Merge tag 'mfd-for-linus-3.6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6

Pull mfd fixes from Samuel Ortiz:
 "This is the remaining MFD fixes for 3.6, with 5 pending fixes:

   - A tps65217 build error fix.
   - A lcp_ich regression fix caused by the MFD driver failing to
     initialize the watchdog sub device due to ACPI conflicts.
   - 2 MAX77693 interrupt handling bug fixes.
   - An MFD core fix, adding an IRQ domain argument to the MFD device
     addition API in order to prevent silent and potentially harmful
     remapping behaviour changes for drivers supporting non-DT
     platforms."

* tag 'mfd-for-linus-3.6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6:
  mfd: MAX77693: Fix NULL pointer error when initializing irqs
  mfd: MAX77693: Fix interrupt handling bug
  mfd: core: Push irqdomain mapping out into devices
  mfd: lpc_ich: Fix a 3.5 kernel regression for iTCO_wdt driver
  mfd: Move tps65217 regulator plat data handling to regulator
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 34f5110..dff1f48 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -210,3 +210,15 @@
 		firmware assigned instance number of the PCI
 		device that can help in understanding the firmware
 		intended order of the PCI device.
+
+What:		/sys/bus/pci/devices/.../d3cold_allowed
+Date:		July 2012
+Contact:	Huang Ying <ying.huang@intel.com>
+Description:
+		d3cold_allowed is bit to control whether the corresponding PCI
+		device can be put into D3Cold state.  If it is cleared, the
+		device will never be put into D3Cold state.  If it is set, the
+		device may be put into D3Cold state if other requirements are
+		satisfied too.  Reading this attribute will show the current
+		value of d3cold_allowed bit.  Writing this attribute will set
+		the value of d3cold_allowed bit.
diff --git a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
index 814b013..b31e782 100644
--- a/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-ideapad-laptop
@@ -5,4 +5,15 @@
 Description:
 		Control the power of camera module. 1 means on, 0 means off.
 
+What:		/sys/devices/platform/ideapad/fan_mode
+Date:		June 2012
+KernelVersion:	3.6
+Contact:	"Maxim Mikityanskiy <maxtram95@gmail.com>"
+Description:
+		Change fan mode
+		There are four available modes:
+			* 0 -> Super Silent Mode
+			* 1 -> Standard Mode
+			* 2 -> Dust Cleaning
+			* 4 -> Efficient Thermal Dissipation Mode
 
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-tuner.xml b/Documentation/DocBook/media/v4l/vidioc-g-tuner.xml
index 7203951..701138f 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-tuner.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-tuner.xml
@@ -125,7 +125,7 @@
 <constant>V4L2_TUNER_CAP_NORM</constant> flags can't be used.</para>
 <para>If multiple frequency bands are supported, then
 <structfield>capability</structfield> is the union of all
-<structfield>capability></structfield> fields of each &v4l2-frequency-band;.
+<structfield>capability</structfield> fields of each &v4l2-frequency-band;.
 </para></entry>
 	  </row>
 	  <row>
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index d111e3b..d18ecd8 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -3,15 +3,21 @@
 biodoc.txt
 	- Notes on the Generic Block Layer Rewrite in Linux 2.5
 capability.txt
-	- Generic Block Device Capability (/sys/block/<disk>/capability)
+	- Generic Block Device Capability (/sys/block/<device>/capability)
+cfq-iosched.txt
+	- CFQ IO scheduler tunables
+data-integrity.txt
+	- Block data integrity
 deadline-iosched.txt
 	- Deadline IO scheduler tunables
 ioprio.txt
 	- Block io priorities (in CFQ scheduler)
+queue-sysfs.txt
+	- Queue's sysfs entries
 request.txt
 	- The members of struct request (in include/linux/blkdev.h)
 stat.txt
-	- Block layer statistics in /sys/block/<dev>/stat
+	- Block layer statistics in /sys/block/<device>/stat
 switching-sched.txt
 	- Switching I/O schedulers at runtime
 writeback_cache_control.txt
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
index 6d670f5..d89b4fe 100644
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@@ -1,3 +1,14 @@
+CFQ (Complete Fairness Queueing)
+===============================
+
+The main aim of CFQ scheduler is to provide a fair allocation of the disk
+I/O bandwidth for all the processes which requests an I/O operation.
+
+CFQ maintains the per process queue for the processes which request I/O
+operation(syncronous requests). In case of asynchronous requests, all the
+requests from all the processes are batched together according to their
+process's I/O priority.
+
 CFQ ioscheduler tunables
 ========================
 
@@ -25,6 +36,72 @@
 controller or for storage arrays), setting slice_idle=0 might end up in better
 throughput and acceptable latencies.
 
+back_seek_max
+-------------
+This specifies, given in Kbytes, the maximum "distance" for backward seeking.
+The distance is the amount of space from the current head location to the
+sectors that are backward in terms of distance.
+
+This parameter allows the scheduler to anticipate requests in the "backward"
+direction and consider them as being the "next" if they are within this
+distance from the current head location.
+
+back_seek_penalty
+-----------------
+This parameter is used to compute the cost of backward seeking. If the
+backward distance of request is just 1/back_seek_penalty from a "front"
+request, then the seeking cost of two requests is considered equivalent.
+
+So scheduler will not bias toward one or the other request (otherwise scheduler
+will bias toward front request). Default value of back_seek_penalty is 2.
+
+fifo_expire_async
+-----------------
+This parameter is used to set the timeout of asynchronous requests. Default
+value of this is 248ms.
+
+fifo_expire_sync
+----------------
+This parameter is used to set the timeout of synchronous requests. Default
+value of this is 124ms. In case to favor synchronous requests over asynchronous
+one, this value should be decreased relative to fifo_expire_async.
+
+slice_async
+-----------
+This parameter is same as of slice_sync but for asynchronous queue. The
+default value is 40ms.
+
+slice_async_rq
+--------------
+This parameter is used to limit the dispatching of asynchronous request to
+device request queue in queue's slice time. The maximum number of request that
+are allowed to be dispatched also depends upon the io priority. Default value
+for this is 2.
+
+slice_sync
+----------
+When a queue is selected for execution, the queues IO requests are only
+executed for a certain amount of time(time_slice) before switching to another
+queue. This parameter is used to calculate the time slice of synchronous
+queue.
+
+time_slice is computed using the below equation:-
+time_slice = slice_sync + (slice_sync/5 * (4 - prio)). To increase the
+time_slice of synchronous queue, increase the value of slice_sync. Default
+value is 100ms.
+
+quantum
+-------
+This specifies the number of request dispatched to the device queue. In a
+queue's time slice, a request will not be dispatched if the number of request
+in the device exceeds this parameter. This parameter is used for synchronous
+request.
+
+In case of storage with several disk, this setting can limit the parallel
+processing of request. Therefore, increasing the value can imporve the
+performace although this can cause the latency of some I/O to increase due
+to more number of requests.
+
 CFQ IOPS Mode for group scheduling
 ===================================
 Basic CFQ design is to provide priority based time slices. Higher priority
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index 6518a55..e54ac1d 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -9,20 +9,71 @@
 Files denoted with a RO postfix are readonly and the RW postfix means
 read-write.
 
+add_random (RW)
+----------------
+This file allows to trun off the disk entropy contribution. Default
+value of this file is '1'(on).
+
+discard_granularity (RO)
+-----------------------
+This shows the size of internal allocation of the device in bytes, if
+reported by the device. A value of '0' means device does not support
+the discard functionality.
+
+discard_max_bytes (RO)
+----------------------
+Devices that support discard functionality may have internal limits on
+the number of bytes that can be trimmed or unmapped in a single operation.
+The discard_max_bytes parameter is set by the device driver to the maximum
+number of bytes that can be discarded in a single operation. Discard
+requests issued to the device must not exceed this limit. A discard_max_bytes
+value of 0 means that the device does not support discard functionality.
+
+discard_zeroes_data (RO)
+------------------------
+When read, this file will show if the discarded block are zeroed by the
+device or not. If its value is '1' the blocks are zeroed otherwise not.
+
 hw_sector_size (RO)
 -------------------
 This is the hardware sector size of the device, in bytes.
 
+iostats (RW)
+-------------
+This file is used to control (on/off) the iostats accounting of the
+disk.
+
+logical_block_size (RO)
+-----------------------
+This is the logcal block size of the device, in bytes.
+
 max_hw_sectors_kb (RO)
 ----------------------
 This is the maximum number of kilobytes supported in a single data transfer.
 
+max_integrity_segments (RO)
+---------------------------
+When read, this file shows the max limit of integrity segments as
+set by block layer which a hardware controller can handle.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow
 for a filesystem request. Must be smaller than or equal to the maximum
 size allowed by the hardware.
 
+max_segments (RO)
+-----------------
+Maximum number of segments of the device.
+
+max_segment_size (RO)
+---------------------
+Maximum segment size of the device.
+
+minimum_io_size (RO)
+--------------------
+This is the smallest preferred io size reported by the device.
+
 nomerges (RW)
 -------------
 This enables the user to disable the lookup logic involved with IO
@@ -45,11 +96,24 @@
 each request queue may have upto N request pools, each independently
 regulated by nr_requests.
 
+optimal_io_size (RO)
+--------------------
+This is the optimal io size reported by the device.
+
+physical_block_size (RO)
+------------------------
+This is the physical block size of device, in bytes.
+
 read_ahead_kb (RW)
 ------------------
 Maximum number of kilobytes to read-ahead for filesystems on this block
 device.
 
+rotational (RW)
+---------------
+This file is used to stat if the device is of rotational type or
+non-rotational type.
+
 rq_affinity (RW)
 ----------------
 If this option is '1', the block layer will migrate request completions to the
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index 70cd49b..1dd6225 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -10,8 +10,8 @@
 - compatible : Should be "fsl,<chip>-esdhc"
 
 Optional properties:
-- fsl,cd-internal : Indicate to use controller internal card detection
-- fsl,wp-internal : Indicate to use controller internal write protection
+- fsl,cd-controller : Indicate to use controller internal card detection
+- fsl,wp-controller : Indicate to use controller internal write protection
 
 Examples:
 
@@ -19,8 +19,8 @@
 	compatible = "fsl,imx51-esdhc";
 	reg = <0x70004000 0x4000>;
 	interrupts = <1>;
-	fsl,cd-internal;
-	fsl,wp-internal;
+	fsl,cd-controller;
+	fsl,wp-controller;
 };
 
 esdhc@70008000 {
diff --git a/Documentation/devicetree/bindings/regulator/tps6586x.txt b/Documentation/devicetree/bindings/regulator/tps6586x.txt
index d156e1b..da80c2a 100644
--- a/Documentation/devicetree/bindings/regulator/tps6586x.txt
+++ b/Documentation/devicetree/bindings/regulator/tps6586x.txt
@@ -9,9 +9,9 @@
 - regulators: list of regulators provided by this controller, must have
   property "regulator-compatible" to match their hardware counterparts:
   sm[0-2], ldo[0-9] and ldo_rtc
-- sm0-supply: The input supply for the SM0.
-- sm1-supply: The input supply for the SM1.
-- sm2-supply: The input supply for the SM2.
+- vin-sm0-supply: The input supply for the SM0.
+- vin-sm1-supply: The input supply for the SM1.
+- vin-sm2-supply: The input supply for the SM2.
 - vinldo01-supply: The input supply for the LDO1 and LDO2
 - vinldo23-supply: The input supply for the LDO2 and LDO3
 - vinldo4-supply: The input supply for the LDO4
@@ -30,9 +30,9 @@
 		#gpio-cells = <2>;
 		gpio-controller;
 
-		sm0-supply = <&some_reg>;
-		sm1-supply = <&some_reg>;
-		sm2-supply = <&some_reg>;
+		vin-sm0-supply = <&some_reg>;
+		vin-sm1-supply = <&some_reg>;
+		vin-sm2-supply = <&some_reg>;
 		vinldo01-supply = <...>;
 		vinldo23-supply = <...>;
 		vinldo4-supply = <...>;
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index afaff31..f4d8c71 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -579,7 +579,7 @@
 ----------------------------
 
 What:	at91-mci driver ("CONFIG_MMC_AT91")
-When:	3.7
+When:	3.8
 Why:	There are two mci drivers: at91-mci and atmel-mci. The PDC support
 	was added to atmel-mci as a first step to support more chips.
 	Then at91-mci was kept only for old IP versions (on at91rm9200 and
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index ead764b..de1e6c4 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -137,6 +137,17 @@
 		 without doing anything or remount the partition in
 		 read-only mode (default behavior).
 
+discard       -- If set, issues discard/TRIM commands to the block
+		 device when blocks are freed. This is useful for SSD devices
+		 and sparse/thinly-provisoned LUNs.
+
+nfs           -- This option maintains an index (cache) of directory
+		 inodes by i_logstart which is used by the nfs-related code to
+		 improve look-ups.
+
+		 Enable this only if you want to export the FAT filesystem
+		 over NFS
+
 <bool>: 0,1,yes,no,true,false
 
 TODO
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 615142d..157416e 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -21,6 +21,7 @@
   * Intel DH89xxCC (PCH)
   * Intel Panther Point (PCH)
   * Intel Lynx Point (PCH)
+  * Intel Lynx Point-LP (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/networking/netconsole.txt b/Documentation/networking/netconsole.txt
index 8d02207..2e9e0ae2 100644
--- a/Documentation/networking/netconsole.txt
+++ b/Documentation/networking/netconsole.txt
@@ -51,8 +51,23 @@
 initialized and attempts to bring up the supplied dev at the supplied
 address.
 
-The remote host can run either 'netcat -u -l -p <port>',
-'nc -l -u <port>' or syslogd.
+The remote host has several options to receive the kernel messages,
+for example:
+
+1) syslogd
+
+2) netcat
+
+   On distributions using a BSD-based netcat version (e.g. Fedora,
+   openSUSE and Ubuntu) the listening port must be specified without
+   the -p switch:
+
+   'nc -u -l -p <port>' / 'nc -u -l <port>' or
+   'netcat -u -l -p <port>' / 'netcat -u -l <port>'
+
+3) socat
+
+   'socat udp-recv:<port> -'
 
 Dynamic reconfiguration:
 ========================
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index e40f4b4..1479aca 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -840,9 +840,9 @@
 
 static struct pinctrl_map __initdata mapping[] = {
 	PIN_MAP_MUX_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", "i2c0"),
-	PIN_MAP_MUX_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", i2c_grp_configs),
-	PIN_MAP_MUX_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0scl", i2c_pin_configs),
-	PIN_MAP_MUX_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0sda", i2c_pin_configs),
+	PIN_MAP_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", i2c_grp_configs),
+	PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0scl", i2c_pin_configs),
+	PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0sda", i2c_pin_configs),
 };
 
 Finally, some devices expect the mapping table to contain certain specific
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index f8551b3..4ac359b 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -299,11 +299,17 @@
 *******************************************************************
 
 /*
- * hugepage-shm:  see Documentation/vm/hugepage-shm.c
+ * map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
  */
 
 *******************************************************************
 
 /*
- * hugepage-mmap:  see Documentation/vm/hugepage-mmap.c
+ * hugepage-shm:  see tools/testing/selftests/vm/hugepage-shm.c
+ */
+
+*******************************************************************
+
+/*
+ * hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
  */
diff --git a/Documentation/w1/slaves/w1_therm b/Documentation/w1/slaves/w1_therm
index 0403aaa..874a8ca 100644
--- a/Documentation/w1/slaves/w1_therm
+++ b/Documentation/w1/slaves/w1_therm
@@ -3,6 +3,7 @@
 
 Supported chips:
   * Maxim ds18*20 based temperature sensors.
+  * Maxim ds1825 based temperature sensors.
 
 Author: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
 
@@ -15,6 +16,7 @@
 W1_THERM_DS18S20	0x10
 W1_THERM_DS1822		0x22
 W1_THERM_DS18B20	0x28
+W1_THERM_DS1825		0x3B
 
 Support is provided through the sysfs w1_slave file.  Each open and
 read sequence will initiate a temperature conversion then provide two
diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c
index 73ff5cc..3da8229 100644
--- a/Documentation/watchdog/src/watchdog-test.c
+++ b/Documentation/watchdog/src/watchdog-test.c
@@ -31,7 +31,7 @@
  * or "-e" to enable the card.
  */
 
-void term(int sig)
+static void term(int sig)
 {
     close(fd);
     fprintf(stderr, "Stopping watchdog ticks...\n");
diff --git a/MAINTAINERS b/MAINTAINERS
index 61ad79e..53cc13c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2217,7 +2217,7 @@
 F:	drivers/scsi/tmscsim.*
 
 DC395x SCSI driver
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 M:	Ali Akcaagac <aliakc@web.de>
 M:	Jamie Lenehan <lenehan@twibble.org>
 W:	http://twibble.org/dist/dc395x/
@@ -3388,7 +3388,7 @@
 L:	linux-i2c@vger.kernel.org
 W:	http://i2c.wiki.kernel.org/
 T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-i2c/
-T:	git git://git.fluff.org/bjdooks/linux.git
+T:	git git://git.pengutronix.de/git/wsa/linux.git
 S:	Maintained
 F:	Documentation/i2c/
 F:	drivers/i2c/
@@ -4537,7 +4537,7 @@
 F:	arch/microblaze/
 
 MICROTEK X6 SCANNER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 S:	Maintained
 F:	drivers/usb/image/microtek.*
 
@@ -7076,7 +7076,7 @@
 F:	include/mtd/ubi-user.h
 
 USB ACM DRIVER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	Documentation/usb/acm.txt
@@ -7097,7 +7097,7 @@
 F:	drivers/block/ub.c
 
 USB CDC ETHERNET DRIVER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/net/usb/cdc_*.c
@@ -7170,7 +7170,7 @@
 F:	include/linux/usb/isp116x.h
 
 USB KAWASAKI LSI DRIVER
-M:	Oliver Neukum <oliver@neukum.name>
+M:	Oliver Neukum <oliver@neukum.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/serial/kl5kusb105.*
@@ -7288,6 +7288,12 @@
 S:	Supported
 F:	drivers/usb/serial/whiteheat*
 
+USB SMSC75XX ETHERNET DRIVER
+M:	Steve Glendinning <steve.glendinning@shawell.net>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/usb/smsc75xx.*
+
 USB SMSC95XX ETHERNET DRIVER
 M:	Steve Glendinning <steve.glendinning@shawell.net>
 L:	netdev@vger.kernel.org
@@ -7670,23 +7676,28 @@
 F:	Documentation/hwmon/wm83??
 F:	arch/arm/mach-s3c64xx/mach-crag6410*
 F:	drivers/clk/clk-wm83*.c
+F:	drivers/extcon/extcon-arizona.c
 F:	drivers/leds/leds-wm83*.c
 F:	drivers/gpio/gpio-*wm*.c
+F:	drivers/gpio/gpio-arizona.c
 F:	drivers/hwmon/wm83??-hwmon.c
 F:	drivers/input/misc/wm831x-on.c
 F:	drivers/input/touchscreen/wm831x-ts.c
 F:	drivers/input/touchscreen/wm97*.c
-F:	drivers/mfd/wm8*.c
+F:	drivers/mfd/arizona*
+F:	drivers/mfd/wm*.c
 F:	drivers/power/wm83*.c
 F:	drivers/rtc/rtc-wm83*.c
 F:	drivers/regulator/wm8*.c
 F:	drivers/video/backlight/wm83*_bl.c
 F:	drivers/watchdog/wm83*_wdt.c
+F:	include/linux/mfd/arizona/
 F:	include/linux/mfd/wm831x/
 F:	include/linux/mfd/wm8350/
 F:	include/linux/mfd/wm8400*
 F:	include/linux/wm97xx.h
 F:	include/sound/wm????.h
+F:	sound/soc/codecs/arizona.?
 F:	sound/soc/codecs/wm*
 
 WORKQUEUE
diff --git a/Makefile b/Makefile
index 9cc77ac..0f66f14 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 6
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc5
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index d5b9b5e..9944ded 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -18,6 +18,8 @@
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 3bb7ffe..c2cbe4f 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -14,8 +14,8 @@
  */
 
 
-#define ATOMIC_INIT(i)		( (atomic_t) { (i) } )
-#define ATOMIC64_INIT(i)	( (atomic64_t) { (i) } )
+#define ATOMIC_INIT(i)		{ (i) }
+#define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic64_read(v)	(*(volatile long *)&(v)->counter)
diff --git a/arch/alpha/include/asm/fpu.h b/arch/alpha/include/asm/fpu.h
index db00f78..e477bcd 100644
--- a/arch/alpha/include/asm/fpu.h
+++ b/arch/alpha/include/asm/fpu.h
@@ -1,7 +1,9 @@
 #ifndef __ASM_ALPHA_FPU_H
 #define __ASM_ALPHA_FPU_H
 
+#ifdef __KERNEL__
 #include <asm/special_insns.h>
+#endif
 
 /*
  * Alpha floating-point control register defines:
diff --git a/arch/alpha/include/asm/ptrace.h b/arch/alpha/include/asm/ptrace.h
index fd698a1..b87755a 100644
--- a/arch/alpha/include/asm/ptrace.h
+++ b/arch/alpha/include/asm/ptrace.h
@@ -76,7 +76,10 @@
 #define task_pt_regs(task) \
   ((struct pt_regs *) (task_stack_page(task) + 2*PAGE_SIZE) - 1)
 
-#define force_successful_syscall_return() (task_pt_regs(current)->r0 = 0)
+#define current_pt_regs() \
+  ((struct pt_regs *) ((char *)current_thread_info() + 2*PAGE_SIZE) - 1)
+
+#define force_successful_syscall_return() (current_pt_regs()->r0 = 0)
 
 #endif
 
diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h
index dcb221a..7d2f75b 100644
--- a/arch/alpha/include/asm/socket.h
+++ b/arch/alpha/include/asm/socket.h
@@ -76,9 +76,11 @@
 /* Instruct lower device to use last 4-bytes of skb data as FCS */
 #define SO_NOFCS		43
 
+#ifdef __KERNEL__
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
 #define SOCK_NONBLOCK	0x40000000
+#endif /* __KERNEL__ */
 
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index b49ec2f..766fdfd 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -433,36 +433,12 @@
 #undef __module_address
 #undef __module_call
 
-/* Returns: -EFAULT if exception before terminator, N if the entire
-   buffer filled, else strlen.  */
+#define user_addr_max() \
+        (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
 
-extern long __strncpy_from_user(char *__to, const char __user *__from, long __to_len);
-
-extern inline long
-strncpy_from_user(char *to, const char __user *from, long n)
-{
-	long ret = -EFAULT;
-	if (__access_ok((unsigned long)from, 0, get_fs()))
-		ret = __strncpy_from_user(to, from, n);
-	return ret;
-}
-
-/* Returns: 0 if bad, string length+1 (memory size) of string if ok */
-extern long __strlen_user(const char __user *);
-
-extern inline long strlen_user(const char __user *str)
-{
-	return access_ok(VERIFY_READ,str,0) ? __strlen_user(str) : 0;
-}
-
-/* Returns: 0 if exception before NUL or reaching the supplied limit (N),
- * a value greater than N if the limit would be exceeded, else strlen.  */
-extern long __strnlen_user(const char __user *, long);
-
-extern inline long strnlen_user(const char __user *str, long n)
-{
-	return access_ok(VERIFY_READ,str,0) ? __strnlen_user(str, n) : 0;
-}
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
 
 /*
  * About the exception table:
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index 633b23b..a31a78e 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -465,10 +465,12 @@
 #define __NR_setns			501
 #define __NR_accept4			502
 #define __NR_sendmmsg			503
+#define __NR_process_vm_readv		504
+#define __NR_process_vm_writev		505
 
 #ifdef __KERNEL__
 
-#define NR_SYSCALLS			504
+#define NR_SYSCALLS			506
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
diff --git a/arch/alpha/include/asm/word-at-a-time.h b/arch/alpha/include/asm/word-at-a-time.h
new file mode 100644
index 0000000..6b340d0
--- /dev/null
+++ b/arch/alpha/include/asm/word-at-a-time.h
@@ -0,0 +1,55 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+#include <asm/compiler.h>
+
+/*
+ * word-at-a-time interface for Alpha.
+ */
+
+/*
+ * We do not use the word_at_a_time struct on Alpha, but it needs to be
+ * implemented to humour the generic code.
+ */
+struct word_at_a_time {
+	const unsigned long unused;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { 0 }
+
+/* Return nonzero if val has a zero */
+static inline unsigned long has_zero(unsigned long val, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long zero_locations = __kernel_cmpbge(0, val);
+	*bits = zero_locations;
+	return zero_locations;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long val, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+#define create_zero_mask(bits) (bits)
+
+static inline unsigned long find_zero(unsigned long bits)
+{
+#if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67)
+	/* Simple if have CIX instructions */
+	return __kernel_cttz(bits);
+#else
+	unsigned long t1, t2, t3;
+	/* Retain lowest set bit only */
+	bits &= -bits;
+	/* Binary search for lowest set bit */
+	t1 = bits & 0xf0;
+	t2 = bits & 0xcc;
+	t3 = bits & 0xaa;
+	if (t1) t1 = 4;
+	if (t2) t2 = 2;
+	if (t3) t3 = 1;
+	return t1 + t2 + t3;
+#endif
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c
index d96e742..15fa821 100644
--- a/arch/alpha/kernel/alpha_ksyms.c
+++ b/arch/alpha/kernel/alpha_ksyms.c
@@ -52,7 +52,6 @@
 
 /* entry.S */
 EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(kernel_execve);
 
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_tcpudp_magic);
@@ -74,8 +73,6 @@
  */
 EXPORT_SYMBOL(__copy_user);
 EXPORT_SYMBOL(__do_clear_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(__strnlen_user);
 
 /* 
  * SMP-specific symbols.
diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index 6d159ce..ec0da05 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -663,58 +663,6 @@
 	br	ret_to_kernel
 .end kernel_thread
 
-/*
- * kernel_execve(path, argv, envp)
- */
-	.align	4
-	.globl	kernel_execve
-	.ent	kernel_execve
-kernel_execve:
-	/* We can be called from a module.  */
-	ldgp	$gp, 0($27)
-	lda	$sp, -(32+SIZEOF_PT_REGS+8)($sp)
-	.frame	$sp, 32+SIZEOF_PT_REGS+8, $26, 0
-	stq	$26, 0($sp)
-	stq	$16, 8($sp)
-	stq	$17, 16($sp)
-	stq	$18, 24($sp)
-	.prologue 1
-
-	lda	$16, 32($sp)
-	lda	$17, 0
-	lda	$18, SIZEOF_PT_REGS
-	bsr	$26, memset		!samegp
-
-	/* Avoid the HAE being gratuitously wrong, which would cause us
-	   to do the whole turn off interrupts thing and restore it.  */
-	ldq	$2, alpha_mv+HAE_CACHE
-	stq	$2, 152+32($sp)
-
-	ldq	$16, 8($sp)
-	ldq	$17, 16($sp)
-	ldq	$18, 24($sp)
-	lda	$19, 32($sp)
-	bsr	$26, do_execve		!samegp
-
-	ldq	$26, 0($sp)
-	bne	$0, 1f			/* error! */
-
-	/* Move the temporary pt_regs struct from its current location
-	   to the top of the kernel stack frame.  See copy_thread for
-	   details for a normal process.  */
-	lda	$16, 0x4000 - SIZEOF_PT_REGS($8)
-	lda	$17, 32($sp)
-	lda	$18, SIZEOF_PT_REGS
-	bsr	$26, memmove		!samegp
-
-	/* Take that over as our new stack frame and visit userland!  */
-	lda	$sp, 0x4000 - SIZEOF_PT_REGS($8)
-	br	$31, ret_from_sys_call
-
-1:	lda	$sp, 32+SIZEOF_PT_REGS+8($sp)
-	ret
-.end kernel_execve
-
 
 /*
  * Special system calls.  Most of these are special in that they either
@@ -797,115 +745,6 @@
 .end sys_rt_sigreturn
 
 	.align	4
-	.globl	sys_sethae
-	.ent	sys_sethae
-sys_sethae:
-	.prologue 0
-	stq	$16, 152($sp)
-	ret
-.end sys_sethae
-
-	.align	4
-	.globl	osf_getpriority
-	.ent	osf_getpriority
-osf_getpriority:
-	lda	$sp, -16($sp)
-	stq	$26, 0($sp)
-	.prologue 0
-
-	jsr	$26, sys_getpriority
-
-	ldq	$26, 0($sp)
-	blt	$0, 1f
-
-	/* Return value is the unbiased priority, i.e. 20 - prio.
-	   This does result in negative return values, so signal
-	   no error by writing into the R0 slot.  */
-	lda	$1, 20
-	stq	$31, 16($sp)
-	subl	$1, $0, $0
-	unop
-
-1:	lda	$sp, 16($sp)
-	ret
-.end osf_getpriority
-
-	.align	4
-	.globl	sys_getxuid
-	.ent	sys_getxuid
-sys_getxuid:
-	.prologue 0
-	ldq	$2, TI_TASK($8)
-	ldq	$3, TASK_CRED($2)
-	ldl	$0, CRED_UID($3)
-	ldl	$1, CRED_EUID($3)
-	stq	$1, 80($sp)
-	ret
-.end sys_getxuid
-
-	.align	4
-	.globl	sys_getxgid
-	.ent	sys_getxgid
-sys_getxgid:
-	.prologue 0
-	ldq	$2, TI_TASK($8)
-	ldq	$3, TASK_CRED($2)
-	ldl	$0, CRED_GID($3)
-	ldl	$1, CRED_EGID($3)
-	stq	$1, 80($sp)
-	ret
-.end sys_getxgid
-
-	.align	4
-	.globl	sys_getxpid
-	.ent	sys_getxpid
-sys_getxpid:
-	.prologue 0
-	ldq	$2, TI_TASK($8)
-
-	/* See linux/kernel/timer.c sys_getppid for discussion
-	   about this loop.  */
-	ldq	$3, TASK_GROUP_LEADER($2)
-	ldq	$4, TASK_REAL_PARENT($3)
-	ldl	$0, TASK_TGID($2)
-1:	ldl	$1, TASK_TGID($4)
-#ifdef CONFIG_SMP
-	mov	$4, $5
-	mb
-	ldq	$3, TASK_GROUP_LEADER($2)
-	ldq	$4, TASK_REAL_PARENT($3)
-	cmpeq	$4, $5, $5
-	beq	$5, 1b
-#endif
-	stq	$1, 80($sp)
-	ret
-.end sys_getxpid
-
-	.align	4
-	.globl	sys_alpha_pipe
-	.ent	sys_alpha_pipe
-sys_alpha_pipe:
-	lda	$sp, -16($sp)
-	stq	$26, 0($sp)
-	.prologue 0
-
-	mov	$31, $17
-	lda	$16, 8($sp)
-	jsr	$26, do_pipe_flags
-
-	ldq	$26, 0($sp)
-	bne	$0, 1f
-
-	/* The return values are in $0 and $20.  */
-	ldl	$1, 12($sp)
-	ldl	$0, 8($sp)
-
-	stq	$1, 80+16($sp)
-1:	lda	$sp, 16($sp)
-	ret
-.end sys_alpha_pipe
-
-	.align	4
 	.globl	sys_execve
 	.ent	sys_execve
 sys_execve:
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 98a1036..bc1acdd 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1404,3 +1404,52 @@
 }
 
 #endif
+
+SYSCALL_DEFINE2(osf_getpriority, int, which, int, who)
+{
+	int prio = sys_getpriority(which, who);
+	if (prio >= 0) {
+		/* Return value is the unbiased priority, i.e. 20 - prio.
+		   This does result in negative return values, so signal
+		   no error */
+		force_successful_syscall_return();
+		prio = 20 - prio;
+	}
+	return prio;
+}
+
+SYSCALL_DEFINE0(getxuid)
+{
+	current_pt_regs()->r20 = sys_geteuid();
+	return sys_getuid();
+}
+
+SYSCALL_DEFINE0(getxgid)
+{
+	current_pt_regs()->r20 = sys_getegid();
+	return sys_getgid();
+}
+
+SYSCALL_DEFINE0(getxpid)
+{
+	current_pt_regs()->r20 = sys_getppid();
+	return sys_getpid();
+}
+
+SYSCALL_DEFINE0(alpha_pipe)
+{
+	int fd[2];
+	int res = do_pipe_flags(fd, 0);
+	if (!res) {
+		/* The return values are in $0 and $20.  */
+		current_pt_regs()->r20 = fd[1];
+		res = fd[0];
+	}
+	return res;
+}
+
+SYSCALL_DEFINE1(sethae, unsigned long, val)
+{
+	current_pt_regs()->hae = val;
+	return 0;
+}
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 153d3fc..d6fde98 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -455,3 +455,22 @@
 	}
 	return pc;
 }
+
+int kernel_execve(const char *path, const char *const argv[], const char *const envp[])
+{
+	/* Avoid the HAE being gratuitously wrong, which would cause us
+	   to do the whole turn off interrupts thing and restore it.  */
+	struct pt_regs regs = {.hae = alpha_mv.hae_cache};
+	int err = do_execve(path, argv, envp, &regs);
+	if (!err) {
+		struct pt_regs *p = current_pt_regs();
+		/* copy regs to normal position and off to userland we go... */
+		*p = regs;
+		__asm__ __volatile__ (
+			"mov	%0, $sp;"
+			"br	$31, ret_from_sys_call"
+			: : "r"(p));
+	}
+	return err;
+}
+EXPORT_SYMBOL(kernel_execve);
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index 8783523..2ac6b45 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -111,7 +111,7 @@
 	.quad sys_socket
 	.quad sys_connect
 	.quad sys_accept
-	.quad osf_getpriority			/* 100 */
+	.quad sys_osf_getpriority			/* 100 */
 	.quad sys_send
 	.quad sys_recv
 	.quad sys_sigreturn
@@ -522,6 +522,8 @@
 	.quad sys_setns
 	.quad sys_accept4
 	.quad sys_sendmmsg
+	.quad sys_process_vm_readv
+	.quad sys_process_vm_writev		/* 505 */
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object
diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile
index c0a83ab..5966074 100644
--- a/arch/alpha/lib/Makefile
+++ b/arch/alpha/lib/Makefile
@@ -31,8 +31,6 @@
 	$(ev6-y)memchr.o \
 	$(ev6-y)copy_user.o \
 	$(ev6-y)clear_user.o \
-	$(ev6-y)strncpy_from_user.o \
-	$(ev67-y)strlen_user.o \
 	$(ev6-y)csum_ipv6_magic.o \
 	$(ev6-y)clear_page.o \
 	$(ev6-y)copy_page.o \
diff --git a/arch/alpha/lib/ev6-strncpy_from_user.S b/arch/alpha/lib/ev6-strncpy_from_user.S
deleted file mode 100644
index d2e2817..0000000
--- a/arch/alpha/lib/ev6-strncpy_from_user.S
+++ /dev/null
@@ -1,424 +0,0 @@
-/*
- * arch/alpha/lib/ev6-strncpy_from_user.S
- * 21264 version contributed by Rick Gorton <rick.gorton@alpha-processor.com>
- *
- * Just like strncpy except in the return value:
- *
- * -EFAULT       if an exception occurs before the terminator is copied.
- * N             if the buffer filled.
- *
- * Otherwise the length of the string is returned.
- *
- * Much of the information about 21264 scheduling/coding comes from:
- *	Compiler Writer's Guide for the Alpha 21264
- *	abbreviated as 'CWG' in other comments here
- *	ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
- * Scheduling notation:
- *	E	- either cluster
- *	U	- upper subcluster; U0 - subcluster U0; U1 - subcluster U1
- *	L	- lower subcluster; L0 - subcluster L0; L1 - subcluster L1
- * A bunch of instructions got moved and temp registers were changed
- * to aid in scheduling.  Control flow was also re-arranged to eliminate
- * branches, and to provide longer code sequences to enable better scheduling.
- * A total rewrite (using byte load/stores for start & tail sequences)
- * is desirable, but very difficult to do without a from-scratch rewrite.
- * Save that for the future.
- */
-
-
-#include <asm/errno.h>
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda $31, $exception-99b($0); 	\
-	.previous
-
-
-	.set noat
-	.set noreorder
-	.text
-
-	.globl __strncpy_from_user
-	.ent __strncpy_from_user
-	.frame $30, 0, $26
-	.prologue 0
-
-	.align 4
-__strncpy_from_user:
-	and	a0, 7, t3	# E : find dest misalignment
-	beq	a2, $zerolength	# U :
-
-	/* Are source and destination co-aligned?  */
-	mov	a0, v0		# E : save the string start
-	xor	a0, a1, t4	# E :
-	EX( ldq_u t1, 0(a1) )	# L : Latency=3 load first quadword
-	ldq_u	t0, 0(a0)	# L : load first (partial) aligned dest quadword
-
-	addq	a2, t3, a2	# E : bias count by dest misalignment
-	subq	a2, 1, a3	# E :
-	addq	zero, 1, t10	# E :
-	and	t4, 7, t4	# E : misalignment between the two
-
-	and	a3, 7, t6	# E : number of tail bytes
-	sll	t10, t6, t10	# E : t10 = bitmask of last count byte
-	bne	t4, $unaligned	# U :
-	lda	t2, -1		# E : build a mask against false zero
-
-	/*
-	 * We are co-aligned; take care of a partial first word.
-	 * On entry to this basic block:
-	 * t0 == the first destination word for masking back in
-	 * t1 == the first source word.
-	 */
-
-	srl	a3, 3, a2	# E : a2 = loop counter = (count - 1)/8
-	addq	a1, 8, a1	# E :
-	mskqh	t2, a1, t2	# U :   detection in the src word
-	nop
-
-	/* Create the 1st output word and detect 0's in the 1st input word.  */
-	mskqh	t1, a1, t3	# U :
-	mskql	t0, a1, t0	# U : assemble the first output word
-	ornot	t1, t2, t2	# E :
-	nop
-
-	cmpbge	zero, t2, t8	# E : bits set iff null found
-	or	t0, t3, t0	# E :
-	beq	a2, $a_eoc	# U :
-	bne	t8, $a_eos	# U : 2nd branch in a quad.  Bad.
-
-	/* On entry to this basic block:
-	 * t0 == a source quad not containing a null.
-	 * a0 - current aligned destination address
-	 * a1 - current aligned source address
-	 * a2 - count of quadwords to move.
-	 * NOTE: Loop improvement - unrolling this is going to be
-	 *	a huge win, since we're going to stall otherwise.
-	 *	Fix this later.  For _really_ large copies, look
-	 *	at using wh64 on a look-ahead basis.  See the code
-	 *	in clear_user.S and copy_user.S.
-	 * Presumably, since (a0) and (a1) do not overlap (by C definition)
-	 * Lots of nops here:
-	 *	- Separate loads from stores
-	 *	- Keep it to 1 branch/quadpack so the branch predictor
-	 *	  can train.
-	 */
-$a_loop:
-	stq_u	t0, 0(a0)	# L :
-	addq	a0, 8, a0	# E :
-	nop
-	subq	a2, 1, a2	# E :
-
-	EX( ldq_u t0, 0(a1) )	# L :
-	addq	a1, 8, a1	# E :
-	cmpbge	zero, t0, t8	# E : Stall 2 cycles on t0
-	beq	a2, $a_eoc      # U :
-
-	beq	t8, $a_loop	# U :
-	nop
-	nop
-	nop
-
-	/* Take care of the final (partial) word store.  At this point
-	 * the end-of-count bit is set in t8 iff it applies.
-	 *
-	 * On entry to this basic block we have:
-	 * t0 == the source word containing the null
-	 * t8 == the cmpbge mask that found it.
-	 */
-$a_eos:
-	negq	t8, t12		# E : find low bit set
-	and	t8, t12, t12	# E : 
-
-	/* We're doing a partial word store and so need to combine
-	   our source and original destination words.  */
-	ldq_u	t1, 0(a0)	# L :
-	subq	t12, 1, t6	# E :
-
-	or	t12, t6, t8	# E :
-	zapnot	t0, t8, t0	# U : clear src bytes > null
-	zap	t1, t8, t1	# U : clear dst bytes <= null
-	or	t0, t1, t0	# E :
-
-	stq_u	t0, 0(a0)	# L :
-	br	$finish_up	# L0 :
-	nop
-	nop
-
-	/* Add the end-of-count bit to the eos detection bitmask.  */
-	.align 4
-$a_eoc:
-	or	t10, t8, t8
-	br	$a_eos
-	nop
-	nop
-
-
-/* The source and destination are not co-aligned.  Align the destination
-   and cope.  We have to be very careful about not reading too much and
-   causing a SEGV.  */
-
-	.align 4
-$u_head:
-	/* We know just enough now to be able to assemble the first
-	   full source word.  We can still find a zero at the end of it
-	   that prevents us from outputting the whole thing.
-
-	   On entry to this basic block:
-	   t0 == the first dest word, unmasked
-	   t1 == the shifted low bits of the first source word
-	   t6 == bytemask that is -1 in dest word bytes */
-
-	EX( ldq_u t2, 8(a1) )	# L : load second src word
-	addq	a1, 8, a1	# E :
-	mskql	t0, a0, t0	# U : mask trailing garbage in dst
-	extqh	t2, a1, t4	# U :
-
-	or	t1, t4, t1	# E : first aligned src word complete
-	mskqh	t1, a0, t1	# U : mask leading garbage in src
-	or	t0, t1, t0	# E : first output word complete
-	or	t0, t6, t6	# E : mask original data for zero test
-
-	cmpbge	zero, t6, t8	# E :
-	beq	a2, $u_eocfin	# U :
-	bne	t8, $u_final	# U : bad news - 2nd branch in a quad
-	lda	t6, -1		# E : mask out the bits we have
-
-	mskql	t6, a1, t6	# U :   already seen
-	stq_u	t0, 0(a0)	# L : store first output word
-	or      t6, t2, t2	# E :
-	cmpbge	zero, t2, t8	# E : find nulls in second partial
-
-	addq	a0, 8, a0		# E :
-	subq	a2, 1, a2		# E :
-	bne	t8, $u_late_head_exit	# U :
-	nop
-
-	/* Finally, we've got all the stupid leading edge cases taken care
-	   of and we can set up to enter the main loop.  */
-
-	extql	t2, a1, t1	# U : position hi-bits of lo word
-	EX( ldq_u t2, 8(a1) )	# L : read next high-order source word
-	addq	a1, 8, a1	# E :
-	cmpbge	zero, t2, t8	# E :
-
-	beq	a2, $u_eoc	# U :
-	bne	t8, $u_eos	# U :
-	nop
-	nop
-
-	/* Unaligned copy main loop.  In order to avoid reading too much,
-	   the loop is structured to detect zeros in aligned source words.
-	   This has, unfortunately, effectively pulled half of a loop
-	   iteration out into the head and half into the tail, but it does
-	   prevent nastiness from accumulating in the very thing we want
-	   to run as fast as possible.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word
-
-	   We further know that t2 does not contain a null terminator.  */
-
-	/*
-	 * Extra nops here:
-	 *	separate load quads from store quads
-	 *	only one branch/quad to permit predictor training
-	 */
-
-	.align 4
-$u_loop:
-	extqh	t2, a1, t0	# U : extract high bits for current word
-	addq	a1, 8, a1	# E :
-	extql	t2, a1, t3	# U : extract low bits for next time
-	addq	a0, 8, a0	# E :
-
-	or	t0, t1, t0	# E : current dst word now complete
-	EX( ldq_u t2, 0(a1) )	# L : load high word for next time
-	subq	a2, 1, a2	# E :
-	nop
-
-	stq_u	t0, -8(a0)	# L : save the current word
-	mov	t3, t1		# E :
-	cmpbge	zero, t2, t8	# E : test new word for eos
-	beq	a2, $u_eoc	# U :
-
-	beq	t8, $u_loop	# U :
-	nop
-	nop
-	nop
-
-	/* We've found a zero somewhere in the source word we just read.
-	   If it resides in the lower half, we have one (probably partial)
-	   word to write out, and if it resides in the upper half, we
-	   have one full and one partial word left to write out.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word.  */
-	.align 4
-$u_eos:
-	extqh	t2, a1, t0	# U :
-	or	t0, t1, t0	# E : first (partial) source word complete
-	cmpbge	zero, t0, t8	# E : is the null in this first bit?
-	nop
-
-	bne	t8, $u_final	# U :
-	stq_u	t0, 0(a0)	# L : the null was in the high-order bits
-	addq	a0, 8, a0	# E :
-	subq	a2, 1, a2	# E :
-
-	.align 4
-$u_late_head_exit:
-	extql	t2, a1, t0	# U :
-	cmpbge	zero, t0, t8	# E :
-	or	t8, t10, t6	# E :
-	cmoveq	a2, t6, t8	# E :
-
-	/* Take care of a final (probably partial) result word.
-	   On entry to this basic block:
-	   t0 == assembled source word
-	   t8 == cmpbge mask that found the null.  */
-	.align 4
-$u_final:
-	negq	t8, t6		# E : isolate low bit set
-	and	t6, t8, t12	# E :
-	ldq_u	t1, 0(a0)	# L :
-	subq	t12, 1, t6	# E :
-
-	or	t6, t12, t8	# E :
-	zapnot	t0, t8, t0	# U : kill source bytes > null
-	zap	t1, t8, t1	# U : kill dest bytes <= null
-	or	t0, t1, t0	# E :
-
-	stq_u	t0, 0(a0)	# E :
-	br	$finish_up	# U :
-	nop
-	nop
-
-	.align 4
-$u_eoc:				# end-of-count
-	extqh	t2, a1, t0	# U :
-	or	t0, t1, t0	# E :
-	cmpbge	zero, t0, t8	# E :
-	nop
-
-	.align 4
-$u_eocfin:			# end-of-count, final word
-	or	t10, t8, t8	# E :
-	br	$u_final	# U :
-	nop
-	nop
-
-	/* Unaligned copy entry point.  */
-	.align 4
-$unaligned:
-
-	srl	a3, 3, a2	# U : a2 = loop counter = (count - 1)/8
-	and	a0, 7, t4	# E : find dest misalignment
-	and	a1, 7, t5	# E : find src misalignment
-	mov	zero, t0	# E :
-
-	/* Conditionally load the first destination word and a bytemask
-	   with 0xff indicating that the destination byte is sacrosanct.  */
-
-	mov	zero, t6	# E :
-	beq	t4, 1f		# U :
-	ldq_u	t0, 0(a0)	# L :
-	lda	t6, -1		# E :
-
-	mskql	t6, a0, t6	# E :
-	nop
-	nop
-	nop
-
-	.align 4
-1:
-	subq	a1, t4, a1	# E : sub dest misalignment from src addr
-	/* If source misalignment is larger than dest misalignment, we need
-	   extra startup checks to avoid SEGV.  */
-	cmplt	t4, t5, t12	# E :
-	extql	t1, a1, t1	# U : shift src into place
-	lda	t2, -1		# E : for creating masks later
-
-	beq	t12, $u_head	# U :
-	mskqh	t2, t5, t2	# U : begin src byte validity mask
-	cmpbge	zero, t1, t8	# E : is there a zero?
-	nop
-
-	extql	t2, a1, t2	# U :
-	or	t8, t10, t5	# E : test for end-of-count too
-	cmpbge	zero, t2, t3	# E :
-	cmoveq	a2, t5, t8	# E : Latency=2, extra map slot
-
-	nop			# E : goes with cmov
-	andnot	t8, t3, t8	# E :
-	beq	t8, $u_head	# U :
-	nop
-
-	/* At this point we've found a zero in the first partial word of
-	   the source.  We need to isolate the valid source data and mask
-	   it into the original destination data.  (Incidentally, we know
-	   that we'll need at least one byte of that original dest word.) */
-
-	ldq_u	t0, 0(a0)	# L :
-	negq	t8, t6		# E : build bitmask of bytes <= zero
-	mskqh	t1, t4, t1	# U :
-	and	t6, t8, t12	# E :
-
-	subq	t12, 1, t6	# E :
-	or	t6, t12, t8	# E :
-	zapnot	t2, t8, t2	# U : prepare source word; mirror changes
-	zapnot	t1, t8, t1	# U : to source validity mask
-
-	andnot	t0, t2, t0	# E : zero place for source to reside
-	or	t0, t1, t0	# E : and put it there
-	stq_u	t0, 0(a0)	# L :
-	nop
-
-	.align 4
-$finish_up:
-	zapnot	t0, t12, t4	# U : was last byte written null?
-	and	t12, 0xf0, t3	# E : binary search for the address of the
-	cmovne	t4, 1, t4	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-
-	and	t12, 0xcc, t2	# E : last byte written
-	and	t12, 0xaa, t1	# E :
-	cmovne	t3, 4, t3	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-
-	bic	a0, 7, t0
-	cmovne	t2, 2, t2	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-	nop
-
-	cmovne	t1, 1, t1	# E : Latency=2, extra map slot
-	nop			# E : with cmovne
-	addq	t0, t3, t0	# E :
-	addq	t1, t2, t1	# E :
-
-	addq	t0, t1, t0	# E :
-	addq	t0, t4, t0	# add one if we filled the buffer
-	subq	t0, v0, v0	# find string length
-	ret			# L0 :
-
-	.align 4
-$zerolength:
-	nop
-	nop
-	nop
-	clr	v0
-
-$exception:
-	nop
-	nop
-	nop
-	ret
-
-	.end __strncpy_from_user
diff --git a/arch/alpha/lib/ev67-strlen_user.S b/arch/alpha/lib/ev67-strlen_user.S
deleted file mode 100644
index 57e0d77..0000000
--- a/arch/alpha/lib/ev67-strlen_user.S
+++ /dev/null
@@ -1,107 +0,0 @@
-/*
- * arch/alpha/lib/ev67-strlen_user.S
- * 21264 version contributed by Rick Gorton <rick.gorton@api-networks.com>
- *
- * Return the length of the string including the NULL terminator
- * (strlen+1) or zero if an error occurred.
- *
- * In places where it is critical to limit the processing time,
- * and the data is not trusted, strnlen_user() should be used.
- * It will return a value greater than its second argument if
- * that limit would be exceeded. This implementation is allowed
- * to access memory beyond the limit, but will not cross a page
- * boundary when doing so.
- *
- * Much of the information about 21264 scheduling/coding comes from:
- *      Compiler Writer's Guide for the Alpha 21264
- *      abbreviated as 'CWG' in other comments here
- *      ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
- * Scheduling notation:
- *      E       - either cluster
- *      U       - upper subcluster; U0 - subcluster U0; U1 - subcluster U1
- *      L       - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
- * Try not to change the actual algorithm if possible for consistency.
- */
-
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda v0, $exception-99b(zero);	\
-	.previous
-
-
-	.set noreorder
-	.set noat
-	.text
-
-	.globl __strlen_user
-	.ent __strlen_user
-	.frame sp, 0, ra
-
-	.align 4
-__strlen_user:
-	ldah	a1, 32767(zero)	# do not use plain strlen_user() for strings
-				# that might be almost 2 GB long; you should
-				# be using strnlen_user() instead
-	nop
-	nop
-	nop
-
-	.globl __strnlen_user
-
-	.align 4
-__strnlen_user:
-	.prologue 0
-	EX( ldq_u t0, 0(a0) )	# L : load first quadword (a0 may be misaligned)
-	lda     t1, -1(zero)	# E :
-
-	insqh   t1, a0, t1	# U :
-	andnot  a0, 7, v0	# E :
-	or      t1, t0, t0	# E :
-	subq	a0, 1, a0	# E : get our +1 for the return 
-
-	cmpbge  zero, t0, t1	# E : t1 <- bitmask: bit i == 1 <==> i-th byte == 0
-	subq	a1, 7, t2	# E :
-	subq	a0, v0, t0	# E :
-	bne     t1, $found	# U :
-
-	addq	t2, t0, t2	# E :
-	addq	a1, 1, a1	# E :
-	nop			# E :
-	nop			# E :
-
-	.align 4
-$loop:	ble	t2, $limit	# U :
-	EX( ldq t0, 8(v0) )	# L :
-	nop			# E :
-	nop			# E :
-
-	cmpbge  zero, t0, t1	# E :
-	subq	t2, 8, t2	# E :
-	addq    v0, 8, v0	# E : addr += 8
-	beq     t1, $loop	# U :
-
-$found: cttz	t1, t2		# U0 :
-	addq	v0, t2, v0	# E :
-	subq    v0, a0, v0	# E :
-	ret			# L0 :
-
-$exception:
-	nop
-	nop
-	nop
-	ret
-
-	.align 4		# currently redundant
-$limit:
-	nop
-	nop
-	subq	a1, t2, v0
-	ret
-
-	.end __strlen_user
diff --git a/arch/alpha/lib/strlen_user.S b/arch/alpha/lib/strlen_user.S
deleted file mode 100644
index 508a18e..0000000
--- a/arch/alpha/lib/strlen_user.S
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * arch/alpha/lib/strlen_user.S
- *
- * Return the length of the string including the NUL terminator
- * (strlen+1) or zero if an error occurred.
- *
- * In places where it is critical to limit the processing time,
- * and the data is not trusted, strnlen_user() should be used.
- * It will return a value greater than its second argument if
- * that limit would be exceeded. This implementation is allowed
- * to access memory beyond the limit, but will not cross a page
- * boundary when doing so.
- */
-
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda v0, $exception-99b(zero);	\
-	.previous
-
-
-	.set noreorder
-	.set noat
-	.text
-
-	.globl __strlen_user
-	.ent __strlen_user
-	.frame sp, 0, ra
-
-	.align 3
-__strlen_user:
-	ldah	a1, 32767(zero)	# do not use plain strlen_user() for strings
-				# that might be almost 2 GB long; you should
-				# be using strnlen_user() instead
-
-	.globl __strnlen_user
-
-	.align 3
-__strnlen_user:
-	.prologue 0
-
-	EX( ldq_u t0, 0(a0) )	# load first quadword (a0 may be misaligned)
-	lda     t1, -1(zero)
-	insqh   t1, a0, t1
-	andnot  a0, 7, v0
-	or      t1, t0, t0
-	subq	a0, 1, a0	# get our +1 for the return 
-	cmpbge  zero, t0, t1	# t1 <- bitmask: bit i == 1 <==> i-th byte == 0
-	subq	a1, 7, t2
-	subq	a0, v0, t0
-	bne     t1, $found
-
-	addq	t2, t0, t2
-	addq	a1, 1, a1
-
-	.align 3
-$loop:	ble	t2, $limit
-	EX( ldq t0, 8(v0) )
-	subq	t2, 8, t2
-	addq    v0, 8, v0	# addr += 8
-	cmpbge  zero, t0, t1
-	beq     t1, $loop
-
-$found:	negq    t1, t2		# clear all but least set bit
-	and     t1, t2, t1
-
-	and     t1, 0xf0, t2	# binary search for that set bit
-	and	t1, 0xcc, t3
-	and	t1, 0xaa, t4
-	cmovne	t2, 4, t2
-	cmovne	t3, 2, t3
-	cmovne	t4, 1, t4
-	addq	t2, t3, t2
-	addq	v0, t4, v0
-	addq	v0, t2, v0
-	nop			# dual issue next two on ev4 and ev5
-	subq    v0, a0, v0
-$exception:
-	ret
-
-	.align 3		# currently redundant
-$limit:
-	subq	a1, t2, v0
-	ret
-
-	.end __strlen_user
diff --git a/arch/alpha/lib/strncpy_from_user.S b/arch/alpha/lib/strncpy_from_user.S
deleted file mode 100644
index 73ee211..0000000
--- a/arch/alpha/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,339 +0,0 @@
-/*
- * arch/alpha/lib/strncpy_from_user.S
- * Contributed by Richard Henderson (rth@tamu.edu)
- *
- * Just like strncpy except in the return value:
- *
- * -EFAULT       if an exception occurs before the terminator is copied.
- * N             if the buffer filled.
- *
- * Otherwise the length of the string is returned.
- */
-
-
-#include <asm/errno.h>
-#include <asm/regdef.h>
-
-
-/* Allow an exception for an insn; exit if we get one.  */
-#define EX(x,y...)			\
-	99: x,##y;			\
-	.section __ex_table,"a";	\
-	.long 99b - .;			\
-	lda $31, $exception-99b($0); 	\
-	.previous
-
-
-	.set noat
-	.set noreorder
-	.text
-
-	.globl __strncpy_from_user
-	.ent __strncpy_from_user
-	.frame $30, 0, $26
-	.prologue 0
-
-	.align 3
-$aligned:
-	/* On entry to this basic block:
-	   t0 == the first destination word for masking back in
-	   t1 == the first source word.  */
-
-	/* Create the 1st output word and detect 0's in the 1st input word.  */
-	lda	t2, -1		# e1    : build a mask against false zero
-	mskqh	t2, a1, t2	# e0    :   detection in the src word
-	mskqh	t1, a1, t3	# e0    :
-	ornot	t1, t2, t2	# .. e1 :
-	mskql	t0, a1, t0	# e0    : assemble the first output word
-	cmpbge	zero, t2, t8	# .. e1 : bits set iff null found
-	or	t0, t3, t0	# e0    :
-	beq	a2, $a_eoc	# .. e1 :
-	bne	t8, $a_eos	# .. e1 :
-
-	/* On entry to this basic block:
-	   t0 == a source word not containing a null.  */
-
-$a_loop:
-	stq_u	t0, 0(a0)	# e0    :
-	addq	a0, 8, a0	# .. e1 :
-	EX( ldq_u t0, 0(a1) )	# e0    :
-	addq	a1, 8, a1	# .. e1 :
-	subq	a2, 1, a2	# e0    :
-	cmpbge	zero, t0, t8	# .. e1 (stall)
-	beq	a2, $a_eoc      # e1    :
-	beq	t8, $a_loop	# e1    :
-
-	/* Take care of the final (partial) word store.  At this point
-	   the end-of-count bit is set in t8 iff it applies.
-
-	   On entry to this basic block we have:
-	   t0 == the source word containing the null
-	   t8 == the cmpbge mask that found it.  */
-
-$a_eos:
-	negq	t8, t12		# e0    : find low bit set
-	and	t8, t12, t12	# e1 (stall)
-
-	/* For the sake of the cache, don't read a destination word
-	   if we're not going to need it.  */
-	and	t12, 0x80, t6	# e0    :
-	bne	t6, 1f		# .. e1 (zdb)
-
-	/* We're doing a partial word store and so need to combine
-	   our source and original destination words.  */
-	ldq_u	t1, 0(a0)	# e0    :
-	subq	t12, 1, t6	# .. e1 :
-	or	t12, t6, t8	# e0    :
-	unop			#
-	zapnot	t0, t8, t0	# e0    : clear src bytes > null
-	zap	t1, t8, t1	# .. e1 : clear dst bytes <= null
-	or	t0, t1, t0	# e1    :
-
-1:	stq_u	t0, 0(a0)
-	br	$finish_up
-
-	/* Add the end-of-count bit to the eos detection bitmask.  */
-$a_eoc:
-	or	t10, t8, t8
-	br	$a_eos
-
-	/*** The Function Entry Point ***/
-	.align 3
-__strncpy_from_user:
-	mov	a0, v0		# save the string start
-	beq	a2, $zerolength
-
-	/* Are source and destination co-aligned?  */
-	xor	a0, a1, t1	# e0    :
-	and	a0, 7, t0	# .. e1 : find dest misalignment
-	and	t1, 7, t1	# e0    :
-	addq	a2, t0, a2	# .. e1 : bias count by dest misalignment
-	subq	a2, 1, a2	# e0    :
-	and	a2, 7, t2	# e1    :
-	srl	a2, 3, a2	# e0    : a2 = loop counter = (count - 1)/8
-	addq	zero, 1, t10	# .. e1 :
-	sll	t10, t2, t10	# e0    : t10 = bitmask of last count byte
-	bne	t1, $unaligned	# .. e1 :
-
-	/* We are co-aligned; take care of a partial first word.  */
-
-	EX( ldq_u t1, 0(a1) )	# e0    : load first src word
-	addq	a1, 8, a1	# .. e1 :
-
-	beq	t0, $aligned	# avoid loading dest word if not needed
-	ldq_u	t0, 0(a0)	# e0    :
-	br	$aligned	# .. e1 :
-
-
-/* The source and destination are not co-aligned.  Align the destination
-   and cope.  We have to be very careful about not reading too much and
-   causing a SEGV.  */
-
-	.align 3
-$u_head:
-	/* We know just enough now to be able to assemble the first
-	   full source word.  We can still find a zero at the end of it
-	   that prevents us from outputting the whole thing.
-
-	   On entry to this basic block:
-	   t0 == the first dest word, unmasked
-	   t1 == the shifted low bits of the first source word
-	   t6 == bytemask that is -1 in dest word bytes */
-
-	EX( ldq_u t2, 8(a1) )	# e0    : load second src word
-	addq	a1, 8, a1	# .. e1 :
-	mskql	t0, a0, t0	# e0    : mask trailing garbage in dst
-	extqh	t2, a1, t4	# e0    :
-	or	t1, t4, t1	# e1    : first aligned src word complete
-	mskqh	t1, a0, t1	# e0    : mask leading garbage in src
-	or	t0, t1, t0	# e0    : first output word complete
-	or	t0, t6, t6	# e1    : mask original data for zero test
-	cmpbge	zero, t6, t8	# e0    :
-	beq	a2, $u_eocfin	# .. e1 :
-	bne	t8, $u_final	# e1    :
-
-	lda	t6, -1			# e1    : mask out the bits we have
-	mskql	t6, a1, t6		# e0    :   already seen
-	stq_u	t0, 0(a0)		# e0    : store first output word
-	or      t6, t2, t2		# .. e1 :
-	cmpbge	zero, t2, t8		# e0    : find nulls in second partial
-	addq	a0, 8, a0		# .. e1 :
-	subq	a2, 1, a2		# e0    :
-	bne	t8, $u_late_head_exit	# .. e1 :
-
-	/* Finally, we've got all the stupid leading edge cases taken care
-	   of and we can set up to enter the main loop.  */
-
-	extql	t2, a1, t1	# e0    : position hi-bits of lo word
-	EX( ldq_u t2, 8(a1) )	# .. e1 : read next high-order source word
-	addq	a1, 8, a1	# e0    :
-	cmpbge	zero, t2, t8	# e1 (stall)
-	beq	a2, $u_eoc	# e1    :
-	bne	t8, $u_eos	# e1    :
-
-	/* Unaligned copy main loop.  In order to avoid reading too much,
-	   the loop is structured to detect zeros in aligned source words.
-	   This has, unfortunately, effectively pulled half of a loop
-	   iteration out into the head and half into the tail, but it does
-	   prevent nastiness from accumulating in the very thing we want
-	   to run as fast as possible.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word
-
-	   We further know that t2 does not contain a null terminator.  */
-
-	.align 3
-$u_loop:
-	extqh	t2, a1, t0	# e0    : extract high bits for current word
-	addq	a1, 8, a1	# .. e1 :
-	extql	t2, a1, t3	# e0    : extract low bits for next time
-	addq	a0, 8, a0	# .. e1 :
-	or	t0, t1, t0	# e0    : current dst word now complete
-	EX( ldq_u t2, 0(a1) )	# .. e1 : load high word for next time
-	stq_u	t0, -8(a0)	# e0    : save the current word
-	mov	t3, t1		# .. e1 :
-	subq	a2, 1, a2	# e0    :
-	cmpbge	zero, t2, t8	# .. e1 : test new word for eos
-	beq	a2, $u_eoc	# e1    :
-	beq	t8, $u_loop	# e1    :
-
-	/* We've found a zero somewhere in the source word we just read.
-	   If it resides in the lower half, we have one (probably partial)
-	   word to write out, and if it resides in the upper half, we
-	   have one full and one partial word left to write out.
-
-	   On entry to this basic block:
-	   t1 == the shifted high-order bits from the previous source word
-	   t2 == the unshifted current source word.  */
-$u_eos:
-	extqh	t2, a1, t0	# e0    :
-	or	t0, t1, t0	# e1    : first (partial) source word complete
-
-	cmpbge	zero, t0, t8	# e0    : is the null in this first bit?
-	bne	t8, $u_final	# .. e1 (zdb)
-
-	stq_u	t0, 0(a0)	# e0    : the null was in the high-order bits
-	addq	a0, 8, a0	# .. e1 :
-	subq	a2, 1, a2	# e1    :
-
-$u_late_head_exit:
-	extql	t2, a1, t0	# .. e0 :
-	cmpbge	zero, t0, t8	# e0    :
-	or	t8, t10, t6	# e1    :
-	cmoveq	a2, t6, t8	# e0    :
-	nop			# .. e1 :
-
-	/* Take care of a final (probably partial) result word.
-	   On entry to this basic block:
-	   t0 == assembled source word
-	   t8 == cmpbge mask that found the null.  */
-$u_final:
-	negq	t8, t6		# e0    : isolate low bit set
-	and	t6, t8, t12	# e1    :
-
-	and	t12, 0x80, t6	# e0    : avoid dest word load if we can
-	bne	t6, 1f		# .. e1 (zdb)
-
-	ldq_u	t1, 0(a0)	# e0    :
-	subq	t12, 1, t6	# .. e1 :
-	or	t6, t12, t8	# e0    :
-	zapnot	t0, t8, t0	# .. e1 : kill source bytes > null
-	zap	t1, t8, t1	# e0    : kill dest bytes <= null
-	or	t0, t1, t0	# e1    :
-
-1:	stq_u	t0, 0(a0)	# e0    :
-	br	$finish_up
-
-$u_eoc:				# end-of-count
-	extqh	t2, a1, t0
-	or	t0, t1, t0
-	cmpbge	zero, t0, t8
-
-$u_eocfin:			# end-of-count, final word
-	or	t10, t8, t8
-	br	$u_final
-
-	/* Unaligned copy entry point.  */
-	.align 3
-$unaligned:
-
-	EX( ldq_u t1, 0(a1) )	# e0    : load first source word
-
-	and	a0, 7, t4	# .. e1 : find dest misalignment
-	and	a1, 7, t5	# e0    : find src misalignment
-
-	/* Conditionally load the first destination word and a bytemask
-	   with 0xff indicating that the destination byte is sacrosanct.  */
-
-	mov	zero, t0	# .. e1 :
-	mov	zero, t6	# e0    :
-	beq	t4, 1f		# .. e1 :
-	ldq_u	t0, 0(a0)	# e0    :
-	lda	t6, -1		# .. e1 :
-	mskql	t6, a0, t6	# e0    :
-1:
-	subq	a1, t4, a1	# .. e1 : sub dest misalignment from src addr
-
-	/* If source misalignment is larger than dest misalignment, we need
-	   extra startup checks to avoid SEGV.  */
-
-	cmplt	t4, t5, t12	# e1    :
-	extql	t1, a1, t1	# .. e0 : shift src into place
-	lda	t2, -1		# e0    : for creating masks later
-	beq	t12, $u_head	# e1    :
-
-	mskqh	t2, t5, t2	# e0    : begin src byte validity mask
-	cmpbge	zero, t1, t8	# .. e1 : is there a zero?
-	extql	t2, a1, t2	# e0    :
-	or	t8, t10, t5	# .. e1 : test for end-of-count too
-	cmpbge	zero, t2, t3	# e0    :
-	cmoveq	a2, t5, t8	# .. e1 :
-	andnot	t8, t3, t8	# e0    :
-	beq	t8, $u_head	# .. e1 (zdb)
-
-	/* At this point we've found a zero in the first partial word of
-	   the source.  We need to isolate the valid source data and mask
-	   it into the original destination data.  (Incidentally, we know
-	   that we'll need at least one byte of that original dest word.) */
-
-	ldq_u	t0, 0(a0)	# e0    :
-	negq	t8, t6		# .. e1 : build bitmask of bytes <= zero
-	mskqh	t1, t4, t1	# e0    :
-	and	t6, t8, t12	# .. e1 :
-	subq	t12, 1, t6	# e0    :
-	or	t6, t12, t8	# e1    :
-
-	zapnot	t2, t8, t2	# e0    : prepare source word; mirror changes
-	zapnot	t1, t8, t1	# .. e1 : to source validity mask
-
-	andnot	t0, t2, t0	# e0    : zero place for source to reside
-	or	t0, t1, t0	# e1    : and put it there
-	stq_u	t0, 0(a0)	# e0    :
-
-$finish_up:
-	zapnot	t0, t12, t4	# was last byte written null?
-	cmovne	t4, 1, t4
-
-	and	t12, 0xf0, t3	# binary search for the address of the
-	and	t12, 0xcc, t2	# last byte written
-	and	t12, 0xaa, t1
-	bic	a0, 7, t0
-	cmovne	t3, 4, t3
-	cmovne	t2, 2, t2
-	cmovne	t1, 1, t1
-	addq	t0, t3, t0
-	addq	t1, t2, t1
-	addq	t0, t1, t0
-	addq	t0, t4, t0	# add one if we filled the buffer
-
-	subq	t0, v0, v0	# find string length
-	ret
-
-$zerolength:
-	clr	v0
-$exception:
-	ret
-
-	.end __strncpy_from_user
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 5eecab1..0c4132d 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,6 +89,8 @@
 	const struct exception_table_entry *fixup;
 	int fault, si_code = SEGV_MAPERR;
 	siginfo_t info;
+	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+			      (cause > 0 ? FAULT_FLAG_WRITE : 0));
 
 	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
 	   (or is suppressed by the PALcode).  Support that for older CPUs
@@ -114,6 +116,7 @@
 		goto vmalloc_fault;
 #endif
 
+retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -144,8 +147,11 @@
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(mm, vma, address, cause > 0 ? FAULT_FLAG_WRITE : 0);
-	up_read(&mm->mmap_sem);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -153,10 +159,26 @@
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR)
-		current->maj_flt++;
-	else
-		current->min_flt++;
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR)
+			current->maj_flt++;
+		else
+			current->min_flt++;
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			 /* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
+	}
+
+	up_read(&mm->mmap_sem);
+
 	return;
 
 	/* Something tried to access memory that isn't in our memory map.
@@ -186,12 +208,14 @@
 	/* We ran out of memory, or some other thing happened to us that
 	   made us unable to handle the page fault gracefully.  */
  out_of_memory:
+	up_read(&mm->mmap_sem);
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();
 	return;
 
  do_sigbus:
+	up_read(&mm->mmap_sem);
 	/* Send a sigbus, regardless of whether we were in kernel
 	   or user mode.  */
 	info.si_signo = SIGBUS;
diff --git a/arch/alpha/oprofile/common.c b/arch/alpha/oprofile/common.c
index a0a5d27..b8ce18f 100644
--- a/arch/alpha/oprofile/common.c
+++ b/arch/alpha/oprofile/common.c
@@ -12,6 +12,7 @@
 #include <linux/smp.h>
 #include <linux/errno.h>
 #include <asm/ptrace.h>
+#include <asm/special_insns.h>
 
 #include "op_impl.h"
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e91c7cd..2f88d8d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,7 +6,7 @@
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
@@ -38,7 +38,6 @@
 	select HARDIRQS_SW_RESEND
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_PROBE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HARDIRQS_SW_RESEND
 	select CPU_PM if (SUSPEND || CPU_IDLE)
@@ -126,11 +125,6 @@
 	bool
 	default y
 
-config GENERIC_LOCKBREAK
-	bool
-	default y
-	depends on SMP && PREEMPT
-
 config RWSEM_GENERIC_SPINLOCK
 	bool
 	default y
@@ -2150,6 +2144,7 @@
 config CPU_FREQ_IMX
 	tristate "CPUfreq driver for i.MX CPUs"
 	depends on ARCH_MXC && CPU_FREQ
+	select CPU_FREQ_TABLE
 	help
 	  This enables the CPUfreq driver for i.MX CPUs.
 
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f15f82b..e968a52 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -356,15 +356,15 @@
 		  is nothing connected to read from the DCC.
 
 	config DEBUG_SEMIHOSTING
-		bool "Kernel low-level debug output via semihosting I"
+		bool "Kernel low-level debug output via semihosting I/O"
 		help
 		  Semihosting enables code running on an ARM target to use
 		  the I/O facilities on a host debugger/emulator through a
-		  simple SVC calls. The host debugger or emulator must have
+		  simple SVC call. The host debugger or emulator must have
 		  semihosting enabled for the special svc call to be trapped
 		  otherwise the kernel will crash.
 
-		  This is known to work with OpenOCD, as wellas
+		  This is known to work with OpenOCD, as well as
 		  ARM's Fast Models, or any other controlling environment
 		  that implements semihosting.
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 30eae87..a051dfb 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -284,10 +284,10 @@
 zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
-%.dtb:
+%.dtb: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-dtbs:
+dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
 # We use MRPROPER_FILES and CLEAN_FILES now
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index b8c64b8..81769c1 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -659,10 +659,14 @@
 #ifdef CONFIG_CPU_ENDIAN_BE8
 		orr	r0, r0, #1 << 25	@ big-endian page tables
 #endif
+		mrcne   p15, 0, r6, c2, c0, 2   @ read ttb control reg
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client
+		bic     r6, r6, #1 << 31        @ 32-bit translation system
+		bic     r6, r6, #3 << 0         @ use only ttbr0
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
+		mcrne   p15, 0, r6, c2, c0, 2   @ load ttb control
 #endif
 		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mcr	p15, 0, r0, c1, c0, 0	@ load control register
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 59509c4..bd0cff3 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -154,5 +154,10 @@
 			#size-cells = <0>;
 			ti,hwmods = "i2c3";
 		};
+
+		wdt2: wdt@44e35000 {
+			compatible = "ti,omap3-wdt";
+			ti,hwmods = "wd_timer2";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index 7829a4d..96514c1 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -15,7 +15,7 @@
 	compatible = "atmel,at91sam9g25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
+		bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
 	};
 
 	ahb {
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index cd86177..59d9789 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -25,8 +25,8 @@
 		aips@70000000 { /* aips-1 */
 			spba@70000000 {
 				esdhc@70004000 { /* ESDHC1 */
-					fsl,cd-internal;
-					fsl,wp-internal;
+					fsl,cd-controller;
+					fsl,wp-controller;
 					status = "okay";
 				};
 
diff --git a/arch/arm/boot/dts/kirkwood-iconnect.dts b/arch/arm/boot/dts/kirkwood-iconnect.dts
index 52d9470..f8ca6fa 100644
--- a/arch/arm/boot/dts/kirkwood-iconnect.dts
+++ b/arch/arm/boot/dts/kirkwood-iconnect.dts
@@ -41,9 +41,13 @@
 		};
 		power-blue {
 			label = "power:blue";
-			gpios = <&gpio1 11 0>;
+			gpios = <&gpio1 10 0>;
 			linux,default-trigger = "timer";
 		};
+		power-red {
+			label = "power:red";
+			gpios = <&gpio1 11 0>;
+		};
 		usb1 {
 			label = "usb1:blue";
 			gpios = <&gpio1 12 0>;
diff --git a/arch/arm/boot/dts/twl6030.dtsi b/arch/arm/boot/dts/twl6030.dtsi
index 3b2f351..d351b27 100644
--- a/arch/arm/boot/dts/twl6030.dtsi
+++ b/arch/arm/boot/dts/twl6030.dtsi
@@ -66,6 +66,7 @@
 
 	vcxio: regulator@8 {
 		compatible = "ti,twl6030-vcxio";
+		regulator-always-on;
 	};
 
 	vusb: regulator@9 {
@@ -74,10 +75,12 @@
 
 	v1v8: regulator@10 {
 		compatible = "ti,twl6030-v1v8";
+		regulator-always-on;
 	};
 
 	v2v1: regulator@11 {
 		compatible = "ti,twl6030-v2v1";
+		regulator-always-on;
 	};
 
 	clk32kg: regulator@12 {
diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig
index 7d87184..90610c7 100644
--- a/arch/arm/configs/armadillo800eva_defconfig
+++ b/arch/arm/configs/armadillo800eva_defconfig
@@ -33,7 +33,7 @@
 CONFIG_FORCE_MAX_ZONEORDER=13
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096"
+CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096 rw"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_KEXEC=y
 CONFIG_VFP=y
diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig
index 2d4f661..da68454 100644
--- a/arch/arm/configs/u8500_defconfig
+++ b/arch/arm/configs/u8500_defconfig
@@ -86,6 +86,7 @@
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_LM3530=y
 CONFIG_LEDS_LP5521=y
+CONFIG_LEDS_GPIO=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AB8500=y
 CONFIG_RTC_DRV_PL031=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 03fb936..5c8b3bf4 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -320,4 +320,12 @@
 	.size \name , . - \name
 	.endm
 
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcccs	\tmp, \tmp, \limit
+	bcs	\bad
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 2ae842d..5c44dcb 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -203,6 +203,13 @@
 }
 
 /*
+ * This can be called during early boot to increase the size of the atomic
+ * coherent DMA pool above the default value of 256KiB. It must be called
+ * before postcore_initcall.
+ */
+extern void __init init_dma_coherent_pool_size(unsigned long size);
+
+/*
  * This can be called during boot to increase the size of the consistent
  * DMA region above it's default value of 2MB. It must be called before the
  * memory allocator is initialised, i.e. before any core_initcall.
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index e965f1b..5f6ddcc 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -187,6 +187,7 @@
 #define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
 #endif
 #endif
+#endif /* __ASSEMBLY__ */
 
 #ifndef PHYS_OFFSET
 #ifdef PLAT_PHYS_OFFSET
@@ -196,6 +197,8 @@
 #endif
 #endif
 
+#ifndef __ASSEMBLY__
+
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f66626d..41dc31f 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -195,25 +195,6 @@
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
-#if __LINUX_ARM_ARCH__ < 6
-static inline void __sync_icache_dcache(pte_t pteval)
-{
-}
-#else
-extern void __sync_icache_dcache(pte_t pteval);
-#endif
-
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pteval)
-{
-	if (addr >= TASK_SIZE)
-		set_pte_ext(ptep, pteval, 0);
-	else {
-		__sync_icache_dcache(pteval);
-		set_pte_ext(ptep, pteval, PTE_EXT_NG);
-	}
-}
-
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
 #define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
@@ -226,6 +207,27 @@
 	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
 	 (L_PTE_PRESENT | L_PTE_USER))
 
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_present_user(pteval)) {
+		__sync_icache_dcache(pteval);
+		ext |= PTE_EXT_NG;
+	}
+
+	set_pte_ext(ptep, pteval, ext);
+}
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
@@ -251,13 +253,13 @@
  *
  *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
  *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset --------------------> <- type --> 0 0 0
+ *   <--------------- offset ----------------------> < type -> 0 0 0
  *
- * This gives us up to 63 swap files and 32GB per swap file.  Note that
+ * This gives us up to 31 swap files and 64GB per swap file.  Note that
  * the offset field is always non-zero.
  */
 #define __SWP_TYPE_SHIFT	3
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
 
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index e3f7572..05b8e82 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -10,5 +10,7 @@
 
 extern void sched_clock_postinit(void);
 extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
+extern void setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
+		unsigned long rate);
 
 #endif
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 314d466..99a1951 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -199,6 +199,9 @@
 {
 	pgtable_page_dtor(pte);
 
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+#else
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
@@ -206,6 +209,7 @@
 	addr &= PMD_MASK;
 	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
 	tlb_add_flush(tlb, addr + SZ_1M);
+#endif
 
 	tlb_remove_page(tlb, pte);
 }
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 479a635..77bd79f 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -101,28 +101,39 @@
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
 
-#define __get_user_x(__r2,__p,__e,__s,__i...)				\
+#define __GUP_CLOBBER_1	"lr", "cc"
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define __GUP_CLOBBER_2	"ip", "lr", "cc"
+#else
+#define __GUP_CLOBBER_2 "lr", "cc"
+#endif
+#define __GUP_CLOBBER_4	"lr", "cc"
+
+#define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%1", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__get_user_" #__s				\
 		: "=&r" (__e), "=r" (__r2)				\
-		: "0" (__p)						\
-		: __i, "cc")
+		: "0" (__p), "r" (__l)					\
+		: __GUP_CLOBBER_##__s)
 
-#define get_user(x,p)							\
+#define __get_user_check(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
 		register unsigned long __r2 asm("r2");			\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__get_user_x(__r2, __p, __e, 1, "lr");		\
-	       		break;						\
+			__get_user_x(__r2, __p, __e, __l, 1);		\
+			break;						\
 		case 2:							\
-			__get_user_x(__r2, __p, __e, 2, "r3", "lr");	\
+			__get_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-	       		__get_user_x(__r2, __p, __e, 4, "lr");		\
+			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
@@ -130,42 +141,57 @@
 		__e;							\
 	})
 
+#define get_user(x,p)							\
+	({								\
+		might_fault();						\
+		__get_user_check(x,p);					\
+	 })
+
 extern int __put_user_1(void *, unsigned int);
 extern int __put_user_2(void *, unsigned int);
 extern int __put_user_4(void *, unsigned int);
 extern int __put_user_8(void *, unsigned long long);
 
-#define __put_user_x(__r2,__p,__e,__s)					\
+#define __put_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%2", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__put_user_" #__s				\
 		: "=&r" (__e)						\
-		: "0" (__p), "r" (__r2)					\
+		: "0" (__p), "r" (__r2), "r" (__l)			\
 		: "ip", "lr", "cc")
 
-#define put_user(x,p)							\
+#define __put_user_check(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__put_user_x(__r2, __p, __e, 1);		\
+			__put_user_x(__r2, __p, __e, __l, 1);		\
 			break;						\
 		case 2:							\
-			__put_user_x(__r2, __p, __e, 2);		\
+			__put_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-			__put_user_x(__r2, __p, __e, 4);		\
+			__put_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		case 8:							\
-			__put_user_x(__r2, __p, __e, 8);		\
+			__put_user_x(__r2, __p, __e, __l, 8);		\
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
 		__e;							\
 	})
 
+#define put_user(x,p)							\
+	({								\
+		might_fault();						\
+		__put_user_check(x,p);					\
+	 })
+
 #else /* CONFIG_MMU */
 
 /*
@@ -219,6 +245,7 @@
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val,__gu_addr,err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val,__gu_addr,err);	break;	\
@@ -300,6 +327,7 @@
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val,__pu_addr,err);	break;	\
 	case 2: __put_user_asm_half(__pu_val,__pu_addr,err);	break;	\
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index ba386bd..281bf33 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -159,6 +159,12 @@
 		arch >= ARM_DEBUG_ARCH_V7_1;
 }
 
+/* Can we determine the watchpoint access type from the fsr? */
+static int debug_exception_updates_fsr(void)
+{
+	return 0;
+}
+
 /* Determine number of WRP registers available. */
 static int get_num_wrp_resources(void)
 {
@@ -604,13 +610,14 @@
 		/* Aligned */
 		break;
 	case 1:
-		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
-			break;
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
 		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
+	case 3:
+		/* Allow single byte watchpoint. */
+		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			break;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -619,18 +626,35 @@
 	info->address &= ~alignment_mask;
 	info->ctrl.len <<= offset;
 
-	/*
-	 * Currently we rely on an overflow handler to take
-	 * care of single-stepping the breakpoint when it fires.
-	 * In the case of userspace breakpoints on a core with V7 debug,
-	 * we can use the mismatch feature as a poor-man's hardware
-	 * single-step, but this only works for per-task breakpoints.
-	 */
-	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
-	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
-		pr_warning("overflow handler required but none found\n");
-		ret = -EINVAL;
+	if (!bp->overflow_handler) {
+		/*
+		 * Mismatch breakpoints are required for single-stepping
+		 * breakpoints.
+		 */
+		if (!core_has_mismatch_brps())
+			return -EINVAL;
+
+		/* We don't allow mismatch breakpoints in kernel space. */
+		if (arch_check_bp_in_kernelspace(bp))
+			return -EPERM;
+
+		/*
+		 * Per-cpu breakpoints are not supported by our stepping
+		 * mechanism.
+		 */
+		if (!bp->hw.bp_target)
+			return -EINVAL;
+
+		/*
+		 * We only support specific access types if the fsr
+		 * reports them.
+		 */
+		if (!debug_exception_updates_fsr() &&
+		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+			return -EINVAL;
 	}
+
 out:
 	return ret;
 }
@@ -706,10 +730,12 @@
 				goto unlock;
 
 			/* Check that the access type matches. */
-			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
-				 HW_BREAKPOINT_R;
-			if (!(access & hw_breakpoint_type(wp)))
-				goto unlock;
+			if (debug_exception_updates_fsr()) {
+				access = (fsr & ARM_FSR_ACCESS_MASK) ?
+					  HW_BREAKPOINT_W : HW_BREAKPOINT_R;
+				if (!(access & hw_breakpoint_type(wp)))
+					goto unlock;
+			}
 
 			/* We have a winner. */
 			info->trigger = addr;
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 27d186a..f451539 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -21,6 +21,8 @@
 	u32 epoch_cyc_copy;
 	u32 mult;
 	u32 shift;
+	bool suspended;
+	bool needs_suspend;
 };
 
 static void sched_clock_poll(unsigned long wrap_ticks);
@@ -49,6 +51,9 @@
 	u64 epoch_ns;
 	u32 epoch_cyc;
 
+	if (cd.suspended)
+		return cd.epoch_ns;
+
 	/*
 	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
 	 * ensuring that we always write epoch_cyc, epoch_ns and
@@ -98,6 +103,13 @@
 	update_sched_clock();
 }
 
+void __init setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
+		unsigned long rate)
+{
+	setup_sched_clock(read, bits, rate);
+	cd.needs_suspend = true;
+}
+
 void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 {
 	unsigned long r, w;
@@ -169,11 +181,23 @@
 static int sched_clock_suspend(void)
 {
 	sched_clock_poll(sched_clock_timer.data);
+	if (cd.needs_suspend)
+		cd.suspended = true;
 	return 0;
 }
 
+static void sched_clock_resume(void)
+{
+	if (cd.needs_suspend) {
+		cd.epoch_cyc = read_sched_clock();
+		cd.epoch_cyc_copy = cd.epoch_cyc;
+		cd.suspended = false;
+	}
+}
+
 static struct syscore_ops sched_clock_ops = {
 	.suspend = sched_clock_suspend,
+	.resume = sched_clock_resume,
 };
 
 static int __init sched_clock_syscore_init(void)
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 198b084..26c12c6 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -321,7 +321,7 @@
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
  */
-void init_cpu_topology(void)
+void __init init_cpu_topology(void)
 {
 	unsigned int cpu;
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index f794521..b0179b8 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -420,20 +420,23 @@
 #endif
 			instr = *(u32 *) pc;
 	} else if (thumb_mode(regs)) {
-		get_user(instr, (u16 __user *)pc);
+		if (get_user(instr, (u16 __user *)pc))
+			goto die_sig;
 		if (is_wide_instruction(instr)) {
 			unsigned int instr2;
-			get_user(instr2, (u16 __user *)pc+1);
+			if (get_user(instr2, (u16 __user *)pc+1))
+				goto die_sig;
 			instr <<= 16;
 			instr |= instr2;
 		}
-	} else {
-		get_user(instr, (u32 __user *)pc);
+	} else if (get_user(instr, (u32 __user *)pc)) {
+		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
 		return;
 
+die_sig:
 #ifdef CONFIG_DEBUG_USER
 	if (user_debug & UDBG_UNDEFINED) {
 		printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 2473fd1..af72969 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -16,13 +16,30 @@
 		   call_with_stack.o
 
 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
-mmu-y	+= copy_from_user.o copy_to_user.o
+
+# the code in uaccess.S is not preemption safe and
+# probably faster on ARMv3 only
+ifeq ($(CONFIG_PREEMPT),y)
+  mmu-y	+= copy_from_user.o copy_to_user.o
+else
+ifneq ($(CONFIG_CPU_32v3),y)
+  mmu-y	+= copy_from_user.o copy_to_user.o
+else
+  mmu-y	+= uaccess.o
+endif
+endif
 
 # using lib_ here won't override already available weak symbols
 obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o
 
-lib-$(CONFIG_MMU)		+= $(mmu-y)
-lib-y				+= io-readsw-armv4.o io-writesw-armv4.o
+lib-$(CONFIG_MMU) += $(mmu-y)
+
+ifeq ($(CONFIG_CPU_32v3),y)
+  lib-y	+= io-readsw-armv3.o io-writesw-armv3.o
+else
+  lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
+endif
+
 lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
 lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index d6dacc6..395d5fb 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -59,6 +59,7 @@
 {
 	pr_info("Switching to timer-based delay loop\n");
 	lpj_fine			= freq / HZ;
+	loops_per_jiffy			= lpj_fine;
 	arm_delay_ops.delay		= __timer_delay;
 	arm_delay_ops.const_udelay	= __timer_const_udelay;
 	arm_delay_ops.udelay		= __timer_udelay;
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 11093a7..9b06bb4 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -16,8 +16,9 @@
  * __get_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  * Outputs:	r0 is the error code
- *		r2, r3 contains the zero-extended value
+ *		r2 contains the zero-extended value
  *		lr corrupted
  *
  * No other registers must be altered.  (see <asm/uaccess.h>
@@ -27,33 +28,39 @@
  * Note also that it is intended that __get_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__get_user_1)
+	check_uaccess r0, 1, r1, r2, __get_user_bad
 1: TUSER(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-#ifdef CONFIG_THUMB2_KERNEL
-2: TUSER(ldrb)	r2, [r0]
-3: TUSER(ldrb)	r3, [r0, #1]
+	check_uaccess r0, 2, r1, r2, __get_user_bad
+#ifdef CONFIG_CPU_USE_DOMAINS
+rb	.req	ip
+2:	ldrbt	r2, [r0], #1
+3:	ldrbt	rb, [r0], #0
 #else
-2: TUSER(ldrb)	r2, [r0], #1
-3: TUSER(ldrb)	r3, [r0]
+rb	.req	r0
+2:	ldrb	r2, [r0]
+3:	ldrb	rb, [r0, #1]
 #endif
 #ifndef __ARMEB__
-	orr	r2, r2, r3, lsl #8
+	orr	r2, r2, rb, lsl #8
 #else
-	orr	r2, r3, r2, lsl #8
+	orr	r2, rb, r2, lsl #8
 #endif
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
+	check_uaccess r0, 4, r1, r2, __get_user_bad
 4: TUSER(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
new file mode 100644
index 0000000..88487c8
--- /dev/null
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -0,0 +1,106 @@
+/*
+ *  linux/arch/arm/lib/io-readsw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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/linkage.h>
+#include <asm/assembler.h>
+
+.Linsw_bad_alignment:
+		adr	r0, .Linsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.Linsw_bad_align_msg:
+		.asciz	"insw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.Linsw_align:	tst	r1, #1
+		bne	.Linsw_bad_alignment
+
+		ldr	r3, [r0]
+		strb	r3, [r1], #1
+		mov	r3, r3, lsr #8
+		strb	r3, [r1], #1
+
+		subs	r2, r2, #1
+		moveq	pc, lr
+
+ENTRY(__raw_readsw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Linsw_align
+
+.Linsw_aligned:	mov	ip, #0xff
+		orr	ip, ip, ip, lsl #8
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_insw_8
+
+.Linsw_8_lp:	ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		ldr	r5, [r0]
+		and	r5, r5, ip
+		ldr	r6, [r0]
+		orr	r5, r5, r6, lsl #16
+
+		ldr	r6, [r0]
+		and	r6, r6, ip
+		ldr	lr, [r0]
+		orr	r6, r6, lr, lsl #16
+
+		stmia	r1!, {r3 - r6}
+
+		subs	r2, r2, #8
+		bpl	.Linsw_8_lp
+
+		tst	r2, #7
+		ldmeqfd	sp!, {r4, r5, r6, pc}
+
+.Lno_insw_8:	tst	r2, #4
+		beq	.Lno_insw_4
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		stmia	r1!, {r3, r4}
+
+.Lno_insw_4:	tst	r2, #2
+		beq	.Lno_insw_2
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		str	r3, [r1], #4
+
+.Lno_insw_2:	tst	r2, #1
+		ldrne	r3, [r0]
+		strneb	r3, [r1], #1
+		movne	r3, r3, lsr #8
+		strneb	r3, [r1]
+
+		ldmfd	sp!, {r4, r5, r6, pc}
+
+
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
new file mode 100644
index 0000000..49b8004
--- /dev/null
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -0,0 +1,126 @@
+/*
+ *  linux/arch/arm/lib/io-writesw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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/linkage.h>
+#include <asm/assembler.h>
+
+.Loutsw_bad_alignment:
+		adr	r0, .Loutsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.Loutsw_bad_align_msg:
+		.asciz	"outsw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.Loutsw_align:	tst	r1, #1
+		bne	.Loutsw_bad_alignment
+
+		add	r1, r1, #2
+
+		ldr	r3, [r1, #-4]
+		mov	r3, r3, lsr #16
+		orr	r3, r3, r3, lsl #16
+		str	r3, [r0]
+		subs	r2, r2, #1
+		moveq	pc, lr
+
+ENTRY(__raw_writesw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Loutsw_align
+
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_outsw_8
+
+.Loutsw_8_lp:	ldmia	r1!, {r3, r4, r5, r6}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		subs	r2, r2, #8
+		bpl	.Loutsw_8_lp
+
+		tst	r2, #7
+		ldmeqfd	sp!, {r4, r5, r6, pc}
+
+.Lno_outsw_8:	tst	r2, #4
+		beq	.Lno_outsw_4
+
+		ldmia	r1!, {r3, r4}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.Lno_outsw_4:	tst	r2, #2
+		beq	.Lno_outsw_2
+
+		ldr	r3, [r1], #4
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.Lno_outsw_2:	tst	r2, #1
+
+		ldrne	r3, [r1]
+
+		movne	ip, r3, lsl #16
+		orrne	ip, ip, ip, lsr #16
+		strne	ip, [r0]
+
+		ldmfd	sp!, {r4, r5, r6, pc}
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 7db2599..3d73dcb 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -16,6 +16,7 @@
  * __put_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  *		r2, r3 contains the value
  * Outputs:	r0 is the error code
  *		lr corrupted
@@ -27,16 +28,19 @@
  * Note also that it is intended that __put_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__put_user_1)
+	check_uaccess r0, 1, r1, ip, __put_user_bad
 1: TUSER(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
+	check_uaccess r0, 2, r1, ip, __put_user_bad
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
@@ -60,12 +64,14 @@
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
+	check_uaccess r0, 4, r1, ip, __put_user_bad
 4: TUSER(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
+	check_uaccess r0, 8, r1, ip, __put_user_bad
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(str)	r2, [r0]
 6: TUSER(str)	r3, [r0, #4]
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
new file mode 100644
index 0000000..5c908b1
--- /dev/null
+++ b/arch/arm/lib/uaccess.S
@@ -0,0 +1,564 @@
+/*
+ *  linux/arch/arm/lib/uaccess.S
+ *
+ *  Copyright (C) 1995, 1996,1997,1998 Russell King
+ *
+ * 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.
+ *
+ *  Routines to block copy data to/from user memory
+ *   These are highly optimised both for the 4k page size
+ *   and for various alignments.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/domain.h>
+
+		.text
+
+#define PAGE_SHIFT 12
+
+/* Prototype: int __copy_to_user(void *to, const char *from, size_t n)
+ * Purpose  : copy a block to user memory from kernel memory
+ * Params   : to   - user memory
+ *          : from - kernel memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+
+.Lc2u_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		sub	r2, r2, ip
+		b	.Lc2u_dest_aligned
+
+ENTRY(__copy_to_user)
+		stmfd	sp!, {r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.Lc2u_not_enough
+		ands	ip, r0, #3
+		bne	.Lc2u_dest_not_aligned
+.Lc2u_dest_aligned:
+
+		ands	ip, r1, #3
+		bne	.Lc2u_src_not_aligned
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lc2u_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_0nowords
+		ldr	r3, [r1], #4
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.Lc2u_0rem8lp
+
+.Lc2u_0cpy8lp:	ldmia	r1!, {r3 - r6}
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		ldmia	r1!, {r3 - r6}
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_0cpy8lp
+
+.Lc2u_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}
+		stmgeia	r0!, {r3 - r6}			@ Shouldnt fault
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		ldrne	r3, [r1], #4
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_0fupi
+.Lc2u_0nowords:	teq	ip, #0
+		beq	.Lc2u_finished
+.Lc2u_nowords:	cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_not_enough:
+		movs	ip, r2
+		bne	.Lc2u_nowords
+.Lc2u_finished:	mov	r0, #0
+		ldmfd	sp!, {r2, r4 - r7, pc}
+
+.Lc2u_src_not_aligned:
+		bic	r1, r1, #3
+		ldr	r7, [r1], #4
+		cmp	ip, #2
+		bgt	.Lc2u_3fupi
+		beq	.Lc2u_2fupi
+.Lc2u_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_1nowords
+		mov	r3, r7, pull #8
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #24
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_1rem8lp
+
+.Lc2u_1cpy8lp:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_1cpy8lp
+
+.Lc2u_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #8
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #24
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_1fupi
+.Lc2u_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.Lc2u_finished
+		cmp	ip, #2
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_2
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		movgt	r3, r7, get_byte_3
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_2nowords
+		mov	r3, r7, pull #16
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #16
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_2rem8lp
+
+.Lc2u_2cpy8lp:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_2cpy8lp
+
+.Lc2u_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #16
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #16
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_2fupi
+.Lc2u_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.Lc2u_finished
+		cmp	ip, #2
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_3
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+
+.Lc2u_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lc2u_3nowords
+		mov	r3, r7, pull #24
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #8
+USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lc2u_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lc2u_3rem8lp
+
+.Lc2u_3cpy8lp:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.Lc2u_3cpy8lp
+
+.Lc2u_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #24
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #8
+	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.Lc2u_3fupi
+.Lc2u_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.Lc2u_finished
+		cmp	ip, #2
+USER(	TUSER(	strb)	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(	TUSER(	strgeb) r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
+		b	.Lc2u_finished
+ENDPROC(__copy_to_user)
+
+		.pushsection .fixup,"ax"
+		.align	0
+9001:		ldmfd	sp!, {r0, r4 - r7, pc}
+		.popsection
+
+/* Prototype: unsigned long __copy_from_user(void *to,const void *from,unsigned long n);
+ * Purpose  : copy a block from user memory to kernel memory
+ * Params   : to   - kernel memory
+ *          : from - user memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+.Lcfu_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+USER(	TUSER(	ldrb)	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		sub	r2, r2, ip
+		b	.Lcfu_dest_aligned
+
+ENTRY(__copy_from_user)
+		stmfd	sp!, {r0, r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.Lcfu_not_enough
+		ands	ip, r0, #3
+		bne	.Lcfu_dest_not_aligned
+.Lcfu_dest_aligned:
+		ands	ip, r1, #3
+		bne	.Lcfu_src_not_aligned
+
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.Lcfu_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_0nowords
+USER(	TUSER(	ldr)	r3, [r1], #4)
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.Lcfu_0rem8lp
+
+.Lcfu_0cpy8lp:	ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmia	r0!, {r3 - r6}
+		ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_0cpy8lp
+
+.Lcfu_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmgeia	r0!, {r3 - r6}
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+	TUSER(	ldrne) r3, [r1], #4			@ Shouldnt fault
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_0fupi
+.Lcfu_0nowords:	teq	ip, #0
+		beq	.Lcfu_finished
+.Lcfu_nowords:	cmp	ip, #2
+USER(	TUSER(	ldrb)	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_not_enough:
+		movs	ip, r2
+		bne	.Lcfu_nowords
+.Lcfu_finished:	mov	r0, #0
+		add	sp, sp, #8
+		ldmfd	sp!, {r4 - r7, pc}
+
+.Lcfu_src_not_aligned:
+		bic	r1, r1, #3
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		cmp	ip, #2
+		bgt	.Lcfu_3fupi
+		beq	.Lcfu_2fupi
+.Lcfu_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_1nowords
+		mov	r3, r7, pull #8
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #24
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_1rem8lp
+
+.Lcfu_1cpy8lp:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_1cpy8lp
+
+.Lcfu_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #8
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #24
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_1fupi
+.Lcfu_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_2
+		strgeb	r3, [r0], #1
+		movgt	r3, r7, get_byte_3
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_2nowords
+		mov	r3, r7, pull #16
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #16
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_2rem8lp
+
+
+.Lcfu_2cpy8lp:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}
+		bpl	.Lcfu_2cpy8lp
+
+.Lcfu_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #16
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #16
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_2fupi
+.Lcfu_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_3
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #0)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+
+.Lcfu_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.Lcfu_3nowords
+		mov	r3, r7, pull #24
+USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #8
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.Lcfu_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.Lcfu_3rem8lp
+
+.Lcfu_3cpy8lp:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}
+		subs	ip, ip, #16
+		bpl	.Lcfu_3cpy8lp
+
+.Lcfu_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #24
+USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #8
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.Lcfu_3fupi
+.Lcfu_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.Lcfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+USER(	TUSER(	ldrgeb) r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(	TUSER(	ldrgtb) r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.Lcfu_finished
+ENDPROC(__copy_from_user)
+
+		.pushsection .fixup,"ax"
+		.align	0
+		/*
+		 * We took an exception.  r0 contains a pointer to
+		 * the byte not copied.
+		 */
+9001:		ldr	r2, [sp], #4			@ void *to
+		sub	r2, r0, r2			@ bytes copied
+		ldr	r1, [sp], #4			@ unsigned long count
+		subs	r4, r1, r2			@ bytes left to copy
+		movne	r1, r4
+		blne	__memzero
+		mov	r0, r4
+		ldmfd	sp!, {r4 - r7, pc}
+		.popsection
+
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index 104ca40..aaa443b 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -197,7 +197,7 @@
 	at91_st_read(AT91_ST_SR);
 
 	/* Make IRQs happen for the system timer */
-	setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
+	setup_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq);
 
 	/* The 32KiHz "Slow Clock" (tick every 30517.58 nanoseconds) is used
 	 * directly for the clocksource and all clockevents, after adjusting
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 7b9c2ba..bce572a 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -726,6 +726,8 @@
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	},
 };
 
@@ -744,10 +746,12 @@
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9260_rtt_device.num_resources = 2;
+	at91sam9260_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9260_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 8df5c1b..bc2590d 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -609,6 +609,8 @@
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -626,10 +628,12 @@
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9261_rtt_device.num_resources = 2;
+	at91sam9261_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9261_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index eb6bbf8..9b6ca73 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -990,6 +990,8 @@
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1006,6 +1008,8 @@
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1027,14 +1031,14 @@
 		 * The second resource is needed only for the chosen RTT:
 		 * GPBR will serve as the storage for RTC time offset
 		 */
-		at91sam9263_rtt0_device.num_resources = 2;
+		at91sam9263_rtt0_device.num_resources = 3;
 		at91sam9263_rtt1_device.num_resources = 1;
 		pdev = &at91sam9263_rtt0_device;
 		r = rtt0_resources;
 		break;
 	case 1:
 		at91sam9263_rtt0_device.num_resources = 1;
-		at91sam9263_rtt1_device.num_resources = 2;
+		at91sam9263_rtt1_device.num_resources = 3;
 		pdev = &at91sam9263_rtt1_device;
 		r = rtt1_resources;
 		break;
@@ -1047,6 +1051,8 @@
 	pdev->name = "rtc-at91sam9";
 	r[1].start = AT91SAM9263_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	r[1].end = r[1].start + 3;
+	r[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	r[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 0607399..1b47319 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -1293,6 +1293,8 @@
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1310,10 +1312,12 @@
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9g45_rtt_device.num_resources = 2;
+	at91sam9g45_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9G45_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index f09fff9..b3d365d 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -688,6 +688,8 @@
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -705,10 +707,12 @@
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9rl_rtt_device.num_resources = 2;
+	at91sam9rl_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9RL_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index de2ec6b..188c829 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -63,6 +63,12 @@
 
 #define cpu_has_300M_plla()	(cpu_is_at91sam9g10())
 
+#define cpu_has_240M_plla()	(cpu_is_at91sam9261() \
+				|| cpu_is_at91sam9263() \
+				|| cpu_is_at91sam9rl())
+
+#define cpu_has_210M_plla()	(cpu_is_at91sam9260())
+
 #define cpu_has_pllb()		(!(cpu_is_at91sam9rl() \
 				|| cpu_is_at91sam9g45() \
 				|| cpu_is_at91sam9x5() \
@@ -706,6 +712,12 @@
 	} else if (cpu_has_800M_plla()) {
 		if (plla.rate_hz > 800000000)
 			pll_overclock = true;
+	} else if (cpu_has_240M_plla()) {
+		if (plla.rate_hz > 240000000)
+			pll_overclock = true;
+	} else if (cpu_has_210M_plla()) {
+		if (plla.rate_hz > 210000000)
+			pll_overclock = true;
 	} else {
 		if (plla.rate_hz > 209000000)
 			pll_overclock = true;
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index 4db5de5..6321567 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -102,7 +102,8 @@
 void __init dove_ge00_init(struct mv643xx_eth_platform_data *eth_data)
 {
 	orion_ge00_init(eth_data, DOVE_GE00_PHYS_BASE,
-			IRQ_DOVE_GE00_SUM, IRQ_DOVE_GE00_ERR);
+			IRQ_DOVE_GE00_SUM, IRQ_DOVE_GE00_ERR,
+			1600);
 }
 
 /*****************************************************************************
diff --git a/arch/arm/mach-exynos/mach-origen.c b/arch/arm/mach-exynos/mach-origen.c
index 5ca8030..4e574c2 100644
--- a/arch/arm/mach-exynos/mach-origen.c
+++ b/arch/arm/mach-exynos/mach-origen.c
@@ -42,6 +42,7 @@
 #include <plat/backlight.h>
 #include <plat/fb.h>
 #include <plat/mfc.h>
+#include <plat/hdmi.h>
 
 #include <mach/ohci.h>
 #include <mach/map.h>
@@ -734,6 +735,11 @@
 	s3c_gpio_setpull(EXYNOS4_GPX2(2), S3C_GPIO_PULL_NONE);
 }
 
+/* I2C module and id for HDMIPHY */
+static struct i2c_board_info hdmiphy_info = {
+	I2C_BOARD_INFO("hdmiphy-exynos4210", 0x38),
+};
+
 static void s5p_tv_setup(void)
 {
 	/* Direct HPD to HDMI chip */
@@ -781,6 +787,7 @@
 
 	s5p_tv_setup();
 	s5p_i2c_hdmiphy_set_platdata(NULL);
+	s5p_hdmi_set_platdata(&hdmiphy_info, NULL, 0);
 
 #ifdef CONFIG_DRM_EXYNOS
 	s5p_device_fimd0.dev.platform_data = &drm_fimd_pdata;
diff --git a/arch/arm/mach-exynos/mach-smdkv310.c b/arch/arm/mach-exynos/mach-smdkv310.c
index 3cfa688..73f2bce 100644
--- a/arch/arm/mach-exynos/mach-smdkv310.c
+++ b/arch/arm/mach-exynos/mach-smdkv310.c
@@ -40,6 +40,7 @@
 #include <plat/mfc.h>
 #include <plat/ehci.h>
 #include <plat/clock.h>
+#include <plat/hdmi.h>
 
 #include <mach/map.h>
 #include <mach/ohci.h>
@@ -354,6 +355,11 @@
 	.pwm_period_ns  = 1000,
 };
 
+/* I2C module and id for HDMIPHY */
+static struct i2c_board_info hdmiphy_info = {
+	I2C_BOARD_INFO("hdmiphy-exynos4210", 0x38),
+};
+
 static void s5p_tv_setup(void)
 {
 	/* direct HPD to HDMI chip */
@@ -388,6 +394,7 @@
 
 	s5p_tv_setup();
 	s5p_i2c_hdmiphy_set_platdata(NULL);
+	s5p_hdmi_set_platdata(&hdmiphy_info, NULL, 0);
 
 	samsung_keypad_set_platdata(&smdkv310_keypad_data);
 
diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c
index ca70e5f..020852d 100644
--- a/arch/arm/mach-gemini/irq.c
+++ b/arch/arm/mach-gemini/irq.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
+#include <asm/system_misc.h>
 #include <mach/hardware.h>
 
 #define IRQ_SOURCE(base_addr)	(base_addr + 0x00)
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 07f7c22..d004d37 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -9,7 +9,8 @@
 obj-$(CONFIG_SOC_IMX31) += mm-imx3.o cpu-imx31.o clk-imx31.o iomux-imx31.o ehci-imx31.o pm-imx3.o
 obj-$(CONFIG_SOC_IMX35) += mm-imx3.o cpu-imx35.o clk-imx35.o ehci-imx35.o pm-imx3.o
 
-obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o pm-imx5.o cpu_op-mx51.o
+imx5-pm-$(CONFIG_PM) += pm-imx5.o
+obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o $(imx5-pm-y) cpu_op-mx51.o
 
 obj-$(CONFIG_COMMON_CLK) += clk-pllv1.o clk-pllv2.o clk-pllv3.o clk-gate2.o \
 			    clk-pfd.o clk-busy.o
@@ -70,14 +71,13 @@
 obj-$(CONFIG_HAVE_IMX_GPC) += gpc.o
 obj-$(CONFIG_HAVE_IMX_MMDC) += mmdc.o
 obj-$(CONFIG_HAVE_IMX_SRC) += src.o
-obj-$(CONFIG_CPU_V7) += head-v7.o
-AFLAGS_head-v7.o :=-Wa,-march=armv7-a
-obj-$(CONFIG_SMP) += platsmp.o
+AFLAGS_headsmp.o :=-Wa,-march=armv7-a
+obj-$(CONFIG_SMP) += headsmp.o platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
 obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o
 
 ifeq ($(CONFIG_PM),y)
-obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o
+obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o
 endif
 
 # i.MX5 based machines
diff --git a/arch/arm/mach-imx/clk-imx25.c b/arch/arm/mach-imx/clk-imx25.c
index fdd8cc8..4431a62 100644
--- a/arch/arm/mach-imx/clk-imx25.c
+++ b/arch/arm/mach-imx/clk-imx25.c
@@ -222,10 +222,8 @@
 	clk_register_clkdev(clk[lcdc_ipg], "ipg", "imx-fb.0");
 	clk_register_clkdev(clk[lcdc_ahb], "ahb", "imx-fb.0");
 	clk_register_clkdev(clk[wdt_ipg], NULL, "imx2-wdt.0");
-	clk_register_clkdev(clk[ssi1_ipg_per], "per", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi1_ipg], "ipg", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi2_ipg_per], "per", "imx-ssi.1");
-	clk_register_clkdev(clk[ssi2_ipg], "ipg", "imx-ssi.1");
+	clk_register_clkdev(clk[ssi1_ipg], NULL, "imx-ssi.0");
+	clk_register_clkdev(clk[ssi2_ipg], NULL, "imx-ssi.1");
 	clk_register_clkdev(clk[esdhc1_ipg_per], "per", "sdhci-esdhc-imx25.0");
 	clk_register_clkdev(clk[esdhc1_ipg], "ipg", "sdhci-esdhc-imx25.0");
 	clk_register_clkdev(clk[esdhc1_ahb], "ahb", "sdhci-esdhc-imx25.0");
diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c
index c6422fb..65fb8bc 100644
--- a/arch/arm/mach-imx/clk-imx35.c
+++ b/arch/arm/mach-imx/clk-imx35.c
@@ -230,10 +230,8 @@
 	clk_register_clkdev(clk[ipu_gate], NULL, "mx3_sdc_fb");
 	clk_register_clkdev(clk[owire_gate], NULL, "mxc_w1");
 	clk_register_clkdev(clk[sdma_gate], NULL, "imx35-sdma");
-	clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi1_div_post], "per", "imx-ssi.0");
-	clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.1");
-	clk_register_clkdev(clk[ssi2_div_post], "per", "imx-ssi.1");
+	clk_register_clkdev(clk[ssi1_gate], NULL, "imx-ssi.0");
+	clk_register_clkdev(clk[ssi2_gate], NULL, "imx-ssi.1");
 	/* i.mx35 has the i.mx21 type uart */
 	clk_register_clkdev(clk[uart1_gate], "per", "imx21-uart.0");
 	clk_register_clkdev(clk[ipg], "ipg", "imx21-uart.0");
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index ea89520..4233d9e 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -152,7 +152,7 @@
 	ssi2, ssi3, uart_ipg, uart_serial, usboh3, usdhc1, usdhc2, usdhc3,
 	usdhc4, vdo_axi, vpu_axi, cko1, pll1_sys, pll2_bus, pll3_usb_otg,
 	pll4_audio, pll5_video, pll6_mlb, pll7_usb_host, pll8_enet, ssi1_ipg,
-	ssi2_ipg, ssi3_ipg, rom, usbphy1, usbphy2,
+	ssi2_ipg, ssi3_ipg, rom, usbphy1, usbphy2, ldb_di0_div_3_5, ldb_di1_div_3_5,
 	clk_max
 };
 
@@ -288,8 +288,10 @@
 	clk[gpu3d_shader]     = imx_clk_divider("gpu3d_shader",     "gpu3d_shader_sel",  base + 0x18, 29, 3);
 	clk[ipu1_podf]        = imx_clk_divider("ipu1_podf",        "ipu1_sel",          base + 0x3c, 11, 3);
 	clk[ipu2_podf]        = imx_clk_divider("ipu2_podf",        "ipu2_sel",          base + 0x3c, 16, 3);
-	clk[ldb_di0_podf]     = imx_clk_divider("ldb_di0_podf",     "ldb_di0_sel",       base + 0x20, 10, 1);
-	clk[ldb_di1_podf]     = imx_clk_divider("ldb_di1_podf",     "ldb_di1_sel",       base + 0x20, 11, 1);
+	clk[ldb_di0_div_3_5]  = imx_clk_fixed_factor("ldb_di0_div_3_5", "ldb_di0_sel", 2, 7);
+	clk[ldb_di0_podf]     = imx_clk_divider("ldb_di0_podf",     "ldb_di0_div_3_5",       base + 0x20, 10, 1);
+	clk[ldb_di1_div_3_5]  = imx_clk_fixed_factor("ldb_di1_div_3_5", "ldb_di1_sel", 2, 7);
+	clk[ldb_di1_podf]     = imx_clk_divider("ldb_di1_podf",     "ldb_di1_div_3_5",   base + 0x20, 11, 1);
 	clk[ipu1_di0_pre]     = imx_clk_divider("ipu1_di0_pre",     "ipu1_di0_pre_sel",  base + 0x34, 3,  3);
 	clk[ipu1_di1_pre]     = imx_clk_divider("ipu1_di1_pre",     "ipu1_di1_pre_sel",  base + 0x34, 12, 3);
 	clk[ipu2_di0_pre]     = imx_clk_divider("ipu2_di0_pre",     "ipu2_di0_pre_sel",  base + 0x38, 3,  3);
diff --git a/arch/arm/mach-imx/head-v7.S b/arch/arm/mach-imx/headsmp.S
similarity index 100%
rename from arch/arm/mach-imx/head-v7.S
rename to arch/arm/mach-imx/headsmp.S
diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c
index 20ed2d5..f8f7437 100644
--- a/arch/arm/mach-imx/hotplug.c
+++ b/arch/arm/mach-imx/hotplug.c
@@ -42,22 +42,6 @@
 	  : "cc");
 }
 
-static inline void cpu_leave_lowpower(void)
-{
-	unsigned int v;
-
-	asm volatile(
-		"mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, %1\n"
-	"	mcr	p15, 0, %0, c1, c0, 0\n"
-	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	orr	%0, %0, %2\n"
-	"	mcr	p15, 0, %0, c1, c0, 1\n"
-	  : "=&r" (v)
-	  : "Ir" (CR_C), "Ir" (0x40)
-	  : "cc");
-}
-
 /*
  * platform-specific code to shutdown a CPU
  *
@@ -67,11 +51,10 @@
 {
 	cpu_enter_lowpower();
 	imx_enable_cpu(cpu, false);
-	cpu_do_idle();
-	cpu_leave_lowpower();
 
-	/* We should never return from idle */
-	panic("cpu %d unexpectedly exit from shutdown\n", cpu);
+	/* spin here until hardware takes it down */
+	while (1)
+		;
 }
 
 int platform_cpu_disable(unsigned int cpu)
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 5ec0608..045b3f6 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -71,7 +71,7 @@
 /* For imx6q sabrelite board: set KSZ9021RN RGMII pad skew */
 static int ksz9021rn_phy_fixup(struct phy_device *phydev)
 {
-	if (IS_ENABLED(CONFIG_PHYLIB)) {
+	if (IS_BUILTIN(CONFIG_PHYLIB)) {
 		/* min rx data delay */
 		phy_write(phydev, 0x0b, 0x8105);
 		phy_write(phydev, 0x0c, 0x0000);
@@ -112,7 +112,7 @@
 
 static void __init imx6q_sabrelite_init(void)
 {
-	if (IS_ENABLED(CONFIG_PHYLIB))
+	if (IS_BUILTIN(CONFIG_PHYLIB))
 		phy_register_fixup_for_uid(PHY_ID_KSZ9021, MICREL_PHY_ID_MASK,
 				ksz9021rn_phy_fixup);
 	imx6q_sabrelite_cko1_setup();
diff --git a/arch/arm/mach-kirkwood/Makefile.boot b/arch/arm/mach-kirkwood/Makefile.boot
index a571755..a13299d 100644
--- a/arch/arm/mach-kirkwood/Makefile.boot
+++ b/arch/arm/mach-kirkwood/Makefile.boot
@@ -7,7 +7,8 @@
 dtb-$(CONFIG_MACH_DLINK_KIRKWOOD_DT) += kirkwood-dns325.dtb
 dtb-$(CONFIG_MACH_ICONNECT_DT) += kirkwood-iconnect.dtb
 dtb-$(CONFIG_MACH_IB62X0_DT) += kirkwood-ib62x0.dtb
-dtb-$(CONFIG_MACH_TS219_DT)	+= kirkwood-qnap-ts219.dtb
+dtb-$(CONFIG_MACH_TS219_DT)	+= kirkwood-ts219-6281.dtb
+dtb-$(CONFIG_MACH_TS219_DT)	+= kirkwood-ts219-6282.dtb
 dtb-$(CONFIG_MACH_GOFLEXNET_DT) += kirkwood-goflexnet.dtb
 dtb-$(CONFIG_MACH_LSXL_DT) += kirkwood-lschlv2.dtb
 dtb-$(CONFIG_MACH_LSXL_DT) += kirkwood-lsxhl.dtb
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index c4b64ad..1201191 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -301,7 +301,7 @@
 {
 	orion_ge00_init(eth_data,
 			GE00_PHYS_BASE, IRQ_KIRKWOOD_GE00_SUM,
-			IRQ_KIRKWOOD_GE00_ERR);
+			IRQ_KIRKWOOD_GE00_ERR, 1600);
 	/* The interface forgets the MAC address assigned by u-boot if
 	the clock is turned off, so claim the clk now. */
 	clk_prepare_enable(ge0);
@@ -315,7 +315,7 @@
 {
 	orion_ge01_init(eth_data,
 			GE01_PHYS_BASE, IRQ_KIRKWOOD_GE01_SUM,
-			IRQ_KIRKWOOD_GE01_ERR);
+			IRQ_KIRKWOOD_GE01_ERR, 1600);
 	clk_prepare_enable(ge1);
 }
 
@@ -517,6 +517,13 @@
 void __init kirkwood_init_early(void)
 {
 	orion_time_set_base(TIMER_VIRT_BASE);
+
+	/*
+	 * Some Kirkwood devices allocate their coherent buffers from atomic
+	 * context. Increase size of atomic coherent pool to make sure such
+	 * the allocations won't fail.
+	 */
+	init_dma_coherent_pool_size(SZ_1M);
 }
 
 int kirkwood_tclk;
diff --git a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
index d933593..be90b7d 100644
--- a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
+++ b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/sizes.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/partitions.h>
 #include <linux/ata_platform.h>
diff --git a/arch/arm/mach-mmp/sram.c b/arch/arm/mach-mmp/sram.c
index 4304f95..7e8a5a2 100644
--- a/arch/arm/mach-mmp/sram.c
+++ b/arch/arm/mach-mmp/sram.c
@@ -68,7 +68,7 @@
 	struct resource *res;
 	int ret = 0;
 
-	if (!pdata && !pdata->pool_name)
+	if (!pdata || !pdata->pool_name)
 		return -ENODEV;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
diff --git a/arch/arm/mach-mv78xx0/addr-map.c b/arch/arm/mach-mv78xx0/addr-map.c
index 62b53d7..a9bc841 100644
--- a/arch/arm/mach-mv78xx0/addr-map.c
+++ b/arch/arm/mach-mv78xx0/addr-map.c
@@ -37,7 +37,7 @@
 #define WIN0_OFF(n)		(BRIDGE_VIRT_BASE + 0x0000 + ((n) << 4))
 #define WIN8_OFF(n)		(BRIDGE_VIRT_BASE + 0x0900 + (((n) - 8) << 4))
 
-static void __init __iomem *win_cfg_base(int win)
+static void __init __iomem *win_cfg_base(const struct orion_addr_map_cfg *cfg, int win)
 {
 	/*
 	 * Find the control register base address for this window.
diff --git a/arch/arm/mach-mv78xx0/common.c b/arch/arm/mach-mv78xx0/common.c
index b4c53b8..3057f7d 100644
--- a/arch/arm/mach-mv78xx0/common.c
+++ b/arch/arm/mach-mv78xx0/common.c
@@ -213,7 +213,8 @@
 {
 	orion_ge00_init(eth_data,
 			GE00_PHYS_BASE, IRQ_MV78XX0_GE00_SUM,
-			IRQ_MV78XX0_GE_ERR);
+			IRQ_MV78XX0_GE_ERR,
+			MV643XX_TX_CSUM_DEFAULT_LIMIT);
 }
 
 
@@ -224,7 +225,8 @@
 {
 	orion_ge01_init(eth_data,
 			GE01_PHYS_BASE, IRQ_MV78XX0_GE01_SUM,
-			NO_IRQ);
+			NO_IRQ,
+			MV643XX_TX_CSUM_DEFAULT_LIMIT);
 }
 
 
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index dd2db02..346fd26 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -62,13 +62,14 @@
 	select PM_OPP if PM
 	select USB_ARCH_HAS_EHCI if USB_SUPPORT
 	select ARM_CPU_SUSPEND if PM
-	select ARCH_NEEDS_CPU_IDLE_COUPLED
+	select ARCH_NEEDS_CPU_IDLE_COUPLED if SMP
 
 config SOC_OMAP5
 	bool "TI OMAP5"
 	select CPU_V7
 	select ARM_GIC
 	select HAVE_SMP
+	select ARM_CPU_SUSPEND if PM
 
 comment "OMAP Core Type"
 	depends on ARCH_OMAP2
@@ -231,10 +232,11 @@
 	select OMAP_PACKAGE_CBB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
-config MACH_OMAP3_TOUCHBOOK
+config MACH_TOUCHBOOK
 	bool "OMAP3 Touch Book"
 	depends on ARCH_OMAP3
 	default y
+	select OMAP_PACKAGE_CBB
 
 config MACH_OMAP_3430SDP
 	bool "OMAP 3430 SDP board"
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index f6a24b3..34c2c7f 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -255,7 +255,7 @@
 obj-$(CONFIG_MACH_CM_T35)		+= board-cm-t35.o
 obj-$(CONFIG_MACH_CM_T3517)		+= board-cm-t3517.o
 obj-$(CONFIG_MACH_IGEP0020)		+= board-igep0020.o
-obj-$(CONFIG_MACH_OMAP3_TOUCHBOOK)	+= board-omap3touchbook.o
+obj-$(CONFIG_MACH_TOUCHBOOK)		+= board-omap3touchbook.o
 obj-$(CONFIG_MACH_OMAP_4430SDP)		+= board-4430sdp.o
 obj-$(CONFIG_MACH_OMAP4_PANDA)		+= board-omap4panda.o
 
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 7491529..2821448 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -554,6 +554,8 @@
 
 #ifdef CONFIG_OMAP_MUX
 static struct omap_board_mux board_mux[] __initdata = {
+	/* SMSC9221 LAN Controller ETH IRQ (GPIO_176) */
+	OMAP3_MUX(MCSPI1_CS2, OMAP_MUX_MODE4 | OMAP_PIN_INPUT),
 	{ .reg_offset = OMAP_MUX_TERMINATOR },
 };
 #endif
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index ef230a0..0d362e9 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -58,6 +58,7 @@
 #include "hsmmc.h"
 #include "common-board-devices.h"
 
+#define OMAP3_EVM_TS_GPIO	175
 #define OMAP3_EVM_EHCI_VBUS	22
 #define OMAP3_EVM_EHCI_SELECT	61
 
diff --git a/arch/arm/mach-omap2/clock33xx_data.c b/arch/arm/mach-omap2/clock33xx_data.c
index 25bbcc7..ae27de8 100644
--- a/arch/arm/mach-omap2/clock33xx_data.c
+++ b/arch/arm/mach-omap2/clock33xx_data.c
@@ -1036,13 +1036,13 @@
 	CLK(NULL,	"mmu_fck",		&mmu_fck,	CK_AM33XX),
 	CLK(NULL,	"smartreflex0_fck",	&smartreflex0_fck,	CK_AM33XX),
 	CLK(NULL,	"smartreflex1_fck",	&smartreflex1_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt1_fck",		&timer1_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt2_fck",		&timer2_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt3_fck",		&timer3_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt4_fck",		&timer4_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt5_fck",		&timer5_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt6_fck",		&timer6_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt7_fck",		&timer7_fck,	CK_AM33XX),
+	CLK(NULL,	"timer1_fck",		&timer1_fck,	CK_AM33XX),
+	CLK(NULL,	"timer2_fck",		&timer2_fck,	CK_AM33XX),
+	CLK(NULL,	"timer3_fck",		&timer3_fck,	CK_AM33XX),
+	CLK(NULL,	"timer4_fck",		&timer4_fck,	CK_AM33XX),
+	CLK(NULL,	"timer5_fck",		&timer5_fck,	CK_AM33XX),
+	CLK(NULL,	"timer6_fck",		&timer6_fck,	CK_AM33XX),
+	CLK(NULL,	"timer7_fck",		&timer7_fck,	CK_AM33XX),
 	CLK(NULL,	"usbotg_fck",		&usbotg_fck,	CK_AM33XX),
 	CLK(NULL,	"ieee5000_fck",		&ieee5000_fck,	CK_AM33XX),
 	CLK(NULL,	"wdt1_fck",		&wdt1_fck,	CK_AM33XX),
diff --git a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
index a0d68db..f99e65c 100644
--- a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
+++ b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
@@ -241,6 +241,52 @@
 		_clkdm_del_autodeps(clkdm);
 }
 
+static int omap3xxx_clkdm_clk_enable(struct clockdomain *clkdm)
+{
+	bool hwsup = false;
+
+	if (!clkdm->clktrctrl_mask)
+		return 0;
+
+	hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs,
+				clkdm->clktrctrl_mask);
+
+	if (hwsup) {
+		/* Disable HW transitions when we are changing deps */
+		_disable_hwsup(clkdm);
+		_clkdm_add_autodeps(clkdm);
+		_enable_hwsup(clkdm);
+	} else {
+		if (clkdm->flags & CLKDM_CAN_FORCE_WAKEUP)
+			omap3_clkdm_wakeup(clkdm);
+	}
+
+	return 0;
+}
+
+static int omap3xxx_clkdm_clk_disable(struct clockdomain *clkdm)
+{
+	bool hwsup = false;
+
+	if (!clkdm->clktrctrl_mask)
+		return 0;
+
+	hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs,
+				clkdm->clktrctrl_mask);
+
+	if (hwsup) {
+		/* Disable HW transitions when we are changing deps */
+		_disable_hwsup(clkdm);
+		_clkdm_del_autodeps(clkdm);
+		_enable_hwsup(clkdm);
+	} else {
+		if (clkdm->flags & CLKDM_CAN_FORCE_SLEEP)
+			omap3_clkdm_sleep(clkdm);
+	}
+
+	return 0;
+}
+
 struct clkdm_ops omap2_clkdm_operations = {
 	.clkdm_add_wkdep	= omap2_clkdm_add_wkdep,
 	.clkdm_del_wkdep	= omap2_clkdm_del_wkdep,
@@ -267,6 +313,6 @@
 	.clkdm_wakeup		= omap3_clkdm_wakeup,
 	.clkdm_allow_idle	= omap3_clkdm_allow_idle,
 	.clkdm_deny_idle	= omap3_clkdm_deny_idle,
-	.clkdm_clk_enable	= omap2_clkdm_clk_enable,
-	.clkdm_clk_disable	= omap2_clkdm_clk_disable,
+	.clkdm_clk_enable	= omap3xxx_clkdm_clk_enable,
+	.clkdm_clk_disable	= omap3xxx_clkdm_clk_disable,
 };
diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h
index 766338f..975f6bd 100644
--- a/arch/arm/mach-omap2/cm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-34xx.h
@@ -67,6 +67,7 @@
 #define OMAP3430_EN_IVA2_DPLL_MASK			(0x7 << 0)
 
 /* CM_IDLEST_IVA2 */
+#define OMAP3430_ST_IVA2_SHIFT				0
 #define OMAP3430_ST_IVA2_MASK				(1 << 0)
 
 /* CM_IDLEST_PLL_IVA2 */
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index 1473474..c187586 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -35,16 +35,6 @@
 	.turbo_mode	= 0,
 };
 
-/*
- * ADS7846 driver maybe request a gpio according to the value
- * of pdata->get_pendown_state, but we have done this. So set
- * get_pendown_state to avoid twice gpio requesting.
- */
-static int omap3_get_pendown_state(void)
-{
-	return !gpio_get_value(OMAP3_EVM_TS_GPIO);
-}
-
 static struct ads7846_platform_data ads7846_config = {
 	.x_max			= 0x0fff,
 	.y_max			= 0x0fff,
@@ -55,7 +45,6 @@
 	.debounce_rep		= 1,
 	.gpio_pendown		= -EINVAL,
 	.keep_vref_on		= 1,
-	.get_pendown_state	= &omap3_get_pendown_state,
 };
 
 static struct spi_board_info ads7846_spi_board_info __initdata = {
diff --git a/arch/arm/mach-omap2/common-board-devices.h b/arch/arm/mach-omap2/common-board-devices.h
index 4c4ef6a..a0b4a428 100644
--- a/arch/arm/mach-omap2/common-board-devices.h
+++ b/arch/arm/mach-omap2/common-board-devices.h
@@ -4,7 +4,6 @@
 #include "twl-common.h"
 
 #define NAND_BLOCK_SIZE	SZ_128K
-#define OMAP3_EVM_TS_GPIO	175
 
 struct mtd_partition;
 struct ads7846_platform_data;
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index ee05e19..288bee6 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -238,8 +238,9 @@
 	for_each_cpu(cpu_id, cpu_online_mask) {
 		dev = &per_cpu(omap4_idle_dev, cpu_id);
 		dev->cpu = cpu_id;
+#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
 		dev->coupled_cpus = *cpu_online_mask;
-
+#endif
 		cpuidle_register_driver(&omap4_idle_driver);
 
 		if (cpuidle_register_device(dev)) {
diff --git a/arch/arm/mach-omap2/mux.h b/arch/arm/mach-omap2/mux.h
index 471e62a..76f9b3c 100644
--- a/arch/arm/mach-omap2/mux.h
+++ b/arch/arm/mach-omap2/mux.h
@@ -127,7 +127,6 @@
  * @gpio:	GPIO number
  * @muxnames:	available signal modes for a ball
  * @balls:	available balls on the package
- * @partition:	mux partition
  */
 struct omap_mux {
 	u16	reg_offset;
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 05fdebf..330d4c6 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -46,7 +46,7 @@
 static void __iomem *wakeupgen_base;
 static void __iomem *sar_base;
 static DEFINE_SPINLOCK(wakeupgen_lock);
-static unsigned int irq_target_cpu[NR_IRQS];
+static unsigned int irq_target_cpu[MAX_IRQS];
 static unsigned int irq_banks = MAX_NR_REG_BANKS;
 static unsigned int max_irqs = MAX_IRQS;
 static unsigned int omap_secure_apis;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 6ca8e51..37afbd1 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1889,6 +1889,7 @@
 			_enable_sysc(oh);
 		}
 	} else {
+		_omap4_disable_module(oh);
 		_disable_clocks(oh);
 		pr_debug("omap_hwmod: %s: _wait_target_ready: %d\n",
 			 oh->name, r);
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index c9e3820..ce7e606 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -100,9 +100,9 @@
 
 /* IVA2 (IVA2) */
 static struct omap_hwmod_rst_info omap3xxx_iva_resets[] = {
-	{ .name = "logic", .rst_shift = 0 },
-	{ .name = "seq0", .rst_shift = 1 },
-	{ .name = "seq1", .rst_shift = 2 },
+	{ .name = "logic", .rst_shift = 0, .st_shift = 8 },
+	{ .name = "seq0", .rst_shift = 1, .st_shift = 9 },
+	{ .name = "seq1", .rst_shift = 2, .st_shift = 10 },
 };
 
 static struct omap_hwmod omap3xxx_iva_hwmod = {
@@ -112,6 +112,15 @@
 	.rst_lines	= omap3xxx_iva_resets,
 	.rst_lines_cnt	= ARRAY_SIZE(omap3xxx_iva_resets),
 	.main_clk	= "iva2_ck",
+	.prcm = {
+		.omap2 = {
+			.module_offs = OMAP3430_IVA2_MOD,
+			.prcm_reg_id = 1,
+			.module_bit = OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT,
+			.idlest_reg_id = 1,
+			.idlest_idle_bit = OMAP3430_ST_IVA2_SHIFT,
+		}
+	},
 };
 
 /* timer class */
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 242aee4..afb6091 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -4210,7 +4210,7 @@
 };
 
 /* dsp -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_dsp__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_dsp__sl2if = {
 	.master		= &omap44xx_dsp_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "dpll_iva_m5x2_ck",
@@ -4828,7 +4828,7 @@
 };
 
 /* iva -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_iva__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_iva__sl2if = {
 	.master		= &omap44xx_iva_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "dpll_iva_m5x2_ck",
@@ -5362,7 +5362,7 @@
 };
 
 /* l3_main_2 -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_l3_main_2__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l3_main_2__sl2if = {
 	.master		= &omap44xx_l3_main_2_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "l3_div_ck",
@@ -6032,7 +6032,7 @@
 	&omap44xx_l4_abe__dmic,
 	&omap44xx_l4_abe__dmic_dma,
 	&omap44xx_dsp__iva,
-	&omap44xx_dsp__sl2if,
+	/* &omap44xx_dsp__sl2if, */
 	&omap44xx_l4_cfg__dsp,
 	&omap44xx_l3_main_2__dss,
 	&omap44xx_l4_per__dss,
@@ -6068,7 +6068,7 @@
 	&omap44xx_l4_per__i2c4,
 	&omap44xx_l3_main_2__ipu,
 	&omap44xx_l3_main_2__iss,
-	&omap44xx_iva__sl2if,
+	/* &omap44xx_iva__sl2if, */
 	&omap44xx_l3_main_2__iva,
 	&omap44xx_l4_wkup__kbd,
 	&omap44xx_l4_cfg__mailbox,
@@ -6099,7 +6099,7 @@
 	&omap44xx_l4_cfg__cm_core,
 	&omap44xx_l4_wkup__prm,
 	&omap44xx_l4_wkup__scrm,
-	&omap44xx_l3_main_2__sl2if,
+	/* &omap44xx_l3_main_2__sl2if, */
 	&omap44xx_l4_abe__slimbus1,
 	&omap44xx_l4_abe__slimbus1_dma,
 	&omap44xx_l4_per__slimbus2,
diff --git a/arch/arm/mach-omap2/opp4xxx_data.c b/arch/arm/mach-omap2/opp4xxx_data.c
index 2293ba2..c95415d 100644
--- a/arch/arm/mach-omap2/opp4xxx_data.c
+++ b/arch/arm/mach-omap2/opp4xxx_data.c
@@ -94,7 +94,7 @@
 {
 	int r = -ENODEV;
 
-	if (!cpu_is_omap44xx())
+	if (!cpu_is_omap443x())
 		return r;
 
 	r = omap_init_opp_table(omap44xx_opp_def_list,
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index e4fc88c..05bd8f0 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -272,21 +272,16 @@
 	per_next_state = pwrdm_read_next_pwrst(per_pwrdm);
 	core_next_state = pwrdm_read_next_pwrst(core_pwrdm);
 
-	if (mpu_next_state < PWRDM_POWER_ON) {
-		pwrdm_pre_transition(mpu_pwrdm);
-		pwrdm_pre_transition(neon_pwrdm);
-	}
+	pwrdm_pre_transition(NULL);
 
 	/* PER */
 	if (per_next_state < PWRDM_POWER_ON) {
-		pwrdm_pre_transition(per_pwrdm);
 		per_going_off = (per_next_state == PWRDM_POWER_OFF) ? 1 : 0;
 		omap2_gpio_prepare_for_idle(per_going_off);
 	}
 
 	/* CORE */
 	if (core_next_state < PWRDM_POWER_ON) {
-		pwrdm_pre_transition(core_pwrdm);
 		if (core_next_state == PWRDM_POWER_OFF) {
 			omap3_core_save_context();
 			omap3_cm_save_context();
@@ -339,20 +334,14 @@
 			omap2_prm_clear_mod_reg_bits(OMAP3430_AUTO_OFF_MASK,
 					       OMAP3430_GR_MOD,
 					       OMAP3_PRM_VOLTCTRL_OFFSET);
-		pwrdm_post_transition(core_pwrdm);
 	}
 	omap3_intc_resume_idle();
 
-	/* PER */
-	if (per_next_state < PWRDM_POWER_ON) {
-		omap2_gpio_resume_after_idle();
-		pwrdm_post_transition(per_pwrdm);
-	}
+	pwrdm_post_transition(NULL);
 
-	if (mpu_next_state < PWRDM_POWER_ON) {
-		pwrdm_post_transition(mpu_pwrdm);
-		pwrdm_post_transition(neon_pwrdm);
-	}
+	/* PER */
+	if (per_next_state < PWRDM_POWER_ON)
+		omap2_gpio_resume_after_idle();
 }
 
 static void omap3_pm_idle(void)
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index 9f6b83d..91e71d8 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -56,9 +56,13 @@
  * The restore function pointer is stored at CPUx_WAKEUP_NS_PA_ADDR_OFFSET.
  * It returns to the caller for CPU INACTIVE and ON power states or in case
  * CPU failed to transition to targeted OFF/DORMANT state.
+ *
+ * omap4_finish_suspend() calls v7_flush_dcache_all() which doesn't save
+ * stack frame and it expects the caller to take care of it. Hence the entire
+ * stack frame is saved to avoid possible stack corruption.
  */
 ENTRY(omap4_finish_suspend)
-	stmfd	sp!, {lr}
+	stmfd	sp!, {r4-r12, lr}
 	cmp	r0, #0x0
 	beq	do_WFI				@ No lowpower state, jump to WFI
 
@@ -226,7 +230,7 @@
 skip_scu_gp_clear:
 	isb
 	dsb
-	ldmfd	sp!, {pc}
+	ldmfd	sp!, {r4-r12, pc}
 ENDPROC(omap4_finish_suspend)
 
 /*
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 2ff6d41..2ba4f57 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -260,6 +260,7 @@
 	return 0;
 }
 
+#ifdef CONFIG_OMAP_32K_TIMER
 /* Setup free-running counter for clocksource */
 static int __init omap2_sync32k_clocksource_init(void)
 {
@@ -299,6 +300,12 @@
 
 	return ret;
 }
+#else
+static inline int omap2_sync32k_clocksource_init(void)
+{
+	return -ENODEV;
+}
+#endif
 
 static void __init omap2_gptimer_clocksource_init(int gptimer_id,
 						const char *fck_source)
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index de47f17..db5ff66 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -67,6 +67,7 @@
 			   const char *pmic_type, int pmic_irq,
 			   struct twl4030_platform_data *pmic_data)
 {
+	omap_mux_init_signal("sys_nirq", OMAP_PIN_INPUT_PULLUP | OMAP_PIN_OFF_WAKEUPENABLE);
 	strncpy(pmic_i2c_board_info.type, pmic_type,
 		sizeof(pmic_i2c_board_info.type));
 	pmic_i2c_board_info.irq = pmic_irq;
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index 9148b22..410291c 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -109,7 +109,8 @@
 {
 	orion_ge00_init(eth_data,
 			ORION5X_ETH_PHYS_BASE, IRQ_ORION5X_ETH_SUM,
-			IRQ_ORION5X_ETH_ERR);
+			IRQ_ORION5X_ETH_ERR,
+			MV643XX_TX_CSUM_DEFAULT_LIMIT);
 }
 
 
diff --git a/arch/arm/mach-s3c24xx/include/mach/dma.h b/arch/arm/mach-s3c24xx/include/mach/dma.h
index 454831b..ee99fd5 100644
--- a/arch/arm/mach-s3c24xx/include/mach/dma.h
+++ b/arch/arm/mach-s3c24xx/include/mach/dma.h
@@ -24,7 +24,8 @@
 */
 
 enum dma_ch {
-	DMACH_XD0,
+	DMACH_DT_PROP = -1,	/* not yet supported, do not use */
+	DMACH_XD0 = 0,
 	DMACH_XD1,
 	DMACH_SDI,
 	DMACH_SPI0,
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index cf10f92..453a6e5 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -520,13 +520,14 @@
 };
 
 /* GPIO KEY */
-#define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
+#define GPIO_KEY(c, g, d, ...) \
+	{ .code = c, .gpio = g, .desc = d, .active_low = 1, __VA_ARGS__ }
 
 static struct gpio_keys_button gpio_buttons[] = {
-	GPIO_KEY(KEY_POWER,	GPIO_PORT99,	"SW1"),
-	GPIO_KEY(KEY_BACK,	GPIO_PORT100,	"SW2"),
-	GPIO_KEY(KEY_MENU,	GPIO_PORT97,	"SW3"),
-	GPIO_KEY(KEY_HOME,	GPIO_PORT98,	"SW4"),
+	GPIO_KEY(KEY_POWER,	GPIO_PORT99,	"SW3", .wakeup = 1),
+	GPIO_KEY(KEY_BACK,	GPIO_PORT100,	"SW4"),
+	GPIO_KEY(KEY_MENU,	GPIO_PORT97,	"SW5"),
+	GPIO_KEY(KEY_HOME,	GPIO_PORT98,	"SW6"),
 };
 
 static struct gpio_keys_platform_data gpio_key_info = {
@@ -901,8 +902,8 @@
 	&camera_device,
 	&ceu0_device,
 	&fsi_device,
-	&fsi_hdmi_device,
 	&fsi_wm8978_device,
+	&fsi_hdmi_device,
 };
 
 static void __init eva_clock_init(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 7ea2b31..c129542 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -695,6 +695,7 @@
  *  - J30 "open"
  *  - modify usbhs1_get_id() USBHS_HOST -> USBHS_GADGET
  *  - add .get_vbus = usbhs_get_vbus in usbhs1_private
+ *  - check usbhs0_device(pio)/usbhs1_device(irq) order in mackerel_devices.
  */
 #define IRQ8 evt2irq(0x0300)
 #define USB_PHY_MODE		(1 << 4)
@@ -1325,8 +1326,8 @@
 	&nor_flash_device,
 	&smc911x_device,
 	&lcdc_device,
-	&usbhs1_device,
 	&usbhs0_device,
+	&usbhs1_device,
 	&leds_device,
 	&fsi_device,
 	&fsi_ak4643_device,
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index 3a528cf..fcf5a47 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -67,7 +67,7 @@
 
 static struct platform_device eth_device = {
 	.name		= "smsc911x",
-	.id		= 0,
+	.id		= -1,
 	.dev  = {
 		.platform_data = &smsc911x_platdata,
 	},
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
index ee44740..588555a 100644
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ b/arch/arm/mach-shmobile/intc-sh73a0.c
@@ -259,9 +259,9 @@
 	return 0; /* always allow wakeup */
 }
 
-#define RELOC_BASE 0x1000
+#define RELOC_BASE 0x1200
 
-/* INTCA IRQ pins at INTCS + 0x1000 to make space for GIC+INTC handling */
+/* INTCA IRQ pins at INTCS + RELOC_BASE to make space for GIC+INTC handling */
 #define INTCS_VECT_RELOC(n, vect) INTCS_VECT((n), (vect) + RELOC_BASE)
 
 INTC_IRQ_PINS_32(intca_irq_pins, 0xe6900000,
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index c013bbf..53d3d46 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -41,7 +41,6 @@
 config MACH_SNOWBALL
 	bool "U8500 Snowball platform"
 	select MACH_MOP500
-	select LEDS_GPIO
 	help
 	  Include support for the snowball development platform.
 
diff --git a/arch/arm/mach-ux500/board-mop500-msp.c b/arch/arm/mach-ux500/board-mop500-msp.c
index 9960480..df15646 100644
--- a/arch/arm/mach-ux500/board-mop500-msp.c
+++ b/arch/arm/mach-ux500/board-mop500-msp.c
@@ -191,9 +191,9 @@
 	return pdev;
 }
 
-/* Platform device for ASoC U8500 machine */
-static struct platform_device snd_soc_u8500 = {
-		.name = "snd-soc-u8500",
+/* Platform device for ASoC MOP500 machine */
+static struct platform_device snd_soc_mop500 = {
+		.name = "snd-soc-mop500",
 		.id = 0,
 		.dev = {
 			.platform_data = NULL,
@@ -227,8 +227,8 @@
 {
 	struct platform_device *msp1;
 
-	pr_info("%s: Register platform-device 'snd-soc-u8500'.\n", __func__);
-	platform_device_register(&snd_soc_u8500);
+	pr_info("%s: Register platform-device 'snd-soc-mop500'.\n", __func__);
+	platform_device_register(&snd_soc_mop500);
 
 	pr_info("Initialize MSP I2S-devices.\n");
 	db8500_add_msp_i2s(parent, 0, U8500_MSP0_BASE, IRQ_DB8500_MSP0,
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 8674a89..a534d88 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -797,6 +797,7 @@
 				ARRAY_SIZE(mop500_platform_devs));
 
 		mop500_sdi_init(parent);
+		mop500_msp_init(parent);
 		i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
 		i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs);
 		i2c_register_board_info(2, mop500_i2c2_devices,
@@ -804,6 +805,8 @@
 
 		mop500_uib_init();
 
+	} else if (of_machine_is_compatible("calaosystems,snowball-a9500")) {
+		mop500_msp_init(parent);
 	} else if (of_machine_is_compatible("st-ericsson,hrefv60+")) {
 		/*
 		 * The HREFv60 board removed a GPIO expander and routed
@@ -815,6 +818,7 @@
 				ARRAY_SIZE(mop500_platform_devs));
 
 		hrefv60_sdi_init(parent);
+		mop500_msp_init(parent);
 
 		i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
 		i2c0_devs -= NUM_PRE_V60_I2C0_DEVICES;
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 119bc52..4e07eec 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -63,10 +63,11 @@
 	pid = task_pid_nr(thread->task) << ASID_BITS;
 	asm volatile(
 	"	mrc	p15, 0, %0, c13, c0, 1\n"
-	"	bfi	%1, %0, #0, %2\n"
-	"	mcr	p15, 0, %1, c13, c0, 1\n"
+	"	and	%0, %0, %2\n"
+	"	orr	%0, %0, %1\n"
+	"	mcr	p15, 0, %0, c13, c0, 1\n"
 	: "=r" (contextidr), "+r" (pid)
-	: "I" (ASID_BITS));
+	: "I" (~ASID_MASK));
 	isb();
 
 	return NOTIFY_OK;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4e7d118..e59c4ab 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -267,17 +267,19 @@
 	vunmap(cpu_addr);
 }
 
+#define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
+
 struct dma_pool {
 	size_t size;
 	spinlock_t lock;
 	unsigned long *bitmap;
 	unsigned long nr_pages;
 	void *vaddr;
-	struct page *page;
+	struct page **pages;
 };
 
 static struct dma_pool atomic_pool = {
-	.size = SZ_256K,
+	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,
 };
 
 static int __init early_coherent_pool(char *p)
@@ -287,6 +289,21 @@
 }
 early_param("coherent_pool", early_coherent_pool);
 
+void __init init_dma_coherent_pool_size(unsigned long size)
+{
+	/*
+	 * Catch any attempt to set the pool size too late.
+	 */
+	BUG_ON(atomic_pool.vaddr);
+
+	/*
+	 * Set architecture specific coherent pool size only if
+	 * it has not been changed by kernel command line parameter.
+	 */
+	if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)
+		atomic_pool.size = size;
+}
+
 /*
  * Initialise the coherent pool for atomic allocations.
  */
@@ -297,6 +314,7 @@
 	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
 	unsigned long *bitmap;
 	struct page *page;
+	struct page **pages;
 	void *ptr;
 	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
@@ -304,21 +322,31 @@
 	if (!bitmap)
 		goto no_bitmap;
 
+	pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		goto no_pages;
+
 	if (IS_ENABLED(CONFIG_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
 	else
 		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
 					   &page, NULL);
 	if (ptr) {
+		int i;
+
+		for (i = 0; i < nr_pages; i++)
+			pages[i] = page + i;
+
 		spin_lock_init(&pool->lock);
 		pool->vaddr = ptr;
-		pool->page = page;
+		pool->pages = pages;
 		pool->bitmap = bitmap;
 		pool->nr_pages = nr_pages;
 		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
 		       (unsigned)pool->size / 1024);
 		return 0;
 	}
+no_pages:
 	kfree(bitmap);
 no_bitmap:
 	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
@@ -443,27 +471,45 @@
 	if (pageno < pool->nr_pages) {
 		bitmap_set(pool->bitmap, pageno, count);
 		ptr = pool->vaddr + PAGE_SIZE * pageno;
-		*ret_page = pool->page + pageno;
+		*ret_page = pool->pages[pageno];
+	} else {
+		pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
+			    "Please increase it with coherent_pool= kernel parameter!\n",
+			    (unsigned)pool->size / 1024);
 	}
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	return ptr;
 }
 
+static bool __in_atomic_pool(void *start, size_t size)
+{
+	struct dma_pool *pool = &atomic_pool;
+	void *end = start + size;
+	void *pool_start = pool->vaddr;
+	void *pool_end = pool->vaddr + pool->size;
+
+	if (start < pool_start || start >= pool_end)
+		return false;
+
+	if (end <= pool_end)
+		return true;
+
+	WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
+	     start, end - 1, pool_start, pool_end - 1);
+
+	return false;
+}
+
 static int __free_from_pool(void *start, size_t size)
 {
 	struct dma_pool *pool = &atomic_pool;
 	unsigned long pageno, count;
 	unsigned long flags;
 
-	if (start < pool->vaddr || start > pool->vaddr + pool->size)
+	if (!__in_atomic_pool(start, size))
 		return 0;
 
-	if (start + size > pool->vaddr + pool->size) {
-		WARN(1, "freeing wrong coherent size from pool\n");
-		return 0;
-	}
-
 	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
 	count = size >> PAGE_SHIFT;
 
@@ -1090,10 +1136,22 @@
 	return 0;
 }
 
+static struct page **__atomic_get_pages(void *addr)
+{
+	struct dma_pool *pool = &atomic_pool;
+	struct page **pages = pool->pages;
+	int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+
+	return pages + offs;
+}
+
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 {
 	struct vm_struct *area;
 
+	if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
+		return __atomic_get_pages(cpu_addr);
+
 	if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
 		return cpu_addr;
 
@@ -1103,6 +1161,34 @@
 	return NULL;
 }
 
+static void *__iommu_alloc_atomic(struct device *dev, size_t size,
+				  dma_addr_t *handle)
+{
+	struct page *page;
+	void *addr;
+
+	addr = __alloc_from_pool(size, &page);
+	if (!addr)
+		return NULL;
+
+	*handle = __iommu_create_mapping(dev, &page, size);
+	if (*handle == DMA_ERROR_CODE)
+		goto err_mapping;
+
+	return addr;
+
+err_mapping:
+	__free_from_pool(addr, size);
+	return NULL;
+}
+
+static void __iommu_free_atomic(struct device *dev, struct page **pages,
+				dma_addr_t handle, size_t size)
+{
+	__iommu_remove_mapping(dev, handle, size);
+	__free_from_pool(page_address(pages[0]), size);
+}
+
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
@@ -1113,6 +1199,9 @@
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
+	if (gfp & GFP_ATOMIC)
+		return __iommu_alloc_atomic(dev, size, handle);
+
 	pages = __iommu_alloc_buffer(dev, size, gfp);
 	if (!pages)
 		return NULL;
@@ -1179,6 +1268,11 @@
 		return;
 	}
 
+	if (__in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, pages, handle, size);
+		return;
+	}
+
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
 		unmap_kernel_range((unsigned long)cpu_addr, size);
 		vunmap(cpu_addr);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 7745854..40ca11e 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -231,8 +231,6 @@
 	struct page *page;
 	struct address_space *mapping;
 
-	if (!pte_present_user(pteval))
-		return;
 	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
 		/* only flush non-aliasing VIPT caches for exec mappings */
 		return;
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 6776160..a8ee92d 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -55,6 +55,9 @@
 /* permanent static mappings from iotable_init() */
 #define VM_ARM_STATIC_MAPPING	0x40000000
 
+/* empty mapping */
+#define VM_ARM_EMPTY_MAPPING	0x20000000
+
 /* mapping type (attributes) for permanent static mappings */
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4c2d045..c2fa21d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -807,7 +807,7 @@
 	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
 	vm->addr = (void *)addr;
 	vm->size = SECTION_SIZE;
-	vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
+	vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING;
 	vm->caller = pmd_empty_section_gap;
 	vm_area_add_early(vm);
 }
@@ -820,7 +820,7 @@
 
 	/* we're still single threaded hence no lock needed here */
 	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+		if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING)))
 			continue;
 		addr = (unsigned long)vm->addr;
 		if (addr < next)
@@ -961,8 +961,8 @@
 		 * Check whether this memory bank would partially overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start + bank->size) > vmalloc_min ||
-		    __va(bank->start + bank->size) < __va(bank->start)) {
+		if (__va(bank->start + bank->size - 1) >= vmalloc_min ||
+		    __va(bank->start + bank->size - 1) <= __va(bank->start)) {
 			unsigned long newsize = vmalloc_min - __va(bank->start);
 			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
 			       "to -%.8llx (vmalloc region overlap).\n",
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index c202113..ea94765 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -38,10 +38,10 @@
 	dsb
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
-#ifdef CONFIG_ARM_ERRATA_720789
-	mov	r3, #0
-#else
 	asid	r3, r3				@ mask ASID
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(W(mov)	r3, #0	)
+	ALT_UP(W(nop)		)
 #endif
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index 626ad8c..938b50a 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -189,6 +189,7 @@
 		timer->reserved = 1;
 		break;
 	}
+	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
 	if (timer) {
 		ret = omap_dm_timer_prepare(timer);
@@ -197,7 +198,6 @@
 			timer = NULL;
 		}
 	}
-	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
 	if (!timer)
 		pr_debug("%s: timer request failed!\n", __func__);
@@ -220,6 +220,7 @@
 			break;
 		}
 	}
+	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
 	if (timer) {
 		ret = omap_dm_timer_prepare(timer);
@@ -228,7 +229,6 @@
 			timer = NULL;
 		}
 	}
-	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
 	if (!timer)
 		pr_debug("%s: timer%d request failed!\n", __func__, id);
@@ -258,7 +258,7 @@
 
 void omap_dm_timer_disable(struct omap_dm_timer *timer)
 {
-	pm_runtime_put(&timer->pdev->dev);
+	pm_runtime_put_sync(&timer->pdev->dev);
 }
 EXPORT_SYMBOL_GPL(omap_dm_timer_disable);
 
diff --git a/arch/arm/plat-omap/include/plat/cpu.h b/arch/arm/plat-omap/include/plat/cpu.h
index 68b180e..bb5d08a 100644
--- a/arch/arm/plat-omap/include/plat/cpu.h
+++ b/arch/arm/plat-omap/include/plat/cpu.h
@@ -372,7 +372,8 @@
 #define cpu_class_is_omap1()	(cpu_is_omap7xx() || cpu_is_omap15xx() || \
 				cpu_is_omap16xx())
 #define cpu_class_is_omap2()	(cpu_is_omap24xx() || cpu_is_omap34xx() || \
-				cpu_is_omap44xx() || soc_is_omap54xx())
+				cpu_is_omap44xx() || soc_is_omap54xx() || \
+				soc_is_am33xx())
 
 /* Various silicon revisions for omap2 */
 #define OMAP242X_CLASS		0x24200024
diff --git a/arch/arm/plat-omap/include/plat/multi.h b/arch/arm/plat-omap/include/plat/multi.h
index 045e320..324d31b 100644
--- a/arch/arm/plat-omap/include/plat/multi.h
+++ b/arch/arm/plat-omap/include/plat/multi.h
@@ -108,4 +108,13 @@
 # endif
 #endif
 
+#ifdef CONFIG_SOC_AM33XX
+# ifdef OMAP_NAME
+#  undef  MULTI_OMAP2
+#  define MULTI_OMAP2
+# else
+#  define OMAP_NAME am33xx
+# endif
+#endif
+
 #endif	/* __PLAT_OMAP_MULTI_H */
diff --git a/arch/arm/plat-omap/include/plat/uncompress.h b/arch/arm/plat-omap/include/plat/uncompress.h
index b8d19a1..7f7b112 100644
--- a/arch/arm/plat-omap/include/plat/uncompress.h
+++ b/arch/arm/plat-omap/include/plat/uncompress.h
@@ -110,7 +110,7 @@
 	_DEBUG_LL_ENTRY(mach, AM33XX_UART##p##_BASE, OMAP_PORT_SHIFT,	\
 		AM33XXUART##p)
 
-static inline void __arch_decomp_setup(unsigned long arch_id)
+static inline void arch_decomp_setup(void)
 {
 	int port = 0;
 
@@ -198,8 +198,6 @@
 	} while (0);
 }
 
-#define arch_decomp_setup()	__arch_decomp_setup(arch_id)
-
 /*
  * nothing to do
  */
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 766181c..024f3b0 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -68,6 +68,7 @@
 
 static unsigned long omap_sram_start;
 static void __iomem *omap_sram_base;
+static unsigned long omap_sram_skip;
 static unsigned long omap_sram_size;
 static void __iomem *omap_sram_ceil;
 
@@ -106,6 +107,7 @@
  */
 static void __init omap_detect_sram(void)
 {
+	omap_sram_skip = SRAM_BOOTLOADER_SZ;
 	if (cpu_class_is_omap2()) {
 		if (is_sram_locked()) {
 			if (cpu_is_omap34xx()) {
@@ -113,6 +115,7 @@
 				if ((omap_type() == OMAP2_DEVICE_TYPE_EMU) ||
 				    (omap_type() == OMAP2_DEVICE_TYPE_SEC)) {
 					omap_sram_size = 0x7000; /* 28K */
+					omap_sram_skip += SZ_16K;
 				} else {
 					omap_sram_size = 0x8000; /* 32K */
 				}
@@ -175,8 +178,10 @@
 		return;
 
 #ifdef CONFIG_OMAP4_ERRATA_I688
+	if (cpu_is_omap44xx()) {
 		omap_sram_start += PAGE_SIZE;
 		omap_sram_size -= SZ_16K;
+	}
 #endif
 	if (cpu_is_omap34xx()) {
 		/*
@@ -203,8 +208,8 @@
 	 * Looks like we need to preserve some bootloader code at the
 	 * beginning of SRAM for jumping to flash for reboot to work...
 	 */
-	memset_io(omap_sram_base + SRAM_BOOTLOADER_SZ, 0,
-		  omap_sram_size - SRAM_BOOTLOADER_SZ);
+	memset_io(omap_sram_base + omap_sram_skip, 0,
+		  omap_sram_size - omap_sram_skip);
 }
 
 /*
@@ -218,7 +223,7 @@
 {
 	unsigned long available, new_ceil = (unsigned long)omap_sram_ceil;
 
-	available = omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ);
+	available = omap_sram_ceil - (omap_sram_base + omap_sram_skip);
 
 	if (size > available) {
 		pr_err("Not enough space in SRAM\n");
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index d245a87..b8b747a 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -291,10 +291,12 @@
 void __init orion_ge00_init(struct mv643xx_eth_platform_data *eth_data,
 			    unsigned long mapbase,
 			    unsigned long irq,
-			    unsigned long irq_err)
+			    unsigned long irq_err,
+			    unsigned int tx_csum_limit)
 {
 	fill_resources(&orion_ge00_shared, orion_ge00_shared_resources,
 		       mapbase + 0x2000, SZ_16K - 1, irq_err);
+	orion_ge00_shared_data.tx_csum_limit = tx_csum_limit;
 	ge_complete(&orion_ge00_shared_data,
 		    orion_ge00_resources, irq, &orion_ge00_shared,
 		    eth_data, &orion_ge00);
@@ -343,10 +345,12 @@
 void __init orion_ge01_init(struct mv643xx_eth_platform_data *eth_data,
 			    unsigned long mapbase,
 			    unsigned long irq,
-			    unsigned long irq_err)
+			    unsigned long irq_err,
+			    unsigned int tx_csum_limit)
 {
 	fill_resources(&orion_ge01_shared, orion_ge01_shared_resources,
 		       mapbase + 0x2000, SZ_16K - 1, irq_err);
+	orion_ge01_shared_data.tx_csum_limit = tx_csum_limit;
 	ge_complete(&orion_ge01_shared_data,
 		    orion_ge01_resources, irq, &orion_ge01_shared,
 		    eth_data, &orion_ge01);
diff --git a/arch/arm/plat-orion/include/plat/common.h b/arch/arm/plat-orion/include/plat/common.h
index e00fdb2..ae2377e 100644
--- a/arch/arm/plat-orion/include/plat/common.h
+++ b/arch/arm/plat-orion/include/plat/common.h
@@ -39,12 +39,14 @@
 void __init orion_ge00_init(struct mv643xx_eth_platform_data *eth_data,
 			    unsigned long mapbase,
 			    unsigned long irq,
-			    unsigned long irq_err);
+			    unsigned long irq_err,
+			    unsigned int tx_csum_limit);
 
 void __init orion_ge01_init(struct mv643xx_eth_platform_data *eth_data,
 			    unsigned long mapbase,
 			    unsigned long irq,
-			    unsigned long irq_err);
+			    unsigned long irq_err,
+			    unsigned int tx_csum_limit);
 
 void __init orion_ge10_init(struct mv643xx_eth_platform_data *eth_data,
 			    unsigned long mapbase,
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index 28f898f..db98e70 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -430,7 +430,7 @@
  * when necessary.
 */
 
-int s3c2410_dma_enqueue(unsigned int channel, void *id,
+int s3c2410_dma_enqueue(enum dma_ch channel, void *id,
 			dma_addr_t data, int size)
 {
 	struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 74e31ce..fc49f3d 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -32,6 +32,8 @@
 #include <linux/platform_data/s3c-hsudc.h>
 #include <linux/platform_data/s3c-hsotg.h>
 
+#include <media/s5p_hdmi.h>
+
 #include <asm/irq.h>
 #include <asm/pmu.h>
 #include <asm/mach/arch.h>
@@ -748,7 +750,8 @@
 	if (!pd) {
 		pd = &default_i2c_data;
 
-		if (soc_is_exynos4210())
+		if (soc_is_exynos4210() ||
+		    soc_is_exynos4212() || soc_is_exynos4412())
 			pd->bus_num = 8;
 		else if (soc_is_s5pv210())
 			pd->bus_num = 3;
@@ -759,6 +762,30 @@
 	npd = s3c_set_platdata(pd, sizeof(struct s3c2410_platform_i2c),
 			       &s5p_device_i2c_hdmiphy);
 }
+
+struct s5p_hdmi_platform_data s5p_hdmi_def_platdata;
+
+void __init s5p_hdmi_set_platdata(struct i2c_board_info *hdmiphy_info,
+				  struct i2c_board_info *mhl_info, int mhl_bus)
+{
+	struct s5p_hdmi_platform_data *pd = &s5p_hdmi_def_platdata;
+
+	if (soc_is_exynos4210() ||
+	    soc_is_exynos4212() || soc_is_exynos4412())
+		pd->hdmiphy_bus = 8;
+	else if (soc_is_s5pv210())
+		pd->hdmiphy_bus = 3;
+	else
+		pd->hdmiphy_bus = 0;
+
+	pd->hdmiphy_info = hdmiphy_info;
+	pd->mhl_info = mhl_info;
+	pd->mhl_bus = mhl_bus;
+
+	s3c_set_platdata(pd, sizeof(struct s5p_hdmi_platform_data),
+			 &s5p_device_hdmi);
+}
+
 #endif /* CONFIG_S5P_DEV_I2C_HDMIPHY */
 
 /* I2S */
diff --git a/arch/arm/plat-samsung/include/plat/hdmi.h b/arch/arm/plat-samsung/include/plat/hdmi.h
new file mode 100644
index 0000000..331d046
--- /dev/null
+++ b/arch/arm/plat-samsung/include/plat/hdmi.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright (C) 2012 Samsung Electronics Co.Ltd
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __PLAT_SAMSUNG_HDMI_H
+#define __PLAT_SAMSUNG_HDMI_H __FILE__
+
+extern void s5p_hdmi_set_platdata(struct i2c_board_info *hdmiphy_info,
+				  struct i2c_board_info *mhl_info, int mhl_bus);
+
+#endif /* __PLAT_SAMSUNG_HDMI_H */
diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c
index 64ab65f..1507028 100644
--- a/arch/arm/plat-samsung/pm.c
+++ b/arch/arm/plat-samsung/pm.c
@@ -74,7 +74,7 @@
 
 #ifdef CONFIG_SAMSUNG_PM_DEBUG
 
-struct pm_uart_save uart_save[CONFIG_SERIAL_SAMSUNG_UARTS];
+static struct pm_uart_save uart_save[CONFIG_SERIAL_SAMSUNG_UARTS];
 
 static void s3c_pm_save_uart(unsigned int uart, struct pm_uart_save *save)
 {
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index fb849d0..c834b32 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -719,8 +719,10 @@
 			if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100)
 				elf_hwcap |= HWCAP_NEON;
 #endif
+#ifdef CONFIG_VFPv3
 			if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000)
 				elf_hwcap |= HWCAP_VFPv4;
+#endif
 		}
 	}
 	return 0;
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index f348619..c7092e6 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -38,6 +38,7 @@
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
 	select IRQ_PER_CPU if SMP
+	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_NMI_WATCHDOG if NMI_WATCHDOG
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS
diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile
index d3d7e64..66cf000 100644
--- a/arch/blackfin/Makefile
+++ b/arch/blackfin/Makefile
@@ -20,7 +20,6 @@
 KBUILD_AFLAGS           += $(call cc-option,-mno-fdpic)
 KBUILD_CFLAGS_MODULE    += -mlong-calls
 LDFLAGS                 += -m elf32bfin
-KALLSYMS         += --symbol-prefix=_
 
 KBUILD_DEFCONFIG := BF537-STAMP_defconfig
 
diff --git a/arch/blackfin/include/asm/smp.h b/arch/blackfin/include/asm/smp.h
index dc3d144..9631598 100644
--- a/arch/blackfin/include/asm/smp.h
+++ b/arch/blackfin/include/asm/smp.h
@@ -18,6 +18,8 @@
 #define raw_smp_processor_id()  blackfin_core_id()
 
 extern void bfin_relocate_coreb_l1_mem(void);
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_ICACHE_FLUSH_L1)
 asmlinkage void blackfin_icache_flush_range_l1(unsigned long *ptr);
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 00bbe67..a401513 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -48,10 +48,13 @@
 
 struct blackfin_initial_pda __cpuinitdata initial_pda_coreb;
 
-#define BFIN_IPI_TIMER	      0
-#define BFIN_IPI_RESCHEDULE   1
-#define BFIN_IPI_CALL_FUNC    2
-#define BFIN_IPI_CPU_STOP     3
+enum ipi_message_type {
+	BFIN_IPI_TIMER,
+	BFIN_IPI_RESCHEDULE,
+	BFIN_IPI_CALL_FUNC,
+	BFIN_IPI_CALL_FUNC_SINGLE,
+	BFIN_IPI_CPU_STOP,
+};
 
 struct blackfin_flush_data {
 	unsigned long start;
@@ -60,35 +63,20 @@
 
 void *secondary_stack;
 
-
-struct smp_call_struct {
-	void (*func)(void *info);
-	void *info;
-	int wait;
-	cpumask_t *waitmask;
-};
-
 static struct blackfin_flush_data smp_flush_data;
 
 static DEFINE_SPINLOCK(stop_lock);
 
-struct ipi_message {
-	unsigned long type;
-	struct smp_call_struct call_struct;
-};
-
 /* A magic number - stress test shows this is safe for common cases */
 #define BFIN_IPI_MSGQ_LEN 5
 
 /* Simple FIFO buffer, overflow leads to panic */
-struct ipi_message_queue {
-	spinlock_t lock;
+struct ipi_data {
 	unsigned long count;
-	unsigned long head; /* head of the queue */
-	struct ipi_message ipi_message[BFIN_IPI_MSGQ_LEN];
+	unsigned long bits;
 };
 
-static DEFINE_PER_CPU(struct ipi_message_queue, ipi_msg_queue);
+static DEFINE_PER_CPU(struct ipi_data, bfin_ipi);
 
 static void ipi_cpu_stop(unsigned int cpu)
 {
@@ -129,28 +117,6 @@
 	blackfin_icache_flush_range(fdata->start, fdata->end);
 }
 
-static void ipi_call_function(unsigned int cpu, struct ipi_message *msg)
-{
-	int wait;
-	void (*func)(void *info);
-	void *info;
-	func = msg->call_struct.func;
-	info = msg->call_struct.info;
-	wait = msg->call_struct.wait;
-	func(info);
-	if (wait) {
-#ifdef __ARCH_SYNC_CORE_DCACHE
-		/*
-		 * 'wait' usually means synchronization between CPUs.
-		 * Invalidate D cache in case shared data was changed
-		 * by func() to ensure cache coherence.
-		 */
-		resync_core_dcache();
-#endif
-		cpumask_clear_cpu(cpu, msg->call_struct.waitmask);
-	}
-}
-
 /* Use IRQ_SUPPLE_0 to request reschedule.
  * When returning from interrupt to user space,
  * there is chance to reschedule */
@@ -172,152 +138,95 @@
 
 static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 {
-	struct ipi_message *msg;
-	struct ipi_message_queue *msg_queue;
+	struct ipi_data *bfin_ipi_data;
 	unsigned int cpu = smp_processor_id();
-	unsigned long flags;
+	unsigned long pending;
+	unsigned long msg;
 
 	platform_clear_ipi(cpu, IRQ_SUPPLE_1);
 
-	msg_queue = &__get_cpu_var(ipi_msg_queue);
+	bfin_ipi_data = &__get_cpu_var(bfin_ipi);
 
-	spin_lock_irqsave(&msg_queue->lock, flags);
+	while ((pending = xchg(&bfin_ipi_data->bits, 0)) != 0) {
+		msg = 0;
+		do {
+			msg = find_next_bit(&pending, BITS_PER_LONG, msg + 1);
+			switch (msg) {
+			case BFIN_IPI_TIMER:
+				ipi_timer();
+				break;
+			case BFIN_IPI_RESCHEDULE:
+				scheduler_ipi();
+				break;
+			case BFIN_IPI_CALL_FUNC:
+				generic_smp_call_function_interrupt();
+				break;
 
-	while (msg_queue->count) {
-		msg = &msg_queue->ipi_message[msg_queue->head];
-		switch (msg->type) {
-		case BFIN_IPI_TIMER:
-			ipi_timer();
-			break;
-		case BFIN_IPI_RESCHEDULE:
-			scheduler_ipi();
-			break;
-		case BFIN_IPI_CALL_FUNC:
-			ipi_call_function(cpu, msg);
-			break;
-		case BFIN_IPI_CPU_STOP:
-			ipi_cpu_stop(cpu);
-			break;
-		default:
-			printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%lx\n",
-			       cpu, msg->type);
-			break;
-		}
-		msg_queue->head++;
-		msg_queue->head %= BFIN_IPI_MSGQ_LEN;
-		msg_queue->count--;
+			case BFIN_IPI_CALL_FUNC_SINGLE:
+				generic_smp_call_function_single_interrupt();
+				break;
+
+			case BFIN_IPI_CPU_STOP:
+				ipi_cpu_stop(cpu);
+				break;
+			}
+		} while (msg < BITS_PER_LONG);
+
+		smp_mb();
 	}
-	spin_unlock_irqrestore(&msg_queue->lock, flags);
 	return IRQ_HANDLED;
 }
 
-static void ipi_queue_init(void)
+static void bfin_ipi_init(void)
 {
 	unsigned int cpu;
-	struct ipi_message_queue *msg_queue;
+	struct ipi_data *bfin_ipi_data;
 	for_each_possible_cpu(cpu) {
-		msg_queue = &per_cpu(ipi_msg_queue, cpu);
-		spin_lock_init(&msg_queue->lock);
-		msg_queue->count = 0;
-		msg_queue->head = 0;
+		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
+		bfin_ipi_data->bits = 0;
+		bfin_ipi_data->count = 0;
 	}
 }
 
-static inline void smp_send_message(cpumask_t callmap, unsigned long type,
-					void (*func) (void *info), void *info, int wait)
+void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg)
 {
 	unsigned int cpu;
-	struct ipi_message_queue *msg_queue;
-	struct ipi_message *msg;
-	unsigned long flags, next_msg;
-	cpumask_t waitmask; /* waitmask is shared by all cpus */
+	struct ipi_data *bfin_ipi_data;
+	unsigned long flags;
 
-	cpumask_copy(&waitmask, &callmap);
-	for_each_cpu(cpu, &callmap) {
-		msg_queue = &per_cpu(ipi_msg_queue, cpu);
-		spin_lock_irqsave(&msg_queue->lock, flags);
-		if (msg_queue->count < BFIN_IPI_MSGQ_LEN) {
-			next_msg = (msg_queue->head + msg_queue->count)
-					% BFIN_IPI_MSGQ_LEN;
-			msg = &msg_queue->ipi_message[next_msg];
-			msg->type = type;
-			if (type == BFIN_IPI_CALL_FUNC) {
-				msg->call_struct.func = func;
-				msg->call_struct.info = info;
-				msg->call_struct.wait = wait;
-				msg->call_struct.waitmask = &waitmask;
-			}
-			msg_queue->count++;
-		} else
-			panic("IPI message queue overflow\n");
-		spin_unlock_irqrestore(&msg_queue->lock, flags);
+	local_irq_save(flags);
+
+	for_each_cpu(cpu, cpumask) {
+		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
+		smp_mb();
+		set_bit(msg, &bfin_ipi_data->bits);
+		bfin_ipi_data->count++;
 		platform_send_ipi_cpu(cpu, IRQ_SUPPLE_1);
 	}
 
-	if (wait) {
-		while (!cpumask_empty(&waitmask))
-			blackfin_dcache_invalidate_range(
-				(unsigned long)(&waitmask),
-				(unsigned long)(&waitmask));
-#ifdef __ARCH_SYNC_CORE_DCACHE
-		/*
-		 * Invalidate D cache in case shared data was changed by
-		 * other processors to ensure cache coherence.
-		 */
-		resync_core_dcache();
-#endif
-	}
+	local_irq_restore(flags);
 }
 
-int smp_call_function(void (*func)(void *info), void *info, int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	cpumask_t callmap;
-
-	preempt_disable();
-	cpumask_copy(&callmap, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), &callmap);
-	if (!cpumask_empty(&callmap))
-		smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
-
-	preempt_enable();
-
-	return 0;
+	send_ipi(cpumask_of(cpu), BFIN_IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL_GPL(smp_call_function);
 
-int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
-				int wait)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	unsigned int cpu = cpuid;
-	cpumask_t callmap;
-
-	if (cpu_is_offline(cpu))
-		return 0;
-	cpumask_clear(&callmap);
-	cpumask_set_cpu(cpu, &callmap);
-
-	smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
-
-	return 0;
+	send_ipi(mask, BFIN_IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL_GPL(smp_call_function_single);
 
 void smp_send_reschedule(int cpu)
 {
-	cpumask_t callmap;
-	/* simply trigger an ipi */
-
-	cpumask_clear(&callmap);
-	cpumask_set_cpu(cpu, &callmap);
-
-	smp_send_message(callmap, BFIN_IPI_RESCHEDULE, NULL, NULL, 0);
+	send_ipi(cpumask_of(cpu), BFIN_IPI_RESCHEDULE);
 
 	return;
 }
 
 void smp_send_msg(const struct cpumask *mask, unsigned long type)
 {
-	smp_send_message(*mask, type, NULL, NULL, 0);
+	send_ipi(mask, type);
 }
 
 void smp_timer_broadcast(const struct cpumask *mask)
@@ -333,7 +242,7 @@
 	cpumask_copy(&callmap, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &callmap);
 	if (!cpumask_empty(&callmap))
-		smp_send_message(callmap, BFIN_IPI_CPU_STOP, NULL, NULL, 0);
+		send_ipi(&callmap, BFIN_IPI_CPU_STOP);
 
 	preempt_enable();
 
@@ -436,7 +345,7 @@
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	platform_prepare_cpus(max_cpus);
-	ipi_queue_init();
+	bfin_ipi_init();
 	platform_request_ipi(IRQ_SUPPLE_0, ipi_handler_int0);
 	platform_request_ipi(IRQ_SUPPLE_1, ipi_handler_int1);
 }
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 052f81a..983c859 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -6,6 +6,7 @@
 config C6X
 	def_bool y
 	select CLKDEV_LOOKUP
+	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h
index 6d521d9..09c5a0f 100644
--- a/arch/c6x/include/asm/cache.h
+++ b/arch/c6x/include/asm/cache.h
@@ -1,7 +1,7 @@
 /*
  *  Port on Texas Instruments TMS320C6x architecture
  *
- *  Copyright (C) 2005, 2006, 2009, 2010 Texas Instruments Incorporated
+ *  Copyright (C) 2005, 2006, 2009, 2010, 2012 Texas Instruments Incorporated
  *  Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com)
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -16,9 +16,14 @@
 /*
  * Cache line size
  */
-#define L1D_CACHE_BYTES   64
-#define L1P_CACHE_BYTES   32
-#define L2_CACHE_BYTES	  128
+#define L1D_CACHE_SHIFT   6
+#define L1D_CACHE_BYTES   (1 << L1D_CACHE_SHIFT)
+
+#define L1P_CACHE_SHIFT   5
+#define L1P_CACHE_BYTES   (1 << L1P_CACHE_SHIFT)
+
+#define L2_CACHE_SHIFT    7
+#define L2_CACHE_BYTES    (1 << L2_CACHE_SHIFT)
 
 /*
  * L2 used as cache
@@ -29,7 +34,8 @@
  * For practical reasons the L1_CACHE_BYTES defines should not be smaller than
  * the L2 line size
  */
-#define L1_CACHE_BYTES        L2_CACHE_BYTES
+#define L1_CACHE_SHIFT        L2_CACHE_SHIFT
+#define L1_CACHE_BYTES        (1 << L1_CACHE_SHIFT)
 
 #define L2_CACHE_ALIGN_LOW(x) \
 	(((x) & ~(L2_CACHE_BYTES - 1)))
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index 954d81e..7913695 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -234,5 +234,4 @@
 CONFIG_CRYPTO_MD5=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRC_T10DIF=y
-CONFIG_MISC_DEVICES=y
 CONFIG_INTEL_IOMMU=y
diff --git a/arch/ia64/configs/gensparse_defconfig b/arch/ia64/configs/gensparse_defconfig
index 91c41ec..f8e9133 100644
--- a/arch/ia64/configs/gensparse_defconfig
+++ b/arch/ia64/configs/gensparse_defconfig
@@ -209,4 +209,3 @@
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_CRYPTO_MD5=y
-CONFIG_MISC_DEVICES=y
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 4a46990..b22df94 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -5,6 +5,7 @@
 	select HAVE_AOUT if MMU
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
+	select GENERIC_ATOMIC64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
 	select GENERIC_CPU_DEVICES
 	select GENERIC_STRNCPY_FROM_USER if MMU
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 8206834..c4eb79e 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -28,6 +28,7 @@
 	select CPU_HAS_NO_BITFIELDS
 	select CPU_HAS_NO_MULDIV64
 	select GENERIC_CSUM
+	select HAVE_CLK
 
 endchoice
 
@@ -58,7 +59,6 @@
 config M68020
 	bool "68020 support"
 	depends on MMU
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68020
@@ -69,7 +69,6 @@
 config M68030
 	bool "68030 support"
 	depends on MMU && !MMU_SUN3
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68030
@@ -79,7 +78,6 @@
 config M68040
 	bool "68040 support"
 	depends on MMU && !MMU_SUN3
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68LC040
@@ -90,7 +88,6 @@
 config M68060
 	bool "68060 support"
 	depends on MMU && !MMU_SUN3
-	select GENERIC_ATOMIC64
 	select CPU_HAS_ADDRESS_SPACES
 	help
 	  If you anticipate running this kernel on a computer with a MC68060
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 331d574..faf6528 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -89,6 +89,7 @@
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select HAVE_CLK
 	select IRQ_CPU
 	select MIPS_MACHINE
 	select SYS_HAS_CPU_MIPS32_R2
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 9996948..a124c25 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -228,6 +228,8 @@
 	 * adapter on the mtx-1 "singleboard" variant. It triggers a custom
 	 * logic chip connected to EXT_IO3 (GPIO1) to suppress IDSEL signals.
 	 */
+	udelay(1);
+
 	if (assert && devsel != 0)
 		/* Suppress signal to Cardbus */
 		alchemy_gpio_set_value(1, 0);	/* set EXT_IO3 OFF */
diff --git a/arch/mips/ath79/dev-usb.c b/arch/mips/ath79/dev-usb.c
index 36e9570..b2a2311 100644
--- a/arch/mips/ath79/dev-usb.c
+++ b/arch/mips/ath79/dev-usb.c
@@ -145,6 +145,8 @@
 
 	ath79_ohci_resources[0].start = AR7240_OHCI_BASE;
 	ath79_ohci_resources[0].end = AR7240_OHCI_BASE + AR7240_OHCI_SIZE - 1;
+	ath79_ohci_resources[1].start = ATH79_CPU_IRQ_USB;
+	ath79_ohci_resources[1].end = ATH79_CPU_IRQ_USB;
 	platform_device_register(&ath79_ohci_device);
 }
 
diff --git a/arch/mips/ath79/gpio.c b/arch/mips/ath79/gpio.c
index 29054f2..48fe762 100644
--- a/arch/mips/ath79/gpio.c
+++ b/arch/mips/ath79/gpio.c
@@ -188,8 +188,10 @@
 
 	if (soc_is_ar71xx())
 		ath79_gpio_count = AR71XX_GPIO_COUNT;
-	else if (soc_is_ar724x())
-		ath79_gpio_count = AR724X_GPIO_COUNT;
+	else if (soc_is_ar7240())
+		ath79_gpio_count = AR7240_GPIO_COUNT;
+	else if (soc_is_ar7241() || soc_is_ar7242())
+		ath79_gpio_count = AR7241_GPIO_COUNT;
 	else if (soc_is_ar913x())
 		ath79_gpio_count = AR913X_GPIO_COUNT;
 	else if (soc_is_ar933x())
diff --git a/arch/mips/bcm63xx/dev-spi.c b/arch/mips/bcm63xx/dev-spi.c
index e39f730..f1c9c3e 100644
--- a/arch/mips/bcm63xx/dev-spi.c
+++ b/arch/mips/bcm63xx/dev-spi.c
@@ -106,11 +106,15 @@
 	if (BCMCPU_IS_6338() || BCMCPU_IS_6348()) {
 		spi_resources[0].end += BCM_6338_RSET_SPI_SIZE - 1;
 		spi_pdata.fifo_size = SPI_6338_MSG_DATA_SIZE;
+		spi_pdata.msg_type_shift = SPI_6338_MSG_TYPE_SHIFT;
+		spi_pdata.msg_ctl_width = SPI_6338_MSG_CTL_WIDTH;
 	}
 
 	if (BCMCPU_IS_6358() || BCMCPU_IS_6368()) {
 		spi_resources[0].end += BCM_6358_RSET_SPI_SIZE - 1;
 		spi_pdata.fifo_size = SPI_6358_MSG_DATA_SIZE;
+		spi_pdata.msg_type_shift = SPI_6358_MSG_TYPE_SHIFT;
+		spi_pdata.msg_ctl_width = SPI_6358_MSG_CTL_WIDTH;
 	}
 
 	bcm63xx_spi_regs_init();
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 7fb1f22..274cd4f 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -61,6 +61,12 @@
 	octeon_irq_ciu_to_irq[line][bit] = irq;
 }
 
+static void octeon_irq_force_ciu_mapping(struct irq_domain *domain,
+					 int irq, int line, int bit)
+{
+	irq_domain_associate(domain, irq, line << 6 | bit);
+}
+
 static int octeon_coreid_for_cpu(int cpu)
 {
 #ifdef CONFIG_SMP
@@ -183,19 +189,9 @@
 		mutex_init(&cd->core_irq_mutex);
 
 		irq = OCTEON_IRQ_SW0 + i;
-		switch (irq) {
-		case OCTEON_IRQ_TIMER:
-		case OCTEON_IRQ_SW0:
-		case OCTEON_IRQ_SW1:
-		case OCTEON_IRQ_5:
-		case OCTEON_IRQ_PERF:
-			irq_set_chip_data(irq, cd);
-			irq_set_chip_and_handler(irq, &octeon_irq_chip_core,
-						 handle_percpu_irq);
-			break;
-		default:
-			break;
-		}
+		irq_set_chip_data(irq, cd);
+		irq_set_chip_and_handler(irq, &octeon_irq_chip_core,
+					 handle_percpu_irq);
 	}
 }
 
@@ -890,7 +886,6 @@
 	unsigned int type;
 	unsigned int pin;
 	unsigned int trigger;
-	struct octeon_irq_gpio_domain_data *gpiod;
 
 	if (d->of_node != node)
 		return -EINVAL;
@@ -925,8 +920,7 @@
 		break;
 	}
 	*out_type = type;
-	gpiod = d->host_data;
-	*out_hwirq = gpiod->base_hwirq + pin;
+	*out_hwirq = pin;
 
 	return 0;
 }
@@ -996,19 +990,21 @@
 static int octeon_irq_gpio_map(struct irq_domain *d,
 			       unsigned int virq, irq_hw_number_t hw)
 {
-	unsigned int line = hw >> 6;
-	unsigned int bit = hw & 63;
+	struct octeon_irq_gpio_domain_data *gpiod = d->host_data;
+	unsigned int line, bit;
 
 	if (!octeon_irq_virq_in_range(virq))
 		return -EINVAL;
 
+	hw += gpiod->base_hwirq;
+	line = hw >> 6;
+	bit = hw & 63;
 	if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 
 	octeon_irq_set_ciu_mapping(virq, line, bit,
 				   octeon_irq_gpio_chip,
 				   octeon_irq_handle_gpio);
-
 	return 0;
 }
 
@@ -1149,6 +1145,7 @@
 	struct irq_chip *chip_wd;
 	struct device_node *gpio_node;
 	struct device_node *ciu_node;
+	struct irq_domain *ciu_domain = NULL;
 
 	octeon_irq_init_ciu_percpu();
 	octeon_irq_setup_secondary = octeon_irq_setup_secondary_ciu;
@@ -1177,31 +1174,6 @@
 	/* Mips internal */
 	octeon_irq_init_core();
 
-	/* CIU_0 */
-	for (i = 0; i < 16; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WORKQ0, 0, i + 0, chip, handle_level_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX0, 0, 32, chip_mbox, handle_percpu_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX1, 0, 33, chip_mbox, handle_percpu_irq);
-
-	for (i = 0; i < 4; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_PCI_INT0, 0, i + 36, chip, handle_level_irq);
-	for (i = 0; i < 4; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_PCI_MSI0, 0, i + 40, chip, handle_level_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_RML, 0, 46, chip, handle_level_irq);
-	for (i = 0; i < 4; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_TIMER0, 0, i + 52, chip, handle_edge_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_USB0, 0, 56, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_BOOTDMA, 0, 63, chip, handle_level_irq);
-
-	/* CIU_1 */
-	for (i = 0; i < 16; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WDOG0, 1, i + 0, chip_wd, handle_level_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_USB1, 1, 17, chip, handle_level_irq);
-
 	gpio_node = of_find_compatible_node(NULL, NULL, "cavium,octeon-3860-gpio");
 	if (gpio_node) {
 		struct octeon_irq_gpio_domain_data *gpiod;
@@ -1219,10 +1191,35 @@
 
 	ciu_node = of_find_compatible_node(NULL, NULL, "cavium,octeon-3860-ciu");
 	if (ciu_node) {
-		irq_domain_add_tree(ciu_node, &octeon_irq_domain_ciu_ops, NULL);
+		ciu_domain = irq_domain_add_tree(ciu_node, &octeon_irq_domain_ciu_ops, NULL);
 		of_node_put(ciu_node);
 	} else
-		pr_warn("Cannot find device node for cavium,octeon-3860-ciu.\n");
+		panic("Cannot find device node for cavium,octeon-3860-ciu.");
+
+	/* CIU_0 */
+	for (i = 0; i < 16; i++)
+		octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_WORKQ0, 0, i + 0);
+
+	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX0, 0, 32, chip_mbox, handle_percpu_irq);
+	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX1, 0, 33, chip_mbox, handle_percpu_irq);
+
+	for (i = 0; i < 4; i++)
+		octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_PCI_INT0, 0, i + 36);
+	for (i = 0; i < 4; i++)
+		octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_PCI_MSI0, 0, i + 40);
+
+	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_RML, 0, 46);
+	for (i = 0; i < 4; i++)
+		octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_TIMER0, 0, i + 52);
+
+	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 0, 56);
+	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_BOOTDMA, 0, 63);
+
+	/* CIU_1 */
+	for (i = 0; i < 16; i++)
+		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WDOG0, 1, i + 0, chip_wd, handle_level_irq);
+
+	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB1, 1, 17);
 
 	/* Enable the CIU lines */
 	set_c0_status(STATUSF_IP3 | STATUSF_IP2);
diff --git a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
index 1caa78a..dde5044 100644
--- a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
+++ b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
@@ -393,7 +393,8 @@
 #define AR71XX_GPIO_REG_FUNC		0x28
 
 #define AR71XX_GPIO_COUNT		16
-#define AR724X_GPIO_COUNT		18
+#define AR7240_GPIO_COUNT		18
+#define AR7241_GPIO_COUNT		20
 #define AR913X_GPIO_COUNT		22
 #define AR933X_GPIO_COUNT		30
 #define AR934X_GPIO_COUNT		23
diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
index 4476fa0..6ddae92 100644
--- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
@@ -42,7 +42,6 @@
 #define cpu_has_mips64r1	0
 #define cpu_has_mips64r2	0
 
-#define cpu_has_dsp		0
 #define cpu_has_mipsmt		0
 
 #define cpu_has_64bits		0
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
index 7d98dbe..c9bae13 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
@@ -9,6 +9,8 @@
 
 struct bcm63xx_spi_pdata {
 	unsigned int	fifo_size;
+	unsigned int	msg_type_shift;
+	unsigned int	msg_ctl_width;
 	int		bus_num;
 	int		num_chipselect;
 	u32		speed_hz;
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h
index 4ccc2a7..61f2a2a 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h
@@ -1054,7 +1054,8 @@
 #define SPI_6338_FILL_BYTE		0x07
 #define SPI_6338_MSG_TAIL		0x09
 #define SPI_6338_RX_TAIL		0x0b
-#define SPI_6338_MSG_CTL		0x40
+#define SPI_6338_MSG_CTL		0x40	/* 8-bits register */
+#define SPI_6338_MSG_CTL_WIDTH		8
 #define SPI_6338_MSG_DATA		0x41
 #define SPI_6338_MSG_DATA_SIZE		0x3f
 #define SPI_6338_RX_DATA		0x80
@@ -1070,7 +1071,8 @@
 #define SPI_6348_FILL_BYTE		0x07
 #define SPI_6348_MSG_TAIL		0x09
 #define SPI_6348_RX_TAIL		0x0b
-#define SPI_6348_MSG_CTL		0x40
+#define SPI_6348_MSG_CTL		0x40	/* 8-bits register */
+#define SPI_6348_MSG_CTL_WIDTH		8
 #define SPI_6348_MSG_DATA		0x41
 #define SPI_6348_MSG_DATA_SIZE		0x3f
 #define SPI_6348_RX_DATA		0x80
@@ -1078,6 +1080,7 @@
 
 /* BCM 6358 SPI core */
 #define SPI_6358_MSG_CTL		0x00	/* 16-bits register */
+#define SPI_6358_MSG_CTL_WIDTH		16
 #define SPI_6358_MSG_DATA		0x02
 #define SPI_6358_MSG_DATA_SIZE		0x21e
 #define SPI_6358_RX_DATA		0x400
@@ -1094,6 +1097,7 @@
 
 /* BCM 6358 SPI core */
 #define SPI_6368_MSG_CTL		0x00	/* 16-bits register */
+#define SPI_6368_MSG_CTL_WIDTH		16
 #define SPI_6368_MSG_DATA		0x02
 #define SPI_6368_MSG_DATA_SIZE		0x21e
 #define SPI_6368_RX_DATA		0x400
@@ -1115,7 +1119,10 @@
 #define SPI_HD_W			0x01
 #define SPI_HD_R			0x02
 #define SPI_BYTE_CNT_SHIFT		0
-#define SPI_MSG_TYPE_SHIFT		14
+#define SPI_6338_MSG_TYPE_SHIFT		6
+#define SPI_6348_MSG_TYPE_SHIFT		6
+#define SPI_6358_MSG_TYPE_SHIFT		14
+#define SPI_6368_MSG_TYPE_SHIFT		14
 
 /* Command */
 #define SPI_CMD_NOOP			0x00
diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h
index 4189920..c22a307 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/irq.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h
@@ -21,14 +21,10 @@
 	OCTEON_IRQ_TIMER,
 /* sources in CIU_INTX_EN0 */
 	OCTEON_IRQ_WORKQ0,
-	OCTEON_IRQ_GPIO0 = OCTEON_IRQ_WORKQ0 + 16,
-	OCTEON_IRQ_WDOG0 = OCTEON_IRQ_GPIO0 + 16,
+	OCTEON_IRQ_WDOG0 = OCTEON_IRQ_WORKQ0 + 16,
 	OCTEON_IRQ_WDOG15 = OCTEON_IRQ_WDOG0 + 15,
 	OCTEON_IRQ_MBOX0 = OCTEON_IRQ_WDOG0 + 16,
 	OCTEON_IRQ_MBOX1,
-	OCTEON_IRQ_UART0,
-	OCTEON_IRQ_UART1,
-	OCTEON_IRQ_UART2,
 	OCTEON_IRQ_PCI_INT0,
 	OCTEON_IRQ_PCI_INT1,
 	OCTEON_IRQ_PCI_INT2,
@@ -38,8 +34,6 @@
 	OCTEON_IRQ_PCI_MSI2,
 	OCTEON_IRQ_PCI_MSI3,
 
-	OCTEON_IRQ_TWSI,
-	OCTEON_IRQ_TWSI2,
 	OCTEON_IRQ_RML,
 	OCTEON_IRQ_TIMER0,
 	OCTEON_IRQ_TIMER1,
@@ -47,8 +41,6 @@
 	OCTEON_IRQ_TIMER3,
 	OCTEON_IRQ_USB0,
 	OCTEON_IRQ_USB1,
-	OCTEON_IRQ_MII0,
-	OCTEON_IRQ_MII1,
 	OCTEON_IRQ_BOOTDMA,
 #ifndef CONFIG_PCI_MSI
 	OCTEON_IRQ_LAST = 127
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index 7531ecd..dca8bce 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -10,6 +10,7 @@
 	struct list_head dbe_list;
 	const struct exception_table_entry *dbe_start;
 	const struct exception_table_entry *dbe_end;
+	struct mips_hi16 *r_mips_hi16_list;
 };
 
 typedef uint8_t Elf64_Byte;		/* Type for a 8-bit quantity.  */
diff --git a/arch/mips/include/asm/r4k-timer.h b/arch/mips/include/asm/r4k-timer.h
index a37d12b..afe9e0e 100644
--- a/arch/mips/include/asm/r4k-timer.h
+++ b/arch/mips/include/asm/r4k-timer.h
@@ -12,16 +12,16 @@
 
 #ifdef CONFIG_SYNC_R4K
 
-extern void synchronise_count_master(void);
-extern void synchronise_count_slave(void);
+extern void synchronise_count_master(int cpu);
+extern void synchronise_count_slave(int cpu);
 
 #else
 
-static inline void synchronise_count_master(void)
+static inline void synchronise_count_master(int cpu)
 {
 }
 
-static inline void synchronise_count_slave(void)
+static inline void synchronise_count_slave(int cpu)
 {
 }
 
diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c
index a5066b1..4f8c3cb 100644
--- a/arch/mips/kernel/module.c
+++ b/arch/mips/kernel/module.c
@@ -39,8 +39,6 @@
 	Elf_Addr value;
 };
 
-static struct mips_hi16 *mips_hi16_list;
-
 static LIST_HEAD(dbe_list);
 static DEFINE_SPINLOCK(dbe_lock);
 
@@ -128,8 +126,8 @@
 
 	n->addr = (Elf_Addr *)location;
 	n->value = v;
-	n->next = mips_hi16_list;
-	mips_hi16_list = n;
+	n->next = me->arch.r_mips_hi16_list;
+	me->arch.r_mips_hi16_list = n;
 
 	return 0;
 }
@@ -142,18 +140,28 @@
 	return 0;
 }
 
+static void free_relocation_chain(struct mips_hi16 *l)
+{
+	struct mips_hi16 *next;
+
+	while (l) {
+		next = l->next;
+		kfree(l);
+		l = next;
+	}
+}
+
 static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v)
 {
 	unsigned long insnlo = *location;
+	struct mips_hi16 *l;
 	Elf_Addr val, vallo;
 
 	/* Sign extend the addend we extract from the lo insn.  */
 	vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000;
 
-	if (mips_hi16_list != NULL) {
-		struct mips_hi16 *l;
-
-		l = mips_hi16_list;
+	if (me->arch.r_mips_hi16_list != NULL) {
+		l = me->arch.r_mips_hi16_list;
 		while (l != NULL) {
 			struct mips_hi16 *next;
 			unsigned long insn;
@@ -188,7 +196,7 @@
 			l = next;
 		}
 
-		mips_hi16_list = NULL;
+		me->arch.r_mips_hi16_list = NULL;
 	}
 
 	/*
@@ -201,6 +209,9 @@
 	return 0;
 
 out_danger:
+	free_relocation_chain(l);
+	me->arch.r_mips_hi16_list = NULL;
+
 	pr_err("module %s: dangerous R_MIPS_LO16 REL relocation\n", me->name);
 
 	return -ENOEXEC;
@@ -273,6 +284,7 @@
 	pr_debug("Applying relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
 
+	me->arch.r_mips_hi16_list = NULL;
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
 		/* This is where to make the change */
 		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
@@ -296,6 +308,19 @@
 			return res;
 	}
 
+	/*
+	 * Normally the hi16 list should be deallocated at this point.  A
+	 * malformed binary however could contain a series of R_MIPS_HI16
+	 * relocations not followed by a R_MIPS_LO16 relocation.  In that
+	 * case, free up the list and return an error.
+	 */
+	if (me->arch.r_mips_hi16_list) {
+		free_relocation_chain(me->arch.r_mips_hi16_list);
+		me->arch.r_mips_hi16_list = NULL;
+
+		return -ENOEXEC;
+	}
+
 	return 0;
 }
 
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 31637d8..9005bf9 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -130,7 +130,7 @@
 
 	cpu_set(cpu, cpu_callin_map);
 
-	synchronise_count_slave();
+	synchronise_count_slave(cpu);
 
 	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
@@ -173,7 +173,6 @@
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	mp_ops->cpus_done();
-	synchronise_count_master();
 }
 
 /* called from main before smp_init() */
@@ -206,6 +205,7 @@
 	while (!cpu_isset(cpu, cpu_callin_map))
 		udelay(100);
 
+	synchronise_count_master(cpu);
 	return 0;
 }
 
diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c
index 842d55e..7f1eca3 100644
--- a/arch/mips/kernel/sync-r4k.c
+++ b/arch/mips/kernel/sync-r4k.c
@@ -28,12 +28,11 @@
 #define COUNTON	100
 #define NR_LOOPS 5
 
-void __cpuinit synchronise_count_master(void)
+void __cpuinit synchronise_count_master(int cpu)
 {
 	int i;
 	unsigned long flags;
 	unsigned int initcount;
-	int nslaves;
 
 #ifdef CONFIG_MIPS_MT_SMTC
 	/*
@@ -43,8 +42,7 @@
 	return;
 #endif
 
-	printk(KERN_INFO "Synchronize counters across %u CPUs: ",
-	       num_online_cpus());
+	printk(KERN_INFO "Synchronize counters for CPU %u: ", cpu);
 
 	local_irq_save(flags);
 
@@ -52,7 +50,7 @@
 	 * Notify the slaves that it's time to start
 	 */
 	atomic_set(&count_reference, read_c0_count());
-	atomic_set(&count_start_flag, 1);
+	atomic_set(&count_start_flag, cpu);
 	smp_wmb();
 
 	/* Count will be initialised to current timer for all CPU's */
@@ -69,10 +67,9 @@
 	 * two CPUs.
 	 */
 
-	nslaves = num_online_cpus()-1;
 	for (i = 0; i < NR_LOOPS; i++) {
-		/* slaves loop on '!= ncpus' */
-		while (atomic_read(&count_count_start) != nslaves)
+		/* slaves loop on '!= 2' */
+		while (atomic_read(&count_count_start) != 1)
 			mb();
 		atomic_set(&count_count_stop, 0);
 		smp_wmb();
@@ -89,7 +86,7 @@
 		/*
 		 * Wait for all slaves to leave the synchronization point:
 		 */
-		while (atomic_read(&count_count_stop) != nslaves)
+		while (atomic_read(&count_count_stop) != 1)
 			mb();
 		atomic_set(&count_count_start, 0);
 		smp_wmb();
@@ -97,6 +94,7 @@
 	}
 	/* Arrange for an interrupt in a short while */
 	write_c0_compare(read_c0_count() + COUNTON);
+	atomic_set(&count_start_flag, 0);
 
 	local_irq_restore(flags);
 
@@ -108,11 +106,10 @@
 	printk("done.\n");
 }
 
-void __cpuinit synchronise_count_slave(void)
+void __cpuinit synchronise_count_slave(int cpu)
 {
 	int i;
 	unsigned int initcount;
-	int ncpus;
 
 #ifdef CONFIG_MIPS_MT_SMTC
 	/*
@@ -127,16 +124,15 @@
 	 * so we first wait for the master to say everyone is ready
 	 */
 
-	while (!atomic_read(&count_start_flag))
+	while (atomic_read(&count_start_flag) != cpu)
 		mb();
 
 	/* Count will be initialised to next expire for all CPU's */
 	initcount = atomic_read(&count_reference);
 
-	ncpus = num_online_cpus();
 	for (i = 0; i < NR_LOOPS; i++) {
 		atomic_inc(&count_count_start);
-		while (atomic_read(&count_count_start) != ncpus)
+		while (atomic_read(&count_count_start) != 2)
 			mb();
 
 		/*
@@ -146,7 +142,7 @@
 			write_c0_count(initcount);
 
 		atomic_inc(&count_count_stop);
-		while (atomic_read(&count_count_stop) != ncpus)
+		while (atomic_read(&count_count_stop) != 2)
 			mb();
 	}
 	/* Arrange for an interrupt in a short while */
diff --git a/arch/mips/mti-malta/malta-pci.c b/arch/mips/mti-malta/malta-pci.c
index 284dea5..2147cb3 100644
--- a/arch/mips/mti-malta/malta-pci.c
+++ b/arch/mips/mti-malta/malta-pci.c
@@ -252,16 +252,3 @@
 
 	register_pci_controller(controller);
 }
-
-/* Enable PCI 2.1 compatibility in PIIX4 */
-static void __devinit quirk_dlcsetup(struct pci_dev *dev)
-{
-	u8 odlc, ndlc;
-	(void) pci_read_config_byte(dev, 0x82, &odlc);
-	/* Enable passive releases and delayed transaction */
-	ndlc = odlc | 7;
-	(void) pci_write_config_byte(dev, 0x82, ndlc);
-}
-
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0,
-	quirk_dlcsetup);
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 414a745..86d77a6 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -23,9 +23,12 @@
 #define AR724X_PCI_MEM_BASE	0x10000000
 #define AR724X_PCI_MEM_SIZE	0x08000000
 
+#define AR724X_PCI_REG_RESET		0x18
 #define AR724X_PCI_REG_INT_STATUS	0x4c
 #define AR724X_PCI_REG_INT_MASK		0x50
 
+#define AR724X_PCI_RESET_LINK_UP	BIT(0)
+
 #define AR724X_PCI_INT_DEV0		BIT(14)
 
 #define AR724X_PCI_IRQ_COUNT		1
@@ -38,6 +41,15 @@
 
 static u32 ar724x_pci_bar0_value;
 static bool ar724x_pci_bar0_is_cached;
+static bool ar724x_pci_link_up;
+
+static inline bool ar724x_pci_check_link(void)
+{
+	u32 reset;
+
+	reset = __raw_readl(ar724x_pci_ctrl_base + AR724X_PCI_REG_RESET);
+	return reset & AR724X_PCI_RESET_LINK_UP;
+}
 
 static int ar724x_pci_read(struct pci_bus *bus, unsigned int devfn, int where,
 			    int size, uint32_t *value)
@@ -46,6 +58,9 @@
 	void __iomem *base;
 	u32 data;
 
+	if (!ar724x_pci_link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	if (devfn)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
@@ -96,6 +111,9 @@
 	u32 data;
 	int s;
 
+	if (!ar724x_pci_link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	if (devfn)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
@@ -280,6 +298,10 @@
 	if (ar724x_pci_ctrl_base == NULL)
 		goto err_unmap_devcfg;
 
+	ar724x_pci_link_up = ar724x_pci_check_link();
+	if (!ar724x_pci_link_up)
+		pr_warn("ar724x: PCIe link is down\n");
+
 	ar724x_pci_irq_init(irq);
 	register_pci_controller(&ar724x_pci_controller);
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 6c6defc..af9cf30 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -141,7 +141,7 @@
 
 #define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
 
-#define ATOMIC_INIT(i)	((atomic_t) { (i) })
+#define ATOMIC_INIT(i)	{ (i) }
 
 #define smp_mb__before_atomic_dec()	smp_mb()
 #define smp_mb__after_atomic_dec()	smp_mb()
@@ -150,7 +150,7 @@
 
 #ifdef CONFIG_64BIT
 
-#define ATOMIC64_INIT(i) ((atomic64_t) { (i) })
+#define ATOMIC64_INIT(i) { (i) }
 
 static __inline__ s64
 __atomic64_add_return(s64 i, atomic64_t *v)
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index d4b94b3..2c05a92 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -309,7 +309,7 @@
 		cregs->ksp = (unsigned long)stack
 			+ (pregs->gr[21] & (THREAD_SIZE - 1));
 		cregs->gr[30] = usp;
-		if (p->personality == PER_HPUX) {
+		if (personality(p->personality) == PER_HPUX) {
 #ifdef CONFIG_HPUX
 			cregs->kpc = (unsigned long) &hpux_child_return;
 #else
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index c9b9322..7426e40 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -225,12 +225,12 @@
 	long err;
 
 	if (personality(current->personality) == PER_LINUX32
-	    && personality == PER_LINUX)
-		personality = PER_LINUX32;
+	    && personality(personality) == PER_LINUX)
+		personality = (personality & ~PER_MASK) | PER_LINUX32;
 
 	err = sys_personality(personality);
-	if (err == PER_LINUX32)
-		err = PER_LINUX;
+	if (personality(err) == PER_LINUX32)
+		err = (err & ~PER_MASK) | PER_LINUX;
 
 	return err;
 }
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
index 8d35d2c..4f9c9f6 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
@@ -345,6 +345,13 @@
 /include/ "qoriq-duart-1.dtsi"
 /include/ "qoriq-gpio-0.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
+	usb@210000 {
+		compatible = "fsl-usb2-mph-v1.6", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
+		port0;
+	};
 /include/ "qoriq-usb2-dr-0.dtsi"
+	usb@211000 {
+		compatible = "fsl-usb2-dr-v1.6", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
+	};
 /include/ "qoriq-sec4.0-0.dtsi"
 };
diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig
index f4337ba..26e541c 100644
--- a/arch/powerpc/configs/85xx/p1023rds_defconfig
+++ b/arch/powerpc/configs/85xx/p1023rds_defconfig
@@ -6,28 +6,27 @@
 CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_AUDIT=y
-CONFIG_SPARSE_IRQ=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_EMBEDDED=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
 CONFIG_P1023_RDS=y
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
 CONFIG_CPM2=y
-CONFIG_GPIO_MPC8XXX=y
 CONFIG_HIGHMEM=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_MATH_EMULATION=y
@@ -63,11 +62,11 @@
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_LEGACY=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
@@ -80,15 +79,14 @@
 CONFIG_SATA_SIL24=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
+CONFIG_FS_ENET=y
+CONFIG_FSL_PQ_MDIO=y
+CONFIG_E1000E=y
 CONFIG_MARVELL_PHY=y
 CONFIG_DAVICOM_PHY=y
 CONFIG_CICADA_PHY=y
 CONFIG_VITESSE_PHY=y
 CONFIG_FIXED_PHY=y
-CONFIG_NET_ETHERNET=y
-CONFIG_FS_ENET=y
-CONFIG_E1000E=y
-CONFIG_FSL_PQ_MDIO=y
 CONFIG_INPUT_FF_MEMLESS=m
 # CONFIG_INPUT_MOUSEDEV is not set
 # CONFIG_INPUT_KEYBOARD is not set
@@ -98,16 +96,15 @@
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=2
 CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_QE=m
-CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_I2C=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
+CONFIG_GPIO_MPC8XXX=y
 # CONFIG_HWMON is not set
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 CONFIG_SOUND=y
@@ -123,7 +120,6 @@
 CONFIG_FSL_DMA=y
 # CONFIG_NET_DMA is not set
 CONFIG_STAGING=y
-# CONFIG_STAGING_EXCLUDE_BUILD is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
@@ -150,22 +146,15 @@
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
 CONFIG_CRC_T10DIF=y
 CONFIG_FRAME_WARN=8092
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index cbb98c1..8b3d57c 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -6,8 +6,8 @@
 CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_AUDIT=y
-CONFIG_SPARSE_IRQ=y
-CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -21,23 +21,22 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
 CONFIG_P2041_RDB=y
 CONFIG_P3041_DS=y
 CONFIG_P4080_DS=y
 CONFIG_P5020_DS=y
 CONFIG_HIGHMEM=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_KEXEC=y
 CONFIG_IRQ_ALL_CPUS=y
 CONFIG_FORCE_MAX_ZONEORDER=13
-CONFIG_FSL_LBC=y
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
-CONFIG_PCI_MSI=y
 # CONFIG_PCIEASPM is not set
+CONFIG_PCI_MSI=y
 CONFIG_RAPIDIO=y
 CONFIG_FSL_RIO=y
 CONFIG_NET=y
@@ -70,6 +69,7 @@
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
@@ -77,17 +77,14 @@
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ECC=y
-CONFIG_MTD_NAND_IDS=y
-CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_M25P80=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_MTD_NAND_FSL_IFC=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_MISC_DEVICES=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
 CONFIG_BLK_DEV_SR=y
@@ -115,11 +112,9 @@
 CONFIG_PPC_EPAPR_HV_BYTECHAN=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
-CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
@@ -132,7 +127,6 @@
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 CONFIG_USB_HID=m
 CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
 CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_FSL=y
@@ -142,8 +136,6 @@
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
-CONFIG_MMC_SDHCI_OF=y
-CONFIG_MMC_SDHCI_OF_ESDHC=y
 CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_MPC85XX=y
@@ -170,19 +162,16 @@
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_RCU_TRACE=y
 CONFIG_CRYPTO_NULL=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index dd89de8..0516e22 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -56,6 +56,7 @@
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 1513006..07b7f2a 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -1,8 +1,10 @@
+CONFIG_PPC64=y
+CONFIG_ALTIVEC=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_BLK_DEV_INITRD=y
@@ -13,15 +15,16 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=4
-CONFIG_KEXEC=y
-# CONFIG_RELOCATABLE is not set
+# CONFIG_PPC_PSERIES is not set
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_PMAC64=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_KEXEC=y
+CONFIG_IRQ_ALL_CPUS=y
+# CONFIG_MIGRATION is not set
 CONFIG_PCI_MSI=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -49,6 +52,7 @@
 CONFIG_NF_CONNTRACK_IPV4=m
 CONFIG_IP_NF_QUEUE=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
@@ -56,6 +60,8 @@
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDE_PMAC=y
+CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
 CONFIG_BLK_DEV_SR=y
@@ -79,24 +85,33 @@
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
-CONFIG_MACINTOSH_DRIVERS=y
+CONFIG_IEEE1394=y
+CONFIG_IEEE1394_OHCI1394=y
+CONFIG_IEEE1394_SBP2=m
+CONFIG_IEEE1394_ETH1394=m
+CONFIG_IEEE1394_RAWIO=y
+CONFIG_IEEE1394_VIDEO1394=m
+CONFIG_IEEE1394_DV1394=m
+CONFIG_ADB_PMU=y
+CONFIG_PMAC_SMU=y
 CONFIG_MAC_EMUMOUSEBTN=y
+CONFIG_THERM_PM72=y
+CONFIG_WINDFARM=y
+CONFIG_WINDFARM_PM81=y
+CONFIG_WINDFARM_PM91=y
+CONFIG_WINDFARM_PM112=y
+CONFIG_WINDFARM_PM121=y
 CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
 CONFIG_DUMMY=m
-CONFIG_MII=y
+CONFIG_BONDING=m
 CONFIG_TUN=m
+CONFIG_NET_ETHERNET=y
+CONFIG_MII=y
+CONFIG_SUNGEM=y
 CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
-CONFIG_TIGON3=y
 CONFIG_E1000=y
-CONFIG_SUNGEM=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
+CONFIG_TIGON3=y
 CONFIG_USB_CATC=m
 CONFIG_USB_KAWETH=m
 CONFIG_USB_PEGASUS=m
@@ -106,24 +121,36 @@
 # CONFIG_USB_NET_NET1080 is not set
 # CONFIG_USB_NET_CDC_SUBSET is not set
 # CONFIG_USB_NET_ZAURUS is not set
+CONFIG_PPP=m
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_BSDCOMP=m
+CONFIG_PPPOE=m
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_JOYDEV=m
 CONFIG_INPUT_EVDEV=y
+# CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_MOUSE_PS2 is not set
+# CONFIG_SERIO_I8042 is not set
 # CONFIG_SERIO_SERPORT is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_GEN_RTC=y
 CONFIG_RAW_DRIVER=y
 CONFIG_I2C_CHARDEV=y
 # CONFIG_HWMON is not set
-CONFIG_AGP=y
-CONFIG_DRM=y
-CONFIG_DRM_NOUVEAU=y
+CONFIG_AGP=m
+CONFIG_AGP_UNINORTH=m
 CONFIG_VIDEO_OUTPUT_CONTROL=m
+CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_TILEBLITTING=y
+CONFIG_FB_OF=y
+CONFIG_FB_NVIDIA=y
+CONFIG_FB_NVIDIA_I2C=y
 CONFIG_FB_RADEON=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
@@ -131,7 +158,15 @@
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
 CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_POWERMAC=m
+CONFIG_SND_AOA=m
+CONFIG_SND_AOA_FABRIC_LAYOUT=m
+CONFIG_SND_AOA_ONYX=m
+CONFIG_SND_AOA_TAS=m
+CONFIG_SND_AOA_TOONIE=m
 CONFIG_SND_USB_AUDIO=m
+CONFIG_HID_PID=y
+CONFIG_USB_HIDDEV=y
 CONFIG_HID_GYRATION=y
 CONFIG_LOGITECH_FF=y
 CONFIG_HID_PANTHERLORD=y
@@ -139,12 +174,13 @@
 CONFIG_HID_SAMSUNG=y
 CONFIG_HID_SONY=y
 CONFIG_HID_SUNPLUS=y
-CONFIG_HID_PID=y
-CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
+CONFIG_USB_DEVICEFS=y
 CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_HCD_PPC_OF is not set
 CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 CONFIG_USB_ACM=m
 CONFIG_USB_PRINTER=y
 CONFIG_USB_STORAGE=y
@@ -208,6 +244,8 @@
 CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_POSIX_ACL=y
+CONFIG_INOTIFY=y
+CONFIG_AUTOFS_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
@@ -221,12 +259,14 @@
 CONFIG_HFSPLUS_FS=m
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_CIFS=m
+CONFIG_PARTITION_ADVANCED=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_1250=y
 CONFIG_NLS_CODEPAGE_1251=y
@@ -234,23 +274,29 @@
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_UTF8=y
+CONFIG_CRC_T10DIF=y
+CONFIG_LIBCRC32C=m
 CONFIG_MAGIC_SYSRQ=y
-# CONFIG_UNUSED_SYMBOLS is not set
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_LATENCYTOP=y
-CONFIG_STRICT_DEVMEM=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_BOOTX_TEXT=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES=m
 CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
@@ -260,6 +306,3 @@
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-# CONFIG_VIRTUALIZATION is not set
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=m
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 5aac9a8..9352e44 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -2,12 +2,12 @@
 CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
 # CONFIG_PPC_CHRP is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_83xx=y
@@ -25,7 +25,6 @@
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
 CONFIG_MATH_EMULATION=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_PCI=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -42,10 +41,9 @@
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_OF_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
@@ -64,15 +62,14 @@
 CONFIG_SATA_FSL=y
 CONFIG_SATA_SIL=y
 CONFIG_NETDEVICES=y
+CONFIG_MII=y
+CONFIG_UCC_GETH=y
+CONFIG_GIANFAR=y
 CONFIG_MARVELL_PHY=y
 CONFIG_DAVICOM_PHY=y
 CONFIG_VITESSE_PHY=y
 CONFIG_ICPLUS_PHY=y
 CONFIG_FIXED_PHY=y
-CONFIG_NET_ETHERNET=y
-CONFIG_MII=y
-CONFIG_GIANFAR=y
-CONFIG_UCC_GETH=y
 CONFIG_INPUT_FF_MEMLESS=m
 # CONFIG_INPUT_MOUSEDEV is not set
 # CONFIG_INPUT_KEYBOARD is not set
@@ -112,17 +109,12 @@
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_INOTIFY=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
 CONFIG_CRC_T10DIF=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index 03ee911c..8b5bda2 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -5,7 +5,9 @@
 CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_AUDIT=y
-CONFIG_SPARSE_IRQ=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -17,6 +19,8 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
 CONFIG_MPC8540_ADS=y
 CONFIG_MPC8560_ADS=y
 CONFIG_MPC85xx_CDS=y
@@ -40,8 +44,6 @@
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
 CONFIG_HIGHMEM=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BINFMT_MISC=m
 CONFIG_MATH_EMULATION=y
 CONFIG_FORCE_MAX_ZONEORDER=12
@@ -74,36 +76,25 @@
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
 CONFIG_FTL=y
-CONFIG_MTD_GEN_PROBE=y
-CONFIG_MTD_MAP_BANK_WIDTH_1=y
-CONFIG_MTD_MAP_BANK_WIDTH_2=y
-CONFIG_MTD_MAP_BANK_WIDTH_4=y
-CONFIG_MTD_CFI_I1=y
-CONFIG_MTD_CFI_I2=y
+CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_CFI_UTIL=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_NAND_IDS=y
-CONFIG_MTD_NAND_ECC=y
-CONFIG_MTD_M25P80=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_LEGACY=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
@@ -115,6 +106,7 @@
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_FSL=y
 CONFIG_PATA_ALI=y
+CONFIG_PATA_VIA=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
 CONFIG_FS_ENET=y
@@ -134,7 +126,6 @@
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=2
 CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
@@ -183,7 +174,6 @@
 CONFIG_HID_SONY=y
 CONFIG_HID_SUNPLUS=y
 CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
 CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_FSL=y
@@ -229,18 +219,13 @@
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
 CONFIG_CRC_T10DIF=y
 CONFIG_DEBUG_FS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index fdfa84d..b0974e7 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -7,7 +7,9 @@
 CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_AUDIT=y
-CONFIG_SPARSE_IRQ=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -19,6 +21,8 @@
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
 CONFIG_MPC8540_ADS=y
 CONFIG_MPC8560_ADS=y
 CONFIG_MPC85xx_CDS=y
@@ -42,8 +46,6 @@
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
 CONFIG_HIGHMEM=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BINFMT_MISC=m
 CONFIG_MATH_EMULATION=y
 CONFIG_IRQ_ALL_CPUS=y
@@ -77,36 +79,25 @@
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
 CONFIG_FTL=y
-CONFIG_MTD_GEN_PROBE=y
-CONFIG_MTD_MAP_BANK_WIDTH_1=y
-CONFIG_MTD_MAP_BANK_WIDTH_2=y
-CONFIG_MTD_MAP_BANK_WIDTH_4=y
-CONFIG_MTD_CFI_I1=y
-CONFIG_MTD_CFI_I2=y
+CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_CFI_UTIL=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_NAND_IDS=y
-CONFIG_MTD_NAND_ECC=y
-CONFIG_MTD_M25P80=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_LEGACY=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
@@ -137,7 +128,6 @@
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=2
 CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
@@ -186,7 +176,6 @@
 CONFIG_HID_SONY=y
 CONFIG_HID_SUNPLUS=y
 CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
 CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_FSL=y
@@ -232,18 +221,13 @@
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
 CONFIG_CRC_T10DIF=y
 CONFIG_DEBUG_FS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 50d82c8..b3c083d 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -553,9 +553,7 @@
 		& feature);
 }
 
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
 #define HBP_NUM 1
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 50ea12f..a8bf5c6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -33,6 +33,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/processor.h>
 #include <asm/page.h>
+#include <asm/cacheflush.h>
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 0124937..e006f0b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -219,4 +219,16 @@
 void kvmppc_free_lpid(long lpid);
 void kvmppc_init_lpid(unsigned long nr_lpids);
 
+static inline void kvmppc_mmu_flush_icache(pfn_t pfn)
+{
+	/* Clear i-cache for new pages */
+	struct page *page;
+	page = pfn_to_page(pfn);
+	if (!test_bit(PG_arch_1, &page->flags)) {
+		flush_dcache_icache_page(page);
+		set_bit(PG_arch_1, &page->flags);
+	}
+}
+
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/include/asm/mpic_msgr.h b/arch/powerpc/include/asm/mpic_msgr.h
index 326d33c..d4f471f 100644
--- a/arch/powerpc/include/asm/mpic_msgr.h
+++ b/arch/powerpc/include/asm/mpic_msgr.h
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <asm/smp.h>
+#include <asm/io.h>
 
 struct mpic_msgr {
 	u32 __iomem *base;
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 53b6dfa..54b73a2 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -386,6 +386,7 @@
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
+extern void power7_nap(void);
 
 #ifdef CONFIG_PSERIES_IDLE
 extern void update_smt_snooze_delay(int snooze);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85b05c4..e899572 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -76,6 +76,7 @@
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
 	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+	DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 5b25c80..a892680 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -28,6 +28,8 @@
 
 void doorbell_cause_ipi(int cpu, unsigned long data)
 {
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	mb();
 	ppc_msgsnd(PPC_DBELL, 0, data);
 }
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 2d7bb8c..e489752 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -83,11 +83,10 @@
 		return 0;
 	}
 
-	if ((tbl->it_offset + tbl->it_size) > (mask >> IOMMU_PAGE_SHIFT)) {
-		dev_info(dev, "Warning: IOMMU window too big for device mask\n");
-		dev_info(dev, "mask: 0x%08llx, table end: 0x%08lx\n",
-				mask, (tbl->it_offset + tbl->it_size) <<
-				IOMMU_PAGE_SHIFT);
+	if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) {
+		dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
+		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
+				mask, tbl->it_offset << IOMMU_PAGE_SHIFT);
 		return 0;
 	} else
 		return 1;
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 4b01a25..b40e0b4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -370,6 +370,12 @@
 	li	r3,0
 	b	syscall_exit
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -509,9 +515,6 @@
 	mr	r1,r8		/* start using new stack pointer */
 	std	r7,PACAKSAVE(r13)
 
-	ld	r6,_CCR(r1)
-	mtcrf	0xFF,r6
-
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	ld	r0,THREAD_VRSAVE(r4)
@@ -520,14 +523,22 @@
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+	lwz	r6,THREAD_DSCR_INHERIT(r4)
+	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
-	cmpd	r0,r25
-	beq	1f
+	cmpwi	r6,0
+	bne	1f
+	ld	r0,0(r7)
+1:	cmpd	r0,r25
+	beq	2f
 	mtspr	SPRN_DSCR,r0
-1:	
+2:
 END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 #endif
 
+	ld	r6,_CCR(r1)
+	mtcrf	0xFF,r6
+
 	/* r3-r13 are destroyed -- Cort */
 	REST_8GPRS(14, r1)
 	REST_10GPRS(22, r1)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e894515..39aa97d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -186,7 +186,7 @@
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
+	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -486,6 +486,7 @@
 
 	STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
 	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
+	STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
 	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index f3a82dd..956a4c4 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -253,7 +253,7 @@
 
 	/* Do not emulate user-space instructions, instead single-step them */
 	if (user_mode(regs)) {
-		bp->ctx->task->thread.last_hit_ubp = bp;
+		current->thread.last_hit_ubp = bp;
 		regs->msr |= MSR_SE;
 		goto out;
 	}
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 7140d83..e11863f 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -28,7 +28,9 @@
 	lwz	r4,ADDROFF(powersave_nap)(r3)
 	cmpwi	0,r4,0
 	beqlr
+	/* fall through */
 
+_GLOBAL(power7_nap)
 	/* NAP is a state loss, we create a regs frame on the
 	 * stack, fill it up with the state we care about and
 	 * stick a pointer to it in PACAR1. We really only
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 782bd0a..c470a40 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -25,6 +25,7 @@
 #include <asm/processor.h>
 #include <asm/machdep.h>
 #include <asm/debug.h>
+#include <linux/slab.h>
 
 /*
  * This table contains the mapping between PowerPC hardware trap types, and
@@ -101,6 +102,21 @@
 	return SIGHUP;		/* default for things we don't know about */
 }
 
+/**
+ *
+ *	kgdb_skipexception - Bail out of KGDB when we've been triggered.
+ *	@exception: Exception vector number
+ *	@regs: Current &struct pt_regs.
+ *
+ *	On some architectures we need to skip a breakpoint exception when
+ *	it occurs after a breakpoint has been removed.
+ *
+ */
+int kgdb_skipexception(int exception, struct pt_regs *regs)
+{
+	return kgdb_isremovedbreak(regs->nip);
+}
+
 static int kgdb_call_nmi_hook(struct pt_regs *regs)
 {
 	kgdb_nmicallback(raw_smp_processor_id(), regs);
@@ -138,6 +154,8 @@
 static int kgdb_singlestep(struct pt_regs *regs)
 {
 	struct thread_info *thread_info, *exception_thread_info;
+	struct thread_info *backup_current_thread_info = \
+		(struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL);
 
 	if (user_mode(regs))
 		return 0;
@@ -155,13 +173,17 @@
 	thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
 	exception_thread_info = current_thread_info();
 
-	if (thread_info != exception_thread_info)
+	if (thread_info != exception_thread_info) {
+		/* Save the original current_thread_info. */
+		memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
 		memcpy(exception_thread_info, thread_info, sizeof *thread_info);
+	}
 
 	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 
 	if (thread_info != exception_thread_info)
-		memcpy(thread_info, exception_thread_info, sizeof *thread_info);
+		/* Restore current_thread_info lastly. */
+		memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
 
 	return 1;
 }
@@ -410,7 +432,6 @@
 #else
 			linux_regs->msr |= MSR_SE;
 #endif
-			kgdb_single_step = 1;
 			atomic_set(&kgdb_cpu_doing_single_step,
 				   raw_smp_processor_id());
 		}
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 710f400..1a1f2dd 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -802,16 +802,8 @@
 #endif /* CONFIG_PPC_STD_MMU_64 */
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		if (current->thread.dscr_inherit) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = current->thread.dscr;
-		} else if (0 != dscr_default) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = dscr_default;
-		} else {
-			p->thread.dscr_inherit = 0;
-			p->thread.dscr = 0;
-		}
+		p->thread.dscr_inherit = current->thread.dscr_inherit;
+		p->thread.dscr = current->thread.dscr;
 	}
 #endif
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007..8d4214a 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -198,8 +198,15 @@
 	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
 	char *message = (char *)&info->messages;
 
+	/*
+	 * Order previous accesses before accesses in the IPI handler.
+	 */
+	smp_mb();
 	message[msg] = 1;
-	mb();
+	/*
+	 * cause_ipi functions are required to include a full barrier
+	 * before doing whatever causes the IPI.
+	 */
 	smp_ops->cause_ipi(cpu, info->data);
 }
 
@@ -211,7 +218,7 @@
 	mb();	/* order any irq clear */
 
 	do {
-		all = xchg_local(&info->messages, 0);
+		all = xchg(&info->messages, 0);
 
 #ifdef __BIG_ENDIAN
 		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index f2496f2..4e3cc47 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -107,11 +107,11 @@
 	long ret;
 
 	if (personality(current->personality) == PER_LINUX32
-	    && personality == PER_LINUX)
-		personality = PER_LINUX32;
+	    && personality(personality) == PER_LINUX)
+		personality = (personality & ~PER_MASK) | PER_LINUX32;
 	ret = sys_personality(personality);
-	if (ret == PER_LINUX32)
-		ret = PER_LINUX;
+	if (personality(ret) == PER_LINUX32)
+		ret = (ret & ~PER_MASK) | PER_LINUX;
 	return ret;
 }
 #endif
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 3529446..8302af6 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -194,6 +194,14 @@
 	return sprintf(buf, "%lx\n", dscr_default);
 }
 
+static void update_dscr(void *dummy)
+{
+	if (!current->thread.dscr_inherit) {
+		current->thread.dscr = dscr_default;
+		mtspr(SPRN_DSCR, dscr_default);
+	}
+}
+
 static ssize_t __used store_dscr_default(struct device *dev,
 		struct device_attribute *attr, const char *buf,
 		size_t count)
@@ -206,6 +214,8 @@
 		return -EINVAL;
 	dscr_default = val;
 
+	on_each_cpu(update_dscr, NULL, 1);
+
 	return count;
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be171ee..e49e931 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -535,6 +535,15 @@
 	trace_timer_interrupt_exit(regs);
 }
 
+/*
+ * Hypervisor decrementer interrupts shouldn't occur but are sometimes
+ * left pending on exit from a KVM guest.  We don't need to do anything
+ * to clear them, as they are edge-triggered.
+ */
+void hdec_interrupt(struct pt_regs *regs)
+{
+}
+
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1589723..ae0843f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -972,8 +972,9 @@
 			cpu_has_feature(CPU_FTR_DSCR)) {
 		PPC_WARN_EMULATED(mtdscr, regs);
 		rd = (instword >> 21) & 0x1f;
-		mtspr(SPRN_DSCR, regs->gpr[rd]);
+		current->thread.dscr = regs->gpr[rd];
 		current->thread.dscr_inherit = 1;
+		mtspr(SPRN_DSCR, current->thread.dscr);
 		return 0;
 	}
 #endif
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index f922c29..837f13e 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -211,6 +211,9 @@
 		pteg1 |= PP_RWRX;
 	}
 
+	if (orig_pte->may_execute)
+		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
+
 	local_irq_disable();
 
 	if (pteg[rr]) {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 10fc8ec..0688b6b 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -126,6 +126,8 @@
 
 	if (!orig_pte->may_execute)
 		rflags |= HPTE_R_N;
+	else
+		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
 
 	hash = hpt_hash(va, PTE_SIZE, MMU_SEGSIZE_256M);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5a84c8d..44b72fe 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1421,13 +1421,13 @@
 	sync			/* order setting ceded vs. testing prodded */
 	lbz	r5,VCPU_PRODDED(r3)
 	cmpwi	r5,0
-	bne	1f
+	bne	kvm_cede_prodded
 	li	r0,0		/* set trap to 0 to say hcall is handled */
 	stw	r0,VCPU_TRAP(r3)
 	li	r0,H_SUCCESS
 	std	r0,VCPU_GPR(R3)(r3)
 BEGIN_FTR_SECTION
-	b	2f		/* just send it up to host on 970 */
+	b	kvm_cede_exit	/* just send it up to host on 970 */
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 
 	/*
@@ -1446,7 +1446,7 @@
 	or	r4,r4,r0
 	PPC_POPCNTW(R7,R4)
 	cmpw	r7,r8
-	bge	2f
+	bge	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
 	li	r0,1
@@ -1555,7 +1555,8 @@
 	b	hcall_real_fallback
 
 	/* cede when already previously prodded case */
-1:	li	r0,0
+kvm_cede_prodded:
+	li	r0,0
 	stb	r0,VCPU_PRODDED(r3)
 	sync			/* order testing prodded vs. clearing ceded */
 	stb	r0,VCPU_CEDED(r3)
@@ -1563,7 +1564,8 @@
 	blr
 
 	/* we've ceded but we want to give control to the host */
-2:	li	r3,H_TOO_HARD
+kvm_cede_exit:
+	li	r3,H_TOO_HARD
 	blr
 
 secondary_too_late:
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index c510fc9..a2b6671 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -322,11 +322,11 @@
 static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	if (vcpu_e500->g2h_tlb1_map)
-		memset(vcpu_e500->g2h_tlb1_map,
-		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries, 0);
+		memset(vcpu_e500->g2h_tlb1_map, 0,
+		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
 	if (vcpu_e500->h2g_tlb1_rmap)
-		memset(vcpu_e500->h2g_tlb1_rmap,
-		       sizeof(unsigned int) * host_tlb_params[1].entries, 0);
+		memset(vcpu_e500->h2g_tlb1_rmap, 0,
+		       sizeof(unsigned int) * host_tlb_params[1].entries);
 }
 
 static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
@@ -539,6 +539,9 @@
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
 				ref, gvaddr, stlbe);
+
+	/* Clear i-cache for new pages */
+	kvmppc_mmu_flush_icache(pfn);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index dd223b3..17e5b23 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -20,7 +20,7 @@
 {
 	int err;
 
-	err = __put_user(instr, addr);
+	__put_user_size(instr, addr, 4, err);
 	if (err)
 		return err;
 	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index f9ede7c..0d24ff1 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -288,7 +288,7 @@
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	bl	.enter_vmx_usercopy
-	cmpwi	r3,0
+	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
 	ld	r3,STACKFRAMESIZE+48(r1)
 	ld	r4,STACKFRAMESIZE+56(r1)
@@ -326,38 +326,7 @@
 	dcbt	r0,r8,0b01010	/* GO */
 .machine pop
 
-	/*
-	 * We prefetch both the source and destination using enhanced touch
-	 * instructions. We use a stream ID of 0 for the load side and
-	 * 1 for the store side.
-	 */
-	clrrdi	r6,r4,7
-	clrrdi	r9,r3,7
-	ori	r9,r9,1		/* stream=1 */
-
-	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
-	cmpldi	cr1,r7,0x3FF
-	ble	cr1,1f
-	li	r7,0x3FF
-1:	lis	r0,0x0E00	/* depth=7 */
-	sldi	r7,r7,7
-	or	r7,r7,r0
-	ori	r10,r7,1	/* stream=1 */
-
-	lis	r8,0x8000	/* GO=1 */
-	clrldi	r8,r8,32
-
-.machine push
-.machine "power4"
-	dcbt	r0,r6,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
-	eieio
-	dcbt	r0,r8,0b01010	/* GO */
-.machine pop
-
-	beq	.Lunwind_stack_nonvmx_copy
+	beq	cr1,.Lunwind_stack_nonvmx_copy
 
 	/*
 	 * If source and destination are not relatively aligned we use a
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 0efdc51..7ba6c96 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -222,7 +222,7 @@
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	bl	.enter_vmx_copy
-	cmpwi	r3,0
+	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
 	ld	r3,STACKFRAMESIZE+48(r1)
 	ld	r4,STACKFRAMESIZE+56(r1)
@@ -260,7 +260,7 @@
 	dcbt	r0,r8,0b01010	/* GO */
 .machine pop
 
-	beq	.Lunwind_stack_nonvmx_copy
+	beq	cr1,.Lunwind_stack_nonvmx_copy
 
 	/*
 	 * If source and destination are not relatively aligned we use a
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index baaafde..fbdad0e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -469,6 +469,7 @@
 	__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
 #endif
 }
+EXPORT_SYMBOL(flush_dcache_icache_page);
 
 void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
 {
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 39b1597..59213cf 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1436,11 +1436,11 @@
 
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
- * has changed.
+ * has changed. Returns 1 when the topology has changed, and 0 otherwise.
  */
 int arch_update_cpu_topology(void)
 {
-	int cpu, nid, old_nid;
+	int cpu, nid, old_nid, changed = 0;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	struct device *dev;
 
@@ -1466,9 +1466,10 @@
 		dev = get_cpu_device(cpu);
 		if (dev)
 			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+		changed = 1;
 	}
 
-	return 1;
+	return changed;
 }
 
 static void topology_work_fn(struct work_struct *work)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 77b49dd..7cd2dbd 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1431,7 +1431,7 @@
 		if (!event->hw.idx || is_limited_pmc(event->hw.idx))
 			continue;
 		val = read_pmc(event->hw.idx);
-		if ((int)val < 0) {
+		if (pmc_overflow(val)) {
 			/* event has overflowed */
 			found = 1;
 			record_and_restart(event, val, regs);
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 3ef4625..7698b6e 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -106,14 +106,6 @@
 {
 	unsigned int cpu;
 
-	/* If powersave_nap is enabled, use NAP mode, else just
-	 * spin aimlessly
-	 */
-	if (!powersave_nap) {
-		generic_mach_cpu_die();
-		return;
-	}
-
 	/* Standard hot unplug procedure */
 	local_irq_disable();
 	idle_task_exit();
@@ -128,7 +120,7 @@
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
-		power7_idle();
+		power7_nap();
 		if (!generic_check_cpu_restart(cpu)) {
 			DBG("CPU%d Unexpected exit while offline !\n", cpu);
 			/* We may be getting an IPI, so we re-enable
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index a7b2a60..c37f461 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -465,7 +465,7 @@
 			iounmap(hose->cfg_data);
 		iounmap(hose->cfg_addr);
 		pcibios_free_controller(hose);
-		return 0;
+		return -ENODEV;
 	}
 
 	setup_pci_cmd(hose);
@@ -827,6 +827,7 @@
 
 void __devinit fsl_pci_init(void)
 {
+	int ret;
 	struct device_node *node;
 	struct pci_controller *hose;
 	dma_addr_t max = 0xffffffff;
@@ -855,10 +856,12 @@
 			if (!fsl_pci_primary)
 				fsl_pci_primary = node;
 
-			fsl_add_bridge(node, fsl_pci_primary == node);
-			hose = pci_find_hose_for_OF_device(node);
-			max = min(max, hose->dma_window_base_cur +
-					hose->dma_window_size);
+			ret = fsl_add_bridge(node, fsl_pci_primary == node);
+			if (ret == 0) {
+				hose = pci_find_hose_for_OF_device(node);
+				max = min(max, hose->dma_window_base_cur +
+						hose->dma_window_size);
+			}
 		}
 	}
 
diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c
index 483d8fa..e961f8c 100644
--- a/arch/powerpc/sysdev/mpic_msgr.c
+++ b/arch/powerpc/sysdev/mpic_msgr.c
@@ -14,6 +14,9 @@
 #include <linux/list.h>
 #include <linux/of_platform.h>
 #include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/slab.h>
 #include <asm/prom.h>
 #include <asm/hw_irq.h>
 #include <asm/ppc-pci.h>
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 14469cf..df0fc58 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -65,7 +65,11 @@
 static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 {
 	int hw_cpu = get_hard_smp_processor_id(n_cpu);
-	long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+	long rc;
+
+	/* Make sure all previous accesses are ordered before IPI sending */
+	mb();
+	rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
 	if (rc != H_SUCCESS) {
 		pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
 			"returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index eab3492..9b49c65 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -17,6 +17,7 @@
 #include <linux/reboot.h>
 #include <linux/delay.h>
 #include <linux/kallsyms.h>
+#include <linux/kmsg_dump.h>
 #include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/sysrq.h>
@@ -894,13 +895,13 @@
 #endif
 		default:
 			printf("Unrecognized command: ");
-		        do {
+			do {
 				if (' ' < cmd && cmd <= '~')
 					putchar(cmd);
 				else
 					printf("\\x%x", cmd);
 				cmd = inchar();
-		        } while (cmd != '\n'); 
+			} while (cmd != '\n');
 			printf(" (type ? for help)\n");
 			break;
 		}
@@ -1097,7 +1098,7 @@
 	return 1;
 }
 
-static char *breakpoint_help_string = 
+static char *breakpoint_help_string =
     "Breakpoint command usage:\n"
     "b                show breakpoints\n"
     "b <addr> [cnt]   set breakpoint at given instr addr\n"
@@ -1193,7 +1194,7 @@
 
 	default:
 		termch = cmd;
-	        cmd = skipbl();
+		cmd = skipbl();
 		if (cmd == '?') {
 			printf(breakpoint_help_string);
 			break;
@@ -1359,7 +1360,7 @@
 				       sp + REGS_OFFSET);
 				break;
 			}
-                        printf("--- Exception: %lx %s at ", regs.trap,
+			printf("--- Exception: %lx %s at ", regs.trap,
 			       getvecname(TRAP(&regs)));
 			pc = regs.nip;
 			lr = regs.link;
@@ -1623,14 +1624,14 @@
 
 	cmd = skipbl();
 	if (cmd == '\n') {
-	        unsigned long sp, toc;
+		unsigned long sp, toc;
 		asm("mr %0,1" : "=r" (sp) :);
 		asm("mr %0,2" : "=r" (toc) :);
 
 		printf("msr  = "REG"  sprg0= "REG"\n",
 		       mfmsr(), mfspr(SPRN_SPRG0));
 		printf("pvr  = "REG"  sprg1= "REG"\n",
-		       mfspr(SPRN_PVR), mfspr(SPRN_SPRG1)); 
+		       mfspr(SPRN_PVR), mfspr(SPRN_SPRG1));
 		printf("dec  = "REG"  sprg2= "REG"\n",
 		       mfspr(SPRN_DEC), mfspr(SPRN_SPRG2));
 		printf("sp   = "REG"  sprg3= "REG"\n", sp, mfspr(SPRN_SPRG3));
@@ -1783,7 +1784,7 @@
 static int brev;
 static int mnoread;
 
-static char *memex_help_string = 
+static char *memex_help_string =
     "Memory examine command usage:\n"
     "m [addr] [flags] examine/change memory\n"
     "  addr is optional.  will start where left off.\n"
@@ -1798,7 +1799,7 @@
     "NOTE: flags are saved as defaults\n"
     "";
 
-static char *memex_subcmd_help_string = 
+static char *memex_subcmd_help_string =
     "Memory examine subcommands:\n"
     "  hexval   write this val to current location\n"
     "  'string' write chars from string to this location\n"
@@ -2064,7 +2065,7 @@
 		nr = mread(adrs, temp, r);
 		adrs += nr;
 		for (m = 0; m < r; ++m) {
-		        if ((m & (sizeof(long) - 1)) == 0 && m > 0)
+			if ((m & (sizeof(long) - 1)) == 0 && m > 0)
 				putchar(' ');
 			if (m < nr)
 				printf("%.2x", temp[m]);
@@ -2072,7 +2073,7 @@
 				printf("%s", fault_chars[fault_type]);
 		}
 		for (; m < 16; ++m) {
-		        if ((m & (sizeof(long) - 1)) == 0)
+			if ((m & (sizeof(long) - 1)) == 0)
 				putchar(' ');
 			printf("  ");
 		}
@@ -2148,45 +2149,28 @@
 void
 dump_log_buf(void)
 {
-        const unsigned long size = 128;
-        unsigned long end, addr;
-        unsigned char buf[size + 1];
+	struct kmsg_dumper dumper = { .active = 1 };
+	unsigned char buf[128];
+	size_t len;
 
-        addr = 0;
-        buf[size] = '\0';
+	if (setjmp(bus_error_jmp) != 0) {
+		printf("Error dumping printk buffer!\n");
+		return;
+	}
 
-        if (setjmp(bus_error_jmp) != 0) {
-                printf("Unable to lookup symbol __log_buf!\n");
-                return;
-        }
+	catch_memory_errors = 1;
+	sync();
 
-        catch_memory_errors = 1;
-        sync();
-        addr = kallsyms_lookup_name("__log_buf");
+	kmsg_dump_rewind_nolock(&dumper);
+	while (kmsg_dump_get_line_nolock(&dumper, false, buf, sizeof(buf), &len)) {
+		buf[len] = '\0';
+		printf("%s", buf);
+	}
 
-        if (! addr)
-                printf("Symbol __log_buf not found!\n");
-        else {
-                end = addr + (1 << CONFIG_LOG_BUF_SHIFT);
-                while (addr < end) {
-                        if (! mread(addr, buf, size)) {
-                                printf("Can't read memory at address 0x%lx\n", addr);
-                                break;
-                        }
-
-                        printf("%s", buf);
-
-                        if (strlen(buf) < size)
-                                break;
-
-                        addr += size;
-                }
-        }
-
-        sync();
-        /* wait a little while to see if we get a machine check */
-        __delay(200);
-        catch_memory_errors = 0;
+	sync();
+	/* wait a little while to see if we get a machine check */
+	__delay(200);
+	catch_memory_errors = 0;
 }
 
 /*
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 32e8449..9b94a16 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -180,7 +180,8 @@
 #define ELF_PLATFORM (elf_platform)
 
 #ifndef CONFIG_64BIT
-#define SET_PERSONALITY(ex) set_personality(PER_LINUX)
+#define SET_PERSONALITY(ex) \
+	set_personality(PER_LINUX | (current->personality & (~PER_MASK)))
 #else /* CONFIG_64BIT */
 #define SET_PERSONALITY(ex)					\
 do {								\
diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h
index 7bcc14e..bf2a2ad 100644
--- a/arch/s390/include/asm/posix_types.h
+++ b/arch/s390/include/asm/posix_types.h
@@ -13,6 +13,7 @@
  */
 
 typedef unsigned long   __kernel_size_t;
+typedef long            __kernel_ssize_t;
 #define __kernel_size_t __kernel_size_t
 
 typedef unsigned short	__kernel_old_dev_t;
@@ -25,7 +26,6 @@
 typedef unsigned short  __kernel_ipc_pid_t;
 typedef unsigned short  __kernel_uid_t;
 typedef unsigned short  __kernel_gid_t;
-typedef int             __kernel_ssize_t;
 typedef int             __kernel_ptrdiff_t;
 
 #else /* __s390x__ */
@@ -35,7 +35,6 @@
 typedef int             __kernel_ipc_pid_t;
 typedef unsigned int    __kernel_uid_t;
 typedef unsigned int    __kernel_gid_t;
-typedef long            __kernel_ssize_t;
 typedef long            __kernel_ptrdiff_t;
 typedef unsigned long   __kernel_sigset_t;      /* at least 32 bits */
 
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index a0a8340..ce26ac3 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -44,6 +44,7 @@
 }
 
 static inline int smp_find_processor_id(int address) { return 0; }
+static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_yield(void) { }
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index a1e9d69..584b936 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -169,7 +169,7 @@
 	if (*offset)
 		return -EINVAL;
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val < oprofile_min_interval)
 		oprofile_hw_interval = oprofile_min_interval;
@@ -212,7 +212,7 @@
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val != 0)
 		return -EINVAL;
@@ -243,7 +243,7 @@
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -278,7 +278,7 @@
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -317,7 +317,7 @@
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index f602385..0748fe0 100644
--- a/arch/um/os-Linux/time.c
+++ b/arch/um/os-Linux/time.c
@@ -114,7 +114,7 @@
 	skew += this_tick - last_tick;
 
 	while (skew >= one_tick) {
-		alarm_handler(SIGVTALRM, NULL);
+		alarm_handler(SIGVTALRM, NULL, NULL);
 		skew -= one_tick;
 	}
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b0c5276..682e9c2 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -27,6 +27,10 @@
 
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
+        # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
+        # with nonstandard options
+        KBUILD_CFLAGS += -fno-pic
+
         # prevent gcc from keeping the stack 16 byte aligned
         KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 5a747dd..f7535be 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -57,7 +57,7 @@
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/code16gcc.h \
-		   -fno-strict-aliasing -fomit-frame-pointer \
+		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
 			$(call cc-option, -fno-unit-at-a-time)) \
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index b315a33..33692ea 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -12,8 +12,7 @@
  * Simple spin lock operations.  There are two variants, one clears IRQ's
  * on the local processor, one does not.
  *
- * These are fair FIFO ticket locks, which are currently limited to 256
- * CPUs.
+ * These are fair FIFO ticket locks, which support up to 2^16 CPUs.
  *
  * (the type definitions are in asm/spinlock_types.h)
  */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index afb7ff7..ced4534 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -165,7 +165,7 @@
 #endif
 
 #ifdef P6_NOP1
-static const unsigned char  __initconst_or_module p6nops[] =
+static const unsigned char p6nops[] =
 {
 	P6_NOP1,
 	P6_NOP2,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index a6c64aa..c265593 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1356,6 +1356,16 @@
 	if (!IO_APIC_IRQ(irq))
 		return;
 
+	/*
+	 * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC
+	 * can handle this irq and the apic driver is finialized at this point,
+	 * update the cfg->domain.
+	 */
+	if (irq < legacy_pic->nr_legacy_irqs &&
+	    cpumask_equal(cfg->domain, cpumask_of(0)))
+		apic->vector_allocation_domain(0, cfg->domain,
+					       apic->target_cpus());
+
 	if (assign_irq_vector(irq, cfg, apic->target_cpus()))
 		return;
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 46d8786..a5fbc3c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -144,6 +144,8 @@
 {
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
 	return 1;
 }
 __setup("noxsave", x86_xsave_setup);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3823669..0d3d63a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1522,8 +1522,16 @@
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
 	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
 	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+	/*
+	 * If PMU counter has PEBS enabled it is not enough to disable counter
+	 * on a guest entry since PEBS memory write can overshoot guest entry
+	 * and corrupt guest memory. Disabling PEBS solves the problem.
+	 */
+	arr[1].msr = MSR_IA32_PEBS_ENABLE;
+	arr[1].host = cpuc->pebs_enabled;
+	arr[1].guest = 0;
 
-	*nr = 1;
+	*nr = 2;
 	return arr;
 }
 
@@ -2000,6 +2008,7 @@
 		break;
 
 	case 28: /* Atom */
+	case 54: /* Cedariew */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b426..da02e9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@
 	 * to have an operational LBR which can freeze
 	 * on PMU interrupt
 	 */
-	if (boot_cpu_data.x86_mask < 10) {
+	if (boot_cpu_data.x86_model == 28
+	    && boot_cpu_data.x86_mask < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 7563fda..0a55710 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -796,7 +796,6 @@
 
 DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
 DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
-DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63");
 DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
 
@@ -902,16 +901,21 @@
 	.attrs = nhmex_uncore_cbox_formats_attr,
 };
 
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
 static struct intel_uncore_type nhmex_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 6,
-	.num_boxes		= 8,
+	.num_boxes		= 10,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
 	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
 	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
 	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_C_MSR_OFFSET,
+	.msr_offsets		= nhmex_cbox_msr_offsets,
 	.pair_ctr_ctl		= 1,
 	.ops			= &nhmex_uncore_ops,
 	.format_group		= &nhmex_uncore_cbox_format_group
@@ -1032,24 +1036,22 @@
 
 static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
-	if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) {
-		reg1->config = event->attr.config1;
-		reg2->config = event->attr.config2;
-	} else {
-		reg1->config = ~0ULL;
-		reg2->config = ~0ULL;
-	}
+	/* only TO_R_PROG_EV event uses the match/mask register */
+	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+	    NHMEX_S_EVENT_TO_R_PROG_EV)
+		return 0;
 
 	if (box->pmu->pmu_idx == 0)
 		reg1->reg = NHMEX_S0_MSR_MM_CFG;
 	else
 		reg1->reg = NHMEX_S1_MSR_MM_CFG;
-
 	reg1->idx = 0;
-
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
 	return 0;
 }
 
@@ -1059,8 +1061,8 @@
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
-	wrmsrl(reg1->reg, 0);
-	if (reg1->config != ~0ULL || reg2->config != ~0ULL) {
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, 0);
 		wrmsrl(reg1->reg + 1, reg1->config);
 		wrmsrl(reg1->reg + 2, reg2->config);
 		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
@@ -1074,7 +1076,6 @@
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
 	&format_attr_thresh8.attr,
-	&format_attr_mm_cfg.attr,
 	&format_attr_match.attr,
 	&format_attr_mask.attr,
 	NULL,
@@ -1142,6 +1143,9 @@
 	EVENT_EXTRA_END
 };
 
+/* Nehalem-EX or Westmere-EX ? */
+bool uncore_nhmex;
+
 static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
 {
 	struct intel_uncore_extra_reg *er;
@@ -1171,18 +1175,29 @@
 		return false;
 
 	/* mask of the shared fields */
-	mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	if (uncore_nhmex)
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	else
+		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
 	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
 
 	raw_spin_lock_irqsave(&er->lock, flags);
 	/* add mask of the non-shared field if it's in use */
-	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8))
-		mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+		if (uncore_nhmex)
+			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	}
 
 	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
 		atomic_add(1 << (idx * 8), &er->ref);
-		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
-			NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		if (uncore_nhmex)
+			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
 		er->config &= ~mask;
 		er->config |= (config & mask);
 		ret = true;
@@ -1216,7 +1231,10 @@
 
 	/* get the non-shared control bits and shift them */
 	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (uncore_nhmex)
+		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	else
+		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
 	if (new_idx > orig_idx) {
 		idx = new_idx - orig_idx;
 		config <<= 3 * idx;
@@ -1226,6 +1244,10 @@
 	}
 
 	/* add the shared control bits back */
+	if (uncore_nhmex)
+		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	else
+		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
 	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
 	if (modify) {
 		/* adjust the main event selector */
@@ -1264,7 +1286,8 @@
 	}
 
 	/* for the match/mask registers */
-	if ((uncore_box_is_fake(box) || !reg2->alloc) &&
+	if (reg2->idx != EXTRA_REG_NONE &&
+	    (uncore_box_is_fake(box) || !reg2->alloc) &&
 	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
 		goto fail;
 
@@ -1278,7 +1301,8 @@
 		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
 			nhmex_mbox_alter_er(event, idx[0], true);
 		reg1->alloc |= alloc;
-		reg2->alloc = 1;
+		if (reg2->idx != EXTRA_REG_NONE)
+			reg2->alloc = 1;
 	}
 	return NULL;
 fail:
@@ -1342,9 +1366,6 @@
 	struct extra_reg *er;
 	unsigned msr;
 	int reg_idx = 0;
-
-	if (WARN_ON_ONCE(reg1->idx != -1))
-		return -EINVAL;
 	/*
 	 * The mbox events may require 2 extra MSRs at the most. But only
 	 * the lower 32 bits in these MSRs are significant, so we can use
@@ -1355,11 +1376,6 @@
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
-		if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) ||
-		    er->idx == __BITS_VALUE(reg1->idx, 1, 8))
-			continue;
-		if (WARN_ON_ONCE(reg_idx >= 2))
-			return -EINVAL;
 
 		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
 		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
@@ -1368,6 +1384,8 @@
 		/* always use the 32~63 bits to pass the PLD config */
 		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
 			reg_idx = 1;
+		else if (WARN_ON_ONCE(reg_idx > 0))
+			return -EINVAL;
 
 		reg1->idx &= ~(0xff << (reg_idx * 8));
 		reg1->reg &= ~(0xffff << (reg_idx * 16));
@@ -1376,17 +1394,21 @@
 		reg1->config = event->attr.config1;
 		reg_idx++;
 	}
-	/* use config2 to pass the filter config */
-	reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
-	if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
-		reg2->config = event->attr.config2;
-	else
-		reg2->config = ~0ULL;
-	if (box->pmu->pmu_idx == 0)
-		reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
-	else
-		reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
-
+	/*
+	 * The mbox only provides ability to perform address matching
+	 * for the PLD events.
+	 */
+	if (reg_idx == 2) {
+		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+			reg2->config = event->attr.config2;
+		else
+			reg2->config = ~0ULL;
+		if (box->pmu->pmu_idx == 0)
+			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+		else
+			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+	}
 	return 0;
 }
 
@@ -1422,34 +1444,36 @@
 		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
 			nhmex_mbox_shared_reg_config(box, idx));
 
-	wrmsrl(reg2->reg, 0);
-	if (reg2->config != ~0ULL) {
-		wrmsrl(reg2->reg + 1,
-			reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
-		wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
-			(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
-		wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+	if (reg2->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg2->reg, 0);
+		if (reg2->config != ~0ULL) {
+			wrmsrl(reg2->reg + 1,
+				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+		}
 	}
 
 	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
 }
 
-DEFINE_UNCORE_FORMAT_ATTR(count_mode,	count_mode,	"config:2-3");
-DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode,	"config:4-5");
-DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,	wrap_mode,	"config:6");
-DEFINE_UNCORE_FORMAT_ATTR(flag_mode,	flag_mode,	"config:7");
-DEFINE_UNCORE_FORMAT_ATTR(inc_sel,	inc_sel,	"config:9-13");
-DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,	set_flag_sel,	"config:19-21");
-DEFINE_UNCORE_FORMAT_ATTR(filter_cfg,	filter_cfg,	"config2:63");
-DEFINE_UNCORE_FORMAT_ATTR(filter_match,	filter_match,	"config2:0-33");
-DEFINE_UNCORE_FORMAT_ATTR(filter_mask,	filter_mask,	"config2:34-61");
-DEFINE_UNCORE_FORMAT_ATTR(dsp,		dsp,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(thr,		thr,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(fvc,		fvc,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pgt,		pgt,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(map,		map,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(iss,		iss,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pld,		pld,		"config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
 
 static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	&format_attr_count_mode.attr,
@@ -1458,7 +1482,7 @@
 	&format_attr_flag_mode.attr,
 	&format_attr_inc_sel.attr,
 	&format_attr_set_flag_sel.attr,
-	&format_attr_filter_cfg.attr,
+	&format_attr_filter_cfg_en.attr,
 	&format_attr_filter_match.attr,
 	&format_attr_filter_mask.attr,
 	&format_attr_dsp.attr,
@@ -1482,6 +1506,12 @@
 	{ /* end: all zeroes */ },
 };
 
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+	{ /* end: all zeroes */ },
+};
+
 static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
 	NHMEX_UNCORE_OPS_COMMON_INIT(),
 	.enable_event	= nhmex_mbox_msr_enable_event,
@@ -1513,7 +1543,7 @@
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	int port;
 
-	/* adjust the main event selector */
+	/* adjust the main event selector and extra register index */
 	if (reg1->idx % 2) {
 		reg1->idx--;
 		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
@@ -1522,29 +1552,17 @@
 		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
 	}
 
-	/* adjust address or config of extra register */
+	/* adjust extra register config */
 	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
 	switch (reg1->idx % 6) {
-	case 0:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
-		break;
-	case 1:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
-		break;
 	case 2:
-		/* the 8~15 bits to the 0~7 bits */
+		/* shift the 8~15 bits to the 0~7 bits */
 		reg1->config >>= 8;
 		break;
 	case 3:
-		/* the 0~7 bits to the 8~15 bits */
+		/* shift the 0~7 bits to the 8~15 bits */
 		reg1->config <<= 8;
 		break;
-	case 4:
-		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
-		break;
-	case 5:
-		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
-		break;
 	};
 }
 
@@ -1671,7 +1689,7 @@
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
 	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int port, idx;
+	int idx;
 
 	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
 		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
@@ -1681,27 +1699,11 @@
 	reg1->idx = idx;
 	reg1->config = event->attr.config1;
 
-	port = idx / 6 + box->pmu->pmu_idx * 4;
-	idx %= 6;
-	switch (idx) {
-	case 0:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
-		break;
-	case 1:
-		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
-		break;
-	case 2:
-	case 3:
-		reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port);
-		break;
+	switch (idx % 6) {
 	case 4:
 	case 5:
-		if (idx == 4)
-			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
-		else
-			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
-		reg2->config = event->attr.config2;
 		hwc->config |= event->attr.config & (~0ULL << 32);
+		reg2->config = event->attr.config2;
 		break;
 	};
 	return 0;
@@ -1727,28 +1729,34 @@
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx, er_idx;
+	int idx, port;
 
-	idx = reg1->idx % 6;
-	er_idx = idx;
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
+	idx = reg1->idx;
+	port = idx / 6 + box->pmu->pmu_idx * 4;
 
-	switch (idx) {
+	switch (idx % 6) {
 	case 0:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+		break;
 	case 1:
-		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
 		break;
 	case 2:
 	case 3:
-		wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx));
+		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+			nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5));
 		break;
 	case 4:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+		break;
 	case 5:
-		wrmsrl(reg1->reg, reg1->config);
-		wrmsrl(reg1->reg + 1, hwc->config >> 32);
-		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
 		break;
 	};
 
@@ -1756,8 +1764,8 @@
 		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
 }
 
-DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
 DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
 DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
@@ -2303,6 +2311,7 @@
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
 
 	if (event->attr.config == UNCORE_FIXED_EVENT) {
 		/* no fixed counter */
@@ -2373,7 +2382,7 @@
 	type->attr_groups[1] = NULL;
 }
 
-static void uncore_types_exit(struct intel_uncore_type **types)
+static void __init uncore_types_exit(struct intel_uncore_type **types)
 {
 	int i;
 	for (i = 0; types[i]; i++)
@@ -2814,7 +2823,13 @@
 			snbep_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snbep_msr_uncores;
 		break;
-	case 46:
+	case 46: /* Nehalem-EX */
+		uncore_nhmex = true;
+	case 47: /* Westmere-EX aka. Xeon E7 */
+		if (!uncore_nhmex)
+			nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+		if (nhmex_uncore_cbox.num_boxes > max_cores)
+			nhmex_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = nhmex_msr_uncores;
 		break;
 	default:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index c9e5dc5..5b81c18 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -230,6 +230,7 @@
 #define NHMEX_S1_MSR_MASK			0xe5a
 
 #define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV		0
 
 /* NHM-EX Mbox */
 #define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
@@ -275,18 +276,12 @@
 		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
 		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
 
-
-#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK	0x1f
-#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK	(0x7 << 5)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK	(0x7 << 8)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR	(1 << 23)
-#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK			\
-		(NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK  |	\
-		 NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
 #define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (11 + 3 * (n)))
 
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (12 + 3 * (n)))
+
 /*
  * use the 9~13 bits to select event If the 7th bit is not set,
  * otherwise use the 19~21 bits to select event.
@@ -368,6 +363,7 @@
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
 	unsigned pair_ctr_ctl:1;
+	unsigned *msr_offsets;
 	struct event_constraint unconstrainted;
 	struct event_constraint *constraints;
 	struct intel_uncore_pmu *pmus;
@@ -485,29 +481,31 @@
 	return idx * 8 + box->pmu->type->perf_ctr;
 }
 
-static inline
-unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_box_offset(struct intel_uncore_box *box)
+{
+	struct intel_uncore_pmu *pmu = box->pmu;
+	return pmu->type->msr_offsets ?
+		pmu->type->msr_offsets[pmu->pmu_idx] :
+		pmu->type->msr_offset * pmu->pmu_idx;
+}
+
+static inline unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
 {
 	if (!box->pmu->type->box_ctl)
 		return 0;
-	return box->pmu->type->box_ctl +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->box_ctl + uncore_msr_box_offset(box);
 }
 
-static inline
-unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
 {
 	if (!box->pmu->type->fixed_ctl)
 		return 0;
-	return box->pmu->type->fixed_ctl +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box);
 }
 
-static inline
-unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
+static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 {
-	return box->pmu->type->fixed_ctr +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+	return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
 }
 
 static inline
@@ -515,7 +513,7 @@
 {
 	return box->pmu->type->event_ctl +
 		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+		uncore_msr_box_offset(box);
 }
 
 static inline
@@ -523,7 +521,7 @@
 {
 	return box->pmu->type->perf_ctr +
 		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
-		box->pmu->type->msr_offset * box->pmu->pmu_idx;
+		uncore_msr_box_offset(box);
 }
 
 static inline
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7ad683d..d44f782 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -270,7 +270,7 @@
 
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			break_affinity = 1;
-			affinity = cpu_all_mask;
+			affinity = cpu_online_mask;
 		}
 
 		chip = irq_data_get_irq_chip(data);
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 8a2ce8f..82746f9 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -143,11 +143,12 @@
 				  unsigned int *current_size)
 {
 	struct microcode_header_amd *mc_hdr;
-	unsigned int actual_size;
+	unsigned int actual_size, patch_size;
 	u16 equiv_cpu_id;
 
 	/* size of the current patch we're staring at */
-	*current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE;
+	patch_size = *(u32 *)(ucode_ptr + 4);
+	*current_size = patch_size + SECTION_HDR_SIZE;
 
 	equiv_cpu_id = find_equiv_id();
 	if (!equiv_cpu_id)
@@ -174,7 +175,7 @@
 	/*
 	 * now that the header looks sane, verify its size
 	 */
-	actual_size = verify_ucode_size(cpu, *current_size, leftover_size);
+	actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
 	if (!actual_size)
 		return 0;
 
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62..9e5bcf1 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@
 	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
+	if (ret > 0)
+		perf_check_microcode();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 97d9a99..a3b57a2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -475,13 +475,26 @@
 	return address_mask(ctxt, reg);
 }
 
+static void masked_increment(ulong *reg, ulong mask, int inc)
+{
+	assign_masked(reg, *reg + inc, mask);
+}
+
 static inline void
 register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc)
 {
+	ulong mask;
+
 	if (ctxt->ad_bytes == sizeof(unsigned long))
-		*reg += inc;
+		mask = ~0UL;
 	else
-		*reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt));
+		mask = ad_mask(ctxt);
+	masked_increment(reg, mask, inc);
+}
+
+static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
+{
+	masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc);
 }
 
 static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -1522,8 +1535,8 @@
 {
 	struct segmented_address addr;
 
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes);
-	addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+	rsp_increment(ctxt, -bytes);
+	addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
 	addr.seg = VCPU_SREG_SS;
 
 	return segmented_write(ctxt, addr, data, bytes);
@@ -1542,13 +1555,13 @@
 	int rc;
 	struct segmented_address addr;
 
-	addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+	addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
 	addr.seg = VCPU_SREG_SS;
 	rc = segmented_read(ctxt, addr, dest, len);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len);
+	rsp_increment(ctxt, len);
 	return rc;
 }
 
@@ -1688,8 +1701,7 @@
 
 	while (reg >= VCPU_REGS_RAX) {
 		if (reg == VCPU_REGS_RSP) {
-			register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP],
-							ctxt->op_bytes);
+			rsp_increment(ctxt, ctxt->op_bytes);
 			--reg;
 		}
 
@@ -2825,7 +2837,7 @@
 	rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val);
+	rsp_increment(ctxt, ctxt->src.val);
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index e498b18..9fc9aa7 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -318,7 +318,7 @@
 		if (val & 0x10) {
 			u8 edge_irr = s->irr & ~s->elcr;
 			int i;
-			bool found;
+			bool found = false;
 			struct kvm_vcpu *vcpu;
 
 			s->init4 = val & 1;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01ca004..7fbd0d2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4113,16 +4113,21 @@
 		LIST_HEAD(invalid_list);
 
 		/*
+		 * Never scan more than sc->nr_to_scan VM instances.
+		 * Will not hit this condition practically since we do not try
+		 * to shrink more than one VM and it is very unlikely to see
+		 * !n_used_mmu_pages so many times.
+		 */
+		if (!nr_to_scan--)
+			break;
+		/*
 		 * n_used_mmu_pages is accessed without holding kvm->mmu_lock
 		 * here. We may skip a VM instance errorneosly, but we do not
 		 * want to shrink a VM that only started to populate its MMU
 		 * anyway.
 		 */
-		if (kvm->arch.n_used_mmu_pages > 0) {
-			if (!nr_to_scan--)
-				break;
+		if (!kvm->arch.n_used_mmu_pages)
 			continue;
-		}
 
 		idx = srcu_read_lock(&kvm->srcu);
 		spin_lock(&kvm->mmu_lock);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03d..b1eb202 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3619,6 +3619,7 @@
 
 static int alloc_apic_access_page(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3633,7 +3634,13 @@
 	if (r)
 		goto out;
 
-	kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+	page = gfn_to_page(kvm, 0xfee00);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.apic_access_page = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -3641,6 +3648,7 @@
 
 static int alloc_identity_pagetable(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3656,8 +3664,13 @@
 	if (r)
 		goto out;
 
-	kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
-			kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.ept_identity_pagetable = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -6575,7 +6588,7 @@
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
-	    best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6585,7 +6598,7 @@
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 		if (best)
-			best->ecx &= ~bit(X86_FEATURE_INVPCID);
+			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 42bce48..2966c84 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -806,7 +806,7 @@
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	9
+#define KVM_SAVE_MSRS_BEGIN	10
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
@@ -2000,6 +2000,9 @@
 	case MSR_KVM_STEAL_TIME:
 		data = vcpu->arch.st.msr_val;
 		break;
+	case MSR_KVM_PV_EOI_EN:
+		data = vcpu->arch.pv_eoi.msr_val;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:
@@ -5110,17 +5113,20 @@
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct page *page;
 
 	if (!apic || !apic->vapic_addr)
-		return;
+		return 0;
 
 	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
 
 	vcpu->arch.apic->vapic_page = page;
+	return 0;
 }
 
 static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5427,7 +5433,11 @@
 	}
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	vapic_enter(vcpu);
+	r = vapic_enter(vcpu);
+	if (r) {
+		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		return r;
+	}
 
 	r = 1;
 	while (r > 0) {
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f6679a7..b91e485 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -56,9 +56,16 @@
 }
 
 /*
- * search for a shareable pmd page for hugetlb.
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
-static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+static pte_t *
+huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -68,9 +75,10 @@
 	struct vm_area_struct *svma;
 	unsigned long saddr;
 	pte_t *spte = NULL;
+	pte_t *pte;
 
 	if (!vma_shareable(vma, addr))
-		return;
+		return (pte_t *)pmd_alloc(mm, pud, addr);
 
 	mutex_lock(&mapping->i_mmap_mutex);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
@@ -97,7 +105,9 @@
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
+	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
+	return pte;
 }
 
 /*
@@ -142,8 +152,9 @@
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (pud_none(*pud))
-				huge_pmd_share(mm, addr, pud);
-			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+				pte = huge_pmd_share(mm, addr, pud);
+			else
+				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 931930a..a718e0d 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -919,13 +919,11 @@
 
 	/*
 	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it, in the
-	 * error case, and during early boot (for EFI) we fall back
-	 * to cpa_flush_all (which uses wbinvd):
+	 * avoid the wbindv. If the CPU does not support it and in the
+	 * error case we fall back to cpa_flush_all (which uses
+	 * wbindv):
 	 */
-	if (early_boot_irqs_disabled)
-		__cpa_flush_all((void *)(long)cache);
-	else if (!ret && cpu_has_clflush) {
+	if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 2dc29f5..92660eda 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -234,7 +234,22 @@
 	return status;
 }
 
-static int efi_set_rtc_mmss(unsigned long nowtime)
+static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
+					     efi_time_cap_t *tc)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	efi_call_phys_prelog();
+	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
+				virt_to_phys(tc));
+	efi_call_phys_epilog();
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+int efi_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes;
 	efi_status_t 	status;
@@ -263,7 +278,7 @@
 	return 0;
 }
 
-static unsigned long efi_get_time(void)
+unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -606,13 +621,18 @@
 	}
 	/*
 	 * We will only need *early* access to the following
-	 * EFI runtime service before set_virtual_address_map
+	 * two EFI runtime services before set_virtual_address_map
 	 * is invoked.
 	 */
+	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
 	efi_phys.set_virtual_address_map =
 		(efi_set_virtual_address_map_t *)
 		runtime->set_virtual_address_map;
-
+	/*
+	 * Make efi_get_time can be called before entering
+	 * virtual mode.
+	 */
+	efi.get_time = phys_efi_get_time;
 	early_iounmap(runtime, sizeof(efi_runtime_services_t));
 
 	return 0;
@@ -700,10 +720,12 @@
 		efi_enabled = 0;
 		return;
 	}
+#ifdef CONFIG_X86_32
 	if (efi_native) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
+#endif
 
 #if EFI_DEBUG
 	print_efi_memmap();
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index b2d534c..8869287 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -72,7 +72,7 @@
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/../../boot/code16gcc.h \
-		   -fno-strict-aliasing -fomit-frame-pointer \
+		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
 		   $(call cc-option, -ffreestanding) \
 		   $(call cc-option, -fno-toplevel-reorder,\
 			$(call cc-option, -fno-unit-at-a-time)) \
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 29aed7a..a582bfe 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -60,8 +60,8 @@
 51	common	getsockname		sys_getsockname
 52	common	getpeername		sys_getpeername
 53	common	socketpair		sys_socketpair
-54	common	setsockopt		sys_setsockopt
-55	common	getsockopt		sys_getsockopt
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
 56	common	clone			stub_clone
 57	common	fork			stub_fork
 58	common	vfork			stub_vfork
@@ -353,3 +353,5 @@
 538	x32	sendmmsg		compat_sys_sendmmsg
 539	x32	process_vm_readv	compat_sys_process_vm_readv
 540	x32	process_vm_writev	compat_sys_process_vm_writev
+541	x32	setsockopt		compat_sys_setsockopt
+542	x32	getsockopt		compat_sys_getsockopt
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bf4bda6..9642d4a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -31,7 +31,6 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/syscore_ops.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -1470,130 +1469,38 @@
 #endif
 }
 
-#ifdef CONFIG_XEN_PVHVM
-/*
- * The pfn containing the shared_info is located somewhere in RAM. This
- * will cause trouble if the current kernel is doing a kexec boot into a
- * new kernel. The new kernel (and its startup code) can not know where
- * the pfn is, so it can not reserve the page. The hypervisor will
- * continue to update the pfn, and as a result memory corruption occours
- * in the new kernel.
- *
- * One way to work around this issue is to allocate a page in the
- * xen-platform pci device's BAR memory range. But pci init is done very
- * late and the shared_info page is already in use very early to read
- * the pvclock. So moving the pfn from RAM to MMIO is racy because some
- * code paths on other vcpus could access the pfn during the small
- * window when the old pfn is moved to the new pfn. There is even a
- * small window were the old pfn is not backed by a mfn, and during that
- * time all reads return -1.
- *
- * Because it is not known upfront where the MMIO region is located it
- * can not be used right from the start in xen_hvm_init_shared_info.
- *
- * To minimise trouble the move of the pfn is done shortly before kexec.
- * This does not eliminate the race because all vcpus are still online
- * when the syscore_ops will be called. But hopefully there is no work
- * pending at this point in time. Also the syscore_op is run last which
- * reduces the risk further.
- */
-
-static struct shared_info *xen_hvm_shared_info;
-
-static void xen_hvm_connect_shared_info(unsigned long pfn)
+void __ref xen_hvm_init_shared_info(void)
 {
+	int cpu;
 	struct xen_add_to_physmap xatp;
+	static struct shared_info *shared_info_page = 0;
 
+	if (!shared_info_page)
+		shared_info_page = (struct shared_info *)
+			extend_brk(PAGE_SIZE, PAGE_SIZE);
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = pfn;
+	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 
-}
-static void xen_hvm_set_shared_info(struct shared_info *sip)
-{
-	int cpu;
-
-	HYPERVISOR_shared_info = sip;
+	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
 
 	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
 	 * page, we use it in the event channel upcall and in some pvclock
 	 * related functions. We don't need the vcpu_info placement
 	 * optimizations because we don't use any pv_mmu or pv_irq op on
 	 * HVM.
-	 * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is
-	 * online but xen_hvm_set_shared_info is run at resume time too and
+	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
+	 * online but xen_hvm_init_shared_info is run at resume time too and
 	 * in that case multiple vcpus might be online. */
 	for_each_online_cpu(cpu) {
 		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 	}
 }
 
-/* Reconnect the shared_info pfn to a mfn */
-void xen_hvm_resume_shared_info(void)
-{
-	xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT);
-}
-
-#ifdef CONFIG_KEXEC
-static struct shared_info *xen_hvm_shared_info_kexec;
-static unsigned long xen_hvm_shared_info_pfn_kexec;
-
-/* Remember a pfn in MMIO space for kexec reboot */
-void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn)
-{
-	xen_hvm_shared_info_kexec = sip;
-	xen_hvm_shared_info_pfn_kexec = pfn;
-}
-
-static void xen_hvm_syscore_shutdown(void)
-{
-	struct xen_memory_reservation reservation = {
-		.domid = DOMID_SELF,
-		.nr_extents = 1,
-	};
-	unsigned long prev_pfn;
-	int rc;
-
-	if (!xen_hvm_shared_info_kexec)
-		return;
-
-	prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT;
-	set_xen_guest_handle(reservation.extent_start, &prev_pfn);
-
-	/* Move pfn to MMIO, disconnects previous pfn from mfn */
-	xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec);
-
-	/* Update pointers, following hypercall is also a memory barrier */
-	xen_hvm_set_shared_info(xen_hvm_shared_info_kexec);
-
-	/* Allocate new mfn for previous pfn */
-	do {
-		rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
-		if (rc == 0)
-			msleep(123);
-	} while (rc == 0);
-
-	/* Make sure the previous pfn is really connected to a (new) mfn */
-	BUG_ON(rc != 1);
-}
-
-static struct syscore_ops xen_hvm_syscore_ops = {
-	.shutdown = xen_hvm_syscore_shutdown,
-};
-#endif
-
-/* Use a pfn in RAM, may move to MMIO before kexec. */
-static void __init xen_hvm_init_shared_info(void)
-{
-	/* Remember pointer for resume */
-	xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT);
-	xen_hvm_set_shared_info(xen_hvm_shared_info);
-}
-
+#ifdef CONFIG_XEN_PVHVM
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
@@ -1644,9 +1551,6 @@
 	init_hvm_pv_info();
 
 	xen_hvm_init_shared_info();
-#ifdef CONFIG_KEXEC
-	register_syscore_ops(&xen_hvm_syscore_ops);
-#endif
 
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b65a761..5141d80 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1283,7 +1283,7 @@
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
 	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
 		args->op.arg1.linear_addr = start;
 	}
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b2e91d4..76ba0e9 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -196,9 +196,11 @@
 
 /* When we populate back during bootup, the amount of pages can vary. The
  * max we have is seen is 395979, but that does not mean it can't be more.
- * But some machines can have 3GB I/O holes even. So lets reserve enough
- * for 4GB of I/O and E820 holes. */
-RESERVE_BRK(p2m_populated, PMD_SIZE * 4);
+ * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
+ * it can re-use Xen provided mfn_list array, so we only need to allocate at
+ * most three P2M top nodes. */
+RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -575,12 +577,99 @@
 	}
 	return true;
 }
+
+/*
+ * Skim over the P2M tree looking at pages that are either filled with
+ * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and
+ * replace the P2M leaf with a p2m_missing or p2m_identity.
+ * Stick the old page in the new P2M tree location.
+ */
+bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn)
+{
+	unsigned topidx;
+	unsigned mididx;
+	unsigned ident_pfns;
+	unsigned inv_pfns;
+	unsigned long *p2m;
+	unsigned long *mid_mfn_p;
+	unsigned idx;
+	unsigned long pfn;
+
+	/* We only look when this entails a P2M middle layer */
+	if (p2m_index(set_pfn))
+		return false;
+
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+		topidx = p2m_top_index(pfn);
+
+		if (!p2m_top[topidx])
+			continue;
+
+		if (p2m_top[topidx] == p2m_mid_missing)
+			continue;
+
+		mididx = p2m_mid_index(pfn);
+		p2m = p2m_top[topidx][mididx];
+		if (!p2m)
+			continue;
+
+		if ((p2m == p2m_missing) || (p2m == p2m_identity))
+			continue;
+
+		if ((unsigned long)p2m == INVALID_P2M_ENTRY)
+			continue;
+
+		ident_pfns = 0;
+		inv_pfns = 0;
+		for (idx = 0; idx < P2M_PER_PAGE; idx++) {
+			/* IDENTITY_PFNs are 1:1 */
+			if (p2m[idx] == IDENTITY_FRAME(pfn + idx))
+				ident_pfns++;
+			else if (p2m[idx] == INVALID_P2M_ENTRY)
+				inv_pfns++;
+			else
+				break;
+		}
+		if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE))
+			goto found;
+	}
+	return false;
+found:
+	/* Found one, replace old with p2m_identity or p2m_missing */
+	p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing);
+	/* And the other for save/restore.. */
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	/* NOTE: Even if it is a p2m_identity it should still be point to
+	 * a page filled with INVALID_P2M_ENTRY entries. */
+	mid_mfn_p[mididx] = virt_to_mfn(p2m_missing);
+
+	/* Reset where we want to stick the old page in. */
+	topidx = p2m_top_index(set_pfn);
+	mididx = p2m_mid_index(set_pfn);
+
+	/* This shouldn't happen */
+	if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
+		early_alloc_p2m(set_pfn);
+
+	if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
+		return false;
+
+	p2m_init(p2m);
+	p2m_top[topidx][mididx] = p2m;
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+	return true;
+}
 bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
 		if (!early_alloc_p2m(pfn))
 			return false;
 
+		if (early_can_reuse_p2m_middle(pfn, mfn))
+			return __set_phys_to_machine(pfn, mfn);
+
 		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
 			return false;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index ead8557..d11ca11 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -78,9 +78,16 @@
 	memblock_reserve(start, size);
 
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
+	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
+		unsigned long mfn = pfn_to_mfn(pfn);
 
-	for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
+		if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+			continue;
+		WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
+			pfn, mfn);
+
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
 }
 
 static unsigned long __init xen_do_chunk(unsigned long start,
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index ae8a00c..45329c8 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -30,7 +30,7 @@
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
-	xen_hvm_resume_shared_info();
+	xen_hvm_init_shared_info();
 	xen_callback_vector();
 	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 1e4329e..202d4c1 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -41,7 +41,7 @@
 void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
-void xen_hvm_resume_shared_info(void);
+void xen_hvm_init_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2b461b4..19cc761 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -44,6 +44,7 @@
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
 	unsigned int max_discard_sectors;
+	unsigned int granularity, alignment, mask;
 	struct bio_batch bb;
 	struct bio *bio;
 	int ret = 0;
@@ -54,18 +55,20 @@
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
+	/* Zero-sector (unknown) and one-sector granularities are the same.  */
+	granularity = max(q->limits.discard_granularity >> 9, 1U);
+	mask = granularity - 1;
+	alignment = (bdev_discard_alignment(bdev) >> 9) & mask;
+
 	/*
 	 * Ensure that max_discard_sectors is of the proper
-	 * granularity
+	 * granularity, so that requests stay aligned after a split.
 	 */
 	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors = round_down(max_discard_sectors, granularity);
 	if (unlikely(!max_discard_sectors)) {
 		/* Avoid infinite loop below. Being cautious never hurts. */
 		return -EOPNOTSUPP;
-	} else if (q->limits.discard_granularity) {
-		unsigned int disc_sects = q->limits.discard_granularity >> 9;
-
-		max_discard_sectors &= ~(disc_sects - 1);
 	}
 
 	if (flags & BLKDEV_DISCARD_SECURE) {
@@ -79,25 +82,37 @@
 	bb.wait = &wait;
 
 	while (nr_sects) {
+		unsigned int req_sects;
+		sector_t end_sect;
+
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio) {
 			ret = -ENOMEM;
 			break;
 		}
 
+		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
+
+		/*
+		 * If splitting a request, and the next starting sector would be
+		 * misaligned, stop the discard at the previous aligned sector.
+		 */
+		end_sect = sector + req_sects;
+		if (req_sects < nr_sects && (end_sect & mask) != alignment) {
+			end_sect =
+				round_down(end_sect - alignment, granularity)
+				+ alignment;
+			req_sects = end_sect - sector;
+		}
+
 		bio->bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
 		bio->bi_private = &bb;
 
-		if (nr_sects > max_discard_sectors) {
-			bio->bi_size = max_discard_sectors << 9;
-			nr_sects -= max_discard_sectors;
-			sector += max_discard_sectors;
-		} else {
-			bio->bi_size = nr_sects << 9;
-			nr_sects = 0;
-		}
+		bio->bi_size = req_sects << 9;
+		nr_sects -= req_sects;
+		sector = end_sect;
 
 		atomic_inc(&bb.done);
 		submit_bio(type, bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 160035f..e76279e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -110,6 +110,49 @@
 	return 0;
 }
 
+static void
+__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
+		     struct scatterlist *sglist, struct bio_vec **bvprv,
+		     struct scatterlist **sg, int *nsegs, int *cluster)
+{
+
+	int nbytes = bvec->bv_len;
+
+	if (*bvprv && *cluster) {
+		if ((*sg)->length + nbytes > queue_max_segment_size(q))
+			goto new_segment;
+
+		if (!BIOVEC_PHYS_MERGEABLE(*bvprv, bvec))
+			goto new_segment;
+		if (!BIOVEC_SEG_BOUNDARY(q, *bvprv, bvec))
+			goto new_segment;
+
+		(*sg)->length += nbytes;
+	} else {
+new_segment:
+		if (!*sg)
+			*sg = sglist;
+		else {
+			/*
+			 * If the driver previously mapped a shorter
+			 * list, we could see a termination bit
+			 * prematurely unless it fully inits the sg
+			 * table on each mapping. We KNOW that there
+			 * must be more entries here or the driver
+			 * would be buggy, so force clear the
+			 * termination bit to avoid doing a full
+			 * sg_init_table() in drivers for each command.
+			 */
+			(*sg)->page_link &= ~0x02;
+			*sg = sg_next(*sg);
+		}
+
+		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
+		(*nsegs)++;
+	}
+	*bvprv = bvec;
+}
+
 /*
  * map a request to scatterlist, return number of sg entries setup. Caller
  * must make sure sg can hold rq->nr_phys_segments entries
@@ -131,41 +174,8 @@
 	bvprv = NULL;
 	sg = NULL;
 	rq_for_each_segment(bvec, rq, iter) {
-		int nbytes = bvec->bv_len;
-
-		if (bvprv && cluster) {
-			if (sg->length + nbytes > queue_max_segment_size(q))
-				goto new_segment;
-
-			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
-				goto new_segment;
-			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
-				goto new_segment;
-
-			sg->length += nbytes;
-		} else {
-new_segment:
-			if (!sg)
-				sg = sglist;
-			else {
-				/*
-				 * If the driver previously mapped a shorter
-				 * list, we could see a termination bit
-				 * prematurely unless it fully inits the sg
-				 * table on each mapping. We KNOW that there
-				 * must be more entries here or the driver
-				 * would be buggy, so force clear the
-				 * termination bit to avoid doing a full
-				 * sg_init_table() in drivers for each command.
-				 */
-				sg->page_link &= ~0x02;
-				sg = sg_next(sg);
-			}
-
-			sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
-			nsegs++;
-		}
-		bvprv = bvec;
+		__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+				     &nsegs, &cluster);
 	} /* segments in rq */
 
 
@@ -199,6 +209,43 @@
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
+/**
+ * blk_bio_map_sg - map a bio to a scatterlist
+ * @q: request_queue in question
+ * @bio: bio being mapped
+ * @sglist: scatterlist being mapped
+ *
+ * Note:
+ *    Caller must make sure sg can hold bio->bi_phys_segments entries
+ *
+ * Will return the number of sg entries setup
+ */
+int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
+		   struct scatterlist *sglist)
+{
+	struct bio_vec *bvec, *bvprv;
+	struct scatterlist *sg;
+	int nsegs, cluster;
+	unsigned long i;
+
+	nsegs = 0;
+	cluster = blk_queue_cluster(q);
+
+	bvprv = NULL;
+	sg = NULL;
+	bio_for_each_segment(bvec, bio, i) {
+		__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+				     &nsegs, &cluster);
+	} /* segments in bio */
+
+	if (sg)
+		sg_mark_end(sg);
+
+	BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments);
+	return nsegs;
+}
+EXPORT_SYMBOL(blk_bio_map_sg);
+
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
diff --git a/block/genhd.c b/block/genhd.c
index cac7366..d839723 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -835,7 +835,7 @@
 
 static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
 {
-	static void *p;
+	void *p;
 
 	p = disk_seqf_start(seqf, pos);
 	if (!IS_ERR_OR_NULL(p) && !*pos)
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 5ef7ba6..d0583a4 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -336,7 +336,7 @@
 		cryptlen += ivsize;
 	}
 
-	if (sg_is_last(assoc)) {
+	if (req->assoclen && sg_is_last(assoc)) {
 		authenc_ahash_fn = crypto_authenc_ahash;
 		sg_init_table(asg, 2);
 		sg_set_page(asg, sg_page(assoc), assoc->length, assoc->offset);
@@ -490,7 +490,7 @@
 		cryptlen += ivsize;
 	}
 
-	if (sg_is_last(assoc)) {
+	if (req->assoclen && sg_is_last(assoc)) {
 		authenc_ahash_fn = crypto_authenc_ahash;
 		sg_init_table(asg, 2);
 		sg_set_page(asg, sg_page(assoc), assoc->length, assoc->offset);
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index ea4c6d5..29e51bc 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -387,6 +387,7 @@
 
 	return (AE_NOT_FOUND);
 }
+ACPI_EXPORT_SYMBOL(acpi_get_table_with_size)
 
 acpi_status
 acpi_get_table(char *signature,
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 9628652..e059695 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -237,6 +237,16 @@
 	} else if (result == ACPI_STATE_D3_HOT) {
 		result = ACPI_STATE_D3;
 	}
+
+	/*
+	 * If we were unsure about the device parent's power state up to this
+	 * point, the fact that the device is in D0 implies that the parent has
+	 * to be in D0 too.
+	 */
+	if (device->parent && device->parent->power.state == ACPI_STATE_UNKNOWN
+	    && result == ACPI_STATE_D0)
+		device->parent->power.state = ACPI_STATE_D0;
+
 	*state = result;
 
  out:
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index fc18034..40e38a0 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -107,6 +107,7 @@
 
 	/* List of devices relying on this power resource */
 	struct acpi_power_resource_device *devices;
+	struct mutex devices_lock;
 };
 
 static struct list_head acpi_power_resource_list;
@@ -225,7 +226,6 @@
 
 static int __acpi_power_on(struct acpi_power_resource *resource)
 {
-	struct acpi_power_resource_device *device_list = resource->devices;
 	acpi_status status = AE_OK;
 
 	status = acpi_evaluate_object(resource->device->handle, "_ON", NULL, NULL);
@@ -238,19 +238,15 @@
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n",
 			  resource->name));
 
-	while (device_list) {
-		acpi_power_on_device(device_list->device);
-
-		device_list = device_list->next;
-	}
-
 	return 0;
 }
 
 static int acpi_power_on(acpi_handle handle)
 {
 	int result = 0;
+	bool resume_device = false;
 	struct acpi_power_resource *resource = NULL;
+	struct acpi_power_resource_device *device_list;
 
 	result = acpi_power_get_context(handle, &resource);
 	if (result)
@@ -266,10 +262,25 @@
 		result = __acpi_power_on(resource);
 		if (result)
 			resource->ref_count--;
+		else
+			resume_device = true;
 	}
 
 	mutex_unlock(&resource->resource_lock);
 
+	if (!resume_device)
+		return result;
+
+	mutex_lock(&resource->devices_lock);
+
+	device_list = resource->devices;
+	while (device_list) {
+		acpi_power_on_device(device_list->device);
+		device_list = device_list->next;
+	}
+
+	mutex_unlock(&resource->devices_lock);
+
 	return result;
 }
 
@@ -355,7 +366,7 @@
 	if (acpi_power_get_context(res_handle, &resource))
 		return;
 
-	mutex_lock(&resource->resource_lock);
+	mutex_lock(&resource->devices_lock);
 	prev = NULL;
 	curr = resource->devices;
 	while (curr) {
@@ -372,7 +383,7 @@
 		prev = curr;
 		curr = curr->next;
 	}
-	mutex_unlock(&resource->resource_lock);
+	mutex_unlock(&resource->devices_lock);
 }
 
 /* Unlink dev from all power resources in _PR0 */
@@ -414,10 +425,10 @@
 
 	power_resource_device->device = powered_device;
 
-	mutex_lock(&resource->resource_lock);
+	mutex_lock(&resource->devices_lock);
 	power_resource_device->next = resource->devices;
 	resource->devices = power_resource_device;
-	mutex_unlock(&resource->resource_lock);
+	mutex_unlock(&resource->devices_lock);
 
 	return 0;
 }
@@ -462,7 +473,7 @@
 	return ret;
 
 no_power_resource:
-	printk(KERN_WARNING PREFIX "Invalid Power Resource to register!");
+	printk(KERN_DEBUG PREFIX "Invalid Power Resource to register!");
 	return -ENODEV;
 }
 EXPORT_SYMBOL_GPL(acpi_power_resource_register_device);
@@ -721,6 +732,7 @@
 
 	resource->device = device;
 	mutex_init(&resource->resource_lock);
+	mutex_init(&resource->devices_lock);
 	strcpy(resource->name, device->pnp.bus_id);
 	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_POWER_CLASS);
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 2be8ef1..27cecd3 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -115,7 +115,7 @@
 	  If unsure, say N.
 
 config ATA_SFF
-	bool "ATA SFF support"
+	bool "ATA SFF support (for legacy IDE and PATA)"
 	default y
 	help
 	  This option adds support for ATA controllers with SFF
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 062e6a1..7862d17 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -256,10 +256,21 @@
 	{ PCI_VDEVICE(INTEL, 0x8c07), board_ahci }, /* Lynx Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c0e), board_ahci }, /* Lynx Point RAID */
 	{ PCI_VDEVICE(INTEL, 0x8c0f), board_ahci }, /* Lynx Point RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c02), board_ahci }, /* Lynx Point-LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c03), board_ahci }, /* Lynx Point-LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9c04), board_ahci }, /* Lynx Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c05), board_ahci }, /* Lynx Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c06), board_ahci }, /* Lynx Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c07), board_ahci }, /* Lynx Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c0e), board_ahci }, /* Lynx Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9c0f), board_ahci }, /* Lynx Point-LP RAID */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
 	  PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff, board_ahci_ign_iferr },
+	/* JMicron 362B and 362C have an AHCI function with IDE class code */
+	{ PCI_VDEVICE(JMICRON, 0x2362), board_ahci_ign_iferr },
+	{ PCI_VDEVICE(JMICRON, 0x236f), board_ahci_ign_iferr },
 
 	/* ATI */
 	{ PCI_VDEVICE(ATI, 0x4380), board_ahci_sb600 }, /* ATI SB600 */
@@ -385,6 +396,8 @@
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9125 */
 	{ PCI_DEVICE(0x1b4b, 0x917a),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
+	{ PCI_DEVICE(0x1b4b, 0x9192),
+	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 on some Gigabyte */
 	{ PCI_DEVICE(0x1b4b, 0x91a3),
 	  .driver_data = board_ahci_yes_fbs },
 
@@ -392,7 +405,10 @@
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
 
 	/* Asmedia */
-	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1061 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci },	/* ASM1061 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1062 */
 
 	/* Generic, PCI class code for AHCI */
 	{ PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index c2594dd..57eb1c2 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -320,6 +320,7 @@
 extern struct ata_port_operations ahci_ops;
 extern struct ata_port_operations ahci_pmp_retry_srst_ops;
 
+unsigned int ahci_dev_classify(struct ata_port *ap);
 void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
 			u32 opts);
 void ahci_save_initial_config(struct device *dev,
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 3c809bf..ef773e1 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -329,6 +329,14 @@
 	{ 0x8086, 0x8c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	/* SATA Controller IDE (Lynx Point) */
 	{ 0x8086, 0x8c09, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+	/* SATA Controller IDE (Lynx Point-LP) */
+	{ 0x8086, 0x9c00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
+	/* SATA Controller IDE (Lynx Point-LP) */
+	{ 0x8086, 0x9c01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
+	/* SATA Controller IDE (Lynx Point-LP) */
+	{ 0x8086, 0x9c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+	/* SATA Controller IDE (Lynx Point-LP) */
+	{ 0x8086, 0x9c09, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	/* SATA Controller IDE (DH89xxCC) */
 	{ 0x8086, 0x2326, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
 	{ }	/* terminate list */
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index f9eaa82..555c07a 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1139,7 +1139,7 @@
 	}
 }
 
-static unsigned int ahci_dev_classify(struct ata_port *ap)
+unsigned int ahci_dev_classify(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
 	struct ata_taskfile tf;
@@ -1153,6 +1153,7 @@
 
 	return ata_dev_classify(&tf);
 }
+EXPORT_SYMBOL_GPL(ahci_dev_classify);
 
 void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
 			u32 opts)
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 902b5a4..fd9ecf7 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -60,17 +60,7 @@
 	if (ap->flags & ATA_FLAG_ACPI_SATA)
 		return NULL;
 
-	/*
-	 * If acpi bind operation has already happened, we can get the handle
-	 * for the port by checking the corresponding scsi_host device's
-	 * firmware node, otherwise we will need to find out the handle from
-	 * its parent's acpi node.
-	 */
-	if (ap->scsi_host)
-		return DEVICE_ACPI_HANDLE(&ap->scsi_host->shost_gendev);
-	else
-		return acpi_get_child(DEVICE_ACPI_HANDLE(ap->host->dev),
-				ap->port_no);
+	return acpi_get_child(DEVICE_ACPI_HANDLE(ap->host->dev), ap->port_no);
 }
 EXPORT_SYMBOL(ata_ap_acpi_handle);
 
@@ -1101,6 +1091,9 @@
 	if (!*handle)
 		return -ENODEV;
 
+	if (ata_acpi_gtm(ap, &ap->__acpi_init_gtm) == 0)
+		ap->pflags |= ATA_PFLAG_INIT_GTM_VALID;
+
 	return 0;
 }
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index fadd586..8e1039c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4062,7 +4062,7 @@
 	{ "_NEC DV5800A", 	NULL,		ATA_HORKAGE_NODMA },
 	{ "SAMSUNG CD-ROM SN-124", "N001",	ATA_HORKAGE_NODMA },
 	{ "Seagate STT20000A", NULL,		ATA_HORKAGE_NODMA },
-	{ "2GB ATA Flash Disk", "ADMA428M",	ATA_HORKAGE_NODMA },
+	{ " 2GB ATA Flash Disk", "ADMA428M",	ATA_HORKAGE_NODMA },
 	/* Odd clown on sil3726/4726 PMPs */
 	{ "Config  Disk",	NULL,		ATA_HORKAGE_DISABLE },
 
@@ -4128,6 +4128,7 @@
 
 	/* Devices that do not need bridging limits applied */
 	{ "MTRON MSP-SATA*",		NULL,	ATA_HORKAGE_BRIDGE_OK, },
+	{ "BUFFALO HD-QSU2/R5",		NULL,	ATA_HORKAGE_BRIDGE_OK, },
 
 	/* Devices which aren't very happy with higher link speeds */
 	{ "WD My Book",			NULL,	ATA_HORKAGE_1_5_GBPS, },
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 361c75c..24e5105 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <scsi/scsi_host.h>
 #include <linux/libata.h>
+#include <linux/dmi.h>
 
 #define DRV_NAME "pata_atiixp"
 #define DRV_VERSION "0.4.6"
@@ -33,11 +34,26 @@
 	ATIIXP_IDE_UDMA_MODE 	= 0x56
 };
 
+static const struct dmi_system_id attixp_cable_override_dmi_table[] = {
+	{
+		/* Board has onboard PATA<->SATA converters */
+		.ident = "MSI E350DM-E33",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "MSI"),
+			DMI_MATCH(DMI_BOARD_NAME, "E350DM-E33(MS-7720)"),
+		},
+	},
+	{ }
+};
+
 static int atiixp_cable_detect(struct ata_port *ap)
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	u8 udma;
 
+	if (dmi_check_system(attixp_cable_override_dmi_table))
+		return ATA_CBL_PATA40_SHORT;
+
 	/* Hack from drivers/ide/pci. Really we want to know how to do the
 	   raw detection not play follow the bios mode guess */
 	pci_read_config_byte(pdev, ATIIXP_IDE_UDMA_MODE + ap->port_no, &udma);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index f338037..5e6e00b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1865,6 +1865,7 @@
 		 struct va_format *vaf)
 {
 	char dict[128];
+	const char *level_extra = "";
 	size_t dictlen = 0;
 	const char *subsys;
 
@@ -1911,10 +1912,14 @@
 				    "DEVICE=+%s:%s", subsys, dev_name(dev));
 	}
 skip:
+	if (level[2])
+		level_extra = &level[2]; /* skip past KERN_SOH "L" */
+
 	return printk_emit(0, level[1] - '0',
 			   dictlen ? dict : NULL, dictlen,
-			   "%s %s: %pV",
-			   dev_driver_string(dev), dev_name(dev), vaf);
+			   "%s %s: %s%pV",
+			   dev_driver_string(dev), dev_name(dev),
+			   level_extra, vaf);
 }
 EXPORT_SYMBOL(__dev_printk);
 
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 78efb03..34d94c7 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -250,7 +250,7 @@
 		return -EINVAL;
 
 	/* Sanitise input arguments */
-	alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order);
+	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
 	base = ALIGN(base, alignment);
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 5989487..7d9c1cb 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -147,6 +147,8 @@
 	    || (dev->power.request_pending
 			&& dev->power.request == RPM_REQ_RESUME))
 		retval = -EAGAIN;
+	else if (__dev_pm_qos_read_value(dev) < 0)
+		retval = -EPERM;
 	else if (dev->power.runtime_status == RPM_SUSPENDED)
 		retval = 1;
 
@@ -388,7 +390,6 @@
 		goto repeat;
 	}
 
-	dev->power.deferred_resume = false;
 	if (dev->power.no_callbacks)
 		goto no_callback;	/* Assume success. */
 
@@ -403,12 +404,6 @@
 		goto out;
 	}
 
-	if (__dev_pm_qos_read_value(dev) < 0) {
-		/* Negative PM QoS constraint means "never suspend". */
-		retval = -EPERM;
-		goto out;
-	}
-
 	__update_runtime_status(dev, RPM_SUSPENDING);
 
 	if (dev->pm_domain)
@@ -440,6 +435,7 @@
 	wake_up_all(&dev->power.wait_queue);
 
 	if (dev->power.deferred_resume) {
+		dev->power.deferred_resume = false;
 		rpm_resume(dev, 0);
 		retval = -EAGAIN;
 		goto out;
@@ -584,6 +580,7 @@
 		    || dev->parent->power.runtime_status == RPM_ACTIVE) {
 			atomic_inc(&dev->parent->power.child_count);
 			spin_unlock(&dev->parent->power.lock);
+			retval = 1;
 			goto no_callback;	/* Assume success. */
 		}
 		spin_unlock(&dev->parent->power.lock);
@@ -664,7 +661,7 @@
 	}
 	wake_up_all(&dev->power.wait_queue);
 
-	if (!retval)
+	if (retval >= 0)
 		rpm_idle(dev, RPM_ASYNC);
 
  out:
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index acda773..38aa6dd 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -763,16 +763,7 @@
 		{
 			case CMD_TARGET_STATUS:
 				/* Pass it up to the upper layers... */
-				if( ei->ScsiStatus)
-                		{
-#if 0
-                    			printk(KERN_WARNING "cciss: cmd %p "
-						"has SCSI Status = %x\n",
-						c, ei->ScsiStatus);
-#endif
-					cmd->result |= (ei->ScsiStatus << 1);
-                		}
-				else {  /* scsi status is zero??? How??? */
+				if (!ei->ScsiStatus) {
 					
 	/* Ordinarily, this case should never happen, but there is a bug
 	   in some released firmware revisions that allows it to happen
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index ba91b40..d845664 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -889,6 +889,7 @@
 	unsigned int done;
 	unsigned flags;
 #define BM_AIO_COPY_PAGES	1
+#define BM_WRITE_ALL_PAGES	2
 	int error;
 	struct kref kref;
 };
@@ -1059,7 +1060,8 @@
 		if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx)
 			break;
 		if (rw & WRITE) {
-			if (bm_test_page_unchanged(b->bm_pages[i])) {
+			if (!(flags & BM_WRITE_ALL_PAGES) &&
+			    bm_test_page_unchanged(b->bm_pages[i])) {
 				dynamic_dev_dbg(DEV, "skipped bm write for idx %u\n", i);
 				continue;
 			}
@@ -1141,6 +1143,17 @@
 }
 
 /**
+ * drbd_bm_write_all() - Write the whole bitmap to its on disk location.
+ * @mdev:	DRBD device.
+ *
+ * Will write all pages.
+ */
+int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local)
+{
+	return bm_rw(mdev, WRITE, BM_WRITE_ALL_PAGES, 0);
+}
+
+/**
  * drbd_bm_lazy_write_out() - Write bitmap pages 0 to @upper_idx-1, if they have changed.
  * @mdev:	DRBD device.
  * @upper_idx:	0: write all changed pages; +ve: page index to stop scanning for changed pages
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index b2ca143..b953cc7 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1469,6 +1469,7 @@
 extern int  drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(local);
 extern int  drbd_bm_read(struct drbd_conf *mdev) __must_hold(local);
 extern int  drbd_bm_write(struct drbd_conf *mdev) __must_hold(local);
+extern int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local);
 extern int  drbd_bm_write_copy_pages(struct drbd_conf *mdev) __must_hold(local);
 extern unsigned long drbd_bm_ALe_set_all(struct drbd_conf *mdev,
 		unsigned long al_enr);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index dbe6135..f93a032 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -79,6 +79,7 @@
 static void md_sync_timer_fn(unsigned long data);
 static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused);
 static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused);
+static void _tl_clear(struct drbd_conf *mdev);
 
 MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
 	      "Lars Ellenberg <lars@linbit.com>");
@@ -432,19 +433,10 @@
 
 	/* Actions operating on the disk state, also want to work on
 	   requests that got barrier acked. */
-	switch (what) {
-	case fail_frozen_disk_io:
-	case restart_frozen_disk_io:
-		list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
-			req = list_entry(le, struct drbd_request, tl_requests);
-			_req_mod(req, what);
-		}
 
-	case connection_lost_while_pending:
-	case resend:
-		break;
-	default:
-		dev_err(DEV, "what = %d in _tl_restart()\n", what);
+	list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
+		req = list_entry(le, struct drbd_request, tl_requests);
+		_req_mod(req, what);
 	}
 }
 
@@ -459,11 +451,16 @@
  */
 void tl_clear(struct drbd_conf *mdev)
 {
+	spin_lock_irq(&mdev->req_lock);
+	_tl_clear(mdev);
+	spin_unlock_irq(&mdev->req_lock);
+}
+
+static void _tl_clear(struct drbd_conf *mdev)
+{
 	struct list_head *le, *tle;
 	struct drbd_request *r;
 
-	spin_lock_irq(&mdev->req_lock);
-
 	_tl_restart(mdev, connection_lost_while_pending);
 
 	/* we expect this list to be empty. */
@@ -482,7 +479,6 @@
 
 	memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *));
 
-	spin_unlock_irq(&mdev->req_lock);
 }
 
 void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
@@ -1476,12 +1472,12 @@
 	if (ns.susp_fen) {
 		/* case1: The outdate peer handler is successful: */
 		if (os.pdsk > D_OUTDATED  && ns.pdsk <= D_OUTDATED) {
-			tl_clear(mdev);
 			if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
 				drbd_uuid_new_current(mdev);
 				clear_bit(NEW_CUR_UUID, &mdev->flags);
 			}
 			spin_lock_irq(&mdev->req_lock);
+			_tl_clear(mdev);
 			_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
 			spin_unlock_irq(&mdev->req_lock);
 		}
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index fb9dce8..edb490a 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -674,8 +674,8 @@
 			 la_size_changed && md_moved ? "size changed and md moved" :
 			 la_size_changed ? "size changed" : "md moved");
 		/* next line implicitly does drbd_suspend_io()+drbd_resume_io() */
-		err = drbd_bitmap_io(mdev, &drbd_bm_write,
-				"size changed", BM_LOCKED_MASK);
+		err = drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write,
+				     "size changed", BM_LOCKED_MASK);
 		if (err) {
 			rv = dev_size_error;
 			goto out;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 910335c..01b2ac6 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -695,6 +695,12 @@
 		break;
 
 	case resend:
+		/* Simply complete (local only) READs. */
+		if (!(req->rq_state & RQ_WRITE) && !req->w.cb) {
+			_req_may_be_done(req, m);
+			break;
+		}
+
 		/* If RQ_NET_OK is already set, we got a P_WRITE_ACK or P_RECV_ACK
 		   before the connection loss (B&C only); only P_BARRIER_ACK was missing.
 		   Trowing them out of the TL here by pretending we got a BARRIER_ACK
@@ -834,7 +840,15 @@
 		req->private_bio = NULL;
 	}
 	if (rw == WRITE) {
-		remote = 1;
+		/* Need to replicate writes.  Unless it is an empty flush,
+		 * which is better mapped to a DRBD P_BARRIER packet,
+		 * also for drbd wire protocol compatibility reasons. */
+		if (unlikely(size == 0)) {
+			/* The only size==0 bios we expect are empty flushes. */
+			D_ASSERT(bio->bi_rw & REQ_FLUSH);
+			remote = 0;
+		} else
+			remote = 1;
 	} else {
 		/* READ || READA */
 		if (local) {
@@ -870,8 +884,11 @@
 	 * extent.  This waits for any resync activity in the corresponding
 	 * resync extent to finish, and, if necessary, pulls in the target
 	 * extent into the activity log, which involves further disk io because
-	 * of transactional on-disk meta data updates. */
-	if (rw == WRITE && local && !test_bit(AL_SUSPENDED, &mdev->flags)) {
+	 * of transactional on-disk meta data updates.
+	 * Empty flushes don't need to go into the activity log, they can only
+	 * flush data for pending writes which are already in there. */
+	if (rw == WRITE && local && size
+	&& !test_bit(AL_SUSPENDED, &mdev->flags)) {
 		req->rq_state |= RQ_IN_ACT_LOG;
 		drbd_al_begin_io(mdev, sector);
 	}
@@ -994,7 +1011,10 @@
 	if (rw == WRITE && _req_conflicts(req))
 		goto fail_conflicting;
 
-	list_add_tail(&req->tl_requests, &mdev->newest_tle->requests);
+	/* no point in adding empty flushes to the transfer log,
+	 * they are mapped to drbd barriers already. */
+	if (likely(size!=0))
+		list_add_tail(&req->tl_requests, &mdev->newest_tle->requests);
 
 	/* NOTE remote first: to get the concurrent write detection right,
 	 * we must register the request before start of local IO.  */
@@ -1014,6 +1034,14 @@
 	    mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96)
 		maybe_pull_ahead(mdev);
 
+	/* If this was a flush, queue a drbd barrier/start a new epoch.
+	 * Unless the current epoch was empty anyways, or we are not currently
+	 * replicating, in which case there is no point. */
+	if (unlikely(bio->bi_rw & REQ_FLUSH)
+		&& mdev->newest_tle->n_writes
+		&& drbd_should_do_remote(mdev->state))
+		queue_barrier(mdev);
+
 	spin_unlock_irq(&mdev->req_lock);
 	kfree(b); /* if someone else has beaten us to it... */
 
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 10308cd..fc2de55 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -79,12 +79,14 @@
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x0CF3, 0xE004) },
 	{ USB_DEVICE(0x0930, 0x0219) },
+	{ USB_DEVICE(0x0489, 0xe057) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE02C) },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE03C) },
+	{ USB_DEVICE(0x0489, 0xE036) },
 
 	{ }	/* Terminating entry */
 };
@@ -104,9 +106,11 @@
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xE036), .driver_info = BTUSB_ATH3012 },
 
 	{ }	/* Terminating entry */
 };
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index e272214..654e248 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -52,6 +52,9 @@
 	/* Generic Bluetooth USB device */
 	{ USB_DEVICE_INFO(0xe0, 0x01, 0x01) },
 
+	/* Apple-specific (Broadcom) devices */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x05ac, 0xff, 0x01, 0x01) },
+
 	/* Broadcom SoftSailing reporting vendor specific */
 	{ USB_DEVICE(0x0a5c, 0x21e1) },
 
@@ -94,15 +97,14 @@
 
 	/* Broadcom BCM20702A0 */
 	{ USB_DEVICE(0x0489, 0xe042) },
-	{ USB_DEVICE(0x0a5c, 0x21e3) },
-	{ USB_DEVICE(0x0a5c, 0x21e6) },
-	{ USB_DEVICE(0x0a5c, 0x21e8) },
-	{ USB_DEVICE(0x0a5c, 0x21f3) },
 	{ USB_DEVICE(0x413c, 0x8197) },
 
 	/* Foxconn - Hon Hai */
 	{ USB_DEVICE(0x0489, 0xe033) },
 
+	/*Broadcom devices with vendor specific id */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) },
+
 	{ }	/* Terminating entry */
 };
 
@@ -133,12 +135,14 @@
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe036), .driver_info = BTUSB_ATH3012 },
 
 	/* Broadcom BCM2035 */
 	{ USB_DEVICE(0x0a5c, 0x2035), .driver_info = BTUSB_WRONG_SCO_MTU },
diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index 6f007b6..6ec0fff 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -64,6 +64,7 @@
 #define I830_PTE_SYSTEM_CACHED  0x00000006
 /* GT PTE cache control fields */
 #define GEN6_PTE_UNCACHED	0x00000002
+#define HSW_PTE_UNCACHED	0x00000000
 #define GEN6_PTE_LLC		0x00000004
 #define GEN6_PTE_LLC_MLC	0x00000006
 #define GEN6_PTE_GFDT		0x00000008
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 08fc5cb..58e32f7 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -1156,6 +1156,30 @@
 	return true;
 }
 
+static void haswell_write_entry(dma_addr_t addr, unsigned int entry,
+				unsigned int flags)
+{
+	unsigned int type_mask = flags & ~AGP_USER_CACHED_MEMORY_GFDT;
+	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
+	u32 pte_flags;
+
+	if (type_mask == AGP_USER_MEMORY)
+		pte_flags = HSW_PTE_UNCACHED | I810_PTE_VALID;
+	else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) {
+		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
+		if (gfdt)
+			pte_flags |= GEN6_PTE_GFDT;
+	} else { /* set 'normal'/'cached' to LLC by default */
+		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
+		if (gfdt)
+			pte_flags |= GEN6_PTE_GFDT;
+	}
+
+	/* gen6 has bit11-4 for physical addr bit39-32 */
+	addr |= (addr >> 28) & 0xff0;
+	writel(addr | pte_flags, intel_private.gtt + entry);
+}
+
 static void gen6_write_entry(dma_addr_t addr, unsigned int entry,
 			     unsigned int flags)
 {
@@ -1382,6 +1406,15 @@
 	.check_flags = gen6_check_flags,
 	.chipset_flush = i9xx_chipset_flush,
 };
+static const struct intel_gtt_driver haswell_gtt_driver = {
+	.gen = 6,
+	.setup = i9xx_setup,
+	.cleanup = gen6_cleanup,
+	.write_entry = haswell_write_entry,
+	.dma_mask_size = 40,
+	.check_flags = gen6_check_flags,
+	.chipset_flush = i9xx_chipset_flush,
+};
 static const struct intel_gtt_driver valleyview_gtt_driver = {
 	.gen = 7,
 	.setup = i9xx_setup,
@@ -1499,77 +1532,77 @@
 	{ PCI_DEVICE_ID_INTEL_VALLEYVIEW_IG,
 	    "ValleyView", &valleyview_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_PLUS_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ 0, NULL, NULL }
 };
 
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index 540795c..d927938 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -53,7 +53,7 @@
 #define MFGPT_PERIODIC (MFGPT_HZ / HZ)
 
 /*
- * The MFPGT timers on the CS5536 provide us with suitable timers to use
+ * The MFGPT timers on the CS5536 provide us with suitable timers to use
  * as clock event sources - not as good as a HPET or APIC, but certainly
  * better than the PIT.  This isn't a general purpose MFGPT driver, but
  * a simplified one designed specifically to act as a clock event source.
@@ -144,7 +144,7 @@
 
 	timer = cs5535_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING);
 	if (!timer) {
-		printk(KERN_ERR DRV_NAME ": Could not allocate MFPGT timer\n");
+		printk(KERN_ERR DRV_NAME ": Could not allocate MFGPT timer\n");
 		return -ENODEV;
 	}
 	cs5535_event_clock = timer;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 17fa04d..b47034e 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -218,7 +218,7 @@
 
 	policy->cur = policy->min = policy->max = omap_getspeed(policy->cpu);
 
-	if (atomic_inc_return(&freq_table_users) == 1)
+	if (!freq_table)
 		result = opp_init_cpufreq_table(mpu_dev, &freq_table);
 
 	if (result) {
@@ -227,6 +227,8 @@
 		goto fail_ck;
 	}
 
+	atomic_inc_return(&freq_table_users);
+
 	result = cpufreq_frequency_table_cpuinfo(policy, freq_table);
 	if (result)
 		goto fail_table;
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 2c9bf26..3265844 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -678,10 +678,22 @@
 	int cpu = (unsigned long)hcpu;
 	struct cpuidle_device *dev;
 
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+	case CPU_DOWN_PREPARE:
+	case CPU_ONLINE:
+	case CPU_DEAD:
+	case CPU_UP_CANCELED:
+	case CPU_DOWN_FAILED:
+		break;
+	default:
+		return NOTIFY_OK;
+	}
+
 	mutex_lock(&cpuidle_lock);
 
 	dev = per_cpu(cpuidle_devices, cpu);
-	if (!dev->coupled)
+	if (!dev || !dev->coupled)
 		goto out;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 53c8c51..93d1407 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -63,7 +63,7 @@
 
 		head = ACCESS_ONCE(jrp->head);
 
-		spin_lock_bh(&jrp->outlock);
+		spin_lock(&jrp->outlock);
 
 		sw_idx = tail = jrp->tail;
 		hw_idx = jrp->out_ring_read_index;
@@ -115,7 +115,7 @@
 			jrp->tail = tail;
 		}
 
-		spin_unlock_bh(&jrp->outlock);
+		spin_unlock(&jrp->outlock);
 
 		/* Finally, execute user's callback */
 		usercall(dev, userdesc, userstatus, userarg);
@@ -236,14 +236,14 @@
 		return -EIO;
 	}
 
-	spin_lock(&jrp->inplock);
+	spin_lock_bh(&jrp->inplock);
 
 	head = jrp->head;
 	tail = ACCESS_ONCE(jrp->tail);
 
 	if (!rd_reg32(&jrp->rregs->inpring_avail) ||
 	    CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) {
-		spin_unlock(&jrp->inplock);
+		spin_unlock_bh(&jrp->inplock);
 		dma_unmap_single(dev, desc_dma, desc_size, DMA_TO_DEVICE);
 		return -EBUSY;
 	}
@@ -265,7 +265,7 @@
 
 	wr_reg32(&jrp->rregs->inpring_jobadd, 1);
 
-	spin_unlock(&jrp->inplock);
+	spin_unlock_bh(&jrp->inplock);
 
 	return 0;
 }
diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c
index 0028881..d216cd3 100644
--- a/drivers/crypto/caam/key_gen.c
+++ b/drivers/crypto/caam/key_gen.c
@@ -120,3 +120,4 @@
 
 	return ret;
 }
+EXPORT_SYMBOL(gen_split_key);
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index c9c4bef..df14358 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -821,8 +821,8 @@
 	/*
 	 * We must wait at least 256 Pk_clk cycles between two reads of the rng.
 	 */
-	dev->rng_wait_time	= DIV_ROUND_UP(NSEC_PER_SEC, dev->pk_clk_freq) *
-				  256;
+	dev->rng_wait_time	= DIV_ROUND_UP_ULL(NSEC_PER_SEC,
+						   dev->pk_clk_freq) * 256;
 
 	dev->rng.name		= dev->name;
 	dev->rng.data_present	= hifn_rng_data_present,
diff --git a/drivers/extcon/extcon_gpio.c b/drivers/extcon/extcon_gpio.c
index fe3db45..3cc152e 100644
--- a/drivers/extcon/extcon_gpio.c
+++ b/drivers/extcon/extcon_gpio.c
@@ -107,7 +107,8 @@
 	if (ret < 0)
 		return ret;
 
-	ret = gpio_request_one(extcon_data->gpio, GPIOF_DIR_IN, pdev->name);
+	ret = devm_gpio_request_one(&pdev->dev, extcon_data->gpio, GPIOF_DIR_IN,
+				    pdev->name);
 	if (ret < 0)
 		goto err;
 
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index b16c8a7..ba7926f5 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -294,7 +294,7 @@
 
 config GPIO_MC9S08DZ60
 	bool "MX35 3DS BOARD MC9S08DZ60 GPIO functions"
-	depends on I2C && MACH_MX35_3DS
+	depends on I2C=y && MACH_MX35_3DS
 	help
 	  Select this to enable the MC9S08DZ60 GPIO driver
 
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index ae37181..ec48ed5 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -247,9 +247,9 @@
 
 	p->irq_base = irq_alloc_descs(pdata->irq_base, 0,
 				      pdata->number_of_pins, numa_node_id());
-	if (IS_ERR_VALUE(p->irq_base)) {
+	if (p->irq_base < 0) {
 		dev_err(&pdev->dev, "cannot get irq_desc\n");
-		return -ENXIO;
+		return p->irq_base;
 	}
 	pr_debug("gio: hw base = %d, nr = %d, sw base = %d\n",
 		 pdata->gpio_base, pdata->number_of_pins, p->irq_base);
diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c
index e97016a..b62d443 100644
--- a/drivers/gpio/gpio-rdc321x.c
+++ b/drivers/gpio/gpio-rdc321x.c
@@ -170,6 +170,7 @@
 	rdc321x_gpio_dev->reg2_data_base = r->start + 0x4;
 
 	rdc321x_gpio_dev->chip.label = "rdc321x-gpio";
+	rdc321x_gpio_dev->chip.owner = THIS_MODULE;
 	rdc321x_gpio_dev->chip.direction_input = rdc_gpio_direction_input;
 	rdc321x_gpio_dev->chip.direction_output = rdc_gpio_config;
 	rdc321x_gpio_dev->chip.get = rdc_gpio_get_value;
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index a18c4aa..f1a4599 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -82,7 +82,7 @@
 	gpiochip_find(&gg_data, of_gpiochip_find_and_xlate);
 
 	of_node_put(gg_data.gpiospec.np);
-	pr_debug("%s exited with status %d\n", __func__, ret);
+	pr_debug("%s exited with status %d\n", __func__, gg_data.out_gpio);
 	return gg_data.out_gpio;
 }
 EXPORT_SYMBOL(of_get_named_gpio_flags);
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 23120c0..90e2808 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -22,6 +22,7 @@
 config DRM_USB
 	tristate
 	depends on DRM
+	depends on USB_ARCH_HAS_HCD
 	select USB
 
 config DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index d0c4574..3616480 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -193,6 +193,9 @@
 	.mmap = ast_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.read = drm_read,
 };
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 7282c08..a712caf 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -841,7 +841,7 @@
 
 	ast->cursor_cache = obj;
 	ast->cursor_cache_gpu_addr = gpu_addr;
-	DRM_ERROR("pinned cursor cache at %llx\n", ast->cursor_cache_gpu_addr);
+	DRM_DEBUG_KMS("pinned cursor cache at %llx\n", ast->cursor_cache_gpu_addr);
 	return 0;
 fail:
 	return ret;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 7053140..b83a2d7 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -74,6 +74,9 @@
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = cirrus_mmap,
 	.poll = drm_poll,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.fasync = drm_fasync,
 };
 static struct drm_driver driver = {
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 08a7aa7..6fbfc24 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1981,7 +1981,7 @@
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	if (!req->flags)
+	if (!req->flags || (~DRM_MODE_CURSOR_FLAGS & req->flags))
 		return -EINVAL;
 
 	mutex_lock(&dev->mode_config.mutex);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index a8743c3..b7ee230 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -87,6 +87,9 @@
 	int product_id;
 	u32 quirks;
 } edid_quirk_list[] = {
+	/* ASUS VW222S */
+	{ "ACI", 0x22a2, EDID_QUIRK_FORCE_REDUCED_BLANKING },
+
 	/* Acer AL1706 */
 	{ "ACR", 44358, EDID_QUIRK_PREFER_LARGE_60 },
 	/* Acer F51 */
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index b7adb4a..28637c1 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -706,9 +706,6 @@
 	p->crtc_vblank_end = max(p->crtc_vsync_end, p->crtc_vtotal);
 	p->crtc_hblank_start = min(p->crtc_hsync_start, p->crtc_hdisplay);
 	p->crtc_hblank_end = max(p->crtc_hsync_end, p->crtc_htotal);
-
-	p->crtc_hadjusted = false;
-	p->crtc_vadjusted = false;
 }
 EXPORT_SYMBOL(drm_mode_set_crtcinfo);
 
diff --git a/drivers/gpu/drm/drm_proc.c b/drivers/gpu/drm/drm_proc.c
index 371c695..da457b1 100644
--- a/drivers/gpu/drm/drm_proc.c
+++ b/drivers/gpu/drm/drm_proc.c
@@ -89,7 +89,7 @@
  * Create a given set of proc files represented by an array of
  * gdm_proc_lists in the given root directory.
  */
-int drm_proc_create_files(struct drm_info_list *files, int count,
+static int drm_proc_create_files(struct drm_info_list *files, int count,
 			  struct proc_dir_entry *root, struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
@@ -172,7 +172,7 @@
 	return 0;
 }
 
-int drm_proc_remove_files(struct drm_info_list *files, int count,
+static int drm_proc_remove_files(struct drm_info_list *files, int count,
 			  struct drm_minor *minor)
 {
 	struct list_head *pos, *q;
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 7f50967..59a26e5 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -36,6 +36,6 @@
 
 config DRM_EXYNOS_G2D
 	bool "Exynos DRM G2D"
-	depends on DRM_EXYNOS
+	depends on DRM_EXYNOS && !VIDEO_SAMSUNG_S5P_G2D
 	help
 	  Choose this option if you want to use Exynos G2D for DRM.
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
index 613bf8a..ae13feb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
@@ -163,6 +163,12 @@
 	/* TODO */
 }
 
+static int exynos_gem_dmabuf_mmap(struct dma_buf *dma_buf,
+	struct vm_area_struct *vma)
+{
+	return -ENOTTY;
+}
+
 static struct dma_buf_ops exynos_dmabuf_ops = {
 	.map_dma_buf		= exynos_gem_map_dma_buf,
 	.unmap_dma_buf		= exynos_gem_unmap_dma_buf,
@@ -170,6 +176,7 @@
 	.kmap_atomic		= exynos_gem_dmabuf_kmap_atomic,
 	.kunmap			= exynos_gem_dmabuf_kunmap,
 	.kunmap_atomic		= exynos_gem_dmabuf_kunmap_atomic,
+	.mmap			= exynos_gem_dmabuf_mmap,
 	.release		= exynos_dmabuf_release,
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index ebacec6..d070719 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -160,7 +160,6 @@
 	if (!file_priv)
 		return -ENOMEM;
 
-	drm_prime_init_file_private(&file->prime);
 	file->driver_priv = file_priv;
 
 	return exynos_drm_subdrv_open(dev, file);
@@ -184,7 +183,6 @@
 			e->base.destroy(&e->base);
 		}
 	}
-	drm_prime_destroy_file_private(&file->prime);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
 	exynos_drm_subdrv_close(dev, file);
@@ -241,6 +239,9 @@
 	.poll		= drm_poll,
 	.read		= drm_read,
 	.unlocked_ioctl	= drm_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.release	= drm_release,
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index a68d2b3..b19cd93 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -831,11 +831,6 @@
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "failed to find registers\n");
-		ret = -ENOENT;
-		goto err_clk;
-	}
 
 	ctx->regs = devm_request_and_ioremap(&pdev->dev, res);
 	if (!ctx->regs) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index d2d88f2..1065e90 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -129,7 +129,6 @@
 struct g2d_data {
 	struct device			*dev;
 	struct clk			*gate_clk;
-	struct resource			*regs_res;
 	void __iomem			*regs;
 	int				irq;
 	struct workqueue_struct		*g2d_workq;
@@ -751,7 +750,7 @@
 	struct exynos_drm_subdrv *subdrv;
 	int ret;
 
-	g2d = kzalloc(sizeof(*g2d), GFP_KERNEL);
+	g2d = devm_kzalloc(&pdev->dev, sizeof(*g2d), GFP_KERNEL);
 	if (!g2d) {
 		dev_err(dev, "failed to allocate driver data\n");
 		return -ENOMEM;
@@ -759,10 +758,8 @@
 
 	g2d->runqueue_slab = kmem_cache_create("g2d_runqueue_slab",
 			sizeof(struct g2d_runqueue_node), 0, 0, NULL);
-	if (!g2d->runqueue_slab) {
-		ret = -ENOMEM;
-		goto err_free_mem;
-	}
+	if (!g2d->runqueue_slab)
+		return -ENOMEM;
 
 	g2d->dev = dev;
 
@@ -794,38 +791,26 @@
 	pm_runtime_enable(dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "failed to get I/O memory\n");
-		ret = -ENOENT;
-		goto err_put_clk;
-	}
 
-	g2d->regs_res = request_mem_region(res->start, resource_size(res),
-					   dev_name(dev));
-	if (!g2d->regs_res) {
-		dev_err(dev, "failed to request I/O memory\n");
-		ret = -ENOENT;
-		goto err_put_clk;
-	}
-
-	g2d->regs = ioremap(res->start, resource_size(res));
+	g2d->regs = devm_request_and_ioremap(&pdev->dev, res);
 	if (!g2d->regs) {
 		dev_err(dev, "failed to remap I/O memory\n");
 		ret = -ENXIO;
-		goto err_release_res;
+		goto err_put_clk;
 	}
 
 	g2d->irq = platform_get_irq(pdev, 0);
 	if (g2d->irq < 0) {
 		dev_err(dev, "failed to get irq\n");
 		ret = g2d->irq;
-		goto err_unmap_base;
+		goto err_put_clk;
 	}
 
-	ret = request_irq(g2d->irq, g2d_irq_handler, 0, "drm_g2d", g2d);
+	ret = devm_request_irq(&pdev->dev, g2d->irq, g2d_irq_handler, 0,
+								"drm_g2d", g2d);
 	if (ret < 0) {
 		dev_err(dev, "irq request failed\n");
-		goto err_unmap_base;
+		goto err_put_clk;
 	}
 
 	platform_set_drvdata(pdev, g2d);
@@ -838,7 +823,7 @@
 	ret = exynos_drm_subdrv_register(subdrv);
 	if (ret < 0) {
 		dev_err(dev, "failed to register drm g2d device\n");
-		goto err_free_irq;
+		goto err_put_clk;
 	}
 
 	dev_info(dev, "The exynos g2d(ver %d.%d) successfully probed\n",
@@ -846,13 +831,6 @@
 
 	return 0;
 
-err_free_irq:
-	free_irq(g2d->irq, g2d);
-err_unmap_base:
-	iounmap(g2d->regs);
-err_release_res:
-	release_resource(g2d->regs_res);
-	kfree(g2d->regs_res);
 err_put_clk:
 	pm_runtime_disable(dev);
 	clk_put(g2d->gate_clk);
@@ -862,8 +840,6 @@
 	destroy_workqueue(g2d->g2d_workq);
 err_destroy_slab:
 	kmem_cache_destroy(g2d->runqueue_slab);
-err_free_mem:
-	kfree(g2d);
 	return ret;
 }
 
@@ -873,24 +849,18 @@
 
 	cancel_work_sync(&g2d->runqueue_work);
 	exynos_drm_subdrv_unregister(&g2d->subdrv);
-	free_irq(g2d->irq, g2d);
 
 	while (g2d->runqueue_node) {
 		g2d_free_runqueue_node(g2d, g2d->runqueue_node);
 		g2d->runqueue_node = g2d_get_runqueue_node(g2d);
 	}
 
-	iounmap(g2d->regs);
-	release_resource(g2d->regs_res);
-	kfree(g2d->regs_res);
-
 	pm_runtime_disable(&pdev->dev);
 	clk_put(g2d->gate_clk);
 
 	g2d_fini_cmdlist(g2d);
 	destroy_workqueue(g2d->g2d_workq);
 	kmem_cache_destroy(g2d->runqueue_slab);
-	kfree(g2d);
 
 	return 0;
 }
@@ -924,7 +894,7 @@
 }
 #endif
 
-SIMPLE_DEV_PM_OPS(g2d_pm_ops, g2d_suspend, g2d_resume);
+static SIMPLE_DEV_PM_OPS(g2d_pm_ops, g2d_suspend, g2d_resume);
 
 struct platform_driver g2d_driver = {
 	.probe		= g2d_probe,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index f9efde4..a38051c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -122,7 +122,7 @@
 		__free_page(pages[i]);
 
 	drm_free_large(pages);
-	return ERR_PTR(PTR_ERR(p));
+	return ERR_CAST(p);
 }
 
 static void exynos_gem_put_pages(struct drm_gem_object *obj,
@@ -662,7 +662,7 @@
 	 */
 
 	args->pitch = args->width * ((args->bpp + 7) / 8);
-	args->size = PAGE_ALIGN(args->pitch * args->height);
+	args->size = args->pitch * args->height;
 
 	exynos_gem_obj = exynos_drm_gem_create(dev, args->flags, args->size);
 	if (IS_ERR(exynos_gem_obj))
diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
index 8ffcdf8..3fdf0b6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
@@ -345,7 +345,7 @@
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx) {
 		DRM_LOG_KMS("failed to alloc common hdmi context.\n");
 		return -ENOMEM;
@@ -371,7 +371,6 @@
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
 	exynos_drm_subdrv_unregister(&ctx->subdrv);
-	kfree(ctx);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index b89829e..e1f94b7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -29,7 +29,6 @@
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_NV12,
-	DRM_FORMAT_NV12M,
 	DRM_FORMAT_NV12MT,
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index bb1550c..537027a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -633,7 +633,7 @@
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -673,8 +673,6 @@
 		ctx->raw_edid = NULL;
 	}
 
-	kfree(ctx);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 409e2ec..a6aea6f 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -2172,7 +2172,7 @@
 
 	DRM_DEBUG_KMS("HDMI resource init\n");
 
-	memset(res, 0, sizeof *res);
+	memset(res, 0, sizeof(*res));
 
 	/* get clocks, power */
 	res->hdmi = clk_get(dev, "hdmi");
@@ -2204,7 +2204,7 @@
 	clk_set_parent(res->sclk_hdmi, res->sclk_pixel);
 
 	res->regul_bulk = kzalloc(ARRAY_SIZE(supply) *
-		sizeof res->regul_bulk[0], GFP_KERNEL);
+		sizeof(res->regul_bulk[0]), GFP_KERNEL);
 	if (!res->regul_bulk) {
 		DRM_ERROR("failed to get memory for regulators\n");
 		goto fail;
@@ -2243,7 +2243,7 @@
 		clk_put(res->sclk_hdmi);
 	if (!IS_ERR_OR_NULL(res->hdmi))
 		clk_put(res->hdmi);
-	memset(res, 0, sizeof *res);
+	memset(res, 0, sizeof(*res));
 
 	return 0;
 }
@@ -2312,11 +2312,6 @@
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		DRM_ERROR("failed to find registers\n");
-		ret = -ENOENT;
-		goto err_resource;
-	}
 
 	hdata->regs = devm_request_and_ioremap(&pdev->dev, res);
 	if (!hdata->regs) {
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 30fcc12..25b97d5 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -236,11 +236,11 @@
 static void vp_default_filter(struct mixer_resources *res)
 {
 	vp_filter_set(res, VP_POLY8_Y0_LL,
-		filter_y_horiz_tap8, sizeof filter_y_horiz_tap8);
+		filter_y_horiz_tap8, sizeof(filter_y_horiz_tap8));
 	vp_filter_set(res, VP_POLY4_Y0_LL,
-		filter_y_vert_tap4, sizeof filter_y_vert_tap4);
+		filter_y_vert_tap4, sizeof(filter_y_vert_tap4));
 	vp_filter_set(res, VP_POLY4_C0_LL,
-		filter_cr_horiz_tap4, sizeof filter_cr_horiz_tap4);
+		filter_cr_horiz_tap4, sizeof(filter_cr_horiz_tap4));
 }
 
 static void mixer_vsync_set_update(struct mixer_context *ctx, bool enable)
diff --git a/drivers/gpu/drm/gma500/oaktrail_device.c b/drivers/gpu/drm/gma500/oaktrail_device.c
index 0f9b7db..cf49ba5 100644
--- a/drivers/gpu/drm/gma500/oaktrail_device.c
+++ b/drivers/gpu/drm/gma500/oaktrail_device.c
@@ -476,6 +476,7 @@
 		.pos = DSPAPOS,
 		.surf = DSPASURF,
 		.addr = MRST_DSPABASE,
+		.base = MRST_DSPABASE,
 		.status = PIPEASTAT,
 		.linoff = DSPALINOFF,
 		.tileoff = DSPATILEOFF,
@@ -499,6 +500,7 @@
 		.pos = DSPBPOS,
 		.surf = DSPBSURF,
 		.addr = DSPBBASE,
+		.base = DSPBBASE,
 		.status = PIPEBSTAT,
 		.linoff = DSPBLINOFF,
 		.tileoff = DSPBTILEOFF,
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c
index 30dc22a..8033526 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.c
+++ b/drivers/gpu/drm/gma500/psb_intel_display.c
@@ -1362,6 +1362,9 @@
 	    (struct drm_connector **) (psb_intel_crtc + 1);
 	psb_intel_crtc->mode_set.num_connectors = 0;
 	psb_intel_cursor_init(dev, psb_intel_crtc);
+
+	/* Set to true so that the pipe is forced off on initial config. */
+	psb_intel_crtc->active = true;
 }
 
 int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index 57d892e..463ec68 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -115,6 +115,9 @@
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = i810_mmap_buffers,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index f9924ad..48cfcca 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -51,6 +51,9 @@
 	.mmap = drm_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9cf7dfe..914c0df 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1587,6 +1587,7 @@
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->error_lock);
 	spin_lock_init(&dev_priv->rps_lock);
+	spin_lock_init(&dev_priv->dpio_lock);
 
 	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
 		dev_priv->num_pipe = 3;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5c4657a..489e2b1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2365,6 +2365,10 @@
 
 	/* Flush everything onto the inactive list. */
 	for_each_ring(ring, dev_priv, i) {
+		ret = i915_switch_context(ring, NULL, DEFAULT_CONTEXT_ID);
+		if (ret)
+			return ret;
+
 		ret = i915_ring_idle(ring);
 		if (ret)
 			return ret;
@@ -2372,10 +2376,6 @@
 		/* Is the device fubar? */
 		if (WARN_ON(!list_empty(&ring->gpu_write_list)))
 			return -EBUSY;
-
-		ret = i915_switch_context(ring, NULL, DEFAULT_CONTEXT_ID);
-		if (ret)
-			return ret;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ee9b68f..60815b8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -72,7 +72,7 @@
 	/* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024
 	 * entries. For aliasing ppgtt support we just steal them at the end for
 	 * now. */
-	first_pd_entry_in_global_pt = 512*1024 - I915_PPGTT_PD_ENTRIES;
+	first_pd_entry_in_global_pt = dev_priv->mm.gtt->gtt_total_entries - I915_PPGTT_PD_ENTRIES;
 
 	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
 	if (!ppgtt)
@@ -261,7 +261,10 @@
 		pte_flags |= GEN6_PTE_CACHE_LLC;
 		break;
 	case I915_CACHE_NONE:
-		pte_flags |= GEN6_PTE_UNCACHED;
+		if (IS_HASWELL(dev))
+			pte_flags |= HSW_PTE_UNCACHED;
+		else
+			pte_flags |= GEN6_PTE_UNCACHED;
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 8a38285..5249640 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2700,9 +2700,6 @@
 			dev->driver->irq_handler = i8xx_irq_handler;
 			dev->driver->irq_uninstall = i8xx_irq_uninstall;
 		} else if (INTEL_INFO(dev)->gen == 3) {
-			/* IIR "flip pending" means done if this bit is set */
-			I915_WRITE(ECOSKPD, _MASKED_BIT_DISABLE(ECO_FLIP_DONE));
-
 			dev->driver->irq_preinstall = i915_irq_preinstall;
 			dev->driver->irq_postinstall = i915_irq_postinstall;
 			dev->driver->irq_uninstall = i915_irq_uninstall;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index acc99b2..28725ce 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -115,6 +115,7 @@
 
 #define GEN6_PTE_VALID			(1 << 0)
 #define GEN6_PTE_UNCACHED		(1 << 1)
+#define HSW_PTE_UNCACHED		(0)
 #define GEN6_PTE_CACHE_LLC		(2 << 1)
 #define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
 #define GEN6_PTE_CACHE_BITS		(3 << 1)
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 7ed4a41..23bdc8c 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -326,6 +326,36 @@
 	return ret;
 }
 
+static struct edid *intel_crt_get_edid(struct drm_connector *connector,
+				struct i2c_adapter *i2c)
+{
+	struct edid *edid;
+
+	edid = drm_get_edid(connector, i2c);
+
+	if (!edid && !intel_gmbus_is_forced_bit(i2c)) {
+		DRM_DEBUG_KMS("CRT GMBUS EDID read failed, retry using GPIO bit-banging\n");
+		intel_gmbus_force_bit(i2c, true);
+		edid = drm_get_edid(connector, i2c);
+		intel_gmbus_force_bit(i2c, false);
+	}
+
+	return edid;
+}
+
+/* local version of intel_ddc_get_modes() to use intel_crt_get_edid() */
+static int intel_crt_ddc_get_modes(struct drm_connector *connector,
+				struct i2c_adapter *adapter)
+{
+	struct edid *edid;
+
+	edid = intel_crt_get_edid(connector, adapter);
+	if (!edid)
+		return 0;
+
+	return intel_connector_update_modes(connector, edid);
+}
+
 static bool intel_crt_detect_ddc(struct drm_connector *connector)
 {
 	struct intel_crt *crt = intel_attached_crt(connector);
@@ -336,7 +366,7 @@
 	BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
 
 	i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->crt_ddc_pin);
-	edid = drm_get_edid(connector, i2c);
+	edid = intel_crt_get_edid(connector, i2c);
 
 	if (edid) {
 		bool is_digital = edid->input & DRM_EDID_INPUT_DIGITAL;
@@ -544,13 +574,13 @@
 	struct i2c_adapter *i2c;
 
 	i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->crt_ddc_pin);
-	ret = intel_ddc_get_modes(connector, i2c);
+	ret = intel_crt_ddc_get_modes(connector, i2c);
 	if (ret || !IS_G4X(dev))
 		return ret;
 
 	/* Try to probe digital port for output in DVI-I -> VGA mode. */
 	i2c = intel_gmbus_get_adapter(dev_priv, GMBUS_PORT_DPB);
-	return intel_ddc_get_modes(connector, i2c);
+	return intel_crt_ddc_get_modes(connector, i2c);
 }
 
 static int intel_crt_set_property(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a69a3d0..bc2ad34 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1376,7 +1376,8 @@
 	     "PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n",
 	     reg, pipe_name(pipe));
 
-	WARN(HAS_PCH_IBX(dev_priv->dev) && (val & SDVO_PIPE_B_SELECT),
+	WARN(HAS_PCH_IBX(dev_priv->dev) && (val & DP_PORT_EN) == 0
+	     && (val & DP_PIPEB_SELECT),
 	     "IBX PCH dp port still using transcoder B\n");
 }
 
@@ -1384,11 +1385,12 @@
 				     enum pipe pipe, int reg)
 {
 	u32 val = I915_READ(reg);
-	WARN(hdmi_pipe_enabled(dev_priv, val, pipe),
+	WARN(hdmi_pipe_enabled(dev_priv, pipe, val),
 	     "PCH HDMI (0x%08x) enabled on transcoder %c, should be disabled\n",
 	     reg, pipe_name(pipe));
 
-	WARN(HAS_PCH_IBX(dev_priv->dev) && (val & SDVO_PIPE_B_SELECT),
+	WARN(HAS_PCH_IBX(dev_priv->dev) && (val & PORT_ENABLE) == 0
+	     && (val & SDVO_PIPE_B_SELECT),
 	     "IBX PCH hdmi port still using transcoder B\n");
 }
 
@@ -1404,13 +1406,13 @@
 
 	reg = PCH_ADPA;
 	val = I915_READ(reg);
-	WARN(adpa_pipe_enabled(dev_priv, val, pipe),
+	WARN(adpa_pipe_enabled(dev_priv, pipe, val),
 	     "PCH VGA enabled on transcoder %c, should be disabled\n",
 	     pipe_name(pipe));
 
 	reg = PCH_LVDS;
 	val = I915_READ(reg);
-	WARN(lvds_pipe_enabled(dev_priv, val, pipe),
+	WARN(lvds_pipe_enabled(dev_priv, pipe, val),
 	     "PCH LVDS enabled on transcoder %c, should be disabled\n",
 	     pipe_name(pipe));
 
@@ -1872,7 +1874,7 @@
 			     enum pipe pipe, int reg)
 {
 	u32 val = I915_READ(reg);
-	if (hdmi_pipe_enabled(dev_priv, val, pipe)) {
+	if (hdmi_pipe_enabled(dev_priv, pipe, val)) {
 		DRM_DEBUG_KMS("Disabling pch HDMI %x on pipe %d\n",
 			      reg, pipe);
 		I915_WRITE(reg, val & ~PORT_ENABLE);
@@ -1894,12 +1896,12 @@
 
 	reg = PCH_ADPA;
 	val = I915_READ(reg);
-	if (adpa_pipe_enabled(dev_priv, val, pipe))
+	if (adpa_pipe_enabled(dev_priv, pipe, val))
 		I915_WRITE(reg, val & ~ADPA_DAC_ENABLE);
 
 	reg = PCH_LVDS;
 	val = I915_READ(reg);
-	if (lvds_pipe_enabled(dev_priv, val, pipe)) {
+	if (lvds_pipe_enabled(dev_priv, pipe, val)) {
 		DRM_DEBUG_KMS("disable lvds on pipe %d val 0x%08x\n", pipe, val);
 		I915_WRITE(reg, val & ~LVDS_PORT_EN);
 		POSTING_READ(reg);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index a6c426a..ace757a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2533,14 +2533,10 @@
 			break;
 	}
 
-	intel_dp_i2c_init(intel_dp, intel_connector, name);
-
 	/* Cache some DPCD data in the eDP case */
 	if (is_edp(intel_dp)) {
-		bool ret;
 		struct edp_power_seq	cur, vbt;
 		u32 pp_on, pp_off, pp_div;
-		struct edid *edid;
 
 		pp_on = I915_READ(PCH_PP_ON_DELAYS);
 		pp_off = I915_READ(PCH_PP_OFF_DELAYS);
@@ -2591,6 +2587,13 @@
 
 		DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
 			      intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
+	}
+
+	intel_dp_i2c_init(intel_dp, intel_connector, name);
+
+	if (is_edp(intel_dp)) {
+		bool ret;
+		struct edid *edid;
 
 		ironlake_edp_panel_vdd_on(intel_dp);
 		ret = intel_dp_get_dpcd(intel_dp);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 132ab51..cd54cf8 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -342,6 +342,8 @@
 	int interval;
 };
 
+int intel_connector_update_modes(struct drm_connector *connector,
+				struct edid *edid);
 int intel_ddc_get_modes(struct drm_connector *c, struct i2c_adapter *adapter);
 
 extern void intel_attach_force_audio_property(struct drm_connector *connector);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index e05c0d3..e9a6f6a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -780,6 +780,14 @@
 			DMI_MATCH(DMI_BOARD_NAME, "ZBOXSD-ID12/ID13"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Gigabyte GA-D525TUD",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."),
+			DMI_MATCH(DMI_BOARD_NAME, "D525TUD"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 45848b9..29b7259 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -33,6 +33,25 @@
 #include "i915_drv.h"
 
 /**
+ * intel_connector_update_modes - update connector from edid
+ * @connector: DRM connector device to use
+ * @edid: previously read EDID information
+ */
+int intel_connector_update_modes(struct drm_connector *connector,
+				struct edid *edid)
+{
+	int ret;
+
+	drm_mode_connector_update_edid_property(connector, edid);
+	ret = drm_add_edid_modes(connector, edid);
+	drm_edid_to_eld(connector, edid);
+	connector->display_info.raw_edid = NULL;
+	kfree(edid);
+
+	return ret;
+}
+
+/**
  * intel_ddc_get_modes - get modelist from monitor
  * @connector: DRM connector device to use
  * @adapter: i2c adapter
@@ -43,18 +62,12 @@
 			struct i2c_adapter *adapter)
 {
 	struct edid *edid;
-	int ret = 0;
 
 	edid = drm_get_edid(connector, adapter);
-	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
-		ret = drm_add_edid_modes(connector, edid);
-		drm_edid_to_eld(connector, edid);
-		connector->display_info.raw_edid = NULL;
-		kfree(edid);
-	}
+	if (!edid)
+		return 0;
 
-	return ret;
+	return intel_connector_update_modes(connector, edid);
 }
 
 static const struct drm_prop_enum_list force_audio_names[] = {
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 3df4f5f..e019b23 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -162,19 +162,12 @@
 	return val;
 }
 
-u32 intel_panel_get_max_backlight(struct drm_device *dev)
+static u32 _intel_panel_get_max_backlight(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 max;
 
 	max = i915_read_blc_pwm_ctl(dev_priv);
-	if (max == 0) {
-		/* XXX add code here to query mode clock or hardware clock
-		 * and program max PWM appropriately.
-		 */
-		pr_warn_once("fixme: max PWM is zero\n");
-		return 1;
-	}
 
 	if (HAS_PCH_SPLIT(dev)) {
 		max >>= 16;
@@ -188,6 +181,22 @@
 			max *= 0xff;
 	}
 
+	return max;
+}
+
+u32 intel_panel_get_max_backlight(struct drm_device *dev)
+{
+	u32 max;
+
+	max = _intel_panel_get_max_backlight(dev);
+	if (max == 0) {
+		/* XXX add code here to query mode clock or hardware clock
+		 * and program max PWM appropriately.
+		 */
+		pr_warn_once("fixme: max PWM is zero\n");
+		return 1;
+	}
+
 	DRM_DEBUG_DRIVER("max backlight PWM = %d\n", max);
 	return max;
 }
@@ -424,7 +433,11 @@
 
 	memset(&props, 0, sizeof(props));
 	props.type = BACKLIGHT_RAW;
-	props.max_brightness = intel_panel_get_max_backlight(dev);
+	props.max_brightness = _intel_panel_get_max_backlight(dev);
+	if (props.max_brightness == 0) {
+		DRM_ERROR("Failed to get maximum backlight value\n");
+		return -ENODEV;
+	}
 	dev_priv->backlight =
 		backlight_device_register("intel_backlight",
 					  &connector->kdev, dev,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 58c07cd..ba8a27b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2441,17 +2441,10 @@
 		   dev_priv->max_delay << 24 |
 		   dev_priv->min_delay << 16);
 
-	if (IS_HASWELL(dev)) {
-		I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
-		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
-		I915_WRITE(GEN6_RP_UP_EI, 66000);
-		I915_WRITE(GEN6_RP_DOWN_EI, 350000);
-	} else {
-		I915_WRITE(GEN6_RP_UP_THRESHOLD, 10000);
-		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 1000000);
-		I915_WRITE(GEN6_RP_UP_EI, 100000);
-		I915_WRITE(GEN6_RP_DOWN_EI, 5000000);
-	}
+	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
+	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
+	I915_WRITE(GEN6_RP_UP_EI, 66000);
+	I915_WRITE(GEN6_RP_DOWN_EI, 350000);
 
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 	I915_WRITE(GEN6_RP_CONTROL,
@@ -3679,6 +3672,9 @@
 
 	if (IS_PINEVIEW(dev))
 		I915_WRITE(ECOSKPD, _MASKED_BIT_ENABLE(ECO_GATING_CX_ONLY));
+
+	/* IIR "flip pending" means done if this bit is set */
+	I915_WRITE(ECOSKPD, _MASKED_BIT_DISABLE(ECO_FLIP_DONE));
 }
 
 static void i85x_init_clock_gating(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index d172e98..123afd3 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1692,6 +1692,7 @@
 	edid = intel_sdvo_get_edid(connector);
 	if (edid != NULL && edid->input & DRM_EDID_INPUT_DIGITAL)
 		has_audio = drm_detect_monitor_audio(edid);
+	kfree(edid);
 
 	return has_audio;
 }
@@ -2572,7 +2573,6 @@
 		hotplug_mask = intel_sdvo->is_sdvob ?
 			SDVOB_HOTPLUG_INT_STATUS_I915 : SDVOC_HOTPLUG_INT_STATUS_I915;
 	}
-	dev_priv->hotplug_supported_mask |= hotplug_mask;
 
 	drm_encoder_helper_add(&intel_encoder->base, &intel_sdvo_helper_funcs);
 
@@ -2580,14 +2580,6 @@
 	if (!intel_sdvo_get_capabilities(intel_sdvo, &intel_sdvo->caps))
 		goto err;
 
-	/* Set up hotplug command - note paranoia about contents of reply.
-	 * We assume that the hardware is in a sane state, and only touch
-	 * the bits we think we understand.
-	 */
-	intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG,
-			     &intel_sdvo->hotplug_active, 2);
-	intel_sdvo->hotplug_active[0] &= ~0x3;
-
 	if (intel_sdvo_output_setup(intel_sdvo,
 				    intel_sdvo->caps.output_flags) != true) {
 		DRM_DEBUG_KMS("SDVO output failed to setup on %s\n",
@@ -2595,6 +2587,12 @@
 		goto err;
 	}
 
+	/* Only enable the hotplug irq if we need it, to work around noisy
+	 * hotplug lines.
+	 */
+	if (intel_sdvo->hotplug_active[0])
+		dev_priv->hotplug_supported_mask |= hotplug_mask;
+
 	intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo, sdvo_reg);
 
 	/* Set the input timing to the screen. Assume always input 0. */
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index cc8df4d..7644f31 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -60,11 +60,11 @@
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_XBGR8888:
-		sprctl |= SPRITE_FORMAT_RGBX888;
+		sprctl |= SPRITE_FORMAT_RGBX888 | SPRITE_RGB_ORDER_RGBX;
 		pixel_size = 4;
 		break;
 	case DRM_FORMAT_XRGB8888:
-		sprctl |= SPRITE_FORMAT_RGBX888 | SPRITE_RGB_ORDER_RGBX;
+		sprctl |= SPRITE_FORMAT_RGBX888;
 		pixel_size = 4;
 		break;
 	case DRM_FORMAT_YUYV:
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index ea1024d..e5f145d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -84,6 +84,9 @@
 	.mmap = mgag200_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.read = drm_read,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index fc841e8..26ebffe 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -211,11 +211,6 @@
 	return nouveau_dsm_set_discrete_state(nouveau_dsm_priv.dhandle, state);
 }
 
-static int nouveau_dsm_init(void)
-{
-	return 0;
-}
-
 static int nouveau_dsm_get_client_id(struct pci_dev *pdev)
 {
 	/* easy option one - intel vendor ID means Integrated */
@@ -232,7 +227,6 @@
 static struct vga_switcheroo_handler nouveau_dsm_handler = {
 	.switchto = nouveau_dsm_switchto,
 	.power_state = nouveau_dsm_power_state,
-	.init = nouveau_dsm_init,
 	.get_client_id = nouveau_dsm_get_client_id,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 69688ef..7e16dc5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -598,7 +598,7 @@
 	args->size = args->pitch * args->height;
 	args->size = roundup(args->size, PAGE_SIZE);
 
-	ret = nouveau_gem_new(dev, args->size, 0, TTM_PL_FLAG_VRAM, 0, 0, &bo);
+	ret = nouveau_gem_new(dev, args->size, 0, NOUVEAU_GEM_DOMAIN_VRAM, 0, 0, &bo);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index 1866dbb..c610144 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -736,9 +736,11 @@
 			}
 			break;
 		case NV_C0:
-			nvc0_copy_create(dev, 1);
+			if (!(nv_rd32(dev, 0x022500) & 0x00000200))
+				nvc0_copy_create(dev, 1);
 		case NV_D0:
-			nvc0_copy_create(dev, 0);
+			if (!(nv_rd32(dev, 0x022500) & 0x00000100))
+				nvc0_copy_create(dev, 0);
 			break;
 		default:
 			break;
diff --git a/drivers/gpu/drm/nouveau/nv50_gpio.c b/drivers/gpu/drm/nouveau/nv50_gpio.c
index f429e6a..f034905 100644
--- a/drivers/gpu/drm/nouveau/nv50_gpio.c
+++ b/drivers/gpu/drm/nouveau/nv50_gpio.c
@@ -115,6 +115,9 @@
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 
+	/* initialise gpios and routing to vbios defaults */
+	nouveau_gpio_reset(dev);
+
 	/* disable, and ack any pending gpio interrupts */
 	nv_wr32(dev, 0xe050, 0x00000000);
 	nv_wr32(dev, 0xe054, 0xffffffff);
diff --git a/drivers/gpu/drm/nouveau/nvd0_display.c b/drivers/gpu/drm/nouveau/nvd0_display.c
index dac525b..8a2fc89 100644
--- a/drivers/gpu/drm/nouveau/nvd0_display.c
+++ b/drivers/gpu/drm/nouveau/nvd0_display.c
@@ -1510,10 +1510,10 @@
 	case OUTPUT_DP:
 		if (nv_connector->base.display_info.bpc == 6) {
 			nv_encoder->dp.datarate = mode->clock * 18 / 8;
-			syncs |= 0x00000140;
+			syncs |= 0x00000002 << 6;
 		} else {
 			nv_encoder->dp.datarate = mode->clock * 24 / 8;
-			syncs |= 0x00000180;
+			syncs |= 0x00000005 << 6;
 		}
 
 		if (nv_encoder->dcb->sorconf.link & 1)
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index c6fcb5b..e721e30 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -258,7 +258,6 @@
 		radeon_crtc->enabled = true;
 		/* adjust pm to dpms changes BEFORE enabling crtcs */
 		radeon_pm_compute_clocks(rdev);
-		/* disable crtc pair power gating before programming */
 		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set)
 			atombios_powergate_crtc(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_ENABLE);
@@ -278,25 +277,8 @@
 			atombios_enable_crtc_memreq(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_DISABLE);
 		radeon_crtc->enabled = false;
-		/* power gating is per-pair */
-		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set) {
-			struct drm_crtc *other_crtc;
-			struct radeon_crtc *other_radeon_crtc;
-			list_for_each_entry(other_crtc, &rdev->ddev->mode_config.crtc_list, head) {
-				other_radeon_crtc = to_radeon_crtc(other_crtc);
-				if (((radeon_crtc->crtc_id == 0) && (other_radeon_crtc->crtc_id == 1)) ||
-				    ((radeon_crtc->crtc_id == 1) && (other_radeon_crtc->crtc_id == 0)) ||
-				    ((radeon_crtc->crtc_id == 2) && (other_radeon_crtc->crtc_id == 3)) ||
-				    ((radeon_crtc->crtc_id == 3) && (other_radeon_crtc->crtc_id == 2)) ||
-				    ((radeon_crtc->crtc_id == 4) && (other_radeon_crtc->crtc_id == 5)) ||
-				    ((radeon_crtc->crtc_id == 5) && (other_radeon_crtc->crtc_id == 4))) {
-					/* if both crtcs in the pair are off, enable power gating */
-					if (other_radeon_crtc->enabled == false)
-						atombios_powergate_crtc(crtc, ATOM_ENABLE);
-					break;
-				}
-			}
-		}
+		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set)
+			atombios_powergate_crtc(crtc, ATOM_ENABLE);
 		/* adjust pm to dpms changes AFTER disabling crtcs */
 		radeon_pm_compute_clocks(rdev);
 		break;
@@ -444,11 +426,28 @@
 static void atombios_crtc_program_ss(struct radeon_device *rdev,
 				     int enable,
 				     int pll_id,
+				     int crtc_id,
 				     struct radeon_atom_ss *ss)
 {
+	unsigned i;
 	int index = GetIndexIntoMasterTable(COMMAND, EnableSpreadSpectrumOnPPLL);
 	union atom_enable_ss args;
 
+	if (!enable) {
+		for (i = 0; i < rdev->num_crtc; i++) {
+			if (rdev->mode_info.crtcs[i] &&
+			    rdev->mode_info.crtcs[i]->enabled &&
+			    i != crtc_id &&
+			    pll_id == rdev->mode_info.crtcs[i]->pll_id) {
+				/* one other crtc is using this pll don't turn
+				 * off spread spectrum as it might turn off
+				 * display on active crtc
+				 */
+				return;
+			}
+		}
+	}
+
 	memset(&args, 0, sizeof(args));
 
 	if (ASIC_IS_DCE5(rdev)) {
@@ -1028,7 +1027,7 @@
 		radeon_compute_pll_legacy(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div,
 					  &ref_div, &post_div);
 
-	atombios_crtc_program_ss(rdev, ATOM_DISABLE, radeon_crtc->pll_id, &ss);
+	atombios_crtc_program_ss(rdev, ATOM_DISABLE, radeon_crtc->pll_id, radeon_crtc->crtc_id, &ss);
 
 	atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
 				  encoder_mode, radeon_encoder->encoder_id, mode->clock,
@@ -1051,7 +1050,7 @@
 			ss.step = step_size;
 		}
 
-		atombios_crtc_program_ss(rdev, ATOM_ENABLE, radeon_crtc->pll_id, &ss);
+		atombios_crtc_program_ss(rdev, ATOM_ENABLE, radeon_crtc->pll_id, radeon_crtc->crtc_id, &ss);
 	}
 }
 
@@ -1480,14 +1479,98 @@
 	}
 }
 
+/**
+ * radeon_get_pll_use_mask - look up a mask of which pplls are in use
+ *
+ * @crtc: drm crtc
+ *
+ * Returns the mask of which PPLLs (Pixel PLLs) are in use.
+ */
+static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_crtc *test_crtc;
+	struct radeon_crtc *radeon_test_crtc;
+	u32 pll_in_use = 0;
+
+	list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
+		if (crtc == test_crtc)
+			continue;
+
+		radeon_test_crtc = to_radeon_crtc(test_crtc);
+		if (radeon_test_crtc->pll_id != ATOM_PPLL_INVALID)
+			pll_in_use |= (1 << radeon_test_crtc->pll_id);
+	}
+	return pll_in_use;
+}
+
+/**
+ * radeon_get_shared_dp_ppll - return the PPLL used by another crtc for DP
+ *
+ * @crtc: drm crtc
+ *
+ * Returns the PPLL (Pixel PLL) used by another crtc/encoder which is
+ * also in DP mode.  For DP, a single PPLL can be used for all DP
+ * crtcs/encoders.
+ */
+static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_encoder *test_encoder;
+	struct radeon_crtc *radeon_test_crtc;
+
+	list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) {
+		if (test_encoder->crtc && (test_encoder->crtc != crtc)) {
+			if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) {
+				/* for DP use the same PLL for all */
+				radeon_test_crtc = to_radeon_crtc(test_encoder->crtc);
+				if (radeon_test_crtc->pll_id != ATOM_PPLL_INVALID)
+					return radeon_test_crtc->pll_id;
+			}
+		}
+	}
+	return ATOM_PPLL_INVALID;
+}
+
+/**
+ * radeon_atom_pick_pll - Allocate a PPLL for use by the crtc.
+ *
+ * @crtc: drm crtc
+ *
+ * Returns the PPLL (Pixel PLL) to be used by the crtc.  For DP monitors
+ * a single PPLL can be used for all DP crtcs/encoders.  For non-DP
+ * monitors a dedicated PPLL must be used.  If a particular board has
+ * an external DP PLL, return ATOM_PPLL_INVALID to skip PLL programming
+ * as there is no need to program the PLL itself.  If we are not able to
+ * allocate a PLL, return ATOM_PPLL_INVALID to skip PLL programming to
+ * avoid messing up an existing monitor.
+ *
+ * Asic specific PLL information
+ *
+ * DCE 6.1
+ * - PPLL2 is only available to UNIPHYA (both DP and non-DP)
+ * - PPLL0, PPLL1 are available for UNIPHYB/C/D/E/F (both DP and non-DP)
+ *
+ * DCE 6.0
+ * - PPLL0 is available to all UNIPHY (DP only)
+ * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC
+ *
+ * DCE 5.0
+ * - DCPLL is available to all UNIPHY (DP only)
+ * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC
+ *
+ * DCE 3.0/4.0/4.1
+ * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC
+ *
+ */
 static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct drm_encoder *test_encoder;
-	struct drm_crtc *test_crtc;
-	uint32_t pll_in_use = 0;
+	u32 pll_in_use;
+	int pll;
 
 	if (ASIC_IS_DCE61(rdev)) {
 		list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) {
@@ -1499,32 +1582,40 @@
 
 				if ((test_radeon_encoder->encoder_id ==
 				     ENCODER_OBJECT_ID_INTERNAL_UNIPHY) &&
-				    (dig->linkb == false)) /* UNIPHY A uses PPLL2 */
+				    (dig->linkb == false))
+					/* UNIPHY A uses PPLL2 */
 					return ATOM_PPLL2;
+				else if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) {
+					/* UNIPHY B/C/D/E/F */
+					if (rdev->clock.dp_extclk)
+						/* skip PPLL programming if using ext clock */
+						return ATOM_PPLL_INVALID;
+					else {
+						/* use the same PPLL for all DP monitors */
+						pll = radeon_get_shared_dp_ppll(crtc);
+						if (pll != ATOM_PPLL_INVALID)
+							return pll;
+					}
+				}
+				break;
 			}
 		}
 		/* UNIPHY B/C/D/E/F */
-		list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
-			struct radeon_crtc *radeon_test_crtc;
-
-			if (crtc == test_crtc)
-				continue;
-
-			radeon_test_crtc = to_radeon_crtc(test_crtc);
-			if ((radeon_test_crtc->pll_id == ATOM_PPLL0) ||
-			    (radeon_test_crtc->pll_id == ATOM_PPLL1))
-				pll_in_use |= (1 << radeon_test_crtc->pll_id);
-		}
-		if (!(pll_in_use & 4))
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL0)))
 			return ATOM_PPLL0;
-		return ATOM_PPLL1;
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
+			return ATOM_PPLL1;
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
 	} else if (ASIC_IS_DCE4(rdev)) {
 		list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) {
 			if (test_encoder->crtc && (test_encoder->crtc == crtc)) {
 				/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
 				 * depending on the asic:
 				 * DCE4: PPLL or ext clock
-				 * DCE5: DCPLL or ext clock
+				 * DCE5: PPLL, DCPLL, or ext clock
+				 * DCE6: PPLL, PPLL0, or ext clock
 				 *
 				 * Setting ATOM_PPLL_INVALID will cause SetPixelClock to skip
 				 * PPLL/DCPLL programming and only program the DP DTO for the
@@ -1532,31 +1623,34 @@
 				 */
 				if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) {
 					if (rdev->clock.dp_extclk)
+						/* skip PPLL programming if using ext clock */
 						return ATOM_PPLL_INVALID;
 					else if (ASIC_IS_DCE6(rdev))
+						/* use PPLL0 for all DP */
 						return ATOM_PPLL0;
 					else if (ASIC_IS_DCE5(rdev))
+						/* use DCPLL for all DP */
 						return ATOM_DCPLL;
+					else {
+						/* use the same PPLL for all DP monitors */
+						pll = radeon_get_shared_dp_ppll(crtc);
+						if (pll != ATOM_PPLL_INVALID)
+							return pll;
+					}
 				}
+				break;
 			}
 		}
-
-		/* otherwise, pick one of the plls */
-		list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) {
-			struct radeon_crtc *radeon_test_crtc;
-
-			if (crtc == test_crtc)
-				continue;
-
-			radeon_test_crtc = to_radeon_crtc(test_crtc);
-			if ((radeon_test_crtc->pll_id >= ATOM_PPLL1) &&
-			    (radeon_test_crtc->pll_id <= ATOM_PPLL2))
-				pll_in_use |= (1 << radeon_test_crtc->pll_id);
-		}
-		if (!(pll_in_use & 1))
+		/* all other cases */
+		pll_in_use = radeon_get_pll_use_mask(crtc);
+		if (!(pll_in_use & (1 << ATOM_PPLL2)))
+			return ATOM_PPLL2;
+		if (!(pll_in_use & (1 << ATOM_PPLL1)))
 			return ATOM_PPLL1;
-		return ATOM_PPLL2;
+		DRM_ERROR("unable to allocate a PPLL\n");
+		return ATOM_PPLL_INVALID;
 	} else
+		/* use PPLL1 or PPLL2 */
 		return radeon_crtc->crtc_id;
 
 }
@@ -1572,11 +1666,11 @@
 								   ASIC_INTERNAL_SS_ON_DCPLL,
 								   rdev->clock.default_dispclk);
 		if (ss_enabled)
-			atombios_crtc_program_ss(rdev, ATOM_DISABLE, ATOM_DCPLL, &ss);
+			atombios_crtc_program_ss(rdev, ATOM_DISABLE, ATOM_DCPLL, -1, &ss);
 		/* XXX: DCE5, make sure voltage, dispclk is high enough */
 		atombios_crtc_set_disp_eng_pll(rdev, rdev->clock.default_dispclk);
 		if (ss_enabled)
-			atombios_crtc_program_ss(rdev, ATOM_ENABLE, ATOM_DCPLL, &ss);
+			atombios_crtc_program_ss(rdev, ATOM_ENABLE, ATOM_DCPLL, -1, &ss);
 	}
 
 }
@@ -1665,9 +1759,22 @@
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_atom_ss ss;
+	int i;
 
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 
+	for (i = 0; i < rdev->num_crtc; i++) {
+		if (rdev->mode_info.crtcs[i] &&
+		    rdev->mode_info.crtcs[i]->enabled &&
+		    i != radeon_crtc->crtc_id &&
+		    radeon_crtc->pll_id == rdev->mode_info.crtcs[i]->pll_id) {
+			/* one other crtc is using this pll don't turn
+			 * off the pll
+			 */
+			goto done;
+		}
+	}
+
 	switch (radeon_crtc->pll_id) {
 	case ATOM_PPLL1:
 	case ATOM_PPLL2:
@@ -1684,7 +1791,8 @@
 	default:
 		break;
 	}
-	radeon_crtc->pll_id = -1;
+done:
+	radeon_crtc->pll_id = ATOM_PPLL_INVALID;
 }
 
 static const struct drm_crtc_helper_funcs atombios_helper_funcs = {
@@ -1733,6 +1841,6 @@
 		else
 			radeon_crtc->crtc_offset = 0;
 	}
-	radeon_crtc->pll_id = -1;
+	radeon_crtc->pll_id = ATOM_PPLL_INVALID;
 	drm_crtc_helper_add(&radeon_crtc->base, &atombios_helper_funcs);
 }
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 7712cf5..3623b98 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -577,30 +577,25 @@
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
+	u16 dp_bridge = radeon_connector_encoder_get_dp_bridge_encoder_id(connector);
+	u8 tmp;
 
 	if (!ASIC_IS_DCE4(rdev))
 		return panel_mode;
 
-	if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-	    ENCODER_OBJECT_ID_NUTMEG)
-		panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
-	else if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-		 ENCODER_OBJECT_ID_TRAVIS) {
-		u8 id[6];
-		int i;
-		for (i = 0; i < 6; i++)
-			id[i] = radeon_read_dpcd_reg(radeon_connector, 0x503 + i);
-		if (id[0] == 0x73 &&
-		    id[1] == 0x69 &&
-		    id[2] == 0x76 &&
-		    id[3] == 0x61 &&
-		    id[4] == 0x72 &&
-		    id[5] == 0x54)
+	if (dp_bridge != ENCODER_OBJECT_ID_NONE) {
+		/* DP bridge chips */
+		tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP);
+		if (tmp & 1)
+			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+		else if ((dp_bridge == ENCODER_OBJECT_ID_NUTMEG) ||
+			 (dp_bridge == ENCODER_OBJECT_ID_TRAVIS))
 			panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
 		else
-			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+			panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
 	} else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
-		u8 tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP);
+		/* eDP */
+		tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP);
 		if (tmp & 1)
 			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
 	}
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index f9bc27f..6e8803a 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1379,6 +1379,8 @@
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct drm_encoder *ext_encoder = radeon_get_external_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	struct radeon_connector *radeon_connector = NULL;
 	struct radeon_connector_atom_dig *radeon_dig_connector = NULL;
@@ -1390,19 +1392,37 @@
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
-		/* some early dce3.2 boards have a bug in their transmitter control table */
-		if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730) ||
-		    ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
-			if (ASIC_IS_DCE6(rdev)) {
-				/* It seems we need to call ATOM_ENCODER_CMD_SETUP again
-				 * before reenabling encoder on DPMS ON, otherwise we never
-				 * get picture
-				 */
-				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
+		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+			if (!connector)
+				dig->panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
+			else
+				dig->panel_mode = radeon_dp_get_panel_mode(encoder, connector);
+
+			/* setup and enable the encoder */
+			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
+			atombios_dig_encoder_setup(encoder,
+						   ATOM_ENCODER_CMD_SETUP_PANEL_MODE,
+						   dig->panel_mode);
+			if (ext_encoder) {
+				if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev))
+					atombios_external_encoder_setup(encoder, ext_encoder,
+									EXTERNAL_ENCODER_ACTION_V3_ENCODER_SETUP);
 			}
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-		} else {
+		} else if (ASIC_IS_DCE4(rdev)) {
+			/* setup and enable the encoder */
+			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
+			/* enable the transmitter */
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
+		} else {
+			/* setup and enable the encoder and transmitter */
+			atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
+			/* some early dce3.2 boards have a bug in their transmitter control table */
+			if ((rdev->family != CHIP_RV710) || (rdev->family != CHIP_RV730))
+				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
 			if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
@@ -1420,10 +1440,19 @@
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev))
+		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+			/* disable the transmitter */
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-		else
+		} else if (ASIC_IS_DCE4(rdev)) {
+			/* disable the transmitter */
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
+		} else {
+			/* disable the encoder and transmitter */
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0);
+			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
+			atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0);
+		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
 			if (ASIC_IS_DCE4(rdev))
 				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_OFF, 0);
@@ -1740,13 +1769,34 @@
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct drm_encoder *test_encoder;
-	struct radeon_encoder_atom_dig *dig;
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	uint32_t dig_enc_in_use = 0;
 
-	/* DCE4/5 */
-	if (ASIC_IS_DCE4(rdev)) {
-		dig = radeon_encoder->enc_priv;
-		if (ASIC_IS_DCE41(rdev)) {
+	if (ASIC_IS_DCE6(rdev)) {
+		/* DCE6 */
+		switch (radeon_encoder->encoder_id) {
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
+			if (dig->linkb)
+				return 1;
+			else
+				return 0;
+			break;
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
+			if (dig->linkb)
+				return 3;
+			else
+				return 2;
+			break;
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+			if (dig->linkb)
+				return 5;
+			else
+				return 4;
+			break;
+		}
+	} else if (ASIC_IS_DCE4(rdev)) {
+		/* DCE4/5 */
+		if (ASIC_IS_DCE41(rdev) && !ASIC_IS_DCE61(rdev)) {
 			/* ontario follows DCE4 */
 			if (rdev->family == CHIP_PALM) {
 				if (dig->linkb)
@@ -1848,10 +1898,12 @@
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-	struct drm_encoder *ext_encoder = radeon_get_external_encoder(encoder);
 
 	radeon_encoder->pixel_clock = adjusted_mode->clock;
 
+	/* need to call this here rather than in prepare() since we need some crtc info */
+	radeon_atom_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
+
 	if (ASIC_IS_AVIVO(rdev) && !ASIC_IS_DCE4(rdev)) {
 		if (radeon_encoder->active_device & (ATOM_DEVICE_CV_SUPPORT | ATOM_DEVICE_TV_SUPPORT))
 			atombios_yuv_setup(encoder, true);
@@ -1870,38 +1922,7 @@
 	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
 	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
-		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
-			struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
-			struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-
-			if (!connector)
-				dig->panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
-			else
-				dig->panel_mode = radeon_dp_get_panel_mode(encoder, connector);
-
-			/* setup and enable the encoder */
-			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
-			atombios_dig_encoder_setup(encoder,
-						   ATOM_ENCODER_CMD_SETUP_PANEL_MODE,
-						   dig->panel_mode);
-		} else if (ASIC_IS_DCE4(rdev)) {
-			/* disable the transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-			/* setup and enable the encoder */
-			atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
-
-			/* enable the transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-		} else {
-			/* disable the encoder and transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-			atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0);
-
-			/* setup and enable the encoder and transmitter */
-			atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-		}
+		/* handled in dpms */
 		break;
 	case ENCODER_OBJECT_ID_INTERNAL_DDI:
 	case ENCODER_OBJECT_ID_INTERNAL_DVO1:
@@ -1922,14 +1943,6 @@
 		break;
 	}
 
-	if (ext_encoder) {
-		if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev))
-			atombios_external_encoder_setup(encoder, ext_encoder,
-							EXTERNAL_ENCODER_ACTION_V3_ENCODER_SETUP);
-		else
-			atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE);
-	}
-
 	atombios_apply_encoder_quirks(encoder, adjusted_mode);
 
 	if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_HDMI) {
@@ -2116,7 +2129,6 @@
 	}
 
 	radeon_atom_output_lock(encoder, true);
-	radeon_atom_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
 
 	if (connector) {
 		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
@@ -2137,6 +2149,7 @@
 
 static void radeon_atom_encoder_commit(struct drm_encoder *encoder)
 {
+	/* need to call this here as we need the crtc set up */
 	radeon_atom_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
 	radeon_atom_output_lock(encoder, false);
 }
@@ -2177,14 +2190,7 @@
 	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
 	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
-		if (ASIC_IS_DCE4(rdev))
-			/* disable the transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-		else {
-			/* disable the encoder and transmitter */
-			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0);
-			atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0);
-		}
+		/* handled in dpms */
 		break;
 	case ENCODER_OBJECT_ID_INTERNAL_DDI:
 	case ENCODER_OBJECT_ID_INTERNAL_DVO1:
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 3dab49c..f37676d 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -47,18 +47,23 @@
 	u32			npipes;
 	/* value we track */
 	u32			sq_config;
+	u32			log_nsamples;
 	u32			nsamples;
 	u32			cb_color_base_last[8];
 	struct radeon_bo	*cb_color_bo[8];
 	u64			cb_color_bo_mc[8];
-	u32			cb_color_bo_offset[8];
-	struct radeon_bo	*cb_color_frag_bo[8]; /* unused */
-	struct radeon_bo	*cb_color_tile_bo[8]; /* unused */
+	u64			cb_color_bo_offset[8];
+	struct radeon_bo	*cb_color_frag_bo[8];
+	u64			cb_color_frag_offset[8];
+	struct radeon_bo	*cb_color_tile_bo[8];
+	u64			cb_color_tile_offset[8];
+	u32			cb_color_mask[8];
 	u32			cb_color_info[8];
 	u32			cb_color_view[8];
 	u32			cb_color_size_idx[8]; /* unused */
 	u32			cb_target_mask;
 	u32			cb_shader_mask;  /* unused */
+	bool			is_resolve;
 	u32			cb_color_size[8];
 	u32			vgt_strmout_en;
 	u32			vgt_strmout_buffer_en;
@@ -311,7 +316,15 @@
 		track->cb_color_bo[i] = NULL;
 		track->cb_color_bo_offset[i] = 0xFFFFFFFF;
 		track->cb_color_bo_mc[i] = 0xFFFFFFFF;
+		track->cb_color_frag_bo[i] = NULL;
+		track->cb_color_frag_offset[i] = 0xFFFFFFFF;
+		track->cb_color_tile_bo[i] = NULL;
+		track->cb_color_tile_offset[i] = 0xFFFFFFFF;
+		track->cb_color_mask[i] = 0xFFFFFFFF;
 	}
+	track->is_resolve = false;
+	track->nsamples = 16;
+	track->log_nsamples = 4;
 	track->cb_target_mask = 0xFFFFFFFF;
 	track->cb_shader_mask = 0xFFFFFFFF;
 	track->cb_dirty = true;
@@ -348,11 +361,9 @@
 	volatile u32 *ib = p->ib.ptr;
 	unsigned array_mode;
 	u32 format;
+	/* When resolve is used, the second colorbuffer has always 1 sample. */
+	unsigned nsamples = track->is_resolve && i == 1 ? 1 : track->nsamples;
 
-	if (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
-		dev_warn(p->dev, "FMASK or CMASK buffer are not supported by this kernel\n");
-		return -EINVAL;
-	}
 	size = radeon_bo_size(track->cb_color_bo[i]) - track->cb_color_bo_offset[i];
 	format = G_0280A0_FORMAT(track->cb_color_info[i]);
 	if (!r600_fmt_is_valid_color(format)) {
@@ -375,7 +386,7 @@
 	array_check.group_size = track->group_size;
 	array_check.nbanks = track->nbanks;
 	array_check.npipes = track->npipes;
-	array_check.nsamples = track->nsamples;
+	array_check.nsamples = nsamples;
 	array_check.blocksize = r600_fmt_get_blocksize(format);
 	if (r600_get_array_mode_alignment(&array_check,
 					  &pitch_align, &height_align, &depth_align, &base_align)) {
@@ -420,7 +431,8 @@
 	}
 
 	/* check offset */
-	tmp = r600_fmt_get_nblocksy(format, height) * r600_fmt_get_nblocksx(format, pitch) * r600_fmt_get_blocksize(format);
+	tmp = r600_fmt_get_nblocksy(format, height) * r600_fmt_get_nblocksx(format, pitch) *
+	      r600_fmt_get_blocksize(format) * nsamples;
 	switch (array_mode) {
 	default:
 	case V_0280A0_ARRAY_LINEAR_GENERAL:
@@ -441,7 +453,7 @@
 			 * broken userspace.
 			 */
 		} else {
-			dev_warn(p->dev, "%s offset[%d] %d %d %d %lu too big (%d %d) (%d %d %d)\n",
+			dev_warn(p->dev, "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n",
 				 __func__, i, array_mode,
 				 track->cb_color_bo_offset[i], tmp,
 				 radeon_bo_size(track->cb_color_bo[i]),
@@ -458,6 +470,51 @@
 	tmp = S_028060_PITCH_TILE_MAX((pitch / 8) - 1) |
 		S_028060_SLICE_TILE_MAX(slice_tile_max - 1);
 	ib[track->cb_color_size_idx[i]] = tmp;
+
+	/* FMASK/CMASK */
+	switch (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
+	case V_0280A0_TILE_DISABLE:
+		break;
+	case V_0280A0_FRAG_ENABLE:
+		if (track->nsamples > 1) {
+			uint32_t tile_max = G_028100_FMASK_TILE_MAX(track->cb_color_mask[i]);
+			/* the tile size is 8x8, but the size is in units of bits.
+			 * for bytes, do just * 8. */
+			uint32_t bytes = track->nsamples * track->log_nsamples * 8 * (tile_max + 1);
+
+			if (bytes + track->cb_color_frag_offset[i] >
+			    radeon_bo_size(track->cb_color_frag_bo[i])) {
+				dev_warn(p->dev, "%s FMASK_TILE_MAX too large "
+					 "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+					 __func__, tile_max, bytes,
+					 track->cb_color_frag_offset[i],
+					 radeon_bo_size(track->cb_color_frag_bo[i]));
+				return -EINVAL;
+			}
+		}
+		/* fall through */
+	case V_0280A0_CLEAR_ENABLE:
+	{
+		uint32_t block_max = G_028100_CMASK_BLOCK_MAX(track->cb_color_mask[i]);
+		/* One block = 128x128 pixels, one 8x8 tile has 4 bits..
+		 * (128*128) / (8*8) / 2 = 128 bytes per block. */
+		uint32_t bytes = (block_max + 1) * 128;
+
+		if (bytes + track->cb_color_tile_offset[i] >
+		    radeon_bo_size(track->cb_color_tile_bo[i])) {
+			dev_warn(p->dev, "%s CMASK_BLOCK_MAX too large "
+				 "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+				 __func__, block_max, bytes,
+				 track->cb_color_tile_offset[i],
+				 radeon_bo_size(track->cb_color_tile_bo[i]));
+			return -EINVAL;
+		}
+		break;
+	}
+	default:
+		dev_warn(p->dev, "%s invalid tile mode\n", __func__);
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -566,7 +623,7 @@
 
 		ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
 		nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
-		tmp = ntiles * bpe * 64 * nviews;
+		tmp = ntiles * bpe * 64 * nviews * track->nsamples;
 		if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
 			dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
 					array_mode,
@@ -746,6 +803,12 @@
 	 */
 	if (track->cb_dirty) {
 		tmp = track->cb_target_mask;
+
+		/* We must check both colorbuffers for RESOLVE. */
+		if (track->is_resolve) {
+			tmp |= 0xff;
+		}
+
 		for (i = 0; i < 8; i++) {
 			if ((tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
@@ -1231,9 +1294,15 @@
 		break;
 	case R_028C04_PA_SC_AA_CONFIG:
 		tmp = G_028C04_MSAA_NUM_SAMPLES(radeon_get_ib_value(p, idx));
+		track->log_nsamples = tmp;
 		track->nsamples = 1 << tmp;
 		track->cb_dirty = true;
 		break;
+	case R_028808_CB_COLOR_CONTROL:
+		tmp = G_028808_SPECIAL_OP(radeon_get_ib_value(p, idx));
+		track->is_resolve = tmp == V_028808_SPECIAL_RESOLVE_BOX;
+		track->cb_dirty = true;
+		break;
 	case R_0280A0_CB_COLOR0_INFO:
 	case R_0280A4_CB_COLOR1_INFO:
 	case R_0280A8_CB_COLOR2_INFO:
@@ -1312,16 +1381,21 @@
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] = track->cb_color_base_last[tmp];
 			track->cb_color_frag_bo[tmp] = track->cb_color_bo[tmp];
+			track->cb_color_frag_offset[tmp] = track->cb_color_bo_offset[tmp];
+			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 			track->cb_color_frag_bo[tmp] = reloc->robj;
+			track->cb_color_frag_offset[tmp] = (u64)ib[idx] << 8;
+			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		}
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
 		}
 		break;
 	case R_0280C0_CB_COLOR0_TILE:
@@ -1338,16 +1412,35 @@
 				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] = track->cb_color_base_last[tmp];
 			track->cb_color_tile_bo[tmp] = track->cb_color_bo[tmp];
+			track->cb_color_tile_offset[tmp] = track->cb_color_bo_offset[tmp];
+			ib[idx] = track->cb_color_base_last[tmp];
 		} else {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
 				return -EINVAL;
 			}
-			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
 			track->cb_color_tile_bo[tmp] = reloc->robj;
+			track->cb_color_tile_offset[tmp] = (u64)ib[idx] << 8;
+			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		}
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
+		}
+		break;
+	case R_028100_CB_COLOR0_MASK:
+	case R_028104_CB_COLOR1_MASK:
+	case R_028108_CB_COLOR2_MASK:
+	case R_02810C_CB_COLOR3_MASK:
+	case R_028110_CB_COLOR4_MASK:
+	case R_028114_CB_COLOR5_MASK:
+	case R_028118_CB_COLOR6_MASK:
+	case R_02811C_CB_COLOR7_MASK:
+		tmp = (reg - R_028100_CB_COLOR0_MASK) / 4;
+		track->cb_color_mask[tmp] = radeon_get_ib_value(p, idx);
+		if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) {
+			track->cb_dirty = true;
 		}
 		break;
 	case CB_COLOR0_BASE:
@@ -1492,7 +1585,7 @@
 }
 
 static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned llevel,
-			      unsigned w0, unsigned h0, unsigned d0, unsigned format,
+			      unsigned w0, unsigned h0, unsigned d0, unsigned nsamples, unsigned format,
 			      unsigned block_align, unsigned height_align, unsigned base_align,
 			      unsigned *l0_size, unsigned *mipmap_size)
 {
@@ -1520,7 +1613,7 @@
 
 		depth = r600_mip_minify(d0, i);
 
-		size = nbx * nby * blocksize;
+		size = nbx * nby * blocksize * nsamples;
 		if (nfaces)
 			size *= nfaces;
 		else
@@ -1672,7 +1765,7 @@
 
 		nfaces = larray - barray + 1;
 	}
-	r600_texture_size(nfaces, blevel, llevel, w0, h0, d0, format,
+	r600_texture_size(nfaces, blevel, llevel, w0, h0, d0, array_check.nsamples, format,
 			  pitch_align, height_align, base_align,
 			  &l0_size, &mipmap_size);
 	/* using get ib will give us the offset into the texture bo */
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index fd328f4..fa6f370 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -66,6 +66,14 @@
 #define	CC_RB_BACKEND_DISABLE				0x98F4
 #define		BACKEND_DISABLE(x)				((x) << 16)
 
+#define R_028808_CB_COLOR_CONTROL			0x28808
+#define   S_028808_SPECIAL_OP(x)                       (((x) & 0x7) << 4)
+#define   G_028808_SPECIAL_OP(x)                       (((x) >> 4) & 0x7)
+#define   C_028808_SPECIAL_OP                          0xFFFFFF8F
+#define     V_028808_SPECIAL_NORMAL                     0x00
+#define     V_028808_SPECIAL_DISABLE                    0x01
+#define     V_028808_SPECIAL_RESOLVE_BOX                0x07
+
 #define	CB_COLOR0_BASE					0x28040
 #define	CB_COLOR1_BASE					0x28044
 #define	CB_COLOR2_BASE					0x28048
@@ -92,6 +100,20 @@
 #define R_028094_CB_COLOR5_VIEW                      0x028094
 #define R_028098_CB_COLOR6_VIEW                      0x028098
 #define R_02809C_CB_COLOR7_VIEW                      0x02809C
+#define R_028100_CB_COLOR0_MASK                      0x028100
+#define   S_028100_CMASK_BLOCK_MAX(x)                  (((x) & 0xFFF) << 0)
+#define   G_028100_CMASK_BLOCK_MAX(x)                  (((x) >> 0) & 0xFFF)
+#define   C_028100_CMASK_BLOCK_MAX                     0xFFFFF000
+#define   S_028100_FMASK_TILE_MAX(x)                   (((x) & 0xFFFFF) << 12)
+#define   G_028100_FMASK_TILE_MAX(x)                   (((x) >> 12) & 0xFFFFF)
+#define   C_028100_FMASK_TILE_MAX                      0x00000FFF
+#define R_028104_CB_COLOR1_MASK                      0x028104
+#define R_028108_CB_COLOR2_MASK                      0x028108
+#define R_02810C_CB_COLOR3_MASK                      0x02810C
+#define R_028110_CB_COLOR4_MASK                      0x028110
+#define R_028114_CB_COLOR5_MASK                      0x028114
+#define R_028118_CB_COLOR6_MASK                      0x028118
+#define R_02811C_CB_COLOR7_MASK                      0x02811C
 #define CB_COLOR0_INFO                                  0x280a0
 #	define CB_FORMAT(x)				((x) << 2)
 #       define CB_ARRAY_MODE(x)                         ((x) << 8)
@@ -1400,6 +1422,9 @@
 #define   S_0280A0_TILE_MODE(x)                        (((x) & 0x3) << 18)
 #define   G_0280A0_TILE_MODE(x)                        (((x) >> 18) & 0x3)
 #define   C_0280A0_TILE_MODE                           0xFFF3FFFF
+#define     V_0280A0_TILE_DISABLE			0
+#define     V_0280A0_CLEAR_ENABLE			1
+#define     V_0280A0_FRAG_ENABLE			2
 #define   S_0280A0_BLEND_CLAMP(x)                      (((x) & 0x1) << 20)
 #define   G_0280A0_BLEND_CLAMP(x)                      (((x) >> 20) & 0x1)
 #define   C_0280A0_BLEND_CLAMP                         0xFFEFFFFF
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 9930419..59a1531 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -142,21 +142,6 @@
 /*
  * BIOS.
  */
-#define ATRM_BIOS_PAGE 4096
-
-#if defined(CONFIG_VGA_SWITCHEROO)
-bool radeon_atrm_supported(struct pci_dev *pdev);
-int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len);
-#else
-static inline bool radeon_atrm_supported(struct pci_dev *pdev)
-{
-	return false;
-}
-
-static inline int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len){
-	return -EINVAL;
-}
-#endif
 bool radeon_get_bios(struct radeon_device *rdev);
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index f9c21f9..d67d4f3 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -452,7 +452,7 @@
 	}
 
 	/* Fujitsu D3003-S2 board lists DVI-I as DVI-D and VGA */
-	if ((dev->pdev->device == 0x9802) &&
+	if (((dev->pdev->device == 0x9802) || (dev->pdev->device == 0x9806)) &&
 	    (dev->pdev->subsystem_vendor == 0x1734) &&
 	    (dev->pdev->subsystem_device == 0x11bd)) {
 		if (*connector_type == DRM_MODE_CONNECTOR_VGA) {
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 98724fc..2a2cf0b 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -30,57 +30,8 @@
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
 	acpi_handle atpx_handle;
-	acpi_handle atrm_handle;
 } radeon_atpx_priv;
 
-/* retrieve the ROM in 4k blocks */
-static int radeon_atrm_call(acpi_handle atrm_handle, uint8_t *bios,
-			    int offset, int len)
-{
-	acpi_status status;
-	union acpi_object atrm_arg_elements[2], *obj;
-	struct acpi_object_list atrm_arg;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
-
-	atrm_arg.count = 2;
-	atrm_arg.pointer = &atrm_arg_elements[0];
-
-	atrm_arg_elements[0].type = ACPI_TYPE_INTEGER;
-	atrm_arg_elements[0].integer.value = offset;
-
-	atrm_arg_elements[1].type = ACPI_TYPE_INTEGER;
-	atrm_arg_elements[1].integer.value = len;
-
-	status = acpi_evaluate_object(atrm_handle, NULL, &atrm_arg, &buffer);
-	if (ACPI_FAILURE(status)) {
-		printk("failed to evaluate ATRM got %s\n", acpi_format_exception(status));
-		return -ENODEV;
-	}
-
-	obj = (union acpi_object *)buffer.pointer;
-	memcpy(bios+offset, obj->buffer.pointer, obj->buffer.length);
-	len = obj->buffer.length;
-	kfree(buffer.pointer);
-	return len;
-}
-
-bool radeon_atrm_supported(struct pci_dev *pdev)
-{
-	/* get the discrete ROM only via ATRM */
-	if (!radeon_atpx_priv.atpx_detected)
-		return false;
-
-	if (radeon_atpx_priv.dhandle == DEVICE_ACPI_HANDLE(&pdev->dev))
-		return false;
-	return true;
-}
-
-
-int radeon_atrm_get_bios_chunk(uint8_t *bios, int offset, int len)
-{
-	return radeon_atrm_call(radeon_atpx_priv.atrm_handle, bios, offset, len);
-}
-
 static int radeon_atpx_get_version(acpi_handle handle)
 {
 	acpi_status status;
@@ -198,7 +149,7 @@
 
 static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 {
-	acpi_handle dhandle, atpx_handle, atrm_handle;
+	acpi_handle dhandle, atpx_handle;
 	acpi_status status;
 
 	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
@@ -209,13 +160,8 @@
 	if (ACPI_FAILURE(status))
 		return false;
 
-	status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
-	if (ACPI_FAILURE(status))
-		return false;
-
 	radeon_atpx_priv.dhandle = dhandle;
 	radeon_atpx_priv.atpx_handle = atpx_handle;
-	radeon_atpx_priv.atrm_handle = atrm_handle;
 	return true;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 501f488..d306cc8 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -32,6 +32,7 @@
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
+#include <linux/acpi.h>
 /*
  * BIOS.
  */
@@ -98,16 +99,81 @@
 	return true;
 }
 
+#ifdef CONFIG_ACPI
 /* ATRM is used to get the BIOS on the discrete cards in
  * dual-gpu systems.
  */
+/* retrieve the ROM in 4k blocks */
+#define ATRM_BIOS_PAGE 4096
+/**
+ * radeon_atrm_call - fetch a chunk of the vbios
+ *
+ * @atrm_handle: acpi ATRM handle
+ * @bios: vbios image pointer
+ * @offset: offset of vbios image data to fetch
+ * @len: length of vbios image data to fetch
+ *
+ * Executes ATRM to fetch a chunk of the discrete
+ * vbios image on PX systems (all asics).
+ * Returns the length of the buffer fetched.
+ */
+static int radeon_atrm_call(acpi_handle atrm_handle, uint8_t *bios,
+			    int offset, int len)
+{
+	acpi_status status;
+	union acpi_object atrm_arg_elements[2], *obj;
+	struct acpi_object_list atrm_arg;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
+
+	atrm_arg.count = 2;
+	atrm_arg.pointer = &atrm_arg_elements[0];
+
+	atrm_arg_elements[0].type = ACPI_TYPE_INTEGER;
+	atrm_arg_elements[0].integer.value = offset;
+
+	atrm_arg_elements[1].type = ACPI_TYPE_INTEGER;
+	atrm_arg_elements[1].integer.value = len;
+
+	status = acpi_evaluate_object(atrm_handle, NULL, &atrm_arg, &buffer);
+	if (ACPI_FAILURE(status)) {
+		printk("failed to evaluate ATRM got %s\n", acpi_format_exception(status));
+		return -ENODEV;
+	}
+
+	obj = (union acpi_object *)buffer.pointer;
+	memcpy(bios+offset, obj->buffer.pointer, obj->buffer.length);
+	len = obj->buffer.length;
+	kfree(buffer.pointer);
+	return len;
+}
+
 static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 {
 	int ret;
 	int size = 256 * 1024;
 	int i;
+	struct pci_dev *pdev = NULL;
+	acpi_handle dhandle, atrm_handle;
+	acpi_status status;
+	bool found = false;
 
-	if (!radeon_atrm_supported(rdev->pdev))
+	/* ATRM is for the discrete card only */
+	if (rdev->flags & RADEON_IS_IGP)
+		return false;
+
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
+		dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+		if (!dhandle)
+			continue;
+
+		status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
+		if (!ACPI_FAILURE(status)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
 		return false;
 
 	rdev->bios = kmalloc(size, GFP_KERNEL);
@@ -117,9 +183,10 @@
 	}
 
 	for (i = 0; i < size / ATRM_BIOS_PAGE; i++) {
-		ret = radeon_atrm_get_bios_chunk(rdev->bios,
-						 (i * ATRM_BIOS_PAGE),
-						 ATRM_BIOS_PAGE);
+		ret = radeon_atrm_call(atrm_handle,
+				       rdev->bios,
+				       (i * ATRM_BIOS_PAGE),
+				       ATRM_BIOS_PAGE);
 		if (ret < ATRM_BIOS_PAGE)
 			break;
 	}
@@ -130,6 +197,12 @@
 	}
 	return true;
 }
+#else
+static inline bool radeon_atrm_get_bios(struct radeon_device *rdev)
+{
+	return false;
+}
+#endif
 
 static bool ni_read_disabled_bios(struct radeon_device *rdev)
 {
@@ -476,6 +549,61 @@
 		return legacy_read_disabled_bios(rdev);
 }
 
+#ifdef CONFIG_ACPI
+static bool radeon_acpi_vfct_bios(struct radeon_device *rdev)
+{
+	bool ret = false;
+	struct acpi_table_header *hdr;
+	acpi_size tbl_size;
+	UEFI_ACPI_VFCT *vfct;
+	GOP_VBIOS_CONTENT *vbios;
+	VFCT_IMAGE_HEADER *vhdr;
+
+	if (!ACPI_SUCCESS(acpi_get_table_with_size("VFCT", 1, &hdr, &tbl_size)))
+		return false;
+	if (tbl_size < sizeof(UEFI_ACPI_VFCT)) {
+		DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n");
+		goto out_unmap;
+	}
+
+	vfct = (UEFI_ACPI_VFCT *)hdr;
+	if (vfct->VBIOSImageOffset + sizeof(VFCT_IMAGE_HEADER) > tbl_size) {
+		DRM_ERROR("ACPI VFCT table present but broken (too short #2)\n");
+		goto out_unmap;
+	}
+
+	vbios = (GOP_VBIOS_CONTENT *)((char *)hdr + vfct->VBIOSImageOffset);
+	vhdr = &vbios->VbiosHeader;
+	DRM_INFO("ACPI VFCT contains a BIOS for %02x:%02x.%d %04x:%04x, size %d\n",
+			vhdr->PCIBus, vhdr->PCIDevice, vhdr->PCIFunction,
+			vhdr->VendorID, vhdr->DeviceID, vhdr->ImageLength);
+
+	if (vhdr->PCIBus != rdev->pdev->bus->number ||
+	    vhdr->PCIDevice != PCI_SLOT(rdev->pdev->devfn) ||
+	    vhdr->PCIFunction != PCI_FUNC(rdev->pdev->devfn) ||
+	    vhdr->VendorID != rdev->pdev->vendor ||
+	    vhdr->DeviceID != rdev->pdev->device) {
+		DRM_INFO("ACPI VFCT table is not for this card\n");
+		goto out_unmap;
+	};
+
+	if (vfct->VBIOSImageOffset + sizeof(VFCT_IMAGE_HEADER) + vhdr->ImageLength > tbl_size) {
+		DRM_ERROR("ACPI VFCT image truncated\n");
+		goto out_unmap;
+	}
+
+	rdev->bios = kmemdup(&vbios->VbiosContent, vhdr->ImageLength, GFP_KERNEL);
+	ret = !!rdev->bios;
+
+out_unmap:
+	return ret;
+}
+#else
+static inline bool radeon_acpi_vfct_bios(struct radeon_device *rdev)
+{
+	return false;
+}
+#endif
 
 bool radeon_get_bios(struct radeon_device *rdev)
 {
@@ -484,6 +612,8 @@
 
 	r = radeon_atrm_get_bios(rdev);
 	if (r == false)
+		r = radeon_acpi_vfct_bios(rdev);
+	if (r == false)
 		r = igp_read_bios_from_vram(rdev);
 	if (r == false)
 		r = radeon_read_bios(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index d2e2438..7a3daeb 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1051,7 +1051,7 @@
 	if (rdev->flags & RADEON_IS_AGP)
 		rdev->need_dma32 = true;
 	if ((rdev->flags & RADEON_IS_PCI) &&
-	    (rdev->family < CHIP_RS400))
+	    (rdev->family <= CHIP_RS740))
 		rdev->need_dma32 = true;
 
 	dma_bits = rdev->need_dma32 ? 32 : 40;
@@ -1346,12 +1346,15 @@
 		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
 			radeon_ring_restore(rdev, &rdev->ring[i],
 					    ring_sizes[i], ring_data[i]);
+			ring_sizes[i] = 0;
+			ring_data[i] = NULL;
 		}
 
 		r = radeon_ib_ring_tests(rdev);
 		if (r) {
 			dev_err(rdev->dev, "ib ring test failed (%d).\n", r);
 			if (saved) {
+				saved = false;
 				radeon_suspend(rdev);
 				goto retry;
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d7269f4..8c593ea 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -62,9 +62,11 @@
  *   2.18.0 - r600-eg: allow "invalid" DB formats
  *   2.19.0 - r600-eg: MSAA textures
  *   2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query
+ *   2.21.0 - r600-r700: FMASK and CMASK
+ *   2.22.0 - r600 only: RESOLVE_BOX allowed
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	20
+#define KMS_DRIVER_MINOR	22
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 7b737b9..2a59375 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -131,7 +131,7 @@
  */
 void radeon_fence_process(struct radeon_device *rdev, int ring)
 {
-	uint64_t seq, last_seq;
+	uint64_t seq, last_seq, last_emitted;
 	unsigned count_loop = 0;
 	bool wake = false;
 
@@ -158,13 +158,15 @@
 	 */
 	last_seq = atomic64_read(&rdev->fence_drv[ring].last_seq);
 	do {
+		last_emitted = rdev->fence_drv[ring].sync_seq[ring];
 		seq = radeon_fence_read(rdev, ring);
 		seq |= last_seq & 0xffffffff00000000LL;
 		if (seq < last_seq) {
-			seq += 0x100000000LL;
+			seq &= 0xffffffff;
+			seq |= last_emitted & 0xffffffff00000000LL;
 		}
 
-		if (seq == last_seq) {
+		if (seq <= last_seq || seq > last_emitted) {
 			break;
 		}
 		/* If we loop over we don't want to return without
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 1cb014b..9024e72 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -132,6 +132,7 @@
 	acc_size = ttm_bo_dma_acc_size(&rdev->mman.bdev, size,
 				       sizeof(struct radeon_bo));
 
+retry:
 	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
@@ -145,8 +146,6 @@
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
 	INIT_LIST_HEAD(&bo->va);
-
-retry:
 	radeon_ttm_placement_from_domain(bo, domain);
 	/* Kernel allocation are uninterruptible */
 	down_read(&rdev->pm.mclk_lock);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index ec79b37..43c431a 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -706,6 +706,7 @@
 	if (radeon_debugfs_ring_init(rdev, ring)) {
 		DRM_ERROR("Failed to register debugfs file for rings !\n");
 	}
+	radeon_ring_lockup_update(ring);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index 5e659b0..20bfbda 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -744,15 +744,6 @@
 0x00028C38 CB_CLRCMP_DST
 0x00028C3C CB_CLRCMP_MSK
 0x00028C34 CB_CLRCMP_SRC
-0x00028100 CB_COLOR0_MASK
-0x00028104 CB_COLOR1_MASK
-0x00028108 CB_COLOR2_MASK
-0x0002810C CB_COLOR3_MASK
-0x00028110 CB_COLOR4_MASK
-0x00028114 CB_COLOR5_MASK
-0x00028118 CB_COLOR6_MASK
-0x0002811C CB_COLOR7_MASK
-0x00028808 CB_COLOR_CONTROL
 0x0002842C CB_FOG_BLUE
 0x00028428 CB_FOG_GREEN
 0x00028424 CB_FOG_RED
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index d31d4cc..c5a1643 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -43,6 +43,9 @@
 	.mmap = drm_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index 7f11987..867dc03 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -74,6 +74,9 @@
 	.mmap = drm_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index 90f6b13..a7f4d6b 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -49,6 +49,9 @@
 	.mmap = drm_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/udl/Kconfig b/drivers/gpu/drm/udl/Kconfig
index 0b5e096..56e0bf3 100644
--- a/drivers/gpu/drm/udl/Kconfig
+++ b/drivers/gpu/drm/udl/Kconfig
@@ -1,6 +1,7 @@
 config DRM_UDL
 	tristate "DisplayLink"
 	depends on DRM && EXPERIMENTAL
+	depends on USB_ARCH_HAS_HCD
 	select DRM_USB
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 6e52069..9f84128 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -66,6 +66,9 @@
 	.unlocked_ioctl	= drm_ioctl,
 	.release = drm_release,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index f5dd89e..9159d48 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -354,8 +354,7 @@
 
 static void udl_crtc_disable(struct drm_crtc *crtc)
 {
-
-
+	udl_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
 
 static void udl_crtc_destroy(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index e927b4c..af1b914 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -65,6 +65,9 @@
 	.mmap = drm_mmap,
 	.poll = drm_poll,
 	.fasync = drm_fasync,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 794ff67..b71bcd0 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -12,3 +12,11 @@
 	  This is a KMS enabled DRM driver for the VMware SVGA2
 	  virtual hardware.
 	  The compiled module will be called "vmwgfx.ko".
+
+config DRM_VMWGFX_FBCON
+	depends on DRM_VMWGFX
+	bool "Enable framebuffer console under vmwgfx by default"
+	help
+	   Choose this option if you are shipping a new vmwgfx
+	   userspace driver that supports using the kernel driver.
+
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 4d9edea..ba2c35d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -182,8 +182,9 @@
 	{0x15ad, 0x0405, PCI_ANY_ID, PCI_ANY_ID, 0, 0, VMWGFX_CHIP_SVGAII},
 	{0, 0, 0}
 };
+MODULE_DEVICE_TABLE(pci, vmw_pci_id_list);
 
-static int enable_fbdev;
+static int enable_fbdev = IS_ENABLED(CONFIG_DRM_VMWGFX_FBCON);
 
 static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
 static void vmw_master_init(struct vmw_master *);
@@ -1154,6 +1155,11 @@
 	.open = vmw_driver_open,
 	.preclose = vmw_preclose,
 	.postclose = vmw_postclose,
+
+	.dumb_create = vmw_dumb_create,
+	.dumb_map_offset = vmw_dumb_map_offset,
+	.dumb_destroy = vmw_dumb_destroy,
+
 	.fops = &vmwgfx_driver_fops,
 	.name = VMWGFX_DRIVER_NAME,
 	.desc = VMWGFX_DRIVER_DESC,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index d0f2c07..29c984f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -645,6 +645,16 @@
 int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
 
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args);
+
+int vmw_dumb_map_offset(struct drm_file *file_priv,
+			struct drm_device *dev, uint32_t handle,
+			uint64_t *offset);
+int vmw_dumb_destroy(struct drm_file *file_priv,
+		     struct drm_device *dev,
+		     uint32_t handle);
 /**
  * Overlay control - vmwgfx_overlay.c
  */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 6b0078f..c50724b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1688,15 +1688,19 @@
 	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
 	struct drm_framebuffer *old_fb = crtc->fb;
 	struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(fb);
-	struct drm_file *file_priv = event->base.file_priv;
+	struct drm_file *file_priv ;
 	struct vmw_fence_obj *fence = NULL;
 	struct drm_clip_rect clips;
 	int ret;
 
+	if (event == NULL)
+		return -EINVAL;
+
 	/* require ScreenObject support for page flipping */
 	if (!dev_priv->sou_priv)
 		return -ENOSYS;
 
+	file_priv = event->base.file_priv;
 	if (!vmw_kms_screen_object_flippable(dev_priv, crtc))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 22bf9a2..2c6ffe0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1917,3 +1917,76 @@
 	vmw_resource_unreference(&res);
 	return ret;
 }
+
+
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_master *vmaster = vmw_master(file_priv->master);
+	struct vmw_user_dma_buffer *vmw_user_bo;
+	struct ttm_buffer_object *tmp;
+	int ret;
+
+	args->pitch = args->width * ((args->bpp + 7) / 8);
+	args->size = args->pitch * args->height;
+
+	vmw_user_bo = kzalloc(sizeof(*vmw_user_bo), GFP_KERNEL);
+	if (vmw_user_bo == NULL)
+		return -ENOMEM;
+
+	ret = ttm_read_lock(&vmaster->lock, true);
+	if (ret != 0) {
+		kfree(vmw_user_bo);
+		return ret;
+	}
+
+	ret = vmw_dmabuf_init(dev_priv, &vmw_user_bo->dma, args->size,
+			      &vmw_vram_sys_placement, true,
+			      &vmw_user_dmabuf_destroy);
+	if (ret != 0)
+		goto out_no_dmabuf;
+
+	tmp = ttm_bo_reference(&vmw_user_bo->dma.base);
+	ret = ttm_base_object_init(vmw_fpriv(file_priv)->tfile,
+				   &vmw_user_bo->base,
+				   false,
+				   ttm_buffer_type,
+				   &vmw_user_dmabuf_release, NULL);
+	if (unlikely(ret != 0))
+		goto out_no_base_object;
+
+	args->handle = vmw_user_bo->base.hash.key;
+
+out_no_base_object:
+	ttm_bo_unref(&tmp);
+out_no_dmabuf:
+	ttm_read_unlock(&vmaster->lock);
+	return ret;
+}
+
+int vmw_dumb_map_offset(struct drm_file *file_priv,
+			struct drm_device *dev, uint32_t handle,
+			uint64_t *offset)
+{
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_dma_buffer *out_buf;
+	int ret;
+
+	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf);
+	if (ret != 0)
+		return -EINVAL;
+
+	*offset = out_buf->base.addr_space_offset;
+	vmw_dmabuf_unreference(&out_buf);
+	return 0;
+}
+
+int vmw_dumb_destroy(struct drm_file *file_priv,
+		     struct drm_device *dev,
+		     uint32_t handle)
+{
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 handle, TTM_REF_USAGE);
+}
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index 5b3c7d1..e25cf31 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -70,27 +70,12 @@
 	.clients = LIST_HEAD_INIT(vgasr_priv.clients),
 };
 
-int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler)
+static bool vga_switcheroo_ready(void)
 {
-	mutex_lock(&vgasr_mutex);
-	if (vgasr_priv.handler) {
-		mutex_unlock(&vgasr_mutex);
-		return -EINVAL;
-	}
-
-	vgasr_priv.handler = handler;
-	mutex_unlock(&vgasr_mutex);
-	return 0;
+	/* we're ready if we get two clients + handler */
+	return !vgasr_priv.active &&
+	       vgasr_priv.registered_clients == 2 && vgasr_priv.handler;
 }
-EXPORT_SYMBOL(vga_switcheroo_register_handler);
-
-void vga_switcheroo_unregister_handler(void)
-{
-	mutex_lock(&vgasr_mutex);
-	vgasr_priv.handler = NULL;
-	mutex_unlock(&vgasr_mutex);
-}
-EXPORT_SYMBOL(vga_switcheroo_unregister_handler);
 
 static void vga_switcheroo_enable(void)
 {
@@ -98,7 +83,8 @@
 	struct vga_switcheroo_client *client;
 
 	/* call the handler to init */
-	vgasr_priv.handler->init();
+	if (vgasr_priv.handler->init)
+		vgasr_priv.handler->init();
 
 	list_for_each_entry(client, &vgasr_priv.clients, list) {
 		if (client->id != -1)
@@ -113,6 +99,37 @@
 	vgasr_priv.active = true;
 }
 
+int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler)
+{
+	mutex_lock(&vgasr_mutex);
+	if (vgasr_priv.handler) {
+		mutex_unlock(&vgasr_mutex);
+		return -EINVAL;
+	}
+
+	vgasr_priv.handler = handler;
+	if (vga_switcheroo_ready()) {
+		printk(KERN_INFO "vga_switcheroo: enabled\n");
+		vga_switcheroo_enable();
+	}
+	mutex_unlock(&vgasr_mutex);
+	return 0;
+}
+EXPORT_SYMBOL(vga_switcheroo_register_handler);
+
+void vga_switcheroo_unregister_handler(void)
+{
+	mutex_lock(&vgasr_mutex);
+	vgasr_priv.handler = NULL;
+	if (vgasr_priv.active) {
+		pr_info("vga_switcheroo: disabled\n");
+		vga_switcheroo_debugfs_fini(&vgasr_priv);
+		vgasr_priv.active = false;
+	}
+	mutex_unlock(&vgasr_mutex);
+}
+EXPORT_SYMBOL(vga_switcheroo_unregister_handler);
+
 static int register_client(struct pci_dev *pdev,
 			   const struct vga_switcheroo_client_ops *ops,
 			   int id, bool active)
@@ -134,9 +151,7 @@
 	if (client_is_vga(client))
 		vgasr_priv.registered_clients++;
 
-	/* if we get two clients + handler */
-	if (!vgasr_priv.active &&
-	    vgasr_priv.registered_clients == 2 && vgasr_priv.handler) {
+	if (vga_switcheroo_ready()) {
 		printk(KERN_INFO "vga_switcheroo: enabled\n");
 		vga_switcheroo_enable();
 	}
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 60ea284..8bcd168 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -996,7 +996,8 @@
 	struct hid_driver *hdrv = hid->driver;
 	int ret;
 
-	hid_dump_input(hid, usage, value);
+	if (!list_empty(&hid->debug_list))
+		hid_dump_input(hid, usage, value);
 
 	if (hdrv && hdrv->event && hid_match_usage(hid, usage)) {
 		ret = hdrv->event(hid, field, usage, value);
@@ -1558,7 +1559,9 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
- 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) },
+#if IS_ENABLED(CONFIG_HID_LENOVO_TPKBD)
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) },
+#endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER_2) },
@@ -1624,7 +1627,6 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ORTEK, USB_DEVICE_ID_ORTEK_WKB2000) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PETALYNX, USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_KEYBOARD) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ARVO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKU) },
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 0f9c146..4d524b5 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -439,7 +439,7 @@
 	struct dj_report *dj_report;
 	int retval;
 
-	dj_report = kzalloc(sizeof(dj_report), GFP_KERNEL);
+	dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL);
 	if (!dj_report)
 		return -ENOMEM;
 	dj_report->report_id = REPORT_ID_DJ_SHORT;
@@ -456,7 +456,7 @@
 	struct dj_report *dj_report;
 	int retval;
 
-	dj_report = kzalloc(sizeof(dj_report), GFP_KERNEL);
+	dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL);
 	if (!dj_report)
 		return -ENOMEM;
 	dj_report->report_id = REPORT_ID_DJ_SHORT;
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 903eef3..991e85c 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -70,6 +70,7 @@
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN1, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN2, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index 351d1f4..4ee5789 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -34,6 +34,12 @@
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "SABERTOOTH X58")
 		}
+	}, {
+		/* Old interface reads the same sensor for fan0 and fan1 */
+		.ident = "Asus M5A78L",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "M5A78L")
+		}
 	},
 	{ }
 };
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index faa16f8..0fa356f 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -196,7 +196,7 @@
 	int tjmax;
 };
 
-static struct tjmax __cpuinitconst tjmax_table[] = {
+static const struct tjmax __cpuinitconst tjmax_table[] = {
 	{ "CPU D410", 100000 },
 	{ "CPU D425", 100000 },
 	{ "CPU D510", 100000 },
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 7f3f4a3..6021482 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -69,22 +69,6 @@
 	u16 regs[INA2XX_MAX_REGISTERS];
 };
 
-int ina2xx_read_word(struct i2c_client *client, int reg)
-{
-	int val = i2c_smbus_read_word_data(client, reg);
-	if (unlikely(val < 0)) {
-		dev_dbg(&client->dev,
-			"Failed to read register: %d\n", reg);
-		return val;
-	}
-	return be16_to_cpu(val);
-}
-
-void ina2xx_write_word(struct i2c_client *client, int reg, int data)
-{
-	i2c_smbus_write_word_data(client, reg, cpu_to_be16(data));
-}
-
 static struct ina2xx_data *ina2xx_update_device(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
@@ -102,7 +86,7 @@
 
 		/* Read all registers */
 		for (i = 0; i < data->registers; i++) {
-			int rv = ina2xx_read_word(client, i);
+			int rv = i2c_smbus_read_word_swapped(client, i);
 			if (rv < 0) {
 				ret = ERR_PTR(rv);
 				goto abort;
@@ -279,22 +263,26 @@
 	switch (data->kind) {
 	case ina219:
 		/* device configuration */
-		ina2xx_write_word(client, INA2XX_CONFIG, INA219_CONFIG_DEFAULT);
+		i2c_smbus_write_word_swapped(client, INA2XX_CONFIG,
+					     INA219_CONFIG_DEFAULT);
 
 		/* set current LSB to 1mA, shunt is in uOhms */
 		/* (equation 13 in data