Lpcmvpg:.long	0x00080000,0x80000000 + .Lchkmvpg
 .Lpcidte:.long	0x00080000,0x80000000 + .Lchkidte
 .Lpcdiag9c:.long 0x00080000,0x80000000 + .Lchkdiag9c
-.Lmemsize:.long memory_size
 .Lmchunk:.long	memory_chunk
 .Lmflags:.long	machine_flags
 .Lbss_bgn:  .long __bss_start
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 42f54d482441..c526279e1123 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -70,7 +70,20 @@ startup_continue:
 	sgr	%r5,%r5 		# set src,length and pad to zero
 	mvcle	%r2,%r4,0		# clear mem
 	jo	.-4			# branch back, if not finish
+					# set program check new psw mask
+	mvc	__LC_PGM_NEW_PSW(8),.Lpcmsk-.LPG1(%r13)
+	larl	%r1,.Lslowmemdetect	# set program check address
+	stg	%r1,__LC_PGM_NEW_PSW+8
+	lghi	%r1,0xc
+	diag	%r0,%r1,0x260		# get memory size of virtual machine
+	cgr	%r0,%r1			# different? -> old detection routine
+	jne	.Lslowmemdetect
+	aghi	%r1,1			# size is one more than end
+	larl	%r2,memory_chunk
+	stg	%r1,8(%r2)		# store size of chunk
+	j	.Ldonemem
 
+.Lslowmemdetect:
 	l	%r2,.Lrcp-.LPG1(%r13)	# Read SCP forced command word
 .Lservicecall:
 	stosm	.Lpmask-.LPG1(%r13),0x01	# authorize ext interrupts
@@ -139,8 +152,6 @@ startup_continue:
 	.int	0x100000
 
 .Lfchunk:
-					# set program check new psw mask
-	mvc	__LC_PGM_NEW_PSW(8),.Lpcmsk-.LPG1(%r13)
 
 #
 # find memory chunks.
@@ -175,8 +186,6 @@ startup_continue:
 	stg	%r0,8(%r3)		# store size of chunk
 	st	%r6,20(%r3)		# store type of chunk
 	la	%r3,24(%r3)
-	larl	%r8,memory_size
-	stg	%r5,0(%r8)		# store memory size
 	ahi	%r10,-1			# update chunk number
 .Lchkloop:
 	lr	%r6,%r7			# set access code to last cc
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 1f5e782b3d05..a36bea1188d9 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -13,12 +13,21 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
+#include <linux/ctype.h>
 #include <asm/smp.h>
 #include <asm/setup.h>
 #include <asm/cpcmd.h>
 #include <asm/cio.h>
+#include <asm/ebcdic.h>
+#include <asm/reset.h>
 
 #define IPL_PARM_BLOCK_VERSION 0
+#define LOADPARM_LEN 8
+
+extern char s390_readinfo_sccb[];
+#define SCCB_VALID (*((__u16*)&s390_readinfo_sccb[6]) == 0x0010)
+#define SCCB_LOADPARM (&s390_readinfo_sccb[24])
+#define SCCB_FLAG (s390_readinfo_sccb[91])
 
 enum ipl_type {
 	IPL_TYPE_NONE	 = 1,
@@ -289,9 +298,25 @@ static struct attribute_group ipl_fcp_attr_group = {
 
 /* CCW ipl device attributes */
 
+static ssize_t ipl_ccw_loadparm_show(struct subsystem *subsys, char *page)
+{
+	char loadparm[LOADPARM_LEN + 1] = {};
+
+	if (!SCCB_VALID)
+		return sprintf(page, "#unknown#\n");
+	memcpy(loadparm, SCCB_LOADPARM, LOADPARM_LEN);
+	EBCASC(loadparm, LOADPARM_LEN);
+	strstrip(loadparm);
+	return sprintf(page, "%s\n", loadparm);
+}
+
+static struct subsys_attribute sys_ipl_ccw_loadparm_attr =
+	__ATTR(loadparm, 0444, ipl_ccw_loadparm_show, NULL);
+
 static struct attribute *ipl_ccw_attrs[] = {
 	&sys_ipl_type_attr.attr,
 	&sys_ipl_device_attr.attr,
+	&sys_ipl_ccw_loadparm_attr.attr,
 	NULL,
 };
 
@@ -348,8 +373,57 @@ static struct attribute_group reipl_fcp_attr_group = {
 DEFINE_IPL_ATTR_RW(reipl_ccw, device, "0.0.%04llx\n", "0.0.%llx\n",
 	reipl_block_ccw->ipl_info.ccw.devno);
 
+static void reipl_get_ascii_loadparm(char *loadparm)
+{
+	memcpy(loadparm, &reipl_block_ccw->ipl_info.ccw.load_param,
+	       LOADPARM_LEN);
+	EBCASC(loadparm, LOADPARM_LEN);
+	loadparm[LOADPARM_LEN] = 0;
+	strstrip(loadparm);
+}
+
+static ssize_t reipl_ccw_loadparm_show(struct subsystem *subsys, char *page)
+{
+	char buf[LOADPARM_LEN + 1];
+
+	reipl_get_ascii_loadparm(buf);
+	return sprintf(page, "%s\n", buf);
+}
+
+static ssize_t reipl_ccw_loadparm_store(struct subsystem *subsys,
+					const char *buf, size_t len)
+{
+	int i, lp_len;
+
+	/* ignore trailing newline */
+	lp_len = len;
+	if ((len > 0) && (buf[len - 1] == '\n'))
+		lp_len--;
+	/* loadparm can have max 8 characters and must not start with a blank */
+	if ((lp_len > LOADPARM_LEN) || ((lp_len > 0) && (buf[0] == ' ')))
+		return -EINVAL;
+	/* loadparm can only contain "a-z,A-Z,0-9,SP,." */
+	for (i = 0; i < lp_len; i++) {
+		if (isalpha(buf[i]) || isdigit(buf[i]) || (buf[i] == ' ') ||
+		    (buf[i] == '.'))
+			continue;
+		return -EINVAL;
+	}
+	/* initialize loadparm with blanks */
+	memset(&reipl_block_ccw->ipl_info.ccw.load_param, ' ', LOADPARM_LEN);
+	/* copy and convert to ebcdic */
+	memcpy(&reipl_block_ccw->ipl_info.ccw.load_param, buf, lp_len);
+	ASCEBC(reipl_block_ccw->ipl_info.ccw.load_param, LOADPARM_LEN);
+	return len;
+}
+
+static struct subsys_attribute sys_reipl_ccw_loadparm_attr =
+	__ATTR(loadparm, 0644, reipl_ccw_loadparm_show,
+	       reipl_ccw_loadparm_store);
+
 static struct attribute *reipl_ccw_attrs[] = {
 	&sys_reipl_ccw_device_attr.attr,
+	&sys_reipl_ccw_loadparm_attr.attr,
 	NULL,
 };
 
@@ -502,23 +576,6 @@ static struct subsys_attribute dump_type_attr =
 
 static decl_subsys(dump, NULL, NULL);
 
-#ifdef CONFIG_SMP
-static void dump_smp_stop_all(void)
-{
-	int cpu;
-	preempt_disable();
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		while (signal_processor(cpu, sigp_stop) == sigp_busy)
-			udelay(10);
-	}
-	preempt_enable();
-}
-#else
-#define dump_smp_stop_all() do { } while (0)
-#endif
-
 /*
  * Shutdown actions section
  */
@@ -571,11 +628,14 @@ void do_reipl(void)
 {
 	struct ccw_dev_id devid;
 	static char buf[100];
+	char loadparm[LOADPARM_LEN + 1];
 
 	switch (reipl_type) {
 	case IPL_TYPE_CCW:
+		reipl_get_ascii_loadparm(loadparm);
 		printk(KERN_EMERG "reboot on ccw device: 0.0.%04x\n",
 			reipl_block_ccw->ipl_info.ccw.devno);
+		printk(KERN_EMERG "loadparm = '%s'\n", loadparm);
 		break;
 	case IPL_TYPE_FCP:
 		printk(KERN_EMERG "reboot on fcp device:\n");
@@ -588,12 +648,19 @@ void do_reipl(void)
 	switch (reipl_method) {
 	case IPL_METHOD_CCW_CIO:
 		devid.devno = reipl_block_ccw->ipl_info.ccw.devno;
+		if (ipl_get_type() == IPL_TYPE_CCW && devid.devno == ipl_devno)
+			diag308(DIAG308_IPL, NULL);
 		devid.ssid  = 0;
 		reipl_ccw_dev(&devid);
 		break;
 	case IPL_METHOD_CCW_VM:
-		sprintf(buf, "IPL %X", reipl_block_ccw->ipl_info.ccw.devno);
-		cpcmd(buf, NULL, 0, NULL);
+		if (strlen(loadparm) == 0)
+			sprintf(buf, "IPL %X",
+				reipl_block_ccw->ipl_info.ccw.devno);
+		else
+			sprintf(buf, "IPL %X LOADPARM '%s'",
+				reipl_block_ccw->ipl_info.ccw.devno, loadparm);
+		__cpcmd(buf, NULL, 0, NULL);
 		break;
 	case IPL_METHOD_CCW_DIAG:
 		diag308(DIAG308_SET, reipl_block_ccw);
@@ -607,16 +674,17 @@ void do_reipl(void)
 		diag308(DIAG308_IPL, NULL);
 		break;
 	case IPL_METHOD_FCP_RO_VM:
-		cpcmd("IPL", NULL, 0, NULL);
+		__cpcmd("IPL", NULL, 0, NULL);
 		break;
 	case IPL_METHOD_NONE:
 	default:
 		if (MACHINE_IS_VM)
-			cpcmd("IPL", NULL, 0, NULL);
+			__cpcmd("IPL", NULL, 0, NULL);
 		diag308(DIAG308_IPL, NULL);
 		break;
 	}
-	panic("reipl failed!\n");
+	printk(KERN_EMERG "reboot failed!\n");
+	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
 }
 
 static void do_dump(void)
@@ -639,17 +707,17 @@ static void do_dump(void)
 
 	switch (dump_method) {
 	case IPL_METHOD_CCW_CIO:
-		dump_smp_stop_all();
+		smp_send_stop();
 		devid.devno = dump_block_ccw->ipl_info.ccw.devno;
 		devid.ssid  = 0;
 		reipl_ccw_dev(&devid);
 		break;
 	case IPL_METHOD_CCW_VM:
-		dump_smp_stop_all();
+		smp_send_stop();
 		sprintf(buf, "STORE STATUS");
-		cpcmd(buf, NULL, 0, NULL);
+		__cpcmd(buf, NULL, 0, NULL);
 		sprintf(buf, "IPL %X", dump_block_ccw->ipl_info.ccw.devno);
-		cpcmd(buf, NULL, 0, NULL);
+		__cpcmd(buf, NULL, 0, NULL);
 		break;
 	case IPL_METHOD_CCW_DIAG:
 		diag308(DIAG308_SET, dump_block_ccw);
@@ -746,6 +814,17 @@ static int __init reipl_ccw_init(void)
 	reipl_block_ccw->hdr.version = IPL_PARM_BLOCK_VERSION;
 	reipl_block_ccw->hdr.blk0_len = sizeof(reipl_block_ccw->ipl_info.ccw);
 	reipl_block_ccw->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+	/* check if read scp info worked and set loadparm */
+	if (SCCB_VALID)
+		memcpy(reipl_block_ccw->ipl_info.ccw.load_param,
+		       SCCB_LOADPARM, LOADPARM_LEN);
+	else
+		/* read scp info failed: set empty loadparm (EBCDIC blanks) */
+		memset(reipl_block_ccw->ipl_info.ccw.load_param, 0x40,
+		       LOADPARM_LEN);
+	/* FIXME: check for diag308_set_works when enabling diag ccw reipl */
+	if (!MACHINE_IS_VM)
+		sys_reipl_ccw_loadparm_attr.attr.mode = S_IRUGO;
 	if (ipl_get_type() == IPL_TYPE_CCW)
 		reipl_block_ccw->ipl_info.ccw.devno = ipl_devno;
 	reipl_capabilities |= IPL_TYPE_CCW;
@@ -827,13 +906,11 @@ static int __init dump_ccw_init(void)
 	return 0;
 }
 
-extern char s390_readinfo_sccb[];
-
 static int __init dump_fcp_init(void)
 {
 	int rc;
 
-	if(!(s390_readinfo_sccb[91] & 0x2))
+	if(!(SCCB_FLAG & 0x2) || !SCCB_VALID)
 		return 0; /* LDIPL DUMP is not installed */
 	if (!diag308_set_works)
 		return 0;
@@ -931,3 +1008,53 @@ static int __init s390_ipl_init(void)
 }
 
 __initcall(s390_ipl_init);
+
+static LIST_HEAD(rcall);
+static DEFINE_MUTEX(rcall_mutex);
+
+void register_reset_call(struct reset_call *reset)
+{
+	mutex_lock(&rcall_mutex);
+	list_add(&reset->list, &rcall);
+	mutex_unlock(&rcall_mutex);
+}
+EXPORT_SYMBOL_GPL(register_reset_call);
+
+void unregister_reset_call(struct reset_call *reset)
+{
+	mutex_lock(&rcall_mutex);
+	list_del(&reset->list);
+	mutex_unlock(&rcall_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_reset_call);
+
+static void do_reset_calls(void)
+{
+	struct reset_call *reset;
+
+	list_for_each_entry(reset, &rcall, list)
+		reset->fn();
+}
+
+extern void reset_mcck_handler(void);
+
+void s390_reset_system(void)
+{
+	struct _lowcore *lc;
+
+	/* Stack for interrupt/machine check handler */
+	lc = (struct _lowcore *)(unsigned long) store_prefix();
+	lc->panic_stack = S390_lowcore.panic_stack;
+
+	/* Disable prefixing */
+	set_prefix(0);
+
+	/* Disable lowcore protection */
+	__ctl_clear_bit(0,28);
+
+	/* Set new machine check handler */
+	S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS & ~PSW_MASK_MCHECK;
+	S390_lowcore.mcck_new_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) &reset_mcck_handler;
+	do_reset_calls();
+}
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 60b1ea9f946b..f6d9bcc0f75b 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -1,15 +1,10 @@
 /*
  * arch/s390/kernel/machine_kexec.c
  *
- * (C) Copyright IBM Corp. 2005
+ * Copyright IBM Corp. 2005,2006
  *
- * Author(s): Rolf Adelsberger <adelsberger@de.ibm.com>
- *
- */
-
-/*
- * s390_machine_kexec.c - handle the transition of Linux booting another kernel
- * on the S390 architecture.
+ * Author(s): Rolf Adelsberger,
+ *	      Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
 #include <linux/device.h>
@@ -22,86 +17,49 @@
 #include <asm/pgalloc.h>
 #include <asm/system.h>
 #include <asm/smp.h>
+#include <asm/reset.h>
 
-static void kexec_halt_all_cpus(void *);
-
-typedef void (*relocate_kernel_t) (kimage_entry_t *, unsigned long);
+typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long);
 
 extern const unsigned char relocate_kernel[];
 extern const unsigned long long relocate_kernel_len;
 
-int
-machine_kexec_prepare(struct kimage *image)
+int machine_kexec_prepare(struct kimage *image)
 {
-	unsigned long reboot_code_buffer;
+	void *reboot_code_buffer;
 
 	/* We don't support anything but the default image type for now. */
 	if (image->type != KEXEC_TYPE_DEFAULT)
 		return -EINVAL;
 
 	/* Get the destination where the assembler code should be copied to.*/
-	reboot_code_buffer = page_to_pfn(image->control_code_page)<<PAGE_SHIFT;
+	reboot_code_buffer = (void *) page_to_phys(image->control_code_page);
 
 	/* Then copy it */
-	memcpy((void *) reboot_code_buffer, relocate_kernel,
-	       relocate_kernel_len);
+	memcpy(reboot_code_buffer, relocate_kernel, relocate_kernel_len);
 	return 0;
 }
 
-void
-machine_kexec_cleanup(struct kimage *image)
+void machine_kexec_cleanup(struct kimage *image)
 {
 }
 
-void
-machine_shutdown(void)
+void machine_shutdown(void)
 {
 	printk(KERN_INFO "kexec: machine_shutdown called\n");
 }
 
-NORET_TYPE void
-machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
-	clear_all_subchannels();
-	cio_reset_channel_paths();
-
-	/* Disable lowcore protection */
-	ctl_clear_bit(0,28);
-
-	on_each_cpu(kexec_halt_all_cpus, image, 0, 0);
-	for (;;);
-}
-
-extern void pfault_fini(void);
-
-static void
-kexec_halt_all_cpus(void *kernel_image)
-{
-	static atomic_t cpuid = ATOMIC_INIT(-1);
-	int cpu;
-	struct kimage *image;
 	relocate_kernel_t data_mover;
 
-#ifdef CONFIG_PFAULT
-	if (MACHINE_IS_VM)
-		pfault_fini();
-#endif
+	smp_send_stop();
+	pfault_fini();
+	s390_reset_system();
 
-	if (atomic_cmpxchg(&cpuid, -1, smp_processor_id()) != -1)
-		signal_processor(smp_processor_id(), sigp_stop);
-
-	/* Wait for all other cpus to enter stopped state */
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		while (!smp_cpu_not_running(cpu))
-			cpu_relax();
-	}
-
-	image = (struct kimage *) kernel_image;
-	data_mover = (relocate_kernel_t)
-		(page_to_pfn(image->control_code_page) << PAGE_SHIFT);
+	data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page);
 
 	/* Call the moving routine */
-	(*data_mover) (&image->head, image->start);
+	(*data_mover)(&image->head, image->start);
+	for (;;);
 }
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 0340477f3b08..f9434d42ce9f 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -11,19 +11,10 @@
 		.globl	do_reipl_asm
 do_reipl_asm:	basr	%r13,0
 .Lpg0:		lpsw	.Lnewpsw-.Lpg0(%r13)
-
-		# switch off lowcore protection
-
-.Lpg1:		stctl	%c0,%c0,.Lctlsave1-.Lpg0(%r13)
-		stctl	%c0,%c0,.Lctlsave2-.Lpg0(%r13)
-		ni	.Lctlsave1-.Lpg0(%r13),0xef
-		lctl	%c0,%c0,.Lctlsave1-.Lpg0(%r13)
-
-		# do store status of all registers
+.Lpg1:		# do store status of all registers
 
 		stm	%r0,%r15,__LC_GPREGS_SAVE_AREA
 		stctl	%c0,%c15,__LC_CREGS_SAVE_AREA
-		mvc	__LC_CREGS_SAVE_AREA(4),.Lctlsave2-.Lpg0(%r13)
 		stam	%a0,%a15,__LC_AREGS_SAVE_AREA
 		stpx	__LC_PREFIX_SAVE_AREA
 		stckc	.Lclkcmp-.Lpg0(%r13)
@@ -56,8 +47,7 @@ do_reipl_asm:	basr	%r13,0
 .L002:		tm	.Liplirb+8-.Lpg0(%r13),0xf3
 		jz	.L003
 		bas	%r14,.Ldisab-.Lpg0(%r13)
-.L003:		spx	.Lnull-.Lpg0(%r13)
-		st	%r1,__LC_SUBCHANNEL_ID
+.L003:		st	%r1,__LC_SUBCHANNEL_ID
 		lpsw	0
 		sigp	0,0,0(6)
 .Ldisab:	st	%r14,.Ldispsw+4-.Lpg0(%r13)
@@ -65,9 +55,6 @@ do_reipl_asm:	basr	%r13,0
 		.align	8
 .Lclkcmp:	.quad	0x0000000000000000
 .Lall:		.long	0xff000000
-.Lnull:		.long	0x00000000
-.Lctlsave1:	.long	0x00000000
-.Lctlsave2:	.long	0x00000000
 		.align	8
 .Lnewpsw:	.long	0x00080000,0x80000000+.Lpg1
 .Lpcnew:	.long	0x00080000,0x80000000+.Lecs
diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S
index de7435054f7c..f18ef260ca23 100644
--- a/arch/s390/kernel/reipl64.S
+++ b/arch/s390/kernel/reipl64.S
@@ -10,10 +10,10 @@
 #include <asm/lowcore.h>
 		.globl	do_reipl_asm
 do_reipl_asm:	basr	%r13,0
+.Lpg0:		lpswe	.Lnewpsw-.Lpg0(%r13)
+.Lpg1:		# do store status of all registers
 
-		# do store status of all registers
-
-.Lpg0:		stg	%r1,.Lregsave-.Lpg0(%r13)
+		stg	%r1,.Lregsave-.Lpg0(%r13)
 		lghi	%r1,0x1000
 		stmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-0x1000(%r1)
 		lg	%r0,.Lregsave-.Lpg0(%r13)
@@ -27,11 +27,7 @@ do_reipl_asm:	basr	%r13,0
 		stpt	__LC_CPU_TIMER_SAVE_AREA-0x1000(%r1)
 		stg	%r13, __LC_PSW_SAVE_AREA-0x1000+8(%r1)
 
-		lpswe	.Lnewpsw-.Lpg0(%r13)
-.Lpg1:		lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
-		stctg	%c0,%c0,.Lregsave-.Lpg0(%r13)
-		ni	.Lregsave+4-.Lpg0(%r13),0xef
-		lctlg	%c0,%c0,.Lregsave-.Lpg0(%r13)
+		lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
 		lgr	%r1,%r2
 		mvc	__LC_PGM_NEW_PSW(16),.Lpcnew-.Lpg0(%r13)
 		stsch	.Lschib-.Lpg0(%r13)
@@ -56,8 +52,7 @@ do_reipl_asm:	basr	%r13,0
 .L002:		tm	.Liplirb+8-.Lpg0(%r13),0xf3
 		jz	.L003
 		bas	%r14,.Ldisab-.Lpg0(%r13)
-.L003:		spx	.Lnull-.Lpg0(%r13)
-		st	%r1,__LC_SUBCHANNEL_ID
+.L003:		st	%r1,__LC_SUBCHANNEL_ID
 		lhi	%r1,0		 # mode 0 = esa
 		slr	%r0,%r0 	 # set cpuid to zero
 		sigp	%r1,%r0,0x12	 # switch to esa mode
@@ -70,7 +65,6 @@ do_reipl_asm:	basr	%r13,0
 .Lclkcmp:	.quad	0x0000000000000000
 .Lall:		.quad	0x00000000ff000000
 .Lregsave:	.quad	0x0000000000000000
-.Lnull:		.long	0x0000000000000000
 		.align	16
 /*
  * These addresses have to be 31 bit otherwise
diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S
index f9899ff2e5b0..3b456b80bcee 100644
--- a/arch/s390/kernel/relocate_kernel.S
+++ b/arch/s390/kernel/relocate_kernel.S
@@ -26,8 +26,7 @@
 	relocate_kernel:
 		basr	%r13,0		# base address
 	.base:
-		stnsm	sys_msk-.base(%r13),0xf8	# disable DAT and IRQ (external)
-		spx	zero64-.base(%r13)	# absolute addressing mode
+		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
 		stctl	%c0,%c15,ctlregs-.base(%r13)
 		stm	%r0,%r15,gprregs-.base(%r13)
 		la	%r1,load_psw-.base(%r13)
@@ -97,8 +96,6 @@
 		lpsw	0		# hopefully start new kernel...
 
 		.align	8
-	zero64:
-		.quad	0
 	load_psw:
 		.long	0x00080000,0x80000000
 	sys_msk:
diff --git a/arch/s390/kernel/relocate_kernel64.S b/arch/s390/kernel/relocate_kernel64.S
index 4fb443042d9c..1f9ea2067b59 100644
--- a/arch/s390/kernel/relocate_kernel64.S
+++ b/arch/s390/kernel/relocate_kernel64.S
@@ -27,8 +27,7 @@
 	relocate_kernel:
 		basr	%r13,0		# base address
 	.base:
-		stnsm	sys_msk-.base(%r13),0xf8	# disable DAT and IRQs
-		spx	zero64-.base(%r13)	# absolute addressing mode
+		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
 		stctg	%c0,%c15,ctlregs-.base(%r13)
 		stmg	%r0,%r15,gprregs-.base(%r13)
 		lghi	%r0,3
@@ -100,8 +99,6 @@
 		lpsw	0		# hopefully start new kernel...
 
 		.align	8
-	zero64:
-		.quad	0
 	load_psw:
 		.long	0x00080000,0x80000000
 	sys_msk:
diff --git a/arch/s390/kernel/reset.S b/arch/s390/kernel/reset.S
new file mode 100644
index 000000000000..be8688c0665c
--- /dev/null
+++ b/arch/s390/kernel/reset.S
@@ -0,0 +1,48 @@
+/*
+ *  arch/s390/kernel/reset.S
+ *
+ *    Copyright (C) IBM Corp. 2006
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <asm/ptrace.h>
+#include <asm/lowcore.h>
+
+#ifdef CONFIG_64BIT
+
+	.globl	reset_mcck_handler
+reset_mcck_handler:
+	basr	%r13,0
+0:	lg	%r15,__LC_PANIC_STACK	# load panic stack
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	lg	%r1,s390_reset_mcck_handler-0b(%r13)
+	ltgr	%r1,%r1
+	jz	1f
+	basr	%r14,%r1
+1:	la	%r1,4095
+	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
+	lpswe	__LC_MCK_OLD_PSW
+
+	.globl	s390_reset_mcck_handler
+s390_reset_mcck_handler:
+	.quad	0
+
+#else /* CONFIG_64BIT */
+
+	.globl	reset_mcck_handler
+reset_mcck_handler:
+	basr	%r13,0
+0:	l	%r15,__LC_PANIC_STACK	# load panic stack
+	ahi	%r15,-STACK_FRAME_OVERHEAD
+	l	%r1,s390_reset_mcck_handler-0b(%r13)
+	ltr	%r1,%r1
+	jz	1f
+	basr	%r14,%r1
+1:	lm	%r0,%r15,__LC_GPREGS_SAVE_AREA
+	lpsw	__LC_MCK_OLD_PSW
+
+	.globl	s390_reset_mcck_handler
+s390_reset_mcck_handler:
+	.long	0
+
+#endif /* CONFIG_64BIT */
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 2aa13e8e000a..b928fecdc743 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -62,13 +62,9 @@ EXPORT_SYMBOL_GPL(uaccess);
 unsigned int console_mode = 0;
 unsigned int console_devno = -1;
 unsigned int console_irq = -1;
-unsigned long memory_size = 0;
 unsigned long machine_flags = 0;
-struct {
-	unsigned long addr, size, type;
-} memory_chunk[MEMORY_CHUNKS] = { { 0 } };
-#define CHUNK_READ_WRITE 0
-#define CHUNK_READ_ONLY 1
+
+struct mem_chunk memory_chunk[MEMORY_CHUNKS];
 volatile int __cpu_logical_map[NR_CPUS]; /* logical cpu to cpu address */
 unsigned long __initdata zholes_size[MAX_NR_ZONES];
 static unsigned long __initdata memory_end;
@@ -229,11 +225,11 @@ static void __init conmode_default(void)
 	char *ptr;
 
         if (MACHINE_IS_VM) {
-		__cpcmd("QUERY CONSOLE", query_buffer, 1024, NULL);
+		cpcmd("QUERY CONSOLE", query_buffer, 1024, NULL);
 		console_devno = simple_strtoul(query_buffer + 5, NULL, 16);
 		ptr = strstr(query_buffer, "SUBCHANNEL =");
 		console_irq = simple_strtoul(ptr + 13, NULL, 16);
-		__cpcmd("QUERY TERM", query_buffer, 1024, NULL);
+		cpcmd("QUERY TERM", query_buffer, 1024, NULL);
 		ptr = strstr(query_buffer, "CONMODE");
 		/*
 		 * Set the conmode to 3215 so that the device recognition 
@@ -242,7 +238,7 @@ static void __init conmode_default(void)
 		 * 3215 and the 3270 driver will try to access the console
 		 * device (3215 as console and 3270 as normal tty).
 		 */
-		__cpcmd("TERM CONMODE 3215", NULL, 0, NULL);
+		cpcmd("TERM CONMODE 3215", NULL, 0, NULL);
 		if (ptr == NULL) {
 #if defined(CONFIG_SCLP_CONSOLE)
 			SET_CONSOLE_SCLP;
@@ -299,14 +295,14 @@ static void do_machine_restart_nonsmp(char * __unused)
 static void do_machine_halt_nonsmp(void)
 {
         if (MACHINE_IS_VM && strlen(vmhalt_cmd) > 0)
-                cpcmd(vmhalt_cmd, NULL, 0, NULL);
+		__cpcmd(vmhalt_cmd, NULL, 0, NULL);
         signal_processor(smp_processor_id(), sigp_stop_and_store_status);
 }
 
 static void do_machine_power_off_nonsmp(void)
 {
         if (MACHINE_IS_VM && strlen(vmpoff_cmd) > 0)
-                cpcmd(vmpoff_cmd, NULL, 0, NULL);
+		__cpcmd(vmpoff_cmd, NULL, 0, NULL);
         signal_processor(smp_processor_id(), sigp_stop_and_store_status);
 }
 
@@ -489,6 +485,37 @@ setup_resources(void)
 	}
 }
 
+static void __init setup_memory_end(void)
+{
+	unsigned long real_size, memory_size;
+	unsigned long max_mem, max_phys;
+	int i;
+
+	memory_size = real_size = 0;
+	max_phys = VMALLOC_END - VMALLOC_MIN_SIZE;
+	memory_end &= PAGE_MASK;
+
+	max_mem = memory_end ? min(max_phys, memory_end) : max_phys;
+
+	for (i = 0; i < MEMORY_CHUNKS; i++) {
+		struct mem_chunk *chunk = &memory_chunk[i];
+
+		real_size = max(real_size, chunk->addr + chunk->size);
+		if (chunk->addr >= max_mem) {
+			memset(chunk, 0, sizeof(*chunk));
+			continue;
+		}
+		if (chunk->addr + chunk->size > max_mem)
+			chunk->size = max_mem - chunk->addr;
+		memory_size = max(memory_size, chunk->addr + chunk->size);
+	}
+	if (!memory_end)
+		memory_end = memory_size;
+	if (real_size > memory_end)
+		printk("More memory detected than supported. Unused: %luk\n",
+		       (real_size - memory_end) >> 10);
+}
+
 static void __init
 setup_memory(void)
 {
@@ -645,8 +672,6 @@ setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) &_edata;
 	init_mm.brk = (unsigned long) &_end;
 
-	memory_end = memory_size;
-
 	if (MACHINE_HAS_MVCOS)
 		memcpy(&uaccess, &uaccess_mvcos, sizeof(uaccess));
 	else
@@ -654,20 +679,7 @@ setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-#ifndef CONFIG_64BIT
-	memory_end &= ~0x400000UL;
-
-        /*
-         * We need some free virtual space to be able to do vmalloc.
-         * On a machine with 2GB memory we make sure that we have at
-         * least 128 MB free space for vmalloc.
-         */
-        if (memory_end > 1920*1024*1024)
-                memory_end = 1920*1024*1024;
-#else /* CONFIG_64BIT */
-	memory_end &= ~0x200000UL;
-#endif /* CONFIG_64BIT */
-
+	setup_memory_end();
 	setup_memory();
 	setup_resources();
 	setup_lowcore();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 62822245f9be..19090f7d4f51 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -230,18 +230,37 @@ static inline void do_store_status(void)
         }
 }
 
+static inline void do_wait_for_stop(void)
+{
+	int cpu;
+
+	/* Wait for all other cpus to enter stopped state */
+	for_each_online_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+		while(!smp_cpu_not_running(cpu))
+			cpu_relax();
+	}
+}
+
 /*
  * this function sends a 'stop' sigp to all other CPUs in the system.
  * it goes straight through.
  */
 void smp_send_stop(void)
 {
+	/* Disable all interrupts/machine checks */
+	__load_psw_mask(PSW_KERNEL_BITS & ~PSW_MASK_MCHECK);
+
         /* write magic number to zero page (absolute 0) */
 	lowcore_ptr[smp_processor_id()]->panic_magic = __PANIC_MAGIC;
 
 	/* stop other processors. */
 	do_send_stop();
 
+	/* wait until other processors are stopped */
+	do_wait_for_stop();
+
 	/* store status of other processors. */
 	do_store_status();
 }
@@ -250,88 +269,28 @@ void smp_send_stop(void)
  * Reboot, halt and power_off routines for SMP.
  */
 
-static void do_machine_restart(void * __unused)
-{
-	int cpu;
-	static atomic_t cpuid = ATOMIC_INIT(-1);
-
-	if (atomic_cmpxchg(&cpuid, -1, smp_processor_id()) != -1)
-		signal_processor(smp_processor_id(), sigp_stop);
-
-	/* Wait for all other cpus to enter stopped state */
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		while(!smp_cpu_not_running(cpu))
-			cpu_relax();
-	}
-
-	/* Store status of other cpus. */
-	do_store_status();
-
-	/*
-	 * Finally call reipl. Because we waited for all other
-	 * cpus to enter this function we know that they do
-	 * not hold any s390irq-locks (the cpus have been
-	 * interrupted by an external interrupt and s390irq
-	 * locks are always held disabled).
-	 */
-	do_reipl();
-}
-
 void machine_restart_smp(char * __unused) 
 {
-        on_each_cpu(do_machine_restart, NULL, 0, 0);
-}
-
-static void do_wait_for_stop(void)
-{
-	unsigned long cr[16];
-
-	__ctl_store(cr, 0, 15);
-	cr[0] &= ~0xffff;
-	cr[6] = 0;
-	__ctl_load(cr, 0, 15);
-	for (;;)
-		enabled_wait();
-}
-
-static void do_machine_halt(void * __unused)
-{
-	static atomic_t cpuid = ATOMIC_INIT(-1);
-
-	if (atomic_cmpxchg(&cpuid, -1, smp_processor_id()) == -1) {
-		smp_send_stop();
-		if (MACHINE_IS_VM && strlen(vmhalt_cmd) > 0)
-			cpcmd(vmhalt_cmd, NULL, 0, NULL);
-		signal_processor(smp_processor_id(),
-				 sigp_stop_and_store_status);
-	}
-	do_wait_for_stop();
+	smp_send_stop();
+	do_reipl();
 }
 
 void machine_halt_smp(void)
 {
-        on_each_cpu(do_machine_halt, NULL, 0, 0);
-}
-
-static void do_machine_power_off(void * __unused)
-{
-	static atomic_t cpuid = ATOMIC_INIT(-1);
-
-	if (atomic_cmpxchg(&cpuid, -1, smp_processor_id()) == -1) {
-		smp_send_stop();
-		if (MACHINE_IS_VM && strlen(vmpoff_cmd) > 0)
-			cpcmd(vmpoff_cmd, NULL, 0, NULL);
-		signal_processor(smp_processor_id(),
-				 sigp_stop_and_store_status);
-	}
-	do_wait_for_stop();
+	smp_send_stop();
+	if (MACHINE_IS_VM && strlen(vmhalt_cmd) > 0)
+		__cpcmd(vmhalt_cmd, NULL, 0, NULL);
+	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
+	for (;;);
 }
 
 void machine_power_off_smp(void)
 {
-        on_each_cpu(do_machine_power_off, NULL, 0, 0);
+	smp_send_stop();
+	if (MACHINE_IS_VM && strlen(vmpoff_cmd) > 0)
+		__cpcmd(vmpoff_cmd, NULL, 0, NULL);
+	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
+	for (;;);
 }
 
 /*
@@ -501,8 +460,6 @@ __init smp_count_cpus(void)
  */
 extern void init_cpu_timer(void);
 extern void init_cpu_vtimer(void);
-extern int pfault_init(void);
-extern void pfault_fini(void);
 
 int __devinit start_secondary(void *cpuvoid)
 {
@@ -514,11 +471,9 @@ int __devinit start_secondary(void *cpuvoid)
 #ifdef CONFIG_VIRT_TIMER
         init_cpu_vtimer();
 #endif
-#ifdef CONFIG_PFAULT
 	/* Enable pfault pseudo page faults on this cpu. */
-	if (MACHINE_IS_VM)
-		pfault_init();
-#endif
+	pfault_init();
+
 	/* Mark this cpu as online */
 	cpu_set(smp_processor_id(), cpu_online_map);
 	/* Switch on interrupts */
@@ -708,11 +663,8 @@ __cpu_disable(void)
 	}
 	cpu_clear(cpu, cpu_online_map);
 
-#ifdef CONFIG_PFAULT
 	/* Disable pfault pseudo page faults on this cpu. */
-	if (MACHINE_IS_VM)
-		pfault_fini();
-#endif
+	pfault_fini();
 
 	memset(&cr_parms.orvals, 0, sizeof(cr_parms.orvals));
 	memset(&cr_parms.andvals, 0xff, sizeof(cr_parms.andvals));
@@ -860,4 +812,3 @@ EXPORT_SYMBOL(smp_ctl_clear_bit);
 EXPORT_SYMBOL(smp_call_function);
 EXPORT_SYMBOL(smp_get_cpu);
 EXPORT_SYMBOL(smp_put_cpu);
-
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 92ecffbc8d82..3cbb0dcf1f1d 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -58,12 +58,6 @@ int sysctl_userprocess_debug = 0;
 
 extern pgm_check_handler_t do_protection_exception;
 extern pgm_check_handler_t do_dat_exception;
-#ifdef CONFIG_PFAULT
-extern int pfault_init(void);
-extern void pfault_fini(void);
-extern void pfault_interrupt(__u16 error_code);
-static ext_int_info_t ext_int_pfault;
-#endif
 extern pgm_check_handler_t do_monitor_call;
 
 #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
@@ -135,7 +129,7 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 	}
 }
 
-void show_trace(struct task_struct *task, unsigned long * stack)
+void show_trace(struct task_struct *task, unsigned long *stack)
 {
 	register unsigned long __r15 asm ("15");
 	unsigned long sp;
@@ -157,6 +151,9 @@ void show_trace(struct task_struct *task, unsigned long * stack)
 		__show_trace(sp, S390_lowcore.thread_info,
 			     S390_lowcore.thread_info + THREAD_SIZE);
 	printk("\n");
+	if (!task)
+		task = current;
+	debug_show_held_locks(task);
 }
 
 void show_stack(struct task_struct *task, unsigned long *sp)
@@ -739,22 +736,5 @@ void __init trap_init(void)
         pgm_check_table[0x1C] = &space_switch_exception;
         pgm_check_table[0x1D] = &hfp_sqrt_exception;
 	pgm_check_table[0x40] = &do_monitor_call;
-
-	if (MACHINE_IS_VM) {
-#ifdef CONFIG_PFAULT
-		/*
-		 * Try to get pfault pseudo page faults going.
-		 */
-		if (register_early_external_interrupt(0x2603, pfault_interrupt,
-						      &ext_int_pfault) != 0)
-			panic("Couldn't request external interrupt 0x2603");
-
-		if (pfault_init() == 0) 
-			return;
-		
-		/* Tough luck, no pfault. */
-		unregister_early_external_interrupt(0x2603, pfault_interrupt,
-						    &ext_int_pfault);
-#endif
-	}
+	pfault_irq_init();
 }
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index b0cfa6c4883d..b5f94cf3bde8 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -4,7 +4,7 @@
 
 EXTRA_AFLAGS := -traditional
 
-lib-y += delay.o string.o uaccess_std.o
+lib-y += delay.o string.o uaccess_std.o uaccess_pt.o
 lib-$(CONFIG_32BIT) += div64.o
 lib-$(CONFIG_64BIT) += uaccess_mvcos.o
 lib-$(CONFIG_SMP) += spinlock.o
diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c
index 121b2935a422..f9a23d57eb79 100644
--- a/arch/s390/lib/uaccess_mvcos.c
+++ b/arch/s390/lib/uaccess_mvcos.c
@@ -27,6 +27,9 @@
 #define SLR	"slgr"
 #endif
 
+extern size_t copy_from_user_std(size_t, const void __user *, void *);
+extern size_t copy_to_user_std(size_t, void __user *, const void *);
+
 size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
 {
 	register unsigned long reg0 asm("0") = 0x81UL;
@@ -66,6 +69,13 @@ size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
 	return size;
 }
 
+size_t copy_from_user_mvcos_check(size_t size, const void __user *ptr, void *x)
+{
+	if (size <= 256)
+		return copy_from_user_std(size, ptr, x);
+	return copy_from_user_mvcos(size, ptr, x);
+}
+
 size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
 {
 	register unsigned long reg0 asm("0") = 0x810000UL;
@@ -95,6 +105,13 @@ size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
 	return size;
 }
 
+size_t copy_to_user_mvcos_check(size_t size, void __user *ptr, const void *x)
+{
+	if (size <= 256)
+		return copy_to_user_std(size, ptr, x);
+	return copy_to_user_mvcos(size, ptr, x);
+}
+
 size_t copy_in_user_mvcos(size_t size, void __user *to, const void __user *from)
 {
 	register unsigned long reg0 asm("0") = 0x810081UL;
@@ -145,18 +162,16 @@ size_t clear_user_mvcos(size_t size, void __user *to)
 	return size;
 }
 
-extern size_t copy_from_user_std_small(size_t, const void __user *, void *);
-extern size_t copy_to_user_std_small(size_t, void __user *, const void *);
 extern size_t strnlen_user_std(size_t, const char __user *);
 extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
 extern int futex_atomic_op(int, int __user *, int, int *);
 extern int futex_atomic_cmpxchg(int __user *, int, int);
 
 struct uaccess_ops uaccess_mvcos = {
-	.copy_from_user = copy_from_user_mvcos,
-	.copy_from_user_small = copy_from_user_std_small,
-	.copy_to_user = copy_to_user_mvcos,
-	.copy_to_user_small = copy_to_user_std_small,
+	.copy_from_user = copy_from_user_mvcos_check,
+	.copy_from_user_small = copy_from_user_std,
+	.copy_to_user = copy_to_user_mvcos_check,
+	.copy_to_user_small = copy_to_user_std,
 	.copy_in_user = copy_in_user_mvcos,
 	.clear_user = clear_user_mvcos,
 	.strnlen_user = strnlen_user_std,
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
new file mode 100644
index 000000000000..8741bdc09299
--- /dev/null
+++ b/arch/s390/lib/uaccess_pt.c
@@ -0,0 +1,153 @@
+/*
+ *  arch/s390/lib/uaccess_pt.c
+ *
+ *  User access functions based on page table walks.
+ *
+ *    Copyright IBM Corp. 2006
+ *    Author(s): Gerald Schaefer (gerald.schaefer@de.ibm.com)
+ */
+
+#include <linux/errno.h>
+#include <asm/uaccess.h>
+#include <linux/mm.h>
+#include <asm/futex.h>
+
+static inline int __handle_fault(struct mm_struct *mm, unsigned long address,
+				 int write_access)
+{
+	struct vm_area_struct *vma;
+	int ret = -EFAULT;
+
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, address);
+	if (unlikely(!vma))
+		goto out;
+	if (unlikely(vma->vm_start > address)) {
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			goto out;
+		if (expand_stack(vma, address))
+			goto out;
+	}
+
+	if (!write_access) {
+		/* page not present, check vm flags */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+			goto out;
+	} else {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto out;
+	}
+
+survive:
+	switch (handle_mm_fault(mm, vma, address, write_access)) {
+	case VM_FAULT_MINOR:
+		current->min_flt++;
+		break;
+	case VM_FAULT_MAJOR:
+		current->maj_flt++;
+		break;
+	case VM_FAULT_SIGBUS:
+		goto out_sigbus;
+	case VM_FAULT_OOM:
+		goto out_of_memory;
+	default:
+		BUG();
+	}
+	ret = 0;
+out:
+	up_read(&mm->mmap_sem);
+	return ret;
+
+out_of_memory:
+	up_read(&mm->mmap_sem);
+	if (current->pid == 1) {
+		yield();
+		goto survive;
+	}
+	printk("VM: killing process %s\n", current->comm);
+	return ret;
+
+out_sigbus:
+	up_read(&mm->mmap_sem);
+	current->thread.prot_addr = address;
+	current->thread.trap_no = 0x11;
+	force_sig(SIGBUS, current);
+	return ret;
+}
+
+static inline size_t __user_copy_pt(unsigned long uaddr, void *kptr,
+				    size_t n, int write_user)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long offset, pfn, done, size;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte;
+	void *from, *to;
+
+	done = 0;
+retry:
+	spin_lock(&mm->page_table_lock);
+	do {
+		pgd = pgd_offset(mm, uaddr);
+		if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+			goto fault;
+
+		pmd = pmd_offset(pgd, uaddr);
+		if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+			goto fault;
+
+		pte = pte_offset_map(pmd, uaddr);
+		if (!pte || !pte_present(*pte) ||
+		    (write_user && !pte_write(*pte)))
+			goto fault;
+
+		pfn = pte_pfn(*pte);
+		if (!pfn_valid(pfn))
+			goto out;
+
+		offset = uaddr & (PAGE_SIZE - 1);
+		size = min(n - done, PAGE_SIZE - offset);
+		if (write_user) {
+			to = (void *)((pfn << PAGE_SHIFT) + offset);
+			from = kptr + done;
+		} else {
+			from = (void *)((pfn << PAGE_SHIFT) + offset);
+			to = kptr + done;
+		}
+		memcpy(to, from, size);
+		done += size;
+		uaddr += size;
+	} while (done < n);
+out:
+	spin_unlock(&mm->page_table_lock);
+	return n - done;
+fault:
+	spin_unlock(&mm->page_table_lock);
+	if (__handle_fault(mm, uaddr, write_user))
+		return n - done;
+	goto retry;
+}
+
+size_t copy_from_user_pt(size_t n, const void __user *from, void *to)
+{
+	size_t rc;
+
+	if (segment_eq(get_fs(), KERNEL_DS)) {
+		memcpy(to, (void __kernel __force *) from, n);
+		return 0;
+	}
+	rc = __user_copy_pt((unsigned long) from, to, n, 0);
+	if (unlikely(rc))
+		memset(to + n - rc, 0, rc);
+	return rc;
+}
+
+size_t copy_to_user_pt(size_t n, void __user *to, const void *from)
+{
+	if (segment_eq(get_fs(), KERNEL_DS)) {
+		memcpy((void __kernel __force *) to, from, n);
+		return 0;
+	}
+	return __user_copy_pt((unsigned long) to, (void *) from, n, 1);
+}
diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c
index f44f0078b354..2d549ed2e113 100644
--- a/arch/s390/lib/uaccess_std.c
+++ b/arch/s390/lib/uaccess_std.c
@@ -28,6 +28,9 @@
 #define SLR	"slgr"
 #endif
 
+extern size_t copy_from_user_pt(size_t n, const void __user *from, void *to);
+extern size_t copy_to_user_pt(size_t n, void __user *to, const void *from);
+
 size_t copy_from_user_std(size_t size, const void __user *ptr, void *x)
 {
 	unsigned long tmp1, tmp2;
@@ -69,34 +72,11 @@ size_t copy_from_user_std(size_t size, const void __user *ptr, void *x)
 	return size;
 }
 
-size_t copy_from_user_std_small(size_t size, const void __user *ptr, void *x)
+size_t copy_from_user_std_check(size_t size, const void __user *ptr, void *x)
 {
-	unsigned long tmp1, tmp2;
-
-	tmp1 = 0UL;
-	asm volatile(
-		"0: mvcp  0(%0,%2),0(%1),%3\n"
-		"  "SLR"  %0,%0\n"
-		"   j     5f\n"
-		"1: la    %4,255(%1)\n" /* %4 = ptr + 255 */
-		"  "LHI"  %3,-4096\n"
-		"   nr    %4,%3\n"	/* %4 = (ptr + 255) & -4096 */
-		"  "SLR"  %4,%1\n"
-		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
-		"   jnh   5f\n"
-		"2: mvcp  0(%4,%2),0(%1),%3\n"
-		"  "SLR"  %0,%4\n"
-		"  "ALR"  %2,%4\n"
-		"3:"LHI"  %4,-1\n"
-		"  "ALR"  %4,%0\n"	/* copy remaining size, subtract 1 */
-		"   bras  %3,4f\n"
-		"   xc    0(1,%2),0(%2)\n"
-		"4: ex    %4,0(%3)\n"
-		"5:\n"
-		EX_TABLE(0b,1b) EX_TABLE(2b,3b)
-		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
-		: : "cc", "memory");
-	return size;
+	if (size <= 1024)
+		return copy_from_user_std(size, ptr, x);
+	return copy_from_user_pt(size, ptr, x);
 }
 
 size_t copy_to_user_std(size_t size, void __user *ptr, const void *x)
@@ -130,28 +110,11 @@ size_t copy_to_user_std(size_t size, void __user *ptr, const void *x)
 	return size;
 }
 
-size_t copy_to_user_std_small(size_t size, void __user *ptr, const void *x)
+size_t copy_to_user_std_check(size_t size, void __user *ptr, const void *x)
 {
-	unsigned long tmp1, tmp2;
-
-	tmp1 = 0UL;
-	asm volatile(
-		"0: mvcs  0(%0,%1),0(%2),%3\n"
-		"  "SLR"  %0,%0\n"
-		"   j     3f\n"
-		"1: la    %4,255(%1)\n" /* ptr + 255 */
-		"  "LHI"  %3,-4096\n"
-		"   nr    %4,%3\n"	/* (ptr + 255) & -4096UL */
-		"  "SLR"  %4,%1\n"
-		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
-		"   jnh   3f\n"
-		"2: mvcs  0(%4,%1),0(%2),%3\n"
-		"  "SLR"  %0,%4\n"
-		"3:\n"
-		EX_TABLE(0b,1b) EX_TABLE(2b,3b)
-		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
-		: : "cc", "memory");
-	return size;
+	if (size <= 1024)
+		return copy_to_user_std(size, ptr, x);
+	return copy_to_user_pt(size, ptr, x);
 }
 
 size_t copy_in_user_std(size_t size, void __user *to, const void __user *from)
@@ -343,10 +306,10 @@ int futex_atomic_cmpxchg(int __user *uaddr, int oldval, int newval)
 }
 
 struct uaccess_ops uaccess_std = {
-	.copy_from_user = copy_from_user_std,
-	.copy_from_user_small = copy_from_user_std_small,
-	.copy_to_user = copy_to_user_std,
-	.copy_to_user_small = copy_to_user_std_small,
+	.copy_from_user = copy_from_user_std_check,
+	.copy_from_user_small = copy_from_user_std,
+	.copy_to_user = copy_to_user_std_check,
+	.copy_to_user_small = copy_to_user_std,
 	.copy_in_user = copy_in_user_std,
 	.clear_user = clear_user_std,
 	.strnlen_user = strnlen_user_std,
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 226275d5c4f6..9e9bc48463a5 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -14,12 +14,13 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bootmem.h>
+#include <linux/ctype.h>
 #include <asm/page.h>
 #include <asm/ebcdic.h>
 #include <asm/errno.h>
 #include <asm/extmem.h>
 #include <asm/cpcmd.h>
-#include <linux/ctype.h>
+#include <asm/setup.h>
 
 #define DCSS_DEBUG	/* Debug messages on/off */
 
@@ -77,15 +78,11 @@ struct dcss_segment {
 	int segcnt;
 };
 
-static DEFINE_SPINLOCK(dcss_lock);
+static DEFINE_MUTEX(dcss_lock);
 static struct list_head dcss_list = LIST_HEAD_INIT(dcss_list);
 static char *segtype_string[] = { "SW", "EW", "SR", "ER", "SN", "EN", "SC",
 					"EW/EN-MIXED" };
 
-extern struct {
-	unsigned long addr, size, type;
-} memory_chunk[MEMORY_CHUNKS];
-
 /*
  * Create the 8 bytes, ebcdic VM segment name from
  * an ascii name.
@@ -117,7 +114,7 @@ segment_by_name (char *name)
 	struct list_head *l;
 	struct dcss_segment *tmp, *retval = NULL;
 
-	assert_spin_locked(&dcss_lock);
+	BUG_ON(!mutex_is_locked(&dcss_lock));
 	dcss_mkname (name, dcss_name);
 	list_for_each (l, &dcss_list) {
 		tmp = list_entry (l, struct dcss_segment, list);
@@ -249,8 +246,8 @@ segment_overlaps_storage(struct dcss_segment *seg)
 {
 	int i;
 
-	for (i=0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) {
-		if (memory_chunk[i].type != 0)
+	for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) {
+		if (memory_chunk[i].type != CHUNK_READ_WRITE)
 			continue;
 		if ((memory_chunk[i].addr >> 20) > (seg->end >> 20))
 			continue;
@@ -272,7 +269,7 @@ segment_overlaps_others (struct dcss_segment *seg)
 	struct list_head *l;
 	struct dcss_segment *tmp;
 
-	assert_spin_locked(&dcss_lock);
+	BUG_ON(!mutex_is_locked(&dcss_lock));
 	list_for_each(l, &dcss_list) {
 		tmp = list_entry(l, struct dcss_segment, list);
 		if ((tmp->start_addr >> 20) > (seg->end >> 20))
@@ -429,7 +426,7 @@ segment_load (char *name, int do_nonshared, unsigned long *addr,
 	if (!MACHINE_IS_VM)
 		return -ENOSYS;
 
-	spin_lock (&dcss_lock);
+	mutex_lock(&dcss_lock);
 	seg = segment_by_name (name);
 	if (seg == NULL)
 		rc = __segment_load (name, do_nonshared, addr, end);
@@ -444,7 +441,7 @@ segment_load (char *name, int do_nonshared, unsigned long *addr,
 			rc    = -EPERM;
 		}
 	}
-	spin_unlock (&dcss_lock);
+	mutex_unlock(&dcss_lock);
 	return rc;
 }
 
@@ -467,7 +464,7 @@ segment_modify_shared (char *name, int do_nonshared)
 	unsigned long dummy;
 	int dcss_command, rc, diag_cc;
 
-	spin_lock (&dcss_lock);
+	mutex_lock(&dcss_lock);
 	seg = segment_by_name (name);
 	if (seg == NULL) {
 		rc = -EINVAL;
@@ -508,7 +505,7 @@ segment_modify_shared (char *name, int do_nonshared)
 		  &dummy, &dummy);
 	kfree(seg);
  out_unlock:
-	spin_unlock(&dcss_lock);
+	mutex_unlock(&dcss_lock);
 	return rc;
 }
 
@@ -526,7 +523,7 @@ segment_unload(char *name)
 	if (!MACHINE_IS_VM)
 		return;
 
-	spin_lock(&dcss_lock);
+	mutex_lock(&dcss_lock);
 	seg = segment_by_name (name);
 	if (seg == NULL) {
 		PRINT_ERR ("could not find segment %s in segment_unload, "
@@ -540,7 +537,7 @@ segment_unload(char *name)
 		kfree(seg);
 	}
 out_unlock:
-	spin_unlock(&dcss_lock);
+	mutex_unlock(&dcss_lock);
 }
 
 /*
@@ -559,12 +556,13 @@ segment_save(char *name)
 	if (!MACHINE_IS_VM)
 		return;
 
-	spin_lock(&dcss_lock);
+	mutex_lock(&dcss_lock);
 	seg = segment_by_name (name);
 
 	if (seg == NULL) {
-		PRINT_ERR ("could not find segment %s in segment_save, please report to linux390@de.ibm.com\n",name);
-		return;
+		PRINT_ERR("could not find segment %s in segment_save, please "
+			  "report to linux390@de.ibm.com\n", name);
+		goto out;
 	}
 
 	startpfn = seg->start_addr >> PAGE_SHIFT;
@@ -591,7 +589,7 @@ segment_save(char *name)
 		goto out;
 	}
 out:
-	spin_unlock(&dcss_lock);
+	mutex_unlock(&dcss_lock);
 }
 
 EXPORT_SYMBOL(segment_load);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 1c323bbfda91..cd85e34d8703 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -31,6 +31,7 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
+#include <asm/s390_ext.h>
 
 #ifndef CONFIG_64BIT
 #define __FAIL_ADDR_MASK 0x7ffff000
@@ -394,6 +395,7 @@ void do_dat_exception(struct pt_regs *regs, unsigned long error_code)
 /*
  * 'pfault' pseudo page faults routines.
  */
+static ext_int_info_t ext_int_pfault;
 static int pfault_disable = 0;
 
 static int __init nopfault(char *str)
@@ -422,7 +424,7 @@ int pfault_init(void)
 		  __PF_RES_FIELD };
         int rc;
 
-	if (pfault_disable)
+	if (!MACHINE_IS_VM || pfault_disable)
 		return -1;
 	asm volatile(
 		"	diag	%1,%0,0x258\n"
@@ -440,7 +442,7 @@ void pfault_fini(void)
 	pfault_refbk_t refbk =
 	{ 0x258, 1, 5, 2, 0ULL, 0ULL, 0ULL, 0ULL };
 
-	if (pfault_disable)
+	if (!MACHINE_IS_VM || pfault_disable)
 		return;
 	__ctl_clear_bit(0,9);
 	asm volatile(
@@ -500,5 +502,25 @@ pfault_interrupt(__u16 error_code)
 			set_tsk_need_resched(tsk);
 	}
 }
-#endif
 
+void __init pfault_irq_init(void)
+{
+	if (!MACHINE_IS_VM)
+		return;
+
+	/*
+	 * Try to get pfault pseudo page faults going.
+	 */
+	if (register_early_external_interrupt(0x2603, pfault_interrupt,
+					      &ext_int_pfault) != 0)
+		panic("Couldn't request external interrupt 0x2603");
+
+	if (pfault_init() == 0)
+		return;
+
+	/* Tough luck, no pfault. */
+	pfault_disable = 1;
+	unregister_early_external_interrupt(0x2603, pfault_interrupt,
+					    &ext_int_pfault);
+}
+#endif
diff --git a/block/Kconfig b/block/Kconfig
index 83766a6bdee2..a50f48111647 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -19,11 +19,9 @@ config BLOCK
 
 if BLOCK
 
-#XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64
-#for instance.
 config LBD
 	bool "Support for Large Block Devices"
-	depends on X86 || (MIPS && 32BIT) || PPC32 || (S390 && !64BIT) || SUPERH || UML
+	depends on !64BIT
 	help
 	  Say Y here if you want to attach large (bigger than 2TB) discs to
 	  your machine, or if you want to have a raid or loopback device
@@ -44,7 +42,7 @@ config BLK_DEV_IO_TRACE
 
 config LSF
 	bool "Support for Large Single Files"
-	depends on X86 || (MIPS && 32BIT) || PPC32 || ARCH_S390_31 || SUPERH || UML
+	depends on !64BIT
 	help
 	  Say Y here if you want to be able to handle very large files (bigger
 	  than 2TB), otherwise say N.
diff --git a/block/blktrace.c b/block/blktrace.c
index 562ca7cbf858..74e02c04b2da 100644
--- a/block/blktrace.c
+++ b/block/blktrace.c
@@ -31,26 +31,24 @@ static unsigned int blktrace_seq __read_mostly = 1;
 /*
  * Send out a notify message.
  */
-static inline unsigned int trace_note(struct blk_trace *bt,
-		pid_t pid, int action,
-		const void *data, size_t len)
+static void trace_note(struct blk_trace *bt, pid_t pid, int action,
+		       const void *data, size_t len)
 {
 	struct blk_io_trace *t;
-	int cpu = smp_processor_id();
 
 	t = relay_reserve(bt->rchan, sizeof(*t) + len);
-	if (t == NULL)
-		return 0;
-
-	t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-	t->time = sched_clock() - per_cpu(blk_trace_cpu_offset, cpu);
-	t->device = bt->dev;
-	t->action = action;
-	t->pid = pid;
-	t->cpu = cpu;
-	t->pdu_len = len;
-	memcpy((void *) t + sizeof(*t), data, len);
-	return blktrace_seq;
+	if (t) {
+		const int cpu = smp_processor_id();
+
+		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+		t->time = sched_clock() - per_cpu(blk_trace_cpu_offset, cpu);
+		t->device = bt->dev;
+		t->action = action;
+		t->pid = pid;
+		t->cpu = cpu;
+		t->pdu_len = len;
+		memcpy((void *) t + sizeof(*t), data, len);
+	}
 }
 
 /*
@@ -59,9 +57,8 @@ static inline unsigned int trace_note(struct blk_trace *bt,
  */
 static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
 {
-	tsk->btrace_seq = trace_note(bt, tsk->pid,
-			BLK_TN_PROCESS,
-			tsk->comm, sizeof(tsk->comm));
+	tsk->btrace_seq = blktrace_seq;
+	trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
 }
 
 static void trace_note_time(struct blk_trace *bt)
diff --git a/drivers/Makefile b/drivers/Makefile
index 4ac14dab3079..67711770b1d9 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -77,3 +77,4 @@ obj-$(CONFIG_CRYPTO)		+= crypto/
 obj-$(CONFIG_SUPERH)		+= sh/
 obj-$(CONFIG_GENERIC_TIME)	+= clocksource/
 obj-$(CONFIG_DMA_ENGINE)	+= dma/
+obj-$(CONFIG_PPC_PS3)		+= ps3/
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 578b99b71d9c..bf5b79ed3613 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/notifier.h>
+#include <linux/jiffies.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 03f6338acc8f..984ab284382a 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -328,6 +328,15 @@ config PATA_TRIFLEX
 
 	  If unsure, say N.
 
+config PATA_MARVELL
+	tristate "Marvell PATA support via legacy mode"
+	depends on PCI
+	help
+	  This option enables limited support for the Marvell 88SE6145 ATA
+	  controller.
+
+	  If unsure, say N.
+
 config PATA_MPIIX
 	tristate "Intel PATA MPIIX support"
 	depends on PCI
@@ -483,6 +492,32 @@ config PATA_WINBOND
 
 	  If unsure, say N.
 
+config PATA_WINBOND_VLB
+	tristate "Winbond W83759A VLB PATA support (Experimental)"
+	depends on ISA && EXPERIMENTAL
+	help
+	  Support for the Winbond W83759A controller on Vesa Local Bus
+	  systems.
+
+config PATA_PLATFORM
+	tristate "Generic platform device PATA support"
+	depends on EMBEDDED
+	help
+	  This option enables support for generic directly connected ATA
+	  devices commonly found on embedded systems.
+
+	  If unsure, say N.
+
+config PATA_IXP4XX_CF
+	tristate "IXP4XX Compact Flash support"
+	depends on ARCH_IXP4XX
+	help
+	  This option enables support for a Compact Flash connected on
+	  the ixp4xx expansion bus. This driver had been written for
+	  Loft/Avila boards in mind but can work with others.
+
+	  If unsure, say N.
+
 endif
 endmenu
 
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 72243a677f9b..bc3d81ae757e 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_PATA_NETCELL)	+= pata_netcell.o
 obj-$(CONFIG_PATA_NS87410)	+= pata_ns87410.o
 obj-$(CONFIG_PATA_OPTI)		+= pata_opti.o
 obj-$(CONFIG_PATA_OPTIDMA)	+= pata_optidma.o
+obj-$(CONFIG_PATA_MARVELL)	+= pata_marvell.o
 obj-$(CONFIG_PATA_MPIIX)	+= pata_mpiix.o
 obj-$(CONFIG_PATA_OLDPIIX)	+= pata_oldpiix.o
 obj-$(CONFIG_PATA_PCMCIA)	+= pata_pcmcia.o
@@ -51,8 +52,11 @@ obj-$(CONFIG_PATA_SERVERWORKS)	+= pata_serverworks.o
 obj-$(CONFIG_PATA_SIL680)	+= pata_sil680.o
 obj-$(CONFIG_PATA_VIA)		+= pata_via.o
 obj-$(CONFIG_PATA_WINBOND)	+= pata_sl82c105.o
+obj-$(CONFIG_PATA_WINBOND_VLB)	+= pata_winbond.o
 obj-$(CONFIG_PATA_SIS)		+= pata_sis.o
 obj-$(CONFIG_PATA_TRIFLEX)	+= pata_triflex.o
+obj-$(CONFIG_PATA_IXP4XX_CF)	+= pata_ixp4xx_cf.o
+obj-$(CONFIG_PATA_PLATFORM)	+= pata_platform.o
 # Should be last but one libata driver
 obj-$(CONFIG_ATA_GENERIC)	+= ata_generic.o
 # Should be last libata driver
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index bddb14e91d3c..f36da488a2c1 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -53,6 +53,7 @@
 
 enum {
 	AHCI_PCI_BAR		= 5,
+	AHCI_MAX_PORTS		= 32,
 	AHCI_MAX_SG		= 168, /* hardware max is 64K */
 	AHCI_DMA_BOUNDARY	= 0xffffffff,
 	AHCI_USE_CLUSTERING	= 0,
@@ -77,8 +78,9 @@ enum {
 	RX_FIS_UNK		= 0x60, /* offset of Unknown FIS data */
 
 	board_ahci		= 0,
-	board_ahci_vt8251	= 1,
-	board_ahci_ign_iferr	= 2,
+	board_ahci_pi		= 1,
+	board_ahci_vt8251	= 2,
+	board_ahci_ign_iferr	= 3,
 
 	/* global controller registers */
 	HOST_CAP		= 0x00, /* host capabilities */
@@ -167,9 +169,9 @@ enum {
 	AHCI_FLAG_MSI		= (1 << 0),
 
 	/* ap->flags bits */
-	AHCI_FLAG_RESET_NEEDS_CLO	= (1 << 24),
-	AHCI_FLAG_NO_NCQ		= (1 << 25),
-	AHCI_FLAG_IGN_IRQ_IF_ERR	= (1 << 26), /* ignore IRQ_IF_ERR */
+	AHCI_FLAG_NO_NCQ		= (1 << 24),
+	AHCI_FLAG_IGN_IRQ_IF_ERR	= (1 << 25), /* ignore IRQ_IF_ERR */
+	AHCI_FLAG_HONOR_PI		= (1 << 26), /* honor PORTS_IMPL */
 };
 
 struct ahci_cmd_hdr {
@@ -216,6 +218,7 @@ static u8 ahci_check_status(struct ata_port *ap);
 static void ahci_freeze(struct ata_port *ap);
 static void ahci_thaw(struct ata_port *ap);
 static void ahci_error_handler(struct ata_port *ap);
+static void ahci_vt8251_error_handler(struct ata_port *ap);
 static void ahci_post_internal_cmd(struct ata_queued_cmd *qc);
 static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg);
 static int ahci_port_resume(struct ata_port *ap);
@@ -275,6 +278,37 @@ static const struct ata_port_operations ahci_ops = {
 	.port_stop		= ahci_port_stop,
 };
 
+static const struct ata_port_operations ahci_vt8251_ops = {
+	.port_disable		= ata_port_disable,
+
+	.check_status		= ahci_check_status,
+	.check_altstatus	= ahci_check_status,
+	.dev_select		= ata_noop_dev_select,
+
+	.tf_read		= ahci_tf_read,
+
+	.qc_prep		= ahci_qc_prep,
+	.qc_issue		= ahci_qc_issue,
+
+	.irq_handler		= ahci_interrupt,
+	.irq_clear		= ahci_irq_clear,
+
+	.scr_read		= ahci_scr_read,
+	.scr_write		= ahci_scr_write,
+
+	.freeze			= ahci_freeze,
+	.thaw			= ahci_thaw,
+
+	.error_handler		= ahci_vt8251_error_handler,
+	.post_internal_cmd	= ahci_post_internal_cmd,
+
+	.port_suspend		= ahci_port_suspend,
+	.port_resume		= ahci_port_resume,
+
+	.port_start		= ahci_port_start,
+	.port_stop		= ahci_port_stop,
+};
+
 static const struct ata_port_info ahci_port_info[] = {
 	/* board_ahci */
 	{
@@ -286,16 +320,26 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
 		.port_ops	= &ahci_ops,
 	},
+	/* board_ahci_pi */
+	{
+		.sht		= &ahci_sht,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
+				  ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA |
+				  ATA_FLAG_SKIP_D2H_BSY | AHCI_FLAG_HONOR_PI,
+		.pio_mask	= 0x1f, /* pio0-4 */
+		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
+		.port_ops	= &ahci_ops,
+	},
 	/* board_ahci_vt8251 */
 	{
 		.sht		= &ahci_sht,
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
 				  ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA |
 				  ATA_FLAG_SKIP_D2H_BSY |
-				  AHCI_FLAG_RESET_NEEDS_CLO | AHCI_FLAG_NO_NCQ,
+				  ATA_FLAG_HRST_TO_RESUME | AHCI_FLAG_NO_NCQ,
 		.pio_mask	= 0x1f, /* pio0-4 */
 		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
-		.port_ops	= &ahci_ops,
+		.port_ops	= &ahci_vt8251_ops,
 	},
 	/* board_ahci_ign_iferr */
 	{
@@ -322,22 +366,22 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x2682), board_ahci }, /* ESB2 */
 	{ PCI_VDEVICE(INTEL, 0x2683), board_ahci }, /* ESB2 */
 	{ PCI_VDEVICE(INTEL, 0x27c6), board_ahci }, /* ICH7-M DH */
-	{ PCI_VDEVICE(INTEL, 0x2821), board_ahci }, /* ICH8 */
-	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* ICH8 */
-	{ PCI_VDEVICE(INTEL, 0x2824), board_ahci }, /* ICH8 */
-	{ PCI_VDEVICE(INTEL, 0x2829), board_ahci }, /* ICH8M */
-	{ PCI_VDEVICE(INTEL, 0x282a), board_ahci }, /* ICH8M */
-	{ PCI_VDEVICE(INTEL, 0x2922), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x2923), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x2924), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x2925), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x2927), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x2929), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292a), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292b), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x292f), board_ahci }, /* ICH9M */
-	{ PCI_VDEVICE(INTEL, 0x294d), board_ahci }, /* ICH9 */
-	{ PCI_VDEVICE(INTEL, 0x294e), board_ahci }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x2821), board_ahci_pi }, /* ICH8 */
+	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci_pi }, /* ICH8 */
+	{ PCI_VDEVICE(INTEL, 0x2824), board_ahci_pi }, /* ICH8 */
+	{ PCI_VDEVICE(INTEL, 0x2829), board_ahci_pi }, /* ICH8M */
+	{ PCI_VDEVICE(INTEL, 0x282a), board_ahci_pi }, /* ICH8M */
+	{ PCI_VDEVICE(INTEL, 0x2922), board_ahci_pi }, /* ICH9 */
+	{ PCI_VDEVICE(INTEL, 0x2923), board_ahci_pi }, /* ICH9 */
+	{ PCI_VDEVICE(INTEL, 0x2924), board_ahci_pi }, /* ICH9 */
+	{ PCI_VDEVICE(INTEL, 0x2925), board_ahci_pi }, /* ICH9 */
+	{ PCI_VDEVICE(INTEL, 0x2927), board_ahci_pi }, /* ICH9 */
+	{ PCI_VDEVICE(INTEL, 0x2929), board_ahci_pi }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292a), board_ahci_pi }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292b), board_ahci_pi }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x292f), board_ahci_pi }, /* ICH9M */
+	{ PCI_VDEVICE(INTEL, 0x294d), board_ahci_pi }, /* ICH9 */
+	{ PCI_VDEVICE(INTEL, 0x294e), board_ahci_pi }, /* ICH9M */
 
 	/* JMicron */
 	{ PCI_VDEVICE(JMICRON, 0x2360), board_ahci_ign_iferr }, /* JMB360 */
@@ -372,6 +416,10 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(SI, 0x1185), board_ahci }, /* SiS 966 */
 	{ PCI_VDEVICE(SI, 0x0186), board_ahci }, /* SiS 968 */
 
+	/* Generic, PCI class code for AHCI */
+	{ PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+	  0x010601, 0xffffff, board_ahci },
+
 	{ }	/* terminate list */
 };
 
@@ -386,6 +434,11 @@ static struct pci_driver ahci_pci_driver = {
 };
 
 
+static inline int ahci_nr_ports(u32 cap)
+{
+	return (cap & 0x1f) + 1;
+}
+
 static inline unsigned long ahci_port_base_ul (unsigned long base, unsigned int port)
 {
 	return base + 0x100 + (port * 0x80);
@@ -559,9 +612,6 @@ static void ahci_power_down(void __iomem *port_mmio, u32 cap)
 static void ahci_init_port(void __iomem *port_mmio, u32 cap,
 			   dma_addr_t cmd_slot_dma, dma_addr_t rx_fis_dma)
 {
-	/* power up */
-	ahci_power_up(port_mmio, cap);
-
 	/* enable FIS reception */
 	ahci_start_fis_rx(port_mmio, cap, cmd_slot_dma, rx_fis_dma);
 
@@ -587,19 +637,17 @@ static int ahci_deinit_port(void __iomem *port_mmio, u32 cap, const char **emsg)
 		return rc;
 	}
 
-	/* put device into slumber mode */
-	ahci_power_down(port_mmio, cap);
-
 	return 0;
 }
 
 static int ahci_reset_controller(void __iomem *mmio, struct pci_dev *pdev)
 {
-	u32 cap_save, tmp;
+	u32 cap_save, impl_save, tmp;
 
 	cap_save = readl(mmio + HOST_CAP);
 	cap_save &= ( (1<<28) | (1<<17) );
 	cap_save |= (1 << 27);
+	impl_save = readl(mmio + HOST_PORTS_IMPL);
 
 	/* global controller reset */
 	tmp = readl(mmio + HOST_CTL);
@@ -620,10 +668,21 @@ static int ahci_reset_controller(void __iomem *mmio, struct pci_dev *pdev)
 		return -EIO;
 	}
 
+	/* turn on AHCI mode */
 	writel(HOST_AHCI_EN, mmio + HOST_CTL);
 	(void) readl(mmio + HOST_CTL);	/* flush */
+
+	/* These write-once registers are normally cleared on reset.
+	 * Restore BIOS values... which we HOPE were present before
+	 * reset.
+	 */
+	if (!impl_save) {
+		impl_save = (1 << ahci_nr_ports(cap_save)) - 1;
+		dev_printk(KERN_WARNING, &pdev->dev,
+			   "PORTS_IMPL is zero, forcing 0x%x\n", impl_save);
+	}
 	writel(cap_save, mmio + HOST_CAP);
-	writel(0xf, mmio + HOST_PORTS_IMPL);
+	writel(impl_save, mmio + HOST_PORTS_IMPL);
 	(void) readl(mmio + HOST_PORTS_IMPL);	/* flush */
 
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
@@ -639,7 +698,8 @@ static int ahci_reset_controller(void __iomem *mmio, struct pci_dev *pdev)
 }
 
 static void ahci_init_controller(void __iomem *mmio, struct pci_dev *pdev,
-				 int n_ports, u32 cap)
+				 int n_ports, unsigned int port_flags,
+				 struct ahci_host_priv *hpriv)
 {
 	int i, rc;
 	u32 tmp;
@@ -648,13 +708,12 @@ static void ahci_init_controller(void __iomem *mmio, struct pci_dev *pdev,
 		void __iomem *port_mmio = ahci_port_base(mmio, i);
 		const char *emsg = NULL;
 
-#if 0 /* BIOSen initialize this incorrectly */
-		if (!(hpriv->port_map & (1 << i)))
+		if ((port_flags & AHCI_FLAG_HONOR_PI) &&
+		    !(hpriv->port_map & (1 << i)))
 			continue;
-#endif
 
 		/* make sure port is not active */
-		rc = ahci_deinit_port(port_mmio, cap, &emsg);
+		rc = ahci_deinit_port(port_mmio, hpriv->cap, &emsg);
 		if (rc)
 			dev_printk(KERN_WARNING, &pdev->dev,
 				   "%s (%d)\n", emsg, rc);
@@ -729,17 +788,6 @@ static int ahci_clo(struct ata_port *ap)
 	return 0;
 }
 
-static int ahci_prereset(struct ata_port *ap)
-{
-	if ((ap->flags & AHCI_FLAG_RESET_NEEDS_CLO) &&
-	    (ata_busy_wait(ap, ATA_BUSY, 1000) & ATA_BUSY)) {
-		/* ATA_BUSY hasn't cleared, so send a CLO */
-		ahci_clo(ap);
-	}
-
-	return ata_std_prereset(ap);
-}
-
 static int ahci_softreset(struct ata_port *ap, unsigned int *class)
 {
 	struct ahci_port_priv *pp = ap->private_data;
@@ -877,6 +925,31 @@ static int ahci_hardreset(struct ata_port *ap, unsigned int *class)
 	return rc;
 }
 
+static int ahci_vt8251_hardreset(struct ata_port *ap, unsigned int *class)
+{
+	void __iomem *mmio = ap->host->mmio_base;
+	void __iomem *port_mmio = ahci_port_base(mmio, ap->port_no);
+	int rc;
+
+	DPRINTK("ENTER\n");
+
+	ahci_stop_engine(port_mmio);
+
+	rc = sata_port_hardreset(ap, sata_ehc_deb_timing(&ap->eh_context));
+
+	/* vt8251 needs SError cleared for the port to operate */
+	ahci_scr_write(ap, SCR_ERROR, ahci_scr_read(ap, SCR_ERROR));
+
+	ahci_start_engine(port_mmio);
+
+	DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
+
+	/* vt8251 doesn't clear BSY on signature FIS reception,
+	 * request follow-up softreset.
+	 */
+	return rc ?: -EAGAIN;
+}
+
 static void ahci_postreset(struct ata_port *ap, unsigned int *class)
 {
 	void __iomem *port_mmio = (void __iomem *) ap->ioaddr.cmd_addr;
@@ -1196,7 +1269,23 @@ static void ahci_error_handler(struct ata_port *ap)
 	}
 
 	/* perform recovery */
-	ata_do_eh(ap, ahci_prereset, ahci_softreset, ahci_hardreset,
+	ata_do_eh(ap, ata_std_prereset, ahci_softreset, ahci_hardreset,
+		  ahci_postreset);
+}
+
+static void ahci_vt8251_error_handler(struct ata_port *ap)
+{
+	void __iomem *mmio = ap->host->mmio_base;
+	void __iomem *port_mmio = ahci_port_base(mmio, ap->port_no);
+
+	if (!(ap->pflags & ATA_PFLAG_FROZEN)) {
+		/* restart engine */
+		ahci_stop_engine(port_mmio);
+		ahci_start_engine(port_mmio);
+	}
+
+	/* perform recovery */
+	ata_do_eh(ap, ata_std_prereset, ahci_softreset, ahci_vt8251_hardreset,
 		  ahci_postreset);
 }
 
@@ -1226,7 +1315,9 @@ static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
 	int rc;
 
 	rc = ahci_deinit_port(port_mmio, hpriv->cap, &emsg);
-	if (rc) {
+	if (rc == 0)
+		ahci_power_down(port_mmio, hpriv->cap);
+	else {
 		ata_port_printk(ap, KERN_ERR, "%s (%d)\n", emsg, rc);
 		ahci_init_port(port_mmio, hpriv->cap,
 			       pp->cmd_slot_dma, pp->rx_fis_dma);
@@ -1242,6 +1333,7 @@ static int ahci_port_resume(struct ata_port *ap)
 	void __iomem *mmio = ap->host->mmio_base;
 	void __iomem *port_mmio = ahci_port_base(mmio, ap->port_no);
 
+	ahci_power_up(port_mmio, hpriv->cap);
 	ahci_init_port(port_mmio, hpriv->cap, pp->cmd_slot_dma, pp->rx_fis_dma);
 
 	return 0;
@@ -1281,7 +1373,8 @@ static int ahci_pci_device_resume(struct pci_dev *pdev)
 		if (rc)
 			return rc;
 
-		ahci_init_controller(mmio, pdev, host->n_ports, hpriv->cap);
+		ahci_init_controller(mmio, pdev, host->n_ports,
+				     host->ports[0]->flags, hpriv);
 	}
 
 	ata_host_resume(host);
@@ -1347,6 +1440,9 @@ static int ahci_port_start(struct ata_port *ap)
 
 	ap->private_data = pp;
 
+	/* power up port */
+	ahci_power_up(port_mmio, hpriv->cap);
+
 	/* initialize port */
 	ahci_init_port(port_mmio, hpriv->cap, pp->cmd_slot_dma, pp->rx_fis_dma);
 
@@ -1393,7 +1489,7 @@ static int ahci_host_init(struct ata_probe_ent *probe_ent)
 	struct ahci_host_priv *hpriv = probe_ent->private_data;
 	struct pci_dev *pdev = to_pci_dev(probe_ent->dev);
 	void __iomem *mmio = probe_ent->mmio_base;
-	unsigned int i, using_dac;
+	unsigned int i, cap_n_ports, using_dac;
 	int rc;
 
 	rc = ahci_reset_controller(mmio, pdev);
@@ -1402,10 +1498,34 @@ static int ahci_host_init(struct ata_probe_ent *probe_ent)
 
 	hpriv->cap = readl(mmio + HOST_CAP);
 	hpriv->port_map = readl(mmio + HOST_PORTS_IMPL);
-	probe_ent->n_ports = (hpriv->cap & 0x1f) + 1;
+	cap_n_ports = ahci_nr_ports(hpriv->cap);
 
 	VPRINTK("cap 0x%x  port_map 0x%x  n_ports %d\n",
-		hpriv->cap, hpriv->port_map, probe_ent->n_ports);
+		hpriv->cap, hpriv->port_map, cap_n_ports);
+
+	if (probe_ent->port_flags & AHCI_FLAG_HONOR_PI) {
+		unsigned int n_ports = cap_n_ports;
+		u32 port_map = hpriv->port_map;
+		int max_port = 0;
+
+		for (i = 0; i < AHCI_MAX_PORTS && n_ports; i++) {
+			if (port_map & (1 << i)) {
+				n_ports--;
+				port_map &= ~(1 << i);
+				max_port = i;
+			} else
+				probe_ent->dummy_port_mask |= 1 << i;
+		}
+
+		if (n_ports || port_map)
+			dev_printk(KERN_WARNING, &pdev->dev,
+				   "nr_ports (%u) and implemented port map "
+				   "(0x%x) don't match\n",
+				   cap_n_ports, hpriv->port_map);
+
+		probe_ent->n_ports = max_port + 1;
+	} else
+		probe_ent->n_ports = cap_n_ports;
 
 	using_dac = hpriv->cap & HOST_CAP_64;
 	if (using_dac &&
@@ -1437,7 +1557,8 @@ static int ahci_host_init(struct ata_probe_ent *probe_ent)
 	for (i = 0; i < probe_ent->n_ports; i++)
 		ahci_setup_port(&probe_ent->port[i], (unsigned long) mmio, i);
 
-	ahci_init_controller(mmio, pdev, probe_ent->n_ports, hpriv->cap);
+	ahci_init_controller(mmio, pdev, probe_ent->n_ports,
+			     probe_ent->port_flags, hpriv);
 
 	pci_set_master(pdev);
 
diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c
index 4a80ff9312b8..908751d27e76 100644
--- a/drivers/ata/ata_generic.c
+++ b/drivers/ata/ata_generic.c
@@ -26,7 +26,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "ata_generic"
-#define DRV_VERSION "0.2.6"
+#define DRV_VERSION "0.2.10"
 
 /*
  *	A generic parallel ATA driver using libata
@@ -109,7 +109,6 @@ static struct scsi_host_template generic_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -118,6 +117,8 @@ static struct scsi_host_template generic_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations generic_port_ops = {
@@ -226,12 +227,14 @@ static struct pci_driver ata_generic_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= ata_generic,
 	.probe 		= ata_generic_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init ata_generic_init(void)
 {
-	return pci_module_init(&ata_generic_pci_driver);
+	return pci_register_driver(&ata_generic_pci_driver);
 }
 
 
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 720174d628fa..c7de0bb1591f 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -40,7 +40,7 @@
  * Documentation
  *	Publically available from Intel web site. Errata documentation
  * is also publically available. As an aide to anyone hacking on this
- * driver the list of errata that are relevant is below.going back to
+ * driver the list of errata that are relevant is below, going back to
  * PIIX4. Older device documentation is now a bit tricky to find.
  *
  * The chipsets all follow very much the same design. The orginal Triton
@@ -93,7 +93,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"ata_piix"
-#define DRV_VERSION	"2.00ac6"
+#define DRV_VERSION	"2.00ac7"
 
 enum {
 	PIIX_IOCFG		= 0x54, /* IDE I/O configuration register */
@@ -101,11 +101,13 @@ enum {
 	ICH5_PCS		= 0x92,	/* port control and status */
 	PIIX_SCC		= 0x0A, /* sub-class code register */
 
-	PIIX_FLAG_IGNORE_PCS	= (1 << 25), /* ignore PCS present bits */
 	PIIX_FLAG_SCR		= (1 << 26), /* SCR available */
 	PIIX_FLAG_AHCI		= (1 << 27), /* AHCI possible */
 	PIIX_FLAG_CHECKINTR	= (1 << 28), /* make sure PCI INTx enabled */
 
+	PIIX_PATA_FLAGS		= ATA_FLAG_SLAVE_POSS,
+	PIIX_SATA_FLAGS		= ATA_FLAG_SATA | PIIX_FLAG_CHECKINTR,
+
 	/* combined mode.  if set, PATA is channel 0.
 	 * if clear, PATA is channel 1.
 	 */
@@ -122,11 +124,10 @@ enum {
 	ich_pata_100		= 3,	/* ICH up to UDMA 100 */
 	ich_pata_133		= 4,	/* ICH up to UDMA 133 */
 	ich5_sata		= 5,
-	esb_sata		= 6,
-	ich6_sata		= 7,
-	ich6_sata_ahci		= 8,
-	ich6m_sata_ahci		= 9,
-	ich8_sata_ahci		= 10,
+	ich6_sata		= 6,
+	ich6_sata_ahci		= 7,
+	ich6m_sata_ahci		= 8,
+	ich8_sata_ahci		= 9,
 
 	/* constants for mapping table */
 	P0			= 0,  /* port 0 */
@@ -143,13 +144,11 @@ enum {
 struct piix_map_db {
 	const u32 mask;
 	const u16 port_enable;
-	const int present_shift;
 	const int map[][4];
 };
 
 struct piix_host_priv {
 	const int *map;
-	const struct piix_map_db *map_db;
 };
 
 static int piix_init_one (struct pci_dev *pdev,
@@ -214,9 +213,9 @@ static const struct pci_device_id piix_pci_tbl[] = {
 	/* 82801EB (ICH5) */
 	{ 0x8086, 0x24df, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich5_sata },
 	/* 6300ESB (ICH5 variant with broken PCS present bits) */
-	{ 0x8086, 0x25a3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, esb_sata },
+	{ 0x8086, 0x25a3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich5_sata },
 	/* 6300ESB pretending RAID */
-	{ 0x8086, 0x25b0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, esb_sata },
+	{ 0x8086, 0x25b0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich5_sata },
 	/* 82801FB/FW (ICH6/ICH6W) */
 	{ 0x8086, 0x2651, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich6_sata },
 	/* 82801FR/FRW (ICH6R/ICH6RW) */
@@ -367,7 +366,6 @@ static const struct ata_port_operations piix_sata_ops = {
 static const struct piix_map_db ich5_map_db = {
 	.mask = 0x7,
 	.port_enable = 0x3,
-	.present_shift = 4,
 	.map = {
 		/* PM   PS   SM   SS       MAP  */
 		{  P0,  NA,  P1,  NA }, /* 000b */
@@ -384,7 +382,6 @@ static const struct piix_map_db ich5_map_db = {
 static const struct piix_map_db ich6_map_db = {
 	.mask = 0x3,
 	.port_enable = 0xf,
-	.present_shift = 4,
 	.map = {
 		/* PM   PS   SM   SS       MAP */
 		{  P0,  P2,  P1,  P3 }, /* 00b */
@@ -397,7 +394,6 @@ static const struct piix_map_db ich6_map_db = {
 static const struct piix_map_db ich6m_map_db = {
 	.mask = 0x3,
 	.port_enable = 0x5,
-	.present_shift = 4,
 
 	/* Map 01b isn't specified in the doc but some notebooks use
 	 * it anyway.  MAP 01b have been spotted on both ICH6M and
@@ -415,7 +411,6 @@ static const struct piix_map_db ich6m_map_db = {
 static const struct piix_map_db ich8_map_db = {
 	.mask = 0x3,
 	.port_enable = 0x3,
-	.present_shift = 8,
 	.map = {
 		/* PM   PS   SM   SS       MAP */
 		{  P0,  P2,  P1,  P3 }, /* 00b (hardwired when in AHCI) */
@@ -427,7 +422,6 @@ static const struct piix_map_db ich8_map_db = {
 
 static const struct piix_map_db *piix_map_db_table[] = {
 	[ich5_sata]		= &ich5_map_db,
-	[esb_sata]		= &ich5_map_db,
 	[ich6_sata]		= &ich6_map_db,
 	[ich6_sata_ahci]	= &ich6_map_db,
 	[ich6m_sata_ahci]	= &ich6m_map_db,
@@ -438,7 +432,7 @@ static struct ata_port_info piix_port_info[] = {
 	/* piix_pata_33: 0:  PIIX3 or 4 at 33MHz */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags		= PIIX_PATA_FLAGS,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x06, /* mwdma1-2 ?? CHECK 0 should be ok but slow */
 		.udma_mask	= ATA_UDMA_MASK_40C,
@@ -448,7 +442,7 @@ static struct ata_port_info piix_port_info[] = {
 	/* ich_pata_33: 1 	ICH0 - ICH at 33Mhz*/
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SRST | ATA_FLAG_SLAVE_POSS,
+		.flags		= PIIX_PATA_FLAGS,
 		.pio_mask 	= 0x1f,	/* pio 0-4 */
 		.mwdma_mask	= 0x06, /* Check: maybe 0x07  */
 		.udma_mask	= ATA_UDMA2, /* UDMA33 */
@@ -457,7 +451,7 @@ static struct ata_port_info piix_port_info[] = {
 	/* ich_pata_66: 2 	ICH controllers up to 66MHz */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SRST | ATA_FLAG_SLAVE_POSS,
+		.flags		= PIIX_PATA_FLAGS,
 		.pio_mask 	= 0x1f,	/* pio 0-4 */
 		.mwdma_mask	= 0x06, /* MWDMA0 is broken on chip */
 		.udma_mask	= ATA_UDMA4,
@@ -467,7 +461,7 @@ static struct ata_port_info piix_port_info[] = {
 	/* ich_pata_100: 3 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SRST | ATA_FLAG_SLAVE_POSS | PIIX_FLAG_CHECKINTR,
+		.flags		= PIIX_PATA_FLAGS | PIIX_FLAG_CHECKINTR,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x06, /* mwdma1-2 */
 		.udma_mask	= ATA_UDMA5, /* udma0-5 */
@@ -477,7 +471,7 @@ static struct ata_port_info piix_port_info[] = {
 	/* ich_pata_133: 4 	ICH with full UDMA6 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SRST | ATA_FLAG_SLAVE_POSS | PIIX_FLAG_CHECKINTR,
+		.flags		= PIIX_PATA_FLAGS | PIIX_FLAG_CHECKINTR,
 		.pio_mask 	= 0x1f,	/* pio 0-4 */
 		.mwdma_mask	= 0x06, /* Check: maybe 0x07  */
 		.udma_mask	= ATA_UDMA6, /* UDMA133 */
@@ -487,41 +481,27 @@ static struct ata_port_info piix_port_info[] = {
 	/* ich5_sata: 5 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SATA | PIIX_FLAG_CHECKINTR |
-				  PIIX_FLAG_IGNORE_PCS,
-		.pio_mask	= 0x1f,	/* pio0-4 */
-		.mwdma_mask	= 0x07, /* mwdma0-2 */
-		.udma_mask	= 0x7f,	/* udma0-6 */
-		.port_ops	= &piix_sata_ops,
-	},
-
-	/* i6300esb_sata: 6 */
-	{
-		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SATA |
-				  PIIX_FLAG_CHECKINTR | PIIX_FLAG_IGNORE_PCS,
+		.flags		= PIIX_SATA_FLAGS,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
 		.udma_mask	= 0x7f,	/* udma0-6 */
 		.port_ops	= &piix_sata_ops,
 	},
 
-	/* ich6_sata: 7 */
+	/* ich6_sata: 6 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SATA |
-				  PIIX_FLAG_CHECKINTR | PIIX_FLAG_SCR,
+		.flags		= PIIX_SATA_FLAGS | PIIX_FLAG_SCR,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
 		.udma_mask	= 0x7f,	/* udma0-6 */
 		.port_ops	= &piix_sata_ops,
 	},
 
-	/* ich6_sata_ahci: 8 */
+	/* ich6_sata_ahci: 7 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SATA |
-				  PIIX_FLAG_CHECKINTR | PIIX_FLAG_SCR |
+		.flags		= PIIX_SATA_FLAGS | PIIX_FLAG_SCR |
 				  PIIX_FLAG_AHCI,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
@@ -529,11 +509,10 @@ static struct ata_port_info piix_port_info[] = {
 		.port_ops	= &piix_sata_ops,
 	},
 
-	/* ich6m_sata_ahci: 9 */
+	/* ich6m_sata_ahci: 8 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SATA |
-				  PIIX_FLAG_CHECKINTR | PIIX_FLAG_SCR |
+		.flags		= PIIX_SATA_FLAGS | PIIX_FLAG_SCR |
 				  PIIX_FLAG_AHCI,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
@@ -541,11 +520,10 @@ static struct ata_port_info piix_port_info[] = {
 		.port_ops	= &piix_sata_ops,
 	},
 
-	/* ich8_sata_ahci: 10 */
+	/* ich8_sata_ahci: 9 */
 	{
 		.sht		= &piix_sht,
-		.flags		= ATA_FLAG_SATA |
-				  PIIX_FLAG_CHECKINTR | PIIX_FLAG_SCR |
+		.flags		= PIIX_SATA_FLAGS | PIIX_FLAG_SCR |
 				  PIIX_FLAG_AHCI,
 		.pio_mask	= 0x1f,	/* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
@@ -566,10 +544,22 @@ MODULE_LICENSE("GPL");
 MODULE_DEVICE_TABLE(pci, piix_pci_tbl);
 MODULE_VERSION(DRV_VERSION);
 
-static int force_pcs = 0;
-module_param(force_pcs, int, 0444);
-MODULE_PARM_DESC(force_pcs, "force honoring or ignoring PCS to work around "
-		 "device mis-detection (0=default, 1=ignore PCS, 2=honor PCS)");
+struct ich_laptop {
+	u16 device;
+	u16 subvendor;
+	u16 subdevice;
+};
+
+/*
+ *	List of laptops that use short cables rather than 80 wire
+ */
+
+static const struct ich_laptop ich_laptop[] = {
+	/* devid, subvendor, subdev */
+	{ 0x27DF, 0x0005, 0x0280 },	/* ICH7 on Acer 5602WLMi */
+	/* end marker */
+	{ 0, }
+};
 
 /**
  *	piix_pata_cbl_detect - Probe host controller cable detect info
@@ -585,12 +575,24 @@ MODULE_PARM_DESC(force_pcs, "force honoring or ignoring PCS to work around "
 static void ich_pata_cbl_detect(struct ata_port *ap)
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	const struct ich_laptop *lap = &ich_laptop[0];
 	u8 tmp, mask;
 
 	/* no 80c support in host controller? */
 	if ((ap->udma_mask & ~ATA_UDMA_MASK_40C) == 0)
 		goto cbl40;
 
+	/* Check for specials - Acer Aspire 5602WLMi */
+	while (lap->device) {
+		if (lap->device == pdev->device &&
+		    lap->subvendor == pdev->subsystem_vendor &&
+		    lap->subdevice == pdev->subsystem_device) {
+			ap->cbl = ATA_CBL_PATA40_SHORT;
+		    	return;
+		}
+		lap++;
+	}
+
 	/* check BIOS cable detect results */
 	mask = ap->port_no == 0 ? PIIX_80C_PRI : PIIX_80C_SEC;
 	pci_read_config_byte(pdev, PIIX_IOCFG, &tmp);
@@ -659,84 +661,9 @@ static void ich_pata_error_handler(struct ata_port *ap)
 			   ata_std_postreset);
 }
 
-/**
- *	piix_sata_present_mask - determine present mask for SATA host controller
- *	@ap: Target port
- *
- *	Reads SATA PCI device's PCI config register Port Configuration
- *	and Status (PCS) to determine port and device availability.
- *
- *	LOCKING:
- *	None (inherited from caller).
- *
- *	RETURNS:
- *	determined present_mask
- */
-static unsigned int piix_sata_present_mask(struct ata_port *ap)
-{
-	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
-	struct piix_host_priv *hpriv = ap->host->private_data;
-	const unsigned int *map = hpriv->map;
-	int base = 2 * ap->port_no;
-	unsigned int present_mask = 0;
-	int port, i;
-	u16 pcs;
-
-	pci_read_config_word(pdev, ICH5_PCS, &pcs);
-	DPRINTK("ata%u: ENTER, pcs=0x%x base=%d\n", ap->id, pcs, base);
-
-	for (i = 0; i < 2; i++) {
-		port = map[base + i];
-		if (port < 0)
-			continue;
-		if ((ap->flags & PIIX_FLAG_IGNORE_PCS) ||
-		    (pcs & 1 << (hpriv->map_db->present_shift + port)))
-			present_mask |= 1 << i;
-	}
-
-	DPRINTK("ata%u: LEAVE, pcs=0x%x present_mask=0x%x\n",
-		ap->id, pcs, present_mask);
-
-	return present_mask;
-}
-
-/**
- *	piix_sata_softreset - reset SATA host port via ATA SRST
- *	@ap: port to reset
- *	@classes: resulting classes of attached devices
- *
- *	Reset SATA host port via ATA SRST.  On controllers with
- *	reliable PCS present bits, the bits are used to determine
- *	device presence.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep)
- *
- *	RETURNS:
- *	0 on success, -errno otherwise.
- */
-static int piix_sata_softreset(struct ata_port *ap, unsigned int *classes)
-{
-	unsigned int present_mask;
-	int i, rc;
-
-	present_mask = piix_sata_present_mask(ap);
-
-	rc = ata_std_softreset(ap, classes);
-	if (rc)
-		return rc;
-
-	for (i = 0; i < ATA_MAX_DEVICES; i++) {
-		if (!(present_mask & (1 << i)))
-			classes[i] = ATA_DEV_NONE;
-	}
-
-	return 0;
-}
-
 static void piix_sata_error_handler(struct ata_port *ap)
 {
-	ata_bmdma_drive_eh(ap, ata_std_prereset, piix_sata_softreset, NULL,
+	ata_bmdma_drive_eh(ap, ata_std_prereset, ata_std_softreset, NULL,
 			   ata_std_postreset);
 }
 
@@ -1051,18 +978,6 @@ static void __devinit piix_init_pcs(struct pci_dev *pdev,
 		pci_write_config_word(pdev, ICH5_PCS, new_pcs);
 		msleep(150);
 	}
-
-	if (force_pcs == 1) {
-		dev_printk(KERN_INFO, &pdev->dev,
-			   "force ignoring PCS (0x%x)\n", new_pcs);
-		pinfo[0].flags |= PIIX_FLAG_IGNORE_PCS;
-		pinfo[1].flags |= PIIX_FLAG_IGNORE_PCS;
-	} else if (force_pcs == 2) {
-		dev_printk(KERN_INFO, &pdev->dev,
-			   "force honoring PCS (0x%x)\n", new_pcs);
-		pinfo[0].flags &= ~PIIX_FLAG_IGNORE_PCS;
-		pinfo[1].flags &= ~PIIX_FLAG_IGNORE_PCS;
-	}
 }
 
 static void __devinit piix_init_sata_map(struct pci_dev *pdev,
@@ -1112,7 +1027,6 @@ static void __devinit piix_init_sata_map(struct pci_dev *pdev,
 			   "invalid MAP value %u\n", map_value);
 
 	hpriv->map = map;
-	hpriv->map_db = map_db;
 }
 
 /**
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index b5f2da6ac80e..8816e30fb7a4 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -199,7 +199,8 @@ static const u8 ata_rw_cmds[] = {
 
 /**
  *	ata_rwcmd_protocol - set taskfile r/w commands and protocol
- *	@qc: command to examine and configure
+ *	@tf: command to examine and configure
+ *	@dev: device tf belongs to
  *
  *	Examine the device configuration and tf->flags to calculate
  *	the proper read/write commands and protocol to use.
@@ -207,10 +208,8 @@ static const u8 ata_rw_cmds[] = {
  *	LOCKING:
  *	caller.
  */
-int ata_rwcmd_protocol(struct ata_queued_cmd *qc)
+static int ata_rwcmd_protocol(struct ata_taskfile *tf, struct ata_device *dev)
 {
-	struct ata_taskfile *tf = &qc->tf;
-	struct ata_device *dev = qc->dev;
 	u8 cmd;
 
 	int index, fua, lba48, write;
@@ -222,7 +221,7 @@ int ata_rwcmd_protocol(struct ata_queued_cmd *qc)
 	if (dev->flags & ATA_DFLAG_PIO) {
 		tf->protocol = ATA_PROT_PIO;
 		index = dev->multi_count ? 0 : 8;
-	} else if (lba48 && (qc->ap->flags & ATA_FLAG_PIO_LBA48)) {
+	} else if (lba48 && (dev->ap->flags & ATA_FLAG_PIO_LBA48)) {
 		/* Unable to use DMA due to host limitation */
 		tf->protocol = ATA_PROT_PIO;
 		index = dev->multi_count ? 0 : 8;
@@ -240,6 +239,174 @@ int ata_rwcmd_protocol(struct ata_queued_cmd *qc)
 }
 
 /**
+ *	ata_tf_read_block - Read block address from ATA taskfile
+ *	@tf: ATA taskfile of interest
+ *	@dev: ATA device @tf belongs to
+ *
+ *	LOCKING:
+ *	None.
+ *
+ *	Read block address from @tf.  This function can handle all
+ *	three address formats - LBA, LBA48 and CHS.  tf->protocol and
+ *	flags select the address format to use.
+ *
+ *	RETURNS:
+ *	Block address read from @tf.
+ */
+u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev)
+{
+	u64 block = 0;
+
+	if (tf->flags & ATA_TFLAG_LBA) {
+		if (tf->flags & ATA_TFLAG_LBA48) {
+			block |= (u64)tf->hob_lbah << 40;
+			block |= (u64)tf->hob_lbam << 32;
+			block |= tf->hob_lbal << 24;
+		} else
+			block |= (tf->device & 0xf) << 24;
+
+		block |= tf->lbah << 16;
+		block |= tf->lbam << 8;
+		block |= tf->lbal;
+	} else {
+		u32 cyl, head, sect;
+
+		cyl = tf->lbam | (tf->lbah << 8);
+		head = tf->device & 0xf;
+		sect = tf->lbal;
+
+		block = (cyl * dev->heads + head) * dev->sectors + sect;
+	}
+
+	return block;
+}
+
+/**
+ *	ata_build_rw_tf - Build ATA taskfile for given read/write request
+ *	@tf: Target ATA taskfile
+ *	@dev: ATA device @tf belongs to
+ *	@block: Block address
+ *	@n_block: Number of blocks
+ *	@tf_flags: RW/FUA etc...
+ *	@tag: tag
+ *
+ *	LOCKING:
+ *	None.
+ *
+ *	Build ATA taskfile @tf for read/write request described by
+ *	@block, @n_block, @tf_flags and @tag on @dev.
+ *
+ *	RETURNS:
+ *
+ *	0 on success, -ERANGE if the request is too large for @dev,
+ *	-EINVAL if the request is invalid.
+ */
+int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
+		    u64 block, u32 n_block, unsigned int tf_flags,
+		    unsigned int tag)
+{
+	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
+	tf->flags |= tf_flags;
+
+	if ((dev->flags & (ATA_DFLAG_PIO | ATA_DFLAG_NCQ_OFF |
+			   ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ &&
+	    likely(tag != ATA_TAG_INTERNAL)) {
+		/* yay, NCQ */
+		if (!lba_48_ok(block, n_block))
+			return -ERANGE;
+
+		tf->protocol = ATA_PROT_NCQ;
+		tf->flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
+
+		if (tf->flags & ATA_TFLAG_WRITE)
+			tf->command = ATA_CMD_FPDMA_WRITE;
+		else
+			tf->command = ATA_CMD_FPDMA_READ;
+
+		tf->nsect = tag << 3;
+		tf->hob_feature = (n_block >> 8) & 0xff;
+		tf->feature = n_block & 0xff;
+
+		tf->hob_lbah = (block >> 40) & 0xff;
+		tf->hob_lbam = (block >> 32) & 0xff;
+		tf->hob_lbal = (block >> 24) & 0xff;
+		tf->lbah = (block >> 16) & 0xff;
+		tf->lbam = (block >> 8) & 0xff;
+		tf->lbal = block & 0xff;
+
+		tf->device = 1 << 6;
+		if (tf->flags & ATA_TFLAG_FUA)
+			tf->device |= 1 << 7;
+	} else if (dev->flags & ATA_DFLAG_LBA) {
+		tf->flags |= ATA_TFLAG_LBA;
+
+		if (lba_28_ok(block, n_block)) {
+			/* use LBA28 */
+			tf->device |= (block >> 24) & 0xf;
+		} else if (lba_48_ok(block, n_block)) {
+			if (!(dev->flags & ATA_DFLAG_LBA48))
+				return -ERANGE;
+
+			/* use LBA48 */
+			tf->flags |= ATA_TFLAG_LBA48;
+
+			tf->hob_nsect = (n_block >> 8) & 0xff;
+
+			tf->hob_lbah = (block >> 40) & 0xff;
+			tf->hob_lbam = (block >> 32) & 0xff;
+			tf->hob_lbal = (block >> 24) & 0xff;
+		} else
+			/* request too large even for LBA48 */
+			return -ERANGE;
+
+		if (unlikely(ata_rwcmd_protocol(tf, dev) < 0))
+			return -EINVAL;
+
+		tf->nsect = n_block & 0xff;
+
+		tf->lbah = (block >> 16) & 0xff;
+		tf->lbam = (block >> 8) & 0xff;
+		tf->lbal = block & 0xff;
+
+		tf->device |= ATA_LBA;
+	} else {
+		/* CHS */
+		u32 sect, head, cyl, track;
+
+		/* The request -may- be too large for CHS addressing. */
+		if (!lba_28_ok(block, n_block))
+			return -ERANGE;
+
+		if (unlikely(ata_rwcmd_protocol(tf, dev) < 0))
+			return -EINVAL;
+
+		/* Convert LBA to CHS */
+		track = (u32)block / dev->sectors;
+		cyl   = track / dev->heads;
+		head  = track % dev->heads;
+		sect  = (u32)block % dev->sectors + 1;
+
+		DPRINTK("block %u track %u cyl %u head %u sect %u\n",
+			(u32)block, track, cyl, head, sect);
+
+		/* Check whether the converted CHS can fit.
+		   Cylinder: 0-65535
+		   Head: 0-15
+		   Sector: 1-255*/
+		if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect))
+			return -ERANGE;
+
+		tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */
+		tf->lbal = sect;
+		tf->lbam = cyl;
+		tf->lbah = cyl >> 8;
+		tf->device |= head;
+	}
+
+	return 0;
+}
+
+/**
  *	ata_pack_xfermask - Pack pio, mwdma and udma masks into xfer_mask
  *	@pio_mask: pio_mask
  *	@mwdma_mask: mwdma_mask
@@ -997,13 +1164,13 @@ void ata_qc_complete_internal(struct ata_queued_cmd *qc)
 }
 
 /**
- *	ata_exec_internal - execute libata internal command
+ *	ata_exec_internal_sg - execute libata internal command
  *	@dev: Device to which the command is sent
  *	@tf: Taskfile registers for the command and the result
  *	@cdb: CDB for packet command
  *	@dma_dir: Data tranfer direction of the command
- *	@buf: Data buffer of the command
- *	@buflen: Length of data buffer
+ *	@sg: sg list for the data buffer of the command
+ *	@n_elem: Number of sg entries
  *
  *	Executes libata internal command with timeout.  @tf contains
  *	command on entry and result on return.  Timeout and error
@@ -1017,9 +1184,10 @@ void ata_qc_complete_internal(struct ata_queued_cmd *qc)
  *	RETURNS:
  *	Zero on success, AC_ERR_* mask on failure
  */
-unsigned ata_exec_internal(struct ata_device *dev,
-			   struct ata_taskfile *tf, const u8 *cdb,
-			   int dma_dir, void *buf, unsigned int buflen)
+unsigned ata_exec_internal_sg(struct ata_device *dev,
+			      struct ata_taskfile *tf, const u8 *cdb,
+			      int dma_dir, struct scatterlist *sg,
+			      unsigned int n_elem)
 {
 	struct ata_port *ap = dev->ap;
 	u8 command = tf->command;
@@ -1075,7 +1243,12 @@ unsigned ata_exec_internal(struct ata_device *dev,
 	qc->flags |= ATA_QCFLAG_RESULT_TF;
 	qc->dma_dir = dma_dir;
 	if (dma_dir != DMA_NONE) {
-		ata_sg_init_one(qc, buf, buflen);
+		unsigned int i, buflen = 0;
+
+		for (i = 0; i < n_elem; i++)
+			buflen += sg[i].length;
+
+		ata_sg_init(qc, sg, n_elem);
 		qc->nsect = buflen / ATA_SECT_SIZE;
 	}
 
@@ -1159,6 +1332,35 @@ unsigned ata_exec_internal(struct ata_device *dev,
 }
 
 /**
+ *	ata_exec_internal_sg - execute libata internal command
+ *	@dev: Device to which the command is sent
+ *	@tf: Taskfile registers for the command and the result
+ *	@cdb: CDB for packet command
+ *	@dma_dir: Data tranfer direction of the command
+ *	@buf: Data buffer of the command
+ *	@buflen: Length of data buffer
+ *
+ *	Wrapper around ata_exec_internal_sg() which takes simple
+ *	buffer instead of sg list.
+ *
+ *	LOCKING:
+ *	None.  Should be called with kernel context, might sleep.
+ *
+ *	RETURNS:
+ *	Zero on success, AC_ERR_* mask on failure
+ */
+unsigned ata_exec_internal(struct ata_device *dev,
+			   struct ata_taskfile *tf, const u8 *cdb,
+			   int dma_dir, void *buf, unsigned int buflen)
+{
+	struct scatterlist sg;
+
+	sg_init_one(&sg, buf, buflen);
+
+	return ata_exec_internal_sg(dev, tf, cdb, dma_dir, &sg, 1);
+}
+
+/**
  *	ata_do_simple_cmd - execute simple internal command
  *	@dev: Device to which the command is sent
  *	@cmd: Opcode to execute
@@ -1222,7 +1424,7 @@ unsigned int ata_pio_need_iordy(const struct ata_device *adev)
  *	ata_dev_read_id - Read ID data from the specified device
  *	@dev: target device
  *	@p_class: pointer to class of the target device (may be changed)
- *	@post_reset: is this read ID post-reset?
+ *	@flags: ATA_READID_* flags
  *	@id: buffer to read IDENTIFY data into
  *
  *	Read ID data from the specified device.  ATA_CMD_ID_ATA is
@@ -1237,7 +1439,7 @@ unsigned int ata_pio_need_iordy(const struct ata_device *adev)
  *	0 on success, -errno otherwise.
  */
 int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
-		    int post_reset, u16 *id)
+		    unsigned int flags, u16 *id)
 {
 	struct ata_port *ap = dev->ap;
 	unsigned int class = *p_class;
@@ -1269,10 +1471,17 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
 	}
 
 	tf.protocol = ATA_PROT_PIO;
+	tf.flags |= ATA_TFLAG_POLLING; /* for polling presence detection */
 
 	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_FROM_DEVICE,
 				     id, sizeof(id[0]) * ATA_ID_WORDS);
 	if (err_mask) {
+		if (err_mask & AC_ERR_NODEV_HINT) {
+			DPRINTK("ata%u.%d: NODEV after polling detection\n",
+				ap->id, dev->devno);
+			return -ENOENT;
+		}
+
 		rc = -EIO;
 		reason = "I/O error";
 		goto err_out;
@@ -1292,7 +1501,7 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
 			goto err_out;
 	}
 
-	if (post_reset && class == ATA_DEV_ATA) {
+	if ((flags & ATA_READID_POSTRESET) && class == ATA_DEV_ATA) {
 		/*
 		 * The exact sequence expected by certain pre-ATA4 drives is:
 		 * SRST RESET
@@ -1312,7 +1521,7 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
 			/* current CHS translation info (id[53-58]) might be
 			 * changed. reread the identify device info.
 			 */
-			post_reset = 0;
+			flags &= ~ATA_READID_POSTRESET;
 			goto retry;
 		}
 	}
@@ -1343,7 +1552,10 @@ static void ata_dev_config_ncq(struct ata_device *dev,
 		desc[0] = '\0';
 		return;
 	}
-
+	if (ata_device_blacklisted(dev) & ATA_HORKAGE_NONCQ) {
+		snprintf(desc, desc_sz, "NCQ (not used)");
+		return;
+	}
 	if (ap->flags & ATA_FLAG_NCQ) {
 		hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE - 1);
 		dev->flags |= ATA_DFLAG_NCQ;
@@ -1372,7 +1584,6 @@ static void ata_set_port_max_cmd_len(struct ata_port *ap)
 /**
  *	ata_dev_configure - Configure the specified ATA/ATAPI device
  *	@dev: Target device to configure
- *	@print_info: Enable device info printout
  *
  *	Configure @dev according to @dev->id.  Generic and low-level
  *	driver specific fixups are also applied.
@@ -1383,9 +1594,10 @@ static void ata_set_port_max_cmd_len(struct ata_port *ap)
  *	RETURNS:
  *	0 on success, -errno otherwise
  */
-int ata_dev_configure(struct ata_device *dev, int print_info)
+int ata_dev_configure(struct ata_device *dev)
 {
 	struct ata_port *ap = dev->ap;
+	int print_info = ap->eh_context.i.flags & ATA_EHI_PRINTINFO;
 	const u16 *id = dev->id;
 	unsigned int xfer_mask;
 	char revbuf[7];		/* XYZ-99\0 */
@@ -1452,6 +1664,10 @@ int ata_dev_configure(struct ata_device *dev, int print_info)
 			if (ata_id_has_lba48(id)) {
 				dev->flags |= ATA_DFLAG_LBA48;
 				lba_desc = "LBA48";
+
+				if (dev->n_sectors >= (1UL << 28) &&
+				    ata_id_has_flush_ext(id))
+					dev->flags |= ATA_DFLAG_FLUSH_EXT;
 			}
 
 			/* config NCQ */
@@ -1528,6 +1744,11 @@ int ata_dev_configure(struct ata_device *dev, int print_info)
 				       cdb_intr_string);
 	}
 
+	/* determine max_sectors */
+	dev->max_sectors = ATA_MAX_SECTORS;
+	if (dev->flags & ATA_DFLAG_LBA48)
+		dev->max_sectors = ATA_MAX_SECTORS_LBA48;
+
 	if (dev->horkage & ATA_HORKAGE_DIAGNOSTIC) {
 		/* Let the user know. We don't want to disallow opens for
 		   rescue purposes, or in case the vendor is just a blithering
@@ -1629,11 +1850,14 @@ int ata_bus_probe(struct ata_port *ap)
 		if (!ata_dev_enabled(dev))
 			continue;
 
-		rc = ata_dev_read_id(dev, &dev->class, 1, dev->id);
+		rc = ata_dev_read_id(dev, &dev->class, ATA_READID_POSTRESET,
+				     dev->id);
 		if (rc)
 			goto fail;
 
-		rc = ata_dev_configure(dev, 1);
+		ap->eh_context.i.flags |= ATA_EHI_PRINTINFO;
+		rc = ata_dev_configure(dev);
+		ap->eh_context.i.flags &= ~ATA_EHI_PRINTINFO;
 		if (rc)
 			goto fail;
 	}
@@ -2151,6 +2375,7 @@ int ata_down_xfermask_limit(struct ata_device *dev, int force_pio0)
 
 static int ata_dev_set_mode(struct ata_device *dev)
 {
+	struct ata_eh_context *ehc = &dev->ap->eh_context;
 	unsigned int err_mask;
 	int rc;
 
@@ -2165,7 +2390,9 @@ static int ata_dev_set_mode(struct ata_device *dev)
 		return -EIO;
 	}
 
+	ehc->i.flags |= ATA_EHI_POST_SETMODE;
 	rc = ata_dev_revalidate(dev, 0);
+	ehc->i.flags &= ~ATA_EHI_POST_SETMODE;
 	if (rc)
 		return rc;
 
@@ -2323,11 +2550,14 @@ static inline void ata_tf_to_host(struct ata_port *ap,
  *	Sleep until ATA Status register bit BSY clears,
  *	or a timeout occurs.
  *
- *	LOCKING: None.
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
  */
-
-unsigned int ata_busy_sleep (struct ata_port *ap,
-			     unsigned long tmout_pat, unsigned long tmout)
+int ata_busy_sleep(struct ata_port *ap,
+		   unsigned long tmout_pat, unsigned long tmout)
 {
 	unsigned long timer_start, timeout;
 	u8 status;
@@ -2335,27 +2565,32 @@ unsigned int ata_busy_sleep (struct ata_port *ap,
 	status = ata_busy_wait(ap, ATA_BUSY, 300);
 	timer_start = jiffies;
 	timeout = timer_start + tmout_pat;
-	while ((status & ATA_BUSY) && (time_before(jiffies, timeout))) {
+	while (status != 0xff && (status & ATA_BUSY) &&
+	       time_before(jiffies, timeout)) {
 		msleep(50);
 		status = ata_busy_wait(ap, ATA_BUSY, 3);
 	}
 
-	if (status & ATA_BUSY)
+	if (status != 0xff && (status & ATA_BUSY))
 		ata_port_printk(ap, KERN_WARNING,
 				"port is slow to respond, please be patient "
 				"(Status 0x%x)\n", status);
 
 	timeout = timer_start + tmout;
-	while ((status & ATA_BUSY) && (time_before(jiffies, timeout))) {
+	while (status != 0xff && (status & ATA_BUSY) &&
+	       time_before(jiffies, timeout)) {
 		msleep(50);
 		status = ata_chk_status(ap);
 	}
 
+	if (status == 0xff)
+		return -ENODEV;
+
 	if (status & ATA_BUSY) {
 		ata_port_printk(ap, KERN_ERR, "port failed to respond "
 				"(%lu secs, Status 0x%x)\n",
 				tmout / HZ, status);
-		return 1;
+		return -EBUSY;
 	}
 
 	return 0;
@@ -2446,10 +2681,8 @@ static unsigned int ata_bus_softreset(struct ata_port *ap,
 	 * the bus shows 0xFF because the odd clown forgets the D7
 	 * pulldown resistor.
 	 */
-	if (ata_check_status(ap) == 0xFF) {
-		ata_port_printk(ap, KERN_ERR, "SRST failed (status 0xFF)\n");
-		return AC_ERR_OTHER;
-	}
+	if (ata_check_status(ap) == 0xFF)
+		return 0;
 
 	ata_bus_post_reset(ap, devmask);
 
@@ -2775,9 +3008,9 @@ int ata_std_softreset(struct ata_port *ap, unsigned int *classes)
 }
 
 /**
- *	sata_std_hardreset - reset host port via SATA phy reset
+ *	sata_port_hardreset - reset port via SATA phy reset
  *	@ap: port to reset
- *	@class: resulting class of attached device
+ *	@timing: timing parameters { interval, duratinon, timeout } in msec
  *
  *	SATA phy-reset host port using DET bits of SControl register.
  *
@@ -2787,10 +3020,8 @@ int ata_std_softreset(struct ata_port *ap, unsigned int *classes)
  *	RETURNS:
  *	0 on success, -errno otherwise.
  */
-int sata_std_hardreset(struct ata_port *ap, unsigned int *class)
+int sata_port_hardreset(struct ata_port *ap, const unsigned long *timing)
 {
-	struct ata_eh_context *ehc = &ap->eh_context;
-	const unsigned long *timing = sata_ehc_deb_timing(ehc);
 	u32 scontrol;
 	int rc;
 
@@ -2803,24 +3034,24 @@ int sata_std_hardreset(struct ata_port *ap, unsigned int *class)
 		 * and Sil3124.
 		 */
 		if ((rc = sata_scr_read(ap, SCR_CONTROL, &scontrol)))
-			return rc;
+			goto out;
 
 		scontrol = (scontrol & 0x0f0) | 0x304;
 
 		if ((rc = sata_scr_write(ap, SCR_CONTROL, scontrol)))
-			return rc;
+			goto out;
 
 		sata_set_spd(ap);
 	}
 
 	/* issue phy wake/reset */
 	if ((rc = sata_scr_read(ap, SCR_CONTROL, &scontrol)))
-		return rc;
+		goto out;
 
 	scontrol = (scontrol & 0x0f0) | 0x301;
 
 	if ((rc = sata_scr_write_flush(ap, SCR_CONTROL, scontrol)))
-		return rc;
+		goto out;
 
 	/* Couldn't find anything in SATA I/II specs, but AHCI-1.1
 	 * 10.4.2 says at least 1 ms.
@@ -2828,7 +3059,40 @@ int sata_std_hardreset(struct ata_port *ap, unsigned int *class)
 	msleep(1);
 
 	/* bring phy back */
-	sata_phy_resume(ap, timing);
+	rc = sata_phy_resume(ap, timing);
+ out:
+	DPRINTK("EXIT, rc=%d\n", rc);
+	return rc;
+}
+
+/**
+ *	sata_std_hardreset - reset host port via SATA phy reset
+ *	@ap: port to reset
+ *	@class: resulting class of attached device
+ *
+ *	SATA phy-reset host port using DET bits of SControl register,
+ *	wait for !BSY and classify the attached device.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep)
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
+ */
+int sata_std_hardreset(struct ata_port *ap, unsigned int *class)
+{
+	const unsigned long *timing = sata_ehc_deb_timing(&ap->eh_context);
+	int rc;
+
+	DPRINTK("ENTER\n");
+
+	/* do hardreset */
+	rc = sata_port_hardreset(ap, timing);
+	if (rc) {
+		ata_port_printk(ap, KERN_ERR,
+				"COMRESET failed (errno=%d)\n", rc);
+		return rc;
+	}
 
 	/* TODO: phy layer with polling, timeouts, etc. */
 	if (ata_port_offline(ap)) {
@@ -2967,7 +3231,7 @@ static int ata_dev_same_device(struct ata_device *dev, unsigned int new_class,
 /**
  *	ata_dev_revalidate - Revalidate ATA device
  *	@dev: device to revalidate
- *	@post_reset: is this revalidation after reset?
+ *	@readid_flags: read ID flags
  *
  *	Re-read IDENTIFY page and make sure @dev is still attached to
  *	the port.
@@ -2978,7 +3242,7 @@ static int ata_dev_same_device(struct ata_device *dev, unsigned int new_class,
  *	RETURNS:
  *	0 on success, negative errno otherwise
  */
-int ata_dev_revalidate(struct ata_device *dev, int post_reset)
+int ata_dev_revalidate(struct ata_device *dev, unsigned int readid_flags)
 {
 	unsigned int class = dev->class;
 	u16 *id = (void *)dev->ap->sector_buf;
@@ -2990,7 +3254,7 @@ int ata_dev_revalidate(struct ata_device *dev, int post_reset)
 	}
 
 	/* read ID data */
-	rc = ata_dev_read_id(dev, &class, post_reset, id);
+	rc = ata_dev_read_id(dev, &class, readid_flags, id);
 	if (rc)
 		goto fail;
 
@@ -3003,7 +3267,7 @@ int ata_dev_revalidate(struct ata_device *dev, int post_reset)
 	memcpy(dev->id, id, sizeof(id[0]) * ATA_ID_WORDS);
 
 	/* configure device according to the new ID */
-	rc = ata_dev_configure(dev, 0);
+	rc = ata_dev_configure(dev);
 	if (rc == 0)
 		return 0;
 
@@ -3012,37 +3276,55 @@ int ata_dev_revalidate(struct ata_device *dev, int post_reset)
 	return rc;
 }
 
-static const char * const ata_dma_blacklist [] = {
-	"WDC AC11000H", NULL,
-	"WDC AC22100H", NULL,
-	"WDC AC32500H", NULL,
-	"WDC AC33100H", NULL,
-	"WDC AC31600H", NULL,
-	"WDC AC32100H", "24.09P07",
-	"WDC AC23200L", "21.10N21",
-	"Compaq CRD-8241B",  NULL,
-	"CRD-8400B", NULL,
-	"CRD-8480B", NULL,
-	"CRD-8482B", NULL,
- 	"CRD-84", NULL,
-	"SanDisk SDP3B", NULL,
-	"SanDisk SDP3B-64", NULL,
-	"SANYO CD-ROM CRD", NULL,
-	"HITACHI CDR-8", NULL,
-	"HITACHI CDR-8335", NULL,
-	"HITACHI CDR-8435", NULL,
-	"Toshiba CD-ROM XM-6202B", NULL,
-	"TOSHIBA CD-ROM XM-1702BC", NULL,
-	"CD-532E-A", NULL,
-	"E-IDE CD-ROM CR-840", NULL,
-	"CD-ROM Drive/F5A", NULL,
-	"WPI CDD-820", NULL,
-	"SAMSUNG CD-ROM SC-148C", NULL,
-	"SAMSUNG CD-ROM SC", NULL,
-	"SanDisk SDP3B-64", NULL,
-	"ATAPI CD-ROM DRIVE 40X MAXIMUM",NULL,
-	"_NEC DV5800A", NULL,
-	"SAMSUNG CD-ROM SN-124", "N001"
+struct ata_blacklist_entry {
+	const char *model_num;
+	const char *model_rev;
+	unsigned long horkage;
+};
+
+static const struct ata_blacklist_entry ata_device_blacklist [] = {
+	/* Devices with DMA related problems under Linux */
+	{ "WDC AC11000H",	NULL,		ATA_HORKAGE_NODMA },
+	{ "WDC AC22100H",	NULL,		ATA_HORKAGE_NODMA },
+	{ "WDC AC32500H",	NULL,		ATA_HORKAGE_NODMA },
+	{ "WDC AC33100H",	NULL,		ATA_HORKAGE_NODMA },
+	{ "WDC AC31600H",	NULL,		ATA_HORKAGE_NODMA },
+	{ "WDC AC32100H",	"24.09P07",	ATA_HORKAGE_NODMA },
+	{ "WDC AC23200L",	"21.10N21",	ATA_HORKAGE_NODMA },
+	{ "Compaq CRD-8241B", 	NULL,		ATA_HORKAGE_NODMA },
+	{ "CRD-8400B",		NULL, 		ATA_HORKAGE_NODMA },
+	{ "CRD-8480B",		NULL,		ATA_HORKAGE_NODMA },
+	{ "CRD-8482B",		NULL,		ATA_HORKAGE_NODMA },
+	{ "CRD-84",		NULL,		ATA_HORKAGE_NODMA },
+	{ "SanDisk SDP3B",	NULL,		ATA_HORKAGE_NODMA },
+	{ "SanDisk SDP3B-64",	NULL,		ATA_HORKAGE_NODMA },
+	{ "SANYO CD-ROM CRD",	NULL,		ATA_HORKAGE_NODMA },
+	{ "HITACHI CDR-8",	NULL,		ATA_HORKAGE_NODMA },
+	{ "HITACHI CDR-8335",	NULL,		ATA_HORKAGE_NODMA },
+	{ "HITACHI CDR-8435",	NULL,		ATA_HORKAGE_NODMA },
+	{ "Toshiba CD-ROM XM-6202B", NULL,	ATA_HORKAGE_NODMA },
+	{ "TOSHIBA CD-ROM XM-1702BC", NULL,	ATA_HORKAGE_NODMA },
+	{ "CD-532E-A", 		NULL,		ATA_HORKAGE_NODMA },
+	{ "E-IDE CD-ROM CR-840",NULL,		ATA_HORKAGE_NODMA },
+	{ "CD-ROM Drive/F5A",	NULL,		ATA_HORKAGE_NODMA },
+	{ "WPI CDD-820", 	NULL,		ATA_HORKAGE_NODMA },
+	{ "SAMSUNG CD-ROM SC-148C", NULL,	ATA_HORKAGE_NODMA },
+	{ "SAMSUNG CD-ROM SC",	NULL,		ATA_HORKAGE_NODMA },
+	{ "SanDisk SDP3B-64", 	NULL,		ATA_HORKAGE_NODMA },
+	{ "ATAPI CD-ROM DRIVE 40X MAXIMUM",NULL,ATA_HORKAGE_NODMA },
+	{ "_NEC DV5800A", 	NULL,		ATA_HORKAGE_NODMA },
+	{ "SAMSUNG CD-ROM SN-124","N001",	ATA_HORKAGE_NODMA },
+
+	/* Devices we expect to fail diagnostics */
+
+	/* Devices where NCQ should be avoided */
+	/* NCQ is slow */
+        { "WDC WD740ADFD-00",   NULL,		ATA_HORKAGE_NONCQ },
+
+	/* Devices with NCQ limits */
+
+	/* End Marker */
+	{ }
 };
 
 static int ata_strim(char *s, size_t len)
@@ -3057,20 +3339,12 @@ static int ata_strim(char *s, size_t len)
 	return len;
 }
 
-static int ata_dma_blacklisted(const struct ata_device *dev)
+unsigned long ata_device_blacklisted(const struct ata_device *dev)
 {
 	unsigned char model_num[40];
 	unsigned char model_rev[16];
 	unsigned int nlen, rlen;
-	int i;
-
-	/* We don't support polling DMA.
-	 * DMA blacklist those ATAPI devices with CDB-intr (and use PIO)
-	 * if the LLDD handles only interrupts in the HSM_ST_LAST state.
-	 */
-	if ((dev->ap->flags & ATA_FLAG_PIO_POLLING) &&
-	    (dev->flags & ATA_DFLAG_CDB_INTR))
-		return 1;
+	const struct ata_blacklist_entry *ad = ata_device_blacklist;
 
 	ata_id_string(dev->id, model_num, ATA_ID_PROD_OFS,
 			  sizeof(model_num));
@@ -3079,17 +3353,30 @@ static int ata_dma_blacklisted(const struct ata_device *dev)
 	nlen = ata_strim(model_num, sizeof(model_num));
 	rlen = ata_strim(model_rev, sizeof(model_rev));
 
-	for (i = 0; i < ARRAY_SIZE(ata_dma_blacklist); i += 2) {
-		if (!strncmp(ata_dma_blacklist[i], model_num, nlen)) {
-			if (ata_dma_blacklist[i+1] == NULL)
-				return 1;
-			if (!strncmp(ata_dma_blacklist[i], model_rev, rlen))
-				return 1;
+	while (ad->model_num) {
+		if (!strncmp(ad->model_num, model_num, nlen)) {
+			if (ad->model_rev == NULL)
+				return ad->horkage;
+			if (!strncmp(ad->model_rev, model_rev, rlen))
+				return ad->horkage;
 		}
+		ad++;
 	}
 	return 0;
 }
 
+static int ata_dma_blacklisted(const struct ata_device *dev)
+{
+	/* We don't support polling DMA.
+	 * DMA blacklist those ATAPI devices with CDB-intr (and use PIO)
+	 * if the LLDD handles only interrupts in the HSM_ST_LAST state.
+	 */
+	if ((dev->ap->flags & ATA_FLAG_PIO_POLLING) &&
+	    (dev->flags & ATA_DFLAG_CDB_INTR))
+		return 1;
+	return (ata_device_blacklisted(dev) & ATA_HORKAGE_NODMA) ? 1 : 0;
+}
+
 /**
  *	ata_dev_xfermask - Compute supported xfermask of the given device
  *	@dev: Device to compute xfermask for
@@ -3117,6 +3404,13 @@ static void ata_dev_xfermask(struct ata_device *dev)
 	 */
 	if (ap->cbl == ATA_CBL_PATA40)
 		xfer_mask &= ~(0xF8 << ATA_SHIFT_UDMA);
+	/* Apply drive side cable rule. Unknown or 80 pin cables reported
+	 * host side are checked drive side as well. Cases where we know a
+	 * 40wire cable is used safely for 80 are not checked here.
+	 */
+        if (ata_drive_40wire(dev->id) && (ap->cbl == ATA_CBL_PATA_UNK || ap->cbl == ATA_CBL_PATA80))
+		xfer_mask &= ~(0xF8 << ATA_SHIFT_UDMA);
+
 
 	xfer_mask &= ata_pack_xfermask(dev->pio_mask,
 				       dev->mwdma_mask, dev->udma_mask);
@@ -3234,8 +3528,7 @@ static unsigned int ata_dev_init_params(struct ata_device *dev,
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-
-static void ata_sg_clean(struct ata_queued_cmd *qc)
+void ata_sg_clean(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct scatterlist *sg = qc->__sg;
@@ -3393,19 +3686,15 @@ void ata_noop_qc_prep(struct ata_queued_cmd *qc) { }
 
 void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, unsigned int buflen)
 {
-	struct scatterlist *sg;
-
 	qc->flags |= ATA_QCFLAG_SINGLE;
 
-	memset(&qc->sgent, 0, sizeof(qc->sgent));
 	qc->__sg = &qc->sgent;
 	qc->n_elem = 1;
 	qc->orig_n_elem = 1;
 	qc->buf_virt = buf;
 	qc->nbytes = buflen;
 
-	sg = qc->__sg;
-	sg_init_one(sg, buf, buflen);
+	sg_init_one(&qc->sgent, buf, buflen);
 }
 
 /**
@@ -4198,8 +4487,12 @@ fsm_start:
 					/* device stops HSM for abort/error */
 					qc->err_mask |= AC_ERR_DEV;
 				else
-					/* HSM violation. Let EH handle this */
-					qc->err_mask |= AC_ERR_HSM;
+					/* HSM violation. Let EH handle this.
+					 * Phantom devices also trigger this
+					 * condition.  Mark hint.
+					 */
+					qc->err_mask |= AC_ERR_HSM |
+							AC_ERR_NODEV_HINT;
 
 				ap->hsm_task_state = HSM_ST_ERR;
 				goto fsm_start;
@@ -4439,6 +4732,14 @@ void __ata_qc_complete(struct ata_queued_cmd *qc)
 	qc->complete_fn(qc);
 }
 
+static void fill_result_tf(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+
+	ap->ops->tf_read(ap, &qc->result_tf);
+	qc->result_tf.flags = qc->tf.flags;
+}
+
 /**
  *	ata_qc_complete - Complete an active ATA command
  *	@qc: Command to complete
@@ -4476,7 +4777,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 		if (unlikely(qc->flags & ATA_QCFLAG_FAILED)) {
 			if (!ata_tag_internal(qc->tag)) {
 				/* always fill result TF for failed qc */
-				ap->ops->tf_read(ap, &qc->result_tf);
+				fill_result_tf(qc);
 				ata_qc_schedule_eh(qc);
 				return;
 			}
@@ -4484,7 +4785,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 
 		/* read result TF if requested */
 		if (qc->flags & ATA_QCFLAG_RESULT_TF)
-			ap->ops->tf_read(ap, &qc->result_tf);
+			fill_result_tf(qc);
 
 		__ata_qc_complete(qc);
 	} else {
@@ -4493,7 +4794,7 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 
 		/* read result TF if failed or requested */
 		if (qc->err_mask || qc->flags & ATA_QCFLAG_RESULT_TF)
-			ap->ops->tf_read(ap, &qc->result_tf);
+			fill_result_tf(qc);
 
 		__ata_qc_complete(qc);
 	}
@@ -4673,6 +4974,14 @@ unsigned int ata_qc_issue_prot(struct ata_queued_cmd *qc)
 		}
 	}
 
+	/* Some controllers show flaky interrupt behavior after
+	 * setting xfer mode.  Use polling instead.
+	 */
+	if (unlikely(qc->tf.command == ATA_CMD_SET_FEATURES &&
+		     qc->tf.feature == SETFEATURES_XFER) &&
+	    (ap->flags & ATA_FLAG_SETXFER_POLLING))
+		qc->tf.flags |= ATA_TFLAG_POLLING;
+
 	/* select the device */
 	ata_dev_select(ap, qc->dev->devno, 1, 0);
 
@@ -4781,6 +5090,7 @@ unsigned int ata_qc_issue_prot(struct ata_queued_cmd *qc)
 inline unsigned int ata_host_intr (struct ata_port *ap,
 				   struct ata_queued_cmd *qc)
 {
+	struct ata_eh_info *ehi = &ap->eh_info;
 	u8 status, host_stat = 0;
 
 	VPRINTK("ata%u: protocol %d task_state %d\n",
@@ -4841,6 +5151,11 @@ inline unsigned int ata_host_intr (struct ata_port *ap,
 	ap->ops->irq_clear(ap);
 
 	ata_hsm_move(ap, qc, status, 0);
+
+	if (unlikely(qc->err_mask) && (qc->tf.protocol == ATA_PROT_DMA ||
+				       qc->tf.protocol == ATA_PROT_ATAPI_DMA))
+		ata_ehi_push_desc(ehi, "BMDMA stat 0x%x", host_stat);
+
 	return 1;	/* irq handled */
 
 idle_irq:
@@ -5047,7 +5362,7 @@ int ata_flush_cache(struct ata_device *dev)
 	if (!ata_try_flush_cache(dev))
 		return 0;
 
-	if (ata_id_has_flush_ext(dev->id))
+	if (dev->flags & ATA_DFLAG_FLUSH_EXT)
 		cmd = ATA_CMD_FLUSH_EXT;
 	else
 		cmd = ATA_CMD_FLUSH;
@@ -5519,9 +5834,8 @@ int ata_device_add(const struct ata_probe_ent *ent)
 				ap->ioaddr.bmdma_addr,
 				irq_line);
 
-		ata_chk_status(ap);
-		host->ops->irq_clear(ap);
-		ata_eh_freeze_port(ap);	/* freeze port before requesting IRQ */
+		/* freeze port before requesting IRQ */
+		ata_eh_freeze_port(ap);
 	}
 
 	/* obtain irq, that may be shared between channels */
@@ -6119,6 +6433,7 @@ EXPORT_SYMBOL_GPL(__sata_phy_reset);
 EXPORT_SYMBOL_GPL(ata_bus_reset);
 EXPORT_SYMBOL_GPL(ata_std_prereset);
 EXPORT_SYMBOL_GPL(ata_std_softreset);
+EXPORT_SYMBOL_GPL(sata_port_hardreset);
 EXPORT_SYMBOL_GPL(sata_std_hardreset);
 EXPORT_SYMBOL_GPL(ata_std_postreset);
 EXPORT_SYMBOL_GPL(ata_dev_classify);
@@ -6145,6 +6460,7 @@ EXPORT_SYMBOL_GPL(ata_host_suspend);
 EXPORT_SYMBOL_GPL(ata_host_resume);
 EXPORT_SYMBOL_GPL(ata_id_string);
 EXPORT_SYMBOL_GPL(ata_id_c_string);
+EXPORT_SYMBOL_GPL(ata_device_blacklisted);
 EXPORT_SYMBOL_GPL(ata_scsi_simulate);
 
 EXPORT_SYMBOL_GPL(ata_pio_need_iordy);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 9f6b7cc74fd9..08ad44b3e48f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1136,19 +1136,21 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 		break;
 
 	case ATA_DEV_ATAPI:
-		tmp = atapi_eh_request_sense(qc->dev,
-					     qc->scsicmd->sense_buffer);
-		if (!tmp) {
-			/* ATA_QCFLAG_SENSE_VALID is used to tell
-			 * atapi_qc_complete() that sense data is
-			 * already valid.
-			 *
-			 * TODO: interpret sense data and set
-			 * appropriate err_mask.
-			 */
-			qc->flags |= ATA_QCFLAG_SENSE_VALID;
-		} else
-			qc->err_mask |= tmp;
+		if (!(qc->ap->pflags & ATA_PFLAG_FROZEN)) {
+			tmp = atapi_eh_request_sense(qc->dev,
+						     qc->scsicmd->sense_buffer);
+			if (!tmp) {
+				/* ATA_QCFLAG_SENSE_VALID is used to
+				 * tell atapi_qc_complete() that sense
+				 * data is already valid.
+				 *
+				 * TODO: interpret sense data and set
+				 * appropriate err_mask.
+				 */
+				qc->flags |= ATA_QCFLAG_SENSE_VALID;
+			} else
+				qc->err_mask |= tmp;
+		}
 	}
 
 	if (qc->err_mask & (AC_ERR_HSM | AC_ERR_TIMEOUT | AC_ERR_ATA_BUS))
@@ -1433,16 +1435,39 @@ static void ata_eh_report(struct ata_port *ap)
 	}
 
 	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
+		static const char *dma_str[] = {
+			[DMA_BIDIRECTIONAL]	= "bidi",
+			[DMA_TO_DEVICE]		= "out",
+			[DMA_FROM_DEVICE]	= "in",
+			[DMA_NONE]		= "",
+		};
 		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
+		struct ata_taskfile *cmd = &qc->tf, *res = &qc->result_tf;
+		unsigned int nbytes;
 
 		if (!(qc->flags & ATA_QCFLAG_FAILED) || !qc->err_mask)
 			continue;
 
-		ata_dev_printk(qc->dev, KERN_ERR, "tag %d cmd 0x%x "
-			       "Emask 0x%x stat 0x%x err 0x%x (%s)\n",
-			       qc->tag, qc->tf.command, qc->err_mask,
-			       qc->result_tf.command, qc->result_tf.feature,
-			       ata_err_string(qc->err_mask));
+		nbytes = qc->nbytes;
+		if (!nbytes)
+			nbytes = qc->nsect << 9;
+
+		ata_dev_printk(qc->dev, KERN_ERR,
+			"cmd %02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x "
+			"tag %d cdb 0x%x data %u %s\n         "
+			"res %02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x "
+			"Emask 0x%x (%s)\n",
+			cmd->command, cmd->feature, cmd->nsect,
+			cmd->lbal, cmd->lbam, cmd->lbah,
+			cmd->hob_feature, cmd->hob_nsect,
+			cmd->hob_lbal, cmd->hob_lbam, cmd->hob_lbah,
+			cmd->device, qc->tag, qc->cdb[0], nbytes,
+			dma_str[qc->dma_dir],
+			res->command, res->feature, res->nsect,
+			res->lbal, res->lbam, res->lbah,
+			res->hob_feature, res->hob_nsect,
+			res->hob_lbal, res->hob_lbam, res->hob_lbah,
+			res->device, qc->err_mask, ata_err_string(qc->err_mask));
 	}
 }
 
@@ -1634,11 +1659,14 @@ static int ata_eh_revalidate_and_attach(struct ata_port *ap,
 	DPRINTK("ENTER\n");
 
 	for (i = 0; i < ATA_MAX_DEVICES; i++) {
-		unsigned int action;
+		unsigned int action, readid_flags = 0;
 
 		dev = &ap->device[i];
 		action = ata_eh_dev_action(dev);
 
+		if (ehc->i.flags & ATA_EHI_DID_RESET)
+			readid_flags |= ATA_READID_POSTRESET;
+
 		if (action & ATA_EH_REVALIDATE && ata_dev_ready(dev)) {
 			if (ata_port_offline(ap)) {
 				rc = -EIO;
@@ -1646,13 +1674,17 @@ static int ata_eh_revalidate_and_attach(struct ata_port *ap,
 			}
 
 			ata_eh_about_to_do(ap, dev, ATA_EH_REVALIDATE);
-			rc = ata_dev_revalidate(dev,
-					ehc->i.flags & ATA_EHI_DID_RESET);
+			rc = ata_dev_revalidate(dev, readid_flags);
 			if (rc)
 				break;
 
 			ata_eh_done(ap, dev, ATA_EH_REVALIDATE);
 
+			/* Configuration may have changed, reconfigure
+			 * transfer mode.
+			 */
+			ehc->i.flags |= ATA_EHI_SETMODE;
+
 			/* schedule the scsi_rescan_device() here */
 			queue_work(ata_aux_wq, &(ap->scsi_rescan_task));
 		} else if (dev->class == ATA_DEV_UNKNOWN &&
@@ -1660,18 +1692,35 @@ static int ata_eh_revalidate_and_attach(struct ata_port *ap,
 			   ata_class_enabled(ehc->classes[dev->devno])) {
 			dev->class = ehc->classes[dev->devno];
 
-			rc = ata_dev_read_id(dev, &dev->class, 1, dev->id);
-			if (rc == 0)
-				rc = ata_dev_configure(dev, 1);
+			rc = ata_dev_read_id(dev, &dev->class, readid_flags,
+					     dev->id);
+			if (rc == 0) {
+				ehc->i.flags |= ATA_EHI_PRINTINFO;
+				rc = ata_dev_configure(dev);
+				ehc->i.flags &= ~ATA_EHI_PRINTINFO;
+			} else if (rc == -ENOENT) {
+				/* IDENTIFY was issued to non-existent
+				 * device.  No need to reset.  Just
+				 * thaw and kill the device.
+				 */
+				ata_eh_thaw_port(ap);
+				dev->class = ATA_DEV_UNKNOWN;
+				rc = 0;
+			}
 
 			if (rc) {
 				dev->class = ATA_DEV_UNKNOWN;
 				break;
 			}
 
-			spin_lock_irqsave(ap->lock, flags);
-			ap->pflags |= ATA_PFLAG_SCSI_HOTPLUG;
-			spin_unlock_irqrestore(ap->lock, flags);
+			if (ata_dev_enabled(dev)) {
+				spin_lock_irqsave(ap->lock, flags);
+				ap->pflags |= ATA_PFLAG_SCSI_HOTPLUG;
+				spin_unlock_irqrestore(ap->lock, flags);
+
+				/* new device discovered, configure xfermode */
+				ehc->i.flags |= ATA_EHI_SETMODE;
+			}
 		}
 	}
 
@@ -1987,13 +2036,14 @@ static int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 	if (rc)
 		goto dev_fail;
 
-	/* configure transfer mode if the port has been reset */
-	if (ehc->i.flags & ATA_EHI_DID_RESET) {
+	/* configure transfer mode if necessary */
+	if (ehc->i.flags & ATA_EHI_SETMODE) {
 		rc = ata_set_mode(ap, &dev);
 		if (rc) {
 			down_xfermask = 1;
 			goto dev_fail;
 		}
+		ehc->i.flags &= ~ATA_EHI_SETMODE;
 	}
 
 	/* suspend devices */
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 4c32d93d44b1..664e1377b54c 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -671,7 +671,7 @@ void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk, u8 *asc,
 }
 
 /*
- *	ata_gen_ata_desc_sense - Generate check condition sense block.
+ *	ata_gen_passthru_sense - Generate check condition sense block.
  *	@qc: Command that completed.
  *
  *	This function is specific to the ATA descriptor format sense
@@ -681,9 +681,9 @@ void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk, u8 *asc,
  *	block. Clear sense key, ASC & ASCQ if there is no error.
  *
  *	LOCKING:
- *	spin_lock_irqsave(host lock)
+ *	None.
  */
-void ata_gen_ata_desc_sense(struct ata_queued_cmd *qc)
+static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *cmd = qc->scsicmd;
 	struct ata_taskfile *tf = &qc->result_tf;
@@ -713,12 +713,9 @@ void ata_gen_ata_desc_sense(struct ata_queued_cmd *qc)
 
 	desc[0] = 0x09;
 
-	/*
-	 * Set length of additional sense data.
-	 * Since we only populate descriptor 0, the total
-	 * length is the same (fixed) length as descriptor 0.
-	 */
-	desc[1] = sb[7] = 14;
+	/* set length of additional sense data */
+	sb[7] = 14;
+	desc[1] = 12;
 
 	/*
 	 * Copy registers into sense buffer.
@@ -746,56 +743,56 @@ void ata_gen_ata_desc_sense(struct ata_queued_cmd *qc)
 }
 
 /**
- *	ata_gen_fixed_sense - generate a SCSI fixed sense block
+ *	ata_gen_ata_sense - generate a SCSI fixed sense block
  *	@qc: Command that we are erroring out
  *
- *	Leverage ata_to_sense_error() to give us the codes.  Fit our
- *	LBA in here if there's room.
+ *	Generate sense block for a failed ATA command @qc.  Descriptor
+ *	format is used to accomodate LBA48 block address.
  *
  *	LOCKING:
- *	inherited from caller
+ *	None.
  */
-void ata_gen_fixed_sense(struct ata_queued_cmd *qc)
+static void ata_gen_ata_sense(struct ata_queued_cmd *qc)
 {
+	struct ata_device *dev = qc->dev;
 	struct scsi_cmnd *cmd = qc->scsicmd;
 	struct ata_taskfile *tf = &qc->result_tf;
 	unsigned char *sb = cmd->sense_buffer;
+	unsigned char *desc = sb + 8;
 	int verbose = qc->ap->ops->error_handler == NULL;
+	u64 block;
 
 	memset(sb, 0, SCSI_SENSE_BUFFERSIZE);
 
 	cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION;
 
-	/*
-	 * Use ata_to_sense_error() to map status register bits
+	/* sense data is current and format is descriptor */
+	sb[0] = 0x72;
+
+	/* Use ata_to_sense_error() to map status register bits
 	 * onto sense key, asc & ascq.
 	 */
 	if (qc->err_mask ||
 	    tf->command & (ATA_BUSY | ATA_DF | ATA_ERR | ATA_DRQ)) {
 		ata_to_sense_error(qc->ap->id, tf->command, tf->feature,
-				   &sb[2], &sb[12], &sb[13], verbose);
-		sb[2] &= 0x0f;
+				   &sb[1], &sb[2], &sb[3], verbose);
+		sb[1] &= 0x0f;
 	}
 
-	sb[0] = 0x70;
-	sb[7] = 0x0a;
-
-	if (tf->flags & ATA_TFLAG_LBA48) {
-		/* TODO: find solution for LBA48 descriptors */
-	}
+	block = ata_tf_read_block(&qc->result_tf, dev);
 
-	else if (tf->flags & ATA_TFLAG_LBA) {
-		/* A small (28b) LBA will fit in the 32b info field */
-		sb[0] |= 0x80;		/* set valid bit */
-		sb[3] = tf->device & 0x0f;
-		sb[4] = tf->lbah;
-		sb[5] = tf->lbam;
-		sb[6] = tf->lbal;
-	}
+	/* information sense data descriptor */
+	sb[7] = 12;
+	desc[0] = 0x00;
+	desc[1] = 10;
 
-	else {
-		/* TODO: C/H/S */
-	}
+	desc[2] |= 0x80;	/* valid */
+	desc[6] = block >> 40;
+	desc[7] = block >> 32;
+	desc[8] = block >> 24;
+	desc[9] = block >> 16;
+	desc[10] = block >> 8;
+	desc[11] = block;
 }
 
 static void ata_scsi_sdev_config(struct scsi_device *sdev)
@@ -807,23 +804,10 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
 static void ata_scsi_dev_config(struct scsi_device *sdev,
 				struct ata_device *dev)
 {
-	unsigned int max_sectors;
-
-	/* TODO: 2048 is an arbitrary number, not the
-	 * hardware maximum.  This should be increased to
-	 * 65534 when Jens Axboe's patch for dynamically
-	 * determining max_sectors is merged.
-	 */
-	max_sectors = ATA_MAX_SECTORS;
-	if (dev->flags & ATA_DFLAG_LBA48)
-		max_sectors = ATA_MAX_SECTORS_LBA48;
-	if (dev->max_sectors)
-		max_sectors = dev->max_sectors;
+	/* configure max sectors */
+	blk_queue_max_sectors(sdev->request_queue, dev->max_sectors);
 
-	blk_queue_max_sectors(sdev->request_queue, max_sectors);
-
-	/*
-	 * SATA DMA transfers must be multiples of 4 byte, so
+	/* SATA DMA transfers must be multiples of 4 byte, so
 	 * we need to pad ATAPI transfers using an extra sg.
 	 * Decrement max hw segments accordingly.
 	 */
@@ -1040,8 +1024,7 @@ static unsigned int ata_scsi_flush_xlat(struct ata_queued_cmd *qc, const u8 *scs
 	tf->flags |= ATA_TFLAG_DEVICE;
 	tf->protocol = ATA_PROT_NODATA;
 
-	if ((qc->dev->flags & ATA_DFLAG_LBA48) &&
-	    (ata_id_has_flush_ext(qc->dev->id)))
+	if (qc->dev->flags & ATA_DFLAG_FLUSH_EXT)
 		tf->command = ATA_CMD_FLUSH_EXT;
 	else
 		tf->command = ATA_CMD_FLUSH;
@@ -1282,17 +1265,14 @@ nothing_to_do:
 
 static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc, const u8 *scsicmd)
 {
-	struct ata_taskfile *tf = &qc->tf;
-	struct ata_device *dev = qc->dev;
+	unsigned int tf_flags = 0;
 	u64 block;
 	u32 n_block;
-
-	qc->flags |= ATA_QCFLAG_IO;
-	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
+	int rc;
 
 	if (scsicmd[0] == WRITE_10 || scsicmd[0] == WRITE_6 ||
 	    scsicmd[0] == WRITE_16)
-		tf->flags |= ATA_TFLAG_WRITE;
+		tf_flags |= ATA_TFLAG_WRITE;
 
 	/* Calculate the SCSI LBA, transfer length and FUA. */
 	switch (scsicmd[0]) {
@@ -1300,7 +1280,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc, const u8 *scsicm
 	case WRITE_10:
 		scsi_10_lba_len(scsicmd, &block, &n_block);
 		if (unlikely(scsicmd[1] & (1 << 3)))
-			tf->flags |= ATA_TFLAG_FUA;
+			tf_flags |= ATA_TFLAG_FUA;
 		break;
 	case READ_6:
 	case WRITE_6:
@@ -1316,7 +1296,7 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc, const u8 *scsicm
 	case WRITE_16:
 		scsi_16_lba_len(scsicmd, &block, &n_block);
 		if (unlikely(scsicmd[1] & (1 << 3)))
-			tf->flags |= ATA_TFLAG_FUA;
+			tf_flags |= ATA_TFLAG_FUA;
 		break;
 	default:
 		DPRINTK("no-byte command\n");
@@ -1334,106 +1314,17 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc, const u8 *scsicm
 		 */
 		goto nothing_to_do;
 
-	if ((dev->flags & (ATA_DFLAG_PIO | ATA_DFLAG_NCQ_OFF |
-			   ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ) {
-		/* yay, NCQ */
-		if (!lba_48_ok(block, n_block))
-			goto out_of_range;
-
-		tf->protocol = ATA_PROT_NCQ;
-		tf->flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
-
-		if (tf->flags & ATA_TFLAG_WRITE)
-			tf->command = ATA_CMD_FPDMA_WRITE;
-		else
-			tf->command = ATA_CMD_FPDMA_READ;
-
-		qc->nsect = n_block;
-
-		tf->nsect = qc->tag << 3;
-		tf->hob_feature = (n_block >> 8) & 0xff;
-		tf->feature = n_block & 0xff;
-
-		tf->hob_lbah = (block >> 40) & 0xff;
-		tf->hob_lbam = (block >> 32) & 0xff;
-		tf->hob_lbal = (block >> 24) & 0xff;
-		tf->lbah = (block >> 16) & 0xff;
-		tf->lbam = (block >> 8) & 0xff;
-		tf->lbal = block & 0xff;
-
-		tf->device = 1 << 6;
-		if (tf->flags & ATA_TFLAG_FUA)
-			tf->device |= 1 << 7;
-	} else if (dev->flags & ATA_DFLAG_LBA) {
-		tf->flags |= ATA_TFLAG_LBA;
-
-		if (lba_28_ok(block, n_block)) {
-			/* use LBA28 */
-			tf->device |= (block >> 24) & 0xf;
-		} else if (lba_48_ok(block, n_block)) {
-			if (!(dev->flags & ATA_DFLAG_LBA48))
-				goto out_of_range;
-
-			/* use LBA48 */
-			tf->flags |= ATA_TFLAG_LBA48;
-
-			tf->hob_nsect = (n_block >> 8) & 0xff;
-
-			tf->hob_lbah = (block >> 40) & 0xff;
-			tf->hob_lbam = (block >> 32) & 0xff;
-			tf->hob_lbal = (block >> 24) & 0xff;
-		} else
-			/* request too large even for LBA48 */
-			goto out_of_range;
-
-		if (unlikely(ata_rwcmd_protocol(qc) < 0))
-			goto invalid_fld;
-
-		qc->nsect = n_block;
-		tf->nsect = n_block & 0xff;
-
-		tf->lbah = (block >> 16) & 0xff;
-		tf->lbam = (block >> 8) & 0xff;
-		tf->lbal = block & 0xff;
-
-		tf->device |= ATA_LBA;
-	} else {
-		/* CHS */
-		u32 sect, head, cyl, track;
-
-		/* The request -may- be too large for CHS addressing. */
-		if (!lba_28_ok(block, n_block))
-			goto out_of_range;
-
-		if (unlikely(ata_rwcmd_protocol(qc) < 0))
-			goto invalid_fld;
-
-		/* Convert LBA to CHS */
-		track = (u32)block / dev->sectors;
-		cyl   = track / dev->heads;
-		head  = track % dev->heads;
-		sect  = (u32)block % dev->sectors + 1;
-
-		DPRINTK("block %u track %u cyl %u head %u sect %u\n",
-			(u32)block, track, cyl, head, sect);
-
-		/* Check whether the converted CHS can fit.
-		   Cylinder: 0-65535
-		   Head: 0-15
-		   Sector: 1-255*/
-		if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect))
-			goto out_of_range;
-
-		qc->nsect = n_block;
-		tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */
-		tf->lbal = sect;
-		tf->lbam = cyl;
-		tf->lbah = cyl >> 8;
-		tf->device |= head;
-	}
+	qc->flags |= ATA_QCFLAG_IO;
+	qc->nsect = n_block;
 
-	return 0;
+	rc = ata_build_rw_tf(&qc->tf, qc->dev, block, n_block, tf_flags,
+			     qc->tag);
+	if (likely(rc == 0))
+		return 0;
 
+	if (rc == -ERANGE)
+		goto out_of_range;
+	/* treat all other errors as -EINVAL, fall through */
 invalid_fld:
 	ata_scsi_set_sense(qc->scsicmd, ILLEGAL_REQUEST, 0x24, 0x0);
 	/* "Invalid field in cbd" */
@@ -1477,7 +1368,7 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
 	 */
 	if (((cdb[0] == ATA_16) || (cdb[0] == ATA_12)) &&
  	    ((cdb[2] & 0x20) || need_sense)) {
- 		ata_gen_ata_desc_sense(qc);
+		ata_gen_passthru_sense(qc);
 	} else {
 		if (!need_sense) {
 			cmd->result = SAM_STAT_GOOD;
@@ -1488,7 +1379,7 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
 			 * good for smaller LBA (and maybe CHS?)
 			 * devices.
 			 */
-			ata_gen_fixed_sense(qc);
+			ata_gen_ata_sense(qc);
 		}
 	}
 
@@ -1715,6 +1606,22 @@ void ata_scsi_rbuf_fill(struct ata_scsi_args *args,
 }
 
 /**
+ *	ATA_SCSI_RBUF_SET - helper to set values in SCSI response buffer
+ *	@idx: byte index into SCSI response buffer
+ *	@val: value to set
+ *
+ *	To be used by SCSI command simulator functions.  This macros
+ *	expects two local variables, u8 *rbuf and unsigned int buflen,
+ *	are in scope.
+ *
+ *	LOCKING:
+ *	None.
+ */
+#define ATA_SCSI_RBUF_SET(idx, val) do { \
+		if ((idx) < buflen) rbuf[(idx)] = (u8)(val); \
+	} while (0)
+
+/**
  *	ata_scsiop_inq_std - Simulate INQUIRY command
  *	@args: device IDENTIFY data / SCSI command of interest.
  *	@rbuf: Response buffer, to which simulated SCSI cmd output is sent.
@@ -2173,67 +2080,42 @@ saving_not_supp:
  *	Simulate READ CAPACITY commands.
  *
  *	LOCKING:
- *	spin_lock_irqsave(host lock)
+ *	None.
  */
-
 unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf,
 			        unsigned int buflen)
 {
-	u64 n_sectors;
-	u32 tmp;
+	u64 last_lba = args->dev->n_sectors - 1; /* LBA of the last block */
 
 	VPRINTK("ENTER\n");
 
-	if (ata_id_has_lba(args->id)) {
-		if (ata_id_has_lba48(args->id))
-			n_sectors = ata_id_u64(args->id, 100);
-		else
-			n_sectors = ata_id_u32(args->id, 60);
-	} else {
-		/* CHS default translation */
-		n_sectors = args->id[1] * args->id[3] * args->id[6];
-
-		if (ata_id_current_chs_valid(args->id))
-			/* CHS current translation */
-			n_sectors = ata_id_u32(args->id, 57);
-	}
-
-	n_sectors--;		/* ATA TotalUserSectors - 1 */
-
 	if (args->cmd->cmnd[0] == READ_CAPACITY) {
-		if( n_sectors >= 0xffffffffULL )
-			tmp = 0xffffffff ;  /* Return max count on overflow */
-		else
-			tmp = n_sectors ;
+		if (last_lba >= 0xffffffffULL)
+			last_lba = 0xffffffff;
 
 		/* sector count, 32-bit */
-		rbuf[0] = tmp >> (8 * 3);
-		rbuf[1] = tmp >> (8 * 2);
-		rbuf[2] = tmp >> (8 * 1);
-		rbuf[3] = tmp;
+		ATA_SCSI_RBUF_SET(0, last_lba >> (8 * 3));
+		ATA_SCSI_RBUF_SET(1, last_lba >> (8 * 2));
+		ATA_SCSI_RBUF_SET(2, last_lba >> (8 * 1));
+		ATA_SCSI_RBUF_SET(3, last_lba);
 
 		/* sector size */
-		tmp = ATA_SECT_SIZE;
-		rbuf[6] = tmp >> 8;
-		rbuf[7] = tmp;
-
+		ATA_SCSI_RBUF_SET(6, ATA_SECT_SIZE >> 8);
+		ATA_SCSI_RBUF_SET(7, ATA_SECT_SIZE);
 	} else {
 		/* sector count, 64-bit */
-		tmp = n_sectors >> (8 * 4);
-		rbuf[2] = tmp >> (8 * 3);
-		rbuf[3] = tmp >> (8 * 2);
-		rbuf[4] = tmp >> (8 * 1);
-		rbuf[5] = tmp;
-		tmp = n_sectors;
-		rbuf[6] = tmp >> (8 * 3);
-		rbuf[7] = tmp >> (8 * 2);
-		rbuf[8] = tmp >> (8 * 1);
-		rbuf[9] = tmp;
+		ATA_SCSI_RBUF_SET(0, last_lba >> (8 * 7));
+		ATA_SCSI_RBUF_SET(1, last_lba >> (8 * 6));
+		ATA_SCSI_RBUF_SET(2, last_lba >> (8 * 5));
+		ATA_SCSI_RBUF_SET(3, last_lba >> (8 * 4));
+		ATA_SCSI_RBUF_SET(4, last_lba >> (8 * 3));
+		ATA_SCSI_RBUF_SET(5, last_lba >> (8 * 2));
+		ATA_SCSI_RBUF_SET(6, last_lba >> (8 * 1));
+		ATA_SCSI_RBUF_SET(7, last_lba);
 
 		/* sector size */
-		tmp = ATA_SECT_SIZE;
-		rbuf[12] = tmp >> 8;
-		rbuf[13] = tmp;
+		ATA_SCSI_RBUF_SET(10, ATA_SECT_SIZE >> 8);
+		ATA_SCSI_RBUF_SET(11, ATA_SECT_SIZE);
 	}
 
 	return 0;
@@ -2319,7 +2201,7 @@ static void atapi_sense_complete(struct ata_queued_cmd *qc)
 		 * a sense descriptors, since that's only
 		 * correct for ATA, not ATAPI
 		 */
-		ata_gen_ata_desc_sense(qc);
+		ata_gen_passthru_sense(qc);
 	}
 
 	qc->scsidone(qc->scsicmd);
@@ -2394,7 +2276,7 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
 			 * sense descriptors, since that's only
 			 * correct for ATA, not ATAPI
 			 */
-			ata_gen_ata_desc_sense(qc);
+			ata_gen_passthru_sense(qc);
 		}
 
 		/* SCSI EH automatically locks door if sdev->locked is
@@ -2427,7 +2309,7 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
 		 * a sense descriptors, since that's only
 		 * correct for ATA, not ATAPI
 		 */
-		ata_gen_ata_desc_sense(qc);
+		ata_gen_passthru_sense(qc);
 	} else {
 		u8 *scsicmd = cmd->cmnd;
 
@@ -3183,10 +3065,12 @@ static int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
 			rc = -EINVAL;
 	}
 
-	if (rc == 0)
+	if (rc == 0) {
 		ata_port_schedule_eh(ap);
-
-	spin_unlock_irqrestore(ap->lock, flags);
+		spin_unlock_irqrestore(ap->lock, flags);
+		ata_port_wait_eh(ap);
+	} else
+		spin_unlock_irqrestore(ap->lock, flags);
 
 	return rc;
 }
@@ -3207,15 +3091,27 @@ void ata_scsi_dev_rescan(struct work_struct *work)
 {
 	struct ata_port *ap =
 		container_of(work, struct ata_port, scsi_rescan_task);
-	struct ata_device *dev;
+	unsigned long flags;
 	unsigned int i;
 
+	spin_lock_irqsave(ap->lock, flags);
+
 	for (i = 0; i < ATA_MAX_DEVICES; i++) {
-		dev = &ap->device[i];
+		struct ata_device *dev = &ap->device[i];
+		struct scsi_device *sdev = dev->sdev;
 
-		if (ata_dev_enabled(dev) && dev->sdev)
-			scsi_rescan_device(&(dev->sdev->sdev_gendev));
+		if (!ata_dev_enabled(dev) || !sdev)
+			continue;
+		if (scsi_device_get(sdev))
+			continue;
+
+		spin_unlock_irqrestore(ap->lock, flags);
+		scsi_rescan_device(&(sdev->sdev_gendev));
+		scsi_device_put(sdev);
+		spin_lock_irqsave(ap->lock, flags);
 	}
+
+	spin_unlock_irqrestore(ap->lock, flags);
 }
 
 /**
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 7645f2b30ccf..10ee22ae5c15 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -39,6 +39,35 @@
 #include "libata.h"
 
 /**
+ *	ata_irq_on - Enable interrupts on a port.
+ *	@ap: Port on which interrupts are enabled.
+ *
+ *	Enable interrupts on a legacy IDE device using MMIO or PIO,
+ *	wait for idle, clear any pending interrupts.
+ *
+ *	LOCKING:
+ *	Inherited from caller.
+ */
+u8 ata_irq_on(struct ata_port *ap)
+{
+	struct ata_ioports *ioaddr = &ap->ioaddr;
+	u8 tmp;
+
+	ap->ctl &= ~ATA_NIEN;
+	ap->last_ctl = ap->ctl;
+
+	if (ap->flags & ATA_FLAG_MMIO)
+		writeb(ap->ctl, (void __iomem *) ioaddr->ctl_addr);
+	else
+		outb(ap->ctl, ioaddr->ctl_addr);
+	tmp = ata_wait_idle(ap);
+
+	ap->ops->irq_clear(ap);
+
+	return tmp;
+}
+
+/**
  *	ata_tf_load_pio - send taskfile registers to host controller
  *	@ap: Port to which output is sent
  *	@tf: ATA taskfile register set
@@ -671,6 +700,14 @@ void ata_bmdma_freeze(struct ata_port *ap)
 		writeb(ap->ctl, (void __iomem *)ioaddr->ctl_addr);
 	else
 		outb(ap->ctl, ioaddr->ctl_addr);
+
+	/* Under certain circumstances, some controllers raise IRQ on
+	 * ATA_NIEN manipulation.  Also, many controllers fail to mask
+	 * previously pending IRQ on ATA_NIEN assertion.  Clear it.
+	 */
+	ata_chk_status(ap);
+
+	ap->ops->irq_clear(ap);
 }
 
 /**
@@ -714,7 +751,6 @@ void ata_bmdma_drive_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
 			ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
 			ata_postreset_fn_t postreset)
 {
-	struct ata_eh_context *ehc = &ap->eh_context;
 	struct ata_queued_cmd *qc;
 	unsigned long flags;
 	int thaw = 0;
@@ -732,9 +768,7 @@ void ata_bmdma_drive_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
 		   qc->tf.protocol == ATA_PROT_ATAPI_DMA)) {
 		u8 host_stat;
 
-		host_stat = ata_bmdma_status(ap);
-
-		ata_ehi_push_desc(&ehc->i, "BMDMA stat 0x%x", host_stat);
+		host_stat = ap->ops->bmdma_status(ap);
 
 		/* BMDMA controllers indicate host bus error by
 		 * setting DMA_ERR bit and timing out.  As it wasn't
@@ -877,6 +911,7 @@ static struct ata_probe_ent *ata_pci_init_legacy_port(struct pci_dev *pdev,
 		return NULL;
 
 	probe_ent->n_ports = 2;
+	probe_ent->irq_flags = IRQF_SHARED;
 
 	if (port_mask & ATA_PORT_PRIMARY) {
 		probe_ent->irq = ATA_PRIMARY_IRQ;
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 7e0f3aff873d..81ae41d5f23f 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -39,26 +39,39 @@ struct ata_scsi_args {
 };
 
 /* libata-core.c */
+enum {
+	/* flags for ata_dev_read_id() */
+	ATA_READID_POSTRESET	= (1 << 0), /* reading ID after reset */
+};
+
 extern struct workqueue_struct *ata_aux_wq;
 extern int atapi_enabled;
 extern int atapi_dmadir;
 extern int libata_fua;
 extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev);
-extern int ata_rwcmd_protocol(struct ata_queued_cmd *qc);
+extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
+			   u64 block, u32 n_block, unsigned int tf_flags,
+			   unsigned int tag);
+extern u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev);
 extern void ata_dev_disable(struct ata_device *dev);
 extern void ata_port_flush_task(struct ata_port *ap);
 extern unsigned ata_exec_internal(struct ata_device *dev,
 				  struct ata_taskfile *tf, const u8 *cdb,
 				  int dma_dir, void *buf, unsigned int buflen);
+extern unsigned ata_exec_internal_sg(struct ata_device *dev,
+				     struct ata_taskfile *tf, const u8 *cdb,
+				     int dma_dir, struct scatterlist *sg,
+				     unsigned int n_elem);
 extern unsigned int ata_do_simple_cmd(struct ata_device *dev, u8 cmd);
 extern int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class,
-			   int post_reset, u16 *id);
-extern int ata_dev_revalidate(struct ata_device *dev, int post_reset);
-extern int ata_dev_configure(struct ata_device *dev, int print_info);
+			   unsigned int flags, u16 *id);
+extern int ata_dev_revalidate(struct ata_device *dev, unsigned int flags);
+extern int ata_dev_configure(struct ata_device *dev);
 extern int sata_down_spd_limit(struct ata_port *ap);
 extern int sata_set_spd_needed(struct ata_port *ap);
 extern int ata_down_xfermask_limit(struct ata_device *dev, int force_pio0);
 extern int ata_set_mode(struct ata_port *ap, struct ata_device **r_failed_dev);
+extern void ata_sg_clean(struct ata_queued_cmd *qc);
 extern void ata_qc_free(struct ata_queued_cmd *qc);
 extern void ata_qc_issue(struct ata_queued_cmd *qc);
 extern void __ata_qc_complete(struct ata_queued_cmd *qc);
@@ -120,4 +133,7 @@ extern void ata_scsi_error(struct Scsi_Host *host);
 extern void ata_port_wait_eh(struct ata_port *ap);
 extern void ata_qc_schedule_eh(struct ata_queued_cmd *qc);
 
+/* libata-sff.c */
+extern u8 ata_irq_on(struct ata_port *ap);
+
 #endif /* __LIBATA_H__ */
diff --git a/drivers/ata/pata_ali.c b/drivers/ata/pata_ali.c
index 64eed99f6814..c5d61d1911a5 100644
--- a/drivers/ata/pata_ali.c
+++ b/drivers/ata/pata_ali.c
@@ -34,7 +34,7 @@
 #include <linux/dmi.h>
 
 #define DRV_NAME "pata_ali"
-#define DRV_VERSION "0.6.6"
+#define DRV_VERSION "0.7.2"
 
 /*
  *	Cable special cases
@@ -78,7 +78,7 @@ static int ali_c2_cable_detect(struct ata_port *ap)
 	   implement the detect logic */
 
 	if (ali_cable_override(pdev))
-		return ATA_CBL_PATA80;
+		return ATA_CBL_PATA40_SHORT;
 
 	/* Host view cable detect 0x4A bit 0 primary bit 1 secondary
 	   Bit set for 40 pin */
@@ -337,9 +337,6 @@ static struct scsi_host_template ali_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	/* Keep LBA28 counts so large I/O's don't turn LBA48 and PIO
-	   with older controllers. Not locked so will grow on C5 or later */
-	.max_sectors		= 255,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -348,6 +345,8 @@ static struct scsi_host_template ali_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 /*
@@ -497,6 +496,69 @@ static struct ata_port_operations ali_c5_port_ops = {
 	.host_stop	= ata_host_stop
 };
 
+
+/**
+ *	ali_init_chipset	-	chip setup function
+ *	@pdev: PCI device of ATA controller
+ *
+ *	Perform the setup on the device that must be done both at boot
+ *	and at resume time.
+ */
+ 
+static void ali_init_chipset(struct pci_dev *pdev)
+{
+	u8 rev, tmp;
+	struct pci_dev *north, *isa_bridge;
+
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &rev);
+
+	/*
+	 * The chipset revision selects the driver operations and
+	 * mode data.
+	 */
+
+	if (rev >= 0x20 && rev < 0xC2) {
+		/* 1543-E/F, 1543C-C, 1543C-D, 1543C-E */
+		pci_read_config_byte(pdev, 0x4B, &tmp);
+		/* Clear CD-ROM DMA write bit */
+		tmp &= 0x7F;
+		pci_write_config_byte(pdev, 0x4B, tmp);
+	} else if (rev >= 0xC2) {
+		/* Enable cable detection logic */
+		pci_read_config_byte(pdev, 0x4B, &tmp);
+		pci_write_config_byte(pdev, 0x4B, tmp | 0x08);
+	}
+	north = pci_get_bus_and_slot(0, PCI_DEVFN(0,0));
+	isa_bridge = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
+
+	if (north && north->vendor == PCI_VENDOR_ID_AL && isa_bridge) {
+		/* Configure the ALi bridge logic. For non ALi rely on BIOS.
+		   Set the south bridge enable bit */
+		pci_read_config_byte(isa_bridge, 0x79, &tmp);
+		if (rev == 0xC2)
+			pci_write_config_byte(isa_bridge, 0x79, tmp | 0x04);
+		else if (rev > 0xC2 && rev < 0xC5)
+			pci_write_config_byte(isa_bridge, 0x79, tmp | 0x02);
+	}
+	if (rev >= 0x20) {
+		/*
+		 * CD_ROM DMA on (0x53 bit 0). Enable this even if we want
+		 * to use PIO. 0x53 bit 1 (rev 20 only) - enable FIFO control
+		 * via 0x54/55.
+		 */
+		pci_read_config_byte(pdev, 0x53, &tmp);
+		if (rev <= 0x20)
+			tmp &= ~0x02;
+		if (rev >= 0xc7)
+			tmp |= 0x03;
+		else
+			tmp |= 0x01;	/* CD_ROM enable for DMA */
+		pci_write_config_byte(pdev, 0x53, tmp);
+	}
+	pci_dev_put(isa_bridge);
+	pci_dev_put(north);
+	ata_pci_clear_simplex(pdev);
+}
 /**
  *	ali_init_one		-	discovery callback
  *	@pdev: PCI device ID
@@ -570,7 +632,7 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	static struct ata_port_info *port_info[2];
 	u8 rev, tmp;
-	struct pci_dev *north, *isa_bridge;
+	struct pci_dev *isa_bridge;
 
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &rev);
 
@@ -582,11 +644,6 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rev < 0x20) {
 		port_info[0] = port_info[1] = &info_early;
 	} else if (rev < 0xC2) {
-		/* 1543-E/F, 1543C-C, 1543C-D, 1543C-E */
-		pci_read_config_byte(pdev, 0x4B, &tmp);
-		/* Clear CD-ROM DMA write bit */
-		tmp &= 0x7F;
-		pci_write_config_byte(pdev, 0x4B, tmp);
         	port_info[0] = port_info[1] = &info_20;
 	} else if (rev == 0xC2) {
         	port_info[0] = port_info[1] = &info_c2;
@@ -597,54 +654,25 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	} else
         	port_info[0] = port_info[1] = &info_c5;
 
-	if (rev >= 0xC2) {
-		/* Enable cable detection logic */
-		pci_read_config_byte(pdev, 0x4B, &tmp);
-		pci_write_config_byte(pdev, 0x4B, tmp | 0x08);
-	}
-
-	north = pci_get_slot(pdev->bus, PCI_DEVFN(0,0));
+	ali_init_chipset(pdev);
+	
 	isa_bridge = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
-
-	if (north && north->vendor == PCI_VENDOR_ID_AL) {
-		/* Configure the ALi bridge logic. For non ALi rely on BIOS.
-		   Set the south bridge enable bit */
-		pci_read_config_byte(isa_bridge, 0x79, &tmp);
-		if (rev == 0xC2)
-			pci_write_config_byte(isa_bridge, 0x79, tmp | 0x04);
-		else if (rev > 0xC2)
-			pci_write_config_byte(isa_bridge, 0x79, tmp | 0x02);
-	}
-
-	if (rev >= 0x20) {
-		if (rev < 0xC2) {
-			/* Are we paired with a UDMA capable chip */
-			pci_read_config_byte(isa_bridge, 0x5E, &tmp);
-			if ((tmp & 0x1E) == 0x12)
-		        	port_info[0] = port_info[1] = &info_20_udma;
-		}
-		/*
-		 * CD_ROM DMA on (0x53 bit 0). Enable this even if we want
-		 * to use PIO. 0x53 bit 1 (rev 20 only) - enable FIFO control
-		 * via 0x54/55.
-		 */
-		pci_read_config_byte(pdev, 0x53, &tmp);
-		if (rev <= 0x20)
-			tmp &= ~0x02;
-		if (rev >= 0xc7)
-			tmp |= 0x03;
-		else
-			tmp |= 0x01;	/* CD_ROM enable for DMA */
-		pci_write_config_byte(pdev, 0x53, tmp);
+	if (isa_bridge && rev >= 0x20 && rev < 0xC2) {
+		/* Are we paired with a UDMA capable chip */
+		pci_read_config_byte(isa_bridge, 0x5E, &tmp);
+		if ((tmp & 0x1E) == 0x12)
+	        	port_info[0] = port_info[1] = &info_20_udma;
+		pci_dev_put(isa_bridge);
 	}
-
-	pci_dev_put(isa_bridge);
-	pci_dev_put(north);
-
-	ata_pci_clear_simplex(pdev);
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+static int ali_reinit_one(struct pci_dev *pdev)
+{
+	ali_init_chipset(pdev);
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id ali[] = {
 	{ PCI_VDEVICE(AL, PCI_DEVICE_ID_AL_M5228), },
 	{ PCI_VDEVICE(AL, PCI_DEVICE_ID_AL_M5229), },
@@ -656,7 +684,9 @@ static struct pci_driver ali_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= ali,
 	.probe 		= ali_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ali_reinit_one,
 };
 
 static int __init ali_init(void)
diff --git a/drivers/ata/pata_amd.c b/drivers/ata/pata_amd.c
index 8be46a63af74..a6b330089f22 100644
--- a/drivers/ata/pata_amd.c
+++ b/drivers/ata/pata_amd.c
@@ -25,7 +25,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_amd"
-#define DRV_VERSION "0.2.4"
+#define DRV_VERSION "0.2.7"
 
 /**
  *	timing_setup		-	shared timing computation and load
@@ -326,7 +326,6 @@ static struct scsi_host_template amd_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -335,6 +334,8 @@ static struct scsi_host_template amd_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations amd33_port_ops = {
@@ -662,6 +663,23 @@ static int amd_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+static int amd_reinit_one(struct pci_dev *pdev)
+{
+	if (pdev->vendor == PCI_VENDOR_ID_AMD) {
+		u8 fifo;
+		pci_read_config_byte(pdev, 0x41, &fifo);
+		if (pdev->device == PCI_DEVICE_ID_AMD_VIPER_7411)
+			/* FIFO is broken */
+			pci_write_config_byte(pdev, 0x41, fifo & 0x0F);
+		else
+			pci_write_config_byte(pdev, 0x41, fifo | 0xF0);
+		if (pdev->device == PCI_DEVICE_ID_AMD_VIPER_7409 ||
+		    pdev->device == PCI_DEVICE_ID_AMD_COBRA_7401)
+		    	ata_pci_clear_simplex(pdev);
+	}
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id amd[] = {
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_COBRA_7401),		0 },
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_VIPER_7409),		1 },
@@ -689,7 +707,9 @@ static struct pci_driver amd_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= amd,
 	.probe 		= amd_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= amd_reinit_one,
 };
 
 static int __init amd_init(void)
diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c
index 2cd30761ca1f..37bc1323bda7 100644
--- a/drivers/ata/pata_artop.c
+++ b/drivers/ata/pata_artop.c
@@ -307,7 +307,6 @@ static struct scsi_host_template artop_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 4e1d3b59adbb..6f6672c55131 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -22,7 +22,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_atiixp"
-#define DRV_VERSION "0.4.3"
+#define DRV_VERSION "0.4.4"
 
 enum {
 	ATIIXP_IDE_PIO_TIMING	= 0x40,
@@ -209,7 +209,6 @@ static struct scsi_host_template atiixp_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -218,6 +217,8 @@ static struct scsi_host_template atiixp_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations atiixp_port_ops = {
@@ -281,7 +282,9 @@ static struct pci_driver atiixp_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= atiixp,
 	.probe 		= atiixp_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.resume		= ata_pci_device_resume,
+	.suspend	= ata_pci_device_suspend,
 };
 
 static int __init atiixp_init(void)
diff --git a/drivers/ata/pata_cmd64x.c b/drivers/ata/pata_cmd64x.c
index 29a60df465da..15841a563694 100644
--- a/drivers/ata/pata_cmd64x.c
+++ b/drivers/ata/pata_cmd64x.c
@@ -31,7 +31,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_cmd64x"
-#define DRV_VERSION "0.2.1"
+#define DRV_VERSION "0.2.2"
 
 /*
  * CMD64x specific registers definition.
@@ -268,7 +268,6 @@ static struct scsi_host_template cmd64x_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -277,6 +276,8 @@ static struct scsi_host_template cmd64x_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations cmd64x_port_ops = {
@@ -469,6 +470,20 @@ static int cmd64x_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+static int cmd64x_reinit_one(struct pci_dev *pdev)
+{
+	u8 mrdmode;
+	pci_write_config_byte(pdev, PCI_LATENCY_TIMER, 64);
+	pci_read_config_byte(pdev, MRDMODE, &mrdmode);
+	mrdmode &= ~ 0x30;	/* IRQ set up */
+	mrdmode |= 0x02;	/* Memory read line enable */
+	pci_write_config_byte(pdev, MRDMODE, mrdmode);
+#ifdef CONFIG_PPC
+	pci_write_config_byte(pdev, UDIDETCR0, 0xF0);
+#endif
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id cmd64x[] = {
 	{ PCI_VDEVICE(CMD, PCI_DEVICE_ID_CMD_643), 0 },
 	{ PCI_VDEVICE(CMD, PCI_DEVICE_ID_CMD_646), 1 },
@@ -482,7 +497,9 @@ static struct pci_driver cmd64x_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= cmd64x,
 	.probe 		= cmd64x_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= cmd64x_reinit_one,
 };
 
 static int __init cmd64x_init(void)
diff --git a/drivers/ata/pata_cs5520.c b/drivers/ata/pata_cs5520.c
index 33d2b88f9c79..9f165a8e032d 100644
--- a/drivers/ata/pata_cs5520.c
+++ b/drivers/ata/pata_cs5520.c
@@ -41,7 +41,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_cs5520"
-#define DRV_VERSION	"0.6.2"
+#define DRV_VERSION	"0.6.3"
 
 struct pio_clocks
 {
@@ -159,7 +159,6 @@ static struct scsi_host_template cs5520_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -168,6 +167,8 @@ static struct scsi_host_template cs5520_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations cs5520_port_ops = {
@@ -297,6 +298,22 @@ static void __devexit cs5520_remove_one(struct pci_dev *pdev)
 	dev_set_drvdata(dev, NULL);
 }
 
+/**
+ *	cs5520_reinit_one	-	device resume
+ *	@pdev: PCI device
+ *
+ *	Do any reconfiguration work needed by a resume from RAM. We need
+ *	to restore DMA mode support on BIOSen which disabled it
+ */
+ 
+static int cs5520_reinit_one(struct pci_dev *pdev)
+{
+	u8 pcicfg;
+	pci_read_config_byte(pdev, 0x60, &pcicfg);
+	if ((pcicfg & 0x40) == 0)
+		pci_write_config_byte(pdev, 0x60, pcicfg | 0x40);
+	return ata_pci_device_resume(pdev);
+}
 /* For now keep DMA off. We can set it for all but A rev CS5510 once the
    core ATA code can handle it */
 
@@ -311,7 +328,9 @@ static struct pci_driver cs5520_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= pata_cs5520,
 	.probe 		= cs5520_init_one,
-	.remove		= cs5520_remove_one
+	.remove		= cs5520_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= cs5520_reinit_one,
 };
 
 static int __init cs5520_init(void)
diff --git a/drivers/ata/pata_cs5530.c b/drivers/ata/pata_cs5530.c
index 981f49223469..1c628014dae6 100644
--- a/drivers/ata/pata_cs5530.c
+++ b/drivers/ata/pata_cs5530.c
@@ -35,7 +35,7 @@
 #include <linux/dmi.h>
 
 #define DRV_NAME	"pata_cs5530"
-#define DRV_VERSION	"0.6"
+#define DRV_VERSION	"0.7.1"
 
 /**
  *	cs5530_set_piomode		-	PIO setup
@@ -173,7 +173,6 @@ static struct scsi_host_template cs5530_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -182,6 +181,8 @@ static struct scsi_host_template cs5530_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations cs5530_port_ops = {
@@ -239,38 +240,18 @@ static int cs5530_is_palmax(void)
 	return 0;
 }
 
+
 /**
- *	cs5530_init_one		-	Initialise a CS5530
- *	@dev: PCI device
- *	@id: Entry in match table
+ *	cs5530_init_chip	-	Chipset init
  *
- *	Install a driver for the newly found CS5530 companion chip. Most of
- *	this is just housekeeping. We have to set the chip up correctly and
- *	turn off various bits of emulation magic.
+ *	Perform the chip initialisation work that is shared between both
+ *	setup and resume paths
  */
-
-static int cs5530_init_one(struct pci_dev *dev, const struct pci_device_id *id)
+ 
+static int cs5530_init_chip(void)
 {
-	int compiler_warning_pointless_fix;
-	struct pci_dev *master_0 = NULL, *cs5530_0 = NULL;
-	static struct ata_port_info info = {
-		.sht = &cs5530_sht,
-		.flags = ATA_FLAG_SLAVE_POSS|ATA_FLAG_SRST,
-		.pio_mask = 0x1f,
-		.mwdma_mask = 0x07,
-		.udma_mask = 0x07,
-		.port_ops = &cs5530_port_ops
-	};
-	/* The docking connector doesn't do UDMA, and it seems not MWDMA */
-	static struct ata_port_info info_palmax_secondary = {
-		.sht = &cs5530_sht,
-		.flags = ATA_FLAG_SLAVE_POSS|ATA_FLAG_SRST,
-		.pio_mask = 0x1f,
-		.port_ops = &cs5530_port_ops
-	};
-	static struct ata_port_info *port_info[2] = { &info, &info };
+	struct pci_dev *master_0 = NULL, *cs5530_0 = NULL, *dev = NULL;
 
-	dev = NULL;
 	while ((dev = pci_get_device(PCI_VENDOR_ID_CYRIX, PCI_ANY_ID, dev)) != NULL) {
 		switch (dev->device) {
 			case PCI_DEVICE_ID_CYRIX_PCI_MASTER:
@@ -291,7 +272,7 @@ static int cs5530_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	pci_set_master(cs5530_0);
-	compiler_warning_pointless_fix = pci_set_mwi(cs5530_0);
+	pci_set_mwi(cs5530_0);
 
 	/*
 	 * Set PCI CacheLineSize to 16-bytes:
@@ -339,13 +320,7 @@ static int cs5530_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 
 	pci_dev_put(master_0);
 	pci_dev_put(cs5530_0);
-
-	if (cs5530_is_palmax())
-		port_info[1] = &info_palmax_secondary;
-
-	/* Now kick off ATA set up */
-	return ata_pci_init_one(dev, port_info, 2);
-
+	return 0;
 fail_put:
 	if (master_0)
 		pci_dev_put(master_0);
@@ -354,6 +329,53 @@ fail_put:
 	return -ENODEV;
 }
 
+/**
+ *	cs5530_init_one		-	Initialise a CS5530
+ *	@dev: PCI device
+ *	@id: Entry in match table
+ *
+ *	Install a driver for the newly found CS5530 companion chip. Most of
+ *	this is just housekeeping. We have to set the chip up correctly and
+ *	turn off various bits of emulation magic.
+ */
+
+static int cs5530_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	static struct ata_port_info info = {
+		.sht = &cs5530_sht,
+		.flags = ATA_FLAG_SLAVE_POSS|ATA_FLAG_SRST,
+		.pio_mask = 0x1f,
+		.mwdma_mask = 0x07,
+		.udma_mask = 0x07,
+		.port_ops = &cs5530_port_ops
+	};
+	/* The docking connector doesn't do UDMA, and it seems not MWDMA */
+	static struct ata_port_info info_palmax_secondary = {
+		.sht = &cs5530_sht,
+		.flags = ATA_FLAG_SLAVE_POSS|ATA_FLAG_SRST,
+		.pio_mask = 0x1f,
+		.port_ops = &cs5530_port_ops
+	};
+	static struct ata_port_info *port_info[2] = { &info, &info };
+	
+	/* Chip initialisation */
+	if (cs5530_init_chip())
+		return -ENODEV;
+		
+	if (cs5530_is_palmax())
+		port_info[1] = &info_palmax_secondary;
+
+	/* Now kick off ATA set up */
+	return ata_pci_init_one(pdev, port_info, 2);
+}
+
+static int cs5530_reinit_one(struct pci_dev *pdev)
+{
+	/* If we fail on resume we are doomed */
+	BUG_ON(cs5530_init_chip());
+	return ata_pci_device_resume(pdev);
+}
+	
 static const struct pci_device_id cs5530[] = {
 	{ PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5530_IDE), },
 
@@ -364,7 +386,9 @@ static struct pci_driver cs5530_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= cs5530,
 	.probe 		= cs5530_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= cs5530_reinit_one,
 };
 
 static int __init cs5530_init(void)
diff --git a/drivers/ata/pata_cs5535.c b/drivers/ata/pata_cs5535.c
index 8dafa4a49fdc..e3efec4ffc79 100644
--- a/drivers/ata/pata_cs5535.c
+++ b/drivers/ata/pata_cs5535.c
@@ -39,7 +39,7 @@
 #include <asm/msr.h>
 
 #define DRV_NAME	"cs5535"
-#define DRV_VERSION	"0.2.10"
+#define DRV_VERSION	"0.2.11"
 
 /*
  *	The Geode (Aka Athlon GX now) uses an internal MSR based
@@ -177,7 +177,6 @@ static struct scsi_host_template cs5535_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -186,6 +185,8 @@ static struct scsi_host_template cs5535_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations cs5535_port_ops = {
@@ -268,7 +269,9 @@ static struct pci_driver cs5535_pci_driver = {
 	.name		= DRV_NAME,
 	.id_table	= cs5535,
 	.probe 		= cs5535_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init cs5535_init(void)
diff --git a/drivers/ata/pata_cypress.c b/drivers/ata/pata_cypress.c
index 5a0b811907ee..e2a95699bae7 100644
--- a/drivers/ata/pata_cypress.c
+++ b/drivers/ata/pata_cypress.c
@@ -18,7 +18,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_cypress"
-#define DRV_VERSION "0.1.2"
+#define DRV_VERSION "0.1.4"
 
 /* here are the offset definitions for the registers */
 
@@ -128,7 +128,6 @@ static struct scsi_host_template cy82c693_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -137,6 +136,8 @@ static struct scsi_host_template cy82c693_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations cy82c693_port_ops = {
@@ -204,7 +205,9 @@ static struct pci_driver cy82c693_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= cy82c693,
 	.probe 		= cy82c693_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init cy82c693_init(void)
diff --git a/drivers/ata/pata_efar.c b/drivers/ata/pata_efar.c
index 755f79279de3..edf8a63f50af 100644
--- a/drivers/ata/pata_efar.c
+++ b/drivers/ata/pata_efar.c
@@ -22,7 +22,7 @@
 #include <linux/ata.h>
 
 #define DRV_NAME	"pata_efar"
-#define DRV_VERSION	"0.4.2"
+#define DRV_VERSION	"0.4.3"
 
 /**
  *	efar_pre_reset	-	check for 40/80 pin
@@ -226,7 +226,6 @@ static struct scsi_host_template efar_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -235,6 +234,8 @@ static struct scsi_host_template efar_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static const struct ata_port_operations efar_ops = {
@@ -316,6 +317,8 @@ static struct pci_driver efar_pci_driver = {
 	.id_table		= efar_pci_tbl,
 	.probe			= efar_init_one,
 	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
 };
 
 static int __init efar_init(void)
diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c
index c0e150a9586b..2663599a7c02 100644
--- a/drivers/ata/pata_hpt366.c
+++ b/drivers/ata/pata_hpt366.c
@@ -27,7 +27,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_hpt366"
-#define DRV_VERSION	"0.5"
+#define DRV_VERSION	"0.5.3"
 
 struct hpt_clock {
 	u8	xfer_speed;
@@ -222,9 +222,17 @@ static u32 hpt36x_find_mode(struct ata_port *ap, int speed)
 
 static int hpt36x_pre_reset(struct ata_port *ap)
 {
+	static const struct pci_bits hpt36x_enable_bits[] = {
+		{ 0x50, 1, 0x04, 0x04 },
+		{ 0x54, 1, 0x04, 0x04 }
+	};
+
 	u8 ata66;
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 
+	if (!pci_test_config_bits(pdev, &hpt36x_enable_bits[ap->port_no]))
+		return -ENOENT;
+		
 	pci_read_config_byte(pdev, 0x5A, &ata66);
 	if (ata66 & (1 << ap->port_no))
 		ap->cbl = ATA_CBL_PATA40;
@@ -322,7 +330,6 @@ static struct scsi_host_template hpt36x_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -331,6 +338,8 @@ static struct scsi_host_template hpt36x_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 /*
@@ -373,6 +382,27 @@ static struct ata_port_operations hpt366_port_ops = {
 };
 
 /**
+ *	hpt36x_init_chipset	-	common chip setup
+ *	@dev: PCI device
+ *
+ *	Perform the chip setup work that must be done at both init and
+ *	resume time
+ */
+
+static void hpt36x_init_chipset(struct pci_dev *dev)
+{
+	u8 drive_fast;
+	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, (L1_CACHE_BYTES / 4));
+	pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0x78);
+	pci_write_config_byte(dev, PCI_MIN_GNT, 0x08);
+	pci_write_config_byte(dev, PCI_MAX_LAT, 0x08);
+
+	pci_read_config_byte(dev, 0x51, &drive_fast);
+	if (drive_fast & 0x80)
+		pci_write_config_byte(dev, 0x51, drive_fast & ~0x80);
+}
+
+/**
  *	hpt36x_init_one		-	Initialise an HPT366/368
  *	@dev: PCI device
  *	@id: Entry in match table
@@ -407,7 +437,6 @@ static int hpt36x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 
 	u32 class_rev;
 	u32 reg1;
-	u8 drive_fast;
 
 	pci_read_config_dword(dev, PCI_CLASS_REVISION, &class_rev);
 	class_rev &= 0xFF;
@@ -417,14 +446,7 @@ static int hpt36x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 	if (class_rev > 2)
 			return -ENODEV;
 
-	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, (L1_CACHE_BYTES / 4));
-	pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0x78);
-	pci_write_config_byte(dev, PCI_MIN_GNT, 0x08);
-	pci_write_config_byte(dev, PCI_MAX_LAT, 0x08);
-
-	pci_read_config_byte(dev, 0x51, &drive_fast);
-	if (drive_fast & 0x80)
-		pci_write_config_byte(dev, 0x51, drive_fast & ~0x80);
+	hpt36x_init_chipset(dev);
 
 	pci_read_config_dword(dev, 0x40,  &reg1);
 
@@ -445,9 +467,15 @@ static int hpt36x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 	return ata_pci_init_one(dev, port_info, 2);
 }
 
+static int hpt36x_reinit_one(struct pci_dev *dev)
+{
+	hpt36x_init_chipset(dev);
+	return ata_pci_device_resume(dev);
+}
+
+
 static const struct pci_device_id hpt36x[] = {
 	{ PCI_VDEVICE(TTI, PCI_DEVICE_ID_TTI_HPT366), },
-
 	{ },
 };
 
@@ -455,7 +483,9 @@ static struct pci_driver hpt36x_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= hpt36x,
 	.probe 		= hpt36x_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= hpt36x_reinit_one,
 };
 
 static int __init hpt36x_init(void)
@@ -463,13 +493,11 @@ static int __init hpt36x_init(void)
 	return pci_register_driver(&hpt36x_pci_driver);
 }
 
-
 static void __exit hpt36x_exit(void)
 {
 	pci_unregister_driver(&hpt36x_pci_driver);
 }
 
-
 MODULE_AUTHOR("Alan Cox");
 MODULE_DESCRIPTION("low-level driver for the Highpoint HPT366/368");
 MODULE_LICENSE("GPL");
diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index 1eeb16f0fb02..47082df7199e 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -768,7 +768,6 @@ static struct scsi_host_template hpt37x_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_hpt3x2n.c b/drivers/ata/pata_hpt3x2n.c
index 47d7664e9eee..f6817b4093a4 100644
--- a/drivers/ata/pata_hpt3x2n.c
+++ b/drivers/ata/pata_hpt3x2n.c
@@ -334,7 +334,6 @@ static struct scsi_host_template hpt3x2n_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_hpt3x3.c b/drivers/ata/pata_hpt3x3.c
index d216cc564b56..5f1d385eb592 100644
--- a/drivers/ata/pata_hpt3x3.c
+++ b/drivers/ata/pata_hpt3x3.c
@@ -23,7 +23,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_hpt3x3"
-#define DRV_VERSION	"0.4.1"
+#define DRV_VERSION	"0.4.2"
 
 static int hpt3x3_probe_init(struct ata_port *ap)
 {
@@ -111,7 +111,6 @@ static struct scsi_host_template hpt3x3_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -120,6 +119,8 @@ static struct scsi_host_template hpt3x3_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations hpt3x3_port_ops = {
@@ -158,6 +159,27 @@ static struct ata_port_operations hpt3x3_port_ops = {
 };
 
 /**
+ *	hpt3x3_init_chipset	-	chip setup
+ *	@dev: PCI device
+ *
+ *	Perform the setup required at boot and on resume.
+ */
+ 
+static void hpt3x3_init_chipset(struct pci_dev *dev)
+{
+	u16 cmd;
+	/* Initialize the board */
+	pci_write_config_word(dev, 0x80, 0x00);
+	/* Check if it is a 343 or a 363. 363 has COMMAND_MEMORY set */
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	if (cmd & PCI_COMMAND_MEMORY)
+		pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0xF0);
+	else
+		pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0x20);
+}
+
+
+/**
  *	hpt3x3_init_one		-	Initialise an HPT343/363
  *	@dev: PCI device
  *	@id: Entry in match table
@@ -178,21 +200,18 @@ static int hpt3x3_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 		.port_ops = &hpt3x3_port_ops
 	};
 	static struct ata_port_info *port_info[2] = { &info, &info };
-	u16 cmd;
-
-	/* Initialize the board */
-	pci_write_config_word(dev, 0x80, 0x00);
-	/* Check if it is a 343 or a 363. 363 has COMMAND_MEMORY set */
-	pci_read_config_word(dev, PCI_COMMAND, &cmd);
-	if (cmd & PCI_COMMAND_MEMORY)
-		pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0xF0);
-	else
-		pci_write_config_byte(dev, PCI_LATENCY_TIMER, 0x20);
 
+	hpt3x3_init_chipset(dev);
 	/* Now kick off ATA set up */
 	return ata_pci_init_one(dev, port_info, 2);
 }
 
+static int hpt3x3_reinit_one(struct pci_dev *dev)
+{
+	hpt3x3_init_chipset(dev);
+	return ata_pci_device_resume(dev);
+}
+
 static const struct pci_device_id hpt3x3[] = {
 	{ PCI_VDEVICE(TTI, PCI_DEVICE_ID_TTI_HPT343), },
 
@@ -203,7 +222,9 @@ static struct pci_driver hpt3x3_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= hpt3x3,
 	.probe 		= hpt3x3_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= hpt3x3_reinit_one,
 };
 
 static int __init hpt3x3_init(void)
diff --git a/drivers/ata/pata_isapnp.c b/drivers/ata/pata_isapnp.c
index 40ca2b82b7fc..a97d55ae95c9 100644
--- a/drivers/ata/pata_isapnp.c
+++ b/drivers/ata/pata_isapnp.c
@@ -27,7 +27,6 @@ static struct scsi_host_template isapnp_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c
index 7f68f14be6fd..0b56ff3d1cfe 100644
--- a/drivers/ata/pata_it821x.c
+++ b/drivers/ata/pata_it821x.c
@@ -80,7 +80,7 @@
 
 
 #define DRV_NAME "pata_it821x"
-#define DRV_VERSION "0.3.2"
+#define DRV_VERSION "0.3.3"
 
 struct it821x_dev
 {
@@ -666,9 +666,6 @@ static struct scsi_host_template it821x_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	/* 255 sectors to begin with. This is locked in smart mode but not
-	   in pass through */
-	.max_sectors		= 255,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -677,6 +674,8 @@ static struct scsi_host_template it821x_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations it821x_smart_port_ops = {
@@ -809,6 +808,14 @@ static int it821x_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+static int it821x_reinit_one(struct pci_dev *pdev)
+{
+	/* Resume - turn raid back off if need be */
+	if (it8212_noraid)
+		it821x_disable_raid(pdev);
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id it821x[] = {
 	{ PCI_VDEVICE(ITE, PCI_DEVICE_ID_ITE_8211), },
 	{ PCI_VDEVICE(ITE, PCI_DEVICE_ID_ITE_8212), },
@@ -820,7 +827,9 @@ static struct pci_driver it821x_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= it821x,
 	.probe 		= it821x_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= it821x_reinit_one,
 };
 
 static int __init it821x_init(void)
diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c
new file mode 100644
index 000000000000..cb8924109f59
--- /dev/null
+++ b/drivers/ata/pata_ixp4xx_cf.c
@@ -0,0 +1,271 @@
+/*
+ * ixp4xx PATA/Compact Flash driver
+ * Copyright (c) 2006 Tower Technologies
+ * Author: Alessandro Zummo <a.zummo@towertech.it>
+ *
+ * An ATA driver to handle a Compact Flash connected
+ * to the ixp4xx expansion bus in TrueIDE mode. The CF
+ * must have it chip selects connected to two CS lines
+ * on the ixp4xx. The interrupt line is optional, if not
+ * specified the driver will run in polling mode.
+ *
+ * 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/module.h>
+#include <linux/libata.h>
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <scsi/scsi_host.h>
+
+#define DRV_NAME	"pata_ixp4xx_cf"
+#define DRV_VERSION	"0.1.1"
+
+static void ixp4xx_set_mode(struct ata_port *ap)
+{
+	int i;
+
+	for (i = 0; i < ATA_MAX_DEVICES; i++) {
+		struct ata_device *dev = &ap->device[i];
+		if (ata_dev_enabled(dev)) {
+			dev->pio_mode = XFER_PIO_0;
+			dev->xfer_mode = XFER_PIO_0;
+			dev->xfer_shift = ATA_SHIFT_PIO;
+			dev->flags |= ATA_DFLAG_PIO;
+		}
+	}
+}
+
+static void ixp4xx_phy_reset(struct ata_port *ap)
+{
+	ap->cbl = ATA_CBL_PATA40;
+	ata_port_probe(ap);
+	ata_bus_reset(ap);
+}
+
+static void ixp4xx_mmio_data_xfer(struct ata_device *adev, unsigned char *buf,
+				unsigned int buflen, int write_data)
+{
+	unsigned int i;
+	unsigned int words = buflen >> 1;
+	u16 *buf16 = (u16 *) buf;
+	struct ata_port *ap = adev->ap;
+	void __iomem *mmio = (void __iomem *)ap->ioaddr.data_addr;
+	struct ixp4xx_pata_data *data = ap->host->dev->platform_data;
+
+	/* set the expansion bus in 16bit mode and restore
+	 * 8 bit mode after the transaction.
+	 */
+	*data->cs0_cfg &= ~(0x01);
+	udelay(100);
+
+	/* Transfer multiple of 2 bytes */
+	if (write_data) {
+		for (i = 0; i < words; i++)
+			writew(buf16[i], mmio);
+	} else {
+		for (i = 0; i < words; i++)
+			buf16[i] = readw(mmio);
+	}
+
+	/* Transfer trailing 1 byte, if any. */
+	if (unlikely(buflen & 0x01)) {
+		u16 align_buf[1] = { 0 };
+		unsigned char *trailing_buf = buf + buflen - 1;
+
+		if (write_data) {
+			memcpy(align_buf, trailing_buf, 1);
+			writew(align_buf[0], mmio);
+		} else {
+			align_buf[0] = readw(mmio);
+			memcpy(trailing_buf, align_buf, 1);
+		}
+	}
+
+	udelay(100);
+	*data->cs0_cfg |= 0x01;
+}
+
+static void ixp4xx_irq_clear(struct ata_port *ap)
+{
+}
+
+static void ixp4xx_host_stop (struct ata_host *host)
+{
+	struct ixp4xx_pata_data *data = host->dev->platform_data;
+
+	iounmap(data->cs0);
+	iounmap(data->cs1);
+}
+
+static struct scsi_host_template ixp4xx_sht = {
+	.module			= THIS_MODULE,
+	.name			= DRV_NAME,
+	.ioctl			= ata_scsi_ioctl,
+	.queuecommand		= ata_scsi_queuecmd,
+	.can_queue		= ATA_DEF_QUEUE,
+	.this_id		= ATA_SHT_THIS_ID,
+	.sg_tablesize		= LIBATA_MAX_PRD,
+	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
+	.emulated		= ATA_SHT_EMULATED,
+	.use_clustering		= ATA_SHT_USE_CLUSTERING,
+	.proc_name		= DRV_NAME,
+	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.slave_configure	= ata_scsi_slave_config,
+	.slave_destroy		= ata_scsi_slave_destroy,
+	.bios_param		= ata_std_bios_param,
+};
+
+static struct ata_port_operations ixp4xx_port_ops = {
+	.set_mode	= ixp4xx_set_mode,
+	.mode_filter	= ata_pci_default_filter,
+
+	.port_disable	= ata_port_disable,
+	.tf_load	= ata_tf_load,
+	.tf_read	= ata_tf_read,
+	.check_status 	= ata_check_status,
+	.exec_command	= ata_exec_command,
+	.dev_select 	= ata_std_dev_select,
+
+	.qc_prep 	= ata_qc_prep,
+	.qc_issue	= ata_qc_issue_prot,
+	.eng_timeout	= ata_eng_timeout,
+	.data_xfer	= ixp4xx_mmio_data_xfer,
+
+	.irq_handler	= ata_interrupt,
+	.irq_clear	= ixp4xx_irq_clear,
+
+	.port_start	= ata_port_start,
+	.port_stop	= ata_port_stop,
+	.host_stop	= ixp4xx_host_stop,
+
+	.phy_reset	= ixp4xx_phy_reset,
+};
+
+static void ixp4xx_setup_port(struct ata_ioports *ioaddr,
+				struct ixp4xx_pata_data *data)
+{
+	ioaddr->cmd_addr	= (unsigned long) data->cs0;
+	ioaddr->altstatus_addr	= (unsigned long) data->cs1 + 0x06;
+	ioaddr->ctl_addr	= (unsigned long) data->cs1 + 0x06;
+
+	ata_std_ports(ioaddr);
+
+#ifndef __ARMEB__
+
+	/* adjust the addresses to handle the address swizzling of the
+	 * ixp4xx in little endian mode.
+	 */
+
+	ioaddr->data_addr	^= 0x02;
+	ioaddr->cmd_addr	^= 0x03;
+	ioaddr->altstatus_addr	^= 0x03;
+	ioaddr->ctl_addr	^= 0x03;
+	ioaddr->error_addr	^= 0x03;
+	ioaddr->feature_addr	^= 0x03;
+	ioaddr->nsect_addr	^= 0x03;
+	ioaddr->lbal_addr 	^= 0x03;
+	ioaddr->lbam_addr	^= 0x03;
+	ioaddr->lbah_addr	^= 0x03;
+	ioaddr->device_addr	^= 0x03;
+	ioaddr->status_addr	^= 0x03;
+	ioaddr->command_addr	^= 0x03;
+#endif
+}
+
+static __devinit int ixp4xx_pata_probe(struct platform_device *pdev)
+{
+	int ret;
+	unsigned int irq;
+	struct resource *cs0, *cs1;
+	struct ata_probe_ent ae;
+
+	struct ixp4xx_pata_data *data = pdev->dev.platform_data;
+
+	cs0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cs1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+
+	if (!cs0 || !cs1)
+		return -EINVAL;
+
+	pdev->dev.coherent_dma_mask = DMA_32BIT_MASK;
+
+	data->cs0 = ioremap(cs0->start, 0x1000);
+	data->cs1 = ioremap(cs1->start, 0x1000);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq)
+		set_irq_type(irq, IRQT_HIGH);
+
+	/* Setup expansion bus chip selects */
+	*data->cs0_cfg = data->cs0_bits;
+	*data->cs1_cfg = data->cs1_bits;
+
+	memset(&ae, 0, sizeof(struct ata_probe_ent));
+	INIT_LIST_HEAD(&ae.node);
+
+	ae.dev		= &pdev->dev;
+	ae.port_ops	= &ixp4xx_port_ops;
+	ae.sht		= &ixp4xx_sht;
+	ae.n_ports	= 1;
+	ae.pio_mask	= 0x1f; /* PIO4 */
+	ae.irq		= irq;
+	ae.irq_flags	= 0;
+	ae.port_flags	= ATA_FLAG_MMIO | ATA_FLAG_NO_LEGACY
+			| ATA_FLAG_NO_ATAPI | ATA_FLAG_SRST;
+
+	/* run in polling mode if no irq has been assigned */
+	if (!irq)
+		ae.port_flags |= ATA_FLAG_PIO_POLLING;
+
+	ixp4xx_setup_port(&ae.port[0], data);
+
+	dev_printk(KERN_INFO, &pdev->dev, "version " DRV_VERSION "\n");
+
+	ret = ata_device_add(&ae);
+	if (ret == 0)
+		return -ENODEV;
+
+	return 0;
+}
+
+static __devexit int ixp4xx_pata_remove(struct platform_device *dev)
+{
+	struct ata_host *host = platform_get_drvdata(dev);
+
+	ata_host_remove(host);
+	platform_set_drvdata(dev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver ixp4xx_pata_platform_driver = {
+	.driver	 = {
+		.name   = DRV_NAME,
+		.owner  = THIS_MODULE,
+	},
+	.probe		= ixp4xx_pata_probe,
+	.remove		= __devexit_p(ixp4xx_pata_remove),
+};
+
+static int __init ixp4xx_pata_init(void)
+{
+	return platform_driver_register(&ixp4xx_pata_platform_driver);
+}
+
+static void __exit ixp4xx_pata_exit(void)
+{
+	platform_driver_unregister(&ixp4xx_pata_platform_driver);
+}
+
+MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>");
+MODULE_DESCRIPTION("low-level driver for ixp4xx Compact Flash PATA");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
+
+module_init(ixp4xx_pata_init);
+module_exit(ixp4xx_pata_exit);
diff --git a/drivers/ata/pata_jmicron.c b/drivers/ata/pata_jmicron.c
index 0210b10d49cd..2d661cb4df3c 100644
--- a/drivers/ata/pata_jmicron.c
+++ b/drivers/ata/pata_jmicron.c
@@ -19,7 +19,7 @@
 #include <linux/ata.h>
 
 #define DRV_NAME	"pata_jmicron"
-#define DRV_VERSION	"0.1.2"
+#define DRV_VERSION	"0.1.4"
 
 typedef enum {
 	PORT_PATA0 = 0,
@@ -128,8 +128,6 @@ static struct scsi_host_template jmicron_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	/* Special handling needed if you have sector or LBA48 limits */
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -213,12 +211,11 @@ static int jmicron_init_one (struct pci_dev *pdev, const struct pci_device_id *i
 
 		/* FIXME: We may want a way to override this in future */
 		pci_write_config_byte(pdev, 0x41, 0xa1);
-	}
-
-	/* PATA controller is fn 1, AHCI is fn 0 */
-	if (PCI_FUNC(pdev->devfn) != 1)
-		return -ENODEV;
 
+		/* PATA controller is fn 1, AHCI is fn 0 */
+		if (PCI_FUNC(pdev->devfn) != 1)
+			return -ENODEV;
+	}
 	if ( id->driver_data == 365 || id->driver_data == 366) {
 		/* The 365/66 have two PATA channels, redirect the second */
 		pci_read_config_dword(pdev, 0x80, &reg);
@@ -229,6 +226,27 @@ static int jmicron_init_one (struct pci_dev *pdev, const struct pci_device_id *i
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+static int jmicron_reinit_one(struct pci_dev *pdev)
+{
+	u32 reg;
+	
+	switch(pdev->device) {
+		case PCI_DEVICE_ID_JMICRON_JMB368:
+			break;
+		case PCI_DEVICE_ID_JMICRON_JMB365:
+		case PCI_DEVICE_ID_JMICRON_JMB366:
+			/* Restore mapping or disks swap and boy does it get ugly */
+			pci_read_config_dword(pdev, 0x80, &reg);
+			reg |= (1 << 24);	/* IDE1 to PATA IDE secondary */
+			pci_write_config_dword(pdev, 0x80, reg);
+			/* Fall through */
+		default:
+			/* Make sure AHCI is turned back on */
+			pci_write_config_byte(pdev, 0x41, 0xa1);
+	}
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id jmicron_pci_tbl[] = {
 	{ PCI_VDEVICE(JMICRON, PCI_DEVICE_ID_JMICRON_JMB361), 361},
 	{ PCI_VDEVICE(JMICRON, PCI_DEVICE_ID_JMICRON_JMB363), 363},
@@ -244,6 +262,8 @@ static struct pci_driver jmicron_pci_driver = {
 	.id_table		= jmicron_pci_tbl,
 	.probe			= jmicron_init_one,
 	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= jmicron_reinit_one,
 };
 
 static int __init jmicron_init(void)
diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c
index b39078b2a47b..c7d1738e4e69 100644
--- a/drivers/ata/pata_legacy.c
+++ b/drivers/ata/pata_legacy.c
@@ -128,7 +128,6 @@ static struct scsi_host_template legacy_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
new file mode 100644
index 000000000000..1c810ea00253
--- /dev/null
+++ b/drivers/ata/pata_marvell.c
@@ -0,0 +1,224 @@
+/*
+ *	Marvell PATA driver.
+ *
+ *	For the moment we drive the PATA port in legacy mode. That
+ *	isn't making full use of the device functionality but it is
+ *	easy to get working.
+ *
+ *	(c) 2006 Red Hat  <alan@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <scsi/scsi_host.h>
+#include <linux/libata.h>
+#include <linux/ata.h>
+
+#define DRV_NAME	"pata_marvell"
+#define DRV_VERSION	"0.1.1"
+
+/**
+ *	marvell_pre_reset	-	check for 40/80 pin
+ *	@ap: Port
+ *
+ *	Perform the PATA port setup we need.
+ */
+
+static int marvell_pre_reset(struct ata_port *ap)
+{
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	u32 devices;
+	void __iomem *barp;
+	int i;
+
+	/* Check if our port is enabled */
+
+	barp = pci_iomap(pdev, 5, 0x10);
+	if (barp == NULL)
+		return -ENOMEM;
+	printk("BAR5:");
+	for(i = 0; i <= 0x0F; i++)
+		printk("%02X:%02X ", i, readb(barp + i));
+	printk("\n");
+	
+	devices = readl(barp + 0x0C);
+	pci_iounmap(pdev, barp);
+	
+	if ((pdev->device == 0x6145) && (ap->port_no == 0) &&
+	    (!(devices & 0x10)))	/* PATA enable ? */
+		return -ENOENT;
+
+	/* Cable type */
+	switch(ap->port_no)
+	{
+	case 0:
+		if (inb(ap->ioaddr.bmdma_addr + 1) & 1)
+			ap->cbl = ATA_CBL_PATA40;
+		else
+			ap->cbl = ATA_CBL_PATA80;
+		break;
+
+	case 1: /* Legacy SATA port */
+		ap->cbl = ATA_CBL_SATA;
+		break;
+	}
+	return ata_std_prereset(ap);
+}
+
+/**
+ *	marvell_error_handler - Setup and error handler
+ *	@ap: Port to handle
+ *
+ *	LOCKING:
+ *	None (inherited from caller).
+ */
+
+static void marvell_error_handler(struct ata_port *ap)
+{
+	return ata_bmdma_drive_eh(ap, marvell_pre_reset, ata_std_softreset,
+				  NULL, ata_std_postreset);
+}
+
+/* No PIO or DMA methods needed for this device */
+
+static struct scsi_host_template marvell_sht = {
+	.module			= THIS_MODULE,
+	.name			= DRV_NAME,
+	.ioctl			= ata_scsi_ioctl,
+	.queuecommand		= ata_scsi_queuecmd,
+	.can_queue		= ATA_DEF_QUEUE,
+	.this_id		= ATA_SHT_THIS_ID,
+	.sg_tablesize		= LIBATA_MAX_PRD,
+	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
+	.emulated		= ATA_SHT_EMULATED,
+	.use_clustering		= ATA_SHT_USE_CLUSTERING,
+	.proc_name		= DRV_NAME,
+	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.slave_configure	= ata_scsi_slave_config,
+	.slave_destroy		= ata_scsi_slave_destroy,
+	/* Use standard CHS mapping rules */
+	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
+};
+
+static const struct ata_port_operations marvell_ops = {
+	.port_disable		= ata_port_disable,
+
+	/* Task file is PCI ATA format, use helpers */
+	.tf_load		= ata_tf_load,
+	.tf_read		= ata_tf_read,
+	.check_status		= ata_check_status,
+	.exec_command		= ata_exec_command,
+	.dev_select		= ata_std_dev_select,
+
+	.freeze			= ata_bmdma_freeze,
+	.thaw			= ata_bmdma_thaw,
+	.error_handler		= marvell_error_handler,
+	.post_internal_cmd	= ata_bmdma_post_internal_cmd,
+
+	/* BMDMA handling is PCI ATA format, use helpers */
+	.bmdma_setup		= ata_bmdma_setup,
+	.bmdma_start		= ata_bmdma_start,
+	.bmdma_stop		= ata_bmdma_stop,
+	.bmdma_status		= ata_bmdma_status,
+	.qc_prep		= ata_qc_prep,
+	.qc_issue		= ata_qc_issue_prot,
+	.data_xfer		= ata_pio_data_xfer,
+
+	/* Timeout handling */
+	.irq_handler		= ata_interrupt,
+	.irq_clear		= ata_bmdma_irq_clear,
+
+	/* Generic PATA PCI ATA helpers */
+	.port_start		= ata_port_start,
+	.port_stop		= ata_port_stop,
+	.host_stop		= ata_host_stop,
+};
+
+
+/**
+ *	marvell_init_one - Register Marvell ATA PCI device with kernel services
+ *	@pdev: PCI device to register
+ *	@ent: Entry in marvell_pci_tbl matching with @pdev
+ *
+ *	Called from kernel PCI layer.
+ *
+ *	LOCKING:
+ *	Inherited from PCI layer (may sleep).
+ *
+ *	RETURNS:
+ *	Zero on success, or -ERRNO value.
+ */
+
+static int marvell_init_one (struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	static struct ata_port_info info = {
+		.sht		= &marvell_sht,
+		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+
+		.pio_mask	= 0x1f,
+		.mwdma_mask	= 0x07,
+		.udma_mask 	= 0x3f,
+
+		.port_ops	= &marvell_ops,
+	};
+	static struct ata_port_info info_sata = {
+		.sht		= &marvell_sht,
+		/* Slave possible as its magically mapped not real */
+		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+
+		.pio_mask	= 0x1f,
+		.mwdma_mask	= 0x07,
+		.udma_mask 	= 0x7f,
+
+		.port_ops	= &marvell_ops,
+	};
+	struct ata_port_info *port_info[2] = { &info, &info_sata };
+	int n_port = 2;
+
+	if (pdev->device == 0x6101)
+		n_port = 1;
+
+	return ata_pci_init_one(pdev, port_info, n_port);
+}
+
+static const struct pci_device_id marvell_pci_tbl[] = {
+	{ PCI_DEVICE(0x11AB, 0x6101), },
+	{ PCI_DEVICE(0x11AB, 0x6145), },
+	{ }	/* terminate list */
+};
+
+static struct pci_driver marvell_pci_driver = {
+	.name			= DRV_NAME,
+	.id_table		= marvell_pci_tbl,
+	.probe			= marvell_init_one,
+	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
+};
+
+static int __init marvell_init(void)
+{
+	return pci_register_driver(&marvell_pci_driver);
+}
+
+static void __exit marvell_exit(void)
+{
+	pci_unregister_driver(&marvell_pci_driver);
+}
+
+module_init(marvell_init);
+module_exit(marvell_exit);
+
+MODULE_AUTHOR("Alan Cox");
+MODULE_DESCRIPTION("SCSI low-level driver for Marvell ATA in legacy mode");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pci, marvell_pci_tbl);
+MODULE_VERSION(DRV_VERSION);
+
diff --git a/drivers/ata/pata_mpiix.c b/drivers/ata/pata_mpiix.c
index e00d406bfdf5..4ccca938675e 100644
--- a/drivers/ata/pata_mpiix.c
+++ b/drivers/ata/pata_mpiix.c
@@ -35,7 +35,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_mpiix"
-#define DRV_VERSION "0.7.2"
+#define DRV_VERSION "0.7.3"
 
 enum {
 	IDETIM = 0x6C,		/* IDE control register */
@@ -159,7 +159,6 @@ static struct scsi_host_template mpiix_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -168,6 +167,8 @@ static struct scsi_host_template mpiix_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations mpiix_port_ops = {
@@ -285,7 +286,9 @@ static struct pci_driver mpiix_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= mpiix,
 	.probe 		= mpiix_init_one,
-	.remove		= mpiix_remove_one
+	.remove		= mpiix_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init mpiix_init(void)
diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c
index 1963a4d35873..cf7fe037471c 100644
--- a/drivers/ata/pata_netcell.c
+++ b/drivers/ata/pata_netcell.c
@@ -16,7 +16,7 @@
 #include <linux/ata.h>
 
 #define DRV_NAME	"pata_netcell"
-#define DRV_VERSION	"0.1.5"
+#define DRV_VERSION	"0.1.6"
 
 /**
  *	netcell_probe_init	-	check for 40/80 pin
@@ -54,8 +54,6 @@ static struct scsi_host_template netcell_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	/* Special handling needed if you have sector or LBA48 limits */
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -65,6 +63,8 @@ static struct scsi_host_template netcell_sht = {
 	.slave_destroy		= ata_scsi_slave_destroy,
 	/* Use standard CHS mapping rules */
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static const struct ata_port_operations netcell_ops = {
@@ -153,6 +153,8 @@ static struct pci_driver netcell_pci_driver = {
 	.id_table		= netcell_pci_tbl,
 	.probe			= netcell_init_one,
 	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
 };
 
 static int __init netcell_init(void)
diff --git a/drivers/ata/pata_ns87410.c b/drivers/ata/pata_ns87410.c
index 7ec800f00ec8..c3032eb9010d 100644
--- a/drivers/ata/pata_ns87410.c
+++ b/drivers/ata/pata_ns87410.c
@@ -28,7 +28,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_ns87410"
-#define DRV_VERSION "0.4.2"
+#define DRV_VERSION "0.4.3"
 
 /**
  *	ns87410_pre_reset		-	probe begin
@@ -149,7 +149,6 @@ static struct scsi_host_template ns87410_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -158,6 +157,8 @@ static struct scsi_host_template ns87410_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations ns87410_port_ops = {
@@ -210,7 +211,9 @@ static struct pci_driver ns87410_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= ns87410,
 	.probe 		= ns87410_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init ns87410_init(void)
diff --git a/drivers/ata/pata_oldpiix.c b/drivers/ata/pata_oldpiix.c
index 8837256632e9..10ac3cc10181 100644
--- a/drivers/ata/pata_oldpiix.c
+++ b/drivers/ata/pata_oldpiix.c
@@ -224,7 +224,6 @@ static struct scsi_host_template oldpiix_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -233,6 +232,8 @@ static struct scsi_host_template oldpiix_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static const struct ata_port_operations oldpiix_pata_ops = {
@@ -314,6 +315,8 @@ static struct pci_driver oldpiix_pci_driver = {
 	.id_table		= oldpiix_pci_tbl,
 	.probe			= oldpiix_init_one,
 	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
 };
 
 static int __init oldpiix_init(void)
diff --git a/drivers/ata/pata_opti.c b/drivers/ata/pata_opti.c
index c6319cf50de4..c2988b0aa8ea 100644
--- a/drivers/ata/pata_opti.c
+++ b/drivers/ata/pata_opti.c
@@ -34,7 +34,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_opti"
-#define DRV_VERSION "0.2.5"
+#define DRV_VERSION "0.2.7"
 
 enum {
 	READ_REG	= 0,	/* index of Read cycle timing register */
@@ -109,30 +109,6 @@ static void opti_write_reg(struct ata_port *ap, u8 val, int reg)
 	outb(0x83, regio + 2);
 }
 
-#if 0
-/**
- *	opti_read_reg		-	control register read
- *	@ap: ATA port
- *	@reg: control register number
- *
- *	The Opti uses magic 'trapdoor' register accesses to do configuration
- *	rather than using PCI space as other controllers do. The double inw
- *	on the error register activates configuration mode. We can then read
- *	the control register
- */
-
-static u8 opti_read_reg(struct ata_port *ap, int reg)
-{
-	unsigned long regio = ap->ioaddr.cmd_addr;
-	u8 ret;
-	inw(regio + 1);
-	inw(regio + 1);
-	outb(3, regio + 2);
-	ret = inb(regio + reg);
-	outb(0x83, regio + 2);
-}
-#endif
-
 /**
  *	opti_set_piomode	-	set initial PIO mode data
  *	@ap: ATA interface
@@ -195,7 +171,6 @@ static struct scsi_host_template opti_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -204,12 +179,13 @@ static struct scsi_host_template opti_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations opti_port_ops = {
 	.port_disable	= ata_port_disable,
 	.set_piomode	= opti_set_piomode,
-/*	.set_dmamode	= opti_set_dmamode, */
 	.tf_load	= ata_tf_load,
 	.tf_read	= ata_tf_read,
 	.check_status 	= ata_check_status,
@@ -267,7 +243,9 @@ static struct pci_driver opti_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= opti,
 	.probe 		= opti_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init opti_init(void)
diff --git a/drivers/ata/pata_optidma.c b/drivers/ata/pata_optidma.c
index 2f4770cce04e..80d111c569dc 100644
--- a/drivers/ata/pata_optidma.c
+++ b/drivers/ata/pata_optidma.c
@@ -33,7 +33,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_optidma"
-#define DRV_VERSION "0.2.2"
+#define DRV_VERSION "0.2.3"
 
 enum {
 	READ_REG	= 0,	/* index of Read cycle timing register */
@@ -352,7 +352,6 @@ static struct scsi_host_template optidma_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -361,6 +360,8 @@ static struct scsi_host_template optidma_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations optidma_port_ops = {
@@ -522,7 +523,9 @@ static struct pci_driver optidma_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= optidma,
 	.probe 		= optidma_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init optidma_init(void)
diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c
index 999922de476e..4ca6fa5dcb42 100644
--- a/drivers/ata/pata_pcmcia.c
+++ b/drivers/ata/pata_pcmcia.c
@@ -62,7 +62,6 @@ static struct scsi_host_template pcmcia_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index beb6d10a234b..76dd1c935dbd 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -134,7 +134,6 @@ static struct scsi_host_template pdc2027x_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -854,7 +853,7 @@ static void __devexit pdc2027x_remove_one(struct pci_dev *pdev)
  */
 static int __init pdc2027x_init(void)
 {
-	return pci_module_init(&pdc2027x_pci_driver);
+	return pci_register_driver(&pdc2027x_pci_driver);
 }
 
 /**
diff --git a/drivers/ata/pata_pdc202xx_old.c b/drivers/ata/pata_pdc202xx_old.c
index 6baf51b2fda1..ad691b9e7743 100644
--- a/drivers/ata/pata_pdc202xx_old.c
+++ b/drivers/ata/pata_pdc202xx_old.c
@@ -21,7 +21,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_pdc202xx_old"
-#define DRV_VERSION "0.2.1"
+#define DRV_VERSION "0.2.3"
 
 /**
  *	pdc2024x_pre_reset		-	probe begin
@@ -63,7 +63,7 @@ static void pdc2026x_error_handler(struct ata_port *ap)
 }
 
 /**
- *	pdc_configure_piomode	-	set chip PIO timing
+ *	pdc202xx_configure_piomode	-	set chip PIO timing
  *	@ap: ATA interface
  *	@adev: ATA device
  *	@pio: PIO mode
@@ -73,7 +73,7 @@ static void pdc2026x_error_handler(struct ata_port *ap)
  *	versa
  */
 
-static void pdc_configure_piomode(struct ata_port *ap, struct ata_device *adev, int pio)
+static void pdc202xx_configure_piomode(struct ata_port *ap, struct ata_device *adev, int pio)
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	int port = 0x60 + 4 * ap->port_no + 2 * adev->devno;
@@ -98,7 +98,7 @@ static void pdc_configure_piomode(struct ata_port *ap, struct ata_device *adev,
 }
 
 /**
- *	pdc_set_piomode	-	set initial PIO mode data
+ *	pdc202xx_set_piomode	-	set initial PIO mode data
  *	@ap: ATA interface
  *	@adev: ATA device
  *
@@ -106,13 +106,13 @@ static void pdc_configure_piomode(struct ata_port *ap, struct ata_device *adev,
  *	but we want to set the PIO timing by default.
  */
 
-static void pdc_set_piomode(struct ata_port *ap, struct ata_device *adev)
+static void pdc202xx_set_piomode(struct ata_port *ap, struct ata_device *adev)
 {
-	pdc_configure_piomode(ap, adev, adev->pio_mode - XFER_PIO_0);
+	pdc202xx_configure_piomode(ap, adev, adev->pio_mode - XFER_PIO_0);
 }
 
 /**
- *	pdc_configure_dmamode	-	set DMA mode in chip
+ *	pdc202xx_configure_dmamode	-	set DMA mode in chip
  *	@ap: ATA interface
  *	@adev: ATA device
  *
@@ -120,7 +120,7 @@ static void pdc_set_piomode(struct ata_port *ap, struct ata_device *adev)
  *	to occur.
  */
 
-static void pdc_set_dmamode(struct ata_port *ap, struct ata_device *adev)
+static void pdc202xx_set_dmamode(struct ata_port *ap, struct ata_device *adev)
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	int port = 0x60 + 4 * ap->port_no + 2 * adev->devno;
@@ -184,7 +184,7 @@ static void pdc2026x_bmdma_start(struct ata_queued_cmd *qc)
 
 	/* The DMA clocks may have been trashed by a reset. FIXME: make conditional
 	   and move to qc_issue ? */
-	pdc_set_dmamode(ap, qc->dev);
+	pdc202xx_set_dmamode(ap, qc->dev);
 
 	/* Cases the state machine will not complete correctly without help */
 	if ((tf->flags & ATA_TFLAG_LBA48) ||  tf->protocol == ATA_PROT_ATAPI_DMA)
@@ -254,7 +254,7 @@ static void pdc2026x_dev_config(struct ata_port *ap, struct ata_device *adev)
 	adev->max_sectors = 256;
 }
 
-static struct scsi_host_template pdc_sht = {
+static struct scsi_host_template pdc202xx_sht = {
 	.module			= THIS_MODULE,
 	.name			= DRV_NAME,
 	.ioctl			= ata_scsi_ioctl,
@@ -262,7 +262,6 @@ static struct scsi_host_template pdc_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -271,12 +270,14 @@ static struct scsi_host_template pdc_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations pdc2024x_port_ops = {
 	.port_disable	= ata_port_disable,
-	.set_piomode	= pdc_set_piomode,
-	.set_dmamode	= pdc_set_dmamode,
+	.set_piomode	= pdc202xx_set_piomode,
+	.set_dmamode	= pdc202xx_set_dmamode,
 	.mode_filter	= ata_pci_default_filter,
 	.tf_load	= ata_tf_load,
 	.tf_read	= ata_tf_read,
@@ -308,8 +309,8 @@ static struct ata_port_operations pdc2024x_port_ops = {
 
 static struct ata_port_operations pdc2026x_port_ops = {
 	.port_disable	= ata_port_disable,
-	.set_piomode	= pdc_set_piomode,
-	.set_dmamode	= pdc_set_dmamode,
+	.set_piomode	= pdc202xx_set_piomode,
+	.set_dmamode	= pdc202xx_set_dmamode,
 	.mode_filter	= ata_pci_default_filter,
 	.tf_load	= ata_tf_load,
 	.tf_read	= ata_tf_read,
@@ -340,11 +341,11 @@ static struct ata_port_operations pdc2026x_port_ops = {
 	.host_stop	= ata_host_stop
 };
 
-static int pdc_init_one(struct pci_dev *dev, const struct pci_device_id *id)
+static int pdc202xx_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	static struct ata_port_info info[3] = {
 		{
-			.sht = &pdc_sht,
+			.sht = &pdc202xx_sht,
 			.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
 			.pio_mask = 0x1f,
 			.mwdma_mask = 0x07,
@@ -352,7 +353,7 @@ static int pdc_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 			.port_ops = &pdc2024x_port_ops
 		},
 		{
-			.sht = &pdc_sht,
+			.sht = &pdc202xx_sht,
 			.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
 			.pio_mask = 0x1f,
 			.mwdma_mask = 0x07,
@@ -360,7 +361,7 @@ static int pdc_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 			.port_ops = &pdc2026x_port_ops
 		},
 		{
-			.sht = &pdc_sht,
+			.sht = &pdc202xx_sht,
 			.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
 			.pio_mask = 0x1f,
 			.mwdma_mask = 0x07,
@@ -386,7 +387,7 @@ static int pdc_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 	return ata_pci_init_one(dev, port_info, 2);
 }
 
-static const struct pci_device_id pdc[] = {
+static const struct pci_device_id pdc202xx[] = {
 	{ PCI_VDEVICE(PROMISE, PCI_DEVICE_ID_PROMISE_20246), 0 },
 	{ PCI_VDEVICE(PROMISE, PCI_DEVICE_ID_PROMISE_20262), 1 },
 	{ PCI_VDEVICE(PROMISE, PCI_DEVICE_ID_PROMISE_20263), 1 },
@@ -396,28 +397,30 @@ static const struct pci_device_id pdc[] = {
 	{ },
 };
 
-static struct pci_driver pdc_pci_driver = {
+static struct pci_driver pdc202xx_pci_driver = {
 	.name 		= DRV_NAME,
-	.id_table	= pdc,
-	.probe 		= pdc_init_one,
-	.remove		= ata_pci_remove_one
+	.id_table	= pdc202xx,
+	.probe 		= pdc202xx_init_one,
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
-static int __init pdc_init(void)
+static int __init pdc202xx_init(void)
 {
-	return pci_register_driver(&pdc_pci_driver);
+	return pci_register_driver(&pdc202xx_pci_driver);
 }
 
-static void __exit pdc_exit(void)
+static void __exit pdc202xx_exit(void)
 {
-	pci_unregister_driver(&pdc_pci_driver);
+	pci_unregister_driver(&pdc202xx_pci_driver);
 }
 
 MODULE_AUTHOR("Alan Cox");
 MODULE_DESCRIPTION("low-level driver for Promise 2024x and 20262-20267");
 MODULE_LICENSE("GPL");
-MODULE_DEVICE_TABLE(pci, pdc);
+MODULE_DEVICE_TABLE(pci, pdc202xx);
 MODULE_VERSION(DRV_VERSION);
 
-module_init(pdc_init);
-module_exit(pdc_exit);
+module_init(pdc202xx_init);
+module_exit(pdc202xx_exit);
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
new file mode 100644
index 000000000000..443b1d85c6c4
--- /dev/null
+++ b/drivers/ata/pata_platform.c
@@ -0,0 +1,295 @@
+/*
+ * Generic platform device PATA driver
+ *
+ * Copyright (C) 2006  Paul Mundt
+ *
+ * Based on pata_pcmcia:
+ *
+ *   Copyright 2005-2006 Red Hat Inc <alan@redhat.com>, all rights reserved.
+ *
+ * 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/init.h>
+#include <linux/blkdev.h>
+#include <scsi/scsi_host.h>
+#include <linux/ata.h>
+#include <linux/libata.h>
+#include <linux/platform_device.h>
+#include <linux/pata_platform.h>
+
+#define DRV_NAME "pata_platform"
+#define DRV_VERSION "0.1.2"
+
+static int pio_mask = 1;
+
+/*
+ * Provide our own set_mode() as we don't want to change anything that has
+ * already been configured..
+ */
+static void pata_platform_set_mode(struct ata_port *ap)
+{
+	int i;
+
+	for (i = 0; i < ATA_MAX_DEVICES; i++) {
+		struct ata_device *dev = &ap->device[i];
+
+		if (ata_dev_enabled(dev)) {
+			/* We don't really care */
+			dev->pio_mode = dev->xfer_mode = XFER_PIO_0;
+			dev->xfer_shift = ATA_SHIFT_PIO;
+			dev->flags |= ATA_DFLAG_PIO;
+		}
+	}
+}
+
+static void pata_platform_host_stop(struct ata_host *host)
+{
+	int i;
+
+	/*
+	 * Unmap the bases for MMIO
+	 */
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+
+		if (ap->flags & ATA_FLAG_MMIO) {
+			iounmap((void __iomem *)ap->ioaddr.ctl_addr);
+			iounmap((void __iomem *)ap->ioaddr.cmd_addr);
+		}
+	}
+}
+
+static struct scsi_host_template pata_platform_sht = {
+	.module			= THIS_MODULE,
+	.name			= DRV_NAME,
+	.ioctl			= ata_scsi_ioctl,
+	.queuecommand		= ata_scsi_queuecmd,
+	.can_queue		= ATA_DEF_QUEUE,
+	.this_id		= ATA_SHT_THIS_ID,
+	.sg_tablesize		= LIBATA_MAX_PRD,
+	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
+	.emulated		= ATA_SHT_EMULATED,
+	.use_clustering		= ATA_SHT_USE_CLUSTERING,
+	.proc_name		= DRV_NAME,
+	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.slave_configure	= ata_scsi_slave_config,
+	.slave_destroy		= ata_scsi_slave_destroy,
+	.bios_param		= ata_std_bios_param,
+};
+
+static struct ata_port_operations pata_platform_port_ops = {
+	.set_mode		= pata_platform_set_mode,
+
+	.port_disable		= ata_port_disable,
+	.tf_load		= ata_tf_load,
+	.tf_read		= ata_tf_read,
+	.check_status		= ata_check_status,
+	.exec_command		= ata_exec_command,
+	.dev_select		= ata_std_dev_select,
+
+	.freeze			= ata_bmdma_freeze,
+	.thaw			= ata_bmdma_thaw,
+	.error_handler		= ata_bmdma_error_handler,
+	.post_internal_cmd	= ata_bmdma_post_internal_cmd,
+
+	.qc_prep		= ata_qc_prep,
+	.qc_issue		= ata_qc_issue_prot,
+
+	.data_xfer		= ata_pio_data_xfer_noirq,
+
+	.irq_handler		= ata_interrupt,
+	.irq_clear		= ata_bmdma_irq_clear,
+
+	.port_start		= ata_port_start,
+	.port_stop		= ata_port_stop,
+	.host_stop		= pata_platform_host_stop
+};
+
+static void pata_platform_setup_port(struct ata_ioports *ioaddr,
+				     struct pata_platform_info *info)
+{
+	unsigned int shift = 0;
+
+	/* Fixup the port shift for platforms that need it */
+	if (info && info->ioport_shift)
+		shift = info->ioport_shift;
+
+	ioaddr->data_addr	= ioaddr->cmd_addr + (ATA_REG_DATA    << shift);
+	ioaddr->error_addr	= ioaddr->cmd_addr + (ATA_REG_ERR     << shift);
+	ioaddr->feature_addr	= ioaddr->cmd_addr + (ATA_REG_FEATURE << shift);
+	ioaddr->nsect_addr	= ioaddr->cmd_addr + (ATA_REG_NSECT   << shift);
+	ioaddr->lbal_addr	= ioaddr->cmd_addr + (ATA_REG_LBAL    << shift);
+	ioaddr->lbam_addr	= ioaddr->cmd_addr + (ATA_REG_LBAM    << shift);
+	ioaddr->lbah_addr	= ioaddr->cmd_addr + (ATA_REG_LBAH    << shift);
+	ioaddr->device_addr	= ioaddr->cmd_addr + (ATA_REG_DEVICE  << shift);
+	ioaddr->status_addr	= ioaddr->cmd_addr + (ATA_REG_STATUS  << shift);
+	ioaddr->command_addr	= ioaddr->cmd_addr + (ATA_REG_CMD     << shift);
+}
+
+/**
+ *	pata_platform_probe		-	attach a platform interface
+ *	@pdev: platform device
+ *
+ *	Register a platform bus IDE interface. Such interfaces are PIO and we
+ *	assume do not support IRQ sharing.
+ *
+ *	Platform devices are expected to contain 3 resources per port:
+ *
+ *		- I/O Base (IORESOURCE_IO or IORESOURCE_MEM)
+ *		- CTL Base (IORESOURCE_IO or IORESOURCE_MEM)
+ *		- IRQ	   (IORESOURCE_IRQ)
+ *
+ *	If the base resources are both mem types, the ioremap() is handled
+ *	here. For IORESOURCE_IO, it's assumed that there's no remapping
+ *	necessary.
+ */
+static int __devinit pata_platform_probe(struct platform_device *pdev)
+{
+	struct resource *io_res, *ctl_res;
+	struct ata_probe_ent ae;
+	unsigned int mmio;
+	int ret;
+
+	/*
+	 * Simple resource validation ..
+	 */
+	if (unlikely(pdev->num_resources != 3)) {
+		dev_err(&pdev->dev, "invalid number of resources\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Get the I/O base first
+	 */
+	io_res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+	if (io_res == NULL) {
+		io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (unlikely(io_res == NULL))
+			return -EINVAL;
+	}
+
+	/*
+	 * Then the CTL base
+	 */
+	ctl_res = platform_get_resource(pdev, IORESOURCE_IO, 1);
+	if (ctl_res == NULL) {
+		ctl_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		if (unlikely(ctl_res == NULL))
+			return -EINVAL;
+	}
+
+	/*
+	 * Check for MMIO
+	 */
+	mmio = (( io_res->flags == IORESOURCE_MEM) &&
+		(ctl_res->flags == IORESOURCE_MEM));
+
+	/*
+	 * Now that that's out of the way, wire up the port..
+	 */
+	memset(&ae, 0, sizeof(struct ata_probe_ent));
+	INIT_LIST_HEAD(&ae.node);
+	ae.dev = &pdev->dev;
+	ae.port_ops = &pata_platform_port_ops;
+	ae.sht = &pata_platform_sht;
+	ae.n_ports = 1;
+	ae.pio_mask = pio_mask;
+	ae.irq = platform_get_irq(pdev, 0);
+	ae.irq_flags = 0;
+	ae.port_flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST;
+
+	/*
+	 * Handle the MMIO case
+	 */
+	if (mmio) {
+		ae.port_flags |= ATA_FLAG_MMIO;
+
+		ae.port[0].cmd_addr = (unsigned long)ioremap(io_res->start,
+				io_res->end - io_res->start + 1);
+		if (unlikely(!ae.port[0].cmd_addr)) {
+			dev_err(&pdev->dev, "failed to remap IO base\n");
+			return -ENXIO;
+		}
+
+		ae.port[0].ctl_addr = (unsigned long)ioremap(ctl_res->start,
+				ctl_res->end - ctl_res->start + 1);
+		if (unlikely(!ae.port[0].ctl_addr)) {
+			dev_err(&pdev->dev, "failed to remap CTL base\n");
+			ret = -ENXIO;
+			goto bad_remap;
+		}
+	} else {
+		ae.port[0].cmd_addr = io_res->start;
+		ae.port[0].ctl_addr = ctl_res->start;
+	}
+
+	ae.port[0].altstatus_addr = ae.port[0].ctl_addr;
+
+	pata_platform_setup_port(&ae.port[0], pdev->dev.platform_data);
+
+	if (unlikely(ata_device_add(&ae) == 0)) {
+		ret = -ENODEV;
+		goto add_failed;
+	}
+
+	return 0;
+
+add_failed:
+	if (ae.port[0].ctl_addr && mmio)
+		iounmap((void __iomem *)ae.port[0].ctl_addr);
+bad_remap:
+	if (ae.port[0].cmd_addr && mmio)
+		iounmap((void __iomem *)ae.port[0].cmd_addr);
+
+	return ret;
+}
+
+/**
+ *	pata_platform_remove	-	unplug a platform interface
+ *	@pdev: platform device
+ *
+ *	A platform bus ATA device has been unplugged. Perform the needed
+ *	cleanup. Also called on module unload for any active devices.
+ */
+static int __devexit pata_platform_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ata_host *host = dev_get_drvdata(dev);
+
+	ata_host_remove(host);
+	dev_set_drvdata(dev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver pata_platform_driver = {
+	.probe		= pata_platform_probe,
+	.remove		= __devexit_p(pata_platform_remove),
+	.driver = {
+		.name		= DRV_NAME,
+		.owner		= THIS_MODULE,
+	},
+};
+
+static int __init pata_platform_init(void)
+{
+	return platform_driver_register(&pata_platform_driver);
+}
+
+static void __exit pata_platform_exit(void)
+{
+	platform_driver_unregister(&pata_platform_driver);
+}
+module_init(pata_platform_init);
+module_exit(pata_platform_exit);
+
+module_param(pio_mask, int, 0);
+
+MODULE_AUTHOR("Paul Mundt");
+MODULE_DESCRIPTION("low-level driver for platform device ATA");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/ata/pata_qdi.c b/drivers/ata/pata_qdi.c
index 314938dea1fc..36f621abc390 100644
--- a/drivers/ata/pata_qdi.c
+++ b/drivers/ata/pata_qdi.c
@@ -157,7 +157,6 @@ static struct scsi_host_template qdi_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_radisys.c b/drivers/ata/pata_radisys.c
index 048c2bb21ef1..065541d034ad 100644
--- a/drivers/ata/pata_radisys.c
+++ b/drivers/ata/pata_radisys.c
@@ -220,7 +220,6 @@ static struct scsi_host_template radisys_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -229,6 +228,8 @@ static struct scsi_host_template radisys_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static const struct ata_port_operations radisys_pata_ops = {
@@ -311,6 +312,8 @@ static struct pci_driver radisys_pci_driver = {
 	.id_table		= radisys_pci_tbl,
 	.probe			= radisys_init_one,
 	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
 };
 
 static int __init radisys_init(void)
diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c
index e4e5ea423fef..3677c642c9f9 100644
--- a/drivers/ata/pata_rz1000.c
+++ b/drivers/ata/pata_rz1000.c
@@ -21,7 +21,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_rz1000"
-#define DRV_VERSION	"0.2.2"
+#define DRV_VERSION	"0.2.3"
 
 
 /**
@@ -83,7 +83,6 @@ static struct scsi_host_template rz1000_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -92,6 +91,8 @@ static struct scsi_host_template rz1000_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations rz1000_port_ops = {
@@ -129,6 +130,19 @@ static struct ata_port_operations rz1000_port_ops = {
 	.host_stop	= ata_host_stop
 };
 
+static int rz1000_fifo_disable(struct pci_dev *pdev)
+{
+	u16 reg;
+	/* Be exceptionally paranoid as we must be sure to apply the fix */
+	if (pci_read_config_word(pdev, 0x40, &reg) != 0)
+		return -1;
+	reg &= 0xDFFF;
+	if (pci_write_config_word(pdev, 0x40, reg) != 0)
+		return -1;
+	printk(KERN_INFO DRV_NAME ": disabled chipset readahead.\n");
+	return 0;
+}
+
 /**
  *	rz1000_init_one - Register RZ1000 ATA PCI device with kernel services
  *	@pdev: PCI device to register
@@ -143,7 +157,6 @@ static int rz1000_init_one (struct pci_dev *pdev, const struct pci_device_id *en
 {
 	static int printed_version;
 	struct ata_port_info *port_info[2];
-	u16 reg;
 	static struct ata_port_info info = {
 		.sht = &rz1000_sht,
 		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
@@ -154,23 +167,25 @@ static int rz1000_init_one (struct pci_dev *pdev, const struct pci_device_id *en
 	if (!printed_version++)
 		printk(KERN_DEBUG DRV_NAME " version " DRV_VERSION "\n");
 
-	/* Be exceptionally paranoid as we must be sure to apply the fix */
-	if (pci_read_config_word(pdev, 0x40, &reg) != 0)
-		goto fail;
-	reg &= 0xDFFF;
-	if (pci_write_config_word(pdev, 0x40, reg) != 0)
-		goto fail;
-	printk(KERN_INFO DRV_NAME ": disabled chipset readahead.\n");
-
-	port_info[0] = &info;
-	port_info[1] = &info;
-	return ata_pci_init_one(pdev, port_info, 2);
-fail:
+	if (rz1000_fifo_disable(pdev) == 0) {
+		port_info[0] = &info;
+		port_info[1] = &info;
+		return ata_pci_init_one(pdev, port_info, 2);
+	}
 	printk(KERN_ERR DRV_NAME ": failed to disable read-ahead on chipset..\n");
 	/* Not safe to use so skip */
 	return -ENODEV;
 }
 
+static int rz1000_reinit_one(struct pci_dev *pdev)
+{
+	/* If this fails on resume (which is a "cant happen" case), we
+	   must stop as any progress risks data loss */
+	if (rz1000_fifo_disable(pdev))
+		panic("rz1000 fifo");
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id pata_rz1000[] = {
 	{ PCI_VDEVICE(PCTECH, PCI_DEVICE_ID_PCTECH_RZ1000), },
 	{ PCI_VDEVICE(PCTECH, PCI_DEVICE_ID_PCTECH_RZ1001), },
@@ -182,7 +197,9 @@ static struct pci_driver rz1000_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= pata_rz1000,
 	.probe 		= rz1000_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= rz1000_reinit_one,
 };
 
 static int __init rz1000_init(void)
diff --git a/drivers/ata/pata_sc1200.c b/drivers/ata/pata_sc1200.c
index 0c75dae74764..a3b35bc50394 100644
--- a/drivers/ata/pata_sc1200.c
+++ b/drivers/ata/pata_sc1200.c
@@ -40,7 +40,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"sc1200"
-#define DRV_VERSION	"0.2.3"
+#define DRV_VERSION	"0.2.4"
 
 #define SC1200_REV_A	0x00
 #define SC1200_REV_B1	0x01
@@ -186,7 +186,6 @@ static struct scsi_host_template sc1200_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -195,6 +194,8 @@ static struct scsi_host_template sc1200_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations sc1200_port_ops = {
@@ -264,7 +265,9 @@ static struct pci_driver sc1200_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= sc1200,
 	.probe 		= sc1200_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init sc1200_init(void)
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index be7f60efcb61..f02b6a3b0f10 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -41,7 +41,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_serverworks"
-#define DRV_VERSION "0.3.7"
+#define DRV_VERSION "0.3.9"
 
 #define SVWKS_CSB5_REVISION_NEW	0x92 /* min PCI_REVISION_ID for UDMA5 (A2.0) */
 #define SVWKS_CSB6_REVISION	0xa0 /* min PCI_REVISION_ID for UDMA4 (A1.0) */
@@ -318,7 +318,6 @@ static struct scsi_host_template serverworks_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -327,6 +326,8 @@ static struct scsi_host_template serverworks_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations serverworks_osb4_port_ops = {
@@ -554,6 +555,30 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 	return ata_pci_init_one(pdev, port_info, ports);
 }
 
+static int serverworks_reinit_one(struct pci_dev *pdev)
+{
+	/* Force master latency timer to 64 PCI clocks */
+	pci_write_config_byte(pdev, PCI_LATENCY_TIMER, 0x40);
+	
+	switch (pdev->device)
+	{
+		case PCI_DEVICE_ID_SERVERWORKS_OSB4IDE:
+			serverworks_fixup_osb4(pdev);
+			break;
+		case PCI_DEVICE_ID_SERVERWORKS_CSB5IDE:
+			ata_pci_clear_simplex(pdev);
+			/* fall through */
+		case PCI_DEVICE_ID_SERVERWORKS_CSB6IDE:
+		case PCI_DEVICE_ID_SERVERWORKS_CSB6IDE2:
+			serverworks_fixup_csb(pdev);
+			break;
+		case PCI_DEVICE_ID_SERVERWORKS_HT1000IDE:
+			serverworks_fixup_ht1000(pdev);
+			break;
+	}
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id serverworks[] = {
 	{ PCI_VDEVICE(SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_OSB4IDE), 0},
 	{ PCI_VDEVICE(SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_CSB5IDE), 2},
@@ -568,7 +593,9 @@ static struct pci_driver serverworks_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= serverworks,
 	.probe 		= serverworks_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= serverworks_reinit_one,
 };
 
 static int __init serverworks_init(void)
diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c
index 11942fd03b55..32cf0bfa8921 100644
--- a/drivers/ata/pata_sil680.c
+++ b/drivers/ata/pata_sil680.c
@@ -33,7 +33,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_sil680"
-#define DRV_VERSION "0.3.2"
+#define DRV_VERSION "0.4.1"
 
 /**
  *	sil680_selreg		-	return register base
@@ -218,7 +218,6 @@ static struct scsi_host_template sil680_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -263,32 +262,20 @@ static struct ata_port_operations sil680_port_ops = {
 	.host_stop	= ata_host_stop
 };
 
-static int sil680_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+/**
+ *	sil680_init_chip		-	chip setup
+ *	@pdev: PCI device
+ *
+ *	Perform all the chip setup which must be done both when the device
+ *	is powered up on boot and when we resume in case we resumed from RAM.
+ *	Returns the final clock settings.
+ */
+ 
+static u8 sil680_init_chip(struct pci_dev *pdev)
 {
-	static struct ata_port_info info = {
-		.sht = &sil680_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
-		.pio_mask = 0x1f,
-		.mwdma_mask = 0x07,
-		.udma_mask = 0x7f,
-		.port_ops = &sil680_port_ops
-	};
-	static struct ata_port_info info_slow = {
-		.sht = &sil680_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
-		.pio_mask = 0x1f,
-		.mwdma_mask = 0x07,
-		.udma_mask = 0x3f,
-		.port_ops = &sil680_port_ops
-	};
-	static struct ata_port_info *port_info[2] = {&info, &info};
-	static int printed_version;
 	u32 class_rev	= 0;
 	u8 tmpbyte	= 0;
 
-	if (!printed_version++)
-		dev_printk(KERN_DEBUG, &pdev->dev, "version " DRV_VERSION "\n");
-
         pci_read_config_dword(pdev, PCI_CLASS_REVISION, &class_rev);
         class_rev &= 0xff;
         /* FIXME: double check */
@@ -323,8 +310,6 @@ static int sil680_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_read_config_byte(pdev,   0x8A, &tmpbyte);
 	printk(KERN_INFO "sil680: BA5_EN = %d clock = %02X\n",
 			tmpbyte & 1, tmpbyte & 0x30);
-	if ((tmpbyte & 0x30) == 0)
-		port_info[0] = port_info[1] = &info_slow;
 
 	pci_write_config_byte(pdev,  0xA1, 0x72);
 	pci_write_config_word(pdev,  0xA2, 0x328A);
@@ -343,11 +328,51 @@ static int sil680_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		case 0x20: printk(KERN_INFO "sil680: Using PCI clock.\n");break;
 		/* This last case is _NOT_ ok */
 		case 0x30: printk(KERN_ERR "sil680: Clock disabled ?\n");
-			return -EIO;
+	}
+	return tmpbyte & 0x30;
+}
+
+static int sil680_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	static struct ata_port_info info = {
+		.sht = &sil680_sht,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.pio_mask = 0x1f,
+		.mwdma_mask = 0x07,
+		.udma_mask = 0x7f,
+		.port_ops = &sil680_port_ops
+	};
+	static struct ata_port_info info_slow = {
+		.sht = &sil680_sht,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.pio_mask = 0x1f,
+		.mwdma_mask = 0x07,
+		.udma_mask = 0x3f,
+		.port_ops = &sil680_port_ops
+	};
+	static struct ata_port_info *port_info[2] = {&info, &info};
+	static int printed_version;
+
+	if (!printed_version++)
+		dev_printk(KERN_DEBUG, &pdev->dev, "version " DRV_VERSION "\n");
+
+	switch(sil680_init_chip(pdev))
+	{
+		case 0:
+			port_info[0] = port_info[1] = &info_slow;
+			break;
+		case 0x30:
+			return -ENODEV;
 	}
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+static int sil680_reinit_one(struct pci_dev *pdev)
+{
+	sil680_init_chip(pdev);
+	return ata_pci_device_resume(pdev);
+}
+
 static const struct pci_device_id sil680[] = {
 	{ PCI_VDEVICE(CMD, PCI_DEVICE_ID_SII_680), },
 
@@ -358,7 +383,9 @@ static struct pci_driver sil680_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= sil680,
 	.probe 		= sil680_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= sil680_reinit_one,
 };
 
 static int __init sil680_init(void)
diff --git a/drivers/ata/pata_sis.c b/drivers/ata/pata_sis.c
index 91e85f90941d..916cedb3d755 100644
--- a/drivers/ata/pata_sis.c
+++ b/drivers/ata/pata_sis.c
@@ -34,7 +34,7 @@
 #include <linux/ata.h>
 
 #define DRV_NAME	"pata_sis"
-#define DRV_VERSION	"0.4.4"
+#define DRV_VERSION	"0.4.5"
 
 struct sis_chipset {
 	u16 device;			/* PCI host ID */
@@ -538,7 +538,6 @@ static struct scsi_host_template sis_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -547,6 +546,8 @@ static struct scsi_host_template sis_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static const struct ata_port_operations sis_133_ops = {
@@ -1000,6 +1001,8 @@ static struct pci_driver sis_pci_driver = {
 	.id_table		= sis_pci_tbl,
 	.probe			= sis_init_one,
 	.remove			= ata_pci_remove_one,
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
 };
 
 static int __init sis_init(void)
diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c
index dc1cfc6d805b..e94f515ef54b 100644
--- a/drivers/ata/pata_sl82c105.c
+++ b/drivers/ata/pata_sl82c105.c
@@ -230,7 +230,6 @@ static struct scsi_host_template sl82c105_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
diff --git a/drivers/ata/pata_triflex.c b/drivers/ata/pata_triflex.c
index bfda1f7e760a..a142971f1307 100644
--- a/drivers/ata/pata_triflex.c
+++ b/drivers/ata/pata_triflex.c
@@ -43,7 +43,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_triflex"
-#define DRV_VERSION "0.2.5"
+#define DRV_VERSION "0.2.7"
 
 /**
  *	triflex_prereset		-	probe begin
@@ -185,7 +185,6 @@ static struct scsi_host_template triflex_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -194,6 +193,8 @@ static struct scsi_host_template triflex_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations triflex_port_ops = {
@@ -258,7 +259,9 @@ static struct pci_driver triflex_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= triflex,
 	.probe 		= triflex_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
 };
 
 static int __init triflex_init(void)
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index c5f1616d224d..cc09d47fb927 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -23,6 +23,7 @@
  *	VIA VT8233c	-	UDMA100
  *	VIA VT8235	-	UDMA133
  *	VIA VT8237	-	UDMA133
+ *	VIA VT8251	-	UDMA133
  *
  *	Most registers remain compatible across chips. Others start reserved
  *	and acquire sensible semantics if set to 1 (eg cable detect). A few
@@ -60,7 +61,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME "pata_via"
-#define DRV_VERSION "0.1.14"
+#define DRV_VERSION "0.2.0"
 
 /*
  *	The following comes directly from Vojtech Pavlik's ide/pci/via82cxxx
@@ -94,6 +95,7 @@ static const struct via_isa_bridge {
 	u8 rev_max;
 	u16 flags;
 } via_isa_bridges[] = {
+	{ "vt8251",	PCI_DEVICE_ID_VIA_8251,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
 	{ "cx700",	PCI_DEVICE_ID_VIA_CX700,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
 	{ "vt6410",	PCI_DEVICE_ID_VIA_6410,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_NO_ENABLES},
 	{ "vt8237a",	PCI_DEVICE_ID_VIA_8237A,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
@@ -288,7 +290,6 @@ static struct scsi_host_template via_sht = {
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
 	.sg_tablesize		= LIBATA_MAX_PRD,
-	.max_sectors		= ATA_MAX_SECTORS,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= ATA_SHT_USE_CLUSTERING,
@@ -297,6 +298,8 @@ static struct scsi_host_template via_sht = {
 	.slave_configure	= ata_scsi_slave_config,
 	.slave_destroy		= ata_scsi_slave_destroy,
 	.bios_param		= ata_std_bios_param,
+	.resume			= ata_scsi_device_resume,
+	.suspend		= ata_scsi_device_suspend,
 };
 
 static struct ata_port_operations via_port_ops = {
@@ -370,8 +373,42 @@ static struct ata_port_operations via_port_ops_noirq = {
 };
 
 /**
+ *	via_config_fifo		-	set up the FIFO
+ *	@pdev: PCI device
+ *	@flags: configuration flags
+ *
+ *	Set the FIFO properties for this device if neccessary. Used both on
+ *	set up and on and the resume path
+ */
+
+static void via_config_fifo(struct pci_dev *pdev, unsigned int flags)
+{
+	u8 enable;
+	
+	/* 0x40 low bits indicate enabled channels */
+	pci_read_config_byte(pdev, 0x40 , &enable);
+	enable &= 3;
+	
+	if (flags & VIA_SET_FIFO) {
+		u8 fifo_setting[4] = {0x00, 0x60, 0x00, 0x20};
+		u8 fifo;
+
+		pci_read_config_byte(pdev, 0x43, &fifo);
+
+		/* Clear PREQ# until DDACK# for errata */
+		if (flags & VIA_BAD_PREQ)
+			fifo &= 0x7F;
+		else
+			fifo &= 0x9f;
+		/* Turn on FIFO for enabled channels */
+		fifo |= fifo_setting[enable];
+		pci_write_config_byte(pdev, 0x43, fifo);
+	}
+}
+
+/**
  *	via_init_one		-	discovery callback
- *	@pdev: PCI device ID
+ *	@pdev: PCI device
  *	@id: PCI table info
  *
  *	A VIA IDE interface has been discovered. Figure out what revision
@@ -383,7 +420,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Early VIA without UDMA support */
 	static struct ata_port_info via_mwdma_info = {
 		.sht = &via_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SETXFER_POLLING,
 		.pio_mask = 0x1f,
 		.mwdma_mask = 0x07,
 		.port_ops = &via_port_ops
@@ -391,7 +428,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Ditto with IRQ masking required */
 	static struct ata_port_info via_mwdma_info_borked = {
 		.sht = &via_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SETXFER_POLLING,
 		.pio_mask = 0x1f,
 		.mwdma_mask = 0x07,
 		.port_ops = &via_port_ops_noirq,
@@ -399,7 +436,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* VIA UDMA 33 devices (and borked 66) */
 	static struct ata_port_info via_udma33_info = {
 		.sht = &via_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SETXFER_POLLING,
 		.pio_mask = 0x1f,
 		.mwdma_mask = 0x07,
 		.udma_mask = 0x7,
@@ -408,7 +445,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* VIA UDMA 66 devices */
 	static struct ata_port_info via_udma66_info = {
 		.sht = &via_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SETXFER_POLLING,
 		.pio_mask = 0x1f,
 		.mwdma_mask = 0x07,
 		.udma_mask = 0x1f,
@@ -417,7 +454,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* VIA UDMA 100 devices */
 	static struct ata_port_info via_udma100_info = {
 		.sht = &via_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SETXFER_POLLING,
 		.pio_mask = 0x1f,
 		.mwdma_mask = 0x07,
 		.udma_mask = 0x3f,
@@ -426,7 +463,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* UDMA133 with bad AST (All current 133) */
 	static struct ata_port_info via_udma133_info = {
 		.sht = &via_sht,
-		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SETXFER_POLLING,
 		.pio_mask = 0x1f,
 		.mwdma_mask = 0x07,
 		.udma_mask = 0x7f,	/* FIXME: should check north bridge */
@@ -471,21 +508,8 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	/* Initialise the FIFO for the enabled channels. */
-	if (config->flags & VIA_SET_FIFO) {
-		u8 fifo_setting[4] = {0x00, 0x60, 0x00, 0x20};
-		u8 fifo;
-
-		pci_read_config_byte(pdev, 0x43, &fifo);
-
-		/* Clear PREQ# until DDACK# for errata */
-		if (config->flags & VIA_BAD_PREQ)
-			fifo &= 0x7F;
-		else
-			fifo &= 0x9f;
-		/* Turn on FIFO for enabled channels */
-		fifo |= fifo_setting[enable];
-		pci_write_config_byte(pdev, 0x43, fifo);
-	}
+	via_config_fifo(pdev, config->flags);
+	
 	/* Clock set up */
 	switch(config->flags & VIA_UDMA) {
 		case VIA_UDMA_NONE:
@@ -529,6 +553,39 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_init_one(pdev, port_info, 2);
 }
 
+/**
+ *	via_reinit_one		-	reinit after resume
+ *	@pdev; PCI device
+ *
+ *	Called when the VIA PATA device is resumed. We must then
+ *	reconfigure the fifo and other setup we may have altered. In
+ *	addition the kernel needs to have the resume methods on PCI
+ *	quirk supported.
+ */
+
+static int via_reinit_one(struct pci_dev *pdev)
+{
+	u32 timing;
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	const struct via_isa_bridge *config = host->private_data;
+	
+	via_config_fifo(pdev, config->flags);
+
+	if ((config->flags & VIA_UDMA) == VIA_UDMA_66) {
+		/* The 66 MHz devices require we enable the clock */
+		pci_read_config_dword(pdev, 0x50, &timing);
+		timing |= 0x80008;
+		pci_write_config_dword(pdev, 0x50, timing);
+	}
+	if (config->flags & VIA_BAD_CLK66) {
+		/* Disable the 66MHz clock on problem devices */
+		pci_read_config_dword(pdev, 0x50, &timing);
+		timing &= ~0x80008;
+		pci_write_config_dword(pdev, 0x50, timing);
+	}
+	return ata_pci_device_resume(pdev);	
+}
+
 static const struct pci_device_id via[] = {
 	{ PCI_VDEVICE(VIA, PCI_DEVICE_ID_VIA_82C576_1), },
 	{ PCI_VDEVICE(VIA, PCI_DEVICE_ID_VIA_82C586_1), },
@@ -542,7 +599,9 @@ static struct pci_driver via_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= via,
 	.probe 		= via_init_one,
-	.remove		= ata_pci_remove_one
+	.remove		= ata_pci_remove_one,
+	.suspend	= ata_pci_device_suspend,
+	.resume		= via_reinit_one,
 };
 
 static int __init via_init(void)
diff --git a/drivers/ata/pata_winbond.c b/drivers/ata/pata_winbond.c
new file mode 100644
index 000000000000..3ea345cde52e
--- /dev/null
+++ b/drivers/ata/pata_winbond.c
@@ -0,0 +1,306 @@
+/*
+ *    pata_winbond.c - Winbond VLB ATA controllers
+ *	(C) 2006 Red Hat <alan@redhat.com>
+ *
+ *    Support for the Winbond 83759A when operating in advanced mode.
+ *    Multichip mode is not currently supported.
+ */
+ 
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <scsi/scsi_host.h>
+#include <linux/libata.h>
+#include <linux/platform_device.h>
+
+#define DRV_NAME "pata_winbond"
+#define DRV_VERSION "0.0.1"
+
+#define NR_HOST 4	/* Two winbond controllers, two channels each */
+
+struct winbond_data {
+	unsigned long config;
+	struct platform_device *platform_dev;
+};
+
+static struct ata_host *winbond_host[NR_HOST];
+static struct winbond_data winbond_data[NR_HOST];
+static int nr_winbond_host;
+
+#ifdef MODULE
+static int probe_winbond = 1;
+#else
+static int probe_winbond;
+#endif
+
+static spinlock_t winbond_lock = SPIN_LOCK_UNLOCKED;
+
+static void winbond_writecfg(unsigned long port, u8 reg, u8 val)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&winbond_lock, flags);
+	outb(reg, port + 0x01);
+	outb(val, port + 0x02);
+	spin_unlock_irqrestore(&winbond_lock, flags);
+}
+
+static u8 winbond_readcfg(unsigned long port, u8 reg)
+{
+	u8 val;
+
+	unsigned long flags;
+	spin_lock_irqsave(&winbond_lock, flags);
+	outb(reg, port + 0x01);
+	val = inb(port + 0x02);
+	spin_unlock_irqrestore(&winbond_lock, flags);
+
+	return val;
+}
+
+static void winbond_set_piomode(struct ata_port *ap, struct ata_device *adev)
+{
+	struct ata_timing t;
+	struct winbond_data *winbond = ap->host->private_data;
+	int active, recovery;
+	u8 reg;
+	int timing = 0x88 + (ap->port_no * 4) + (adev->devno * 2);
+
+	reg = winbond_readcfg(winbond->config, 0x81);
+	
+	/* Get the timing data in cycles */
+	if (reg & 0x40)		/* Fast VLB bus, assume 50MHz */
+		ata_timing_compute(adev, adev->pio_mode, &t, 20000, 1000);
+	else
+		ata_timing_compute(adev, adev->pio_mode, &t, 30303, 1000);
+
+	active = (FIT(t.active, 3, 17) - 1) & 0x0F;
+	recovery = (FIT(t.recover, 1, 15) + 1) & 0x0F;
+	timing = (active << 4) | recovery;
+	winbond_writecfg(winbond->config, timing, reg);
+	
+	/* Load the setup timing */
+	
+	reg = 0x35;
+	if (adev->class != ATA_DEV_ATA)
+		reg |= 0x08;	/* FIFO off */
+	if (!ata_pio_need_iordy(adev))
+		reg |= 0x02;	/* IORDY off */
+	reg |= (FIT(t.setup, 0, 3) << 6);
+	winbond_writecfg(winbond->config, timing + 1, reg);
+}
+
+
+static void winbond_data_xfer(struct ata_device *adev, unsigned char *buf, unsigned int buflen, int write_data)
+{
+	struct ata_port *ap = adev->ap;
+	int slop = buflen & 3;
+
+	if (ata_id_has_dword_io(adev->id)) {
+		if (write_data)
+			outsl(ap->ioaddr.data_addr, buf, buflen >> 2);
+		else
+			insl(ap->ioaddr.data_addr, buf, buflen >> 2);
+
+		if (unlikely(slop)) {
+			u32 pad;
+			if (write_data) {
+				memcpy(&pad, buf + buflen - slop, slop);
+				outl(le32_to_cpu(pad), ap->ioaddr.data_addr);
+			} else {
+				pad = cpu_to_le16(inl(ap->ioaddr.data_addr));
+				memcpy(buf + buflen - slop, &pad, slop);
+			}
+		}
+	} else
+		ata_pio_data_xfer(adev, buf, buflen, write_data);
+}
+
+static struct scsi_host_template winbond_sht = {
+	.module			= THIS_MODULE,
+	.name			= DRV_NAME,
+	.ioctl			= ata_scsi_ioctl,
+	.queuecommand		= ata_scsi_queuecmd,
+	.can_queue		= ATA_DEF_QUEUE,
+	.this_id		= ATA_SHT_THIS_ID,
+	.sg_tablesize		= LIBATA_MAX_PRD,
+	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
+	.emulated		= ATA_SHT_EMULATED,
+	.use_clustering		= ATA_SHT_USE_CLUSTERING,
+	.proc_name		= DRV_NAME,
+	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.slave_configure	= ata_scsi_slave_config,
+	.slave_destroy		= ata_scsi_slave_destroy,
+	.bios_param		= ata_std_bios_param,
+};
+
+static struct ata_port_operations winbond_port_ops = {
+	.port_disable	= ata_port_disable,
+	.set_piomode	= winbond_set_piomode,
+
+	.tf_load	= ata_tf_load,
+	.tf_read	= ata_tf_read,
+	.check_status 	= ata_check_status,
+	.exec_command	= ata_exec_command,
+	.dev_select 	= ata_std_dev_select,
+
+	.freeze		= ata_bmdma_freeze,
+	.thaw		= ata_bmdma_thaw,
+	.error_handler	= ata_bmdma_error_handler,
+	.post_internal_cmd = ata_bmdma_post_internal_cmd,
+
+	.qc_prep 	= ata_qc_prep,
+	.qc_issue	= ata_qc_issue_prot,
+
+	.data_xfer	= winbond_data_xfer,
+
+	.irq_handler	= ata_interrupt,
+	.irq_clear	= ata_bmdma_irq_clear,
+
+	.port_start	= ata_port_start,
+	.port_stop	= ata_port_stop,
+	.host_stop	= ata_host_stop
+};
+
+/**
+ *	winbond_init_one		-	attach a winbond interface
+ *	@type: Type to display
+ *	@io: I/O port start
+ *	@irq: interrupt line
+ *	@fast: True if on a > 33Mhz VLB
+ *
+ *	Register a VLB bus IDE interface. Such interfaces are PIO and we
+ *	assume do not support IRQ sharing.
+ */
+
+static __init int winbond_init_one(unsigned long port)
+{
+	struct ata_probe_ent ae;
+	struct platform_device *pdev;
+	int ret;
+	u8 reg;
+	int i;
+
+	reg = winbond_readcfg(port, 0x81);
+	reg |= 0x80;	/* jumpered mode off */
+	winbond_writecfg(port, 0x81, reg);
+	reg = winbond_readcfg(port, 0x83);
+	reg |= 0xF0;	/* local control */
+	winbond_writecfg(port, 0x83, reg);
+	reg = winbond_readcfg(port, 0x85);
+	reg |= 0xF0;	/* programmable timing */
+	winbond_writecfg(port, 0x85, reg);
+
+	reg = winbond_readcfg(port, 0x81);
+	
+	if (!(reg & 0x03))		/* Disabled */
+		return 0;
+
+	for (i = 0; i < 2 ; i ++) {
+
+		if (reg & (1 << i)) {		
+			/*
+			 *	Fill in a probe structure first of all
+			 */
+
+			pdev = platform_device_register_simple(DRV_NAME, nr_winbond_host, NULL, 0);
+			if (pdev == NULL)
+				return -ENOMEM;
+
+			memset(&ae, 0, sizeof(struct ata_probe_ent));
+			INIT_LIST_HEAD(&ae.node);
+			ae.dev = &pdev->dev;
+
+			ae.port_ops = &winbond_port_ops;
+			ae.pio_mask = 0x1F;
+
+			ae.sht = &winbond_sht;
+	
+			ae.n_ports = 1;
+			ae.irq = 14 + i;
+			ae.irq_flags = 0;
+			ae.port_flags = ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST;
+			ae.port[0].cmd_addr = 0x1F0 - (0x80 * i);
+			ae.port[0].altstatus_addr = ae.port[0].cmd_addr + 0x0206;
+			ae.port[0].ctl_addr = ae.port[0].altstatus_addr;
+			ata_std_ports(&ae.port[0]);
+			/*
+			 *	Hook in a private data structure per channel
+			 */
+			ae.private_data = &winbond_data[nr_winbond_host];
+			winbond_data[nr_winbond_host].config = port;
+			winbond_data[nr_winbond_host].platform_dev = pdev;
+
+			ret = ata_device_add(&ae);
+			if (ret == 0) {
+				platform_device_unregister(pdev);
+				return -ENODEV;
+			}
+			winbond_host[nr_winbond_host++] = dev_get_drvdata(&pdev->dev);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ *	winbond_init		-	attach winbond interfaces
+ *
+ *	Attach winbond IDE interfaces by scanning the ports it may occupy.
+ */
+
+static __init int winbond_init(void)
+{
+	static const unsigned long config[2] = { 0x130, 0x1B0 };
+
+	int ct = 0;
+	int i;
+	
+	if (probe_winbond == 0)
+		return -ENODEV;
+
+	/*
+ 	 *	Check both base addresses
+	 */
+
+	for (i = 0; i < 2; i++) {
+		if (probe_winbond & (1<<i)) {
+			int ret = 0;
+			unsigned long port = config[i];
+
+			if (request_region(port, 2, "pata_winbond")) {
+				ret = winbond_init_one(port);
+				if(ret <= 0)
+					release_region(port, 2);
+				else ct+= ret;
+			}
+		}
+	}
+	if (ct != 0)
+		return 0;
+	return -ENODEV;
+}
+
+static __exit void winbond_exit(void)
+{
+	int i;
+
+	for (i = 0; i < nr_winbond_host; i++) {
+		ata_host_remove(winbond_host[i]);
+		release_region(winbond_data[i].config, 2);
+		platform_device_unregister(winbond_data[i].platform_dev);
+	}
+}
+
+MODULE_AUTHOR("Alan Cox");
+MODULE_DESCRIPTION("low-level driver for Winbond VL ATA");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
+
+module_init(winbond_init);
+module_exit(winbond_exit);
+
+module_param(probe_winbond, int, 0);
+
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index d65ebfd7c7b2..0d316eb3c214 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -29,6 +29,11 @@
  *  NV-specific details such as register offsets, SATA phy location,
  *  hotplug info, etc.
  *
+ *  CK804/MCP04 controllers support an alternate programming interface
+ *  similar to the ADMA specification (with some modifications).
+ *  This allows the use of NCQ. Non-DMA-mapped ATA commands are still
+ *  sent through the legacy interface.
+ *
  */
 
 #include <linux/kernel.h>
@@ -40,10 +45,13 @@
 #include <linux/interrupt.h>
 #include <linux/device.h>
 #include <scsi/scsi_host.h>
+#include <scsi/scsi_device.h>
 #include <linux/libata.h>
 
 #define DRV_NAME			"sata_nv"
-#define DRV_VERSION			"2.0"
+#define DRV_VERSION			"3.2"
+
+#define NV_ADMA_DMA_BOUNDARY		0xffffffffUL
 
 enum {
 	NV_PORTS			= 2,
@@ -78,8 +86,138 @@ enum {
 	// For PCI config register 20
 	NV_MCP_SATA_CFG_20		= 0x50,
 	NV_MCP_SATA_CFG_20_SATA_SPACE_EN = 0x04,
+	NV_MCP_SATA_CFG_20_PORT0_EN	= (1 << 17),
+	NV_MCP_SATA_CFG_20_PORT1_EN	= (1 << 16),
+	NV_MCP_SATA_CFG_20_PORT0_PWB_EN	= (1 << 14),
+	NV_MCP_SATA_CFG_20_PORT1_PWB_EN	= (1 << 12),
+
+	NV_ADMA_MAX_CPBS		= 32,
+	NV_ADMA_CPB_SZ			= 128,
+	NV_ADMA_APRD_SZ			= 16,
+	NV_ADMA_SGTBL_LEN		= (1024 - NV_ADMA_CPB_SZ) /
+					   NV_ADMA_APRD_SZ,
+	NV_ADMA_SGTBL_TOTAL_LEN		= NV_ADMA_SGTBL_LEN + 5,
+	NV_ADMA_SGTBL_SZ                = NV_ADMA_SGTBL_LEN * NV_ADMA_APRD_SZ,
+	NV_ADMA_PORT_PRIV_DMA_SZ        = NV_ADMA_MAX_CPBS *
+					   (NV_ADMA_CPB_SZ + NV_ADMA_SGTBL_SZ),
+
+	/* BAR5 offset to ADMA general registers */
+	NV_ADMA_GEN			= 0x400,
+	NV_ADMA_GEN_CTL			= 0x00,
+	NV_ADMA_NOTIFIER_CLEAR		= 0x30,
+
+	/* BAR5 offset to ADMA ports */
+	NV_ADMA_PORT			= 0x480,
+
+	/* size of ADMA port register space  */
+	NV_ADMA_PORT_SIZE		= 0x100,
+
+	/* ADMA port registers */
+	NV_ADMA_CTL			= 0x40,
+	NV_ADMA_CPB_COUNT		= 0x42,
+	NV_ADMA_NEXT_CPB_IDX		= 0x43,
+	NV_ADMA_STAT			= 0x44,
+	NV_ADMA_CPB_BASE_LOW		= 0x48,
+	NV_ADMA_CPB_BASE_HIGH		= 0x4C,
+	NV_ADMA_APPEND			= 0x50,
+	NV_ADMA_NOTIFIER		= 0x68,
+	NV_ADMA_NOTIFIER_ERROR		= 0x6C,
+
+	/* NV_ADMA_CTL register bits */
+	NV_ADMA_CTL_HOTPLUG_IEN		= (1 << 0),
+	NV_ADMA_CTL_CHANNEL_RESET	= (1 << 5),
+	NV_ADMA_CTL_GO			= (1 << 7),
+	NV_ADMA_CTL_AIEN		= (1 << 8),
+	NV_ADMA_CTL_READ_NON_COHERENT	= (1 << 11),
+	NV_ADMA_CTL_WRITE_NON_COHERENT	= (1 << 12),
+
+	/* CPB response flag bits */
+	NV_CPB_RESP_DONE		= (1 << 0),
+	NV_CPB_RESP_ATA_ERR		= (1 << 3),
+	NV_CPB_RESP_CMD_ERR		= (1 << 4),
+	NV_CPB_RESP_CPB_ERR		= (1 << 7),
+
+	/* CPB control flag bits */
+	NV_CPB_CTL_CPB_VALID		= (1 << 0),
+	NV_CPB_CTL_QUEUE		= (1 << 1),
+	NV_CPB_CTL_APRD_VALID		= (1 << 2),
+	NV_CPB_CTL_IEN			= (1 << 3),
+	NV_CPB_CTL_FPDMA		= (1 << 4),
+
+	/* APRD flags */
+	NV_APRD_WRITE			= (1 << 1),
+	NV_APRD_END			= (1 << 2),
+	NV_APRD_CONT			= (1 << 3),
+
+	/* NV_ADMA_STAT flags */
+	NV_ADMA_STAT_TIMEOUT		= (1 << 0),
+	NV_ADMA_STAT_HOTUNPLUG		= (1 << 1),
+	NV_ADMA_STAT_HOTPLUG		= (1 << 2),
+	NV_ADMA_STAT_CPBERR		= (1 << 4),
+	NV_ADMA_STAT_SERROR		= (1 << 5),
+	NV_ADMA_STAT_CMD_COMPLETE	= (1 << 6),
+	NV_ADMA_STAT_IDLE		= (1 << 8),
+	NV_ADMA_STAT_LEGACY		= (1 << 9),
+	NV_ADMA_STAT_STOPPED		= (1 << 10),
+	NV_ADMA_STAT_DONE		= (1 << 12),
+	NV_ADMA_STAT_ERR		= NV_ADMA_STAT_CPBERR |
+	 				  NV_ADMA_STAT_TIMEOUT,
+
+	/* port flags */
+	NV_ADMA_PORT_REGISTER_MODE	= (1 << 0),
+	NV_ADMA_ATAPI_SETUP_COMPLETE	= (1 << 1),
+
+};
+
+/* ADMA Physical Region Descriptor - one SG segment */
+struct nv_adma_prd {
+	__le64			addr;
+	__le32			len;
+	u8			flags;
+	u8			packet_len;
+	__le16			reserved;
+};
+
+enum nv_adma_regbits {
+	CMDEND	= (1 << 15),		/* end of command list */
+	WNB	= (1 << 14),		/* wait-not-BSY */
+	IGN	= (1 << 13),		/* ignore this entry */
+	CS1n	= (1 << (4 + 8)),	/* std. PATA signals follow... */
+	DA2	= (1 << (2 + 8)),
+	DA1	= (1 << (1 + 8)),
+	DA0	= (1 << (0 + 8)),
+};
+
+/* ADMA Command Parameter Block
+   The first 5 SG segments are stored inside the Command Parameter Block itself.
+   If there are more than 5 segments the remainder are stored in a separate
+   memory area indicated by next_aprd. */
+struct nv_adma_cpb {
+	u8			resp_flags;    /* 0 */
+	u8			reserved1;     /* 1 */
+	u8			ctl_flags;     /* 2 */
+	/* len is length of taskfile in 64 bit words */
+ 	u8			len;           /* 3  */
+	u8			tag;           /* 4 */
+	u8			next_cpb_idx;  /* 5 */
+	__le16			reserved2;     /* 6-7 */
+	__le16			tf[12];        /* 8-31 */
+	struct nv_adma_prd	aprd[5];       /* 32-111 */
+	__le64			next_aprd;     /* 112-119 */
+	__le64			reserved3;     /* 120-127 */
+};
+
+
+struct nv_adma_port_priv {
+	struct nv_adma_cpb	*cpb;
+	dma_addr_t		cpb_dma;
+	struct nv_adma_prd	*aprd;
+	dma_addr_t		aprd_dma;
+	u8			flags;
 };
 
+#define NV_ADMA_CHECK_INTR(GCTL, PORT) ((GCTL) & ( 1 << (19 + (12 * (PORT)))))
+
 static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent);
 static void nv_ck804_host_stop(struct ata_host *host);
 static irqreturn_t nv_generic_interrupt(int irq, void *dev_instance);
@@ -93,13 +231,28 @@ static void nv_nf2_thaw(struct ata_port *ap);
 static void nv_ck804_freeze(struct ata_port *ap);
 static void nv_ck804_thaw(struct ata_port *ap);
 static void nv_error_handler(struct ata_port *ap);
+static int nv_adma_slave_config(struct scsi_device *sdev);
+static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
+static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
+static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
+static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance);
+static void nv_adma_irq_clear(struct ata_port *ap);
+static int nv_adma_port_start(struct ata_port *ap);
+static void nv_adma_port_stop(struct ata_port *ap);
+static void nv_adma_error_handler(struct ata_port *ap);
+static void nv_adma_host_stop(struct ata_host *host);
+static void nv_adma_bmdma_setup(struct ata_queued_cmd *qc);
+static void nv_adma_bmdma_start(struct ata_queued_cmd *qc);
+static void nv_adma_bmdma_stop(struct ata_queued_cmd *qc);
+static u8 nv_adma_bmdma_status(struct ata_port *ap);
 
 enum nv_host_type
 {
 	GENERIC,
 	NFORCE2,
 	NFORCE3 = NFORCE2,	/* NF2 == NF3 as far as sata_nv is concerned */
-	CK804
+	CK804,
+	ADMA
 };
 
 static const struct pci_device_id nv_pci_tbl[] = {
@@ -160,6 +313,24 @@ static struct scsi_host_template nv_sht = {
 	.bios_param		= ata_std_bios_param,
 };
 
+static struct scsi_host_template nv_adma_sht = {
+	.module			= THIS_MODULE,
+	.name			= DRV_NAME,
+	.ioctl			= ata_scsi_ioctl,
+	.queuecommand		= ata_scsi_queuecmd,
+	.can_queue		= NV_ADMA_MAX_CPBS,
+	.this_id		= ATA_SHT_THIS_ID,
+	.sg_tablesize		= NV_ADMA_SGTBL_TOTAL_LEN,
+	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
+	.emulated		= ATA_SHT_EMULATED,
+	.use_clustering		= ATA_SHT_USE_CLUSTERING,
+	.proc_name		= DRV_NAME,
+	.dma_boundary		= NV_ADMA_DMA_BOUNDARY,
+	.slave_configure	= nv_adma_slave_config,
+	.slave_destroy		= ata_scsi_slave_destroy,
+	.bios_param		= ata_std_bios_param,
+};
+
 static const struct ata_port_operations nv_generic_ops = {
 	.port_disable		= ata_port_disable,
 	.tf_load		= ata_tf_load,
@@ -241,11 +412,40 @@ static const struct ata_port_operations nv_ck804_ops = {
 	.host_stop		= nv_ck804_host_stop,
 };
 
+static const struct ata_port_operations nv_adma_ops = {
+	.port_disable		= ata_port_disable,
+	.tf_load		= ata_tf_load,
+	.tf_read		= ata_tf_read,
+	.check_atapi_dma	= nv_adma_check_atapi_dma,
+	.exec_command		= ata_exec_command,
+	.check_status		= ata_check_status,
+	.dev_select		= ata_std_dev_select,
+	.bmdma_setup		= nv_adma_bmdma_setup,
+	.bmdma_start		= nv_adma_bmdma_start,
+	.bmdma_stop		= nv_adma_bmdma_stop,
+	.bmdma_status		= nv_adma_bmdma_status,
+	.qc_prep		= nv_adma_qc_prep,
+	.qc_issue		= nv_adma_qc_issue,
+	.freeze			= nv_ck804_freeze,
+	.thaw			= nv_ck804_thaw,
+	.error_handler		= nv_adma_error_handler,
+	.post_internal_cmd	= nv_adma_bmdma_stop,
+	.data_xfer		= ata_mmio_data_xfer,
+	.irq_handler		= nv_adma_interrupt,
+	.irq_clear		= nv_adma_irq_clear,
+	.scr_read		= nv_scr_read,
+	.scr_write		= nv_scr_write,
+	.port_start		= nv_adma_port_start,
+	.port_stop		= nv_adma_port_stop,
+	.host_stop		= nv_adma_host_stop,
+};
+
 static struct ata_port_info nv_port_info[] = {
 	/* generic */
 	{
 		.sht		= &nv_sht,
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
+				  ATA_FLAG_HRST_TO_RESUME,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -254,7 +454,8 @@ static struct ata_port_info nv_port_info[] = {
 	/* nforce2/3 */
 	{
 		.sht		= &nv_sht,
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
+				  ATA_FLAG_HRST_TO_RESUME,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -263,12 +464,23 @@ static struct ata_port_info nv_port_info[] = {
 	/* ck804 */
 	{
 		.sht		= &nv_sht,
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
+				  ATA_FLAG_HRST_TO_RESUME,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
 		.port_ops	= &nv_ck804_ops,
 	},
+	/* ADMA */
+	{
+		.sht		= &nv_adma_sht,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
+				  ATA_FLAG_MMIO | ATA_FLAG_NCQ,
+		.pio_mask	= NV_PIO_MASK,
+		.mwdma_mask	= NV_MWDMA_MASK,
+		.udma_mask	= NV_UDMA_MASK,
+		.port_ops	= &nv_adma_ops,
+	},
 };
 
 MODULE_AUTHOR("NVIDIA");
@@ -277,37 +489,220 @@ MODULE_LICENSE("GPL");
 MODULE_DEVICE_TABLE(pci, nv_pci_tbl);
 MODULE_VERSION(DRV_VERSION);
 
-static irqreturn_t nv_generic_interrupt(int irq, void *dev_instance)
+static int adma_enabled = 1;
+
+static inline void __iomem *__nv_adma_ctl_block(void __iomem *mmio,
+					        unsigned int port_no)
 {
-	struct ata_host *host = dev_instance;
-	unsigned int i;
-	unsigned int handled = 0;
-	unsigned long flags;
+	mmio += NV_ADMA_PORT + port_no * NV_ADMA_PORT_SIZE;
+	return mmio;
+}
 
-	spin_lock_irqsave(&host->lock, flags);
+static inline void __iomem *nv_adma_ctl_block(struct ata_port *ap)
+{
+	return __nv_adma_ctl_block(ap->host->mmio_base, ap->port_no);
+}
 
-	for (i = 0; i < host->n_ports; i++) {
-		struct ata_port *ap;
+static inline void __iomem *nv_adma_gen_block(struct ata_port *ap)
+{
+	return (ap->host->mmio_base + NV_ADMA_GEN);
+}
 
-		ap = host->ports[i];
-		if (ap &&
-		    !(ap->flags & ATA_FLAG_DISABLED)) {
-			struct ata_queued_cmd *qc;
+static inline void __iomem *nv_adma_notifier_clear_block(struct ata_port *ap)
+{
+	return (nv_adma_gen_block(ap) + NV_ADMA_NOTIFIER_CLEAR + (4 * ap->port_no));
+}
 
-			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)))
-				handled += ata_host_intr(ap, qc);
-			else
-				// No request pending?  Clear interrupt status
-				// anyway, in case there's one pending.
-				ap->ops->check_status(ap);
-		}
+static void nv_adma_register_mode(struct ata_port *ap)
+{
+	void __iomem *mmio = nv_adma_ctl_block(ap);
+	struct nv_adma_port_priv *pp = ap->private_data;
+	u16 tmp;
+
+	if (pp->flags & NV_ADMA_PORT_REGISTER_MODE)
+		return;
+
+	tmp = readw(mmio + NV_ADMA_CTL);
+	writew(tmp & ~NV_ADMA_CTL_GO, mmio + NV_ADMA_CTL);
+
+	pp->flags |= NV_ADMA_PORT_REGISTER_MODE;
+}
+
+static void nv_adma_mode(struct ata_port *ap)
+{
+	void __iomem *mmio = nv_adma_ctl_block(ap);
+	struct nv_adma_port_priv *pp = ap->private_data;
+	u16 tmp;
 
+	if (!(pp->flags & NV_ADMA_PORT_REGISTER_MODE))
+		return;
+		
+	WARN_ON(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE);
+
+	tmp = readw(mmio + NV_ADMA_CTL);
+	writew(tmp | NV_ADMA_CTL_GO, mmio + NV_ADMA_CTL);
+
+	pp->flags &= ~NV_ADMA_PORT_REGISTER_MODE;
+}
+
+static int nv_adma_slave_config(struct scsi_device *sdev)
+{
+	struct ata_port *ap = ata_shost_to_port(sdev->host);
+	struct nv_adma_port_priv *pp = ap->private_data;
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	u64 bounce_limit;
+	unsigned long segment_boundary;
+	unsigned short sg_tablesize;
+	int rc;
+	int adma_enable;
+	u32 current_reg, new_reg, config_mask;
+
+	rc = ata_scsi_slave_config(sdev);
+
+	if (sdev->id >= ATA_MAX_DEVICES || sdev->channel || sdev->lun)
+		/* Not a proper libata device, ignore */
+		return rc;
+
+	if (ap->device[sdev->id].class == ATA_DEV_ATAPI) {
+		/*
+		 * NVIDIA reports that ADMA mode does not support ATAPI commands.
+		 * Therefore ATAPI commands are sent through the legacy interface.
+		 * However, the legacy interface only supports 32-bit DMA.
+		 * Restrict DMA parameters as required by the legacy interface
+		 * when an ATAPI device is connected.
+		 */
+		bounce_limit = ATA_DMA_MASK;
+		segment_boundary = ATA_DMA_BOUNDARY;
+		/* Subtract 1 since an extra entry may be needed for padding, see
+		   libata-scsi.c */
+		sg_tablesize = LIBATA_MAX_PRD - 1;
+		
+		/* Since the legacy DMA engine is in use, we need to disable ADMA
+		   on the port. */
+		adma_enable = 0;
+		nv_adma_register_mode(ap);
+	}
+	else {
+		bounce_limit = *ap->dev->dma_mask;
+		segment_boundary = NV_ADMA_DMA_BOUNDARY;
+		sg_tablesize = NV_ADMA_SGTBL_TOTAL_LEN;
+		adma_enable = 1;
+	}
+	
+	pci_read_config_dword(pdev, NV_MCP_SATA_CFG_20, &current_reg);
+
+	if(ap->port_no == 1)
+		config_mask = NV_MCP_SATA_CFG_20_PORT1_EN |
+			      NV_MCP_SATA_CFG_20_PORT1_PWB_EN;
+	else
+		config_mask = NV_MCP_SATA_CFG_20_PORT0_EN |
+			      NV_MCP_SATA_CFG_20_PORT0_PWB_EN;
+	
+	if(adma_enable) {
+		new_reg = current_reg | config_mask;
+		pp->flags &= ~NV_ADMA_ATAPI_SETUP_COMPLETE;
+	}
+	else {
+		new_reg = current_reg & ~config_mask;
+		pp->flags |= NV_ADMA_ATAPI_SETUP_COMPLETE;
 	}
+	
+	if(current_reg != new_reg)
+		pci_write_config_dword(pdev, NV_MCP_SATA_CFG_20, new_reg);
+	
+	blk_queue_bounce_limit(sdev->request_queue, bounce_limit);
+	blk_queue_segment_boundary(sdev->request_queue, segment_boundary);
+	blk_queue_max_hw_segments(sdev->request_queue, sg_tablesize);
+	ata_port_printk(ap, KERN_INFO,
+		"bounce limit 0x%llX, segment boundary 0x%lX, hw segs %hu\n",
+		(unsigned long long)bounce_limit, segment_boundary, sg_tablesize);
+	return rc;
+}
 
-	spin_unlock_irqrestore(&host->lock, flags);
+static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc)
+{
+	struct nv_adma_port_priv *pp = qc->ap->private_data;
+	return !(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE);
+}
 
-	return IRQ_RETVAL(handled);
+static unsigned int nv_adma_tf_to_cpb(struct ata_taskfile *tf, __le16 *cpb)
+{
+	unsigned int idx = 0;
+
+	cpb[idx++] = cpu_to_le16((ATA_REG_DEVICE << 8) | tf->device | WNB);
+
+	if ((tf->flags & ATA_TFLAG_LBA48) == 0) {
+		cpb[idx++] = cpu_to_le16(IGN);
+		cpb[idx++] = cpu_to_le16(IGN);
+		cpb[idx++] = cpu_to_le16(IGN);
+		cpb[idx++] = cpu_to_le16(IGN);
+		cpb[idx++] = cpu_to_le16(IGN);
+	}
+	else {
+		cpb[idx++] = cpu_to_le16((ATA_REG_ERR   << 8) | tf->hob_feature);
+		cpb[idx++] = cpu_to_le16((ATA_REG_NSECT << 8) | tf->hob_nsect);
+		cpb[idx++] = cpu_to_le16((ATA_REG_LBAL  << 8) | tf->hob_lbal);
+		cpb[idx++] = cpu_to_le16((ATA_REG_LBAM  << 8) | tf->hob_lbam);
+		cpb[idx++] = cpu_to_le16((ATA_REG_LBAH  << 8) | tf->hob_lbah);
+	}
+	cpb[idx++] = cpu_to_le16((ATA_REG_ERR    << 8) | tf->feature);
+	cpb[idx++] = cpu_to_le16((ATA_REG_NSECT  << 8) | tf->nsect);
+	cpb[idx++] = cpu_to_le16((ATA_REG_LBAL   << 8) | tf->lbal);
+	cpb[idx++] = cpu_to_le16((ATA_REG_LBAM   << 8) | tf->lbam);
+	cpb[idx++] = cpu_to_le16((ATA_REG_LBAH   << 8) | tf->lbah);
+
+	cpb[idx++] = cpu_to_le16((ATA_REG_CMD    << 8) | tf->command | CMDEND);
+
+	return idx;
+}
+
+static void nv_adma_check_cpb(struct ata_port *ap, int cpb_num, int force_err)
+{
+	struct nv_adma_port_priv *pp = ap->private_data;
+	int complete = 0, have_err = 0;
+	u8 flags = pp->cpb[cpb_num].resp_flags;
+
+	VPRINTK("CPB %d, flags=0x%x\n", cpb_num, flags);
+
+	if (flags & NV_CPB_RESP_DONE) {
+		VPRINTK("CPB flags done, flags=0x%x\n", flags);
+		complete = 1;
+	}
+	if (flags & NV_CPB_RESP_ATA_ERR) {
+		ata_port_printk(ap, KERN_ERR, "CPB flags ATA err, flags=0x%x\n", flags);
+		have_err = 1;
+		complete = 1;
+	}
+	if (flags & NV_CPB_RESP_CMD_ERR) {
+		ata_port_printk(ap, KERN_ERR, "CPB flags CMD err, flags=0x%x\n", flags);
+		have_err = 1;
+		complete = 1;
+	}
+	if (flags & NV_CPB_RESP_CPB_ERR) {
+		ata_port_printk(ap, KERN_ERR, "CPB flags CPB err, flags=0x%x\n", flags);
+		have_err = 1;
+		complete = 1;
+	}
+	if(complete || force_err)
+	{
+		struct ata_queued_cmd *qc = ata_qc_from_tag(ap, cpb_num);
+		if(likely(qc)) {
+			u8 ata_status = 0;
+			/* Only use the ATA port status for non-NCQ commands.
+			   For NCQ commands the current status may have nothing to do with
+			   the command just completed. */
+			if(qc->tf.protocol != ATA_PROT_NCQ)
+				ata_status = readb(nv_adma_ctl_block(ap) + (ATA_REG_STATUS * 4));
+
+			if(have_err || force_err)
+				ata_status |= ATA_ERR;
+
+			qc->err_mask |= ac_err_mask(ata_status);
+			DPRINTK("Completing qc from tag %d with err_mask %u\n",cpb_num,
+				qc->err_mask);
+			ata_qc_complete(qc);
+		}
+	}
 }
 
 static int nv_host_intr(struct ata_port *ap, u8 irq_stat)
@@ -341,6 +736,486 @@ static int nv_host_intr(struct ata_port *ap, u8 irq_stat)
 	return 1;
 }
 
+static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance)
+{
+	struct ata_host *host = dev_instance;
+	int i, handled = 0;
+	u32 notifier_clears[2];
+
+	spin_lock(&host->lock);
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+		notifier_clears[i] = 0;
+
+		if (ap && !(ap->flags & ATA_FLAG_DISABLED)) {
+			struct nv_adma_port_priv *pp = ap->private_data;
+			void __iomem *mmio = nv_adma_ctl_block(ap);
+			u16 status;
+			u32 gen_ctl;
+			int have_global_err = 0;
+			u32 notifier, notifier_error;
+
+			/* if in ATA register mode, use standard ata interrupt handler */
+			if (pp->flags & NV_ADMA_PORT_REGISTER_MODE) {
+				u8 irq_stat = readb(host->mmio_base + NV_INT_STATUS_CK804)
+					>> (NV_INT_PORT_SHIFT * i);
+				handled += nv_host_intr(ap, irq_stat);
+				continue;
+			}
+
+			notifier = readl(mmio + NV_ADMA_NOTIFIER);
+			notifier_error = readl(mmio + NV_ADMA_NOTIFIER_ERROR);
+			notifier_clears[i] = notifier | notifier_error;
+
+			gen_ctl = readl(nv_adma_gen_block(ap) + NV_ADMA_GEN_CTL);
+
+			if( !NV_ADMA_CHECK_INTR(gen_ctl, ap->port_no) && !notifier &&
+			    !notifier_error)
+				/* Nothing to do */
+				continue;
+
+			status = readw(mmio + NV_ADMA_STAT);
+
+			/* Clear status. Ensure the controller sees the clearing before we start
+			   looking at any of the CPB statuses, so that any CPB completions after
+			   this point in the handler will raise another interrupt. */
+			writew(status, mmio + NV_ADMA_STAT);
+			readw(mmio + NV_ADMA_STAT); /* flush posted write */
+			rmb();
+
+			/* freeze if hotplugged */
+			if (unlikely(status & (NV_ADMA_STAT_HOTPLUG | NV_ADMA_STAT_HOTUNPLUG))) {
+				ata_port_printk(ap, KERN_NOTICE, "Hotplug event, freezing\n");
+				ata_port_freeze(ap);
+				handled++;
+				continue;
+			}
+
+			if (status & NV_ADMA_STAT_TIMEOUT) {
+				ata_port_printk(ap, KERN_ERR, "timeout, stat=0x%x\n", status);
+				have_global_err = 1;
+			}
+			if (status & NV_ADMA_STAT_CPBERR) {
+				ata_port_printk(ap, KERN_ERR, "CPB error, stat=0x%x\n", status);
+				have_global_err = 1;
+			}
+			if ((status & NV_ADMA_STAT_DONE) || have_global_err) {
+				/** Check CPBs for completed commands */
+
+				if(ata_tag_valid(ap->active_tag))
+					/* Non-NCQ command */
+					nv_adma_check_cpb(ap, ap->active_tag, have_global_err ||
+						(notifier_error & (1 << ap->active_tag)));
+				else {
+					int pos;
+					u32 active = ap->sactive;
+					while( (pos = ffs(active)) ) {
+						pos--;
+						nv_adma_check_cpb(ap, pos, have_global_err ||
+							(notifier_error & (1 << pos)) );
+						active &= ~(1 << pos );
+					}
+				}
+			}
+
+			handled++; /* irq handled if we got here */
+		}
+	}
+	
+	if(notifier_clears[0] || notifier_clears[1]) {
+		/* Note: Both notifier clear registers must be written
+		   if either is set, even if one is zero, according to NVIDIA. */
+		writel(notifier_clears[0], 
+			nv_adma_notifier_clear_block(host->ports[0]));
+		writel(notifier_clears[1], 
+			nv_adma_notifier_clear_block(host->ports[1]));
+	}
+
+	spin_unlock(&host->lock);
+
+	return IRQ_RETVAL(handled);
+}
+
+static void nv_adma_irq_clear(struct ata_port *ap)
+{
+	void __iomem *mmio = nv_adma_ctl_block(ap);
+	u16 status = readw(mmio + NV_ADMA_STAT);
+	u32 notifier = readl(mmio + NV_ADMA_NOTIFIER);
+	u32 notifier_error = readl(mmio + NV_ADMA_NOTIFIER_ERROR);
+	unsigned long dma_stat_addr = ap->ioaddr.bmdma_addr + ATA_DMA_STATUS;
+
+	/* clear ADMA status */
+	writew(status, mmio + NV_ADMA_STAT);
+	writel(notifier | notifier_error,
+	       nv_adma_notifier_clear_block(ap));
+
+	/** clear legacy status */
+	outb(inb(dma_stat_addr), dma_stat_addr);
+}
+
+static void nv_adma_bmdma_setup(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	unsigned int rw = (qc->tf.flags & ATA_TFLAG_WRITE);
+	struct nv_adma_port_priv *pp = ap->private_data;
+	u8 dmactl;
+
+	if(!(pp->flags & NV_ADMA_PORT_REGISTER_MODE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	/* load PRD table addr. */
+	outl(ap->prd_dma, ap->ioaddr.bmdma_addr + ATA_DMA_TABLE_OFS);
+
+	/* specify data direction, triple-check start bit is clear */
+	dmactl = inb(ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
+	dmactl &= ~(ATA_DMA_WR | ATA_DMA_START);
+	if (!rw)
+		dmactl |= ATA_DMA_WR;
+
+	outb(dmactl, ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
+
+	/* issue r/w command */
+	ata_exec_command(ap, &qc->tf);
+}
+
+static void nv_adma_bmdma_start(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct nv_adma_port_priv *pp = ap->private_data;
+	u8 dmactl;
+
+	if(!(pp->flags & NV_ADMA_PORT_REGISTER_MODE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	/* start host DMA transaction */
+	dmactl = inb(ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
+	outb(dmactl | ATA_DMA_START,
+	     ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
+}
+
+static void nv_adma_bmdma_stop(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct nv_adma_port_priv *pp = ap->private_data;
+
+	if(!(pp->flags & NV_ADMA_PORT_REGISTER_MODE))
+		return;
+
+	/* clear start/stop bit */
+	outb(inb(ap->ioaddr.bmdma_addr + ATA_DMA_CMD) & ~ATA_DMA_START,
+		ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
+
+	/* one-PIO-cycle guaranteed wait, per spec, for HDMA1:0 transition */
+	ata_altstatus(ap);        /* dummy read */
+}
+
+static u8 nv_adma_bmdma_status(struct ata_port *ap)
+{
+	struct nv_adma_port_priv *pp = ap->private_data;
+
+	WARN_ON(!(pp->flags & NV_ADMA_PORT_REGISTER_MODE));
+
+	return inb(ap->ioaddr.bmdma_addr + ATA_DMA_STATUS);
+}
+
+static int nv_adma_port_start(struct ata_port *ap)
+{
+	struct device *dev = ap->host->dev;
+	struct nv_adma_port_priv *pp;
+	int rc;
+	void *mem;
+	dma_addr_t mem_dma;
+	void __iomem *mmio = nv_adma_ctl_block(ap);
+	u16 tmp;
+
+	VPRINTK("ENTER\n");
+
+	rc = ata_port_start(ap);
+	if (rc)
+		return rc;
+
+	pp = kzalloc(sizeof(*pp), GFP_KERNEL);
+	if (!pp) {
+		rc = -ENOMEM;
+		goto err_out;
+	}
+
+	mem = dma_alloc_coherent(dev, NV_ADMA_PORT_PRIV_DMA_SZ,
+				 &mem_dma, GFP_KERNEL);
+
+	if (!mem) {
+		rc = -ENOMEM;
+		goto err_out_kfree;
+	}
+	memset(mem, 0, NV_ADMA_PORT_PRIV_DMA_SZ);
+
+	/*
+	 * First item in chunk of DMA memory:
+	 * 128-byte command parameter block (CPB)
+	 * one for each command tag
+	 */
+	pp->cpb     = mem;
+	pp->cpb_dma = mem_dma;
+
+	writel(mem_dma & 0xFFFFFFFF, 	mmio + NV_ADMA_CPB_BASE_LOW);
+	writel((mem_dma >> 16 ) >> 16,	mmio + NV_ADMA_CPB_BASE_HIGH);
+
+	mem     += NV_ADMA_MAX_CPBS * NV_ADMA_CPB_SZ;
+	mem_dma += NV_ADMA_MAX_CPBS * NV_ADMA_CPB_SZ;
+
+	/*
+	 * Second item: block of ADMA_SGTBL_LEN s/g entries
+	 */
+	pp->aprd = mem;
+	pp->aprd_dma = mem_dma;
+
+	ap->private_data = pp;
+
+	/* clear any outstanding interrupt conditions */
+	writew(0xffff, mmio + NV_ADMA_STAT);
+
+	/* initialize port variables */
+	pp->flags = NV_ADMA_PORT_REGISTER_MODE;
+
+	/* clear CPB fetch count */
+	writew(0, mmio + NV_ADMA_CPB_COUNT);
+
+	/* clear GO for register mode */
+	tmp = readw(mmio + NV_ADMA_CTL);
+	writew(tmp & ~NV_ADMA_CTL_GO, mmio + NV_ADMA_CTL);
+
+	tmp = readw(mmio + NV_ADMA_CTL);
+	writew(tmp | NV_ADMA_CTL_CHANNEL_RESET, mmio + NV_ADMA_CTL);
+	readl( mmio + NV_ADMA_CTL );	/* flush posted write */
+	udelay(1);
+	writew(tmp & ~NV_ADMA_CTL_CHANNEL_RESET, mmio + NV_ADMA_CTL);
+	readl( mmio + NV_ADMA_CTL );	/* flush posted write */
+
+	return 0;
+
+err_out_kfree:
+	kfree(pp);
+err_out:
+	ata_port_stop(ap);
+	return rc;
+}
+
+static void nv_adma_port_stop(struct ata_port *ap)
+{
+	struct device *dev = ap->host->dev;
+	struct nv_adma_port_priv *pp = ap->private_data;
+	void __iomem *mmio = nv_adma_ctl_block(ap);
+
+	VPRINTK("ENTER\n");
+
+	writew(0, mmio + NV_ADMA_CTL);
+
+	ap->private_data = NULL;
+	dma_free_coherent(dev, NV_ADMA_PORT_PRIV_DMA_SZ, pp->cpb, pp->cpb_dma);
+	kfree(pp);
+	ata_port_stop(ap);
+}
+
+
+static void nv_adma_setup_port(struct ata_probe_ent *probe_ent, unsigned int port)
+{
+	void __iomem *mmio = probe_ent->mmio_base;
+	struct ata_ioports *ioport = &probe_ent->port[port];
+
+	VPRINTK("ENTER\n");
+
+	mmio += NV_ADMA_PORT + port * NV_ADMA_PORT_SIZE;
+
+	ioport->cmd_addr	= (unsigned long) mmio;
+	ioport->data_addr	= (unsigned long) mmio + (ATA_REG_DATA * 4);
+	ioport->error_addr	=
+	ioport->feature_addr	= (unsigned long) mmio + (ATA_REG_ERR * 4);
+	ioport->nsect_addr	= (unsigned long) mmio + (ATA_REG_NSECT * 4);
+	ioport->lbal_addr	= (unsigned long) mmio + (ATA_REG_LBAL * 4);
+	ioport->lbam_addr	= (unsigned long) mmio + (ATA_REG_LBAM * 4);
+	ioport->lbah_addr	= (unsigned long) mmio + (ATA_REG_LBAH * 4);
+	ioport->device_addr	= (unsigned long) mmio + (ATA_REG_DEVICE * 4);
+	ioport->status_addr	=
+	ioport->command_addr	= (unsigned long) mmio + (ATA_REG_STATUS * 4);
+	ioport->altstatus_addr	=
+	ioport->ctl_addr	= (unsigned long) mmio + 0x20;
+}
+
+static int nv_adma_host_init(struct ata_probe_ent *probe_ent)
+{
+	struct pci_dev *pdev = to_pci_dev(probe_ent->dev);
+	unsigned int i;
+	u32 tmp32;
+
+	VPRINTK("ENTER\n");
+
+	/* enable ADMA on the ports */
+	pci_read_config_dword(pdev, NV_MCP_SATA_CFG_20, &tmp32);
+	tmp32 |= NV_MCP_SATA_CFG_20_PORT0_EN |
+		 NV_MCP_SATA_CFG_20_PORT0_PWB_EN |
+		 NV_MCP_SATA_CFG_20_PORT1_EN |
+		 NV_MCP_SATA_CFG_20_PORT1_PWB_EN;
+
+	pci_write_config_dword(pdev, NV_MCP_SATA_CFG_20, tmp32);
+
+	for (i = 0; i < probe_ent->n_ports; i++)
+		nv_adma_setup_port(probe_ent, i);
+
+	for (i = 0; i < probe_ent->n_ports; i++) {
+		void __iomem *mmio = __nv_adma_ctl_block(probe_ent->mmio_base, i);
+		u16 tmp;
+
+		/* enable interrupt, clear reset if not already clear */
+		tmp = readw(mmio + NV_ADMA_CTL);
+		writew(tmp | NV_ADMA_CTL_AIEN, mmio + NV_ADMA_CTL);
+	}
+
+	return 0;
+}
+
+static void nv_adma_fill_aprd(struct ata_queued_cmd *qc,
+			      struct scatterlist *sg,
+			      int idx,
+			      struct nv_adma_prd *aprd)
+{
+	u8 flags;
+
+	memset(aprd, 0, sizeof(struct nv_adma_prd));
+
+	flags = 0;
+	if (qc->tf.flags & ATA_TFLAG_WRITE)
+		flags |= NV_APRD_WRITE;
+	if (idx == qc->n_elem - 1)
+		flags |= NV_APRD_END;
+	else if (idx != 4)
+		flags |= NV_APRD_CONT;
+
+	aprd->addr  = cpu_to_le64(((u64)sg_dma_address(sg)));
+	aprd->len   = cpu_to_le32(((u32)sg_dma_len(sg))); /* len in bytes */
+	aprd->flags = flags;
+}
+
+static void nv_adma_fill_sg(struct ata_queued_cmd *qc, struct nv_adma_cpb *cpb)
+{
+	struct nv_adma_port_priv *pp = qc->ap->private_data;
+	unsigned int idx;
+	struct nv_adma_prd *aprd;
+	struct scatterlist *sg;
+
+	VPRINTK("ENTER\n");
+
+	idx = 0;
+
+	ata_for_each_sg(sg, qc) {
+		aprd = (idx < 5) ? &cpb->aprd[idx] : &pp->aprd[NV_ADMA_SGTBL_LEN * qc->tag + (idx-5)];
+		nv_adma_fill_aprd(qc, sg, idx, aprd);
+		idx++;
+	}
+	if (idx > 5)
+		cpb->next_aprd = cpu_to_le64(((u64)(pp->aprd_dma + NV_ADMA_SGTBL_SZ * qc->tag)));
+}
+
+static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
+{
+	struct nv_adma_port_priv *pp = qc->ap->private_data;
+	struct nv_adma_cpb *cpb = &pp->cpb[qc->tag];
+	u8 ctl_flags = NV_CPB_CTL_CPB_VALID |
+		       NV_CPB_CTL_APRD_VALID |
+		       NV_CPB_CTL_IEN;
+
+	VPRINTK("qc->flags = 0x%lx\n", qc->flags);
+
+	if (!(qc->flags & ATA_QCFLAG_DMAMAP) ||
+	     (pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
+		nv_adma_register_mode(qc->ap);
+		ata_qc_prep(qc);
+		return;
+	}
+
+	memset(cpb, 0, sizeof(struct nv_adma_cpb));
+
+	cpb->len		= 3;
+	cpb->tag		= qc->tag;
+	cpb->next_cpb_idx	= 0;
+
+	/* turn on NCQ flags for NCQ commands */
+	if (qc->tf.protocol == ATA_PROT_NCQ)
+		ctl_flags |= NV_CPB_CTL_QUEUE | NV_CPB_CTL_FPDMA;
+
+	nv_adma_tf_to_cpb(&qc->tf, cpb->tf);
+
+	nv_adma_fill_sg(qc, cpb);
+
+	/* Be paranoid and don't let the device see NV_CPB_CTL_CPB_VALID until we are
+	   finished filling in all of the contents */
+	wmb();
+	cpb->ctl_flags = ctl_flags;
+}
+
+static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
+{
+	struct nv_adma_port_priv *pp = qc->ap->private_data;
+	void __iomem *mmio = nv_adma_ctl_block(qc->ap);
+
+	VPRINTK("ENTER\n");
+
+	if (!(qc->flags & ATA_QCFLAG_DMAMAP) ||
+	     (pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
+		/* use ATA register mode */
+		VPRINTK("no dmamap or ATAPI, using ATA register mode: 0x%lx\n", qc->flags);
+		nv_adma_register_mode(qc->ap);
+		return ata_qc_issue_prot(qc);
+	} else
+		nv_adma_mode(qc->ap);
+
+	/* write append register, command tag in lower 8 bits
+	   and (number of cpbs to append -1) in top 8 bits */
+	wmb();
+	writew(qc->tag, mmio + NV_ADMA_APPEND);
+
+	DPRINTK("Issued tag %u\n",qc->tag);
+
+	return 0;
+}
+
+static irqreturn_t nv_generic_interrupt(int irq, void *dev_instance)
+{
+	struct ata_host *host = dev_instance;
+	unsigned int i;
+	unsigned int handled = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap;
+
+		ap = host->ports[i];
+		if (ap &&
+		    !(ap->flags & ATA_FLAG_DISABLED)) {
+			struct ata_queued_cmd *qc;
+
+			qc = ata_qc_from_tag(ap, ap->active_tag);
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)))
+				handled += ata_host_intr(ap, qc);
+			else
+				// No request pending?  Clear interrupt status
+				// anyway, in case there's one pending.
+				ap->ops->check_status(ap);
+		}
+
+	}
+
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	return IRQ_RETVAL(handled);
+}
+
 static irqreturn_t nv_do_interrupt(struct ata_host *host, u8 irq_stat)
 {
 	int i, handled = 0;
@@ -466,6 +1341,56 @@ static void nv_error_handler(struct ata_port *ap)
 			   nv_hardreset, ata_std_postreset);
 }
 
+static void nv_adma_error_handler(struct ata_port *ap)
+{
+	struct nv_adma_port_priv *pp = ap->private_data;
+	if(!(pp->flags & NV_ADMA_PORT_REGISTER_MODE)) {
+		void __iomem *mmio = nv_adma_ctl_block(ap);
+		int i;
+		u16 tmp;
+
+		u32 notifier = readl(mmio + NV_ADMA_NOTIFIER);
+		u32 notifier_error = readl(mmio + NV_ADMA_NOTIFIER_ERROR);
+		u32 gen_ctl = readl(nv_adma_gen_block(ap) + NV_ADMA_GEN_CTL);
+		u32 status = readw(mmio + NV_ADMA_STAT);
+
+		ata_port_printk(ap, KERN_ERR, "EH in ADMA mode, notifier 0x%X "
+			"notifier_error 0x%X gen_ctl 0x%X status 0x%X\n",
+			notifier, notifier_error, gen_ctl, status);
+
+		for( i=0;i<NV_ADMA_MAX_CPBS;i++) {
+			struct nv_adma_cpb *cpb = &pp->cpb[i];
+			if( cpb->ctl_flags || cpb->resp_flags )
+				ata_port_printk(ap, KERN_ERR,
+					"CPB %d: ctl_flags 0x%x, resp_flags 0x%x\n",
+					i, cpb->ctl_flags, cpb->resp_flags);
+		}
+
+		/* Push us back into port register mode for error handling. */
+		nv_adma_register_mode(ap);
+
+		ata_port_printk(ap, KERN_ERR, "Resetting port\n");
+
+		/* Mark all of the CPBs as invalid to prevent them from being executed */
+		for( i=0;i<NV_ADMA_MAX_CPBS;i++)
+			pp->cpb[i].ctl_flags &= ~NV_CPB_CTL_CPB_VALID;
+
+		/* clear CPB fetch count */
+		writew(0, mmio + NV_ADMA_CPB_COUNT);
+
+		/* Reset channel */
+		tmp = readw(mmio + NV_ADMA_CTL);
+		writew(tmp | NV_ADMA_CTL_CHANNEL_RESET, mmio + NV_ADMA_CTL);
+		readl( mmio + NV_ADMA_CTL );	/* flush posted write */
+		udelay(1);
+		writew(tmp & ~NV_ADMA_CTL_CHANNEL_RESET, mmio + NV_ADMA_CTL);
+		readl( mmio + NV_ADMA_CTL );	/* flush posted write */
+	}
+
+	ata_bmdma_drive_eh(ap, ata_std_prereset, ata_std_softreset,
+			   nv_hardreset, ata_std_postreset);
+}
+
 static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	static int printed_version = 0;
@@ -475,6 +1400,8 @@ static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	int rc;
 	u32 bar;
 	unsigned long base;
+	unsigned long type = ent->driver_data;
+	int mask_set = 0;
 
         // Make sure this is a SATA controller by counting the number of bars
         // (NVIDIA SATA controllers will always have six bars).  Otherwise,
@@ -483,7 +1410,7 @@ static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (pci_resource_start(pdev, bar) == 0)
 			return -ENODEV;
 
-	if (!printed_version++)
+	if (	!printed_version++)
 		dev_printk(KERN_DEBUG, &pdev->dev, "version " DRV_VERSION "\n");
 
 	rc = pci_enable_device(pdev);
@@ -496,16 +1423,26 @@ static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_disable;
 	}
 
-	rc = pci_set_dma_mask(pdev, ATA_DMA_MASK);
-	if (rc)
-		goto err_out_regions;
-	rc = pci_set_consistent_dma_mask(pdev, ATA_DMA_MASK);
-	if (rc)
-		goto err_out_regions;
+	if(type >= CK804 && adma_enabled) {
+		dev_printk(KERN_NOTICE, &pdev->dev, "Using ADMA mode\n");
+		type = ADMA;
+		if(!pci_set_dma_mask(pdev, DMA_64BIT_MASK) &&
+		   !pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK))
+			mask_set = 1;
+	}
+
+	if(!mask_set) {
+		rc = pci_set_dma_mask(pdev, ATA_DMA_MASK);
+		if (rc)
+			goto err_out_regions;
+		rc = pci_set_consistent_dma_mask(pdev, ATA_DMA_MASK);
+		if (rc)
+			goto err_out_regions;
+	}
 
 	rc = -ENOMEM;
 
-	ppi[0] = ppi[1] = &nv_port_info[ent->driver_data];
+	ppi[0] = ppi[1] = &nv_port_info[type];
 	probe_ent = ata_pci_init_native_mode(pdev, ppi, ATA_PORT_PRIMARY | ATA_PORT_SECONDARY);
 	if (!probe_ent)
 		goto err_out_regions;
@@ -522,7 +1459,7 @@ static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	probe_ent->port[1].scr_addr = base + NV_PORT1_SCR_REG_OFFSET;
 
 	/* enable SATA space for CK804 */
-	if (ent->driver_data == CK804) {
+	if (type >= CK804) {
 		u8 regval;
 
 		pci_read_config_byte(pdev, NV_MCP_SATA_CFG_20, &regval);
@@ -532,6 +1469,12 @@ static int nv_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
+	if (type == ADMA) {
+		rc = nv_adma_host_init(probe_ent);
+		if (rc)
+			goto err_out_iounmap;
+	}
+
 	rc = ata_device_add(probe_ent);
 	if (rc != NV_PORTS)
 		goto err_out_iounmap;
@@ -566,6 +1509,33 @@ static void nv_ck804_host_stop(struct ata_host *host)
 	ata_pci_host_stop(host);
 }
 
+static void nv_adma_host_stop(struct ata_host *host)
+{
+	struct pci_dev *pdev = to_pci_dev(host->dev);
+	int i;
+	u32 tmp32;
+
+	for (i = 0; i < host->n_ports; i++) {
+		void __iomem *mmio = __nv_adma_ctl_block(host->mmio_base, i);
+		u16 tmp;
+
+		/* disable interrupt */
+		tmp = readw(mmio + NV_ADMA_CTL);
+		writew(tmp & ~NV_ADMA_CTL_AIEN, mmio + NV_ADMA_CTL);
+	}
+
+	/* disable ADMA on the ports */
+	pci_read_config_dword(pdev, NV_MCP_SATA_CFG_20, &tmp32);
+	tmp32 &= ~(NV_MCP_SATA_CFG_20_PORT0_EN |
+		   NV_MCP_SATA_CFG_20_PORT0_PWB_EN |
+		   NV_MCP_SATA_CFG_20_PORT1_EN |
+		   NV_MCP_SATA_CFG_20_PORT1_PWB_EN);
+
+	pci_write_config_dword(pdev, NV_MCP_SATA_CFG_20, tmp32);
+
+	nv_ck804_host_stop(host);
+}
+
 static int __init nv_init(void)
 {
 	return pci_register_driver(&nv_pci_driver);
@@ -578,3 +1548,5 @@ static void __exit nv_exit(void)
 
 module_init(nv_init);
 module_exit(nv_exit);
+module_param_named(adma, adma_enabled, bool, 0444);
+MODULE_PARM_DESC(adma, "Enable use of ADMA (Default: true)");
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 72eda5160fad..a2778cf016bc 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -46,20 +46,19 @@
 #include "sata_promise.h"
 
 #define DRV_NAME	"sata_promise"
-#define DRV_VERSION	"1.04"
+#define DRV_VERSION	"1.05"
 
 
 enum {
 	PDC_PKT_SUBMIT		= 0x40, /* Command packet pointer addr */
 	PDC_INT_SEQMASK		= 0x40,	/* Mask of asserted SEQ INTs */
-	PDC_TBG_MODE		= 0x41,	/* TBG mode */
 	PDC_FLASH_CTL		= 0x44, /* Flash control register */
-	PDC_PCI_CTL		= 0x48, /* PCI control and status register */
 	PDC_GLOBAL_CTL		= 0x48, /* Global control/status (per port) */
 	PDC_CTLSTAT		= 0x60,	/* IDE control and status (per port) */
 	PDC_SATA_PLUG_CSR	= 0x6C, /* SATA Plug control/status reg */
 	PDC2_SATA_PLUG_CSR	= 0x60, /* SATAII Plug control/status reg */
-	PDC_SLEW_CTL		= 0x470, /* slew rate control reg */
+	PDC_TBG_MODE		= 0x41C, /* TBG mode (not SATAII) */
+	PDC_SLEW_CTL		= 0x470, /* slew rate control reg (not SATAII) */
 
 	PDC_ERR_MASK		= (1<<19) | (1<<20) | (1<<21) | (1<<22) |
 				  (1<<8) | (1<<9) | (1<<10),
@@ -78,6 +77,9 @@ enum {
 	PDC_COMMON_FLAGS	= ATA_FLAG_NO_LEGACY | ATA_FLAG_SRST |
 				  ATA_FLAG_MMIO | ATA_FLAG_NO_ATAPI |
 				  ATA_FLAG_PIO_POLLING,
+
+	/* hp->flags bits */
+	PDC_FLAG_GEN_II		= (1 << 0),
 };
 
 
@@ -87,6 +89,7 @@ struct pdc_port_priv {
 };
 
 struct pdc_host_priv {
+	unsigned long		flags;
 	int			hotplug_offset;
 };
 
@@ -235,20 +238,20 @@ static const struct ata_port_info pdc_port_info[] = {
 
 static const struct pci_device_id pdc_ata_pci_tbl[] = {
 	{ PCI_VDEVICE(PROMISE, 0x3371), board_2037x },
-	{ PCI_VDEVICE(PROMISE, 0x3570), board_2037x },
-	{ PCI_VDEVICE(PROMISE, 0x3571), board_2037x },
 	{ PCI_VDEVICE(PROMISE, 0x3373), board_2037x },
 	{ PCI_VDEVICE(PROMISE, 0x3375), board_2037x },
 	{ PCI_VDEVICE(PROMISE, 0x3376), board_2037x },
+	{ PCI_VDEVICE(PROMISE, 0x3570), board_2057x },
+	{ PCI_VDEVICE(PROMISE, 0x3571), board_2057x },
 	{ PCI_VDEVICE(PROMISE, 0x3574), board_2057x },
+	{ PCI_VDEVICE(PROMISE, 0x3d73), board_2057x },
 	{ PCI_VDEVICE(PROMISE, 0x3d75), board_2057x },
-	{ PCI_VDEVICE(PROMISE, 0x3d73), board_2037x },
 
 	{ PCI_VDEVICE(PROMISE, 0x3318), board_20319 },
 	{ PCI_VDEVICE(PROMISE, 0x3319), board_20319 },
 	{ PCI_VDEVICE(PROMISE, 0x3515), board_20319 },
 	{ PCI_VDEVICE(PROMISE, 0x3519), board_20319 },
-	{ PCI_VDEVICE(PROMISE, 0x3d17), board_20319 },
+	{ PCI_VDEVICE(PROMISE, 0x3d17), board_40518 },
 	{ PCI_VDEVICE(PROMISE, 0x3d18), board_40518 },
 
 	{ PCI_VDEVICE(PROMISE, 0x6629), board_20619 },
@@ -277,6 +280,7 @@ static struct pci_driver pdc_ata_pci_driver = {
 static int pdc_port_start(struct ata_port *ap)
 {
 	struct device *dev = ap->host->dev;
+	struct pdc_host_priv *hp = ap->host->private_data;
 	struct pdc_port_priv *pp;
 	int rc;
 
@@ -298,6 +302,16 @@ static int pdc_port_start(struct ata_port *ap)
 
 	ap->private_data = pp;
 
+	/* fix up PHYMODE4 align timing */
+	if ((hp->flags & PDC_FLAG_GEN_II) && sata_scr_valid(ap)) {
+		void __iomem *mmio = (void __iomem *) ap->ioaddr.scr_addr;
+		unsigned int tmp;
+
+		tmp = readl(mmio + 0x014);
+		tmp = (tmp & ~3) | 1;	/* set bits 1:0 = 0:1 */
+		writel(tmp, mmio + 0x014);
+	}
+
 	return 0;
 
 err_out_kfree:
@@ -640,9 +654,11 @@ static void pdc_host_init(unsigned int chip_id, struct ata_probe_ent *pe)
 	 * "TODO: figure out why we do this"
 	 */
 
-	/* change FIFO_SHD to 8 dwords, enable BMR_BURST */
+	/* enable BMR_BURST, maybe change FIFO_SHD to 8 dwords */
 	tmp = readl(mmio + PDC_FLASH_CTL);
-	tmp |= 0x12000;	/* bit 16 (fifo 8 dw) and 13 (bmr burst?) */
+	tmp |= 0x02000;	/* bit 13 (enable bmr burst) */
+	if (!(hp->flags & PDC_FLAG_GEN_II))
+		tmp |= 0x10000;	/* bit 16 (fifo threshold at 8 dw) */
 	writel(tmp, mmio + PDC_FLASH_CTL);
 
 	/* clear plug/unplug flags for all ports */
@@ -653,6 +669,10 @@ static void pdc_host_init(unsigned int chip_id, struct ata_probe_ent *pe)
 	tmp = readl(mmio + hotplug_offset);
 	writel(tmp | 0xff0000, mmio + hotplug_offset);
 
+	/* don't initialise TBG or SLEW on 2nd generation chips */
+	if (hp->flags & PDC_FLAG_GEN_II)
+		return;
+
 	/* reduce TBG clock to 133 Mhz. */
 	tmp = readl(mmio + PDC_TBG_MODE);
 	tmp &= ~0x30000; /* clear bit 17, 16*/
@@ -746,6 +766,7 @@ static int pdc_ata_init_one (struct pci_dev *pdev, const struct pci_device_id *e
 	/* notice 4-port boards */
 	switch (board_idx) {
 	case board_40518:
+		hp->flags |= PDC_FLAG_GEN_II;
 		/* Override hotplug offset for SATAII150 */
 		hp->hotplug_offset = PDC2_SATA_PLUG_CSR;
 		/* Fall through */
@@ -759,15 +780,14 @@ static int pdc_ata_init_one (struct pci_dev *pdev, const struct pci_device_id *e
 		probe_ent->port[3].scr_addr = base + 0x700;
 		break;
 	case board_2057x:
+	case board_20771:
+		hp->flags |= PDC_FLAG_GEN_II;
 		/* Override hotplug offset for SATAII150 */
 		hp->hotplug_offset = PDC2_SATA_PLUG_CSR;
 		/* Fall through */
 	case board_2037x:
 		probe_ent->n_ports = 2;
 		break;
-	case board_20771:
-		probe_ent->n_ports = 2;
-		break;
 	case board_20619:
 		probe_ent->n_ports = 4;
 
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index ca8d99312472..7808d0369d91 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -356,6 +356,7 @@ static void sil_scr_write (struct ata_port *ap, unsigned int sc_reg, u32 val)
 
 static void sil_host_intr(struct ata_port *ap, u32 bmdma2)
 {
+	struct ata_eh_info *ehi = &ap->eh_info;
 	struct ata_queued_cmd *qc = ata_qc_from_tag(ap, ap->active_tag);
 	u8 status;
 
@@ -428,6 +429,10 @@ static void sil_host_intr(struct ata_port *ap, u32 bmdma2)
 	/* kick HSM in the ass */
 	ata_hsm_move(ap, qc, status, 0);
 
+	if (unlikely(qc->err_mask) && (qc->tf.protocol == ATA_PROT_DMA ||
+				       qc->tf.protocol == ATA_PROT_ATAPI_DMA))
+		ata_ehi_push_desc(ehi, "BMDMA2 stat 0x%x", bmdma2);
+
 	return;
 
  err_hsm:
@@ -534,6 +539,7 @@ static void sil_thaw(struct ata_port *ap)
  */
 static void sil_dev_config(struct ata_port *ap, struct ata_device *dev)
 {
+	int print_info = ap->eh_context.i.flags & ATA_EHI_PRINTINFO;
 	unsigned int n, quirks = 0;
 	unsigned char model_num[41];
 
@@ -549,16 +555,18 @@ static void sil_dev_config(struct ata_port *ap, struct ata_device *dev)
 	if (slow_down ||
 	    ((ap->flags & SIL_FLAG_MOD15WRITE) &&
 	     (quirks & SIL_QUIRK_MOD15WRITE))) {
-		ata_dev_printk(dev, KERN_INFO, "applying Seagate errata fix "
-			       "(mod15write workaround)\n");
+		if (print_info)
+			ata_dev_printk(dev, KERN_INFO, "applying Seagate "
+				       "errata fix (mod15write workaround)\n");
 		dev->max_sectors = 15;
 		return;
 	}
 
 	/* limit to udma5 */
 	if (quirks & SIL_QUIRK_UDMA5MAX) {
-		ata_dev_printk(dev, KERN_INFO,
-			       "applying Maxtor errata fix %s\n", model_num);
+		if (print_info)
+			ata_dev_printk(dev, KERN_INFO, "applying Maxtor "
+				       "errata fix %s\n", model_num);
 		dev->udma_mask &= ATA_UDMA5;
 		return;
 	}
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 169e200a6a71..5aa288d2fb86 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -100,10 +100,14 @@ enum {
 	 */
 	PORT_REGS_SIZE		= 0x2000,
 
-	PORT_LRAM		= 0x0000, /* 31 LRAM slots and PM regs */
+	PORT_LRAM		= 0x0000, /* 31 LRAM slots and PMP regs */
 	PORT_LRAM_SLOT_SZ	= 0x0080, /* 32 bytes PRB + 2 SGE, ACT... */
 
-	PORT_PM			= 0x0f80, /* 8 bytes PM * 16 (128 bytes) */
+	PORT_PMP		= 0x0f80, /* 8 bytes PMP * 16 (128 bytes) */
+	PORT_PMP_STATUS		= 0x0000, /* port device status offset */
+	PORT_PMP_QACTIVE	= 0x0004, /* port device QActive offset */
+	PORT_PMP_SIZE		= 0x0008, /* 8 bytes per PMP */
+
 		/* 32 bit regs */
 	PORT_CTRL_STAT		= 0x1000, /* write: ctrl-set, read: stat */
 	PORT_CTRL_CLR		= 0x1004, /* write: ctrl-clear */
@@ -126,6 +130,7 @@ enum {
 	PORT_PHY_CFG		= 0x1050,
 	PORT_SLOT_STAT		= 0x1800,
 	PORT_CMD_ACTIVATE	= 0x1c00, /* 64 bit cmd activate * 31 (248 bytes) */
+	PORT_CONTEXT		= 0x1e04,
 	PORT_EXEC_DIAG		= 0x1e00, /* 32bit exec diag * 16 (64 bytes, 0-10 used on 3124) */
 	PORT_PSD_DIAG		= 0x1e40, /* 32bit psd diag * 16 (64 bytes, 0-8 used on 3124) */
 	PORT_SCONTROL		= 0x1f00,
@@ -139,9 +144,9 @@ enum {
 	PORT_CS_INIT		= (1 << 2), /* port initialize */
 	PORT_CS_IRQ_WOC		= (1 << 3), /* interrupt write one to clear */
 	PORT_CS_CDB16		= (1 << 5), /* 0=12b cdb, 1=16b cdb */
-	PORT_CS_RESUME		= (1 << 6), /* port resume */
+	PORT_CS_PMP_RESUME	= (1 << 6), /* PMP resume */
 	PORT_CS_32BIT_ACTV	= (1 << 10), /* 32-bit activation */
-	PORT_CS_PM_EN		= (1 << 13), /* port multiplier enable */
+	PORT_CS_PMP_EN		= (1 << 13), /* port multiplier enable */
 	PORT_CS_RDY		= (1 << 31), /* port ready to accept commands */
 
 	/* PORT_IRQ_STAT/ENABLE_SET/CLR */
@@ -562,7 +567,7 @@ static int sil24_softreset(struct ata_port *ap, unsigned int *class)
 
 	/* do SRST */
 	prb->ctrl = cpu_to_le16(PRB_CTRL_SRST);
-	prb->fis[1] = 0; /* no PM yet */
+	prb->fis[1] = 0; /* no PMP yet */
 
 	writel((u32)paddr, port + PORT_CMD_ACTIVATE);
 	writel((u64)paddr >> 32, port + PORT_CMD_ACTIVATE + 4);
@@ -1050,7 +1055,8 @@ static void sil24_init_controller(struct pci_dev *pdev, int n_ports,
 		writel(PORT_CS_32BIT_ACTV, port + PORT_CTRL_CLR);
 
 		/* Clear port multiplier enable and resume bits */
-		writel(PORT_CS_PM_EN | PORT_CS_RESUME, port + PORT_CTRL_CLR);
+		writel(PORT_CS_PMP_EN | PORT_CS_PMP_RESUME,
+		       port + PORT_CTRL_CLR);
 	}
 
 	/* Turn on interrupts */
diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
index 9d1235ba06b1..9c25a1e91730 100644
--- a/drivers/ata/sata_sis.c
+++ b/drivers/ata/sata_sis.c
@@ -173,7 +173,7 @@ static u32 sis_scr_cfg_read (struct ata_port *ap, unsigned int sc_reg)
 	if ((pdev->device == 0x182) || (pmr & SIS_PMR_COMBINED))
 		pci_read_config_dword(pdev, cfg_addr+0x10, &val2);
 
-	return val|val2;
+	return (val|val2) &  0xfffffffb; /* avoid problems with powerdowned ports */
 }
 
 static void sis_scr_cfg_write (struct ata_port *ap, unsigned int scr, u32 val)
@@ -212,7 +212,7 @@ static u32 sis_scr_read (struct ata_port *ap, unsigned int sc_reg)
 	if ((pdev->device == 0x182) || (pmr & SIS_PMR_COMBINED))
 		val2 = inl(ap->ioaddr.scr_addr + (sc_reg * 4) + 0x10);
 
-	return val | val2;
+	return (val | val2) &  0xfffffffb;
 }
 
 static void sis_scr_write (struct ata_port *ap, unsigned int sc_reg, u32 val)
@@ -239,7 +239,7 @@ static int sis_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	static int printed_version;
 	struct ata_probe_ent *probe_ent = NULL;
 	int rc;
-	u32 genctl;
+	u32 genctl, val;
 	struct ata_port_info pi = sis_port_info, *ppi[2] = { &pi, &pi };
 	int pci_dev_busy = 0;
 	u8 pmr;
@@ -285,17 +285,24 @@ static int sis_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ent->device != 0x182) {
 		if ((pmr & SIS_PMR_COMBINED) == 0) {
 			dev_printk(KERN_INFO, &pdev->dev,
-				   "Detected SiS 180/181 chipset in SATA mode\n");
+				   "Detected SiS 180/181/964 chipset in SATA mode\n");
 			port2_start = 64;
 		}
 		else {
 			dev_printk(KERN_INFO, &pdev->dev,
 				   "Detected SiS 180/181 chipset in combined mode\n");
 			port2_start=0;
+			pi.flags |= ATA_FLAG_SLAVE_POSS;
 		}
 	}
 	else {
-		dev_printk(KERN_INFO, &pdev->dev, "Detected SiS 182 chipset\n");
+		pci_read_config_dword ( pdev, 0x6C, &val);
+		if (val & (1L << 31)) {
+			dev_printk(KERN_INFO, &pdev->dev, "Detected SiS 182/965 chipset\n");
+			pi.flags |= ATA_FLAG_SLAVE_POSS;
+		}
+		else
+			dev_printk(KERN_INFO, &pdev->dev, "Detected SiS 182/965L chipset\n");
 		port2_start = 0x20;
 	}
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4bef76a2f3f2..1f745f12f94e 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -5,6 +5,7 @@
 #include <linux/sysdev.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/cpu.h>
 #include <linux/topology.h>
 #include <linux/device.h>
diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c
index ec5a1b90a0a2..e19ba4ebcd4e 100644
--- a/drivers/block/viodasd.c
+++ b/drivers/block/viodasd.c
@@ -759,6 +759,8 @@ static struct vio_driver viodasd_driver = {
 	}
 };
 
+static int need_delete_probe;
+
 /*
  * Initialize the whole device driver.  Handle module and non-module
  * versions
@@ -773,46 +775,67 @@ static int __init viodasd_init(void)
 
 	if (viopath_hostLp == HvLpIndexInvalid) {
 		printk(VIOD_KERN_WARNING "invalid hosting partition\n");
-		return -EIO;
+		rc = -EIO;
+		goto early_fail;
 	}
 
 	printk(VIOD_KERN_INFO "vers " VIOD_VERS ", hosting partition %d\n",
 			viopath_hostLp);
 
         /* register the block device */
-	if (register_blkdev(VIODASD_MAJOR, VIOD_GENHD_NAME)) {
+	rc =  register_blkdev(VIODASD_MAJOR, VIOD_GENHD_NAME);
+	if (rc) {
 		printk(VIOD_KERN_WARNING
 				"Unable to get major number %d for %s\n",
 				VIODASD_MAJOR, VIOD_GENHD_NAME);
-		return -EIO;
+		goto early_fail;
 	}
 	/* Actually open the path to the hosting partition */
-	if (viopath_open(viopath_hostLp, viomajorsubtype_blockio,
-				VIOMAXREQ + 2)) {
+	rc = viopath_open(viopath_hostLp, viomajorsubtype_blockio,
+				VIOMAXREQ + 2);
+	if (rc) {
 		printk(VIOD_KERN_WARNING
 		       "error opening path to host partition %d\n",
 		       viopath_hostLp);
-		unregister_blkdev(VIODASD_MAJOR, VIOD_GENHD_NAME);
-		return -EIO;
+		goto unregister_blk;
 	}
 
 	/* Initialize our request handler */
 	vio_setHandler(viomajorsubtype_blockio, handle_block_event);
 
 	rc = vio_register_driver(&viodasd_driver);
-	if (rc == 0)
-		driver_create_file(&viodasd_driver.driver, &driver_attr_probe);
+	if (rc) {
+		printk(VIOD_KERN_WARNING "vio_register_driver failed\n");
+		goto unset_handler;
+	}
+
+	/*
+	 * If this call fails, it just means that we cannot dynamically
+	 * add virtual disks, but the driver will still work fine for
+	 * all existing disk, so ignore the failure.
+	 */
+	if (!driver_create_file(&viodasd_driver.driver, &driver_attr_probe))
+		need_delete_probe = 1;
+
+	return 0;
+
+unset_handler:
+	vio_clearHandler(viomajorsubtype_blockio);
+	viopath_close(viopath_hostLp, viomajorsubtype_blockio, VIOMAXREQ + 2);
+unregister_blk:
+	unregister_blkdev(VIODASD_MAJOR, VIOD_GENHD_NAME);
+early_fail:
 	return rc;
 }
 module_init(viodasd_init);
 
-void viodasd_exit(void)
+void __exit viodasd_exit(void)
 {
-	driver_remove_file(&viodasd_driver.driver, &driver_attr_probe);
+	if (need_delete_probe)
+		driver_remove_file(&viodasd_driver.driver, &driver_attr_probe);
 	vio_unregister_driver(&viodasd_driver);
 	vio_clearHandler(viomajorsubtype_blockio);
-	unregister_blkdev(VIODASD_MAJOR, VIOD_GENHD_NAME);
 	viopath_close(viopath_hostLp, viomajorsubtype_blockio, VIOMAXREQ + 2);
+	unregister_blkdev(VIODASD_MAJOR, VIOD_GENHD_NAME);
 }
-
 module_exit(viodasd_exit);
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 091a11cd878c..20dc3be5ecfc 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -21,6 +21,7 @@
 #include <linux/fcntl.h>
 #include <linux/init.h>
 #include <linux/poll.h>
+#include <linux/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/spinlock.h>
 #include <linux/sysctl.h>
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index ebace201bec6..26a860adcb38 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -36,6 +36,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 050ced247f68..bb9a43c6cf3d 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -22,6 +22,7 @@
 #include <linux/pci.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/miscdevice.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
diff --git a/drivers/hwmon/abituguru.c b/drivers/hwmon/abituguru.c
index e5cb0fdab9b1..b1dc63e4ac7b 100644
--- a/drivers/hwmon/abituguru.c
+++ b/drivers/hwmon/abituguru.c
@@ -21,6 +21,7 @@
     etc voltage & frequency control is not supported!
 */
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/jiffies.h>
diff --git a/drivers/hwmon/hdaps.c b/drivers/hwmon/hdaps.c
index 26be4ea8a38a..e8ef62b83d6b 100644
--- a/drivers/hwmon/hdaps.c
+++ b/drivers/hwmon/hdaps.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/dmi.h>
+#include <linux/jiffies.h>
 #include <asm/io.h>
 
 #define HDAPS_LOW_PORT		0x1600	/* first port used by hdaps */
diff --git a/drivers/ide/pci/via82cxxx.c b/drivers/ide/pci/via82cxxx.c
index 2af634d7acf4..eb7ab112c050 100644
--- a/drivers/ide/pci/via82cxxx.c
+++ b/drivers/ide/pci/via82cxxx.c
@@ -35,7 +35,7 @@
 #include <linux/ide.h>
 #include <asm/io.h>
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
+#ifdef CONFIG_PPC_CHRP
 #include <asm/processor.h>
 #endif
 
@@ -442,7 +442,7 @@ static void __devinit init_hwif_via82cxxx(ide_hwif_t *hwif)
 	hwif->speedproc = &via_set_drive;
 
 
-#if defined(CONFIG_PPC_CHRP) && defined(CONFIG_PPC32)
+#ifdef CONFIG_PPC_CHRP
 	if(machine_is(chrp) && _chrp_type == _CHRP_Pegasos) {
 		hwif->irq = hwif->channel ? 15 : 14;
 	}
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 0606744c3f84..5e122501fd80 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <asm/io.h>
 #include <asm/scatterlist.h>
 #include <linux/scatterlist.h>
diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c
index 1f5ebe9ee72c..03319ea5aa0c 100644
--- a/drivers/isdn/divert/isdn_divert.c
+++ b/drivers/isdn/divert/isdn_divert.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/proc_fs.h>
+#include <linux/timer.h>
+#include <linux/jiffies.h>
 
 #include "isdn_divert.h"
 
diff --git a/drivers/leds/ledtrig-ide-disk.c b/drivers/leds/ledtrig-ide-disk.c
index fa651886ab4f..54b155c7026f 100644
--- a/drivers/leds/ledtrig-ide-disk.c
+++ b/drivers/leds/ledtrig-ide-disk.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/drivers/leds/ledtrig-timer.c b/drivers/leds/ledtrig-timer.c
index 29a8818a32ec..d756bdb01c59 100644
--- a/drivers/leds/ledtrig-timer.c
+++ b/drivers/leds/ledtrig-timer.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/list.h>
diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig
index 7f8477d3a661..92ccee85e2a2 100644
--- a/drivers/macintosh/Kconfig
+++ b/drivers/macintosh/Kconfig
@@ -228,4 +228,11 @@ config ANSLCD
 	tristate "Support for ANS LCD display"
 	depends on ADB_CUDA && PPC_PMAC
 
+config PMAC_RACKMETER
+	tristate "Support for Apple XServe front panel LEDs"
+	depends on PPC_PMAC
+	help
+	  This driver procides some support to control the front panel
+          blue LEDs "vu-meter" of the XServer macs.
+
 endmenu
diff --git a/drivers/macintosh/Makefile b/drivers/macintosh/Makefile
index b53d45f87b0b..2dfc3f4eaf42 100644
--- a/drivers/macintosh/Makefile
+++ b/drivers/macintosh/Makefile
@@ -42,3 +42,4 @@ obj-$(CONFIG_WINDFARM_PM112)	+= windfarm_pm112.o windfarm_smu_sat.o \
 				   windfarm_smu_sensors.o \
 				   windfarm_max6690_sensor.o \
 				   windfarm_lm75_sensor.o windfarm_pid.o
+obj-$(CONFIG_PMAC_RACKMETER)	+= rack-meter.o
diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c
new file mode 100644
index 000000000000..f1b6f563673a
--- /dev/null
+++ b/drivers/macintosh/rack-meter.c
@@ -0,0 +1,612 @@
+/*
+ * RackMac vu-meter driver
+ *
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ *
+ * Released under the term of the GNU GPL v2.
+ *
+ * Support the CPU-meter LEDs of the Xserve G5
+ *
+ * TODO: Implement PWM to do variable intensity and provide userland
+ * interface for fun. Also, the CPU-meter could be made nicer by being
+ * a bit less "immediate" but giving instead a more average load over
+ * time. Patches welcome :-)
+ *
+ */
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/kernel_stat.h>
+
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/pmac_feature.h>
+#include <asm/dbdma.h>
+#include <asm/dbdma.h>
+#include <asm/macio.h>
+#include <asm/keylargo.h>
+
+/* Number of samples in a sample buffer */
+#define SAMPLE_COUNT		256
+
+/* CPU meter sampling rate in ms */
+#define CPU_SAMPLING_RATE	250
+
+struct rackmeter_dma {
+	struct dbdma_cmd	cmd[4]			____cacheline_aligned;
+	u32			mark			____cacheline_aligned;
+	u32			buf1[SAMPLE_COUNT]	____cacheline_aligned;
+	u32			buf2[SAMPLE_COUNT]	____cacheline_aligned;
+} ____cacheline_aligned;
+
+struct rackmeter_cpu {
+	struct work_struct	sniffer;
+	cputime64_t		prev_wall;
+	cputime64_t		prev_idle;
+	int			zero;
+} ____cacheline_aligned;
+
+struct rackmeter {
+	struct macio_dev		*mdev;
+	unsigned int			irq;
+	struct device_node		*i2s;
+	u8				*ubuf;
+	struct dbdma_regs __iomem	*dma_regs;
+	void __iomem			*i2s_regs;
+	dma_addr_t			dma_buf_p;
+	struct rackmeter_dma		*dma_buf_v;
+	int				stale_irq;
+	struct rackmeter_cpu		cpu[2];
+	int				paused;
+	struct mutex			sem;
+};
+
+/* To be set as a tunable */
+static int rackmeter_ignore_nice;
+
+/* This GPIO is whacked by the OS X driver when initializing */
+#define RACKMETER_MAGIC_GPIO	0x78
+
+/* This is copied from cpufreq_ondemand, maybe we should put it in
+ * a common header somewhere
+ */
+static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
+{
+	cputime64_t retval;
+
+	retval = cputime64_add(kstat_cpu(cpu).cpustat.idle,
+			kstat_cpu(cpu).cpustat.iowait);
+
+	if (rackmeter_ignore_nice)
+		retval = cputime64_add(retval, kstat_cpu(cpu).cpustat.nice);
+
+	return retval;
+}
+
+static void rackmeter_setup_i2s(struct rackmeter *rm)
+{
+	struct macio_chip *macio = rm->mdev->bus->chip;
+
+	/* First whack magic GPIO */
+	pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, RACKMETER_MAGIC_GPIO, 5);
+
+
+	/* Call feature code to enable the sound channel and the proper
+	 * clock sources
+	 */
+	pmac_call_feature(PMAC_FTR_SOUND_CHIP_ENABLE, rm->i2s, 0, 1);
+
+	/* Power i2s and stop i2s clock. We whack MacIO FCRs directly for now.
+	 * This is a bit racy, thus we should add new platform functions to
+	 * handle that. snd-aoa needs that too
+	 */
+	MACIO_BIS(KEYLARGO_FCR1, KL1_I2S0_ENABLE);
+	MACIO_BIC(KEYLARGO_FCR1, KL1_I2S0_CLK_ENABLE_BIT);
+	(void)MACIO_IN32(KEYLARGO_FCR1);
+	udelay(10);
+
+	/* Then setup i2s. For now, we use the same magic value that
+	 * the OS X driver seems to use. We might want to play around
+	 * with the clock divisors later
+	 */
+	out_le32(rm->i2s_regs + 0x10, 0x01fa0000);
+	(void)in_le32(rm->i2s_regs + 0x10);
+	udelay(10);
+
+	/* Fully restart i2s*/
+	MACIO_BIS(KEYLARGO_FCR1, KL1_I2S0_CELL_ENABLE |
+		  KL1_I2S0_CLK_ENABLE_BIT);
+	(void)MACIO_IN32(KEYLARGO_FCR1);
+	udelay(10);
+}
+
+static void rackmeter_set_default_pattern(struct rackmeter *rm)
+{
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		if (i < 8)
+			rm->ubuf[i] = (i & 1) * 255;
+		else
+			rm->ubuf[i] = ((~i) & 1) * 255;
+	}
+}
+
+static void rackmeter_do_pause(struct rackmeter *rm, int pause)
+{
+	struct rackmeter_dma *rdma = rm->dma_buf_v;
+
+	pr_debug("rackmeter: %s\n", pause ? "paused" : "started");
+
+	rm->paused = pause;
+	if (pause) {
+		DBDMA_DO_STOP(rm->dma_regs);
+		return;
+	}
+	memset(rdma->buf1, 0, SAMPLE_COUNT & sizeof(u32));
+	memset(rdma->buf2, 0, SAMPLE_COUNT & sizeof(u32));
+
+	rm->dma_buf_v->mark = 0;
+
+	mb();
+	out_le32(&rm->dma_regs->cmdptr_hi, 0);
+	out_le32(&rm->dma_regs->cmdptr, rm->dma_buf_p);
+	out_le32(&rm->dma_regs->control, (RUN << 16) | RUN);
+}
+
+static void rackmeter_setup_dbdma(struct rackmeter *rm)
+{
+	struct rackmeter_dma *db = rm->dma_buf_v;
+	struct dbdma_cmd *cmd = db->cmd;
+
+	/* Make sure dbdma is reset */
+	DBDMA_DO_RESET(rm->dma_regs);
+
+	pr_debug("rackmeter: mark offset=0x%lx\n",
+		 offsetof(struct rackmeter_dma, mark));
+	pr_debug("rackmeter: buf1 offset=0x%lx\n",
+		 offsetof(struct rackmeter_dma, buf1));
+	pr_debug("rackmeter: buf2 offset=0x%lx\n",
+		 offsetof(struct rackmeter_dma, buf2));
+
+	/* Prepare 4 dbdma commands for the 2 buffers */
+	memset(cmd, 0, 4 * sizeof(struct dbdma_cmd));
+	st_le16(&cmd->req_count, 4);
+	st_le16(&cmd->command, STORE_WORD | INTR_ALWAYS | KEY_SYSTEM);
+	st_le32(&cmd->phy_addr, rm->dma_buf_p +
+		offsetof(struct rackmeter_dma, mark));
+	st_le32(&cmd->cmd_dep, 0x02000000);
+	cmd++;
+
+	st_le16(&cmd->req_count, SAMPLE_COUNT * 4);
+	st_le16(&cmd->command, OUTPUT_MORE);
+	st_le32(&cmd->phy_addr, rm->dma_buf_p +
+		offsetof(struct rackmeter_dma, buf1));
+	cmd++;
+
+	st_le16(&cmd->req_count, 4);
+	st_le16(&cmd->command, STORE_WORD | INTR_ALWAYS | KEY_SYSTEM);
+	st_le32(&cmd->phy_addr, rm->dma_buf_p +
+		offsetof(struct rackmeter_dma, mark));
+	st_le32(&cmd->cmd_dep, 0x01000000);
+	cmd++;
+
+	st_le16(&cmd->req_count, SAMPLE_COUNT * 4);
+	st_le16(&cmd->command, OUTPUT_MORE | BR_ALWAYS);
+	st_le32(&cmd->phy_addr, rm->dma_buf_p +
+		offsetof(struct rackmeter_dma, buf2));
+	st_le32(&cmd->cmd_dep, rm->dma_buf_p);
+
+	rackmeter_do_pause(rm, 0);
+}
+
+static void rackmeter_do_timer(void *data)
+{
+	struct rackmeter *rm = data;
+	unsigned int cpu = smp_processor_id();
+	struct rackmeter_cpu *rcpu = &rm->cpu[cpu];
+	cputime64_t cur_jiffies, total_idle_ticks;
+	unsigned int total_ticks, idle_ticks;
+	int i, offset, load, cumm, pause;
+
+	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
+	total_ticks = (unsigned int)cputime64_sub(cur_jiffies,
+						  rcpu->prev_wall);
+	rcpu->prev_wall = cur_jiffies;
+
+	total_idle_ticks = get_cpu_idle_time(cpu);
+	idle_ticks = (unsigned int) cputime64_sub(total_idle_ticks,
+				rcpu->prev_idle);
+	rcpu->prev_idle = total_idle_ticks;
+
+	/* We do a very dumb calculation to update the LEDs for now,
+	 * we'll do better once we have actual PWM implemented
+	 */
+	load = (9 * (total_ticks - idle_ticks)) / total_ticks;
+
+	offset = cpu << 3;
+	cumm = 0;
+	for (i = 0; i < 8; i++) {
+		u8 ub = (load > i) ? 0xff : 0;
+		rm->ubuf[i + offset] = ub;
+		cumm |= ub;
+	}
+	rcpu->zero = (cumm == 0);
+
+	/* Now check if LEDs are all 0, we can stop DMA */
+	pause = (rm->cpu[0].zero && rm->cpu[1].zero);
+	if (pause != rm->paused) {
+		mutex_lock(&rm->sem);
+		pause = (rm->cpu[0].zero && rm->cpu[1].zero);
+		rackmeter_do_pause(rm, pause);
+		mutex_unlock(&rm->sem);
+	}
+	schedule_delayed_work_on(cpu, &rcpu->sniffer,
+				 msecs_to_jiffies(CPU_SAMPLING_RATE));
+}
+
+static void __devinit rackmeter_init_cpu_sniffer(struct rackmeter *rm)
+{
+	unsigned int cpu;
+
+	/* This driver works only with 1 or 2 CPUs numbered 0 and 1,
+	 * but that's really all we have on Apple Xserve. It doesn't
+	 * play very nice with CPU hotplug neither but we don't do that
+	 * on those machines yet
+	 */
+
+	INIT_WORK(&rm->cpu[0].sniffer, rackmeter_do_timer, rm);
+	INIT_WORK(&rm->cpu[1].sniffer, rackmeter_do_timer, rm);
+
+	for_each_online_cpu(cpu) {
+		struct rackmeter_cpu *rcpu;
+
+		if (cpu > 1)
+			continue;
+		rcpu = &rm->cpu[cpu];;
+		rcpu->prev_idle = get_cpu_idle_time(cpu);
+		rcpu->prev_wall = jiffies64_to_cputime64(get_jiffies_64());
+		schedule_delayed_work_on(cpu, &rm->cpu[cpu].sniffer,
+					 msecs_to_jiffies(CPU_SAMPLING_RATE));
+	}
+}
+
+static void __devexit rackmeter_stop_cpu_sniffer(struct rackmeter *rm)
+{
+	cancel_rearming_delayed_work(&rm->cpu[0].sniffer);
+	cancel_rearming_delayed_work(&rm->cpu[1].sniffer);
+}
+
+static int rackmeter_setup(struct rackmeter *rm)
+{
+	pr_debug("rackmeter: setting up i2s..\n");
+	rackmeter_setup_i2s(rm);
+
+	pr_debug("rackmeter: setting up default pattern..\n");
+	rackmeter_set_default_pattern(rm);
+
+	pr_debug("rackmeter: setting up dbdma..\n");
+	rackmeter_setup_dbdma(rm);
+
+	pr_debug("rackmeter: start CPU measurements..\n");
+	rackmeter_init_cpu_sniffer(rm);
+
+	printk(KERN_INFO "RackMeter initialized\n");
+
+	return 0;
+}
+
+/*  XXX FIXME: No PWM yet, this is 0/1 */
+static u32 rackmeter_calc_sample(struct rackmeter *rm, unsigned int index)
+{
+	int led;
+	u32 sample = 0;
+
+	for (led = 0; led < 16; led++) {
+		sample >>= 1;
+		sample |= ((rm->ubuf[led] >= 0x80) << 15);
+	}
+	return (sample << 17) | (sample >> 15);
+}
+
+static irqreturn_t rackmeter_irq(int irq, void *arg)
+{
+	struct rackmeter *rm = arg;
+	struct rackmeter_dma *db = rm->dma_buf_v;
+	unsigned int mark, i;
+	u32 *buf;
+
+	/* Flush PCI buffers with an MMIO read. Maybe we could actually
+	 * check the status one day ... in case things go wrong, though
+	 * this never happened to me
+	 */
+	(void)in_le32(&rm->dma_regs->status);
+
+	/* Make sure the CPU gets us in order */
+	rmb();
+
+	/* Read mark */
+	mark = db->mark;
+	if (mark != 1 && mark != 2) {
+		printk(KERN_WARNING "rackmeter: Incorrect DMA mark 0x%08x\n",
+		       mark);
+		/* We allow for 3 errors like that (stale DBDMA irqs) */
+		if (++rm->stale_irq > 3) {
+			printk(KERN_ERR "rackmeter: Too many errors,"
+			       " stopping DMA\n");
+			DBDMA_DO_RESET(rm->dma_regs);
+		}
+		return IRQ_HANDLED;
+	}
+
+	/* Next buffer we need to fill is mark value */
+	buf = mark == 1 ? db->buf1 : db->buf2;
+
+	/* Fill it now. This routine converts the 8 bits depth sample array
+	 * into the PWM bitmap for each LED.
+	 */
+	for (i = 0; i < SAMPLE_COUNT; i++)
+		buf[i] = rackmeter_calc_sample(rm, i);
+
+
+	return IRQ_HANDLED;
+}
+
+static int __devinit rackmeter_probe(struct macio_dev* mdev,
+				     const struct of_device_id *match)
+{
+	struct device_node *i2s = NULL, *np = NULL;
+	struct rackmeter *rm = NULL;
+	struct resource ri2s, rdma;
+	int rc = -ENODEV;
+
+	pr_debug("rackmeter_probe()\n");
+
+	/* Get i2s-a node */
+	while ((i2s = of_get_next_child(mdev->ofdev.node, i2s)) != NULL)
+	       if (strcmp(i2s->name, "i2s-a") == 0)
+		       break;
+	if (i2s == NULL) {
+		pr_debug("  i2s-a child not found\n");
+		goto bail;
+	}
+	/* Get lightshow or virtual sound */
+	while ((np = of_get_next_child(i2s, np)) != NULL) {
+	       if (strcmp(np->name, "lightshow") == 0)
+		       break;
+	       if ((strcmp(np->name, "sound") == 0) &&
+		   get_property(np, "virtual", NULL) != NULL)
+		       break;
+	}
+	if (np == NULL) {
+		pr_debug("  lightshow or sound+virtual child not found\n");
+		goto bail;
+	}
+
+	/* Create and initialize our instance data */
+	rm = kzalloc(sizeof(struct rackmeter), GFP_KERNEL);
+	if (rm == NULL) {
+		printk(KERN_ERR "rackmeter: failed to allocate memory !\n");
+		rc = -ENOMEM;
+		goto bail_release;
+	}
+	rm->mdev = mdev;
+	rm->i2s = i2s;
+	mutex_init(&rm->sem);
+	dev_set_drvdata(&mdev->ofdev.dev, rm);
+	/* Check resources availability. We need at least resource 0 and 1 */
+#if 0 /* Use that when i2s-a is finally an mdev per-se */
+	if (macio_resource_count(mdev) < 2 || macio_irq_count(mdev) < 2) {
+		printk(KERN_ERR
+		       "rackmeter: found match but lacks resources: %s"
+		       " (%d resources, %d interrupts)\n",
+		       mdev->ofdev.node->full_name);
+		rc = -ENXIO;
+		goto bail_free;
+	}
+	if (macio_request_resources(mdev, "rackmeter")) {
+		printk(KERN_ERR
+		       "rackmeter: failed to request resources: %s\n",
+		       mdev->ofdev.node->full_name);
+		rc = -EBUSY;
+		goto bail_free;
+	}
+	rm->irq = macio_irq(mdev, 1);
+#else
+	rm->irq = irq_of_parse_and_map(i2s, 1);
+	if (rm->irq == NO_IRQ ||
+	    of_address_to_resource(i2s, 0, &ri2s) ||
+	    of_address_to_resource(i2s, 1, &rdma)) {
+		printk(KERN_ERR
+		       "rackmeter: found match but lacks resources: %s",
+		       mdev->ofdev.node->full_name);
+		rc = -ENXIO;
+		goto bail_free;
+	}
+#endif
+
+	pr_debug("  i2s @0x%08x\n", (unsigned int)ri2s.start);
+	pr_debug("  dma @0x%08x\n", (unsigned int)rdma.start);
+	pr_debug("  irq %d\n", rm->irq);
+
+	rm->ubuf = (u8 *)__get_free_page(GFP_KERNEL);
+	if (rm->ubuf == NULL) {
+		printk(KERN_ERR
+		       "rackmeter: failed to allocate samples page !\n");
+		rc = -ENOMEM;
+		goto bail_release;
+	}
+
+	rm->dma_buf_v = dma_alloc_coherent(&macio_get_pci_dev(mdev)->dev,
+					   sizeof(struct rackmeter_dma),
+					   &rm->dma_buf_p, GFP_KERNEL);
+	if (rm->dma_buf_v == NULL) {
+		printk(KERN_ERR
+		       "rackmeter: failed to allocate dma buffer !\n");
+		rc = -ENOMEM;
+		goto bail_free_samples;
+	}
+#if 0
+	rm->i2s_regs = ioremap(macio_resource_start(mdev, 0), 0x1000);
+#else
+	rm->i2s_regs = ioremap(ri2s.start, 0x1000);
+#endif
+	if (rm->i2s_regs == NULL) {
+		printk(KERN_ERR
+		       "rackmeter: failed to map i2s registers !\n");
+		rc = -ENXIO;
+		goto bail_free_dma;
+	}
+#if 0
+	rm->dma_regs = ioremap(macio_resource_start(mdev, 1), 0x100);
+#else
+	rm->dma_regs = ioremap(rdma.start, 0x100);
+#endif
+	if (rm->dma_regs == NULL) {
+		printk(KERN_ERR
+		       "rackmeter: failed to map dma registers !\n");
+		rc = -ENXIO;
+		goto bail_unmap_i2s;
+	}
+
+	rc = rackmeter_setup(rm);
+	if (rc) {
+		printk(KERN_ERR
+		       "rackmeter: failed to initialize !\n");
+		rc = -ENXIO;
+		goto bail_unmap_dma;
+	}
+
+	rc = request_irq(rm->irq, rackmeter_irq, 0, "rackmeter", rm);
+	if (rc != 0) {
+		printk(KERN_ERR
+		       "rackmeter: failed to request interrupt !\n");
+		goto bail_stop_dma;
+	}
+	of_node_put(np);
+	return 0;
+
+ bail_stop_dma:
+	DBDMA_DO_RESET(rm->dma_regs);
+ bail_unmap_dma:
+	iounmap(rm->dma_regs);
+ bail_unmap_i2s:
+	iounmap(rm->i2s_regs);
+ bail_free_dma:
+	dma_free_coherent(&macio_get_pci_dev(mdev)->dev,
+			  sizeof(struct rackmeter_dma),
+			  rm->dma_buf_v, rm->dma_buf_p);
+ bail_free_samples:
+	free_page((unsigned long)rm->ubuf);
+ bail_release:
+#if 0
+	macio_release_resources(mdev);
+#endif
+ bail_free:
+	kfree(rm);
+ bail:
+	of_node_put(i2s);
+	of_node_put(np);
+	dev_set_drvdata(&mdev->ofdev.dev, NULL);
+	return rc;
+}
+
+static int __devexit rackmeter_remove(struct macio_dev* mdev)
+{
+	struct rackmeter *rm = dev_get_drvdata(&mdev->ofdev.dev);
+
+	/* Stop CPU sniffer timer & work queues */
+	rackmeter_stop_cpu_sniffer(rm);
+
+	/* Clear reference to private data */
+	dev_set_drvdata(&mdev->ofdev.dev, NULL);
+
+	/* Stop/reset dbdma */
+	DBDMA_DO_RESET(rm->dma_regs);
+
+	/* Release the IRQ */
+	free_irq(rm->irq, rm);
+
+	/* Unmap registers */
+	iounmap(rm->dma_regs);
+	iounmap(rm->i2s_regs);
+
+	/* Free DMA */
+	dma_free_coherent(&macio_get_pci_dev(mdev)->dev,
+			  sizeof(struct rackmeter_dma),
+			  rm->dma_buf_v, rm->dma_buf_p);
+
+	/* Free samples */
+	free_page((unsigned long)rm->ubuf);
+
+#if 0
+	/* Release resources */
+	macio_release_resources(mdev);
+#endif
+
+	/* Get rid of me */
+	kfree(rm);
+
+	return 0;
+}
+
+static int rackmeter_shutdown(struct macio_dev* mdev)
+{
+	struct rackmeter *rm = dev_get_drvdata(&mdev->ofdev.dev);
+
+	if (rm == NULL)
+		return -ENODEV;
+
+	/* Stop CPU sniffer timer & work queues */
+	rackmeter_stop_cpu_sniffer(rm);
+
+	/* Stop/reset dbdma */
+	DBDMA_DO_RESET(rm->dma_regs);
+
+	return 0;
+}
+
+static struct of_device_id rackmeter_match[] = {
+	{ .name = "i2s" },
+	{ }
+};
+
+static struct macio_driver rackmeter_drv = {
+	.name = "rackmeter",
+	.owner = THIS_MODULE,
+	.match_table = rackmeter_match,
+	.probe = rackmeter_probe,
+	.remove = rackmeter_remove,
+	.shutdown = rackmeter_shutdown,
+};
+
+
+static int __init rackmeter_init(void)
+{
+	pr_debug("rackmeter_init()\n");
+
+	return macio_register_driver(&rackmeter_drv);
+}
+
+static void __exit rackmeter_exit(void)
+{
+	pr_debug("rackmeter_exit()\n");
+
+	macio_unregister_driver(&rackmeter_drv);
+}
+
+module_init(rackmeter_init);
+module_exit(rackmeter_exit);
+
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Benjamin Herrenschmidt <benh@kernel.crashing.org>");
+MODULE_DESCRIPTION("RackMeter: Support vu-meter on XServe front panel");
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 4871158aca3e..6dde27ab79a8 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -46,6 +46,7 @@
 #include <asm/abs_addr.h>
 #include <asm/uaccess.h>
 #include <asm/of_device.h>
+#include <asm/of_platform.h>
 
 #define VERSION "0.7"
 #define AUTHOR  "(c) 2005 Benjamin Herrenschmidt, IBM Corp."
@@ -653,7 +654,7 @@ static int __init smu_init_sysfs(void)
 	 * I'm a bit too far from figuring out how that works with those
 	 * new chipsets, but that will come back and bite us
 	 */
-	of_register_driver(&smu_of_platform_driver);
+	of_register_platform_driver(&smu_of_platform_driver);
 	return 0;
 }
 
diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index a0f30d0853ea..13b953ae8ebc 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -30,7 +30,7 @@
 #include <asm/io.h>
 #include <asm/system.h>
 #include <asm/sections.h>
-#include <asm/of_device.h>
+#include <asm/of_platform.h>
 
 #undef DEBUG
 
diff --git a/drivers/macintosh/therm_pm72.c b/drivers/macintosh/therm_pm72.c
index d00c0c37a12e..2e4ad44a8636 100644
--- a/drivers/macintosh/therm_pm72.c
+++ b/drivers/macintosh/therm_pm72.c
@@ -129,6 +129,7 @@
 #include <asm/sections.h>
 #include <asm/of_device.h>
 #include <asm/macio.h>
+#include <asm/of_platform.h>
 
 #include "therm_pm72.h"
 
@@ -2236,14 +2237,14 @@ static int __init therm_pm72_init(void)
 		return -ENODEV;
 	}
 
-	of_register_driver(&fcu_of_platform_driver);
+	of_register_platform_driver(&fcu_of_platform_driver);
 	
 	return 0;
 }
 
 static void __exit therm_pm72_exit(void)
 {
-	of_unregister_driver(&fcu_of_platform_driver);
+	of_unregister_platform_driver(&fcu_of_platform_driver);
 
 	if (of_dev)
 		of_device_unregister(of_dev);
diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c
index 738faab1b22c..a1d3a987cb3a 100644
--- a/drivers/macintosh/therm_windtunnel.c
+++ b/drivers/macintosh/therm_windtunnel.c
@@ -36,12 +36,13 @@
 #include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
 #include <asm/system.h>
 #include <asm/sections.h>
-#include <asm/of_device.h>
+#include <asm/of_platform.h>
 #include <asm/macio.h>
 
 #define LOG_TEMP		0			/* continously log temperature */
@@ -511,14 +512,14 @@ g4fan_init( void )
 		return -ENODEV;
 	}
 
-	of_register_driver( &therm_of_driver );
+	of_register_platform_driver( &therm_of_driver );
 	return 0;
 }
 
 static void __exit
 g4fan_exit( void )
 {
-	of_unregister_driver( &therm_of_driver );
+	of_unregister_platform_driver( &therm_of_driver );
 
 	if( x.of_dev )
 		of_device_unregister( x.of_dev );
diff --git a/drivers/media/dvb/cinergyT2/cinergyT2.c b/drivers/media/dvb/cinergyT2/cinergyT2.c
index 8458ff3f351e..206c13e47a06 100644
--- a/drivers/media/dvb/cinergyT2/cinergyT2.c
+++ b/drivers/media/dvb/cinergyT2/cinergyT2.c
@@ -30,6 +30,7 @@
 #include <linux/input.h>
 #include <linux/dvb/frontend.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include "dmxdev.h"
 #include "dvb_demux.h"
diff --git a/drivers/net/ehea/ehea_qmr.c b/drivers/net/ehea/ehea_qmr.c
index 72ef7bde3346..f143e13b229d 100644
--- a/drivers/net/ehea/ehea_qmr.c
+++ b/drivers/net/ehea/ehea_qmr.c
@@ -26,6 +26,7 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/mm.h>
 #include "ehea.h"
 #include "ehea_phyp.h"
 #include "ehea_qmr.h"
diff --git a/drivers/net/ibm_emac/ibm_emac_mal.h b/drivers/net/ibm_emac/ibm_emac_mal.h
index f73f10a0a562..407d2acbf7c7 100644
--- a/drivers/net/ibm_emac/ibm_emac_mal.h
+++ b/drivers/net/ibm_emac/ibm_emac_mal.h
@@ -24,6 +24,7 @@
 #include <linux/netdevice.h>
 
 #include <asm/io.h>
+#include <asm/dcr.h>
 
 /*
  * These MAL "versions" probably aren't the real versions IBM uses for these 
@@ -191,6 +192,7 @@ struct mal_commac {
 
 struct ibm_ocp_mal {
 	int			dcrbase;
+	dcr_host_t		dcrhost;
 
 	struct list_head	poll_list;
 	struct net_device	poll_dev;
@@ -207,12 +209,12 @@ struct ibm_ocp_mal {
 
 static inline u32 get_mal_dcrn(struct ibm_ocp_mal *mal, int reg)
 {
-	return mfdcr(mal->dcrbase + reg);
+	return dcr_read(mal->dcrhost, mal->dcrbase + reg);
 }
 
 static inline void set_mal_dcrn(struct ibm_ocp_mal *mal, int reg, u32 val)
 {
-	mtdcr(mal->dcrbase + reg, val);
+	dcr_write(mal->dcrhost, mal->dcrbase + reg, val);
 }
 
 /* Register MAL devices */
diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c
index 44c9f993dcc4..99343b5836b8 100644
--- a/drivers/net/ibmveth.c
+++ b/drivers/net/ibmveth.c
@@ -50,7 +50,6 @@
 #include <asm/semaphore.h>
 #include <asm/hvcall.h>
 #include <asm/atomic.h>
-#include <asm/iommu.h>
 #include <asm/vio.h>
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
@@ -1000,8 +999,6 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_
 	adapter->mac_addr = 0;
 	memcpy(&adapter->mac_addr, mac_addr_p, 6);
 
-	adapter->liobn = dev->iommu_table->it_index;
-
 	netdev->irq = dev->irq;
 	netdev->open               = ibmveth_open;
 	netdev->poll               = ibmveth_poll;
@@ -1115,7 +1112,6 @@ static int ibmveth_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "%s %s\n\n", ibmveth_driver_string, ibmveth_driver_version);
 
 	seq_printf(seq, "Unit Address:    0x%x\n", adapter->vdev->unit_address);
-	seq_printf(seq, "LIOBN:           0x%lx\n", adapter->liobn);
 	seq_printf(seq, "Current MAC:     %02X:%02X:%02X:%02X:%02X:%02X\n",
 		   current_mac[0], current_mac[1], current_mac[2],
 		   current_mac[3], current_mac[4], current_mac[5]);
diff --git a/drivers/net/ibmveth.h b/drivers/net/ibmveth.h
index f5b25bff1540..bb69ccae8ace 100644
--- a/drivers/net/ibmveth.h
+++ b/drivers/net/ibmveth.h
@@ -118,7 +118,6 @@ struct ibmveth_adapter {
     struct net_device_stats stats;
     unsigned int mcastFilterSize;
     unsigned long mac_addr;
-    unsigned long liobn;
     void * buffer_list_addr;
     void * filter_list_addr;
     dma_addr_t buffer_list_dma;
diff --git a/drivers/net/lance.c b/drivers/net/lance.c
index 6efbd499d752..4256c13c73c2 100644
--- a/drivers/net/lance.c
+++ b/drivers/net/lance.c
@@ -57,6 +57,7 @@ static const char version[] = "lance.c:v1.16 2006/11/09 dplatt@3do.com, becker@c
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
+#include <linux/mm.h>
 #include <linux/bitops.h>
 
 #include <asm/io.h>
diff --git a/drivers/net/ne3210.c b/drivers/net/ne3210.c
index d66328975425..1a6fed76d4cc 100644
--- a/drivers/net/ne3210.c
+++ b/drivers/net/ne3210.c
@@ -36,6 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/mm.h>
 
 #include <asm/io.h>
 #include <asm/system.h>
diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
index f14e99276dba..096d4a100bf2 100644
--- a/drivers/net/phy/fixed.c
+++ b/drivers/net/phy/fixed.c
@@ -254,7 +254,7 @@ static int fixed_mdio_register_device(int number, int speed, int duplex)
 		goto device_create_fail;
 	}
 
-	phydev->irq = -1;
+	phydev->irq = PHY_IGNORE_INTERRUPT;
 	phydev->dev.bus = &mdio_bus_type;
 
 	if(number)
diff --git a/drivers/net/sk98lin/skge.c b/drivers/net/sk98lin/skge.c
index 12cbfd190dd7..92d11b961db8 100644
--- a/drivers/net/sk98lin/skge.c
+++ b/drivers/net/sk98lin/skge.c
@@ -114,6 +114,7 @@
 #include	<linux/dma-mapping.h>
 #include	<linux/ip.h>
 #include	<linux/mii.h>
+#include	<linux/mm.h>
 
 #include	"h/skdrv1st.h"
 #include	"h/skdrv2nd.h"
diff --git a/drivers/net/spider_net.c b/drivers/net/spider_net.c
index f16f696c1ff2..ebb6aa39f9c7 100644
--- a/drivers/net/spider_net.c
+++ b/drivers/net/spider_net.c
@@ -88,12 +88,11 @@ MODULE_DEVICE_TABLE(pci, spider_net_pci_tbl);
 static inline u32
 spider_net_read_reg(struct spider_net_card *card, u32 reg)
 {
-	u32 value;
-
-	value = readl(card->regs + reg);
-	value = le32_to_cpu(value);
-
-	return value;
+	/* We use the powerpc specific variants instead of readl_be() because
+	 * we know spidernet is not a real PCI device and we can thus avoid the
+	 * performance hit caused by the PCI workarounds.
+	 */
+	return in_be32(card->regs + reg);
 }
 
 /**
@@ -105,8 +104,11 @@ spider_net_read_reg(struct spider_net_card *card, u32 reg)
 static inline void
 spider_net_write_reg(struct spider_net_card *card, u32 reg, u32 value)
 {
-	value = cpu_to_le32(value);
-	writel(value, card->regs + reg);
+	/* We use the powerpc specific variants instead of writel_be() because
+	 * we know spidernet is not a real PCI device and we can thus avoid the
+	 * performance hit caused by the PCI workarounds.
+	 */
+	out_be32(card->regs + reg, value);
 }
 
 /** spider_net_write_phy - write to phy register
diff --git a/drivers/net/starfire.c b/drivers/net/starfire.c
index 7a0aee6c869d..bf873ea25797 100644
--- a/drivers/net/starfire.c
+++ b/drivers/net/starfire.c
@@ -41,6 +41,7 @@
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/if_vlan.h>
+#include <linux/mm.h>
 #include <asm/processor.h>		/* Processor type for cache alignment. */
 #include <asm/uaccess.h>
 #include <asm/io.h>
diff --git a/drivers/net/sun3lance.c b/drivers/net/sun3lance.c
index b865db363ba0..47a1c09d19ac 100644
--- a/drivers/net/sun3lance.c
+++ b/drivers/net/sun3lance.c
@@ -38,6 +38,7 @@ static char *version = "sun3lance.c: v1.2 1/12/2001  Sam Creasey (sammy@sammy.ne
 #include <linux/skbuff.h>
 #include <linux/bitops.h>
 
+#include <asm/cacheflush.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
 #include <asm/io.h>
diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c
index d03a9a849c06..785e4a535f9e 100644
--- a/drivers/net/sungem.c
+++ b/drivers/net/sungem.c
@@ -56,6 +56,7 @@
 #include <linux/if_vlan.h>
 #include <linux/bitops.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include <asm/system.h>
 #include <asm/io.h>
diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c
index ec432ea879fb..ef671739cfea 100644
--- a/drivers/net/sunhme.c
+++ b/drivers/net/sunhme.c
@@ -32,6 +32,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
+#include <linux/mm.h>
 #include <linux/bitops.h>
 
 #include <asm/system.h>
@@ -3012,6 +3013,11 @@ static int __devinit happy_meal_pci_probe(struct pci_dev *pdev,
 #endif
 
 	err = -ENODEV;
+
+	if (pci_enable_device(pdev))
+		goto err_out;
+	pci_set_master(pdev);
+
 	if (!strcmp(prom_name, "SUNW,qfe") || !strcmp(prom_name, "qfe")) {
 		qp = quattro_pci_find(pdev);
 		if (qp == NULL)
diff --git a/drivers/net/tokenring/ibmtr.c b/drivers/net/tokenring/ibmtr.c
index bfe59865b1dd..0d97e10ccac5 100644
--- a/drivers/net/tokenring/ibmtr.c
+++ b/drivers/net/tokenring/ibmtr.c
@@ -1826,7 +1826,7 @@ static void tr_rx(struct net_device *dev)
 	skb->protocol = tr_type_trans(skb, dev);
 	if (IPv4_p) {
 		skb->csum = chksum;
-		skb->ip_summed = 1;
+		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 	netif_rx(skb);
 	dev->last_rx = jiffies;
diff --git a/drivers/net/tulip/de4x5.c b/drivers/net/tulip/de4x5.c
index 3f4b6408b755..4b3cd3d8b62a 100644
--- a/drivers/net/tulip/de4x5.c
+++ b/drivers/net/tulip/de4x5.c
@@ -473,9 +473,9 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 #include <asm/uaccess.h>
-#ifdef CONFIG_PPC_MULTIPLATFORM
+#ifdef CONFIG_PPC_PMAC
 #include <asm/machdep.h>
-#endif /* CONFIG_PPC_MULTIPLATFORM */
+#endif /* CONFIG_PPC_PMAC */
 
 #include "de4x5.h"
 
@@ -4151,7 +4151,7 @@ get_hw_addr(struct net_device *dev)
     /* If possible, try to fix a broken card - SMC only so far */
     srom_repair(dev, broken);
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
+#ifdef CONFIG_PPC_PMAC
     /*
     ** If the address starts with 00 a0, we have to bit-reverse
     ** each byte of the address.
@@ -4168,7 +4168,7 @@ get_hw_addr(struct net_device *dev)
 		    dev->dev_addr[i] = ((x & 0x55) << 1) + ((x & 0xaa) >> 1);
 	    }
     }
-#endif /* CONFIG_PPC_MULTIPLATFORM */
+#endif /* CONFIG_PPC_PMAC */
 
     /* Test for a bad enet address */
     status = test_bad_enet(dev, status);
diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c
index 8ddea1da7c05..9781b16bb8b6 100644
--- a/drivers/net/typhoon.c
+++ b/drivers/net/typhoon.c
@@ -117,6 +117,7 @@ static const int multicast_filter_limit = 32;
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
+#include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/ethtool.h>
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 73a58c73d526..fc405f0165d9 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -1,5 +1,6 @@
 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/wait.h>
 
diff --git a/drivers/ps3/Makefile b/drivers/ps3/Makefile
new file mode 100644
index 000000000000..b52d547b7a78
--- /dev/null
+++ b/drivers/ps3/Makefile
@@ -0,0 +1 @@
+obj-y += system-bus.o
diff --git a/drivers/ps3/system-bus.c b/drivers/ps3/system-bus.c
new file mode 100644
index 000000000000..d79f949bcb2a
--- /dev/null
+++ b/drivers/ps3/system-bus.c
@@ -0,0 +1,362 @@
+/*
+ *  PS3 system bus driver.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+
+#include <asm/udbg.h>
+#include <asm/ps3.h>
+#include <asm/lv1call.h>
+#include <asm/firmware.h>
+
+#define dump_mmio_region(_a) _dump_mmio_region(_a, __func__, __LINE__)
+static void _dump_mmio_region(const struct ps3_mmio_region* r,
+	const char* func, int line)
+{
+	pr_debug("%s:%d: dev       %u:%u\n", func, line, r->did.bus_id,
+		r->did.dev_id);
+	pr_debug("%s:%d: bus_addr  %lxh\n", func, line, r->bus_addr);
+	pr_debug("%s:%d: len       %lxh\n", func, line, r->len);
+	pr_debug("%s:%d: lpar_addr %lxh\n", func, line, r->lpar_addr);
+}
+
+int ps3_mmio_region_create(struct ps3_mmio_region *r)
+{
+	int result;
+
+	result = lv1_map_device_mmio_region(r->did.bus_id, r->did.dev_id,
+		r->bus_addr, r->len, r->page_size, &r->lpar_addr);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_map_device_mmio_region failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+		r->lpar_addr = r->len = r->bus_addr = 0;
+	}
+
+	dump_mmio_region(r);
+	return result;
+}
+
+int ps3_free_mmio_region(struct ps3_mmio_region *r)
+{
+	int result;
+
+	result = lv1_unmap_device_mmio_region(r->did.bus_id, r->did.dev_id,
+		r->bus_addr);
+
+	if (result)
+		pr_debug("%s:%d: lv1_unmap_device_mmio_region failed: %s\n",
+			__func__, __LINE__, ps3_result(result));
+
+	r->lpar_addr = r->len = r->bus_addr = 0;
+	return result;
+}
+
+static int ps3_system_bus_match(struct device *_dev,
+	struct device_driver *_drv)
+{
+	int result;
+	struct ps3_system_bus_driver *drv = to_ps3_system_bus_driver(_drv);
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+
+	result = dev->match_id == drv->match_id;
+
+	pr_info("%s:%d: dev=%u(%s), drv=%u(%s): %s\n", __func__, __LINE__,
+		dev->match_id, dev->core.bus_id, drv->match_id, drv->core.name,
+		(result ? "match" : "miss"));
+	return result;
+}
+
+static int ps3_system_bus_probe(struct device *_dev)
+{
+	int result;
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+	struct ps3_system_bus_driver *drv =
+		to_ps3_system_bus_driver(_dev->driver);
+
+	result = lv1_open_device(dev->did.bus_id, dev->did.dev_id, 0);
+
+	if (result) {
+		pr_debug("%s:%d: lv1_open_device failed (%d)\n",
+			__func__, __LINE__, result);
+		result = -EACCES;
+		goto clean_none;
+	}
+
+	if (dev->d_region->did.bus_id) {
+		result = ps3_dma_region_create(dev->d_region);
+
+		if (result) {
+			pr_debug("%s:%d: ps3_dma_region_create failed (%d)\n",
+				__func__, __LINE__, result);
+			BUG_ON("check region type");
+			result = -EINVAL;
+			goto clean_device;
+		}
+	}
+
+	BUG_ON(!drv);
+
+	if (drv->probe)
+		result = drv->probe(dev);
+	else
+		pr_info("%s:%d: %s no probe method\n", __func__, __LINE__,
+			dev->core.bus_id);
+
+	if (result) {
+		pr_debug("%s:%d: drv->probe failed\n", __func__, __LINE__);
+		goto clean_dma;
+	}
+
+	return result;
+
+clean_dma:
+	ps3_dma_region_free(dev->d_region);
+clean_device:
+	lv1_close_device(dev->did.bus_id, dev->did.dev_id);
+clean_none:
+	return result;
+}
+
+static int ps3_system_bus_remove(struct device *_dev)
+{
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+	struct ps3_system_bus_driver *drv =
+		to_ps3_system_bus_driver(_dev->driver);
+
+	if (drv->remove)
+		drv->remove(dev);
+	else
+		pr_info("%s:%d: %s no remove method\n", __func__, __LINE__,
+			dev->core.bus_id);
+
+	ps3_dma_region_free(dev->d_region);
+	ps3_free_mmio_region(dev->m_region);
+	lv1_close_device(dev->did.bus_id, dev->did.dev_id);
+
+	return 0;
+}
+
+struct bus_type ps3_system_bus_type = {
+        .name = "ps3_system_bus",
+	.match = ps3_system_bus_match,
+	.probe = ps3_system_bus_probe,
+	.remove = ps3_system_bus_remove,
+};
+
+int __init ps3_system_bus_init(void)
+{
+	int result;
+
+	if (!firmware_has_feature(FW_FEATURE_PS3_LV1))
+		return 0;
+
+	result = bus_register(&ps3_system_bus_type);
+	BUG_ON(result);
+	return result;
+}
+
+core_initcall(ps3_system_bus_init);
+
+/* Allocates a contiguous real buffer and creates mappings over it.
+ * Returns the virtual address of the buffer and sets dma_handle
+ * to the dma address (mapping) of the first page.
+ */
+
+static void * ps3_alloc_coherent(struct device *_dev, size_t size,
+	dma_addr_t *dma_handle, gfp_t flag)
+{
+	int result;
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+	unsigned long virt_addr;
+
+	BUG_ON(!dev->d_region->bus_addr);
+
+	flag &= ~(__GFP_DMA | __GFP_HIGHMEM);
+	flag |= __GFP_ZERO;
+
+	virt_addr = __get_free_pages(flag, get_order(size));
+
+	if (!virt_addr) {
+		pr_debug("%s:%d: get_free_pages failed\n", __func__, __LINE__);
+		goto clean_none;
+	}
+
+	result = ps3_dma_map(dev->d_region, virt_addr, size, dma_handle);
+
+	if (result) {
+		pr_debug("%s:%d: ps3_dma_map failed (%d)\n",
+			__func__, __LINE__, result);
+		BUG_ON("check region type");
+		goto clean_alloc;
+	}
+
+	return (void*)virt_addr;
+
+clean_alloc:
+	free_pages(virt_addr, get_order(size));
+clean_none:
+	dma_handle = NULL;
+	return NULL;
+}
+
+static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr,
+	dma_addr_t dma_handle)
+{
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+
+	ps3_dma_unmap(dev->d_region, dma_handle, size);
+	free_pages((unsigned long)vaddr, get_order(size));
+}
+
+/* Creates TCEs for a user provided buffer.  The user buffer must be
+ * contiguous real kernel storage (not vmalloc).  The address of the buffer
+ * passed here is the kernel (virtual) address of the buffer.  The buffer
+ * need not be page aligned, the dma_addr_t returned will point to the same
+ * byte within the page as vaddr.
+ */
+
+static dma_addr_t ps3_map_single(struct device *_dev, void *ptr, size_t size,
+	enum dma_data_direction direction)
+{
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+	int result;
+	unsigned long bus_addr;
+
+	result = ps3_dma_map(dev->d_region, (unsigned long)ptr, size,
+		&bus_addr);
+
+	if (result) {
+		pr_debug("%s:%d: ps3_dma_map failed (%d)\n",
+			__func__, __LINE__, result);
+	}
+
+	return bus_addr;
+}
+
+static void ps3_unmap_single(struct device *_dev, dma_addr_t dma_addr,
+	size_t size, enum dma_data_direction direction)
+{
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+	int result;
+
+	result = ps3_dma_unmap(dev->d_region, dma_addr, size);
+
+	if (result) {
+		pr_debug("%s:%d: ps3_dma_unmap failed (%d)\n",
+			__func__, __LINE__, result);
+	}
+}
+
+static int ps3_map_sg(struct device *_dev, struct scatterlist *sg, int nents,
+	enum dma_data_direction direction)
+{
+#if defined(CONFIG_PS3_DYNAMIC_DMA)
+	BUG_ON("do");
+#endif
+	return 0;
+}
+
+static void ps3_unmap_sg(struct device *_dev, struct scatterlist *sg,
+	int nents, enum dma_data_direction direction)
+{
+#if defined(CONFIG_PS3_DYNAMIC_DMA)
+	BUG_ON("do");
+#endif
+}
+
+static int ps3_dma_supported(struct device *_dev, u64 mask)
+{
+	return 1;
+}
+
+static struct dma_mapping_ops ps3_dma_ops = {
+	.alloc_coherent = ps3_alloc_coherent,
+	.free_coherent = ps3_free_coherent,
+	.map_single = ps3_map_single,
+	.unmap_single = ps3_unmap_single,
+	.map_sg = ps3_map_sg,
+	.unmap_sg = ps3_unmap_sg,
+	.dma_supported = ps3_dma_supported
+};
+
+/**
+ * ps3_system_bus_release_device - remove a device from the system bus
+ */
+
+static void ps3_system_bus_release_device(struct device *_dev)
+{
+	struct ps3_system_bus_device *dev = to_ps3_system_bus_device(_dev);
+	kfree(dev);
+}
+
+/**
+ * ps3_system_bus_device_register - add a device to the system bus
+ *
+ * ps3_system_bus_device_register() expects the dev object to be allocated
+ * dynamically by the caller.  The system bus takes ownership of the dev
+ * object and frees the object in ps3_system_bus_release_device().
+ */
+
+int ps3_system_bus_device_register(struct ps3_system_bus_device *dev)
+{
+	int result;
+	static unsigned int dev_count = 1;
+
+	dev->core.parent = NULL;
+	dev->core.bus = &ps3_system_bus_type;
+	dev->core.release = ps3_system_bus_release_device;
+
+	dev->core.archdata.of_node = NULL;
+	dev->core.archdata.dma_ops = &ps3_dma_ops;
+	dev->core.archdata.numa_node = 0;
+
+	snprintf(dev->core.bus_id, sizeof(dev->core.bus_id), "sb_%02x",
+		dev_count++);
+
+	pr_debug("%s:%d add %s\n", __func__, __LINE__, dev->core.bus_id);
+
+	result = device_register(&dev->core);
+	return result;
+}
+
+EXPORT_SYMBOL_GPL(ps3_system_bus_device_register);
+
+int ps3_system_bus_driver_register(struct ps3_system_bus_driver *drv)
+{
+	int result;
+
+	drv->core.bus = &ps3_system_bus_type;
+
+	result = driver_register(&drv->core);
+	return result;
+}
+
+EXPORT_SYMBOL_GPL(ps3_system_bus_driver_register);
+
+void ps3_system_bus_driver_unregister(struct ps3_system_bus_driver *drv)
+{
+	driver_unregister(&drv->core);
+}
+
+EXPORT_SYMBOL_GPL(ps3_system_bus_driver_unregister);
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 79ffef6bfaf8..a2cef57d7bcb 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1264,15 +1264,21 @@ __dasd_check_expire(struct dasd_device * device)
 	if (list_empty(&device->ccw_queue))
 		return;
 	cqr = list_entry(device->ccw_queue.next, struct dasd_ccw_req, list);
-	if (cqr->status == DASD_CQR_IN_IO && cqr->expires != 0) {
-		if (time_after_eq(jiffies, cqr->expires + cqr->starttime)) {
+	if ((cqr->status == DASD_CQR_IN_IO && cqr->expires != 0) &&
+	    (time_after_eq(jiffies, cqr->expires + cqr->starttime))) {
+		if (device->discipline->term_IO(cqr) != 0) {
+			/* Hmpf, try again in 5 sec */
+			dasd_set_timer(device, 5*HZ);
+			DEV_MESSAGE(KERN_ERR, device,
+				    "internal error - timeout (%is) expired "
+				    "for cqr %p, termination failed, "
+				    "retrying in 5s",
+				    (cqr->expires/HZ), cqr);
+		} else {
 			DEV_MESSAGE(KERN_ERR, device,
 				    "internal error - timeout (%is) expired "
 				    "for cqr %p (%i retries left)",
 				    (cqr->expires/HZ), cqr, cqr->retries);
-			if (device->discipline->term_IO(cqr) != 0)
-				/* Hmpf, try again in 1/10 sec */
-				dasd_set_timer(device, 10);
 		}
 	}
 }
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 91cf971f0652..17fdd8c9f740 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -684,21 +684,26 @@ dasd_ro_store(struct device *dev, struct device_attribute *attr,
 	      const char *buf, size_t count)
 {
 	struct dasd_devmap *devmap;
-	int ro_flag;
+	int val;
+	char *endp;
 
 	devmap = dasd_devmap_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(devmap))
 		return PTR_ERR(devmap);
-	ro_flag = buf[0] == '1';
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (((endp + 1) < (buf + count)) || (val > 1))
+		return -EINVAL;
+
 	spin_lock(&dasd_devmap_lock);
-	if (ro_flag)
+	if (val)
 		devmap->features |= DASD_FEATURE_READONLY;
 	else
 		devmap->features &= ~DASD_FEATURE_READONLY;
 	if (devmap->device)
 		devmap->device->features = devmap->features;
 	if (devmap->device && devmap->device->gdp)
-		set_disk_ro(devmap->device->gdp, ro_flag);
+		set_disk_ro(devmap->device->gdp, val);
 	spin_unlock(&dasd_devmap_lock);
 	return count;
 }
@@ -729,17 +734,22 @@ dasd_use_diag_store(struct device *dev, struct device_attribute *attr,
 {
 	struct dasd_devmap *devmap;
 	ssize_t rc;
-	int use_diag;
+	int val;
+	char *endp;
 
 	devmap = dasd_devmap_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(devmap))
 		return PTR_ERR(devmap);
-	use_diag = buf[0] == '1';
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (((endp + 1) < (buf + count)) || (val > 1))
+		return -EINVAL;
+
 	spin_lock(&dasd_devmap_lock);
 	/* Changing diag discipline flag is only allowed in offline state. */
 	rc = count;
 	if (!devmap->device) {
-		if (use_diag)
+		if (val)
 			devmap->features |= DASD_FEATURE_USEDIAG;
 		else
 			devmap->features &= ~DASD_FEATURE_USEDIAG;
@@ -854,14 +864,20 @@ dasd_eer_store(struct device *dev, struct device_attribute *attr,
 	       const char *buf, size_t count)
 {
 	struct dasd_devmap *devmap;
-	int rc;
+	int val, rc;
+	char *endp;
 
 	devmap = dasd_devmap_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(devmap))
 		return PTR_ERR(devmap);
 	if (!devmap->device)
-		return count;
-	if (buf[0] == '1') {
+		return -ENODEV;
+
+	val = simple_strtoul(buf, &endp, 0);
+	if (((endp + 1) < (buf + count)) || (val > 1))
+		return -EINVAL;
+
+	if (val) {
 		rc = dasd_eer_enable(devmap->device);
 		if (rc)
 			return rc;
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index d7de175d53f0..c9321b920e90 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -299,14 +299,14 @@ raw3215_timeout(unsigned long __data)
 	struct raw3215_info *raw = (struct raw3215_info *) __data;
 	unsigned long flags;
 
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	if (raw->flags & RAW3215_TIMER_RUNS) {
 		del_timer(&raw->timer);
 		raw->flags &= ~RAW3215_TIMER_RUNS;
 		raw3215_mk_write_req(raw);
 		raw3215_start_io(raw);
 	}
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 }
 
 /*
@@ -355,10 +355,10 @@ raw3215_tasklet(void *data)
 	unsigned long flags;
 
 	raw = (struct raw3215_info *) data;
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	raw3215_mk_write_req(raw);
 	raw3215_try_io(raw);
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 	/* Check for pending message from raw3215_irq */
 	if (raw->message != NULL) {
 		printk(raw->message, raw->msg_dstat, raw->msg_cstat);
@@ -512,9 +512,9 @@ raw3215_make_room(struct raw3215_info *raw, unsigned int length)
 		if (RAW3215_BUFFER_SIZE - raw->count >= length)
 			break;
 		/* there might be another cpu waiting for the lock */
-		spin_unlock(raw->lock);
+		spin_unlock(get_ccwdev_lock(raw->cdev));
 		udelay(100);
-		spin_lock(raw->lock);
+		spin_lock(get_ccwdev_lock(raw->cdev));
 	}
 }
 
@@ -528,7 +528,7 @@ raw3215_write(struct raw3215_info *raw, const char *str, unsigned int length)
 	int c, count;
 
 	while (length > 0) {
-		spin_lock_irqsave(raw->lock, flags);
+		spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 		count = (length > RAW3215_BUFFER_SIZE) ?
 					     RAW3215_BUFFER_SIZE : length;
 		length -= count;
@@ -555,7 +555,7 @@ raw3215_write(struct raw3215_info *raw, const char *str, unsigned int length)
 			/* start or queue request */
 			raw3215_try_io(raw);
 		}
-		spin_unlock_irqrestore(raw->lock, flags);
+		spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 	}
 }
 
@@ -568,7 +568,7 @@ raw3215_putchar(struct raw3215_info *raw, unsigned char ch)
 	unsigned long flags;
 	unsigned int length, i;
 
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	if (ch == '\t') {
 		length = TAB_STOP_SIZE - (raw->line_pos%TAB_STOP_SIZE);
 		raw->line_pos += length;
@@ -592,7 +592,7 @@ raw3215_putchar(struct raw3215_info *raw, unsigned char ch)
 		/* start or queue request */
 		raw3215_try_io(raw);
 	}
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 }
 
 /*
@@ -604,13 +604,13 @@ raw3215_flush_buffer(struct raw3215_info *raw)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	if (raw->count > 0) {
 		raw->flags |= RAW3215_FLUSHING;
 		raw3215_try_io(raw);
 		raw->flags &= ~RAW3215_FLUSHING;
 	}
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 }
 
 /*
@@ -625,9 +625,9 @@ raw3215_startup(struct raw3215_info *raw)
 		return 0;
 	raw->line_pos = 0;
 	raw->flags |= RAW3215_ACTIVE;
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	raw3215_try_io(raw);
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 
 	return 0;
 }
@@ -644,21 +644,21 @@ raw3215_shutdown(struct raw3215_info *raw)
 	if (!(raw->flags & RAW3215_ACTIVE) || (raw->flags & RAW3215_FIXED))
 		return;
 	/* Wait for outstanding requests, then free irq */
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	if ((raw->flags & RAW3215_WORKING) ||
 	    raw->queued_write != NULL ||
 	    raw->queued_read != NULL) {
 		raw->flags |= RAW3215_CLOSING;
 		add_wait_queue(&raw->empty_wait, &wait);
 		set_current_state(TASK_INTERRUPTIBLE);
-		spin_unlock_irqrestore(raw->lock, flags);
+		spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 		schedule();
-		spin_lock_irqsave(raw->lock, flags);
+		spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 		remove_wait_queue(&raw->empty_wait, &wait);
 		set_current_state(TASK_RUNNING);
 		raw->flags &= ~(RAW3215_ACTIVE | RAW3215_CLOSING);
 	}
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 }
 
 static int
@@ -686,7 +686,6 @@ raw3215_probe (struct ccw_device *cdev)
 	}
 
 	raw->cdev = cdev;
-	raw->lock = get_ccwdev_lock(cdev);
 	raw->inbuf = (char *) raw + sizeof(struct raw3215_info);
 	memset(raw, 0, sizeof(struct raw3215_info));
 	raw->buffer = (char *) kmalloc(RAW3215_BUFFER_SIZE,
@@ -809,9 +808,9 @@ con3215_unblank(void)
 	unsigned long flags;
 
 	raw = raw3215[0];  /* console 3215 is the first one */
-	spin_lock_irqsave(raw->lock, flags);
+	spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 	raw3215_make_room(raw, RAW3215_BUFFER_SIZE);
-	spin_unlock_irqrestore(raw->lock, flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 }
 
 static int __init 
@@ -873,7 +872,6 @@ con3215_init(void)
 	raw->buffer = (char *) alloc_bootmem_low(RAW3215_BUFFER_SIZE);
 	raw->inbuf = (char *) alloc_bootmem_low(RAW3215_INBUF_SIZE);
 	raw->cdev = cdev;
-	raw->lock = get_ccwdev_lock(cdev);
 	cdev->dev.driver_data = raw;
 	cdev->handler = raw3215_irq;
 
@@ -1066,10 +1064,10 @@ tty3215_unthrottle(struct tty_struct * tty)
 
 	raw = (struct raw3215_info *) tty->driver_data;
 	if (raw->flags & RAW3215_THROTTLED) {
-		spin_lock_irqsave(raw->lock, flags);
+		spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 		raw->flags &= ~RAW3215_THROTTLED;
 		raw3215_try_io(raw);
-		spin_unlock_irqrestore(raw->lock, flags);
+		spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 	}
 }
 
@@ -1096,10 +1094,10 @@ tty3215_start(struct tty_struct *tty)
 
 	raw = (struct raw3215_info *) tty->driver_data;
 	if (raw->flags & RAW3215_STOPPED) {
-		spin_lock_irqsave(raw->lock, flags);
+		spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
 		raw->flags &= ~RAW3215_STOPPED;
 		raw3215_try_io(raw);
-		spin_unlock_irqrestore(raw->lock, flags);
+		spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
 	}
 }
 
diff --git a/drivers/s390/char/sclp_quiesce.c b/drivers/s390/char/sclp_quiesce.c
index 32004aae95c1..ffa9282ce97a 100644
--- a/drivers/s390/char/sclp_quiesce.c
+++ b/drivers/s390/char/sclp_quiesce.c
@@ -19,52 +19,17 @@
 
 #include "sclp.h"
 
-
-#ifdef CONFIG_SMP
-/* Signal completion of shutdown process. All CPUs except the first to enter
- * this function: go to stopped state. First CPU: wait until all other
- * CPUs are in stopped or check stop state. Afterwards, load special PSW
- * to indicate completion. */
-static void
-do_load_quiesce_psw(void * __unused)
-{
-	static atomic_t cpuid = ATOMIC_INIT(-1);
-	psw_t quiesce_psw;
-	int cpu;
-
-	if (atomic_cmpxchg(&cpuid, -1, smp_processor_id()) != -1)
-		signal_processor(smp_processor_id(), sigp_stop);
-	/* Wait for all other cpus to enter stopped state */
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		while(!smp_cpu_not_running(cpu))
-			cpu_relax();
-	}
-	/* Quiesce the last cpu with the special psw */
-	quiesce_psw.mask = PSW_BASE_BITS | PSW_MASK_WAIT;
-	quiesce_psw.addr = 0xfff;
-	__load_psw(quiesce_psw);
-}
-
-/* Shutdown handler. Perform shutdown function on all CPUs. */
-static void
-do_machine_quiesce(void)
-{
-	on_each_cpu(do_load_quiesce_psw, NULL, 0, 0);
-}
-#else
 /* Shutdown handler. Signal completion of shutdown by loading special PSW. */
 static void
 do_machine_quiesce(void)
 {
 	psw_t quiesce_psw;
 
+	smp_send_stop();
 	quiesce_psw.mask = PSW_BASE_BITS | PSW_MASK_WAIT;
 	quiesce_psw.addr = 0xfff;
 	__load_psw(quiesce_psw);
 }
-#endif
 
 /* Handler for quiesce event. Start shutdown procedure. */
 static void
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 2d78f0f4a40f..dbfb77b03928 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -251,6 +251,8 @@ s390_subchannel_remove_chpid(struct device *dev, void *data)
 		cc = cio_clear(sch);
 		if (cc == -ENODEV)
 			goto out_unreg;
+		/* Request retry of internal operation. */
+		device_set_intretry(sch);
 		/* Call handler. */
 		if (sch->driver && sch->driver->termination)
 			sch->driver->termination(&sch->dev);
@@ -711,9 +713,6 @@ static inline int check_for_io_on_path(struct subchannel *sch, int index)
 {
 	int cc;
 
-	if (!device_is_online(sch))
-		/* cio could be doing I/O. */
-		return 0;
 	cc = stsch(sch->schid, &sch->schib);
 	if (cc)
 		return 0;
@@ -722,6 +721,26 @@ static inline int check_for_io_on_path(struct subchannel *sch, int index)
 	return 0;
 }
 
+static void terminate_internal_io(struct subchannel *sch)
+{
+	if (cio_clear(sch)) {
+		/* Recheck device in case clear failed. */
+		sch->lpm = 0;
+		if (device_trigger_verify(sch) != 0) {
+			if(css_enqueue_subchannel_slow(sch->schid)) {
+				css_clear_subchannel_slow_list();
+				need_rescan = 1;
+			}
+		}
+		return;
+	}
+	/* Request retry of internal operation. */
+	device_set_intretry(sch);
+	/* Call handler. */
+	if (sch->driver && sch->driver->termination)
+		sch->driver->termination(&sch->dev);
+}
+
 static inline void
 __s390_subchannel_vary_chpid(struct subchannel *sch, __u8 chpid, int on)
 {
@@ -744,20 +763,26 @@ __s390_subchannel_vary_chpid(struct subchannel *sch, __u8 chpid, int on)
 				device_trigger_reprobe(sch);
 			else if (sch->driver && sch->driver->verify)
 				sch->driver->verify(&sch->dev);
-		} else {
-			sch->opm &= ~(0x80 >> chp);
-			sch->lpm &= ~(0x80 >> chp);
-			if (check_for_io_on_path(sch, chp))
+			break;
+		}
+		sch->opm &= ~(0x80 >> chp);
+		sch->lpm &= ~(0x80 >> chp);
+		if (check_for_io_on_path(sch, chp)) {
+			if (device_is_online(sch))
 				/* Path verification is done after killing. */
 				device_kill_io(sch);
-			else if (!sch->lpm) {
+			else
+				/* Kill and retry internal I/O. */
+				terminate_internal_io(sch);
+		} else if (!sch->lpm) {
+			if (device_trigger_verify(sch) != 0) {
 				if (css_enqueue_subchannel_slow(sch->schid)) {
 					css_clear_subchannel_slow_list();
 					need_rescan = 1;
 				}
-			} else if (sch->driver && sch->driver->verify)
-				sch->driver->verify(&sch->dev);
-		}
+			}
+		} else if (sch->driver && sch->driver->verify)
+			sch->driver->verify(&sch->dev);
 		break;
 	}
 	spin_unlock_irqrestore(&sch->lock, flags);
@@ -1465,41 +1490,6 @@ chsc_get_chp_desc(struct subchannel *sch, int chp_no)
 	return desc;
 }
 
-static int reset_channel_path(struct channel_path *chp)
-{
-	int cc;
-
-	cc = rchp(chp->id);
-	switch (cc) {
-	case 0:
-		return 0;
-	case 2:
-		return -EBUSY;
-	default:
-		return -ENODEV;
-	}
-}
-
-static void reset_channel_paths_css(struct channel_subsystem *css)
-{
-	int i;
-
-	for (i = 0; i <= __MAX_CHPID; i++) {
-		if (css->chps[i])
-			reset_channel_path(css->chps[i]);
-	}
-}
-
-void cio_reset_channel_paths(void)
-{
-	int i;
-
-	for (i = 0; i <= __MAX_CSSID; i++) {
-		if (css[i] && css[i]->valid)
-			reset_channel_paths_css(css[i]);
-	}
-}
-
 static int __init
 chsc_alloc_sei_area(void)
 {
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 8936e460a807..20aee2783847 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -21,6 +21,7 @@
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/setup.h>
+#include <asm/reset.h>
 #include "airq.h"
 #include "cio.h"
 #include "css.h"
@@ -28,6 +29,7 @@
 #include "ioasm.h"
 #include "blacklist.h"
 #include "cio_debug.h"
+#include "../s390mach.h"
 
 debug_info_t *cio_debug_msg_id;
 debug_info_t *cio_debug_trace_id;
@@ -841,26 +843,12 @@ __clear_subchannel_easy(struct subchannel_id schid)
 	return -EBUSY;
 }
 
-struct sch_match_id {
-	struct subchannel_id schid;
-	struct ccw_dev_id devid;
-	int rc;
-};
-
-static int __shutdown_subchannel_easy_and_match(struct subchannel_id schid,
-	void *data)
+static int __shutdown_subchannel_easy(struct subchannel_id schid, void *data)
 {
 	struct schib schib;
-	struct sch_match_id *match_id = data;
 
 	if (stsch_err(schid, &schib))
 		return -ENXIO;
-	if (match_id && schib.pmcw.dnv &&
-		(schib.pmcw.dev == match_id->devid.devno) &&
-		(schid.ssid == match_id->devid.ssid)) {
-		match_id->schid = schid;
-		match_id->rc = 0;
-	}
 	if (!schib.pmcw.ena)
 		return 0;
 	switch(__disable_subchannel_easy(schid, &schib)) {
@@ -876,27 +864,111 @@ static int __shutdown_subchannel_easy_and_match(struct subchannel_id schid,
 	return 0;
 }
 
-static int clear_all_subchannels_and_match(struct ccw_dev_id *devid,
-	struct subchannel_id *schid)
+static atomic_t chpid_reset_count;
+
+static void s390_reset_chpids_mcck_handler(void)
+{
+	struct crw crw;
+	struct mci *mci;
+
+	/* Check for pending channel report word. */
+	mci = (struct mci *)&S390_lowcore.mcck_interruption_code;
+	if (!mci->cp)
+		return;
+	/* Process channel report words. */
+	while (stcrw(&crw) == 0) {
+		/* Check for responses to RCHP. */
+		if (crw.slct && crw.rsc == CRW_RSC_CPATH)
+			atomic_dec(&chpid_reset_count);
+	}
+}
+
+#define RCHP_TIMEOUT (30 * USEC_PER_SEC)
+static void css_reset(void)
+{
+	int i, ret;
+	unsigned long long timeout;
+
+	/* Reset subchannels. */
+	for_each_subchannel(__shutdown_subchannel_easy,  NULL);
+	/* Reset channel paths. */
+	s390_reset_mcck_handler = s390_reset_chpids_mcck_handler;
+	/* Enable channel report machine checks. */
+	__ctl_set_bit(14, 28);
+	/* Temporarily reenable machine checks. */
+	local_mcck_enable();
+	for (i = 0; i <= __MAX_CHPID; i++) {
+		ret = rchp(i);
+		if ((ret == 0) || (ret == 2))
+			/*
+			 * rchp either succeeded, or another rchp is already
+			 * in progress. In either case, we'll get a crw.
+			 */
+			atomic_inc(&chpid_reset_count);
+	}
+	/* Wait for machine check for all channel paths. */
+	timeout = get_clock() + (RCHP_TIMEOUT << 12);
+	while (atomic_read(&chpid_reset_count) != 0) {
+		if (get_clock() > timeout)
+			break;
+		cpu_relax();
+	}
+	/* Disable machine checks again. */
+	local_mcck_disable();
+	/* Disable channel report machine checks. */
+	__ctl_clear_bit(14, 28);
+	s390_reset_mcck_handler = NULL;
+}
+
+static struct reset_call css_reset_call = {
+	.fn = css_reset,
+};
+
+static int __init init_css_reset_call(void)
+{
+	atomic_set(&chpid_reset_count, 0);
+	register_reset_call(&css_reset_call);
+	return 0;
+}
+
+arch_initcall(init_css_reset_call);
+
+struct sch_match_id {
+	struct subchannel_id schid;
+	struct ccw_dev_id devid;
+	int rc;
+};
+
+static int __reipl_subchannel_match(struct subchannel_id schid, void *data)
+{
+	struct schib schib;
+	struct sch_match_id *match_id = data;
+
+	if (stsch_err(schid, &schib))
+		return -ENXIO;
+	if (schib.pmcw.dnv &&
+	    (schib.pmcw.dev == match_id->devid.devno) &&
+	    (schid.ssid == match_id->devid.ssid)) {
+		match_id->schid = schid;
+		match_id->rc = 0;
+		return 1;
+	}
+	return 0;
+}
+
+static int reipl_find_schid(struct ccw_dev_id *devid,
+			    struct subchannel_id *schid)
 {
 	struct sch_match_id match_id;
 
 	match_id.devid = *devid;
 	match_id.rc = -ENODEV;
-	local_irq_disable();
-	for_each_subchannel(__shutdown_subchannel_easy_and_match, &match_id);
+	for_each_subchannel(__reipl_subchannel_match, &match_id);
 	if (match_id.rc == 0)
 		*schid = match_id.schid;
 	return match_id.rc;
 }
 
-
-void clear_all_subchannels(void)
-{
-	local_irq_disable();
-	for_each_subchannel(__shutdown_subchannel_easy_and_match, NULL);
-}
-
 extern void do_reipl_asm(__u32 schid);
 
 /* Make sure all subchannels are quiet before we re-ipl an lpar. */
@@ -904,9 +976,9 @@ void reipl_ccw_dev(struct ccw_dev_id *devid)
 {
 	struct subchannel_id schid;
 
-	if (clear_all_subchannels_and_match(devid, &schid))
+	s390_reset_system();
+	if (reipl_find_schid(devid, &schid) != 0)
 		panic("IPL Device not found\n");
-	cio_reset_channel_paths();
 	do_reipl_asm(*((__u32*)&schid));
 }
 
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 4c2ff8336288..9ff064e71767 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -94,6 +94,7 @@ struct ccw_device_private {
 		unsigned int donotify:1;    /* call notify function */
 		unsigned int recog_done:1;  /* dev. recog. complete */
 		unsigned int fake_irb:1;    /* deliver faked irb */
+		unsigned int intretry:1;    /* retry internal operation */
 	} __attribute__((packed)) flags;
 	unsigned long intparm;	/* user interruption parameter */
 	struct qdio_irq *qdio_data;
@@ -171,6 +172,8 @@ void device_trigger_reprobe(struct subchannel *);
 /* Helper functions for vary on/off. */
 int device_is_online(struct subchannel *);
 void device_kill_io(struct subchannel *);
+void device_set_intretry(struct subchannel *sch);
+int device_trigger_verify(struct subchannel *sch);
 
 /* Machine check helper function. */
 void device_kill_pending_timer(struct subchannel *);
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 39c98f940507..d3d3716ff84b 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -687,8 +687,20 @@ io_subchannel_register(void *data)
 	cdev = data;
 	sch = to_subchannel(cdev->dev.parent);
 
+	/*
+	 * io_subchannel_register() will also be called after device
+	 * recognition has been done for a boxed device (which will already
+	 * be registered). We need to reprobe since we may now have sense id
+	 * information.
+	 */
 	if (klist_node_attached(&cdev->dev.knode_parent)) {
-		bus_rescan_devices(&ccw_bus_type);
+		if (!cdev->drv) {
+			ret = device_reprobe(&cdev->dev);
+			if (ret)
+				/* We can't do much here. */
+				dev_info(&cdev->dev, "device_reprobe() returned"
+					 " %d\n", ret);
+		}
 		goto out;
 	}
 	/* make it known to the system */
@@ -948,6 +960,9 @@ io_subchannel_ioterm(struct device *dev)
 	cdev = dev->driver_data;
 	if (!cdev)
 		return;
+	/* Internal I/O will be retried by the interrupt handler. */
+	if (cdev->private->flags.intretry)
+		return;
 	cdev->private->state = DEV_STATE_CLEAR_VERIFY;
 	if (cdev->handler)
 		cdev->handler(cdev, cdev->private->intparm,
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index de3d0857db9f..09c7672eb3f3 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -59,6 +59,27 @@ device_set_disconnected(struct subchannel *sch)
 	cdev->private->state = DEV_STATE_DISCONNECTED;
 }
 
+void device_set_intretry(struct subchannel *sch)
+{
+	struct ccw_device *cdev;
+
+	cdev = sch->dev.driver_data;
+	if (!cdev)
+		return;
+	cdev->private->flags.intretry = 1;
+}
+
+int device_trigger_verify(struct subchannel *sch)
+{
+	struct ccw_device *cdev;
+
+	cdev = sch->dev.driver_data;
+	if (!cdev || !cdev->online)
+		return -EINVAL;
+	dev_fsm_event(cdev, DEV_EVENT_VERIFY);
+	return 0;
+}
+
 /*
  * Timeout function. It just triggers a DEV_EVENT_TIMEOUT.
  */
@@ -893,6 +914,12 @@ ccw_device_w4sense(struct ccw_device *cdev, enum dev_event dev_event)
 	 * had killed the original request.
 	 */
 	if (irb->scsw.fctl & (SCSW_FCTL_CLEAR_FUNC | SCSW_FCTL_HALT_FUNC)) {
+		/* Retry Basic Sense if requested. */
+		if (cdev->private->flags.intretry) {
+			cdev->private->flags.intretry = 0;
+			ccw_device_do_sense(cdev, irb);
+			return;
+		}
 		cdev->private->flags.dosense = 0;
 		memset(&cdev->private->irb, 0, sizeof(struct irb));
 		ccw_device_accumulate_irb(cdev, irb);
diff --git a/drivers/s390/cio/device_id.c b/drivers/s390/cio/device_id.c
index a74785b9e4eb..f17275917fe5 100644
--- a/drivers/s390/cio/device_id.c
+++ b/drivers/s390/cio/device_id.c
@@ -191,6 +191,8 @@ __ccw_device_sense_id_start(struct ccw_device *cdev)
 		if ((sch->opm & cdev->private->imask) != 0 &&
 		    cdev->private->iretry > 0) {
 			cdev->private->iretry--;
+			/* Reset internal retry indication. */
+			cdev->private->flags.intretry = 0;
 			ret = cio_start (sch, cdev->private->iccws,
 					 cdev->private->imask);
 			/* ret is 0, -EBUSY, -EACCES or -ENODEV */
@@ -237,8 +239,14 @@ ccw_device_check_sense_id(struct ccw_device *cdev)
 		return 0; /* Success */
 	}
 	/* Check the error cases. */
-	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC))
+	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC)) {
+		/* Retry Sense ID if requested. */
+		if (cdev->private->flags.intretry) {
+			cdev->private->flags.intretry = 0;
+			return -EAGAIN;
+		}
 		return -ETIME;
+	}
 	if (irb->esw.esw0.erw.cons && (irb->ecw[0] & SNS0_CMD_REJECT)) {
 		/*
 		 * if the device doesn't support the SenseID
diff --git a/drivers/s390/cio/device_pgid.c b/drivers/s390/cio/device_pgid.c
index 2975ce888c19..cb1879a96818 100644
--- a/drivers/s390/cio/device_pgid.c
+++ b/drivers/s390/cio/device_pgid.c
@@ -71,6 +71,8 @@ __ccw_device_sense_pgid_start(struct ccw_device *cdev)
 		ccw->cda = (__u32) __pa (&cdev->private->pgid[i]);
 		if (cdev->private->iretry > 0) {
 			cdev->private->iretry--;
+			/* Reset internal retry indication. */
+			cdev->private->flags.intretry = 0;
 			ret = cio_start (sch, cdev->private->iccws, 
 					 cdev->private->imask);
 			/* ret is 0, -EBUSY, -EACCES or -ENODEV */
@@ -122,8 +124,14 @@ __ccw_device_check_sense_pgid(struct ccw_device *cdev)
 
 	sch = to_subchannel(cdev->dev.parent);
 	irb = &cdev->private->irb;
-	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC))
+	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC)) {
+		/* Retry Sense PGID if requested. */
+		if (cdev->private->flags.intretry) {
+			cdev->private->flags.intretry = 0;
+			return -EAGAIN;
+		}
 		return -ETIME;
+	}
 	if (irb->esw.esw0.erw.cons &&
 	    (irb->ecw[0]&(SNS0_CMD_REJECT|SNS0_INTERVENTION_REQ))) {
 		/*
@@ -253,6 +261,8 @@ __ccw_device_do_pgid(struct ccw_device *cdev, __u8 func)
 	ret = -EACCES;
 	if (cdev->private->iretry > 0) {
 		cdev->private->iretry--;
+		/* Reset internal retry indication. */
+		cdev->private->flags.intretry = 0;
 		ret = cio_start (sch, cdev->private->iccws,
 				 cdev->private->imask);
 		/* We expect an interrupt in case of success or busy
@@ -293,6 +303,8 @@ static int __ccw_device_do_nop(struct ccw_device *cdev)
 	ret = -EACCES;
 	if (cdev->private->iretry > 0) {
 		cdev->private->iretry--;
+		/* Reset internal retry indication. */
+		cdev->private->flags.intretry = 0;
 		ret = cio_start (sch, cdev->private->iccws,
 				 cdev->private->imask);
 		/* We expect an interrupt in case of success or busy
@@ -321,8 +333,14 @@ __ccw_device_check_pgid(struct ccw_device *cdev)
 
 	sch = to_subchannel(cdev->dev.parent);
 	irb = &cdev->private->irb;
-	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC))
+	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC)) {
+		/* Retry Set PGID if requested. */
+		if (cdev->private->flags.intretry) {
+			cdev->private->flags.intretry = 0;
+			return -EAGAIN;
+		}
 		return -ETIME;
+	}
 	if (irb->esw.esw0.erw.cons) {
 		if (irb->ecw[0] & SNS0_CMD_REJECT)
 			return -EOPNOTSUPP;
@@ -360,8 +378,14 @@ static int __ccw_device_check_nop(struct ccw_device *cdev)
 
 	sch = to_subchannel(cdev->dev.parent);
 	irb = &cdev->private->irb;
-	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC))
+	if (irb->scsw.fctl & (SCSW_FCTL_HALT_FUNC | SCSW_FCTL_CLEAR_FUNC)) {
+		/* Retry NOP if requested. */
+		if (cdev->private->flags.intretry) {
+			cdev->private->flags.intretry = 0;
+			return -EAGAIN;
+		}
 		return -ETIME;
+	}
 	if (irb->scsw.cc == 3) {
 		CIO_MSG_EVENT(2, "NOP - Device %04x on Subchannel 0.%x.%04x,"
 			      " lpm %02X, became 'not operational'\n",
diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c
index 3f7cbce4cd87..bdcf930f7beb 100644
--- a/drivers/s390/cio/device_status.c
+++ b/drivers/s390/cio/device_status.c
@@ -319,6 +319,9 @@ ccw_device_do_sense(struct ccw_device *cdev, struct irb *irb)
 	sch->sense_ccw.count = SENSE_MAX_COUNT;
 	sch->sense_ccw.flags = CCW_FLAG_SLI;
 
+	/* Reset internal retry indication. */
+	cdev->private->flags.intretry = 0;
+
 	return cio_start (sch, &sch->sense_ccw, 0xff);
 }
 
diff --git a/drivers/s390/cio/qdio.c b/drivers/s390/cio/qdio.c
index 476aa1da5cbc..8d5fa1b4d11f 100644
--- a/drivers/s390/cio/qdio.c
+++ b/drivers/s390/cio/qdio.c
@@ -481,7 +481,7 @@ qdio_stop_polling(struct qdio_q *q)
        unsigned char state = 0;
        struct qdio_irq *irq = (struct qdio_irq *) q->irq_ptr;
 
-	if (!atomic_swap(&q->polling,0)) 
+	if (!atomic_xchg(&q->polling,0))
 		return 1;
 
 	QDIO_DBF_TEXT4(0,trace,"stoppoll");
@@ -1964,8 +1964,8 @@ qdio_irq_check_sense(struct subchannel_id schid, struct irb *irb)
 		QDIO_DBF_HEX0(0,sense,irb,QDIO_DBF_SENSE_LEN);
 
 		QDIO_PRINT_WARN("sense data available on qdio channel.\n");
-		HEXDUMP16(WARN,"irb: ",irb);
-		HEXDUMP16(WARN,"sense data: ",irb->ecw);
+		QDIO_HEXDUMP16(WARN,"irb: ",irb);
+		QDIO_HEXDUMP16(WARN,"sense data: ",irb->ecw);
 	}
 		
 }
@@ -3425,7 +3425,7 @@ do_qdio_handle_inbound(struct qdio_q *q, unsigned int callflags,
 	
 	if ((used_elements+count==QDIO_MAX_BUFFERS_PER_Q)&&
 	    (callflags&QDIO_FLAG_UNDER_INTERRUPT))
-		atomic_swap(&q->polling,0);
+		atomic_xchg(&q->polling,0);
 	
 	if (used_elements) 
 		return;
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 49bb9e371c32..42927c1b7451 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -236,7 +236,7 @@ enum qdio_irq_states {
 #define QDIO_PRINT_EMERG(x...) do { } while (0)
 #endif
 
-#define HEXDUMP16(importance,header,ptr) \
+#define QDIO_HEXDUMP16(importance,header,ptr) \
 QDIO_PRINT_##importance(header "%02x %02x %02x %02x  " \
 			"%02x %02x %02x %02x  %02x %02x %02x %02x  " \
 			"%02x %02x %02x %02x\n",*(((char*)ptr)), \
@@ -429,8 +429,6 @@ struct qdio_perf_stats {
 };
 #endif /* QDIO_PERFORMANCE_STATS */
 
-#define atomic_swap(a,b) xchg((int*)a.counter,b)
-
 /* unlikely as the later the better */
 #define SYNC_MEMORY if (unlikely(q->siga_sync)) qdio_siga_sync_q(q)
 #define SYNC_MEMORY_ALL if (unlikely(q->siga_sync)) \
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 79d89c368919..6a54334ffe09 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -431,7 +431,15 @@ static int ap_uevent (struct device *dev, char **envp, int num_envp,
 			   ap_dev->device_type);
 	if (buffer_size - length <= 0)
 		return -ENOMEM;
-	envp[1] = 0;
+	buffer += length;
+	buffer_size -= length;
+	/* Add MODALIAS= */
+	envp[1] = buffer;
+	length = scnprintf(buffer, buffer_size, "MODALIAS=ap:t%02X",
+			   ap_dev->device_type);
+	if (buffer_size - length <= 0)
+		return -ENOMEM;
+	envp[2] = NULL;
 	return 0;
 }
 
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
index 66a8aec6efa6..08d4e47070bd 100644
--- a/drivers/s390/net/lcs.c
+++ b/drivers/s390/net/lcs.c
@@ -54,6 +54,8 @@
 #error Cannot compile lcs.c without some net devices switched on.
 #endif
 
+#define PRINTK_HEADER		" lcs: "
+
 /**
  * initialization string for output
  */
@@ -120,7 +122,7 @@ lcs_alloc_channel(struct lcs_channel *channel)
 			kzalloc(LCS_IOBUFFERSIZE, GFP_DMA | GFP_KERNEL);
 		if (channel->iob[cnt].data == NULL)
 			break;
-		channel->iob[cnt].state = BUF_STATE_EMPTY;
+		channel->iob[cnt].state = LCS_BUF_STATE_EMPTY;
 	}
 	if (cnt < LCS_NUM_BUFFS) {
 		/* Not all io buffers could be allocated. */
@@ -236,7 +238,7 @@ lcs_setup_read_ccws(struct lcs_card *card)
 		((struct lcs_header *)
 		 card->read.iob[cnt].data)->offset = LCS_ILLEGAL_OFFSET;
 		card->read.iob[cnt].callback = lcs_get_frames_cb;
-		card->read.iob[cnt].state = BUF_STATE_READY;
+		card->read.iob[cnt].state = LCS_BUF_STATE_READY;
 		card->read.iob[cnt].count = LCS_IOBUFFERSIZE;
 	}
 	card->read.ccws[0].flags &= ~CCW_FLAG_PCI;
@@ -247,7 +249,7 @@ lcs_setup_read_ccws(struct lcs_card *card)
 	card->read.ccws[LCS_NUM_BUFFS].cda =
 		(__u32) __pa(card->read.ccws);
 	/* Setg initial state of the read channel. */
-	card->read.state = CH_STATE_INIT;
+	card->read.state = LCS_CH_STATE_INIT;
 
 	card->read.io_idx = 0;
 	card->read.buf_idx = 0;
@@ -294,7 +296,7 @@ lcs_setup_write_ccws(struct lcs_card *card)
 	card->write.ccws[LCS_NUM_BUFFS].cda =
 		(__u32) __pa(card->write.ccws);
 	/* Set initial state of the write channel. */
-	card->read.state = CH_STATE_INIT;
+	card->read.state = LCS_CH_STATE_INIT;
 
 	card->write.io_idx = 0;
 	card->write.buf_idx = 0;
@@ -496,7 +498,7 @@ lcs_start_channel(struct lcs_channel *channel)
 			      channel->ccws + channel->io_idx, 0, 0,
 			      DOIO_DENY_PREFETCH | DOIO_ALLOW_SUSPEND);
 	if (rc == 0)
-		channel->state = CH_STATE_RUNNING;
+		channel->state = LCS_CH_STATE_RUNNING;
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
 		LCS_DBF_TEXT_(4,trace,"essh%s", channel->ccwdev->dev.bus_id);
@@ -520,8 +522,8 @@ lcs_clear_channel(struct lcs_channel *channel)
 		LCS_DBF_TEXT_(4,trace,"ecsc%s", channel->ccwdev->dev.bus_id);
 		return rc;
 	}
-	wait_event(channel->wait_q, (channel->state == CH_STATE_CLEARED));
-	channel->state = CH_STATE_STOPPED;
+	wait_event(channel->wait_q, (channel->state == LCS_CH_STATE_CLEARED));
+	channel->state = LCS_CH_STATE_STOPPED;
 	return rc;
 }
 
@@ -535,11 +537,11 @@ lcs_stop_channel(struct lcs_channel *channel)
 	unsigned long flags;
 	int rc;
 
-	if (channel->state == CH_STATE_STOPPED)
+	if (channel->state == LCS_CH_STATE_STOPPED)
 		return 0;
 	LCS_DBF_TEXT(4,trace,"haltsch");
 	LCS_DBF_TEXT_(4,trace,"%s", channel->ccwdev->dev.bus_id);
-	channel->state = CH_STATE_INIT;
+	channel->state = LCS_CH_STATE_INIT;
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
 	rc = ccw_device_halt(channel->ccwdev, (addr_t) channel);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
@@ -548,7 +550,7 @@ lcs_stop_channel(struct lcs_channel *channel)
 		return rc;
 	}
 	/* Asynchronous halt initialted. Wait for its completion. */
-	wait_event(channel->wait_q, (channel->state == CH_STATE_HALTED));
+	wait_event(channel->wait_q, (channel->state == LCS_CH_STATE_HALTED));
 	lcs_clear_channel(channel);
 	return 0;
 }
@@ -596,8 +598,8 @@ __lcs_get_buffer(struct lcs_channel *channel)
 	LCS_DBF_TEXT(5, trace, "_getbuff");
 	index = channel->io_idx;
 	do {
-		if (channel->iob[index].state == BUF_STATE_EMPTY) {
-			channel->iob[index].state = BUF_STATE_LOCKED;
+		if (channel->iob[index].state == LCS_BUF_STATE_EMPTY) {
+			channel->iob[index].state = LCS_BUF_STATE_LOCKED;
 			return channel->iob + index;
 		}
 		index = (index + 1) & (LCS_NUM_BUFFS - 1);
@@ -626,7 +628,7 @@ __lcs_resume_channel(struct lcs_channel *channel)
 {
 	int rc;
 
-	if (channel->state != CH_STATE_SUSPENDED)
+	if (channel->state != LCS_CH_STATE_SUSPENDED)
 		return 0;
 	if (channel->ccws[channel->io_idx].flags & CCW_FLAG_SUSPEND)
 		return 0;
@@ -636,7 +638,7 @@ __lcs_resume_channel(struct lcs_channel *channel)
 		LCS_DBF_TEXT_(4, trace, "ersc%s", channel->ccwdev->dev.bus_id);
 		PRINT_ERR("Error in lcs_resume_channel: rc=%d\n",rc);
 	} else
-		channel->state = CH_STATE_RUNNING;
+		channel->state = LCS_CH_STATE_RUNNING;
 	return rc;
 
 }
@@ -670,10 +672,10 @@ lcs_ready_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
 	int index, rc;
 
 	LCS_DBF_TEXT(5, trace, "rdybuff");
-	BUG_ON(buffer->state != BUF_STATE_LOCKED &&
-	       buffer->state != BUF_STATE_PROCESSED);
+	BUG_ON(buffer->state != LCS_BUF_STATE_LOCKED &&
+	       buffer->state != LCS_BUF_STATE_PROCESSED);
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer->state = BUF_STATE_READY;
+	buffer->state = LCS_BUF_STATE_READY;
 	index = buffer - channel->iob;
 	/* Set length. */
 	channel->ccws[index].count = buffer->count;
@@ -695,8 +697,8 @@ __lcs_processed_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
 	int index, prev, next;
 
 	LCS_DBF_TEXT(5, trace, "prcsbuff");
-	BUG_ON(buffer->state != BUF_STATE_READY);
-	buffer->state = BUF_STATE_PROCESSED;
+	BUG_ON(buffer->state != LCS_BUF_STATE_READY);
+	buffer->state = LCS_BUF_STATE_PROCESSED;
 	index = buffer - channel->iob;
 	prev = (index - 1) & (LCS_NUM_BUFFS - 1);
 	next = (index + 1) & (LCS_NUM_BUFFS - 1);
@@ -704,7 +706,7 @@ __lcs_processed_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
 	channel->ccws[index].flags |= CCW_FLAG_SUSPEND;
 	channel->ccws[index].flags &= ~CCW_FLAG_PCI;
 	/* Check the suspend bit of the previous buffer. */
-	if (channel->iob[prev].state == BUF_STATE_READY) {
+	if (channel->iob[prev].state == LCS_BUF_STATE_READY) {
 		/*
 		 * Previous buffer is in state ready. It might have
 		 * happened in lcs_ready_buffer that the suspend bit
@@ -727,10 +729,10 @@ lcs_release_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
 	unsigned long flags;
 
 	LCS_DBF_TEXT(5, trace, "relbuff");
-	BUG_ON(buffer->state != BUF_STATE_LOCKED &&
-	       buffer->state != BUF_STATE_PROCESSED);
+	BUG_ON(buffer->state != LCS_BUF_STATE_LOCKED &&
+	       buffer->state != LCS_BUF_STATE_PROCESSED);
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer->state = BUF_STATE_EMPTY;
+	buffer->state = LCS_BUF_STATE_EMPTY;
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 }
 
@@ -1264,7 +1266,7 @@ lcs_register_mc_addresses(void *data)
 	netif_carrier_off(card->dev);
 	netif_tx_disable(card->dev);
 	wait_event(card->write.wait_q,
-			(card->write.state != CH_STATE_RUNNING));
+			(card->write.state != LCS_CH_STATE_RUNNING));
 	lcs_fix_multicast_list(card);
 	if (card->state == DEV_STATE_UP) {
 		netif_carrier_on(card->dev);
@@ -1404,7 +1406,7 @@ lcs_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
 		}
 	}
 	/* How far in the ccw chain have we processed? */
-	if ((channel->state != CH_STATE_INIT) &&
+	if ((channel->state != LCS_CH_STATE_INIT) &&
 	    (irb->scsw.fctl & SCSW_FCTL_START_FUNC)) {
 		index = (struct ccw1 *) __va((addr_t) irb->scsw.cpa)
 			- channel->ccws;
@@ -1424,20 +1426,20 @@ lcs_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
 	    (irb->scsw.dstat & DEV_STAT_CHN_END) ||
 	    (irb->scsw.dstat & DEV_STAT_UNIT_CHECK))
 		/* Mark channel as stopped. */
-		channel->state = CH_STATE_STOPPED;
+		channel->state = LCS_CH_STATE_STOPPED;
 	else if (irb->scsw.actl & SCSW_ACTL_SUSPENDED)
 		/* CCW execution stopped on a suspend bit. */
-		channel->state = CH_STATE_SUSPENDED;
+		channel->state = LCS_CH_STATE_SUSPENDED;
 	if (irb->scsw.fctl & SCSW_FCTL_HALT_FUNC) {
 		if (irb->scsw.cc != 0) {
 			ccw_device_halt(channel->ccwdev, (addr_t) channel);
 			return;
 		}
 		/* The channel has been stopped by halt_IO. */
-		channel->state = CH_STATE_HALTED;
+		channel->state = LCS_CH_STATE_HALTED;
 	}
 	if (irb->scsw.fctl & SCSW_FCTL_CLEAR_FUNC) {
-		channel->state = CH_STATE_CLEARED;
+		channel->state = LCS_CH_STATE_CLEARED;
 	}
 	/* Do the rest in the tasklet. */
 	tasklet_schedule(&channel->irq_tasklet);
@@ -1461,7 +1463,7 @@ lcs_tasklet(unsigned long data)
 	/* Check for processed buffers. */
 	iob = channel->iob;
 	buf_idx = channel->buf_idx;
-	while (iob[buf_idx].state == BUF_STATE_PROCESSED) {
+	while (iob[buf_idx].state == LCS_BUF_STATE_PROCESSED) {
 		/* Do the callback thing. */
 		if (iob[buf_idx].callback != NULL)
 			iob[buf_idx].callback(channel, iob + buf_idx);
@@ -1469,12 +1471,12 @@ lcs_tasklet(unsigned long data)
 	}
 	channel->buf_idx = buf_idx;
 
-	if (channel->state == CH_STATE_STOPPED)
+	if (channel->state == LCS_CH_STATE_STOPPED)
 		// FIXME: what if rc != 0 ??
 		rc = lcs_start_channel(channel);
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	if (channel->state == CH_STATE_SUSPENDED &&
-	    channel->iob[channel->io_idx].state == BUF_STATE_READY) {
+	if (channel->state == LCS_CH_STATE_SUSPENDED &&
+	    channel->iob[channel->io_idx].state == LCS_BUF_STATE_READY) {
 		// FIXME: what if rc != 0 ??
 		rc = __lcs_resume_channel(channel);
 	}
@@ -1689,8 +1691,8 @@ lcs_detect(struct lcs_card *card)
 		card->state = DEV_STATE_UP;
 	} else {
 		card->state = DEV_STATE_DOWN;
-		card->write.state = CH_STATE_INIT;
-		card->read.state =  CH_STATE_INIT;
+		card->write.state = LCS_CH_STATE_INIT;
+		card->read.state =  LCS_CH_STATE_INIT;
 	}
 	return rc;
 }
@@ -1705,8 +1707,8 @@ lcs_stopcard(struct lcs_card *card)
 
 	LCS_DBF_TEXT(3, setup, "stopcard");
 
-	if (card->read.state != CH_STATE_STOPPED &&
-	    card->write.state != CH_STATE_STOPPED &&
+	if (card->read.state != LCS_CH_STATE_STOPPED &&
+	    card->write.state != LCS_CH_STATE_STOPPED &&
 	    card->state == DEV_STATE_UP) {
 		lcs_clear_multicast_list(card);
 		rc = lcs_send_stoplan(card,LCS_INITIATOR_TCPIP);
@@ -1871,7 +1873,7 @@ lcs_stop_device(struct net_device *dev)
 	netif_tx_disable(dev);
 	dev->flags &= ~IFF_UP;
 	wait_event(card->write.wait_q,
-		(card->write.state != CH_STATE_RUNNING));
+		(card->write.state != LCS_CH_STATE_RUNNING));
 	rc = lcs_stopcard(card);
 	if (rc)
 		PRINT_ERR("Try it again!\n ");
diff --git a/drivers/s390/net/lcs.h b/drivers/s390/net/lcs.h
index b5247dc08b57..0e1e4a0a88f0 100644
--- a/drivers/s390/net/lcs.h
+++ b/drivers/s390/net/lcs.h
@@ -23,11 +23,6 @@ do {                                       \
 } while (0)
 
 /**
- * some more definitions for debug or output stuff
- */
-#define PRINTK_HEADER		" lcs: "
-
-/**
  *	sysfs related stuff
  */
 #define CARD_FROM_DEV(cdev) \
@@ -127,22 +122,22 @@ do {                                       \
  * LCS Buffer states
  */
 enum lcs_buffer_states {
-	BUF_STATE_EMPTY,	/* buffer is empty */
-	BUF_STATE_LOCKED,	/* buffer is locked, don't touch */
-	BUF_STATE_READY,	/* buffer is ready for read/write */
-	BUF_STATE_PROCESSED,
+	LCS_BUF_STATE_EMPTY,	/* buffer is empty */
+	LCS_BUF_STATE_LOCKED,	/* buffer is locked, don't touch */
+	LCS_BUF_STATE_READY,	/* buffer is ready for read/write */
+	LCS_BUF_STATE_PROCESSED,
 };
 
 /**
  * LCS Channel State Machine declarations
  */
 enum lcs_channel_states {
-	CH_STATE_INIT,
-	CH_STATE_HALTED,
-	CH_STATE_STOPPED,
-	CH_STATE_RUNNING,
-	CH_STATE_SUSPENDED,
-	CH_STATE_CLEARED,
+	LCS_CH_STATE_INIT,
+	LCS_CH_STATE_HALTED,
+	LCS_CH_STATE_STOPPED,
+	LCS_CH_STATE_RUNNING,
+	LCS_CH_STATE_SUSPENDED,
+	LCS_CH_STATE_CLEARED,
 };
 
 /**
diff --git a/drivers/s390/net/qeth.h b/drivers/s390/net/qeth.h
index 821383d8cbe7..53c358c7d368 100644
--- a/drivers/s390/net/qeth.h
+++ b/drivers/s390/net/qeth.h
@@ -151,8 +151,6 @@ qeth_hex_dump(unsigned char *buf, size_t len)
 #define SENSE_RESETTING_EVENT_BYTE 1
 #define SENSE_RESETTING_EVENT_FLAG 0x80
 
-#define atomic_swap(a,b) xchg((int *)a.counter, b)
-
 /*
  * Common IO related definitions
  */
diff --git a/drivers/s390/net/qeth_main.c b/drivers/s390/net/qeth_main.c
index 8364d5475ac7..7fdc5272c446 100644
--- a/drivers/s390/net/qeth_main.c
+++ b/drivers/s390/net/qeth_main.c
@@ -2982,7 +2982,7 @@ qeth_check_outbound_queue(struct qeth_qdio_out_q *queue)
 	 */
 	if ((atomic_read(&queue->used_buffers) <= QETH_LOW_WATERMARK_PACK) ||
 	    !atomic_read(&queue->set_pci_flags_count)){
-		if (atomic_swap(&queue->state, QETH_OUT_Q_LOCKED_FLUSH) ==
+		if (atomic_xchg(&queue->state, QETH_OUT_Q_LOCKED_FLUSH) ==
 				QETH_OUT_Q_UNLOCKED) {
 			/*
 			 * If we get in here, there was no action in
@@ -3245,7 +3245,7 @@ qeth_free_qdio_buffers(struct qeth_card *card)
 	int i, j;
 
 	QETH_DBF_TEXT(trace, 2, "freeqdbf");
-	if (atomic_swap(&card->qdio.state, QETH_QDIO_UNINITIALIZED) ==
+	if (atomic_xchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED) ==
 		QETH_QDIO_UNINITIALIZED)
 		return;
 	kfree(card->qdio.in_q);
@@ -4366,7 +4366,7 @@ out:
 	if (flush_count)
 		qeth_flush_buffers(queue, 0, start_index, flush_count);
 	else if (!atomic_read(&queue->set_pci_flags_count))
-		atomic_swap(&queue->state, QETH_OUT_Q_LOCKED_FLUSH);
+		atomic_xchg(&queue->state, QETH_OUT_Q_LOCKED_FLUSH);
 	/*
 	 * queue->state will go from LOCKED -> UNLOCKED or from
 	 * LOCKED_FLUSH -> LOCKED if output_handler wanted to 'notify' us
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index b5b0c2cba96b..5c0b75bbfa10 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -25,6 +25,7 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/jiffies.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/string.h>
diff --git a/drivers/serial/cpm_uart/cpm_uart_cpm2.c b/drivers/serial/cpm_uart/cpm_uart_cpm2.c
index b691d3e14754..787a8f134677 100644
--- a/drivers/serial/cpm_uart/cpm_uart_cpm2.c
+++ b/drivers/serial/cpm_uart/cpm_uart_cpm2.c
@@ -282,7 +282,7 @@ void cpm_uart_freebuf(struct uart_cpm_port *pinfo)
 }
 
 /* Setup any dynamic params in the uart desc */
-int cpm_uart_init_portdesc(void)
+int __init cpm_uart_init_portdesc(void)
 {
 #if defined(CONFIG_SERIAL_CPM_SMC1) || defined(CONFIG_SERIAL_CPM_SMC2)
 	u32 addr;
diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c
index 4f80c5b4a753..6dd579ed9777 100644
--- a/drivers/serial/mpc52xx_uart.c
+++ b/drivers/serial/mpc52xx_uart.c
@@ -1,6 +1,4 @@
 /*
- * drivers/serial/mpc52xx_uart.c
- *
  * Driver for the PSC of the Freescale MPC52xx PSCs configured as UARTs.
  *
  * FIXME According to the usermanual the status bits in the status register
@@ -14,18 +12,20 @@
  *
  *
  * Maintainer : Sylvain Munaut <tnt@246tNt.com>
- * 
+ *
  * Some of the code has been inspired/copied from the 2.4 code written
  * by Dale Farnsworth <dfarnsworth@mvista.com>.
- * 
- * Copyright (C) 2004-2005 Sylvain Munaut <tnt@246tNt.com>
+ *
+ * Copyright (C) 2006 Secret Lab Technologies Ltd.
+ *                    Grant Likely <grant.likely@secretlab.ca>
+ * Copyright (C) 2004-2006 Sylvain Munaut <tnt@246tNt.com>
  * Copyright (C) 2003 MontaVista, Software, Inc.
- * 
+ *
  * This file is licensed under the terms of the GNU General Public License
  * version 2. This program is licensed "as is" without any warranty of any
  * kind, whether express or implied.
  */
- 
+
 /* Platform device Usage :
  *
  * Since PSCs can have multiple function, the correct driver for each one
@@ -44,7 +44,24 @@
  * will be mapped to.
  */
 
-#include <linux/platform_device.h>
+/* OF Platform device Usage :
+ *
+ * This driver is only used for PSCs configured in uart mode.  The device
+ * tree will have a node for each PSC in uart mode w/ device_type = "serial"
+ * and "mpc52xx-psc-uart" in the compatible string
+ *
+ * By default, PSC devices are enumerated in the order they are found.  However
+ * a particular PSC number can be forces by adding 'device_no = <port#>'
+ * to the device node.
+ *
+ * The driver init all necessary registers to place the PSC in uart mode without
+ * DCD. However, the pin multiplexing aren't changed and should be set either
+ * by the bootloader or in the platform init code.
+ */
+
+#undef DEBUG
+
+#include <linux/device.h>
 #include <linux/module.h>
 #include <linux/tty.h>
 #include <linux/serial.h>
@@ -54,6 +71,12 @@
 #include <asm/delay.h>
 #include <asm/io.h>
 
+#if defined(CONFIG_PPC_MERGE)
+#include <asm/of_platform.h>
+#else
+#include <linux/platform_device.h>
+#endif
+
 #include <asm/mpc52xx.h>
 #include <asm/mpc52xx_psc.h>
 
@@ -80,6 +103,12 @@ static struct uart_port mpc52xx_uart_ports[MPC52xx_PSC_MAXNUM];
 	 *        it's cleared, then a memset(...,0,...) should be added to
 	 *        the console_init
 	 */
+#if defined(CONFIG_PPC_MERGE)
+/* lookup table for matching device nodes to index numbers */
+static struct device_node *mpc52xx_uart_nodes[MPC52xx_PSC_MAXNUM];
+
+static void mpc52xx_uart_of_enumerate(void);
+#endif
 
 #define PSC(port) ((struct mpc52xx_psc __iomem *)((port)->membase))
 
@@ -96,32 +125,40 @@ static irqreturn_t mpc52xx_uart_int(int irq,void *dev_id);
 #define uart_console(port)	(0)
 #endif
 
+#if defined(CONFIG_PPC_MERGE)
+static struct of_device_id mpc52xx_uart_of_match[] = {
+	{ .type = "serial", .compatible = "mpc52xx-psc-uart", },
+	{ .type = "serial", .compatible = "mpc5200-psc", }, /* Efika only! */
+	{},
+};
+#endif
+
 
 /* ======================================================================== */
 /* UART operations                                                          */
 /* ======================================================================== */
 
-static unsigned int 
+static unsigned int
 mpc52xx_uart_tx_empty(struct uart_port *port)
 {
 	int status = in_be16(&PSC(port)->mpc52xx_psc_status);
 	return (status & MPC52xx_PSC_SR_TXEMP) ? TIOCSER_TEMT : 0;
 }
 
-static void 
+static void
 mpc52xx_uart_set_mctrl(struct uart_port *port, unsigned int mctrl)
 {
 	/* Not implemented */
 }
 
-static unsigned int 
+static unsigned int
 mpc52xx_uart_get_mctrl(struct uart_port *port)
 {
 	/* Not implemented */
 	return TIOCM_CTS | TIOCM_DSR | TIOCM_CAR;
 }
 
-static void 
+static void
 mpc52xx_uart_stop_tx(struct uart_port *port)
 {
 	/* port->lock taken by caller */
@@ -129,7 +166,7 @@ mpc52xx_uart_stop_tx(struct uart_port *port)
 	out_be16(&PSC(port)->mpc52xx_psc_imr,port->read_status_mask);
 }
 
-static void 
+static void
 mpc52xx_uart_start_tx(struct uart_port *port)
 {
 	/* port->lock taken by caller */
@@ -137,12 +174,12 @@ mpc52xx_uart_start_tx(struct uart_port *port)
 	out_be16(&PSC(port)->mpc52xx_psc_imr,port->read_status_mask);
 }
 
-static void 
+static void
 mpc52xx_uart_send_xchar(struct uart_port *port, char ch)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&port->lock, flags);
-	
+
 	port->x_char = ch;
 	if (ch) {
 		/* Make sure tx interrupts are on */
@@ -150,7 +187,7 @@ mpc52xx_uart_send_xchar(struct uart_port *port, char ch)
 		port->read_status_mask |= MPC52xx_PSC_IMR_TXRDY;
 		out_be16(&PSC(port)->mpc52xx_psc_imr,port->read_status_mask);
 	}
-	
+
 	spin_unlock_irqrestore(&port->lock, flags);
 }
 
@@ -178,7 +215,7 @@ mpc52xx_uart_break_ctl(struct uart_port *port, int ctl)
 		out_8(&PSC(port)->command,MPC52xx_PSC_START_BRK);
 	else
 		out_8(&PSC(port)->command,MPC52xx_PSC_STOP_BRK);
-	
+
 	spin_unlock_irqrestore(&port->lock, flags);
 }
 
@@ -197,11 +234,11 @@ mpc52xx_uart_startup(struct uart_port *port)
 	/* Reset/activate the port, clear and enable interrupts */
 	out_8(&psc->command,MPC52xx_PSC_RST_RX);
 	out_8(&psc->command,MPC52xx_PSC_RST_TX);
-	
+
 	out_be32(&psc->sicr,0);	/* UART mode DCD ignored */
 
 	out_be16(&psc->mpc52xx_psc_clock_select, 0xdd00); /* /16 prescaler on */
-	
+
 	out_8(&psc->rfcntl, 0x00);
 	out_be16(&psc->rfalarm, 0x1ff);
 	out_8(&psc->tfcntl, 0x07);
@@ -209,10 +246,10 @@ mpc52xx_uart_startup(struct uart_port *port)
 
 	port->read_status_mask |= MPC52xx_PSC_IMR_RXRDY | MPC52xx_PSC_IMR_TXRDY;
 	out_be16(&psc->mpc52xx_psc_imr,port->read_status_mask);
-	
+
 	out_8(&psc->command,MPC52xx_PSC_TX_ENABLE);
 	out_8(&psc->command,MPC52xx_PSC_RX_ENABLE);
-		
+
 	return 0;
 }
 
@@ -220,19 +257,19 @@ static void
 mpc52xx_uart_shutdown(struct uart_port *port)
 {
 	struct mpc52xx_psc __iomem *psc = PSC(port);
-	
+
 	/* Shut down the port, interrupt and all */
 	out_8(&psc->command,MPC52xx_PSC_RST_RX);
 	out_8(&psc->command,MPC52xx_PSC_RST_TX);
-	
-	port->read_status_mask = 0; 
+
+	port->read_status_mask = 0;
 	out_be16(&psc->mpc52xx_psc_imr,port->read_status_mask);
 
 	/* Release interrupt */
 	free_irq(port->irq, port);
 }
 
-static void 
+static void
 mpc52xx_uart_set_termios(struct uart_port *port, struct termios *new,
                          struct termios *old)
 {
@@ -241,10 +278,10 @@ mpc52xx_uart_set_termios(struct uart_port *port, struct termios *new,
 	unsigned char mr1, mr2;
 	unsigned short ctr;
 	unsigned int j, baud, quot;
-	
+
 	/* Prepare what we're gonna write */
 	mr1 = 0;
-	
+
 	switch (new->c_cflag & CSIZE) {
 		case CS5:	mr1 |= MPC52xx_PSC_MODE_5_BITS;
 				break;
@@ -261,8 +298,8 @@ mpc52xx_uart_set_termios(struct uart_port *port, struct termios *new,
 			MPC52xx_PSC_MODE_PARODD : MPC52xx_PSC_MODE_PAREVEN;
 	} else
 		mr1 |= MPC52xx_PSC_MODE_PARNONE;
-	
-	
+
+
 	mr2 = 0;
 
 	if (new->c_cflag & CSTOPB)
@@ -276,7 +313,7 @@ mpc52xx_uart_set_termios(struct uart_port *port, struct termios *new,
 	baud = uart_get_baud_rate(port, new, old, 0, port->uartclk/16);
 	quot = uart_get_divisor(port, baud);
 	ctr = quot & 0xffff;
-	
+
 	/* Get the lock */
 	spin_lock_irqsave(&port->lock, flags);
 
@@ -290,14 +327,14 @@ mpc52xx_uart_set_termios(struct uart_port *port, struct termios *new,
 	 * boot for the console, all stuff is not yet ready to receive at that
 	 * time and that just makes the kernel oops */
 	/* while (j-- && mpc52xx_uart_int_rx_chars(port)); */
-	while (!(in_be16(&psc->mpc52xx_psc_status) & MPC52xx_PSC_SR_TXEMP) && 
+	while (!(in_be16(&psc->mpc52xx_psc_status) & MPC52xx_PSC_SR_TXEMP) &&
 	       --j)
 		udelay(1);
 
 	if (!j)
 		printk(	KERN_ERR "mpc52xx_uart.c: "
 			"Unable to flush RX & TX fifos in-time in set_termios."
-			"Some chars may have been lost.\n" ); 
+			"Some chars may have been lost.\n" );
 
 	/* Reset the TX & RX */
 	out_8(&psc->command,MPC52xx_PSC_RST_RX);
@@ -309,7 +346,7 @@ mpc52xx_uart_set_termios(struct uart_port *port, struct termios *new,
 	out_8(&psc->mode,mr2);
 	out_8(&psc->ctur,ctr >> 8);
 	out_8(&psc->ctlr,ctr & 0xff);
-	
+
 	/* Reenable TX & RX */
 	out_8(&psc->command,MPC52xx_PSC_TX_ENABLE);
 	out_8(&psc->command,MPC52xx_PSC_RX_ENABLE);
@@ -332,7 +369,7 @@ mpc52xx_uart_release_port(struct uart_port *port)
 		port->membase = NULL;
 	}
 
-	release_mem_region(port->mapbase, MPC52xx_PSC_SIZE);
+	release_mem_region(port->mapbase, sizeof(struct mpc52xx_psc));
 }
 
 static int
@@ -341,12 +378,13 @@ mpc52xx_uart_request_port(struct uart_port *port)
 	int err;
 
 	if (port->flags & UPF_IOREMAP) /* Need to remap ? */
-		port->membase = ioremap(port->mapbase, MPC52xx_PSC_SIZE);
+		port->membase = ioremap(port->mapbase,
+		                        sizeof(struct mpc52xx_psc));
 
 	if (!port->membase)
 		return -EINVAL;
 
-	err = request_mem_region(port->mapbase, MPC52xx_PSC_SIZE,
+	err = request_mem_region(port->mapbase, sizeof(struct mpc52xx_psc),
 			"mpc52xx_psc_uart") != NULL ? 0 : -EBUSY;
 
 	if (err && (port->flags & UPF_IOREMAP)) {
@@ -373,7 +411,7 @@ mpc52xx_uart_verify_port(struct uart_port *port, struct serial_struct *ser)
 
 	if ( (ser->irq != port->irq) ||
 	     (ser->io_type != SERIAL_IO_MEM) ||
-	     (ser->baud_base != port->uartclk)  || 
+	     (ser->baud_base != port->uartclk)  ||
 	     (ser->iomem_base != (void*)port->mapbase) ||
 	     (ser->hub6 != 0 ) )
 		return -EINVAL;
@@ -404,11 +442,11 @@ static struct uart_ops mpc52xx_uart_ops = {
 	.verify_port	= mpc52xx_uart_verify_port
 };
 
-	
+
 /* ======================================================================== */
 /* Interrupt handling                                                       */
 /* ======================================================================== */
-	
+
 static inline int
 mpc52xx_uart_int_rx_chars(struct uart_port *port)
 {
@@ -435,11 +473,11 @@ mpc52xx_uart_int_rx_chars(struct uart_port *port)
 
 		flag = TTY_NORMAL;
 		port->icount.rx++;
-	
+
 		if ( status & (MPC52xx_PSC_SR_PE |
 		               MPC52xx_PSC_SR_FE |
 		               MPC52xx_PSC_SR_RB) ) {
-			
+
 			if (status & MPC52xx_PSC_SR_RB) {
 				flag = TTY_BREAK;
 				uart_handle_break(port);
@@ -464,7 +502,7 @@ mpc52xx_uart_int_rx_chars(struct uart_port *port)
 	}
 
 	tty_flip_buffer_push(tty);
-	
+
 	return in_be16(&PSC(port)->mpc52xx_psc_status) & MPC52xx_PSC_SR_RXRDY;
 }
 
@@ -509,25 +547,25 @@ mpc52xx_uart_int_tx_chars(struct uart_port *port)
 	return 1;
 }
 
-static irqreturn_t 
+static irqreturn_t
 mpc52xx_uart_int(int irq, void *dev_id)
 {
 	struct uart_port *port = dev_id;
 	unsigned long pass = ISR_PASS_LIMIT;
 	unsigned int keepgoing;
 	unsigned short status;
-	
+
 	spin_lock(&port->lock);
-	
+
 	/* While we have stuff to do, we continue */
 	do {
 		/* If we don't find anything to do, we stop */
-		keepgoing = 0; 
-		
+		keepgoing = 0;
+
 		/* Read status */
 		status = in_be16(&PSC(port)->mpc52xx_psc_isr);
 		status &= port->read_status_mask;
-			
+
 		/* Do we need to receive chars ? */
 		/* For this RX interrupts must be on and some chars waiting */
 		if ( status & MPC52xx_PSC_IMR_RXRDY )
@@ -537,15 +575,15 @@ mpc52xx_uart_int(int irq, void *dev_id)
 		/* For this, TX must be ready and TX interrupt enabled */
 		if ( status & MPC52xx_PSC_IMR_TXRDY )
 			keepgoing |= mpc52xx_uart_int_tx_chars(port);
-		
+
 		/* Limit number of iteration */
 		if ( !(--pass) )
 			keepgoing = 0;
 
 	} while (keepgoing);
-	
+
 	spin_unlock(&port->lock);
-	
+
 	return IRQ_HANDLED;
 }
 
@@ -563,13 +601,18 @@ mpc52xx_console_get_options(struct uart_port *port,
 	struct mpc52xx_psc __iomem *psc = PSC(port);
 	unsigned char mr1;
 
+	pr_debug("mpc52xx_console_get_options(port=%p)\n", port);
+
 	/* Read the mode registers */
 	out_8(&psc->command,MPC52xx_PSC_SEL_MODE_REG_1);
 	mr1 = in_8(&psc->mode);
-	
+
 	/* CT{U,L}R are write-only ! */
-	*baud = __res.bi_baudrate ?
-		__res.bi_baudrate : CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD;
+	*baud = CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD;
+#if !defined(CONFIG_PPC_MERGE)
+	if (__res.bi_baudrate)
+		*baud = __res.bi_baudrate;
+#endif
 
 	/* Parse them */
 	switch (mr1 & MPC52xx_PSC_MODE_BITS_MASK) {
@@ -579,26 +622,26 @@ mpc52xx_console_get_options(struct uart_port *port,
 		case MPC52xx_PSC_MODE_8_BITS:
 		default:			*bits = 8;
 	}
-	
+
 	if (mr1 & MPC52xx_PSC_MODE_PARNONE)
 		*parity = 'n';
 	else
 		*parity = mr1 & MPC52xx_PSC_MODE_PARODD ? 'o' : 'e';
 }
 
-static void  
+static void
 mpc52xx_console_write(struct console *co, const char *s, unsigned int count)
 {
 	struct uart_port *port = &mpc52xx_uart_ports[co->index];
 	struct mpc52xx_psc __iomem *psc = PSC(port);
 	unsigned int i, j;
-	
+
 	/* Disable interrupts */
 	out_be16(&psc->mpc52xx_psc_imr, 0);
 
 	/* Wait the TX buffer to be empty */
-	j = 5000000;	/* Maximum wait */	
-	while (!(in_be16(&psc->mpc52xx_psc_status) & MPC52xx_PSC_SR_TXEMP) && 
+	j = 5000000;	/* Maximum wait */
+	while (!(in_be16(&psc->mpc52xx_psc_status) & MPC52xx_PSC_SR_TXEMP) &&
 	       --j)
 		udelay(1);
 
@@ -607,13 +650,13 @@ mpc52xx_console_write(struct console *co, const char *s, unsigned int count)
 		/* Line return handling */
 		if (*s == '\n')
 			out_8(&psc->mpc52xx_psc_buffer_8, '\r');
-		
+
 		/* Send the char */
 		out_8(&psc->mpc52xx_psc_buffer_8, *s);
 
 		/* Wait the TX buffer to be empty */
-		j = 20000;	/* Maximum wait */	
-		while (!(in_be16(&psc->mpc52xx_psc_status) & 
+		j = 20000;	/* Maximum wait */
+		while (!(in_be16(&psc->mpc52xx_psc_status) &
 		         MPC52xx_PSC_SR_TXEMP) && --j)
 			udelay(1);
 	}
@@ -622,6 +665,7 @@ mpc52xx_console_write(struct console *co, const char *s, unsigned int count)
 	out_be16(&psc->mpc52xx_psc_imr, port->read_status_mask);
 }
 
+#if !defined(CONFIG_PPC_MERGE)
 static int __init
 mpc52xx_console_setup(struct console *co, char *options)
 {
@@ -634,7 +678,7 @@ mpc52xx_console_setup(struct console *co, char *options)
 
 	if (co->index < 0 || co->index >= MPC52xx_PSC_MAXNUM)
 		return -EINVAL;
-	
+
 	/* Basic port init. Needed since we use some uart_??? func before
 	 * real init for early access */
 	spin_lock_init(&port->lock);
@@ -656,6 +700,78 @@ mpc52xx_console_setup(struct console *co, char *options)
 	return uart_set_options(port, co, baud, parity, bits, flow);
 }
 
+#else
+
+static int __init
+mpc52xx_console_setup(struct console *co, char *options)
+{
+	struct uart_port *port = &mpc52xx_uart_ports[co->index];
+	struct device_node *np = mpc52xx_uart_nodes[co->index];
+	unsigned int ipb_freq;
+	struct resource res;
+	int ret;
+
+	int baud = CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD;
+	int bits = 8;
+	int parity = 'n';
+	int flow = 'n';
+
+	pr_debug("mpc52xx_console_setup co=%p, co->index=%i, options=%s\n",
+		 co, co->index, options);
+
+	if ((co->index < 0) || (co->index > MPC52xx_PSC_MAXNUM)) {
+		pr_debug("PSC%x out of range\n", co->index);
+		return -EINVAL;
+	}
+
+	if (!np) {
+		pr_debug("PSC%x not found in device tree\n", co->index);
+		return -EINVAL;
+	}
+
+	pr_debug("Console on ttyPSC%x is %s\n",
+	         co->index, mpc52xx_uart_nodes[co->index]->full_name);
+
+	/* Fetch register locations */
+	if ((ret = of_address_to_resource(np, 0, &res)) != 0) {
+		pr_debug("Could not get resources for PSC%x\n", co->index);
+		return ret;
+	}
+
+	/* Search for bus-frequency property in this node or a parent */
+	if ((ipb_freq = mpc52xx_find_ipb_freq(np)) == 0) {
+		pr_debug("Could not find IPB bus frequency!\n");
+		return -EINVAL;
+	}
+
+	/* Basic port init. Needed since we use some uart_??? func before
+	 * real init for early access */
+	spin_lock_init(&port->lock);
+	port->uartclk	= ipb_freq / 2;
+	port->ops	= &mpc52xx_uart_ops;
+	port->mapbase = res.start;
+	port->membase = ioremap(res.start, sizeof(struct mpc52xx_psc));
+	port->irq = irq_of_parse_and_map(np, 0);
+
+	if (port->membase == NULL)
+		return -EINVAL;
+
+	pr_debug("mpc52xx-psc uart at %lx, mapped to %p, irq=%x, freq=%i\n",
+	         port->mapbase, port->membase, port->irq, port->uartclk);
+
+	/* Setup the port parameters accoding to options */
+	if (options)
+		uart_parse_options(options, &baud, &parity, &bits, &flow);
+	else
+		mpc52xx_console_get_options(port, &baud, &parity, &bits, &flow);
+
+	pr_debug("Setting console parameters: %i %i%c1 flow=%c\n",
+	         baud, bits, parity, flow);
+
+	return uart_set_options(port, co, baud, parity, bits, flow);
+}
+#endif /* defined(CONFIG_PPC_MERGE) */
+
 
 static struct uart_driver mpc52xx_uart_driver;
 
@@ -669,10 +785,11 @@ static struct console mpc52xx_console = {
 	.data	= &mpc52xx_uart_driver,
 };
 
-	
-static int __init 
+
+static int __init
 mpc52xx_console_init(void)
 {
+	mpc52xx_uart_of_enumerate();
 	register_console(&mpc52xx_console);
 	return 0;
 }
@@ -700,6 +817,7 @@ static struct uart_driver mpc52xx_uart_driver = {
 };
 
 
+#if !defined(CONFIG_PPC_MERGE)
 /* ======================================================================== */
 /* Platform Driver                                                          */
 /* ======================================================================== */
@@ -723,8 +841,6 @@ mpc52xx_uart_probe(struct platform_device *dev)
 	/* Init the port structure */
 	port = &mpc52xx_uart_ports[idx];
 
-	memset(port, 0x00, sizeof(struct uart_port));
-
 	spin_lock_init(&port->lock);
 	port->uartclk	= __res.bi_ipbfreq / 2; /* Look at CTLR doc */
 	port->fifosize	= 512;
@@ -733,6 +849,7 @@ mpc52xx_uart_probe(struct platform_device *dev)
 			  ( uart_console(port) ? 0 : UPF_IOREMAP );
 	port->line	= idx;
 	port->ops	= &mpc52xx_uart_ops;
+	port->dev	= &dev->dev;
 
 	/* Search for IRQ and mapbase */
 	for (i=0 ; i<dev->num_resources ; i++, res++) {
@@ -771,7 +888,7 @@ mpc52xx_uart_suspend(struct platform_device *dev, pm_message_t state)
 {
 	struct uart_port *port = (struct uart_port *) platform_get_drvdata(dev);
 
-	if (sport)
+	if (port)
 		uart_suspend_port(&mpc52xx_uart_driver, port);
 
 	return 0;
@@ -789,6 +906,7 @@ mpc52xx_uart_resume(struct platform_device *dev)
 }
 #endif
 
+
 static struct platform_driver mpc52xx_uart_platform_driver = {
 	.probe		= mpc52xx_uart_probe,
 	.remove		= mpc52xx_uart_remove,
@@ -800,6 +918,184 @@ static struct platform_driver mpc52xx_uart_platform_driver = {
 		.name	= "mpc52xx-psc",
 	},
 };
+#endif /* !defined(CONFIG_PPC_MERGE) */
+
+
+#if defined(CONFIG_PPC_MERGE)
+/* ======================================================================== */
+/* OF Platform Driver                                                       */
+/* ======================================================================== */
+
+static int __devinit
+mpc52xx_uart_of_probe(struct of_device *op, const struct of_device_id *match)
+{
+	int idx = -1;
+	unsigned int ipb_freq;
+	struct uart_port *port = NULL;
+	struct resource res;
+	int ret;
+
+	dev_dbg(&op->dev, "mpc52xx_uart_probe(op=%p, match=%p)\n", op, match);
+
+	/* Check validity & presence */
+	for (idx = 0; idx < MPC52xx_PSC_MAXNUM; idx++)
+		if (mpc52xx_uart_nodes[idx] == op->node)
+			break;
+	if (idx >= MPC52xx_PSC_MAXNUM)
+		return -EINVAL;
+	pr_debug("Found %s assigned to ttyPSC%x\n",
+	         mpc52xx_uart_nodes[idx]->full_name, idx);
+
+	/* Search for bus-frequency property in this node or a parent */
+	if ((ipb_freq = mpc52xx_find_ipb_freq(op->node)) == 0) {
+		dev_dbg(&op->dev, "Could not find IPB bus frequency!\n");
+		return -EINVAL;
+	}
+
+	/* Init the port structure */
+	port = &mpc52xx_uart_ports[idx];
+
+	spin_lock_init(&port->lock);
+	port->uartclk	= ipb_freq / 2;
+	port->fifosize	= 512;
+	port->iotype	= UPIO_MEM;
+	port->flags	= UPF_BOOT_AUTOCONF |
+			  ( uart_console(port) ? 0 : UPF_IOREMAP );
+	port->line	= idx;
+	port->ops	= &mpc52xx_uart_ops;
+	port->dev	= &op->dev;
+
+	/* Search for IRQ and mapbase */
+	if ((ret = of_address_to_resource(op->node, 0, &res)) != 0)
+		return ret;
+
+	port->mapbase = res.start;
+	port->irq = irq_of_parse_and_map(op->node, 0);
+
+	dev_dbg(&op->dev, "mpc52xx-psc uart at %lx, irq=%x, freq=%i\n",
+	        port->mapbase, port->irq, port->uartclk);
+
+	if ((port->irq==NO_IRQ) || !port->mapbase) {
+		printk(KERN_ERR "Could not allocate resources for PSC\n");
+		return -EINVAL;
+	}
+
+	/* Add the port to the uart sub-system */
+	ret = uart_add_one_port(&mpc52xx_uart_driver, port);
+	if (!ret)
+		dev_set_drvdata(&op->dev, (void*)port);
+
+	return ret;
+}
+
+static int
+mpc52xx_uart_of_remove(struct of_device *op)
+{
+	struct uart_port *port = dev_get_drvdata(&op->dev);
+	dev_set_drvdata(&op->dev, NULL);
+
+	if (port)
+		uart_remove_one_port(&mpc52xx_uart_driver, port);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int
+mpc52xx_uart_of_suspend(struct of_device *op, pm_message_t state)
+{
+	struct uart_port *port = (struct uart_port *) dev_get_drvdata(&op->dev);
+
+	if (port)
+		uart_suspend_port(&mpc52xx_uart_driver, port);
+
+	return 0;
+}
+
+static int
+mpc52xx_uart_of_resume(struct of_device *op)
+{
+	struct uart_port *port = (struct uart_port *) dev_get_drvdata(&op->dev);
+
+	if (port)
+		uart_resume_port(&mpc52xx_uart_driver, port);
+
+	return 0;
+}
+#endif
+
+static void
+mpc52xx_uart_of_assign(struct device_node *np, int idx)
+{
+	int free_idx = -1;
+	int i;
+
+	/* Find the first free node */
+	for (i = 0; i < MPC52xx_PSC_MAXNUM; i++) {
+		if (mpc52xx_uart_nodes[i] == NULL) {
+			free_idx = i;
+			break;
+		}
+	}
+
+	if ((idx < 0) || (idx >= MPC52xx_PSC_MAXNUM))
+		idx = free_idx;
+
+	if (idx < 0)
+		return; /* No free slot; abort */
+
+	/* If the slot is already occupied, then swap slots */
+	if (mpc52xx_uart_nodes[idx] && (free_idx != -1))
+		mpc52xx_uart_nodes[free_idx] = mpc52xx_uart_nodes[idx];
+	mpc52xx_uart_nodes[i] = np;
+}
+
+static void
+mpc52xx_uart_of_enumerate(void)
+{
+	static int enum_done = 0;
+	struct device_node *np;
+	const unsigned int *devno;
+	int i;
+
+	if (enum_done)
+		return;
+
+	for_each_node_by_type(np, "serial") {
+		if (!of_match_node(mpc52xx_uart_of_match, np))
+			continue;
+
+		/* Is a particular device number requested? */
+		devno = get_property(np, "device_no", NULL);
+		mpc52xx_uart_of_assign(of_node_get(np), devno ? *devno : -1);
+	}
+
+	enum_done = 1;
+
+	for (i = 0; i < MPC52xx_PSC_MAXNUM; i++) {
+		if (mpc52xx_uart_nodes[i])
+			pr_debug("%s assigned to ttyPSC%x\n",
+			         mpc52xx_uart_nodes[i]->full_name, i);
+	}
+}
+
+MODULE_DEVICE_TABLE(of, mpc52xx_uart_of_match);
+
+static struct of_platform_driver mpc52xx_uart_of_driver = {
+	.owner		= THIS_MODULE,
+	.name		= "mpc52xx-psc-uart",
+	.match_table	= mpc52xx_uart_of_match,
+	.probe		= mpc52xx_uart_of_probe,
+	.remove		= mpc52xx_uart_of_remove,
+#ifdef CONFIG_PM
+	.suspend	= mpc52xx_uart_of_suspend,
+	.resume		= mpc52xx_uart_of_resume,
+#endif
+	.driver		= {
+		.name	= "mpc52xx-psc-uart",
+	},
+};
+#endif /* defined(CONFIG_PPC_MERGE) */
 
 
 /* ======================================================================== */
@@ -811,22 +1107,45 @@ mpc52xx_uart_init(void)
 {
 	int ret;
 
-	printk(KERN_INFO "Serial: MPC52xx PSC driver\n");
+	printk(KERN_INFO "Serial: MPC52xx PSC UART driver\n");
 
-	ret = uart_register_driver(&mpc52xx_uart_driver);
-	if (ret == 0) {
-		ret = platform_driver_register(&mpc52xx_uart_platform_driver);
-		if (ret)
-			uart_unregister_driver(&mpc52xx_uart_driver);
+	if ((ret = uart_register_driver(&mpc52xx_uart_driver)) != 0) {
+		printk(KERN_ERR "%s: uart_register_driver failed (%i)\n",
+		       __FILE__, ret);
+		return ret;
 	}
 
-	return ret;
+#if defined(CONFIG_PPC_MERGE)
+	mpc52xx_uart_of_enumerate();
+
+	ret = of_register_platform_driver(&mpc52xx_uart_of_driver);
+	if (ret) {
+		printk(KERN_ERR "%s: of_register_platform_driver failed (%i)\n",
+		       __FILE__, ret);
+		uart_unregister_driver(&mpc52xx_uart_driver);
+		return ret;
+	}
+#else
+	ret = platform_driver_register(&mpc52xx_uart_platform_driver);
+	if (ret) {
+		printk(KERN_ERR "%s: platform_driver_register failed (%i)\n",
+		       __FILE__, ret);
+		uart_unregister_driver(&mpc52xx_uart_driver);
+		return ret;
+	}
+#endif
+
+	return 0;
 }
 
 static void __exit
 mpc52xx_uart_exit(void)
 {
+#if defined(CONFIG_PPC_MERGE)
+	of_unregister_platform_driver(&mpc52xx_uart_of_driver);
+#else
 	platform_driver_unregister(&mpc52xx_uart_platform_driver);
+#endif
 	uart_unregister_driver(&mpc52xx_uart_driver);
 }
 
diff --git a/drivers/spi/spi_butterfly.c b/drivers/spi/spi_butterfly.c
index 39d9b20f2038..c2f601f8e4f2 100644
--- a/drivers/spi/spi_butterfly.c
+++ b/drivers/spi/spi_butterfly.c
@@ -23,6 +23,7 @@
 #include <linux/platform_device.h>
 #include <linux/parport.h>
 
+#include <linux/sched.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/spi/flash.h>
diff --git a/drivers/video/platinumfb.c b/drivers/video/platinumfb.c
index fdb33cd21a27..cb26c6df0583 100644
--- a/drivers/video/platinumfb.c
+++ b/drivers/video/platinumfb.c
@@ -34,6 +34,7 @@
 #include <asm/prom.h>
 #include <asm/pgtable.h>
 #include <asm/of_device.h>
+#include <asm/of_platform.h>
 
 #include "macmodes.h"
 #include "platinumfb.h"
@@ -682,14 +683,14 @@ static int __init platinumfb_init(void)
 		return -ENODEV;
 	platinumfb_setup(option);
 #endif
-	of_register_driver(&platinum_driver);
+	of_register_platform_driver(&platinum_driver);
 
 	return 0;
 }
 
 static void __exit platinumfb_exit(void)
 {
-	of_unregister_driver(&platinum_driver);	
+	of_unregister_platform_driver(&platinum_driver);
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c
index 5372cfcbd054..b022fffd8c51 100644
--- a/drivers/w1/slaves/w1_therm.c
+++ b/drivers/w1/slaves/w1_therm.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/sched.h>
 #include <linux/device.h>
 #include <linux/types.h>
 #include <linux/delay.h>
diff --git a/fs/9p/conv.c b/fs/9p/conv.c
index 56d88c1a09c5..a3ed571eee31 100644
--- a/fs/9p/conv.c
+++ b/fs/9p/conv.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/idr.h>
 #include <asm/uaccess.h>
 #include "debug.h"
diff --git a/fs/9p/fcall.c b/fs/9p/fcall.c
index 8556097fcda8..dc336a67592f 100644
--- a/fs/9p/fcall.c
+++ b/fs/9p/fcall.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/idr.h>
 
 #include "debug.h"
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 70492ccb4385..27507201f9e7 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -23,6 +23,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/idr.h>
 
 #include "debug.h"
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 0f628041e3f7..0b96fae8b479 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/parser.h>
 #include <linux/idr.h>
 
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index e32d5971039b..905c882f4e2f 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -30,6 +30,7 @@
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <linux/smp_lock.h>
+#include <linux/sched.h>
 #include <linux/inet.h>
 #include <linux/idr.h>
 
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index c3c47eda7574..79e6f9cd7340 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/file.h>
 #include <linux/stat.h>
 #include <linux/string.h>
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 79b05a1a4365..cc72bb43061d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1582,6 +1582,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 		
 		sz += thread_status_size;
 
+#ifdef ELF_CORE_WRITE_EXTRA_NOTES
+		sz += ELF_CORE_EXTRA_NOTES_SIZE;
+#endif
+
 		fill_elf_note_phdr(&phdr, sz, offset);
 		offset += sz;
 		DUMP_WRITE(&phdr, sizeof(phdr));
@@ -1622,6 +1626,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file)
 		if (!writenote(notes + i, file, &foffset))
 			goto end_coredump;
 
+#ifdef ELF_CORE_WRITE_EXTRA_NOTES
+	ELF_CORE_WRITE_EXTRA_NOTES;
+#endif
+
 	/* write out the thread status notes section */
 	list_for_each(t, &thread_list) {
 		struct elf_thread_status *tmp =
diff --git a/fs/compat.c b/fs/compat.c
index 8d0a0018a7d2..06dad665b88f 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -45,6 +45,8 @@
 #include <linux/personality.h>
 #include <linux/rwsem.h>
 #include <linux/tsacct_kern.h>
+#include <linux/highmem.h>
+#include <linux/poll.h>
 #include <linux/mm.h>
 
 #include <net/sock.h>		/* siocdevprivate_ioctl */
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 8a3b6a1a6ad1..c398861f78a5 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -93,8 +93,8 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * pare
  *
  * called with parent inode's i_mutex held
  */
-int configfs_dirent_exists(struct configfs_dirent *parent_sd,
-			   const unsigned char *new)
+static int configfs_dirent_exists(struct configfs_dirent *parent_sd,
+				  const unsigned char *new)
 {
 	struct configfs_dirent * sd;
 
@@ -1176,8 +1176,9 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
 		return;
 	}
 
-	mutex_lock(&configfs_sb->s_root->d_inode->i_mutex);
-	mutex_lock(&dentry->d_inode->i_mutex);
+	mutex_lock_nested(&configfs_sb->s_root->d_inode->i_mutex,
+			  I_MUTEX_PARENT);
+	mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
 	if (configfs_detach_prep(dentry)) {
 		printk(KERN_ERR "configfs: Tried to unregister non-empty subsystem!\n");
 	}
diff --git a/fs/gfs2/locking/dlm/plock.c b/fs/gfs2/locking/dlm/plock.c
index 7365aec9511b..3799f19b282f 100644
--- a/fs/gfs2/locking/dlm/plock.c
+++ b/fs/gfs2/locking/dlm/plock.c
@@ -8,6 +8,7 @@
 
 #include <linux/miscdevice.h>
 #include <linux/lock_dlm_plock.h>
+#include <linux/poll.h>
 
 #include "lock_dlm.h"
 
diff --git a/fs/inotify.c b/fs/inotify.c
index 723836a1f718..f5099d86fd91 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -27,6 +27,7 @@
 #include <linux/idr.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/writeback.h>
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 0ae3cd10702c..73f0d60f73a5 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
 #include <linux/time.h>
 #include <linux/crc32.h>
 #include <linux/jffs2.h>
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index b9b700730dfe..70707309dfa1 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -19,6 +19,7 @@
 #include <linux/crc32.h>
 #include <linux/mtd/nand.h>
 #include <linux/jiffies.h>
+#include <linux/sched.h>
 
 #include "nodelist.h"
 
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 37db52488262..ed814b1ff4d9 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -9,6 +9,7 @@
 #include <linux/ctype.h>
 #include <linux/capability.h>
 #include <linux/time.h>
+#include <linux/sched.h>
 #include <asm/current.h>
 #include <asm/uaccess.h>
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 0b2ad163005e..edc91ca3792a 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -52,14 +52,14 @@ static int ocfs2_extent_contig(struct inode *inode,
 			       u64 blkno);
 
 static int ocfs2_create_new_meta_bhs(struct ocfs2_super *osb,
-				     struct ocfs2_journal_handle *handle,
+				     handle_t *handle,
 				     struct inode *inode,
 				     int wanted,
 				     struct ocfs2_alloc_context *meta_ac,
 				     struct buffer_head *bhs[]);
 
 static int ocfs2_add_branch(struct ocfs2_super *osb,
-			    struct ocfs2_journal_handle *handle,
+			    handle_t *handle,
 			    struct inode *inode,
 			    struct buffer_head *fe_bh,
 			    struct buffer_head *eb_bh,
@@ -67,14 +67,14 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
 			    struct ocfs2_alloc_context *meta_ac);
 
 static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
-				  struct ocfs2_journal_handle *handle,
+				  handle_t *handle,
 				  struct inode *inode,
 				  struct buffer_head *fe_bh,
 				  struct ocfs2_alloc_context *meta_ac,
 				  struct buffer_head **ret_new_eb_bh);
 
 static int ocfs2_do_insert_extent(struct ocfs2_super *osb,
-				  struct ocfs2_journal_handle *handle,
+				  handle_t *handle,
 				  struct inode *inode,
 				  struct buffer_head *fe_bh,
 				  u64 blkno,
@@ -152,7 +152,7 @@ bail:
  * l_count for you
  */
 static int ocfs2_create_new_meta_bhs(struct ocfs2_super *osb,
-				     struct ocfs2_journal_handle *handle,
+				     handle_t *handle,
 				     struct inode *inode,
 				     int wanted,
 				     struct ocfs2_alloc_context *meta_ac,
@@ -253,7 +253,7 @@ bail:
  * contain a single record with e_clusters == 0.
  */
 static int ocfs2_add_branch(struct ocfs2_super *osb,
-			    struct ocfs2_journal_handle *handle,
+			    handle_t *handle,
 			    struct inode *inode,
 			    struct buffer_head *fe_bh,
 			    struct buffer_head *eb_bh,
@@ -418,7 +418,7 @@ bail:
  * after this call.
  */
 static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
-				  struct ocfs2_journal_handle *handle,
+				  handle_t *handle,
 				  struct inode *inode,
 				  struct buffer_head *fe_bh,
 				  struct ocfs2_alloc_context *meta_ac,
@@ -520,7 +520,7 @@ bail:
  * down.
  */
 static int ocfs2_do_insert_extent(struct ocfs2_super *osb,
-				  struct ocfs2_journal_handle *handle,
+				  handle_t *handle,
 				  struct inode *inode,
 				  struct buffer_head *fe_bh,
 				  u64 start_blk,
@@ -809,7 +809,7 @@ bail:
 
 /* the caller needs to update fe->i_clusters */
 int ocfs2_insert_extent(struct ocfs2_super *osb,
-			struct ocfs2_journal_handle *handle,
+			handle_t *handle,
 			struct inode *inode,
 			struct buffer_head *fe_bh,
 			u64 start_blk,
@@ -951,7 +951,7 @@ static int ocfs2_truncate_log_can_coalesce(struct ocfs2_truncate_log *tl,
 }
 
 static int ocfs2_truncate_log_append(struct ocfs2_super *osb,
-				     struct ocfs2_journal_handle *handle,
+				     handle_t *handle,
 				     u64 start_blk,
 				     unsigned int num_clusters)
 {
@@ -1034,7 +1034,7 @@ bail:
 }
 
 static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
-					 struct ocfs2_journal_handle *handle,
+					 handle_t *handle,
 					 struct inode *data_alloc_inode,
 					 struct buffer_head *data_alloc_bh)
 {
@@ -1113,7 +1113,7 @@ static int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 {
 	int status;
 	unsigned int num_to_flush;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle;
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct inode *data_alloc_inode = NULL;
 	struct buffer_head *tl_bh = osb->osb_tl_bh;
@@ -1130,7 +1130,7 @@ static int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 	if (!OCFS2_IS_VALID_DINODE(di)) {
 		OCFS2_RO_ON_INVALID_DINODE(osb->sb, di);
 		status = -EIO;
-		goto bail;
+		goto out;
 	}
 
 	num_to_flush = le16_to_cpu(tl->tl_used);
@@ -1138,14 +1138,7 @@ static int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 	     num_to_flush, (unsigned long long)OCFS2_I(tl_inode)->ip_blkno);
 	if (!num_to_flush) {
 		status = 0;
-		goto bail;
-	}
-
-	handle = ocfs2_alloc_handle(osb);
-	if (!handle) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
+		goto out;
 	}
 
 	data_alloc_inode = ocfs2_get_system_file_inode(osb,
@@ -1154,41 +1147,40 @@ static int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 	if (!data_alloc_inode) {
 		status = -EINVAL;
 		mlog(ML_ERROR, "Could not get bitmap inode!\n");
-		goto bail;
+		goto out;
 	}
 
-	ocfs2_handle_add_inode(handle, data_alloc_inode);
-	status = ocfs2_meta_lock(data_alloc_inode, handle, &data_alloc_bh, 1);
+	mutex_lock(&data_alloc_inode->i_mutex);
+
+	status = ocfs2_meta_lock(data_alloc_inode, &data_alloc_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
-		goto bail;
+		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_TRUNCATE_LOG_UPDATE);
+	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
-		handle = NULL;
 		mlog_errno(status);
-		goto bail;
+		goto out_unlock;
 	}
 
 	status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode,
 					       data_alloc_bh);
-	if (status < 0) {
+	if (status < 0)
 		mlog_errno(status);
-		goto bail;
-	}
 
-bail:
-	if (handle)
-		ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 
-	if (data_alloc_inode)
-		iput(data_alloc_inode);
+out_unlock:
+	brelse(data_alloc_bh);
+	ocfs2_meta_unlock(data_alloc_inode, 1);
 
-	if (data_alloc_bh)
-		brelse(data_alloc_bh);
+out_mutex:
+	mutex_unlock(&data_alloc_inode->i_mutex);
+	iput(data_alloc_inode);
 
+out:
 	mlog_exit(status);
 	return status;
 }
@@ -1349,7 +1341,7 @@ int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
 	int i;
 	unsigned int clusters, num_recs, start_cluster;
 	u64 start_blk;
-	struct ocfs2_journal_handle *handle;
+	handle_t *handle;
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct ocfs2_truncate_log *tl;
 
@@ -1375,8 +1367,7 @@ int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
 			}
 		}
 
-		handle = ocfs2_start_trans(osb, NULL,
-					   OCFS2_TRUNCATE_LOG_UPDATE);
+		handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
@@ -1389,7 +1380,7 @@ int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
 
 		status = ocfs2_truncate_log_append(osb, handle,
 						   start_blk, clusters);
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail_up;
@@ -1546,7 +1537,7 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb,
 			     struct inode *inode,
 			     struct buffer_head *fe_bh,
 			     struct buffer_head *old_last_eb_bh,
-			     struct ocfs2_journal_handle *handle,
+			     handle_t *handle,
 			     struct ocfs2_truncate_context *tc)
 {
 	int status, i, depth;
@@ -1785,7 +1776,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 	struct ocfs2_extent_block *eb;
 	struct ocfs2_extent_list *el;
 	struct buffer_head *last_eb_bh;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct inode *tl_inode = osb->osb_tl_inode;
 
 	mlog_entry_void();
@@ -1871,7 +1862,7 @@ start:
 
 	credits = ocfs2_calc_tree_trunc_credits(osb->sb, clusters_to_del,
 						fe, el);
-	handle = ocfs2_start_trans(osb, NULL, credits);
+	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -1894,7 +1885,7 @@ start:
 	mutex_unlock(&tl_inode->i_mutex);
 	tl_sem = 0;
 
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 	handle = NULL;
 
 	BUG_ON(le32_to_cpu(fe->i_clusters) < target_i_clusters);
@@ -1909,7 +1900,7 @@ bail:
 		mutex_unlock(&tl_inode->i_mutex);
 
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 
 	if (last_eb_bh)
 		brelse(last_eb_bh);
@@ -2014,10 +2005,7 @@ int ocfs2_prepare_truncate(struct ocfs2_super *osb,
 		mutex_lock(&ext_alloc_inode->i_mutex);
 		(*tc)->tc_ext_alloc_inode = ext_alloc_inode;
 
-		status = ocfs2_meta_lock(ext_alloc_inode,
-					 NULL,
-					 &ext_alloc_bh,
-					 1);
+		status = ocfs2_meta_lock(ext_alloc_inode, &ext_alloc_bh, 1);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail;
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index 12ba897743f4..0b82e8044325 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -28,7 +28,7 @@
 
 struct ocfs2_alloc_context;
 int ocfs2_insert_extent(struct ocfs2_super *osb,
-			struct ocfs2_journal_handle *handle,
+			handle_t *handle,
 			struct inode *inode,
 			struct buffer_head *fe_bh,
 			u64 blkno,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3d7c082a8f58..2f7268e81520 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -200,7 +200,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 
 	mlog_entry("(0x%p, %lu)\n", file, (page ? page->index : 0));
 
-	ret = ocfs2_meta_lock_with_page(inode, NULL, NULL, 0, page);
+	ret = ocfs2_meta_lock_with_page(inode, NULL, 0, page);
 	if (ret != 0) {
 		if (ret == AOP_TRUNCATED_PAGE)
 			unlock = 0;
@@ -305,7 +305,7 @@ static int ocfs2_prepare_write(struct file *file, struct page *page,
 
 	mlog_entry("(0x%p, 0x%p, %u, %u)\n", file, page, from, to);
 
-	ret = ocfs2_meta_lock_with_page(inode, NULL, NULL, 0, page);
+	ret = ocfs2_meta_lock_with_page(inode, NULL, 0, page);
 	if (ret != 0) {
 		mlog_errno(ret);
 		goto out;
@@ -355,16 +355,16 @@ static int walk_page_buffers(	handle_t *handle,
 	return ret;
 }
 
-struct ocfs2_journal_handle *ocfs2_start_walk_page_trans(struct inode *inode,
+handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 struct page *page,
 							 unsigned from,
 							 unsigned to)
 {
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	int ret = 0;
 
-	handle = ocfs2_start_trans(osb, NULL, OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (!handle) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
@@ -372,7 +372,7 @@ struct ocfs2_journal_handle *ocfs2_start_walk_page_trans(struct inode *inode,
 	}
 
 	if (ocfs2_should_order_data(inode)) {
-		ret = walk_page_buffers(handle->k_handle,
+		ret = walk_page_buffers(handle,
 					page_buffers(page),
 					from, to, NULL,
 					ocfs2_journal_dirty_data);
@@ -382,7 +382,7 @@ struct ocfs2_journal_handle *ocfs2_start_walk_page_trans(struct inode *inode,
 out:
 	if (ret) {
 		if (handle)
-			ocfs2_commit_trans(handle);
+			ocfs2_commit_trans(osb, handle);
 		handle = ERR_PTR(ret);
 	}
 	return handle;
@@ -394,7 +394,7 @@ static int ocfs2_commit_write(struct file *file, struct page *page,
 	int ret;
 	struct buffer_head *di_bh = NULL;
 	struct inode *inode = page->mapping->host;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_dinode *di;
 
 	mlog_entry("(0x%p, 0x%p, %u, %u)\n", file, page, from, to);
@@ -412,7 +412,7 @@ static int ocfs2_commit_write(struct file *file, struct page *page,
 	 *    stale inode allocation image (i_size, i_clusters, etc).
 	 */
 
-	ret = ocfs2_meta_lock_with_page(inode, NULL, &di_bh, 1, page);
+	ret = ocfs2_meta_lock_with_page(inode, &di_bh, 1, page);
 	if (ret != 0) {
 		mlog_errno(ret);
 		goto out;
@@ -464,7 +464,7 @@ static int ocfs2_commit_write(struct file *file, struct page *page,
 	}
 
 out_commit:
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
 out_unlock_data:
 	ocfs2_data_unlock(inode, 1);
 out_unlock_meta:
@@ -490,7 +490,7 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 	 * accessed concurrently from multiple nodes.
 	 */
 	if (!INODE_JOURNAL(inode)) {
-		err = ocfs2_meta_lock(inode, NULL, NULL, 0);
+		err = ocfs2_meta_lock(inode, NULL, 0);
 		if (err) {
 			if (err != -ENOENT)
 				mlog_errno(err);
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index e88c3f0b8fa9..f446a15eab88 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -25,7 +25,7 @@
 int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page,
 			       unsigned from, unsigned to);
 
-struct ocfs2_journal_handle *ocfs2_start_walk_page_trans(struct inode *inode,
+handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 struct page *page,
 							 unsigned from,
 							 unsigned to);
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 04e01915b86e..baad2aa27c14 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -82,6 +82,7 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct super_block * sb = inode->i_sb;
 	unsigned int ra_sectors = 16;
+	int lock_level = 0;
 
 	mlog_entry("dirino=%llu\n",
 		   (unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -89,7 +90,15 @@ int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	stored = 0;
 	bh = NULL;
 
-	error = ocfs2_meta_lock(inode, NULL, NULL, 0);
+	error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
+	if (lock_level && error >= 0) {
+		/* We release EX lock which used to update atime
+		 * and get PR lock again to reduce contention
+		 * on commonly accessed directories. */
+		ocfs2_meta_unlock(inode, 1);
+		lock_level = 0;
+		error = ocfs2_meta_lock(inode, NULL, 0);
+	}
 	if (error < 0) {
 		if (error != -ENOENT)
 			mlog_errno(error);
@@ -198,7 +207,7 @@ revalidate:
 
 	stored = 0;
 bail:
-	ocfs2_meta_unlock(inode, 0);
+	ocfs2_meta_unlock(inode, lock_level);
 
 bail_nolock:
 	mlog_exit(stored);
@@ -340,7 +349,7 @@ int ocfs2_empty_dir(struct inode *inode)
 
 /* returns a bh of the 1st new block in the allocation. */
 int ocfs2_do_extend_dir(struct super_block *sb,
-			struct ocfs2_journal_handle *handle,
+			handle_t *handle,
 			struct inode *dir,
 			struct buffer_head *parent_fe_bh,
 			struct ocfs2_alloc_context *data_ac,
@@ -398,7 +407,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
 	struct ocfs2_alloc_context *data_ac = NULL;
 	struct ocfs2_alloc_context *meta_ac = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct buffer_head *new_bh = NULL;
 	struct ocfs2_dir_entry * de;
 	struct super_block *sb = osb->sb;
@@ -409,13 +418,6 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 	mlog(0, "extending dir %llu (i_size = %lld)\n",
 	     (unsigned long long)OCFS2_I(dir)->ip_blkno, dir_i_size);
 
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	/* dir->i_size is always block aligned. */
 	spin_lock(&OCFS2_I(dir)->ip_lock);
 	if (dir_i_size == ocfs2_clusters_to_bytes(sb, OCFS2_I(dir)->ip_clusters)) {
@@ -428,8 +430,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 		}
 
 		if (!num_free_extents) {
-			status = ocfs2_reserve_new_metadata(osb, handle,
-							    fe, &meta_ac);
+			status = ocfs2_reserve_new_metadata(osb, fe, &meta_ac);
 			if (status < 0) {
 				if (status != -ENOSPC)
 					mlog_errno(status);
@@ -437,7 +438,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 			}
 		}
 
-		status = ocfs2_reserve_clusters(osb, handle, 1, &data_ac);
+		status = ocfs2_reserve_clusters(osb, 1, &data_ac);
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
@@ -450,7 +451,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 		credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS;
 	}
 
-	handle = ocfs2_start_trans(osb, handle, credits);
+	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -496,7 +497,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 	get_bh(*new_de_bh);
 bail:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 
 	if (data_ac)
 		ocfs2_free_alloc_context(data_ac);
diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h
index 5f614ec9649c..3f67e146864a 100644
--- a/fs/ocfs2/dir.h
+++ b/fs/ocfs2/dir.h
@@ -45,7 +45,7 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 				 struct buffer_head **ret_de_bh);
 struct ocfs2_alloc_context;
 int ocfs2_do_extend_dir(struct super_block *sb,
-			struct ocfs2_journal_handle *handle,
+			handle_t *handle,
 			struct inode *dir,
 			struct buffer_head *parent_fe_bh,
 			struct ocfs2_alloc_context *data_ac,
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 637646e6922e..420a375a3949 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -68,7 +68,8 @@ static void **dlm_alloc_pagevec(int pages)
 			goto out_free;
 
 	mlog(0, "Allocated DLM hash pagevec; %d pages (%lu expected), %lu buckets per page\n",
-	     pages, DLM_HASH_PAGES, (unsigned long)DLM_BUCKETS_PER_PAGE);
+	     pages, (unsigned long)DLM_HASH_PAGES,
+	     (unsigned long)DLM_BUCKETS_PER_PAGE);
 	return vec;
 out_free:
 	dlm_free_pagevec(vec, i);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8801e41afe80..69fba16efbd1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -49,6 +49,7 @@
 #include "dcache.h"
 #include "dlmglue.h"
 #include "extent_map.h"
+#include "file.h"
 #include "heartbeat.h"
 #include "inode.h"
 #include "journal.h"
@@ -1063,10 +1064,10 @@ static void ocfs2_cluster_unlock(struct ocfs2_super *osb,
 	mlog_exit_void();
 }
 
-int ocfs2_create_new_lock(struct ocfs2_super *osb,
-			  struct ocfs2_lock_res *lockres,
-			  int ex,
-			  int local)
+static int ocfs2_create_new_lock(struct ocfs2_super *osb,
+				 struct ocfs2_lock_res *lockres,
+				 int ex,
+				 int local)
 {
 	int level =  ex ? LKM_EXMODE : LKM_PRMODE;
 	unsigned long flags;
@@ -1579,7 +1580,6 @@ static int ocfs2_assign_bh(struct inode *inode,
  * the result of the lock will be communicated via the callback.
  */
 int ocfs2_meta_lock_full(struct inode *inode,
-			 struct ocfs2_journal_handle *handle,
 			 struct buffer_head **ret_bh,
 			 int ex,
 			 int arg_flags)
@@ -1668,12 +1668,6 @@ int ocfs2_meta_lock_full(struct inode *inode,
 		}
 	}
 
-	if (handle) {
-		status = ocfs2_handle_add_lock(handle, inode);
-		if (status < 0)
-			mlog_errno(status);
-	}
-
 bail:
 	if (status < 0) {
 		if (ret_bh && (*ret_bh)) {
@@ -1713,18 +1707,16 @@ bail:
  * the lock inversion simply.
  */
 int ocfs2_meta_lock_with_page(struct inode *inode,
-			      struct ocfs2_journal_handle *handle,
 			      struct buffer_head **ret_bh,
 			      int ex,
 			      struct page *page)
 {
 	int ret;
 
-	ret = ocfs2_meta_lock_full(inode, handle, ret_bh, ex,
-				   OCFS2_LOCK_NONBLOCK);
+	ret = ocfs2_meta_lock_full(inode, ret_bh, ex, OCFS2_LOCK_NONBLOCK);
 	if (ret == -EAGAIN) {
 		unlock_page(page);
-		if (ocfs2_meta_lock(inode, handle, ret_bh, ex) == 0)
+		if (ocfs2_meta_lock(inode, ret_bh, ex) == 0)
 			ocfs2_meta_unlock(inode, ex);
 		ret = AOP_TRUNCATED_PAGE;
 	}
@@ -1732,6 +1724,44 @@ int ocfs2_meta_lock_with_page(struct inode *inode,
 	return ret;
 }
 
+int ocfs2_meta_lock_atime(struct inode *inode,
+			  struct vfsmount *vfsmnt,
+			  int *level)
+{
+	int ret;
+
+	mlog_entry_void();
+	ret = ocfs2_meta_lock(inode, NULL, 0);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	/*
+	 * If we should update atime, we will get EX lock,
+	 * otherwise we just get PR lock.
+	 */
+	if (ocfs2_should_update_atime(inode, vfsmnt)) {
+		struct buffer_head *bh = NULL;
+
+		ocfs2_meta_unlock(inode, 0);
+		ret = ocfs2_meta_lock(inode, &bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			return ret;
+		}
+		*level = 1;
+		if (ocfs2_should_update_atime(inode, vfsmnt))
+			ocfs2_update_inode_atime(inode, bh);
+		if (bh)
+			brelse(bh);
+	} else
+		*level = 0;
+
+	mlog_exit(ret);
+	return ret;
+}
+
 void ocfs2_meta_unlock(struct inode *inode,
 		       int ex)
 {
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index 4a2769387229..c343fca68cf1 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -68,8 +68,6 @@ void ocfs2_dentry_lock_res_init(struct ocfs2_dentry_lock *dl,
 				u64 parent, struct inode *inode);
 void ocfs2_lock_res_free(struct ocfs2_lock_res *res);
 int ocfs2_create_new_inode_locks(struct inode *inode);
-int ocfs2_create_new_lock(struct ocfs2_super *osb,
-			  struct ocfs2_lock_res *lockres, int ex, int local);
 int ocfs2_drop_inode_locks(struct inode *inode);
 int ocfs2_data_lock_full(struct inode *inode,
 			 int write,
@@ -82,19 +80,20 @@ void ocfs2_data_unlock(struct inode *inode,
 		       int write);
 int ocfs2_rw_lock(struct inode *inode, int write);
 void ocfs2_rw_unlock(struct inode *inode, int write);
+int ocfs2_meta_lock_atime(struct inode *inode,
+			  struct vfsmount *vfsmnt,
+			  int *level);
 int ocfs2_meta_lock_full(struct inode *inode,
-			 struct ocfs2_journal_handle *handle,
 			 struct buffer_head **ret_bh,
 			 int ex,
 			 int arg_flags);
 int ocfs2_meta_lock_with_page(struct inode *inode,
-			      struct ocfs2_journal_handle *handle,
 			      struct buffer_head **ret_bh,
 			      int ex,
 			      struct page *page);
 /* 99% of the time we don't want to supply any additional flags --
  * those are for very specific cases only. */
-#define ocfs2_meta_lock(i, h, b, e) ocfs2_meta_lock_full(i, h, b, e, 0)
+#define ocfs2_meta_lock(i, b, e) ocfs2_meta_lock_full(i, b, e, 0)
 void ocfs2_meta_unlock(struct inode *inode,
 		       int ex);
 int ocfs2_super_lock(struct ocfs2_super *osb,
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index fb91089a60a7..06be6e774cf9 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -100,7 +100,7 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 	mlog(0, "find parent of directory %llu\n",
 	     (unsigned long long)OCFS2_I(dir)->ip_blkno);
 
-	status = ocfs2_meta_lock(dir, NULL, NULL, 0);
+	status = ocfs2_meta_lock(dir, NULL, 0);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 1be74c4e7814..8786b3c490aa 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -31,6 +31,8 @@
 #include <linux/pagemap.h>
 #include <linux/uio.h>
 #include <linux/sched.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/mount.h>
 
 #define MLOG_MASK_PREFIX ML_INODE
 #include <cluster/masklog.h>
@@ -134,7 +136,58 @@ bail:
 	return (err < 0) ? -EIO : 0;
 }
 
-int ocfs2_set_inode_size(struct ocfs2_journal_handle *handle,
+int ocfs2_should_update_atime(struct inode *inode,
+			      struct vfsmount *vfsmnt)
+{
+	struct timespec now;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+		return 0;
+
+	if ((inode->i_flags & S_NOATIME) ||
+	    ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode)))
+		return 0;
+
+	if ((vfsmnt->mnt_flags & MNT_NOATIME) ||
+	    ((vfsmnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
+		return 0;
+
+	now = CURRENT_TIME;
+	if ((now.tv_sec - inode->i_atime.tv_sec <= osb->s_atime_quantum))
+		return 0;
+	else
+		return 1;
+}
+
+int ocfs2_update_inode_atime(struct inode *inode,
+			     struct buffer_head *bh)
+{
+	int ret;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	handle_t *handle;
+
+	mlog_entry_void();
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (handle == NULL) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	inode->i_atime = CURRENT_TIME;
+	ret = ocfs2_mark_inode_dirty(handle, inode, bh);
+	if (ret < 0)
+		mlog_errno(ret);
+
+	ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out:
+	mlog_exit(ret);
+	return ret;
+}
+
+int ocfs2_set_inode_size(handle_t *handle,
 			 struct inode *inode,
 			 struct buffer_head *fe_bh,
 			 u64 new_i_size)
@@ -163,10 +216,9 @@ static int ocfs2_simple_size_update(struct inode *inode,
 {
 	int ret;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 
-	handle = ocfs2_start_trans(osb, NULL,
-				   OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (handle == NULL) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
@@ -178,7 +230,7 @@ static int ocfs2_simple_size_update(struct inode *inode,
 	if (ret < 0)
 		mlog_errno(ret);
 
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 out:
 	return ret;
 }
@@ -189,14 +241,14 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
 				     u64 new_i_size)
 {
 	int status;
-	struct ocfs2_journal_handle *handle;
+	handle_t *handle;
 
 	mlog_entry_void();
 
 	/* TODO: This needs to actually orphan the inode in this
 	 * transaction. */
 
-	handle = ocfs2_start_trans(osb, NULL, OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -207,7 +259,7 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
 	if (status < 0)
 		mlog_errno(status);
 
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 out:
 	mlog_exit(status);
 	return status;
@@ -328,7 +380,7 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
 			       struct inode *inode,
 			       u32 clusters_to_add,
 			       struct buffer_head *fe_bh,
-			       struct ocfs2_journal_handle *handle,
+			       handle_t *handle,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       enum ocfs2_alloc_restarted *reason_ret)
@@ -433,7 +485,7 @@ static int ocfs2_extend_allocation(struct inode *inode,
 	u32 prev_clusters;
 	struct buffer_head *bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_alloc_context *data_ac = NULL;
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	enum ocfs2_alloc_restarted why;
@@ -463,13 +515,6 @@ restart_all:
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno, i_size_read(inode),
 	     fe->i_clusters, clusters_to_add);
 
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto leave;
-	}
-
 	num_free_extents = ocfs2_num_free_extents(osb,
 						  inode,
 						  fe);
@@ -480,10 +525,7 @@ restart_all:
 	}
 
 	if (!num_free_extents) {
-		status = ocfs2_reserve_new_metadata(osb,
-						    handle,
-						    fe,
-						    &meta_ac);
+		status = ocfs2_reserve_new_metadata(osb, fe, &meta_ac);
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
@@ -491,10 +533,7 @@ restart_all:
 		}
 	}
 
-	status = ocfs2_reserve_clusters(osb,
-					handle,
-					clusters_to_add,
-					&data_ac);
+	status = ocfs2_reserve_clusters(osb, clusters_to_add, &data_ac);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -509,7 +548,7 @@ restart_all:
 	drop_alloc_sem = 1;
 
 	credits = ocfs2_calc_extend_credits(osb->sb, fe, clusters_to_add);
-	handle = ocfs2_start_trans(osb, handle, credits);
+	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -589,7 +628,7 @@ leave:
 		drop_alloc_sem = 0;
 	}
 	if (handle) {
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 		handle = NULL;
 	}
 	if (data_ac) {
@@ -624,7 +663,7 @@ static int ocfs2_write_zero_page(struct inode *inode,
 	struct page *page;
 	unsigned long index;
 	unsigned int offset;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	int ret;
 
 	offset = (size & (PAGE_CACHE_SIZE-1)); /* Within page */
@@ -668,7 +707,7 @@ static int ocfs2_write_zero_page(struct inode *inode,
 		ret = 0;
 
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
 out_unlock:
 	unlock_page(page);
 	page_cache_release(page);
@@ -789,7 +828,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	struct super_block *sb = inode->i_sb;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 	struct buffer_head *bh = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 
 	mlog_entry("(0x%p, '%.*s')\n", dentry,
 	           dentry->d_name.len, dentry->d_name.name);
@@ -825,7 +864,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	status = ocfs2_meta_lock(inode, NULL, &bh, 1);
+	status = ocfs2_meta_lock(inode, &bh, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -845,7 +884,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	handle = ocfs2_start_trans(osb, NULL, OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -863,7 +902,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		mlog_errno(status);
 
 bail_commit:
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 bail_unlock:
 	ocfs2_meta_unlock(inode, 1);
 bail_unlock_rw:
@@ -906,19 +945,41 @@ bail:
 	return err;
 }
 
+int ocfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+	int ret;
+
+	mlog_entry_void();
+
+	ret = ocfs2_meta_lock(inode, NULL, 0);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = generic_permission(inode, mask, NULL);
+	if (ret)
+		mlog_errno(ret);
+
+	ocfs2_meta_unlock(inode, 0);
+out:
+	mlog_exit(ret);
+	return ret;
+}
+
 static int ocfs2_write_remove_suid(struct inode *inode)
 {
 	int ret;
 	struct buffer_head *bh = NULL;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	struct ocfs2_journal_handle *handle;
+	handle_t *handle;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_dinode *di;
 
 	mlog_entry("(Inode %llu, mode 0%o)\n",
 		   (unsigned long long)oi->ip_blkno, inode->i_mode);
 
-	handle = ocfs2_start_trans(osb, NULL, OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (handle == NULL) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
@@ -951,75 +1012,29 @@ static int ocfs2_write_remove_suid(struct inode *inode)
 out_bh:
 	brelse(bh);
 out_trans:
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 out:
 	mlog_exit(ret);
 	return ret;
 }
 
-static inline int ocfs2_write_should_remove_suid(struct inode *inode)
-{
-	mode_t mode = inode->i_mode;
-
-	if (!capable(CAP_FSETID)) {
-		if (unlikely(mode & S_ISUID))
-			return 1;
-
-		if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
-			return 1;
-	}
-	return 0;
-}
-
-static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs,
-				    loff_t pos)
+static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
+					 loff_t *ppos,
+					 size_t count,
+					 int appending)
 {
-	int ret, rw_level = -1, meta_level = -1, have_alloc_sem = 0;
+	int ret = 0, meta_level = appending;
+	struct inode *inode = dentry->d_inode;
 	u32 clusters;
-	struct file *filp = iocb->ki_filp;
-	struct inode *inode = filp->f_dentry->d_inode;
 	loff_t newsize, saved_pos;
 
-	mlog_entry("(0x%p, %u, '%.*s')\n", filp,
-		   (unsigned int)nr_segs,
-		   filp->f_dentry->d_name.len,
-		   filp->f_dentry->d_name.name);
-
-	/* happy write of zero bytes */
-	if (iocb->ki_left == 0)
-		return 0;
-
-	if (!inode) {
-		mlog(0, "bad inode\n");
-		return -EIO;
-	}
-
-	mutex_lock(&inode->i_mutex);
-	/* to match setattr's i_mutex -> i_alloc_sem -> rw_lock ordering */
-	if (filp->f_flags & O_DIRECT) {
-		have_alloc_sem = 1;
-		down_read(&inode->i_alloc_sem);
-	}
-
-	/* concurrent O_DIRECT writes are allowed */
-	rw_level = (filp->f_flags & O_DIRECT) ? 0 : 1;
-	ret = ocfs2_rw_lock(inode, rw_level);
-	if (ret < 0) {
-		rw_level = -1;
-		mlog_errno(ret);
-		goto out;
-	}
-
 	/* 
 	 * We sample i_size under a read level meta lock to see if our write
 	 * is extending the file, if it is we back off and get a write level
 	 * meta lock.
 	 */
-	meta_level = (filp->f_flags & O_APPEND) ? 1 : 0;
 	for(;;) {
-		ret = ocfs2_meta_lock(inode, NULL, NULL, meta_level);
+		ret = ocfs2_meta_lock(inode, NULL, meta_level);
 		if (ret < 0) {
 			meta_level = -1;
 			mlog_errno(ret);
@@ -1035,7 +1050,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		 * inode. There's also the dinode i_size state which
 		 * can be lost via setattr during extending writes (we
 		 * set inode->i_size at the end of a write. */
-		if (ocfs2_write_should_remove_suid(inode)) {
+		if (should_remove_suid(dentry)) {
 			if (meta_level == 0) {
 				ocfs2_meta_unlock(inode, meta_level);
 				meta_level = 1;
@@ -1045,19 +1060,19 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 			ret = ocfs2_write_remove_suid(inode);
 			if (ret < 0) {
 				mlog_errno(ret);
-				goto out;
+				goto out_unlock;
 			}
 		}
 
 		/* work on a copy of ppos until we're sure that we won't have
 		 * to recalculate it due to relocking. */
-		if (filp->f_flags & O_APPEND) {
+		if (appending) {
 			saved_pos = i_size_read(inode);
 			mlog(0, "O_APPEND: inode->i_size=%llu\n", saved_pos);
 		} else {
-			saved_pos = iocb->ki_pos;
+			saved_pos = *ppos;
 		}
-		newsize = iocb->ki_left + saved_pos;
+		newsize = count + saved_pos;
 
 		mlog(0, "pos=%lld newsize=%lld cursize=%lld\n",
 		     (long long) saved_pos, (long long) newsize,
@@ -1090,19 +1105,66 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		if (!clusters)
 			break;
 
-		ret = ocfs2_extend_file(inode, NULL, newsize, iocb->ki_left);
+		ret = ocfs2_extend_file(inode, NULL, newsize, count);
 		if (ret < 0) {
 			if (ret != -ENOSPC)
 				mlog_errno(ret);
-			goto out;
+			goto out_unlock;
 		}
 		break;
 	}
 
-	/* ok, we're done with i_size and alloc work */
-	iocb->ki_pos = saved_pos;
+	if (appending)
+		*ppos = saved_pos;
+
+out_unlock:
 	ocfs2_meta_unlock(inode, meta_level);
-	meta_level = -1;
+
+out:
+	return ret;
+}
+
+static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
+				    const struct iovec *iov,
+				    unsigned long nr_segs,
+				    loff_t pos)
+{
+	int ret, rw_level, have_alloc_sem = 0;
+	struct file *filp = iocb->ki_filp;
+	struct inode *inode = filp->f_dentry->d_inode;
+	int appending = filp->f_flags & O_APPEND ? 1 : 0;
+
+	mlog_entry("(0x%p, %u, '%.*s')\n", filp,
+		   (unsigned int)nr_segs,
+		   filp->f_dentry->d_name.len,
+		   filp->f_dentry->d_name.name);
+
+	/* happy write of zero bytes */
+	if (iocb->ki_left == 0)
+		return 0;
+
+	mutex_lock(&inode->i_mutex);
+	/* to match setattr's i_mutex -> i_alloc_sem -> rw_lock ordering */
+	if (filp->f_flags & O_DIRECT) {
+		have_alloc_sem = 1;
+		down_read(&inode->i_alloc_sem);
+	}
+
+	/* concurrent O_DIRECT writes are allowed */
+	rw_level = (filp->f_flags & O_DIRECT) ? 0 : 1;
+	ret = ocfs2_rw_lock(inode, rw_level);
+	if (ret < 0) {
+		rw_level = -1;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_prepare_inode_for_write(filp->f_dentry, &iocb->ki_pos,
+					    iocb->ki_left, appending);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
 
 	/* communicate with ocfs2_dio_end_io */
 	ocfs2_iocb_set_rw_locked(iocb);
@@ -1128,8 +1190,6 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	}
 
 out:
-	if (meta_level != -1)
-		ocfs2_meta_unlock(inode, meta_level);
 	if (have_alloc_sem)
 		up_read(&inode->i_alloc_sem);
 	if (rw_level != -1) 
@@ -1140,12 +1200,83 @@ out:
 	return ret;
 }
 
+static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
+				       struct file *out,
+				       loff_t *ppos,
+				       size_t len,
+				       unsigned int flags)
+{
+	int ret;
+	struct inode *inode = out->f_dentry->d_inode;
+
+	mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", out, pipe,
+		   (unsigned int)len,
+		   out->f_dentry->d_name.len,
+		   out->f_dentry->d_name.name);
+
+	inode_double_lock(inode, pipe->inode);
+
+	ret = ocfs2_rw_lock(inode, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_prepare_inode_for_write(out->f_dentry, ppos, len, 0);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out_unlock;
+	}
+
+	/* ok, we're done with i_size and alloc work */
+	ret = generic_file_splice_write_nolock(pipe, out, ppos, len, flags);
+
+out_unlock:
+	ocfs2_rw_unlock(inode, 1);
+out:
+	inode_double_unlock(inode, pipe->inode);
+
+	mlog_exit(ret);
+	return ret;
+}
+
+static ssize_t ocfs2_file_splice_read(struct file *in,
+				      loff_t *ppos,
+				      struct pipe_inode_info *pipe,
+				      size_t len,
+				      unsigned int flags)
+{
+	int ret = 0;
+	struct inode *inode = in->f_dentry->d_inode;
+
+	mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", in, pipe,
+		   (unsigned int)len,
+		   in->f_dentry->d_name.len,
+		   in->f_dentry->d_name.name);
+
+	/*
+	 * See the comment in ocfs2_file_aio_read()
+	 */
+	ret = ocfs2_meta_lock(inode, NULL, 0);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto bail;
+	}
+	ocfs2_meta_unlock(inode, 0);
+
+	ret = generic_file_splice_read(in, ppos, pipe, len, flags);
+
+bail:
+	mlog_exit(ret);
+	return ret;
+}
+
 static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 				   const struct iovec *iov,
 				   unsigned long nr_segs,
 				   loff_t pos)
 {
-	int ret = 0, rw_level = -1, have_alloc_sem = 0;
+	int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
 	struct file *filp = iocb->ki_filp;
 	struct inode *inode = filp->f_dentry->d_inode;
 
@@ -1187,12 +1318,12 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	 * like i_size. This allows the checks down below
 	 * generic_file_aio_read() a chance of actually working. 
 	 */
-	ret = ocfs2_meta_lock(inode, NULL, NULL, 0);
+	ret = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto bail;
 	}
-	ocfs2_meta_unlock(inode, 0);
+	ocfs2_meta_unlock(inode, lock_level);
 
 	ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
 	if (ret == -EINVAL)
@@ -1220,11 +1351,13 @@ bail:
 struct inode_operations ocfs2_file_iops = {
 	.setattr	= ocfs2_setattr,
 	.getattr	= ocfs2_getattr,
+	.permission	= ocfs2_permission,
 };
 
 struct inode_operations ocfs2_special_file_iops = {
 	.setattr	= ocfs2_setattr,
 	.getattr	= ocfs2_getattr,
+	.permission	= ocfs2_permission,
 };
 
 const struct file_operations ocfs2_fops = {
@@ -1238,6 +1371,8 @@ const struct file_operations ocfs2_fops = {
 	.aio_read	= ocfs2_file_aio_read,
 	.aio_write	= ocfs2_file_aio_write,
 	.ioctl		= ocfs2_ioctl,
+	.splice_read	= ocfs2_file_splice_read,
+	.splice_write	= ocfs2_file_splice_write,
 };
 
 const struct file_operations ocfs2_dops = {
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 740c9e7ca599..601a453f18a8 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -41,17 +41,24 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
 			       struct inode *inode,
 			       u32 clusters_to_add,
 			       struct buffer_head *fe_bh,
-			       struct ocfs2_journal_handle *handle,
+			       handle_t *handle,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       enum ocfs2_alloc_restarted *reason);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
+int ocfs2_permission(struct inode *inode, int mask,
+		     struct nameidata *nd);
 
-int ocfs2_set_inode_size(struct ocfs2_journal_handle *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 			 struct inode *inode,
 			 struct buffer_head *fe_bh,
 			 u64 new_i_size);
 
+int ocfs2_should_update_atime(struct inode *inode,
+			      struct vfsmount *vfsmnt);
+int ocfs2_update_inode_atime(struct inode *inode,
+			     struct buffer_head *bh);
+
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 16e8e74dc966..42e361f3054f 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -360,7 +360,6 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 				  inode);
 
 	ocfs2_set_inode_flags(inode);
-	inode->i_flags |= S_NOATIME;
 
 	status = 0;
 bail:
@@ -441,7 +440,7 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 				  generation, inode);
 
 	if (can_lock) {
-		status = ocfs2_meta_lock(inode, NULL, NULL, 0);
+		status = ocfs2_meta_lock(inode, NULL, 0);
 		if (status) {
 			make_bad_inode(inode);
 			mlog_errno(status);
@@ -512,7 +511,7 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 				     struct buffer_head *fe_bh)
 {
 	int status = 0;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_truncate_context *tc = NULL;
 	struct ocfs2_dinode *fe;
 
@@ -524,7 +523,7 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 	if (!fe->i_clusters)
 		goto bail;
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -538,7 +537,7 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 		goto bail;
 	}
 
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 	handle = NULL;
 
 	status = ocfs2_prepare_truncate(osb, inode, fe_bh, &tc);
@@ -554,7 +553,7 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 	}
 bail:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 
 	mlog_exit(status);
 	return status;
@@ -568,7 +567,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 	int status;
 	struct inode *inode_alloc_inode = NULL;
 	struct buffer_head *inode_alloc_bh = NULL;
-	struct ocfs2_journal_handle *handle;
+	handle_t *handle;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
 
@@ -582,7 +581,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 	}
 
 	mutex_lock(&inode_alloc_inode->i_mutex);
-	status = ocfs2_meta_lock(inode_alloc_inode, NULL, &inode_alloc_bh, 1);
+	status = ocfs2_meta_lock(inode_alloc_inode, &inode_alloc_bh, 1);
 	if (status < 0) {
 		mutex_unlock(&inode_alloc_inode->i_mutex);
 
@@ -590,7 +589,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 		goto bail;
 	}
 
-	handle = ocfs2_start_trans(osb, NULL, OCFS2_DELETE_INODE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_DELETE_INODE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -629,7 +628,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 		mlog_errno(status);
 
 bail_commit:
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 bail_unlock:
 	ocfs2_meta_unlock(inode_alloc_inode, 1);
 	mutex_unlock(&inode_alloc_inode->i_mutex);
@@ -705,7 +704,7 @@ static int ocfs2_wipe_inode(struct inode *inode,
 	 * delete_inode operation. We do this now to avoid races with
 	 * recovery completion on other nodes. */
 	mutex_lock(&orphan_dir_inode->i_mutex);
-	status = ocfs2_meta_lock(orphan_dir_inode, NULL, &orphan_dir_bh, 1);
+	status = ocfs2_meta_lock(orphan_dir_inode, &orphan_dir_bh, 1);
 	if (status < 0) {
 		mutex_unlock(&orphan_dir_inode->i_mutex);
 
@@ -933,7 +932,7 @@ void ocfs2_delete_inode(struct inode *inode)
 	 * allocation lock here as it won't be needed - nobody will
 	 * have the file open.
 	 */
-	status = ocfs2_meta_lock(inode, NULL, &di_bh, 1);
+	status = ocfs2_meta_lock(inode, &di_bh, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -1067,12 +1066,6 @@ void ocfs2_clear_inode(struct inode *inode)
 	mlog_bug_on_msg(oi->ip_open_count,
 			"Clear inode of %llu has open count %d\n",
 			(unsigned long long)oi->ip_blkno, oi->ip_open_count);
-	mlog_bug_on_msg(!list_empty(&oi->ip_handle_list),
-			"Clear inode of %llu has non empty handle list\n",
-			(unsigned long long)oi->ip_blkno);
-	mlog_bug_on_msg(oi->ip_handle,
-			"Clear inode of %llu has non empty handle pointer\n",
-			(unsigned long long)oi->ip_blkno);
 
 	/* Clear all other flags. */
 	oi->ip_flags = OCFS2_INODE_CACHE_INLINE;
@@ -1186,7 +1179,7 @@ int ocfs2_inode_revalidate(struct dentry *dentry)
 
 	/* Let ocfs2_meta_lock do the work of updating our struct
 	 * inode for us. */
-	status = ocfs2_meta_lock(inode, NULL, NULL, 0);
+	status = ocfs2_meta_lock(inode, NULL, 0);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -1204,7 +1197,7 @@ bail:
  * struct inode.
  * Only takes ip_lock.
  */
-int ocfs2_mark_inode_dirty(struct ocfs2_journal_handle *handle,
+int ocfs2_mark_inode_dirty(handle_t *handle,
 			   struct inode *inode,
 			   struct buffer_head *bh)
 {
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 9957810fdf85..46a378fbc40b 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -48,13 +48,6 @@ struct ocfs2_inode_info
 
 	struct mutex			ip_io_mutex;
 
-	/* Used by the journalling code to attach an inode to a
-	 * handle.  These are protected by ip_io_mutex in order to lock
-	 * out other I/O to the inode until we either commit or
-	 * abort. */
-	struct list_head		ip_handle_list;
-	struct ocfs2_journal_handle	*ip_handle;
-
 	u32				ip_flags; /* see below */
 	u32				ip_attr; /* inode attributes */
 
@@ -143,7 +136,7 @@ ssize_t ocfs2_rw_direct(int rw, struct file *filp, char *buf,
 void ocfs2_sync_blockdev(struct super_block *sb);
 void ocfs2_refresh_inode(struct inode *inode,
 			 struct ocfs2_dinode *fe);
-int ocfs2_mark_inode_dirty(struct ocfs2_journal_handle *handle,
+int ocfs2_mark_inode_dirty(handle_t *handle,
 			   struct inode *inode,
 			   struct buffer_head *bh);
 int ocfs2_aio_read(struct file *file, struct kiocb *req, struct iocb *iocb);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 3663cef80689..4768be5f3086 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -26,7 +26,7 @@ static int ocfs2_get_inode_attr(struct inode *inode, unsigned *flags)
 {
 	int status;
 
-	status = ocfs2_meta_lock(inode, NULL, NULL, 0);
+	status = ocfs2_meta_lock(inode, NULL, 0);
 	if (status < 0) {
 		mlog_errno(status);
 		return status;
@@ -43,14 +43,14 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 {
 	struct ocfs2_inode_info *ocfs2_inode = OCFS2_I(inode);
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct buffer_head *bh = NULL;
 	unsigned oldflags;
 	int status;
 
 	mutex_lock(&inode->i_mutex);
 
-	status = ocfs2_meta_lock(inode, NULL, &bh, 1);
+	status = ocfs2_meta_lock(inode, &bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -67,7 +67,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if (!S_ISDIR(inode->i_mode))
 		flags &= ~OCFS2_DIRSYNC_FL;
 
-	handle = ocfs2_start_trans(osb, NULL, OCFS2_INODE_UPDATE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -96,7 +96,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if (status < 0)
 		mlog_errno(status);
 
-	ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
 bail_unlock:
 	ocfs2_meta_unlock(inode, 1);
 bail:
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index d95ee2720e6e..1d7f4ab1e5ed 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -57,9 +57,6 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 static int __ocfs2_recovery_thread(void *arg);
 static int ocfs2_commit_cache(struct ocfs2_super *osb);
 static int ocfs2_wait_on_mount(struct ocfs2_super *osb);
-static void ocfs2_handle_cleanup_locks(struct ocfs2_journal *journal,
-				       struct ocfs2_journal_handle *handle);
-static void ocfs2_commit_unstarted_handle(struct ocfs2_journal_handle *handle);
 static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 				      int dirty);
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
@@ -113,46 +110,18 @@ finally:
 	return status;
 }
 
-struct ocfs2_journal_handle *ocfs2_alloc_handle(struct ocfs2_super *osb)
-{
-	struct ocfs2_journal_handle *retval = NULL;
-
-	retval = kcalloc(1, sizeof(*retval), GFP_NOFS);
-	if (!retval) {
-		mlog(ML_ERROR, "Failed to allocate memory for journal "
-		     "handle!\n");
-		return NULL;
-	}
-
-	retval->max_buffs = 0;
-	retval->num_locks = 0;
-	retval->k_handle = NULL;
-
-	INIT_LIST_HEAD(&retval->locks);
-	INIT_LIST_HEAD(&retval->inode_list);
-	retval->journal = osb->journal;
-
-	return retval;
-}
-
 /* pass it NULL and it will allocate a new handle object for you.  If
  * you pass it a handle however, it may still return error, in which
  * case it has free'd the passed handle for you. */
-struct ocfs2_journal_handle *ocfs2_start_trans(struct ocfs2_super *osb,
-					       struct ocfs2_journal_handle *handle,
-					       int max_buffs)
+handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
 {
-	int ret;
 	journal_t *journal = osb->journal->j_journal;
-
-	mlog_entry("(max_buffs = %d)\n", max_buffs);
+	handle_t *handle;
 
 	BUG_ON(!osb || !osb->journal->j_journal);
 
-	if (ocfs2_is_hard_readonly(osb)) {
-		ret = -EROFS;
-		goto done_free;
-	}
+	if (ocfs2_is_hard_readonly(osb))
+		return ERR_PTR(-EROFS);
 
 	BUG_ON(osb->journal->j_state == OCFS2_JOURNAL_FREE);
 	BUG_ON(max_buffs <= 0);
@@ -163,154 +132,39 @@ struct ocfs2_journal_handle *ocfs2_start_trans(struct ocfs2_super *osb,
 		BUG();
 	}
 
-	if (!handle)
-		handle = ocfs2_alloc_handle(osb);
-	if (!handle) {
-		ret = -ENOMEM;
-		mlog(ML_ERROR, "Failed to allocate memory for journal "
-		     "handle!\n");
-		goto done_free;
-	}
-
-	handle->max_buffs = max_buffs;
-
 	down_read(&osb->journal->j_trans_barrier);
 
-	/* actually start the transaction now */
-	handle->k_handle = journal_start(journal, max_buffs);
-	if (IS_ERR(handle->k_handle)) {
+	handle = journal_start(journal, max_buffs);
+	if (IS_ERR(handle)) {
 		up_read(&osb->journal->j_trans_barrier);
 
-		ret = PTR_ERR(handle->k_handle);
-		handle->k_handle = NULL;
-		mlog_errno(ret);
+		mlog_errno(PTR_ERR(handle));
 
 		if (is_journal_aborted(journal)) {
 			ocfs2_abort(osb->sb, "Detected aborted journal");
-			ret = -EROFS;
+			handle = ERR_PTR(-EROFS);
 		}
-		goto done_free;
-	}
-
-	atomic_inc(&(osb->journal->j_num_trans));
-	handle->flags |= OCFS2_HANDLE_STARTED;
+	} else
+		atomic_inc(&(osb->journal->j_num_trans));
 
-	mlog_exit_ptr(handle);
 	return handle;
-
-done_free:
-	if (handle)
-		ocfs2_commit_unstarted_handle(handle); /* will kfree handle */
-
-	mlog_exit(ret);
-	return ERR_PTR(ret);
-}
-
-void ocfs2_handle_add_inode(struct ocfs2_journal_handle *handle,
-			    struct inode *inode)
-{
-	BUG_ON(!handle);
-	BUG_ON(!inode);
-
-	atomic_inc(&inode->i_count);
-
-	/* we're obviously changing it... */
-	mutex_lock(&inode->i_mutex);
-
-	/* sanity check */
-	BUG_ON(OCFS2_I(inode)->ip_handle);
-	BUG_ON(!list_empty(&OCFS2_I(inode)->ip_handle_list));
-
-	OCFS2_I(inode)->ip_handle = handle;
-	list_move_tail(&(OCFS2_I(inode)->ip_handle_list), &(handle->inode_list));
-}
-
-static void ocfs2_handle_unlock_inodes(struct ocfs2_journal_handle *handle)
-{
-	struct list_head *p, *n;
-	struct inode *inode;
-	struct ocfs2_inode_info *oi;
-
-	list_for_each_safe(p, n, &handle->inode_list) {
-		oi = list_entry(p, struct ocfs2_inode_info,
-				ip_handle_list);
-		inode = &oi->vfs_inode;
-
-		OCFS2_I(inode)->ip_handle = NULL;
-		list_del_init(&OCFS2_I(inode)->ip_handle_list);
-
-		mutex_unlock(&inode->i_mutex);
-		iput(inode);
-	}
-}
-
-/* This is trivial so we do it out of the main commit
- * paths. Beware, it can be called from start_trans too! */
-static void ocfs2_commit_unstarted_handle(struct ocfs2_journal_handle *handle)
-{
-	mlog_entry_void();
-
-	BUG_ON(handle->flags & OCFS2_HANDLE_STARTED);
-
-	ocfs2_handle_unlock_inodes(handle);
-	/* You are allowed to add journal locks before the transaction
-	 * has started. */
-	ocfs2_handle_cleanup_locks(handle->journal, handle);
-
-	kfree(handle);
-
-	mlog_exit_void();
 }
 
-void ocfs2_commit_trans(struct ocfs2_journal_handle *handle)
+int ocfs2_commit_trans(struct ocfs2_super *osb,
+		       handle_t *handle)
 {
-	handle_t *jbd_handle;
-	int retval;
-	struct ocfs2_journal *journal = handle->journal;
-
-	mlog_entry_void();
+	int ret;
+	struct ocfs2_journal *journal = osb->journal;
 
 	BUG_ON(!handle);
 
-	if (!(handle->flags & OCFS2_HANDLE_STARTED)) {
-		ocfs2_commit_unstarted_handle(handle);
-		mlog_exit_void();
-		return;
-	}
-
-	/* release inode semaphores we took during this transaction */
-	ocfs2_handle_unlock_inodes(handle);
-
-	/* ocfs2_extend_trans may have had to call journal_restart
-	 * which will always commit the transaction, but may return
-	 * error for any number of reasons. If this is the case, we
-	 * clear k_handle as it's not valid any more. */
-	if (handle->k_handle) {
-		jbd_handle = handle->k_handle;
-
-		if (handle->flags & OCFS2_HANDLE_SYNC)
-			jbd_handle->h_sync = 1;
-		else
-			jbd_handle->h_sync = 0;
-
-		/* actually stop the transaction. if we've set h_sync,
-		 * it'll have been committed when we return */
-		retval = journal_stop(jbd_handle);
-		if (retval < 0) {
-			mlog_errno(retval);
-			mlog(ML_ERROR, "Could not commit transaction\n");
-			BUG();
-		}
-
-		handle->k_handle = NULL; /* it's been free'd in journal_stop */
-	}
-
-	ocfs2_handle_cleanup_locks(journal, handle);
+	ret = journal_stop(handle);
+	if (ret < 0)
+		mlog_errno(ret);
 
 	up_read(&journal->j_trans_barrier);
 
-	kfree(handle);
-	mlog_exit_void();
+	return ret;
 }
 
 /*
@@ -326,20 +180,18 @@ void ocfs2_commit_trans(struct ocfs2_journal_handle *handle)
  * good because transaction ids haven't yet been recorded on the
  * cluster locks associated with this handle.
  */
-int ocfs2_extend_trans(struct ocfs2_journal_handle *handle,
-		       int nblocks)
+int ocfs2_extend_trans(handle_t *handle, int nblocks)
 {
 	int status;
 
 	BUG_ON(!handle);
-	BUG_ON(!(handle->flags & OCFS2_HANDLE_STARTED));
 	BUG_ON(!nblocks);
 
 	mlog_entry_void();
 
 	mlog(0, "Trying to extend transaction by %d blocks\n", nblocks);
 
-	status = journal_extend(handle->k_handle, nblocks);
+	status = journal_extend(handle, nblocks);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -347,15 +199,12 @@ int ocfs2_extend_trans(struct ocfs2_journal_handle *handle,
 
 	if (status > 0) {
 		mlog(0, "journal_extend failed, trying journal_restart\n");
-		status = journal_restart(handle->k_handle, nblocks);
+		status = journal_restart(handle, nblocks);
 		if (status < 0) {
-			handle->k_handle = NULL;
 			mlog_errno(status);
 			goto bail;
 		}
-		handle->max_buffs = nblocks;
-	} else
-		handle->max_buffs += nblocks;
+	}
 
 	status = 0;
 bail:
@@ -364,7 +213,7 @@ bail:
 	return status;
 }
 
-int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
+int ocfs2_journal_access(handle_t *handle,
 			 struct inode *inode,
 			 struct buffer_head *bh,
 			 int type)
@@ -374,7 +223,6 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
 	BUG_ON(!inode);
 	BUG_ON(!handle);
 	BUG_ON(!bh);
-	BUG_ON(!(handle->flags & OCFS2_HANDLE_STARTED));
 
 	mlog_entry("bh->b_blocknr=%llu, type=%d (\"%s\"), bh->b_size = %zu\n",
 		   (unsigned long long)bh->b_blocknr, type,
@@ -403,11 +251,11 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
 	switch (type) {
 	case OCFS2_JOURNAL_ACCESS_CREATE:
 	case OCFS2_JOURNAL_ACCESS_WRITE:
-		status = journal_get_write_access(handle->k_handle, bh);
+		status = journal_get_write_access(handle, bh);
 		break;
 
 	case OCFS2_JOURNAL_ACCESS_UNDO:
-		status = journal_get_undo_access(handle->k_handle, bh);
+		status = journal_get_undo_access(handle, bh);
 		break;
 
 	default:
@@ -424,17 +272,15 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
 	return status;
 }
 
-int ocfs2_journal_dirty(struct ocfs2_journal_handle *handle,
+int ocfs2_journal_dirty(handle_t *handle,
 			struct buffer_head *bh)
 {
 	int status;
 
-	BUG_ON(!(handle->flags & OCFS2_HANDLE_STARTED));
-
 	mlog_entry("(bh->b_blocknr=%llu)\n",
 		   (unsigned long long)bh->b_blocknr);
 
-	status = journal_dirty_metadata(handle->k_handle, bh);
+	status = journal_dirty_metadata(handle, bh);
 	if (status < 0)
 		mlog(ML_ERROR, "Could not dirty metadata buffer. "
 		     "(bh->b_blocknr=%llu)\n",
@@ -456,59 +302,6 @@ int ocfs2_journal_dirty_data(handle_t *handle,
 	return err;
 }
 
-/* We always assume you're adding a metadata lock at level 'ex' */
-int ocfs2_handle_add_lock(struct ocfs2_journal_handle *handle,
-			  struct inode *inode)
-{
-	int status;
-	struct ocfs2_journal_lock *lock;
-
-	BUG_ON(!inode);
-
-	lock = kmem_cache_alloc(ocfs2_lock_cache, GFP_NOFS);
-	if (!lock) {
-		status = -ENOMEM;
-		mlog_errno(-ENOMEM);
-		goto bail;
-	}
-
-	if (!igrab(inode))
-		BUG();
-	lock->jl_inode = inode;
-
-	list_add_tail(&(lock->jl_lock_list), &(handle->locks));
-	handle->num_locks++;
-
-	status = 0;
-bail:
-	mlog_exit(status);
-	return status;
-}
-
-static void ocfs2_handle_cleanup_locks(struct ocfs2_journal *journal,
-				       struct ocfs2_journal_handle *handle)
-{
-	struct list_head *p, *n;
-	struct ocfs2_journal_lock *lock;
-	struct inode *inode;
-
-	list_for_each_safe(p, n, &(handle->locks)) {
-		lock = list_entry(p, struct ocfs2_journal_lock,
-				  jl_lock_list);
-		list_del(&lock->jl_lock_list);
-		handle->num_locks--;
-
-		inode = lock->jl_inode;
-		ocfs2_meta_unlock(inode, 1);
-		if (atomic_read(&inode->i_count) == 1)
-			mlog(ML_ERROR,
-			     "Inode %llu, I'm doing a last iput for!",
-			     (unsigned long long)OCFS2_I(inode)->ip_blkno);
-		iput(inode);
-		kmem_cache_free(ocfs2_lock_cache, lock);
-	}
-}
-
 #define OCFS2_DEFAULT_COMMIT_INTERVAL 	(HZ * 5)
 
 void ocfs2_set_journal_params(struct ocfs2_super *osb)
@@ -562,8 +355,7 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 	/* Skip recovery waits here - journal inode metadata never
 	 * changes in a live cluster so it can be considered an
 	 * exception to the rule. */
-	status = ocfs2_meta_lock_full(inode, NULL, &bh, 1,
-				      OCFS2_META_LOCK_RECOVERY);
+	status = ocfs2_meta_lock_full(inode, &bh, 1, OCFS2_META_LOCK_RECOVERY);
 	if (status < 0) {
 		if (status != -ERESTARTSYS)
 			mlog(ML_ERROR, "Could not get lock on journal!\n");
@@ -1161,8 +953,7 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 	}
 	SET_INODE_JOURNAL(inode);
 
-	status = ocfs2_meta_lock_full(inode, NULL, &bh, 1,
-				      OCFS2_META_LOCK_RECOVERY);
+	status = ocfs2_meta_lock_full(inode, &bh, 1, OCFS2_META_LOCK_RECOVERY);
 	if (status < 0) {
 		mlog(0, "status returned from ocfs2_meta_lock=%d\n", status);
 		if (status != -ERESTARTSYS)
@@ -1351,7 +1142,7 @@ static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 	SET_INODE_JOURNAL(inode);
 
 	flags = OCFS2_META_LOCK_RECOVERY | OCFS2_META_LOCK_NOQUEUE;
-	status = ocfs2_meta_lock_full(inode, NULL, NULL, 1, flags);
+	status = ocfs2_meta_lock_full(inode, NULL, 1, flags);
 	if (status < 0) {
 		if (status != -EAGAIN)
 			mlog_errno(status);
@@ -1434,7 +1225,7 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 	}	
 
 	mutex_lock(&orphan_dir_inode->i_mutex);
-	status = ocfs2_meta_lock(orphan_dir_inode, NULL, NULL, 0);
+	status = ocfs2_meta_lock(orphan_dir_inode, NULL, 0);
 	if (status < 0) {
 		mlog_errno(status);
 		goto out;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 5be161a4ad9f..899112ad8136 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -37,7 +37,6 @@ enum ocfs2_journal_state {
 
 struct ocfs2_super;
 struct ocfs2_dinode;
-struct ocfs2_journal_handle;
 
 struct ocfs2_journal {
 	enum ocfs2_journal_state   j_state;    /* Journals current state   */
@@ -133,44 +132,6 @@ static inline void ocfs2_inode_set_new(struct ocfs2_super *osb,
 	spin_unlock(&trans_inc_lock);
 }
 
-extern kmem_cache_t *ocfs2_lock_cache;
-
-struct ocfs2_journal_lock {
-	struct inode     *jl_inode;
-	struct list_head  jl_lock_list;
-};
-
-struct ocfs2_journal_handle {
-	handle_t            *k_handle; /* kernel handle.                */
-	struct ocfs2_journal        *journal;
-	u32                 flags;     /* see flags below.              */
-	int                 max_buffs; /* Buffs reserved by this handle */
-
-	/* The following two fields are for ocfs2_handle_add_lock */
-	int                 num_locks;
-	struct list_head    locks;     /* A bunch of locks to
-					* release on commit. This
-					* should be a list_head */
-
-	struct list_head     inode_list;
-};
-
-#define OCFS2_HANDLE_STARTED			1
-/* should we sync-commit this handle? */
-#define OCFS2_HANDLE_SYNC			2
-static inline int ocfs2_handle_started(struct ocfs2_journal_handle *handle)
-{
-	return handle->flags & OCFS2_HANDLE_STARTED;
-}
-
-static inline void ocfs2_handle_set_sync(struct ocfs2_journal_handle *handle, int sync)
-{
-	if (sync)
-		handle->flags |= OCFS2_HANDLE_SYNC;
-	else
-		handle->flags &= ~OCFS2_HANDLE_SYNC;
-}
-
 /* Exported only for the journal struct init code in super.c. Do not call. */
 void ocfs2_complete_recovery(struct work_struct *work);
 
@@ -231,15 +192,14 @@ static inline void ocfs2_checkpoint_inode(struct inode *inode)
  *  Transaction Handling:
  *  Manage the lifetime of a transaction handle.
  *
- *  ocfs2_alloc_handle     - Only allocate a handle so we can start putting
- *                          cluster locks on it. To actually change blocks,
- *                          call ocfs2_start_trans with the handle returned
- *                          from this function. You may call ocfs2_commit_trans
- *                           at any time in the lifetime of a handle.
  *  ocfs2_start_trans      - Begin a transaction. Give it an upper estimate of
  *                          the number of blocks that will be changed during
  *                          this handle.
- *  ocfs2_commit_trans     - Complete a handle.
+ *  ocfs2_commit_trans - Complete a handle. It might return -EIO if
+ *                       the journal was aborted. The majority of paths don't
+ *                       check the return value as an error there comes too
+ *                       late to do anything (and will be picked up in a
+ *                       later transaction).
  *  ocfs2_extend_trans     - Extend a handle by nblocks credits. This may
  *                          commit the handle to disk in the process, but will
  *                          not release any locks taken during the transaction.
@@ -249,24 +209,16 @@ static inline void ocfs2_checkpoint_inode(struct inode *inode)
  *  ocfs2_journal_dirty    - Mark a journalled buffer as having dirty data.
  *  ocfs2_journal_dirty_data - Indicate that a data buffer should go out before
  *                             the current handle commits.
- *  ocfs2_handle_add_lock  - Sometimes we need to delay lock release
- *                          until after a transaction has been completed. Use
- *                          ocfs2_handle_add_lock to indicate that a lock needs
- *                          to be released at the end of that handle. Locks
- *                          will be released in the order that they are added.
- *  ocfs2_handle_add_inode - Add a locked inode to a transaction.
  */
 
 /* You must always start_trans with a number of buffs > 0, but it's
  * perfectly legal to go through an entire transaction without having
  * dirtied any buffers. */
-struct ocfs2_journal_handle *ocfs2_alloc_handle(struct ocfs2_super *osb);
-struct ocfs2_journal_handle *ocfs2_start_trans(struct ocfs2_super *osb,
-					       struct ocfs2_journal_handle *handle,
+handle_t		    *ocfs2_start_trans(struct ocfs2_super *osb,
 					       int max_buffs);
-void			     ocfs2_commit_trans(struct ocfs2_journal_handle *handle);
-int			     ocfs2_extend_trans(struct ocfs2_journal_handle *handle,
-						int nblocks);
+int			     ocfs2_commit_trans(struct ocfs2_super *osb,
+						handle_t *handle);
+int			     ocfs2_extend_trans(handle_t *handle, int nblocks);
 
 /*
  * Create access is for when we get a newly created buffer and we're
@@ -283,7 +235,7 @@ int			     ocfs2_extend_trans(struct ocfs2_journal_handle *handle,
 #define OCFS2_JOURNAL_ACCESS_WRITE  1
 #define OCFS2_JOURNAL_ACCESS_UNDO   2
 
-int                  ocfs2_journal_access(struct ocfs2_journal_handle *handle,
+int                  ocfs2_journal_access(handle_t *handle,
 					  struct inode *inode,
 					  struct buffer_head *bh,
 					  int type);
@@ -306,18 +258,10 @@ int                  ocfs2_journal_access(struct ocfs2_journal_handle *handle,
  *	<modify the bh>
  * 	ocfs2_journal_dirty(handle, bh);
  */
-int                  ocfs2_journal_dirty(struct ocfs2_journal_handle *handle,
+int                  ocfs2_journal_dirty(handle_t *handle,
 					 struct buffer_head *bh);
 int                  ocfs2_journal_dirty_data(handle_t *handle,
 					      struct buffer_head *bh);
-int                  ocfs2_handle_add_lock(struct ocfs2_journal_handle *handle,
-					   struct inode *inode);
-/*
- * Use this to protect from other processes reading buffer state while
- * it's in flight.
- */
-void                 ocfs2_handle_add_inode(struct ocfs2_journal_handle *handle,
-					    struct inode *inode);
 
 /*
  *  Credit Macros:
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 1f17a4d08287..698d79a74ef8 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -58,19 +58,18 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb,
 static void ocfs2_clear_local_alloc(struct ocfs2_dinode *alloc);
 
 static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
-				    struct ocfs2_journal_handle *handle,
+				    handle_t *handle,
 				    struct ocfs2_dinode *alloc,
 				    struct inode *main_bm_inode,
 				    struct buffer_head *main_bm_bh);
 
 static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb,
-						struct ocfs2_journal_handle *handle,
 						struct ocfs2_alloc_context **ac,
 						struct inode **bitmap_inode,
 						struct buffer_head **bitmap_bh);
 
 static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
-					struct ocfs2_journal_handle *handle,
+					handle_t *handle,
 					struct ocfs2_alloc_context *ac);
 
 static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
@@ -196,7 +195,7 @@ bail:
 void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 {
 	int status;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle;
 	struct inode *local_alloc_inode = NULL;
 	struct buffer_head *bh = NULL;
 	struct buffer_head *main_bm_bh = NULL;
@@ -207,7 +206,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	mlog_entry_void();
 
 	if (osb->local_alloc_state == OCFS2_LA_UNUSED)
-		goto bail;
+		goto out;
 
 	local_alloc_inode =
 		ocfs2_get_system_file_inode(osb,
@@ -216,40 +215,34 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	if (!local_alloc_inode) {
 		status = -ENOENT;
 		mlog_errno(status);
-		goto bail;
+		goto out;
 	}
 
 	osb->local_alloc_state = OCFS2_LA_DISABLED;
 
-	handle = ocfs2_alloc_handle(osb);
-	if (!handle) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	main_bm_inode = ocfs2_get_system_file_inode(osb,
 						    GLOBAL_BITMAP_SYSTEM_INODE,
 						    OCFS2_INVALID_SLOT);
 	if (!main_bm_inode) {
 		status = -EINVAL;
 		mlog_errno(status);
-		goto bail;
+		goto out;
 	}
 
-	ocfs2_handle_add_inode(handle, main_bm_inode);
-	status = ocfs2_meta_lock(main_bm_inode, handle, &main_bm_bh, 1);
+	mutex_lock(&main_bm_inode->i_mutex);
+
+	status = ocfs2_meta_lock(main_bm_inode, &main_bm_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
-		goto bail;
+		goto out_mutex;
 	}
 
 	/* WINDOW_MOVE_CREDITS is a bit heavy... */
-	handle = ocfs2_start_trans(osb, handle, OCFS2_WINDOW_MOVE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS);
 	if (IS_ERR(handle)) {
 		mlog_errno(PTR_ERR(handle));
 		handle = NULL;
-		goto bail;
+		goto out_unlock;
 	}
 
 	bh = osb->local_alloc_bh;
@@ -258,7 +251,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	alloc_copy = kmalloc(bh->b_size, GFP_KERNEL);
 	if (!alloc_copy) {
 		status = -ENOMEM;
-		goto bail;
+		goto out_commit;
 	}
 	memcpy(alloc_copy, alloc, bh->b_size);
 
@@ -266,7 +259,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (status < 0) {
 		mlog_errno(status);
-		goto bail;
+		goto out_commit;
 	}
 
 	ocfs2_clear_local_alloc(alloc);
@@ -274,7 +267,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	status = ocfs2_journal_dirty(handle, bh);
 	if (status < 0) {
 		mlog_errno(status);
-		goto bail;
+		goto out_commit;
 	}
 
 	brelse(bh);
@@ -286,16 +279,20 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	if (status < 0)
 		mlog_errno(status);
 
-bail:
-	if (handle)
-		ocfs2_commit_trans(handle);
+out_commit:
+	ocfs2_commit_trans(osb, handle);
 
+out_unlock:
 	if (main_bm_bh)
 		brelse(main_bm_bh);
 
-	if (main_bm_inode)
-		iput(main_bm_inode);
+	ocfs2_meta_unlock(main_bm_inode, 1);
 
+out_mutex:
+	mutex_unlock(&main_bm_inode->i_mutex);
+	iput(main_bm_inode);
+
+out:
 	if (local_alloc_inode)
 		iput(local_alloc_inode);
 
@@ -385,61 +382,59 @@ int ocfs2_complete_local_alloc_recovery(struct ocfs2_super *osb,
 					struct ocfs2_dinode *alloc)
 {
 	int status;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle;
 	struct buffer_head *main_bm_bh = NULL;
-	struct inode *main_bm_inode = NULL;
+	struct inode *main_bm_inode;
 
 	mlog_entry_void();
 
-	handle = ocfs2_alloc_handle(osb);
-	if (!handle) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	main_bm_inode = ocfs2_get_system_file_inode(osb,
 						    GLOBAL_BITMAP_SYSTEM_INODE,
 						    OCFS2_INVALID_SLOT);
 	if (!main_bm_inode) {
 		status = -EINVAL;
 		mlog_errno(status);
-		goto bail;
+		goto out;
 	}
 
-	ocfs2_handle_add_inode(handle, main_bm_inode);
-	status = ocfs2_meta_lock(main_bm_inode, handle, &main_bm_bh, 1);
+	mutex_lock(&main_bm_inode->i_mutex);
+
+	status = ocfs2_meta_lock(main_bm_inode, &main_bm_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
-		goto bail;
+		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_WINDOW_MOVE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
 		mlog_errno(status);
-		goto bail;
+		goto out_unlock;
 	}
 
 	/* we want the bitmap change to be recorded on disk asap */
-	ocfs2_handle_set_sync(handle, 1);
+	handle->h_sync = 1;
 
 	status = ocfs2_sync_local_to_main(osb, handle, alloc,
 					  main_bm_inode, main_bm_bh);
 	if (status < 0)
 		mlog_errno(status);
 
-bail:
-	if (handle)
-		ocfs2_commit_trans(handle);
+	ocfs2_commit_trans(osb, handle);
+
+out_unlock:
+	ocfs2_meta_unlock(main_bm_inode, 1);
+
+out_mutex:
+	mutex_unlock(&main_bm_inode->i_mutex);
 
 	if (main_bm_bh)
 		brelse(main_bm_bh);
 
-	if (main_bm_inode)
-		iput(main_bm_inode);
+	iput(main_bm_inode);
 
+out:
 	mlog_exit(status);
 	return status;
 }
@@ -452,7 +447,6 @@ bail:
  * our own in order to shift windows.
  */
 int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
-				   struct ocfs2_journal_handle *passed_handle,
 				   u32 bits_wanted,
 				   struct ocfs2_alloc_context *ac)
 {
@@ -463,9 +457,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 
 	mlog_entry_void();
 
-	BUG_ON(!passed_handle);
 	BUG_ON(!ac);
-	BUG_ON(passed_handle->flags & OCFS2_HANDLE_STARTED);
 
 	local_alloc_inode =
 		ocfs2_get_system_file_inode(osb,
@@ -476,7 +468,11 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 		mlog_errno(status);
 		goto bail;
 	}
-	ocfs2_handle_add_inode(passed_handle, local_alloc_inode);
+
+	mutex_lock(&local_alloc_inode->i_mutex);
+
+	ac->ac_inode = local_alloc_inode;
+	ac->ac_which = OCFS2_AC_USE_LOCAL;
 
 	if (osb->local_alloc_state != OCFS2_LA_ENABLED) {
 		status = -ENOSPC;
@@ -515,21 +511,17 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 		}
 	}
 
-	ac->ac_inode = igrab(local_alloc_inode);
 	get_bh(osb->local_alloc_bh);
 	ac->ac_bh = osb->local_alloc_bh;
-	ac->ac_which = OCFS2_AC_USE_LOCAL;
 	status = 0;
 bail:
-	if (local_alloc_inode)
-		iput(local_alloc_inode);
 
 	mlog_exit(status);
 	return status;
 }
 
 int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
-				 struct ocfs2_journal_handle *handle,
+				 handle_t *handle,
 				 struct ocfs2_alloc_context *ac,
 				 u32 min_bits,
 				 u32 *bit_off,
@@ -707,7 +699,7 @@ static void ocfs2_verify_zero_bits(unsigned long *bitmap,
  * passed is used for caching.
  */
 static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
-				    struct ocfs2_journal_handle *handle,
+				    handle_t *handle,
 				    struct ocfs2_dinode *alloc,
 				    struct inode *main_bm_inode,
 				    struct buffer_head *main_bm_bh)
@@ -778,7 +770,6 @@ bail:
 }
 
 static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb,
-						struct ocfs2_journal_handle *handle,
 						struct ocfs2_alloc_context **ac,
 						struct inode **bitmap_inode,
 						struct buffer_head **bitmap_bh)
@@ -792,7 +783,6 @@ static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb,
 		goto bail;
 	}
 
-	(*ac)->ac_handle = handle;
 	(*ac)->ac_bits_wanted = ocfs2_local_alloc_window_bits(osb);
 
 	status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac);
@@ -821,7 +811,7 @@ bail:
  * pass it the bitmap lock in lock_bh if you have it.
  */
 static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
-					struct ocfs2_journal_handle *handle,
+					handle_t *handle,
 					struct ocfs2_alloc_context *ac)
 {
 	int status = 0;
@@ -888,23 +878,15 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
 	int status = 0;
 	struct buffer_head *main_bm_bh = NULL;
 	struct inode *main_bm_inode = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_dinode *alloc;
 	struct ocfs2_dinode *alloc_copy = NULL;
 	struct ocfs2_alloc_context *ac = NULL;
 
 	mlog_entry_void();
 
-	handle = ocfs2_alloc_handle(osb);
-	if (!handle) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	/* This will lock the main bitmap for us. */
 	status = ocfs2_local_alloc_reserve_for_window(osb,
-						      handle,
 						      &ac,
 						      &main_bm_inode,
 						      &main_bm_bh);
@@ -914,7 +896,7 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
 		goto bail;
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_WINDOW_MOVE_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -972,7 +954,7 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
 	status = 0;
 bail:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 
 	if (main_bm_bh)
 		brelse(main_bm_bh);
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index 30f88ce14e46..385a10152f9c 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -42,12 +42,11 @@ int ocfs2_alloc_should_use_local(struct ocfs2_super *osb,
 
 struct ocfs2_alloc_context;
 int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
-				   struct ocfs2_journal_handle *passed_handle,
 				   u32 bits_wanted,
 				   struct ocfs2_alloc_context *ac);
 
 int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
-				 struct ocfs2_journal_handle *handle,
+				 handle_t *handle,
 				 struct ocfs2_alloc_context *ac,
 				 u32 min_bits,
 				 u32 *bit_off,
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 83934e33e5b0..69f85ae392dc 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -82,6 +82,8 @@ static struct vm_operations_struct ocfs2_file_vm_ops = {
 
 int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	int ret = 0, lock_level = 0;
+
 	/* We don't want to support shared writable mappings yet. */
 	if (((vma->vm_flags & VM_SHARED) || (vma->vm_flags & VM_MAYSHARE))
 	    && ((vma->vm_flags & VM_WRITE) || (vma->vm_flags & VM_MAYWRITE))) {
@@ -91,7 +93,14 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 
-	file_accessed(file);
+	ret = ocfs2_meta_lock_atime(file->f_dentry->d_inode,
+				    file->f_vfsmnt, &lock_level);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+	ocfs2_meta_unlock(file->f_dentry->d_inode, lock_level);
+out:
 	vma->vm_ops = &ocfs2_file_vm_ops;
 	return 0;
 }
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index a57b751d4f40..21db45ddf144 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -75,12 +75,12 @@ static int inline ocfs2_search_dirblock(struct buffer_head *bh,
 					unsigned long offset,
 					struct ocfs2_dir_entry **res_dir);
 
-static int ocfs2_delete_entry(struct ocfs2_journal_handle *handle,
+static int ocfs2_delete_entry(handle_t *handle,
 			      struct inode *dir,
 			      struct ocfs2_dir_entry *de_del,
 			      struct buffer_head *bh);
 
-static int __ocfs2_add_entry(struct ocfs2_journal_handle *handle,
+static int __ocfs2_add_entry(handle_t *handle,
 			     struct inode *dir,
 			     const char *name, int namelen,
 			     struct inode *inode, u64 blkno,
@@ -93,43 +93,37 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 			      dev_t dev,
 			      struct buffer_head **new_fe_bh,
 			      struct buffer_head *parent_fe_bh,
-			      struct ocfs2_journal_handle *handle,
+			      handle_t *handle,
 			      struct inode **ret_inode,
 			      struct ocfs2_alloc_context *inode_ac);
 
 static int ocfs2_fill_new_dir(struct ocfs2_super *osb,
-			      struct ocfs2_journal_handle *handle,
+			      handle_t *handle,
 			      struct inode *parent,
 			      struct inode *inode,
 			      struct buffer_head *fe_bh,
 			      struct ocfs2_alloc_context *data_ac);
 
-static int ocfs2_double_lock(struct ocfs2_super *osb,
-			     struct ocfs2_journal_handle *handle,
-			     struct buffer_head **bh1,
-			     struct inode *inode1,
-			     struct buffer_head **bh2,
-			     struct inode *inode2);
-
 static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
-				    struct ocfs2_journal_handle *handle,
+				    struct inode **ret_orphan_dir,
 				    struct inode *inode,
 				    char *name,
 				    struct buffer_head **de_bh);
 
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
-			    struct ocfs2_journal_handle *handle,
+			    handle_t *handle,
 			    struct inode *inode,
 			    struct ocfs2_dinode *fe,
 			    char *name,
-			    struct buffer_head *de_bh);
+			    struct buffer_head *de_bh,
+			    struct inode *orphan_dir_inode);
 
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
-				     struct ocfs2_journal_handle *handle,
+				     handle_t *handle,
 				     struct inode *inode,
 				     const char *symname);
 
-static inline int ocfs2_add_entry(struct ocfs2_journal_handle *handle,
+static inline int ocfs2_add_entry(handle_t *handle,
 				  struct dentry *dentry,
 				  struct inode *inode, u64 blkno,
 				  struct buffer_head *parent_fe_bh,
@@ -165,7 +159,7 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 	mlog(0, "find name %.*s in directory %llu\n", dentry->d_name.len,
 	     dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno);
 
-	status = ocfs2_meta_lock(dir, NULL, NULL, 0);
+	status = ocfs2_meta_lock(dir, NULL, 0);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -242,7 +236,7 @@ bail:
 }
 
 static int ocfs2_fill_new_dir(struct ocfs2_super *osb,
-			      struct ocfs2_journal_handle *handle,
+			      handle_t *handle,
 			      struct inode *parent,
 			      struct inode *inode,
 			      struct buffer_head *fe_bh,
@@ -317,7 +311,7 @@ static int ocfs2_mknod(struct inode *dir,
 {
 	int status = 0;
 	struct buffer_head *parent_fe_bh = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_super *osb;
 	struct ocfs2_dinode *dirfe;
 	struct buffer_head *new_fe_bh = NULL;
@@ -333,18 +327,11 @@ static int ocfs2_mknod(struct inode *dir,
 	/* get our super block */
 	osb = OCFS2_SB(dir->i_sb);
 
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto leave;
-	}
-
-	status = ocfs2_meta_lock(dir, handle, &parent_fe_bh, 1);
+	status = ocfs2_meta_lock(dir, &parent_fe_bh, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
-		goto leave;
+		return status;
 	}
 
 	if (S_ISDIR(mode) && (dir->i_nlink >= OCFS2_LINK_MAX)) {
@@ -374,7 +361,7 @@ static int ocfs2_mknod(struct inode *dir,
 	}
 
 	/* reserve an inode spot */
-	status = ocfs2_reserve_new_inode(osb, handle, &inode_ac);
+	status = ocfs2_reserve_new_inode(osb, &inode_ac);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -384,7 +371,7 @@ static int ocfs2_mknod(struct inode *dir,
 	/* are we making a directory? If so, reserve a cluster for his
 	 * 1st extent. */
 	if (S_ISDIR(mode)) {
-		status = ocfs2_reserve_clusters(osb, handle, 1, &data_ac);
+		status = ocfs2_reserve_clusters(osb, 1, &data_ac);
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
@@ -392,7 +379,7 @@ static int ocfs2_mknod(struct inode *dir,
 		}
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_MKNOD_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_MKNOD_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -453,7 +440,9 @@ static int ocfs2_mknod(struct inode *dir,
 	status = 0;
 leave:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
+
+	ocfs2_meta_unlock(dir, 1);
 
 	if (status == -ENOSPC)
 		mlog(0, "Disk is full\n");
@@ -487,7 +476,7 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 			      dev_t dev,
 			      struct buffer_head **new_fe_bh,
 			      struct buffer_head *parent_fe_bh,
-			      struct ocfs2_journal_handle *handle,
+			      handle_t *handle,
 			      struct inode **ret_inode,
 			      struct ocfs2_alloc_context *inode_ac)
 {
@@ -653,7 +642,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 		      struct inode *dir,
 		      struct dentry *dentry)
 {
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle;
 	struct inode *inode = old_dentry->d_inode;
 	int err;
 	struct buffer_head *fe_bh = NULL;
@@ -666,68 +655,60 @@ static int ocfs2_link(struct dentry *old_dentry,
 		   old_dentry->d_name.len, old_dentry->d_name.name,
 		   dentry->d_name.len, dentry->d_name.name);
 
-	if (S_ISDIR(inode->i_mode)) {
-		err = -EPERM;
-		goto bail;
-	}
-
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		err = -ENOMEM;
-		goto bail;
-	}
+	if (S_ISDIR(inode->i_mode))
+		return -EPERM;
 
-	err = ocfs2_meta_lock(dir, handle, &parent_fe_bh, 1);
+	err = ocfs2_meta_lock(dir, &parent_fe_bh, 1);
 	if (err < 0) {
 		if (err != -ENOENT)
 			mlog_errno(err);
-		goto bail;
+		return err;
 	}
 
 	if (!dir->i_nlink) {
 		err = -ENOENT;
-		goto bail;
+		goto out;
 	}
 
 	err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name,
 					dentry->d_name.len);
 	if (err)
-		goto bail;
+		goto out;
 
 	err = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh,
 					   dentry->d_name.name,
 					   dentry->d_name.len, &de_bh);
 	if (err < 0) {
 		mlog_errno(err);
-		goto bail;
+		goto out;
 	}
 
-	err = ocfs2_meta_lock(inode, handle, &fe_bh, 1);
+	err = ocfs2_meta_lock(inode, &fe_bh, 1);
 	if (err < 0) {
 		if (err != -ENOENT)
 			mlog_errno(err);
-		goto bail;
+		goto out;
 	}
 
 	fe = (struct ocfs2_dinode *) fe_bh->b_data;
 	if (le16_to_cpu(fe->i_links_count) >= OCFS2_LINK_MAX) {
 		err = -EMLINK;
-		goto bail;
+		goto out_unlock_inode;
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_LINK_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_LINK_CREDITS);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		handle = NULL;
 		mlog_errno(err);
-		goto bail;
+		goto out_unlock_inode;
 	}
 
 	err = ocfs2_journal_access(handle, inode, fe_bh,
 				   OCFS2_JOURNAL_ACCESS_WRITE);
 	if (err < 0) {
 		mlog_errno(err);
-		goto bail;
+		goto out_commit;
 	}
 
 	inc_nlink(inode);
@@ -741,7 +722,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 		le16_add_cpu(&fe->i_links_count, -1);
 		drop_nlink(inode);
 		mlog_errno(err);
-		goto bail;
+		goto out_commit;
 	}
 
 	err = ocfs2_add_entry(handle, dentry, inode,
@@ -751,21 +732,27 @@ static int ocfs2_link(struct dentry *old_dentry,
 		le16_add_cpu(&fe->i_links_count, -1);
 		drop_nlink(inode);
 		mlog_errno(err);
-		goto bail;
+		goto out_commit;
 	}
 
 	err = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno);
 	if (err) {
 		mlog_errno(err);
-		goto bail;
+		goto out_commit;
 	}
 
 	atomic_inc(&inode->i_count);
 	dentry->d_op = &ocfs2_dentry_ops;
 	d_instantiate(dentry, inode);
-bail:
-	if (handle)
-		ocfs2_commit_trans(handle);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+out_unlock_inode:
+	ocfs2_meta_unlock(inode, 1);
+
+out:
+	ocfs2_meta_unlock(dir, 1);
+
 	if (de_bh)
 		brelse(de_bh);
 	if (fe_bh)
@@ -812,13 +799,15 @@ static int ocfs2_unlink(struct inode *dir,
 			struct dentry *dentry)
 {
 	int status;
+	int child_locked = 0;
 	struct inode *inode = dentry->d_inode;
+	struct inode *orphan_dir = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
 	u64 blkno;
 	struct ocfs2_dinode *fe = NULL;
 	struct buffer_head *fe_bh = NULL;
 	struct buffer_head *parent_node_bh = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_dir_entry *dirent = NULL;
 	struct buffer_head *dirent_bh = NULL;
 	char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
@@ -833,22 +822,14 @@ static int ocfs2_unlink(struct inode *dir,
 
 	if (inode == osb->root_inode) {
 		mlog(0, "Cannot delete the root directory\n");
-		status = -EPERM;
-		goto leave;
+		return -EPERM;
 	}
 
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto leave;
-	}
-
-	status = ocfs2_meta_lock(dir, handle, &parent_node_bh, 1);
+	status = ocfs2_meta_lock(dir, &parent_node_bh, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
-		goto leave;
+		return status;
 	}
 
 	status = ocfs2_find_files_on_disk(dentry->d_name.name,
@@ -869,12 +850,13 @@ static int ocfs2_unlink(struct inode *dir,
 		goto leave;
 	}
 
-	status = ocfs2_meta_lock(inode, handle, &fe_bh, 1);
+	status = ocfs2_meta_lock(inode, &fe_bh, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
 		goto leave;
 	}
+	child_locked = 1;
 
 	if (S_ISDIR(inode->i_mode)) {
 	       	if (!ocfs2_empty_dir(inode)) {
@@ -895,7 +877,7 @@ static int ocfs2_unlink(struct inode *dir,
 	}
 
 	if (inode_is_unlinkable(inode)) {
-		status = ocfs2_prepare_orphan_dir(osb, handle, inode,
+		status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, inode,
 						  orphan_name,
 						  &orphan_entry_bh);
 		if (status < 0) {
@@ -904,7 +886,7 @@ static int ocfs2_unlink(struct inode *dir,
 		}
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_UNLINK_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_UNLINK_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -923,7 +905,7 @@ static int ocfs2_unlink(struct inode *dir,
 
 	if (inode_is_unlinkable(inode)) {
 		status = ocfs2_orphan_add(osb, handle, inode, fe, orphan_name,
-					  orphan_entry_bh);
+					  orphan_entry_bh, orphan_dir);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -960,7 +942,19 @@ static int ocfs2_unlink(struct inode *dir,
 
 leave:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
+
+	if (child_locked)
+		ocfs2_meta_unlock(inode, 1);
+
+	ocfs2_meta_unlock(dir, 1);
+
+	if (orphan_dir) {
+		/* This was locked for us in ocfs2_prepare_orphan_dir() */
+		ocfs2_meta_unlock(orphan_dir, 1);
+		mutex_unlock(&orphan_dir->i_mutex);
+		iput(orphan_dir);
+	}
 
 	if (fe_bh)
 		brelse(fe_bh);
@@ -984,7 +978,6 @@ leave:
  * if they have the same id, then the 1st one is the only one locked.
  */
 static int ocfs2_double_lock(struct ocfs2_super *osb,
-			     struct ocfs2_journal_handle *handle,
 			     struct buffer_head **bh1,
 			     struct inode *inode1,
 			     struct buffer_head **bh2,
@@ -1000,8 +993,6 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 		   (unsigned long long)oi1->ip_blkno,
 		   (unsigned long long)oi2->ip_blkno);
 
-	BUG_ON(!handle);
-
 	if (*bh1)
 		*bh1 = NULL;
 	if (*bh2)
@@ -1021,25 +1012,41 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 			inode1 = tmpinode;
 		}
 		/* lock id2 */
-		status = ocfs2_meta_lock(inode2, handle, bh2, 1);
+		status = ocfs2_meta_lock(inode2, bh2, 1);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
 			goto bail;
 		}
 	}
+
 	/* lock id1 */
-	status = ocfs2_meta_lock(inode1, handle, bh1, 1);
+	status = ocfs2_meta_lock(inode1, bh1, 1);
 	if (status < 0) {
+		/*
+		 * An error return must mean that no cluster locks
+		 * were held on function exit.
+		 */
+		if (oi1->ip_blkno != oi2->ip_blkno)
+			ocfs2_meta_unlock(inode2, 1);
+
 		if (status != -ENOENT)
 			mlog_errno(status);
-		goto bail;
 	}
+
 bail:
 	mlog_exit(status);
 	return status;
 }
 
+static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2)
+{
+	ocfs2_meta_unlock(inode1, 1);
+
+	if (inode1 != inode2)
+		ocfs2_meta_unlock(inode2, 1);
+}
+
 #define PARENT_INO(buffer) \
 	((struct ocfs2_dir_entry *) \
 	 ((char *)buffer + \
@@ -1050,9 +1057,11 @@ static int ocfs2_rename(struct inode *old_dir,
 			struct inode *new_dir,
 			struct dentry *new_dentry)
 {
-	int status = 0, rename_lock = 0;
+	int status = 0, rename_lock = 0, parents_locked = 0;
+	int old_child_locked = 0, new_child_locked = 0;
 	struct inode *old_inode = old_dentry->d_inode;
 	struct inode *new_inode = new_dentry->d_inode;
+	struct inode *orphan_dir = NULL;
 	struct ocfs2_dinode *newfe = NULL;
 	char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
 	struct buffer_head *orphan_entry_bh = NULL;
@@ -1060,7 +1069,7 @@ static int ocfs2_rename(struct inode *old_dir,
 	struct buffer_head *insert_entry_bh = NULL;
 	struct ocfs2_super *osb = NULL;
 	u64 newfe_blkno;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct buffer_head *old_dir_bh = NULL;
 	struct buffer_head *new_dir_bh = NULL;
 	struct ocfs2_dir_entry *old_de = NULL, *new_de = NULL; // dirent for old_dentry
@@ -1105,21 +1114,14 @@ static int ocfs2_rename(struct inode *old_dir,
 		rename_lock = 1;
 	}
 
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	/* if old and new are the same, this'll just do one lock. */
-	status = ocfs2_double_lock(osb, handle,
-				  &old_dir_bh, old_dir,
-				  &new_dir_bh, new_dir);
+	status = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
+				   &new_dir_bh, new_dir);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
 	}
+	parents_locked = 1;
 
 	/* make sure both dirs have bhs
 	 * get an extra ref on old_dir_bh if old==new */
@@ -1140,12 +1142,13 @@ static int ocfs2_rename(struct inode *old_dir,
 	 * the vote thread on other nodes won't have to concurrently
 	 * downconvert the inode and the dentry locks.
 	 */
-	status = ocfs2_meta_lock(old_inode, handle, NULL, 1);
+	status = ocfs2_meta_lock(old_inode, NULL, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
 		goto bail;
 	}
+	old_child_locked = 1;
 
 	status = ocfs2_remote_dentry_delete(old_dentry);
 	if (status < 0) {
@@ -1231,12 +1234,13 @@ static int ocfs2_rename(struct inode *old_dir,
 			goto bail;
 		}
 
-		status = ocfs2_meta_lock(new_inode, handle, &newfe_bh, 1);
+		status = ocfs2_meta_lock(new_inode, &newfe_bh, 1);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
 			goto bail;
 		}
+		new_child_locked = 1;
 
 		status = ocfs2_remote_dentry_delete(new_dentry);
 		if (status < 0) {
@@ -1252,7 +1256,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		     (unsigned long long)newfe_bh->b_blocknr : 0ULL);
 
 		if (S_ISDIR(new_inode->i_mode) || (new_inode->i_nlink == 1)) {
-			status = ocfs2_prepare_orphan_dir(osb, handle,
+			status = ocfs2_prepare_orphan_dir(osb, &orphan_dir,
 							  new_inode,
 							  orphan_name,
 							  &orphan_entry_bh);
@@ -1280,7 +1284,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		}
 	}
 
-	handle = ocfs2_start_trans(osb, handle, OCFS2_RENAME_CREDITS);
+	handle = ocfs2_start_trans(osb, OCFS2_RENAME_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -1307,7 +1311,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		    (newfe->i_links_count == cpu_to_le16(1))){
 			status = ocfs2_orphan_add(osb, handle, new_inode,
 						  newfe, orphan_name,
-						  orphan_entry_bh);
+						  orphan_entry_bh, orphan_dir);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -1424,7 +1428,23 @@ bail:
 		ocfs2_rename_unlock(osb);
 
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
+
+	if (parents_locked)
+		ocfs2_double_unlock(old_dir, new_dir);
+
+	if (old_child_locked)
+		ocfs2_meta_unlock(old_inode, 1);
+
+	if (new_child_locked)
+		ocfs2_meta_unlock(new_inode, 1);
+
+	if (orphan_dir) {
+		/* This was locked for us in ocfs2_prepare_orphan_dir() */
+		ocfs2_meta_unlock(orphan_dir, 1);
+		mutex_unlock(&orphan_dir->i_mutex);
+		iput(orphan_dir);
+	}
 
 	if (new_inode)
 		sync_mapping_buffers(old_inode->i_mapping);
@@ -1458,7 +1478,7 @@ bail:
  * data, including the null terminator.
  */
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
-				     struct ocfs2_journal_handle *handle,
+				     handle_t *handle,
 				     struct inode *inode,
 				     const char *symname)
 {
@@ -1573,7 +1593,7 @@ static int ocfs2_symlink(struct inode *dir,
 	struct buffer_head *parent_fe_bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_dinode *dirfe;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	struct ocfs2_alloc_context *inode_ac = NULL;
 	struct ocfs2_alloc_context *data_ac = NULL;
 
@@ -1587,19 +1607,12 @@ static int ocfs2_symlink(struct inode *dir,
 
 	credits = ocfs2_calc_symlink_credits(sb);
 
-	handle = ocfs2_alloc_handle(osb);
-	if (handle == NULL) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	/* lock the parent directory */
-	status = ocfs2_meta_lock(dir, handle, &parent_fe_bh, 1);
+	status = ocfs2_meta_lock(dir, &parent_fe_bh, 1);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
-		goto bail;
+		return status;
 	}
 
 	dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
@@ -1622,7 +1635,7 @@ static int ocfs2_symlink(struct inode *dir,
 		goto bail;
 	}
 
-	status = ocfs2_reserve_new_inode(osb, handle, &inode_ac);
+	status = ocfs2_reserve_new_inode(osb, &inode_ac);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -1631,7 +1644,7 @@ static int ocfs2_symlink(struct inode *dir,
 
 	/* don't reserve bitmap space for fast symlinks. */
 	if (l > ocfs2_fast_symlink_chars(sb)) {
-		status = ocfs2_reserve_clusters(osb, handle, 1, &data_ac);
+		status = ocfs2_reserve_clusters(osb, 1, &data_ac);
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
@@ -1639,7 +1652,7 @@ static int ocfs2_symlink(struct inode *dir,
 		}
 	}
 
-	handle = ocfs2_start_trans(osb, handle, credits);
+	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -1717,7 +1730,10 @@ static int ocfs2_symlink(struct inode *dir,
 	d_instantiate(dentry, inode);
 bail:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
+
+	ocfs2_meta_unlock(dir, 1);
+
 	if (new_fe_bh)
 		brelse(new_fe_bh);
 	if (parent_fe_bh)
@@ -1768,7 +1784,7 @@ int ocfs2_check_dir_entry(struct inode * dir,
  * If you pass me insert_bh, I'll skip the search of the other dir
  * blocks and put the record in there.
  */
-static int __ocfs2_add_entry(struct ocfs2_journal_handle *handle,
+static int __ocfs2_add_entry(handle_t *handle,
 			     struct inode *dir,
 			     const char *name, int namelen,
 			     struct inode *inode, u64 blkno,
@@ -1854,7 +1870,7 @@ bail:
  * ocfs2_delete_entry deletes a directory entry by merging it with the
  * previous entry
  */
-static int ocfs2_delete_entry(struct ocfs2_journal_handle *handle,
+static int ocfs2_delete_entry(handle_t *handle,
 			      struct inode *dir,
 			      struct ocfs2_dir_entry *de_del,
 			      struct buffer_head *bh)
@@ -2085,19 +2101,19 @@ bail:
 }
 
 static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
-				    struct ocfs2_journal_handle *handle,
+				    struct inode **ret_orphan_dir,
 				    struct inode *inode,
 				    char *name,
 				    struct buffer_head **de_bh)
 {
-	struct inode *orphan_dir_inode = NULL;
+	struct inode *orphan_dir_inode;
 	struct buffer_head *orphan_dir_bh = NULL;
 	int status = 0;
 
 	status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name);
 	if (status < 0) {
 		mlog_errno(status);
-		goto leave;
+		return status;
 	}
 
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
@@ -2106,11 +2122,12 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 	if (!orphan_dir_inode) {
 		status = -ENOENT;
 		mlog_errno(status);
-		goto leave;
+		return status;
 	}
 
-	ocfs2_handle_add_inode(handle, orphan_dir_inode);
-	status = ocfs2_meta_lock(orphan_dir_inode, handle, &orphan_dir_bh, 1);
+	mutex_lock(&orphan_dir_inode->i_mutex);
+
+	status = ocfs2_meta_lock(orphan_dir_inode, &orphan_dir_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -2120,13 +2137,19 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 					      orphan_dir_bh, name,
 					      OCFS2_ORPHAN_NAMELEN, de_bh);
 	if (status < 0) {
+		ocfs2_meta_unlock(orphan_dir_inode, 1);
+
 		mlog_errno(status);
 		goto leave;
 	}
 
+	*ret_orphan_dir = orphan_dir_inode;
+
 leave:
-	if (orphan_dir_inode)
+	if (status) {
+		mutex_unlock(&orphan_dir_inode->i_mutex);
 		iput(orphan_dir_inode);
+	}
 
 	if (orphan_dir_bh)
 		brelse(orphan_dir_bh);
@@ -2136,28 +2159,19 @@ leave:
 }
 
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
-			    struct ocfs2_journal_handle *handle,
+			    handle_t *handle,
 			    struct inode *inode,
 			    struct ocfs2_dinode *fe,
 			    char *name,
-			    struct buffer_head *de_bh)
+			    struct buffer_head *de_bh,
+			    struct inode *orphan_dir_inode)
 {
-	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
 	int status = 0;
 	struct ocfs2_dinode *orphan_fe;
 
 	mlog_entry("(inode->i_ino = %lu)\n", inode->i_ino);
 
-	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
-						       ORPHAN_DIR_SYSTEM_INODE,
-						       osb->slot_num);
-	if (!orphan_dir_inode) {
-		status = -ENOENT;
-		mlog_errno(status);
-		goto leave;
-	}
-
 	status = ocfs2_read_block(osb,
 				  OCFS2_I(orphan_dir_inode)->ip_blkno,
 				  &orphan_dir_bh, OCFS2_BH_CACHED,
@@ -2209,9 +2223,6 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno, osb->slot_num);
 
 leave:
-	if (orphan_dir_inode)
-		iput(orphan_dir_inode);
-
 	if (orphan_dir_bh)
 		brelse(orphan_dir_bh);
 
@@ -2221,7 +2232,7 @@ leave:
 
 /* unlike orphan_add, we expect the orphan dir to already be locked here. */
 int ocfs2_orphan_del(struct ocfs2_super *osb,
-		     struct ocfs2_journal_handle *handle,
+		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
 		     struct buffer_head *orphan_dir_bh)
@@ -2300,4 +2311,5 @@ struct inode_operations ocfs2_dir_iops = {
 	.rename		= ocfs2_rename,
 	.setattr	= ocfs2_setattr,
 	.getattr	= ocfs2_getattr,
+	.permission	= ocfs2_permission,
 };
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index deaaa97dbf0b..8425944fcccd 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -39,7 +39,7 @@ struct buffer_head *ocfs2_find_entry(const char *name,
 				     struct inode *dir,
 				     struct ocfs2_dir_entry **res_dir);
 int ocfs2_orphan_del(struct ocfs2_super *osb,
-		     struct ocfs2_journal_handle *handle,
+		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
 		     struct buffer_head *orphan_dir_bh);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 9b1bad1d48ec..b767fd7da6eb 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -34,6 +34,7 @@
 #include <linux/workqueue.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
+#include <linux/jbd.h>
 
 #include "cluster/nodemanager.h"
 #include "cluster/heartbeat.h"
@@ -179,9 +180,9 @@ enum ocfs2_mount_options
 #define OCFS2_OSB_SOFT_RO	0x0001
 #define OCFS2_OSB_HARD_RO	0x0002
 #define OCFS2_OSB_ERROR_FS	0x0004
+#define OCFS2_DEFAULT_ATIME_QUANTUM	60
 
 struct ocfs2_journal;
-struct ocfs2_journal_handle;
 struct ocfs2_super
 {
 	struct task_struct *commit_task;
@@ -218,6 +219,7 @@ struct ocfs2_super
 	unsigned long osb_flags;
 
 	unsigned long s_mount_opt;
+	unsigned int s_atime_quantum;
 
 	u16 max_slots;
 	s16 node_num;
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 9d91e66f51a9..000d71cca6c5 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -49,7 +49,7 @@
 static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
 static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
 static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
-static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle,
+static int ocfs2_block_group_fill(handle_t *handle,
 				  struct inode *alloc_inode,
 				  struct buffer_head *bg_bh,
 				  u64 group_blkno,
@@ -59,9 +59,6 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 				   struct inode *alloc_inode,
 				   struct buffer_head *bh);
 
-static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
-				       struct ocfs2_alloc_context *ac);
-
 static int ocfs2_cluster_group_search(struct inode *inode,
 				      struct buffer_head *group_bh,
 				      u32 bits_wanted, u32 min_bits,
@@ -72,6 +69,7 @@ static int ocfs2_block_group_search(struct inode *inode,
 				    u16 *bit_off, u16 *bits_found);
 static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 				     struct ocfs2_alloc_context *ac,
+				     handle_t *handle,
 				     u32 bits_wanted,
 				     u32 min_bits,
 				     u16 *bit_off,
@@ -79,20 +77,20 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 				     u64 *bg_blkno);
 static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 					 int nr);
-static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle,
+static inline int ocfs2_block_group_set_bits(handle_t *handle,
 					     struct inode *alloc_inode,
 					     struct ocfs2_group_desc *bg,
 					     struct buffer_head *group_bh,
 					     unsigned int bit_off,
 					     unsigned int num_bits);
-static inline int ocfs2_block_group_clear_bits(struct ocfs2_journal_handle *handle,
+static inline int ocfs2_block_group_clear_bits(handle_t *handle,
 					       struct inode *alloc_inode,
 					       struct ocfs2_group_desc *bg,
 					       struct buffer_head *group_bh,
 					       unsigned int bit_off,
 					       unsigned int num_bits);
 
-static int ocfs2_relink_block_group(struct ocfs2_journal_handle *handle,
+static int ocfs2_relink_block_group(handle_t *handle,
 				    struct inode *alloc_inode,
 				    struct buffer_head *fe_bh,
 				    struct buffer_head *bg_bh,
@@ -100,7 +98,7 @@ static int ocfs2_relink_block_group(struct ocfs2_journal_handle *handle,
 				    u16 chain);
 static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg,
 						     u32 wanted);
-static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle,
+static int ocfs2_free_suballoc_bits(handle_t *handle,
 				    struct inode *alloc_inode,
 				    struct buffer_head *alloc_bh,
 				    unsigned int start_bit,
@@ -120,8 +118,16 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode,
 
 void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
 {
-	if (ac->ac_inode)
-		iput(ac->ac_inode);
+	struct inode *inode = ac->ac_inode;
+
+	if (inode) {
+		if (ac->ac_which != OCFS2_AC_USE_LOCAL)
+			ocfs2_meta_unlock(inode, 1);
+
+		mutex_unlock(&inode->i_mutex);
+
+		iput(inode);
+	}
 	if (ac->ac_bh)
 		brelse(ac->ac_bh);
 	kfree(ac);
@@ -190,7 +196,7 @@ static int ocfs2_check_group_descriptor(struct super_block *sb,
 	return 0;
 }
 
-static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle,
+static int ocfs2_block_group_fill(handle_t *handle,
 				  struct inode *alloc_inode,
 				  struct buffer_head *bg_bh,
 				  u64 group_blkno,
@@ -273,7 +279,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) bh->b_data;
 	struct ocfs2_chain_list *cl;
 	struct ocfs2_alloc_context *ac = NULL;
-	struct ocfs2_journal_handle *handle = NULL;
+	handle_t *handle = NULL;
 	u32 bit_off, num_bits;
 	u16 alloc_rec;
 	u64 bg_blkno;
@@ -284,16 +290,8 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	mlog_entry_void();
 
-	handle = ocfs2_alloc_handle(osb);
-	if (!handle) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
 	cl = &fe->id2.i_chain;
 	status = ocfs2_reserve_clusters(osb,
-					handle,
 					le16_to_cpu(cl->cl_cpg),
 					&ac);
 	if (status < 0) {
@@ -304,7 +302,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	credits = ocfs2_calc_group_alloc_credits(osb->sb,
 						 le16_to_cpu(cl->cl_cpg));
-	handle = ocfs2_start_trans(osb, handle, credits);
+	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -389,7 +387,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 	status = 0;
 bail:
 	if (handle)
-		ocfs2_commit_trans(handle);
+		ocfs2_commit_trans(osb, handle);
 
 	if (ac)
 		ocfs2_free_alloc_context(ac);
@@ -402,27 +400,38 @@ bail:
 }
 
 static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
-				       struct ocfs2_alloc_context *ac)
+				       struct ocfs2_alloc_context *ac,
+				       int type,
+				       u32 slot)
 {
 	int status;
 	u32 bits_wanted = ac->ac_bits_wanted;
-	struct inode *alloc_inode = ac->ac_inode;
+	struct inode *alloc_inode;
 	struct buffer_head *bh = NULL;
-	struct ocfs2_journal_handle *handle = ac->ac_handle;
 	struct ocfs2_dinode *fe;
 	u32 free_bits;
 
 	mlog_entry_void();
 
-	BUG_ON(handle->flags & OCFS2_HANDLE_STARTED);
+	alloc_inode = ocfs2_get_system_file_inode(osb, type, slot);
+	if (!alloc_inode) {
+		mlog_errno(-EINVAL);
+		return -EINVAL;
+	}
 
-	ocfs2_handle_add_inode(handle, alloc_inode);
-	status = ocfs2_meta_lock(alloc_inode, handle, &bh, 1);
+	mutex_lock(&alloc_inode->i_mutex);
+
+	status = ocfs2_meta_lock(alloc_inode, &bh, 1);
 	if (status < 0) {
+		mutex_unlock(&alloc_inode->i_mutex);
+		iput(alloc_inode);
+
 		mlog_errno(status);
-		goto bail;
+		return status;
 	}
 
+	ac->ac_inode = alloc_inode;
+
 	fe = (struct ocfs2_dinode *) bh->b_data;
 	if (!OCFS2_IS_VALID_DINODE(fe)) {
 		OCFS2_RO_ON_INVALID_DINODE(alloc_inode->i_sb, fe);
@@ -473,12 +482,11 @@ bail:
 }
 
 int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
-			       struct ocfs2_journal_handle *handle,
 			       struct ocfs2_dinode *fe,
 			       struct ocfs2_alloc_context **ac)
 {
 	int status;
-	struct inode *alloc_inode = NULL;
+	u32 slot;
 
 	*ac = kcalloc(1, sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
 	if (!(*ac)) {
@@ -488,28 +496,18 @@ int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
 	}
 
 	(*ac)->ac_bits_wanted = ocfs2_extend_meta_needed(fe);
-	(*ac)->ac_handle = handle;
 	(*ac)->ac_which = OCFS2_AC_USE_META;
 
 #ifndef OCFS2_USE_ALL_METADATA_SUBALLOCATORS
-	alloc_inode = ocfs2_get_system_file_inode(osb,
-						  EXTENT_ALLOC_SYSTEM_INODE,
-						  0);
+	slot = 0;
 #else
-	alloc_inode = ocfs2_get_system_file_inode(osb,
-						  EXTENT_ALLOC_SYSTEM_INODE,
-						  osb->slot_num);
+	slot = osb->slot_num;
 #endif
-	if (!alloc_inode) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
 
-	(*ac)->ac_inode = igrab(alloc_inode);
 	(*ac)->ac_group_search = ocfs2_block_group_search;
 
-	status = ocfs2_reserve_suballoc_bits(osb, (*ac));
+	status = ocfs2_reserve_suballoc_bits(osb, (*ac),
+					     EXTENT_ALLOC_SYSTEM_INODE, slot);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -523,19 +521,14 @@ bail:
 		*ac = NULL;
 	}
 
-	if (alloc_inode)
-		iput(alloc_inode);
-
 	mlog_exit(status);
 	return status;
 }
 
 int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
-			    struct ocfs2_journal_handle *handle,
 			    struct ocfs2_alloc_context **ac)
 {
 	int status;
-	struct inode *alloc_inode = NULL;
 
 	*ac = kcalloc(1, sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
 	if (!(*ac)) {
@@ -545,22 +538,13 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
 	}
 
 	(*ac)->ac_bits_wanted = 1;
-	(*ac)->ac_handle = handle;
 	(*ac)->ac_which = OCFS2_AC_USE_INODE;
 
-	alloc_inode = ocfs2_get_system_file_inode(osb,
-						  INODE_ALLOC_SYSTEM_INODE,
-						  osb->slot_num);
-	if (!alloc_inode) {
-		status = -ENOMEM;
-		mlog_errno(status);
-		goto bail;
-	}
-
-	(*ac)->ac_inode = igrab(alloc_inode);
 	(*ac)->ac_group_search = ocfs2_block_group_search;
 
-	status = ocfs2_reserve_suballoc_bits(osb, *ac);
+	status = ocfs2_reserve_suballoc_bits(osb, *ac,
+					     INODE_ALLOC_SYSTEM_INODE,
+					     osb->slot_num);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -574,9 +558,6 @@ bail:
 		*ac = NULL;
 	}
 
-	if (alloc_inode)
-		iput(alloc_inode);
-
 	mlog_exit(status);
 	return status;
 }
@@ -588,20 +569,17 @@ int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb,
 {
 	int status;
 
-	ac->ac_inode = ocfs2_get_system_file_inode(osb,
-						   GLOBAL_BITMAP_SYSTEM_INODE,
-						   OCFS2_INVALID_SLOT);
-	if (!ac->ac_inode) {
-		status = -EINVAL;
-		mlog(ML_ERROR, "Could not get bitmap inode!\n");
-		goto bail;
-	}
 	ac->ac_which = OCFS2_AC_USE_MAIN;
 	ac->ac_group_search = ocfs2_cluster_group_search;
 
-	status = ocfs2_reserve_suballoc_bits(osb, ac);
-	if (status < 0 && status != -ENOSPC)
+	status = ocfs2_reserve_suballoc_bits(osb, ac,
+					     GLOBAL_BITMAP_SYSTEM_INODE,
+					     OCFS2_INVALID_SLOT);
+	if (status < 0 && status != -ENOSPC) {
 		mlog_errno(status);
+		goto bail;
+	}
+
 bail:
 	return status;
 }
@@ -610,7 +588,6 @@ bail:
  * use so we figure it out for them, but unfortunately this clutters
  * things a bit. */
 int ocfs2_reserve_clusters(struct ocfs2_super *osb,
-			   struct ocfs2_journal_handle *handle,
 			   u32 bits_wanted,
 			   struct ocfs2_alloc_context **ac)
 {
@@ -618,8 +595,6 @@ int ocfs2_reserve_clusters(struct ocfs2_super *osb,
 
 	mlog_entry_void();
 
-	BUG_ON(!handle);
-
 	*ac = kcalloc(1, sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
 	if (!(*ac)) {
 		status = -ENOMEM;
@@ -628,12 +603,10 @@ int ocfs2_reserve_clusters(struct ocfs2_super *osb,
 	}
 
 	(*ac)->ac_bits_wanted = bits_wanted;
-	(*ac)->ac_handle = handle;
 
 	status = -ENOSPC;
 	if (ocfs2_alloc_should_use_local(osb, bits_wanted)) {
 		status = ocfs2_reserve_local_alloc_bits(osb,
-							handle,
 							bits_wanted,
 							*ac);
 		if ((status < 0) && (status != -ENOSPC)) {
@@ -774,7 +747,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 	return status;
 }
 
-static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle,
+static inline int ocfs2_block_group_set_bits(handle_t *handle,
 					     struct inode *alloc_inode,
 					     struct ocfs2_group_desc *bg,
 					     struct buffer_head *group_bh,
@@ -845,7 +818,7 @@ static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl)
 	return best;
 }
 
-static int ocfs2_relink_block_group(struct ocfs2_journal_handle *handle,
+static int ocfs2_relink_block_group(handle_t *handle,
 				    struct inode *alloc_inode,
 				    struct buffer_head *fe_bh,
 				    struct buffer_head *bg_bh,
@@ -1025,7 +998,7 @@ static int ocfs2_block_group_search(struct inode *inode,
 }
 
 static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
-				       struct ocfs2_journal_handle *handle,
+				       handle_t *handle,
 				       struct buffer_head *di_bh,
 				       u32 num_bits,
 				       u16 chain)
@@ -1055,6 +1028,7 @@ out:
 }
 
 static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
+				  handle_t *handle,
 				  u32 bits_wanted,
 				  u32 min_bits,
 				  u16 *bit_off,
@@ -1067,7 +1041,6 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
 	struct buffer_head *group_bh = NULL;
 	struct ocfs2_group_desc *gd;
 	struct inode *alloc_inode = ac->ac_inode;
-	struct ocfs2_journal_handle *handle = ac->ac_handle;
 
 	ret = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb), gd_blkno,
 			       &group_bh, OCFS2_BH_CACHED, alloc_inode);
@@ -1115,6 +1088,7 @@ out:
 }
 
 static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
+			      handle_t *handle,
 			      u32 bits_wanted,
 			      u32 min_bits,
 			      u16 *bit_off,
@@ -1126,7 +1100,6 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	u16 chain, tmp_bits;
 	u32 tmp_used;
 	u64 next_group;
-	struct ocfs2_journal_handle *handle = ac->ac_handle;
 	struct inode *alloc_inode = ac->ac_inode;
 	struct buffer_head *group_bh = NULL;
 	struct buffer_head *prev_group_bh = NULL;
@@ -1272,6 +1245,7 @@ bail:
 /* will give out up to bits_wanted contiguous bits. */
 static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 				     struct ocfs2_alloc_context *ac,
+				     handle_t *handle,
 				     u32 bits_wanted,
 				     u32 min_bits,
 				     u16 *bit_off,
@@ -1313,8 +1287,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 		 * by jumping straight to the most recently used
 		 * allocation group. This helps us mantain some
 		 * contiguousness across allocations. */
-		status = ocfs2_search_one_group(ac, bits_wanted, min_bits,
-						bit_off, num_bits,
+		status = ocfs2_search_one_group(ac, handle, bits_wanted,
+						min_bits, bit_off, num_bits,
 						hint_blkno, &bits_left);
 		if (!status) {
 			/* Be careful to update *bg_blkno here as the
@@ -1336,7 +1310,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 	ac->ac_chain = victim;
 	ac->ac_allow_chain_relink = 1;
 
-	status = ocfs2_search_chain(ac, bits_wanted, min_bits, bit_off,
+	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, bit_off,
 				    num_bits, bg_blkno, &bits_left);
 	if (!status)
 		goto set_hint;
@@ -1360,7 +1334,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
 			continue;
 
 		ac->ac_chain = i;
-		status = ocfs2_search_chain(ac, bits_wanted, min_bits,
+		status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 					    bit_off, num_bits, bg_blkno,
 					    &bits_left);
 		if (!status)
@@ -1388,7 +1362,7 @@ bail:
 }
 
 int ocfs2_claim_metadata(struct ocfs2_super *osb,
-			 struct ocfs2_journal_handle *handle,
+			 handle_t *handle,
 			 struct ocfs2_alloc_context *ac,
 			 u32 bits_wanted,
 			 u16 *suballoc_bit_start,
@@ -1401,10 +1375,10 @@ int ocfs2_claim_metadata(struct ocfs2_super *osb,
 	BUG_ON(!ac);
 	BUG_ON(ac->ac_bits_wanted < (ac->ac_bits_given + bits_wanted));
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_META);
-	BUG_ON(ac->ac_handle != handle);
 
 	status = ocfs2_claim_suballoc_bits(osb,
 					   ac,
+					   handle,
 					   bits_wanted,
 					   1,
 					   suballoc_bit_start,
@@ -1425,7 +1399,7 @@ bail:
 }
 
 int ocfs2_claim_new_inode(struct ocfs2_super *osb,
-			  struct ocfs2_journal_handle *handle,
+			  handle_t *handle,
 			  struct ocfs2_alloc_context *ac,
 			  u16 *suballoc_bit,
 			  u64 *fe_blkno)
@@ -1440,10 +1414,10 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 	BUG_ON(ac->ac_bits_given != 0);
 	BUG_ON(ac->ac_bits_wanted != 1);
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_INODE);
-	BUG_ON(ac->ac_handle != handle);
 
 	status = ocfs2_claim_suballoc_bits(osb,
 					   ac,
+					   handle,
 					   1,
 					   1,
 					   suballoc_bit,
@@ -1528,7 +1502,7 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode,
  * of any size.
  */
 int ocfs2_claim_clusters(struct ocfs2_super *osb,
-			 struct ocfs2_journal_handle *handle,
+			 handle_t *handle,
 			 struct ocfs2_alloc_context *ac,
 			 u32 min_clusters,
 			 u32 *cluster_start,
@@ -1546,7 +1520,6 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb,
 
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
 	       && ac->ac_which != OCFS2_AC_USE_MAIN);
-	BUG_ON(ac->ac_handle != handle);
 
 	if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
 		status = ocfs2_claim_local_alloc_bits(osb,
@@ -1572,6 +1545,7 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb,
 
 		status = ocfs2_claim_suballoc_bits(osb,
 						   ac,
+						   handle,
 						   bits_wanted,
 						   min_clusters,
 						   &bg_bit_off,
@@ -1598,7 +1572,7 @@ bail:
 	return status;
 }
 
-static inline int ocfs2_block_group_clear_bits(struct ocfs2_journal_handle *handle,
+static inline int ocfs2_block_group_clear_bits(handle_t *handle,
 					       struct inode *alloc_inode,
 					       struct ocfs2_group_desc *bg,
 					       struct buffer_head *group_bh,
@@ -1653,7 +1627,7 @@ bail:
 /*
  * expects the suballoc inode to already be locked.
  */
-static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle,
+static int ocfs2_free_suballoc_bits(handle_t *handle,
 				    struct inode *alloc_inode,
 				    struct buffer_head *alloc_bh,
 				    unsigned int start_bit,
@@ -1737,7 +1711,7 @@ static inline u64 ocfs2_which_suballoc_group(u64 block, unsigned int bit)
 	return group;
 }
 
-int ocfs2_free_dinode(struct ocfs2_journal_handle *handle,
+int ocfs2_free_dinode(handle_t *handle,
 		      struct inode *inode_alloc_inode,
 		      struct buffer_head *inode_alloc_bh,
 		      struct ocfs2_dinode *di)
@@ -1750,7 +1724,7 @@ int ocfs2_free_dinode(struct ocfs2_journal_handle *handle,
 					inode_alloc_bh, bit, bg_blkno, 1);
 }
 
-int ocfs2_free_extent_block(struct ocfs2_journal_handle *handle,
+int ocfs2_free_extent_block(handle_t *handle,
 			    struct inode *eb_alloc_inode,
 			    struct buffer_head *eb_alloc_bh,
 			    struct ocfs2_extent_block *eb)
@@ -1763,7 +1737,7 @@ int ocfs2_free_extent_block(struct ocfs2_journal_handle *handle,
 					bit, bg_blkno, 1);
 }
 
-int ocfs2_free_clusters(struct ocfs2_journal_handle *handle,
+int ocfs2_free_clusters(handle_t *handle,
 		       struct inode *bitmap_inode,
 		       struct buffer_head *bitmap_bh,
 		       u64 start_blk,
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index c787838d1052..1a3c94cb9250 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -43,7 +43,6 @@ struct ocfs2_alloc_context {
 #define OCFS2_AC_USE_INODE 3
 #define OCFS2_AC_USE_META  4
 	u32    ac_which;
-	struct ocfs2_journal_handle *ac_handle;
 
 	/* these are used by the chain search */
 	u16    ac_chain;
@@ -60,45 +59,42 @@ static inline int ocfs2_alloc_context_bits_left(struct ocfs2_alloc_context *ac)
 }
 
 int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
-			       struct ocfs2_journal_handle *handle,
 			       struct ocfs2_dinode *fe,
 			       struct ocfs2_alloc_context **ac);
 int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
-			    struct ocfs2_journal_handle *handle,
 			    struct ocfs2_alloc_context **ac);
 int ocfs2_reserve_clusters(struct ocfs2_super *osb,
-			   struct ocfs2_journal_handle *handle,
 			   u32 bits_wanted,
 			   struct ocfs2_alloc_context **ac);
 
 int ocfs2_claim_metadata(struct ocfs2_super *osb,
-			 struct ocfs2_journal_handle *handle,
+			 handle_t *handle,
 			 struct ocfs2_alloc_context *ac,
 			 u32 bits_wanted,
 			 u16 *suballoc_bit_start,
 			 u32 *num_bits,
 			 u64 *blkno_start);
 int ocfs2_claim_new_inode(struct ocfs2_super *osb,
-			  struct ocfs2_journal_handle *handle,
+			  handle_t *handle,
 			  struct ocfs2_alloc_context *ac,
 			  u16 *suballoc_bit,
 			  u64 *fe_blkno);
 int ocfs2_claim_clusters(struct ocfs2_super *osb,
-			 struct ocfs2_journal_handle *handle,
+			 handle_t *handle,
 			 struct ocfs2_alloc_context *ac,
 			 u32 min_clusters,
 			 u32 *cluster_start,
 			 u32 *num_clusters);
 
-int ocfs2_free_dinode(struct ocfs2_journal_handle *handle,
+int ocfs2_free_dinode(handle_t *handle,
 		      struct inode *inode_alloc_inode,
 		      struct buffer_head *inode_alloc_bh,
 		      struct ocfs2_dinode *di);
-int ocfs2_free_extent_block(struct ocfs2_journal_handle *handle,
+int ocfs2_free_extent_block(handle_t *handle,
 			    struct inode *eb_alloc_inode,
 			    struct buffer_head *eb_alloc_bh,
 			    struct ocfs2_extent_block *eb);
-int ocfs2_free_clusters(struct ocfs2_journal_handle *handle,
+int ocfs2_free_clusters(handle_t *handle,
 			struct inode *bitmap_inode,
 			struct buffer_head *bitmap_bh,
 			u64 start_blk,
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 9a8089030f55..d9b4214a12da 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -70,8 +70,6 @@
 
 static kmem_cache_t *ocfs2_inode_cachep = NULL;
 
-kmem_cache_t *ocfs2_lock_cache = NULL;
-
 /* OCFS2 needs to schedule several differnt types of work which
  * require cluster locking, disk I/O, recovery waits, etc. Since these
  * types of work tend to be heavy we avoid using the kernel events
@@ -141,6 +139,7 @@ enum {
 	Opt_hb_local,
 	Opt_data_ordered,
 	Opt_data_writeback,
+	Opt_atime_quantum,
 	Opt_err,
 };
 
@@ -154,6 +153,7 @@ static match_table_t tokens = {
 	{Opt_hb_local, OCFS2_HB_LOCAL},
 	{Opt_data_ordered, "data=ordered"},
 	{Opt_data_writeback, "data=writeback"},
+	{Opt_atime_quantum, "atime_quantum=%u"},
 	{Opt_err, NULL}
 };
 
@@ -707,6 +707,7 @@ static int ocfs2_parse_options(struct super_block *sb,
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token, option;
 		substring_t args[MAX_OPT_ARGS];
+		struct ocfs2_super * osb = OCFS2_SB(sb);
 
 		if (!*p)
 			continue;
@@ -747,6 +748,16 @@ static int ocfs2_parse_options(struct super_block *sb,
 		case Opt_data_writeback:
 			*mount_opt |= OCFS2_MOUNT_DATA_WRITEBACK;
 			break;
+		case Opt_atime_quantum:
+			if (match_int(&args[0], &option)) {
+				status = 0;
+				goto bail;
+			}
+			if (option >= 0)
+				osb->s_atime_quantum = option;
+			else
+				osb->s_atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
+			break;
 		default:
 			mlog(ML_ERROR,
 			     "Unrecognized mount option \"%s\" "
@@ -867,7 +878,7 @@ static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
 		goto bail;
 	}
 
-	status = ocfs2_meta_lock(inode, NULL, &bh, 0);
+	status = ocfs2_meta_lock(inode, &bh, 0);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -914,9 +925,7 @@ static void ocfs2_inode_init_once(void *data,
 		oi->ip_open_count = 0;
 		spin_lock_init(&oi->ip_lock);
 		ocfs2_extent_map_init(&oi->vfs_inode);
-		INIT_LIST_HEAD(&oi->ip_handle_list);
 		INIT_LIST_HEAD(&oi->ip_io_markers);
-		oi->ip_handle = NULL;
 		oi->ip_created_trans = 0;
 		oi->ip_last_trans = 0;
 		oi->ip_dir_start_lookup = 0;
@@ -948,14 +957,6 @@ static int ocfs2_initialize_mem_caches(void)
 	if (!ocfs2_inode_cachep)
 		return -ENOMEM;
 
-	ocfs2_lock_cache = kmem_cache_create("ocfs2_lock",
-					     sizeof(struct ocfs2_journal_lock),
-					     0,
-					     SLAB_HWCACHE_ALIGN,
-					     NULL, NULL);
-	if (!ocfs2_lock_cache)
-		return -ENOMEM;
-
 	return 0;
 }
 
@@ -963,11 +964,8 @@ static void ocfs2_free_mem_caches(void)
 {
 	if (ocfs2_inode_cachep)
 		kmem_cache_destroy(ocfs2_inode_cachep);
-	if (ocfs2_lock_cache)
-		kmem_cache_destroy(ocfs2_lock_cache);
 
 	ocfs2_inode_cachep = NULL;
-	ocfs2_lock_cache = NULL;
 }
 
 static int ocfs2_get_sector(struct super_block *sb,
@@ -1280,6 +1278,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	init_waitqueue_head(&osb->checkpoint_event);
 	atomic_set(&osb->needs_checkpoint, 0);
 
+	osb->s_atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
+
 	osb->node_num = O2NM_INVALID_NODE_NUM;
 	osb->slot_num = OCFS2_INVALID_SLOT;
 
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index c0f68aa6c175..957d6878b03e 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -126,6 +126,10 @@ static int ocfs2_readlink(struct dentry *dentry,
 		goto out;
 	}
 
+	/*
+	 * Without vfsmount we can't update atime now,
+	 * but we will update atime here ultimately.
+	 */
 	ret = vfs_readlink(dentry, buffer, buflen, link);
 
 	brelse(bh);
diff --git a/fs/partitions/mac.c b/fs/partitions/mac.c
index c0871002d00d..d4a0fad3563b 100644
--- a/fs/partitions/mac.c
+++ b/fs/partitions/mac.c
@@ -74,6 +74,8 @@ int mac_partition(struct parsed_partitions *state, struct block_device *bdev)
 			be32_to_cpu(part->start_block) * (secsize/512),
 			be32_to_cpu(part->block_count) * (secsize/512));
 
+		if (!strnicmp(part->type, "Linux_RAID", 10))
+			state->parts[slot].flags = 1;
 #ifdef CONFIG_PPC_PMAC
 		/*
 		 * If this is the first bootable partition, tell the
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ffe66c38488b..64d242b6dcfa 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -13,6 +13,7 @@
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/smp_lock.h>
diff --git a/fs/super.c b/fs/super.c
index 47e554c12e76..84c320f6ad7e 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -221,6 +221,24 @@ static int grab_super(struct super_block *s) __releases(sb_lock)
 }
 
 /*
+ * Superblock locking.  We really ought to get rid of these two.
+ */
+void lock_super(struct super_block * sb)
+{
+	get_fs_excl();
+	mutex_lock(&sb->s_lock);
+}
+
+void unlock_super(struct super_block * sb)
+{
+	put_fs_excl();
+	mutex_unlock(&sb->s_lock);
+}
+
+EXPORT_SYMBOL(lock_super);
+EXPORT_SYMBOL(unlock_super);
+
+/*
  * Write out and wait upon all dirty data associated with this
  * superblock.  Filesystem data as well as the underlying block
  * device.  Takes the superblock lock.  Requires a second blkdev
diff --git a/fs/sync.c b/fs/sync.c
index 1de747b5ddb9..865f32be386e 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -6,6 +6,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
 #include <linux/linkage.h>
diff --git a/fs/utimes.c b/fs/utimes.c
index 1bcd852fc4a9..99cf2cb11fec 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -2,6 +2,7 @@
 #include <linux/fs.h>
 #include <linux/linkage.h>
 #include <linux/namei.h>
+#include <linux/sched.h>
 #include <linux/utime.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
diff --git a/include/asm-arm/arch-ixp4xx/platform.h b/include/asm-arm/arch-ixp4xx/platform.h
index 8d10a9187693..ab194e5f6653 100644
--- a/include/asm-arm/arch-ixp4xx/platform.h
+++ b/include/asm-arm/arch-ixp4xx/platform.h
@@ -86,6 +86,19 @@ struct ixp4xx_i2c_pins {
 	unsigned long scl_pin;
 };
 
+/*
+ * This structure provide a means for the board setup code
+ * to give information to th pata_ixp4xx driver. It is
+ * passed as platform_data.
+ */
+struct ixp4xx_pata_data {
+	volatile u32	*cs0_cfg;
+	volatile u32	*cs1_cfg;
+	unsigned long	cs0_bits;
+	unsigned long	cs1_bits;
+	void __iomem	*cs0;
+	void __iomem	*cs1;
+};
 
 struct sys_timer;
 
diff --git a/include/asm-avr32/types.h b/include/asm-avr32/types.h
index 3f47db9675af..2bff153a32ed 100644
--- a/include/asm-avr32/types.h
+++ b/include/asm-avr32/types.h
@@ -57,11 +57,6 @@ typedef unsigned long long u64;
 
 typedef u32 dma_addr_t;
 
-#ifdef CONFIG_LBD
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-h8300/types.h b/include/asm-h8300/types.h
index da2402b86540..2a8b1b2be782 100644
--- a/include/asm-h8300/types.h
+++ b/include/asm-h8300/types.h
@@ -55,12 +55,6 @@ typedef unsigned long long u64;
 
 typedef u32 dma_addr_t;
 
-#define HAVE_SECTOR_T
-typedef u64 sector_t;
-
-#define HAVE_BLKCNT_T
-typedef u64 blkcnt_t;
-
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/asm-i386/types.h b/include/asm-i386/types.h
index 4b4b295ccdb9..ad0a55bd782f 100644
--- a/include/asm-i386/types.h
+++ b/include/asm-i386/types.h
@@ -57,16 +57,6 @@ typedef u32 dma_addr_t;
 #endif
 typedef u64 dma64_addr_t;
 
-#ifdef CONFIG_LBD
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-#endif
-
-#ifdef CONFIG_LSF
-typedef u64 blkcnt_t;
-#define HAVE_BLKCNT_T
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-m68knommu/dma-mapping.h b/include/asm-m68knommu/dma-mapping.h
index 5622b855a577..6aeab18e58bd 100644
--- a/include/asm-m68knommu/dma-mapping.h
+++ b/include/asm-m68knommu/dma-mapping.h
@@ -1,9 +1,10 @@
 #ifndef _M68KNOMMU_DMA_MAPPING_H
 #define _M68KNOMMU_DMA_MAPPING_H
 
-
 #ifdef CONFIG_PCI
 #include <asm-generic/dma-mapping.h>
+#else
+#include <asm-generic/dma-mapping-broken.h>
 #endif
 
 #endif  /* _M68KNOMMU_DMA_MAPPING_H */
diff --git a/include/asm-m68knommu/m520xsim.h b/include/asm-m68knommu/m520xsim.h
index 1dac22ea95ba..49d016e6391a 100644
--- a/include/asm-m68knommu/m520xsim.h
+++ b/include/asm-m68knommu/m520xsim.h
@@ -31,6 +31,16 @@
 #define MCFINT_QSPI         31          /* Interrupt number for QSPI */
 #define MCFINT_PIT1         4           /* Interrupt number for PIT1 (PIT0 in processor) */
 
+/*
+ *  SDRAM configuration registers.
+ */
+#define MCFSIM_SDMR         0x000a8000	/* SDRAM Mode/Extended Mode Register */
+#define MCFSIM_SDCR         0x000a8004	/* SDRAM Control Register */
+#define MCFSIM_SDCFG1       0x000a8008	/* SDRAM Configuration Register 1 */
+#define MCFSIM_SDCFG2       0x000a800c	/* SDRAM Configuration Register 2 */
+#define MCFSIM_SDCS0        0x000a8110	/* SDRAM Chip Select 0 Configuration */
+#define MCFSIM_SDCS1        0x000a8114	/* SDRAM Chip Select 1 Configuration */
+
 
 #define MCF_GPIO_PAR_UART                   (0xA4036)
 #define MCF_GPIO_PAR_FECI2C                 (0xA4033)
@@ -47,7 +57,7 @@
 
 #define ICR_INTRCONF		0x05
 #define MCFPIT_IMR		MCFINTC_IMRL
-#define MCFPIT_IMR_IBIT	(1 << MCFINT_PIT1)
+#define MCFPIT_IMR_IBIT		(1 << MCFINT_PIT1)
 
 /****************************************************************************/
 #endif  /* m520xsim_h */
diff --git a/include/asm-m68knommu/scatterlist.h b/include/asm-m68knommu/scatterlist.h
index 12309b181d29..2085d6ff8782 100644
--- a/include/asm-m68knommu/scatterlist.h
+++ b/include/asm-m68knommu/scatterlist.h
@@ -10,7 +10,7 @@ struct scatterlist {
 	unsigned int	length;
 };
 
-#define sg_address(sg) (page_address((sg)->page) + (sg)->offset
+#define sg_address(sg)		(page_address((sg)->page) + (sg)->offset)
 #define sg_dma_address(sg)      ((sg)->dma_address)
 #define sg_dma_len(sg)          ((sg)->length)
 
diff --git a/include/asm-mips/atomic.h b/include/asm-mips/atomic.h
index 7978d8e11647..c1a2409bb52a 100644
--- a/include/asm-mips/atomic.h
+++ b/include/asm-mips/atomic.h
@@ -15,6 +15,7 @@
 #define _ASM_ATOMIC_H
 
 #include <linux/irqflags.h>
+#include <asm/barrier.h>
 #include <asm/cpu-features.h>
 #include <asm/war.h>
 
@@ -130,6 +131,8 @@ static __inline__ int atomic_add_return(int i, atomic_t * v)
 {
 	unsigned long result;
 
+	smp_mb();
+
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
 		unsigned long temp;
 
@@ -140,7 +143,6 @@ static __inline__ int atomic_add_return(int i, atomic_t * v)
 		"	sc	%0, %2					\n"
 		"	beqzl	%0, 1b					\n"
 		"	addu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -155,7 +157,6 @@ static __inline__ int atomic_add_return(int i, atomic_t * v)
 		"	sc	%0, %2					\n"
 		"	beqz	%0, 1b					\n"
 		"	addu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -170,6 +171,8 @@ static __inline__ int atomic_add_return(int i, atomic_t * v)
 		local_irq_restore(flags);
 	}
 
+	smp_mb();
+
 	return result;
 }
 
@@ -177,6 +180,8 @@ static __inline__ int atomic_sub_return(int i, atomic_t * v)
 {
 	unsigned long result;
 
+	smp_mb();
+
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
 		unsigned long temp;
 
@@ -187,7 +192,6 @@ static __inline__ int atomic_sub_return(int i, atomic_t * v)
 		"	sc	%0, %2					\n"
 		"	beqzl	%0, 1b					\n"
 		"	subu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -202,7 +206,6 @@ static __inline__ int atomic_sub_return(int i, atomic_t * v)
 		"	sc	%0, %2					\n"
 		"	beqz	%0, 1b					\n"
 		"	subu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -217,6 +220,8 @@ static __inline__ int atomic_sub_return(int i, atomic_t * v)
 		local_irq_restore(flags);
 	}
 
+	smp_mb();
+
 	return result;
 }
 
@@ -232,6 +237,8 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 {
 	unsigned long result;
 
+	smp_mb();
+
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
 		unsigned long temp;
 
@@ -245,7 +252,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"	beqzl	%0, 1b					\n"
 		"	 subu	%0, %1, %3				\n"
 		"	.set	reorder					\n"
-		"	sync						\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
@@ -264,7 +270,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"	beqz	%0, 1b					\n"
 		"	 subu	%0, %1, %3				\n"
 		"	.set	reorder					\n"
-		"	sync						\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
@@ -281,6 +286,8 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		local_irq_restore(flags);
 	}
 
+	smp_mb();
+
 	return result;
 }
 
@@ -375,7 +382,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 
 #ifdef CONFIG_64BIT
 
-typedef struct { volatile __s64 counter; } atomic64_t;
+typedef struct { volatile long counter; } atomic64_t;
 
 #define ATOMIC64_INIT(i)    { (i) }
 
@@ -484,6 +491,8 @@ static __inline__ long atomic64_add_return(long i, atomic64_t * v)
 {
 	unsigned long result;
 
+	smp_mb();
+
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
 		unsigned long temp;
 
@@ -494,7 +503,6 @@ static __inline__ long atomic64_add_return(long i, atomic64_t * v)
 		"	scd	%0, %2					\n"
 		"	beqzl	%0, 1b					\n"
 		"	addu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -509,7 +517,6 @@ static __inline__ long atomic64_add_return(long i, atomic64_t * v)
 		"	scd	%0, %2					\n"
 		"	beqz	%0, 1b					\n"
 		"	addu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -524,6 +531,8 @@ static __inline__ long atomic64_add_return(long i, atomic64_t * v)
 		local_irq_restore(flags);
 	}
 
+	smp_mb();
+
 	return result;
 }
 
@@ -531,6 +540,8 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 {
 	unsigned long result;
 
+	smp_mb();
+
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
 		unsigned long temp;
 
@@ -541,7 +552,6 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 		"	scd	%0, %2					\n"
 		"	beqzl	%0, 1b					\n"
 		"	subu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -556,7 +566,6 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 		"	scd	%0, %2					\n"
 		"	beqz	%0, 1b					\n"
 		"	subu	%0, %1, %3				\n"
-		"	sync						\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
@@ -571,6 +580,8 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 		local_irq_restore(flags);
 	}
 
+	smp_mb();
+
 	return result;
 }
 
@@ -586,6 +597,8 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 {
 	unsigned long result;
 
+	smp_mb();
+
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
 		unsigned long temp;
 
@@ -599,7 +612,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"	beqzl	%0, 1b					\n"
 		"	 dsubu	%0, %1, %3				\n"
 		"	.set	reorder					\n"
-		"	sync						\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
@@ -618,7 +630,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"	beqz	%0, 1b					\n"
 		"	 dsubu	%0, %1, %3				\n"
 		"	.set	reorder					\n"
-		"	sync						\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
@@ -635,6 +646,8 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		local_irq_restore(flags);
 	}
 
+	smp_mb();
+
 	return result;
 }
 
diff --git a/include/asm-mips/barrier.h b/include/asm-mips/barrier.h
new file mode 100644
index 000000000000..ed82631b0017
--- /dev/null
+++ b/include/asm-mips/barrier.h
@@ -0,0 +1,132 @@
+/*
+ * 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) 2006 by Ralf Baechle (ralf@linux-mips.org)
+ */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+/*
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	b = 2;
+ *	memory_barrier();
+ *	p = &b;				q = p;
+ *					read_barrier_depends();
+ *					d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	a = 2;
+ *	memory_barrier();
+ *	b = 3;				y = b;
+ *					read_barrier_depends();
+ *					x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ */
+
+#define read_barrier_depends()		do { } while(0)
+#define smp_read_barrier_depends()	do { } while(0)
+
+#ifdef CONFIG_CPU_HAS_SYNC
+#define __sync()				\
+	__asm__ __volatile__(			\
+		".set	push\n\t"		\
+		".set	noreorder\n\t"		\
+		".set	mips2\n\t"		\
+		"sync\n\t"			\
+		".set	pop"			\
+		: /* no output */		\
+		: /* no input */		\
+		: "memory")
+#else
+#define __sync()	do { } while(0)
+#endif
+
+#define __fast_iob()				\
+	__asm__ __volatile__(			\
+		".set	push\n\t"		\
+		".set	noreorder\n\t"		\
+		"lw	$0,%0\n\t"		\
+		"nop\n\t"			\
+		".set	pop"			\
+		: /* no output */		\
+		: "m" (*(int *)CKSEG1)		\
+		: "memory")
+
+#define fast_wmb()	__sync()
+#define fast_rmb()	__sync()
+#define fast_mb()	__sync()
+#define fast_iob()				\
+	do {					\
+		__sync();			\
+		__fast_iob();			\
+	} while (0)
+
+#ifdef CONFIG_CPU_HAS_WB
+
+#include <asm/wbflush.h>
+
+#define wmb()		fast_wmb()
+#define rmb()		fast_rmb()
+#define mb()		wbflush()
+#define iob()		wbflush()
+
+#else /* !CONFIG_CPU_HAS_WB */
+
+#define wmb()		fast_wmb()
+#define rmb()		fast_rmb()
+#define mb()		fast_mb()
+#define iob()		fast_iob()
+
+#endif /* !CONFIG_CPU_HAS_WB */
+
+#if defined(CONFIG_WEAK_ORDERING) && defined(CONFIG_SMP)
+#define __WEAK_ORDERING_MB	"       sync	\n"
+#else
+#define __WEAK_ORDERING_MB	"		\n"
+#endif
+
+#define smp_mb()	__asm__ __volatile__(__WEAK_ORDERING_MB : : :"memory")
+#define smp_rmb()	__asm__ __volatile__(__WEAK_ORDERING_MB : : :"memory")
+#define smp_wmb()	__asm__ __volatile__(__WEAK_ORDERING_MB : : :"memory")
+
+#define set_mb(var, value) \
+	do { var = value; smp_mb(); } while (0)
+
+#endif /* __ASM_BARRIER_H */
diff --git a/include/asm-mips/bitops.h b/include/asm-mips/bitops.h
index b9007411b60f..06445de1324b 100644
--- a/include/asm-mips/bitops.h
+++ b/include/asm-mips/bitops.h
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 1994 - 1997, 1999, 2000  Ralf Baechle (ralf@gnu.org)
+ * Copyright (c) 1994 - 1997, 1999, 2000, 06  Ralf Baechle (ralf@linux-mips.org)
  * Copyright (c) 1999, 2000  Silicon Graphics, Inc.
  */
 #ifndef _ASM_BITOPS_H
@@ -12,6 +12,7 @@
 #include <linux/compiler.h>
 #include <linux/irqflags.h>
 #include <linux/types.h>
+#include <asm/barrier.h>
 #include <asm/bug.h>
 #include <asm/byteorder.h>		/* sigh ... */
 #include <asm/cpu-features.h>
@@ -204,9 +205,6 @@ static inline int test_and_set_bit(unsigned long nr,
 		"	" __SC	"%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (temp), "=m" (*m), "=&r" (res)
 		: "r" (1UL << (nr & SZLONG_MASK)), "m" (*m)
@@ -226,9 +224,6 @@ static inline int test_and_set_bit(unsigned long nr,
 		"	" __SC	"%2, %1					\n"
 		"	beqz	%2, 1b					\n"
 		"	 and	%2, %0, %3				\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	pop					\n"
 		: "=&r" (temp), "=m" (*m), "=&r" (res)
 		: "r" (1UL << (nr & SZLONG_MASK)), "m" (*m)
@@ -250,6 +245,8 @@ static inline int test_and_set_bit(unsigned long nr,
 
 		return retval;
 	}
+
+	smp_mb();
 }
 
 /*
@@ -275,9 +272,6 @@ static inline int test_and_clear_bit(unsigned long nr,
 		"	" __SC 	"%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (temp), "=m" (*m), "=&r" (res)
 		: "r" (1UL << (nr & SZLONG_MASK)), "m" (*m)
@@ -298,9 +292,6 @@ static inline int test_and_clear_bit(unsigned long nr,
 		"	" __SC 	"%2, %1					\n"
 		"	beqz	%2, 1b					\n"
 		"	 and	%2, %0, %3				\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	pop					\n"
 		: "=&r" (temp), "=m" (*m), "=&r" (res)
 		: "r" (1UL << (nr & SZLONG_MASK)), "m" (*m)
@@ -322,6 +313,8 @@ static inline int test_and_clear_bit(unsigned long nr,
 
 		return retval;
 	}
+
+	smp_mb();
 }
 
 /*
@@ -346,9 +339,6 @@ static inline int test_and_change_bit(unsigned long nr,
 		"	" __SC	"%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (temp), "=m" (*m), "=&r" (res)
 		: "r" (1UL << (nr & SZLONG_MASK)), "m" (*m)
@@ -368,9 +358,6 @@ static inline int test_and_change_bit(unsigned long nr,
 		"	" __SC	"\t%2, %1				\n"
 		"	beqz	%2, 1b					\n"
 		"	 and	%2, %0, %3				\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	pop					\n"
 		: "=&r" (temp), "=m" (*m), "=&r" (res)
 		: "r" (1UL << (nr & SZLONG_MASK)), "m" (*m)
@@ -391,6 +378,8 @@ static inline int test_and_change_bit(unsigned long nr,
 
 		return retval;
 	}
+
+	smp_mb();
 }
 
 #include <asm-generic/bitops/non-atomic.h>
diff --git a/include/asm-mips/compat.h b/include/asm-mips/compat.h
index 900f472fdd2b..55a0152feb08 100644
--- a/include/asm-mips/compat.h
+++ b/include/asm-mips/compat.h
@@ -32,6 +32,7 @@ typedef struct {
 	s32	val[2];
 } compat_fsid_t;
 typedef s32		compat_timer_t;
+typedef s32		compat_key_t;
 
 typedef s32		compat_int_t;
 typedef s32		compat_long_t;
@@ -146,4 +147,71 @@ static inline void __user *compat_alloc_user_space(long len)
 	return (void __user *) (regs->regs[29] - len);
 }
 
+struct compat_ipc64_perm {
+	compat_key_t key;
+	__compat_uid32_t uid;
+	__compat_gid32_t gid;
+	__compat_uid32_t cuid;
+	__compat_gid32_t cgid;
+	compat_mode_t mode;
+	unsigned short seq;
+	unsigned short __pad2;
+	compat_ulong_t __unused1;
+	compat_ulong_t __unused2;
+};
+
+struct compat_semid64_ds {
+	struct compat_ipc64_perm sem_perm;
+	compat_time_t	sem_otime;
+	compat_time_t	sem_ctime;
+	compat_ulong_t	sem_nsems;
+	compat_ulong_t	__unused1;
+	compat_ulong_t	__unused2;
+};
+
+struct compat_msqid64_ds {
+	struct compat_ipc64_perm msg_perm;
+#ifndef CONFIG_CPU_LITTLE_ENDIAN
+	compat_ulong_t	__unused1;
+#endif
+	compat_time_t	msg_stime;
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	compat_ulong_t	__unused1;
+#endif
+#ifndef CONFIG_CPU_LITTLE_ENDIAN
+	compat_ulong_t	__unused2;
+#endif
+	compat_time_t	msg_rtime;
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	compat_ulong_t	__unused2;
+#endif
+#ifndef CONFIG_CPU_LITTLE_ENDIAN
+	compat_ulong_t	__unused3;
+#endif
+	compat_time_t	msg_ctime;
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	compat_ulong_t	__unused3;
+#endif
+	compat_ulong_t	msg_cbytes;
+	compat_ulong_t	msg_qnum;
+	compat_ulong_t	msg_qbytes;
+	compat_pid_t	msg_lspid;
+	compat_pid_t	msg_lrpid;
+	compat_ulong_t	__unused4;
+	compat_ulong_t	__unused5;
+};
+
+struct compat_shmid64_ds {
+	struct compat_ipc64_perm shm_perm;
+	compat_size_t	shm_segsz;
+	compat_time_t	shm_atime;
+	compat_time_t	shm_dtime;
+	compat_time_t	shm_ctime;
+	compat_pid_t	shm_cpid;
+	compat_pid_t	shm_lpid;
+	compat_ulong_t	shm_nattch;
+	compat_ulong_t	__unused1;
+	compat_ulong_t	__unused2;
+};
+
 #endif /* _ASM_COMPAT_H */
diff --git a/include/asm-mips/futex.h b/include/asm-mips/futex.h
index ed023eae0674..927a216bd530 100644
--- a/include/asm-mips/futex.h
+++ b/include/asm-mips/futex.h
@@ -1,19 +1,21 @@
+/*
+ * 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) 2006  Ralf Baechle (ralf@linux-mips.org)
+ */
 #ifndef _ASM_FUTEX_H
 #define _ASM_FUTEX_H
 
 #ifdef __KERNEL__
 
 #include <linux/futex.h>
+#include <asm/barrier.h>
 #include <asm/errno.h>
 #include <asm/uaccess.h>
 #include <asm/war.h>
 
-#ifdef CONFIG_SMP
-#define __FUTEX_SMP_SYNC "	sync					\n"
-#else
-#define __FUTEX_SMP_SYNC
-#endif
-
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)		\
 {									\
 	if (cpu_has_llsc && R10000_LLSC_WAR) {				\
@@ -27,7 +29,7 @@
 		"	.set	mips3				\n"	\
 		"2:	sc	$1, %2				\n"	\
 		"	beqzl	$1, 1b				\n"	\
-		__FUTEX_SMP_SYNC					\
+		__WEAK_ORDERING_MB					\
 		"3:						\n"	\
 		"	.set	pop				\n"	\
 		"	.set	mips0				\n"	\
@@ -53,7 +55,7 @@
 		"	.set	mips3				\n"	\
 		"2:	sc	$1, %2				\n"	\
 		"	beqz	$1, 1b				\n"	\
-		__FUTEX_SMP_SYNC					\
+		__WEAK_ORDERING_MB					\
 		"3:						\n"	\
 		"	.set	pop				\n"	\
 		"	.set	mips0				\n"	\
@@ -150,7 +152,7 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		"	.set	mips3					\n"
 		"2:	sc	$1, %1					\n"
 		"	beqzl	$1, 1b					\n"
-		__FUTEX_SMP_SYNC
+		__WEAK_ORDERING_MB
 		"3:							\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
@@ -177,7 +179,7 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		"	.set	mips3					\n"
 		"2:	sc	$1, %1					\n"
 		"	beqz	$1, 1b					\n"
-		__FUTEX_SMP_SYNC
+		__WEAK_ORDERING_MB
 		"3:							\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
diff --git a/include/asm-mips/sn/klconfig.h b/include/asm-mips/sn/klconfig.h
index b63cd0655b3d..15d70ca56187 100644
--- a/include/asm-mips/sn/klconfig.h
+++ b/include/asm-mips/sn/klconfig.h
@@ -176,7 +176,7 @@ typedef struct kl_config_hdr {
 /* --- New Macros for the changed kl_config_hdr_t structure --- */
 
 #define PTR_CH_MALLOC_HDR(_k)   ((klc_malloc_hdr_t *)\
-			(unsigned long)_k + (_k->ch_malloc_hdr_off)))
+			((unsigned long)_k + (_k->ch_malloc_hdr_off)))
 
 #define KL_CONFIG_CH_MALLOC_HDR(_n)   PTR_CH_MALLOC_HDR(KL_CONFIG_HDR(_n))
 
diff --git a/include/asm-mips/spinlock.h b/include/asm-mips/spinlock.h
index c8d5587467bb..fc3217fc1118 100644
--- a/include/asm-mips/spinlock.h
+++ b/include/asm-mips/spinlock.h
@@ -3,12 +3,13 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 1999, 2000 by Ralf Baechle
+ * Copyright (C) 1999, 2000, 06 by Ralf Baechle
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
  */
 #ifndef _ASM_SPINLOCK_H
 #define _ASM_SPINLOCK_H
 
+#include <asm/barrier.h>
 #include <asm/war.h>
 
 /*
@@ -40,7 +41,6 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
 		"	 nop						\n"
-		"	sync						\n"
 		"	.set	reorder					\n"
 		: "=m" (lock->lock), "=&r" (tmp)
 		: "m" (lock->lock)
@@ -53,19 +53,22 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 		"	 li	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqz	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
 		"	.set	reorder					\n"
 		: "=m" (lock->lock), "=&r" (tmp)
 		: "m" (lock->lock)
 		: "memory");
 	}
+
+	smp_mb();
 }
 
 static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
+	smp_mb();
+
 	__asm__ __volatile__(
 	"	.set	noreorder	# __raw_spin_unlock	\n"
-	"	sync						\n"
 	"	sw	$0, %0					\n"
 	"	.set\treorder					\n"
 	: "=m" (lock->lock)
@@ -86,7 +89,6 @@ static inline unsigned int __raw_spin_trylock(raw_spinlock_t *lock)
 		"	beqzl	%2, 1b					\n"
 		"	 nop						\n"
 		"	andi	%2, %0, 1				\n"
-		"	sync						\n"
 		"	.set	reorder"
 		: "=&r" (temp), "=m" (lock->lock), "=&r" (res)
 		: "m" (lock->lock)
@@ -99,13 +101,14 @@ static inline unsigned int __raw_spin_trylock(raw_spinlock_t *lock)
 		"	sc	%2, %1					\n"
 		"	beqz	%2, 1b					\n"
 		"	 andi	%2, %0, 1				\n"
-		"	sync						\n"
 		"	.set	reorder"
 		: "=&r" (temp), "=m" (lock->lock), "=&r" (res)
 		: "m" (lock->lock)
 		: "memory");
 	}
 
+	smp_mb();
+
 	return res == 0;
 }
 
@@ -143,7 +146,6 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
 		"	 nop						\n"
-		"	sync						\n"
 		"	.set	reorder					\n"
 		: "=m" (rw->lock), "=&r" (tmp)
 		: "m" (rw->lock)
@@ -156,12 +158,14 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
 		"	 addu	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqz	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
 		"	.set	reorder					\n"
 		: "=m" (rw->lock), "=&r" (tmp)
 		: "m" (rw->lock)
 		: "memory");
 	}
+
+	smp_mb();
 }
 
 /* Note the use of sub, not subu which will make the kernel die with an
@@ -171,13 +175,14 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 {
 	unsigned int tmp;
 
+	smp_mb();
+
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
 		"1:	ll	%1, %2		# __raw_read_unlock	\n"
 		"	sub	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
-		"	sync						\n"
 		: "=m" (rw->lock), "=&r" (tmp)
 		: "m" (rw->lock)
 		: "memory");
@@ -188,7 +193,7 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 		"	sub	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqz	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
 		"	.set	reorder					\n"
 		: "=m" (rw->lock), "=&r" (tmp)
 		: "m" (rw->lock)
@@ -208,7 +213,7 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
 		"	 lui	%1, 0x8000				\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
 		"	.set	reorder					\n"
 		: "=m" (rw->lock), "=&r" (tmp)
 		: "m" (rw->lock)
@@ -221,18 +226,22 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
 		"	 lui	%1, 0x8000				\n"
 		"	sc	%1, %0					\n"
 		"	beqz	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
 		"	.set	reorder					\n"
 		: "=m" (rw->lock), "=&r" (tmp)
 		: "m" (rw->lock)
 		: "memory");
 	}
+
+	smp_mb();
 }
 
 static inline void __raw_write_unlock(raw_rwlock_t *rw)
 {
+	smp_mb();
+
 	__asm__ __volatile__(
-	"	sync			# __raw_write_unlock	\n"
+	"				# __raw_write_unlock	\n"
 	"	sw	$0, %0					\n"
 	: "=m" (rw->lock)
 	: "m" (rw->lock)
@@ -252,11 +261,10 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw)
 		"	bnez	%1, 2f					\n"
 		"	 addu	%1, 1					\n"
 		"	sc	%1, %0					\n"
-		"	beqzl	%1, 1b					\n"
 		"	.set	reorder					\n"
-#ifdef CONFIG_SMP
-		"	 sync						\n"
-#endif
+		"	beqzl	%1, 1b					\n"
+		"	 nop						\n"
+		__WEAK_ORDERING_MB
 		"	li	%2, 1					\n"
 		"2:							\n"
 		: "=m" (rw->lock), "=&r" (tmp), "=&r" (ret)
@@ -271,10 +279,9 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw)
 		"	 addu	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqz	%1, 1b					\n"
+		"	 nop						\n"
 		"	.set	reorder					\n"
-#ifdef CONFIG_SMP
-		"	 sync						\n"
-#endif
+		__WEAK_ORDERING_MB
 		"	li	%2, 1					\n"
 		"2:							\n"
 		: "=m" (rw->lock), "=&r" (tmp), "=&r" (ret)
@@ -299,7 +306,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 		"	 lui	%1, 0x8000				\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
+		__WEAK_ORDERING_MB
 		"	li	%2, 1					\n"
 		"	.set	reorder					\n"
 		"2:							\n"
@@ -315,7 +323,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 		"	lui	%1, 0x8000				\n"
 		"	sc	%1, %0					\n"
 		"	beqz	%1, 1b					\n"
-		"	 sync						\n"
+		"	 nop						\n"
+		__WEAK_ORDERING_MB
 		"	li	%2, 1					\n"
 		"	.set	reorder					\n"
 		"2:							\n"
diff --git a/include/asm-mips/system.h b/include/asm-mips/system.h
index 3056feed5a36..9428057a50cf 100644
--- a/include/asm-mips/system.h
+++ b/include/asm-mips/system.h
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 1994, 95, 96, 97, 98, 99, 2003 by Ralf Baechle
+ * Copyright (C) 1994, 95, 96, 97, 98, 99, 2003, 06 by Ralf Baechle
  * Copyright (C) 1996 by Paul M. Antoine
  * Copyright (C) 1999 Silicon Graphics
  * Kevin D. Kissell, kevink@mips.org and Carsten Langgaard, carstenl@mips.com
@@ -16,132 +16,12 @@
 #include <linux/irqflags.h>
 
 #include <asm/addrspace.h>
+#include <asm/barrier.h>
 #include <asm/cpu-features.h>
 #include <asm/dsp.h>
 #include <asm/ptrace.h>
 #include <asm/war.h>
 
-/*
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-
-#define read_barrier_depends()	do { } while(0)
-
-#ifdef CONFIG_CPU_HAS_SYNC
-#define __sync()				\
-	__asm__ __volatile__(			\
-		".set	push\n\t"		\
-		".set	noreorder\n\t"		\
-		".set	mips2\n\t"		\
-		"sync\n\t"			\
-		".set	pop"			\
-		: /* no output */		\
-		: /* no input */		\
-		: "memory")
-#else
-#define __sync()	do { } while(0)
-#endif
-
-#define __fast_iob()				\
-	__asm__ __volatile__(			\
-		".set	push\n\t"		\
-		".set	noreorder\n\t"		\
-		"lw	$0,%0\n\t"		\
-		"nop\n\t"			\
-		".set	pop"			\
-		: /* no output */		\
-		: "m" (*(int *)CKSEG1)		\
-		: "memory")
-
-#define fast_wmb()	__sync()
-#define fast_rmb()	__sync()
-#define fast_mb()	__sync()
-#define fast_iob()				\
-	do {					\
-		__sync();			\
-		__fast_iob();			\
-	} while (0)
-
-#ifdef CONFIG_CPU_HAS_WB
-
-#include <asm/wbflush.h>
-
-#define wmb()		fast_wmb()
-#define rmb()		fast_rmb()
-#define mb()		wbflush()
-#define iob()		wbflush()
-
-#else /* !CONFIG_CPU_HAS_WB */
-
-#define wmb()		fast_wmb()
-#define rmb()		fast_rmb()
-#define mb()		fast_mb()
-#define iob()		fast_iob()
-
-#endif /* !CONFIG_CPU_HAS_WB */
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
-#endif
-
-#define set_mb(var, value) \
-do { var = value; mb(); } while (0)
 
 /*
  * switch_to(n) should switch tasks to task nr n, first
@@ -217,9 +97,6 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 		"	.set	mips3					\n"
 		"	sc	%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
 		: "R" (*m), "Jr" (val)
@@ -235,9 +112,6 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 		"	.set	mips3					\n"
 		"	sc	%2, %1					\n"
 		"	beqz	%2, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
 		: "R" (*m), "Jr" (val)
@@ -251,6 +125,8 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 		local_irq_restore(flags);	/* implies memory barrier  */
 	}
 
+	smp_mb();
+
 	return retval;
 }
 
@@ -268,9 +144,6 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 		"	move	%2, %z4					\n"
 		"	scd	%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
 		: "R" (*m), "Jr" (val)
@@ -284,9 +157,6 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 		"	move	%2, %z4					\n"
 		"	scd	%2, %1					\n"
 		"	beqz	%2, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"	.set	mips0					\n"
 		: "=&r" (retval), "=m" (*m), "=&r" (dummy)
 		: "R" (*m), "Jr" (val)
@@ -300,6 +170,8 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 		local_irq_restore(flags);	/* implies memory barrier  */
 	}
 
+	smp_mb();
+
 	return retval;
 }
 #else
@@ -345,9 +217,6 @@ static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
 		"	.set	mips3					\n"
 		"	sc	$1, %1					\n"
 		"	beqzl	$1, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"2:							\n"
 		"	.set	pop					\n"
 		: "=&r" (retval), "=R" (*m)
@@ -365,9 +234,6 @@ static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
 		"	.set	mips3					\n"
 		"	sc	$1, %1					\n"
 		"	beqz	$1, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"2:							\n"
 		"	.set	pop					\n"
 		: "=&r" (retval), "=R" (*m)
@@ -383,6 +249,8 @@ static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
 		local_irq_restore(flags);	/* implies memory barrier  */
 	}
 
+	smp_mb();
+
 	return retval;
 }
 
@@ -402,9 +270,6 @@ static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 		"	move	$1, %z4					\n"
 		"	scd	$1, %1					\n"
 		"	beqzl	$1, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"2:							\n"
 		"	.set	pop					\n"
 		: "=&r" (retval), "=R" (*m)
@@ -420,9 +285,6 @@ static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 		"	move	$1, %z4					\n"
 		"	scd	$1, %1					\n"
 		"	beqz	$1, 1b					\n"
-#ifdef CONFIG_SMP
-		"	sync						\n"
-#endif
 		"2:							\n"
 		"	.set	pop					\n"
 		: "=&r" (retval), "=R" (*m)
@@ -438,6 +300,8 @@ static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
 		local_irq_restore(flags);	/* implies memory barrier  */
 	}
 
+	smp_mb();
+
 	return retval;
 }
 #else
diff --git a/include/asm-mips/types.h b/include/asm-mips/types.h
index 2b52e180c6f2..63a13c5bd832 100644
--- a/include/asm-mips/types.h
+++ b/include/asm-mips/types.h
@@ -93,16 +93,6 @@ typedef unsigned long long phys_t;
 typedef unsigned long phys_t;
 #endif
 
-#ifdef CONFIG_LBD
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-#endif
-
-#ifdef CONFIG_LSF
-typedef u64 blkcnt_t;
-#define HAVE_BLKCNT_T
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-powerpc/Kbuild b/include/asm-powerpc/Kbuild
index 9827849953a3..1e637381c118 100644
--- a/include/asm-powerpc/Kbuild
+++ b/include/asm-powerpc/Kbuild
@@ -17,6 +17,7 @@ header-y += ipc.h
 header-y += poll.h
 header-y += shmparam.h
 header-y += sockios.h
+header-y += spu_info.h
 header-y += ucontext.h
 header-y += ioctl.h
 header-y += linkage.h
diff --git a/include/asm-powerpc/cell-pmu.h b/include/asm-powerpc/cell-pmu.h
new file mode 100644
index 000000000000..e8c2ebd3ddda
--- /dev/null
+++ b/include/asm-powerpc/cell-pmu.h
@@ -0,0 +1,113 @@
+/*
+ * Cell Broadband Engine Performance Monitor
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author:
+ *   David Erb (djerb@us.ibm.com)
+ *   Kevin Corry (kevcorry@us.ibm.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, 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 __ASM_CELL_PMU_H__
+#define __ASM_CELL_PMU_H__
+
+/* The Cell PMU has four hardware performance counters, which can be
+ * configured as four 32-bit counters or eight 16-bit counters.
+ */
+#define NR_PHYS_CTRS 4
+#define NR_CTRS      (NR_PHYS_CTRS * 2)
+
+/* Macros for the pm_control register. */
+#define CBE_PM_16BIT_CTR(ctr)              (1 << (24 - ((ctr) & (NR_PHYS_CTRS - 1))))
+#define CBE_PM_ENABLE_PERF_MON             0x80000000
+#define CBE_PM_STOP_AT_MAX                 0x40000000
+#define CBE_PM_TRACE_MODE_GET(pm_control)  (((pm_control) >> 28) & 0x3)
+#define CBE_PM_TRACE_MODE_SET(mode)        (((mode)  & 0x3) << 28)
+#define CBE_PM_COUNT_MODE_SET(count)       (((count) & 0x3) << 18)
+#define CBE_PM_FREEZE_ALL_CTRS             0x00100000
+#define CBE_PM_ENABLE_EXT_TRACE            0x00008000
+
+/* Macros for the trace_address register. */
+#define CBE_PM_TRACE_BUF_FULL              0x00000800
+#define CBE_PM_TRACE_BUF_EMPTY             0x00000400
+#define CBE_PM_TRACE_BUF_DATA_COUNT(ta)    ((ta) & 0x3ff)
+#define CBE_PM_TRACE_BUF_MAX_COUNT         0x400
+
+/* Macros for the pm07_control registers. */
+#define CBE_PM_CTR_INPUT_MUX(pm07_control) (((pm07_control) >> 26) & 0x3f)
+#define CBE_PM_CTR_INPUT_CONTROL           0x02000000
+#define CBE_PM_CTR_POLARITY                0x01000000
+#define CBE_PM_CTR_COUNT_CYCLES            0x00800000
+#define CBE_PM_CTR_ENABLE                  0x00400000
+
+/* Macros for the pm_status register. */
+#define CBE_PM_CTR_OVERFLOW_INTR(ctr)      (1 << (31 - ((ctr) & 7)))
+
+enum pm_reg_name {
+	group_control,
+	debug_bus_control,
+	trace_address,
+	ext_tr_timer,
+	pm_status,
+	pm_control,
+	pm_interval,
+	pm_start_stop,
+};
+
+/* Routines for reading/writing the PMU registers. */
+extern u32  cbe_read_phys_ctr(u32 cpu, u32 phys_ctr);
+extern void cbe_write_phys_ctr(u32 cpu, u32 phys_ctr, u32 val);
+extern u32  cbe_read_ctr(u32 cpu, u32 ctr);
+extern void cbe_write_ctr(u32 cpu, u32 ctr, u32 val);
+
+extern u32  cbe_read_pm07_control(u32 cpu, u32 ctr);
+extern void cbe_write_pm07_control(u32 cpu, u32 ctr, u32 val);
+extern u32  cbe_read_pm(u32 cpu, enum pm_reg_name reg);
+extern void cbe_write_pm(u32 cpu, enum pm_reg_name reg, u32 val);
+
+extern u32  cbe_get_ctr_size(u32 cpu, u32 phys_ctr);
+extern void cbe_set_ctr_size(u32 cpu, u32 phys_ctr, u32 ctr_size);
+
+extern void cbe_enable_pm(u32 cpu);
+extern void cbe_disable_pm(u32 cpu);
+
+extern void cbe_read_trace_buffer(u32 cpu, u64 *buf);
+
+extern void cbe_enable_pm_interrupts(u32 cpu, u32 thread, u32 mask);
+extern void cbe_disable_pm_interrupts(u32 cpu);
+extern u32  cbe_query_pm_interrupts(u32 cpu);
+extern u32  cbe_clear_pm_interrupts(u32 cpu);
+extern void cbe_sync_irq(int node);
+
+/* Utility functions, macros */
+extern u32 cbe_get_hw_thread_id(int cpu);
+
+#define cbe_cpu_to_node(cpu) ((cpu) >> 1)
+
+#define CBE_COUNT_SUPERVISOR_MODE       0
+#define CBE_COUNT_HYPERVISOR_MODE       1
+#define CBE_COUNT_PROBLEM_MODE          2
+#define CBE_COUNT_ALL_MODES             3
+
+/* Macros for the pm07_control registers. */
+#define PM07_CTR_INPUT_MUX(x)                    (((x) & 0x3F) << 26)
+#define PM07_CTR_INPUT_CONTROL(x)                (((x) & 1) << 25)
+#define PM07_CTR_POLARITY(x)                     (((x) & 1) << 24)
+#define PM07_CTR_COUNT_CYCLES(x)                 (((x) & 1) << 23)
+#define PM07_CTR_ENABLE(x)                       (((x) & 1) << 22)
+
+#endif /* __ASM_CELL_PMU_H__ */
diff --git a/include/asm-powerpc/cputable.h b/include/asm-powerpc/cputable.h
index a9a40149a7c0..6fe5c9d4ca3b 100644
--- a/include/asm-powerpc/cputable.h
+++ b/include/asm-powerpc/cputable.h
@@ -24,6 +24,8 @@
 #define PPC_FEATURE_ICACHE_SNOOP	0x00002000
 #define PPC_FEATURE_ARCH_2_05		0x00001000
 #define PPC_FEATURE_PA6T		0x00000800
+#define PPC_FEATURE_HAS_DFP		0x00000400
+#define PPC_FEATURE_POWER6_EXT		0x00000200
 
 #define PPC_FEATURE_TRUE_LE		0x00000002
 #define PPC_FEATURE_PPC_LE		0x00000001
@@ -45,6 +47,7 @@ enum powerpc_oprofile_type {
 	PPC_OPROFILE_POWER4 = 2,
 	PPC_OPROFILE_G4 = 3,
 	PPC_OPROFILE_BOOKE = 4,
+	PPC_OPROFILE_CELL = 5,
 };
 
 struct cpu_spec {
@@ -91,7 +94,7 @@ extern struct cpu_spec		*cur_cpu_spec;
 
 extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
 
-extern struct cpu_spec *identify_cpu(unsigned long offset);
+extern struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr);
 extern void do_feature_fixups(unsigned long value, void *fixup_start,
 			      void *fixup_end);
 
@@ -148,19 +151,13 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start,
 #define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000200000000000)
 #define CPU_FTR_PURR			LONG_ASM_CONST(0x0000400000000000)
 #define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000800000000000)
+#define CPU_FTR_SPURR			LONG_ASM_CONST(0x0001000000000000)
 
 #ifndef __ASSEMBLY__
 
-#define CPU_FTR_PPCAS_ARCH_V2_BASE (CPU_FTR_SLB | \
-					CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | \
-					CPU_FTR_NODSISRALIGN)
-
-/* iSeries doesn't support large pages */
-#ifdef CONFIG_PPC_ISERIES
-#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_PPCAS_ARCH_V2_BASE)
-#else
-#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_PPCAS_ARCH_V2_BASE | CPU_FTR_16M_PAGE)
-#endif /* CONFIG_PPC_ISERIES */
+#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_SLB | \
+				 CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | \
+				 CPU_FTR_NODSISRALIGN | CPU_FTR_16M_PAGE)
 
 /* We only set the altivec features if the kernel was compiled with altivec
  * support
@@ -311,7 +308,8 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start,
 #define CPU_FTRS_E500_2	(CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB | \
 	    CPU_FTR_BIG_PHYS | CPU_FTR_NODSISRALIGN)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
-#ifdef __powerpc64__
+
+/* 64-bit CPUs */
 #define CPU_FTRS_POWER3	(CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB | \
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | CPU_FTR_PPC_LE)
 #define CPU_FTRS_RS64	(CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB | \
@@ -332,7 +330,13 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start,
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
-	    CPU_FTR_PURR | CPU_FTR_CI_LARGE_PAGE | CPU_FTR_REAL_LE)
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE)
+#define CPU_FTRS_POWER6X (CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB | \
+	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
+	    CPU_FTR_PURR | CPU_FTR_CI_LARGE_PAGE | \
+	    CPU_FTR_SPURR | CPU_FTR_REAL_LE)
 #define CPU_FTRS_CELL	(CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB | \
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -343,7 +347,6 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start,
 	    CPU_FTR_PURR | CPU_FTR_REAL_LE)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB | \
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2)
-#endif
 
 #ifdef __powerpc64__
 #define CPU_FTRS_POSSIBLE	\
diff --git a/include/asm-powerpc/dbdma.h b/include/asm-powerpc/dbdma.h
index 8973565f95d3..e23f07e73cb3 100644
--- a/include/asm-powerpc/dbdma.h
+++ b/include/asm-powerpc/dbdma.h
@@ -95,7 +95,13 @@ struct dbdma_cmd {
 #define DBDMA_DO_STOP(regs) do {				\
 	out_le32(&((regs)->control), (RUN|FLUSH)<<16);		\
 	while(in_le32(&((regs)->status)) & (ACTIVE|FLUSH))	\
-		;						\
+		; \
+} while(0)
+
+#define DBDMA_DO_RESET(regs) do {				\
+	out_le32(&((regs)->control), (ACTIVE|DEAD|WAKE|FLUSH|PAUSE|RUN)<<16);\
+	while(in_le32(&((regs)->status)) & (RUN)) \
+		; \
 } while(0)
 
 #endif /* _ASM_DBDMA_H_ */
diff --git a/include/asm-powerpc/dcr-mmio.h b/include/asm-powerpc/dcr-mmio.h
new file mode 100644
index 000000000000..5dbfca8dde36
--- /dev/null
+++ b/include/asm-powerpc/dcr-mmio.h
@@ -0,0 +1,51 @@
+/*
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ *
+ *   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
+ */
+
+#ifndef _ASM_POWERPC_DCR_MMIO_H
+#define _ASM_POWERPC_DCR_MMIO_H
+#ifdef __KERNEL__
+
+#include <asm/io.h>
+
+typedef struct { void __iomem *token; unsigned int stride; } dcr_host_t;
+
+#define DCR_MAP_OK(host)	((host).token != NULL)
+
+extern dcr_host_t dcr_map(struct device_node *dev, unsigned int dcr_n,
+			  unsigned int dcr_c);
+extern void dcr_unmap(dcr_host_t host, unsigned int dcr_n, unsigned int dcr_c);
+
+static inline u32 dcr_read(dcr_host_t host, unsigned int dcr_n)
+{
+	return in_be32(host.token + dcr_n * host.stride);
+}
+
+static inline void dcr_write(dcr_host_t host, unsigned int dcr_n, u32 value)
+{
+	out_be32(host.token + dcr_n * host.stride, value);
+}
+
+extern u64 of_translate_dcr_address(struct device_node *dev,
+				    unsigned int dcr_n,
+				    unsigned int *stride);
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_DCR_MMIO_H */
+
+
diff --git a/include/asm-powerpc/dcr-native.h b/include/asm-powerpc/dcr-native.h
new file mode 100644
index 000000000000..fd4a5f5e33d1
--- /dev/null
+++ b/include/asm-powerpc/dcr-native.h
@@ -0,0 +1,39 @@
+/*
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ *
+ *   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
+ */
+
+#ifndef _ASM_POWERPC_DCR_NATIVE_H
+#define _ASM_POWERPC_DCR_NATIVE_H
+#ifdef __KERNEL__
+
+#include <asm/reg.h>
+
+typedef struct {} dcr_host_t;
+
+#define DCR_MAP_OK(host)	(1)
+
+#define dcr_map(dev, dcr_n, dcr_c)	{}
+#define dcr_unmap(host, dcr_n, dcr_c)	{}
+#define dcr_read(host, dcr_n)		mfdcr(dcr_n)
+#define dcr_write(host, dcr_n, value)	mtdcr(dcr_n, value)
+
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_DCR_NATIVE_H */
+
+
diff --git a/include/asm-powerpc/dcr.h b/include/asm-powerpc/dcr.h
new file mode 100644
index 000000000000..473f2c7fd892
--- /dev/null
+++ b/include/asm-powerpc/dcr.h
@@ -0,0 +1,42 @@
+/*
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ *
+ *   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
+ */
+
+#ifndef _ASM_POWERPC_DCR_H
+#define _ASM_POWERPC_DCR_H
+#ifdef __KERNEL__
+
+#ifdef CONFIG_PPC_DCR_NATIVE
+#include <asm/dcr-native.h>
+#else
+#include <asm/dcr-mmio.h>
+#endif
+
+/*
+ * On CONFIG_PPC_MERGE, we have additional helpers to read the DCR
+ * base from the device-tree
+ */
+#ifdef CONFIG_PPC_MERGE
+extern unsigned int dcr_resource_start(struct device_node *np,
+				       unsigned int index);
+extern unsigned int dcr_resource_len(struct device_node *np,
+				     unsigned int index);
+#endif /* CONFIG_PPC_MERGE */
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_DCR_H */
diff --git a/include/asm-powerpc/device.h b/include/asm-powerpc/device.h
index d8f9872b0e2d..228ab2a315b9 100644
--- a/include/asm-powerpc/device.h
+++ b/include/asm-powerpc/device.h
@@ -3,5 +3,22 @@
  *
  * This file is released under the GPLv2
  */
-#include <asm-generic/device.h>
+#ifndef _ASM_POWERPC_DEVICE_H
+#define _ASM_POWERPC_DEVICE_H
 
+struct dma_mapping_ops;
+struct device_node;
+
+struct dev_archdata {
+	/* Optional pointer to an OF device node */
+	struct device_node	*of_node;
+
+	/* DMA operations on that device */
+	struct dma_mapping_ops	*dma_ops;
+	void			*dma_data;
+
+	/* NUMA node if applicable */
+	int			numa_node;
+};
+
+#endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/include/asm-powerpc/dma-mapping.h b/include/asm-powerpc/dma-mapping.h
index 2ab9baf78bb4..7e38b5fddada 100644
--- a/include/asm-powerpc/dma-mapping.h
+++ b/include/asm-powerpc/dma-mapping.h
@@ -44,26 +44,150 @@ extern void __dma_sync_page(struct page *page, unsigned long offset,
 #endif /* ! CONFIG_NOT_COHERENT_CACHE */
 
 #ifdef CONFIG_PPC64
+/*
+ * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO
+ */
+struct dma_mapping_ops {
+	void *		(*alloc_coherent)(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t flag);
+	void		(*free_coherent)(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle);
+	dma_addr_t	(*map_single)(struct device *dev, void *ptr,
+				size_t size, enum dma_data_direction direction);
+	void		(*unmap_single)(struct device *dev, dma_addr_t dma_addr,
+				size_t size, enum dma_data_direction direction);
+	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction direction);
+	void		(*unmap_sg)(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction direction);
+	int		(*dma_supported)(struct device *dev, u64 mask);
+	int		(*dac_dma_supported)(struct device *dev, u64 mask);
+	int		(*set_dma_mask)(struct device *dev, u64 dma_mask);
+};
+
+static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+{
+	/* We don't handle the NULL dev case for ISA for now. We could
+	 * do it via an out of line call but it is not needed for now. The
+	 * only ISA DMA device we support is the floppy and we have a hack
+	 * in the floppy driver directly to get a device for us.
+	 */
+	if (unlikely(dev == NULL || dev->archdata.dma_ops == NULL))
+		return NULL;
+	return dev->archdata.dma_ops;
+}
 
-extern int dma_supported(struct device *dev, u64 mask);
-extern int dma_set_mask(struct device *dev, u64 dma_mask);
-extern void *dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag);
-extern void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_handle);
-extern dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-		size_t size, enum dma_data_direction direction);
-extern void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction direction);
-extern dma_addr_t dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction direction);
-extern void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-		size_t size, enum dma_data_direction direction);
-extern int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction direction);
-extern void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nhwentries, enum dma_data_direction direction);
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	if (unlikely(dma_ops == NULL))
+		return 0;
+	if (dma_ops->dma_supported == NULL)
+		return 1;
+	return dma_ops->dma_supported(dev, mask);
+}
+
+static inline int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	if (unlikely(dma_ops == NULL))
+		return -EIO;
+	if (dma_ops->set_dma_mask != NULL)
+		return dma_ops->set_dma_mask(dev, dma_mask);
+	if (!dev->dma_mask || !dma_supported(dev, *dev->dma_mask))
+		return -EIO;
+	*dev->dma_mask = dma_mask;
+	return 0;
+}
+
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
+static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
+					size_t size,
+					enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->map_single(dev, cpu_addr, size, direction);
+}
+
+static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
+				    size_t size,
+				    enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->unmap_single(dev, dma_addr, size, direction);
+}
+
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+				      unsigned long offset, size_t size,
+				      enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->map_single(dev, page_address(page) + offset, size,
+			direction);
+}
+
+static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
+				  size_t size,
+				  enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->unmap_single(dev, dma_address, size, direction);
+}
+
+static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	return dma_ops->map_sg(dev, sg, nents, direction);
+}
+
+static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+				int nhwentries,
+				enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->unmap_sg(dev, sg, nhwentries, direction);
+}
+
+
+/*
+ * Available generic sets of operations
+ */
+extern struct dma_mapping_ops dma_iommu_ops;
+extern struct dma_mapping_ops dma_direct_ops;
+
+extern unsigned long dma_direct_offset;
 
 #else /* CONFIG_PPC64 */
 
@@ -261,25 +385,5 @@ static inline void dma_cache_sync(void *vaddr, size_t size,
 	__dma_sync(vaddr, size, (int)direction);
 }
 
-/*
- * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO
- */
-struct dma_mapping_ops {
-	void *		(*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag);
-	void		(*free_coherent)(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle);
-	dma_addr_t	(*map_single)(struct device *dev, void *ptr,
-				size_t size, enum dma_data_direction direction);
-	void		(*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction direction);
-	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction);
-	void		(*unmap_sg)(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction);
-	int		(*dma_supported)(struct device *dev, u64 mask);
-	int		(*dac_dma_supported)(struct device *dev, u64 mask);
-};
-
 #endif /* __KERNEL__ */
 #endif	/* _ASM_DMA_MAPPING_H */
diff --git a/include/asm-powerpc/eeh.h b/include/asm-powerpc/eeh.h
index 6a784396660b..b886bec67016 100644
--- a/include/asm-powerpc/eeh.h
+++ b/include/asm-powerpc/eeh.h
@@ -120,10 +120,6 @@ static inline u8 eeh_readb(const volatile void __iomem *addr)
 		return eeh_check_failure(addr, val);
 	return val;
 }
-static inline void eeh_writeb(u8 val, volatile void __iomem *addr)
-{
-	out_8(addr, val);
-}
 
 static inline u16 eeh_readw(const volatile void __iomem *addr)
 {
@@ -132,21 +128,6 @@ static inline u16 eeh_readw(const volatile void __iomem *addr)
 		return eeh_check_failure(addr, val);
 	return val;
 }
-static inline void eeh_writew(u16 val, volatile void __iomem *addr)
-{
-	out_le16(addr, val);
-}
-static inline u16 eeh_raw_readw(const volatile void __iomem *addr)
-{
-	u16 val = in_be16(addr);
-	if (EEH_POSSIBLE_ERROR(val, u16))
-		return eeh_check_failure(addr, val);
-	return val;
-}
-static inline void eeh_raw_writew(u16 val, volatile void __iomem *addr) {
-	volatile u16 __iomem *vaddr = (volatile u16 __iomem *) addr;
-	out_be16(vaddr, val);
-}
 
 static inline u32 eeh_readl(const volatile void __iomem *addr)
 {
@@ -155,205 +136,75 @@ static inline u32 eeh_readl(const volatile void __iomem *addr)
 		return eeh_check_failure(addr, val);
 	return val;
 }
-static inline void eeh_writel(u32 val, volatile void __iomem *addr)
-{
-	out_le32(addr, val);
-}
-static inline u32 eeh_raw_readl(const volatile void __iomem *addr)
+
+static inline u64 eeh_readq(const volatile void __iomem *addr)
 {
-	u32 val = in_be32(addr);
-	if (EEH_POSSIBLE_ERROR(val, u32))
+	u64 val = in_le64(addr);
+	if (EEH_POSSIBLE_ERROR(val, u64))
 		return eeh_check_failure(addr, val);
 	return val;
 }
-static inline void eeh_raw_writel(u32 val, volatile void __iomem *addr)
-{
-	out_be32(addr, val);
-}
 
-static inline u64 eeh_readq(const volatile void __iomem *addr)
+static inline u16 eeh_readw_be(const volatile void __iomem *addr)
 {
-	u64 val = in_le64(addr);
-	if (EEH_POSSIBLE_ERROR(val, u64))
+	u16 val = in_be16(addr);
+	if (EEH_POSSIBLE_ERROR(val, u16))
 		return eeh_check_failure(addr, val);
 	return val;
 }
-static inline void eeh_writeq(u64 val, volatile void __iomem *addr)
+
+static inline u32 eeh_readl_be(const volatile void __iomem *addr)
 {
-	out_le64(addr, val);
+	u32 val = in_be32(addr);
+	if (EEH_POSSIBLE_ERROR(val, u32))
+		return eeh_check_failure(addr, val);
+	return val;
 }
-static inline u64 eeh_raw_readq(const volatile void __iomem *addr)
+
+static inline u64 eeh_readq_be(const volatile void __iomem *addr)
 {
 	u64 val = in_be64(addr);
 	if (EEH_POSSIBLE_ERROR(val, u64))
 		return eeh_check_failure(addr, val);
 	return val;
 }
-static inline void eeh_raw_writeq(u64 val, volatile void __iomem *addr)
-{
-	out_be64(addr, val);
-}
-
-#define EEH_CHECK_ALIGN(v,a) \
-	((((unsigned long)(v)) & ((a) - 1)) == 0)
 
-static inline void eeh_memset_io(volatile void __iomem *addr, int c,
-				 unsigned long n)
-{
-	void *p = (void __force *)addr;
-	u32 lc = c;
-	lc |= lc << 8;
-	lc |= lc << 16;
-
-	__asm__ __volatile__ ("sync" : : : "memory");
-	while(n && !EEH_CHECK_ALIGN(p, 4)) {
-		*((volatile u8 *)p) = c;
-		p++;
-		n--;
-	}
-	while(n >= 4) {
-		*((volatile u32 *)p) = lc;
-		p += 4;
-		n -= 4;
-	}
-	while(n) {
-		*((volatile u8 *)p) = c;
-		p++;
-		n--;
-	}
-	__asm__ __volatile__ ("sync" : : : "memory");
-}
-static inline void eeh_memcpy_fromio(void *dest, const volatile void __iomem *src,
+static inline void eeh_memcpy_fromio(void *dest, const
+				     volatile void __iomem *src,
 				     unsigned long n)
 {
-	void *vsrc = (void __force *) src;
-	void *destsave = dest;
-	unsigned long nsave = n;
-
-	__asm__ __volatile__ ("sync" : : : "memory");
-	while(n && (!EEH_CHECK_ALIGN(vsrc, 4) || !EEH_CHECK_ALIGN(dest, 4))) {
-		*((u8 *)dest) = *((volatile u8 *)vsrc);
-		__asm__ __volatile__ ("eieio" : : : "memory");
-		vsrc++;
-		dest++;
-		n--;
-	}
-	while(n > 4) {
-		*((u32 *)dest) = *((volatile u32 *)vsrc);
-		__asm__ __volatile__ ("eieio" : : : "memory");
-		vsrc += 4;
-		dest += 4;
-		n -= 4;
-	}
-	while(n) {
-		*((u8 *)dest) = *((volatile u8 *)vsrc);
-		__asm__ __volatile__ ("eieio" : : : "memory");
-		vsrc++;
-		dest++;
-		n--;
-	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	_memcpy_fromio(dest, src, n);
 
 	/* Look for ffff's here at dest[n].  Assume that at least 4 bytes
 	 * were copied. Check all four bytes.
 	 */
-	if ((nsave >= 4) &&
-		(EEH_POSSIBLE_ERROR((*((u32 *) destsave+nsave-4)), u32))) {
-		eeh_check_failure(src, (*((u32 *) destsave+nsave-4)));
-	}
-}
-
-static inline void eeh_memcpy_toio(volatile void __iomem *dest, const void *src,
-				   unsigned long n)
-{
-	void *vdest = (void __force *) dest;
-
-	__asm__ __volatile__ ("sync" : : : "memory");
-	while(n && (!EEH_CHECK_ALIGN(vdest, 4) || !EEH_CHECK_ALIGN(src, 4))) {
-		*((volatile u8 *)vdest) = *((u8 *)src);
-		src++;
-		vdest++;
-		n--;
-	}
-	while(n > 4) {
-		*((volatile u32 *)vdest) = *((volatile u32 *)src);
-		src += 4;
-		vdest += 4;
-		n-=4;
-	}
-	while(n) {
-		*((volatile u8 *)vdest) = *((u8 *)src);
-		src++;
-		vdest++;
-		n--;
-	}
-	__asm__ __volatile__ ("sync" : : : "memory");
-}
-
-#undef EEH_CHECK_ALIGN
-
-static inline u8 eeh_inb(unsigned long port)
-{
-	u8 val;
-	val = in_8((u8 __iomem *)(port+pci_io_base));
-	if (EEH_POSSIBLE_ERROR(val, u8))
-		return eeh_check_failure((void __iomem *)(port), val);
-	return val;
-}
-
-static inline void eeh_outb(u8 val, unsigned long port)
-{
-	out_8((u8 __iomem *)(port+pci_io_base), val);
-}
-
-static inline u16 eeh_inw(unsigned long port)
-{
-	u16 val;
-	val = in_le16((u16 __iomem *)(port+pci_io_base));
-	if (EEH_POSSIBLE_ERROR(val, u16))
-		return eeh_check_failure((void __iomem *)(port), val);
-	return val;
-}
-
-static inline void eeh_outw(u16 val, unsigned long port)
-{
-	out_le16((u16 __iomem *)(port+pci_io_base), val);
-}
-
-static inline u32 eeh_inl(unsigned long port)
-{
-	u32 val;
-	val = in_le32((u32 __iomem *)(port+pci_io_base));
-	if (EEH_POSSIBLE_ERROR(val, u32))
-		return eeh_check_failure((void __iomem *)(port), val);
-	return val;
-}
-
-static inline void eeh_outl(u32 val, unsigned long port)
-{
-	out_le32((u32 __iomem *)(port+pci_io_base), val);
+	if (n >= 4 && EEH_POSSIBLE_ERROR(*((u32 *)(dest + n - 4)), u32))
+		eeh_check_failure(src, *((u32 *)(dest + n - 4)));
 }
 
 /* in-string eeh macros */
-static inline void eeh_insb(unsigned long port, void * buf, int ns)
+static inline void eeh_readsb(const volatile void __iomem *addr, void * buf,
+			      int ns)
 {
-	_insb((u8 __iomem *)(port+pci_io_base), buf, ns);
+	_insb(addr, buf, ns);
 	if (EEH_POSSIBLE_ERROR((*(((u8*)buf)+ns-1)), u8))
-		eeh_check_failure((void __iomem *)(port), *(u8*)buf);
+		eeh_check_failure(addr, *(u8*)buf);
 }
 
-static inline void eeh_insw_ns(unsigned long port, void * buf, int ns)
+static inline void eeh_readsw(const volatile void __iomem *addr, void * buf,
+			      int ns)
 {
-	_insw_ns((u16 __iomem *)(port+pci_io_base), buf, ns);
+	_insw(addr, buf, ns);
 	if (EEH_POSSIBLE_ERROR((*(((u16*)buf)+ns-1)), u16))
-		eeh_check_failure((void __iomem *)(port), *(u16*)buf);
+		eeh_check_failure(addr, *(u16*)buf);
 }
 
-static inline void eeh_insl_ns(unsigned long port, void * buf, int nl)
+static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
+			      int nl)
 {
-	_insl_ns((u32 __iomem *)(port+pci_io_base), buf, nl);
+	_insl(addr, buf, nl);
 	if (EEH_POSSIBLE_ERROR((*(((u32*)buf)+nl-1)), u32))
-		eeh_check_failure((void __iomem *)(port), *(u32*)buf);
+		eeh_check_failure(addr, *(u32*)buf);
 }
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-powerpc/elf.h b/include/asm-powerpc/elf.h
index 9a83a987d396..b5436642a109 100644
--- a/include/asm-powerpc/elf.h
+++ b/include/asm-powerpc/elf.h
@@ -411,4 +411,17 @@ do {									\
 /* Keep this the last entry.  */
 #define R_PPC64_NUM		107
 
+#ifdef CONFIG_SPU_BASE
+/* Notes used in ET_CORE. Note name is "SPU/<fd>/<filename>". */
+#define NT_SPU		1
+
+extern int arch_notes_size(void);
+extern void arch_write_notes(struct file *file);
+
+#define ELF_CORE_EXTRA_NOTES_SIZE arch_notes_size()
+#define ELF_CORE_WRITE_EXTRA_NOTES arch_write_notes(file)
+
+#define ARCH_HAVE_EXTRA_ELF_NOTES
+#endif /* CONFIG_PPC_CELL */
+
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/include/asm-powerpc/firmware.h b/include/asm-powerpc/firmware.h
index fdf9aff71150..98f7b62422c9 100644
--- a/include/asm-powerpc/firmware.h
+++ b/include/asm-powerpc/firmware.h
@@ -42,6 +42,7 @@
 #define FW_FEATURE_SPLPAR	ASM_CONST(0x0000000000100000)
 #define FW_FEATURE_ISERIES	ASM_CONST(0x0000000000200000)
 #define FW_FEATURE_LPAR		ASM_CONST(0x0000000000400000)
+#define FW_FEATURE_PS3_LV1	ASM_CONST(0x0000000000800000)
 
 #ifndef __ASSEMBLY__
 
@@ -58,6 +59,10 @@ enum {
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
 	FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
+	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
+	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
+	FW_FEATURE_NATIVE_POSSIBLE = 0,
+	FW_FEATURE_NATIVE_ALWAYS = 0,
 	FW_FEATURE_POSSIBLE =
 #ifdef CONFIG_PPC_PSERIES
 		FW_FEATURE_PSERIES_POSSIBLE |
@@ -65,6 +70,12 @@ enum {
 #ifdef CONFIG_PPC_ISERIES
 		FW_FEATURE_ISERIES_POSSIBLE |
 #endif
+#ifdef CONFIG_PPC_PS3
+		FW_FEATURE_PS3_POSSIBLE |
+#endif
+#ifdef CONFIG_PPC_NATIVE
+		FW_FEATURE_NATIVE_ALWAYS |
+#endif
 		0,
 	FW_FEATURE_ALWAYS =
 #ifdef CONFIG_PPC_PSERIES
@@ -73,6 +84,12 @@ enum {
 #ifdef CONFIG_PPC_ISERIES
 		FW_FEATURE_ISERIES_ALWAYS &
 #endif
+#ifdef CONFIG_PPC_PS3
+		FW_FEATURE_PS3_ALWAYS &
+#endif
+#ifdef CONFIG_PPC_NATIVE
+		FW_FEATURE_NATIVE_ALWAYS &
+#endif
 		FW_FEATURE_POSSIBLE,
 
 #else /* CONFIG_PPC64 */
diff --git a/include/asm-powerpc/hw_irq.h b/include/asm-powerpc/hw_irq.h
index d40359204aba..d604863d72fb 100644
--- a/include/asm-powerpc/hw_irq.h
+++ b/include/asm-powerpc/hw_irq.h
@@ -7,16 +7,40 @@
 #ifdef __KERNEL__
 
 #include <linux/errno.h>
+#include <linux/compiler.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 
 extern void timer_interrupt(struct pt_regs *);
 
-#ifdef CONFIG_PPC_ISERIES
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+
+static inline unsigned long local_get_flags(void)
+{
+	unsigned long flags;
+
+	__asm__ __volatile__("lbz %0,%1(13)"
+	: "=r" (flags)
+	: "i" (offsetof(struct paca_struct, soft_enabled)));
+
+	return flags;
+}
+
+static inline unsigned long local_irq_disable(void)
+{
+	unsigned long flags, zero;
+
+	__asm__ __volatile__("li %1,0; lbz %0,%2(13); stb %1,%2(13)"
+	: "=r" (flags), "=&r" (zero)
+	: "i" (offsetof(struct paca_struct, soft_enabled))
+	: "memory");
+
+	return flags;
+}
 
-extern unsigned long local_get_flags(void);
-extern unsigned long local_irq_disable(void);
 extern void local_irq_restore(unsigned long);
+extern void iseries_handle_interrupts(void);
 
 #define local_irq_enable()	local_irq_restore(1)
 #define local_save_flags(flags)	((flags) = local_get_flags())
@@ -24,17 +48,14 @@ extern void local_irq_restore(unsigned long);
 
 #define irqs_disabled()		(local_get_flags() == 0)
 
+#define hard_irq_enable()	__mtmsrd(mfmsr() | MSR_EE, 1)
+#define hard_irq_disable()	__mtmsrd(mfmsr() & ~MSR_EE, 1)
+
 #else
 
 #if defined(CONFIG_BOOKE)
 #define SET_MSR_EE(x)	mtmsr(x)
 #define local_irq_restore(flags)	__asm__ __volatile__("wrtee %0" : : "r" (flags) : "memory")
-#elif defined(__powerpc64__)
-#define SET_MSR_EE(x)	__mtmsrd(x, 1)
-#define local_irq_restore(flags) do { \
-	__asm__ __volatile__("": : :"memory"); \
-	__mtmsrd((flags), 1); \
-} while(0)
 #else
 #define SET_MSR_EE(x)	mtmsr(x)
 #define local_irq_restore(flags)	mtmsr(flags)
@@ -81,7 +102,10 @@ static inline void local_irq_save_ptr(unsigned long *flags)
 #define local_irq_save(flags)	local_irq_save_ptr(&flags)
 #define irqs_disabled()		((mfmsr() & MSR_EE) == 0)
 
-#endif /* CONFIG_PPC_ISERIES */
+#define hard_irq_enable()	local_irq_enable()
+#define hard_irq_disable()	local_irq_disable()
+
+#endif /* CONFIG_PPC64 */
 
 #define mask_irq(irq)						\
 	({							\
diff --git a/include/asm-powerpc/ibmebus.h b/include/asm-powerpc/ibmebus.h
index 3493429b70f5..66112114b8c5 100644
--- a/include/asm-powerpc/ibmebus.h
+++ b/include/asm-powerpc/ibmebus.h
@@ -44,7 +44,6 @@
 #include <linux/mod_devicetable.h>
 #include <asm/of_device.h>
 
-extern struct dma_mapping_ops ibmebus_dma_ops;
 extern struct bus_type ibmebus_bus_type;
 
 struct ibmebus_dev {	
diff --git a/include/asm-powerpc/ide.h b/include/asm-powerpc/ide.h
index c8390f9485de..0f66f0f82c32 100644
--- a/include/asm-powerpc/ide.h
+++ b/include/asm-powerpc/ide.h
@@ -22,10 +22,10 @@
 #endif
 #endif
 
-#define __ide_mm_insw(p, a, c)	_insw_ns((volatile u16 __iomem *)(p), (a), (c))
-#define __ide_mm_insl(p, a, c)	_insl_ns((volatile u32 __iomem *)(p), (a), (c))
-#define __ide_mm_outsw(p, a, c)	_outsw_ns((volatile u16 __iomem *)(p), (a), (c))
-#define __ide_mm_outsl(p, a, c)	_outsl_ns((volatile u32 __iomem *)(p), (a), (c))
+#define __ide_mm_insw(p, a, c)	readsw((void __iomem *)(p), (a), (c))
+#define __ide_mm_insl(p, a, c)	readsl((void __iomem *)(p), (a), (c))
+#define __ide_mm_outsw(p, a, c)	writesw((void __iomem *)(p), (a), (c))
+#define __ide_mm_outsl(p, a, c)	writesl((void __iomem *)(p), (a), (c))
 
 #ifndef  __powerpc64__
 #include <linux/hdreg.h>
diff --git a/include/asm-powerpc/immap_qe.h b/include/asm-powerpc/immap_qe.h
index ce12f85fff9b..9fdd0491f6a3 100644
--- a/include/asm-powerpc/immap_qe.h
+++ b/include/asm-powerpc/immap_qe.h
@@ -136,22 +136,7 @@ struct qe_timers {
 
 /* BRG */
 struct qe_brg {
-	__be32	brgc1;		/* BRG1 configuration register */
-	__be32	brgc2;		/* BRG2 configuration register */
-	__be32	brgc3;		/* BRG3 configuration register */
-	__be32	brgc4;		/* BRG4 configuration register */
-	__be32	brgc5;		/* BRG5 configuration register */
-	__be32	brgc6;		/* BRG6 configuration register */
-	__be32	brgc7;		/* BRG7 configuration register */
-	__be32	brgc8;		/* BRG8 configuration register */
-	__be32	brgc9;		/* BRG9 configuration register */
-	__be32	brgc10;		/* BRG10 configuration register */
-	__be32	brgc11;		/* BRG11 configuration register */
-	__be32	brgc12;		/* BRG12 configuration register */
-	__be32	brgc13;		/* BRG13 configuration register */
-	__be32	brgc14;		/* BRG14 configuration register */
-	__be32	brgc15;		/* BRG15 configuration register */
-	__be32	brgc16;		/* BRG16 configuration register */
+	__be32	brgc[16];	/* BRG configuration registers */
 	u8	res0[0x40];
 } __attribute__ ((packed));
 
diff --git a/include/asm-powerpc/io-defs.h b/include/asm-powerpc/io-defs.h
new file mode 100644
index 000000000000..03691ab69217
--- /dev/null
+++ b/include/asm-powerpc/io-defs.h
@@ -0,0 +1,59 @@
+/* This file is meant to be include multiple times by other headers */
+
+DEF_PCI_AC_RET(readb, u8, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_RET(readw, u16, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_RET(readl, u32, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_RET(readw_be, u16, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_RET(readl_be, u32, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_NORET(writeb, (u8 val, PCI_IO_ADDR addr), (val, addr))
+DEF_PCI_AC_NORET(writew, (u16 val, PCI_IO_ADDR addr), (val, addr))
+DEF_PCI_AC_NORET(writel, (u32 val, PCI_IO_ADDR addr), (val, addr))
+DEF_PCI_AC_NORET(writew_be, (u16 val, PCI_IO_ADDR addr), (val, addr))
+DEF_PCI_AC_NORET(writel_be, (u32 val, PCI_IO_ADDR addr), (val, addr))
+
+#ifdef __powerpc64__
+DEF_PCI_AC_RET(readq, u64, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_RET(readq_be, u64, (const PCI_IO_ADDR addr), (addr))
+DEF_PCI_AC_NORET(writeq, (u64 val, PCI_IO_ADDR addr), (val, addr))
+DEF_PCI_AC_NORET(writeq_be, (u64 val, PCI_IO_ADDR addr), (val, addr))
+#endif /* __powerpc64__ */
+
+DEF_PCI_AC_RET(inb, u8, (unsigned long port), (port))
+DEF_PCI_AC_RET(inw, u16, (unsigned long port), (port))
+DEF_PCI_AC_RET(inl, u32, (unsigned long port), (port))
+DEF_PCI_AC_NORET(outb, (u8 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(outw, (u16 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(outl, (u32 val, unsigned long port), (val, port))
+
+DEF_PCI_AC_NORET(readsb, (const PCI_IO_ADDR a, void *b, unsigned long c), \
+		 (a, b, c))
+DEF_PCI_AC_NORET(readsw, (const PCI_IO_ADDR a, void *b, unsigned long c), \
+		 (a, b, c))
+DEF_PCI_AC_NORET(readsl, (const PCI_IO_ADDR a, void *b, unsigned long c), \
+		 (a, b, c))
+DEF_PCI_AC_NORET(writesb, (PCI_IO_ADDR a, const void *b, unsigned long c), \
+		 (a, b, c))
+DEF_PCI_AC_NORET(writesw, (PCI_IO_ADDR a, const void *b, unsigned long c), \
+		 (a, b, c))
+DEF_PCI_AC_NORET(writesl, (PCI_IO_ADDR a, const void *b, unsigned long c), \
+		 (a, b, c))
+
+DEF_PCI_AC_NORET(insb, (unsigned long p, void *b, unsigned long c), \
+		 (p, b, c))
+DEF_PCI_AC_NORET(insw, (unsigned long p, void *b, unsigned long c), \
+		 (p, b, c))
+DEF_PCI_AC_NORET(insl, (unsigned long p, void *b, unsigned long c), \
+		 (p, b, c))
+DEF_PCI_AC_NORET(outsb, (unsigned long p, const void *b, unsigned long c), \
+		 (p, b, c))
+DEF_PCI_AC_NORET(outsw, (unsigned long p, const void *b, unsigned long c), \
+		 (p, b, c))
+DEF_PCI_AC_NORET(outsl, (unsigned long p, const void *b, unsigned long c), \
+		 (p, b, c))
+
+DEF_PCI_AC_NORET(memset_io, (PCI_IO_ADDR a, int c, unsigned long n),	   \
+		 (a, c, n))
+DEF_PCI_AC_NORET(memcpy_fromio,(void *d,const PCI_IO_ADDR s,unsigned long n), \
+		 (d, s, n))
+DEF_PCI_AC_NORET(memcpy_toio,(PCI_IO_ADDR d,const void *s,unsigned long n),   \
+		 (d, s, n))
diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h
index c2c5f14b5f5f..1cd532379c30 100644
--- a/include/asm-powerpc/io.h
+++ b/include/asm-powerpc/io.h
@@ -13,154 +13,530 @@
 extern int check_legacy_ioport(unsigned long base_port);
 #define PNPBIOS_BASE	0xf000	/* only relevant for PReP */
 
-#ifndef CONFIG_PPC64
-#include <asm-ppc/io.h>
-#else
-
 #include <linux/compiler.h>
 #include <asm/page.h>
 #include <asm/byteorder.h>
-#include <asm/paca.h>
 #include <asm/synch.h>
 #include <asm/delay.h>
+#include <asm/mmu.h>
 
 #include <asm-generic/iomap.h>
 
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+#endif
+
 #define SIO_CONFIG_RA	0x398
 #define SIO_CONFIG_RD	0x399
 
 #define SLOW_DOWN_IO
 
+/* 32 bits uses slightly different variables for the various IO
+ * bases. Most of this file only uses _IO_BASE though which we
+ * define properly based on the platform
+ */
+#ifndef CONFIG_PCI
+#define _IO_BASE	0
+#define _ISA_MEM_BASE	0
+#define PCI_DRAM_OFFSET 0
+#elif defined(CONFIG_PPC32)
+#define _IO_BASE	isa_io_base
+#define _ISA_MEM_BASE	isa_mem_base
+#define PCI_DRAM_OFFSET	pci_dram_offset
+#else
+#define _IO_BASE	pci_io_base
+#define _ISA_MEM_BASE	0
+#define PCI_DRAM_OFFSET	0
+#endif
+
 extern unsigned long isa_io_base;
+extern unsigned long isa_mem_base;
 extern unsigned long pci_io_base;
+extern unsigned long pci_dram_offset;
+
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_INDIRECT_IO)
+#error CONFIG_PPC_INDIRECT_IO is not yet supported on 32 bits
+#endif
+
+/*
+ *
+ * Low level MMIO accessors
+ *
+ * This provides the non-bus specific accessors to MMIO. Those are PowerPC
+ * specific and thus shouldn't be used in generic code. The accessors
+ * provided here are:
+ *
+ *	in_8, in_le16, in_be16, in_le32, in_be32, in_le64, in_be64
+ *	out_8, out_le16, out_be16, out_le32, out_be32, out_le64, out_be64
+ *	_insb, _insw_ns, _insl_ns, _outsb, _outsw_ns, _outsl_ns
+ *
+ * Those operate directly on a kernel virtual address. Note that the prototype
+ * for the out_* accessors has the arguments in opposite order from the usual
+ * linux PCI accessors. Unlike those, they take the address first and the value
+ * next.
+ *
+ * Note: I might drop the _ns suffix on the stream operations soon as it is
+ * simply normal for stream operations to not swap in the first place.
+ *
+ */
+
+#ifdef CONFIG_PPC64
+#define IO_SET_SYNC_FLAG()	do { get_paca()->io_sync = 1; } while(0)
+#else
+#define IO_SET_SYNC_FLAG()
+#endif
+
+#define DEF_MMIO_IN(name, type, insn)					\
+static inline type name(const volatile type __iomem *addr)		\
+{									\
+	type ret;							\
+	__asm__ __volatile__("sync;" insn ";twi 0,%0,0;isync"		\
+ 		: "=r" (ret) : "r" (addr), "m" (*addr));		\
+	return ret;							\
+}
+
+#define DEF_MMIO_OUT(name, type, insn)					\
+static inline void name(volatile type __iomem *addr, type val)		\
+{									\
+	__asm__ __volatile__("sync;" insn				\
+ 		: "=m" (*addr) : "r" (val), "r" (addr));		\
+	IO_SET_SYNC_FLAG();					\
+}
+
+
+#define DEF_MMIO_IN_BE(name, size, insn) \
+	DEF_MMIO_IN(name, u##size, __stringify(insn)"%U2%X2 %0,%2")
+#define DEF_MMIO_IN_LE(name, size, insn) \
+	DEF_MMIO_IN(name, u##size, __stringify(insn)" %0,0,%1")
+
+#define DEF_MMIO_OUT_BE(name, size, insn) \
+	DEF_MMIO_OUT(name, u##size, __stringify(insn)"%U0%X0 %1,%0")
+#define DEF_MMIO_OUT_LE(name, size, insn) \
+	DEF_MMIO_OUT(name, u##size, __stringify(insn)" %1,0,%2")
+
+DEF_MMIO_IN_BE(in_8,     8, lbz);
+DEF_MMIO_IN_BE(in_be16, 16, lhz);
+DEF_MMIO_IN_BE(in_be32, 32, lwz);
+DEF_MMIO_IN_LE(in_le16, 16, lhbrx);
+DEF_MMIO_IN_LE(in_le32, 32, lwbrx);
+
+DEF_MMIO_OUT_BE(out_8,     8, stb);
+DEF_MMIO_OUT_BE(out_be16, 16, sth);
+DEF_MMIO_OUT_BE(out_be32, 32, stw);
+DEF_MMIO_OUT_LE(out_le16, 16, sthbrx);
+DEF_MMIO_OUT_LE(out_le32, 32, stwbrx);
+
+#ifdef __powerpc64__
+DEF_MMIO_OUT_BE(out_be64, 64, std);
+DEF_MMIO_IN_BE(in_be64, 64, ld);
+
+/* There is no asm instructions for 64 bits reverse loads and stores */
+static inline u64 in_le64(const volatile u64 __iomem *addr)
+{
+	return le64_to_cpu(in_be64(addr));
+}
+
+static inline void out_le64(volatile u64 __iomem *addr, u64 val)
+{
+	out_be64(addr, cpu_to_le64(val));
+}
+#endif /* __powerpc64__ */
+
+/*
+ * Low level IO stream instructions are defined out of line for now
+ */
+extern void _insb(const volatile u8 __iomem *addr, void *buf, long count);
+extern void _outsb(volatile u8 __iomem *addr,const void *buf,long count);
+extern void _insw_ns(const volatile u16 __iomem *addr, void *buf, long count);
+extern void _outsw_ns(volatile u16 __iomem *addr, const void *buf, long count);
+extern void _insl_ns(const volatile u32 __iomem *addr, void *buf, long count);
+extern void _outsl_ns(volatile u32 __iomem *addr, const void *buf, long count);
+
+/* The _ns naming is historical and will be removed. For now, just #define
+ * the non _ns equivalent names
+ */
+#define _insw	_insw_ns
+#define _insl	_insl_ns
+#define _outsw	_outsw_ns
+#define _outsl	_outsl_ns
+
+
+/*
+ * memset_io, memcpy_toio, memcpy_fromio base implementations are out of line
+ */
+
+extern void _memset_io(volatile void __iomem *addr, int c, unsigned long n);
+extern void _memcpy_fromio(void *dest, const volatile void __iomem *src,
+			   unsigned long n);
+extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
+			 unsigned long n);
+
+/*
+ *
+ * PCI and standard ISA accessors
+ *
+ * Those are globally defined linux accessors for devices on PCI or ISA
+ * busses. They follow the Linux defined semantics. The current implementation
+ * for PowerPC is as close as possible to the x86 version of these, and thus
+ * provides fairly heavy weight barriers for the non-raw versions
+ *
+ * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_IO
+ * allowing the platform to provide its own implementation of some or all
+ * of the accessors.
+ */
+
+/*
+ * Include the EEH definitions when EEH is enabled only so they don't get
+ * in the way when building for 32 bits
+ */
+#ifdef CONFIG_EEH
+#include <asm/eeh.h>
+#endif
+
+/* Shortcut to the MMIO argument pointer */
+#define PCI_IO_ADDR	volatile void __iomem *
+
+/* Indirect IO address tokens:
+ *
+ * When CONFIG_PPC_INDIRECT_IO is set, the platform can provide hooks
+ * on all IOs. (Note that this is all 64 bits only for now)
+ *
+ * To help platforms who may need to differenciate MMIO addresses in
+ * their hooks, a bitfield is reserved for use by the platform near the
+ * top of MMIO addresses (not PIO, those have to cope the hard way).
+ *
+ * This bit field is 12 bits and is at the top of the IO virtual
+ * addresses PCI_IO_INDIRECT_TOKEN_MASK.
+ *
+ * The kernel virtual space is thus:
+ *
+ *  0xD000000000000000		: vmalloc
+ *  0xD000080000000000		: PCI PHB IO space
+ *  0xD000080080000000		: ioremap
+ *  0xD0000fffffffffff		: end of ioremap region
+ *
+ * Since the top 4 bits are reserved as the region ID, we use thus
+ * the next 12 bits and keep 4 bits available for the future if the
+ * virtual address space is ever to be extended.
+ *
+ * The direct IO mapping operations will then mask off those bits
+ * before doing the actual access, though that only happen when
+ * CONFIG_PPC_INDIRECT_IO is set, thus be careful when you use that
+ * mechanism
+ */
+
+#ifdef CONFIG_PPC_INDIRECT_IO
+#define PCI_IO_IND_TOKEN_MASK	0x0fff000000000000ul
+#define PCI_IO_IND_TOKEN_SHIFT	48
+#define PCI_FIX_ADDR(addr)						\
+	((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK))
+#define PCI_GET_ADDR_TOKEN(addr)					\
+	(((unsigned long)(addr) & PCI_IO_IND_TOKEN_MASK) >> 		\
+		PCI_IO_IND_TOKEN_SHIFT)
+#define PCI_SET_ADDR_TOKEN(addr, token) 				\
+do {									\
+	unsigned long __a = (unsigned long)(addr);			\
+	__a &= ~PCI_IO_IND_TOKEN_MASK;					\
+	__a |= ((unsigned long)(token)) << PCI_IO_IND_TOKEN_SHIFT;	\
+	(addr) = (void __iomem *)__a;					\
+} while(0)
+#else
+#define PCI_FIX_ADDR(addr) (addr)
+#endif
 
-#ifdef CONFIG_PPC_ISERIES
-
-extern int in_8(const volatile unsigned char __iomem *addr);
-extern void out_8(volatile unsigned char __iomem *addr, int val);
-extern int in_le16(const volatile unsigned short __iomem *addr);
-extern int in_be16(const volatile unsigned short __iomem *addr);
-extern void out_le16(volatile unsigned short __iomem *addr, int val);
-extern void out_be16(volatile unsigned short __iomem *addr, int val);
-extern unsigned in_le32(const volatile unsigned __iomem *addr);
-extern unsigned in_be32(const volatile unsigned __iomem *addr);
-extern void out_le32(volatile unsigned __iomem *addr, int val);
-extern void out_be32(volatile unsigned __iomem *addr, int val);
-extern unsigned long in_le64(const volatile unsigned long __iomem *addr);
-extern unsigned long in_be64(const volatile unsigned long __iomem *addr);
-extern void out_le64(volatile unsigned long __iomem *addr, unsigned long val);
-extern void out_be64(volatile unsigned long __iomem *addr, unsigned long val);
-
-extern unsigned char __raw_readb(const volatile void __iomem *addr);
-extern unsigned short __raw_readw(const volatile void __iomem *addr);
-extern unsigned int __raw_readl(const volatile void __iomem *addr);
-extern unsigned long __raw_readq(const volatile void __iomem *addr);
-extern void __raw_writeb(unsigned char v, volatile void __iomem *addr);
-extern void __raw_writew(unsigned short v, volatile void __iomem *addr);
-extern void __raw_writel(unsigned int v, volatile void __iomem *addr);
-extern void __raw_writeq(unsigned long v, volatile void __iomem *addr);
-
-extern void memset_io(volatile void __iomem *addr, int c, unsigned long n);
-extern void memcpy_fromio(void *dest, const volatile void __iomem *src,
-                                 unsigned long n);
-extern void memcpy_toio(volatile void __iomem *dest, const void *src,
-                                 unsigned long n);
-
-#else /* CONFIG_PPC_ISERIES */
-
-#define in_8(addr)		__in_8((addr))
-#define out_8(addr, val)	__out_8((addr), (val))
-#define in_le16(addr)		__in_le16((addr))
-#define in_be16(addr)		__in_be16((addr))
-#define out_le16(addr, val)	__out_le16((addr), (val))
-#define out_be16(addr, val)	__out_be16((addr), (val))
-#define in_le32(addr)		__in_le32((addr))
-#define in_be32(addr)		__in_be32((addr))
-#define out_le32(addr, val)	__out_le32((addr), (val))
-#define out_be32(addr, val)	__out_be32((addr), (val))
-#define in_le64(addr)		__in_le64((addr))
-#define in_be64(addr)		__in_be64((addr))
-#define out_le64(addr, val)	__out_le64((addr), (val))
-#define out_be64(addr, val)	__out_be64((addr), (val))
+
+/*
+ * Non ordered and non-swapping "raw" accessors
+ */
 
 static inline unsigned char __raw_readb(const volatile void __iomem *addr)
 {
-	return *(volatile unsigned char __force *)addr;
+	return *(volatile unsigned char __force *)PCI_FIX_ADDR(addr);
 }
 static inline unsigned short __raw_readw(const volatile void __iomem *addr)
 {
-	return *(volatile unsigned short __force *)addr;
+	return *(volatile unsigned short __force *)PCI_FIX_ADDR(addr);
 }
 static inline unsigned int __raw_readl(const volatile void __iomem *addr)
 {
-	return *(volatile unsigned int __force *)addr;
-}
-static inline unsigned long __raw_readq(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned long __force *)addr;
+	return *(volatile unsigned int __force *)PCI_FIX_ADDR(addr);
 }
 static inline void __raw_writeb(unsigned char v, volatile void __iomem *addr)
 {
-	*(volatile unsigned char __force *)addr = v;
+	*(volatile unsigned char __force *)PCI_FIX_ADDR(addr) = v;
 }
 static inline void __raw_writew(unsigned short v, volatile void __iomem *addr)
 {
-	*(volatile unsigned short __force *)addr = v;
+	*(volatile unsigned short __force *)PCI_FIX_ADDR(addr) = v;
 }
 static inline void __raw_writel(unsigned int v, volatile void __iomem *addr)
 {
-	*(volatile unsigned int __force *)addr = v;
+	*(volatile unsigned int __force *)PCI_FIX_ADDR(addr) = v;
+}
+
+#ifdef __powerpc64__
+static inline unsigned long __raw_readq(const volatile void __iomem *addr)
+{
+	return *(volatile unsigned long __force *)PCI_FIX_ADDR(addr);
 }
 static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr)
 {
-	*(volatile unsigned long __force *)addr = v;
+	*(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v;
+}
+#endif /* __powerpc64__ */
+
+/*
+ *
+ * PCI PIO and MMIO accessors.
+ *
+ *
+ * On 32 bits, PIO operations have a recovery mechanism in case they trigger
+ * machine checks (which they occasionally do when probing non existing
+ * IO ports on some platforms, like PowerMac and 8xx).
+ * I always found it to be of dubious reliability and I am tempted to get
+ * rid of it one of these days. So if you think it's important to keep it,
+ * please voice up asap. We never had it for 64 bits and I do not intend
+ * to port it over
+ */
+
+#ifdef CONFIG_PPC32
+
+#define __do_in_asm(name, op)				\
+static inline unsigned int name(unsigned int port)	\
+{							\
+	unsigned int x;					\
+	__asm__ __volatile__(				\
+		"sync\n"				\
+		"0:"	op "	%0,0,%1\n"		\
+		"1:	twi	0,%0,0\n"		\
+		"2:	isync\n"			\
+		"3:	nop\n"				\
+		"4:\n"					\
+		".section .fixup,\"ax\"\n"		\
+		"5:	li	%0,-1\n"		\
+		"	b	4b\n"			\
+		".previous\n"				\
+		".section __ex_table,\"a\"\n"		\
+		"	.align	2\n"			\
+		"	.long	0b,5b\n"		\
+		"	.long	1b,5b\n"		\
+		"	.long	2b,5b\n"		\
+		"	.long	3b,5b\n"		\
+		".previous"				\
+		: "=&r" (x)				\
+		: "r" (port + _IO_BASE));		\
+	return x;					\
+}
+
+#define __do_out_asm(name, op)				\
+static inline void name(unsigned int val, unsigned int port) \
+{							\
+	__asm__ __volatile__(				\
+		"sync\n"				\
+		"0:" op " %0,0,%1\n"			\
+		"1:	sync\n"				\
+		"2:\n"					\
+		".section __ex_table,\"a\"\n"		\
+		"	.align	2\n"			\
+		"	.long	0b,2b\n"		\
+		"	.long	1b,2b\n"		\
+		".previous"				\
+		: : "r" (val), "r" (port + _IO_BASE));	\
+}
+
+__do_in_asm(_rec_inb, "lbzx")
+__do_in_asm(_rec_inw, "lhbrx")
+__do_in_asm(_rec_inl, "lwbrx")
+__do_out_asm(_rec_outb, "stbx")
+__do_out_asm(_rec_outw, "sthbrx")
+__do_out_asm(_rec_outl, "stwbrx")
+
+#endif /* CONFIG_PPC32 */
+
+/* The "__do_*" operations below provide the actual "base" implementation
+ * for each of the defined acccessor. Some of them use the out_* functions
+ * directly, some of them still use EEH, though we might change that in the
+ * future. Those macros below provide the necessary argument swapping and
+ * handling of the IO base for PIO.
+ *
+ * They are themselves used by the macros that define the actual accessors
+ * and can be used by the hooks if any.
+ *
+ * Note that PIO operations are always defined in terms of their corresonding
+ * MMIO operations. That allows platforms like iSeries who want to modify the
+ * behaviour of both to only hook on the MMIO version and get both. It's also
+ * possible to hook directly at the toplevel PIO operation if they have to
+ * be handled differently
+ */
+#define __do_writeb(val, addr)	out_8(PCI_FIX_ADDR(addr), val)
+#define __do_writew(val, addr)	out_le16(PCI_FIX_ADDR(addr), val)
+#define __do_writel(val, addr)	out_le32(PCI_FIX_ADDR(addr), val)
+#define __do_writeq(val, addr)	out_le64(PCI_FIX_ADDR(addr), val)
+#define __do_writew_be(val, addr) out_be16(PCI_FIX_ADDR(addr), val)
+#define __do_writel_be(val, addr) out_be32(PCI_FIX_ADDR(addr), val)
+#define __do_writeq_be(val, addr) out_be64(PCI_FIX_ADDR(addr), val)
+
+#ifdef CONFIG_EEH
+#define __do_readb(addr)	eeh_readb(PCI_FIX_ADDR(addr))
+#define __do_readw(addr)	eeh_readw(PCI_FIX_ADDR(addr))
+#define __do_readl(addr)	eeh_readl(PCI_FIX_ADDR(addr))
+#define __do_readq(addr)	eeh_readq(PCI_FIX_ADDR(addr))
+#define __do_readw_be(addr)	eeh_readw_be(PCI_FIX_ADDR(addr))
+#define __do_readl_be(addr)	eeh_readl_be(PCI_FIX_ADDR(addr))
+#define __do_readq_be(addr)	eeh_readq_be(PCI_FIX_ADDR(addr))
+#else /* CONFIG_EEH */
+#define __do_readb(addr)	in_8(PCI_FIX_ADDR(addr))
+#define __do_readw(addr)	in_le16(PCI_FIX_ADDR(addr))
+#define __do_readl(addr)	in_le32(PCI_FIX_ADDR(addr))
+#define __do_readq(addr)	in_le64(PCI_FIX_ADDR(addr))
+#define __do_readw_be(addr)	in_be16(PCI_FIX_ADDR(addr))
+#define __do_readl_be(addr)	in_be32(PCI_FIX_ADDR(addr))
+#define __do_readq_be(addr)	in_be64(PCI_FIX_ADDR(addr))
+#endif /* !defined(CONFIG_EEH) */
+
+#ifdef CONFIG_PPC32
+#define __do_outb(val, port)	_rec_outb(val, port)
+#define __do_outw(val, port)	_rec_outw(val, port)
+#define __do_outl(val, port)	_rec_outl(val, port)
+#define __do_inb(port)		_rec_inb(port)
+#define __do_inw(port)		_rec_inw(port)
+#define __do_inl(port)		_rec_inl(port)
+#else /* CONFIG_PPC32 */
+#define __do_outb(val, port)	writeb(val,(PCI_IO_ADDR)_IO_BASE+port);
+#define __do_outw(val, port)	writew(val,(PCI_IO_ADDR)_IO_BASE+port);
+#define __do_outl(val, port)	writel(val,(PCI_IO_ADDR)_IO_BASE+port);
+#define __do_inb(port)		readb((PCI_IO_ADDR)_IO_BASE + port);
+#define __do_inw(port)		readw((PCI_IO_ADDR)_IO_BASE + port);
+#define __do_inl(port)		readl((PCI_IO_ADDR)_IO_BASE + port);
+#endif /* !CONFIG_PPC32 */
+
+#ifdef CONFIG_EEH
+#define __do_readsb(a, b, n)	eeh_readsb(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsw(a, b, n)	eeh_readsw(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsl(a, b, n)	eeh_readsl(PCI_FIX_ADDR(a), (b), (n))
+#else /* CONFIG_EEH */
+#define __do_readsb(a, b, n)	_insb(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsw(a, b, n)	_insw(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsl(a, b, n)	_insl(PCI_FIX_ADDR(a), (b), (n))
+#endif /* !CONFIG_EEH */
+#define __do_writesb(a, b, n)	_outsb(PCI_FIX_ADDR(a),(b),(n))
+#define __do_writesw(a, b, n)	_outsw(PCI_FIX_ADDR(a),(b),(n))
+#define __do_writesl(a, b, n)	_outsl(PCI_FIX_ADDR(a),(b),(n))
+
+#define __do_insb(p, b, n)	readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
+#define __do_insw(p, b, n)	readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
+#define __do_insl(p, b, n)	readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
+#define __do_outsb(p, b, n)	writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
+#define __do_outsw(p, b, n)	writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
+#define __do_outsl(p, b, n)	writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
+
+#define __do_memset_io(addr, c, n)	\
+				_memset_io(PCI_FIX_ADDR(addr), c, n)
+#define __do_memcpy_toio(dst, src, n)	\
+				_memcpy_toio(PCI_FIX_ADDR(dst), src, n)
+
+#ifdef CONFIG_EEH
+#define __do_memcpy_fromio(dst, src, n)	\
+				eeh_memcpy_fromio(dst, PCI_FIX_ADDR(src), n)
+#else /* CONFIG_EEH */
+#define __do_memcpy_fromio(dst, src, n)	\
+				_memcpy_fromio(dst,PCI_FIX_ADDR(src),n)
+#endif /* !CONFIG_EEH */
+
+#ifdef CONFIG_PPC_INDIRECT_IO
+#define DEF_PCI_HOOK(x)		x
+#else
+#define DEF_PCI_HOOK(x)		NULL
+#endif
+
+/* Structure containing all the hooks */
+extern struct ppc_pci_io {
+
+#define DEF_PCI_AC_RET(name, ret, at, al)	ret (*name) at;
+#define DEF_PCI_AC_NORET(name, at, al)		void (*name) at;
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+} ppc_pci_io;
+
+/* The inline wrappers */
+#define DEF_PCI_AC_RET(name, ret, at, al)			\
+static inline ret name at					\
+{								\
+	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
+		return ppc_pci_io.name al;			\
+	return __do_##name al;					\
+}
+
+#define DEF_PCI_AC_NORET(name, at, al)				\
+static inline void name at					\
+{								\
+	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
+		ppc_pci_io.name al;				\
+	else							\
+		__do_##name al;					\
 }
-#define memset_io(a,b,c)	eeh_memset_io((a),(b),(c))
-#define memcpy_fromio(a,b,c)	eeh_memcpy_fromio((a),(b),(c))
-#define memcpy_toio(a,b,c)	eeh_memcpy_toio((a),(b),(c))
 
-#endif /* CONFIG_PPC_ISERIES */
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+/* Some drivers check for the presence of readq & writeq with
+ * a #ifdef, so we make them happy here.
+ */
+#ifdef __powerpc64__
+#define readq	readq
+#define writeq	writeq
+#endif
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+
+#define dma_cache_inv(_start,_size) \
+	invalidate_dcache_range(_start, (_start + _size))
+#define dma_cache_wback(_start,_size) \
+	clean_dcache_range(_start, (_start + _size))
+#define dma_cache_wback_inv(_start,_size) \
+	flush_dcache_range(_start, (_start + _size))
+
+#else /* CONFIG_NOT_COHERENT_CACHE */
+
+#define dma_cache_inv(_start,_size)		do { } while (0)
+#define dma_cache_wback(_start,_size)		do { } while (0)
+#define dma_cache_wback_inv(_start,_size)	do { } while (0)
+
+#endif /* !CONFIG_NOT_COHERENT_CACHE */
 
 /*
- * The insw/outsw/insl/outsl macros don't do byte-swapping.
- * They are only used in practice for transferring buffers which
- * are arrays of bytes, and byte-swapping is not appropriate in
- * that case.  - paulus */
-#define insb(port, buf, ns)	eeh_insb((port), (buf), (ns))
-#define insw(port, buf, ns)	eeh_insw_ns((port), (buf), (ns))
-#define insl(port, buf, nl)	eeh_insl_ns((port), (buf), (nl))
-
-#define outsb(port, buf, ns)  _outsb((u8 __iomem *)((port)+pci_io_base), (buf), (ns))
-#define outsw(port, buf, ns)  _outsw_ns((u16 __iomem *)((port)+pci_io_base), (buf), (ns))
-#define outsl(port, buf, nl)  _outsl_ns((u32 __iomem *)((port)+pci_io_base), (buf), (nl))
-
-#define readb(addr)		eeh_readb(addr)
-#define readw(addr)		eeh_readw(addr)
-#define readl(addr)		eeh_readl(addr)
-#define readq(addr)		eeh_readq(addr)
-#define writeb(data, addr)	eeh_writeb((data), (addr))
-#define writew(data, addr)	eeh_writew((data), (addr))
-#define writel(data, addr)	eeh_writel((data), (addr))
-#define writeq(data, addr)	eeh_writeq((data), (addr))
-#define inb(port)		eeh_inb((unsigned long)port)
-#define outb(val, port)		eeh_outb(val, (unsigned long)port)
-#define inw(port)		eeh_inw((unsigned long)port)
-#define outw(val, port)		eeh_outw(val, (unsigned long)port)
-#define inl(port)		eeh_inl((unsigned long)port)
-#define outl(val, port)		eeh_outl(val, (unsigned long)port)
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)	__va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
 
+/*
+ * We don't do relaxed operations yet, at least not with this semantic
+ */
 #define readb_relaxed(addr) readb(addr)
 #define readw_relaxed(addr) readw(addr)
 #define readl_relaxed(addr) readl(addr)
 #define readq_relaxed(addr) readq(addr)
 
-extern void _insb(volatile u8 __iomem *port, void *buf, long count);
-extern void _outsb(volatile u8 __iomem *port, const void *buf, long count);
-extern void _insw_ns(volatile u16 __iomem *port, void *buf, long count);
-extern void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count);
-extern void _insl_ns(volatile u32 __iomem *port, void *buf, long count);
-extern void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count);
-
+#ifdef CONFIG_PPC32
+#define mmiowb()
+#else
+/*
+ * Enforce synchronisation of stores vs. spin_unlock
+ * (this does it explicitely, though our implementation of spin_unlock
+ * does it implicitely too)
+ */
 static inline void mmiowb(void)
 {
 	unsigned long tmp;
@@ -169,6 +545,24 @@ static inline void mmiowb(void)
 	: "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
 	: "memory");
 }
+#endif /* !CONFIG_PPC32 */
+
+static inline void iosync(void)
+{
+        __asm__ __volatile__ ("sync" : : : "memory");
+}
+
+/* Enforce in-order execution of data I/O.
+ * No distinction between read/write on PPC; use eieio for all three.
+ * Those are fairly week though. They don't provide a barrier between
+ * MMIO and cacheable storage nor do they provide a barrier vs. locks,
+ * they only provide barriers between 2 __raw MMIO operations and
+ * possibly break write combining.
+ */
+#define iobarrier_rw() eieio()
+#define iobarrier_r()  eieio()
+#define iobarrier_w()  eieio()
+
 
 /*
  * output pause versions need a delay at least for the
@@ -185,11 +579,6 @@ static inline void mmiowb(void)
 #define IO_SPACE_LIMIT ~(0UL)
 
 
-extern int __ioremap_explicit(unsigned long p_addr, unsigned long v_addr,
-		     	      unsigned long size, unsigned long flags);
-extern void __iomem *__ioremap(unsigned long address, unsigned long size,
-		       unsigned long flags);
-
 /**
  * ioremap     -   map bus memory into CPU space
  * @address:   bus address of the memory
@@ -200,14 +589,77 @@ extern void __iomem *__ioremap(unsigned long address, unsigned long size,
  * writew/writel functions and the other mmio helpers. The returned
  * address is not guaranteed to be usable directly as a virtual
  * address.
+ *
+ * We provide a few variations of it:
+ *
+ * * ioremap is the standard one and provides non-cacheable guarded mappings
+ *   and can be hooked by the platform via ppc_md
+ *
+ * * ioremap_flags allows to specify the page flags as an argument and can
+ *   also be hooked by the platform via ppc_md
+ *
+ * * ioremap_nocache is identical to ioremap
+ *
+ * * iounmap undoes such a mapping and can be hooked
+ *
+ * * __ioremap_explicit (and the pending __iounmap_explicit) are low level
+ *   functions to create hand-made mappings for use only by the PCI code
+ *   and cannot currently be hooked.
+ *
+ * * __ioremap is the low level implementation used by ioremap and
+ *   ioremap_flags and cannot be hooked (but can be used by a hook on one
+ *   of the previous ones)
+ *
+ * * __iounmap, is the low level implementation used by iounmap and cannot
+ *   be hooked (but can be used by a hook on iounmap)
+ *
  */
-extern void __iomem *ioremap(unsigned long address, unsigned long size);
-
+extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
+extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size,
+				   unsigned long flags);
 #define ioremap_nocache(addr, size)	ioremap((addr), (size))
-extern int iounmap_explicit(volatile void __iomem *addr, unsigned long size);
 extern void iounmap(volatile void __iomem *addr);
+
+extern void __iomem *__ioremap(phys_addr_t, unsigned long size,
+			       unsigned long flags);
+extern void __iounmap(volatile void __iomem *addr);
+
+extern int __ioremap_explicit(phys_addr_t p_addr, unsigned long v_addr,
+		     	      unsigned long size, unsigned long flags);
+extern int __iounmap_explicit(volatile void __iomem *start,
+			      unsigned long size);
+
 extern void __iomem * reserve_phb_iospace(unsigned long size);
 
+/* Those are more 32 bits only functions */
+extern unsigned long iopa(unsigned long addr);
+extern unsigned long mm_ptov(unsigned long addr) __attribute_const__;
+extern void io_block_mapping(unsigned long virt, phys_addr_t phys,
+			     unsigned int size, int flags);
+
+
+/*
+ * When CONFIG_PPC_INDIRECT_IO is set, we use the generic iomap implementation
+ * which needs some additional definitions here. They basically allow PIO
+ * space overall to be 1GB. This will work as long as we never try to use
+ * iomap to map MMIO below 1GB which should be fine on ppc64
+ */
+#define HAVE_ARCH_PIO_SIZE		1
+#define PIO_OFFSET			0x00000000UL
+#define PIO_MASK			0x3fffffffUL
+#define PIO_RESERVED			0x40000000UL
+
+#define mmio_read16be(addr)		readw_be(addr)
+#define mmio_read32be(addr)		readl_be(addr)
+#define mmio_write16be(val, addr)	writew_be(val, addr)
+#define mmio_write32be(val, addr)	writel_be(val, addr)
+#define mmio_insb(addr, dst, count)	readsb(addr, dst, count)
+#define mmio_insw(addr, dst, count)	readsw(addr, dst, count)
+#define mmio_insl(addr, dst, count)	readsl(addr, dst, count)
+#define mmio_outsb(addr, src, count)	writesb(addr, src, count)
+#define mmio_outsw(addr, src, count)	writesw(addr, src, count)
+#define mmio_outsl(addr, src, count)	writesl(addr, src, count)
+
 /**
  *	virt_to_phys	-	map virtual addresses to physical
  *	@address: address to remap
@@ -254,178 +706,33 @@ static inline void * phys_to_virt(unsigned long address)
  */
 #define BIO_VMERGE_BOUNDARY	0
 
-static inline void iosync(void)
-{
-        __asm__ __volatile__ ("sync" : : : "memory");
-}
-
-/* Enforce in-order execution of data I/O. 
- * No distinction between read/write on PPC; use eieio for all three.
- */
-#define iobarrier_rw() eieio()
-#define iobarrier_r()  eieio()
-#define iobarrier_w()  eieio()
-
 /*
- * 8, 16 and 32 bit, big and little endian I/O operations, with barrier.
- * These routines do not perform EEH-related I/O address translation,
- * and should not be used directly by device drivers.  Use inb/readb
- * instead.
+ * 32 bits still uses virt_to_bus() for it's implementation of DMA
+ * mappings se we have to keep it defined here. We also have some old
+ * drivers (shame shame shame) that use bus_to_virt() and haven't been
+ * fixed yet so I need to define it here.
  */
-static inline int __in_8(const volatile unsigned char __iomem *addr)
-{
-	int ret;
+#ifdef CONFIG_PPC32
 
-	__asm__ __volatile__("sync; lbz%U1%X1 %0,%1; twi 0,%0,0; isync"
-			     : "=r" (ret) : "m" (*addr));
-	return ret;
-}
-
-static inline void __out_8(volatile unsigned char __iomem *addr, int val)
-{
-	__asm__ __volatile__("sync; stb%U0%X0 %1,%0"
-			     : "=m" (*addr) : "r" (val));
-	get_paca()->io_sync = 1;
-}
-
-static inline int __in_le16(const volatile unsigned short __iomem *addr)
+static inline unsigned long virt_to_bus(volatile void * address)
 {
-	int ret;
-
-	__asm__ __volatile__("sync; lhbrx %0,0,%1; twi 0,%0,0; isync"
-			     : "=r" (ret) : "r" (addr), "m" (*addr));
-	return ret;
+        if (address == NULL)
+		return 0;
+        return __pa(address) + PCI_DRAM_OFFSET;
 }
 
-static inline int __in_be16(const volatile unsigned short __iomem *addr)
+static inline void * bus_to_virt(unsigned long address)
 {
-	int ret;
-
-	__asm__ __volatile__("sync; lhz%U1%X1 %0,%1; twi 0,%0,0; isync"
-			     : "=r" (ret) : "m" (*addr));
-	return ret;
+        if (address == 0)
+		return NULL;
+        return __va(address - PCI_DRAM_OFFSET);
 }
 
-static inline void __out_le16(volatile unsigned short __iomem *addr, int val)
-{
-	__asm__ __volatile__("sync; sthbrx %1,0,%2"
-			     : "=m" (*addr) : "r" (val), "r" (addr));
-	get_paca()->io_sync = 1;
-}
-
-static inline void __out_be16(volatile unsigned short __iomem *addr, int val)
-{
-	__asm__ __volatile__("sync; sth%U0%X0 %1,%0"
-			     : "=m" (*addr) : "r" (val));
-	get_paca()->io_sync = 1;
-}
-
-static inline unsigned __in_le32(const volatile unsigned __iomem *addr)
-{
-	unsigned ret;
-
-	__asm__ __volatile__("sync; lwbrx %0,0,%1; twi 0,%0,0; isync"
-			     : "=r" (ret) : "r" (addr), "m" (*addr));
-	return ret;
-}
+#define page_to_bus(page)	(page_to_phys(page) + PCI_DRAM_OFFSET)
 
-static inline unsigned __in_be32(const volatile unsigned __iomem *addr)
-{
-	unsigned ret;
-
-	__asm__ __volatile__("sync; lwz%U1%X1 %0,%1; twi 0,%0,0; isync"
-			     : "=r" (ret) : "m" (*addr));
-	return ret;
-}
-
-static inline void __out_le32(volatile unsigned __iomem *addr, int val)
-{
-	__asm__ __volatile__("sync; stwbrx %1,0,%2" : "=m" (*addr)
-			     : "r" (val), "r" (addr));
-	get_paca()->io_sync = 1;
-}
-
-static inline void __out_be32(volatile unsigned __iomem *addr, int val)
-{
-	__asm__ __volatile__("sync; stw%U0%X0 %1,%0"
-			     : "=m" (*addr) : "r" (val));
-	get_paca()->io_sync = 1;
-}
-
-static inline unsigned long __in_le64(const volatile unsigned long __iomem *addr)
-{
-	unsigned long tmp, ret;
-
-	__asm__ __volatile__(
-			     "sync\n"
-			     "ld %1,0(%2)\n"
-			     "twi 0,%1,0\n"
-			     "isync\n"
-			     "rldimi %0,%1,5*8,1*8\n"
-			     "rldimi %0,%1,3*8,2*8\n"
-			     "rldimi %0,%1,1*8,3*8\n"
-			     "rldimi %0,%1,7*8,4*8\n"
-			     "rldicl %1,%1,32,0\n"
-			     "rlwimi %0,%1,8,8,31\n"
-			     "rlwimi %0,%1,24,16,23\n"
-			     : "=r" (ret) , "=r" (tmp) : "b" (addr) , "m" (*addr));
-	return ret;
-}
-
-static inline unsigned long __in_be64(const volatile unsigned long __iomem *addr)
-{
-	unsigned long ret;
+#endif /* CONFIG_PPC32 */
 
-	__asm__ __volatile__("sync; ld%U1%X1 %0,%1; twi 0,%0,0; isync"
-			     : "=r" (ret) : "m" (*addr));
-	return ret;
-}
-
-static inline void __out_le64(volatile unsigned long __iomem *addr, unsigned long val)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__(
-			     "rldimi %0,%1,5*8,1*8\n"
-			     "rldimi %0,%1,3*8,2*8\n"
-			     "rldimi %0,%1,1*8,3*8\n"
-			     "rldimi %0,%1,7*8,4*8\n"
-			     "rldicl %1,%1,32,0\n"
-			     "rlwimi %0,%1,8,8,31\n"
-			     "rlwimi %0,%1,24,16,23\n"
-			     "sync\n"
-			     "std %0,0(%3)"
-			     : "=&r" (tmp) , "=&r" (val) : "1" (val) , "b" (addr) , "m" (*addr));
-	get_paca()->io_sync = 1;
-}
-
-static inline void __out_be64(volatile unsigned long __iomem *addr, unsigned long val)
-{
-	__asm__ __volatile__("sync; std%U0%X0 %1,%0" : "=m" (*addr) : "r" (val));
-	get_paca()->io_sync = 1;
-}
-
-#include <asm/eeh.h>
-
-/* Nothing to do */
-
-#define dma_cache_inv(_start,_size)		do { } while (0)
-#define dma_cache_wback(_start,_size)		do { } while (0)
-#define dma_cache_wback_inv(_start,_size)	do { } while (0)
-
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
 
 #endif /* __KERNEL__ */
 
-#endif /* CONFIG_PPC64 */
 #endif /* _ASM_POWERPC_IO_H */
diff --git a/include/asm-powerpc/iommu.h b/include/asm-powerpc/iommu.h
index 39fad685ffab..f85dbd305558 100644
--- a/include/asm-powerpc/iommu.h
+++ b/include/asm-powerpc/iommu.h
@@ -34,7 +34,9 @@
 #define IOMMU_PAGE_MASK       (~((1 << IOMMU_PAGE_SHIFT) - 1))
 #define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE)
 
-#ifndef __ASSEMBLY__
+/* Boot time flags */
+extern int iommu_is_off;
+extern int iommu_force_on;
 
 /* Pure 2^n version of get_order */
 static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
@@ -42,8 +44,6 @@ static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
 	return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT) + 1;
 }
 
-#endif   /* __ASSEMBLY__ */
-
 
 /*
  * IOMAP_MAX_ORDER defines the largest contiguous block
@@ -70,39 +70,31 @@ struct iommu_table {
 struct scatterlist;
 struct device_node;
 
-#ifdef CONFIG_PPC_MULTIPLATFORM
-
-/* Walks all buses and creates iommu tables */
-extern void iommu_setup_pSeries(void);
-extern void iommu_setup_dart(void);
-
 /* Frees table for an individual device node */
 extern void iommu_free_table(struct device_node *dn);
 
-#endif /* CONFIG_PPC_MULTIPLATFORM */
-
 /* Initializes an iommu_table based in values set in the passed-in
  * structure
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
 					    int nid);
 
-extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
-		struct scatterlist *sglist, int nelems, unsigned long mask,
-		enum dma_data_direction direction);
+extern int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist,
+			int nelems, unsigned long mask,
+			enum dma_data_direction direction);
 extern void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
-		int nelems, enum dma_data_direction direction);
+			   int nelems, enum dma_data_direction direction);
 
 extern void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
-		dma_addr_t *dma_handle, unsigned long mask,
-		gfp_t flag, int node);
+				  dma_addr_t *dma_handle, unsigned long mask,
+				  gfp_t flag, int node);
 extern void iommu_free_coherent(struct iommu_table *tbl, size_t size,
-		void *vaddr, dma_addr_t dma_handle);
+				void *vaddr, dma_addr_t dma_handle);
 extern dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
-		size_t size, unsigned long mask,
-		enum dma_data_direction direction);
+				   size_t size, unsigned long mask,
+				   enum dma_data_direction direction);
 extern void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction direction);
+			       size_t size, enum dma_data_direction direction);
 
 extern void iommu_init_early_pSeries(void);
 extern void iommu_init_early_iSeries(void);
diff --git a/include/asm-powerpc/irq.h b/include/asm-powerpc/irq.h
index f960f5346f40..46476e9a494a 100644
--- a/include/asm-powerpc/irq.h
+++ b/include/asm-powerpc/irq.h
@@ -135,6 +135,10 @@ struct irq_map_entry {
 
 extern struct irq_map_entry irq_map[NR_IRQS];
 
+static inline irq_hw_number_t virq_to_hw(unsigned int virq)
+{
+	return irq_map[virq].hwirq;
+}
 
 /**
  * irq_alloc_host - Allocate a new irq_host data structure
diff --git a/include/asm-powerpc/iseries/iommu.h b/include/asm-powerpc/iseries/iommu.h
index 0edbfe10cb37..6e323a13ac30 100644
--- a/include/asm-powerpc/iseries/iommu.h
+++ b/include/asm-powerpc/iseries/iommu.h
@@ -21,11 +21,13 @@
  * Boston, MA  02111-1307  USA
  */
 
+struct pci_dev;
 struct device_node;
 struct iommu_table;
 
 /* Creates table for an individual device node */
-extern void iommu_devnode_init_iSeries(struct device_node *dn);
+extern void iommu_devnode_init_iSeries(struct pci_dev *pdev,
+				       struct device_node *dn);
 
 /* Get table parameters from HV */
 extern void iommu_table_getparms_iSeries(unsigned long busno,
diff --git a/include/asm-powerpc/lv1call.h b/include/asm-powerpc/lv1call.h
new file mode 100644
index 000000000000..f733beeea63a
--- /dev/null
+++ b/include/asm-powerpc/lv1call.h
@@ -0,0 +1,345 @@
+/*
+ *  PS3 hvcall interface.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *  Copyright 2003, 2004 (c) MontaVista Software, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  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
+ */
+
+#if !defined(_ASM_POWERPC_LV1CALL_H)
+#define _ASM_POWERPC_LV1CALL_H
+
+#if !defined(__ASSEMBLY__)
+
+#include <linux/types.h>
+
+/* lv1 call declaration macros */
+
+#define LV1_1_IN_ARG_DECL u64 in_1
+#define LV1_2_IN_ARG_DECL LV1_1_IN_ARG_DECL, u64 in_2
+#define LV1_3_IN_ARG_DECL LV1_2_IN_ARG_DECL, u64 in_3
+#define LV1_4_IN_ARG_DECL LV1_3_IN_ARG_DECL, u64 in_4
+#define LV1_5_IN_ARG_DECL LV1_4_IN_ARG_DECL, u64 in_5
+#define LV1_6_IN_ARG_DECL LV1_5_IN_ARG_DECL, u64 in_6
+#define LV1_7_IN_ARG_DECL LV1_6_IN_ARG_DECL, u64 in_7
+#define LV1_8_IN_ARG_DECL LV1_7_IN_ARG_DECL, u64 in_8
+#define LV1_1_OUT_ARG_DECL u64 *out_1
+#define LV1_2_OUT_ARG_DECL LV1_1_OUT_ARG_DECL, u64 *out_2
+#define LV1_3_OUT_ARG_DECL LV1_2_OUT_ARG_DECL, u64 *out_3
+#define LV1_4_OUT_ARG_DECL LV1_3_OUT_ARG_DECL, u64 *out_4
+#define LV1_5_OUT_ARG_DECL LV1_4_OUT_ARG_DECL, u64 *out_5
+#define LV1_6_OUT_ARG_DECL LV1_5_OUT_ARG_DECL, u64 *out_6
+#define LV1_7_OUT_ARG_DECL LV1_6_OUT_ARG_DECL, u64 *out_7
+
+#define LV1_0_IN_0_OUT_ARG_DECL void
+#define LV1_1_IN_0_OUT_ARG_DECL LV1_1_IN_ARG_DECL
+#define LV1_2_IN_0_OUT_ARG_DECL LV1_2_IN_ARG_DECL
+#define LV1_3_IN_0_OUT_ARG_DECL LV1_3_IN_ARG_DECL
+#define LV1_4_IN_0_OUT_ARG_DECL LV1_4_IN_ARG_DECL
+#define LV1_5_IN_0_OUT_ARG_DECL LV1_5_IN_ARG_DECL
+#define LV1_6_IN_0_OUT_ARG_DECL LV1_6_IN_ARG_DECL
+#define LV1_7_IN_0_OUT_ARG_DECL LV1_7_IN_ARG_DECL
+
+#define LV1_0_IN_1_OUT_ARG_DECL                    LV1_1_OUT_ARG_DECL
+#define LV1_1_IN_1_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_2_IN_1_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_3_IN_1_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_4_IN_1_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_5_IN_1_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_6_IN_1_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_7_IN_1_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+#define LV1_8_IN_1_OUT_ARG_DECL LV1_8_IN_ARG_DECL, LV1_1_OUT_ARG_DECL
+
+#define LV1_0_IN_2_OUT_ARG_DECL                    LV1_2_OUT_ARG_DECL
+#define LV1_1_IN_2_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+#define LV1_2_IN_2_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+#define LV1_3_IN_2_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+#define LV1_4_IN_2_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+#define LV1_5_IN_2_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+#define LV1_6_IN_2_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+#define LV1_7_IN_2_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_2_OUT_ARG_DECL
+
+#define LV1_0_IN_3_OUT_ARG_DECL                    LV1_3_OUT_ARG_DECL
+#define LV1_1_IN_3_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+#define LV1_2_IN_3_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+#define LV1_3_IN_3_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+#define LV1_4_IN_3_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+#define LV1_5_IN_3_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+#define LV1_6_IN_3_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+#define LV1_7_IN_3_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_3_OUT_ARG_DECL
+
+#define LV1_0_IN_4_OUT_ARG_DECL                    LV1_4_OUT_ARG_DECL
+#define LV1_1_IN_4_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+#define LV1_2_IN_4_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+#define LV1_3_IN_4_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+#define LV1_4_IN_4_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+#define LV1_5_IN_4_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+#define LV1_6_IN_4_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+#define LV1_7_IN_4_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_4_OUT_ARG_DECL
+
+#define LV1_0_IN_5_OUT_ARG_DECL                    LV1_5_OUT_ARG_DECL
+#define LV1_1_IN_5_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+#define LV1_2_IN_5_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+#define LV1_3_IN_5_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+#define LV1_4_IN_5_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+#define LV1_5_IN_5_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+#define LV1_6_IN_5_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+#define LV1_7_IN_5_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_5_OUT_ARG_DECL
+
+#define LV1_0_IN_6_OUT_ARG_DECL                    LV1_6_OUT_ARG_DECL
+#define LV1_1_IN_6_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+#define LV1_2_IN_6_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+#define LV1_3_IN_6_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+#define LV1_4_IN_6_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+#define LV1_5_IN_6_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+#define LV1_6_IN_6_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+#define LV1_7_IN_6_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_6_OUT_ARG_DECL
+
+#define LV1_0_IN_7_OUT_ARG_DECL                    LV1_7_OUT_ARG_DECL
+#define LV1_1_IN_7_OUT_ARG_DECL LV1_1_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+#define LV1_2_IN_7_OUT_ARG_DECL LV1_2_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+#define LV1_3_IN_7_OUT_ARG_DECL LV1_3_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+#define LV1_4_IN_7_OUT_ARG_DECL LV1_4_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+#define LV1_5_IN_7_OUT_ARG_DECL LV1_5_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+#define LV1_6_IN_7_OUT_ARG_DECL LV1_6_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+#define LV1_7_IN_7_OUT_ARG_DECL LV1_7_IN_ARG_DECL, LV1_7_OUT_ARG_DECL
+
+#define LV1_1_IN_ARGS in_1
+#define LV1_2_IN_ARGS LV1_1_IN_ARGS, in_2
+#define LV1_3_IN_ARGS LV1_2_IN_ARGS, in_3
+#define LV1_4_IN_ARGS LV1_3_IN_ARGS, in_4
+#define LV1_5_IN_ARGS LV1_4_IN_ARGS, in_5
+#define LV1_6_IN_ARGS LV1_5_IN_ARGS, in_6
+#define LV1_7_IN_ARGS LV1_6_IN_ARGS, in_7
+#define LV1_8_IN_ARGS LV1_7_IN_ARGS, in_8
+
+#define LV1_1_OUT_ARGS out_1
+#define LV1_2_OUT_ARGS LV1_1_OUT_ARGS, out_2
+#define LV1_3_OUT_ARGS LV1_2_OUT_ARGS, out_3
+#define LV1_4_OUT_ARGS LV1_3_OUT_ARGS, out_4
+#define LV1_5_OUT_ARGS LV1_4_OUT_ARGS, out_5
+#define LV1_6_OUT_ARGS LV1_5_OUT_ARGS, out_6
+#define LV1_7_OUT_ARGS LV1_6_OUT_ARGS, out_7
+
+#define LV1_0_IN_0_OUT_ARGS
+#define LV1_1_IN_0_OUT_ARGS LV1_1_IN_ARGS
+#define LV1_2_IN_0_OUT_ARGS LV1_2_IN_ARGS
+#define LV1_3_IN_0_OUT_ARGS LV1_3_IN_ARGS
+#define LV1_4_IN_0_OUT_ARGS LV1_4_IN_ARGS
+#define LV1_5_IN_0_OUT_ARGS LV1_5_IN_ARGS
+#define LV1_6_IN_0_OUT_ARGS LV1_6_IN_ARGS
+#define LV1_7_IN_0_OUT_ARGS LV1_7_IN_ARGS
+
+#define LV1_0_IN_1_OUT_ARGS                LV1_1_OUT_ARGS
+#define LV1_1_IN_1_OUT_ARGS LV1_1_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_2_IN_1_OUT_ARGS LV1_2_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_3_IN_1_OUT_ARGS LV1_3_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_4_IN_1_OUT_ARGS LV1_4_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_5_IN_1_OUT_ARGS LV1_5_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_6_IN_1_OUT_ARGS LV1_6_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_7_IN_1_OUT_ARGS LV1_7_IN_ARGS, LV1_1_OUT_ARGS
+#define LV1_8_IN_1_OUT_ARGS LV1_8_IN_ARGS, LV1_1_OUT_ARGS
+
+#define LV1_0_IN_2_OUT_ARGS                LV1_2_OUT_ARGS
+#define LV1_1_IN_2_OUT_ARGS LV1_1_IN_ARGS, LV1_2_OUT_ARGS
+#define LV1_2_IN_2_OUT_ARGS LV1_2_IN_ARGS, LV1_2_OUT_ARGS
+#define LV1_3_IN_2_OUT_ARGS LV1_3_IN_ARGS, LV1_2_OUT_ARGS
+#define LV1_4_IN_2_OUT_ARGS LV1_4_IN_ARGS, LV1_2_OUT_ARGS
+#define LV1_5_IN_2_OUT_ARGS LV1_5_IN_ARGS, LV1_2_OUT_ARGS
+#define LV1_6_IN_2_OUT_ARGS LV1_6_IN_ARGS, LV1_2_OUT_ARGS
+#define LV1_7_IN_2_OUT_ARGS LV1_7_IN_ARGS, LV1_2_OUT_ARGS
+
+#define LV1_0_IN_3_OUT_ARGS                LV1_3_OUT_ARGS
+#define LV1_1_IN_3_OUT_ARGS LV1_1_IN_ARGS, LV1_3_OUT_ARGS
+#define LV1_2_IN_3_OUT_ARGS LV1_2_IN_ARGS, LV1_3_OUT_ARGS
+#define LV1_3_IN_3_OUT_ARGS LV1_3_IN_ARGS, LV1_3_OUT_ARGS
+#define LV1_4_IN_3_OUT_ARGS LV1_4_IN_ARGS, LV1_3_OUT_ARGS
+#define LV1_5_IN_3_OUT_ARGS LV1_5_IN_ARGS, LV1_3_OUT_ARGS
+#define LV1_6_IN_3_OUT_ARGS LV1_6_IN_ARGS, LV1_3_OUT_ARGS
+#define LV1_7_IN_3_OUT_ARGS LV1_7_IN_ARGS, LV1_3_OUT_ARGS
+
+#define LV1_0_IN_4_OUT_ARGS                LV1_4_OUT_ARGS
+#define LV1_1_IN_4_OUT_ARGS LV1_1_IN_ARGS, LV1_4_OUT_ARGS
+#define LV1_2_IN_4_OUT_ARGS LV1_2_IN_ARGS, LV1_4_OUT_ARGS
+#define LV1_3_IN_4_OUT_ARGS LV1_3_IN_ARGS, LV1_4_OUT_ARGS
+#define LV1_4_IN_4_OUT_ARGS LV1_4_IN_ARGS, LV1_4_OUT_ARGS
+#define LV1_5_IN_4_OUT_ARGS LV1_5_IN_ARGS, LV1_4_OUT_ARGS
+#define LV1_6_IN_4_OUT_ARGS LV1_6_IN_ARGS, LV1_4_OUT_ARGS
+#define LV1_7_IN_4_OUT_ARGS LV1_7_IN_ARGS, LV1_4_OUT_ARGS
+
+#define LV1_0_IN_5_OUT_ARGS                LV1_5_OUT_ARGS
+#define LV1_1_IN_5_OUT_ARGS LV1_1_IN_ARGS, LV1_5_OUT_ARGS
+#define LV1_2_IN_5_OUT_ARGS LV1_2_IN_ARGS, LV1_5_OUT_ARGS
+#define LV1_3_IN_5_OUT_ARGS LV1_3_IN_ARGS, LV1_5_OUT_ARGS
+#define LV1_4_IN_5_OUT_ARGS LV1_4_IN_ARGS, LV1_5_OUT_ARGS
+#define LV1_5_IN_5_OUT_ARGS LV1_5_IN_ARGS, LV1_5_OUT_ARGS
+#define LV1_6_IN_5_OUT_ARGS LV1_6_IN_ARGS, LV1_5_OUT_ARGS
+#define LV1_7_IN_5_OUT_ARGS LV1_7_IN_ARGS, LV1_5_OUT_ARGS
+
+#define LV1_0_IN_6_OUT_ARGS                LV1_6_OUT_ARGS
+#define LV1_1_IN_6_OUT_ARGS LV1_1_IN_ARGS, LV1_6_OUT_ARGS
+#define LV1_2_IN_6_OUT_ARGS LV1_2_IN_ARGS, LV1_6_OUT_ARGS
+#define LV1_3_IN_6_OUT_ARGS LV1_3_IN_ARGS, LV1_6_OUT_ARGS
+#define LV1_4_IN_6_OUT_ARGS LV1_4_IN_ARGS, LV1_6_OUT_ARGS
+#define LV1_5_IN_6_OUT_ARGS LV1_5_IN_ARGS, LV1_6_OUT_ARGS
+#define LV1_6_IN_6_OUT_ARGS LV1_6_IN_ARGS, LV1_6_OUT_ARGS
+#define LV1_7_IN_6_OUT_ARGS LV1_7_IN_ARGS, LV1_6_OUT_ARGS
+
+#define LV1_0_IN_7_OUT_ARGS                LV1_7_OUT_ARGS
+#define LV1_1_IN_7_OUT_ARGS LV1_1_IN_ARGS, LV1_7_OUT_ARGS
+#define LV1_2_IN_7_OUT_ARGS LV1_2_IN_ARGS, LV1_7_OUT_ARGS
+#define LV1_3_IN_7_OUT_ARGS LV1_3_IN_ARGS, LV1_7_OUT_ARGS
+#define LV1_4_IN_7_OUT_ARGS LV1_4_IN_ARGS, LV1_7_OUT_ARGS
+#define LV1_5_IN_7_OUT_ARGS LV1_5_IN_ARGS, LV1_7_OUT_ARGS
+#define LV1_6_IN_7_OUT_ARGS LV1_6_IN_ARGS, LV1_7_OUT_ARGS
+#define LV1_7_IN_7_OUT_ARGS LV1_7_IN_ARGS, LV1_7_OUT_ARGS
+
+/*
+ * This LV1_CALL() macro is for use by callers.  It expands into an
+ * inline call wrapper and an underscored HV call declaration.  The
+ * wrapper can be used to instrument the lv1 call interface.  The
+ * file lv1call.S defines its own LV1_CALL() macro to expand into
+ * the actual underscored call definition.
+ */
+
+#if !defined(LV1_CALL)
+#define LV1_CALL(name, in, out, num)                               \
+  extern s64 _lv1_##name(LV1_##in##_IN_##out##_OUT_ARG_DECL);      \
+  static inline int lv1_##name(LV1_##in##_IN_##out##_OUT_ARG_DECL) \
+    {return _lv1_##name(LV1_##in##_IN_##out##_OUT_ARGS);}
+#endif
+
+#endif /* !defined(__ASSEMBLY__) */
+
+/* lv1 call table */
+
+LV1_CALL(allocate_memory,                               4, 2,   0 )
+LV1_CALL(write_htab_entry,                              4, 0,   1 )
+LV1_CALL(construct_virtual_address_space,               3, 2,   2 )
+LV1_CALL(invalidate_htab_entries,                       5, 0,   3 )
+LV1_CALL(get_virtual_address_space_id_of_ppe,           1, 1,   4 )
+LV1_CALL(query_logical_partition_address_region_info,   1, 5,   6 )
+LV1_CALL(select_virtual_address_space,                  1, 0,   7 )
+LV1_CALL(pause,                                         1, 0,   9 )
+LV1_CALL(destruct_virtual_address_space,                1, 0,  10 )
+LV1_CALL(configure_irq_state_bitmap,                    3, 0,  11 )
+LV1_CALL(connect_irq_plug_ext,                          5, 0,  12 )
+LV1_CALL(release_memory,                                1, 0,  13 )
+LV1_CALL(disconnect_irq_plug_ext,                       3, 0,  17 )
+LV1_CALL(construct_event_receive_port,                  0, 1,  18 )
+LV1_CALL(destruct_event_receive_port,                   1, 0,  19 )
+LV1_CALL(send_event_locally,                            1, 0,  24 )
+LV1_CALL(end_of_interrupt,                              1, 0,  27 )
+LV1_CALL(connect_irq_plug,                              2, 0,  28 )
+LV1_CALL(disconnect_irq_plug,                           1, 0,  29 )
+LV1_CALL(end_of_interrupt_ext,                          3, 0,  30 )
+LV1_CALL(did_update_interrupt_mask,                     2, 0,  31 )
+LV1_CALL(shutdown_logical_partition,                    1, 0,  44 )
+LV1_CALL(destruct_logical_spe,                          1, 0,  54 )
+LV1_CALL(construct_logical_spe,                         7, 6,  57 )
+LV1_CALL(set_spe_interrupt_mask,                        3, 0,  61 )
+LV1_CALL(set_spe_transition_notifier,                   3, 0,  64 )
+LV1_CALL(disable_logical_spe,                           2, 0,  65 )
+LV1_CALL(clear_spe_interrupt_status,                    4, 0,  66 )
+LV1_CALL(get_spe_interrupt_status,                      2, 1,  67 )
+LV1_CALL(get_logical_ppe_id,                            0, 1,  69 )
+LV1_CALL(set_interrupt_mask,                            5, 0,  73 )
+LV1_CALL(get_logical_partition_id,                      0, 1,  74 )
+LV1_CALL(configure_execution_time_variable,             1, 0,  77 )
+LV1_CALL(get_spe_irq_outlet,                            2, 1,  78 )
+LV1_CALL(set_spe_privilege_state_area_1_register,       3, 0,  79 )
+LV1_CALL(create_repository_node,                        6, 0,  90 )
+LV1_CALL(get_repository_node_value,                     5, 2,  91 )
+LV1_CALL(modify_repository_node_value,                  6, 0,  92 )
+LV1_CALL(remove_repository_node,                        4, 0,  93 )
+LV1_CALL(read_htab_entries,                             2, 5,  95 )
+LV1_CALL(set_dabr,                                      2, 0,  96 )
+LV1_CALL(get_total_execution_time,                      2, 1, 103 )
+LV1_CALL(construct_io_irq_outlet,                       1, 1, 120 )
+LV1_CALL(destruct_io_irq_outlet,                        1, 0, 121 )
+LV1_CALL(map_htab,                                      1, 1, 122 )
+LV1_CALL(unmap_htab,                                    1, 0, 123 )
+LV1_CALL(get_version_info,                              0, 1, 127 )
+LV1_CALL(insert_htab_entry,                             6, 3, 158 )
+LV1_CALL(read_virtual_uart,                             3, 1, 162 )
+LV1_CALL(write_virtual_uart,                            3, 1, 163 )
+LV1_CALL(set_virtual_uart_param,                        3, 0, 164 )
+LV1_CALL(get_virtual_uart_param,                        2, 1, 165 )
+LV1_CALL(configure_virtual_uart_irq,                    1, 1, 166 )
+LV1_CALL(open_device,                                   3, 0, 170 )
+LV1_CALL(close_device,                                  2, 0, 171 )
+LV1_CALL(map_device_mmio_region,                        5, 1, 172 )
+LV1_CALL(unmap_device_mmio_region,                      3, 0, 173 )
+LV1_CALL(allocate_device_dma_region,                    5, 1, 174 )
+LV1_CALL(free_device_dma_region,                        3, 0, 175 )
+LV1_CALL(map_device_dma_region,                         6, 0, 176 )
+LV1_CALL(unmap_device_dma_region,                       4, 0, 177 )
+LV1_CALL(net_add_multicast_address,                     4, 0, 185 )
+LV1_CALL(net_remove_multicast_address,                  4, 0, 186 )
+LV1_CALL(net_start_tx_dma,                              4, 0, 187 )
+LV1_CALL(net_stop_tx_dma,                               3, 0, 188 )
+LV1_CALL(net_start_rx_dma,                              4, 0, 189 )
+LV1_CALL(net_stop_rx_dma,                               3, 0, 190 )
+LV1_CALL(net_set_interrupt_status_indicator,            4, 0, 191 )
+LV1_CALL(net_set_interrupt_mask,                        4, 0, 193 )
+LV1_CALL(net_control,                                   6, 2, 194 )
+LV1_CALL(connect_interrupt_event_receive_port,          4, 0, 197 )
+LV1_CALL(disconnect_interrupt_event_receive_port,       4, 0, 198 )
+LV1_CALL(get_spe_all_interrupt_statuses,                1, 1, 199 )
+LV1_CALL(deconfigure_virtual_uart_irq,                  0, 0, 202 )
+LV1_CALL(enable_logical_spe,                            2, 0, 207 )
+LV1_CALL(gpu_open,                                      1, 0, 210 )
+LV1_CALL(gpu_close,                                     0, 0, 211 )
+LV1_CALL(gpu_device_map,                                1, 2, 212 )
+LV1_CALL(gpu_device_unmap,                              1, 0, 213 )
+LV1_CALL(gpu_memory_allocate,                           5, 2, 214 )
+LV1_CALL(gpu_memory_free,                               1, 0, 216 )
+LV1_CALL(gpu_context_allocate,                          2, 5, 217 )
+LV1_CALL(gpu_context_free,                              1, 0, 218 )
+LV1_CALL(gpu_context_iomap,                             5, 0, 221 )
+LV1_CALL(gpu_context_attribute,                         6, 0, 225 )
+LV1_CALL(gpu_context_intr,                              1, 1, 227 )
+LV1_CALL(gpu_attribute,                                 5, 0, 228 )
+LV1_CALL(get_rtc,                                       0, 2, 232 )
+LV1_CALL(set_ppe_periodic_tracer_frequency,             1, 0, 240 )
+LV1_CALL(start_ppe_periodic_tracer,                     5, 0, 241 )
+LV1_CALL(stop_ppe_periodic_tracer,                      1, 1, 242 )
+LV1_CALL(storage_read,                                  6, 1, 245 )
+LV1_CALL(storage_write,                                 6, 1, 246 )
+LV1_CALL(storage_send_device_command,                   6, 1, 248 )
+LV1_CALL(storage_get_async_status,                      1, 2, 249 )
+LV1_CALL(storage_check_async_status,                    2, 1, 254 )
+LV1_CALL(panic,                                         1, 0, 255 )
+LV1_CALL(construct_lpm,                                 6, 3, 140 )
+LV1_CALL(destruct_lpm,                                  1, 0, 141 )
+LV1_CALL(start_lpm,                                     1, 0, 142 )
+LV1_CALL(stop_lpm,                                      1, 1, 143 )
+LV1_CALL(copy_lpm_trace_buffer,                         3, 1, 144 )
+LV1_CALL(add_lpm_event_bookmark,                        5, 0, 145 )
+LV1_CALL(delete_lpm_event_bookmark,                     3, 0, 146 )
+LV1_CALL(set_lpm_interrupt_mask,                        3, 1, 147 )
+LV1_CALL(get_lpm_interrupt_status,                      1, 1, 148 )
+LV1_CALL(set_lpm_general_control,                       5, 2, 149 )
+LV1_CALL(set_lpm_interval,                              3, 1, 150 )
+LV1_CALL(set_lpm_trigger_control,                       3, 1, 151 )
+LV1_CALL(set_lpm_counter_control,                       4, 1, 152 )
+LV1_CALL(set_lpm_group_control,                         3, 1, 153 )
+LV1_CALL(set_lpm_debug_bus_control,                     3, 1, 154 )
+LV1_CALL(set_lpm_counter,                               5, 2, 155 )
+LV1_CALL(set_lpm_signal,                                7, 0, 156 )
+LV1_CALL(set_lpm_spr_trigger,                           2, 0, 157 )
+
+#endif
diff --git a/include/asm-powerpc/machdep.h b/include/asm-powerpc/machdep.h
index dac90dc341cb..1b04e5723548 100644
--- a/include/asm-powerpc/machdep.h
+++ b/include/asm-powerpc/machdep.h
@@ -26,6 +26,7 @@ struct device_node;
 struct iommu_table;
 struct rtc_time;
 struct file;
+struct pci_controller;
 #ifdef CONFIG_KEXEC
 struct kimage;
 #endif
@@ -84,9 +85,12 @@ struct machdep_calls {
 	unsigned long	(*tce_get)(struct iommu_table *tbl,
 				    long index);
 	void		(*tce_flush)(struct iommu_table *tbl);
-	void		(*iommu_dev_setup)(struct pci_dev *dev);
-	void		(*iommu_bus_setup)(struct pci_bus *bus);
-	void		(*irq_bus_setup)(struct pci_bus *bus);
+	void		(*pci_dma_dev_setup)(struct pci_dev *dev);
+	void		(*pci_dma_bus_setup)(struct pci_bus *bus);
+
+	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
+				   unsigned long flags);
+	void		(*iounmap)(volatile void __iomem *token);
 #endif /* CONFIG_PPC64 */
 
 	int		(*probe)(void);
@@ -106,6 +110,10 @@ struct machdep_calls {
 	/* Called after scanning the bus, before allocating resources */
 	void		(*pcibios_fixup)(void);
 	int		(*pci_probe_mode)(struct pci_bus *);
+	void		(*pci_irq_fixup)(struct pci_dev *dev);
+
+	/* To setup PHBs when using automatic OF platform driver for PCI */
+	int		(*pci_setup_phb)(struct pci_controller *host);
 
 	void		(*restart)(char *cmd);
 	void		(*power_off)(void);
@@ -199,10 +207,6 @@ struct machdep_calls {
 	 * Returns 0 to allow assignment/enabling of the device. */
 	int  (*pcibios_enable_device_hook)(struct pci_dev *, int initial);
 
-	/* For interrupt routing */
-	unsigned char (*pci_swizzle)(struct pci_dev *, unsigned char *);
-	int (*pci_map_irq)(struct pci_dev *, unsigned char, unsigned char);
-
 	/* Called in indirect_* to avoid touching devices */
 	int (*pci_exclude_device)(unsigned char, unsigned char);
 
diff --git a/include/asm-powerpc/mmu.h b/include/asm-powerpc/mmu.h
index c3fc7a28e3cd..41c8c9c5a254 100644
--- a/include/asm-powerpc/mmu.h
+++ b/include/asm-powerpc/mmu.h
@@ -248,21 +248,6 @@ extern void hpte_init_native(void);
 extern void hpte_init_lpar(void);
 extern void hpte_init_iSeries(void);
 
-extern long pSeries_lpar_hpte_insert(unsigned long hpte_group,
-				     unsigned long va, unsigned long prpn,
-				     unsigned long rflags,
-				     unsigned long vflags, int psize);
-
-extern long native_hpte_insert(unsigned long hpte_group,
-			       unsigned long va, unsigned long prpn,
-			       unsigned long rflags,
-			       unsigned long vflags, int psize);
-
-extern long iSeries_hpte_insert(unsigned long hpte_group,
-				unsigned long va, unsigned long prpn,
-				unsigned long rflags,
-				unsigned long vflags, int psize);
-
 extern void stabs_alloc(void);
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
diff --git a/include/asm-powerpc/mpc52xx.h b/include/asm-powerpc/mpc52xx.h
new file mode 100644
index 000000000000..4a28a850998c
--- /dev/null
+++ b/include/asm-powerpc/mpc52xx.h
@@ -0,0 +1,254 @@
+/*
+ * Prototypes, etc. for the Freescale MPC52xx embedded cpu chips
+ * May need to be cleaned as the port goes on ...
+ *
+ * Copyright (C) 2004-2005 Sylvain Munaut <tnt@246tNt.com>
+ * Copyright (C) 2003 MontaVista, Software, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ASM_POWERPC_MPC52xx_H__
+#define __ASM_POWERPC_MPC52xx_H__
+
+#ifndef __ASSEMBLY__
+#include <asm/types.h>
+#include <asm/prom.h>
+#endif /* __ASSEMBLY__ */
+
+
+/* ======================================================================== */
+/* Structures mapping of some unit register set                             */
+/* ======================================================================== */
+
+#ifndef __ASSEMBLY__
+
+/* Memory Mapping Control */
+struct mpc52xx_mmap_ctl {
+	u32 mbar;		/* MMAP_CTRL + 0x00 */
+
+	u32 cs0_start;		/* MMAP_CTRL + 0x04 */
+	u32 cs0_stop;		/* MMAP_CTRL + 0x08 */
+	u32 cs1_start;		/* MMAP_CTRL + 0x0c */
+	u32 cs1_stop;		/* MMAP_CTRL + 0x10 */
+	u32 cs2_start;		/* MMAP_CTRL + 0x14 */
+	u32 cs2_stop;		/* MMAP_CTRL + 0x18 */
+	u32 cs3_start;		/* MMAP_CTRL + 0x1c */
+	u32 cs3_stop;		/* MMAP_CTRL + 0x20 */
+	u32 cs4_start;		/* MMAP_CTRL + 0x24 */
+	u32 cs4_stop;		/* MMAP_CTRL + 0x28 */
+	u32 cs5_start;		/* MMAP_CTRL + 0x2c */
+	u32 cs5_stop;		/* MMAP_CTRL + 0x30 */
+
+	u32 sdram0;		/* MMAP_CTRL + 0x34 */
+	u32 sdram1;		/* MMAP_CTRL + 0X38 */
+
+	u32 reserved[4];	/* MMAP_CTRL + 0x3c .. 0x48 */
+
+	u32 boot_start;		/* MMAP_CTRL + 0x4c */
+	u32 boot_stop;		/* MMAP_CTRL + 0x50 */
+
+	u32 ipbi_ws_ctrl;	/* MMAP_CTRL + 0x54 */
+
+	u32 cs6_start;		/* MMAP_CTRL + 0x58 */
+	u32 cs6_stop;		/* MMAP_CTRL + 0x5c */
+	u32 cs7_start;		/* MMAP_CTRL + 0x60 */
+	u32 cs7_stop;		/* MMAP_CTRL + 0x64 */
+};
+
+/* SDRAM control */
+struct mpc52xx_sdram {
+	u32 mode;		/* SDRAM + 0x00 */
+	u32 ctrl;		/* SDRAM + 0x04 */
+	u32 config1;		/* SDRAM + 0x08 */
+	u32 config2;		/* SDRAM + 0x0c */
+};
+
+/* SDMA */
+struct mpc52xx_sdma {
+	u32 taskBar;		/* SDMA + 0x00 */
+	u32 currentPointer;	/* SDMA + 0x04 */
+	u32 endPointer;		/* SDMA + 0x08 */
+	u32 variablePointer;	/* SDMA + 0x0c */
+
+	u8 IntVect1;		/* SDMA + 0x10 */
+	u8 IntVect2;		/* SDMA + 0x11 */
+	u16 PtdCntrl;		/* SDMA + 0x12 */
+
+	u32 IntPend;		/* SDMA + 0x14 */
+	u32 IntMask;		/* SDMA + 0x18 */
+
+	u16 tcr[16];		/* SDMA + 0x1c .. 0x3a */
+
+	u8 ipr[32];		/* SDMA + 0x3c .. 0x5b */
+
+	u32 cReqSelect;		/* SDMA + 0x5c */
+	u32 task_size0;		/* SDMA + 0x60 */
+	u32 task_size1;		/* SDMA + 0x64 */
+	u32 MDEDebug;		/* SDMA + 0x68 */
+	u32 ADSDebug;		/* SDMA + 0x6c */
+	u32 Value1;		/* SDMA + 0x70 */
+	u32 Value2;		/* SDMA + 0x74 */
+	u32 Control;		/* SDMA + 0x78 */
+	u32 Status;		/* SDMA + 0x7c */
+	u32 PTDDebug;		/* SDMA + 0x80 */
+};
+
+/* GPT */
+struct mpc52xx_gpt {
+	u32 mode;		/* GPTx + 0x00 */
+	u32 count;		/* GPTx + 0x04 */
+	u32 pwm;		/* GPTx + 0x08 */
+	u32 status;		/* GPTx + 0X0c */
+};
+
+/* GPIO */
+struct mpc52xx_gpio {
+	u32 port_config;	/* GPIO + 0x00 */
+	u32 simple_gpioe;	/* GPIO + 0x04 */
+	u32 simple_ode;		/* GPIO + 0x08 */
+	u32 simple_ddr;		/* GPIO + 0x0c */
+	u32 simple_dvo;		/* GPIO + 0x10 */
+	u32 simple_ival;	/* GPIO + 0x14 */
+	u8 outo_gpioe;		/* GPIO + 0x18 */
+	u8 reserved1[3];	/* GPIO + 0x19 */
+	u8 outo_dvo;		/* GPIO + 0x1c */
+	u8 reserved2[3];	/* GPIO + 0x1d */
+	u8 sint_gpioe;		/* GPIO + 0x20 */
+	u8 reserved3[3];	/* GPIO + 0x21 */
+	u8 sint_ode;		/* GPIO + 0x24 */
+	u8 reserved4[3];	/* GPIO + 0x25 */
+	u8 sint_ddr;		/* GPIO + 0x28 */
+	u8 reserved5[3];	/* GPIO + 0x29 */
+	u8 sint_dvo;		/* GPIO + 0x2c */
+	u8 reserved6[3];	/* GPIO + 0x2d */
+	u8 sint_inten;		/* GPIO + 0x30 */
+	u8 reserved7[3];	/* GPIO + 0x31 */
+	u16 sint_itype;		/* GPIO + 0x34 */
+	u16 reserved8;		/* GPIO + 0x36 */
+	u8 gpio_control;	/* GPIO + 0x38 */
+	u8 reserved9[3];	/* GPIO + 0x39 */
+	u8 sint_istat;		/* GPIO + 0x3c */
+	u8 sint_ival;		/* GPIO + 0x3d */
+	u8 bus_errs;		/* GPIO + 0x3e */
+	u8 reserved10;		/* GPIO + 0x3f */
+};
+
+#define MPC52xx_GPIO_PSC_CONFIG_UART_WITHOUT_CD	4
+#define MPC52xx_GPIO_PSC_CONFIG_UART_WITH_CD	5
+#define MPC52xx_GPIO_PCI_DIS			(1<<15)
+
+/* GPIO with WakeUp*/
+struct mpc52xx_gpio_wkup {
+	u8 wkup_gpioe;		/* GPIO_WKUP + 0x00 */
+	u8 reserved1[3];	/* GPIO_WKUP + 0x03 */
+	u8 wkup_ode;		/* GPIO_WKUP + 0x04 */
+	u8 reserved2[3];	/* GPIO_WKUP + 0x05 */
+	u8 wkup_ddr;		/* GPIO_WKUP + 0x08 */
+	u8 reserved3[3];	/* GPIO_WKUP + 0x09 */
+	u8 wkup_dvo;		/* GPIO_WKUP + 0x0C */
+	u8 reserved4[3];	/* GPIO_WKUP + 0x0D */
+	u8 wkup_inten;		/* GPIO_WKUP + 0x10 */
+	u8 reserved5[3];	/* GPIO_WKUP + 0x11 */
+	u8 wkup_iinten;		/* GPIO_WKUP + 0x14 */
+	u8 reserved6[3];	/* GPIO_WKUP + 0x15 */
+	u16 wkup_itype;		/* GPIO_WKUP + 0x18 */
+	u8 reserved7[2];	/* GPIO_WKUP + 0x1A */
+	u8 wkup_maste;		/* GPIO_WKUP + 0x1C */
+	u8 reserved8[3];	/* GPIO_WKUP + 0x1D */
+	u8 wkup_ival;		/* GPIO_WKUP + 0x20 */
+	u8 reserved9[3];	/* GPIO_WKUP + 0x21 */
+	u8 wkup_istat;		/* GPIO_WKUP + 0x24 */
+	u8 reserved10[3];	/* GPIO_WKUP + 0x25 */
+};
+
+/* XLB Bus control */
+struct mpc52xx_xlb {
+	u8 reserved[0x40];
+	u32 config;		/* XLB + 0x40 */
+	u32 version;		/* XLB + 0x44 */
+	u32 status;		/* XLB + 0x48 */
+	u32 int_enable;		/* XLB + 0x4c */
+	u32 addr_capture;	/* XLB + 0x50 */
+	u32 bus_sig_capture;	/* XLB + 0x54 */
+	u32 addr_timeout;	/* XLB + 0x58 */
+	u32 data_timeout;	/* XLB + 0x5c */
+	u32 bus_act_timeout;	/* XLB + 0x60 */
+	u32 master_pri_enable;	/* XLB + 0x64 */
+	u32 master_priority;	/* XLB + 0x68 */
+	u32 base_address;	/* XLB + 0x6c */
+	u32 snoop_window;	/* XLB + 0x70 */
+};
+
+#define MPC52xx_XLB_CFG_PLDIS		(1 << 31)
+#define MPC52xx_XLB_CFG_SNOOP		(1 << 15)
+
+/* Clock Distribution control */
+struct mpc52xx_cdm {
+	u32 jtag_id;		/* CDM + 0x00  reg0 read only */
+	u32 rstcfg;		/* CDM + 0x04  reg1 read only */
+	u32 breadcrumb;		/* CDM + 0x08  reg2 */
+
+	u8 mem_clk_sel;		/* CDM + 0x0c  reg3 byte0 */
+	u8 xlb_clk_sel;		/* CDM + 0x0d  reg3 byte1 read only */
+	u8 ipb_clk_sel;		/* CDM + 0x0e  reg3 byte2 */
+	u8 pci_clk_sel;		/* CDM + 0x0f  reg3 byte3 */
+
+	u8 ext_48mhz_en;	/* CDM + 0x10  reg4 byte0 */
+	u8 fd_enable;		/* CDM + 0x11  reg4 byte1 */
+	u16 fd_counters;	/* CDM + 0x12  reg4 byte2,3 */
+
+	u32 clk_enables;	/* CDM + 0x14  reg5 */
+
+	u8 osc_disable;		/* CDM + 0x18  reg6 byte0 */
+	u8 reserved0[3];	/* CDM + 0x19  reg6 byte1,2,3 */
+
+	u8 ccs_sleep_enable;	/* CDM + 0x1c  reg7 byte0 */
+	u8 osc_sleep_enable;	/* CDM + 0x1d  reg7 byte1 */
+	u8 reserved1;		/* CDM + 0x1e  reg7 byte2 */
+	u8 ccs_qreq_test;	/* CDM + 0x1f  reg7 byte3 */
+
+	u8 soft_reset;		/* CDM + 0x20  u8 byte0 */
+	u8 no_ckstp;		/* CDM + 0x21  u8 byte0 */
+	u8 reserved2[2];	/* CDM + 0x22  u8 byte1,2,3 */
+
+	u8 pll_lock;		/* CDM + 0x24  reg9 byte0 */
+	u8 pll_looselock;	/* CDM + 0x25  reg9 byte1 */
+	u8 pll_sm_lockwin;	/* CDM + 0x26  reg9 byte2 */
+	u8 reserved3;		/* CDM + 0x27  reg9 byte3 */
+
+	u16 reserved4;		/* CDM + 0x28  reg10 byte0,1 */
+	u16 mclken_div_psc1;	/* CDM + 0x2a  reg10 byte2,3 */
+
+	u16 reserved5;		/* CDM + 0x2c  reg11 byte0,1 */
+	u16 mclken_div_psc2;	/* CDM + 0x2e  reg11 byte2,3 */
+
+	u16 reserved6;		/* CDM + 0x30  reg12 byte0,1 */
+	u16 mclken_div_psc3;	/* CDM + 0x32  reg12 byte2,3 */
+
+	u16 reserved7;		/* CDM + 0x34  reg13 byte0,1 */
+	u16 mclken_div_psc6;	/* CDM + 0x36  reg13 byte2,3 */
+};
+
+#endif /* __ASSEMBLY__ */
+
+
+/* ========================================================================= */
+/* Prototypes for MPC52xx sysdev                                             */
+/* ========================================================================= */
+
+#ifndef __ASSEMBLY__
+
+extern void __iomem * mpc52xx_find_and_map(const char *);
+extern unsigned int mpc52xx_find_ipb_freq(struct device_node *node);
+extern void mpc52xx_setup_cpu(void);
+
+extern void mpc52xx_init_irq(void);
+extern unsigned int mpc52xx_get_irq(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_POWERPC_MPC52xx_H__ */
+
diff --git a/include/asm-powerpc/mpc85xx.h b/include/asm-powerpc/mpc85xx.h
index ccdb8a21138f..54142997a584 100644
--- a/include/asm-powerpc/mpc85xx.h
+++ b/include/asm-powerpc/mpc85xx.h
@@ -31,14 +31,6 @@
 #include <platforms/85xx/mpc85xx_cds.h>
 #endif
 
-#define _IO_BASE        isa_io_base
-#define _ISA_MEM_BASE   isa_mem_base
-#ifdef CONFIG_PCI
-#define PCI_DRAM_OFFSET pci_dram_offset
-#else
-#define PCI_DRAM_OFFSET 0
-#endif
-
 /* Let modules/drivers get at CCSRBAR */
 extern phys_addr_t get_ccsrbar(void);
 
diff --git a/include/asm-powerpc/mpic.h b/include/asm-powerpc/mpic.h
index ef0a5458d2b2..b71e7b32a555 100644
--- a/include/asm-powerpc/mpic.h
+++ b/include/asm-powerpc/mpic.h
@@ -3,6 +3,7 @@
 #ifdef __KERNEL__
 
 #include <linux/irq.h>
+#include <asm/dcr.h>
 
 /*
  * Global registers
@@ -225,6 +226,23 @@ struct mpic_irq_fixup
 #endif /* CONFIG_MPIC_BROKEN_U3 */
 
 
+enum mpic_reg_type {
+	mpic_access_mmio_le,
+	mpic_access_mmio_be,
+#ifdef CONFIG_PPC_DCR
+	mpic_access_dcr
+#endif
+};
+
+struct mpic_reg_bank {
+	u32 __iomem	*base;
+#ifdef CONFIG_PPC_DCR
+	dcr_host_t	dhost;
+	unsigned int	dbase;
+	unsigned int	doff;
+#endif /* CONFIG_PPC_DCR */
+};
+
 /* The instance data of a given MPIC */
 struct mpic
 {
@@ -264,11 +282,18 @@ struct mpic
 	spinlock_t		fixup_lock;
 #endif
 
+	/* Register access method */
+	enum mpic_reg_type	reg_type;
+
 	/* The various ioremap'ed bases */
-	volatile u32 __iomem	*gregs;
-	volatile u32 __iomem	*tmregs;
-	volatile u32 __iomem	*cpuregs[MPIC_MAX_CPUS];
-	volatile u32 __iomem	*isus[MPIC_MAX_ISU];
+	struct mpic_reg_bank	gregs;
+	struct mpic_reg_bank	tmregs;
+	struct mpic_reg_bank	cpuregs[MPIC_MAX_CPUS];
+	struct mpic_reg_bank	isus[MPIC_MAX_ISU];
+
+#ifdef CONFIG_PPC_DCR
+	unsigned int		dcr_base;
+#endif
 
 #ifdef CONFIG_MPIC_WEIRD
 	/* Pointer to HW info array */
@@ -305,6 +330,8 @@ struct mpic
 #define MPIC_SPV_EOI			0x00000020
 /* No passthrough disable */
 #define MPIC_NO_PTHROU_DIS		0x00000040
+/* DCR based MPIC */
+#define MPIC_USES_DCR			0x00000080
 
 /* MPIC HW modification ID */
 #define MPIC_REGSET_MASK		0xf0000000
@@ -337,7 +364,7 @@ struct mpic
  * that is senses[0] correspond to linux irq "irq_offset".
  */
 extern struct mpic *mpic_alloc(struct device_node *node,
-			       unsigned long phys_addr,
+			       phys_addr_t phys_addr,
 			       unsigned int flags,
 			       unsigned int isu_size,
 			       unsigned int irq_count,
@@ -350,7 +377,7 @@ extern struct mpic *mpic_alloc(struct device_node *node,
  * @phys_addr:	physical address of the ISU
  */
 extern void mpic_assign_isu(struct mpic *mpic, unsigned int isu_num,
-			    unsigned long phys_addr);
+			    phys_addr_t phys_addr);
 
 /* Set default sense codes
  *
diff --git a/include/asm-powerpc/of_device.h b/include/asm-powerpc/of_device.h
index c5c0b0b3cd52..a889b2005bf5 100644
--- a/include/asm-powerpc/of_device.h
+++ b/include/asm-powerpc/of_device.h
@@ -6,12 +6,6 @@
 #include <linux/mod_devicetable.h>
 #include <asm/prom.h>
 
-/*
- * The of_platform_bus_type is a bus type used by drivers that do not
- * attach to a macio or similar bus but still use OF probing
- * mechanism
- */
-extern struct bus_type of_platform_bus_type;
 
 /*
  * The of_device is a kind of "base class" that is a superset of
@@ -20,46 +14,22 @@ extern struct bus_type of_platform_bus_type;
  */
 struct of_device
 {
-	struct device_node	*node;		/* OF device node */
+	struct device_node	*node;		/* to be obsoleted */
 	u64			dma_mask;	/* DMA mask */
 	struct device		dev;		/* Generic device interface */
 };
 #define	to_of_device(d) container_of(d, struct of_device, dev)
 
+extern const struct of_device_id *of_match_node(
+	const struct of_device_id *matches, const struct device_node *node);
 extern const struct of_device_id *of_match_device(
 	const struct of_device_id *matches, const struct of_device *dev);
 
 extern struct of_device *of_dev_get(struct of_device *dev);
 extern void of_dev_put(struct of_device *dev);
 
-/*
- * An of_platform_driver driver is attached to a basic of_device on
- * the "platform bus" (of_platform_bus_type)
- */
-struct of_platform_driver
-{
-	char			*name;
-	struct of_device_id	*match_table;
-	struct module		*owner;
-
-	int	(*probe)(struct of_device* dev, const struct of_device_id *match);
-	int	(*remove)(struct of_device* dev);
-
-	int	(*suspend)(struct of_device* dev, pm_message_t state);
-	int	(*resume)(struct of_device* dev);
-	int	(*shutdown)(struct of_device* dev);
-
-	struct device_driver	driver;
-};
-#define	to_of_platform_driver(drv) container_of(drv,struct of_platform_driver, driver)
-
-extern int of_register_driver(struct of_platform_driver *drv);
-extern void of_unregister_driver(struct of_platform_driver *drv);
 extern int of_device_register(struct of_device *ofdev);
 extern void of_device_unregister(struct of_device *ofdev);
-extern struct of_device *of_platform_device_create(struct device_node *np,
-						   const char *bus_id,
-						   struct device *parent);
 extern void of_release_dev(struct device *dev);
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-powerpc/of_platform.h b/include/asm-powerpc/of_platform.h
new file mode 100644
index 000000000000..217eafb167e9
--- /dev/null
+++ b/include/asm-powerpc/of_platform.h
@@ -0,0 +1,60 @@
+/*
+ *    Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
+ *			 <benh@kernel.crashing.org>
+ *
+ *  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.
+ *
+ */
+
+#include <asm/of_device.h>
+
+/*
+ * The of_platform_bus_type is a bus type used by drivers that do not
+ * attach to a macio or similar bus but still use OF probing
+ * mechanism
+ */
+extern struct bus_type of_platform_bus_type;
+
+/*
+ * An of_platform_driver driver is attached to a basic of_device on
+ * the "platform bus" (of_platform_bus_type)
+ */
+struct of_platform_driver
+{
+	char			*name;
+	struct of_device_id	*match_table;
+	struct module		*owner;
+
+	int	(*probe)(struct of_device* dev,
+			 const struct of_device_id *match);
+	int	(*remove)(struct of_device* dev);
+
+	int	(*suspend)(struct of_device* dev, pm_message_t state);
+	int	(*resume)(struct of_device* dev);
+	int	(*shutdown)(struct of_device* dev);
+
+	struct device_driver	driver;
+};
+#define	to_of_platform_driver(drv) \
+	container_of(drv,struct of_platform_driver, driver)
+
+/* Platform drivers register/unregister */
+extern int of_register_platform_driver(struct of_platform_driver *drv);
+extern void of_unregister_platform_driver(struct of_platform_driver *drv);
+
+/* Platform devices and busses creation */
+extern struct of_device *of_platform_device_create(struct device_node *np,
+						   const char *bus_id,
+						   struct device *parent);
+/* pseudo "matches" value to not do deep probe */
+#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1)
+
+extern int of_platform_bus_probe(struct device_node *root,
+				 struct of_device_id *matches,
+				 struct device *parent);
+
+extern struct of_device *of_find_device_by_node(struct device_node *np);
+extern struct of_device *of_find_device_by_phandle(phandle ph);
diff --git a/include/asm-powerpc/oprofile_impl.h b/include/asm-powerpc/oprofile_impl.h
index 07a10e590c1d..71043bf3641f 100644
--- a/include/asm-powerpc/oprofile_impl.h
+++ b/include/asm-powerpc/oprofile_impl.h
@@ -44,7 +44,9 @@ struct op_powerpc_model {
 			   int num_counters);
 	void (*cpu_setup) (struct op_counter_config *);
 	void (*start) (struct op_counter_config *);
+        void (*global_start) (struct op_counter_config *);
 	void (*stop) (void);
+	void (*global_stop) (void);
 	void (*handle_interrupt) (struct pt_regs *,
 				  struct op_counter_config *);
 	int num_counters;
@@ -54,6 +56,7 @@ extern struct op_powerpc_model op_model_fsl_booke;
 extern struct op_powerpc_model op_model_rs64;
 extern struct op_powerpc_model op_model_power4;
 extern struct op_powerpc_model op_model_7450;
+extern struct op_powerpc_model op_model_cell;
 
 #ifndef CONFIG_FSL_BOOKE
 
diff --git a/include/asm-powerpc/paca.h b/include/asm-powerpc/paca.h
index 0a4e5c93e8e6..0d3adc09c847 100644
--- a/include/asm-powerpc/paca.h
+++ b/include/asm-powerpc/paca.h
@@ -93,7 +93,8 @@ struct paca_struct {
 	u64 stab_rr;			/* stab/slb round-robin counter */
 	u64 saved_r1;			/* r1 save for RTAS calls */
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
-	u8 proc_enabled;		/* irq soft-enable flag */
+	u8 soft_enabled;		/* irq soft-enable flag */
+	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 
 	/* Stuff for accurate time accounting */
diff --git a/include/asm-powerpc/pci-bridge.h b/include/asm-powerpc/pci-bridge.h
index 86ee46b09b8a..7bb7f9009806 100644
--- a/include/asm-powerpc/pci-bridge.h
+++ b/include/asm-powerpc/pci-bridge.h
@@ -25,6 +25,7 @@ struct pci_controller {
 	int node;
 	void *arch_data;
 	struct list_head list_node;
+	struct device *parent;
 
 	int first_busno;
 	int last_busno;
diff --git a/include/asm-powerpc/pci.h b/include/asm-powerpc/pci.h
index 721c97f09b20..16f13319c769 100644
--- a/include/asm-powerpc/pci.h
+++ b/include/asm-powerpc/pci.h
@@ -70,15 +70,15 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
  */
 #define PCI_DISABLE_MWI
 
-extern struct dma_mapping_ops pci_dma_ops;
+extern struct dma_mapping_ops *pci_dma_ops;
 
 /* For DAC DMA, we currently don't support it by default, but
  * we let 64-bit platforms override this.
  */
 static inline int pci_dac_dma_supported(struct pci_dev *hwdev,u64 mask)
 {
-	if (pci_dma_ops.dac_dma_supported)
-		return pci_dma_ops.dac_dma_supported(&hwdev->dev, mask);
+	if (pci_dma_ops && pci_dma_ops->dac_dma_supported)
+		return pci_dma_ops->dac_dma_supported(&hwdev->dev, mask);
 	return 0;
 }
 
@@ -210,6 +210,8 @@ extern int remap_bus_range(struct pci_bus *bus);
 extern void pcibios_fixup_device_resources(struct pci_dev *dev,
 			struct pci_bus *bus);
 
+extern void pcibios_setup_new_device(struct pci_dev *dev);
+
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
 extern struct pci_controller *init_phb_dynamic(struct device_node *dn);
@@ -232,12 +234,10 @@ extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
 					 unsigned long size,
 					 pgprot_t prot);
 
-#if defined(CONFIG_PPC_MULTIPLATFORM) || defined(CONFIG_PPC32)
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
 extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
 				 const struct resource *rsrc,
 				 resource_size_t *start, resource_size_t *end);
-#endif /* CONFIG_PPC_MULTIPLATFORM || CONFIG_PPC32 */
 
 #endif	/* __KERNEL__ */
 #endif /* __ASM_POWERPC_PCI_H */
diff --git a/include/asm-powerpc/ppc-pci.h b/include/asm-powerpc/ppc-pci.h
index 1115756c79f9..ab6eddb518c7 100644
--- a/include/asm-powerpc/ppc-pci.h
+++ b/include/asm-powerpc/ppc-pci.h
@@ -36,18 +36,17 @@ typedef void *(*traverse_func)(struct device_node *me, void *data);
 void *traverse_pci_devices(struct device_node *start, traverse_func pre,
 		void *data);
 
-void pci_devs_phb_init(void);
-void pci_devs_phb_init_dynamic(struct pci_controller *phb);
-int setup_phb(struct device_node *dev, struct pci_controller *phb);
-void __devinit scan_phb(struct pci_controller *hose);
+extern void pci_devs_phb_init(void);
+extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
+extern void scan_phb(struct pci_controller *hose);
 
 /* From rtas_pci.h */
-void init_pci_config_tokens (void);
-unsigned long get_phb_buid (struct device_node *);
+extern void init_pci_config_tokens (void);
+extern unsigned long get_phb_buid (struct device_node *);
+extern int rtas_setup_phb(struct pci_controller *phb);
 
 /* From pSeries_pci.h */
 extern void pSeries_final_fixup(void);
-extern void pSeries_irq_bus_setup(struct pci_bus *bus);
 
 extern unsigned long pci_probe_only;
 
diff --git a/include/asm-powerpc/processor.h b/include/asm-powerpc/processor.h
index 6cb6fb19e57f..a26c32ee5527 100644
--- a/include/asm-powerpc/processor.h
+++ b/include/asm-powerpc/processor.h
@@ -53,10 +53,6 @@ extern unsigned char ucBoardRevMaj, ucBoardRevMin;
 
 #endif /* CONFIG_PPC_PREP */
 
-#ifndef CONFIG_PPC_MULTIPLATFORM
-#define _machine 0
-#endif /* CONFIG_PPC_MULTIPLATFORM */
-
 #endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */
 
 /*
diff --git a/include/asm-powerpc/prom.h b/include/asm-powerpc/prom.h
index ec11d44eaeb5..0afee17f33b4 100644
--- a/include/asm-powerpc/prom.h
+++ b/include/asm-powerpc/prom.h
@@ -17,6 +17,7 @@
  */
 #include <linux/types.h>
 #include <linux/proc_fs.h>
+#include <linux/platform_device.h>
 #include <asm/atomic.h>
 
 /* Definitions used by the flattened device tree */
@@ -333,6 +334,20 @@ extern int of_irq_map_one(struct device_node *device, int index,
 struct pci_dev;
 extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
 
+static inline int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
+{
+	int irq = irq_of_parse_and_map(dev, index);
+
+	/* Only dereference the resource if both the
+	 * resource and the irq are valid. */
+	if (r && irq != NO_IRQ) {
+		r->start = r->end = irq;
+		r->flags = IORESOURCE_IRQ;
+	}
+
+	return irq;
+}
+
 
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_PROM_H */
diff --git a/include/asm-powerpc/ps3.h b/include/asm-powerpc/ps3.h
new file mode 100644
index 000000000000..52a69ed0d90a
--- /dev/null
+++ b/include/asm-powerpc/ps3.h
@@ -0,0 +1,462 @@
+/*
+ *  PS3 platform declarations.
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ *
+ *  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.
+ *
+ *  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
+ */
+
+#if !defined(_ASM_POWERPC_PS3_H)
+#define _ASM_POWERPC_PS3_H
+
+#include <linux/compiler.h> /* for __deprecated */
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+
+/**
+ * struct ps3_device_id - HV bus device identifier from the system repository
+ * @bus_id: HV bus id, {1..} (zero invalid)
+ * @dev_id: HV device id, {0..}
+ */
+
+struct ps3_device_id {
+	unsigned int bus_id;
+	unsigned int dev_id;
+};
+
+
+/* dma routines */
+
+enum ps3_dma_page_size {
+	PS3_DMA_4K = 12U,
+	PS3_DMA_64K = 16U,
+	PS3_DMA_1M = 20U,
+	PS3_DMA_16M = 24U,
+};
+
+enum ps3_dma_region_type {
+	PS3_DMA_OTHER = 0,
+	PS3_DMA_INTERNAL = 2,
+};
+
+/**
+ * struct ps3_dma_region - A per device dma state variables structure
+ * @did: The HV device id.
+ * @page_size: The ioc pagesize.
+ * @region_type: The HV region type.
+ * @bus_addr: The 'translated' bus address of the region.
+ * @len: The length in bytes of the region.
+ * @chunk_list: Opaque variable used by the ioc page manager.
+ */
+
+struct ps3_dma_region {
+	struct ps3_device_id did;
+	enum ps3_dma_page_size page_size;
+	enum ps3_dma_region_type region_type;
+	unsigned long bus_addr;
+	unsigned long len;
+	struct {
+		spinlock_t lock;
+		struct list_head head;
+	} chunk_list;
+};
+
+/**
+ * struct ps3_dma_region_init - Helper to initialize structure variables
+ *
+ * Helper to properly initialize variables prior to calling
+ * ps3_system_bus_device_register.
+ */
+
+static inline void ps3_dma_region_init(struct ps3_dma_region *r,
+	const struct ps3_device_id* did, enum ps3_dma_page_size page_size,
+	enum ps3_dma_region_type region_type)
+{
+	r->did = *did;
+	r->page_size = page_size;
+	r->region_type = region_type;
+}
+int ps3_dma_region_create(struct ps3_dma_region *r);
+int ps3_dma_region_free(struct ps3_dma_region *r);
+int ps3_dma_map(struct ps3_dma_region *r, unsigned long virt_addr,
+	unsigned long len, unsigned long *bus_addr);
+int ps3_dma_unmap(struct ps3_dma_region *r, unsigned long bus_addr,
+	unsigned long len);
+
+/* mmio routines */
+
+enum ps3_mmio_page_size {
+	PS3_MMIO_4K = 12U,
+	PS3_MMIO_64K = 16U
+};
+
+/**
+ * struct ps3_mmio_region - a per device mmio state variables structure
+ *
+ * Current systems can be supported with a single region per device.
+ */
+
+struct ps3_mmio_region {
+	struct ps3_device_id did;
+	unsigned long bus_addr;
+	unsigned long len;
+	enum ps3_mmio_page_size page_size;
+	unsigned long lpar_addr;
+};
+
+/**
+ * struct ps3_mmio_region_init - Helper to initialize structure variables
+ *
+ * Helper to properly initialize variables prior to calling
+ * ps3_system_bus_device_register.
+ */
+
+static inline void ps3_mmio_region_init(struct ps3_mmio_region *r,
+	const struct ps3_device_id* did, unsigned long bus_addr,
+	unsigned long len, enum ps3_mmio_page_size page_size)
+{
+	r->did = *did;
+	r->bus_addr = bus_addr;
+	r->len = len;
+	r->page_size = page_size;
+}
+int ps3_mmio_region_create(struct ps3_mmio_region *r);
+int ps3_free_mmio_region(struct ps3_mmio_region *r);
+unsigned long ps3_mm_phys_to_lpar(unsigned long phys_addr);
+
+/* inrerrupt routines */
+
+int ps3_alloc_io_irq(unsigned int interrupt_id, unsigned int *virq);
+int ps3_free_io_irq(unsigned int virq);
+int ps3_alloc_event_irq(unsigned int *virq);
+int ps3_free_event_irq(unsigned int virq);
+int ps3_send_event_locally(unsigned int virq);
+int ps3_connect_event_irq(const struct ps3_device_id *did,
+	unsigned int interrupt_id, unsigned int *virq);
+int ps3_disconnect_event_irq(const struct ps3_device_id *did,
+	unsigned int interrupt_id, unsigned int virq);
+int ps3_alloc_vuart_irq(void* virt_addr_bmp, unsigned int *virq);
+int ps3_free_vuart_irq(unsigned int virq);
+int ps3_alloc_spe_irq(unsigned long spe_id, unsigned int class,
+	unsigned int *virq);
+int ps3_free_spe_irq(unsigned int virq);
+
+/* lv1 result codes */
+
+enum lv1_result {
+	LV1_SUCCESS                     = 0,
+	/* not used                       -1 */
+	LV1_RESOURCE_SHORTAGE           = -2,
+	LV1_NO_PRIVILEGE                = -3,
+	LV1_DENIED_BY_POLICY            = -4,
+	LV1_ACCESS_VIOLATION            = -5,
+	LV1_NO_ENTRY                    = -6,
+	LV1_DUPLICATE_ENTRY             = -7,
+	LV1_TYPE_MISMATCH               = -8,
+	LV1_BUSY                        = -9,
+	LV1_EMPTY                       = -10,
+	LV1_WRONG_STATE                 = -11,
+	/* not used                       -12 */
+	LV1_NO_MATCH                    = -13,
+	LV1_ALREADY_CONNECTED           = -14,
+	LV1_UNSUPPORTED_PARAMETER_VALUE = -15,
+	LV1_CONDITION_NOT_SATISFIED     = -16,
+	LV1_ILLEGAL_PARAMETER_VALUE     = -17,
+	LV1_BAD_OPTION                  = -18,
+	LV1_IMPLEMENTATION_LIMITATION   = -19,
+	LV1_NOT_IMPLEMENTED             = -20,
+	LV1_INVALID_CLASS_ID            = -21,
+	LV1_CONSTRAINT_NOT_SATISFIED    = -22,
+	LV1_ALIGNMENT_ERROR             = -23,
+	LV1_INTERNAL_ERROR              = -32768,
+};
+
+static inline const char* ps3_result(int result)
+{
+#if defined(DEBUG)
+	switch (result) {
+	case LV1_SUCCESS:
+		return "LV1_SUCCESS (0)";
+	case -1:
+		return "** unknown result ** (-1)";
+	case LV1_RESOURCE_SHORTAGE:
+		return "LV1_RESOURCE_SHORTAGE (-2)";
+	case LV1_NO_PRIVILEGE:
+		return "LV1_NO_PRIVILEGE (-3)";
+	case LV1_DENIED_BY_POLICY:
+		return "LV1_DENIED_BY_POLICY (-4)";
+	case LV1_ACCESS_VIOLATION:
+		return "LV1_ACCESS_VIOLATION (-5)";
+	case LV1_NO_ENTRY:
+		return "LV1_NO_ENTRY (-6)";
+	case LV1_DUPLICATE_ENTRY:
+		return "LV1_DUPLICATE_ENTRY (-7)";
+	case LV1_TYPE_MISMATCH:
+		return "LV1_TYPE_MISMATCH (-8)";
+	case LV1_BUSY:
+		return "LV1_BUSY (-9)";
+	case LV1_EMPTY:
+		return "LV1_EMPTY (-10)";
+	case LV1_WRONG_STATE:
+		return "LV1_WRONG_STATE (-11)";
+	case -12:
+		return "** unknown result ** (-12)";
+	case LV1_NO_MATCH:
+		return "LV1_NO_MATCH (-13)";
+	case LV1_ALREADY_CONNECTED:
+		return "LV1_ALREADY_CONNECTED (-14)";
+	case LV1_UNSUPPORTED_PARAMETER_VALUE:
+		return "LV1_UNSUPPORTED_PARAMETER_VALUE (-15)";
+	case LV1_CONDITION_NOT_SATISFIED:
+		return "LV1_CONDITION_NOT_SATISFIED (-16)";
+	case LV1_ILLEGAL_PARAMETER_VALUE:
+		return "LV1_ILLEGAL_PARAMETER_VALUE (-17)";
+	case LV1_BAD_OPTION:
+		return "LV1_BAD_OPTION (-18)";
+	case LV1_IMPLEMENTATION_LIMITATION:
+		return "LV1_IMPLEMENTATION_LIMITATION (-19)";
+	case LV1_NOT_IMPLEMENTED:
+		return "LV1_NOT_IMPLEMENTED (-20)";
+	case LV1_INVALID_CLASS_ID:
+		return "LV1_INVALID_CLASS_ID (-21)";
+	case LV1_CONSTRAINT_NOT_SATISFIED:
+		return "LV1_CONSTRAINT_NOT_SATISFIED (-22)";
+	case LV1_ALIGNMENT_ERROR:
+		return "LV1_ALIGNMENT_ERROR (-23)";
+	case LV1_INTERNAL_ERROR:
+		return "LV1_INTERNAL_ERROR (-32768)";
+	default:
+		BUG();
+		return "** unknown result **";
+	};
+#else
+	return "";
+#endif
+}
+
+/* repository bus info */
+
+enum ps3_bus_type {
+	PS3_BUS_TYPE_SB = 4,
+	PS3_BUS_TYPE_STORAGE = 5,
+};
+
+enum ps3_dev_type {
+	PS3_DEV_TYPE_SB_GELIC = 3,
+	PS3_DEV_TYPE_SB_USB = 4,
+	PS3_DEV_TYPE_SB_GPIO = 6,
+};
+
+int ps3_repository_read_bus_str(unsigned int bus_index, const char *bus_str,
+	u64 *value);
+int ps3_repository_read_bus_id(unsigned int bus_index, unsigned int *bus_id);
+int ps3_repository_read_bus_type(unsigned int bus_index,
+	enum ps3_bus_type *bus_type);
+int ps3_repository_read_bus_num_dev(unsigned int bus_index,
+	unsigned int *num_dev);
+
+/* repository bus device info */
+
+enum ps3_interrupt_type {
+	PS3_INTERRUPT_TYPE_EVENT_PORT = 2,
+	PS3_INTERRUPT_TYPE_SB_OHCI = 3,
+	PS3_INTERRUPT_TYPE_SB_EHCI = 4,
+	PS3_INTERRUPT_TYPE_OTHER = 5,
+};
+
+enum ps3_region_type {
+	PS3_REGION_TYPE_SB_OHCI = 3,
+	PS3_REGION_TYPE_SB_EHCI = 4,
+	PS3_REGION_TYPE_SB_GPIO = 5,
+};
+
+int ps3_repository_read_dev_str(unsigned int bus_index,
+	unsigned int dev_index, const char *dev_str, u64 *value);
+int ps3_repository_read_dev_id(unsigned int bus_index, unsigned int dev_index,
+	unsigned int *dev_id);
+int ps3_repository_read_dev_type(unsigned int bus_index,
+	unsigned int dev_index, enum ps3_dev_type *dev_type);
+int ps3_repository_read_dev_intr(unsigned int bus_index,
+	unsigned int dev_index, unsigned int intr_index,
+	enum ps3_interrupt_type *intr_type, unsigned int *interrupt_id);
+int ps3_repository_read_dev_reg_type(unsigned int bus_index,
+	unsigned int dev_index, unsigned int reg_index,
+	enum ps3_region_type *reg_type);
+int ps3_repository_read_dev_reg_addr(unsigned int bus_index,
+	unsigned int dev_index, unsigned int reg_index, u64 *bus_addr,
+	u64 *len);
+int ps3_repository_read_dev_reg(unsigned int bus_index,
+	unsigned int dev_index, unsigned int reg_index,
+	enum ps3_region_type *reg_type, u64 *bus_addr, u64 *len);
+
+/* repository bus enumerators */
+
+struct ps3_repository_device {
+	unsigned int bus_index;
+	unsigned int dev_index;
+	struct ps3_device_id did;
+};
+
+int ps3_repository_find_device(enum ps3_bus_type bus_type,
+	enum ps3_dev_type dev_type,
+	const struct ps3_repository_device *start_dev,
+	struct ps3_repository_device *dev);
+static inline int ps3_repository_find_first_device(
+	enum ps3_bus_type bus_type, enum ps3_dev_type dev_type,
+	struct ps3_repository_device *dev)
+{
+	return ps3_repository_find_device(bus_type, dev_type, NULL, dev);
+}
+int ps3_repository_find_interrupt(const struct ps3_repository_device *dev,
+	enum ps3_interrupt_type intr_type, unsigned int *interrupt_id);
+int ps3_repository_find_region(const struct ps3_repository_device *dev,
+	enum ps3_region_type reg_type, u64 *bus_addr, u64 *len);
+
+/* repository block device info */
+
+int ps3_repository_read_dev_port(unsigned int bus_index,
+	unsigned int dev_index, u64 *port);
+int ps3_repository_read_dev_blk_size(unsigned int bus_index,
+	unsigned int dev_index, u64 *blk_size);
+int ps3_repository_read_dev_num_blocks(unsigned int bus_index,
+	unsigned int dev_index, u64 *num_blocks);
+int ps3_repository_read_dev_num_regions(unsigned int bus_index,
+	unsigned int dev_index, unsigned int *num_regions);
+int ps3_repository_read_dev_region_id(unsigned int bus_index,
+	unsigned int dev_index, unsigned int region_index,
+	unsigned int *region_id);
+int ps3_repository_read_dev_region_size(unsigned int bus_index,
+	unsigned int dev_index,	unsigned int region_index, u64 *region_size);
+int ps3_repository_read_dev_region_start(unsigned int bus_index,
+	unsigned int dev_index, unsigned int region_index, u64 *region_start);
+
+/* repository pu and memory info */
+
+int ps3_repository_read_num_pu(unsigned int *num_pu);
+int ps3_repository_read_ppe_id(unsigned int *pu_index, unsigned int *ppe_id);
+int ps3_repository_read_rm_base(unsigned int ppe_id, u64 *rm_base);
+int ps3_repository_read_rm_size(unsigned int ppe_id, u64 *rm_size);
+int ps3_repository_read_region_total(u64 *region_total);
+int ps3_repository_read_mm_info(u64 *rm_base, u64 *rm_size,
+	u64 *region_total);
+
+/* repository pme info */
+
+int ps3_repository_read_num_be(unsigned int *num_be);
+int ps3_repository_read_be_node_id(unsigned int be_index, u64 *node_id);
+int ps3_repository_read_tb_freq(u64 node_id, u64 *tb_freq);
+int ps3_repository_read_be_tb_freq(unsigned int be_index, u64 *tb_freq);
+
+/* repository 'Other OS' area */
+
+int ps3_repository_read_boot_dat_addr(u64 *lpar_addr);
+int ps3_repository_read_boot_dat_size(unsigned int *size);
+int ps3_repository_read_boot_dat_info(u64 *lpar_addr, unsigned int *size);
+
+/* repository spu info */
+
+/**
+ * enum spu_resource_type - Type of spu resource.
+ * @spu_resource_type_shared: Logical spu is shared with other partions.
+ * @spu_resource_type_exclusive: Logical spu is not shared with other partions.
+ *
+ * Returned by ps3_repository_read_spu_resource_id().
+ */
+
+enum ps3_spu_resource_type {
+	PS3_SPU_RESOURCE_TYPE_SHARED = 0,
+	PS3_SPU_RESOURCE_TYPE_EXCLUSIVE = 0x8000000000000000UL,
+};
+
+int ps3_repository_read_num_spu_reserved(unsigned int *num_spu_reserved);
+int ps3_repository_read_num_spu_resource_id(unsigned int *num_resource_id);
+int ps3_repository_read_spu_resource_id(unsigned int res_index,
+	enum ps3_spu_resource_type* resource_type, unsigned int *resource_id);
+
+
+/* system bus routines */
+
+enum ps3_match_id {
+	PS3_MATCH_ID_EHCI = 1,
+	PS3_MATCH_ID_OHCI,
+	PS3_MATCH_ID_GELIC,
+	PS3_MATCH_ID_AV_SETTINGS,
+	PS3_MATCH_ID_SYSTEM_MANAGER,
+};
+
+/**
+ * struct ps3_system_bus_device - a device on the system bus
+ */
+
+struct ps3_system_bus_device {
+	enum ps3_match_id match_id;
+	struct ps3_device_id did;
+	unsigned int interrupt_id;
+/*	struct iommu_table *iommu_table; -- waiting for Ben's cleanups */
+	struct ps3_dma_region *d_region;
+	struct ps3_mmio_region *m_region;
+	struct device core;
+};
+
+/**
+ * struct ps3_system_bus_driver - a driver for a device on the system bus
+ */
+
+struct ps3_system_bus_driver {
+	enum ps3_match_id match_id;
+	struct device_driver core;
+	int (*probe)(struct ps3_system_bus_device *);
+	int (*remove)(struct ps3_system_bus_device *);
+/*	int (*suspend)(struct ps3_system_bus_device *, pm_message_t); */
+/*	int (*resume)(struct ps3_system_bus_device *); */
+};
+
+int ps3_system_bus_device_register(struct ps3_system_bus_device *dev);
+int ps3_system_bus_driver_register(struct ps3_system_bus_driver *drv);
+void ps3_system_bus_driver_unregister(struct ps3_system_bus_driver *drv);
+static inline struct ps3_system_bus_driver *to_ps3_system_bus_driver(
+	struct device_driver *_drv)
+{
+	return container_of(_drv, struct ps3_system_bus_driver, core);
+}
+static inline struct ps3_system_bus_device *to_ps3_system_bus_device(
+	struct device *_dev)
+{
+	return container_of(_dev, struct ps3_system_bus_device, core);
+}
+
+/**
+ * ps3_system_bus_set_drvdata -
+ * @dev: device structure
+ * @data: Data to set
+ */
+
+static inline void ps3_system_bus_set_driver_data(
+	struct ps3_system_bus_device *dev, void *data)
+{
+	dev->core.driver_data = data;
+}
+static inline void *ps3_system_bus_get_driver_data(
+	struct ps3_system_bus_device *dev)
+{
+	return dev->core.driver_data;
+}
+
+/* These two need global scope for get_dma_ops(). */
+
+extern struct bus_type ps3_system_bus_type;
+
+#endif
diff --git a/include/asm-powerpc/rtas.h b/include/asm-powerpc/rtas.h
index d34f9e1f242c..5a0c136c0416 100644
--- a/include/asm-powerpc/rtas.h
+++ b/include/asm-powerpc/rtas.h
@@ -54,8 +54,6 @@ struct rtas_args {
 	rtas_arg_t *rets;     /* Pointer to return values in args[]. */
 };  
 
-extern struct rtas_args rtas_stop_self_args;
-
 struct rtas_t {
 	unsigned long entry;		/* physical address pointer */
 	unsigned long base;		/* physical address pointer */
diff --git a/include/asm-powerpc/sparsemem.h b/include/asm-powerpc/sparsemem.h
index 38b1ea3b58fd..48ad807a0b8a 100644
--- a/include/asm-powerpc/sparsemem.h
+++ b/include/asm-powerpc/sparsemem.h
@@ -9,8 +9,14 @@
  * MAX_PHYSMEM_BITS		2^N: how much memory we can have in that space
  */
 #define SECTION_SIZE_BITS       24
+
+#if defined(CONFIG_PS3_USE_LPAR_ADDR)
+#define MAX_PHYSADDR_BITS       47
+#define MAX_PHYSMEM_BITS        47
+#else
 #define MAX_PHYSADDR_BITS       44
 #define MAX_PHYSMEM_BITS        44
+#endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern void create_section_mapping(unsigned long start, unsigned long end);
diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h
index e73ea00efd8b..fdad4267b447 100644
--- a/include/asm-powerpc/spu.h
+++ b/include/asm-powerpc/spu.h
@@ -111,14 +111,12 @@ struct spu {
 	u8 *local_store;
 	unsigned long problem_phys;
 	struct spu_problem __iomem *problem;
-	struct spu_priv1 __iomem *priv1;
 	struct spu_priv2 __iomem *priv2;
 	struct list_head list;
 	struct list_head sched_list;
+	struct list_head full_list;
 	int number;
-	int nid;
 	unsigned int irqs[3];
-	u32 isrc;
 	u32 node;
 	u64 flags;
 	u64 dar;
@@ -144,6 +142,7 @@ struct spu {
 	char irq_c1[8];
 	char irq_c2[8];
 
+	void* pdata; /* platform private data */
 	struct sys_device sysdev;
 };
 
@@ -170,6 +169,13 @@ extern struct spufs_calls {
 	struct module *owner;
 } spufs_calls;
 
+/* coredump calls implemented in spufs */
+struct spu_coredump_calls {
+	asmlinkage int (*arch_notes_size)(void);
+	asmlinkage void (*arch_write_notes)(struct file *file);
+	struct module *owner;
+};
+
 /* return status from spu_run, same as in libspe */
 #define SPE_EVENT_DMA_ALIGNMENT		0x0008	/*A DMA alignment error */
 #define SPE_EVENT_SPE_ERROR		0x0010	/*An illegal instruction error*/
@@ -182,8 +188,10 @@ extern struct spufs_calls {
  */
 #define SPU_CREATE_EVENTS_ENABLED	0x0001
 #define SPU_CREATE_GANG			0x0002
+#define SPU_CREATE_NOSCHED		0x0004
+#define SPU_CREATE_ISOLATE		0x0008
 
-#define SPU_CREATE_FLAG_ALL		0x0003 /* mask of all valid flags */
+#define SPU_CREATE_FLAG_ALL		0x000f /* mask of all valid flags */
 
 
 #ifdef CONFIG_SPU_FS_MODULE
@@ -199,6 +207,15 @@ static inline void unregister_spu_syscalls(struct spufs_calls *calls)
 }
 #endif /* MODULE */
 
+int register_arch_coredump_calls(struct spu_coredump_calls *calls);
+void unregister_arch_coredump_calls(struct spu_coredump_calls *calls);
+
+int spu_add_sysdev_attr(struct sysdev_attribute *attr);
+void spu_remove_sysdev_attr(struct sysdev_attribute *attr);
+
+int spu_add_sysdev_attr_group(struct attribute_group *attrs);
+void spu_remove_sysdev_attr_group(struct attribute_group *attrs);
+
 
 /*
  * Notifier blocks:
@@ -277,6 +294,7 @@ struct spu_problem {
 	u32 spu_runcntl_RW;					/* 0x401c */
 #define SPU_RUNCNTL_STOP	0L
 #define SPU_RUNCNTL_RUNNABLE	1L
+#define SPU_RUNCNTL_ISOLATE	2L
 	u8  pad_0x4020_0x4024[0x4];				/* 0x4020 */
 	u32 spu_status_R;					/* 0x4024 */
 #define SPU_STOP_STATUS_SHIFT           16
@@ -289,8 +307,8 @@ struct spu_problem {
 #define SPU_STATUS_INVALID_INSTR        0x20
 #define SPU_STATUS_INVALID_CH           0x40
 #define SPU_STATUS_ISOLATED_STATE       0x80
-#define SPU_STATUS_ISOLATED_LOAD_STAUTUS 0x200
-#define SPU_STATUS_ISOLATED_EXIT_STAUTUS 0x400
+#define SPU_STATUS_ISOLATED_LOAD_STATUS 0x200
+#define SPU_STATUS_ISOLATED_EXIT_STATUS 0x400
 	u8  pad_0x4028_0x402c[0x4];				/* 0x4028 */
 	u32 spu_spe_R;						/* 0x402c */
 	u8  pad_0x4030_0x4034[0x4];				/* 0x4030 */
diff --git a/include/asm-powerpc/spu_csa.h b/include/asm-powerpc/spu_csa.h
index 964c2d38ccb7..bdbf906a767f 100644
--- a/include/asm-powerpc/spu_csa.h
+++ b/include/asm-powerpc/spu_csa.h
@@ -151,7 +151,6 @@ struct spu_priv1_collapsed {
 	u64 mfc_fir_chkstp_enable_RW;
 	u64 smf_sbi_signal_sel;
 	u64 smf_ato_signal_sel;
-	u64 mfc_sdr_RW;
 	u64 tlb_index_hint_RO;
 	u64 tlb_index_W;
 	u64 tlb_vpn_RW;
diff --git a/include/asm-powerpc/spu_info.h b/include/asm-powerpc/spu_info.h
new file mode 100644
index 000000000000..3545efbf9891
--- /dev/null
+++ b/include/asm-powerpc/spu_info.h
@@ -0,0 +1,54 @@
+/*
+ * SPU info structures
+ *
+ * (C) Copyright 2006 IBM Corp.
+ *
+ * Author: Dwayne Grant McConnell <decimal@us.ibm.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, 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 _SPU_INFO_H
+#define _SPU_INFO_H
+
+#ifdef __KERNEL__
+#include <asm/spu.h>
+#include <linux/types.h>
+#else
+struct mfc_cq_sr {
+	__u64 mfc_cq_data0_RW;
+	__u64 mfc_cq_data1_RW;
+	__u64 mfc_cq_data2_RW;
+	__u64 mfc_cq_data3_RW;
+};
+#endif /* __KERNEL__ */
+
+struct spu_dma_info {
+	__u64 dma_info_type;
+	__u64 dma_info_mask;
+	__u64 dma_info_status;
+	__u64 dma_info_stall_and_notify;
+	__u64 dma_info_atomic_command_status;
+	struct mfc_cq_sr dma_info_command_data[16];
+};
+
+struct spu_proxydma_info {
+	__u64 proxydma_info_type;
+	__u64 proxydma_info_mask;
+	__u64 proxydma_info_status;
+	struct mfc_cq_sr proxydma_info_command_data[8];
+};
+
+#endif
diff --git a/include/asm-powerpc/spu_priv1.h b/include/asm-powerpc/spu_priv1.h
index 300c458b6d06..69dcb0c53884 100644
--- a/include/asm-powerpc/spu_priv1.h
+++ b/include/asm-powerpc/spu_priv1.h
@@ -21,12 +21,13 @@
 #define _SPU_PRIV1_H
 #if defined(__KERNEL__)
 
+#include <linux/types.h>
+
 struct spu;
 
 /* access to priv1 registers */
 
-struct spu_priv1_ops
-{
+struct spu_priv1_ops {
 	void (*int_mask_and) (struct spu *spu, int class, u64 mask);
 	void (*int_mask_or) (struct spu *spu, int class, u64 mask);
 	void (*int_mask_set) (struct spu *spu, int class, u64 mask);
@@ -37,7 +38,7 @@ struct spu_priv1_ops
 	u64 (*mfc_dar_get) (struct spu *spu);
 	u64 (*mfc_dsisr_get) (struct spu *spu);
 	void (*mfc_dsisr_set) (struct spu *spu, u64 dsisr);
-	void (*mfc_sdr_set) (struct spu *spu, u64 sdr);
+	void (*mfc_sdr_setup) (struct spu *spu);
 	void (*mfc_sr1_set) (struct spu *spu, u64 sr1);
 	u64 (*mfc_sr1_get) (struct spu *spu);
 	void (*mfc_tclass_id_set) (struct spu *spu, u64 tclass_id);
@@ -112,9 +113,9 @@ spu_mfc_dsisr_set (struct spu *spu, u64 dsisr)
 }
 
 static inline void
-spu_mfc_sdr_set (struct spu *spu, u64 sdr)
+spu_mfc_sdr_setup (struct spu *spu)
 {
-	spu_priv1_ops->mfc_sdr_set(spu, sdr);
+	spu_priv1_ops->mfc_sdr_setup(spu);
 }
 
 static inline void
@@ -171,12 +172,41 @@ spu_resource_allocation_enable_get (struct spu *spu)
 	return spu_priv1_ops->resource_allocation_enable_get(spu);
 }
 
-/* The declarations folowing are put here for convenience
- * and only intended to be used by the platform setup code
- * for initializing spu_priv1_ops.
+/* spu management abstraction */
+
+struct spu_management_ops {
+	int (*enumerate_spus)(int (*fn)(void *data));
+	int (*create_spu)(struct spu *spu, void *data);
+	int (*destroy_spu)(struct spu *spu);
+};
+
+extern const struct spu_management_ops* spu_management_ops;
+
+static inline int
+spu_enumerate_spus (int (*fn)(void *data))
+{
+	return spu_management_ops->enumerate_spus(fn);
+}
+
+static inline int
+spu_create_spu (struct spu *spu, void *data)
+{
+	return spu_management_ops->create_spu(spu, data);
+}
+
+static inline int
+spu_destroy_spu (struct spu *spu)
+{
+	return spu_management_ops->destroy_spu(spu);
+}
+
+/*
+ * The declarations folowing are put here for convenience
+ * and only intended to be used by the platform setup code.
  */
 
 extern const struct spu_priv1_ops spu_priv1_mmio_ops;
+extern const struct spu_management_ops spu_management_of_ops;
 
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/asm-powerpc/todc.h b/include/asm-powerpc/todc.h
deleted file mode 100644
index 60a8c39b8c11..000000000000
--- a/include/asm-powerpc/todc.h
+++ /dev/null
@@ -1,487 +0,0 @@
-/*
- * Definitions for the M48Txx and mc146818 series of Time of day/Real Time
- * Clock chips.
- *
- * Author: Mark A. Greer <mgreer@mvista.com>
- *
- * 2001 (c) MontaVista, Software, Inc.  This file is licensed under
- * the terms of the GNU General Public License version 2.  This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-/*
- * Support for the M48T37/M48T59/.../mc146818 Real Time Clock chips.
- * Purpose is to make one generic file that handles all of these chips instead
- * of every platform implementing the same code over & over again.
- */
-
-#ifndef __PPC_KERNEL_TODC_H
-#define __PPC_KERNEL_TODC_H
-
-typedef struct {
-	uint rtc_type;		/* your particular chip */
-
-	/*
-	 * Following are the addresses of the AS0, AS1, and DATA registers
-	 * of these chips.  Note that these are board-specific.
-	 */
-	unsigned int nvram_as0;
-	unsigned int nvram_as1;
-	unsigned int nvram_data;
-
-	/*
-	 * Define bits to stop external set of regs from changing so
-	 * the chip can be read/written reliably.
-	 */
-	unsigned char enable_read;
-	unsigned char enable_write;
-
-	/*
-	 * Following is the number of AS0 address bits.  This is normally
-	 * 8 but some bad hardware routes address lines incorrectly.
-	 */
-	int as0_bits;
-
-	int nvram_size;	/* Size of NVRAM on chip */
-	int sw_flags;	/* Software control flags */
-
-	/* Following are the register offsets for the particular chip */
-	int year;
-	int month;
-	int day_of_month;
-	int day_of_week;
-	int hours;
-	int minutes;
-	int seconds;
-	int control_b;
-	int control_a;
-	int watchdog;
-	int interrupts;
-	int alarm_date;
-	int alarm_hour;
-	int alarm_minutes;
-	int alarm_seconds;
-	int century;
-	int flags;
-
-	/*
-	 * Some RTC chips have their NVRAM buried behind a addr/data pair of
-	 * regs on the first level/clock registers.  The following fields
-	 * are the addresses for those addr/data regs.
-	 */
-	int nvram_addr_reg;
-	int nvram_data_reg;
-} todc_info_t;
-
-/*
- * Define the types of TODC/RTC variants that are supported in
- * arch/ppc/kernel/todc_time.c
- * Make a new one of these for any chip somehow differs from what's already
- * defined.  That way, if you ever need to put in code to touch those
- * bits/registers in todc_time.c, you can put it inside an
- * 'if (todc_info->rtc_type == TODC_TYPE_XXX)' so you won't break
- * anyone else.
- */
-#define TODC_TYPE_MK48T35		1
-#define TODC_TYPE_MK48T37		2
-#define TODC_TYPE_MK48T59		3
-#define TODC_TYPE_DS1693		4	/* Dallas DS1693 RTC */
-#define TODC_TYPE_DS1743		5	/* Dallas DS1743 RTC */
-#define TODC_TYPE_DS1746		6	/* Dallas DS1746 RTC */
-#define TODC_TYPE_DS1747		7	/* Dallas DS1747 RTC */
-#define TODC_TYPE_DS1501		8	/* Dallas DS1501 RTC */
-#define TODC_TYPE_DS1643		9	/* Dallas DS1643 RTC */
-#define TODC_TYPE_PC97307		10	/* PC97307 internal RTC */
-#define TODC_TYPE_DS1557		11	/* Dallas DS1557 RTC */
-#define TODC_TYPE_DS17285		12	/* Dallas DS17285 RTC */
-#define TODC_TYPE_DS1553		13	/* Dallas DS1553 RTC */
-#define TODC_TYPE_MC146818		100	/* Leave room for m48txx's */
-
-/*
- * Bit to clear/set to enable reads/writes to the chip
- */
-#define TODC_MK48TXX_CNTL_A_R		0x40
-#define TODC_MK48TXX_CNTL_A_W		0x80
-#define TODC_MK48TXX_DAY_CB		0x80
-
-#define TODC_DS1501_CNTL_B_TE		0x80
-
-/*
- * Define flag bits used by todc routines.
- */
-#define TODC_FLAG_2_LEVEL_NVRAM		0x00000001
-
-/*
- * Define the values for the various RTC's that should to into the todc_info
- * table.
- * Note: The XXX_NVRAM_SIZE, XXX_NVRAM_ADDR_REG, and XXX_NVRAM_DATA_REG only
- * matter if XXX_SW_FLAGS has TODC_FLAG_2_LEVEL_NVRAM set.
- */
-#define TODC_TYPE_MK48T35_NVRAM_SIZE		0x7ff8
-#define TODC_TYPE_MK48T35_SW_FLAGS		0
-#define TODC_TYPE_MK48T35_YEAR			0x7fff
-#define TODC_TYPE_MK48T35_MONTH			0x7ffe
-#define TODC_TYPE_MK48T35_DOM			0x7ffd	/* Day of Month */
-#define TODC_TYPE_MK48T35_DOW			0x7ffc	/* Day of Week */
-#define TODC_TYPE_MK48T35_HOURS			0x7ffb
-#define TODC_TYPE_MK48T35_MINUTES		0x7ffa
-#define TODC_TYPE_MK48T35_SECONDS		0x7ff9
-#define TODC_TYPE_MK48T35_CNTL_B		0x7ff9
-#define TODC_TYPE_MK48T35_CNTL_A		0x7ff8
-#define TODC_TYPE_MK48T35_WATCHDOG		0x0000
-#define TODC_TYPE_MK48T35_INTERRUPTS		0x0000
-#define TODC_TYPE_MK48T35_ALARM_DATE		0x0000
-#define TODC_TYPE_MK48T35_ALARM_HOUR		0x0000
-#define TODC_TYPE_MK48T35_ALARM_MINUTES		0x0000
-#define TODC_TYPE_MK48T35_ALARM_SECONDS		0x0000
-#define TODC_TYPE_MK48T35_CENTURY		0x0000
-#define TODC_TYPE_MK48T35_FLAGS			0x0000
-#define TODC_TYPE_MK48T35_NVRAM_ADDR_REG	0
-#define TODC_TYPE_MK48T35_NVRAM_DATA_REG	0
-
-#define TODC_TYPE_MK48T37_NVRAM_SIZE		0x7ff0
-#define TODC_TYPE_MK48T37_SW_FLAGS		0
-#define TODC_TYPE_MK48T37_YEAR			0x7fff
-#define TODC_TYPE_MK48T37_MONTH			0x7ffe
-#define TODC_TYPE_MK48T37_DOM			0x7ffd	/* Day of Month */
-#define TODC_TYPE_MK48T37_DOW			0x7ffc	/* Day of Week */
-#define TODC_TYPE_MK48T37_HOURS			0x7ffb
-#define TODC_TYPE_MK48T37_MINUTES		0x7ffa
-#define TODC_TYPE_MK48T37_SECONDS		0x7ff9
-#define TODC_TYPE_MK48T37_CNTL_B		0x7ff9
-#define TODC_TYPE_MK48T37_CNTL_A		0x7ff8
-#define TODC_TYPE_MK48T37_WATCHDOG		0x7ff7
-#define TODC_TYPE_MK48T37_INTERRUPTS		0x7ff6
-#define TODC_TYPE_MK48T37_ALARM_DATE		0x7ff5
-#define TODC_TYPE_MK48T37_ALARM_HOUR		0x7ff4
-#define TODC_TYPE_MK48T37_ALARM_MINUTES		0x7ff3
-#define TODC_TYPE_MK48T37_ALARM_SECONDS		0x7ff2
-#define TODC_TYPE_MK48T37_CENTURY		0x7ff1
-#define TODC_TYPE_MK48T37_FLAGS			0x7ff0
-#define TODC_TYPE_MK48T37_NVRAM_ADDR_REG	0
-#define TODC_TYPE_MK48T37_NVRAM_DATA_REG	0
-
-#define TODC_TYPE_MK48T59_NVRAM_SIZE		0x1ff0
-#define TODC_TYPE_MK48T59_SW_FLAGS		0
-#define TODC_TYPE_MK48T59_YEAR			0x1fff
-#define TODC_TYPE_MK48T59_MONTH			0x1ffe
-#define TODC_TYPE_MK48T59_DOM			0x1ffd	/* Day of Month */
-#define TODC_TYPE_MK48T59_DOW			0x1ffc	/* Day of Week */
-#define TODC_TYPE_MK48T59_HOURS			0x1ffb
-#define TODC_TYPE_MK48T59_MINUTES		0x1ffa
-#define TODC_TYPE_MK48T59_SECONDS		0x1ff9
-#define TODC_TYPE_MK48T59_CNTL_B		0x1ff9
-#define TODC_TYPE_MK48T59_CNTL_A		0x1ff8
-#define TODC_TYPE_MK48T59_WATCHDOG		0x1fff
-#define TODC_TYPE_MK48T59_INTERRUPTS		0x1fff
-#define TODC_TYPE_MK48T59_ALARM_DATE		0x1fff
-#define TODC_TYPE_MK48T59_ALARM_HOUR		0x1fff
-#define TODC_TYPE_MK48T59_ALARM_MINUTES		0x1fff
-#define TODC_TYPE_MK48T59_ALARM_SECONDS		0x1fff
-#define TODC_TYPE_MK48T59_CENTURY		0x1fff
-#define TODC_TYPE_MK48T59_FLAGS			0x1fff
-#define TODC_TYPE_MK48T59_NVRAM_ADDR_REG	0
-#define TODC_TYPE_MK48T59_NVRAM_DATA_REG	0
-
-#define TODC_TYPE_DS1501_NVRAM_SIZE	0x100
-#define TODC_TYPE_DS1501_SW_FLAGS	TODC_FLAG_2_LEVEL_NVRAM
-#define TODC_TYPE_DS1501_YEAR		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x06)
-#define TODC_TYPE_DS1501_MONTH		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x05)
-#define TODC_TYPE_DS1501_DOM		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x04)
-#define TODC_TYPE_DS1501_DOW		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x03)
-#define TODC_TYPE_DS1501_HOURS		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x02)
-#define TODC_TYPE_DS1501_MINUTES	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x01)
-#define TODC_TYPE_DS1501_SECONDS	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x00)
-#define TODC_TYPE_DS1501_CNTL_B		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x0f)
-#define TODC_TYPE_DS1501_CNTL_A		(TODC_TYPE_DS1501_NVRAM_SIZE + 0x0f)
-#define TODC_TYPE_DS1501_WATCHDOG	(TODC_TYPE_DS1501_NVRAM_SIZE + 0xff)
-#define TODC_TYPE_DS1501_INTERRUPTS	(TODC_TYPE_DS1501_NVRAM_SIZE + 0xff)
-#define TODC_TYPE_DS1501_ALARM_DATE	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x0b)
-#define TODC_TYPE_DS1501_ALARM_HOUR	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x0a)
-#define TODC_TYPE_DS1501_ALARM_MINUTES	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x09)
-#define TODC_TYPE_DS1501_ALARM_SECONDS	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x08)
-#define TODC_TYPE_DS1501_CENTURY	(TODC_TYPE_DS1501_NVRAM_SIZE + 0x07)
-#define TODC_TYPE_DS1501_FLAGS		(TODC_TYPE_DS1501_NVRAM_SIZE + 0xff)
-#define TODC_TYPE_DS1501_NVRAM_ADDR_REG	0x10
-#define TODC_TYPE_DS1501_NVRAM_DATA_REG	0x13
-
-#define TODC_TYPE_DS1553_NVRAM_SIZE		0x1ff0
-#define TODC_TYPE_DS1553_SW_FLAGS		0
-#define TODC_TYPE_DS1553_YEAR			0x1fff
-#define TODC_TYPE_DS1553_MONTH			0x1ffe
-#define TODC_TYPE_DS1553_DOM			0x1ffd	/* Day of Month */
-#define TODC_TYPE_DS1553_DOW			0x1ffc	/* Day of Week */
-#define TODC_TYPE_DS1553_HOURS			0x1ffb
-#define TODC_TYPE_DS1553_MINUTES		0x1ffa
-#define TODC_TYPE_DS1553_SECONDS		0x1ff9
-#define TODC_TYPE_DS1553_CNTL_B			0x1ff9
-#define TODC_TYPE_DS1553_CNTL_A			0x1ff8	/* control_a R/W regs */
-#define TODC_TYPE_DS1553_WATCHDOG		0x1ff7
-#define TODC_TYPE_DS1553_INTERRUPTS		0x1ff6
-#define TODC_TYPE_DS1553_ALARM_DATE		0x1ff5
-#define TODC_TYPE_DS1553_ALARM_HOUR		0x1ff4
-#define TODC_TYPE_DS1553_ALARM_MINUTES		0x1ff3
-#define TODC_TYPE_DS1553_ALARM_SECONDS		0x1ff2
-#define TODC_TYPE_DS1553_CENTURY		0x1ff8
-#define TODC_TYPE_DS1553_FLAGS			0x1ff0
-#define TODC_TYPE_DS1553_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1553_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS1557_NVRAM_SIZE		0x7fff0
-#define TODC_TYPE_DS1557_SW_FLAGS		0
-#define TODC_TYPE_DS1557_YEAR			0x7ffff
-#define TODC_TYPE_DS1557_MONTH			0x7fffe
-#define TODC_TYPE_DS1557_DOM			0x7fffd	/* Day of Month */
-#define TODC_TYPE_DS1557_DOW			0x7fffc	/* Day of Week */
-#define TODC_TYPE_DS1557_HOURS			0x7fffb
-#define TODC_TYPE_DS1557_MINUTES		0x7fffa
-#define TODC_TYPE_DS1557_SECONDS		0x7fff9
-#define TODC_TYPE_DS1557_CNTL_B			0x7fff9
-#define TODC_TYPE_DS1557_CNTL_A			0x7fff8	/* control_a R/W regs */
-#define TODC_TYPE_DS1557_WATCHDOG		0x7fff7
-#define TODC_TYPE_DS1557_INTERRUPTS		0x7fff6
-#define TODC_TYPE_DS1557_ALARM_DATE		0x7fff5
-#define TODC_TYPE_DS1557_ALARM_HOUR		0x7fff4
-#define TODC_TYPE_DS1557_ALARM_MINUTES		0x7fff3
-#define TODC_TYPE_DS1557_ALARM_SECONDS		0x7fff2
-#define TODC_TYPE_DS1557_CENTURY		0x7fff8
-#define TODC_TYPE_DS1557_FLAGS			0x7fff0
-#define TODC_TYPE_DS1557_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1557_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS1643_NVRAM_SIZE		0x1ff8
-#define TODC_TYPE_DS1643_SW_FLAGS		0
-#define TODC_TYPE_DS1643_YEAR			0x1fff
-#define TODC_TYPE_DS1643_MONTH			0x1ffe
-#define TODC_TYPE_DS1643_DOM			0x1ffd	/* Day of Month */
-#define TODC_TYPE_DS1643_DOW			0x1ffc	/* Day of Week */
-#define TODC_TYPE_DS1643_HOURS			0x1ffb
-#define TODC_TYPE_DS1643_MINUTES		0x1ffa
-#define TODC_TYPE_DS1643_SECONDS		0x1ff9
-#define TODC_TYPE_DS1643_CNTL_B			0x1ff9
-#define TODC_TYPE_DS1643_CNTL_A			0x1ff8	/* control_a R/W regs */
-#define TODC_TYPE_DS1643_WATCHDOG		0x1fff
-#define TODC_TYPE_DS1643_INTERRUPTS		0x1fff
-#define TODC_TYPE_DS1643_ALARM_DATE		0x1fff
-#define TODC_TYPE_DS1643_ALARM_HOUR		0x1fff
-#define TODC_TYPE_DS1643_ALARM_MINUTES		0x1fff
-#define TODC_TYPE_DS1643_ALARM_SECONDS		0x1fff
-#define TODC_TYPE_DS1643_CENTURY		0x1ff8
-#define TODC_TYPE_DS1643_FLAGS			0x1fff
-#define TODC_TYPE_DS1643_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1643_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS1693_NVRAM_SIZE		0 /* Not handled yet */
-#define TODC_TYPE_DS1693_SW_FLAGS		0
-#define TODC_TYPE_DS1693_YEAR			0x09
-#define TODC_TYPE_DS1693_MONTH			0x08
-#define TODC_TYPE_DS1693_DOM			0x07	/* Day of Month */
-#define TODC_TYPE_DS1693_DOW			0x06	/* Day of Week */
-#define TODC_TYPE_DS1693_HOURS			0x04
-#define TODC_TYPE_DS1693_MINUTES		0x02
-#define TODC_TYPE_DS1693_SECONDS		0x00
-#define TODC_TYPE_DS1693_CNTL_B			0x0b
-#define TODC_TYPE_DS1693_CNTL_A			0x0a
-#define TODC_TYPE_DS1693_WATCHDOG		0xff
-#define TODC_TYPE_DS1693_INTERRUPTS		0xff
-#define TODC_TYPE_DS1693_ALARM_DATE		0x49
-#define TODC_TYPE_DS1693_ALARM_HOUR		0x05
-#define TODC_TYPE_DS1693_ALARM_MINUTES		0x03
-#define TODC_TYPE_DS1693_ALARM_SECONDS		0x01
-#define TODC_TYPE_DS1693_CENTURY		0x48
-#define TODC_TYPE_DS1693_FLAGS			0xff
-#define TODC_TYPE_DS1693_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1693_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS1743_NVRAM_SIZE		0x1ff8
-#define TODC_TYPE_DS1743_SW_FLAGS		0
-#define TODC_TYPE_DS1743_YEAR			0x1fff
-#define TODC_TYPE_DS1743_MONTH			0x1ffe
-#define TODC_TYPE_DS1743_DOM			0x1ffd	/* Day of Month */
-#define TODC_TYPE_DS1743_DOW			0x1ffc	/* Day of Week */
-#define TODC_TYPE_DS1743_HOURS			0x1ffb
-#define TODC_TYPE_DS1743_MINUTES		0x1ffa
-#define TODC_TYPE_DS1743_SECONDS		0x1ff9
-#define TODC_TYPE_DS1743_CNTL_B			0x1ff9
-#define TODC_TYPE_DS1743_CNTL_A			0x1ff8	/* control_a R/W regs */
-#define TODC_TYPE_DS1743_WATCHDOG		0x1fff
-#define TODC_TYPE_DS1743_INTERRUPTS		0x1fff
-#define TODC_TYPE_DS1743_ALARM_DATE		0x1fff
-#define TODC_TYPE_DS1743_ALARM_HOUR		0x1fff
-#define TODC_TYPE_DS1743_ALARM_MINUTES		0x1fff
-#define TODC_TYPE_DS1743_ALARM_SECONDS		0x1fff
-#define TODC_TYPE_DS1743_CENTURY		0x1ff8
-#define TODC_TYPE_DS1743_FLAGS			0x1fff
-#define TODC_TYPE_DS1743_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1743_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS1746_NVRAM_SIZE		0x1fff8
-#define TODC_TYPE_DS1746_SW_FLAGS		0
-#define TODC_TYPE_DS1746_YEAR			0x1ffff
-#define TODC_TYPE_DS1746_MONTH			0x1fffe
-#define TODC_TYPE_DS1746_DOM			0x1fffd	/* Day of Month */
-#define TODC_TYPE_DS1746_DOW			0x1fffc	/* Day of Week */
-#define TODC_TYPE_DS1746_HOURS			0x1fffb
-#define TODC_TYPE_DS1746_MINUTES		0x1fffa
-#define TODC_TYPE_DS1746_SECONDS		0x1fff9
-#define TODC_TYPE_DS1746_CNTL_B			0x1fff9
-#define TODC_TYPE_DS1746_CNTL_A			0x1fff8	/* control_a R/W regs */
-#define TODC_TYPE_DS1746_WATCHDOG		0x00000
-#define TODC_TYPE_DS1746_INTERRUPTS		0x00000
-#define TODC_TYPE_DS1746_ALARM_DATE		0x00000
-#define TODC_TYPE_DS1746_ALARM_HOUR		0x00000
-#define TODC_TYPE_DS1746_ALARM_MINUTES		0x00000
-#define TODC_TYPE_DS1746_ALARM_SECONDS		0x00000
-#define TODC_TYPE_DS1746_CENTURY		0x00000
-#define TODC_TYPE_DS1746_FLAGS			0x00000
-#define TODC_TYPE_DS1746_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1746_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS1747_NVRAM_SIZE		0x7fff8
-#define TODC_TYPE_DS1747_SW_FLAGS		0
-#define TODC_TYPE_DS1747_YEAR			0x7ffff
-#define TODC_TYPE_DS1747_MONTH			0x7fffe
-#define TODC_TYPE_DS1747_DOM			0x7fffd	/* Day of Month */
-#define TODC_TYPE_DS1747_DOW			0x7fffc	/* Day of Week */
-#define TODC_TYPE_DS1747_HOURS			0x7fffb
-#define TODC_TYPE_DS1747_MINUTES		0x7fffa
-#define TODC_TYPE_DS1747_SECONDS		0x7fff9
-#define TODC_TYPE_DS1747_CNTL_B			0x7fff9
-#define TODC_TYPE_DS1747_CNTL_A			0x7fff8	/* control_a R/W regs */
-#define TODC_TYPE_DS1747_WATCHDOG		0x00000
-#define TODC_TYPE_DS1747_INTERRUPTS		0x00000
-#define TODC_TYPE_DS1747_ALARM_DATE		0x00000
-#define TODC_TYPE_DS1747_ALARM_HOUR		0x00000
-#define TODC_TYPE_DS1747_ALARM_MINUTES		0x00000
-#define TODC_TYPE_DS1747_ALARM_SECONDS		0x00000
-#define TODC_TYPE_DS1747_CENTURY		0x00000
-#define TODC_TYPE_DS1747_FLAGS			0x00000
-#define TODC_TYPE_DS1747_NVRAM_ADDR_REG		0
-#define TODC_TYPE_DS1747_NVRAM_DATA_REG		0
-
-#define TODC_TYPE_DS17285_NVRAM_SIZE		(0x1000-0x80) /* 4Kx8 NVRAM (minus RTC regs) */
-#define TODC_TYPE_DS17285_SW_FLAGS		TODC_FLAG_2_LEVEL_NVRAM
-#define TODC_TYPE_DS17285_SECONDS		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x00)
-#define TODC_TYPE_DS17285_ALARM_SECONDS		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x01)
-#define TODC_TYPE_DS17285_MINUTES		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x02)
-#define TODC_TYPE_DS17285_ALARM_MINUTES		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x03)
-#define TODC_TYPE_DS17285_HOURS			(TODC_TYPE_DS17285_NVRAM_SIZE + 0x04)
-#define TODC_TYPE_DS17285_ALARM_HOUR		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x05)
-#define TODC_TYPE_DS17285_DOW			(TODC_TYPE_DS17285_NVRAM_SIZE + 0x06)
-#define TODC_TYPE_DS17285_DOM			(TODC_TYPE_DS17285_NVRAM_SIZE + 0x07)
-#define TODC_TYPE_DS17285_MONTH			(TODC_TYPE_DS17285_NVRAM_SIZE + 0x08)
-#define TODC_TYPE_DS17285_YEAR			(TODC_TYPE_DS17285_NVRAM_SIZE + 0x09)
-#define TODC_TYPE_DS17285_CNTL_A		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x0A)
-#define TODC_TYPE_DS17285_CNTL_B		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x0B)
-#define TODC_TYPE_DS17285_CNTL_C		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x0C)
-#define TODC_TYPE_DS17285_CNTL_D		(TODC_TYPE_DS17285_NVRAM_SIZE + 0x0D)
-#define TODC_TYPE_DS17285_WATCHDOG		0
-#define TODC_TYPE_DS17285_INTERRUPTS		0
-#define TODC_TYPE_DS17285_ALARM_DATE		0
-#define TODC_TYPE_DS17285_CENTURY		0
-#define TODC_TYPE_DS17285_FLAGS			0
-#define TODC_TYPE_DS17285_NVRAM_ADDR_REG	0x50
-#define TODC_TYPE_DS17285_NVRAM_DATA_REG	0x53
-
-#define TODC_TYPE_MC146818_NVRAM_SIZE		0	/* XXXX */
-#define TODC_TYPE_MC146818_SW_FLAGS		0
-#define TODC_TYPE_MC146818_YEAR			0x09
-#define TODC_TYPE_MC146818_MONTH		0x08
-#define TODC_TYPE_MC146818_DOM			0x07	/* Day of Month */
-#define TODC_TYPE_MC146818_DOW			0x06	/* Day of Week */
-#define TODC_TYPE_MC146818_HOURS		0x04
-#define TODC_TYPE_MC146818_MINUTES		0x02
-#define TODC_TYPE_MC146818_SECONDS		0x00
-#define TODC_TYPE_MC146818_CNTL_B		0x0a
-#define TODC_TYPE_MC146818_CNTL_A		0x0b	/* control_a R/W regs */
-#define TODC_TYPE_MC146818_WATCHDOG		0
-#define TODC_TYPE_MC146818_INTERRUPTS		0x0c
-#define TODC_TYPE_MC146818_ALARM_DATE		0xff
-#define TODC_TYPE_MC146818_ALARM_HOUR		0x05
-#define TODC_TYPE_MC146818_ALARM_MINUTES	0x03
-#define TODC_TYPE_MC146818_ALARM_SECONDS	0x01
-#define TODC_TYPE_MC146818_CENTURY		0xff
-#define TODC_TYPE_MC146818_FLAGS		0xff
-#define TODC_TYPE_MC146818_NVRAM_ADDR_REG	0
-#define TODC_TYPE_MC146818_NVRAM_DATA_REG	0
-
-#define TODC_TYPE_PC97307_NVRAM_SIZE		0	/* No NVRAM? */
-#define TODC_TYPE_PC97307_SW_FLAGS		0
-#define TODC_TYPE_PC97307_YEAR			0x09
-#define TODC_TYPE_PC97307_MONTH			0x08
-#define TODC_TYPE_PC97307_DOM			0x07	/* Day of Month */
-#define TODC_TYPE_PC97307_DOW			0x06	/* Day of Week */
-#define TODC_TYPE_PC97307_HOURS			0x04
-#define TODC_TYPE_PC97307_MINUTES		0x02
-#define TODC_TYPE_PC97307_SECONDS		0x00
-#define TODC_TYPE_PC97307_CNTL_B		0x0a
-#define TODC_TYPE_PC97307_CNTL_A		0x0b	/* control_a R/W regs */
-#define TODC_TYPE_PC97307_WATCHDOG		0x0c
-#define TODC_TYPE_PC97307_INTERRUPTS		0x0d
-#define TODC_TYPE_PC97307_ALARM_DATE		0xff
-#define TODC_TYPE_PC97307_ALARM_HOUR		0x05
-#define TODC_TYPE_PC97307_ALARM_MINUTES		0x03
-#define TODC_TYPE_PC97307_ALARM_SECONDS		0x01
-#define TODC_TYPE_PC97307_CENTURY		0xff
-#define TODC_TYPE_PC97307_FLAGS			0xff
-#define TODC_TYPE_PC97307_NVRAM_ADDR_REG	0
-#define TODC_TYPE_PC97307_NVRAM_DATA_REG	0
-
-/*
- * Define macros to allocate and init the todc_info_t table that will
- * be used by the todc_time.c routines.
- */
-#define TODC_ALLOC()							\
-	static todc_info_t todc_info_alloc;				\
-	todc_info_t *todc_info = &todc_info_alloc;
-
-#define TODC_INIT(clock_type, as0, as1, data, bits) {			\
-	todc_info->rtc_type = clock_type;				\
-									\
-	todc_info->nvram_as0 = (unsigned int)(as0);			\
-	todc_info->nvram_as1 = (unsigned int)(as1);			\
-	todc_info->nvram_data = (unsigned int)(data);			\
-									\
-	todc_info->as0_bits = (bits);					\
-									\
-	todc_info->nvram_size = clock_type ##_NVRAM_SIZE;		\
-	todc_info->sw_flags = clock_type ##_SW_FLAGS;			\
-									\
-	todc_info->year = clock_type ##_YEAR;				\
-	todc_info->month = clock_type ##_MONTH;				\
-	todc_info->day_of_month = clock_type ##_DOM;			\
-	todc_info->day_of_week = clock_type ##_DOW;			\
-	todc_info->hours = clock_type ##_HOURS;				\
-	todc_info->minutes = clock_type ##_MINUTES;			\
-	todc_info->seconds = clock_type ##_SECONDS;			\
-	todc_info->control_b = clock_type ##_CNTL_B;			\
-	todc_info->control_a = clock_type ##_CNTL_A;			\
-	todc_info->watchdog = clock_type ##_WATCHDOG;			\
-	todc_info->interrupts = clock_type ##_INTERRUPTS;		\
-	todc_info->alarm_date = clock_type ##_ALARM_DATE;		\
-	todc_info->alarm_hour = clock_type ##_ALARM_HOUR;		\
-	todc_info->alarm_minutes = clock_type ##_ALARM_MINUTES;		\
-	todc_info->alarm_seconds = clock_type ##_ALARM_SECONDS;		\
-	todc_info->century = clock_type ##_CENTURY;			\
-	todc_info->flags = clock_type ##_FLAGS;				\
-									\
-	todc_info->nvram_addr_reg = clock_type ##_NVRAM_ADDR_REG;	\
-	todc_info->nvram_data_reg = clock_type ##_NVRAM_DATA_REG;	\
-}
-
-extern todc_info_t *todc_info;
-
-unsigned char todc_direct_read_val(int addr);
-void todc_direct_write_val(int addr, unsigned char val);
-unsigned char todc_m48txx_read_val(int addr);
-void todc_m48txx_write_val(int addr, unsigned char val);
-unsigned char todc_mc146818_read_val(int addr);
-void todc_mc146818_write_val(int addr, unsigned char val);
-
-long todc_time_init(void);
-void todc_get_rtc_time(struct rtc_time *);
-int todc_set_rtc_time(struct rtc_time *);
-void todc_calibrate_decr(void);
-
-#endif				/* __PPC_KERNEL_TODC_H */
diff --git a/include/asm-powerpc/topology.h b/include/asm-powerpc/topology.h
index 9fe7894ee035..50c014007de7 100644
--- a/include/asm-powerpc/topology.h
+++ b/include/asm-powerpc/topology.h
@@ -32,7 +32,14 @@ static inline int node_to_first_cpu(int node)
 int of_node_to_nid(struct device_node *device);
 
 struct pci_bus;
+#ifdef CONFIG_PCI
 extern int pcibus_to_node(struct pci_bus *bus);
+#else
+static inline int pcibus_to_node(struct pci_bus *bus)
+{
+	return -1;
+}
+#endif
 
 #define pcibus_to_cpumask(bus)	(pcibus_to_node(bus) == -1 ? \
 					CPU_MASK_ALL : \
diff --git a/include/asm-powerpc/tsi108.h b/include/asm-powerpc/tsi108.h
index 2c702d35a7cf..4e95d153be84 100644
--- a/include/asm-powerpc/tsi108.h
+++ b/include/asm-powerpc/tsi108.h
@@ -98,12 +98,12 @@ typedef struct {
 extern u32 get_vir_csrbase(void);
 extern u32 tsi108_csr_vir_base;
 
-extern inline u32 tsi108_read_reg(u32 reg_offset)
+static inline u32 tsi108_read_reg(u32 reg_offset)
 {
 	return in_be32((volatile u32 *)(tsi108_csr_vir_base + reg_offset));
 }
 
-extern inline void tsi108_write_reg(u32 reg_offset, u32 val)
+static inline void tsi108_write_reg(u32 reg_offset, u32 val)
 {
 	out_be32((volatile u32 *)(tsi108_csr_vir_base + reg_offset), val);
 }
diff --git a/include/asm-powerpc/types.h b/include/asm-powerpc/types.h
index d6fb56b80453..3b363757a2bb 100644
--- a/include/asm-powerpc/types.h
+++ b/include/asm-powerpc/types.h
@@ -97,16 +97,6 @@ typedef struct {
 	unsigned long env;
 } func_descr_t;
 
-#ifdef CONFIG_LBD
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-#endif
-
-#ifdef CONFIG_LSF
-typedef u64 blkcnt_t;
-#define HAVE_BLKCNT_T
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-powerpc/uaccess.h b/include/asm-powerpc/uaccess.h
index d83fc29c2bbf..adbf16b8cfbb 100644
--- a/include/asm-powerpc/uaccess.h
+++ b/include/asm-powerpc/uaccess.h
@@ -304,7 +304,7 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 
 #ifndef __powerpc64__
 
-extern inline unsigned long copy_from_user(void *to,
+static inline unsigned long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
 	unsigned long over;
@@ -319,7 +319,7 @@ extern inline unsigned long copy_from_user(void *to,
 	return n;
 }
 
-extern inline unsigned long copy_to_user(void __user *to,
+static inline unsigned long copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
 	unsigned long over;
diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h
index 0e4ea37f6466..04b6c17cc59b 100644
--- a/include/asm-powerpc/unistd.h
+++ b/include/asm-powerpc/unistd.h
@@ -446,7 +446,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg6
 #include <linux/types.h>
 #include <linux/compiler.h>
 #include <linux/linkage.h>
-#include <asm/syscalls.h>
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
@@ -481,16 +480,9 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5, type6 arg6
 
 /*
  * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
  */
-#ifdef CONFIG_PPC32
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#else
-#define cond_syscall(x) asm(".weak\t." #x "\n\t.set\t." #x ",.sys_ni_syscall")
-#endif
-
+#define cond_syscall(x) \
+	asmlinkage long x (void) __attribute__((weak,alias("sys_ni_syscall")))
 
 #endif		/* __ASSEMBLY__ */
 #endif		/* __KERNEL__ */
diff --git a/include/asm-powerpc/vio.h b/include/asm-powerpc/vio.h
index 4b51d42e1419..0117b544ecbc 100644
--- a/include/asm-powerpc/vio.h
+++ b/include/asm-powerpc/vio.h
@@ -45,7 +45,6 @@ struct iommu_table;
  * The vio_dev structure is used to describe virtual I/O devices.
  */
 struct vio_dev {
-	struct iommu_table *iommu_table;     /* vio_map_* uses this */
 	const char *name;
 	const char *type;
 	uint32_t unit_address;
diff --git a/include/asm-powerpc/xmon.h b/include/asm-powerpc/xmon.h
index f1d337ed68d5..88320a05f0a8 100644
--- a/include/asm-powerpc/xmon.h
+++ b/include/asm-powerpc/xmon.h
@@ -14,8 +14,10 @@
 
 #ifdef CONFIG_XMON
 extern void xmon_setup(void);
+extern void xmon_register_spus(struct list_head *list);
 #else
 static inline void xmon_setup(void) { };
+static inline void xmon_register_spus(struct list_head *list) { };
 #endif
 
 #endif /* __KERNEL __ */
diff --git a/include/asm-ppc/io.h b/include/asm-ppc/io.h
index a4c411b753ef..ccf1a9bb2e43 100644
--- a/include/asm-ppc/io.h
+++ b/include/asm-ppc/io.h
@@ -26,17 +26,11 @@
 
 #if defined(CONFIG_4xx)
 #include <asm/ibm4xx.h>
-#elif defined(CONFIG_PPC_MPC52xx)
-#include <asm/mpc52xx.h>
 #elif defined(CONFIG_8xx)
 #include <asm/mpc8xx.h>
 #elif defined(CONFIG_8260)
 #include <asm/mpc8260.h>
-#elif defined(CONFIG_83xx)
-#include <asm/mpc83xx.h>
-#elif defined(CONFIG_85xx)
-#include <asm/mpc85xx.h>
-#elif defined(CONFIG_APUS)
+#elif defined(CONFIG_APUS) || !defined(CONFIG_PCI)
 #define _IO_BASE	0
 #define _ISA_MEM_BASE	0
 #define PCI_DRAM_OFFSET 0
@@ -237,6 +231,14 @@ static inline void __raw_writel(__u32 b, volatile void __iomem *addr)
 #define insl(port, buf, nl)	_insl_ns((port)+___IO_BASE, (buf), (nl))
 #define outsl(port, buf, nl)	_outsl_ns((port)+___IO_BASE, (buf), (nl))
 
+#define readsb(a, b, n)		_insb((a), (b), (n))
+#define readsw(a, b, n)		_insw_ns((a), (b), (n))
+#define readsl(a, b, n)		_insl_ns((a), (b), (n))
+#define writesb(a, b, n)	_outsb((a),(b),(n))
+#define writesw(a, b, n)	_outsw_ns((a),(b),(n))
+#define writesl(a, b, n)	_outsl_ns((a),(b),(n))
+
+
 /*
  * On powermacs and 8xx we will get a machine check exception 
  * if we try to read data from a non-existent I/O port. Because
@@ -327,12 +329,12 @@ __do_out_asm(outl, "stwbrx")
 #define inl_p(port)		inl((port))
 #define outl_p(val, port)	outl((val), (port))
 
-extern void _insb(volatile u8 __iomem *port, void *buf, long count);
-extern void _outsb(volatile u8 __iomem *port, const void *buf, long count);
-extern void _insw_ns(volatile u16 __iomem *port, void *buf, long count);
-extern void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count);
-extern void _insl_ns(volatile u32 __iomem *port, void *buf, long count);
-extern void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count);
+extern void _insb(const volatile u8 __iomem *addr, void *buf, long count);
+extern void _outsb(volatile u8 __iomem *addr,const void *buf,long count);
+extern void _insw_ns(const volatile u16 __iomem *addr, void *buf, long count);
+extern void _outsw_ns(volatile u16 __iomem *addr, const void *buf, long count);
+extern void _insl_ns(const volatile u32 __iomem *addr, void *buf, long count);
+extern void _outsl_ns(volatile u32 __iomem *addr, const void *buf, long count);
 
 
 #define IO_SPACE_LIMIT ~0
diff --git a/include/asm-ppc/m48t35.h b/include/asm-ppc/m48t35.h
index f3c5e5dfa986..a5277ea4b194 100644
--- a/include/asm-ppc/m48t35.h
+++ b/include/asm-ppc/m48t35.h
@@ -39,7 +39,7 @@
 #define M48T35_RTC_WATCHDOG_RB         0x03
 #define M48T35_RTC_WATCHDOG_BMB        0x7c
 #define M48T35_RTC_WATCHDOG_WDS        0x80
-#define M48T35_RTC_WATCHDOG_ALL        (M48T35_RTC_WATCHDOG_RB|M48T35_RTC_WATCHDOG_BMB|M48T35_RTC_W
+#define M48T35_RTC_WATCHDOG_ALL        (M48T35_RTC_WATCHDOG_RB|M48T35_RTC_WATCHDOG_BMB|M48T35_RTC_W)
 
 #define M48T35_RTC_CONTROL_WRITE       0x80
 #define M48T35_RTC_CONTROL_READ        0x40
diff --git a/include/asm-ppc/mpc52xx.h b/include/asm-ppc/mpc52xx.h
index 64c8874618dc..d9d21aa68ba3 100644
--- a/include/asm-ppc/mpc52xx.h
+++ b/include/asm-ppc/mpc52xx.h
@@ -29,17 +29,6 @@ struct pt_regs;
 #endif /* __ASSEMBLY__ */
 
 
-#ifdef CONFIG_PCI
-#define _IO_BASE	isa_io_base
-#define _ISA_MEM_BASE	isa_mem_base
-#define PCI_DRAM_OFFSET	pci_dram_offset
-#else
-#define _IO_BASE	0
-#define _ISA_MEM_BASE	0
-#define PCI_DRAM_OFFSET	0
-#endif
-
-
 /* ======================================================================== */
 /* PPC Sys devices definition                                               */
 /* ======================================================================== */
diff --git a/include/asm-ppc/mpc83xx.h b/include/asm-ppc/mpc83xx.h
index 02ed2c325714..c3061972309b 100644
--- a/include/asm-ppc/mpc83xx.h
+++ b/include/asm-ppc/mpc83xx.h
@@ -25,14 +25,6 @@
 #include <platforms/83xx/mpc834x_sys.h>
 #endif
 
-#define _IO_BASE        isa_io_base
-#define _ISA_MEM_BASE   isa_mem_base
-#ifdef CONFIG_PCI
-#define PCI_DRAM_OFFSET pci_dram_offset
-#else
-#define PCI_DRAM_OFFSET 0
-#endif
-
 /*
  * The "residual" board information structure the boot loader passes
  * into the kernel.
diff --git a/include/asm-ppc/mpc85xx.h b/include/asm-ppc/mpc85xx.h
index 9b4851199c76..d7e4a79d77fb 100644
--- a/include/asm-ppc/mpc85xx.h
+++ b/include/asm-ppc/mpc85xx.h
@@ -44,14 +44,6 @@
 #include <platforms/85xx/tqm85xx.h>
 #endif
 
-#define _IO_BASE        isa_io_base
-#define _ISA_MEM_BASE   isa_mem_base
-#ifdef CONFIG_PCI
-#define PCI_DRAM_OFFSET pci_dram_offset
-#else
-#define PCI_DRAM_OFFSET 0
-#endif
-
 /*
  * The "residual" board information structure the boot loader passes
  * into the kernel.
diff --git a/include/asm-ppc/pci-bridge.h b/include/asm-ppc/pci-bridge.h
index 9d5230689b31..6c955d0c1ef0 100644
--- a/include/asm-ppc/pci-bridge.h
+++ b/include/asm-ppc/pci-bridge.h
@@ -43,6 +43,7 @@ struct pci_controller {
 	struct pci_controller *next;
         struct pci_bus *bus;
 	void *arch_data;
+	struct device *parent;
 
 	int first_busno;
 	int last_busno;
diff --git a/include/asm-s390/cio.h b/include/asm-s390/cio.h
index 81287d86329d..d92785030980 100644
--- a/include/asm-s390/cio.h
+++ b/include/asm-s390/cio.h
@@ -278,17 +278,16 @@ struct ccw_dev_id {
 static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1,
 				      struct ccw_dev_id *dev_id2)
 {
-	return !memcmp(dev_id1, dev_id2, sizeof(struct ccw_dev_id));
+	if ((dev_id1->ssid == dev_id2->ssid) &&
+	    (dev_id1->devno == dev_id2->devno))
+		return 1;
+	return 0;
 }
 
 extern int diag210(struct diag210 *addr);
 
 extern void wait_cons_dev(void);
 
-extern void clear_all_subchannels(void);
-
-extern void cio_reset_channel_paths(void);
-
 extern void css_schedule_reprobe(void);
 
 extern void reipl_ccw_dev(struct ccw_dev_id *id);
diff --git a/include/asm-s390/cpcmd.h b/include/asm-s390/cpcmd.h
index 1fcf65be7a23..48a9eab16429 100644
--- a/include/asm-s390/cpcmd.h
+++ b/include/asm-s390/cpcmd.h
@@ -7,8 +7,8 @@
  *               Christian Borntraeger (cborntra@de.ibm.com),
  */
 
-#ifndef __CPCMD__
-#define __CPCMD__
+#ifndef _ASM_S390_CPCMD_H
+#define _ASM_S390_CPCMD_H
 
 /*
  * the lowlevel function for cpcmd
@@ -16,9 +16,6 @@
  */
 extern int __cpcmd(const char *cmd, char *response, int rlen, int *response_code);
 
-#ifndef __s390x__
-#define cpcmd __cpcmd
-#else
 /*
  * cpcmd is the in-kernel interface for issuing CP commands
  *
@@ -33,6 +30,5 @@ extern int __cpcmd(const char *cmd, char *response, int rlen, int *response_code
  * NOTE: If the response buffer is not below 2 GB, cpcmd can sleep
  */
 extern int cpcmd(const char *cmd, char *response, int rlen, int *response_code);
-#endif /*__s390x__*/
 
-#endif
+#endif /* _ASM_S390_CPCMD_H */
diff --git a/include/asm-s390/kexec.h b/include/asm-s390/kexec.h
index ce28ddda0f50..9c35c8ad1afd 100644
--- a/include/asm-s390/kexec.h
+++ b/include/asm-s390/kexec.h
@@ -26,7 +26,7 @@
 
 /* Maximum address we can use for the control pages */
 /* Not more than 2GB */
-#define KEXEC_CONTROL_MEMORY_LIMIT (1<<31)
+#define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31)
 
 /* Allocate one page for the pdp and the second for the code */
 #define KEXEC_CONTROL_CODE_SIZE 4096
diff --git a/include/asm-s390/lowcore.h b/include/asm-s390/lowcore.h
index 06583ed0bde7..74f7389bd3ee 100644
--- a/include/asm-s390/lowcore.h
+++ b/include/asm-s390/lowcore.h
@@ -362,6 +362,14 @@ static inline void set_prefix(__u32 address)
 	asm volatile("spx %0" : : "m" (address) : "memory");
 }
 
+static inline __u32 store_prefix(void)
+{
+	__u32 address;
+
+	asm volatile("stpx %0" : "=m" (address));
+	return address;
+}
+
 #define __PANIC_MAGIC           0xDEADC0DE
 
 #endif
diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h
index 36bb6dacf008..2d968a69ed1f 100644
--- a/include/asm-s390/pgtable.h
+++ b/include/asm-s390/pgtable.h
@@ -110,13 +110,22 @@ extern char empty_zero_page[PAGE_SIZE];
 #define VMALLOC_OFFSET  (8*1024*1024)
 #define VMALLOC_START   (((unsigned long) high_memory + VMALLOC_OFFSET) \
 			 & ~(VMALLOC_OFFSET-1))
+
+/*
+ * We need some free virtual space to be able to do vmalloc.
+ * VMALLOC_MIN_SIZE defines the minimum size of the vmalloc
+ * area. On a machine with 2GB memory we make sure that we
+ * have at least 128MB free space for vmalloc. On a machine
+ * with 4TB we make sure we have at least 1GB.
+ */
 #ifndef __s390x__
-# define VMALLOC_END     (0x7fffffffL)
+#define VMALLOC_MIN_SIZE	0x8000000UL
+#define VMALLOC_END		0x80000000UL
 #else /* __s390x__ */
-# define VMALLOC_END     (0x40000000000L)
+#define VMALLOC_MIN_SIZE	0x40000000UL
+#define VMALLOC_END		0x40000000000UL
 #endif /* __s390x__ */
 
-
 /*
  * A 31 bit pagetable entry of S390 has following format:
  *  |   PFRA          |    |  OS  |
diff --git a/include/asm-s390/reset.h b/include/asm-s390/reset.h
new file mode 100644
index 000000000000..9b439cf67800
--- /dev/null
+++ b/include/asm-s390/reset.h
@@ -0,0 +1,23 @@
+/*
+ *  include/asm-s390/reset.h
+ *
+ *    Copyright IBM Corp. 2006
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#ifndef _ASM_S390_RESET_H
+#define _ASM_S390_RESET_H
+
+#include <linux/list.h>
+
+struct reset_call {
+	struct list_head list;
+	void (*fn)(void);
+};
+
+extern void register_reset_call(struct reset_call *reset);
+extern void unregister_reset_call(struct reset_call *reset);
+extern void s390_reset_system(void);
+extern void (*s390_reset_mcck_handler)(void);
+
+#endif /* _ASM_S390_RESET_H */
diff --git a/include/asm-s390/setup.h b/include/asm-s390/setup.h
index 5d72eda8a11b..7664bacdd832 100644
--- a/include/asm-s390/setup.h
+++ b/include/asm-s390/setup.h
@@ -2,7 +2,7 @@
  *  include/asm-s390/setup.h
  *
  *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *    Copyright IBM Corp. 1999,2006
  */
 
 #ifndef _ASM_S390_SETUP_H
@@ -30,6 +30,17 @@
 #endif /* __s390x__ */
 #define COMMAND_LINE      ((char *)            (0x10480))
 
+#define CHUNK_READ_WRITE 0
+#define CHUNK_READ_ONLY  1
+
+struct mem_chunk {
+	unsigned long addr;
+	unsigned long size;
+	unsigned long type;
+};
+
+extern struct mem_chunk memory_chunk[];
+
 /*
  * Machine features detected in head.S
  */
@@ -53,7 +64,6 @@ extern unsigned long machine_flags;
 #define MACHINE_HAS_MVCOS	(machine_flags & 512)
 #endif /* __s390x__ */
 
-
 #define MACHINE_HAS_SCLP	(!MACHINE_IS_P390)
 
 /*
@@ -71,7 +81,6 @@ extern unsigned int console_irq;
 #define SET_CONSOLE_3215	do { console_mode = 2; } while (0)
 #define SET_CONSOLE_3270	do { console_mode = 3; } while (0)
 
-
 struct ipl_list_hdr {
 	u32 len;
 	u8  reserved1[3];
diff --git a/include/asm-s390/smp.h b/include/asm-s390/smp.h
index c3cf030ada4d..7097c96ed026 100644
--- a/include/asm-s390/smp.h
+++ b/include/asm-s390/smp.h
@@ -18,6 +18,7 @@
 
 #include <asm/lowcore.h>
 #include <asm/sigp.h>
+#include <asm/ptrace.h>
 
 /*
   s390 specific smp.c headers
@@ -101,6 +102,13 @@ smp_call_function_on(void (*func) (void *info), void *info,
 	func(info);
 	return 0;
 }
+
+static inline void smp_send_stop(void)
+{
+	/* Disable all interrupts/machine checks */
+	__load_psw_mask(PSW_KERNEL_BITS & ~PSW_MASK_MCHECK);
+}
+
 #define smp_cpu_not_running(cpu)	1
 #define smp_get_cpu(cpu) ({ 0; })
 #define smp_put_cpu(cpu) ({ 0; })
diff --git a/include/asm-s390/system.h b/include/asm-s390/system.h
index ccbafe4bf2cb..bd0b05ae87d2 100644
--- a/include/asm-s390/system.h
+++ b/include/asm-s390/system.h
@@ -115,6 +115,16 @@ extern void account_system_vtime(struct task_struct *);
 #define account_vtime(x) do { /* empty */ } while (0)
 #endif
 
+#ifdef CONFIG_PFAULT
+extern void pfault_irq_init(void);
+extern int pfault_init(void);
+extern void pfault_fini(void);
+#else /* CONFIG_PFAULT */
+#define pfault_irq_init()	do { } while (0)
+#define pfault_init()		({-1;})
+#define pfault_fini()		do { } while (0)
+#endif /* CONFIG_PFAULT */
+
 #define finish_arch_switch(prev) do {					     \
 	set_fs(current->thread.mm_segment);				     \
 	account_vtime(prev);						     \
diff --git a/include/asm-s390/termios.h b/include/asm-s390/termios.h
index d1e29cca54c9..62b23caf370e 100644
--- a/include/asm-s390/termios.h
+++ b/include/asm-s390/termios.h
@@ -75,39 +75,7 @@ struct termio {
 */
 #define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
 
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
-	unsigned short __tmp; \
-	get_user(__tmp,&(termio)->x); \
-	(termios)->x = (0xffff0000 & ((termios)->x)) | __tmp; \
-}
-
-#define user_termio_to_kernel_termios(termios, termio) \
-({ \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
-	copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
-})
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-#define kernel_termios_to_user_termio(termio, termios) \
-({ \
-	put_user((termios)->c_iflag, &(termio)->c_iflag); \
-	put_user((termios)->c_oflag, &(termio)->c_oflag); \
-	put_user((termios)->c_cflag, &(termio)->c_cflag); \
-	put_user((termios)->c_lflag, &(termio)->c_lflag); \
-	put_user((termios)->c_line,  &(termio)->c_line); \
-	copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
-})
-
-#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios))
-#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios))
+#include <asm-generic/termios.h>
 
 #endif	/* __KERNEL__ */
 
diff --git a/include/asm-s390/types.h b/include/asm-s390/types.h
index ae2951cc83ac..fc5d7cf19324 100644
--- a/include/asm-s390/types.h
+++ b/include/asm-s390/types.h
@@ -87,16 +87,6 @@ typedef union {
 	} subreg;
 } register_pair;
 
-#ifdef CONFIG_LBD
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-#endif
-
-#ifdef CONFIG_LSF
-typedef u64 blkcnt_t;
-#define HAVE_BLKCNT_T
-#endif
-
 #endif /* ! __s390x__   */
 #endif /* __ASSEMBLY__  */
 #endif /* __KERNEL__    */
diff --git a/include/asm-s390/uaccess.h b/include/asm-s390/uaccess.h
index 72ae4efddb49..73ac4e82217b 100644
--- a/include/asm-s390/uaccess.h
+++ b/include/asm-s390/uaccess.h
@@ -201,7 +201,7 @@ extern int __get_user_bad(void) __attribute__((noreturn));
  * Returns number of bytes that could not be copied.
  * On success, this will be zero.
  */
-static inline unsigned long
+static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	if (__builtin_constant_p(n) && (n <= 256))
@@ -226,7 +226,7 @@ __copy_to_user(void __user *to, const void *from, unsigned long n)
  * Returns number of bytes that could not be copied.
  * On success, this will be zero.
  */
-static inline unsigned long
+static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_sleep();
@@ -252,7 +252,7 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
  * If some data could not be copied, this function will pad the copied
  * data to the requested size using zero bytes.
  */
-static inline unsigned long
+static inline unsigned long __must_check
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	if (__builtin_constant_p(n) && (n <= 256))
@@ -277,7 +277,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
  * If some data could not be copied, this function will pad the copied
  * data to the requested size using zero bytes.
  */
-static inline unsigned long
+static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	might_sleep();
@@ -288,13 +288,13 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 	return n;
 }
 
-static inline unsigned long
+static inline unsigned long __must_check
 __copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
 	return uaccess.copy_in_user(n, to, from);
 }
 
-static inline unsigned long
+static inline unsigned long __must_check
 copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
 	might_sleep();
@@ -306,7 +306,7 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n)
 /*
  * Copy a null terminated string from userspace.
  */
-static inline long
+static inline long __must_check
 strncpy_from_user(char *dst, const char __user *src, long count)
 {
         long res = -EFAULT;
@@ -343,13 +343,13 @@ strnlen_user(const char __user * src, unsigned long n)
  * Zero Userspace
  */
 
-static inline unsigned long
+static inline unsigned long __must_check
 __clear_user(void __user *to, unsigned long n)
 {
 	return uaccess.clear_user(n, to);
 }
 
-static inline unsigned long
+static inline unsigned long __must_check
 clear_user(void __user *to, unsigned long n)
 {
 	might_sleep();
diff --git a/include/asm-s390/zcrypt.h b/include/asm-s390/zcrypt.h
index 7244c68464f2..b90e55888a55 100644
--- a/include/asm-s390/zcrypt.h
+++ b/include/asm-s390/zcrypt.h
@@ -180,40 +180,8 @@ struct ica_xcRB {
  *	     for the implementation details for the contents of the
  *	     block
  *
- *   Z90STAT_TOTALCOUNT
- *     Return an integer count of all device types together.
- *
- *   Z90STAT_PCICACOUNT
- *     Return an integer count of all PCICAs.
- *
- *   Z90STAT_PCICCCOUNT
- *     Return an integer count of all PCICCs.
- *
- *   Z90STAT_PCIXCCMCL2COUNT
- *     Return an integer count of all MCL2 PCIXCCs.
- *
- *   Z90STAT_PCIXCCMCL3COUNT
- *     Return an integer count of all MCL3 PCIXCCs.
- *
- *   Z90STAT_CEX2CCOUNT
- *     Return an integer count of all CEX2Cs.
- *
- *   Z90STAT_CEX2ACOUNT
- *     Return an integer count of all CEX2As.
- *
- *   Z90STAT_REQUESTQ_COUNT
- *     Return an integer count of the number of entries waiting to be
- *     sent to a device.
- *
- *   Z90STAT_PENDINGQ_COUNT
- *     Return an integer count of the number of entries sent to a
- *     device awaiting the reply.
- *
- *   Z90STAT_TOTALOPEN_COUNT
- *     Return an integer count of the number of open file handles.
- *
- *   Z90STAT_DOMAIN_INDEX
- *     Return the integer value of the Cryptographic Domain.
+ *   ZSECSENDCPRB
+ *     Send an arbitrary CPRB to a crypto card.
  *
  *   Z90STAT_STATUS_MASK
  *     Return an 64 element array of unsigned chars for the status of
@@ -235,28 +203,51 @@ struct ica_xcRB {
  *     of successfully completed requests per device since the device
  *     was detected and made available.
  *
- *   ICAZ90STATUS (deprecated)
+ *   Z90STAT_REQUESTQ_COUNT
+ *     Return an integer count of the number of entries waiting to be
+ *     sent to a device.
+ *
+ *   Z90STAT_PENDINGQ_COUNT
+ *     Return an integer count of the number of entries sent to all
+ *     devices awaiting the reply.
+ *
+ *   Z90STAT_TOTALOPEN_COUNT
+ *     Return an integer count of the number of open file handles.
+ *
+ *   Z90STAT_DOMAIN_INDEX
+ *     Return the integer value of the Cryptographic Domain.
+ *
+ *   The following ioctls are deprecated and should be no longer used:
+ *
+ *   Z90STAT_TOTALCOUNT
+ *     Return an integer count of all device types together.
+ *
+ *   Z90STAT_PCICACOUNT
+ *     Return an integer count of all PCICAs.
+ *
+ *   Z90STAT_PCICCCOUNT
+ *     Return an integer count of all PCICCs.
+ *
+ *   Z90STAT_PCIXCCMCL2COUNT
+ *     Return an integer count of all MCL2 PCIXCCs.
+ *
+ *   Z90STAT_PCIXCCMCL3COUNT
+ *     Return an integer count of all MCL3 PCIXCCs.
+ *
+ *   Z90STAT_CEX2CCOUNT
+ *     Return an integer count of all CEX2Cs.
+ *
+ *   Z90STAT_CEX2ACOUNT
+ *     Return an integer count of all CEX2As.
+ *
+ *   ICAZ90STATUS
  *     Return some device driver status in a ica_z90_status struct
  *     This takes an ica_z90_status struct as its arg.
  *
- *     NOTE: this ioctl() is deprecated, and has been replaced with
- *	     single ioctl()s for each type of status being requested
- *
- *   Z90STAT_PCIXCCCOUNT (deprecated)
+ *   Z90STAT_PCIXCCCOUNT
  *     Return an integer count of all PCIXCCs (MCL2 + MCL3).
  *     This is DEPRECATED now that MCL3 PCIXCCs are treated differently from
  *     MCL2 PCIXCCs.
- *
- *   Z90QUIESCE (not recommended)
- *     Quiesce the driver.  This is intended to stop all new
- *     requests from being processed.  Its use is NOT recommended,
- *     except in circumstances where there is no other way to stop
- *     callers from accessing the driver.  Its original use was to
- *     allow the driver to be "drained" of work in preparation for
- *     a system shutdown.
- *
- *     NOTE: once issued, this ban on new work cannot be undone
- *	     except by unloading and reloading the driver.
  */
 
 /**
diff --git a/include/asm-sh/types.h b/include/asm-sh/types.h
index 3c09dd4ca31c..fd00dbb82f84 100644
--- a/include/asm-sh/types.h
+++ b/include/asm-sh/types.h
@@ -52,16 +52,6 @@ typedef unsigned long long u64;
 
 typedef u32 dma_addr_t;
 
-#ifdef CONFIG_LBD
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-#endif
-
-#ifdef CONFIG_LSF
-typedef u64 blkcnt_t;
-#define HAVE_BLKCNT_T
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86_64/elf.h b/include/asm-x86_64/elf.h
index a406fcb1e924..6d24ea7c4d9d 100644
--- a/include/asm-x86_64/elf.h
+++ b/include/asm-x86_64/elf.h
@@ -45,7 +45,6 @@ typedef struct user_i387_struct elf_fpregset_t;
 
 #ifdef __KERNEL__
 #include <asm/processor.h>
-#include <asm/compat.h>
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
diff --git a/include/asm-x86_64/types.h b/include/asm-x86_64/types.h
index c86c2e6793e2..2d4491aae281 100644
--- a/include/asm-x86_64/types.h
+++ b/include/asm-x86_64/types.h
@@ -48,9 +48,6 @@ typedef unsigned long long u64;
 typedef u64 dma64_addr_t;
 typedef u64 dma_addr_t;
 
-typedef u64 sector_t;
-#define HAVE_SECTOR_T
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86_64/uaccess.h b/include/asm-x86_64/uaccess.h
index 19f99178fe83..d5dbc87274f8 100644
--- a/include/asm-x86_64/uaccess.h
+++ b/include/asm-x86_64/uaccess.h
@@ -6,7 +6,6 @@
  */
 #include <linux/compiler.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/prefetch.h>
 #include <asm/page.h>
 
diff --git a/include/linux/acct.h b/include/linux/acct.h
index 0496d1f09952..302eb727ecb8 100644
--- a/include/linux/acct.h
+++ b/include/linux/acct.h
@@ -119,6 +119,7 @@ struct acct_v3
 #ifdef CONFIG_BSD_PROCESS_ACCT
 struct vfsmount;
 struct super_block;
+struct pacct_struct;
 extern void acct_auto_close_mnt(struct vfsmount *m);
 extern void acct_auto_close(struct super_block *sb);
 extern void acct_init_pacct(struct pacct_struct *pacct);
diff --git a/include/linux/ata.h b/include/linux/ata.h
index d89441907024..1df941648a57 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -200,8 +200,9 @@ enum {
 	ATA_CBL_NONE		= 0,
 	ATA_CBL_PATA40		= 1,
 	ATA_CBL_PATA80		= 2,
-	ATA_CBL_PATA_UNK	= 3,
-	ATA_CBL_SATA		= 4,
+	ATA_CBL_PATA40_SHORT	= 3,		/* 40 wire cable to high UDMA spec */
+	ATA_CBL_PATA_UNK	= 4,
+	ATA_CBL_SATA		= 5,
 
 	/* SATA Status and Control Registers */
 	SCR_STATUS		= 0,
@@ -342,6 +343,15 @@ static inline int ata_id_is_cfa(const u16 *id)
 	return 0;
 }
 
+static inline int ata_drive_40wire(const u16 *dev_id)
+{
+	if (ata_id_major_version(dev_id) >= 5 && ata_id_is_sata(dev_id))
+		return 0;	/* SATA */
+	if (dev_id[93] & 0x4000)
+		return 0;	/* 80 wire */
+	return 1;
+}
+
 static inline int atapi_cdb_len(const u16 *dev_id)
 {
 	u16 tmp = dev_id[0] & 0x3;
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 3fef7d67aedc..f02d71bf6894 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -33,6 +33,14 @@ struct cpu {
 
 extern int register_cpu(struct cpu *cpu, int num);
 extern struct sys_device *get_cpu_sysdev(unsigned cpu);
+
+extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr);
+extern void cpu_remove_sysdev_attr(struct sysdev_attribute *attr);
+
+extern int cpu_add_sysdev_attr_group(struct attribute_group *attrs);
+extern void cpu_remove_sysdev_attr_group(struct attribute_group *attrs);
+
+
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
 #endif
diff --git a/include/linux/elf.h b/include/linux/elf.h
index b70d1d2c8d28..743d5c8e6d36 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -368,5 +368,12 @@ extern Elf64_Dyn _DYNAMIC [];
 
 #endif
 
+#ifndef ARCH_HAVE_EXTRA_ELF_NOTES
+static inline int arch_notes_size(void) { return 0; }
+static inline void arch_write_notes(struct file *file) { }
+
+#define ELF_CORE_EXTRA_NOTES_SIZE arch_notes_size()
+#define ELF_CORE_WRITE_EXTRA_NOTES arch_write_notes(file)
+#endif /* ARCH_HAVE_EXTRA_ELF_NOTES */
 
 #endif /* _LINUX_ELF_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2fe6e3f900ba..cac7b1ef9543 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -276,7 +276,7 @@ extern int dir_notify_enable;
 #include <linux/radix-tree.h>
 #include <linux/prio_tree.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/pid.h>
 #include <linux/mutex.h>
 
 #include <asm/atomic.h>
@@ -977,36 +977,13 @@ enum {
 #define vfs_check_frozen(sb, level) \
 	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
 
-static inline void get_fs_excl(void)
-{
-	atomic_inc(&current->fs_excl);
-}
-
-static inline void put_fs_excl(void)
-{
-	atomic_dec(&current->fs_excl);
-}
-
-static inline int has_fs_excl(void)
-{
-	return atomic_read(&current->fs_excl);
-}
+#define get_fs_excl() atomic_inc(&current->fs_excl)
+#define put_fs_excl() atomic_dec(&current->fs_excl)
+#define has_fs_excl() atomic_read(&current->fs_excl)
 
-
-/*
- * Superblock locking.
- */
-static inline void lock_super(struct super_block * sb)
-{
-	get_fs_excl();
-	mutex_lock(&sb->s_lock);
-}
-
-static inline void unlock_super(struct super_block * sb)
-{
-	put_fs_excl();
-	mutex_unlock(&sb->s_lock);
-}
+/* not quite ready to be deprecated, but... */
+extern void lock_super(struct super_block *);
+extern void unlock_super(struct super_block *);
 
 /*
  * VFS helper functions..
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 6e7ea2f0a57c..9dbb525c5178 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -127,6 +127,7 @@ struct igmpv3_query {
 
 #ifdef __KERNEL__
 #include <linux/skbuff.h>
+#include <linux/timer.h>
 #include <linux/in.h>
 
 extern int sysctl_igmp_max_memberships;
diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h
index 891bb2cf0aa8..aea34e74c496 100644
--- a/include/linux/kernelcapi.h
+++ b/include/linux/kernelcapi.h
@@ -47,6 +47,8 @@ typedef struct kcapi_carddef {
 
 #include <linux/list.h>
 #include <linux/skbuff.h>
+#include <linux/workqueue.h>
+#include <asm/semaphore.h>
 
 #define	KCI_CONTRUP	0	/* arg: struct capi_profile */
 #define	KCI_CONTRDOWN	1	/* arg: NULL */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index b3f32eadbef5..ab2754830322 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -140,6 +140,7 @@ enum {
 	ATA_DFLAG_LBA48		= (1 << 1), /* device supports LBA48 */
 	ATA_DFLAG_CDB_INTR	= (1 << 2), /* device asserts INTRQ when ready for CDB */
 	ATA_DFLAG_NCQ		= (1 << 3), /* device supports NCQ */
+	ATA_DFLAG_FLUSH_EXT	= (1 << 4), /* do FLUSH_EXT instead of FLUSH */
 	ATA_DFLAG_CFG_MASK	= (1 << 8) - 1,
 
 	ATA_DFLAG_PIO		= (1 << 8), /* device limited to PIO mode */
@@ -175,6 +176,7 @@ enum {
 	ATA_FLAG_SKIP_D2H_BSY	= (1 << 12), /* can't wait for the first D2H
 					      * Register FIS clearing BSY */
 	ATA_FLAG_DEBUGMSG	= (1 << 13),
+	ATA_FLAG_SETXFER_POLLING= (1 << 14), /* use polling for SETXFER */
 
 	/* The following flag belongs to ap->pflags but is kept in
 	 * ap->flags because it's referenced in many LLDs and will be
@@ -283,6 +285,9 @@ enum {
 	ATA_EHI_QUIET		= (1 << 3),  /* be quiet */
 
 	ATA_EHI_DID_RESET	= (1 << 16), /* already reset this port */
+	ATA_EHI_PRINTINFO	= (1 << 17), /* print configuration info */
+	ATA_EHI_SETMODE		= (1 << 18), /* configure transfer mode */
+	ATA_EHI_POST_SETMODE	= (1 << 19), /* revaildating after setmode */
 
 	ATA_EHI_RESET_MODIFIER_MASK = ATA_EHI_RESUME_LINK,
 
@@ -307,10 +312,11 @@ enum {
 	   (some horkage may be drive/controller pair dependant */
 
 	ATA_HORKAGE_DIAGNOSTIC	= (1 << 0),	/* Failed boot diag */
+	ATA_HORKAGE_NODMA	= (1 << 1),	/* DMA problems */
+	ATA_HORKAGE_NONCQ	= (1 << 2),	/* Don't use NCQ */
 };
 
 enum hsm_task_states {
-	HSM_ST_UNKNOWN,		/* state unknown */
 	HSM_ST_IDLE,		/* no command on going */
 	HSM_ST,			/* (waiting the device to) transfer data */
 	HSM_ST_LAST,		/* (waiting the device to) complete command */
@@ -329,6 +335,7 @@ enum ata_completion_errors {
 	AC_ERR_SYSTEM		= (1 << 6), /* system error */
 	AC_ERR_INVALID		= (1 << 7), /* invalid argument */
 	AC_ERR_OTHER		= (1 << 8), /* unknown */
+	AC_ERR_NODEV_HINT	= (1 << 9), /* polling device detection hint */
 };
 
 /* forward declarations */
@@ -701,6 +708,8 @@ extern int sata_phy_debounce(struct ata_port *ap, const unsigned long *param);
 extern int sata_phy_resume(struct ata_port *ap, const unsigned long *param);
 extern int ata_std_prereset(struct ata_port *ap);
 extern int ata_std_softreset(struct ata_port *ap, unsigned int *classes);
+extern int sata_port_hardreset(struct ata_port *ap,
+			       const unsigned long *timing);
 extern int sata_std_hardreset(struct ata_port *ap, unsigned int *class);
 extern void ata_std_postreset(struct ata_port *ap, unsigned int *classes);
 extern void ata_port_disable(struct ata_port *);
@@ -745,9 +754,8 @@ extern int ata_scsi_device_suspend(struct scsi_device *, pm_message_t mesg);
 extern int ata_host_suspend(struct ata_host *host, pm_message_t mesg);
 extern void ata_host_resume(struct ata_host *host);
 extern int ata_ratelimit(void);
-extern unsigned int ata_busy_sleep(struct ata_port *ap,
-				   unsigned long timeout_pat,
-				   unsigned long timeout);
+extern int ata_busy_sleep(struct ata_port *ap,
+			  unsigned long timeout_pat, unsigned long timeout);
 extern void ata_port_queue_task(struct ata_port *ap, work_func_t fn,
 				void *data, unsigned long delay);
 extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val,
@@ -788,6 +796,7 @@ extern void ata_id_string(const u16 *id, unsigned char *s,
 			  unsigned int ofs, unsigned int len);
 extern void ata_id_c_string(const u16 *id, unsigned char *s,
 			    unsigned int ofs, unsigned int len);
+extern unsigned long ata_device_blacklisted(const struct ata_device *dev);
 extern void ata_bmdma_setup (struct ata_queued_cmd *qc);
 extern void ata_bmdma_start (struct ata_queued_cmd *qc);
 extern void ata_bmdma_stop(struct ata_queued_cmd *qc);
@@ -1062,7 +1071,7 @@ static inline u8 ata_busy_wait(struct ata_port *ap, unsigned int bits,
 		udelay(10);
 		status = ata_chk_status(ap);
 		max--;
-	} while ((status & bits) && (max > 0));
+	} while (status != 0xff && (status & bits) && (max > 0));
 
 	return status;
 }
@@ -1083,7 +1092,7 @@ static inline u8 ata_wait_idle(struct ata_port *ap)
 {
 	u8 status = ata_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000);
 
-	if (status & (ATA_BUSY | ATA_DRQ)) {
+	if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ))) {
 		unsigned long l = ap->ioaddr.status_addr;
 		if (ata_msg_warn(ap))
 			printk(KERN_WARNING "ATA: abnormal status 0x%X on port 0x%lX\n",
@@ -1149,37 +1158,6 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc)
 }
 
 /**
- *	ata_irq_on - Enable interrupts on a port.
- *	@ap: Port on which interrupts are enabled.
- *
- *	Enable interrupts on a legacy IDE device using MMIO or PIO,
- *	wait for idle, clear any pending interrupts.
- *
- *	LOCKING:
- *	Inherited from caller.
- */
-
-static inline u8 ata_irq_on(struct ata_port *ap)
-{
-	struct ata_ioports *ioaddr = &ap->ioaddr;
-	u8 tmp;
-
-	ap->ctl &= ~ATA_NIEN;
-	ap->last_ctl = ap->ctl;
-
-	if (ap->flags & ATA_FLAG_MMIO)
-		writeb(ap->ctl, (void __iomem *) ioaddr->ctl_addr);
-	else
-		outb(ap->ctl, ioaddr->ctl_addr);
-	tmp = ata_wait_idle(ap);
-
-	ap->ops->irq_clear(ap);
-
-	return tmp;
-}
-
-
-/**
  *	ata_irq_ack - Acknowledge a device interrupt.
  *	@ap: Port on which interrupts are enabled.
  *
diff --git a/include/linux/module.h b/include/linux/module.h
index 9258ffd8a7f0..d33df2408e05 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -6,7 +6,6 @@
  * Rewritten by Richard Henderson <rth@tamu.edu> Dec 1996
  * Rewritten again by Rusty Russell, 2002
  */
-#include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/stat.h>
@@ -411,17 +410,7 @@ static inline int try_module_get(struct module *module)
 	return ret;
 }
 
-static inline void module_put(struct module *module)
-{
-	if (module) {
-		unsigned int cpu = get_cpu();
-		local_dec(&module->ref[cpu].count);
-		/* Maybe they're waiting for us to drop reference? */
-		if (unlikely(!module_is_live(module)))
-			wake_up_process(module->waiter);
-		put_cpu();
-	}
-}
+extern void module_put(struct module *module);
 
 #else /*!CONFIG_MODULE_UNLOAD*/
 static inline int try_module_get(struct module *module)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 949eada46ce1..c57088f575a3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -30,6 +30,7 @@
 #include <linux/if_packet.h>
 
 #ifdef __KERNEL__
+#include <linux/timer.h>
 #include <asm/atomic.h>
 #include <asm/cache.h>
 #include <asm/byteorder.h>
diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h
index 61da56941dce..33581c13d947 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <asm/atomic.h>
 
+#include <linux/timer.h>
 #include <linux/netfilter_ipv4/ip_conntrack_tcp.h>
 #include <linux/netfilter_ipv4/ip_conntrack_icmp.h>
 #include <linux/netfilter_ipv4/ip_conntrack_proto_gre.h>
diff --git a/include/linux/pata_platform.h b/include/linux/pata_platform.h
new file mode 100644
index 000000000000..2d5fd647e0e9
--- /dev/null
+++ b/include/linux/pata_platform.h
@@ -0,0 +1,13 @@
+#ifndef __LINUX_PATA_PLATFORM_H
+#define __LINUX_PATA_PLATFORM_H
+
+struct pata_platform_info {
+	/*
+	 * I/O port shift, for platforms with ports that are
+	 * constantly spaced and need larger than the 1-byte
+	 * spacing used by ata_std_ports().
+	 */
+	unsigned int ioport_shift;
+};
+
+#endif /* __LINUX_PATA_PLATFORM_H */
diff --git a/include/linux/poll.h b/include/linux/poll.h
index 51e1b56741fb..27690798623f 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -8,7 +8,8 @@
 #include <linux/compiler.h>
 #include <linux/wait.h>
 #include <linux/string.h>
-#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
 #include <asm/uaccess.h>
 
 /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 9158a68140c9..cbfa11537421 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -19,7 +19,6 @@
 #ifndef _LINUX_RADIX_TREE_H
 #define _LINUX_RADIX_TREE_H
 
-#include <linux/sched.h>
 #include <linux/preempt.h>
 #include <linux/types.h>
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 14ec16d2d9ba..a05a5f7c0b73 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -22,12 +22,10 @@
 #include <asm/atomic.h>
 #include <asm/types.h>
 #include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/poll.h>
 #include <linux/net.h>
 #include <linux/textsearch.h>
 #include <net/checksum.h>
+#include <linux/rcupdate.h>
 #include <linux/dmaengine.h>
 
 #define HAVE_ALLOC_SKB		/* For the drivers to know */
@@ -1295,24 +1293,6 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
 	return __pskb_trim(skb, len);
 }
 
-static inline void *kmap_skb_frag(const skb_frag_t *frag)
-{
-#ifdef CONFIG_HIGHMEM
-	BUG_ON(in_irq());
-
-	local_bh_disable();
-#endif
-	return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ);
-}
-
-static inline void kunmap_skb_frag(void *vaddr)
-{
-	kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ);
-#ifdef CONFIG_HIGHMEM
-	local_bh_enable();
-#endif
-}
-
 #define skb_queue_walk(queue, skb) \
 		for (skb = (queue)->next;					\
 		     prefetch(skb->next), (skb != (struct sk_buff *)(queue));	\
diff --git a/include/linux/types.h b/include/linux/types.h
index 745c409ebbb5..0351bf2fac85 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -136,15 +136,19 @@ typedef		__s64		int64_t;
  *
  * Linux always considers sectors to be 512 bytes long independently
  * of the devices real block size.
- *
- * If required, asm/types.h can override it and define
- * HAVE_SECTOR_T
  */
-#ifndef HAVE_SECTOR_T
+#ifdef CONFIG_LBD
+typedef u64 sector_t;
+#else
 typedef unsigned long sector_t;
 #endif
 
-#ifndef HAVE_BLKCNT_T
+/*
+ * The type of the inode's block count.
+ */
+#ifdef CONFIG_LSF
+typedef u64 blkcnt_t;
+#else
 typedef unsigned long blkcnt_t;
 #endif
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index cccea051e922..bf16d98d372c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -18,6 +18,7 @@
 #include <linux/compiler.h>
 #include <linux/string.h>
 #include <linux/timer.h>
+#include <linux/poll.h>
 
 #include <net/inet_sock.h>
 #include <net/request_sock.h>
diff --git a/include/net/irda/timer.h b/include/net/irda/timer.h
index 2c5d8864ab77..cb61568547d1 100644
--- a/include/net/irda/timer.h
+++ b/include/net/irda/timer.h
@@ -28,6 +28,7 @@
 #define TIMER_H
 
 #include <linux/timer.h>
+#include <linux/jiffies.h>
 
 #include <asm/param.h>  /* for HZ */
 
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 032b36a0e378..bd01b4633ee2 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -56,6 +56,7 @@ union nf_conntrack_help {
 
 #include <linux/types.h>
 #include <linux/skbuff.h>
+#include <linux/timer.h>
 
 #ifdef CONFIG_NETFILTER_DEBUG
 #define NF_CT_ASSERT(x)							\
diff --git a/include/net/netlink.h b/include/net/netlink.h
index fd75fd65d59e..bcaf67b7a19d 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/netlink.h>
+#include <linux/jiffies.h>
 
 /* ========================================================================
  *         Netlink Messages and Attributes Interface (As Seen On TV)
diff --git a/include/net/sock.h b/include/net/sock.h
index 26fc0b16bc0c..fe3a33fad03f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -47,6 +47,7 @@
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>	/* struct sk_buff */
+#include <linux/mm.h>
 #include <linux/security.h>
 
 #include <linux/filter.h>
diff --git a/include/net/udp.h b/include/net/udp.h
index 1548d68d45da..1b921fa81474 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -29,6 +29,7 @@
 #include <net/ip.h>
 #include <linux/ipv6.h>
 #include <linux/seq_file.h>
+#include <linux/poll.h>
 
 /**
  *	struct udp_skb_cb  -  UDP(-Lite) private variables
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 61eebec00a7b..ea0816d4904d 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -25,6 +25,8 @@
 
 #include <linux/types.h>
 #include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
 #include <scsi/iscsi_proto.h>
 #include <scsi/iscsi_if.h>
 
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index afaf3e88e086..2f645dfd7f70 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -26,6 +26,7 @@
 #include <sound/asound.h>
 #include <sound/memalloc.h>
 #include <linux/poll.h>
+#include <linux/mm.h>
 #include <linux/bitops.h>
 
 #define snd_pcm_substream_chip(substream) ((substream)->private_data)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 42f2f1179711..ab97e5101232 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -64,6 +64,7 @@
 #include <linux/tty.h>
 #include <linux/selinux.h>
 #include <linux/binfmts.h>
+#include <linux/highmem.h>
 #include <linux/syscalls.h>
 
 #include "audit.h"
diff --git a/kernel/latency.c b/kernel/latency.c
index 258f2555abbc..e63fcacb61a7 100644
--- a/kernel/latency.c
+++ b/kernel/latency.c
@@ -36,6 +36,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/notifier.h>
+#include <linux/jiffies.h>
 #include <asm/atomic.h>
 
 struct latency_info {
diff --git a/kernel/module.c b/kernel/module.c
index 45e01cb60101..e2d09d604ca0 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -34,10 +34,10 @@
 #include <linux/err.h>
 #include <linux/vermagic.h>
 #include <linux/notifier.h>
+#include <linux/sched.h>
 #include <linux/stop_machine.h>
 #include <linux/device.h>
 #include <linux/string.h>
-#include <linux/sched.h>
 #include <linux/mutex.h>
 #include <linux/unwind.h>
 #include <asm/uaccess.h>
@@ -790,6 +790,19 @@ static struct module_attribute refcnt = {
 	.show = show_refcnt,
 };
 
+void module_put(struct module *module)
+{
+	if (module) {
+		unsigned int cpu = get_cpu();
+		local_dec(&module->ref[cpu].count);
+		/* Maybe they're waiting for us to drop reference? */
+		if (unlikely(!module_is_live(module)))
+			wake_up_process(module->waiter);
+		put_cpu();
+	}
+}
+EXPORT_SYMBOL(module_put);
+
 #else /* !CONFIG_MODULE_UNLOAD */
 static void print_unload_info(struct seq_file *m, struct module *mod)
 {
diff --git a/lib/iomap.c b/lib/iomap.c
index 55689c5d3379..d6ccdd85df53 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -50,6 +50,16 @@
 	}							\
 } while (0)
 
+#ifndef pio_read16be
+#define pio_read16be(port) swab16(inw(port))
+#define pio_read32be(port) swab32(inl(port))
+#endif
+
+#ifndef mmio_read16be
+#define mmio_read16be(addr) be16_to_cpu(__raw_readw(addr))
+#define mmio_read32be(addr) be32_to_cpu(__raw_readl(addr))
+#endif
+
 unsigned int fastcall ioread8(void __iomem *addr)
 {
 	IO_COND(addr, return inb(port), return readb(addr));
@@ -60,7 +70,7 @@ unsigned int fastcall ioread16(void __iomem *addr)
 }
 unsigned int fastcall ioread16be(void __iomem *addr)
 {
-	IO_COND(addr, return inw(port), return be16_to_cpu(__raw_readw(addr)));
+	IO_COND(addr, return pio_read16be(port), return mmio_read16be(addr));
 }
 unsigned int fastcall ioread32(void __iomem *addr)
 {
@@ -68,7 +78,7 @@ unsigned int fastcall ioread32(void __iomem *addr)
 }
 unsigned int fastcall ioread32be(void __iomem *addr)
 {
-	IO_COND(addr, return inl(port), return be32_to_cpu(__raw_readl(addr)));
+	IO_COND(addr, return pio_read32be(port), return mmio_read32be(addr));
 }
 EXPORT_SYMBOL(ioread8);
 EXPORT_SYMBOL(ioread16);
@@ -76,6 +86,16 @@ EXPORT_SYMBOL(ioread16be);
 EXPORT_SYMBOL(ioread32);
 EXPORT_SYMBOL(ioread32be);
 
+#ifndef pio_write16be
+#define pio_write16be(val,port) outw(swab16(val),port)
+#define pio_write32be(val,port) outl(swab32(val),port)
+#endif
+
+#ifndef mmio_write16be
+#define mmio_write16be(val,port) __raw_writew(be16_to_cpu(val),port)
+#define mmio_write32be(val,port) __raw_writel(be32_to_cpu(val),port)
+#endif
+
 void fastcall iowrite8(u8 val, void __iomem *addr)
 {
 	IO_COND(addr, outb(val,port), writeb(val, addr));
@@ -86,7 +106,7 @@ void fastcall iowrite16(u16 val, void __iomem *addr)
 }
 void fastcall iowrite16be(u16 val, void __iomem *addr)
 {
-	IO_COND(addr, outw(val,port), __raw_writew(cpu_to_be16(val), addr));
+	IO_COND(addr, pio_write16be(val,port), mmio_write16be(val, addr));
 }
 void fastcall iowrite32(u32 val, void __iomem *addr)
 {
@@ -94,7 +114,7 @@ void fastcall iowrite32(u32 val, void __iomem *addr)
 }
 void fastcall iowrite32be(u32 val, void __iomem *addr)
 {
-	IO_COND(addr, outl(val,port), __raw_writel(cpu_to_be32(val), addr));
+	IO_COND(addr, pio_write32be(val,port), mmio_write32be(val, addr));
 }
 EXPORT_SYMBOL(iowrite8);
 EXPORT_SYMBOL(iowrite16);
@@ -108,6 +128,7 @@ EXPORT_SYMBOL(iowrite32be);
  * convert to CPU byte order. We write in "IO byte
  * order" (we also don't have IO barriers).
  */
+#ifndef mmio_insb
 static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
 {
 	while (--count >= 0) {
@@ -132,7 +153,9 @@ static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
 		dst++;
 	}
 }
+#endif
 
+#ifndef mmio_outsb
 static inline void mmio_outsb(void __iomem *addr, const u8 *src, int count)
 {
 	while (--count >= 0) {
@@ -154,6 +177,7 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
 		src++;
 	}
 }
+#endif
 
 void fastcall ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
 {
diff --git a/lib/random32.c b/lib/random32.c
index 4a15ce51cea7..ec7f81d3fb18 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -36,6 +36,7 @@
 #include <linux/types.h>
 #include <linux/percpu.h>
 #include <linux/module.h>
+#include <linux/jiffies.h>
 #include <linux/random.h>
 
 struct rnd_state {
diff --git a/mm/filemap.c b/mm/filemap.c
index 7b84dc814347..13df01c50479 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1893,6 +1893,7 @@ int should_remove_suid(struct dentry *dentry)
 
 	return 0;
 }
+EXPORT_SYMBOL(should_remove_suid);
 
 int __remove_suid(struct dentry *dentry, int kill)
 {
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 485e35c3b28b..3a7052207708 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -61,6 +61,7 @@
 #include <net/tcp_states.h>
 #include <net/route.h>
 #include <linux/atalk.h>
+#include "../core/kmap_skb.h"
 
 struct datalink_proto *ddp_dl, *aarp_dl;
 static const struct proto_ops atalk_dgram_ops;
diff --git a/net/core/kmap_skb.h b/net/core/kmap_skb.h
new file mode 100644
index 000000000000..283c2b993fb8
--- /dev/null
+++ b/net/core/kmap_skb.h
@@ -0,0 +1,19 @@
+#include <linux/highmem.h>
+
+static inline void *kmap_skb_frag(const skb_frag_t *frag)
+{
+#ifdef CONFIG_HIGHMEM
+	BUG_ON(in_irq());
+
+	local_bh_disable();
+#endif
+	return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ);
+}
+
+static inline void kunmap_skb_frag(void *vaddr)
+{
+	kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ);
+#ifdef CONFIG_HIGHMEM
+	local_bh_enable();
+#endif
+}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a90bc439488e..8e1c385e5ba9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -56,7 +56,6 @@
 #include <linux/cache.h>
 #include <linux/rtnetlink.h>
 #include <linux/init.h>
-#include <linux/highmem.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -67,6 +66,8 @@
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
+#include "kmap_skb.h"
+
 static kmem_cache_t *skbuff_head_cache __read_mostly;
 static kmem_cache_t *skbuff_fclone_cache __read_mostly;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index ab8fafadb4ba..419c7d3289c7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -111,6 +111,7 @@
 #include <linux/poll.h>
 #include <linux/tcp.h>
 #include <linux/init.h>
+#include <linux/highmem.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig
index dac89166eb18..80f469887691 100644
--- a/net/dccp/ccids/Kconfig
+++ b/net/dccp/ccids/Kconfig
@@ -89,4 +89,37 @@ config IP_DCCP_CCID3_DEBUG
 	    parameter to 0 or 1.
 
 	    If in doubt, say N.
+
+config IP_DCCP_CCID3_RTO
+	  int "Use higher bound for nofeedback timer"
+	  default 100
+	  depends on IP_DCCP_CCID3 && EXPERIMENTAL
+	  ---help---
+	    Use higher lower bound for nofeedback timer expiration.
+
+	    The TFRC nofeedback timer normally expires after the maximum of 4
+	    RTTs and twice the current send interval (RFC 3448, 4.3). On LANs
+	    with a small RTT this can mean a high processing load and reduced
+	    performance, since then the nofeedback timer is triggered very
+	    frequently.
+
+	    This option enables to set a higher lower bound for the nofeedback
+	    value. Values in units of milliseconds can be set here.
+
+	    A value of 0 disables this feature by enforcing the value specified
+	    in RFC 3448. The following values have been suggested as bounds for
+	    experimental use:
+	    	* 16-20ms to match the typical multimedia inter-frame interval
+	    	* 100ms as a reasonable compromise [default]
+	    	* 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4)
+
+	    The default of 100ms is a compromise between a large value for
+	    efficient DCCP implementations, and a small value to avoid disrupting
+	    the network in times of congestion.
+
+	    The purpose of the nofeedback timer is to slow DCCP down when there
+	    is serious network congestion: experimenting with larger values should
+	    therefore not be performed on WANs.
+
+
 endmenu
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 70ebe705eb75..cf8c07b2704f 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -121,12 +121,15 @@ static inline void ccid3_update_send_time(struct ccid3_hc_tx_sock *hctx)
 /*
  * Update X by
  *    If (p > 0)
- *       x_calc = calcX(s, R, p);
+ *       X_calc = calcX(s, R, p);
  *       X = max(min(X_calc, 2 * X_recv), s / t_mbi);
  *    Else
  *       If (now - tld >= R)
  *          X = max(min(2 * X, 2 * X_recv), s / R);
  *          tld = now;
+ *
+ * If X has changed, we also update the scheduled send time t_now,
+ * the inter-packet interval t_ipi, and the delta value.
  */ 
 static void ccid3_hc_tx_update_x(struct sock *sk, struct timeval *now)
 
@@ -134,8 +137,7 @@ static void ccid3_hc_tx_update_x(struct sock *sk, struct timeval *now)
 	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
 	const __u32 old_x = hctx->ccid3hctx_x;
 
-	/* To avoid large error in calcX */
-	if (hctx->ccid3hctx_p >= TFRC_SMALLEST_P) {
+	if (hctx->ccid3hctx_p > 0) {
 		hctx->ccid3hctx_x_calc = tfrc_calc_x(hctx->ccid3hctx_s,
 						     hctx->ccid3hctx_rtt,
 						     hctx->ccid3hctx_p);
@@ -223,16 +225,14 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
 				       ccid3_tx_state_name(hctx->ccid3hctx_state));
 			/* Halve sending rate */
 
-			/*  If (X_calc > 2 * X_recv)
+			/*  If (p == 0 || X_calc > 2 * X_recv)
 			 *    X_recv = max(X_recv / 2, s / (2 * t_mbi));
 			 *  Else
 			 *    X_recv = X_calc / 4;
 			 */
-			BUG_ON(hctx->ccid3hctx_p >= TFRC_SMALLEST_P &&
-			       hctx->ccid3hctx_x_calc == 0);
+			BUG_ON(hctx->ccid3hctx_p && !hctx->ccid3hctx_x_calc);
 
-			/* check also if p is zero -> x_calc is infinity? */
-			if (hctx->ccid3hctx_p < TFRC_SMALLEST_P ||
+			if (hctx->ccid3hctx_p  == 0 ||
 			    hctx->ccid3hctx_x_calc > 2 * hctx->ccid3hctx_x_recv)
 				hctx->ccid3hctx_x_recv = max_t(u32, hctx->ccid3hctx_x_recv / 2,
 								    hctx->ccid3hctx_s / (2 * TFRC_T_MBI));
@@ -245,9 +245,10 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
 		}
 		/*
 		 * Schedule no feedback timer to expire in
-		 * max(4 * R, 2 * s/X)  =  max(4 * R, 2 * t_ipi)
+		 * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)
+		 * See comments in packet_recv() regarding the value of t_RTO.
 		 */
-		t_nfb = max(4 * hctx->ccid3hctx_rtt, 2 * hctx->ccid3hctx_t_ipi);
+		t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi);
 		break;
 	case TFRC_SSTATE_NO_SENT:
 		DCCP_BUG("Illegal %s state NO_SENT, sk=%p", dccp_role(sk), sk);
@@ -338,7 +339,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 		 * else
 		 *       // send the packet in (t_nom - t_now) milliseconds.
 		 */
-		if (delay >= hctx->ccid3hctx_delta)
+		if (delay - (long)hctx->ccid3hctx_delta >= 0)
 			return delay / 1000L;
 		break;
 	case TFRC_SSTATE_TERM:
@@ -412,10 +413,8 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 	struct dccp_tx_hist_entry *packet;
 	struct timeval now;
 	unsigned long t_nfb;
-	u32 t_elapsed;
 	u32 pinv;
-	u32 x_recv;
-	u32 r_sample;
+	long r_sample, t_elapsed;
 
 	BUG_ON(hctx == NULL);
 
@@ -426,31 +425,44 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 
 	opt_recv = &hctx->ccid3hctx_options_received;
 
-	t_elapsed = dp->dccps_options_received.dccpor_elapsed_time * 10;
-	x_recv = opt_recv->ccid3or_receive_rate;
-	pinv = opt_recv->ccid3or_loss_event_rate;
-
 	switch (hctx->ccid3hctx_state) {
 	case TFRC_SSTATE_NO_FBACK:
 	case TFRC_SSTATE_FBACK:
-		/* Calculate new round trip sample by
-		 * R_sample = (now - t_recvdata) - t_delay */
-		/* get t_recvdata from history */
+		/* get packet from history to look up t_recvdata */
 		packet = dccp_tx_hist_find_entry(&hctx->ccid3hctx_hist,
 						 DCCP_SKB_CB(skb)->dccpd_ack_seq);
 		if (unlikely(packet == NULL)) {
-			DCCP_WARN("%s, sk=%p, seqno %llu(%s) does't exist "
+			DCCP_WARN("%s(%p), seqno %llu(%s) doesn't exist "
 				  "in history!\n",  dccp_role(sk), sk,
 			    (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq,
 				  dccp_packet_name(DCCP_SKB_CB(skb)->dccpd_type));
 			return;
 		}
 
-		/* Update RTT */
+		/* Update receive rate */
+		hctx->ccid3hctx_x_recv = opt_recv->ccid3or_receive_rate;
+
+		/* Update loss event rate */
+		pinv = opt_recv->ccid3or_loss_event_rate;
+		if (pinv == ~0U || pinv == 0)
+			hctx->ccid3hctx_p = 0;
+		else
+ 			hctx->ccid3hctx_p = 1000000 / pinv;
+
 		dccp_timestamp(sk, &now);
-		r_sample = timeval_delta(&now, &packet->dccphtx_tstamp);
-		if (unlikely(r_sample <= t_elapsed))
-			DCCP_WARN("r_sample=%uus,t_elapsed=%uus\n",
+
+		/*
+		 * Calculate new round trip sample as per [RFC 3448, 4.3] by
+		 * 	R_sample  =  (now - t_recvdata) - t_elapsed
+		 */
+		r_sample  = timeval_delta(&now, &packet->dccphtx_tstamp);
+		t_elapsed = dp->dccps_options_received.dccpor_elapsed_time * 10;
+
+		if (unlikely(r_sample <= 0)) {
+			DCCP_WARN("WARNING: R_sample (%ld) <= 0!\n", r_sample);
+			r_sample = 0;
+		} else if (unlikely(r_sample <= t_elapsed))
+			DCCP_WARN("WARNING: r_sample=%ldus <= t_elapsed=%ldus\n",
 				  r_sample, t_elapsed);
 		else
 			r_sample -= t_elapsed;
@@ -473,31 +485,25 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 			hctx->ccid3hctx_t_ld = now;
 
 			ccid3_update_send_time(hctx);
-			ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);
-		} else {
-			hctx->ccid3hctx_rtt = (hctx->ccid3hctx_rtt * 9) / 10 +
-					      r_sample / 10;
-			ccid3_hc_tx_update_x(sk, &now);
-		}
 
-		ccid3_pr_debug("%s, sk=%p, New RTT estimate=%uus, "
-			       "r_sample=%us\n", dccp_role(sk), sk,
-			       hctx->ccid3hctx_rtt, r_sample);
+			ccid3_pr_debug("%s(%p), s=%u, w_init=%u, "
+				       "R_sample=%ldus, X=%u\n", dccp_role(sk),
+				       sk, hctx->ccid3hctx_s, w_init, r_sample,
+				       hctx->ccid3hctx_x);
 
-		/* Update receive rate */
-		hctx->ccid3hctx_x_recv = x_recv;/* X_recv in bytes per sec */
+			ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);
+		} else {
+			hctx->ccid3hctx_rtt = (9 * hctx->ccid3hctx_rtt +
+					           (u32)r_sample        ) / 10;
 
-		/* Update loss event rate */
-		if (pinv == ~0 || pinv == 0)
-			hctx->ccid3hctx_p = 0;
-		else {
-			hctx->ccid3hctx_p = 1000000 / pinv;
+			ccid3_hc_tx_update_x(sk, &now);
 
-			if (hctx->ccid3hctx_p < TFRC_SMALLEST_P) {
-				hctx->ccid3hctx_p = TFRC_SMALLEST_P;
-				ccid3_pr_debug("%s, sk=%p, Smallest p used!\n",
-					       dccp_role(sk), sk);
-			}
+			ccid3_pr_debug("%s(%p), RTT=%uus (sample=%ldus), s=%u, "
+				       "p=%u, X_calc=%u, X=%u\n", dccp_role(sk),
+				       sk, hctx->ccid3hctx_rtt, r_sample,
+				       hctx->ccid3hctx_s, hctx->ccid3hctx_p,
+				       hctx->ccid3hctx_x_calc,
+				       hctx->ccid3hctx_x);
 		}
 
 		/* unschedule no feedback timer */
@@ -512,16 +518,20 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 		 */
 		sk->sk_write_space(sk);
 
-		/* Update timeout interval. We use the alternative variant of
-		 * [RFC 3448, 3.1] which sets the upper bound of t_rto to one
-		 * second, as it is suggested for TCP (see RFC 2988, 2.4). */
+		/*
+		 * Update timeout interval for the nofeedback timer.
+		 * We use a configuration option to increase the lower bound.
+		 * This can help avoid triggering the nofeedback timer too often
+		 * ('spinning') on LANs with small RTTs.
+		 */
 		hctx->ccid3hctx_t_rto = max_t(u32, 4 * hctx->ccid3hctx_rtt,
-					      	   USEC_PER_SEC            );
+						   CONFIG_IP_DCCP_CCID3_RTO *
+						   (USEC_PER_SEC/1000)	     );
 		/*
 		 * Schedule no feedback timer to expire in
-		 * max(4 * R, 2 * s/X)  =  max(4 * R, 2 * t_ipi)
+		 * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)
 		 */
-		t_nfb = max(4 * hctx->ccid3hctx_rtt, 2 * hctx->ccid3hctx_t_ipi);
+		t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi);
 			
 		ccid3_pr_debug("%s, sk=%p, Scheduled no feedback timer to "
 			       "expire in %lu jiffies (%luus)\n",
@@ -535,7 +545,8 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 		hctx->ccid3hctx_idle = 1;   
 		break;
 	case TFRC_SSTATE_NO_SENT:
-		DCCP_WARN("Illegal ACK received - no packet has been sent\n");
+		if (dccp_sk(sk)->dccps_role == DCCP_ROLE_CLIENT)
+			DCCP_WARN("Illegal ACK received - no packet sent\n");
 		/* fall through */
 	case TFRC_SSTATE_TERM:		/* ignore feedback when closing */
 		break;
diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
index 27cb20ae1da8..07596d704ef9 100644
--- a/net/dccp/ccids/ccid3.h
+++ b/net/dccp/ccids/ccid3.h
@@ -51,8 +51,6 @@
 /* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */
 #define TFRC_T_MBI		   64
 
-#define TFRC_SMALLEST_P		   40
-
 enum ccid3_options {
 	TFRC_OPT_LOSS_EVENT_RATE = 192,
 	TFRC_OPT_LOSS_INTERVALS	 = 193,
diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c
index 2601012383fb..ddac2c511e2f 100644
--- a/net/dccp/ccids/lib/tfrc_equation.c
+++ b/net/dccp/ccids/lib/tfrc_equation.c
@@ -18,10 +18,79 @@
 #include "tfrc.h"
 
 #define TFRC_CALC_X_ARRSIZE 500
+#define TFRC_CALC_X_SPLIT   50000	/* 0.05 * 1000000, details below */
+#define TFRC_SMALLEST_P	    (TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE)
 
-#define TFRC_CALC_X_SPLIT 50000
-/* equivalent to 0.05 */
-
+/*
+  TFRC TCP Reno Throughput Equation Lookup Table for f(p)
+
+  The following two-column lookup table implements a part of the TCP throughput
+  equation from [RFC 3448, sec. 3.1]:
+
+	 			     s
+  X_calc  =  --------------------------------------------------------------
+	     R * sqrt(2*b*p/3) + (3 * t_RTO * sqrt(3*b*p/8) * (p + 32*p^3))
+
+  Where:
+	X      is the transmit rate in bytes/second
+	s      is the packet size in bytes
+	R      is the round trip time in seconds
+	p      is the loss event rate, between 0 and 1.0, of the number of loss
+	              events as a fraction of the number of packets transmitted
+	t_RTO  is the TCP retransmission timeout value in seconds
+	b      is the number of packets acknowledged by a single TCP ACK
+
+  We can assume that b = 1 and t_RTO is 4 * R. The equation now becomes:
+
+				     s
+  X_calc  =  -------------------------------------------------------
+	     R * sqrt(p*2/3) + (12 * R * sqrt(p*3/8) * (p + 32*p^3))
+
+  which we can break down into:
+
+                      s
+	X_calc  =  ---------
+	            R * f(p)
+
+  where f(p) is given for 0 < p <= 1 by:
+
+	f(p)  =  sqrt(2*p/3) + 12 * sqrt(3*p/8) *  (p + 32*p^3)
+
+  Since this is kernel code, floating-point arithmetic is avoided in favour of
+  integer arithmetic. This means that nearly all fractional parameters are
+  scaled by 1000000:
+    * the parameters p and R
+    * the return result f(p)
+  The lookup table therefore actually tabulates the following function g(q):
+
+  	g(q)  =  1000000 * f(q/1000000)
+
+  Hence, when p <= 1, q must be less than or equal to 1000000. To achieve finer
+  granularity for the practically more relevant case of small values of p (up to
+  5%), the second column is used; the first one ranges up to 100%.  This split
+  corresponds to the value of q = TFRC_CALC_X_SPLIT. At the same time this also
+  determines the smallest resolution possible with this lookup table:
+
+    TFRC_SMALLEST_P   =  TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE
+
+  The entire table is generated by:
+    for(i=0; i < TFRC_CALC_X_ARRSIZE; i++) {
+	lookup[i][0]  =  g((i+1) * 1000000/TFRC_CALC_X_ARRSIZE);
+	lookup[i][1]  =  g((i+1) * TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE);
+    }
+
+  With the given configuration, we have, with M = TFRC_CALC_X_ARRSIZE-1,
+    lookup[0][0]  =  g(1000000/(M+1)) 		 =  1000000 * f(0.2%)
+    lookup[M][0]  =  g(1000000)			 =  1000000 * f(100%)
+    lookup[0][1]  =  g(TFRC_SMALLEST_P)		  = 1000000 * f(0.01%)
+    lookup[M][1]  =  g(TFRC_CALC_X_SPLIT)	 =  1000000 * f(5%)
+
+  In summary, the two columns represent f(p) for the following ranges:
+    * The first column is for   0.002  <= p <= 1.0
+    * The second column is for  0.0001 <= p <= 0.05
+  Where the columns overlap, the second (finer-grained) is given preference,
+  i.e. the first column is used only for p >= 0.05.
+ */
 static const u32 tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE][2] = {
 	{     37172,   8172 },
 	{     53499,  11567 },
@@ -525,85 +594,69 @@ static const u32 tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE][2] = {
 	{ 243315981, 271305 }
 };
 
-/* Calculate the send rate as per section 3.1 of RFC3448
- 
-Returns send rate in bytes per second
-
-Integer maths and lookups are used as not allowed floating point in kernel
-
-The function for Xcalc as per section 3.1 of RFC3448 is:
-
-X =                            s
-     -------------------------------------------------------------
-     R*sqrt(2*b*p/3) + (t_RTO * (3*sqrt(3*b*p/8) * p * (1+32*p^2)))
-
-where 
-X is the trasmit rate in bytes/second
-s is the packet size in bytes
-R is the round trip time in seconds
-p is the loss event rate, between 0 and 1.0, of the number of loss events 
-  as a fraction of the number of packets transmitted
-t_RTO is the TCP retransmission timeout value in seconds
-b is the number of packets acknowledged by a single TCP acknowledgement
-
-we can assume that b = 1 and t_RTO is 4 * R. With this the equation becomes:
-
-X =                            s
-     -----------------------------------------------------------------------
-     R * sqrt(2 * p / 3) + (12 * R * (sqrt(3 * p / 8) * p * (1 + 32 * p^2)))
-
-
-which we can break down into:
-
-X =     s
-     --------
-     R * f(p)
-
-where f(p) = sqrt(2 * p / 3) + (12 * sqrt(3 * p / 8) * p * (1 + 32 * p * p))
-
-Function parameters:
-s - bytes
-R - RTT in usecs
-p - loss rate (decimal fraction multiplied by 1,000,000)
-
-Returns Xcalc in bytes per second
-
-DON'T alter this code unless you run test cases against it as the code
-has been manipulated to stop underflow/overlow.
+/* return largest index i such that fval <= lookup[i][small] */
+static inline u32 tfrc_binsearch(u32 fval, u8 small)
+{
+	u32 try, low = 0, high = TFRC_CALC_X_ARRSIZE - 1;
+
+	while (low < high) {
+		try = (low + high) / 2;
+		if (fval <= tfrc_calc_x_lookup[try][small])
+			high = try;
+		else
+			low  = try + 1;
+	}
+	return high;
+}
 
-*/
+/**
+ * tfrc_calc_x - Calculate the send rate as per section 3.1 of RFC3448
+ *
+ *  @s: packet size          in bytes
+ *  @R: RTT                  scaled by 1000000   (i.e., microseconds)
+ *  @p: loss ratio estimate  scaled by 1000000
+ *  Returns X_calc           in bytes per second (not scaled).
+ *
+ * Note: DO NOT alter this code unless you run test cases against it,
+ *       as the code has been optimized to stop underflow/overflow.
+ */
 u32 tfrc_calc_x(u16 s, u32 R, u32 p)
 {
 	int index;
 	u32 f;
 	u64 tmp1, tmp2;
 
-	if (p < TFRC_CALC_X_SPLIT)
-		index = (p / (TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE)) - 1;
-	else
-		index = (p / (1000000 / TFRC_CALC_X_ARRSIZE)) - 1;
+	/* check against invalid parameters and divide-by-zero   */
+	BUG_ON(p >  1000000);		/* p must not exceed 100%   */
+	BUG_ON(p == 0);			/* f(0) = 0, divide by zero */
+	if (R == 0) {			/* possible  divide by zero */
+		DCCP_CRIT("WARNING: RTT is 0, returning maximum X_calc.");
+		return ~0U;
+ 	}
 
-	if (index < 0)
-		/* p should be 0 unless there is a bug in my code */
-		index = 0;
+	if (p <= TFRC_CALC_X_SPLIT) 		{     /* 0.0000 < p <= 0.05   */
+		if (p < TFRC_SMALLEST_P) {	      /* 0.0000 < p <  0.0001 */
+			DCCP_WARN("Value of p (%d) below resolution. "
+				  "Substituting %d\n", p, TFRC_SMALLEST_P);
+			index = 0;
+		} else 				      /* 0.0001 <= p <= 0.05  */
+			index =  p/TFRC_SMALLEST_P - 1;
 
-	if (R == 0) {
-		DCCP_WARN("RTT==0, setting to 1\n");
-		R = 1; /* RTT can't be zero or else divide by zero */
-	}
+ 		f = tfrc_calc_x_lookup[index][1];
 
-	BUG_ON(index >= TFRC_CALC_X_ARRSIZE);
+	} else {	 			      /* 0.05   <  p <= 1.00  */
+		index = p/(1000000/TFRC_CALC_X_ARRSIZE) - 1;
 
-	if (p >= TFRC_CALC_X_SPLIT)
 		f = tfrc_calc_x_lookup[index][0];
-	else
-		f = tfrc_calc_x_lookup[index][1];
+	}
 
+	/* The following computes X = s/(R*f(p)) in bytes per second. Since f(p)
+	 * and R are both scaled by 1000000, we need to multiply by 1000000^2.
+	 * ==> DO NOT alter this unless you test against overflow on 32 bit   */
 	tmp1 = ((u64)s * 100000000);
 	tmp2 = ((u64)R * (u64)f);
 	do_div(tmp2, 10000);
 	do_div(tmp1, tmp2); 
-	/* Don't alter above math unless you test due to overflow on 32 bit */
 
 	return (u32)tmp1; 
 }
@@ -611,33 +664,36 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p)
 EXPORT_SYMBOL_GPL(tfrc_calc_x);
 
 /*
- * args: fvalue - function value to match
- * returns: p closest to that value
+ *  tfrc_calc_x_reverse_lookup  -  try to find p given f(p)
  *
- * both fvalue and p are multiplied by 1,000,000 to use ints
+ *  @fvalue: function value to match, scaled by 1000000
+ *  Returns closest match for p, also scaled by 1000000
  */
 u32 tfrc_calc_x_reverse_lookup(u32 fvalue)
 {
-	int ctr = 0;
-	int small;
+	int index;
 
-	if (fvalue < tfrc_calc_x_lookup[0][1])
+	if (fvalue == 0)	/* f(p) = 0  whenever  p = 0 */
 		return 0;
 
-	if (fvalue <= tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][1])
-		small = 1;
-	else if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0])
+	/* Error cases. */
+	if (fvalue < tfrc_calc_x_lookup[0][1]) {
+		DCCP_WARN("fvalue %d smaller than resolution\n", fvalue);
+		return tfrc_calc_x_lookup[0][1];
+	}
+	if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) {
+		DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue);
 		return 1000000;
-	else
-		small = 0;
-
-	while (fvalue > tfrc_calc_x_lookup[ctr][small])
-		ctr++;
+	}
 
-	if (small)
-		return TFRC_CALC_X_SPLIT * ctr / TFRC_CALC_X_ARRSIZE;
-	else
-		return 1000000 * ctr / TFRC_CALC_X_ARRSIZE;
+	if (fvalue <= tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][1]) {
+		index = tfrc_binsearch(fvalue, 1);
+		return (index + 1) * TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE;
+ 	}
+ 
+	/* else ... it must be in the coarse-grained column */
+	index = tfrc_binsearch(fvalue, 0);
+	return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE;
 }
 
 EXPORT_SYMBOL_GPL(tfrc_calc_x_reverse_lookup);
diff --git a/net/ieee80211/ieee80211_crypt_tkip.c b/net/ieee80211/ieee80211_crypt_tkip.c
index 4200ec509866..fc1f99a59732 100644
--- a/net/ieee80211/ieee80211_crypt_tkip.c
+++ b/net/ieee80211/ieee80211_crypt_tkip.c
@@ -16,6 +16,7 @@
 #include <linux/random.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <linux/mm.h>
 #include <linux/if_ether.h>
 #include <linux/if_arp.h>
 #include <asm/string.h>
diff --git a/net/ieee80211/ieee80211_crypt_wep.c b/net/ieee80211/ieee80211_crypt_wep.c
index 1b2efff11d39..7a95c3d81314 100644
--- a/net/ieee80211/ieee80211_crypt_wep.c
+++ b/net/ieee80211/ieee80211_crypt_wep.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/skbuff.h>
+#include <linux/mm.h>
 #include <asm/string.h>
 
 #include <net/ieee80211.h>
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1da3d32f8289..a35209d517ad 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -53,6 +53,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/errno.h>
+#include <linux/highmem.h>
 
 #include <linux/socket.h>
 #include <linux/sockios.h>
diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c
index 524751e031de..a4385a2180ee 100644
--- a/net/ipv4/ipvs/ip_vs_lblc.c
+++ b/net/ipv4/ipvs/ip_vs_lblc.c
@@ -45,6 +45,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
+#include <linux/jiffies.h>
 
 /* for sysctl */
 #include <linux/fs.h>
diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c
index 08990192b6ec..fe1af5d079af 100644
--- a/net/ipv4/ipvs/ip_vs_lblcr.c
+++ b/net/ipv4/ipvs/ip_vs_lblcr.c
@@ -43,6 +43,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
+#include <linux/jiffies.h>
 
 /* for sysctl */
 #include <linux/fs.h>
diff --git a/net/irda/discovery.c b/net/irda/discovery.c
index 3fefc822c1c0..89fd2a2cbca6 100644
--- a/net/irda/discovery.c
+++ b/net/irda/discovery.c
@@ -32,6 +32,7 @@
 
 #include <linux/string.h>
 #include <linux/socket.h>
+#include <linux/fs.h>
 #include <linux/seq_file.h>
 
 #include <net/irda/irda.h>
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index 8cfd076c4c12..8f1c6d65b247 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
+#include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index 9c446a72ff1f..252f11012566 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -26,6 +26,7 @@
 
 #include <linux/skbuff.h>
 #include <linux/init.h>
+#include <linux/fs.h>
 #include <linux/seq_file.h>
 
 #include <asm/byteorder.h>
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 93d97d9f9da8..eaa0f8a1adb6 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -46,6 +46,7 @@
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/socket.h>
+#include <linux/mm.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 58522fc65d33..8996584b8499 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_arp.h>
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 501c564e247f..a98de0b54d65 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -17,6 +17,7 @@
 #include <linux/seq_file.h>
 #include <linux/list.h>
 #include <linux/skbuff.h>
+#include <linux/mm.h>
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 271d2eed0699..08e68b67bbf6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -71,6 +71,7 @@
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
 #include <asm/page.h>
+#include <asm/cacheflush.h>
 #include <asm/io.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 6f97665983d2..311205ffa775 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -858,7 +858,6 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
 	int i;
 
 	xp->xfrm_nr = nr;
-	xp->family = ut->family;
 	for (i = 0; i < nr; i++, ut++) {
 		struct xfrm_tmpl *t = &xp->xfrm_vec[i];
 
@@ -876,19 +875,53 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
 	}
 }
 
+static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
+{
+	int i;
+
+	if (nr > XFRM_MAX_DEPTH)
+		return -EINVAL;
+
+	for (i = 0; i < nr; i++) {
+		/* We never validated the ut->family value, so many
+		 * applications simply leave it at zero.  The check was
+		 * never made and ut->family was ignored because all
+		 * templates could be assumed to have the same family as
+		 * the policy itself.  Now that we will have ipv4-in-ipv6
+		 * and ipv6-in-ipv4 tunnels, this is no longer true.
+		 */
+		if (!ut[i].family)
+			ut[i].family = family;
+
+		switch (ut[i].family) {
+		case AF_INET:
+			break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+		case AF_INET6:
+			break;
+#endif
+		default:
+			return -EINVAL;
+		};
+	}
+
+	return 0;
+}
+
 static int copy_from_user_tmpl(struct xfrm_policy *pol, struct rtattr **xfrma)
 {
 	struct rtattr *rt = xfrma[XFRMA_TMPL-1];
-	struct xfrm_user_tmpl *utmpl;
-	int nr;
 
 	if (!rt) {
 		pol->xfrm_nr = 0;
 	} else {
-		nr = (rt->rta_len - sizeof(*rt)) / sizeof(*utmpl);
+		struct xfrm_user_tmpl *utmpl = RTA_DATA(rt);
+		int nr = (rt->rta_len - sizeof(*rt)) / sizeof(*utmpl);
+		int err;
 
-		if (nr > XFRM_MAX_DEPTH)
-			return -EINVAL;
+		err = validate_tmpl(nr, utmpl, pol->family);
+		if (err)
+			return err;
 
 		copy_templates(pol, RTA_DATA(rt), nr);
 	}
@@ -1530,7 +1563,8 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xf
 	}
 
 	/*   build an XP */
-	xp = xfrm_policy_construct(&ua->policy, (struct rtattr **) xfrma, &err);        if (!xp) {
+	xp = xfrm_policy_construct(&ua->policy, (struct rtattr **) xfrma, &err);
+	if (!xp) {
 		kfree(x);
 		return err;
 	}
@@ -1979,7 +2013,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt,
 		return NULL;
 
 	nr = ((len - sizeof(*p)) / sizeof(*ut));
-	if (nr > XFRM_MAX_DEPTH)
+	if (validate_tmpl(nr, ut, p->sel.family))
 		return NULL;
 
 	if (p->dir > XFRM_POLICY_OUT)
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 74c0319c417e..e73ac1ab7cfd 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -496,7 +496,7 @@ static inline void avc_print_ipv6_addr(struct audit_buffer *ab,
 		audit_log_format(ab, " %s=%d", name2, ntohs(port));
 }
 
-static inline void avc_print_ipv4_addr(struct audit_buffer *ab, u32 addr,
+static inline void avc_print_ipv4_addr(struct audit_buffer *ab, __be32 addr,
 				       __be16 port, char *name1, char *name2)
 {
 	if (addr)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a29d78d3f44c..78f98fe084eb 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3537,7 +3537,7 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		goto out;
 
 	/* Handle mapped IPv4 packets arriving via IPv6 sockets */
-	if (family == PF_INET6 && skb->protocol == ntohs(ETH_P_IP))
+	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
 		family = PF_INET;
 
 	AVC_AUDIT_DATA_INIT(&ad, NET);
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 960ef18ddc41..6ed10c3d3339 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -54,12 +54,12 @@ struct avc_audit_data {
 			char *netif;
 			struct sock *sk;
 			u16 family;
-			u16 dport;
-			u16 sport;
+			__be16 dport;
+			__be16 sport;
 			union {
 				struct {
-					u32 daddr;
-					u32 saddr;
+					__be32 daddr;
+					__be32 saddr;
 				} v4;
 				struct {
 					struct in6_addr daddr;
diff --git a/sound/oss/cs46xx.c b/sound/oss/cs46xx.c
index b1c5d8286e40..147c8a951137 100644
--- a/sound/oss/cs46xx.c
+++ b/sound/oss/cs46xx.c
@@ -91,6 +91,7 @@
 #include <linux/poll.h>
 #include <linux/ac97_codec.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/sound/oss/dmabuf.c b/sound/oss/dmabuf.c
index b256c0401161..eaf69971bf92 100644
--- a/sound/oss/dmabuf.c
+++ b/sound/oss/dmabuf.c
@@ -25,6 +25,7 @@
 #define BE_CONSERVATIVE
 #define SAMPLE_ROUNDUP 0
 
+#include <linux/mm.h>
 #include "sound_config.h"
 
 #define DMAP_FREE_ON_CLOSE      0
diff --git a/sound/oss/emu10k1/audio.c b/sound/oss/emu10k1/audio.c
index cde4d59d5430..86dd23974e05 100644
--- a/sound/oss/emu10k1/audio.c
+++ b/sound/oss/emu10k1/audio.c
@@ -36,6 +36,7 @@
 #include <linux/bitops.h>
 #include <asm/io.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
 #include <linux/smp_lock.h>
 
 #include "hwaccess.h"
diff --git a/sound/oss/es1371.c b/sound/oss/es1371.c
index ddf6b0a0bca5..cc282a0cd539 100644
--- a/sound/oss/es1371.c
+++ b/sound/oss/es1371.c
@@ -130,6 +130,7 @@
 #include <linux/wait.h>
 #include <linux/dma-mapping.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include <asm/io.h>
 #include <asm/page.h>
diff --git a/sound/oss/i810_audio.c b/sound/oss/i810_audio.c
index 240cc7939b69..c3c8a720d555 100644
--- a/sound/oss/i810_audio.c
+++ b/sound/oss/i810_audio.c
@@ -101,6 +101,7 @@
 #include <linux/ac97_codec.h>
 #include <linux/bitops.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 
diff --git a/sound/oss/soundcard.c b/sound/oss/soundcard.c
index 75c5e745705f..8fb8e7f99556 100644
--- a/sound/oss/soundcard.c
+++ b/sound/oss/soundcard.c
@@ -42,6 +42,7 @@
 #include <linux/proc_fs.h>
 #include <linux/smp_lock.h>
 #include <linux/module.h>
+#include <linux/mm.h>
 
 /*
  * This ought to be moved into include/asm/dma.h
diff --git a/sound/oss/sscape.c b/sound/oss/sscape.c
index 51f2fa615413..30c36d1f35d7 100644
--- a/sound/oss/sscape.c
+++ b/sound/oss/sscape.c
@@ -39,6 +39,7 @@
 #include <linux/ioport.h>
 #include <linux/delay.h>
 #include <linux/proc_fs.h>
+#include <linux/mm.h>
 #include <linux/spinlock.h>
 
 #include "coproc.h"
diff --git a/sound/oss/trident.c b/sound/oss/trident.c
index 7a363a178afd..6b1f8c9cdcf8 100644
--- a/sound/oss/trident.c
+++ b/sound/oss/trident.c
@@ -216,6 +216,7 @@
 #include <linux/gameport.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>