Merge branches 'iommu/fixes', 'x86/vt-d', 'x86/amd', 'arm/smmu', 'arm/tegra' and 'core' into next

Conflicts:
	drivers/iommu/amd_iommu.c
	drivers/iommu/tegra-gart.c
	drivers/iommu/tegra-smmu.c
diff --git a/Documentation/CodeOfConflict b/Documentation/CodeOfConflict
new file mode 100644
index 0000000..1684d0b
--- /dev/null
+++ b/Documentation/CodeOfConflict
@@ -0,0 +1,27 @@
+Code of Conflict
+----------------
+
+The Linux kernel development effort is a very personal process compared
+to "traditional" ways of developing software.  Your code and ideas
+behind it will be carefully reviewed, often resulting in critique and
+criticism.  The review will almost always require improvements to the
+code before it can be included in the kernel.  Know that this happens
+because everyone involved wants to see the best possible solution for
+the overall success of Linux.  This development process has been proven
+to create the most robust operating system kernel ever, and we do not
+want to do anything to cause the quality of submission and eventual
+result to ever decrease.
+
+If however, anyone feels personally abused, threatened, or otherwise
+uncomfortable due to this process, that is not acceptable.  If so,
+please contact the Linux Foundation's Technical Advisory Board at
+<tab@lists.linux-foundation.org>, or the individual members, and they
+will work to resolve the issue to the best of their ability.  For more
+information on who is on the Technical Advisory Board and what their
+role is, please see:
+	http://www.linuxfoundation.org/programs/advisory-councils/tab
+
+As a reviewer of code, please strive to keep things civil and focused on
+the technical issues involved.  We are all humans, and frustrations can
+be high on both sides of the process.  Try to keep in mind the immortal
+words of Bill and Ted, "Be excellent to each other."
diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt
index 71daa35..eb102fb 100644
--- a/Documentation/cgroups/unified-hierarchy.txt
+++ b/Documentation/cgroups/unified-hierarchy.txt
@@ -404,8 +404,8 @@
   be understood as an underflow into the highest possible value, -2 or
   -10M etc. do not work, so it's not consistent.
 
-  memory.low, memory.high, and memory.max will use the string
-  "infinity" to indicate and set the highest possible value.
+  memory.low, memory.high, and memory.max will use the string "max" to
+  indicate and set the highest possible value.
 
 5. Planned Changes
 
diff --git a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
index f4445e5..1e097037 100644
--- a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
+++ b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
@@ -22,6 +22,8 @@
 	- pclkN, clkN: Pairs of parent of input clock and input clock to the
 		devices in this power domain. Maximum of 4 pairs (N = 0 to 3)
 		are supported currently.
+- power-domains: phandle pointing to the parent power domain, for more details
+		 see Documentation/devicetree/bindings/power/power_domain.txt
 
 Node of a device using power domains must have a power-domains property
 defined with a phandle to respective power domain.
diff --git a/Documentation/devicetree/bindings/arm/sti.txt b/Documentation/devicetree/bindings/arm/sti.txt
index d70ec35..8d27f6b 100644
--- a/Documentation/devicetree/bindings/arm/sti.txt
+++ b/Documentation/devicetree/bindings/arm/sti.txt
@@ -13,6 +13,10 @@
 Required root node property:
 compatible = "st,stih407";
 
+Boards with the ST STiH410 SoC shall have the following properties:
+Required root node property:
+compatible = "st,stih410";
+
 Boards with the ST STiH418 SoC shall have the following properties:
 Required root node property:
 compatible = "st,stih418";
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.txt b/Documentation/devicetree/bindings/i2c/i2c-imx.txt
index 52d37fd..ce4311d 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx.txt
@@ -7,6 +7,7 @@
   - "fsl,vf610-i2c" for I2C compatible with the one integrated on Vybrid vf610 SoC
 - reg : Should contain I2C/HS-I2C registers location and length
 - interrupts : Should contain I2C/HS-I2C interrupt
+- clocks : Should contain the I2C/HS-I2C clock specifier
 
 Optional properties:
 - clock-frequency : Constains desired I2C/HS-I2C bus clock frequency in Hz.
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
index 33df393..8db3238 100644
--- a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
+++ b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
@@ -27,6 +27,8 @@
 - amd,serdes-cdr-rate: CDR rate speed selection
 - amd,serdes-pq-skew: PQ (data sampling) skew
 - amd,serdes-tx-amp: TX amplitude boost
+- amd,serdes-dfe-tap-config: DFE taps available to run
+- amd,serdes-dfe-tap-enable: DFE taps to enable
 
 Example:
 	xgbe_phy@e1240800 {
@@ -41,4 +43,6 @@
 		amd,serdes-cdr-rate = <2>, <2>, <7>;
 		amd,serdes-pq-skew = <10>, <10>, <30>;
 		amd,serdes-tx-amp = <15>, <15>, <10>;
+		amd,serdes-dfe-tap-config = <3>, <3>, <1>;
+		amd,serdes-dfe-tap-enable = <0>, <0>, <127>;
 	};
diff --git a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt
index cfcc527..6151999 100644
--- a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt
+++ b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt
@@ -4,7 +4,10 @@
 APM X-Gene SoC.
 
 Required properties for all the ethernet interfaces:
-- compatible: Should be "apm,xgene-enet"
+- compatible: Should state binding information from the following list,
+  - "apm,xgene-enet":    RGMII based 1G interface
+  - "apm,xgene1-sgenet": SGMII based 1G interface
+  - "apm,xgene1-xgenet": XFI based 10G interface
 - reg: Address and length of the register set for the device. It contains the
   information of registers in the same order as described by reg-names
 - reg-names: Should contain the register set names
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 98c1667..0f8ed37 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -19,6 +19,16 @@
    providing multiple PM domains (e.g. power controllers), but can be any value
    as specified by device tree binding documentation of particular provider.
 
+Optional properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+                   the power controller specified by phandle.
+   Some power domains might be powered from another power domain (or have
+   other hardware specific dependencies). For representing such dependency
+   a standard PM domain consumer binding is used. When provided, all domains
+   created by the given provider should be subdomains of the domain
+   specified by this binding. More details about power domain specifier are
+   available in the next section.
+
 Example:
 
 	power: power-controller@12340000 {
@@ -30,6 +40,25 @@
 The node above defines a power controller that is a PM domain provider and
 expects one cell as its phandle argument.
 
+Example 2:
+
+	parent: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12340000 0x1000>;
+		#power-domain-cells = <1>;
+	};
+
+	child: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12341000 0x1000>;
+		power-domains = <&parent 0>;
+		#power-domain-cells = <1>;
+	};
+
+The nodes above define two power controllers: 'parent' and 'child'.
+Domains created by the 'child' power controller are subdomains of '0' power
+domain provided by the 'parent' power controller.
+
 ==PM domain consumers==
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/serial/of-serial.txt b/Documentation/devicetree/bindings/serial/8250.txt
similarity index 100%
rename from Documentation/devicetree/bindings/serial/of-serial.txt
rename to Documentation/devicetree/bindings/serial/8250.txt
diff --git a/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt b/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt
new file mode 100644
index 0000000..ebcbb62
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt
@@ -0,0 +1,19 @@
+ETRAX FS UART
+
+Required properties:
+- compatible : "axis,etraxfs-uart"
+- reg: offset and length of the register set for the device.
+- interrupts: device interrupt
+
+Optional properties:
+- {dtr,dsr,ri,cd}-gpios: specify a GPIO for DTR/DSR/RI/CD
+  line respectively.
+
+Example:
+
+serial@b00260000 {
+	compatible = "axis,etraxfs-uart";
+	reg = <0xb0026000 0x1000>;
+	interrupts = <68>;
+	status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt
index 7f76214..289c40e 100644
--- a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt
+++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt
@@ -21,6 +21,18 @@
 - reg-io-width : the size (in bytes) of the IO accesses that should be
   performed on the device.  If this property is not present then single byte
   accesses are used.
+- dcd-override : Override the DCD modem status signal. This signal will always
+  be reported as active instead of being obtained from the modem status
+  register. Define this if your serial port does not use this pin.
+- dsr-override : Override the DTS modem status signal. This signal will always
+  be reported as active instead of being obtained from the modem status
+  register. Define this if your serial port does not use this pin.
+- cts-override : Override the CTS modem status signal. This signal will always
+  be reported as active instead of being obtained from the modem status
+  register. Define this if your serial port does not use this pin.
+- ri-override : Override the RI modem status signal. This signal will always be
+  reported as inactive instead of being obtained from the modem status register.
+  Define this if your serial port does not use this pin.
 
 Example:
 
@@ -31,6 +43,10 @@
 		interrupts = <10>;
 		reg-shift = <2>;
 		reg-io-width = <4>;
+		dcd-override;
+		dsr-override;
+		cts-override;
+		ri-override;
 	};
 
 Example with one clock:
diff --git a/Documentation/devicetree/bindings/submitting-patches.txt b/Documentation/devicetree/bindings/submitting-patches.txt
index 56742bc..7d44eae 100644
--- a/Documentation/devicetree/bindings/submitting-patches.txt
+++ b/Documentation/devicetree/bindings/submitting-patches.txt
@@ -12,6 +12,9 @@
 
        devicetree@vger.kernel.org
 
+     and Cc: the DT maintainers. Use scripts/get_maintainer.pl to identify
+     all of the DT maintainers.
+
   3) The Documentation/ portion of the patch should come in the series before
      the code implementing the binding.
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 389ca13..fae26d0 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -20,6 +20,7 @@
 ams	AMS AG
 amstaos	AMS-Taos Inc.
 apm	Applied Micro Circuits Corporation (APM)
+arasan	Arasan Chip Systems
 arm	ARM Ltd.
 armadeus	ARMadeus Systems SARL
 asahi-kasei	Asahi Kasei Corp.
@@ -27,6 +28,7 @@
 auo	AU Optronics Corporation
 avago	Avago Technologies
 avic	Shanghai AVIC Optoelectronics Co., Ltd.
+axis	Axis Communications AB
 bosch	Bosch Sensortec GmbH
 brcm	Broadcom Corporation
 buffalo	Buffalo, Inc.
diff --git a/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt b/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt
index f90e294..a4d8697 100644
--- a/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt
@@ -26,6 +26,11 @@
 - atmel,disable : Should be present if you want to disable the watchdog.
 - atmel,idle-halt : Should be present if you want to stop the watchdog when
 	entering idle state.
+	CAUTION: This property should be used with care, it actually makes the
+	watchdog not counting when the CPU is in idle state, therefore the
+	watchdog reset time depends on mean CPU usage and will not reset at all
+	if the CPU stop working while it is in idle state, which is probably
+	not what you want.
 - atmel,dbg-halt : Should be present if you want to stop the watchdog when
 	entering debug state.
 
diff --git a/Documentation/filesystems/dlmfs.txt b/Documentation/filesystems/dlmfs.txt
index 1b528b2..fcf4d50 100644
--- a/Documentation/filesystems/dlmfs.txt
+++ b/Documentation/filesystems/dlmfs.txt
@@ -5,8 +5,8 @@
 
 dlmfs is built with OCFS2 as it requires most of its infrastructure.
 
-Project web page:    http://oss.oracle.com/projects/ocfs2
-Tools web page:      http://oss.oracle.com/projects/ocfs2-tools
+Project web page:    http://ocfs2.wiki.kernel.org
+Tools web page:      https://github.com/markfasheh/ocfs2-tools
 OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/
 
 All code copyright 2005 Oracle except when otherwise noted.
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index 28f8c08..4c49e54 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -8,8 +8,8 @@
 You'll want to install the ocfs2-tools package in order to at least
 get "mount.ocfs2" and "ocfs2_hb_ctl".
 
-Project web page:    http://oss.oracle.com/projects/ocfs2
-Tools web page:      http://oss.oracle.com/projects/ocfs2-tools
+Project web page:    http://ocfs2.wiki.kernel.org
+Tools git tree:      https://github.com/markfasheh/ocfs2-tools
 OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/
 
 All code copyright 2005 Oracle except when otherwise noted.
diff --git a/Documentation/power/suspend-and-interrupts.txt b/Documentation/power/suspend-and-interrupts.txt
index 2f9c5a5..8afb29a 100644
--- a/Documentation/power/suspend-and-interrupts.txt
+++ b/Documentation/power/suspend-and-interrupts.txt
@@ -40,8 +40,10 @@
 
 The IRQF_NO_SUSPEND flag is used to indicate that to the IRQ subsystem when
 requesting a special-purpose interrupt.  It causes suspend_device_irqs() to
-leave the corresponding IRQ enabled so as to allow the interrupt to work all
-the time as expected.
+leave the corresponding IRQ enabled so as to allow the interrupt to work as
+expected during the suspend-resume cycle, but does not guarantee that the
+interrupt will wake the system from a suspended state -- for such cases it is
+necessary to use enable_irq_wake().
 
 Note that the IRQF_NO_SUSPEND flag affects the entire IRQ and not just one
 user of it.  Thus, if the IRQ is shared, all of the interrupt handlers installed
@@ -110,8 +112,9 @@
 IRQF_NO_SUSPEND and enable_irq_wake()
 -------------------------------------
 
-There are no valid reasons to use both enable_irq_wake() and the IRQF_NO_SUSPEND
-flag on the same IRQ.
+There are very few valid reasons to use both enable_irq_wake() and the
+IRQF_NO_SUSPEND flag on the same IRQ, and it is never valid to use both for the
+same device.
 
 First of all, if the IRQ is not shared, the rules for handling IRQF_NO_SUSPEND
 interrupts (interrupt handlers are invoked after suspend_device_irqs()) are
@@ -120,4 +123,13 @@
 
 Second, both enable_irq_wake() and IRQF_NO_SUSPEND apply to entire IRQs and not
 to individual interrupt handlers, so sharing an IRQ between a system wakeup
-interrupt source and an IRQF_NO_SUSPEND interrupt source does not make sense.
+interrupt source and an IRQF_NO_SUSPEND interrupt source does not generally
+make sense.
+
+In rare cases an IRQ can be shared between a wakeup device driver and an
+IRQF_NO_SUSPEND user. In order for this to be safe, the wakeup device driver
+must be able to discern spurious IRQs from genuine wakeup events (signalling
+the latter to the core with pm_system_wakeup()), must use enable_irq_wake() to
+ensure that the IRQ will function as a wakeup source, and must request the IRQ
+with IRQF_COND_SUSPEND to tell the core that it meets these requirements. If
+these requirements are not met, it is not valid to use IRQF_COND_SUSPEND.
diff --git a/MAINTAINERS b/MAINTAINERS
index ddc5a8c..1de6afa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1030,6 +1030,16 @@
 F:	arch/arm/boot/dts/imx*
 F:	arch/arm/configs/imx*_defconfig
 
+ARM/FREESCALE VYBRID ARM ARCHITECTURE
+M:	Shawn Guo <shawn.guo@linaro.org>
+M:	Sascha Hauer <kernel@pengutronix.de>
+R:	Stefan Agner <stefan@agner.ch>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
+F:	arch/arm/mach-imx/*vf610*
+F:	arch/arm/boot/dts/vf*
+
 ARM/GLOMATION GESBC9312SX MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1176,7 +1186,7 @@
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-mvebu/
-F:	drivers/rtc/armada38x-rtc
+F:	drivers/rtc/rtc-armada38x.c
 
 ARM/Marvell Berlin SoC support
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
@@ -1188,6 +1198,7 @@
 M:	Jason Cooper <jason@lakedaemon.net>
 M:	Andrew Lunn <andrew@lunn.ch>
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
+M:	Gregory Clement <gregory.clement@free-electrons.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-dove/
@@ -1351,6 +1362,7 @@
 F:	drivers/*/*rockchip*
 F:	drivers/*/*/*rockchip*
 F:	sound/soc/rockchip/
+N:	rockchip
 
 ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
 M:	Kukjin Kim <kgene@kernel.org>
@@ -1664,8 +1676,8 @@
 F:	include/linux/platform_data/at24.h
 
 ATA OVER ETHERNET (AOE) DRIVER
-M:	"Ed L. Cashin" <ecashin@coraid.com>
-W:	http://support.coraid.com/support/linux
+M:	"Ed L. Cashin" <ed.cashin@acm.org>
+W:	http://www.openaoe.org/
 S:	Supported
 F:	Documentation/aoe/
 F:	drivers/block/aoe/
@@ -1730,7 +1742,7 @@
 F:	drivers/net/ethernet/atheros/
 
 ATM
-M:	Chas Williams <chas@cmf.nrl.navy.mil>
+M:	Chas Williams <3chas3@gmail.com>
 L:	linux-atm-general@lists.sourceforge.net (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 W:	http://linux-atm.sourceforge.net
@@ -2065,7 +2077,7 @@
 BONDING DRIVER
 M:	Jay Vosburgh <j.vosburgh@gmail.com>
 M:	Veaceslav Falico <vfalico@gmail.com>
-M:	Andy Gospodarek <andy@greyhouse.net>
+M:	Andy Gospodarek <gospo@cumulusnetworks.com>
 L:	netdev@vger.kernel.org
 W:	http://sourceforge.net/projects/bonding/
 S:	Supported
@@ -2107,7 +2119,6 @@
 
 BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE
 M:	Christian Daudt <bcm@fixthebug.org>
-M:	Matt Porter <mporter@linaro.org>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://github.com/broadcom/mach-bcm
@@ -2369,8 +2380,9 @@
 
 CAN NETWORK LAYER
 M:	Oliver Hartkopp <socketcan@hartkopp.net>
+M:	Marc Kleine-Budde <mkl@pengutronix.de>
 L:	linux-can@vger.kernel.org
-W:	http://gitorious.org/linux-can
+W:	https://github.com/linux-can
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git
 S:	Maintained
@@ -2386,7 +2398,7 @@
 M:	Wolfgang Grandegger <wg@grandegger.com>
 M:	Marc Kleine-Budde <mkl@pengutronix.de>
 L:	linux-can@vger.kernel.org
-W:	http://gitorious.org/linux-can
+W:	https://github.com/linux-can
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git
 S:	Maintained
@@ -3241,6 +3253,13 @@
 F:	Documentation/hwmon/dme1737
 F:	drivers/hwmon/dme1737.c
 
+DMI/SMBIOS SUPPORT
+M:	Jean Delvare <jdelvare@suse.de>
+S:	Maintained
+F:	drivers/firmware/dmi-id.c
+F:	drivers/firmware/dmi_scan.c
+F:	include/linux/dmi.h
+
 DOCKING STATION DRIVER
 M:	Shaohua Li <shaohua.li@intel.com>
 L:	linux-acpi@vger.kernel.org
@@ -7213,8 +7232,7 @@
 M:	Mark Fasheh <mfasheh@suse.com>
 M:	Joel Becker <jlbec@evilplan.org>
 L:	ocfs2-devel@oss.oracle.com (moderated for non-subscribers)
-W:	http://oss.oracle.com/projects/ocfs2/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2.git
+W:	http://ocfs2.wiki.kernel.org
 S:	Supported
 F:	Documentation/filesystems/ocfs2.txt
 F:	Documentation/filesystems/dlmfs.txt
@@ -8481,6 +8499,14 @@
 L:	netdev@vger.kernel.org
 F:	drivers/net/ethernet/samsung/sxgbe/
 
+SAMSUNG THERMAL DRIVER
+M:	Lukasz Majewski <l.majewski@samsung.com>
+L:	linux-pm@vger.kernel.org
+L:	linux-samsung-soc@vger.kernel.org
+S:	Supported
+T:	https://github.com/lmajewski/linux-samsung-thermal.git
+F:	drivers/thermal/samsung/
+
 SAMSUNG USB2 PHY DRIVER
 M:	Kamil Debski <k.debski@samsung.com>
 L:	linux-kernel@vger.kernel.org
@@ -10189,6 +10215,13 @@
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
+USB OTG FSM (Finite State Machine)
+M:	Peter Chen <Peter.Chen@freescale.com>
+T:	git git://github.com/hzpeterchen/linux-usb.git
+L:	linux-usb@vger.kernel.org
+S:	Maintained
+F:	drivers/usb/common/usb-otg-fsm.c
+
 USB OVER IP DRIVER
 M:	Valentina Manea <valentina.manea.m@gmail.com>
 M:	Shuah Khan <shuah.kh@samsung.com>
diff --git a/Makefile b/Makefile
index 9fab639..da36a3b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc6
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 4e54729..52312cb 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -47,9 +47,6 @@
 /* Forward declaration, a strange C thing */
 struct task_struct;
 
-/* Return saved PC of a blocked thread  */
-unsigned long thread_saved_pc(struct task_struct *t);
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1)
 
@@ -72,18 +69,21 @@
 #define release_segments(mm)        do { } while (0)
 
 #define KSTK_EIP(tsk)   (task_pt_regs(tsk)->ret)
+#define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
  * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
-#define KSTK_ESP(tsk)   (tsk->thread.ksp)
+#define TSK_K_ESP(tsk)		(tsk->thread.ksp)
 
-#define KSTK_REG(tsk, off)	(*((unsigned int *)(KSTK_ESP(tsk) + \
+#define TSK_K_REG(tsk, off)	(*((unsigned int *)(TSK_K_ESP(tsk) + \
 					sizeof(struct callee_regs) + off)))
 
-#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4)
-#define KSTK_FP(tsk)    KSTK_REG(tsk, 0)
+#define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
+#define TSK_K_FP(tsk)		TSK_K_REG(tsk, 0)
+
+#define thread_saved_pc(tsk)	TSK_K_BLINK(tsk)
 
 extern void start_thread(struct pt_regs * regs, unsigned long pc,
 			 unsigned long usp);
diff --git a/arch/arc/include/asm/stacktrace.h b/arch/arc/include/asm/stacktrace.h
new file mode 100644
index 0000000..b29b606
--- /dev/null
+++ b/arch/arc/include/asm/stacktrace.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_STACKTRACE_H
+#define __ASM_STACKTRACE_H
+
+#include <linux/sched.h>
+
+/**
+ * arc_unwind_core - Unwind the kernel mode stack for an execution context
+ * @tsk:		NULL for current task, specific task otherwise
+ * @regs:		pt_regs used to seed the unwinder {SP, FP, BLINK, PC}
+ * 			If NULL, use pt_regs of @tsk (if !NULL) otherwise
+ * 			use the current values of {SP, FP, BLINK, PC}
+ * @consumer_fn:	Callback invoked for each frame unwound
+ * 			Returns 0 to continue unwinding, -1 to stop
+ * @arg:		Arg to callback
+ *
+ * Returns the address of first function in stack
+ *
+ * Semantics:
+ *  - synchronous unwinding (e.g. dump_stack): @tsk  NULL, @regs  NULL
+ *  - Asynchronous unwinding of sleeping task: @tsk !NULL, @regs  NULL
+ *  - Asynchronous unwinding of intr/excp etc: @tsk !NULL, @regs !NULL
+ */
+notrace noinline unsigned int arc_unwind_core(
+	struct task_struct *tsk, struct pt_regs *regs,
+	int (*consumer_fn) (unsigned int, void *),
+	void *arg);
+
+#endif /* __ASM_STACKTRACE_H */
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index fdd8971..98c00a2 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -192,29 +192,6 @@
 	return 0;
 }
 
-/*
- * API: expected by schedular Code: If thread is sleeping where is that.
- * What is this good for? it will be always the scheduler or ret_from_fork.
- * So we hard code that anyways.
- */
-unsigned long thread_saved_pc(struct task_struct *t)
-{
-	struct pt_regs *regs = task_pt_regs(t);
-	unsigned long blink = 0;
-
-	/*
-	 * If the thread being queried for in not itself calling this, then it
-	 * implies it is not executing, which in turn implies it is sleeping,
-	 * which in turn implies it got switched OUT by the schedular.
-	 * In that case, it's kernel mode blink can reliably retrieved as per
-	 * the picture above (right above pt_regs).
-	 */
-	if (t != current && t->state != TASK_RUNNING)
-		blink = *((unsigned int *)regs - 1);
-
-	return blink;
-}
-
 int elf_check_arch(const struct elf32_hdr *x)
 {
 	unsigned int eflags;
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 114234e..edda76f 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -67,7 +67,7 @@
 	       sigset_t *set)
 {
 	int err;
-	err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs,
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
@@ -83,7 +83,7 @@
 	if (!err)
 		set_current_blocked(&set);
 
-	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs),
+	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 
 	return err;
@@ -131,6 +131,15 @@
 	/* Don't restart from sigreturn */
 	syscall_wont_restart(regs);
 
+	/*
+	 * Ensure that sigreturn always returns to user mode (in case the
+	 * regs saved on user stack got fudged between save and sigreturn)
+	 * Otherwise it is easy to panic the kernel with a custom
+	 * signal handler and/or restorer which clobberes the status32/ret
+	 * to return to a bogus location in kernel mode.
+	 */
+	regs->status32 |= STATUS_U_MASK;
+
 	return regs->r0;
 
 badframe:
@@ -229,8 +238,11 @@
 
 	/*
 	 * handler returns using sigreturn stub provided already by userpsace
+	 * If not, nuke the process right away
 	 */
-	BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER));
+	if(!(ksig->ka.sa.sa_flags & SA_RESTORER))
+		return 1;
+
 	regs->blink = (unsigned long)ksig->ka.sa.sa_restorer;
 
 	/* User Stack for signal handler will be above the frame just carved */
@@ -296,12 +308,12 @@
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	sigset_t *oldset = sigmask_to_save();
-	int ret;
+	int failed;
 
 	/* Set up the stack frame */
-	ret = setup_rt_frame(ksig, oldset, regs);
+	failed = setup_rt_frame(ksig, oldset, regs);
 
-	signal_setup_done(ret, ksig, 0);
+	signal_setup_done(failed, ksig, 0);
 }
 
 void do_signal(struct pt_regs *regs)
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 9ce47cf..92320d6 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -43,6 +43,10 @@
 				   struct pt_regs *regs,
 				   struct unwind_frame_info *frame_info)
 {
+	/*
+	 * synchronous unwinding (e.g. dump_stack)
+	 *  - uses current values of SP and friends
+	 */
 	if (tsk == NULL && regs == NULL) {
 		unsigned long fp, sp, blink, ret;
 		frame_info->task = current;
@@ -61,12 +65,17 @@
 		frame_info->regs.r63 = ret;
 		frame_info->call_frame = 0;
 	} else if (regs == NULL) {
+		/*
+		 * Asynchronous unwinding of sleeping task
+		 *  - Gets SP etc from task's pt_regs (saved bottom of kernel
+		 *    mode stack of task)
+		 */
 
 		frame_info->task = tsk;
 
-		frame_info->regs.r27 = KSTK_FP(tsk);
-		frame_info->regs.r28 = KSTK_ESP(tsk);
-		frame_info->regs.r31 = KSTK_BLINK(tsk);
+		frame_info->regs.r27 = TSK_K_FP(tsk);
+		frame_info->regs.r28 = TSK_K_ESP(tsk);
+		frame_info->regs.r31 = TSK_K_BLINK(tsk);
 		frame_info->regs.r63 = (unsigned int)__switch_to;
 
 		/* In the prologue of __switch_to, first FP is saved on stack
@@ -83,6 +92,10 @@
 		frame_info->call_frame = 0;
 
 	} else {
+		/*
+		 * Asynchronous unwinding of intr/exception
+		 *  - Just uses the pt_regs passed
+		 */
 		frame_info->task = tsk;
 
 		frame_info->regs.r27 = regs->fp;
@@ -95,7 +108,7 @@
 
 #endif
 
-static noinline unsigned int
+notrace noinline unsigned int
 arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 		int (*consumer_fn) (unsigned int, void *), void *arg)
 {
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index 7ff5b5c..74db59b 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <asm/disasm.h>
@@ -253,6 +254,7 @@
 		}
 	}
 
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address);
 	return 0;
 
 fault:
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 563cb27..6a2e006 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/perf_event.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu.h>
 
@@ -139,13 +140,20 @@
 			return;
 	}
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 	if (likely(!(fault & VM_FAULT_ERROR))) {
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
 			/* To avoid updating stats twice for retry case */
-			if (fault & VM_FAULT_MAJOR)
+			if (fault & VM_FAULT_MAJOR) {
 				tsk->maj_flt++;
-			else
+				perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+					      regs, address);
+			} else {
 				tsk->min_flt++;
+				perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+					      regs, address);
+			}
 
 			if (fault & VM_FAULT_RETRY) {
 				flags &= ~FAULT_FLAG_ALLOW_RETRY;
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9f1f09a..cf4c0c9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -619,6 +619,7 @@
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
 	select HAVE_IDE
+	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 7f99cd6..eb7bb51 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -150,6 +150,7 @@
 machine-$(CONFIG_ARCH_CLPS711X)		+= clps711x
 machine-$(CONFIG_ARCH_CNS3XXX)		+= cns3xxx
 machine-$(CONFIG_ARCH_DAVINCI)		+= davinci
+machine-$(CONFIG_ARCH_DIGICOLOR)	+= digicolor
 machine-$(CONFIG_ARCH_DOVE)		+= dove
 machine-$(CONFIG_ARCH_EBSA110)		+= ebsa110
 machine-$(CONFIG_ARCH_EFM32)		+= efm32
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index 6cc25ed..c3255e0 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -195,6 +195,7 @@
 
 &usb0 {
 	status = "okay";
+	dr_mode = "peripheral";
 };
 
 &usb1 {
@@ -300,3 +301,11 @@
 	cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
 	cd-inverted;
 };
+
+&aes {
+	status = "okay";
+};
+
+&sham {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/am335x-bone.dts b/arch/arm/boot/dts/am335x-bone.dts
index 83d40f7..6b849372 100644
--- a/arch/arm/boot/dts/am335x-bone.dts
+++ b/arch/arm/boot/dts/am335x-bone.dts
@@ -24,11 +24,3 @@
 &mmc1 {
 	vmmc-supply = <&ldo3_reg>;
 };
-
-&sham {
-	status = "okay";
-};
-
-&aes {
-	status = "okay";
-};
diff --git a/arch/arm/boot/dts/am335x-lxm.dts b/arch/arm/boot/dts/am335x-lxm.dts
index 7266a00..5c5667a 100644
--- a/arch/arm/boot/dts/am335x-lxm.dts
+++ b/arch/arm/boot/dts/am335x-lxm.dts
@@ -328,6 +328,10 @@
 	dual_emac_res_vlan = <3>;
 };
 
+&phy_sel {
+	rmii-clock-ext;
+};
+
 &mac {
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&cpsw_default>;
diff --git a/arch/arm/boot/dts/am33xx-clocks.dtsi b/arch/arm/boot/dts/am33xx-clocks.dtsi
index 712edce..071b56a 100644
--- a/arch/arm/boot/dts/am33xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am33xx-clocks.dtsi
@@ -99,7 +99,7 @@
 	ehrpwm0_tbclk: ehrpwm0_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <0>;
 		reg = <0x0664>;
 	};
@@ -107,7 +107,7 @@
 	ehrpwm1_tbclk: ehrpwm1_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <1>;
 		reg = <0x0664>;
 	};
@@ -115,7 +115,7 @@
 	ehrpwm2_tbclk: ehrpwm2_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <2>;
 		reg = <0x0664>;
 	};
diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts
index f9a17e2..0198f5a 100644
--- a/arch/arm/boot/dts/am437x-idk-evm.dts
+++ b/arch/arm/boot/dts/am437x-idk-evm.dts
@@ -133,20 +133,6 @@
 		>;
 	};
 
-	i2c1_pins_default: i2c1_pins_default {
-		pinctrl-single,pins = <
-			0x15c (PIN_INPUT | SLEWCTRL_FAST | MUX_MODE2) /* spi0_cs0.i2c1_scl */
-			0x158 (PIN_INPUT | SLEWCTRL_FAST | MUX_MODE2) /* spi0_d1.i2c1_sda */
-		>;
-	};
-
-	i2c1_pins_sleep: i2c1_pins_sleep {
-		pinctrl-single,pins = <
-			0x15c (PIN_INPUT_PULLDOWN | MUX_MODE7) /* spi0_cs0.i2c1_scl */
-			0x158 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* spi0_d1.i2c1_sda */
-		>;
-	};
-
 	mmc1_pins_default: pinmux_mmc1_pins_default {
 		pinctrl-single,pins = <
 			0x100 (PIN_INPUT | MUX_MODE0) /* mmc0_clk.mmc0_clk */
@@ -254,7 +240,7 @@
 	status = "okay";
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&i2c0_pins_default>;
-	pinctrl-1 = <&i2c0_pins_default>;
+	pinctrl-1 = <&i2c0_pins_sleep>;
 	clock-frequency = <400000>;
 
 	at24@50 {
@@ -262,17 +248,10 @@
 		pagesize = <64>;
 		reg = <0x50>;
 	};
-};
-
-&i2c1 {
-	status = "okay";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&i2c1_pins_default>;
-	pinctrl-1 = <&i2c1_pins_default>;
-	clock-frequency = <400000>;
 
 	tps: tps62362@60 {
 		compatible = "ti,tps62362";
+		reg = <0x60>;
 		regulator-name = "VDD_MPU";
 		regulator-min-microvolt = <950000>;
 		regulator-max-microvolt = <1330000>;
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index c7dc9da..cfb4968 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -107,7 +107,7 @@
 	ehrpwm0_tbclk: ehrpwm0_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <0>;
 		reg = <0x0664>;
 	};
@@ -115,7 +115,7 @@
 	ehrpwm1_tbclk: ehrpwm1_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <1>;
 		reg = <0x0664>;
 	};
@@ -123,7 +123,7 @@
 	ehrpwm2_tbclk: ehrpwm2_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <2>;
 		reg = <0x0664>;
 	};
@@ -131,7 +131,7 @@
 	ehrpwm3_tbclk: ehrpwm3_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <4>;
 		reg = <0x0664>;
 	};
@@ -139,7 +139,7 @@
 	ehrpwm4_tbclk: ehrpwm4_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <5>;
 		reg = <0x0664>;
 	};
@@ -147,7 +147,7 @@
 	ehrpwm5_tbclk: ehrpwm5_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <6>;
 		reg = <0x0664>;
 	};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 03750af..6463f9e 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -549,14 +549,6 @@
 	pinctrl-0 = <&usb1_pins>;
 };
 
-&omap_dwc3_1 {
-	extcon = <&extcon_usb1>;
-};
-
-&omap_dwc3_2 {
-	extcon = <&extcon_usb2>;
-};
-
 &usb2 {
 	dr_mode = "peripheral";
 };
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index fff0ee6..e7f0a4a 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -494,12 +494,12 @@
 
 					pinctrl_usart3_rts: usart3_rts-0 {
 						atmel,pins =
-							<AT91_PIOB 8 AT91_PERIPH_B AT91_PINCTRL_NONE>;	/* PC8 periph B */
+							<AT91_PIOC 8 AT91_PERIPH_B AT91_PINCTRL_NONE>;
 					};
 
 					pinctrl_usart3_cts: usart3_cts-0 {
 						atmel,pins =
-							<AT91_PIOB 10 AT91_PERIPH_B AT91_PINCTRL_NONE>;	/* PC10 periph B */
+							<AT91_PIOC 10 AT91_PERIPH_B AT91_PINCTRL_NONE>;
 					};
 				};
 
@@ -853,7 +853,7 @@
 			};
 
 			usb1: gadget@fffa4000 {
-				compatible = "atmel,at91rm9200-udc";
+				compatible = "atmel,at91sam9260-udc";
 				reg = <0xfffa4000 0x4000>;
 				interrupts = <10 IRQ_TYPE_LEVEL_HIGH 2>;
 				clocks = <&udc_clk>, <&udpck>;
@@ -976,7 +976,6 @@
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
-				atmel,idle-halt;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index e247b0b..d55fdf2 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -124,11 +124,12 @@
 			};
 
 			usb1: gadget@fffa4000 {
-				compatible = "atmel,at91rm9200-udc";
+				compatible = "atmel,at91sam9261-udc";
 				reg = <0xfffa4000 0x4000>;
 				interrupts = <10 IRQ_TYPE_LEVEL_HIGH 2>;
-				clocks = <&usb>, <&udc_clk>, <&udpck>;
-				clock-names = "usb_clk", "udc_clk", "udpck";
+				clocks = <&udc_clk>, <&udpck>;
+				clock-names = "pclk", "hclk";
+				atmel,matrix = <&matrix>;
 				status = "disabled";
 			};
 
@@ -262,7 +263,7 @@
 			};
 
 			matrix: matrix@ffffee00 {
-				compatible = "atmel,at91sam9260-bus-matrix";
+				compatible = "atmel,at91sam9260-bus-matrix", "syscon";
 				reg = <0xffffee00 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 1f67bb4..fce301c 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -69,7 +69,7 @@
 
 	sram1: sram@00500000 {
 		compatible = "mmio-sram";
-		reg = <0x00300000 0x4000>;
+		reg = <0x00500000 0x4000>;
 	};
 
 	ahb {
@@ -856,7 +856,7 @@
 			};
 
 			usb1: gadget@fff78000 {
-				compatible = "atmel,at91rm9200-udc";
+				compatible = "atmel,at91sam9263-udc";
 				reg = <0xfff78000 0x4000>;
 				interrupts = <24 IRQ_TYPE_LEVEL_HIGH 2>;
 				clocks = <&udc_clk>, <&udpck>;
@@ -905,7 +905,6 @@
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
-				atmel,idle-halt;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index ee80aa9..488af63 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -1116,7 +1116,6 @@
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
-				atmel,idle-halt;
 				status = "disabled";
 			};
 
@@ -1301,7 +1300,7 @@
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00800000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
+			clocks = <&utmi>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
 			clock-names = "usb_clk", "ehci_clk", "hclk", "uhpck";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index c2666a7..0c53a37 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -894,7 +894,6 @@
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
-				atmel,idle-halt;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 818dabd..d221179 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -1066,7 +1066,7 @@
 				reg = <0x00500000 0x80000
 				       0xf803c000 0x400>;
 				interrupts = <23 IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&usb>, <&udphs_clk>;
+				clocks = <&utmi>, <&udphs_clk>;
 				clock-names = "hclk", "pclk";
 				status = "disabled";
 
@@ -1130,7 +1130,6 @@
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
-				atmel,idle-halt;
 				status = "disabled";
 			};
 
@@ -1186,7 +1185,7 @@
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00700000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&uhpck>;
+			clocks = <&utmi>, <&uhphs_clk>, <&uhpck>;
 			clock-names = "usb_clk", "ehci_clk", "uhpck";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts
index 857d028..afe678f 100644
--- a/arch/arm/boot/dts/dm8168-evm.dts
+++ b/arch/arm/boot/dts/dm8168-evm.dts
@@ -35,6 +35,32 @@
 			DM816X_IOPAD(0x0aac, PIN_INPUT | MUX_MODE0)	/* SPI_D1 */
 		>;
 	};
+
+	mmc_pins: pinmux_mmc_pins {
+		pinctrl-single,pins = <
+			DM816X_IOPAD(0x0a70, MUX_MODE0)			/* SD_POW */
+			DM816X_IOPAD(0x0a74, MUX_MODE0)			/* SD_CLK */
+			DM816X_IOPAD(0x0a78, MUX_MODE0)			/* SD_CMD */
+			DM816X_IOPAD(0x0a7C, MUX_MODE0)			/* SD_DAT0 */
+			DM816X_IOPAD(0x0a80, MUX_MODE0)			/* SD_DAT1 */
+			DM816X_IOPAD(0x0a84, MUX_MODE0)			/* SD_DAT2 */
+			DM816X_IOPAD(0x0a88, MUX_MODE0)			/* SD_DAT2 */
+			DM816X_IOPAD(0x0a8c, MUX_MODE2)			/* GP1[7] */
+			DM816X_IOPAD(0x0a90, MUX_MODE2)			/* GP1[8] */
+		>;
+	};
+
+	usb0_pins: pinmux_usb0_pins {
+		pinctrl-single,pins = <
+			DM816X_IOPAD(0x0d00, MUX_MODE0)			/* USB0_DRVVBUS */
+		>;
+	};
+
+	usb1_pins: pinmux_usb0_pins {
+		pinctrl-single,pins = <
+			DM816X_IOPAD(0x0d04, MUX_MODE0)			/* USB1_DRVVBUS */
+		>;
+	};
 };
 
 &i2c1 {
@@ -125,5 +151,23 @@
 };
 
 &mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc_pins>;
 	vmmc-supply = <&vmmcsd_fixed>;
+	bus-width = <4>;
+	cd-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
+};
+
+/* At least dm8168-evm rev c won't support multipoint, later may */
+&usb0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_pins>;
+	mentor,multipoint = <0>;
+};
+
+&usb1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb1_pins>;
+	mentor,multipoint = <0>;
 };
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index d98d0f7..f35715b 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -97,10 +97,31 @@
 
 			/* Device Configuration Registers */
 			scm_conf: syscon@600 {
-				compatible = "syscon";
+				compatible = "syscon", "simple-bus";
 				reg = <0x600 0x110>;
 				#address-cells = <1>;
 				#size-cells = <1>;
+				ranges = <0 0x600 0x110>;
+
+				usb_phy0: usb-phy@20 {
+					compatible = "ti,dm8168-usb-phy";
+					reg = <0x20 0x8>;
+					reg-names = "phy";
+					clocks = <&main_fapll 6>;
+					clock-names = "refclk";
+					#phy-cells = <0>;
+					syscon = <&scm_conf>;
+				};
+
+				usb_phy1: usb-phy@28 {
+					compatible = "ti,dm8168-usb-phy";
+					reg = <0x28 0x8>;
+					reg-names = "phy";
+					clocks = <&main_fapll 6>;
+					clock-names = "refclk";
+					#phy-cells = <0>;
+					syscon = <&scm_conf>;
+				};
 			};
 
 			scrm_clocks: clocks {
@@ -129,17 +150,27 @@
 		};
 
 		gpio1: gpio@48032000 {
-			compatible = "ti,omap3-gpio";
+			compatible = "ti,omap4-gpio";
 			ti,hwmods = "gpio1";
+			ti,gpio-always-on;
 			reg = <0x48032000 0x1000>;
-			interrupts = <97>;
+			interrupts = <96>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		gpio2: gpio@4804c000 {
-			compatible = "ti,omap3-gpio";
+			compatible = "ti,omap4-gpio";
 			ti,hwmods = "gpio2";
+			ti,gpio-always-on;
 			reg = <0x4804c000 0x1000>;
-			interrupts = <99>;
+			interrupts = <98>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		gpmc: gpmc@50000000 {
@@ -357,7 +388,10 @@
 				reg-names = "mc", "control";
 				interrupts = <18>;
 				interrupt-names = "mc";
-				dr_mode = "otg";
+				dr_mode = "host";
+				interface-type = <0>;
+				phys = <&usb_phy0>;
+				phy-names = "usb2-phy";
 				mentor,multipoint = <1>;
 				mentor,num-eps = <16>;
 				mentor,ram-bits = <12>;
@@ -366,13 +400,15 @@
 
 			usb1: usb@47401800 {
 				compatible = "ti,musb-am33xx";
-				status = "disabled";
 				reg = <0x47401c00 0x400
 				       0x47401800 0x200>;
 				reg-names = "mc", "control";
 				interrupts = <19>;
 				interrupt-names = "mc";
-				dr_mode = "otg";
+				dr_mode = "host";
+				interface-type = <0>;
+				phys = <&usb_phy1>;
+				phy-names = "usb2-phy";
 				mentor,multipoint = <1>;
 				mentor,num-eps = <16>;
 				mentor,ram-bits = <12>;
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index 746cddb..7563d7c 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -263,17 +263,15 @@
 
 	dcan1_pins_default: dcan1_pins_default {
 		pinctrl-single,pins = <
-			0x3d0   (PIN_OUTPUT | MUX_MODE0) /* dcan1_tx */
-			0x3d4   (MUX_MODE15)		/* dcan1_rx.off */
-			0x418   (PULL_DIS | MUX_MODE1) /* wakeup0.dcan1_rx */
+			0x3d0   (PIN_OUTPUT_PULLUP | MUX_MODE0) /* dcan1_tx */
+			0x418   (PULL_UP | MUX_MODE1) /* wakeup0.dcan1_rx */
 		>;
 	};
 
 	dcan1_pins_sleep: dcan1_pins_sleep {
 		pinctrl-single,pins = <
-			0x3d0   (MUX_MODE15)	/* dcan1_tx.off */
-			0x3d4   (MUX_MODE15)	/* dcan1_rx.off */
-			0x418   (MUX_MODE15)	/* wakeup0.off */
+			0x3d0   (MUX_MODE15 | PULL_UP)	/* dcan1_tx.off */
+			0x418   (MUX_MODE15 | PULL_UP)	/* wakeup0.off */
 		>;
 	};
 };
@@ -543,14 +541,6 @@
 	};
 };
 
-&omap_dwc3_1 {
-	extcon = <&extcon_usb1>;
-};
-
-&omap_dwc3_2 {
-	extcon = <&extcon_usb2>;
-};
-
 &usb1 {
 	dr_mode = "peripheral";
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 5827fed..c4659a9 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -249,8 +249,8 @@
 				     <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
 			#dma-cells = <1>;
-			#dma-channels = <32>;
-			#dma-requests = <127>;
+			dma-channels = <32>;
+			dma-requests = <127>;
 		};
 
 		gpio1: gpio@4ae10000 {
@@ -1090,8 +1090,8 @@
 				      <0x4A096800 0x40>; /* pll_ctrl */
 				reg-names = "phy_rx", "phy_tx", "pll_ctrl";
 				ctrl-module = <&omap_control_sata>;
-				clocks = <&sys_clkin1>;
-				clock-names = "sysclk";
+				clocks = <&sys_clkin1>, <&sata_ref_clk>;
+				clock-names = "sysclk", "refclk";
 				#phy-cells = <0>;
 			};
 
@@ -1111,7 +1111,6 @@
 					      "wkupclk", "refclk",
 					      "div-clk", "phy-div";
 				#phy-cells = <0>;
-				ti,hwmods = "pcie1-phy";
 			};
 
 			pcie2_phy: pciephy@4a095000 {
@@ -1130,7 +1129,6 @@
 					      "wkupclk", "refclk",
 					      "div-clk", "phy-div";
 				#phy-cells = <0>;
-				ti,hwmods = "pcie2-phy";
 				status = "disabled";
 			};
 		};
diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts
index 4d87117..40ed539 100644
--- a/arch/arm/boot/dts/dra72-evm.dts
+++ b/arch/arm/boot/dts/dra72-evm.dts
@@ -119,17 +119,15 @@
 
 	dcan1_pins_default: dcan1_pins_default {
 		pinctrl-single,pins = <
-			0x3d0   (PIN_OUTPUT | MUX_MODE0) /* dcan1_tx */
-			0x3d4   (MUX_MODE15)		/* dcan1_rx.off */
-			0x418   (PULL_DIS | MUX_MODE1) /* wakeup0.dcan1_rx */
+			0x3d0   (PIN_OUTPUT_PULLUP | MUX_MODE0) /* dcan1_tx */
+			0x418   (PULL_UP | MUX_MODE1)	/* wakeup0.dcan1_rx */
 		>;
 	};
 
 	dcan1_pins_sleep: dcan1_pins_sleep {
 		pinctrl-single,pins = <
-			0x3d0   (MUX_MODE15)	/* dcan1_tx.off */
-			0x3d4   (MUX_MODE15)	/* dcan1_rx.off */
-			0x418   (MUX_MODE15)	/* wakeup0.off */
+			0x3d0   (MUX_MODE15 | PULL_UP)	/* dcan1_tx.off */
+			0x418   (MUX_MODE15 | PULL_UP)	/* wakeup0.off */
 		>;
 	};
 
@@ -380,14 +378,6 @@
 	phy-supply = <&ldo4_reg>;
 };
 
-&omap_dwc3_1 {
-	extcon = <&extcon_usb1>;
-};
-
-&omap_dwc3_2 {
-	extcon = <&extcon_usb2>;
-};
-
 &usb1 {
 	dr_mode = "peripheral";
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index 4bdcbd6..99b09a4 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -243,10 +243,18 @@
 		ti,invert-autoidle-bit;
 	};
 
+	dpll_core_byp_mux: dpll_core_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x012c>;
+	};
+
 	dpll_core_ck: dpll_core_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-core-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_core_byp_mux>;
 		reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>;
 	};
 
@@ -309,10 +317,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_dsp_byp_mux: dpll_dsp_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x0240>;
+	};
+
 	dpll_dsp_ck: dpll_dsp_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_dsp_byp_mux>;
 		reg = <0x0234>, <0x0238>, <0x0240>, <0x023c>;
 	};
 
@@ -335,10 +351,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_iva_byp_mux: dpll_iva_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x01ac>;
+	};
+
 	dpll_iva_ck: dpll_iva_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_iva_byp_mux>;
 		reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>;
 	};
 
@@ -361,10 +385,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_gpu_byp_mux: dpll_gpu_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x02e4>;
+	};
+
 	dpll_gpu_ck: dpll_gpu_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_gpu_byp_mux>;
 		reg = <0x02d8>, <0x02dc>, <0x02e4>, <0x02e0>;
 	};
 
@@ -398,10 +430,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_ddr_byp_mux: dpll_ddr_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x021c>;
+	};
+
 	dpll_ddr_ck: dpll_ddr_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_ddr_byp_mux>;
 		reg = <0x0210>, <0x0214>, <0x021c>, <0x0218>;
 	};
 
@@ -416,10 +456,18 @@
 		ti,invert-autoidle-bit;
 	};
 
+	dpll_gmac_byp_mux: dpll_gmac_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x02b4>;
+	};
+
 	dpll_gmac_ck: dpll_gmac_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_gmac_byp_mux>;
 		reg = <0x02a8>, <0x02ac>, <0x02b4>, <0x02b0>;
 	};
 
@@ -482,10 +530,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_eve_byp_mux: dpll_eve_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x0290>;
+	};
+
 	dpll_eve_ck: dpll_eve_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_eve_byp_mux>;
 		reg = <0x0284>, <0x0288>, <0x0290>, <0x028c>;
 	};
 
@@ -1249,10 +1305,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_per_byp_mux: dpll_per_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x014c>;
+	};
+
 	dpll_per_ck: dpll_per_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_per_byp_mux>;
 		reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>;
 	};
 
@@ -1275,10 +1339,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_usb_byp_mux: dpll_usb_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x018c>;
+	};
+
 	dpll_usb_ck: dpll_usb_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-j-type-clock";
-		clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_usb_byp_mux>;
 		reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>;
 	};
 
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 277b48b..ac6b0ae 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -18,6 +18,7 @@
  */
 
 #include "skeleton.dtsi"
+#include "exynos4-cpu-thermal.dtsi"
 #include <dt-bindings/clock/exynos3250.h>
 
 / {
@@ -193,6 +194,7 @@
 			interrupts = <0 216 0>;
 			clocks = <&cmu CLK_TMU_APBIF>;
 			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi
new file mode 100644
index 0000000..735cb2f
--- /dev/null
+++ b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi
@@ -0,0 +1,52 @@
+/*
+ * Device tree sources for Exynos4 thermal zone
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <dt-bindings/thermal/thermal.h>
+
+/ {
+thermal-zones {
+	cpu_thermal: cpu-thermal {
+		thermal-sensors = <&tmu 0>;
+		polling-delay-passive = <0>;
+		polling-delay = <0>;
+		trips {
+			cpu_alert0: cpu-alert-0 {
+				temperature = <70000>; /* millicelsius */
+				hysteresis = <10000>; /* millicelsius */
+				type = "active";
+			};
+			cpu_alert1: cpu-alert-1 {
+				temperature = <95000>; /* millicelsius */
+				hysteresis = <10000>; /* millicelsius */
+				type = "active";
+			};
+			cpu_alert2: cpu-alert-2 {
+				temperature = <110000>; /* millicelsius */
+				hysteresis = <10000>; /* millicelsius */
+				type = "active";
+			};
+			cpu_crit0: cpu-crit-0 {
+				temperature = <120000>; /* millicelsius */
+				hysteresis = <0>; /* millicelsius */
+				type = "critical";
+			};
+		};
+		cooling-maps {
+			map0 {
+				trip = <&cpu_alert0>;
+			};
+			map1 {
+				trip = <&cpu_alert1>;
+			};
+		};
+	};
+};
+};
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index 76173ca..77ea547 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -38,6 +38,7 @@
 		i2c5 = &i2c_5;
 		i2c6 = &i2c_6;
 		i2c7 = &i2c_7;
+		i2c8 = &i2c_8;
 		csis0 = &csis_0;
 		csis1 = &csis_1;
 		fimc0 = &fimc_0;
@@ -104,6 +105,7 @@
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C20 0x20>;
 		#power-domain-cells = <0>;
+		power-domains = <&pd_lcd0>;
 	};
 
 	pd_cam: cam-power-domain@10023C00 {
@@ -554,6 +556,22 @@
 		status = "disabled";
 	};
 
+	i2c_8: i2c@138E0000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "samsung,s3c2440-hdmiphy-i2c";
+		reg = <0x138E0000 0x100>;
+		interrupts = <0 93 0>;
+		clocks = <&clock CLK_I2C_HDMI>;
+		clock-names = "i2c";
+		status = "disabled";
+
+		hdmi_i2c_phy: hdmiphy@38 {
+			compatible = "exynos4210-hdmiphy";
+			reg = <0x38>;
+		};
+	};
+
 	spi_0: spi@13920000 {
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x13920000 0x100>;
@@ -663,6 +681,33 @@
 		status = "disabled";
 	};
 
+	tmu: tmu@100C0000 {
+		#include "exynos4412-tmu-sensor-conf.dtsi"
+	};
+
+	hdmi: hdmi@12D00000 {
+		compatible = "samsung,exynos4210-hdmi";
+		reg = <0x12D00000 0x70000>;
+		interrupts = <0 92 0>;
+		clock-names = "hdmi", "sclk_hdmi", "sclk_pixel", "sclk_hdmiphy",
+			"mout_hdmi";
+		clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>,
+			<&clock CLK_SCLK_PIXEL>, <&clock CLK_SCLK_HDMIPHY>,
+			<&clock CLK_MOUT_HDMI>;
+		phy = <&hdmi_i2c_phy>;
+		power-domains = <&pd_tv>;
+		samsung,syscon-phandle = <&pmu_system_controller>;
+		status = "disabled";
+	};
+
+	mixer: mixer@12C10000 {
+		compatible = "samsung,exynos4210-mixer";
+		interrupts = <0 91 0>;
+		reg = <0x12C10000 0x2100>, <0x12c00000 0x300>;
+		power-domains = <&pd_tv>;
+		status = "disabled";
+	};
+
 	ppmu_dmc0: ppmu_dmc0@106a0000 {
 		compatible = "samsung,exynos-ppmu";
 		reg = <0x106a0000 0x2000>;
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 3d6652a..32c5fd8 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -426,6 +426,25 @@
 		status = "okay";
 	};
 
+	tmu@100C0000 {
+		status = "okay";
+	};
+
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			cooling-maps {
+				map0 {
+				     /* Corresponds to 800MHz at freq_table */
+				     cooling-device = <&cpu0 2 2>;
+				};
+				map1 {
+				     /* Corresponds to 200MHz at freq_table */
+				     cooling-device = <&cpu0 4 4>;
+			       };
+		       };
+		};
+	};
+
 	camera {
 		pinctrl-names = "default";
 		pinctrl-0 = <>;
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index b57e6b8..d4f2b11 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -505,6 +505,63 @@
 			assigned-clock-rates = <0>, <160000000>;
 		};
 	};
+
+	hdmi_en: voltage-regulator-hdmi-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "HDMI_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpe0 1 0>;
+		enable-active-high;
+	};
+
+	hdmi_ddc: i2c-ddc {
+		compatible = "i2c-gpio";
+		gpios = <&gpe4 2 0 &gpe4 3 0>;
+		i2c-gpio,delay-us = <100>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pinctrl-0 = <&i2c_ddc_bus>;
+		pinctrl-names = "default";
+		status = "okay";
+	};
+
+	mixer@12C10000 {
+		status = "okay";
+	};
+
+	hdmi@12D00000 {
+		hpd-gpio = <&gpx3 7 0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hdmi_hpd>;
+		hdmi-en-supply = <&hdmi_en>;
+		vdd-supply = <&ldo3_reg>;
+		vdd_osc-supply = <&ldo4_reg>;
+		vdd_pll-supply = <&ldo3_reg>;
+		ddc = <&hdmi_ddc>;
+		status = "okay";
+	};
+
+	i2c@138E0000 {
+		status = "okay";
+	};
+};
+
+&pinctrl_1 {
+	hdmi_hpd: hdmi-hpd {
+		samsung,pins = "gpx3-7";
+		samsung,pin-pud = <0>;
+	};
+};
+
+&pinctrl_0 {
+	i2c_ddc_bus: i2c-ddc-bus {
+		samsung,pins = "gpe4-2", "gpe4-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
 };
 
 &mdma1 {
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index 67c832c..be89f83 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -21,6 +21,7 @@
 
 #include "exynos4.dtsi"
 #include "exynos4210-pinctrl.dtsi"
+#include "exynos4-cpu-thermal.dtsi"
 
 / {
 	compatible = "samsung,exynos4210", "samsung,exynos4";
@@ -35,10 +36,13 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu@900 {
+		cpu0: cpu@900 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0x900>;
+			cooling-min-level = <4>;
+			cooling-max-level = <2>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 
 		cpu@901 {
@@ -153,16 +157,38 @@
 		reg = <0x03860000 0x1000>;
 	};
 
-	tmu@100C0000 {
+	tmu: tmu@100C0000 {
 		compatible = "samsung,exynos4210-tmu";
 		interrupt-parent = <&combiner>;
 		reg = <0x100C0000 0x100>;
 		interrupts = <2 4>;
 		clocks = <&clock CLK_TMU_APBIF>;
 		clock-names = "tmu_apbif";
+		samsung,tmu_gain = <15>;
+		samsung,tmu_reference_voltage = <7>;
 		status = "disabled";
 	};
 
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tmu 0>;
+
+			trips {
+			      cpu_alert0: cpu-alert-0 {
+				      temperature = <85000>; /* millicelsius */
+			      };
+			      cpu_alert1: cpu-alert-1 {
+				      temperature = <100000>; /* millicelsius */
+			      };
+			      cpu_alert2: cpu-alert-2 {
+				      temperature = <110000>; /* millicelsius */
+			      };
+			};
+		};
+	};
+
 	g2d@12800000 {
 		compatible = "samsung,s5pv210-g2d";
 		reg = <0x12800000 0x1000>;
@@ -203,6 +229,14 @@
 		};
 	};
 
+	mixer: mixer@12C10000 {
+		clock-names = "mixer", "hdmi", "sclk_hdmi", "vp", "mout_mixer",
+			"sclk_mixer";
+		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
+			<&clock CLK_SCLK_HDMI>, <&clock CLK_VP>,
+			<&clock CLK_MOUT_MIXER>, <&clock CLK_SCLK_MIXER>;
+	};
+
 	ppmu_lcd1: ppmu_lcd1@12240000 {
 		compatible = "samsung,exynos-ppmu";
 		reg = <0x12240000 0x2000>;
diff --git a/arch/arm/boot/dts/exynos4212.dtsi b/arch/arm/boot/dts/exynos4212.dtsi
index dd0a43e..5be0328 100644
--- a/arch/arm/boot/dts/exynos4212.dtsi
+++ b/arch/arm/boot/dts/exynos4212.dtsi
@@ -26,10 +26,13 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu@A00 {
+		cpu0: cpu@A00 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA00>;
+			cooling-min-level = <13>;
+			cooling-max-level = <7>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 
 		cpu@A01 {
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index de80b5b..adb4f6a 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -249,6 +249,20 @@
 					regulator-always-on;
 				};
 
+				ldo8_reg: ldo@8 {
+					regulator-compatible = "LDO8";
+					regulator-name = "VDD10_HDMI_1.0V";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+				};
+
+				ldo10_reg: ldo@10 {
+					regulator-compatible = "LDO10";
+					regulator-name = "VDDQ_MIPIHSI_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+				};
+
 				ldo11_reg: LDO11 {
 					regulator-name = "VDD18_ABB1_1.8V";
 					regulator-min-microvolt = <1800000>;
@@ -411,6 +425,51 @@
 	ehci: ehci@12580000 {
 		status = "okay";
 	};
+
+	tmu@100C0000 {
+		vtmu-supply = <&ldo10_reg>;
+		status = "okay";
+	};
+
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			cooling-maps {
+				map0 {
+				     /* Corresponds to 800MHz at freq_table */
+				     cooling-device = <&cpu0 7 7>;
+				};
+				map1 {
+				     /* Corresponds to 200MHz at freq_table */
+				     cooling-device = <&cpu0 13 13>;
+			       };
+		       };
+		};
+	};
+
+	mixer: mixer@12C10000 {
+		status = "okay";
+	};
+
+	hdmi@12D00000 {
+		hpd-gpio = <&gpx3 7 0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hdmi_hpd>;
+		vdd-supply = <&ldo8_reg>;
+		vdd_osc-supply = <&ldo10_reg>;
+		vdd_pll-supply = <&ldo8_reg>;
+		ddc = <&hdmi_ddc>;
+		status = "okay";
+	};
+
+	hdmi_ddc: i2c@13880000 {
+		status = "okay";
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c2_bus>;
+	};
+
+	i2c@138E0000 {
+		status = "okay";
+	};
 };
 
 &pinctrl_1 {
@@ -425,4 +484,9 @@
 		samsung,pin-pud = <0>;
 		samsung,pin-drv = <0>;
 	};
+
+	hdmi_hpd: hdmi-hpd {
+		samsung,pins = "gpx3-7";
+		samsung,pin-pud = <1>;
+	};
 };
diff --git a/arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi
new file mode 100644
index 0000000..e3f7934
--- /dev/null
+++ b/arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi
@@ -0,0 +1,24 @@
+/*
+ * Device tree sources for Exynos4412 TMU sensor configuration
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <dt-bindings/thermal/thermal_exynos.h>
+
+#thermal-sensor-cells = <0>;
+samsung,tmu_gain = <8>;
+samsung,tmu_reference_voltage = <16>;
+samsung,tmu_noise_cancel_mode = <4>;
+samsung,tmu_efuse_value = <55>;
+samsung,tmu_min_efuse_value = <40>;
+samsung,tmu_max_efuse_value = <100>;
+samsung,tmu_first_point_trim = <25>;
+samsung,tmu_second_point_trim = <85>;
+samsung,tmu_default_temp_offset = <50>;
+samsung,tmu_cal_type = <TYPE_ONE_POINT_TRIMMING>;
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 21f7480..173ffa4 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -927,6 +927,21 @@
 		pulldown-ohm = <100000>; /* 100K */
 		io-channels = <&adc 2>;  /* Battery temperature */
 	};
+
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			cooling-maps {
+				map0 {
+				     /* Corresponds to 800MHz at freq_table */
+				     cooling-device = <&cpu0 7 7>;
+				};
+				map1 {
+				     /* Corresponds to 200MHz at freq_table */
+				     cooling-device = <&cpu0 13 13>;
+			       };
+		       };
+		};
+	};
 };
 
 &pmu_system_controller {
diff --git a/arch/arm/boot/dts/exynos4412.dtsi b/arch/arm/boot/dts/exynos4412.dtsi
index 0f6ec93..68ad43b 100644
--- a/arch/arm/boot/dts/exynos4412.dtsi
+++ b/arch/arm/boot/dts/exynos4412.dtsi
@@ -26,10 +26,13 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu@A00 {
+		cpu0: cpu@A00 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA00>;
+			cooling-min-level = <13>;
+			cooling-max-level = <7>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 
 		cpu@A01 {
diff --git a/arch/arm/boot/dts/exynos4x12.dtsi b/arch/arm/boot/dts/exynos4x12.dtsi
index f5e0ae7..6a6abe1 100644
--- a/arch/arm/boot/dts/exynos4x12.dtsi
+++ b/arch/arm/boot/dts/exynos4x12.dtsi
@@ -19,6 +19,7 @@
 
 #include "exynos4.dtsi"
 #include "exynos4x12-pinctrl.dtsi"
+#include "exynos4-cpu-thermal.dtsi"
 
 / {
 	aliases {
@@ -297,4 +298,15 @@
 		clock-names = "tmu_apbif";
 		status = "disabled";
 	};
+
+	hdmi: hdmi@12D00000 {
+		compatible = "samsung,exynos4212-hdmi";
+	};
+
+	mixer: mixer@12C10000 {
+		compatible = "samsung,exynos4212-mixer";
+		clock-names = "mixer", "hdmi", "sclk_hdmi", "vp";
+		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
+			 <&clock CLK_SCLK_HDMI>, <&clock CLK_VP>;
+	};
 };
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 9bb1b0b..adbde1a 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -20,7 +20,7 @@
 #include <dt-bindings/clock/exynos5250.h>
 #include "exynos5.dtsi"
 #include "exynos5250-pinctrl.dtsi"
-
+#include "exynos4-cpu-thermal.dtsi"
 #include <dt-bindings/clock/exynos-audss-clk.h>
 
 / {
@@ -58,11 +58,14 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu@0 {
+		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0>;
 			clock-frequency = <1700000000>;
+			cooling-min-level = <15>;
+			cooling-max-level = <9>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 		cpu@1 {
 			device_type = "cpu";
@@ -102,6 +105,12 @@
 		#power-domain-cells = <0>;
 	};
 
+	pd_disp1: disp1-power-domain@100440A0 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x100440A0 0x20>;
+		#power-domain-cells = <0>;
+	};
+
 	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5250-clock";
 		reg = <0x10010000 0x30000>;
@@ -235,12 +244,32 @@
 		status = "disabled";
 	};
 
-	tmu@10060000 {
+	tmu: tmu@10060000 {
 		compatible = "samsung,exynos5250-tmu";
 		reg = <0x10060000 0x100>;
 		interrupts = <0 65 0>;
 		clocks = <&clock CLK_TMU>;
 		clock-names = "tmu_apbif";
+		#include "exynos4412-tmu-sensor-conf.dtsi"
+	};
+
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tmu 0>;
+
+			cooling-maps {
+				map0 {
+				     /* Corresponds to 800MHz at freq_table */
+				     cooling-device = <&cpu0 9 9>;
+				};
+				map1 {
+				     /* Corresponds to 200MHz at freq_table */
+				     cooling-device = <&cpu0 15 15>;
+			       };
+		       };
+		};
 	};
 
 	serial@12C00000 {
@@ -719,6 +748,7 @@
 	hdmi: hdmi {
 		compatible = "samsung,exynos4212-hdmi";
 		reg = <0x14530000 0x70000>;
+		power-domains = <&pd_disp1>;
 		interrupts = <0 95 0>;
 		clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>,
 			 <&clock CLK_SCLK_PIXEL>, <&clock CLK_SCLK_HDMIPHY>,
@@ -731,9 +761,11 @@
 	mixer {
 		compatible = "samsung,exynos5250-mixer";
 		reg = <0x14450000 0x10000>;
+		power-domains = <&pd_disp1>;
 		interrupts = <0 94 0>;
-		clocks = <&clock CLK_MIXER>, <&clock CLK_SCLK_HDMI>;
-		clock-names = "mixer", "sclk_hdmi";
+		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
+			 <&clock CLK_SCLK_HDMI>;
+		clock-names = "mixer", "hdmi", "sclk_hdmi";
 	};
 
 	dp_phy: video-phy@10040720 {
@@ -743,6 +775,7 @@
 	};
 
 	dp: dp-controller@145B0000 {
+		power-domains = <&pd_disp1>;
 		clocks = <&clock CLK_DP>;
 		clock-names = "dp";
 		phys = <&dp_phy>;
@@ -750,6 +783,7 @@
 	};
 
 	fimd: fimd@14400000 {
+		power-domains = <&pd_disp1>;
 		clocks = <&clock CLK_SCLK_FIMD1>, <&clock CLK_FIMD1>;
 		clock-names = "sclk_fimd", "fimd";
 	};
diff --git a/arch/arm/boot/dts/exynos5420-trip-points.dtsi b/arch/arm/boot/dts/exynos5420-trip-points.dtsi
new file mode 100644
index 0000000..5d31fc14
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5420-trip-points.dtsi
@@ -0,0 +1,35 @@
+/*
+ * Device tree sources for default Exynos5420 thermal zone definition
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+polling-delay-passive = <0>;
+polling-delay = <0>;
+trips {
+	cpu-alert-0 {
+		temperature = <85000>; /* millicelsius */
+		hysteresis = <10000>; /* millicelsius */
+		type = "active";
+	};
+	cpu-alert-1 {
+		temperature = <103000>; /* millicelsius */
+		hysteresis = <10000>; /* millicelsius */
+		type = "active";
+	};
+	cpu-alert-2 {
+		temperature = <110000>; /* millicelsius */
+		hysteresis = <10000>; /* millicelsius */
+		type = "active";
+	};
+	cpu-crit-0 {
+		temperature = <1200000>; /* millicelsius */
+		hysteresis = <0>; /* millicelsius */
+		type = "critical";
+	};
+};
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 9dc2e97..c0e98cf 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -740,8 +740,9 @@
 		compatible = "samsung,exynos5420-mixer";
 		reg = <0x14450000 0x10000>;
 		interrupts = <0 94 0>;
-		clocks = <&clock CLK_MIXER>, <&clock CLK_SCLK_HDMI>;
-		clock-names = "mixer", "sclk_hdmi";
+		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
+			 <&clock CLK_SCLK_HDMI>;
+		clock-names = "mixer", "hdmi", "sclk_hdmi";
 		power-domains = <&disp_pd>;
 	};
 
@@ -782,6 +783,7 @@
 		interrupts = <0 65 0>;
 		clocks = <&clock CLK_TMU>;
 		clock-names = "tmu_apbif";
+		#include "exynos4412-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_cpu1: tmu@10064000 {
@@ -790,6 +792,7 @@
 		interrupts = <0 183 0>;
 		clocks = <&clock CLK_TMU>;
 		clock-names = "tmu_apbif";
+		#include "exynos4412-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_cpu2: tmu@10068000 {
@@ -798,6 +801,7 @@
 		interrupts = <0 184 0>;
 		clocks = <&clock CLK_TMU>, <&clock CLK_TMU>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+		#include "exynos4412-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_cpu3: tmu@1006c000 {
@@ -806,6 +810,7 @@
 		interrupts = <0 185 0>;
 		clocks = <&clock CLK_TMU>, <&clock CLK_TMU_GPU>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+		#include "exynos4412-tmu-sensor-conf.dtsi"
 	};
 
 	tmu_gpu: tmu@100a0000 {
@@ -814,6 +819,30 @@
 		interrupts = <0 215 0>;
 		clocks = <&clock CLK_TMU_GPU>, <&clock CLK_TMU>;
 		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+		#include "exynos4412-tmu-sensor-conf.dtsi"
+	};
+
+	thermal-zones {
+		cpu0_thermal: cpu0-thermal {
+			thermal-sensors = <&tmu_cpu0>;
+			#include "exynos5420-trip-points.dtsi"
+		};
+		cpu1_thermal: cpu1-thermal {
+		       thermal-sensors = <&tmu_cpu1>;
+		       #include "exynos5420-trip-points.dtsi"
+		};
+		cpu2_thermal: cpu2-thermal {
+		       thermal-sensors = <&tmu_cpu2>;
+		       #include "exynos5420-trip-points.dtsi"
+		};
+		cpu3_thermal: cpu3-thermal {
+		       thermal-sensors = <&tmu_cpu3>;
+		       #include "exynos5420-trip-points.dtsi"
+		};
+		gpu_thermal: gpu-thermal {
+		       thermal-sensors = <&tmu_gpu>;
+		       #include "exynos5420-trip-points.dtsi"
+		};
 	};
 
         watchdog: watchdog@101D0000 {
diff --git a/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi
new file mode 100644
index 0000000..7b2fba0
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi
@@ -0,0 +1,24 @@
+/*
+ * Device tree sources for Exynos5440 TMU sensor configuration
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <dt-bindings/thermal/thermal_exynos.h>
+
+#thermal-sensor-cells = <0>;
+samsung,tmu_gain = <5>;
+samsung,tmu_reference_voltage = <16>;
+samsung,tmu_noise_cancel_mode = <4>;
+samsung,tmu_efuse_value = <0x5d2d>;
+samsung,tmu_min_efuse_value = <16>;
+samsung,tmu_max_efuse_value = <76>;
+samsung,tmu_first_point_trim = <25>;
+samsung,tmu_second_point_trim = <70>;
+samsung,tmu_default_temp_offset = <25>;
+samsung,tmu_cal_type = <TYPE_ONE_POINT_TRIMMING>;
diff --git a/arch/arm/boot/dts/exynos5440-trip-points.dtsi b/arch/arm/boot/dts/exynos5440-trip-points.dtsi
new file mode 100644
index 0000000..48adfa8
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5440-trip-points.dtsi
@@ -0,0 +1,25 @@
+/*
+ * Device tree sources for default Exynos5440 thermal zone definition
+ *
+ * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+polling-delay-passive = <0>;
+polling-delay = <0>;
+trips {
+	cpu-alert-0 {
+		temperature = <100000>; /* millicelsius */
+		hysteresis = <0>; /* millicelsius */
+		type = "active";
+	};
+	cpu-crit-0 {
+		temperature = <1050000>; /* millicelsius */
+		hysteresis = <0>; /* millicelsius */
+		type = "critical";
+	};
+};
diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi
index 8f3373c..59d9416 100644
--- a/arch/arm/boot/dts/exynos5440.dtsi
+++ b/arch/arm/boot/dts/exynos5440.dtsi
@@ -219,6 +219,7 @@
 		interrupts = <0 58 0>;
 		clocks = <&clock CLK_B_125>;
 		clock-names = "tmu_apbif";
+		#include "exynos5440-tmu-sensor-conf.dtsi"
 	};
 
 	tmuctrl_1: tmuctrl@16011C {
@@ -227,6 +228,7 @@
 		interrupts = <0 58 0>;
 		clocks = <&clock CLK_B_125>;
 		clock-names = "tmu_apbif";
+		#include "exynos5440-tmu-sensor-conf.dtsi"
 	};
 
 	tmuctrl_2: tmuctrl@160120 {
@@ -235,6 +237,22 @@
 		interrupts = <0 58 0>;
 		clocks = <&clock CLK_B_125>;
 		clock-names = "tmu_apbif";
+		#include "exynos5440-tmu-sensor-conf.dtsi"
+	};
+
+	thermal-zones {
+		cpu0_thermal: cpu0-thermal {
+			thermal-sensors = <&tmuctrl_0>;
+			#include "exynos5440-trip-points.dtsi"
+		};
+		cpu1_thermal: cpu1-thermal {
+		       thermal-sensors = <&tmuctrl_1>;
+		       #include "exynos5440-trip-points.dtsi"
+		};
+		cpu2_thermal: cpu2-thermal {
+		       thermal-sensors = <&tmuctrl_2>;
+		       #include "exynos5440-trip-points.dtsi"
+		};
 	};
 
 	sata@210000 {
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index f1cd214..a626e6d 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -35,6 +35,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio3 22 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_usb_h1_vbus: regulator@1 {
@@ -45,6 +46,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 29 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_audio: regulator@2 {
diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts
index fda4932..945887d 100644
--- a/arch/arm/boot/dts/imx6sl-evk.dts
+++ b/arch/arm/boot/dts/imx6sl-evk.dts
@@ -52,6 +52,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio4 0 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_usb_otg2_vbus: regulator@1 {
@@ -62,6 +63,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio4 2 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_aud3v: regulator@2 {
diff --git a/arch/arm/boot/dts/omap2.dtsi b/arch/arm/boot/dts/omap2.dtsi
index 59d1c29..578fa2a 100644
--- a/arch/arm/boot/dts/omap2.dtsi
+++ b/arch/arm/boot/dts/omap2.dtsi
@@ -87,8 +87,8 @@
 				     <14>,
 				     <15>;
 			#dma-cells = <1>;
-			#dma-channels = <32>;
-			#dma-requests = <64>;
+			dma-channels = <32>;
+			dma-requests = <64>;
 		};
 
 		i2c1: i2c@48070000 {
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 6040327..db80f9d 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -16,6 +16,13 @@
 	model = "Nokia N900";
 	compatible = "nokia,omap3-n900", "ti,omap3430", "ti,omap3";
 
+	aliases {
+		i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+	};
+
 	cpus {
 		cpu@0 {
 			cpu0-supply = <&vcc>;
@@ -704,7 +711,7 @@
 		compatible = "smsc,lan91c94";
 		interrupt-parent = <&gpio2>;
 		interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;	/* gpio54 */
-		reg = <1 0x300 0xf>;		/* 16 byte IO range at offset 0x300 */
+		reg = <1 0 0xf>;		/* 16 byte IO range */
 		bank-width = <2>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&ethernet_pins>;
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 01b7111..3fdc84f 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -92,6 +92,8 @@
 			ti,hwmods = "aes";
 			reg = <0x480c5000 0x50>;
 			interrupts = <0>;
+			dmas = <&sdma 65 &sdma 66>;
+			dma-names = "tx", "rx";
 		};
 
 		prm: prm@48306000 {
@@ -155,8 +157,8 @@
 				     <14>,
 				     <15>;
 			#dma-cells = <1>;
-			#dma-channels = <32>;
-			#dma-requests = <96>;
+			dma-channels = <32>;
+			dma-requests = <96>;
 		};
 
 		omap3_pmx_core: pinmux@48002030 {
@@ -550,6 +552,8 @@
 			ti,hwmods = "sham";
 			reg = <0x480c3000 0x64>;
 			interrupts = <49>;
+			dmas = <&sdma 69>;
+			dma-names = "rx";
 		};
 
 		smartreflex_core: smartreflex@480cb000 {
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 074147c..87401d9 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -223,8 +223,8 @@
 				     <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
 			#dma-cells = <1>;
-			#dma-channels = <32>;
-			#dma-requests = <127>;
+			dma-channels = <32>;
+			dma-requests = <127>;
 		};
 
 		gpio1: gpio@4a310000 {
diff --git a/arch/arm/boot/dts/omap5-core-thermal.dtsi b/arch/arm/boot/dts/omap5-core-thermal.dtsi
index 19212ac..de8a3d4 100644
--- a/arch/arm/boot/dts/omap5-core-thermal.dtsi
+++ b/arch/arm/boot/dts/omap5-core-thermal.dtsi
@@ -13,7 +13,7 @@
 
 core_thermal: core_thermal {
 	polling-delay-passive = <250>; /* milliseconds */
-	polling-delay = <1000>; /* milliseconds */
+	polling-delay = <500>; /* milliseconds */
 
 			/* sensor       ID */
 	thermal-sensors = <&bandgap     2>;
diff --git a/arch/arm/boot/dts/omap5-gpu-thermal.dtsi b/arch/arm/boot/dts/omap5-gpu-thermal.dtsi
index 1b87aca..bc3090f 100644
--- a/arch/arm/boot/dts/omap5-gpu-thermal.dtsi
+++ b/arch/arm/boot/dts/omap5-gpu-thermal.dtsi
@@ -13,7 +13,7 @@
 
 gpu_thermal: gpu_thermal {
 	polling-delay-passive = <250>; /* milliseconds */
-	polling-delay = <1000>; /* milliseconds */
+	polling-delay = <500>; /* milliseconds */
 
 			/* sensor       ID */
 	thermal-sensors = <&bandgap     1>;
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index b321fdf..4a485b6 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -238,8 +238,8 @@
 				     <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
 			#dma-cells = <1>;
-			#dma-channels = <32>;
-			#dma-requests = <127>;
+			dma-channels = <32>;
+			dma-requests = <127>;
 		};
 
 		gpio1: gpio@4ae10000 {
@@ -929,8 +929,8 @@
 				      <0x4A096800 0x40>; /* pll_ctrl */
 				reg-names = "phy_rx", "phy_tx", "pll_ctrl";
 				ctrl-module = <&omap_control_sata>;
-				clocks = <&sys_clkin>;
-				clock-names = "sysclk";
+				clocks = <&sys_clkin>, <&sata_ref_clk>;
+				clock-names = "sysclk", "refclk";
 				#phy-cells = <0>;
 			};
 		};
@@ -1079,4 +1079,8 @@
 	};
 };
 
+&cpu_thermal {
+	polling-delay = <500>; /* milliseconds */
+};
+
 /include/ "omap54xx-clocks.dtsi"
diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi
index 58c2746..83b425f 100644
--- a/arch/arm/boot/dts/omap54xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi
@@ -167,10 +167,18 @@
 		ti,index-starts-at-one;
 	};
 
+	dpll_core_byp_mux: dpll_core_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x012c>;
+	};
+
 	dpll_core_ck: dpll_core_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-core-clock";
-		clocks = <&sys_clkin>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin>, <&dpll_core_byp_mux>;
 		reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>;
 	};
 
@@ -294,10 +302,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_iva_byp_mux: dpll_iva_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin>, <&iva_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x01ac>;
+	};
+
 	dpll_iva_ck: dpll_iva_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin>, <&iva_dpll_hs_clk_div>;
+		clocks = <&sys_clkin>, <&dpll_iva_byp_mux>;
 		reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>;
 	};
 
@@ -599,10 +615,19 @@
 	};
 };
 &cm_core_clocks {
+
+	dpll_per_byp_mux: dpll_per_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin>, <&per_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x014c>;
+	};
+
 	dpll_per_ck: dpll_per_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin>, <&per_dpll_hs_clk_div>;
+		clocks = <&sys_clkin>, <&dpll_per_byp_mux>;
 		reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>;
 	};
 
@@ -714,10 +739,18 @@
 		ti,index-starts-at-one;
 	};
 
+	dpll_usb_byp_mux: dpll_usb_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin>, <&usb_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x018c>;
+	};
+
 	dpll_usb_ck: dpll_usb_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-j-type-clock";
-		clocks = <&sys_clkin>, <&usb_dpll_hs_clk_div>;
+		clocks = <&sys_clkin>, <&dpll_usb_byp_mux>;
 		reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>;
 	};
 
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index d771f68..eccc78d 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -411,6 +411,7 @@
 			"mac_clk_rx", "mac_clk_tx",
 			"clk_mac_ref", "clk_mac_refout",
 			"aclk_mac", "pclk_mac";
+		status = "disabled";
 	};
 
 	usb_host0_ehci: usb@ff500000 {
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 261311b..367af53 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1248,7 +1248,6 @@
 				atmel,watchdog-type = "hardware";
 				atmel,reset-type = "all";
 				atmel,dbg-halt;
-				atmel,idle-halt;
 				status = "disabled";
 			};
 
@@ -1416,7 +1415,7 @@
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00700000 0x100000>;
 			interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&uhpck>;
+			clocks = <&utmi>, <&uhphs_clk>, <&uhpck>;
 			clock-names = "usb_clk", "ehci_clk", "uhpck";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index d986b41..4303874 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -66,6 +66,7 @@
 		gpio4 = &pioE;
 		tcb0 = &tcb0;
 		tcb1 = &tcb1;
+		i2c0 = &i2c0;
 		i2c2 = &i2c2;
 	};
 	cpus {
@@ -259,7 +260,7 @@
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <46 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&uhpck>;
+			clocks = <&utmi>, <&uhphs_clk>, <&uhpck>;
 			clock-names = "usb_clk", "ehci_clk", "uhpck";
 			status = "disabled";
 		};
@@ -461,8 +462,8 @@
 
 					lcdck: lcdck {
 						#clock-cells = <0>;
-						reg = <4>;
-						clocks = <&smd>;
+						reg = <3>;
+						clocks = <&mck>;
 					};
 
 					smdck: smdck {
@@ -770,7 +771,7 @@
 						reg = <50>;
 					};
 
-					lcd_clk: lcd_clk {
+					lcdc_clk: lcdc_clk {
 						#clock-cells = <0>;
 						reg = <51>;
 					};
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 252c3d1..d9176e6 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -660,7 +660,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0xfff01000 0x1000>;
-			interrupts = <0 156 4>;
+			interrupts = <0 155 4>;
 			num-cs = <4>;
 			clocks = <&spi_m_clk>;
 			status = "disabled";
@@ -713,6 +713,9 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&l4_sp_clk>;
+			dmas = <&pdma 28>,
+			       <&pdma 29>;
+			dma-names = "tx", "rx";
 		};
 
 		uart1: serial1@ffc03000 {
@@ -722,6 +725,9 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&l4_sp_clk>;
+			dmas = <&pdma 30>,
+			       <&pdma 31>;
+			dma-names = "tx", "rx";
 		};
 
 		rst: rstmgr@ffd05000 {
diff --git a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
index ab7891c..75742f8 100644
--- a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
+++ b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
@@ -56,6 +56,22 @@
 	model = "Olimex A10-OLinuXino-LIME";
 	compatible = "olimex,a10-olinuxino-lime", "allwinner,sun4i-a10";
 
+	cpus {
+		cpu0: cpu@0 {
+			/*
+			 * The A10-Lime is known to be unstable
+			 * when running at 1008 MHz
+			 */
+			operating-points = <
+				/* kHz    uV */
+				912000  1350000
+				864000  1300000
+				624000  1250000
+				>;
+			cooling-max-level = <2>;
+		};
+	};
+
 	soc@01c00000 {
 		emac: ethernet@01c0b000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 5c29258..eebb785 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -75,7 +75,6 @@
 			clock-latency = <244144>; /* 8 32k periods */
 			operating-points = <
 				/* kHz    uV */
-				1056000 1500000
 				1008000 1400000
 				912000  1350000
 				864000  1300000
@@ -83,7 +82,7 @@
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
-			cooling-max-level = <4>;
+			cooling-max-level = <3>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index f8818f1..883cb4873 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -47,7 +47,6 @@
 			clock-latency = <244144>; /* 8 32k periods */
 			operating-points = <
 				/* kHz    uV */
-				1104000	1500000
 				1008000 1400000
 				912000  1350000
 				864000  1300000
@@ -57,7 +56,7 @@
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
-			cooling-max-level = <6>;
+			cooling-max-level = <5>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 3a8530b..fdd1817 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -105,7 +105,6 @@
 			clock-latency = <244144>; /* 8 32k periods */
 			operating-points = <
 				/* kHz    uV */
-				1008000 1450000
 				960000  1400000
 				912000  1400000
 				864000  1300000
@@ -116,7 +115,7 @@
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
-			cooling-max-level = <7>;
+			cooling-max-level = <6>;
 		};
 
 		cpu@1 {
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index f2670f6..811e72b 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -70,6 +70,7 @@
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
+CONFIG_ARM_AT91_ETHER=y
 CONFIG_MACB=y
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_DM9000=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index e8a4c95..06075b6 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -62,6 +62,17 @@
 CONFIG_ARCH_STI=y
 CONFIG_ARCH_EXYNOS=y
 CONFIG_EXYNOS5420_MCPM=y
+CONFIG_ARCH_SHMOBILE_MULTI=y
+CONFIG_ARCH_EMEV2=y
+CONFIG_ARCH_R7S72100=y
+CONFIG_ARCH_R8A73A4=y
+CONFIG_ARCH_R8A7740=y
+CONFIG_ARCH_R8A7779=y
+CONFIG_ARCH_R8A7790=y
+CONFIG_ARCH_R8A7791=y
+CONFIG_ARCH_R8A7794=y
+CONFIG_ARCH_SH73A0=y
+CONFIG_MACH_MARZEN=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_ARCH_SIRF=y
 CONFIG_ARCH_TEGRA=y
@@ -84,9 +95,11 @@
 CONFIG_PCI_MSI=y
 CONFIG_PCI_MVEBU=y
 CONFIG_PCI_TEGRA=y
+CONFIG_PCI_RCAR_GEN2=y
+CONFIG_PCI_RCAR_GEN2_PCIE=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=16
 CONFIG_HIGHPTE=y
 CONFIG_CMA=y
 CONFIG_ARM_APPENDED_DTB=y
@@ -130,6 +143,7 @@
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=64
 CONFIG_OMAP_OCP2SCP=y
+CONFIG_SIMPLE_PM_BUS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
@@ -157,6 +171,7 @@
 CONFIG_AHCI_TEGRA=y
 CONFIG_SATA_HIGHBANK=y
 CONFIG_SATA_MV=y
+CONFIG_SATA_RCAR=y
 CONFIG_NETDEVICES=y
 CONFIG_HIX5HD2_GMAC=y
 CONFIG_SUN4I_EMAC=y
@@ -167,14 +182,17 @@
 CONFIG_MVNETA=y
 CONFIG_KS8851=y
 CONFIG_R8169=y
+CONFIG_SH_ETH=y
 CONFIG_SMSC911X=y
 CONFIG_STMMAC_ETH=y
 CONFIG_TI_CPSW=y
 CONFIG_XILINX_EMACLITE=y
 CONFIG_AT803X_PHY=y
 CONFIG_MARVELL_PHY=y
+CONFIG_SMSC_PHY=y
 CONFIG_BROADCOM_PHY=y
 CONFIG_ICPLUS_PHY=y
+CONFIG_MICREL_PHY=y
 CONFIG_USB_PEGASUS=y
 CONFIG_USB_USBNET=y
 CONFIG_USB_NET_SMSC75XX=y
@@ -192,15 +210,18 @@
 CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ATMEL_MXT=y
+CONFIG_TOUCHSCREEN_ST1232=m
 CONFIG_TOUCHSCREEN_STMPE=y
 CONFIG_TOUCHSCREEN_SUN4I=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_MPU3050=y
 CONFIG_INPUT_AXP20X_PEK=y
+CONFIG_INPUT_ADXL34X=m
 CONFIG_SERIO_AMBAKMI=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_8250_EM=y
 CONFIG_SERIAL_8250_MT6577=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
@@ -213,6 +234,9 @@
 CONFIG_SERIAL_TEGRA=y
 CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_NR_UARTS=20
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_SERIAL_MSM=y
 CONFIG_SERIAL_MSM_CONSOLE=y
 CONFIG_SERIAL_VT8500=y
@@ -233,19 +257,26 @@
 CONFIG_I2C_MUX_PINCTRL=y
 CONFIG_I2C_CADENCE=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_I2C_GPIO=m
 CONFIG_I2C_EXYNOS5=y
 CONFIG_I2C_MV64XXX=y
+CONFIG_I2C_RIIC=y
 CONFIG_I2C_S3C2410=y
+CONFIG_I2C_SH_MOBILE=y
 CONFIG_I2C_SIRF=y
-CONFIG_I2C_TEGRA=y
 CONFIG_I2C_ST=y
-CONFIG_SPI=y
+CONFIG_I2C_TEGRA=y
 CONFIG_I2C_XILINX=y
-CONFIG_SPI_DAVINCI=y
+CONFIG_I2C_RCAR=y
+CONFIG_SPI=y
 CONFIG_SPI_CADENCE=y
+CONFIG_SPI_DAVINCI=y
 CONFIG_SPI_OMAP24XX=y
 CONFIG_SPI_ORION=y
 CONFIG_SPI_PL022=y
+CONFIG_SPI_RSPI=y
+CONFIG_SPI_SH_MSIOF=m
+CONFIG_SPI_SH_HSPI=y
 CONFIG_SPI_SIRF=y
 CONFIG_SPI_SUN4I=y
 CONFIG_SPI_SUN6I=y
@@ -259,12 +290,15 @@
 CONFIG_PINCTRL_APQ8084=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_GENERIC_PLATFORM=y
-CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_DAVINCI=y
+CONFIG_GPIO_DWAPB=y
+CONFIG_GPIO_EM=y
+CONFIG_GPIO_RCAR=y
 CONFIG_GPIO_XILINX=y
 CONFIG_GPIO_ZYNQ=y
 CONFIG_GPIO_PCA953X=y
 CONFIG_GPIO_PCA953X_IRQ=y
+CONFIG_GPIO_PCF857X=y
 CONFIG_GPIO_TWL4030=y
 CONFIG_GPIO_PALMAS=y
 CONFIG_GPIO_SYSCON=y
@@ -276,10 +310,12 @@
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_KEYSTONE=y
 CONFIG_POWER_RESET_SUN6I=y
+CONFIG_POWER_RESET_RMOBILE=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM95245=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
+CONFIG_RCAR_THERMAL=y
 CONFIG_ARMADA_THERMAL=y
 CONFIG_DAVINCI_WATCHDOG
 CONFIG_ST_THERMAL_SYSCFG=y
@@ -290,6 +326,7 @@
 CONFIG_ORION_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
 CONFIG_MESON_WATCHDOG=y
+CONFIG_MFD_AS3711=y
 CONFIG_MFD_AS3722=y
 CONFIG_MFD_BCM590XX=y
 CONFIG_MFD_AXP20X=y
@@ -304,13 +341,16 @@
 CONFIG_MFD_TPS6586X=y
 CONFIG_MFD_TPS65910=y
 CONFIG_REGULATOR_AB8500=y
+CONFIG_REGULATOR_AS3711=y
 CONFIG_REGULATOR_AS3722=y
 CONFIG_REGULATOR_AXP20X=y
 CONFIG_REGULATOR_BCM590XX=y
+CONFIG_REGULATOR_DA9210=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_MFD_SYSCON=y
 CONFIG_POWER_RESET_SYSCON=y
 CONFIG_REGULATOR_MAX8907=y
+CONFIG_REGULATOR_MAX8973=y
 CONFIG_REGULATOR_MAX77686=y
 CONFIG_REGULATOR_PALMAS=y
 CONFIG_REGULATOR_S2MPS11=y
@@ -324,18 +364,32 @@
 CONFIG_REGULATOR_VEXPRESS=y
 CONFIG_MEDIA_SUPPORT=y
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_MEDIA_CONTROLLER=y
+CONFIG_VIDEO_V4L2_SUBDEV_API=y
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=y
 CONFIG_USB_GSPCA=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_SOC_CAMERA=m
+CONFIG_SOC_CAMERA_PLATFORM=m
+CONFIG_VIDEO_RCAR_VIN=m
+CONFIG_V4L_MEM2MEM_DRIVERS=y
+CONFIG_VIDEO_RENESAS_VSP1=m
+# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
+CONFIG_VIDEO_ADV7180=m
 CONFIG_DRM=y
+CONFIG_DRM_RCAR_DU=m
 CONFIG_DRM_TEGRA=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_FB_ARMCLCD=y
 CONFIG_FB_WM8505=y
+CONFIG_FB_SH_MOBILE_LCDC=y
 CONFIG_FB_SIMPLE=y
+CONFIG_FB_SH_MOBILE_MERAM=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
+CONFIG_BACKLIGHT_AS3711=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_SOUND=y
@@ -343,6 +397,8 @@
 CONFIG_SND_DYNAMIC_MINORS=y
 CONFIG_SND_USB_AUDIO=y
 CONFIG_SND_SOC=y
+CONFIG_SND_SOC_SH4_FSI=m
+CONFIG_SND_SOC_RCAR=m
 CONFIG_SND_SOC_TEGRA=y
 CONFIG_SND_SOC_TEGRA_RT5640=y
 CONFIG_SND_SOC_TEGRA_WM8753=y
@@ -350,6 +406,8 @@
 CONFIG_SND_SOC_TEGRA_TRIMSLICE=y
 CONFIG_SND_SOC_TEGRA_ALC5632=y
 CONFIG_SND_SOC_TEGRA_MAX98090=y
+CONFIG_SND_SOC_AK4642=m
+CONFIG_SND_SOC_WM8978=m
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_MVEBU=y
@@ -362,6 +420,8 @@
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_STI=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_R8A66597_HCD=m
+CONFIG_USB_RENESAS_USBHS=m
 CONFIG_USB_STORAGE=y
 CONFIG_USB_DWC3=y
 CONFIG_USB_CHIPIDEA=y
@@ -374,6 +434,10 @@
 CONFIG_USB_GPIO_VBUS=y
 CONFIG_USB_ISP1301=y
 CONFIG_USB_MXS_PHY=y
+CONFIG_USB_RCAR_PHY=m
+CONFIG_USB_RCAR_GEN2_PHY=m
+CONFIG_USB_GADGET=y
+CONFIG_USB_RENESAS_USBHS_UDC=m
 CONFIG_MMC=y
 CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_ARMMMCI=y
@@ -392,12 +456,14 @@
 CONFIG_MMC_OMAP=y
 CONFIG_MMC_OMAP_HS=y
 CONFIG_MMC_MVSDIO=y
-CONFIG_MMC_SUNXI=y
+CONFIG_MMC_SDHI=y
 CONFIG_MMC_DW=y
 CONFIG_MMC_DW_IDMAC=y
 CONFIG_MMC_DW_PLTFM=y
 CONFIG_MMC_DW_EXYNOS=y
 CONFIG_MMC_DW_ROCKCHIP=y
+CONFIG_MMC_SH_MMCIF=y
+CONFIG_MMC_SUNXI=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
@@ -421,10 +487,12 @@
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_MAX8907=y
 CONFIG_RTC_DRV_MAX77686=y
+CONFIG_RTC_DRV_RS5C372=m
 CONFIG_RTC_DRV_PALMAS=y
 CONFIG_RTC_DRV_TWL4030=y
 CONFIG_RTC_DRV_TPS6586X=y
 CONFIG_RTC_DRV_TPS65910=y
+CONFIG_RTC_DRV_S35390A=m
 CONFIG_RTC_DRV_EM3027=y
 CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_VT8500=y
@@ -436,6 +504,9 @@
 CONFIG_DW_DMAC=y
 CONFIG_MV_XOR=y
 CONFIG_TEGRA20_APB_DMA=y
+CONFIG_SH_DMAE=y
+CONFIG_RCAR_AUDMAC_PP=m
+CONFIG_RCAR_DMAC=y
 CONFIG_STE_DMA40=y
 CONFIG_SIRF_DMA=y
 CONFIG_TI_EDMA=y
@@ -468,6 +539,7 @@
 CONFIG_XILINX_XADC=y
 CONFIG_AK8975=y
 CONFIG_PWM=y
+CONFIG_PWM_RENESAS_TPU=y
 CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
 CONFIG_PHY_HIX5HD2_SATA=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index b738652..8e10859 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -114,6 +114,7 @@
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ECC_BCH=y
 CONFIG_MTD_NAND_OMAP2=y
+CONFIG_MTD_NAND_OMAP_BCH=y
 CONFIG_MTD_ONENAND=y
 CONFIG_MTD_ONENAND_VERIFY_WRITE=y
 CONFIG_MTD_ONENAND_OMAP2=y
@@ -248,6 +249,7 @@
 CONFIG_REGULATOR_PALMAS=y
 CONFIG_REGULATOR_PBIAS=y
 CONFIG_REGULATOR_TI_ABB=y
+CONFIG_REGULATOR_TPS62360=m
 CONFIG_REGULATOR_TPS65023=y
 CONFIG_REGULATOR_TPS6507X=y
 CONFIG_REGULATOR_TPS65217=y
@@ -374,7 +376,8 @@
 CONFIG_PWM_TWL=m
 CONFIG_PWM_TWL_LED=m
 CONFIG_OMAP_USB2=m
-CONFIG_TI_PIPE3=m
+CONFIG_TI_PIPE3=y
+CONFIG_TWL4030_USB=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_FS_XATTR is not set
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index 41d856e..510c747 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -3,8 +3,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EMBEDDED=y
 CONFIG_SLAB=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 38840a8..8f6a570 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -4,6 +4,7 @@
 CONFIG_PERF_EVENTS=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_SMP=y
+CONFIG_NR_CPUS=8
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_HIGHPTE=y
diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig
index f489fda..37fe607 100644
--- a/arch/arm/configs/vexpress_defconfig
+++ b/arch/arm/configs/vexpress_defconfig
@@ -118,8 +118,8 @@
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_MON=y
-CONFIG_USB_ISP1760_HCD=y
 CONFIG_USB_STORAGE=y
+CONFIG_USB_ISP1760=y
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
 CONFIG_NEW_LEDS=y
diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped
index 71e5fc7..1d1800f 100644
--- a/arch/arm/crypto/aesbs-core.S_shipped
+++ b/arch/arm/crypto/aesbs-core.S_shipped
@@ -58,14 +58,18 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -74,8 +78,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2095,9 +2097,11 @@
 	vld1.8	{q8}, [r0]			@ initial tweak
 	adr	r2, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	r9, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	r9, #0x10			@ subtract another 16 bytes
+#endif
 	subs	r9, #0x80
 
 	blo	.Lxts_dec_short
diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl
index be068db..a4d3856 100644
--- a/arch/arm/crypto/bsaes-armv7.pl
+++ b/arch/arm/crypto/bsaes-armv7.pl
@@ -701,14 +701,18 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -717,8 +721,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2076,9 +2078,11 @@
 	vld1.8	{@XMM[8]}, [r0]			@ initial tweak
 	adr	$magic, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	$len, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	$len, #0x10			@ subtract another 16 bytes
+#endif
 	subs	$len, #0x80
 
 	blo	.Lxts_dec_short
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 37ca2a4..4cf48c3 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -149,31 +149,30 @@
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#define kvm_pgd_index(addr)			pgd_index(addr)
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
 	return page_count(ptr_page) == 1;
 }
 
-
 #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
 #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
 #define kvm_pud_table_empty(kvm, pudp) (0)
 
 #define KVM_PREALLOC_LEVEL	0
 
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	return 0;
-}
-
-static inline void kvm_free_hwpgd(struct kvm *kvm) { }
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	return kvm->arch.pgd;
 }
 
+static inline unsigned int kvm_get_hwpgd_size(void)
+{
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
+}
+
 struct kvm;
 
 #define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
@@ -207,7 +206,7 @@
 
 	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
 
-	VM_BUG_ON(size & PAGE_MASK);
+	VM_BUG_ON(size & ~PAGE_MASK);
 
 	if (!need_flush && !icache_is_pipt())
 		goto vipt_cache;
diff --git a/arch/arm/include/debug/at91.S b/arch/arm/include/debug/at91.S
index 80a6501..c3c45e6 100644
--- a/arch/arm/include/debug/at91.S
+++ b/arch/arm/include/debug/at91.S
@@ -18,8 +18,11 @@
 #define AT91_DBGU 0xfc00c000 /* SAMA5D4_BASE_USART3 */
 #endif
 
-/* Keep in sync with mach-at91/include/mach/hardware.h */
+#ifdef CONFIG_MMU
 #define AT91_IO_P2V(x) ((x) - 0x01000000)
+#else
+#define AT91_IO_P2V(x) (x)
+#endif
 
 #define AT91_DBGU_SR		(0x14)	/* Status Register */
 #define AT91_DBGU_THR		(0x1c)	/* Transmitter Holding Register */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index e55408e..1d60beb 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -246,12 +246,9 @@
 		if (cpu_arch)
 			cpu_arch += CPU_ARCH_ARMv3;
 	} else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) {
-		unsigned int mmfr0;
-
 		/* Revised CPUID format. Read the Memory Model Feature
 		 * Register 0 and check for VMSAv7 or PMSAv7 */
-		asm("mrc	p15, 0, %0, c0, c1, 4"
-		    : "=r" (mmfr0));
+		unsigned int mmfr0 = read_cpuid_ext(CPUID_EXT_MMFR0);
 		if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
 		    (mmfr0 & 0x000000f0) >= 0x00000030)
 			cpu_arch = CPU_ARCH_ARMv7;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 07e7eb1..5560f74 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -540,7 +540,7 @@
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		kvm_guest_exit();
-		trace_kvm_exit(*vcpu_pc(vcpu));
+		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
 		 * while executing the guest). This interrupt is still
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 3e6859b..5656d79 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -290,7 +290,7 @@
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
-	pgd = pgdp + pgd_index(addr);
+	pgd = pgdp + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		if (!pgd_none(*pgd))
@@ -355,7 +355,7 @@
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		stage2_flush_puds(kvm, pgd, addr, next);
@@ -632,6 +632,20 @@
 				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
 }
 
+/* Free the HW pgd, one page at a time */
+static void kvm_free_hwpgd(void *hwpgd)
+{
+	free_pages_exact(hwpgd, kvm_get_hwpgd_size());
+}
+
+/* Allocate the HW PGD, making sure that each page gets its own refcount */
+static void *kvm_alloc_hwpgd(void)
+{
+	unsigned int size = kvm_get_hwpgd_size();
+
+	return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+}
+
 /**
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
@@ -645,15 +659,31 @@
  */
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
-	int ret;
 	pgd_t *pgd;
+	void *hwpgd;
 
 	if (kvm->arch.pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
 
+	hwpgd = kvm_alloc_hwpgd();
+	if (!hwpgd)
+		return -ENOMEM;
+
+	/* When the kernel uses more levels of page tables than the
+	 * guest, we allocate a fake PGD and pre-populate it to point
+	 * to the next-level page table, which will be the real
+	 * initial page table pointed to by the VTTBR.
+	 *
+	 * When KVM_PREALLOC_LEVEL==2, we allocate a single page for
+	 * the PMD and the kernel will use folded pud.
+	 * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD
+	 * pages.
+	 */
 	if (KVM_PREALLOC_LEVEL > 0) {
+		int i;
+
 		/*
 		 * Allocate fake pgd for the page table manipulation macros to
 		 * work.  This is not used by the hardware and we have no
@@ -661,30 +691,32 @@
 		 */
 		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
 				       GFP_KERNEL | __GFP_ZERO);
+
+		if (!pgd) {
+			kvm_free_hwpgd(hwpgd);
+			return -ENOMEM;
+		}
+
+		/* Plug the HW PGD into the fake one. */
+		for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+			if (KVM_PREALLOC_LEVEL == 1)
+				pgd_populate(NULL, pgd + i,
+					     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+			else if (KVM_PREALLOC_LEVEL == 2)
+				pud_populate(NULL, pud_offset(pgd, 0) + i,
+					     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+		}
 	} else {
 		/*
 		 * Allocate actual first-level Stage-2 page table used by the
 		 * hardware for Stage-2 page table walks.
 		 */
-		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+		pgd = (pgd_t *)hwpgd;
 	}
 
-	if (!pgd)
-		return -ENOMEM;
-
-	ret = kvm_prealloc_hwpgd(kvm, pgd);
-	if (ret)
-		goto out_err;
-
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
 	return 0;
-out_err:
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(pgd);
-	else
-		free_pages((unsigned long)pgd, S2_PGD_ORDER);
-	return ret;
 }
 
 /**
@@ -785,11 +817,10 @@
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	kvm_free_hwpgd(kvm);
+	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
 	if (KVM_PREALLOC_LEVEL > 0)
 		kfree(kvm->arch.pgd);
-	else
-		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+
 	kvm->arch.pgd = NULL;
 }
 
@@ -799,7 +830,7 @@
 	pgd_t *pgd;
 	pud_t *pud;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	if (WARN_ON(pgd_none(*pgd))) {
 		if (!cache)
 			return NULL;
@@ -1089,7 +1120,7 @@
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index 881874b..6817664 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -25,18 +25,22 @@
 );
 
 TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned long vcpu_pc),
-	TP_ARGS(vcpu_pc),
+	TP_PROTO(unsigned int exit_reason, unsigned long vcpu_pc),
+	TP_ARGS(exit_reason, vcpu_pc),
 
 	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_reason	)
 		__field(	unsigned long,	vcpu_pc		)
 	),
 
 	TP_fast_assign(
+		__entry->exit_reason		= exit_reason;
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("HSR_EC: 0x%04x, PC: 0x%08lx",
+		  __entry->exit_reason,
+		  __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_guest_fault,
diff --git a/arch/arm/mach-asm9260/Kconfig b/arch/arm/mach-asm9260/Kconfig
index 8423be7..5224120 100644
--- a/arch/arm/mach-asm9260/Kconfig
+++ b/arch/arm/mach-asm9260/Kconfig
@@ -2,5 +2,7 @@
 	bool "Alphascale ASM9260"
 	depends on ARCH_MULTI_V5
 	select CPU_ARM926T
+	select ASM9260_TIMER
+	select GENERIC_CLOCKEVENTS
 	help
 	  Support for Alphascale ASM9260 based platform.
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 5e34fb1..aa4116e 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -270,37 +270,35 @@
 	phys_addr_t sram_pbase;
 	unsigned long sram_base;
 	struct device_node *node;
-	struct platform_device *pdev;
+	struct platform_device *pdev = NULL;
 
-	node = of_find_compatible_node(NULL, NULL, "mmio-sram");
-	if (!node) {
-		pr_warn("%s: failed to find sram node!\n", __func__);
-		return;
+	for_each_compatible_node(node, NULL, "mmio-sram") {
+		pdev = of_find_device_by_node(node);
+		if (pdev) {
+			of_node_put(node);
+			break;
+		}
 	}
 
-	pdev = of_find_device_by_node(node);
 	if (!pdev) {
 		pr_warn("%s: failed to find sram device!\n", __func__);
-		goto put_node;
+		return;
 	}
 
 	sram_pool = dev_get_gen_pool(&pdev->dev);
 	if (!sram_pool) {
 		pr_warn("%s: sram pool unavailable!\n", __func__);
-		goto put_node;
+		return;
 	}
 
 	sram_base = gen_pool_alloc(sram_pool, at91_slow_clock_sz);
 	if (!sram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
-		goto put_node;
+		return;
 	}
 
 	sram_pbase = gen_pool_virt_to_phys(sram_pool, sram_base);
 	slow_clock = __arm_ioremap_exec(sram_pbase, at91_slow_clock_sz, false);
-
-put_node:
-	of_node_put(node);
 }
 #endif
 
diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h
index d2c8996..86c0aa8 100644
--- a/arch/arm/mach-at91/pm.h
+++ b/arch/arm/mach-at91/pm.h
@@ -44,7 +44,7 @@
 		"    mcr    p15, 0, %0, c7, c0, 4\n\t"
 		"    str    %5, [%1, %2]"
 		:
-		: "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR),
+		: "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR),
 		  "r" (1), "r" (AT91RM9200_SDRAMC_SRR),
 		  "r" (lpr));
 }
diff --git a/arch/arm/mach-at91/pm_slowclock.S b/arch/arm/mach-at91/pm_slowclock.S
index 556151e8..931f0e3 100644
--- a/arch/arm/mach-at91/pm_slowclock.S
+++ b/arch/arm/mach-at91/pm_slowclock.S
@@ -25,11 +25,6 @@
  */
 #undef SLOWDOWN_MASTER_CLOCK
 
-#define MCKRDY_TIMEOUT		1000
-#define MOSCRDY_TIMEOUT 	1000
-#define PLLALOCK_TIMEOUT	1000
-#define PLLBLOCK_TIMEOUT	1000
-
 pmc	.req	r0
 sdramc	.req	r1
 ramc1	.req	r2
@@ -41,60 +36,42 @@
  * Wait until master clock is ready (after switching master clock source)
  */
 	.macro wait_mckrdy
-	mov	tmp2, #MCKRDY_TIMEOUT
-1:	sub	tmp2, tmp2, #1
-	cmp	tmp2, #0
-	beq	2f
-	ldr	tmp1, [pmc, #AT91_PMC_SR]
+1:	ldr	tmp1, [pmc, #AT91_PMC_SR]
 	tst	tmp1, #AT91_PMC_MCKRDY
 	beq	1b
-2:
 	.endm
 
 /*
  * Wait until master oscillator has stabilized.
  */
 	.macro wait_moscrdy
-	mov	tmp2, #MOSCRDY_TIMEOUT
-1:	sub	tmp2, tmp2, #1
-	cmp	tmp2, #0
-	beq	2f
-	ldr	tmp1, [pmc, #AT91_PMC_SR]
+1:	ldr	tmp1, [pmc, #AT91_PMC_SR]
 	tst	tmp1, #AT91_PMC_MOSCS
 	beq	1b
-2:
 	.endm
 
 /*
  * Wait until PLLA has locked.
  */
 	.macro wait_pllalock
-	mov	tmp2, #PLLALOCK_TIMEOUT
-1:	sub	tmp2, tmp2, #1
-	cmp	tmp2, #0
-	beq	2f
-	ldr	tmp1, [pmc, #AT91_PMC_SR]
+1:	ldr	tmp1, [pmc, #AT91_PMC_SR]
 	tst	tmp1, #AT91_PMC_LOCKA
 	beq	1b
-2:
 	.endm
 
 /*
  * Wait until PLLB has locked.
  */
 	.macro wait_pllblock
-	mov	tmp2, #PLLBLOCK_TIMEOUT
-1:	sub	tmp2, tmp2, #1
-	cmp	tmp2, #0
-	beq	2f
-	ldr	tmp1, [pmc, #AT91_PMC_SR]
+1:	ldr	tmp1, [pmc, #AT91_PMC_SR]
 	tst	tmp1, #AT91_PMC_LOCKB
 	beq	1b
-2:
 	.endm
 
 	.text
 
+	.arm
+
 /* void at91_slow_clock(void __iomem *pmc, void __iomem *sdramc,
  *			void __iomem *ramc1, int memctrl)
  */
@@ -134,6 +111,16 @@
 	cmp	memctrl, #AT91_MEMCTRL_DDRSDR
 	bne	sdr_sr_enable
 
+	/* LPDDR1 --> force DDR2 mode during self-refresh */
+	ldr	tmp1, [sdramc, #AT91_DDRSDRC_MDR]
+	str	tmp1, .saved_sam9_mdr
+	bic	tmp1, tmp1, #~AT91_DDRSDRC_MD
+	cmp	tmp1, #AT91_DDRSDRC_MD_LOW_POWER_DDR
+	ldreq	tmp1, [sdramc, #AT91_DDRSDRC_MDR]
+	biceq	tmp1, tmp1, #AT91_DDRSDRC_MD
+	orreq	tmp1, tmp1, #AT91_DDRSDRC_MD_DDR2
+	streq	tmp1, [sdramc, #AT91_DDRSDRC_MDR]
+
 	/* prepare for DDRAM self-refresh mode */
 	ldr	tmp1, [sdramc, #AT91_DDRSDRC_LPR]
 	str	tmp1, .saved_sam9_lpr
@@ -142,14 +129,26 @@
 
 	/* figure out if we use the second ram controller */
 	cmp	ramc1, #0
-	ldrne	tmp2, [ramc1, #AT91_DDRSDRC_LPR]
-	strne	tmp2, .saved_sam9_lpr1
-	bicne	tmp2, #AT91_DDRSDRC_LPCB
-	orrne	tmp2, #AT91_DDRSDRC_LPCB_SELF_REFRESH
+	beq	ddr_no_2nd_ctrl
+
+	ldr	tmp2, [ramc1, #AT91_DDRSDRC_MDR]
+	str	tmp2, .saved_sam9_mdr1
+	bic	tmp2, tmp2, #~AT91_DDRSDRC_MD
+	cmp	tmp2, #AT91_DDRSDRC_MD_LOW_POWER_DDR
+	ldreq	tmp2, [ramc1, #AT91_DDRSDRC_MDR]
+	biceq	tmp2, tmp2, #AT91_DDRSDRC_MD
+	orreq	tmp2, tmp2, #AT91_DDRSDRC_MD_DDR2
+	streq	tmp2, [ramc1, #AT91_DDRSDRC_MDR]
+
+	ldr	tmp2, [ramc1, #AT91_DDRSDRC_LPR]
+	str	tmp2, .saved_sam9_lpr1
+	bic	tmp2, #AT91_DDRSDRC_LPCB
+	orr	tmp2, #AT91_DDRSDRC_LPCB_SELF_REFRESH
 
 	/* Enable DDRAM self-refresh mode */
+	str	tmp2, [ramc1, #AT91_DDRSDRC_LPR]
+ddr_no_2nd_ctrl:
 	str	tmp1, [sdramc, #AT91_DDRSDRC_LPR]
-	strne	tmp2, [ramc1, #AT91_DDRSDRC_LPR]
 
 	b	sdr_sr_done
 
@@ -208,6 +207,7 @@
 	/* Turn off the main oscillator */
 	ldr	tmp1, [pmc, #AT91_CKGR_MOR]
 	bic	tmp1, tmp1, #AT91_PMC_MOSCEN
+	orr	tmp1, tmp1, #AT91_PMC_KEY
 	str	tmp1, [pmc, #AT91_CKGR_MOR]
 
 	/* Wait for interrupt */
@@ -216,6 +216,7 @@
 	/* Turn on the main oscillator */
 	ldr	tmp1, [pmc, #AT91_CKGR_MOR]
 	orr	tmp1, tmp1, #AT91_PMC_MOSCEN
+	orr	tmp1, tmp1, #AT91_PMC_KEY
 	str	tmp1, [pmc, #AT91_CKGR_MOR]
 
 	wait_moscrdy
@@ -280,12 +281,17 @@
 	 */
 	cmp	memctrl, #AT91_MEMCTRL_DDRSDR
 	bne	sdr_en_restore
+	/* Restore MDR in case of LPDDR1 */
+	ldr	tmp1, .saved_sam9_mdr
+	str	tmp1, [sdramc, #AT91_DDRSDRC_MDR]
 	/* Restore LPR on AT91 with DDRAM */
 	ldr	tmp1, .saved_sam9_lpr
 	str	tmp1, [sdramc, #AT91_DDRSDRC_LPR]
 
 	/* if we use the second ram controller */
 	cmp	ramc1, #0
+	ldrne	tmp2, .saved_sam9_mdr1
+	strne	tmp2, [ramc1, #AT91_DDRSDRC_MDR]
 	ldrne	tmp2, .saved_sam9_lpr1
 	strne	tmp2, [ramc1, #AT91_DDRSDRC_LPR]
 
@@ -319,5 +325,11 @@
 .saved_sam9_lpr1:
 	.word 0
 
+.saved_sam9_mdr:
+	.word 0
+
+.saved_sam9_mdr1:
+	.word 0
+
 ENTRY(at91_slow_clock_sz)
 	.word .-at91_slow_clock
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 3f32c47..d2e9f12 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -126,8 +126,7 @@
  */
 void exynos_cpu_power_down(int cpu)
 {
-	if (cpu == 0 && (of_machine_is_compatible("samsung,exynos5420") ||
-		of_machine_is_compatible("samsung,exynos5800"))) {
+	if (cpu == 0 && (soc_is_exynos5420() || soc_is_exynos5800())) {
 		/*
 		 * Bypass power down for CPU0 during suspend. Check for
 		 * the SYS_PWR_REG value to decide if we are suspending
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index 20f2671..37266a8 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -161,6 +161,34 @@
 		of_genpd_add_provider_simple(np, &pd->pd);
 	}
 
+	/* Assign the child power domains to their parents */
+	for_each_compatible_node(np, NULL, "samsung,exynos4210-pd") {
+		struct generic_pm_domain *child_domain, *parent_domain;
+		struct of_phandle_args args;
+
+		args.np = np;
+		args.args_count = 0;
+		child_domain = of_genpd_get_from_provider(&args);
+		if (!child_domain)
+			continue;
+
+		if (of_parse_phandle_with_args(np, "power-domains",
+					 "#power-domain-cells", 0, &args) != 0)
+			continue;
+
+		parent_domain = of_genpd_get_from_provider(&args);
+		if (!parent_domain)
+			continue;
+
+		if (pm_genpd_add_subdomain(parent_domain, child_domain))
+			pr_warn("%s failed to add subdomain: %s\n",
+				parent_domain->name, child_domain->name);
+		else
+			pr_info("%s has as child subdomain: %s.\n",
+				parent_domain->name, child_domain->name);
+		of_node_put(np);
+	}
+
 	return 0;
 }
 arch_initcall(exynos4_pm_init_power_domain);
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 52e2b1a..318d127 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -87,8 +87,8 @@
 static u32 exynos_irqwake_intmask = 0xffffffff;
 
 static const struct exynos_wkup_irq exynos3250_wkup_irq[] = {
-	{ 73, BIT(1) }, /* RTC alarm */
-	{ 74, BIT(2) }, /* RTC tick */
+	{ 105, BIT(1) }, /* RTC alarm */
+	{ 106, BIT(2) }, /* RTC tick */
 	{ /* sentinel */ },
 };
 
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 4ad6e47..9de3412 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -211,8 +211,9 @@
 	 * set bit IOMUXC_GPR1[21].  Or the PTP clock must be from pad
 	 * (external OSC), and we need to clear the bit.
 	 */
-	clksel = ptp_clk == enet_ref ? IMX6Q_GPR1_ENET_CLK_SEL_ANATOP :
-				       IMX6Q_GPR1_ENET_CLK_SEL_PAD;
+	clksel = clk_is_match(ptp_clk, enet_ref) ?
+				IMX6Q_GPR1_ENET_CLK_SEL_ANATOP :
+				IMX6Q_GPR1_ENET_CLK_SEL_PAD;
 	gpr = syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr");
 	if (!IS_ERR(gpr))
 		regmap_update_bits(gpr, IOMUXC_GPR1,
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index 61bfe58..fc83204 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -20,6 +20,7 @@
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/delay.h>
+#include <linux/smc91x.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -46,15 +47,20 @@
 	[1] = {
 		.start	= MSM_GPIO_TO_INT(49),
 		.end	= MSM_GPIO_TO_INT(49),
-		.flags	= IORESOURCE_IRQ,
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
+static struct smc91x_platdata smc91x_platdata = {
+	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+};
+
 static struct platform_device smc91x_device = {
 	.name		= "smc91x",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(smc91x_resources),
 	.resource	= smc91x_resources,
+	.dev.platform_data = &smc91x_platdata,
 };
 
 static struct platform_device *devices[] __initdata = {
diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c
index 4c74861..10016a3 100644
--- a/arch/arm/mach-msm/board-qsd8x50.c
+++ b/arch/arm/mach-msm/board-qsd8x50.c
@@ -22,6 +22,7 @@
 #include <linux/usb/msm_hsusb.h>
 #include <linux/err.h>
 #include <linux/clkdev.h>
+#include <linux/smc91x.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -49,15 +50,20 @@
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
-		.flags = IORESOURCE_IRQ,
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
+static struct smc91x_platdata smc91x_platdata = {
+	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+};
+
 static struct platform_device smc91x_device = {
 	.name           = "smc91x",
 	.id             = 0,
 	.num_resources  = ARRAY_SIZE(smc91x_resources),
 	.resource       = smc91x_resources,
+	.dev.platform_data = &smc91x_platdata,
 };
 
 static int __init msm_init_smc91x(void)
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 2a2f4d5..25f1bee 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -720,6 +720,8 @@
 		return kasprintf(GFP_KERNEL, "OMAP4");
 	else if (soc_is_omap54xx())
 		return kasprintf(GFP_KERNEL, "OMAP5");
+	else if (soc_is_am33xx() || soc_is_am335x())
+		return kasprintf(GFP_KERNEL, "AM33xx");
 	else if (soc_is_am43xx())
 		return kasprintf(GFP_KERNEL, "AM43xx");
 	else if (soc_is_dra7xx())
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 92afb72..355b089 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1692,16 +1692,15 @@
 	if (ret == -EBUSY)
 		pr_warn("omap_hwmod: %s: failed to hardreset\n", oh->name);
 
-	if (!ret) {
+	if (oh->clkdm) {
 		/*
 		 * Set the clockdomain to HW_AUTO, assuming that the
 		 * previous state was HW_AUTO.
 		 */
-		if (oh->clkdm && hwsup)
+		if (hwsup)
 			clkdm_allow_idle(oh->clkdm);
-	} else {
-		if (oh->clkdm)
-			clkdm_hwmod_disable(oh->clkdm, oh);
+
+		clkdm_hwmod_disable(oh->clkdm, oh);
 	}
 
 	return ret;
@@ -2698,6 +2697,7 @@
 	INIT_LIST_HEAD(&oh->master_ports);
 	INIT_LIST_HEAD(&oh->slave_ports);
 	spin_lock_init(&oh->_lock);
+	lockdep_set_class(&oh->_lock, &oh->hwmod_key);
 
 	oh->_state = _HWMOD_STATE_REGISTERED;
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 9d4bec6e..9611c91 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -674,6 +674,7 @@
 	u32				_sysc_cache;
 	void __iomem			*_mpu_rt_va;
 	spinlock_t			_lock;
+	struct lock_class_key		hwmod_key; /* unique lock class */
 	struct list_head		node;
 	struct omap_hwmod_ocp_if	*_mpu_port;
 	unsigned int			(*xlate_irq)(unsigned int);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index e8692e7..16fe7a1 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1466,55 +1466,18 @@
  *
  */
 
-static struct omap_hwmod_class dra7xx_pcie_hwmod_class = {
+static struct omap_hwmod_class dra7xx_pciess_hwmod_class = {
 	.name	= "pcie",
 };
 
 /* pcie1 */
-static struct omap_hwmod dra7xx_pcie1_hwmod = {
+static struct omap_hwmod dra7xx_pciess1_hwmod = {
 	.name		= "pcie1",
-	.class		= &dra7xx_pcie_hwmod_class,
+	.class		= &dra7xx_pciess_hwmod_class,
 	.clkdm_name	= "pcie_clkdm",
 	.main_clk	= "l4_root_clk_div",
 	.prcm = {
 		.omap4 = {
-			.clkctrl_offs	= DRA7XX_CM_PCIE_CLKSTCTRL_OFFSET,
-			.modulemode	= MODULEMODE_SWCTRL,
-		},
-	},
-};
-
-/* pcie2 */
-static struct omap_hwmod dra7xx_pcie2_hwmod = {
-	.name		= "pcie2",
-	.class		= &dra7xx_pcie_hwmod_class,
-	.clkdm_name	= "pcie_clkdm",
-	.main_clk	= "l4_root_clk_div",
-	.prcm = {
-		.omap4 = {
-			.clkctrl_offs = DRA7XX_CM_PCIE_CLKSTCTRL_OFFSET,
-			.modulemode   = MODULEMODE_SWCTRL,
-		},
-	},
-};
-
-/*
- * 'PCIE PHY' class
- *
- */
-
-static struct omap_hwmod_class dra7xx_pcie_phy_hwmod_class = {
-	.name	= "pcie-phy",
-};
-
-/* pcie1 phy */
-static struct omap_hwmod dra7xx_pcie1_phy_hwmod = {
-	.name		= "pcie1-phy",
-	.class		= &dra7xx_pcie_phy_hwmod_class,
-	.clkdm_name	= "l3init_clkdm",
-	.main_clk	= "l4_root_clk_div",
-	.prcm = {
-		.omap4 = {
 			.clkctrl_offs = DRA7XX_CM_L3INIT_PCIESS1_CLKCTRL_OFFSET,
 			.context_offs = DRA7XX_RM_L3INIT_PCIESS1_CONTEXT_OFFSET,
 			.modulemode   = MODULEMODE_SWCTRL,
@@ -1522,11 +1485,11 @@
 	},
 };
 
-/* pcie2 phy */
-static struct omap_hwmod dra7xx_pcie2_phy_hwmod = {
-	.name		= "pcie2-phy",
-	.class		= &dra7xx_pcie_phy_hwmod_class,
-	.clkdm_name	= "l3init_clkdm",
+/* pcie2 */
+static struct omap_hwmod dra7xx_pciess2_hwmod = {
+	.name		= "pcie2",
+	.class		= &dra7xx_pciess_hwmod_class,
+	.clkdm_name	= "pcie_clkdm",
 	.main_clk	= "l4_root_clk_div",
 	.prcm = {
 		.omap4 = {
@@ -2877,50 +2840,34 @@
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-/* l3_main_1 -> pcie1 */
-static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pcie1 = {
+/* l3_main_1 -> pciess1 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pciess1 = {
 	.master		= &dra7xx_l3_main_1_hwmod,
-	.slave		= &dra7xx_pcie1_hwmod,
+	.slave		= &dra7xx_pciess1_hwmod,
 	.clk		= "l3_iclk_div",
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-/* l4_cfg -> pcie1 */
-static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie1 = {
+/* l4_cfg -> pciess1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pciess1 = {
 	.master		= &dra7xx_l4_cfg_hwmod,
-	.slave		= &dra7xx_pcie1_hwmod,
+	.slave		= &dra7xx_pciess1_hwmod,
 	.clk		= "l4_root_clk_div",
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-/* l3_main_1 -> pcie2 */
-static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pcie2 = {
+/* l3_main_1 -> pciess2 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pciess2 = {
 	.master		= &dra7xx_l3_main_1_hwmod,
-	.slave		= &dra7xx_pcie2_hwmod,
+	.slave		= &dra7xx_pciess2_hwmod,
 	.clk		= "l3_iclk_div",
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-/* l4_cfg -> pcie2 */
-static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie2 = {
+/* l4_cfg -> pciess2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pciess2 = {
 	.master		= &dra7xx_l4_cfg_hwmod,
-	.slave		= &dra7xx_pcie2_hwmod,
-	.clk		= "l4_root_clk_div",
-	.user		= OCP_USER_MPU | OCP_USER_SDMA,
-};
-
-/* l4_cfg -> pcie1 phy */
-static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie1_phy = {
-	.master		= &dra7xx_l4_cfg_hwmod,
-	.slave		= &dra7xx_pcie1_phy_hwmod,
-	.clk		= "l4_root_clk_div",
-	.user		= OCP_USER_MPU | OCP_USER_SDMA,
-};
-
-/* l4_cfg -> pcie2 phy */
-static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie2_phy = {
-	.master		= &dra7xx_l4_cfg_hwmod,
-	.slave		= &dra7xx_pcie2_phy_hwmod,
+	.slave		= &dra7xx_pciess2_hwmod,
 	.clk		= "l4_root_clk_div",
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
@@ -3327,12 +3274,10 @@
 	&dra7xx_l4_cfg__mpu,
 	&dra7xx_l4_cfg__ocp2scp1,
 	&dra7xx_l4_cfg__ocp2scp3,
-	&dra7xx_l3_main_1__pcie1,
-	&dra7xx_l4_cfg__pcie1,
-	&dra7xx_l3_main_1__pcie2,
-	&dra7xx_l4_cfg__pcie2,
-	&dra7xx_l4_cfg__pcie1_phy,
-	&dra7xx_l4_cfg__pcie2_phy,
+	&dra7xx_l3_main_1__pciess1,
+	&dra7xx_l4_cfg__pciess1,
+	&dra7xx_l3_main_1__pciess2,
+	&dra7xx_l4_cfg__pciess2,
 	&dra7xx_l3_main_1__qspi,
 	&dra7xx_l4_per3__rtcss,
 	&dra7xx_l4_cfg__sata,
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 190fa43..e642b07 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -173,6 +173,7 @@
 
 static void __init omap3_evm_legacy_init(void)
 {
+	hsmmc2_internal_input_clk();
 	legacy_init_wl12xx(WL12XX_REFCLOCK_38, 0, 149);
 }
 
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index a08a617..d6d6bc3 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -252,10 +252,10 @@
 {
 	saved_mask[0] =
 		omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
-					OMAP4_PRM_IRQSTATUS_MPU_OFFSET);
+					OMAP4_PRM_IRQENABLE_MPU_OFFSET);
 	saved_mask[1] =
 		omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST,
-					OMAP4_PRM_IRQSTATUS_MPU_2_OFFSET);
+					OMAP4_PRM_IRQENABLE_MPU_2_OFFSET);
 
 	omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST,
 				 OMAP4_PRM_IRQENABLE_MPU_OFFSET);
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index 343c4e3..f6d02e4 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -36,6 +36,7 @@
 #include <linux/platform_data/video-pxafb.h>
 #include <mach/bitfield.h>
 #include <linux/platform_data/mmc-pxamci.h>
+#include <linux/smc91x.h>
 
 #include "generic.h"
 #include "devices.h"
@@ -81,11 +82,16 @@
 	}
 };
 
+static struct smc91x_platdata smc91x_platdata = {
+	.flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+};
+
 static struct platform_device smc91x_device = {
 	.name		= "smc91x",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(smc91x_resources),
 	.resource	= smc91x_resources,
+	.dev.platform_data = &smc91x_platdata,
 };
 
 static void idp_backlight_power(int on)
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 0eecd83..89a7c06 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -11,6 +11,7 @@
  *  it under the terms of the GNU General Public License version 2 as
  *  published by the Free Software Foundation.
  */
+#include <linux/bitops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -40,7 +41,6 @@
 #define ICHP_VAL_IRQ		(1 << 31)
 #define ICHP_IRQ(i)		(((i) >> 16) & 0x7fff)
 #define IPR_VALID		(1 << 31)
-#define IRQ_BIT(n)		(((n) - PXA_IRQ(0)) & 0x1f)
 
 #define MAX_INTERNAL_IRQS	128
 
@@ -51,6 +51,7 @@
 static void __iomem *pxa_irq_base;
 static int pxa_internal_irq_nr;
 static bool cpu_has_ipr;
+static struct irq_domain *pxa_irq_domain;
 
 static inline void __iomem *irq_base(int i)
 {
@@ -66,18 +67,20 @@
 void pxa_mask_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t irq = irqd_to_hwirq(d);
 	uint32_t icmr = __raw_readl(base + ICMR);
 
-	icmr &= ~(1 << IRQ_BIT(d->irq));
+	icmr &= ~BIT(irq & 0x1f);
 	__raw_writel(icmr, base + ICMR);
 }
 
 void pxa_unmask_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t irq = irqd_to_hwirq(d);
 	uint32_t icmr = __raw_readl(base + ICMR);
 
-	icmr |= 1 << IRQ_BIT(d->irq);
+	icmr |= BIT(irq & 0x1f);
 	__raw_writel(icmr, base + ICMR);
 }
 
@@ -118,40 +121,63 @@
 	} while (1);
 }
 
-void __init pxa_init_irq(int irq_nr, int (*fn)(struct irq_data *, unsigned int))
+static int pxa_irq_map(struct irq_domain *h, unsigned int virq,
+		       irq_hw_number_t hw)
 {
-	int irq, i, n;
+	void __iomem *base = irq_base(hw / 32);
 
-	BUG_ON(irq_nr > MAX_INTERNAL_IRQS);
+	/* initialize interrupt priority */
+	if (cpu_has_ipr)
+		__raw_writel(hw | IPR_VALID, pxa_irq_base + IPR(hw));
+
+	irq_set_chip_and_handler(virq, &pxa_internal_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(virq, base);
+	set_irq_flags(virq, IRQF_VALID);
+
+	return 0;
+}
+
+static struct irq_domain_ops pxa_irq_ops = {
+	.map    = pxa_irq_map,
+	.xlate  = irq_domain_xlate_onecell,
+};
+
+static __init void
+pxa_init_irq_common(struct device_node *node, int irq_nr,
+		    int (*fn)(struct irq_data *, unsigned int))
+{
+	int n;
 
 	pxa_internal_irq_nr = irq_nr;
-	cpu_has_ipr = !cpu_is_pxa25x();
-	pxa_irq_base = io_p2v(0x40d00000);
+	pxa_irq_domain = irq_domain_add_legacy(node, irq_nr,
+					       PXA_IRQ(0), 0,
+					       &pxa_irq_ops, NULL);
+	if (!pxa_irq_domain)
+		panic("Unable to add PXA IRQ domain\n");
+	irq_set_default_host(pxa_irq_domain);
 
 	for (n = 0; n < irq_nr; n += 32) {
 		void __iomem *base = irq_base(n >> 5);
 
 		__raw_writel(0, base + ICMR);	/* disable all IRQs */
 		__raw_writel(0, base + ICLR);	/* all IRQs are IRQ, not FIQ */
-		for (i = n; (i < (n + 32)) && (i < irq_nr); i++) {
-			/* initialize interrupt priority */
-			if (cpu_has_ipr)
-				__raw_writel(i | IPR_VALID, pxa_irq_base + IPR(i));
-
-			irq = PXA_IRQ(i);
-			irq_set_chip_and_handler(irq, &pxa_internal_irq_chip,
-						 handle_level_irq);
-			irq_set_chip_data(irq, base);
-			set_irq_flags(irq, IRQF_VALID);
-		}
 	}
-
 	/* only unmasked interrupts kick us out of idle */
 	__raw_writel(1, irq_base(0) + ICCR);
 
 	pxa_internal_irq_chip.irq_set_wake = fn;
 }
 
+void __init pxa_init_irq(int irq_nr, int (*fn)(struct irq_data *, unsigned int))
+{
+	BUG_ON(irq_nr > MAX_INTERNAL_IRQS);
+
+	pxa_irq_base = io_p2v(0x40d00000);
+	cpu_has_ipr = !cpu_is_pxa25x();
+	pxa_init_irq_common(NULL, irq_nr, fn);
+}
+
 #ifdef CONFIG_PM
 static unsigned long saved_icmr[MAX_INTERNAL_IRQS/32];
 static unsigned long saved_ipr[MAX_INTERNAL_IRQS];
@@ -203,30 +229,6 @@
 };
 
 #ifdef CONFIG_OF
-static struct irq_domain *pxa_irq_domain;
-
-static int pxa_irq_map(struct irq_domain *h, unsigned int virq,
-		       irq_hw_number_t hw)
-{
-	void __iomem *base = irq_base(hw / 32);
-
-	/* initialize interrupt priority */
-	if (cpu_has_ipr)
-		__raw_writel(hw | IPR_VALID, pxa_irq_base + IPR(hw));
-
-	irq_set_chip_and_handler(hw, &pxa_internal_irq_chip,
-				 handle_level_irq);
-	irq_set_chip_data(hw, base);
-	set_irq_flags(hw, IRQF_VALID);
-
-	return 0;
-}
-
-static struct irq_domain_ops pxa_irq_ops = {
-	.map    = pxa_irq_map,
-	.xlate  = irq_domain_xlate_onecell,
-};
-
 static const struct of_device_id intc_ids[] __initconst = {
 	{ .compatible = "marvell,pxa-intc", },
 	{}
@@ -236,7 +238,7 @@
 {
 	struct device_node *node;
 	struct resource res;
-	int n, ret;
+	int ret;
 
 	node = of_find_matching_node(NULL, intc_ids);
 	if (!node) {
@@ -267,23 +269,6 @@
 		return;
 	}
 
-	pxa_irq_domain = irq_domain_add_legacy(node, pxa_internal_irq_nr, 0, 0,
-					       &pxa_irq_ops, NULL);
-	if (!pxa_irq_domain)
-		panic("Unable to add PXA IRQ domain\n");
-
-	irq_set_default_host(pxa_irq_domain);
-
-	for (n = 0; n < pxa_internal_irq_nr; n += 32) {
-		void __iomem *base = irq_base(n >> 5);
-
-		__raw_writel(0, base + ICMR);	/* disable all IRQs */
-		__raw_writel(0, base + ICLR);	/* all IRQs are IRQ, not FIQ */
-	}
-
-	/* only unmasked interrupts kick us out of idle */
-	__raw_writel(1, irq_base(0) + ICCR);
-
-	pxa_internal_irq_chip.irq_set_wake = fn;
+	pxa_init_irq_common(node, pxa_internal_irq_nr, fn);
 }
 #endif /* CONFIG_OF */
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index ad777b3..eaee2c2 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -24,6 +24,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/pwm_backlight.h>
+#include <linux/smc91x.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>
@@ -189,15 +190,20 @@
 	[1] = {
 		.start	= LPD270_ETHERNET_IRQ,
 		.end	= LPD270_ETHERNET_IRQ,
-		.flags	= IORESOURCE_IRQ,
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
 
+struct smc91x_platdata smc91x_platdata = {
+	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+};
+
 static struct platform_device smc91x_device = {
 	.name		= "smc91x",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(smc91x_resources),
 	.resource	= smc91x_resources,
+	.dev.platform_data = &smc91x_platdata,
 };
 
 static struct resource lpd270_flash_resources[] = {
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 205f9bf..ac2ae5c 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -412,7 +412,7 @@
 };
 
 static struct platform_device can_regulator_device = {
-	.name	= "reg-fixed-volage",
+	.name	= "reg-fixed-voltage",
 	.id	= 0,
 	.dev	= {
 		.platform_data	= &can_regulator_pdata,
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 850e506..c309593 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -28,6 +28,7 @@
 #include <linux/platform_data/video-clcd-versatile.h>
 #include <linux/io.h>
 #include <linux/smsc911x.h>
+#include <linux/smc91x.h>
 #include <linux/ata_platform.h>
 #include <linux/amba/mmci.h>
 #include <linux/gfp.h>
@@ -94,6 +95,10 @@
 	.phy_interface	= PHY_INTERFACE_MODE_MII,
 };
 
+static struct smc91x_platdata smc91x_platdata = {
+	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+};
+
 static struct platform_device realview_eth_device = {
 	.name		= "smsc911x",
 	.id		= 0,
@@ -107,6 +112,8 @@
 	realview_eth_device.resource = res;
 	if (strcmp(realview_eth_device.name, "smsc911x") == 0)
 		realview_eth_device.dev.platform_data = &smsc911x_config;
+	else
+		realview_eth_device.dev.platform_data = &smc91x_platdata;
 
 	return platform_device_register(&realview_eth_device);
 }
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index 64c88d6..b3869cb 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -234,7 +234,7 @@
 	[1] = {
 		.start		= IRQ_EB_ETH,
 		.end		= IRQ_EB_ETH,
-		.flags		= IORESOURCE_IRQ,
+		.flags		= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE,
 	},
 };
 
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 169262e..af868d25 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/serial_core.h>
 #include <linux/slab.h>
+#include <linux/smc91x.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
@@ -258,12 +259,17 @@
 			0x02000000, "smc91x-attrib"),
 		{ .flags = IORESOURCE_IRQ },
 	};
+	struct smc91x_platdata smc91x_platdata = {
+		.flags = SMC91X_USE_8BIT | SMC91X_IO_SHIFT_2 | SMC91X_NOWAIT,
+	};
 	struct platform_device_info smc91x_devinfo = {
 		.parent = &dev->dev,
 		.name = "smc91x",
 		.id = 0,
 		.res = smc91x_resources,
 		.num_res = ARRAY_SIZE(smc91x_resources),
+		.data = &smc91x_platdata,
+		.size_data = sizeof(smc91x_platdata),
 	};
 	int ret, irq;
 
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 0912618..1525d7b 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -11,6 +11,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/mtd/partitions.h>
+#include <linux/smc91x.h>
 
 #include <mach/hardware.h>
 #include <asm/setup.h>
@@ -43,12 +44,18 @@
 #endif
 };
 
+static struct smc91x_platdata smc91x_platdata = {
+	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+};
 
 static struct platform_device smc91x_device = {
 	.name		= "smc91x",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(smc91x_resources),
 	.resource	= smc91x_resources,
+	.dev = {
+		.platform_data  = &smc91x_platdata,
+	},
 };
 
 static struct platform_device *devices[] __initdata = {
diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h
index 483cb46..a0f3b1c 100644
--- a/arch/arm/mach-socfpga/core.h
+++ b/arch/arm/mach-socfpga/core.h
@@ -45,6 +45,6 @@
 
 extern unsigned long socfpga_cpu1start_addr;
 
-#define SOCFPGA_SCU_VIRT_BASE   0xfffec000
+#define SOCFPGA_SCU_VIRT_BASE   0xfee00000
 
 #endif
diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c
index 383d61e..f5e597c 100644
--- a/arch/arm/mach-socfpga/socfpga.c
+++ b/arch/arm/mach-socfpga/socfpga.c
@@ -23,6 +23,7 @@
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/cacheflush.h>
 
 #include "core.h"
 
@@ -73,6 +74,10 @@
 			(u32 *) &socfpga_cpu1start_addr))
 		pr_err("SMP: Need cpu1-start-addr in device tree.\n");
 
+	/* Ensure that socfpga_cpu1start_addr is visible to other CPUs */
+	smp_wmb();
+	sync_cache_w(&socfpga_cpu1start_addr);
+
 	sys_manager_base_addr = of_iomap(np, 0);
 
 	np = of_find_compatible_node(NULL, NULL, "altr,rst-mgr");
diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c
index b067390..b373aca 100644
--- a/arch/arm/mach-sti/board-dt.c
+++ b/arch/arm/mach-sti/board-dt.c
@@ -18,6 +18,7 @@
 	"st,stih415",
 	"st,stih416",
 	"st,stih407",
+	"st,stih410",
 	"st,stih418",
 	NULL
 };
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index a77604f..81502b9 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -1,10 +1,12 @@
 menuconfig ARCH_SUNXI
 	bool "Allwinner SoCs" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
+	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
 	select PINCTRL
 	select SUN4I_TIMER
+	select RESET_CONTROLLER
 
 if ARCH_SUNXI
 
@@ -20,10 +22,8 @@
 config MACH_SUN6I
 	bool "Allwinner A31 (sun6i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 	select SUN5I_HSTIMER
 
 config MACH_SUN7I
@@ -37,16 +37,12 @@
 config MACH_SUN8I
 	bool "Allwinner A23 (sun8i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 
 config MACH_SUN9I
 	bool "Allwinner (sun9i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
-	select RESET_CONTROLLER
 
 endif
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c6c7696..8f15f70 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1131,23 +1131,22 @@
 	}
 
 	ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_512K);
-	if (ret)
-		return;
-
-	switch (assoc) {
-	case 16:
-		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
-		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		break;
-	case 8:
-		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		break;
-	default:
-		pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n",
-		       assoc);
-		break;
+	if (!ret) {
+		switch (assoc) {
+		case 16:
+			*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
+			*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			break;
+		case 8:
+			*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			break;
+		default:
+			pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n",
+			       assoc);
+			break;
+		}
 	}
 
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 170a116..c274476 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -171,7 +171,7 @@
 	 */
 	if (sizeof(mask) != sizeof(dma_addr_t) &&
 	    mask > (dma_addr_t)~0 &&
-	    dma_to_pfn(dev, ~0) < max_pfn) {
+	    dma_to_pfn(dev, ~0) < max_pfn - 1) {
 		if (warn) {
 			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
 				 mask);
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index a982dc3..6333d9c 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -552,6 +552,7 @@
 
 	pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n",
 		inf->name, fsr, addr);
+	show_pte(current->mm, addr);
 
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index 004e35c..cf30daf 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -49,7 +49,10 @@
 		WARN_ON_ONCE(1);
 	}
 
-	if (!is_module_address(start) || !is_module_address(end - 1))
+	if (start < MODULES_VADDR || start >= MODULES_END)
+		return -EINVAL;
+
+	if (end < MODULES_VADDR || start >= MODULES_END)
 		return -EINVAL;
 
 	data.set_mask = set_mask;
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index db10169..8ca94d3 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -799,6 +799,7 @@
 	struct device *dev = &pdev->dev;
 	const struct of_device_id *match;
 	const struct dmtimer_platform_data *pdata;
+	int ret;
 
 	match = of_match_device(of_match_ptr(omap_timer_match), dev);
 	pdata = match ? match->data : dev->platform_data;
@@ -860,7 +861,12 @@
 	}
 
 	if (!timer->reserved) {
-		pm_runtime_get_sync(dev);
+		ret = pm_runtime_get_sync(dev);
+		if (ret < 0) {
+			dev_err(dev, "%s: pm_runtime_get_sync failed!\n",
+				__func__);
+			goto err_get_sync;
+		}
 		__omap_dm_timer_init_regs(timer);
 		pm_runtime_put(dev);
 	}
@@ -873,6 +879,11 @@
 	dev_dbg(dev, "Device Probed.\n");
 
 	return 0;
+
+err_get_sync:
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	return ret;
 }
 
 /**
@@ -899,6 +910,8 @@
 		}
 	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
+	pm_runtime_disable(&pdev->dev);
+
 	return ret;
 }
 
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index f1ad9c2..a857794 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -622,7 +622,7 @@
 		};
 
 		sgenet0: ethernet@1f210000 {
-			compatible = "apm,xgene-enet";
+			compatible = "apm,xgene1-sgenet";
 			status = "disabled";
 			reg = <0x0 0x1f210000 0x0 0xd100>,
 			      <0x0 0x1f200000 0x0 0Xc300>,
@@ -636,7 +636,7 @@
 		};
 
 		xgenet: ethernet@1f610000 {
-			compatible = "apm,xgene-enet";
+			compatible = "apm,xgene1-xgenet";
 			status = "disabled";
 			reg = <0x0 0x1f610000 0x0 0xd100>,
 			      <0x0 0x1f600000 0x0 0Xc300>,
diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dts b/arch/arm64/boot/dts/arm/foundation-v8.dts
index 27f3296..4eac8dc 100644
--- a/arch/arm64/boot/dts/arm/foundation-v8.dts
+++ b/arch/arm64/boot/dts/arm/foundation-v8.dts
@@ -34,6 +34,7 @@
 			reg = <0x0 0x0>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
 		};
 		cpu@1 {
 			device_type = "cpu";
@@ -41,6 +42,7 @@
 			reg = <0x0 0x1>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
 		};
 		cpu@2 {
 			device_type = "cpu";
@@ -48,6 +50,7 @@
 			reg = <0x0 0x2>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
 		};
 		cpu@3 {
 			device_type = "cpu";
@@ -55,6 +58,11 @@
 			reg = <0x0 0x3>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
+		};
+
+		L2_0: l2-cache0 {
+			compatible = "cache";
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
index ea2b566..c9b89ef 100644
--- a/arch/arm64/boot/dts/arm/juno-clocks.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
@@ -8,7 +8,7 @@
  */
 
 	/* SoC fixed clocks */
-	soc_uartclk: refclk72738khz {
+	soc_uartclk: refclk7273800hz {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <7273800>;
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
index d429129..133ee59 100644
--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -39,6 +39,7 @@
 			reg = <0x0 0x0>;
 			device_type = "cpu";
 			enable-method = "psci";
+			next-level-cache = <&A57_L2>;
 		};
 
 		A57_1: cpu@1 {
@@ -46,6 +47,7 @@
 			reg = <0x0 0x1>;
 			device_type = "cpu";
 			enable-method = "psci";
+			next-level-cache = <&A57_L2>;
 		};
 
 		A53_0: cpu@100 {
@@ -53,6 +55,7 @@
 			reg = <0x0 0x100>;
 			device_type = "cpu";
 			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
 		};
 
 		A53_1: cpu@101 {
@@ -60,6 +63,7 @@
 			reg = <0x0 0x101>;
 			device_type = "cpu";
 			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
 		};
 
 		A53_2: cpu@102 {
@@ -67,6 +71,7 @@
 			reg = <0x0 0x102>;
 			device_type = "cpu";
 			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
 		};
 
 		A53_3: cpu@103 {
@@ -74,6 +79,15 @@
 			reg = <0x0 0x103>;
 			device_type = "cpu";
 			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+		};
+
+		A57_L2: l2-cache0 {
+			compatible = "cache";
+		};
+
+		A53_L2: l2-cache1 {
+			compatible = "cache";
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts
index efc59b3..20addab 100644
--- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts
+++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts
@@ -37,6 +37,7 @@
 			reg = <0x0 0x0>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
 		};
 		cpu@1 {
 			device_type = "cpu";
@@ -44,6 +45,7 @@
 			reg = <0x0 0x1>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
 		};
 		cpu@2 {
 			device_type = "cpu";
@@ -51,6 +53,7 @@
 			reg = <0x0 0x2>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
 		};
 		cpu@3 {
 			device_type = "cpu";
@@ -58,6 +61,11 @@
 			reg = <0x0 0x3>;
 			enable-method = "spin-table";
 			cpu-release-addr = <0x0 0x8000fff8>;
+			next-level-cache = <&L2_0>;
+		};
+
+		L2_0: l2-cache0 {
+			compatible = "cache";
 		};
 	};
 
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 5720608..abb79b3 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -29,7 +29,7 @@
 obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
 aes-neon-blk-y := aes-glue-neon.o aes-neon.o
 
-AFLAGS_aes-ce.o		:= -DINTERLEAVE=2 -DINTERLEAVE_INLINE
+AFLAGS_aes-ce.o		:= -DINTERLEAVE=4
 AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 
 CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 5901480..750bac4 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -20,6 +20,9 @@
 #error "Only include this from assembly code"
 #endif
 
+#ifndef __ASM_ASSEMBLER_H
+#define __ASM_ASSEMBLER_H
+
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 
@@ -155,3 +158,5 @@
 #endif
 	orr	\rd, \lbits, \hbits, lsl #32
 	.endm
+
+#endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index cb95930..d8c25b7 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -246,14 +246,30 @@
 	__ret; \
 })
 
-#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define _protect_cmpxchg_local(pcp, o, n)			\
+({								\
+	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
+	preempt_disable();					\
+	__ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);	\
+	preempt_enable();					\
+	__ret;							\
+})
 
-#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
-	cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
-				o1, o2, n1, n2)
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
+({									\
+	int __ret;							\
+	preempt_disable();						\
+	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
+					raw_cpu_ptr(&(ptr2)),		\
+					o1, o2, n1, n2);		\
+	preempt_enable();						\
+	__ret;								\
+})
 
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
index 0710654..c60643f1 100644
--- a/arch/arm64/include/asm/cpuidle.h
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_CPUIDLE_H
 #define __ASM_CPUIDLE_H
 
+#include <asm/proc-fns.h>
+
 #ifdef CONFIG_CPU_IDLE
 extern int cpu_init_idle(unsigned int cpu);
 extern int cpu_suspend(unsigned long arg);
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index e2ff32a..d2f4942 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -264,8 +264,10 @@
 __AARCH64_INSN_FUNCS(bics,	0x7F200000, 0x6A200000)
 __AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
 __AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
-__AARCH64_INSN_FUNCS(cbz,	0xFE000000, 0x34000000)
-__AARCH64_INSN_FUNCS(cbnz,	0xFE000000, 0x35000000)
+__AARCH64_INSN_FUNCS(cbz,	0x7F000000, 0x34000000)
+__AARCH64_INSN_FUNCS(cbnz,	0x7F000000, 0x35000000)
+__AARCH64_INSN_FUNCS(tbz,	0x7F000000, 0x36000000)
+__AARCH64_INSN_FUNCS(tbnz,	0x7F000000, 0x37000000)
 __AARCH64_INSN_FUNCS(bcond,	0xFF000010, 0x54000000)
 __AARCH64_INSN_FUNCS(svc,	0xFFE0001F, 0xD4000001)
 __AARCH64_INSN_FUNCS(hvc,	0xFFE0001F, 0xD4000002)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 94674eb..54bb4ba 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -129,6 +129,9 @@
  * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
  * not known to exist and will break with this configuration.
  *
+ * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time
+ * (see hyp-init.S).
+ *
  * Note that when using 4K pages, we concatenate two first level page tables
  * together.
  *
@@ -138,7 +141,6 @@
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
@@ -150,7 +152,6 @@
 #else
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6458b53..bbfb600 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@
 #define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
 #define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
+#define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
 /*
  * If we are concatenating first level stage-2 page tables, we would have less
  * than or equal to 16 pointers in the fake PGD, because that's what the
@@ -171,43 +173,6 @@
 #define KVM_PREALLOC_LEVEL	(0)
 #endif
 
-/**
- * kvm_prealloc_hwpgd - allocate inital table for VTTBR
- * @kvm:	The KVM struct pointer for the VM.
- * @pgd:	The kernel pseudo pgd
- *
- * When the kernel uses more levels of page tables than the guest, we allocate
- * a fake PGD and pre-populate it to point to the next-level page table, which
- * will be the real initial page table pointed to by the VTTBR.
- *
- * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
- * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
- * allocate 2 consecutive PUD pages.
- */
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	unsigned int i;
-	unsigned long hwpgd;
-
-	if (KVM_PREALLOC_LEVEL == 0)
-		return 0;
-
-	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
-	if (!hwpgd)
-		return -ENOMEM;
-
-	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
-		if (KVM_PREALLOC_LEVEL == 1)
-			pgd_populate(NULL, pgd + i,
-				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
-		else if (KVM_PREALLOC_LEVEL == 2)
-			pud_populate(NULL, pud_offset(pgd, 0) + i,
-				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
-	}
-
-	return 0;
-}
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	pgd_t *pgd = kvm->arch.pgd;
@@ -224,12 +189,11 @@
 	return pmd_offset(pud, 0);
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	if (KVM_PREALLOC_LEVEL > 0) {
-		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
-		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
-	}
+	if (KVM_PREALLOC_LEVEL > 0)
+		return PTRS_PER_S2_PGD * PAGE_SIZE;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 static inline bool kvm_page_empty(void *ptr)
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a9eee33..101a42b 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@
 {
 	unsigned int cpu = smp_processor_id();
 
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 09da25b..4fde8c1 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -204,25 +204,47 @@
 	return ret;
 }
 
-#define _percpu_add(pcp, val) \
-	__percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+#define _percpu_read(pcp)						\
+({									\
+	typeof(pcp) __retval;						\
+	preempt_disable();						\
+	__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), 	\
+					      sizeof(pcp));		\
+	preempt_enable();						\
+	__retval;							\
+})
 
-#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val))
+#define _percpu_write(pcp, val)						\
+do {									\
+	preempt_disable();						\
+	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), 	\
+				sizeof(pcp));				\
+	preempt_enable();						\
+} while(0)								\
+
+#define _pcp_protect(operation, pcp, val)			\
+({								\
+	typeof(pcp) __retval;					\
+	preempt_disable();					\
+	__retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)),	\
+					  (val), sizeof(pcp));	\
+	preempt_enable();					\
+	__retval;						\
+})
+
+#define _percpu_add(pcp, val) \
+	_pcp_protect(__percpu_add, pcp, val)
+
+#define _percpu_add_return(pcp, val) _percpu_add(pcp, val)
 
 #define _percpu_and(pcp, val) \
-	__percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+	_pcp_protect(__percpu_and, pcp, val)
 
 #define _percpu_or(pcp, val) \
-	__percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
-
-#define _percpu_read(pcp) (typeof(pcp))	\
-	(__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp)))
-
-#define _percpu_write(pcp, val) \
-	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))
+	_pcp_protect(__percpu_or, pcp, val)
 
 #define _percpu_xchg(pcp, val) (typeof(pcp)) \
-	(__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)))
+	_pcp_protect(__percpu_xchg, pcp, (unsigned long)(val))
 
 #define this_cpu_add_1(pcp, val) _percpu_add(pcp, val)
 #define this_cpu_add_2(pcp, val) _percpu_add(pcp, val)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 16449c5..800ec0e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -460,7 +460,7 @@
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE;
+			      PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84..941c375 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -39,7 +39,11 @@
 
 #include <asm/memory.h>
 
-#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
+#define cpu_switch_mm(pgd,mm)				\
+do {							\
+	BUG_ON(pgd == swapper_pg_dir);			\
+	cpu_do_switch_mm(virt_to_phys(pgd),mm);		\
+} while (0)
 
 #define cpu_get_pgd()					\
 ({							\
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index f9be30e..20e9591 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -45,7 +45,8 @@
 #define STACK_TOP		STACK_TOP_MAX
 #endif /* CONFIG_COMPAT */
 
-#define ARCH_LOW_ADDRESS_LIMIT	PHYS_MASK
+extern phys_addr_t arm64_dma_phys_limit;
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
 #endif /* __KERNEL__ */
 
 struct debug_info {
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index c028fe3..53d9c35 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -48,6 +48,7 @@
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	pgtable_page_dtor(pte);
 	tlb_remove_entry(tlb, pte);
 }
@@ -56,6 +57,7 @@
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -64,6 +66,7 @@
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 73f0ce5..c3bb05b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -24,11 +24,6 @@
 #include <linux/sched.h>
 #include <asm/cputype.h>
 
-extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long, struct vm_area_struct *);
-extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long);
-
-extern struct cpu_tlb_fns cpu_tlb;
-
 /*
  *	TLB Management
  *	==============
@@ -149,6 +144,19 @@
 }
 
 /*
+ * Used to invalidate the TLB (walk caches) corresponding to intermediate page
+ * table levels (pgd/pud/pmd).
+ */
+static inline void __flush_tlb_pgtable(struct mm_struct *mm,
+				       unsigned long uaddr)
+{
+	unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48);
+
+	dsb(ishst);
+	asm("tlbi	vae1is, %0" : : "r" (addr));
+	dsb(ish);
+}
+/*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */
 static inline void update_mmu_cache(struct vm_area_struct *vma,
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index bef04af..5ee07ee 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -15,8 +15,9 @@
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o	\
-			   cpuinfo.o cpu_errata.o alternative.o cacheinfo.o
+			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o	\
+			   return_address.o cpuinfo.o cpu_errata.o		\
+			   alternative.o cacheinfo.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o entry32.o		\
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index b42c7b4..ab21e0d 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -337,7 +337,11 @@
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	cpu_switch_mm(mm->pgd, mm);
+	if (mm == &init_mm)
+		cpu_set_reserved_ttbr0();
+	else
+		cpu_switch_mm(mm->pgd, mm);
+
 	flush_tlb_all();
 	if (icache_is_aivivt())
 		__flush_icache_all();
@@ -354,3 +358,12 @@
 	efi_set_pgd(current->active_mm);
 	preempt_enable();
 }
+
+/*
+ * UpdateCapsule() depends on the system being shutdown via
+ * ResetSystem().
+ */
+bool efi_poweroff_required(void)
+{
+	return efi_enabled(EFI_RUNTIME_SERVICES);
+}
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index cf8556a..c851be7 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -156,7 +156,7 @@
 
 	branch = aarch64_insn_gen_branch_imm(pc,
 					     (unsigned long)ftrace_graph_caller,
-					     AARCH64_INSN_BRANCH_LINK);
+					     AARCH64_INSN_BRANCH_NOLINK);
 	nop = aarch64_insn_gen_nop();
 
 	if (enable)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 8ce88e0..07f9305 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -585,8 +585,8 @@
  * zeroing of .bss would clobber it.
  */
 	.pushsection	.data..cacheline_aligned
-ENTRY(__boot_cpu_mode)
 	.align	L1_CACHE_SHIFT
+ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
 	.long	0
 	.popsection
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 27d4864..c8eca88 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -87,8 +87,10 @@
 
 	if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX))
 		page = vmalloc_to_page(addr);
-	else
+	else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA))
 		page = virt_to_page(addr);
+	else
+		return addr;
 
 	BUG_ON(!page);
 	set_fixmap(fixmap, page_to_phys(page));
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index fde9923..c6b1f3b9 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -21,6 +21,7 @@
 #include <stdarg.h>
 
 #include <linux/compat.h>
+#include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -150,6 +151,13 @@
 	local_irq_disable();
 	smp_send_stop();
 
+	/*
+	 * UpdateCapsule() depends on the system being reset via
+	 * ResetSystem().
+	 */
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		efi_reboot(reboot_mode, NULL);
+
 	/* Now call the architecture specific reboot code. */
 	if (arm_pm_restart)
 		arm_pm_restart(reboot_mode, cmd);
diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S
new file mode 100644
index 0000000..cf83e61
--- /dev/null
+++ b/arch/arm64/kernel/psci-call.S
@@ -0,0 +1,28 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/linkage.h>
+
+/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
+ENTRY(__invoke_psci_fn_hvc)
+	hvc	#0
+	ret
+ENDPROC(__invoke_psci_fn_hvc)
+
+/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
+ENTRY(__invoke_psci_fn_smc)
+	smc	#0
+	ret
+ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 3425f31..9b8a70a 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -57,6 +57,9 @@
 static int (*invoke_psci_fn)(u64, u64, u64, u64);
 typedef int (*psci_initcall_t)(const struct device_node *);
 
+asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64);
+asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64);
+
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
@@ -109,40 +112,6 @@
 			PSCI_0_2_POWER_STATE_AFFL_SHIFT;
 }
 
-/*
- * The following two functions are invoked via the invoke_psci_fn pointer
- * and will not be inlined, allowing us to piggyback on the AAPCS.
- */
-static noinline int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1,
-					 u64 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "x0")
-			__asmeq("%1", "x1")
-			__asmeq("%2", "x2")
-			__asmeq("%3", "x3")
-			"hvc	#0\n"
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
-static noinline int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1,
-					 u64 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "x0")
-			__asmeq("%1", "x1")
-			__asmeq("%2", "x2")
-			__asmeq("%3", "x3")
-			"smc	#0\n"
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
 static int psci_get_version(void)
 {
 	int err;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index c20a300..d26fcd4 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -154,8 +154,7 @@
 	case __SI_TIMER:
 		 err |= __put_user(from->si_tid, &to->si_tid);
 		 err |= __put_user(from->si_overrun, &to->si_overrun);
-		 err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr,
-				   &to->si_ptr);
+		 err |= __put_user(from->si_int, &to->si_int);
 		break;
 	case __SI_POLL:
 		err |= __put_user(from->si_band, &to->si_band);
@@ -184,7 +183,7 @@
 	case __SI_MESGQ: /* But this is */
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr);
+		err |= __put_user(from->si_int, &to->si_int);
 		break;
 	case __SI_SYS:
 		err |= __put_user((compat_uptr_t)(unsigned long)
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index fe652ff..efa79e8 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -174,8 +174,6 @@
 /* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */
 ENTRY(__kernel_clock_getres)
 	.cfi_startproc
-	cbz	w1, 3f
-
 	cmp	w0, #CLOCK_REALTIME
 	ccmp	w0, #CLOCK_MONOTONIC, #0x4, ne
 	b.ne	1f
@@ -188,6 +186,7 @@
 	b.ne	4f
 	ldr	x2, 6f
 2:
+	cbz	w1, 3f
 	stp	xzr, x2, [x1]
 
 3:	/* res == NULL. */
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 0a24b9b..ef7d112 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -51,7 +51,7 @@
 }
 early_param("coherent_pool", early_coherent_pool);
 
-static void *__alloc_from_pool(size_t size, struct page **ret_page)
+static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
 {
 	unsigned long val;
 	void *ptr = NULL;
@@ -67,6 +67,8 @@
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
+		if (flags & __GFP_ZERO)
+			memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -101,6 +103,7 @@
 		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
+		void *addr;
 
 		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
@@ -109,7 +112,10 @@
 			return NULL;
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-		return page_address(page);
+		addr = page_address(page);
+		if (flags & __GFP_ZERO)
+			memset(addr, 0, size);
+		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
 	}
@@ -146,7 +152,7 @@
 
 	if (!coherent && !(flags & __GFP_WAIT)) {
 		struct page *page = NULL;
-		void *addr = __alloc_from_pool(size, &page);
+		void *addr = __alloc_from_pool(size, &page, flags);
 
 		if (addr)
 			*dma_handle = phys_to_dma(dev, page_to_phys(page));
@@ -348,8 +354,6 @@
 	.mapping_error = swiotlb_dma_mapping_error,
 };
 
-extern int swiotlb_late_init_with_default_size(size_t default_size);
-
 static int __init atomic_pool_init(void)
 {
 	pgprot_t prot = __pgprot(PROT_NORMAL_NC);
@@ -411,21 +415,13 @@
 	return -ENOMEM;
 }
 
-static int __init swiotlb_late_init(void)
+static int __init arm64_dma_init(void)
 {
-	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+	int ret;
 
 	dma_ops = &swiotlb_dma_ops;
 
-	return swiotlb_late_init_with_default_size(swiotlb_size);
-}
-
-static int __init arm64_dma_init(void)
-{
-	int ret = 0;
-
-	ret |= swiotlb_late_init();
-	ret |= atomic_pool_init();
+	ret = atomic_pool_init();
 
 	return ret;
 }
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 71145f9..ae85da6 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -33,6 +33,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
+#include <linux/swiotlb.h>
 
 #include <asm/fixmap.h>
 #include <asm/memory.h>
@@ -45,6 +46,7 @@
 #include "mm.h"
 
 phys_addr_t memstart_addr __read_mostly = 0;
+phys_addr_t arm64_dma_phys_limit __read_mostly;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 static int __init early_initrd(char *p)
@@ -85,7 +87,7 @@
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
-		max_dma = PFN_DOWN(max_zone_dma_phys());
+		max_dma = PFN_DOWN(arm64_dma_phys_limit);
 		zone_size[ZONE_DMA] = max_dma - min;
 	}
 	zone_size[ZONE_NORMAL] = max - max_dma;
@@ -156,8 +158,6 @@
 
 void __init arm64_memblock_init(void)
 {
-	phys_addr_t dma_phys_limit = 0;
-
 	memblock_enforce_memory_limit(memory_limit);
 
 	/*
@@ -174,8 +174,10 @@
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		dma_phys_limit = max_zone_dma_phys();
-	dma_contiguous_reserve(dma_phys_limit);
+		arm64_dma_phys_limit = max_zone_dma_phys();
+	else
+		arm64_dma_phys_limit = PHYS_MASK + 1;
+	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
 	memblock_dump_all();
@@ -276,6 +278,8 @@
  */
 void __init mem_init(void)
 {
+	swiotlb_init(1);
+
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index bb0ea94..1d3ec3d 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -51,7 +51,10 @@
 		WARN_ON_ONCE(1);
 	}
 
-	if (!is_module_address(start) || !is_module_address(end - 1))
+	if (start < MODULES_VADDR || start >= MODULES_END)
+		return -EINVAL;
+
+	if (end < MODULES_VADDR || end >= MODULES_END)
 		return -EINVAL;
 
 	data.set_mask = set_mask;
diff --git a/arch/c6x/include/asm/pgtable.h b/arch/c6x/include/asm/pgtable.h
index 78d4483b..ec4db6d 100644
--- a/arch/c6x/include/asm/pgtable.h
+++ b/arch/c6x/include/asm/pgtable.h
@@ -67,6 +67,11 @@
  */
 #define pgtable_cache_init()   do { } while (0)
 
+/*
+ * c6x is !MMU, so define the simpliest implementation
+ */
+#define pgprot_writecombine pgprot_noncached
+
 #include <asm-generic/pgtable.h>
 
 #endif /* _ASM_C6X_PGTABLE_H */
diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h
index 93bcf2a..07d7a7e 100644
--- a/arch/frv/include/asm/pgtable.h
+++ b/arch/frv/include/asm/pgtable.h
@@ -123,12 +123,14 @@
 #define PGDIR_MASK		(~(PGDIR_SIZE - 1))
 #define PTRS_PER_PGD		64
 
+#define __PAGETABLE_PUD_FOLDED
 #define PUD_SHIFT		26
 #define PTRS_PER_PUD		1
 #define PUD_SIZE		(1UL << PUD_SHIFT)
 #define PUD_MASK		(~(PUD_SIZE - 1))
 #define PUE_SIZE		256
 
+#define __PAGETABLE_PMD_FOLDED
 #define PMD_SHIFT		26
 #define PMD_SIZE		(1UL << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE - 1))
diff --git a/arch/m32r/include/asm/pgtable-2level.h b/arch/m32r/include/asm/pgtable-2level.h
index 8fd8ee7..421e6ba 100644
--- a/arch/m32r/include/asm/pgtable-2level.h
+++ b/arch/m32r/include/asm/pgtable-2level.h
@@ -13,6 +13,7 @@
  * the M32R is two-level, so we don't really have any
  * PMD directory physically.
  */
+#define __PAGETABLE_PMD_FOLDED
 #define PMD_SHIFT	22
 #define PTRS_PER_PMD	1
 
diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h
index 28a145b..35ed4a9 100644
--- a/arch/m68k/include/asm/pgtable_mm.h
+++ b/arch/m68k/include/asm/pgtable_mm.h
@@ -54,10 +54,12 @@
  */
 #ifdef CONFIG_SUN3
 #define PTRS_PER_PTE   16
+#define __PAGETABLE_PMD_FOLDED
 #define PTRS_PER_PMD   1
 #define PTRS_PER_PGD   2048
 #elif defined(CONFIG_COLDFIRE)
 #define PTRS_PER_PTE	512
+#define __PAGETABLE_PMD_FOLDED
 #define PTRS_PER_PMD	1
 #define PTRS_PER_PGD	1024
 #else
diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h
index 9359e50..d5779b0 100644
--- a/arch/metag/include/asm/io.h
+++ b/arch/metag/include/asm/io.h
@@ -2,6 +2,7 @@
 #define _ASM_METAG_IO_H
 
 #include <linux/types.h>
+#include <asm/pgtable-bits.h>
 
 #define IO_SPACE_LIMIT  0
 
diff --git a/arch/metag/include/asm/pgtable-bits.h b/arch/metag/include/asm/pgtable-bits.h
new file mode 100644
index 0000000..25ba672
--- /dev/null
+++ b/arch/metag/include/asm/pgtable-bits.h
@@ -0,0 +1,104 @@
+/*
+ * Meta page table definitions.
+ */
+
+#ifndef _METAG_PGTABLE_BITS_H
+#define _METAG_PGTABLE_BITS_H
+
+#include <asm/metag_mem.h>
+
+/*
+ * Definitions for MMU descriptors
+ *
+ * These are the hardware bits in the MMCU pte entries.
+ * Derived from the Meta toolkit headers.
+ */
+#define _PAGE_PRESENT		MMCU_ENTRY_VAL_BIT
+#define _PAGE_WRITE		MMCU_ENTRY_WR_BIT
+#define _PAGE_PRIV		MMCU_ENTRY_PRIV_BIT
+/* Write combine bit - this can cause writes to occur out of order */
+#define _PAGE_WR_COMBINE	MMCU_ENTRY_WRC_BIT
+/* Sys coherent bit - this bit is never used by Linux */
+#define _PAGE_SYS_COHERENT	MMCU_ENTRY_SYS_BIT
+#define _PAGE_ALWAYS_ZERO_1	0x020
+#define _PAGE_CACHE_CTRL0	0x040
+#define _PAGE_CACHE_CTRL1	0x080
+#define _PAGE_ALWAYS_ZERO_2	0x100
+#define _PAGE_ALWAYS_ZERO_3	0x200
+#define _PAGE_ALWAYS_ZERO_4	0x400
+#define _PAGE_ALWAYS_ZERO_5	0x800
+
+/* These are software bits that we stuff into the gaps in the hardware
+ * pte entries that are not used.  Note, these DO get stored in the actual
+ * hardware, but the hardware just does not use them.
+ */
+#define _PAGE_ACCESSED		_PAGE_ALWAYS_ZERO_1
+#define _PAGE_DIRTY		_PAGE_ALWAYS_ZERO_2
+
+/* Pages owned, and protected by, the kernel. */
+#define _PAGE_KERNEL		_PAGE_PRIV
+
+/* No cacheing of this page */
+#define _PAGE_CACHE_WIN0	(MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
+/* burst cacheing - good for data streaming */
+#define _PAGE_CACHE_WIN1	(MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
+/* One cache way per thread */
+#define _PAGE_CACHE_WIN2	(MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
+/* Full on cacheing */
+#define _PAGE_CACHE_WIN3	(MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
+
+#define _PAGE_CACHEABLE		(_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
+
+/* which bits are used for cache control ... */
+#define _PAGE_CACHE_MASK	(_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
+				 _PAGE_WR_COMBINE)
+
+/* This is a mask of the bits that pte_modify is allowed to change. */
+#define _PAGE_CHG_MASK		(PAGE_MASK)
+
+#define _PAGE_SZ_SHIFT		1
+#define _PAGE_SZ_4K		(0x0)
+#define _PAGE_SZ_8K		(0x1 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_16K		(0x2 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_32K		(0x3 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_64K		(0x4 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_128K		(0x5 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_256K		(0x6 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_512K		(0x7 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_1M		(0x8 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_2M		(0x9 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_4M		(0xa << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_MASK		(0xf << _PAGE_SZ_SHIFT)
+
+#if defined(CONFIG_PAGE_SIZE_4K)
+#define _PAGE_SZ		(_PAGE_SZ_4K)
+#elif defined(CONFIG_PAGE_SIZE_8K)
+#define _PAGE_SZ		(_PAGE_SZ_8K)
+#elif defined(CONFIG_PAGE_SIZE_16K)
+#define _PAGE_SZ		(_PAGE_SZ_16K)
+#endif
+#define _PAGE_TABLE		(_PAGE_SZ | _PAGE_PRESENT)
+
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_8K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_16K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_32K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_64K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_128K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_256K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_512K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_1M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_2M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_4M)
+#endif
+
+#endif /* _METAG_PGTABLE_BITS_H */
diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h
index d0604c0..ffa3a3a 100644
--- a/arch/metag/include/asm/pgtable.h
+++ b/arch/metag/include/asm/pgtable.h
@@ -5,6 +5,7 @@
 #ifndef _METAG_PGTABLE_H
 #define _METAG_PGTABLE_H
 
+#include <asm/pgtable-bits.h>
 #include <asm-generic/pgtable-nopmd.h>
 
 /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
@@ -21,100 +22,6 @@
 #endif
 
 /*
- * Definitions for MMU descriptors
- *
- * These are the hardware bits in the MMCU pte entries.
- * Derived from the Meta toolkit headers.
- */
-#define _PAGE_PRESENT		MMCU_ENTRY_VAL_BIT
-#define _PAGE_WRITE		MMCU_ENTRY_WR_BIT
-#define _PAGE_PRIV		MMCU_ENTRY_PRIV_BIT
-/* Write combine bit - this can cause writes to occur out of order */
-#define _PAGE_WR_COMBINE	MMCU_ENTRY_WRC_BIT
-/* Sys coherent bit - this bit is never used by Linux */
-#define _PAGE_SYS_COHERENT	MMCU_ENTRY_SYS_BIT
-#define _PAGE_ALWAYS_ZERO_1	0x020
-#define _PAGE_CACHE_CTRL0	0x040
-#define _PAGE_CACHE_CTRL1	0x080
-#define _PAGE_ALWAYS_ZERO_2	0x100
-#define _PAGE_ALWAYS_ZERO_3	0x200
-#define _PAGE_ALWAYS_ZERO_4	0x400
-#define _PAGE_ALWAYS_ZERO_5	0x800
-
-/* These are software bits that we stuff into the gaps in the hardware
- * pte entries that are not used.  Note, these DO get stored in the actual
- * hardware, but the hardware just does not use them.
- */
-#define _PAGE_ACCESSED		_PAGE_ALWAYS_ZERO_1
-#define _PAGE_DIRTY		_PAGE_ALWAYS_ZERO_2
-
-/* Pages owned, and protected by, the kernel. */
-#define _PAGE_KERNEL		_PAGE_PRIV
-
-/* No cacheing of this page */
-#define _PAGE_CACHE_WIN0	(MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
-/* burst cacheing - good for data streaming */
-#define _PAGE_CACHE_WIN1	(MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
-/* One cache way per thread */
-#define _PAGE_CACHE_WIN2	(MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
-/* Full on cacheing */
-#define _PAGE_CACHE_WIN3	(MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
-
-#define _PAGE_CACHEABLE		(_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
-
-/* which bits are used for cache control ... */
-#define _PAGE_CACHE_MASK	(_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
-				 _PAGE_WR_COMBINE)
-
-/* This is a mask of the bits that pte_modify is allowed to change. */
-#define _PAGE_CHG_MASK		(PAGE_MASK)
-
-#define _PAGE_SZ_SHIFT		1
-#define _PAGE_SZ_4K		(0x0)
-#define _PAGE_SZ_8K		(0x1 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_16K		(0x2 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_32K		(0x3 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_64K		(0x4 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_128K		(0x5 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_256K		(0x6 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_512K		(0x7 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_1M		(0x8 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_2M		(0x9 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_4M		(0xa << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_MASK		(0xf << _PAGE_SZ_SHIFT)
-
-#if defined(CONFIG_PAGE_SIZE_4K)
-#define _PAGE_SZ		(_PAGE_SZ_4K)
-#elif defined(CONFIG_PAGE_SIZE_8K)
-#define _PAGE_SZ		(_PAGE_SZ_8K)
-#elif defined(CONFIG_PAGE_SIZE_16K)
-#define _PAGE_SZ		(_PAGE_SZ_16K)
-#endif
-#define _PAGE_TABLE		(_PAGE_SZ | _PAGE_PRESENT)
-
-#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_8K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_16K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_32K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_64K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_128K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_256K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_512K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
-# define _PAGE_SZHUGE		(_PAGE_SZ_1M)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
-# define _PAGE_SZHUGE		(_PAGE_SZ_2M)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
-# define _PAGE_SZHUGE		(_PAGE_SZ_4M)
-#endif
-
-/*
  * The Linux memory management assumes a three-level page table setup. On
  * Meta, we use that, but "fold" the mid level into the top-level page
  * table.
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index 881071c..13272fd 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -149,8 +149,8 @@
 
 unsigned long get_wchan(struct task_struct *p);
 
-#define	KSTK_EIP(tsk)	((tsk)->thread.kernel_context->CurrPC)
-#define	KSTK_ESP(tsk)	((tsk)->thread.kernel_context->AX[0].U0)
+#define	KSTK_EIP(tsk)	(task_pt_regs(tsk)->ctx.CurrPC)
+#define	KSTK_ESP(tsk)	(task_pt_regs(tsk)->ctx.AX[0].U0)
 
 #define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
 
diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S
index 0536bc0..ef548510 100644
--- a/arch/microblaze/kernel/entry.S
+++ b/arch/microblaze/kernel/entry.S
@@ -348,8 +348,9 @@
  * The LP register should point to the location where the called function
  * should return.  [note that MAKE_SYS_CALL uses label 1] */
 	/* See if the system call number is valid */
+	blti	r12, 5f
 	addi	r11, r12, -__NR_syscalls;
-	bgei	r11,5f;
+	bgei	r11, 5f;
 	/* Figure out which function to use for this system call.  */
 	/* Note Microblaze barrel shift is optional, so don't rely on it */
 	add	r12, r12, r12;			/* convert num -> ptr */
@@ -375,7 +376,7 @@
 
 	/* The syscall number is invalid, return an error.  */
 5:
-	rtsd	r15, 8;		/* looks like a normal subroutine return */
+	braid	ret_from_trap
 	addi	r3, r0, -ENOSYS;
 
 /* Entry point used to return from a syscall/trap */
@@ -411,7 +412,7 @@
 	bri	1b
 
 	/* Maybe handle a signal */
-5:	
+5:
 	andi	r11, r19, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME;
 	beqi	r11, 4f;		/* Signals to handle, handle them */
 
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index bbcd822..b6beb0e 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -216,6 +216,7 @@
 	if (idx > current_cpu_data.tlbsize) {
 		kvm_err("%s: Invalid Index: %d\n", __func__, idx);
 		kvm_mips_dump_host_tlbs();
+		local_irq_restore(flags);
 		return -1;
 	}
 
diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h
index c1388d4..bd6437f 100644
--- a/arch/mips/kvm/trace.h
+++ b/arch/mips/kvm/trace.h
@@ -24,18 +24,18 @@
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason),
 	    TP_ARGS(vcpu, reason),
 	    TP_STRUCT__entry(
-			__field(struct kvm_vcpu *, vcpu)
+			__field(unsigned long, pc)
 			__field(unsigned int, reason)
 	    ),
 
 	    TP_fast_assign(
-			__entry->vcpu = vcpu;
+			__entry->pc = vcpu->arch.pc;
 			__entry->reason = reason;
 	    ),
 
 	    TP_printk("[%s]PC: 0x%08lx",
 		      kvm_mips_exit_types_str[__entry->reason],
-		      __entry->vcpu->arch.pc)
+		      __entry->pc)
 );
 
 #endif /* _TRACE_KVM_H */
diff --git a/arch/mn10300/include/asm/pgtable.h b/arch/mn10300/include/asm/pgtable.h
index afab728..96d3f9d 100644
--- a/arch/mn10300/include/asm/pgtable.h
+++ b/arch/mn10300/include/asm/pgtable.h
@@ -56,7 +56,9 @@
 #define PGDIR_SHIFT	22
 #define PTRS_PER_PGD	1024
 #define PTRS_PER_PUD	1	/* we don't really have any PUD physically */
+#define __PAGETABLE_PUD_FOLDED
 #define PTRS_PER_PMD	1	/* we don't really have any PMD physically */
+#define __PAGETABLE_PMD_FOLDED
 #define PTRS_PER_PTE	1024
 
 #define PGD_SIZE	PAGE_SIZE
diff --git a/arch/nios2/include/asm/ptrace.h b/arch/nios2/include/asm/ptrace.h
index 20fb1cf..6424621 100644
--- a/arch/nios2/include/asm/ptrace.h
+++ b/arch/nios2/include/asm/ptrace.h
@@ -15,7 +15,54 @@
 
 #include <uapi/asm/ptrace.h>
 
+/* This struct defines the way the registers are stored on the
+   stack during a system call.  */
+
 #ifndef __ASSEMBLY__
+struct pt_regs {
+	unsigned long  r8;	/* r8-r15 Caller-saved GP registers */
+	unsigned long  r9;
+	unsigned long  r10;
+	unsigned long  r11;
+	unsigned long  r12;
+	unsigned long  r13;
+	unsigned long  r14;
+	unsigned long  r15;
+	unsigned long  r1;	/* Assembler temporary */
+	unsigned long  r2;	/* Retval LS 32bits */
+	unsigned long  r3;	/* Retval MS 32bits */
+	unsigned long  r4;	/* r4-r7 Register arguments */
+	unsigned long  r5;
+	unsigned long  r6;
+	unsigned long  r7;
+	unsigned long  orig_r2;	/* Copy of r2 ?? */
+	unsigned long  ra;	/* Return address */
+	unsigned long  fp;	/* Frame pointer */
+	unsigned long  sp;	/* Stack pointer */
+	unsigned long  gp;	/* Global pointer */
+	unsigned long  estatus;
+	unsigned long  ea;	/* Exception return address (pc) */
+	unsigned long  orig_r7;
+};
+
+/*
+ * This is the extended stack used by signal handlers and the context
+ * switcher: it's pushed after the normal "struct pt_regs".
+ */
+struct switch_stack {
+	unsigned long  r16;	/* r16-r23 Callee-saved GP registers */
+	unsigned long  r17;
+	unsigned long  r18;
+	unsigned long  r19;
+	unsigned long  r20;
+	unsigned long  r21;
+	unsigned long  r22;
+	unsigned long  r23;
+	unsigned long  fp;
+	unsigned long  gp;
+	unsigned long  ra;
+};
+
 #define user_mode(regs)	(((regs)->estatus & ESTATUS_EU))
 
 #define instruction_pointer(regs)	((regs)->ra)
diff --git a/arch/nios2/include/asm/ucontext.h b/arch/nios2/include/asm/ucontext.h
deleted file mode 100644
index 2c87614..0000000
--- a/arch/nios2/include/asm/ucontext.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright (C) 2010 Tobias Klauser <tklauser@distanz.ch>
- * Copyright (C) 2004 Microtronix Datacom Ltd
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_NIOS2_UCONTEXT_H
-#define _ASM_NIOS2_UCONTEXT_H
-
-typedef int greg_t;
-#define NGREG 32
-typedef greg_t gregset_t[NGREG];
-
-struct mcontext {
-	int version;
-	gregset_t gregs;
-};
-
-#define MCONTEXT_VERSION 2
-
-struct ucontext {
-	unsigned long	  uc_flags;
-	struct ucontext  *uc_link;
-	stack_t		  uc_stack;
-	struct mcontext	  uc_mcontext;
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif
diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild
index 4f07ca3f8..e0bb972 100644
--- a/arch/nios2/include/uapi/asm/Kbuild
+++ b/arch/nios2/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 header-y += elf.h
-header-y += ucontext.h
+
+generic-y += ucontext.h
diff --git a/arch/nios2/include/uapi/asm/elf.h b/arch/nios2/include/uapi/asm/elf.h
index a5b91ae..6f06d3b 100644
--- a/arch/nios2/include/uapi/asm/elf.h
+++ b/arch/nios2/include/uapi/asm/elf.h
@@ -50,9 +50,7 @@
 
 typedef unsigned long elf_greg_t;
 
-#define ELF_NGREG	\
-	((sizeof(struct pt_regs) + sizeof(struct switch_stack)) /	\
-		sizeof(elf_greg_t))
+#define ELF_NGREG		49
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef unsigned long elf_fpregset_t;
diff --git a/arch/nios2/include/uapi/asm/ptrace.h b/arch/nios2/include/uapi/asm/ptrace.h
index e83a7c9..71a3305 100644
--- a/arch/nios2/include/uapi/asm/ptrace.h
+++ b/arch/nios2/include/uapi/asm/ptrace.h
@@ -67,53 +67,9 @@
 
 #define NUM_PTRACE_REG (PTR_TLBMISC + 1)
 
-/* this struct defines the way the registers are stored on the
-   stack during a system call.
-
-   There is a fake_regs in setup.c that has to match pt_regs.*/
-
-struct pt_regs {
-	unsigned long  r8;		/* r8-r15 Caller-saved GP registers */
-	unsigned long  r9;
-	unsigned long  r10;
-	unsigned long  r11;
-	unsigned long  r12;
-	unsigned long  r13;
-	unsigned long  r14;
-	unsigned long  r15;
-	unsigned long  r1;		/* Assembler temporary */
-	unsigned long  r2;		/* Retval LS 32bits */
-	unsigned long  r3;		/* Retval MS 32bits */
-	unsigned long  r4;		/* r4-r7 Register arguments */
-	unsigned long  r5;
-	unsigned long  r6;
-	unsigned long  r7;
-	unsigned long  orig_r2;		/* Copy of r2 ?? */
-	unsigned long  ra;		/* Return address */
-	unsigned long  fp;		/* Frame pointer */
-	unsigned long  sp;		/* Stack pointer */
-	unsigned long  gp;		/* Global pointer */
-	unsigned long  estatus;
-	unsigned long  ea;		/* Exception return address (pc) */
-	unsigned long  orig_r7;
-};
-
-/*
- * This is the extended stack used by signal handlers and the context
- * switcher: it's pushed after the normal "struct pt_regs".
- */
-struct switch_stack {
-	unsigned long  r16;		/* r16-r23 Callee-saved GP registers */
-	unsigned long  r17;
-	unsigned long  r18;
-	unsigned long  r19;
-	unsigned long  r20;
-	unsigned long  r21;
-	unsigned long  r22;
-	unsigned long  r23;
-	unsigned long  fp;
-	unsigned long  gp;
-	unsigned long  ra;
+/* User structures for general purpose registers.  */
+struct user_pt_regs {
+	__u32		regs[49];
 };
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/nios2/include/uapi/asm/sigcontext.h b/arch/nios2/include/uapi/asm/sigcontext.h
index 7b8bb41..b67944a 100644
--- a/arch/nios2/include/uapi/asm/sigcontext.h
+++ b/arch/nios2/include/uapi/asm/sigcontext.h
@@ -15,14 +15,16 @@
  * details.
  */
 
-#ifndef _ASM_NIOS2_SIGCONTEXT_H
-#define _ASM_NIOS2_SIGCONTEXT_H
+#ifndef _UAPI__ASM_SIGCONTEXT_H
+#define _UAPI__ASM_SIGCONTEXT_H
 
-#include <asm/ptrace.h>
+#include <linux/types.h>
+
+#define MCONTEXT_VERSION 2
 
 struct sigcontext {
-	struct pt_regs regs;
-	unsigned long  sc_mask;	/* old sigmask */
+	int version;
+	unsigned long gregs[32];
 };
 
 #endif
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index 2d0ea25..dda41e4 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -39,7 +39,7 @@
 					struct ucontext *uc, int *pr2)
 {
 	int temp;
-	greg_t *gregs = uc->uc_mcontext.gregs;
+	unsigned long *gregs = uc->uc_mcontext.gregs;
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -127,7 +127,7 @@
 static inline int rt_setup_ucontext(struct ucontext *uc, struct pt_regs *regs)
 {
 	struct switch_stack *sw = (struct switch_stack *)regs - 1;
-	greg_t *gregs = uc->uc_mcontext.gregs;
+	unsigned long *gregs = uc->uc_mcontext.gregs;
 	int err = 0;
 
 	err |= __put_user(MCONTEXT_VERSION, &uc->uc_mcontext.version);
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 0d231ad..0c9b6af 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -126,7 +126,6 @@
 		break;
 	}
 
-survive:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -220,11 +219,6 @@
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f213f5b..d174372 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 	if (likely(pgd != NULL)) {
 		memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
 		actual_pgd += PTRS_PER_PGD;
 		/* Populate first pmd with allocated memory.  We mark it
 		 * with PxD_FLAG_ATTACHED as a signal to the system that this
@@ -45,7 +45,7 @@
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
 	pgd -= PTRS_PER_PGD;
 #endif
 	free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
@@ -72,12 +72,15 @@
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-#ifdef CONFIG_64BIT
 	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		/* This is the permanent pmd attached to the pgd;
-		 * cannot free it */
+		/*
+		 * This is the permanent pmd attached to the pgd;
+		 * cannot free it.
+		 * Increment the counter to compensate for the decrement
+		 * done by generic mm code.
+		 */
+		mm_inc_nr_pmds(mm);
 		return;
-#endif
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
@@ -99,7 +102,7 @@
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 {
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
 	/* preserve the gateway marker if this is the beginning of
 	 * the permanent pmd */
 	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 8c966b2..15207b9 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -96,6 +96,7 @@
 #if PT_NLEVELS == 3
 #define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
 #else
+#define __PAGETABLE_PMD_FOLDED
 #define BITS_PER_PMD	0
 #endif
 #define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 5a8997d..8eefb12 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -55,8 +55,8 @@
 #define ENTRY_COMP(_name_) .word sys_##_name_
 #endif
 
-	ENTRY_SAME(restart_syscall)	/* 0 */
-	ENTRY_SAME(exit)
+90:	ENTRY_SAME(restart_syscall)	/* 0 */
+91:	ENTRY_SAME(exit)
 	ENTRY_SAME(fork_wrapper)
 	ENTRY_SAME(read)
 	ENTRY_SAME(write)
@@ -439,7 +439,10 @@
 	ENTRY_SAME(bpf)
 	ENTRY_COMP(execveat)
 
-	/* Nothing yet */
+
+.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
+.error "size of syscall table does not fit value of __NR_Linux_syscalls"
+.endif
 
 #undef ENTRY_SAME
 #undef ENTRY_DIFF
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 9cfa370..f1ea597 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -113,6 +113,7 @@
 				 int pci_domain_number, unsigned long pe_num);
 extern int iommu_add_device(struct device *dev);
 extern void iommu_del_device(struct device *dev);
+extern int __init tce_iommu_bus_notifier_init(void);
 #else
 static inline void iommu_register_group(struct iommu_table *tbl,
 					int pci_domain_number,
@@ -128,6 +129,11 @@
 static inline void iommu_del_device(struct device *dev)
 {
 }
+
+static inline int __init tce_iommu_bus_notifier_init(void)
+{
+        return 0;
+}
 #endif /* !CONFIG_IOMMU_API */
 
 static inline void set_iommu_table_base_and_group(struct device *dev,
diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h
new file mode 100644
index 0000000..744fd54
--- /dev/null
+++ b/arch/powerpc/include/asm/irq_work.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_POWERPC_IRQ_WORK_H
+#define _ASM_POWERPC_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return true;
+}
+
+#endif /* _ASM_POWERPC_IRQ_WORK_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 03cd858..4cbe23a 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -153,6 +153,7 @@
 #define PPC_INST_MFSPR_PVR_MASK		0xfc1fffff
 #define PPC_INST_MFTMR			0x7c0002dc
 #define PPC_INST_MSGSND			0x7c00019c
+#define PPC_INST_MSGCLR			0x7c0001dc
 #define PPC_INST_MSGSNDP		0x7c00011c
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
@@ -309,6 +310,8 @@
 					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					___PPC_RB(b))
+#define PPC_MSGCLR(b)		stringify_in_c(.long PPC_INST_MSGCLR | \
+					___PPC_RB(b))
 #define PPC_MSGSNDP(b)		stringify_in_c(.long PPC_INST_MSGSNDP | \
 					___PPC_RB(b))
 #define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1c874fb..af56b5c 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -608,13 +608,16 @@
 #define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
+#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define	  SRR1_WAKEHMI		0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
+#define   SRR1_WAKEDBELL	0x00140000 /* Privileged doorbell on P8 */
 #define   SRR1_WAKETHERM	0x00100000 /* Thermal management interrupt */
 #define	  SRR1_WAKERESET	0x00100000 /* System reset */
+#define   SRR1_WAKEHDBELL	0x000c0000 /* Hypervisor doorbell on P8 */
 #define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
 #define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
 					  * may not be recoverable */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index f337666..f830468 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -437,6 +437,26 @@
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* Power8NVL */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x004c0000,
+		.cpu_name		= "POWER8NVL (raw)",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.flush_tlb		= __flush_tlb_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* Power8 DD1: Does not support doorbell IPIs */
 		.pvr_mask		= 0xffffff00,
 		.pvr_value		= 0x004d0100,
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f421781..2128f3a 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -17,6 +17,7 @@
 
 #include <asm/dbell.h>
 #include <asm/irq_regs.h>
+#include <asm/kvm_ppc.h>
 
 #ifdef CONFIG_SMP
 void doorbell_setup_this_cpu(void)
@@ -41,6 +42,7 @@
 
 	may_hard_irq_enable();
 
+	kvmppc_set_host_ipi(smp_processor_id(), 0);
 	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index c2df815..9519e6b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1408,7 +1408,7 @@
 	bne	9f			/* continue in V mode if we are. */
 
 5:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
 	 * We are coming from kernel context. Check if we are coming from
 	 * guest. if yes, then we can continue. We will fall through
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 5d3968c..b054f33 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1175,4 +1175,30 @@
 }
 EXPORT_SYMBOL_GPL(iommu_del_device);
 
+static int tce_iommu_bus_notifier(struct notifier_block *nb,
+                unsigned long action, void *data)
+{
+        struct device *dev = data;
+
+        switch (action) {
+        case BUS_NOTIFY_ADD_DEVICE:
+                return iommu_add_device(dev);
+        case BUS_NOTIFY_DEL_DEVICE:
+                if (dev->iommu_group)
+                        iommu_del_device(dev);
+                return 0;
+        default:
+                return 0;
+        }
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+        .notifier_call = tce_iommu_bus_notifier,
+};
+
+int __init tce_iommu_bus_notifier_init(void)
+{
+        bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+        return 0;
+}
 #endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 6e19afa..ec9ec20 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -541,8 +541,8 @@
 	if (smp_ops->give_timebase)
 		smp_ops->give_timebase();
 
-	/* Wait until cpu puts itself in the online map */
-	while (!cpu_online(cpu))
+	/* Wait until cpu puts itself in the online & active maps */
+	while (!cpu_online(cpu) || !cpu_active(cpu))
 		cpu_relax();
 
 	return 0;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de4018a..de74756 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -636,7 +636,7 @@
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr;
 	if (lppaca)
-		yield_count = lppaca->yield_count;
+		yield_count = be32_to_cpu(lppaca->yield_count);
 	spin_unlock(&vcpu->arch.vpa_update_lock);
 	return yield_count;
 }
@@ -942,20 +942,20 @@
 static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 		bool preserve_top32)
 {
+	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 mask;
 
+	mutex_lock(&kvm->lock);
 	spin_lock(&vc->lock);
 	/*
 	 * If ILE (interrupt little-endian) has changed, update the
 	 * MSR_LE bit in the intr_msr for each vcpu in this vcore.
 	 */
 	if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
-		struct kvm *kvm = vcpu->kvm;
 		struct kvm_vcpu *vcpu;
 		int i;
 
-		mutex_lock(&kvm->lock);
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->arch.vcore != vc)
 				continue;
@@ -964,7 +964,6 @@
 			else
 				vcpu->arch.intr_msr &= ~MSR_LE;
 		}
-		mutex_unlock(&kvm->lock);
 	}
 
 	/*
@@ -981,6 +980,7 @@
 		mask &= 0xFFFFFFFF;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
+	mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bb94e6f..6cbf163 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1005,6 +1005,7 @@
 	/* Save HEIR (HV emulation assist reg) in emul_inst
 	   if this is an HEI (HV emulation interrupt, e40) */
 	li	r3,KVM_INST_FETCH_FAILED
+	stw	r3,VCPU_LAST_INST(r9)
 	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
 	bne	11f
 	mfspr	r3,SPRN_HEIR
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index e69142f..54323d6 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -836,30 +836,4 @@
 #endif
 }
 
-static int tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_ADD_DEVICE:
-		return iommu_add_device(dev);
-	case BUS_NOTIFY_DEL_DEVICE:
-		if (dev->iommu_group)
-			iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block tce_iommu_bus_nb = {
-	.notifier_call = tce_iommu_bus_notifier,
-};
-
-static int __init tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
-	return 0;
-}
 machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fc34025..38a4508 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -33,6 +33,8 @@
 #include <asm/runlatch.h>
 #include <asm/code-patching.h>
 #include <asm/dbell.h>
+#include <asm/kvm_ppc.h>
+#include <asm/ppc-opcode.h>
 
 #include "powernv.h"
 
@@ -149,7 +151,7 @@
 static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
-	unsigned long srr1;
+	unsigned long srr1, wmask;
 	u32 idle_states;
 
 	/* Standard hot unplug procedure */
@@ -161,6 +163,10 @@
 	generic_set_cpu_dead(cpu);
 	smp_wmb();
 
+	wmask = SRR1_WAKEMASK;
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		wmask = SRR1_WAKEMASK_P8;
+
 	idle_states = pnv_get_supported_cpuidle_states();
 	/* We don't want to take decrementer interrupts while we are offline,
 	 * so clear LPCR:PECE1. We keep PECE2 enabled.
@@ -191,10 +197,14 @@
 		 * having finished executing in a KVM guest, then srr1
 		 * contains 0.
 		 */
-		if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+		if ((srr1 & wmask) == SRR1_WAKEEE) {
 			icp_native_flush_interrupt();
 			local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
 			smp_mb();
+		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
+			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+			kvmppc_set_host_ipi(cpu, 0);
 		}
 
 		if (cpu_core_split_required())
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 1d3d52d..7803a19 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1340,3 +1340,5 @@
 }
 
 __setup("multitce=", disable_multitce);
+
+machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 90cf3dc..8f35d52 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -25,10 +25,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-	u32 phandle;
-	u32 state;
-	u64 reserved;
-	u32 nprops;
+	__be32 phandle;
+	__be32 state;
+	__be64 reserved;
+	__be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK	0xff000000
@@ -54,11 +54,11 @@
 	return rc;
 }
 
-static int delete_dt_node(u32 phandle)
+static int delete_dt_node(__be32 phandle)
 {
 	struct device_node *dn;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn)
 		return -ENOENT;
 
@@ -127,7 +127,7 @@
 	return 0;
 }
 
-static int update_dt_node(u32 phandle, s32 scope)
+static int update_dt_node(__be32 phandle, s32 scope)
 {
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
@@ -136,6 +136,7 @@
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
+	u32 nprops;
 	u32 vd;
 
 	update_properties_token = rtas_token("ibm,update-properties");
@@ -146,7 +147,7 @@
 	if (!rtas_buf)
 		return -ENOMEM;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn) {
 		kfree(rtas_buf);
 		return -ENOENT;
@@ -162,6 +163,7 @@
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
+		nprops = be32_to_cpu(upwa->nprops);
 
 		/* On the first call to ibm,update-properties for a node the
 		 * the first property value descriptor contains an empty
@@ -170,17 +172,17 @@
 		 */
 		if (*prop_data == 0) {
 			prop_data++;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += vd + sizeof(vd);
-			upwa->nprops--;
+			nprops--;
 		}
 
-		for (i = 0; i < upwa->nprops; i++) {
+		for (i = 0; i < nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
 			prop_data += strlen(prop_name) + 1;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += sizeof(vd);
 
 			switch (vd) {
@@ -212,13 +214,13 @@
 	return 0;
 }
 
-static int add_dt_node(u32 parent_phandle, u32 drc_index)
+static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
 {
 	struct device_node *dn;
 	struct device_node *parent_dn;
 	int rc;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
+	parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle));
 	if (!parent_dn)
 		return -ENOENT;
 
@@ -237,7 +239,7 @@
 int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
-	u32 *data;
+	__be32 *data;
 	int update_nodes_token;
 	int rc;
 
@@ -254,17 +256,17 @@
 		if (rc && rc != 1)
 			break;
 
-		data = (u32 *)rtas_buf + 4;
-		while (*data & NODE_ACTION_MASK) {
+		data = (__be32 *)rtas_buf + 4;
+		while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
 			int i;
-			u32 action = *data & NODE_ACTION_MASK;
-			int node_count = *data & NODE_COUNT_MASK;
+			u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
+			u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
 			data++;
 
 			for (i = 0; i < node_count; i++) {
-				u32 phandle = *data++;
-				u32 drc_index;
+				__be32 phandle = *data++;
+				__be32 drc_index;
 
 				switch (action) {
 				case DELETE_DT_NODE:
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index c9df40b..c9c875d 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -211,7 +211,7 @@
 
 extern unsigned long mmap_rnd_mask;
 
-#define STACK_RND_MASK	(mmap_rnd_mask)
+#define STACK_RND_MASK	(test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask)
 
 #define ARCH_DLINFO							    \
 do {									    \
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index d84559e..f407bbf 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -515,15 +515,15 @@
 #define S390_ARCH_FAC_MASK_SIZE_U64 \
 	(S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64))
 
-struct s390_model_fac {
-	/* facilities used in SIE context */
-	__u64 sie[S390_ARCH_FAC_LIST_SIZE_U64];
-	/* subset enabled by kvm */
-	__u64 kvm[S390_ARCH_FAC_LIST_SIZE_U64];
+struct kvm_s390_fac {
+	/* facility list requested by guest */
+	__u64 list[S390_ARCH_FAC_LIST_SIZE_U64];
+	/* facility mask supported by kvm & hosting machine */
+	__u64 mask[S390_ARCH_FAC_LIST_SIZE_U64];
 };
 
 struct kvm_s390_cpu_model {
-	struct s390_model_fac *fac;
+	struct kvm_s390_fac *fac;
 	struct cpuid cpu_id;
 	unsigned short ibc;
 };
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index f49b719..8fb3802 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -62,6 +62,7 @@
 {
 	int cpu = smp_processor_id();
 
+	S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
 	if (prev == next)
 		return;
 	if (MACHINE_HAS_TLB_LC)
@@ -73,7 +74,6 @@
 	atomic_dec(&prev->context.attach_count);
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
-	S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 7b2ac6e..53eacbd 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -37,16 +37,7 @@
 #endif
 }
 
-static inline void clear_page(void *page)
-{
-	register unsigned long reg1 asm ("1") = 0;
-	register void *reg2 asm ("2") = page;
-	register unsigned long reg3 asm ("3") = 4096;
-	asm volatile(
-		"	mvcl	2,0"
-		: "+d" (reg2), "+d" (reg3) : "d" (reg1)
-		: "memory", "cc");
-}
+#define clear_page(page)	memset((page), 0, PAGE_SIZE)
 
 /*
  * copy_page uses the mvcl instruction with 0xb0 padding byte in order to
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index fbb5ee3..e08ec38 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -91,7 +91,9 @@
  */
 #define PTRS_PER_PTE	256
 #ifndef CONFIG_64BIT
+#define __PAGETABLE_PUD_FOLDED
 #define PTRS_PER_PMD	1
+#define __PAGETABLE_PMD_FOLDED
 #define PTRS_PER_PUD	1
 #else /* CONFIG_64BIT */
 #define PTRS_PER_PMD	2048
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 82c1989..6c79f1b 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -57,6 +57,44 @@
 
 unsigned long ftrace_plt;
 
+static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
+{
+#ifdef CC_USING_HOTPATCH
+	/* brcl 0,0 */
+	insn->opc = 0xc004;
+	insn->disp = 0;
+#else
+	/* stg r14,8(r15) */
+	insn->opc = 0xe3e0;
+	insn->disp = 0xf0080024;
+#endif
+}
+
+static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	if (insn->opc == BREAKPOINT_INSTRUCTION)
+		return 1;
+#endif
+	return 0;
+}
+
+static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	insn->opc = BREAKPOINT_INSTRUCTION;
+	insn->disp = KPROBE_ON_FTRACE_NOP;
+#endif
+}
+
+static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	insn->opc = BREAKPOINT_INSTRUCTION;
+	insn->disp = KPROBE_ON_FTRACE_CALL;
+#endif
+}
+
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
@@ -72,16 +110,9 @@
 		return -EFAULT;
 	if (addr == MCOUNT_ADDR) {
 		/* Initial code replacement */
-#ifdef CC_USING_HOTPATCH
-		/* We expect to see brcl 0,0 */
-		ftrace_generate_nop_insn(&orig);
-#else
-		/* We expect to see stg r14,8(r15) */
-		orig.opc = 0xe3e0;
-		orig.disp = 0xf0080024;
-#endif
+		ftrace_generate_orig_insn(&orig);
 		ftrace_generate_nop_insn(&new);
-	} else if (old.opc == BREAKPOINT_INSTRUCTION) {
+	} else if (is_kprobe_on_ftrace(&old)) {
 		/*
 		 * If we find a breakpoint instruction, a kprobe has been
 		 * placed at the beginning of the function. We write the
@@ -89,9 +120,8 @@
 		 * bytes of the original instruction so that the kprobes
 		 * handler can execute a nop, if it reaches this breakpoint.
 		 */
-		new.opc = orig.opc = BREAKPOINT_INSTRUCTION;
-		orig.disp = KPROBE_ON_FTRACE_CALL;
-		new.disp = KPROBE_ON_FTRACE_NOP;
+		ftrace_generate_kprobe_call_insn(&orig);
+		ftrace_generate_kprobe_nop_insn(&new);
 	} else {
 		/* Replace ftrace call with a nop. */
 		ftrace_generate_call_insn(&orig, rec->ip);
@@ -111,7 +141,7 @@
 
 	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
-	if (old.opc == BREAKPOINT_INSTRUCTION) {
+	if (is_kprobe_on_ftrace(&old)) {
 		/*
 		 * If we find a breakpoint instruction, a kprobe has been
 		 * placed at the beginning of the function. We write the
@@ -119,9 +149,8 @@
 		 * bytes of the original instruction so that the kprobes
 		 * handler can execute a brasl if it reaches this breakpoint.
 		 */
-		new.opc = orig.opc = BREAKPOINT_INSTRUCTION;
-		orig.disp = KPROBE_ON_FTRACE_NOP;
-		new.disp = KPROBE_ON_FTRACE_CALL;
+		ftrace_generate_kprobe_nop_insn(&orig);
+		ftrace_generate_kprobe_call_insn(&new);
 	} else {
 		/* Replace nop with an ftrace call. */
 		ftrace_generate_nop_insn(&orig);
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index cb2d51e..830066f 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -36,16 +36,20 @@
 	insn->offset = (entry->target - entry->code) >> 1;
 }
 
-static void jump_label_bug(struct jump_entry *entry, struct insn *insn)
+static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
+			   struct insn *new)
 {
 	unsigned char *ipc = (unsigned char *)entry->code;
-	unsigned char *ipe = (unsigned char *)insn;
+	unsigned char *ipe = (unsigned char *)expected;
+	unsigned char *ipn = (unsigned char *)new;
 
 	pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc);
 	pr_emerg("Found:    %02x %02x %02x %02x %02x %02x\n",
 		 ipc[0], ipc[1], ipc[2], ipc[3], ipc[4], ipc[5]);
 	pr_emerg("Expected: %02x %02x %02x %02x %02x %02x\n",
 		 ipe[0], ipe[1], ipe[2], ipe[3], ipe[4], ipe[5]);
+	pr_emerg("New:      %02x %02x %02x %02x %02x %02x\n",
+		 ipn[0], ipn[1], ipn[2], ipn[3], ipn[4], ipn[5]);
 	panic("Corrupted kernel text");
 }
 
@@ -69,10 +73,10 @@
 	}
 	if (init) {
 		if (memcmp((void *)entry->code, &orignop, sizeof(orignop)))
-			jump_label_bug(entry, &old);
+			jump_label_bug(entry, &orignop, &new);
 	} else {
 		if (memcmp((void *)entry->code, &old, sizeof(old)))
-			jump_label_bug(entry, &old);
+			jump_label_bug(entry, &old, &new);
 	}
 	probe_kernel_write((void *)entry->code, &new, sizeof(new));
 }
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 36154a2..2ca9586 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -436,6 +436,7 @@
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
+	jump_label_apply_nops(me);
 	vfree(me->arch.syminfo);
 	me->arch.syminfo = NULL;
 	return 0;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index c3f8d15..e6a1578 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1415,7 +1415,7 @@
 
 static struct attribute *cpumsf_pmu_events_attr[] = {
 	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
-	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG),
+	NULL,
 	NULL,
 };
 
@@ -1606,8 +1606,11 @@
 		return -EINVAL;
 	}
 
-	if (si.ad)
+	if (si.ad) {
 		sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+		cpumsf_pmu_events_attr[1] =
+			CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
+	}
 
 	sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
 	if (!sfdbg)
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 2610823..dc488e1 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -18,7 +18,7 @@
 
 static DEFINE_PER_CPU(struct cpuid, cpu_id);
 
-void cpu_relax(void)
+void notrace cpu_relax(void)
 {
 	if (!smp_cpu_mtid && MACHINE_HAS_DIAG44)
 		asm volatile("diag 0,0,0x44");
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index 6b09fdf..ca629464 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -177,6 +177,17 @@
 	lhi	%r1,1
 	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
 	sam64
+#ifdef CONFIG_SMP
+	larl	%r1,smp_cpu_mt_shift
+	icm	%r1,15,0(%r1)
+	jz	smt_done
+	llgfr	%r1,%r1
+smt_loop:
+	sigp	%r1,%r0,SIGP_SET_MULTI_THREADING
+	brc	8,smt_done			/* accepted */
+	brc	2,smt_loop			/* busy, try again */
+smt_done:
+#endif
 	larl	%r1,.Lnew_pgm_check_psw
 	lpswe	0(%r1)
 pgm_check_entry:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0c36239..19e17bd 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -165,7 +165,6 @@
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
@@ -522,7 +521,7 @@
 		memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
 		       sizeof(struct cpuid));
 		kvm->arch.model.ibc = proc->ibc;
-		memcpy(kvm->arch.model.fac->kvm, proc->fac_list,
+		memcpy(kvm->arch.model.fac->list, proc->fac_list,
 		       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	} else
 		ret = -EFAULT;
@@ -556,7 +555,7 @@
 	}
 	memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
 	proc->ibc = kvm->arch.model.ibc;
-	memcpy(&proc->fac_list, kvm->arch.model.fac->kvm, S390_ARCH_FAC_LIST_SIZE_BYTE);
+	memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
 	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
 		ret = -EFAULT;
 	kfree(proc);
@@ -576,10 +575,10 @@
 	}
 	get_cpu_id((struct cpuid *) &mach->cpuid);
 	mach->ibc = sclp_get_ibc();
-	memcpy(&mach->fac_mask, kvm_s390_fac_list_mask,
-	       kvm_s390_fac_list_mask_size() * sizeof(u64));
+	memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
+	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
-	       S390_ARCH_FAC_LIST_SIZE_U64);
+	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
 		ret = -EFAULT;
 	kfree(mach);
@@ -778,15 +777,18 @@
 static int kvm_s390_query_ap_config(u8 *config)
 {
 	u32 fcn_code = 0x04000000UL;
-	u32 cc;
+	u32 cc = 0;
 
+	memset(config, 0, 128);
 	asm volatile(
 		"lgr 0,%1\n"
 		"lgr 2,%2\n"
 		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"ipm %0\n"
+		"0: ipm %0\n"
 		"srl %0,28\n"
-		: "=r" (cc)
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+r" (cc)
 		: "r" (fcn_code), "r" (config)
 		: "cc", "0", "2", "memory"
 	);
@@ -839,9 +841,13 @@
 
 	kvm_s390_set_crycb_format(kvm);
 
-	/* Disable AES/DEA protected key functions by default */
-	kvm->arch.crypto.aes_kw = 0;
-	kvm->arch.crypto.dea_kw = 0;
+	/* Enable AES/DEA protected key functions by default */
+	kvm->arch.crypto.aes_kw = 1;
+	kvm->arch.crypto.dea_kw = 1;
+	get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask,
+			 sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
+	get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
+			 sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
 
 	return 0;
 }
@@ -886,40 +892,29 @@
 	/*
 	 * The architectural maximum amount of facilities is 16 kbit. To store
 	 * this amount, 2 kbyte of memory is required. Thus we need a full
-	 * page to hold the active copy (arch.model.fac->sie) and the current
-	 * facilities set (arch.model.fac->kvm). Its address size has to be
+	 * page to hold the guest facility list (arch.model.fac->list) and the
+	 * facility mask (arch.model.fac->mask). Its address size has to be
 	 * 31 bits and word aligned.
 	 */
 	kvm->arch.model.fac =
-		(struct s390_model_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+		(struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 	if (!kvm->arch.model.fac)
 		goto out_nofac;
 
-	memcpy(kvm->arch.model.fac->kvm, S390_lowcore.stfle_fac_list,
-	       S390_ARCH_FAC_LIST_SIZE_U64);
-
-	/*
-	 * If this KVM host runs *not* in a LPAR, relax the facility bits
-	 * of the kvm facility mask by all missing facilities. This will allow
-	 * to determine the right CPU model by means of the remaining facilities.
-	 * Live guest migration must prohibit the migration of KVMs running in
-	 * a LPAR to non LPAR hosts.
-	 */
-	if (!MACHINE_IS_LPAR)
-		for (i = 0; i < kvm_s390_fac_list_mask_size(); i++)
-			kvm_s390_fac_list_mask[i] &= kvm->arch.model.fac->kvm[i];
-
-	/*
-	 * Apply the kvm facility mask to limit the kvm supported/tolerated
-	 * facility list.
-	 */
+	/* Populate the facility mask initially. */
+	memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
+	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
 		if (i < kvm_s390_fac_list_mask_size())
-			kvm->arch.model.fac->kvm[i] &= kvm_s390_fac_list_mask[i];
+			kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
 		else
-			kvm->arch.model.fac->kvm[i] = 0UL;
+			kvm->arch.model.fac->mask[i] = 0UL;
 	}
 
+	/* Populate the facility list initially. */
+	memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
+	       S390_ARCH_FAC_LIST_SIZE_BYTE);
+
 	kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
 	kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff;
 
@@ -1165,8 +1160,6 @@
 
 	mutex_lock(&vcpu->kvm->lock);
 	vcpu->arch.cpu_id = vcpu->kvm->arch.model.cpu_id;
-	memcpy(vcpu->kvm->arch.model.fac->sie, vcpu->kvm->arch.model.fac->kvm,
-	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	vcpu->arch.sie_block->ibc = vcpu->kvm->arch.model.ibc;
 	mutex_unlock(&vcpu->kvm->lock);
 
@@ -1212,7 +1205,7 @@
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
 		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
 	}
-	vcpu->arch.sie_block->fac = (int) (long) kvm->arch.model.fac->sie;
+	vcpu->arch.sie_block->fac = (int) (long) kvm->arch.model.fac->list;
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 985c2114..c34109a 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -128,7 +128,8 @@
 /* test availability of facility in a kvm intance */
 static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
 {
-	return __test_facility(nr, kvm->arch.model.fac->kvm);
+	return __test_facility(nr, kvm->arch.model.fac->mask) &&
+		__test_facility(nr, kvm->arch.model.fac->list);
 }
 
 /* are cpu states controlled by user space */
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index bdd9b5b..3511169 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -348,7 +348,7 @@
 	 * We need to shift the lower 32 facility bits (bit 0-31) from a u64
 	 * into a u32 memory representation. They will remain bits 0-31.
 	 */
-	fac = *vcpu->kvm->arch.model.fac->sie >> 32;
+	fac = *vcpu->kvm->arch.model.fac->list >> 32;
 	rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list),
 			    &fac, sizeof(fac));
 	if (rc)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 753a567..f0b8544 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -287,7 +287,7 @@
 	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
 	return (void __iomem *) addr + offset;
 }
-EXPORT_SYMBOL_GPL(pci_iomap_range);
+EXPORT_SYMBOL(pci_iomap_range);
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
@@ -309,7 +309,7 @@
 	}
 	spin_unlock(&zpci_iomap_lock);
 }
-EXPORT_SYMBOL_GPL(pci_iounmap);
+EXPORT_SYMBOL(pci_iounmap);
 
 static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
 		    int size, u32 *val)
@@ -483,9 +483,8 @@
 	airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
 }
 
-static void zpci_map_resources(struct zpci_dev *zdev)
+static void zpci_map_resources(struct pci_dev *pdev)
 {
-	struct pci_dev *pdev = zdev->pdev;
 	resource_size_t len;
 	int i;
 
@@ -499,9 +498,8 @@
 	}
 }
 
-static void zpci_unmap_resources(struct zpci_dev *zdev)
+static void zpci_unmap_resources(struct pci_dev *pdev)
 {
-	struct pci_dev *pdev = zdev->pdev;
 	resource_size_t len;
 	int i;
 
@@ -651,7 +649,7 @@
 
 	zdev->pdev = pdev;
 	pdev->dev.groups = zpci_attr_groups;
-	zpci_map_resources(zdev);
+	zpci_map_resources(pdev);
 
 	for (i = 0; i < PCI_BAR_COUNT; i++) {
 		res = &pdev->resource[i];
@@ -663,6 +661,11 @@
 	return 0;
 }
 
+void pcibios_release_device(struct pci_dev *pdev)
+{
+	zpci_unmap_resources(pdev);
+}
+
 int pcibios_enable_device(struct pci_dev *pdev, int mask)
 {
 	struct zpci_dev *zdev = get_zdev(pdev);
@@ -670,7 +673,6 @@
 	zdev->pdev = pdev;
 	zpci_debug_init_device(zdev);
 	zpci_fmb_enable_device(zdev);
-	zpci_map_resources(zdev);
 
 	return pci_enable_resources(pdev, mask);
 }
@@ -679,7 +681,6 @@
 {
 	struct zpci_dev *zdev = get_zdev(pdev);
 
-	zpci_unmap_resources(zdev);
 	zpci_fmb_disable_device(zdev);
 	zpci_debug_exit_device(zdev);
 	zdev->pdev = NULL;
@@ -688,7 +689,8 @@
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 static int zpci_restore(struct device *dev)
 {
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
 	int ret = 0;
 
 	if (zdev->state != ZPCI_FN_STATE_ONLINE)
@@ -698,7 +700,7 @@
 	if (ret)
 		goto out;
 
-	zpci_map_resources(zdev);
+	zpci_map_resources(pdev);
 	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
 			   zdev->start_dma + zdev->iommu_size - 1,
 			   (u64) zdev->dma_table);
@@ -709,12 +711,14 @@
 
 static int zpci_freeze(struct device *dev)
 {
-	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
 
 	if (zdev->state != ZPCI_FN_STATE_ONLINE)
 		return 0;
 
 	zpci_unregister_ioat(zdev, 0);
+	zpci_unmap_resources(pdev);
 	return clp_disable_fh(zdev);
 }
 
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 8aa271b..b1bb2b72 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -64,8 +64,7 @@
 	if (copy_from_user(buf, user_buffer, length))
 		goto out;
 
-	memcpy_toio(io_addr, buf, length);
-	ret = 0;
+	ret = zpci_memcpy_toio(io_addr, buf, length);
 out:
 	if (buf != local_buf)
 		kfree(buf);
@@ -98,16 +97,16 @@
 		goto out;
 	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
 
-	ret = -EFAULT;
-	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
+	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) {
+		ret = -EFAULT;
 		goto out;
-
-	memcpy_fromio(buf, io_addr, length);
-
+	}
+	ret = zpci_memcpy_fromio(buf, io_addr, length);
+	if (ret)
+		goto out;
 	if (copy_to_user(user_buffer, buf, length))
-		goto out;
+		ret = -EFAULT;
 
-	ret = 0;
 out:
 	if (buf != local_buf)
 		kfree(buf);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 96ac69c..efb00ec 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -86,6 +86,9 @@
 	default "arch/sparc/configs/sparc32_defconfig" if SPARC32
 	default "arch/sparc/configs/sparc64_defconfig" if SPARC64
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+
 config IOMMU_HELPER
 	bool
 	default y if SPARC64
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 4f6725f..f5b6537 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2957,6 +2957,17 @@
 				   unsigned long reg_val);
 #endif
 
+
+#define HV_FAST_M7_GET_PERFREG	0x43
+#define HV_FAST_M7_SET_PERFREG	0x44
+
+#ifndef	__ASSEMBLY__
+unsigned long sun4v_m7_get_perfreg(unsigned long reg_num,
+				      unsigned long *reg_val);
+unsigned long sun4v_m7_set_perfreg(unsigned long reg_num,
+				      unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2981,6 +2992,7 @@
 #define HV_GRP_SDIO			0x0108
 #define HV_GRP_SDIO_ERR			0x0109
 #define HV_GRP_REBOOT_DATA		0x0110
+#define HV_GRP_M7_PERF			0x0114
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
 #define HV_GRP_N2_CPU			0x0202
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9b672be..50d4840 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -407,16 +407,16 @@
 {
 }
 
-#define ioread8(X)			readb(X)
-#define ioread16(X)			readw(X)
-#define ioread16be(X)			__raw_readw(X)
-#define ioread32(X)			readl(X)
-#define ioread32be(X)			__raw_readl(X)
-#define iowrite8(val,X)			writeb(val,X)
-#define iowrite16(val,X)		writew(val,X)
-#define iowrite16be(val,X)		__raw_writew(val,X)
-#define iowrite32(val,X)		writel(val,X)
-#define iowrite32be(val,X)		__raw_writel(val,X)
+#define ioread8			readb
+#define ioread16		readw
+#define ioread16be		__raw_readw
+#define ioread32		readl
+#define ioread32be		__raw_readl
+#define iowrite8		writeb
+#define iowrite16		writew
+#define iowrite16be		__raw_writew
+#define iowrite32		writel
+#define iowrite32be		__raw_writel
 
 /* Create a virtual mapping cookie for an IO port range */
 void __iomem *ioport_map(unsigned long port, unsigned int nr);
diff --git a/arch/sparc/include/asm/starfire.h b/arch/sparc/include/asm/starfire.h
index c100dc2..176fa0a 100644
--- a/arch/sparc/include/asm/starfire.h
+++ b/arch/sparc/include/asm/starfire.h
@@ -12,7 +12,6 @@
 extern int this_is_starfire;
 
 void check_if_starfire(void);
-int starfire_hard_smp_processor_id(void);
 void starfire_hookup(int);
 unsigned int starfire_translate(unsigned long imap, unsigned int upaid);
 
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 88d322b..07cc49e5 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -98,11 +98,7 @@
 void do_privop(struct pt_regs *regs);
 void do_privact(struct pt_regs *regs);
 void do_cee(struct pt_regs *regs);
-void do_cee_tl1(struct pt_regs *regs);
-void do_dae_tl1(struct pt_regs *regs);
-void do_iae_tl1(struct pt_regs *regs);
 void do_div0_tl1(struct pt_regs *regs);
-void do_fpdis_tl1(struct pt_regs *regs);
 void do_fpieee_tl1(struct pt_regs *regs);
 void do_fpother_tl1(struct pt_regs *regs);
 void do_ill_tl1(struct pt_regs *regs);
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 5c55145..662500f 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -48,6 +48,7 @@
 	{ .group = HV_GRP_VT_CPU,				},
 	{ .group = HV_GRP_T5_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
+	{ .group = HV_GRP_M7_PERF,				},
 };
 
 static DEFINE_SPINLOCK(hvapi_lock);
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index caedf83..afbaba5 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -837,3 +837,19 @@
 	retl
 	 nop
 ENDPROC(sun4v_t5_set_perfreg)
+
+ENTRY(sun4v_m7_get_perfreg)
+	mov	%o1, %o4
+	mov	HV_FAST_M7_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	nop
+ENDPROC(sun4v_m7_get_perfreg)
+
+ENTRY(sun4v_m7_set_perfreg)
+	mov	HV_FAST_M7_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	nop
+ENDPROC(sun4v_m7_set_perfreg)
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 7e967c8..eb978c7 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -217,6 +217,31 @@
 	.pcr_nmi_disable	= PCR_N4_PICNPT,
 };
 
+static u64 m7_pcr_read(unsigned long reg_num)
+{
+	unsigned long val;
+
+	(void) sun4v_m7_get_perfreg(reg_num, &val);
+
+	return val;
+}
+
+static void m7_pcr_write(unsigned long reg_num, u64 val)
+{
+	(void) sun4v_m7_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops m7_pcr_ops = {
+	.read_pcr		= m7_pcr_read,
+	.write_pcr		= m7_pcr_write,
+	.read_pic		= n4_pic_read,
+	.write_pic		= n4_pic_write,
+	.nmi_picl_value		= n4_picl_value,
+	.pcr_nmi_enable		= (PCR_N4_PICNPT | PCR_N4_STRACE |
+				   PCR_N4_UTRACE | PCR_N4_TOE |
+				   (26 << PCR_N4_SL_SHIFT)),
+	.pcr_nmi_disable	= PCR_N4_PICNPT,
+};
 
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
@@ -248,6 +273,10 @@
 			perf_hsvc_group = HV_GRP_T5_CPU;
 			break;
 
+		case SUN4V_CHIP_SPARC_M7:
+			perf_hsvc_group = HV_GRP_M7_PERF;
+			break;
+
 		default:
 			return -ENODEV;
 		}
@@ -293,6 +322,10 @@
 		pcr_ops = &n5_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_SPARC_M7:
+		pcr_ops = &m7_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 46a5e45..86eebfa 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -792,6 +792,42 @@
 	.num_pic_regs	= 4,
 };
 
+static void sparc_m7_write_pmc(int idx, u64 val)
+{
+	u64 pcr;
+
+	pcr = pcr_ops->read_pcr(idx);
+	/* ensure ov and ntc are reset */
+	pcr &= ~(PCR_N4_OV | PCR_N4_NTC);
+
+	pcr_ops->write_pic(idx, val & 0xffffffff);
+
+	pcr_ops->write_pcr(idx, pcr);
+}
+
+static const struct sparc_pmu sparc_m7_pmu = {
+	.event_map	= niagara4_event_map,
+	.cache_map	= &niagara4_cache_map,
+	.max_events	= ARRAY_SIZE(niagara4_perfmon_event_map),
+	.read_pmc	= sparc_vt_read_pmc,
+	.write_pmc	= sparc_m7_write_pmc,
+	.upper_shift	= 5,
+	.lower_shift	= 5,
+	.event_mask	= 0x7ff,
+	.user_bit	= PCR_N4_UTRACE,
+	.priv_bit	= PCR_N4_STRACE,
+
+	/* We explicitly don't support hypervisor tracing. */
+	.hv_bit		= 0,
+
+	.irq_bit	= PCR_N4_TOE,
+	.upper_nop	= 0,
+	.lower_nop	= 0,
+	.flags		= 0,
+	.max_hw_events	= 4,
+	.num_pcrs	= 4,
+	.num_pic_regs	= 4,
+};
 static const struct sparc_pmu *sparc_pmu __read_mostly;
 
 static u64 event_encoding(u64 event_id, int idx)
@@ -960,6 +996,8 @@
 	cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags);
+
 /* On this PMU each PIC has it's own PCR control register.  */
 static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 {
@@ -972,20 +1010,13 @@
 		struct perf_event *cp = cpuc->event[i];
 		struct hw_perf_event *hwc = &cp->hw;
 		int idx = hwc->idx;
-		u64 enc;
 
 		if (cpuc->current_idx[i] != PIC_NO_INDEX)
 			continue;
 
-		sparc_perf_event_set_period(cp, hwc, idx);
 		cpuc->current_idx[i] = idx;
 
-		enc = perf_event_get_enc(cpuc->events[i]);
-		cpuc->pcr[idx] &= ~mask_for_index(idx);
-		if (hwc->state & PERF_HES_STOPPED)
-			cpuc->pcr[idx] |= nop_for_index(idx);
-		else
-			cpuc->pcr[idx] |= event_encoding(enc, idx);
+		sparc_pmu_start(cp, PERF_EF_RELOAD);
 	}
 out:
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1132,6 @@
 	int i;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event[i]) {
@@ -1127,7 +1157,6 @@
 		}
 	}
 
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -1361,7 +1390,6 @@
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
 	if (n0 >= sparc_pmu->max_hw_events)
@@ -1394,7 +1422,6 @@
 
 	ret = 0;
 out:
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -1667,6 +1694,10 @@
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
+	if (!strcmp(sparc_pmu_type, "sparc-m7")) {
+		sparc_pmu = &sparc_m7_pmu;
+		return true;
+	}
 	return false;
 }
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 0be7bf9..46a5964 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -287,6 +287,8 @@
 			printk("             TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
 			       gp->tpc, gp->o7, gp->i7, gp->rpc);
 		}
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
@@ -362,6 +364,8 @@
 		       (cpu == this_cpu ? '*' : ' '), cpu,
 		       pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
 		       pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index da6f1a7..61139d9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1406,11 +1406,32 @@
 	scheduler_ipi();
 }
 
-/* This is a nop because we capture all other cpus
- * anyways when making the PROM active.
- */
+static void stop_this_cpu(void *dummy)
+{
+	prom_stopself();
+}
+
 void smp_send_stop(void)
 {
+	int cpu;
+
+	if (tlb_type == hypervisor) {
+		for_each_online_cpu(cpu) {
+			if (cpu == smp_processor_id())
+				continue;
+#ifdef CONFIG_SUN_LDOMS
+			if (ldom_domaining_enabled) {
+				unsigned long hv_err;
+				hv_err = sun4v_cpu_stop(cpu);
+				if (hv_err)
+					printk(KERN_ERR "sun4v_cpu_stop() "
+					       "failed err=%lu\n", hv_err);
+			} else
+#endif
+				prom_stopcpu_cpuid(cpu);
+		}
+	} else
+		smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 /**
diff --git a/arch/sparc/kernel/starfire.c b/arch/sparc/kernel/starfire.c
index 82281a5..167fdfd 100644
--- a/arch/sparc/kernel/starfire.c
+++ b/arch/sparc/kernel/starfire.c
@@ -28,11 +28,6 @@
 		this_is_starfire = 1;
 }
 
-int starfire_hard_smp_processor_id(void)
-{
-	return upa_readl(0x1fff40000d0UL);
-}
-
 /*
  * Each Starfire board has 32 registers which perform translation
  * and delivery of traditional interrupt packets into the extended
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c85403d..30e7ddb 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -333,7 +333,7 @@
 	long err;
 
 	/* No need for backward compatibility. We can start fresh... */
-	if (call <= SEMCTL) {
+	if (call <= SEMTIMEDOP) {
 		switch (call) {
 		case SEMOP:
 			err = sys_semtimedop(first, ptr,
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index a27651e..0e69974 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2427,6 +2427,8 @@
 		}
 		user_instruction_dump ((unsigned int __user *) regs->tpc);
 	}
+	if (panic_on_oops)
+		panic("Fatal exception");
 	if (regs->tstate & TSTATE_PRIV)
 		do_exit(SIGKILL);
 	do_exit(SIGSEGV);
@@ -2564,27 +2566,6 @@
 	die_if_kernel("TL0: Cache Error Exception", regs);
 }
 
-void do_cee_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: Cache Error Exception", regs);
-}
-
-void do_dae_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: Data Access Exception", regs);
-}
-
-void do_iae_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: Instruction Access Exception", regs);
-}
-
 void do_div0_tl1(struct pt_regs *regs)
 {
 	exception_enter();
@@ -2592,13 +2573,6 @@
 	die_if_kernel("TL1: DIV0 Exception", regs);
 }
 
-void do_fpdis_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: FPU Disabled", regs);
-}
-
 void do_fpieee_tl1(struct pt_regs *regs)
 {
 	exception_enter();
diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index b7f6334..857ad4f 100644
--- a/arch/sparc/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
@@ -8,9 +8,11 @@
 
 	.text
 ENTRY(memmove) /* o0=dst o1=src o2=len */
-	mov		%o0, %g1
+	brz,pn		%o2, 99f
+	 mov		%o0, %g1
+
 	cmp		%o0, %o1
-	bleu,pt		%xcc, memcpy
+	bleu,pt		%xcc, 2f
 	 add		%o1, %o2, %g7
 	cmp		%g7, %o0
 	bleu,pt		%xcc, memcpy
@@ -24,7 +26,34 @@
 	stb		%g7, [%o0]
 	bne,pt		%icc, 1b
 	 sub		%o0, 1, %o0
-
+99:
 	retl
 	 mov		%g1, %o0
+
+	/* We can't just call memcpy for these memmove cases.  On some
+	 * chips the memcpy uses cache initializing stores and when dst
+	 * and src are close enough, those can clobber the source data
+	 * before we've loaded it in.
+	 */
+2:	or		%o0, %o1, %g7
+	or		%o2, %g7, %g7
+	andcc		%g7, 0x7, %g0
+	bne,pn		%xcc, 4f
+	 nop
+
+3:	ldx		[%o1], %g7
+	add		%o1, 8, %o1
+	subcc		%o2, 8, %o2
+	add		%o0, 8, %o0
+	bne,pt		%icc, 3b
+	 stx		%g7, [%o0 - 0x8]
+	ba,a,pt		%xcc, 99b
+
+4:	ldub		[%o1], %g7
+	add		%o1, 1, %o1
+	subcc		%o2, 1, %o2
+	add		%o0, 1, %o0
+	bne,pt		%icc, 4b
+	 stb		%g7, [%o0 - 0x1]
+	ba,a,pt		%xcc, 99b
 ENDPROC(memmove)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3ea267c..4ca0d6b 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2820,7 +2820,7 @@
 
 	return 0;
 }
-device_initcall(report_memory);
+arch_initcall(report_memory);
 
 #ifdef CONFIG_SMP
 #define do_flush_tlb_kernel_range	smp_flush_tlb_kernel_range
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c2fb8a8..b7d31ca 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -499,6 +499,7 @@
 	depends on X86_IO_APIC
 	select IOSF_MBI
 	select INTEL_IMR
+	select COMMON_CLK
 	---help---
 	  Select to include support for Quark X1000 SoC.
 	  Say Y here if you have a Quark based system such as the Arduino
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 7083c16..bb13763 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -14,13 +14,6 @@
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
 
-struct kaslr_setup_data {
-	__u64 next;
-	__u32 type;
-	__u32 len;
-	__u8 data[1];
-} kaslr_setup_data;
-
 #define I8254_PORT_CONTROL	0x43
 #define I8254_PORT_COUNTER0	0x40
 #define I8254_CMD_READBACK	0xC0
@@ -302,29 +295,7 @@
 	return slots_fetch_random();
 }
 
-static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled)
-{
-	struct setup_data *data;
-
-	kaslr_setup_data.type = SETUP_KASLR;
-	kaslr_setup_data.len = 1;
-	kaslr_setup_data.next = 0;
-	kaslr_setup_data.data[0] = enabled;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	if (data)
-		data->next = (unsigned long)&kaslr_setup_data;
-	else
-		params->hdr.setup_data = (unsigned long)&kaslr_setup_data;
-
-}
-
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
@@ -335,17 +306,14 @@
 #ifdef CONFIG_HIBERNATION
 	if (!cmdline_find_option_bool("kaslr")) {
 		debug_putstr("KASLR disabled by default...\n");
-		add_kaslr_setup_data(params, 0);
 		goto out;
 	}
 #else
 	if (cmdline_find_option_bool("nokaslr")) {
 		debug_putstr("KASLR disabled by cmdline...\n");
-		add_kaslr_setup_data(params, 0);
 		goto out;
 	}
 #endif
-	add_kaslr_setup_data(params, 1);
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 5903089..a950864 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -401,8 +401,7 @@
 	 * the entire decompressed kernel plus relocation table, or the
 	 * entire decompressed kernel plus .bss and .brk sections.
 	 */
-	output = choose_kernel_location(real_mode, input_data, input_len,
-					output,
+	output = choose_kernel_location(input_data, input_len, output,
 					output_len > run_size ? output_len
 							      : run_size);
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index ee3576b..04477d6 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -57,8 +57,7 @@
 
 #if CONFIG_RANDOMIZE_BASE
 /* aslr.c */
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size);
@@ -66,8 +65,7 @@
 bool has_cpuflag(int flag);
 #else
 static inline
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 947c6bf..54f60ab 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1155,7 +1155,7 @@
 		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
 		if (!src)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
+		assoc = (src + req->cryptlen);
 		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
 		scatterwalk_map_and_copy(assoc, req->assoc, 0,
 			req->assoclen, 0);
@@ -1180,7 +1180,7 @@
 		scatterwalk_done(&src_sg_walk, 0, 0);
 		scatterwalk_done(&assoc_sg_walk, 0, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1);
+		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
 		kfree(src);
 	}
 	return retval;
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 0dbc082..72ba21a 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -370,7 +370,7 @@
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
-	clear_used_math();
+	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 95e11f7..f97fbe3 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,8 +51,6 @@
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
-extern bool kaslr_enabled;
-
 static inline phys_addr_t get_max_mapped(void)
 {
 	return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195d..164e3f8 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 5fa9770..c9a6d68 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -82,18 +82,15 @@
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XSAVES"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XSAVE"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -112,18 +109,15 @@
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XRSTORS"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XRSTOR"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -149,9 +143,9 @@
 	 */
 	alternative_input_2(
 		"1:"XSAVE,
-		"1:"XSAVEOPT,
+		XSAVEOPT,
 		X86_FEATURE_XSAVEOPT,
-		"1:"XSAVES,
+		XSAVES,
 		X86_FEATURE_XSAVES,
 		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
 		"memory");
@@ -178,7 +172,7 @@
 	 */
 	alternative_input(
 		"1: " XRSTOR,
-		"1: " XRSTORS,
+		XRSTORS,
 		X86_FEATURE_XSAVES,
 		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 		: "memory");
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 44e6dd7..225b098 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -7,7 +7,6 @@
 #define SETUP_DTB			2
 #define SETUP_PCI			3
 #define SETUP_EFI			4
-#define SETUP_KASLR			5
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3d525c6..803b684 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1338,6 +1338,26 @@
 }
 
 /*
+ * ACPI offers an alternative platform interface model that removes
+ * ACPI hardware requirements for platforms that do not implement
+ * the PC Architecture.
+ *
+ * We initialize the Hardware-reduced ACPI model here:
+ */
+static void __init acpi_reduced_hw_init(void)
+{
+	if (acpi_gbl_reduced_hardware) {
+		/*
+		 * Override x86_init functions and bypass legacy pic
+		 * in Hardware-reduced ACPI mode
+		 */
+		x86_init.timers.timer_init	= x86_init_noop;
+		x86_init.irqs.pre_vector_init	= x86_init_noop;
+		legacy_pic			= &null_legacy_pic;
+	}
+}
+
+/*
  * If your system is blacklisted here, but you find that acpi=force
  * works for you, please contact linux-acpi@vger.kernel.org
  */
@@ -1536,6 +1556,11 @@
 	 */
 	early_acpi_process_madt();
 
+	/*
+	 * Hardware-reduced ACPI mode initialization:
+	 */
+	acpi_reduced_hw_init();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index c2fd21f..017149c 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -37,10 +37,12 @@
 static unsigned int get_apic_id(unsigned long x)
 {
 	unsigned long value;
-	unsigned int id;
+	unsigned int id = (x >> 24) & 0xff;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, value);
-	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		id |= (value << 2) & 0xff00;
+	}
 
 	return id;
 }
@@ -155,10 +157,18 @@
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	if (c->phys_proc_id != node) {
-		c->phys_proc_id = node;
-		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	u64 val;
+	u32 nodes = 1;
+
+	this_cpu_write(cpu_llc_id, node);
+
+	/* Account for nodes per socket in multi-core-module processors */
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+		rdmsrl(MSR_FAM10H_NODE_ID, val);
+		nodes = ((val >> 3) & 7) + 1;
 	}
+
+	c->phys_proc_id = node / nodes;
 }
 
 static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b5c8ff5..2346c95 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1396,6 +1396,12 @@
 
 	wait_for_master_cpu(cpu);
 
+	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
+
 	show_ucode_info_early();
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 94d7dcb..50163fa 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -565,8 +565,8 @@
 	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
 	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
 	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
+	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
+	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
 	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
 	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
 	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 000d419..31e2d5b 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@
 ENTRY(xen_do_upcall)
 1:	mov %esp, %eax
 	call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  ret_from_intr
 	CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index db13655..2babb39 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -269,11 +269,14 @@
 	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
 	jz   1f
 
-	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
-	jnz  int_ret_from_sys_call
-
-	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
-	jmp ret_from_sys_call			# go to the SYSRET fastpath
+	/*
+	 * By the time we get here, we have no idea whether our pt_regs,
+	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+	 * the slow path, or one of the ia32entry paths.
+	 * Use int_ret_from_sys_call to return, since it can safely handle
+	 * all of the above.
+	 */
+	jmp  int_ret_from_sys_call
 
 1:
 	subq $REST_SKIP, %rsp	# leave space for volatiles
@@ -361,12 +364,21 @@
  * Has incomplete stack frame and undefined top of stack.
  */
 ret_from_sys_call:
-	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
-	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
-
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+
+	/*
+	 * We must check ti flags with interrupts (or at least preemption)
+	 * off because we must *never* return to userspace without
+	 * processing exit work that is enqueued if we're preempted here.
+	 * In particular, returning to userspace with any of the one-shot
+	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+	 * very bad.
+	 */
+	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
+
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -383,7 +395,7 @@
 
 int_ret_from_sys_call_fixup:
 	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
-	jmp int_ret_from_sys_call
+	jmp int_ret_from_sys_call_irqs_off
 
 	/* Do syscall tracing */
 tracesys:
@@ -429,6 +441,7 @@
 GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+int_ret_from_sys_call_irqs_off:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	mask to check */
 GLOBAL(int_with_check)
@@ -1208,6 +1221,9 @@
 	popq %rsp
 	CFI_DEF_CFA_REGISTER rsp
 	decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  error_exit
 	CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6a1146e..4e3d5a9 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -223,27 +223,48 @@
 __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+	unsigned long faddr;
 
 	kp = get_kprobe((void *)addr);
-	/* There is no probe, return original address */
-	if (!kp)
+	faddr = ftrace_location(addr);
+	/*
+	 * Addresses inside the ftrace location are refused by
+	 * arch_check_ftrace_location(). Something went terribly wrong
+	 * if such an address is checked here.
+	 */
+	if (WARN_ON(faddr && faddr != addr))
+		return 0UL;
+	/*
+	 * Use the current code if it is not modified by Kprobe
+	 * and it cannot be modified by ftrace.
+	 */
+	if (!kp && !faddr)
 		return addr;
 
 	/*
-	 *  Basically, kp->ainsn.insn has an original instruction.
-	 *  However, RIP-relative instruction can not do single-stepping
-	 *  at different place, __copy_instruction() tweaks the displacement of
-	 *  that instruction. In that case, we can't recover the instruction
-	 *  from the kp->ainsn.insn.
+	 * Basically, kp->ainsn.insn has an original instruction.
+	 * However, RIP-relative instruction can not do single-stepping
+	 * at different place, __copy_instruction() tweaks the displacement of
+	 * that instruction. In that case, we can't recover the instruction
+	 * from the kp->ainsn.insn.
 	 *
-	 *  On the other hand, kp->opcode has a copy of the first byte of
-	 *  the probed instruction, which is overwritten by int3. And
-	 *  the instruction at kp->addr is not modified by kprobes except
-	 *  for the first byte, we can recover the original instruction
-	 *  from it and kp->opcode.
+	 * On the other hand, in case on normal Kprobe, kp->opcode has a copy
+	 * of the first byte of the probed instruction, which is overwritten
+	 * by int3. And the instruction at kp->addr is not modified by kprobes
+	 * except for the first byte, we can recover the original instruction
+	 * from it and kp->opcode.
+	 *
+	 * In case of Kprobes using ftrace, we do not have a copy of
+	 * the original instruction. In fact, the ftrace location might
+	 * be modified at anytime and even could be in an inconsistent state.
+	 * Fortunately, we know that the original code is the ideal 5-byte
+	 * long NOP.
 	 */
-	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-	buf[0] = kp->opcode;
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (faddr)
+		memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+	else
+		buf[0] = kp->opcode;
 	return (unsigned long)buf;
 }
 
@@ -251,6 +272,7 @@
  * Recover the probed instruction at addr for further analysis.
  * Caller must lock kprobes by kprobe_mutex, or disable preemption
  * for preventing to release referencing kprobes.
+ * Returns zero if the instruction can not get recovered.
  */
 unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 {
@@ -285,6 +307,8 @@
 		 * normally used, we just go through if there is no kprobe.
 		 */
 		__addr = recover_probed_instruction(buf, addr);
+		if (!__addr)
+			return 0;
 		kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 
@@ -333,6 +357,8 @@
 	unsigned long recovered_insn =
 		recover_probed_instruction(buf, (unsigned long)src);
 
+	if (!recovered_insn)
+		return 0;
 	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 	insn_get_length(&insn);
 	/* Another subsystem puts a breakpoint, failed to recover */
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 0dd8d08..7b3b9d1 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -259,6 +259,8 @@
 			 */
 			return 0;
 		recovered_insn = recover_probed_instruction(buf, addr);
+		if (!recovered_insn)
+			return 0;
 		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 		/* Another subsystem puts a breakpoint */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 9bbb9b3..d1ac80b 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -47,13 +47,21 @@
 
 #ifdef CONFIG_RANDOMIZE_BASE
 static unsigned long module_load_offset;
+static int randomize_modules = 1;
 
 /* Mutex protects the module_load_offset. */
 static DEFINE_MUTEX(module_kaslr_mutex);
 
+static int __init parse_nokaslr(char *p)
+{
+	randomize_modules = 0;
+	return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
 static unsigned long int get_module_load_offset(void)
 {
-	if (kaslr_enabled) {
+	if (randomize_modules) {
 		mutex_lock(&module_kaslr_mutex);
 		/*
 		 * Calculate the module_load_offset the first time this
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 98dc931..0a2421c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -122,8 +122,6 @@
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
-bool __read_mostly kaslr_enabled = false;
-
 #ifdef CONFIG_DMI
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
@@ -427,11 +425,6 @@
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
-{
-	kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
-}
-
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
@@ -457,9 +450,6 @@
 		case SETUP_EFI:
 			parse_efi_setup(pa_data, data_len);
 			break;
-		case SETUP_KASLR:
-			parse_kaslr_setup(pa_data, data_len);
-			break;
 		default:
 			break;
 		}
@@ -842,14 +832,10 @@
 static int
 dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 {
-	if (kaslr_enabled)
-		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
-			 __START_KERNEL,
-			 __START_KERNEL_map,
-			 MODULES_VADDR-1);
-	else
-		pr_emerg("Kernel Offset: disabled\n");
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
+		 "(relocation range: 0x%lx-0x%lx)\n",
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9d2073e..4ff5d16 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -384,7 +384,7 @@
 		goto exit;
 	conditional_sti(regs);
 
-	if (!user_mode(regs))
+	if (!user_mode_vm(regs))
 		die("bounds", regs, error_code);
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
@@ -637,7 +637,7 @@
 	 * then it's very likely the result of an icebp/int01 trap.
 	 * User wants a sigtrap for that.
 	 */
-	if (!dr6 && user_mode(regs))
+	if (!dr6 && user_mode_vm(regs))
 		user_icebp = 1;
 
 	/* Catch kmemcheck conditions first of all! */
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 34f66e5..cdc6cf9 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -379,7 +379,7 @@
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Sanitize the copied state etc.
 		 */
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
@@ -393,14 +393,15 @@
 		 */
 		drop_fpu(tsk);
 
-		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
 		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpu_finit(fpu);
 			err = -1;
 		} else {
 			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-			set_used_math();
 		}
 
+		set_used_math();
 		if (use_eager_fpu()) {
 			preempt_disable();
 			math_state_restore();
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e0b794a..106c015 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4950,7 +4950,8 @@
 			goto done;
 		}
 	}
-	ctxt->dst.orig_val = ctxt->dst.val;
+	/* Copy full 64-bit value for CMPXCHG8B.  */
+	ctxt->dst.orig_val64 = ctxt->dst.val64;
 
 special_insn:
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index cc31f7c..9541ba3 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -507,6 +507,7 @@
 		return -EOPNOTSUPP;
 
 	if (len != 1) {
+		memset(val, 0, len);
 		pr_pic_unimpl("non byte read\n");
 		return 0;
 	}
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index b1947e0..46d4449 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -422,6 +422,7 @@
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
 	int i;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
 		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -443,7 +444,8 @@
 		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
 		spin_lock(&ioapic->lock);
 
-		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+		if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+		    kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
 			continue;
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e55b5fc3..4ee827d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -833,8 +833,7 @@
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+	if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
 		int trigger_mode;
 		if (apic_test_vector(vector, apic->regs + APIC_TMR))
 			trigger_mode = IOAPIC_LEVEL_TRIG;
@@ -1572,7 +1571,7 @@
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
 	apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
-	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0;
 	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
@@ -1782,7 +1781,7 @@
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
-	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+	apic->isr_count = kvm_x86_ops->hwapic_isr_update ?
 				1 : count_vectors(apic->regs + APIC_ISR);
 	apic->highest_isr_cache = -1;
 	if (kvm_x86_ops->hwapic_irr_update)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d319e0c..cc618c8 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3649,11 +3649,6 @@
 	return;
 }
 
-static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
-{
-	return;
-}
-
 static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	return;
@@ -4403,7 +4398,6 @@
 	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
 	.vm_has_apicv = svm_vm_has_apicv,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
-	.hwapic_isr_update = svm_hwapic_isr_update,
 	.sync_pir_to_irr = svm_sync_pir_to_irr,
 
 	.set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14c1a18..ae4f6d3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2168,7 +2168,10 @@
 {
 	unsigned long *msr_bitmap;
 
-	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+	if (is_guest_mode(vcpu))
+		msr_bitmap = vmx_msr_bitmap_nested;
+	else if (irqchip_in_kernel(vcpu->kvm) &&
+		apic_x2apic_mode(vcpu->arch.apic)) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -2476,8 +2479,7 @@
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		vmx->nested.nested_vmx_secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_EPT |
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+			SECONDARY_EXEC_ENABLE_EPT;
 		vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
 			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
 			 VMX_EPT_INVEPT_BIT;
@@ -2491,6 +2493,10 @@
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	if (enable_unrestricted_guest)
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC,
 		vmx->nested.nested_vmx_misc_low,
@@ -4367,6 +4373,18 @@
 	return 0;
 }
 
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_SMP
+	if (vcpu->mode == IN_GUEST_MODE) {
+		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
+				POSTED_INTR_VECTOR);
+		return true;
+	}
+#endif
+	return false;
+}
+
 static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 						int vector)
 {
@@ -4375,9 +4393,7 @@
 	if (is_guest_mode(vcpu) &&
 	    vector == vmx->nested.posted_intr_nv) {
 		/* the PIR and ON have been set by L1. */
-		if (vcpu->mode == IN_GUEST_MODE)
-			apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-				POSTED_INTR_VECTOR);
+		kvm_vcpu_trigger_posted_interrupt(vcpu);
 		/*
 		 * If a posted intr is not recognized by hardware,
 		 * we will accomplish it in the next vmentry.
@@ -4409,12 +4425,7 @@
 
 	r = pi_test_and_set_on(&vmx->pi_desc);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
-#ifdef CONFIG_SMP
-	if (!r && (vcpu->mode == IN_GUEST_MODE))
-		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-				POSTED_INTR_VECTOR);
-	else
-#endif
+	if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu))
 		kvm_vcpu_kick(vcpu);
 }
 
@@ -9213,9 +9224,9 @@
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
-	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) {
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested));
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
+		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
+		/* MSR_BITMAP will be set by following vmx_set_efer. */
 	} else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd7a70b..32bf19e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2744,7 +2744,6 @@
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig
index 4a0890f8..08f41ca 100644
--- a/arch/x86/lguest/Kconfig
+++ b/arch/x86/lguest/Kconfig
@@ -1,6 +1,6 @@
 config LGUEST_GUEST
 	bool "Lguest guest support"
-	depends on X86_32 && PARAVIRT
+	depends on X86_32 && PARAVIRT && PCI
 	select TTY
 	select VIRTUALIZATION
 	select VIRTIO
@@ -8,7 +8,7 @@
 	help
 	  Lguest is a tiny in-kernel hypervisor.  Selecting this will
 	  allow your kernel to boot under lguest.  This option will increase
-	  your kernel size by about 6k.  If in doubt, say N.
+	  your kernel size by about 10k.  If in doubt, say N.
 
 	  If you say Y here, make sure you say Y (or M) to the virtio block
 	  and net drivers which lguest needs.
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 6ac2738..e469598 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -331,7 +331,7 @@
 				struct list_head *list)
 {
 	int ret;
-	struct resource_entry *entry;
+	struct resource_entry *entry, *tmp;
 
 	sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum);
 	info->bridge = device;
@@ -345,8 +345,13 @@
 		dev_dbg(&device->dev,
 			"no IO and memory resources present in _CRS\n");
 	else
-		resource_list_for_each_entry(entry, list)
-			entry->res->name = info->name;
+		resource_list_for_each_entry_safe(entry, tmp, list) {
+			if ((entry->res->flags & IORESOURCE_WINDOW) == 0 ||
+			    (entry->res->flags & IORESOURCE_DISABLED))
+				resource_list_destroy_entry(entry);
+			else
+				entry->res->name = info->name;
+		}
 }
 
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 3d2612b..2fb3847 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -513,31 +513,6 @@
 	}
 }
 
-/*
- * Some device drivers assume dev->irq won't change after calling
- * pci_disable_device(). So delay releasing of IRQ resource to driver
- * unbinding time. Otherwise it will break PM subsystem and drivers
- * like xen-pciback etc.
- */
-static int pci_irq_notifier(struct notifier_block *nb, unsigned long action,
-			    void *data)
-{
-	struct pci_dev *dev = to_pci_dev(data);
-
-	if (action != BUS_NOTIFY_UNBOUND_DRIVER)
-		return NOTIFY_DONE;
-
-	if (pcibios_disable_irq)
-		pcibios_disable_irq(dev);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block pci_irq_nb = {
-	.notifier_call = pci_irq_notifier,
-	.priority = INT_MIN,
-};
-
 int __init pcibios_init(void)
 {
 	if (!raw_pci_ops) {
@@ -550,9 +525,6 @@
 
 	if (pci_bf_sort >= pci_force_bf)
 		pci_sort_breadthfirst();
-
-	bus_register_notifier(&pci_bus_type, &pci_irq_nb);
-
 	return 0;
 }
 
@@ -711,6 +683,12 @@
 	return 0;
 }
 
+void pcibios_disable_device (struct pci_dev *dev)
+{
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+		pcibios_disable_irq(dev);
+}
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index efb8493..852aa4c 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -234,10 +234,10 @@
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (dev->irq_managed && dev->irq > 0) {
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
-		dev->irq = 0;
 	}
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index e71b3db..5dc6ca5 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1256,9 +1256,22 @@
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) {
+	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
 		dev->irq = 0;
 		dev->irq_managed = 0;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 1bbedc4..3005f0c 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -130,7 +130,7 @@
 		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
 	else {
 		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-		pr_info("ARCH: Uknown SoC, assuming PENWELL!\n");
+		pr_info("ARCH: Unknown SoC, assuming PENWELL!\n");
 	}
 
 out:
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S
index 31776d0..d7ec4e2 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/vdso/vdso32/sigreturn.S
@@ -17,6 +17,7 @@
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
 	ALIGN
 __kernel_sigreturn:
 .LSTART_sigreturn:
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bd8b845..5240f56 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1070,6 +1070,23 @@
 	BUG_ON(val);
 }
 #endif
+
+static u64 xen_read_msr_safe(unsigned int msr, int *err)
+{
+	u64 val;
+
+	val = native_read_msr_safe(msr, err);
+	switch (msr) {
+	case MSR_IA32_APICBASE:
+#ifdef CONFIG_X86_X2APIC
+		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
+#endif
+			val &= ~X2APIC_ENABLE;
+		break;
+	}
+	return val;
+}
+
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
@@ -1240,7 +1257,7 @@
 
 	.wbinvd = native_wbinvd,
 
-	.read_msr = native_read_msr_safe,
+	.read_msr = xen_read_msr_safe,
 	.write_msr = xen_write_msr_safe,
 
 	.read_tsc = native_read_tsc,
@@ -1741,6 +1758,7 @@
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
 #else
+	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
 	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
 #endif
 }
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 740ae30..9f93af5 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -563,7 +563,7 @@
 		if (p2m_pfn == PFN_DOWN(__pa(p2m_missing)))
 			p2m_init(p2m);
 		else
-			p2m_init_identity(p2m, pfn);
+			p2m_init_identity(p2m, pfn & ~(P2M_PER_PAGE - 1));
 
 		spin_lock_irqsave(&p2m_update_lock, flags);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index fc1ff3b..fd3fee8 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -592,7 +592,7 @@
 	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
 		struct bio_vec *bprev;
 
-		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
 		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
 			return false;
 	}
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d53a764..be3290c 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -278,9 +278,11 @@
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
-		 * some to complete.
+		 * some to complete. Note that hctx can be NULL here for
+		 * reserved tag allocation.
 		 */
-		blk_mq_run_hw_queue(hctx, false);
+		if (hctx)
+			blk_mq_run_hw_queue(hctx, false);
 
 		/*
 		 * Retry tag allocation after running the hardware queue,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4f4bea2..b7b8933 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1938,7 +1938,7 @@
 	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
 			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_map;
+		goto err_mq_usage;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
 	blk_queue_rq_timeout(q, 30000);
@@ -1981,7 +1981,7 @@
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_hw;
+		goto err_mq_usage;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1993,7 +1993,7 @@
 
 	return q;
 
-err_hw:
+err_mq_usage:
 	blk_cleanup_queue(q);
 err_hctxs:
 	kfree(map);
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 657964e..37fb190 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -65,6 +65,7 @@
 
 struct lpss_device_desc {
 	unsigned int flags;
+	const char *clk_con_id;
 	unsigned int prv_offset;
 	size_t prv_size_override;
 	void (*setup)(struct lpss_private_data *pdata);
@@ -140,6 +141,7 @@
 
 static struct lpss_device_desc lpt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
+	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
@@ -156,6 +158,7 @@
 
 static struct lpss_device_desc byt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
@@ -313,7 +316,7 @@
 		return PTR_ERR(clk);
 
 	pdata->clk = clk;
-	clk_register_clkdev(clk, NULL, devname);
+	clk_register_clkdev(clk, dev_desc->clk_con_id, devname);
 	return 0;
 }
 
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index e7f718d..b1def41 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -485,6 +485,14 @@
 	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
+	/* Keep IOAPIC pin configuration when suspending */
+	if (dev->dev.power.is_prepared)
+		return;
+#ifdef	CONFIG_PM
+	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
+		return;
+#endif
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry)
 		return;
@@ -505,6 +513,5 @@
 	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
 		dev->irq_managed = 0;
-		dev->irq = 0;
 	}
 }
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index c723668..5589a6e 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -42,8 +42,10 @@
 	 * CHECKME: len might be required to check versus a minimum
 	 * length as well. 1 for io is fine, but for memory it does
 	 * not make any sense at all.
+	 * Note: some BIOSes report incorrect length for ACPI address space
+	 * descriptor, so remove check of 'reslen == len' to avoid regression.
 	 */
-	if (len && reslen && reslen == len && start <= end)
+	if (len && reslen && start <= end)
 		return true;
 
 	pr_debug("ACPI: invalid or unassigned resource %s [%016llx - %016llx] length [%016llx]\n",
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index debd309..26eb70c 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -2110,7 +2110,8 @@
 
 int acpi_video_register(void)
 {
-	int result = 0;
+	int ret;
+
 	if (register_count) {
 		/*
 		 * if the function of acpi_video_register is already called,
@@ -2122,9 +2123,9 @@
 	mutex_init(&video_list_lock);
 	INIT_LIST_HEAD(&video_bus_head);
 
-	result = acpi_bus_register_driver(&acpi_video_bus);
-	if (result < 0)
-		return -ENODEV;
+	ret = acpi_bus_register_driver(&acpi_video_bus);
+	if (ret)
+		return ret;
 
 	/*
 	 * When the acpi_video_bus is loaded successfully, increase
@@ -2176,6 +2177,17 @@
 
 static int __init acpi_video_init(void)
 {
+	/*
+	 * Let the module load even if ACPI is disabled (e.g. due to
+	 * a broken BIOS) so that i915.ko can still be loaded on such
+	 * old systems without an AcpiOpRegion.
+	 *
+	 * acpi_video_register() will report -ENODEV later as well due
+	 * to acpi_disabled when i915.ko tries to register itself afterwards.
+	 */
+	if (acpi_disabled)
+		return 0;
+
 	dmi_check_system(video_dmi_table);
 
 	if (intel_opregion_present())
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 33b09b6..6607f3c 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -551,7 +551,6 @@
 {
 	void *page_addr;
 	unsigned long user_page_addr;
-	struct vm_struct tmp_area;
 	struct page **page;
 	struct mm_struct *mm;
 
@@ -600,10 +599,11 @@
 				proc->pid, page_addr);
 			goto err_alloc_page_failed;
 		}
-		tmp_area.addr = page_addr;
-		tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */;
-		ret = map_vm_area(&tmp_area, PAGE_KERNEL, page);
-		if (ret) {
+		ret = map_kernel_range_noflush((unsigned long)page_addr,
+					PAGE_SIZE, PAGE_KERNEL, page);
+		flush_cache_vmap((unsigned long)page_addr,
+				(unsigned long)page_addr + PAGE_SIZE);
+		if (ret != 1) {
 			pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n",
 			       proc->pid, page_addr);
 			goto err_map_kernel_failed;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4c35f08..ef150eb 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4737,7 +4737,7 @@
 		return NULL;
 
 	/* libsas case */
-	if (!ap->scsi_host) {
+	if (ap->flags & ATA_FLAG_SAS_HOST) {
 		tag = ata_sas_allocate_tag(ap);
 		if (tag < 0)
 			return NULL;
@@ -4776,7 +4776,7 @@
 	tag = qc->tag;
 	if (likely(ata_tag_valid(tag))) {
 		qc->tag = ATA_TAG_POISON;
-		if (!ap->scsi_host)
+		if (ap->flags & ATA_FLAG_SAS_HOST)
 			ata_sas_free_tag(tag, ap);
 	}
 }
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index f9054cd..5389579 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -869,6 +869,8 @@
 	 */
 	ata_msleep(ap, 1);
 
+	sata_set_spd(link);
+
 	/*
 	 * Now, bring the host controller online again, this can take time
 	 * as PHY reset and communication establishment, 1st D2H FIS and
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index ba4abbe..45937f8 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2242,7 +2242,7 @@
 }
 
 static int pm_genpd_summary_one(struct seq_file *s,
-		struct generic_pm_domain *gpd)
+				struct generic_pm_domain *genpd)
 {
 	static const char * const status_lookup[] = {
 		[GPD_STATE_ACTIVE] = "on",
@@ -2256,26 +2256,26 @@
 	struct gpd_link *link;
 	int ret;
 
-	ret = mutex_lock_interruptible(&gpd->lock);
+	ret = mutex_lock_interruptible(&genpd->lock);
 	if (ret)
 		return -ERESTARTSYS;
 
-	if (WARN_ON(gpd->status >= ARRAY_SIZE(status_lookup)))
+	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
-	seq_printf(s, "%-30s  %-15s  ", gpd->name, status_lookup[gpd->status]);
+	seq_printf(s, "%-30s  %-15s  ", genpd->name, status_lookup[genpd->status]);
 
 	/*
 	 * Modifications on the list require holding locks on both
 	 * master and slave, so we are safe.
-	 * Also gpd->name is immutable.
+	 * Also genpd->name is immutable.
 	 */
-	list_for_each_entry(link, &gpd->master_links, master_node) {
+	list_for_each_entry(link, &genpd->master_links, master_node) {
 		seq_printf(s, "%s", link->slave->name);
-		if (!list_is_last(&link->master_node, &gpd->master_links))
+		if (!list_is_last(&link->master_node, &genpd->master_links))
 			seq_puts(s, ", ");
 	}
 
-	list_for_each_entry(pm_data, &gpd->dev_list, list_node) {
+	list_for_each_entry(pm_data, &genpd->dev_list, list_node) {
 		kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL);
 		if (kobj_path == NULL)
 			continue;
@@ -2287,14 +2287,14 @@
 
 	seq_puts(s, "\n");
 exit:
-	mutex_unlock(&gpd->lock);
+	mutex_unlock(&genpd->lock);
 
 	return 0;
 }
 
 static int pm_genpd_summary_show(struct seq_file *s, void *data)
 {
-	struct generic_pm_domain *gpd;
+	struct generic_pm_domain *genpd;
 	int ret = 0;
 
 	seq_puts(s, "    domain                      status         slaves\n");
@@ -2305,8 +2305,8 @@
 	if (ret)
 		return -ERESTARTSYS;
 
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
-		ret = pm_genpd_summary_one(s, gpd);
+	list_for_each_entry(genpd, &gpd_list, gpd_list_node) {
+		ret = pm_genpd_summary_one(s, genpd);
 		if (ret)
 			break;
 	}
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index c2744b3..aab7158 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -730,6 +730,7 @@
 	pm_abort_suspend = true;
 	freeze_wake();
 }
+EXPORT_SYMBOL_GPL(pm_system_wakeup);
 
 void pm_wakeup_clear(void)
 {
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index beb8b27..a13587b 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -243,4 +243,12 @@
 extern struct regcache_ops regcache_lzo_ops;
 extern struct regcache_ops regcache_flat_ops;
 
+static inline const char *regmap_name(const struct regmap *map)
+{
+	if (map->dev)
+		return dev_name(map->dev);
+
+	return map->name;
+}
+
 #endif
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index d453a2c..81751a4 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -307,7 +307,7 @@
 	if (pos == 0) {
 		memmove(blk + offset * map->cache_word_size,
 			blk, rbnode->blklen * map->cache_word_size);
-		bitmap_shift_right(present, present, offset, blklen);
+		bitmap_shift_left(present, present, offset, blklen);
 	}
 
 	/* update the rbnode block, its size and the base register */
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index f373c35..87db989 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -218,7 +218,7 @@
 		ret = map->cache_ops->read(map, reg, value);
 
 		if (ret == 0)
-			trace_regmap_reg_read_cache(map->dev, reg, *value);
+			trace_regmap_reg_read_cache(map, reg, *value);
 
 		return ret;
 	}
@@ -311,7 +311,7 @@
 	dev_dbg(map->dev, "Syncing %s cache\n",
 		map->cache_ops->name);
 	name = map->cache_ops->name;
-	trace_regcache_sync(map->dev, name, "start");
+	trace_regcache_sync(map, name, "start");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -346,7 +346,7 @@
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop");
+	trace_regcache_sync(map, name, "stop");
 
 	return ret;
 }
@@ -381,7 +381,7 @@
 	name = map->cache_ops->name;
 	dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max);
 
-	trace_regcache_sync(map->dev, name, "start region");
+	trace_regcache_sync(map, name, "start region");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -401,7 +401,7 @@
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop region");
+	trace_regcache_sync(map, name, "stop region");
 
 	return ret;
 }
@@ -428,7 +428,7 @@
 
 	map->lock(map->lock_arg);
 
-	trace_regcache_drop_region(map->dev, min, max);
+	trace_regcache_drop_region(map, min, max);
 
 	ret = map->cache_ops->drop(map, min, max);
 
@@ -455,7 +455,7 @@
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_bypass && enable);
 	map->cache_only = enable;
-	trace_regmap_cache_only(map->dev, enable);
+	trace_regmap_cache_only(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_only);
@@ -493,7 +493,7 @@
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_only && enable);
 	map->cache_bypass = enable;
-	trace_regmap_cache_bypass(map->dev, enable);
+	trace_regmap_cache_bypass(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_bypass);
@@ -608,7 +608,8 @@
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(cache_present, i))
+		if (!regcache_reg_present(cache_present, i) ||
+		    !regmap_writeable(map, regtmp))
 			continue;
 
 		val = regcache_get_val(map, block, i);
@@ -677,7 +678,8 @@
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(cache_present, i)) {
+		if (!regcache_reg_present(cache_present, i) ||
+		    !regmap_writeable(map, regtmp)) {
 			ret = regcache_sync_block_raw_flush(map, &data,
 							    base, regtmp);
 			if (ret != 0)
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 6299a50..a6c3f75 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -499,7 +499,8 @@
 		goto err_alloc;
 	}
 
-	ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags,
+	ret = request_threaded_irq(irq, NULL, regmap_irq_thread,
+				   irq_flags | IRQF_ONESHOT,
 				   chip->name, d);
 	if (ret != 0) {
 		dev_err(map->dev, "Failed to request IRQ %d for %s: %d\n",
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index f99b098..dbfe6a6 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1281,7 +1281,7 @@
 	if (map->async && map->bus->async_write) {
 		struct regmap_async *async;
 
-		trace_regmap_async_write_start(map->dev, reg, val_len);
+		trace_regmap_async_write_start(map, reg, val_len);
 
 		spin_lock_irqsave(&map->async_lock, flags);
 		async = list_first_entry_or_null(&map->async_free,
@@ -1339,8 +1339,7 @@
 		return ret;
 	}
 
-	trace_regmap_hw_write_start(map->dev, reg,
-				    val_len / map->format.val_bytes);
+	trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes);
 
 	/* If we're doing a single register write we can probably just
 	 * send the work_buf directly, otherwise try to do a gather
@@ -1372,8 +1371,7 @@
 		kfree(buf);
 	}
 
-	trace_regmap_hw_write_done(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -1407,12 +1405,12 @@
 
 	map->format.format_write(map, reg, val);
 
-	trace_regmap_hw_write_start(map->dev, reg, 1);
+	trace_regmap_hw_write_start(map, reg, 1);
 
 	ret = map->bus->write(map->bus_context, map->work_buf,
 			      map->format.buf_size);
 
-	trace_regmap_hw_write_done(map->dev, reg, 1);
+	trace_regmap_hw_write_done(map, reg, 1);
 
 	return ret;
 }
@@ -1470,7 +1468,7 @@
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
-	trace_regmap_reg_write(map->dev, reg, val);
+	trace_regmap_reg_write(map, reg, val);
 
 	return map->reg_write(context, reg, val);
 }
@@ -1773,7 +1771,7 @@
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
 		int val = regs[i].def;
-		trace_regmap_hw_write_start(map->dev, reg, 1);
+		trace_regmap_hw_write_start(map, reg, 1);
 		map->format.format_reg(u8, reg, map->reg_shift);
 		u8 += reg_bytes + pad_bytes;
 		map->format.format_val(u8, val, 0);
@@ -1788,7 +1786,7 @@
 
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
-		trace_regmap_hw_write_done(map->dev, reg, 1);
+		trace_regmap_hw_write_done(map, reg, 1);
 	}
 	return ret;
 }
@@ -2059,15 +2057,13 @@
 	 */
 	u8[0] |= map->read_flag_mask;
 
-	trace_regmap_hw_read_start(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes);
 
 	ret = map->bus->read(map->bus_context, map->work_buf,
 			     map->format.reg_bytes + map->format.pad_bytes,
 			     val, val_len);
 
-	trace_regmap_hw_read_done(map->dev, reg,
-				  val_len / map->format.val_bytes);
+	trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -2123,7 +2119,7 @@
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
-		trace_regmap_reg_read(map->dev, reg, *val);
+		trace_regmap_reg_read(map, reg, *val);
 
 		if (!map->cache_bypass)
 			regcache_write(map, reg, *val);
@@ -2480,7 +2476,7 @@
 	struct regmap *map = async->map;
 	bool wake;
 
-	trace_regmap_async_io_complete(map->dev);
+	trace_regmap_async_io_complete(map);
 
 	spin_lock(&map->async_lock);
 	list_move(&async->list, &map->async_free);
@@ -2525,7 +2521,7 @@
 	if (!map->bus || !map->bus->async_write)
 		return 0;
 
-	trace_regmap_async_complete_start(map->dev);
+	trace_regmap_async_complete_start(map);
 
 	wait_event(map->async_waitq, regmap_async_is_done(map));
 
@@ -2534,7 +2530,7 @@
 	map->async_ret = 0;
 	spin_unlock_irqrestore(&map->async_lock, flags);
 
-	trace_regmap_async_complete_done(map->dev);
+	trace_regmap_async_complete_done(map);
 
 	return ret;
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4bc2a5c..a98c41f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -803,10 +803,6 @@
 		return -EINVAL;
 	}
 
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-	if (!nbd_dev)
-		return -ENOMEM;
-
 	part_shift = 0;
 	if (max_part > 0) {
 		part_shift = fls(max_part);
@@ -828,6 +824,10 @@
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
+	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+	if (!nbd_dev)
+		return -ENOMEM;
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index b64bccb..e23be20 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -482,6 +482,7 @@
 	}
 }
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
 static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
 {
 	if (be32_to_cpu(pi->ref_tag) == v)
@@ -538,6 +539,58 @@
 	kunmap_atomic(pmap);
 }
 
+static int nvme_noop_verify(struct blk_integrity_iter *iter)
+{
+	return 0;
+}
+
+static int nvme_noop_generate(struct blk_integrity_iter *iter)
+{
+	return 0;
+}
+
+struct blk_integrity nvme_meta_noop = {
+	.name			= "NVME_META_NOOP",
+	.generate_fn		= nvme_noop_generate,
+	.verify_fn		= nvme_noop_verify,
+};
+
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+	struct blk_integrity integrity;
+
+	switch (ns->pi_type) {
+	case NVME_NS_DPS_PI_TYPE3:
+		integrity = t10_pi_type3_crc;
+		break;
+	case NVME_NS_DPS_PI_TYPE1:
+	case NVME_NS_DPS_PI_TYPE2:
+		integrity = t10_pi_type1_crc;
+		break;
+	default:
+		integrity = nvme_meta_noop;
+		break;
+	}
+	integrity.tuple_size = ns->ms;
+	blk_integrity_register(ns->disk, &integrity);
+	blk_queue_max_integrity_segments(ns->queue, 1);
+}
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static void nvme_dif_remap(struct request *req,
+			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
+{
+}
+static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+}
+static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+}
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+}
+#endif
+
 static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
@@ -1959,43 +2012,6 @@
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
-static int nvme_noop_verify(struct blk_integrity_iter *iter)
-{
-	return 0;
-}
-
-static int nvme_noop_generate(struct blk_integrity_iter *iter)
-{
-	return 0;
-}
-
-struct blk_integrity nvme_meta_noop = {
-	.name			= "NVME_META_NOOP",
-	.generate_fn		= nvme_noop_generate,
-	.verify_fn		= nvme_noop_verify,
-};
-
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
-	struct blk_integrity integrity;
-
-	switch (ns->pi_type) {
-	case NVME_NS_DPS_PI_TYPE3:
-		integrity = t10_pi_type3_crc;
-		break;
-	case NVME_NS_DPS_PI_TYPE1:
-	case NVME_NS_DPS_PI_TYPE2:
-		integrity = t10_pi_type1_crc;
-		break;
-	default:
-		integrity = nvme_meta_noop;
-		break;
-	}
-	integrity.tuple_size = ns->ms;
-	blk_integrity_register(ns->disk, &integrity);
-	blk_queue_max_integrity_segments(ns->queue, 1);
-}
-
 static int nvme_revalidate_disk(struct gendisk *disk)
 {
 	struct nvme_ns *ns = disk->private_data;
@@ -2036,7 +2052,8 @@
 	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
 					id->dps & NVME_NS_DPS_PI_MASK : 0;
 
-	if (disk->integrity && (ns->pi_type != pi_type || ns->ms != old_ms ||
+	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
+				ns->ms != old_ms ||
 				bs != queue_logical_block_size(disk->queue) ||
 				(ns->ms && id->flbas & NVME_NS_FLBAS_META_EXT)))
 		blk_integrity_unregister(disk);
@@ -2044,11 +2061,11 @@
 	ns->pi_type = pi_type;
 	blk_queue_logical_block_size(ns->queue, bs);
 
-	if (ns->ms && !disk->integrity && (disk->flags & GENHD_FL_UP) &&
+	if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) &&
 				!(id->flbas & NVME_NS_FLBAS_META_EXT))
 		nvme_init_integrity(ns);
 
-	if (id->ncap == 0 || (ns->ms && !disk->integrity))
+	if (id->ncap == 0 || (ns->ms && !blk_get_integrity(disk)))
 		set_capacity(disk, 0);
 	else
 		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
@@ -2652,7 +2669,7 @@
 
 	list_for_each_entry(ns, &dev->namespaces, list) {
 		if (ns->disk->flags & GENHD_FL_UP) {
-			if (ns->disk->integrity)
+			if (blk_get_integrity(ns->disk))
 				blk_integrity_unregister(ns->disk);
 			del_gendisk(ns->disk);
 		}
@@ -2986,6 +3003,7 @@
 	}
 	get_device(dev->device);
 
+	INIT_LIST_HEAD(&dev->node);
 	INIT_WORK(&dev->probe_work, nvme_async_probe);
 	schedule_work(&dev->probe_work);
 	return 0;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 8e233ed..871bd35 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -528,7 +528,7 @@
 static inline void update_used_max(struct zram *zram,
 					const unsigned long pages)
 {
-	int old_max, cur_max;
+	unsigned long old_max, cur_max;
 
 	old_max = atomic_long_read(&zram->stats.max_used_pages);
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b876888..8bfc4c2 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -272,6 +272,7 @@
 	{ USB_DEVICE(0x1286, 0x2046), .driver_info = BTUSB_MARVELL },
 
 	/* Intel Bluetooth devices */
+	{ USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR },
 	{ USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL },
 	{ USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL },
 	{ USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_NEW },
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 1d278cc..e096e9c 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -140,16 +140,6 @@
 {
 	int rc;
 
-	rc = device_add(&chip->dev);
-	if (rc) {
-		dev_err(&chip->dev,
-			"unable to device_register() %s, major %d, minor %d, err=%d\n",
-			chip->devname, MAJOR(chip->dev.devt),
-			MINOR(chip->dev.devt), rc);
-
-		return rc;
-	}
-
 	rc = cdev_add(&chip->cdev, chip->dev.devt, 1);
 	if (rc) {
 		dev_err(&chip->dev,
@@ -161,6 +151,16 @@
 		return rc;
 	}
 
+	rc = device_add(&chip->dev);
+	if (rc) {
+		dev_err(&chip->dev,
+			"unable to device_register() %s, major %d, minor %d, err=%d\n",
+			chip->devname, MAJOR(chip->dev.devt),
+			MINOR(chip->dev.devt), rc);
+
+		return rc;
+	}
+
 	return rc;
 }
 
@@ -174,27 +174,17 @@
  * tpm_chip_register() - create a character device for the TPM chip
  * @chip: TPM chip to use.
  *
- * Creates a character device for the TPM chip and adds sysfs interfaces for
- * the device, PPI and TCPA. As the last step this function adds the
- * chip to the list of TPM chips available for use.
+ * Creates a character device for the TPM chip and adds sysfs attributes for
+ * the device. As the last step this function adds the chip to the list of TPM
+ * chips available for in-kernel use.
  *
- * NOTE: This function should be only called after the chip initialization
- * is complete.
- *
- * Called from tpm_<specific>.c probe function only for devices
- * the driver has determined it should claim.  Prior to calling
- * this function the specific probe function has called pci_enable_device
- * upon errant exit from this function specific probe function should call
- * pci_disable_device
+ * This function should be only called after the chip initialization is
+ * complete.
  */
 int tpm_chip_register(struct tpm_chip *chip)
 {
 	int rc;
 
-	rc = tpm_dev_add_device(chip);
-	if (rc)
-		return rc;
-
 	/* Populate sysfs for TPM1 devices. */
 	if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) {
 		rc = tpm_sysfs_add_device(chip);
@@ -208,6 +198,10 @@
 		chip->bios_dir = tpm_bios_log_setup(chip->devname);
 	}
 
+	rc = tpm_dev_add_device(chip);
+	if (rc)
+		return rc;
+
 	/* Make the chip available. */
 	spin_lock(&driver_lock);
 	list_add_rcu(&chip->list, &tpm_chip_list);
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index b1e53e3..42ffa5e7 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -124,7 +124,7 @@
 {
 	struct ibmvtpm_dev *ibmvtpm;
 	struct ibmvtpm_crq crq;
-	u64 *word = (u64 *) &crq;
+	__be64 *word = (__be64 *)&crq;
 	int rc;
 
 	ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip);
@@ -145,11 +145,11 @@
 	memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_TPM_COMMAND;
-	crq.len = (u16)count;
-	crq.data = ibmvtpm->rtce_dma_handle;
+	crq.len = cpu_to_be16(count);
+	crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(word[0]),
-			      cpu_to_be64(word[1]));
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
+			      be64_to_cpu(word[1]));
 	if (rc != H_SUCCESS) {
 		dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
 		rc = 0;
diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h
index f595f14..6af9289 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.h
+++ b/drivers/char/tpm/tpm_ibmvtpm.h
@@ -22,9 +22,9 @@
 struct ibmvtpm_crq {
 	u8 valid;
 	u8 msg;
-	u16 len;
-	u32 data;
-	u64 reserved;
+	__be16 len;
+	__be32 data;
+	__be64 reserved;
 } __attribute__((packed, aligned(8)));
 
 struct ibmvtpm_crq_queue {
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fae2dbb..72d7028 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -142,6 +142,7 @@
 	 * notification
 	 */
 	struct work_struct control_work;
+	struct work_struct config_work;
 
 	struct list_head ports;
 
@@ -1837,10 +1838,21 @@
 
 	portdev = vdev->priv;
 
+	if (!use_multiport(portdev))
+		schedule_work(&portdev->config_work);
+}
+
+static void config_work_handler(struct work_struct *work)
+{
+	struct ports_device *portdev;
+
+	portdev = container_of(work, struct ports_device, control_work);
 	if (!use_multiport(portdev)) {
+		struct virtio_device *vdev;
 		struct port *port;
 		u16 rows, cols;
 
+		vdev = portdev->vdev;
 		virtio_cread(vdev, struct virtio_console_config, cols, &cols);
 		virtio_cread(vdev, struct virtio_console_config, rows, &rows);
 
@@ -2040,12 +2052,14 @@
 
 	virtio_device_ready(portdev->vdev);
 
+	INIT_WORK(&portdev->config_work, &config_work_handler);
+	INIT_WORK(&portdev->control_work, &control_work_handler);
+
 	if (multiport) {
 		unsigned int nr_added_bufs;
 
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
-		INIT_WORK(&portdev->control_work, &control_work_handler);
 
 		nr_added_bufs = fill_queue(portdev->c_ivq,
 					   &portdev->c_ivq_lock);
@@ -2113,6 +2127,8 @@
 	/* Finish up work that's lined up */
 	if (use_multiport(portdev))
 		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);
@@ -2164,6 +2180,7 @@
 
 	virtqueue_disable_cb(portdev->c_ivq);
 	cancel_work_sync(&portdev->control_work);
+	cancel_work_sync(&portdev->config_work);
 	/*
 	 * Once more: if control_work_handler() was running, it would
 	 * enable the cb as the last step.
diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
index f07c815..3f27d21 100644
--- a/drivers/clk/at91/pmc.c
+++ b/drivers/clk/at91/pmc.c
@@ -89,12 +89,29 @@
 	return 0;
 }
 
+static void pmc_irq_suspend(struct irq_data *d)
+{
+	struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
+
+	pmc->imr = pmc_read(pmc, AT91_PMC_IMR);
+	pmc_write(pmc, AT91_PMC_IDR, pmc->imr);
+}
+
+static void pmc_irq_resume(struct irq_data *d)
+{
+	struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
+
+	pmc_write(pmc, AT91_PMC_IER, pmc->imr);
+}
+
 static struct irq_chip pmc_irq = {
 	.name = "PMC",
 	.irq_disable = pmc_irq_mask,
 	.irq_mask = pmc_irq_mask,
 	.irq_unmask = pmc_irq_unmask,
 	.irq_set_type = pmc_irq_set_type,
+	.irq_suspend = pmc_irq_suspend,
+	.irq_resume = pmc_irq_resume,
 };
 
 static struct lock_class_key pmc_lock_class;
@@ -224,7 +241,8 @@
 		goto out_free_pmc;
 
 	pmc_write(pmc, AT91_PMC_IDR, 0xffffffff);
-	if (request_irq(pmc->virq, pmc_irq_handler, IRQF_SHARED, "pmc", pmc))
+	if (request_irq(pmc->virq, pmc_irq_handler,
+			IRQF_SHARED | IRQF_COND_SUSPEND, "pmc", pmc))
 		goto out_remove_irqdomain;
 
 	return pmc;
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 52d2041..69abb08 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -33,6 +33,7 @@
 	spinlock_t lock;
 	const struct at91_pmc_caps *caps;
 	struct irq_domain *irqdomain;
+	u32 imr;
 };
 
 static inline void pmc_lock(struct at91_pmc *pmc)
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index db7f8bc..25006a8 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -144,12 +144,6 @@
 				   divider->flags);
 }
 
-/*
- * The reverse of DIV_ROUND_UP: The maximum number which
- * divided by m is r
- */
-#define MULT_ROUND_UP(r, m) ((r) * (m) + (m) - 1)
-
 static bool _is_valid_table_div(const struct clk_div_table *table,
 							 unsigned int div)
 {
@@ -225,19 +219,24 @@
 			      unsigned long parent_rate, unsigned long rate,
 			      unsigned long flags)
 {
-	int up, down, div;
+	int up, down;
+	unsigned long up_rate, down_rate;
 
-	up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate);
+	up = DIV_ROUND_UP(parent_rate, rate);
+	down = parent_rate / rate;
 
 	if (flags & CLK_DIVIDER_POWER_OF_TWO) {
-		up = __roundup_pow_of_two(div);
-		down = __rounddown_pow_of_two(div);
+		up = __roundup_pow_of_two(up);
+		down = __rounddown_pow_of_two(down);
 	} else if (table) {
-		up = _round_up_table(table, div);
-		down = _round_down_table(table, div);
+		up = _round_up_table(table, up);
+		down = _round_down_table(table, down);
 	}
 
-	return (up - div) <= (div - down) ? up : down;
+	up_rate = DIV_ROUND_UP(parent_rate, up);
+	down_rate = DIV_ROUND_UP(parent_rate, down);
+
+	return (rate - up_rate) <= (down_rate - rate) ? up : down;
 }
 
 static int _div_round(const struct clk_div_table *table,
@@ -313,7 +312,7 @@
 			return i;
 		}
 		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
-				MULT_ROUND_UP(rate, i));
+					       rate * i);
 		now = DIV_ROUND_UP(parent_rate, i);
 		if (_is_best_div(rate, now, best, flags)) {
 			bestdiv = i;
@@ -353,7 +352,7 @@
 		bestdiv = readl(divider->reg) >> divider->shift;
 		bestdiv &= div_mask(divider->width);
 		bestdiv = _get_div(divider->table, bestdiv, divider->flags);
-		return bestdiv;
+		return DIV_ROUND_UP(*prate, bestdiv);
 	}
 
 	return divider_round_rate(hw, rate, prate, divider->table,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index eb01529..237f23f 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1350,7 +1350,6 @@
 
 	return rate;
 }
-EXPORT_SYMBOL_GPL(clk_core_get_rate);
 
 /**
  * clk_get_rate - return the rate of clk
@@ -2171,6 +2170,32 @@
 }
 
 /**
+ * clk_is_match - check if two clk's point to the same hardware clock
+ * @p: clk compared against q
+ * @q: clk compared against p
+ *
+ * Returns true if the two struct clk pointers both point to the same hardware
+ * clock node. Put differently, returns true if struct clk *p and struct clk *q
+ * share the same struct clk_core object.
+ *
+ * Returns false otherwise. Note that two NULL clks are treated as matching.
+ */
+bool clk_is_match(const struct clk *p, const struct clk *q)
+{
+	/* trivial case: identical struct clk's or both NULL */
+	if (p == q)
+		return true;
+
+	/* true if clk->core pointers match. Avoid derefing garbage */
+	if (!IS_ERR_OR_NULL(p) && !IS_ERR_OR_NULL(q))
+		if (p->core == q->core)
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(clk_is_match);
+
+/**
  * __clk_init - initialize the data structures in a struct clk
  * @dev:	device initializing this clk, placeholder for now
  * @clk:	clk being initialized
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index b0b562b..e60feff 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -48,6 +48,17 @@
 	},
 };
 
+static struct clk_regmap pll4_vote = {
+	.enable_reg = 0x34c0,
+	.enable_mask = BIT(4),
+	.hw.init = &(struct clk_init_data){
+		.name = "pll4_vote",
+		.parent_names = (const char *[]){ "pll4" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
 static struct clk_pll pll8 = {
 	.l_reg = 0x3144,
 	.m_reg = 0x3148,
@@ -3023,6 +3034,7 @@
 
 static struct clk_regmap *gcc_msm8960_clks[] = {
 	[PLL3] = &pll3.clkr,
+	[PLL4_VOTE] = &pll4_vote,
 	[PLL8] = &pll8.clkr,
 	[PLL8_VOTE] = &pll8_vote,
 	[PLL14] = &pll14.clkr,
@@ -3247,6 +3259,7 @@
 
 static struct clk_regmap *gcc_apq8064_clks[] = {
 	[PLL3] = &pll3.clkr,
+	[PLL4_VOTE] = &pll4_vote,
 	[PLL8] = &pll8.clkr,
 	[PLL8_VOTE] = &pll8_vote,
 	[PLL14] = &pll14.clkr,
diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c
index 121ffde..c9ff27b 100644
--- a/drivers/clk/qcom/lcc-ipq806x.c
+++ b/drivers/clk/qcom/lcc-ipq806x.c
@@ -462,7 +462,6 @@
 	.remove		= lcc_ipq806x_remove,
 	.driver		= {
 		.name	= "lcc-ipq806x",
-		.owner	= THIS_MODULE,
 		.of_match_table = lcc_ipq806x_match_table,
 	},
 };
diff --git a/drivers/clk/qcom/lcc-msm8960.c b/drivers/clk/qcom/lcc-msm8960.c
index a75a408..e2c8632 100644
--- a/drivers/clk/qcom/lcc-msm8960.c
+++ b/drivers/clk/qcom/lcc-msm8960.c
@@ -417,8 +417,8 @@
 		.mnctr_en_bit = 8,
 		.mnctr_reset_bit = 7,
 		.mnctr_mode_shift = 5,
-		.n_val_shift = 16,
-		.m_val_shift = 16,
+		.n_val_shift = 24,
+		.m_val_shift = 8,
 		.width = 8,
 	},
 	.p = {
@@ -547,7 +547,7 @@
 		return PTR_ERR(regmap);
 
 	/* Use the correct frequency plan depending on speed of PLL4 */
-	val = regmap_read(regmap, 0x4, &val);
+	regmap_read(regmap, 0x4, &val);
 	if (val == 0x12) {
 		slimbus_src.freq_tbl = clk_tbl_aif_osr_492;
 		mi2s_osr_src.freq_tbl = clk_tbl_aif_osr_492;
@@ -574,7 +574,6 @@
 	.remove		= lcc_msm8960_remove,
 	.driver		= {
 		.name	= "lcc-msm8960",
-		.owner	= THIS_MODULE,
 		.of_match_table = lcc_msm8960_match_table,
 	},
 };
diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c
index 6ef8963..d216406 100644
--- a/drivers/clk/ti/fapll.c
+++ b/drivers/clk/ti/fapll.c
@@ -84,7 +84,7 @@
 	struct fapll_data *fd = to_fapll(hw);
 	u32 v = readl_relaxed(fd->base);
 
-	v |= (1 << FAPLL_MAIN_PLLEN);
+	v |= FAPLL_MAIN_PLLEN;
 	writel_relaxed(v, fd->base);
 
 	return 0;
@@ -95,7 +95,7 @@
 	struct fapll_data *fd = to_fapll(hw);
 	u32 v = readl_relaxed(fd->base);
 
-	v &= ~(1 << FAPLL_MAIN_PLLEN);
+	v &= ~FAPLL_MAIN_PLLEN;
 	writel_relaxed(v, fd->base);
 }
 
@@ -104,7 +104,7 @@
 	struct fapll_data *fd = to_fapll(hw);
 	u32 v = readl_relaxed(fd->base);
 
-	return v & (1 << FAPLL_MAIN_PLLEN);
+	return v & FAPLL_MAIN_PLLEN;
 }
 
 static unsigned long ti_fapll_recalc_rate(struct clk_hw *hw,
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 1c2506f..a0b036c 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -63,6 +63,11 @@
 config CADENCE_TTC_TIMER
 	bool
 
+config ASM9260_TIMER
+	bool
+	select CLKSRC_MMIO
+	select CLKSRC_OF
+
 config CLKSRC_NOMADIK_MTU
 	bool
 	depends on (ARCH_NOMADIK || ARCH_U8500)
@@ -187,6 +192,7 @@
 config SH_TIMER_CMT
 	bool "Renesas CMT timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	default SYS_SUPPORTS_SH_CMT
 	help
 	  This enables build of a clocksource and clockevent driver for
@@ -196,6 +202,7 @@
 config SH_TIMER_MTU2
 	bool "Renesas MTU2 timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	default SYS_SUPPORTS_SH_MTU2
 	help
 	  This enables build of a clockevent driver for the Multi-Function
@@ -205,6 +212,7 @@
 config SH_TIMER_TMU
 	bool "Renesas TMU timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	default SYS_SUPPORTS_SH_TMU
 	help
 	  This enables build of a clocksource and clockevent driver for
@@ -245,15 +253,4 @@
 	help
 	  This enables OST0 support available on PXA and SA-11x0
 	  platforms.
-
-config ASM9260_TIMER
-	bool "Alphascale ASM9260 timer driver"
-	depends on GENERIC_CLOCKEVENTS
-	select CLKSRC_MMIO
-	select CLKSRC_OF
-	default y if MACH_ASM9260
-	help
-	  This enables build of a clocksource and clockevent driver for
-	  the 32-bit System Timer hardware available on a Alphascale ASM9260.
-
 endmenu
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
index 32a3d25..68ab423 100644
--- a/drivers/clocksource/mtk_timer.c
+++ b/drivers/clocksource/mtk_timer.c
@@ -224,6 +224,8 @@
 	}
 	rate = clk_get_rate(clk);
 
+	mtk_timer_global_reset(evt);
+
 	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
 			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
 		pr_warn("failed to setup irq %d\n", evt->dev.irq);
@@ -232,8 +234,6 @@
 
 	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	mtk_timer_global_reset(evt);
-
 	/* Configure clock source */
 	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
 	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
@@ -241,10 +241,11 @@
 
 	/* Configure clock event */
 	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
 	clockevents_config_and_register(&evt->dev, rate, 0x3,
 					0xffffffff);
+
+	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
+
 	return;
 
 err_clk_disable:
diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c
index 941f3f3..d9438af 100644
--- a/drivers/clocksource/pxa_timer.c
+++ b/drivers/clocksource/pxa_timer.c
@@ -163,7 +163,7 @@
 	.dev_id		= &ckevt_pxa_osmr0,
 };
 
-static void pxa_timer_common_init(int irq, unsigned long clock_tick_rate)
+static void __init pxa_timer_common_init(int irq, unsigned long clock_tick_rate)
 {
 	timer_writel(0, OIER);
 	timer_writel(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR);
diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c
index bba62f9..ec57ba2 100644
--- a/drivers/clocksource/time-efm32.c
+++ b/drivers/clocksource/time-efm32.c
@@ -225,12 +225,12 @@
 	clock_event_ddata.base = base;
 	clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ);
 
-	setup_irq(irq, &efm32_clock_event_irq);
-
 	clockevents_config_and_register(&clock_event_ddata.evtdev,
 					DIV_ROUND_CLOSEST(rate, 1024),
 					0xf, 0xffff);
 
+	setup_irq(irq, &efm32_clock_event_irq);
+
 	return 0;
 
 err_get_irq:
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 0226844..58597fb 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -17,7 +17,6 @@
 #include <linux/irq.h>
 #include <linux/irqreturn.h>
 #include <linux/reset.h>
-#include <linux/sched_clock.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -137,11 +136,6 @@
 	.dev_id = &sun5i_clockevent,
 };
 
-static u64 sun5i_timer_sched_read(void)
-{
-	return ~readl(timer_base + TIMER_CNTVAL_LO_REG(1));
-}
-
 static void __init sun5i_timer_init(struct device_node *node)
 {
 	struct reset_control *rstc;
@@ -172,16 +166,11 @@
 	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
 	       timer_base + TIMER_CTL_REG(1));
 
-	sched_clock_register(sun5i_timer_sched_read, 32, rate);
 	clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name,
 			      rate, 340, 32, clocksource_mmio_readl_down);
 
 	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	ret = setup_irq(irq, &sun5i_timer_irq);
-	if (ret)
-		pr_warn("failed to setup irq %d\n", irq);
-
 	/* Enable timer0 interrupt */
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
@@ -191,6 +180,10 @@
 
 	clockevents_config_and_register(&sun5i_clockevent, rate,
 					TIMER_SYNC_TICKS, 0xffffffff);
+
+	ret = setup_irq(irq, &sun5i_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
 }
 CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
 		       sun5i_timer_init);
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index 5e98c6b..82d2fbb 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -159,7 +159,7 @@
 
 static int exynos_cpufreq_probe(struct platform_device *pdev)
 {
-	struct device_node *cpus, *np;
+	struct device_node *cpu0;
 	int ret = -EINVAL;
 
 	exynos_info = kzalloc(sizeof(*exynos_info), GFP_KERNEL);
@@ -206,28 +206,19 @@
 	if (ret)
 		goto err_cpufreq_reg;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (!cpus) {
-		pr_err("failed to find cpus node\n");
+	cpu0 = of_get_cpu_node(0, NULL);
+	if (!cpu0) {
+		pr_err("failed to find cpu0 node\n");
 		return 0;
 	}
 
-	np = of_get_next_child(cpus, NULL);
-	if (!np) {
-		pr_err("failed to find cpus child node\n");
-		of_node_put(cpus);
-		return 0;
-	}
-
-	if (of_find_property(np, "#cooling-cells", NULL)) {
-		cdev = of_cpufreq_cooling_register(np,
+	if (of_find_property(cpu0, "#cooling-cells", NULL)) {
+		cdev = of_cpufreq_cooling_register(cpu0,
 						   cpu_present_mask);
 		if (IS_ERR(cdev))
 			pr_err("running cpufreq without cooling device: %ld\n",
 			       PTR_ERR(cdev));
 	}
-	of_node_put(np);
-	of_node_put(cpus);
 
 	return 0;
 
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index bee5df7..7cb4b76 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -22,6 +22,8 @@
 #include <linux/smp.h>
 #include <sysdev/fsl_soc.h>
 
+#include <asm/smp.h>	/* for get_hard_smp_processor_id() in UP configs */
+
 /**
  * struct cpu_data - per CPU data struct
  * @parent: the parent node of cpu clock
diff --git a/drivers/cpuidle/cpuidle-mvebu-v7.c b/drivers/cpuidle/cpuidle-mvebu-v7.c
index 38e6861..980151f 100644
--- a/drivers/cpuidle/cpuidle-mvebu-v7.c
+++ b/drivers/cpuidle/cpuidle-mvebu-v7.c
@@ -37,11 +37,11 @@
 		deepidle = true;
 
 	ret = mvebu_v7_cpu_suspend(deepidle);
+	cpu_pm_exit();
+
 	if (ret)
 		return ret;
 
-	cpu_pm_exit();
-
 	return index;
 }
 
@@ -50,17 +50,17 @@
 	.states[0]		= ARM_CPUIDLE_WFI_STATE,
 	.states[1]		= {
 		.enter			= mvebu_v7_enter_idle,
-		.exit_latency		= 10,
+		.exit_latency		= 100,
 		.power_usage		= 50,
-		.target_residency	= 100,
+		.target_residency	= 1000,
 		.name			= "MV CPU IDLE",
 		.desc			= "CPU power down",
 	},
 	.states[2]		= {
 		.enter			= mvebu_v7_enter_idle,
-		.exit_latency		= 100,
+		.exit_latency		= 1000,
 		.power_usage		= 5,
-		.target_residency	= 1000,
+		.target_residency	= 10000,
 		.flags			= MVEBU_V7_FLAG_DEEP_IDLE,
 		.name			= "MV CPU DEEP IDLE",
 		.desc			= "CPU and L2 Fabric power down",
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 4d53458..080bd2d 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -44,6 +44,12 @@
 	off = 1;
 }
 
+bool cpuidle_not_available(struct cpuidle_driver *drv,
+			   struct cpuidle_device *dev)
+{
+	return off || !initialized || !drv || !dev || !dev->enabled;
+}
+
 /**
  * cpuidle_play_dead - cpu off-lining
  *
@@ -66,14 +72,8 @@
 	return -ENODEV;
 }
 
-/**
- * cpuidle_find_deepest_state - Find deepest state meeting specific conditions.
- * @drv: cpuidle driver for the given CPU.
- * @dev: cpuidle device for the given CPU.
- * @freeze: Whether or not the state should be suitable for suspend-to-idle.
- */
-static int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
-				      struct cpuidle_device *dev, bool freeze)
+static int find_deepest_state(struct cpuidle_driver *drv,
+			      struct cpuidle_device *dev, bool freeze)
 {
 	unsigned int latency_req = 0;
 	int i, ret = freeze ? -1 : CPUIDLE_DRIVER_STATE_START - 1;
@@ -92,6 +92,17 @@
 	return ret;
 }
 
+/**
+ * cpuidle_find_deepest_state - Find the deepest available idle state.
+ * @drv: cpuidle driver for the given CPU.
+ * @dev: cpuidle device for the given CPU.
+ */
+int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
+			       struct cpuidle_device *dev)
+{
+	return find_deepest_state(drv, dev, false);
+}
+
 static void enter_freeze_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {
@@ -113,15 +124,14 @@
 
 /**
  * cpuidle_enter_freeze - Enter an idle state suitable for suspend-to-idle.
+ * @drv: cpuidle driver for the given CPU.
+ * @dev: cpuidle device for the given CPU.
  *
  * If there are states with the ->enter_freeze callback, find the deepest of
- * them and enter it with frozen tick.  Otherwise, find the deepest state
- * available and enter it normally.
+ * them and enter it with frozen tick.
  */
-void cpuidle_enter_freeze(void)
+int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
-	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int index;
 
 	/*
@@ -129,24 +139,11 @@
 	 * that interrupts won't be enabled when it exits and allows the tick to
 	 * be frozen safely.
 	 */
-	index = cpuidle_find_deepest_state(drv, dev, true);
-	if (index >= 0) {
-		enter_freeze_proper(drv, dev, index);
-		return;
-	}
-
-	/*
-	 * It is not safe to freeze the tick, find the deepest state available
-	 * at all and try to enter it normally.
-	 */
-	index = cpuidle_find_deepest_state(drv, dev, false);
+	index = find_deepest_state(drv, dev, true);
 	if (index >= 0)
-		cpuidle_enter(drv, dev, index);
-	else
-		arch_cpu_idle();
+		enter_freeze_proper(drv, dev, index);
 
-	/* Interrupts are enabled again here. */
-	local_irq_disable();
+	return index;
 }
 
 /**
@@ -205,12 +202,6 @@
  */
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	if (off || !initialized)
-		return -ENODEV;
-
-	if (!drv || !dev || !dev->enabled)
-		return -EBUSY;
-
 	return cpuidle_curr_governor->select(drv, dev);
 }
 
diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c
index e554111..50ef8bd 100644
--- a/drivers/dma-buf/fence.c
+++ b/drivers/dma-buf/fence.c
@@ -159,6 +159,9 @@
 	if (WARN_ON(timeout < 0))
 		return -EINVAL;
 
+	if (timeout == 0)
+		return fence_is_signaled(fence);
+
 	trace_fence_wait_start(fence);
 	ret = fence->ops->wait(fence, intr, timeout);
 	trace_fence_wait_end(fence);
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 3c97c8f..39920d7 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -327,6 +327,9 @@
 	unsigned seq, shared_count, i = 0;
 	long ret = timeout;
 
+	if (!timeout)
+		return reservation_object_test_signaled_rcu(obj, wait_all);
+
 retry:
 	fence = NULL;
 	shared_count = 0;
@@ -402,8 +405,6 @@
 	int ret = 1;
 
 	if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) {
-		int ret;
-
 		fence = fence_get_rcu(lfence);
 		if (!fence)
 			return -1;
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 4a5fd24..83aa55d 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -97,6 +97,12 @@
 
 #define DRIVER_NAME	"pl08xdmac"
 
+#define PL80X_DMA_BUSWIDTHS \
+	BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
+
 static struct amba_driver pl08x_amba_driver;
 struct pl08x_driver_data;
 
@@ -2070,6 +2076,10 @@
 	pl08x->memcpy.device_pause = pl08x_pause;
 	pl08x->memcpy.device_resume = pl08x_resume;
 	pl08x->memcpy.device_terminate_all = pl08x_terminate_all;
+	pl08x->memcpy.src_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->memcpy.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->memcpy.directions = BIT(DMA_MEM_TO_MEM);
+	pl08x->memcpy.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
 	/* Initialize slave engine */
 	dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask);
@@ -2086,6 +2096,10 @@
 	pl08x->slave.device_pause = pl08x_pause;
 	pl08x->slave.device_resume = pl08x_resume;
 	pl08x->slave.device_terminate_all = pl08x_terminate_all;
+	pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->slave.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	pl08x->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
 	/* Get the platform data */
 	pl08x->pd = dev_get_platdata(&adev->dev);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 1e1a4c5..0b4fc6f 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -238,93 +238,126 @@
 }
 
 /*
- * atc_get_current_descriptors -
- * locate the descriptor which equal to physical address in DSCR
- * @atchan: the channel we want to start
- * @dscr_addr: physical descriptor address in DSCR
+ * atc_get_desc_by_cookie - get the descriptor of a cookie
+ * @atchan: the DMA channel
+ * @cookie: the cookie to get the descriptor for
  */
-static struct at_desc *atc_get_current_descriptors(struct at_dma_chan *atchan,
-							u32 dscr_addr)
+static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan,
+						dma_cookie_t cookie)
 {
-	struct at_desc  *desc, *_desc, *child, *desc_cur = NULL;
+	struct at_desc *desc, *_desc;
+
+	list_for_each_entry_safe(desc, _desc, &atchan->queue, desc_node) {
+		if (desc->txd.cookie == cookie)
+			return desc;
+	}
 
 	list_for_each_entry_safe(desc, _desc, &atchan->active_list, desc_node) {
-		if (desc->lli.dscr == dscr_addr) {
-			desc_cur = desc;
-			break;
-		}
-
-		list_for_each_entry(child, &desc->tx_list, desc_node) {
-			if (child->lli.dscr == dscr_addr) {
-				desc_cur = child;
-				break;
-			}
-		}
+		if (desc->txd.cookie == cookie)
+			return desc;
 	}
 
-	return desc_cur;
+	return NULL;
 }
 
-/*
- * atc_get_bytes_left -
- * Get the number of bytes residue in dma buffer,
- * @chan: the channel we want to start
+/**
+ * atc_calc_bytes_left - calculates the number of bytes left according to the
+ * value read from CTRLA.
+ *
+ * @current_len: the number of bytes left before reading CTRLA
+ * @ctrla: the value of CTRLA
+ * @desc: the descriptor containing the transfer width
  */
-static int atc_get_bytes_left(struct dma_chan *chan)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
+					struct at_desc *desc)
+{
+	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
+}
+
+/**
+ * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
+ * to the current value of CTRLA.
+ *
+ * @current_len: the number of bytes left before reading CTRLA
+ * @atchan: the channel to read CTRLA for
+ * @desc: the descriptor containing the transfer width
+ */
+static inline int atc_calc_bytes_left_from_reg(int current_len,
+			struct at_dma_chan *atchan, struct at_desc *desc)
+{
+	u32 ctrla = channel_readl(atchan, CTRLA);
+
+	return atc_calc_bytes_left(current_len, ctrla, desc);
+}
+
+/**
+ * atc_get_bytes_left - get the number of bytes residue for a cookie
+ * @chan: DMA channel
+ * @cookie: transaction identifier to check status of
+ */
+static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 {
 	struct at_dma_chan      *atchan = to_at_dma_chan(chan);
-	struct at_dma           *atdma = to_at_dma(chan->device);
-	int	chan_id = atchan->chan_common.chan_id;
 	struct at_desc *desc_first = atc_first_active(atchan);
-	struct at_desc *desc_cur;
-	int ret = 0, count = 0;
+	struct at_desc *desc;
+	int ret;
+	u32 ctrla, dscr;
 
 	/*
-	 * Initialize necessary values in the first time.
-	 * remain_desc record remain desc length.
+	 * If the cookie doesn't match to the currently running transfer then
+	 * we can return the total length of the associated DMA transfer,
+	 * because it is still queued.
 	 */
-	if (atchan->remain_desc == 0)
-		/* First descriptor embedds the transaction length */
-		atchan->remain_desc = desc_first->len;
+	desc = atc_get_desc_by_cookie(atchan, cookie);
+	if (desc == NULL)
+		return -EINVAL;
+	else if (desc != desc_first)
+		return desc->total_len;
 
-	/*
-	 * This happens when current descriptor transfer complete.
-	 * The residual buffer size should reduce current descriptor length.
-	 */
-	if (unlikely(test_bit(ATC_IS_BTC, &atchan->status))) {
-		clear_bit(ATC_IS_BTC, &atchan->status);
-		desc_cur = atc_get_current_descriptors(atchan,
-						channel_readl(atchan, DSCR));
-		if (!desc_cur) {
-			ret = -EINVAL;
-			goto out;
-		}
+	/* cookie matches to the currently running transfer */
+	ret = desc_first->total_len;
 
-		count = (desc_cur->lli.ctrla & ATC_BTSIZE_MAX)
-			<< desc_first->tx_width;
-		if (atchan->remain_desc < count) {
-			ret = -EINVAL;
-			goto out;
-		}
+	if (desc_first->lli.dscr) {
+		/* hardware linked list transfer */
 
-		atchan->remain_desc -= count;
-		ret = atchan->remain_desc;
-	} else {
 		/*
-		 * Get residual bytes when current
-		 * descriptor transfer in progress.
+		 * Calculate the residue by removing the length of the child
+		 * descriptors already transferred from the total length.
+		 * To get the current child descriptor we can use the value of
+		 * the channel's DSCR register and compare it against the value
+		 * of the hardware linked list structure of each child
+		 * descriptor.
 		 */
-		count = (channel_readl(atchan, CTRLA) & ATC_BTSIZE_MAX)
-				<< (desc_first->tx_width);
-		ret = atchan->remain_desc - count;
-	}
-	/*
-	 * Check fifo empty.
-	 */
-	if (!(dma_readl(atdma, CHSR) & AT_DMA_EMPT(chan_id)))
-		atc_issue_pending(chan);
 
-out:
+		ctrla = channel_readl(atchan, CTRLA);
+		rmb(); /* ensure CTRLA is read before DSCR */
+		dscr = channel_readl(atchan, DSCR);
+
+		/* for the first descriptor we can be more accurate */
+		if (desc_first->lli.dscr == dscr)
+			return atc_calc_bytes_left(ret, ctrla, desc_first);
+
+		ret -= desc_first->len;
+		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
+			if (desc->lli.dscr == dscr)
+				break;
+
+			ret -= desc->len;
+		}
+
+		/*
+		 * For the last descriptor in the chain we can calculate
+		 * the remaining bytes using the channel's register.
+		 * Note that the transfer width of the first and last
+		 * descriptor may differ.
+		 */
+		if (!desc->lli.dscr)
+			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+	} else {
+		/* single transfer */
+		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+	}
+
 	return ret;
 }
 
@@ -539,8 +572,6 @@
 					/* Give information to tasklet */
 					set_bit(ATC_IS_ERROR, &atchan->status);
 				}
-				if (pending & AT_DMA_BTC(i))
-					set_bit(ATC_IS_BTC, &atchan->status);
 				tasklet_schedule(&atchan->tasklet);
 				ret = IRQ_HANDLED;
 			}
@@ -653,14 +684,18 @@
 		desc->lli.ctrlb = ctrlb;
 
 		desc->txd.cookie = 0;
+		desc->len = xfer_count << src_width;
 
 		atc_desc_chain(&first, &prev, desc);
 	}
 
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
-	first->len = len;
+	first->total_len = len;
+
+	/* set transfer width for the calculation of the residue */
 	first->tx_width = src_width;
+	prev->tx_width = src_width;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -752,6 +787,7 @@
 					| ATC_SRC_WIDTH(mem_width)
 					| len >> mem_width;
 			desc->lli.ctrlb = ctrlb;
+			desc->len = len;
 
 			atc_desc_chain(&first, &prev, desc);
 			total_len += len;
@@ -792,6 +828,7 @@
 					| ATC_DST_WIDTH(mem_width)
 					| len >> reg_width;
 			desc->lli.ctrlb = ctrlb;
+			desc->len = len;
 
 			atc_desc_chain(&first, &prev, desc);
 			total_len += len;
@@ -806,8 +843,11 @@
 
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
-	first->len = total_len;
+	first->total_len = total_len;
+
+	/* set transfer width for the calculation of the residue */
 	first->tx_width = reg_width;
+	prev->tx_width = reg_width;
 
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
@@ -872,6 +912,7 @@
 				| ATC_FC_MEM2PER
 				| ATC_SIF(atchan->mem_if)
 				| ATC_DIF(atchan->per_if);
+		desc->len = period_len;
 		break;
 
 	case DMA_DEV_TO_MEM:
@@ -883,6 +924,7 @@
 				| ATC_FC_PER2MEM
 				| ATC_SIF(atchan->per_if)
 				| ATC_DIF(atchan->mem_if);
+		desc->len = period_len;
 		break;
 
 	default:
@@ -964,7 +1006,7 @@
 
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
-	first->len = buf_len;
+	first->total_len = buf_len;
 	first->tx_width = reg_width;
 
 	return &first->txd;
@@ -1118,7 +1160,7 @@
 	spin_lock_irqsave(&atchan->lock, flags);
 
 	/*  Get number of bytes left in the active transactions */
-	bytes = atc_get_bytes_left(chan);
+	bytes = atc_get_bytes_left(chan, cookie);
 
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
@@ -1214,7 +1256,6 @@
 
 	spin_lock_irqsave(&atchan->lock, flags);
 	atchan->descs_allocated = i;
-	atchan->remain_desc = 0;
 	list_splice(&tmp_list, &atchan->free_list);
 	dma_cookie_init(chan);
 	spin_unlock_irqrestore(&atchan->lock, flags);
@@ -1257,7 +1298,6 @@
 	list_splice_init(&atchan->free_list, &list);
 	atchan->descs_allocated = 0;
 	atchan->status = 0;
-	atchan->remain_desc = 0;
 
 	dev_vdbg(chan2dev(chan), "free_chan_resources: done\n");
 }
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index d6bba6c..2727ca5 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -181,8 +181,9 @@
  * @at_lli: hardware lli structure
  * @txd: support for the async_tx api
  * @desc_node: node on the channed descriptors list
- * @len: total transaction bytecount
+ * @len: descriptor byte count
  * @tx_width: transfer width
+ * @total_len: total transaction byte count
  */
 struct at_desc {
 	/* FIRST values the hardware uses */
@@ -194,6 +195,7 @@
 	struct list_head		desc_node;
 	size_t				len;
 	u32				tx_width;
+	size_t				total_len;
 };
 
 static inline struct at_desc *
@@ -213,7 +215,6 @@
 enum atc_status {
 	ATC_IS_ERROR = 0,
 	ATC_IS_PAUSED = 1,
-	ATC_IS_BTC = 2,
 	ATC_IS_CYCLIC = 24,
 };
 
@@ -231,7 +232,6 @@
  * @save_cfg: configuration register that is saved on suspend/resume cycle
  * @save_dscr: for cyclic operations, preserve next descriptor address in
  *             the cyclic list on suspend/resume cycle
- * @remain_desc: to save remain desc length
  * @dma_sconfig: configuration for slave transfers, passed via
  * .device_config
  * @lock: serializes enqueue/dequeue operations to descriptors lists
@@ -251,7 +251,6 @@
 	struct tasklet_struct	tasklet;
 	u32			save_cfg;
 	u32			save_dscr;
-	u32			remain_desc;
 	struct dma_slave_config dma_sconfig;
 
 	spinlock_t		lock;
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 09e2825..d9891d3 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -664,7 +664,6 @@
 	struct at_xdmac_desc	*first = NULL, *prev = NULL;
 	unsigned int		periods = buf_len / period_len;
 	int			i;
-	u32			cfg;
 
 	dev_dbg(chan2dev(chan), "%s: buf_addr=%pad, buf_len=%zd, period_len=%zd, dir=%s, flags=0x%lx\n",
 		__func__, &buf_addr, buf_len, period_len,
@@ -700,17 +699,17 @@
 		if (direction == DMA_DEV_TO_MEM) {
 			desc->lld.mbr_sa = atchan->per_src_addr;
 			desc->lld.mbr_da = buf_addr + i * period_len;
-			cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
+			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
 		} else {
 			desc->lld.mbr_sa = buf_addr + i * period_len;
 			desc->lld.mbr_da = atchan->per_dst_addr;
-			cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
 		}
 		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1
 			| AT_XDMAC_MBR_UBC_NDEN
 			| AT_XDMAC_MBR_UBC_NSEN
 			| AT_XDMAC_MBR_UBC_NDE
-			| period_len >> at_xdmac_get_dwidth(cfg);
+			| period_len >> at_xdmac_get_dwidth(desc->lld.mbr_cfg);
 
 		dev_dbg(chan2dev(chan),
 			 "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 455b7a4..a8ad052 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -626,7 +626,7 @@
 	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__, status);
 
 	/* Check if we have any interrupt from the DMAC */
-	if (!status)
+	if (!status || !dw->in_use)
 		return IRQ_NONE;
 
 	/*
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 6565a36..b2c3ae0 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -26,6 +26,8 @@
 
 #include "internal.h"
 
+#define DRV_NAME	"dw_dmac"
+
 static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 					struct of_dma *ofdma)
 {
@@ -284,7 +286,7 @@
 	.remove		= dw_remove,
 	.shutdown       = dw_shutdown,
 	.driver = {
-		.name	= "dw_dmac",
+		.name	= DRV_NAME,
 		.pm	= &dw_dev_pm_ops,
 		.of_match_table = of_match_ptr(dw_dma_of_id_table),
 		.acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table),
@@ -305,3 +307,4 @@
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 18c0a13..66a0efb 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -531,6 +531,10 @@
 		dev_err(sdma->dev, "Timeout waiting for CH0 ready\n");
 	}
 
+	/* Set bits of CONFIG register with dynamic context switching */
+	if (readl(sdma->regs + SDMA_H_CONFIG) == 0)
+		writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
+
 	return ret ? 0 : -ETIMEDOUT;
 }
 
@@ -1394,9 +1398,6 @@
 
 	writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
-	/* Set bits of CONFIG register with given context switching mode */
-	writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
-
 	/* Initializes channel's priorities */
 	sdma_set_channel_priority(&sdma->channel[0], 7);
 
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 77a6dcf..194ec20 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -230,6 +230,10 @@
 	switch (pdev->device) {
 	case PCI_DEVICE_ID_INTEL_IOAT_BWD2:
 	case PCI_DEVICE_ID_INTEL_IOAT_BWD3:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE0:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE1:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE2:
+	case PCI_DEVICE_ID_INTEL_IOAT_BDXDE3:
 		return true;
 	default:
 		return false;
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index 8926f27..eb41004 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -219,6 +219,9 @@
 
 	while (dint) {
 		i = __ffs(dint);
+		/* only handle interrupts belonging to pdma driver*/
+		if (i >= pdev->dma_channels)
+			break;
 		dint &= (dint - 1);
 		phy = &pdev->phy[i];
 		ret = mmp_pdma_chan_handler(irq, phy);
@@ -999,6 +1002,9 @@
 	struct resource *iores;
 	int i, ret, irq = 0;
 	int dma_channels = 0, irq_num = 0;
+	const enum dma_slave_buswidth widths =
+		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
+		DMA_SLAVE_BUSWIDTH_4_BYTES;
 
 	pdev = devm_kzalloc(&op->dev, sizeof(*pdev), GFP_KERNEL);
 	if (!pdev)
@@ -1066,6 +1072,10 @@
 	pdev->device.device_config = mmp_pdma_config;
 	pdev->device.device_terminate_all = mmp_pdma_terminate_all;
 	pdev->device.copy_align = PDMA_ALIGNMENT;
+	pdev->device.src_addr_widths = widths;
+	pdev->device.dst_addr_widths = widths;
+	pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
+	pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
 
 	if (pdev->dev->coherent_dma_mask)
 		dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask);
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 70c2fa9..b6f4e1f 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -110,7 +110,7 @@
 	struct tasklet_struct		tasklet;
 
 	struct mmp_tdma_desc		*desc_arr;
-	phys_addr_t			desc_arr_phys;
+	dma_addr_t			desc_arr_phys;
 	int				desc_num;
 	enum dma_transfer_direction	dir;
 	dma_addr_t			dev_addr;
@@ -166,9 +166,12 @@
 static int mmp_tdma_disable_chan(struct dma_chan *chan)
 {
 	struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan);
+	u32 tdcr;
 
-	writel(readl(tdmac->reg_base + TDCR) & ~TDCR_CHANEN,
-					tdmac->reg_base + TDCR);
+	tdcr = readl(tdmac->reg_base + TDCR);
+	tdcr |= TDCR_ABR;
+	tdcr &= ~TDCR_CHANEN;
+	writel(tdcr, tdmac->reg_base + TDCR);
 
 	tdmac->status = DMA_COMPLETE;
 
@@ -296,12 +299,27 @@
 	return -EAGAIN;
 }
 
+static size_t mmp_tdma_get_pos(struct mmp_tdma_chan *tdmac)
+{
+	size_t reg;
+
+	if (tdmac->idx == 0) {
+		reg = __raw_readl(tdmac->reg_base + TDSAR);
+		reg -= tdmac->desc_arr[0].src_addr;
+	} else if (tdmac->idx == 1) {
+		reg = __raw_readl(tdmac->reg_base + TDDAR);
+		reg -= tdmac->desc_arr[0].dst_addr;
+	} else
+		return -EINVAL;
+
+	return reg;
+}
+
 static irqreturn_t mmp_tdma_chan_handler(int irq, void *dev_id)
 {
 	struct mmp_tdma_chan *tdmac = dev_id;
 
 	if (mmp_tdma_clear_chan_irq(tdmac) == 0) {
-		tdmac->pos = (tdmac->pos + tdmac->period_len) % tdmac->buf_len;
 		tasklet_schedule(&tdmac->tasklet);
 		return IRQ_HANDLED;
 	} else
@@ -343,7 +361,7 @@
 	int size = tdmac->desc_num * sizeof(struct mmp_tdma_desc);
 
 	gpool = tdmac->pool;
-	if (tdmac->desc_arr)
+	if (gpool && tdmac->desc_arr)
 		gen_pool_free(gpool, (unsigned long)tdmac->desc_arr,
 				size);
 	tdmac->desc_arr = NULL;
@@ -499,6 +517,7 @@
 {
 	struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan);
 
+	tdmac->pos = mmp_tdma_get_pos(tdmac);
 	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
 			 tdmac->buf_len - tdmac->pos);
 
@@ -610,7 +629,7 @@
 	int i, ret;
 	int irq = 0, irq_num = 0;
 	int chan_num = TDMA_CHANNEL_NUM;
-	struct gen_pool *pool;
+	struct gen_pool *pool = NULL;
 
 	of_id = of_match_device(mmp_tdma_dt_ids, &pdev->dev);
 	if (of_id)
diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c
index d7a33b3..9c914d6 100644
--- a/drivers/dma/qcom_bam_dma.c
+++ b/drivers/dma/qcom_bam_dma.c
@@ -162,9 +162,9 @@
 	[BAM_P_IRQ_STTS]	= { 0x1010, 0x1000, 0x00, 0x00 },
 	[BAM_P_IRQ_CLR]		= { 0x1014, 0x1000, 0x00, 0x00 },
 	[BAM_P_IRQ_EN]		= { 0x1018, 0x1000, 0x00, 0x00 },
-	[BAM_P_EVNT_DEST_ADDR]	= { 0x102C, 0x00, 0x1000, 0x00 },
-	[BAM_P_EVNT_REG]	= { 0x1018, 0x00, 0x1000, 0x00 },
-	[BAM_P_SW_OFSTS]	= { 0x1000, 0x00, 0x1000, 0x00 },
+	[BAM_P_EVNT_DEST_ADDR]	= { 0x182C, 0x00, 0x1000, 0x00 },
+	[BAM_P_EVNT_REG]	= { 0x1818, 0x00, 0x1000, 0x00 },
+	[BAM_P_SW_OFSTS]	= { 0x1800, 0x00, 0x1000, 0x00 },
 	[BAM_P_DATA_FIFO_ADDR]	= { 0x1824, 0x00, 0x1000, 0x00 },
 	[BAM_P_DESC_FIFO_ADDR]	= { 0x181C, 0x00, 0x1000, 0x00 },
 	[BAM_P_EVNT_GEN_TRSHLD]	= { 0x1828, 0x00, 0x1000, 0x00 },
@@ -1143,6 +1143,10 @@
 	dma_cap_set(DMA_SLAVE, bdev->common.cap_mask);
 
 	/* initialize dmaengine apis */
+	bdev->common.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	bdev->common.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	bdev->common.src_addr_widths = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	bdev->common.dst_addr_widths = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	bdev->common.device_alloc_chan_resources = bam_alloc_chan;
 	bdev->common.device_free_chan_resources = bam_free_chan;
 	bdev->common.device_prep_slave_sg = bam_prep_slave_sg;
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index b2431aa..9f1d4c7 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -582,15 +582,12 @@
 	}
 }
 
-static void sh_dmae_shutdown(struct platform_device *pdev)
-{
-	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
-	sh_dmae_ctl_stop(shdev);
-}
-
 #ifdef CONFIG_PM
 static int sh_dmae_runtime_suspend(struct device *dev)
 {
+	struct sh_dmae_device *shdev = dev_get_drvdata(dev);
+
+	sh_dmae_ctl_stop(shdev);
 	return 0;
 }
 
@@ -605,6 +602,9 @@
 #ifdef CONFIG_PM_SLEEP
 static int sh_dmae_suspend(struct device *dev)
 {
+	struct sh_dmae_device *shdev = dev_get_drvdata(dev);
+
+	sh_dmae_ctl_stop(shdev);
 	return 0;
 }
 
@@ -929,13 +929,12 @@
 }
 
 static struct platform_driver sh_dmae_driver = {
-	.driver 	= {
+	.driver		= {
 		.pm	= &sh_dmae_pm,
 		.name	= SH_DMAE_DRV_NAME,
 		.of_match_table = sh_dmae_of_match,
 	},
 	.remove		= sh_dmae_remove,
-	.shutdown	= sh_dmae_shutdown,
 };
 
 static int __init sh_dmae_init(void)
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index c5f7b4e..69fac06 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -78,7 +78,7 @@
  *	We have to be cautious here. We have seen BIOSes with DMI pointers
  *	pointing to completely the wrong place for example
  */
-static void dmi_table(u8 *buf, int len, int num,
+static void dmi_table(u8 *buf, u32 len, int num,
 		      void (*decode)(const struct dmi_header *, void *),
 		      void *private_data)
 {
@@ -93,12 +93,6 @@
 		const struct dmi_header *dm = (const struct dmi_header *)data;
 
 		/*
-		 * 7.45 End-of-Table (Type 127) [SMBIOS reference spec v3.0.0]
-		 */
-		if (dm->type == DMI_ENTRY_END_OF_TABLE)
-			break;
-
-		/*
 		 *  We want to know the total length (formatted area and
 		 *  strings) before decoding to make sure we won't run off the
 		 *  table in dmi_decode or dmi_string
@@ -108,13 +102,20 @@
 			data++;
 		if (data - buf < len - 1)
 			decode(dm, private_data);
+
+		/*
+		 * 7.45 End-of-Table (Type 127) [SMBIOS reference spec v3.0.0]
+		 */
+		if (dm->type == DMI_ENTRY_END_OF_TABLE)
+			break;
+
 		data += 2;
 		i++;
 	}
 }
 
 static phys_addr_t dmi_base;
-static u16 dmi_len;
+static u32 dmi_len;
 static u16 dmi_num;
 
 static int __init dmi_walk_early(void (*decode)(const struct dmi_header *,
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 2fe1950..f07d4a6 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -179,12 +179,12 @@
 		start = desc->phys_addr;
 		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
 
-		if ((start + size) > end || (start + size) > max)
-			continue;
-
-		if (end - size > max)
+		if (end > max)
 			end = max;
 
+		if ((start + size) > end)
+			continue;
+
 		if (round_down(end - size, align) < start)
 			continue;
 
diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c
index 472fb5b..9cdbc0c 100644
--- a/drivers/gpio/gpio-tps65912.c
+++ b/drivers/gpio/gpio-tps65912.c
@@ -26,9 +26,12 @@
 	struct gpio_chip gpio_chip;
 };
 
+#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip)
+
 static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 	int val;
 
 	val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset);
@@ -42,7 +45,8 @@
 static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset,
 			      int value)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	if (value)
 		tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset,
@@ -55,7 +59,8 @@
 static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset,
 				int value)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	/* Set the initial value */
 	tps65912_gpio_set(gc, offset, value);
@@ -66,7 +71,8 @@
 
 static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset,
 								GPIO_CFG_MASK);
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 8cad8e4..4650bf8 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -46,12 +46,13 @@
 
 	ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags);
 	if (ret < 0) {
-		/* We've found the gpio chip, but the translation failed.
-		 * Return true to stop looking and return the translation
-		 * error via out_gpio
+		/* We've found a gpio chip, but the translation failed.
+		 * Store translation error in out_gpio.
+		 * Return false to keep looking, as more than one gpio chip
+		 * could be registered per of-node.
 		 */
 		gg_data->out_gpio = ERR_PTR(ret);
-		return true;
+		return false;
 	 }
 
 	gg_data->out_gpio = gpiochip_get_desc(gc, ret);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index b3589d0..d8135ad 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -62,12 +62,18 @@
 	return KFD_MQD_TYPE_CP;
 }
 
-static inline unsigned int get_first_pipe(struct device_queue_manager *dqm)
+unsigned int get_first_pipe(struct device_queue_manager *dqm)
 {
-	BUG_ON(!dqm);
+	BUG_ON(!dqm || !dqm->dev);
 	return dqm->dev->shared_resources.first_compute_pipe;
 }
 
+unsigned int get_pipes_num(struct device_queue_manager *dqm)
+{
+	BUG_ON(!dqm || !dqm->dev);
+	return dqm->dev->shared_resources.compute_pipe_count;
+}
+
 static inline unsigned int get_pipes_num_cpsch(void)
 {
 	return PIPE_PER_ME_CP_SCHEDULING;
@@ -639,6 +645,7 @@
 	pr_debug("     sdma queue id: %d\n", q->properties.sdma_queue_id);
 	pr_debug("     sdma engine id: %d\n", q->properties.sdma_engine_id);
 
+	init_sdma_vm(dqm, q, qpd);
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval != 0) {
@@ -646,7 +653,14 @@
 		return retval;
 	}
 
-	init_sdma_vm(dqm, q, qpd);
+	retval = mqd->load_mqd(mqd, q->mqd, 0,
+				0, NULL);
+	if (retval != 0) {
+		deallocate_sdma_queue(dqm, q->sdma_id);
+		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		return retval;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index d64f86c..488f51d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -163,6 +163,8 @@
 					struct qcm_process_device *qpd);
 int init_pipelines(struct device_queue_manager *dqm,
 		unsigned int pipes_num, unsigned int first_pipe);
+unsigned int get_first_pipe(struct device_queue_manager *dqm);
+unsigned int get_pipes_num(struct device_queue_manager *dqm);
 
 extern inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
@@ -175,10 +177,4 @@
 	return (pdd->lds_base >> 60) & 0x0E;
 }
 
-extern inline unsigned int get_pipes_num(struct device_queue_manager *dqm)
-{
-	BUG_ON(!dqm || !dqm->dev);
-	return dqm->dev->shared_resources.compute_pipe_count;
-}
-
 #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c
index 6b07246..5469efe 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c
@@ -131,5 +131,5 @@
 
 static int initialize_cpsch_cik(struct device_queue_manager *dqm)
 {
-	return init_pipelines(dqm, get_pipes_num(dqm), 0);
+	return init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm));
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index e415a2a..c7d298e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -44,7 +44,7 @@
 	BUG_ON(!kq || !dev);
 	BUG_ON(type != KFD_QUEUE_TYPE_DIQ && type != KFD_QUEUE_TYPE_HIQ);
 
-	pr_debug("kfd: In func %s initializing queue type %d size %d\n",
+	pr_debug("amdkfd: In func %s initializing queue type %d size %d\n",
 			__func__, KFD_QUEUE_TYPE_HIQ, queue_size);
 
 	nop.opcode = IT_NOP;
@@ -69,12 +69,16 @@
 
 	prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off);
 
-	if (prop.doorbell_ptr == NULL)
+	if (prop.doorbell_ptr == NULL) {
+		pr_err("amdkfd: error init doorbell");
 		goto err_get_kernel_doorbell;
+	}
 
 	retval = kfd_gtt_sa_allocate(dev, queue_size, &kq->pq);
-	if (retval != 0)
+	if (retval != 0) {
+		pr_err("amdkfd: error init pq queues size (%d)\n", queue_size);
 		goto err_pq_allocate_vidmem;
+	}
 
 	kq->pq_kernel_addr = kq->pq->cpu_ptr;
 	kq->pq_gpu_addr = kq->pq->gpu_addr;
@@ -165,10 +169,8 @@
 err_eop_allocate_vidmem:
 	kfd_gtt_sa_free(dev, kq->pq);
 err_pq_allocate_vidmem:
-	pr_err("kfd: error init pq\n");
 	kfd_release_kernel_doorbell(dev, prop.doorbell_ptr);
 err_get_kernel_doorbell:
-	pr_err("kfd: error init doorbell");
 	return false;
 
 }
@@ -187,6 +189,8 @@
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
 		kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj);
 
+	kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj);
+
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
 	kq->ops_asic_specific.uninitialize(kq);
@@ -211,7 +215,7 @@
 	queue_address = (unsigned int *)kq->pq_kernel_addr;
 	queue_size_dwords = kq->queue->properties.queue_size / sizeof(uint32_t);
 
-	pr_debug("kfd: In func %s\nrptr: %d\nwptr: %d\nqueue_address 0x%p\n",
+	pr_debug("amdkfd: In func %s\nrptr: %d\nwptr: %d\nqueue_address 0x%p\n",
 			__func__, rptr, wptr, queue_address);
 
 	available_size = (rptr - 1 - wptr + queue_size_dwords) %
@@ -296,7 +300,7 @@
 	}
 
 	if (kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE) == false) {
-		pr_err("kfd: failed to init kernel queue\n");
+		pr_err("amdkfd: failed to init kernel queue\n");
 		kfree(kq);
 		return NULL;
 	}
@@ -319,7 +323,7 @@
 
 	BUG_ON(!dev);
 
-	pr_err("kfd: starting kernel queue test\n");
+	pr_err("amdkfd: starting kernel queue test\n");
 
 	kq = kernel_queue_init(dev, KFD_QUEUE_TYPE_HIQ);
 	BUG_ON(!kq);
@@ -330,7 +334,7 @@
 		buffer[i] = kq->nop_packet;
 	kq->ops.submit_packet(kq);
 
-	pr_err("kfd: ending kernel queue test\n");
+	pr_err("amdkfd: ending kernel queue test\n");
 }
 
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index 0409b90..b3e3068 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -153,7 +153,7 @@
 		     (adj->crtc_hdisplay - 1) |
 		     ((adj->crtc_vdisplay - 1) << 16));
 
-	cfg = ATMEL_HLCDC_CLKPOL;
+	cfg = 0;
 
 	prate = clk_get_rate(crtc->dc->hlcdc->sys_clk);
 	mode_rate = mode->crtc_clock * 1000;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index 7320a6c..c1cb174 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -311,8 +311,6 @@
 
 	pm_runtime_enable(dev->dev);
 
-	pm_runtime_put_sync(dev->dev);
-
 	ret = atmel_hlcdc_dc_modeset_init(dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize mode setting\n");
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c
index 063d2a7..e79bd9b 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c
@@ -311,7 +311,8 @@
 
 	/* Disable the layer */
 	regmap_write(regmap, desc->regs_offset + ATMEL_HLCDC_LAYER_CHDR,
-		     ATMEL_HLCDC_LAYER_RST);
+		     ATMEL_HLCDC_LAYER_RST | ATMEL_HLCDC_LAYER_A2Q |
+		     ATMEL_HLCDC_LAYER_UPDATE);
 
 	/* Clear all pending interrupts */
 	regmap_read(regmap, desc->regs_offset + ATMEL_HLCDC_LAYER_ISR, &isr);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 6b00173..679b10e 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -43,9 +43,10 @@
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
 
-static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
-							struct drm_mode_fb_cmd2 *r,
-							struct drm_file *file_priv);
+static struct drm_framebuffer *
+internal_framebuffer_create(struct drm_device *dev,
+			    struct drm_mode_fb_cmd2 *r,
+			    struct drm_file *file_priv);
 
 /* Avoid boilerplate.  I'm tired of typing. */
 #define DRM_ENUM_NAME_FN(fnname, list)				\
@@ -524,17 +525,6 @@
 }
 EXPORT_SYMBOL(drm_framebuffer_reference);
 
-static void drm_framebuffer_free_bug(struct kref *kref)
-{
-	BUG();
-}
-
-static void __drm_framebuffer_unreference(struct drm_framebuffer *fb)
-{
-	DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
-	kref_put(&fb->refcount, drm_framebuffer_free_bug);
-}
-
 /**
  * drm_framebuffer_unregister_private - unregister a private fb from the lookup idr
  * @fb: fb to unregister
@@ -1319,7 +1309,7 @@
 		return;
 	}
 	/* disconnect the plane from the fb and crtc: */
-	__drm_framebuffer_unreference(plane->old_fb);
+	drm_framebuffer_unreference(plane->old_fb);
 	plane->old_fb = NULL;
 	plane->fb = NULL;
 	plane->crtc = NULL;
@@ -2127,7 +2117,6 @@
 	DRM_DEBUG_KMS("[CONNECTOR:%d:?]\n", out_resp->connector_id);
 
 	mutex_lock(&dev->mode_config.mutex);
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 
 	connector = drm_connector_find(dev, out_resp->connector_id);
 	if (!connector) {
@@ -2157,6 +2146,8 @@
 	out_resp->mm_height = connector->display_info.height_mm;
 	out_resp->subpixel = connector->display_info.subpixel_order;
 	out_resp->connection = connector->status;
+
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 	encoder = drm_connector_get_encoder(connector);
 	if (encoder)
 		out_resp->encoder_id = encoder->base.id;
@@ -2907,13 +2898,11 @@
 	 */
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (req->handle) {
-			fb = add_framebuffer_internal(dev, &fbreq, file_priv);
+			fb = internal_framebuffer_create(dev, &fbreq, file_priv);
 			if (IS_ERR(fb)) {
 				DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n");
 				return PTR_ERR(fb);
 			}
-
-			drm_framebuffer_reference(fb);
 		} else {
 			fb = NULL;
 		}
@@ -3266,9 +3255,10 @@
 	return 0;
 }
 
-static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
-							struct drm_mode_fb_cmd2 *r,
-							struct drm_file *file_priv)
+static struct drm_framebuffer *
+internal_framebuffer_create(struct drm_device *dev,
+			    struct drm_mode_fb_cmd2 *r,
+			    struct drm_file *file_priv)
 {
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_framebuffer *fb;
@@ -3300,12 +3290,6 @@
 		return fb;
 	}
 
-	mutex_lock(&file_priv->fbs_lock);
-	r->fb_id = fb->base.id;
-	list_add(&fb->filp_head, &file_priv->fbs);
-	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
-	mutex_unlock(&file_priv->fbs_lock);
-
 	return fb;
 }
 
@@ -3327,15 +3311,24 @@
 int drm_mode_addfb2(struct drm_device *dev,
 		    void *data, struct drm_file *file_priv)
 {
+	struct drm_mode_fb_cmd2 *r = data;
 	struct drm_framebuffer *fb;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	fb = add_framebuffer_internal(dev, data, file_priv);
+	fb = internal_framebuffer_create(dev, r, file_priv);
 	if (IS_ERR(fb))
 		return PTR_ERR(fb);
 
+	/* Transfer ownership to the filp for reaping on close */
+
+	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
+	mutex_lock(&file_priv->fbs_lock);
+	r->fb_id = fb->base.id;
+	list_add(&fb->filp_head, &file_priv->fbs);
+	mutex_unlock(&file_priv->fbs_lock);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 9a5b687..379ab45 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -733,10 +733,14 @@
 			      struct drm_dp_sideband_msg_tx *txmsg)
 {
 	bool ret;
-	mutex_lock(&mgr->qlock);
+
+	/*
+	 * All updates to txmsg->state are protected by mgr->qlock, and the two
+	 * cases we check here are terminal states. For those the barriers
+	 * provided by the wake_up/wait_event pair are enough.
+	 */
 	ret = (txmsg->state == DRM_DP_SIDEBAND_TX_RX ||
 	       txmsg->state == DRM_DP_SIDEBAND_TX_TIMEOUT);
-	mutex_unlock(&mgr->qlock);
 	return ret;
 }
 
@@ -1363,12 +1367,13 @@
 	return 0;
 }
 
-/* must be called holding qlock */
 static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr)
 {
 	struct drm_dp_sideband_msg_tx *txmsg;
 	int ret;
 
+	WARN_ON(!mutex_is_locked(&mgr->qlock));
+
 	/* construct a chunk from the first msg in the tx_msg queue */
 	if (list_empty(&mgr->tx_msg_downq)) {
 		mgr->tx_down_in_progress = false;
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 04a209e..1134526 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -91,29 +91,29 @@
  */
 
 static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
-						unsigned long size,
+						u64 size,
 						unsigned alignment,
 						unsigned long color,
 						enum drm_mm_search_flags flags);
 static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
-						unsigned long size,
+						u64 size,
 						unsigned alignment,
 						unsigned long color,
-						unsigned long start,
-						unsigned long end,
+						u64 start,
+						u64 end,
 						enum drm_mm_search_flags flags);
 
 static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 				 struct drm_mm_node *node,
-				 unsigned long size, unsigned alignment,
+				 u64 size, unsigned alignment,
 				 unsigned long color,
 				 enum drm_mm_allocator_flags flags)
 {
 	struct drm_mm *mm = hole_node->mm;
-	unsigned long hole_start = drm_mm_hole_node_start(hole_node);
-	unsigned long hole_end = drm_mm_hole_node_end(hole_node);
-	unsigned long adj_start = hole_start;
-	unsigned long adj_end = hole_end;
+	u64 hole_start = drm_mm_hole_node_start(hole_node);
+	u64 hole_end = drm_mm_hole_node_end(hole_node);
+	u64 adj_start = hole_start;
+	u64 adj_end = hole_end;
 
 	BUG_ON(node->allocated);
 
@@ -124,12 +124,15 @@
 		adj_start = adj_end - size;
 
 	if (alignment) {
-		unsigned tmp = adj_start % alignment;
-		if (tmp) {
+		u64 tmp = adj_start;
+		unsigned rem;
+
+		rem = do_div(tmp, alignment);
+		if (rem) {
 			if (flags & DRM_MM_CREATE_TOP)
-				adj_start -= tmp;
+				adj_start -= rem;
 			else
-				adj_start += alignment - tmp;
+				adj_start += alignment - rem;
 		}
 	}
 
@@ -176,9 +179,9 @@
 int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 {
 	struct drm_mm_node *hole;
-	unsigned long end = node->start + node->size;
-	unsigned long hole_start;
-	unsigned long hole_end;
+	u64 end = node->start + node->size;
+	u64 hole_start;
+	u64 hole_end;
 
 	BUG_ON(node == NULL);
 
@@ -227,7 +230,7 @@
  * 0 on success, -ENOSPC if there's no suitable hole.
  */
 int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
-			       unsigned long size, unsigned alignment,
+			       u64 size, unsigned alignment,
 			       unsigned long color,
 			       enum drm_mm_search_flags sflags,
 			       enum drm_mm_allocator_flags aflags)
@@ -246,16 +249,16 @@
 
 static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 				       struct drm_mm_node *node,
-				       unsigned long size, unsigned alignment,
+				       u64 size, unsigned alignment,
 				       unsigned long color,
-				       unsigned long start, unsigned long end,
+				       u64 start, u64 end,
 				       enum drm_mm_allocator_flags flags)
 {
 	struct drm_mm *mm = hole_node->mm;
-	unsigned long hole_start = drm_mm_hole_node_start(hole_node);
-	unsigned long hole_end = drm_mm_hole_node_end(hole_node);
-	unsigned long adj_start = hole_start;
-	unsigned long adj_end = hole_end;
+	u64 hole_start = drm_mm_hole_node_start(hole_node);
+	u64 hole_end = drm_mm_hole_node_end(hole_node);
+	u64 adj_start = hole_start;
+	u64 adj_end = hole_end;
 
 	BUG_ON(!hole_node->hole_follows || node->allocated);
 
@@ -271,12 +274,15 @@
 		mm->color_adjust(hole_node, color, &adj_start, &adj_end);
 
 	if (alignment) {
-		unsigned tmp = adj_start % alignment;
-		if (tmp) {
+		u64 tmp = adj_start;
+		unsigned rem;
+
+		rem = do_div(tmp, alignment);
+		if (rem) {
 			if (flags & DRM_MM_CREATE_TOP)
-				adj_start -= tmp;
+				adj_start -= rem;
 			else
-				adj_start += alignment - tmp;
+				adj_start += alignment - rem;
 		}
 	}
 
@@ -324,9 +330,9 @@
  * 0 on success, -ENOSPC if there's no suitable hole.
  */
 int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node,
-					unsigned long size, unsigned alignment,
+					u64 size, unsigned alignment,
 					unsigned long color,
-					unsigned long start, unsigned long end,
+					u64 start, u64 end,
 					enum drm_mm_search_flags sflags,
 					enum drm_mm_allocator_flags aflags)
 {
@@ -387,32 +393,34 @@
 }
 EXPORT_SYMBOL(drm_mm_remove_node);
 
-static int check_free_hole(unsigned long start, unsigned long end,
-			   unsigned long size, unsigned alignment)
+static int check_free_hole(u64 start, u64 end, u64 size, unsigned alignment)
 {
 	if (end - start < size)
 		return 0;
 
 	if (alignment) {
-		unsigned tmp = start % alignment;
-		if (tmp)
-			start += alignment - tmp;
+		u64 tmp = start;
+		unsigned rem;
+
+		rem = do_div(tmp, alignment);
+		if (rem)
+			start += alignment - rem;
 	}
 
 	return end >= start + size;
 }
 
 static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
-						      unsigned long size,
+						      u64 size,
 						      unsigned alignment,
 						      unsigned long color,
 						      enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *entry;
 	struct drm_mm_node *best;
-	unsigned long adj_start;
-	unsigned long adj_end;
-	unsigned long best_size;
+	u64 adj_start;
+	u64 adj_end;
+	u64 best_size;
 
 	BUG_ON(mm->scanned_blocks);
 
@@ -421,7 +429,7 @@
 
 	__drm_mm_for_each_hole(entry, mm, adj_start, adj_end,
 			       flags & DRM_MM_SEARCH_BELOW) {
-		unsigned long hole_size = adj_end - adj_start;
+		u64 hole_size = adj_end - adj_start;
 
 		if (mm->color_adjust) {
 			mm->color_adjust(entry, color, &adj_start, &adj_end);
@@ -445,18 +453,18 @@
 }
 
 static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
-							unsigned long size,
+							u64 size,
 							unsigned alignment,
 							unsigned long color,
-							unsigned long start,
-							unsigned long end,
+							u64 start,
+							u64 end,
 							enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *entry;
 	struct drm_mm_node *best;
-	unsigned long adj_start;
-	unsigned long adj_end;
-	unsigned long best_size;
+	u64 adj_start;
+	u64 adj_end;
+	u64 best_size;
 
 	BUG_ON(mm->scanned_blocks);
 
@@ -465,7 +473,7 @@
 
 	__drm_mm_for_each_hole(entry, mm, adj_start, adj_end,
 			       flags & DRM_MM_SEARCH_BELOW) {
-		unsigned long hole_size = adj_end - adj_start;
+		u64 hole_size = adj_end - adj_start;
 
 		if (adj_start < start)
 			adj_start = start;
@@ -561,7 +569,7 @@
  * adding/removing nodes to/from the scan list are allowed.
  */
 void drm_mm_init_scan(struct drm_mm *mm,
-		      unsigned long size,
+		      u64 size,
 		      unsigned alignment,
 		      unsigned long color)
 {
@@ -594,11 +602,11 @@
  * adding/removing nodes to/from the scan list are allowed.
  */
 void drm_mm_init_scan_with_range(struct drm_mm *mm,
-				 unsigned long size,
+				 u64 size,
 				 unsigned alignment,
 				 unsigned long color,
-				 unsigned long start,
-				 unsigned long end)
+				 u64 start,
+				 u64 end)
 {
 	mm->scan_color = color;
 	mm->scan_alignment = alignment;
@@ -627,8 +635,8 @@
 {
 	struct drm_mm *mm = node->mm;
 	struct drm_mm_node *prev_node;
-	unsigned long hole_start, hole_end;
-	unsigned long adj_start, adj_end;
+	u64 hole_start, hole_end;
+	u64 adj_start, adj_end;
 
 	mm->scanned_blocks++;
 
@@ -731,7 +739,7 @@
  *
  * Note that @mm must be cleared to 0 before calling this function.
  */
-void drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size)
+void drm_mm_init(struct drm_mm * mm, u64 start, u64 size)
 {
 	INIT_LIST_HEAD(&mm->hole_stack);
 	mm->scanned_blocks = 0;
@@ -766,18 +774,17 @@
 }
 EXPORT_SYMBOL(drm_mm_takedown);
 
-static unsigned long drm_mm_debug_hole(struct drm_mm_node *entry,
-				       const char *prefix)
+static u64 drm_mm_debug_hole(struct drm_mm_node *entry,
+				     const char *prefix)
 {
-	unsigned long hole_start, hole_end, hole_size;
+	u64 hole_start, hole_end, hole_size;
 
 	if (entry->hole_follows) {
 		hole_start = drm_mm_hole_node_start(entry);
 		hole_end = drm_mm_hole_node_end(entry);
 		hole_size = hole_end - hole_start;
-		printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: free\n",
-			prefix, hole_start, hole_end,
-			hole_size);
+		pr_debug("%s %#llx-%#llx: %llu: free\n", prefix, hole_start,
+			 hole_end, hole_size);
 		return hole_size;
 	}
 
@@ -792,35 +799,34 @@
 void drm_mm_debug_table(struct drm_mm *mm, const char *prefix)
 {
 	struct drm_mm_node *entry;
-	unsigned long total_used = 0, total_free = 0, total = 0;
+	u64 total_used = 0, total_free = 0, total = 0;
 
 	total_free += drm_mm_debug_hole(&mm->head_node, prefix);
 
 	drm_mm_for_each_node(entry, mm) {
-		printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: used\n",
-			prefix, entry->start, entry->start + entry->size,
-			entry->size);
+		pr_debug("%s %#llx-%#llx: %llu: used\n", prefix, entry->start,
+			 entry->start + entry->size, entry->size);
 		total_used += entry->size;
 		total_free += drm_mm_debug_hole(entry, prefix);
 	}
 	total = total_free + total_used;
 
-	printk(KERN_DEBUG "%s total: %lu, used %lu free %lu\n", prefix, total,
-		total_used, total_free);
+	pr_debug("%s total: %llu, used %llu free %llu\n", prefix, total,
+		 total_used, total_free);
 }
 EXPORT_SYMBOL(drm_mm_debug_table);
 
 #if defined(CONFIG_DEBUG_FS)
-static unsigned long drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry)
+static u64 drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry)
 {
-	unsigned long hole_start, hole_end, hole_size;
+	u64 hole_start, hole_end, hole_size;
 
 	if (entry->hole_follows) {
 		hole_start = drm_mm_hole_node_start(entry);
 		hole_end = drm_mm_hole_node_end(entry);
 		hole_size = hole_end - hole_start;
-		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
-				hole_start, hole_end, hole_size);
+		seq_printf(m, "%#llx-%#llx: %llu: free\n", hole_start,
+			   hole_end, hole_size);
 		return hole_size;
 	}
 
@@ -835,20 +841,20 @@
 int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm)
 {
 	struct drm_mm_node *entry;
-	unsigned long total_used = 0, total_free = 0, total = 0;
+	u64 total_used = 0, total_free = 0, total = 0;
 
 	total_free += drm_mm_dump_hole(m, &mm->head_node);
 
 	drm_mm_for_each_node(entry, mm) {
-		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: used\n",
-				entry->start, entry->start + entry->size,
-				entry->size);
+		seq_printf(m, "%#016llx-%#016llx: %llu: used\n", entry->start,
+			   entry->start + entry->size, entry->size);
 		total_used += entry->size;
 		total_free += drm_mm_dump_hole(m, entry);
 	}
 	total = total_free + total_used;
 
-	seq_printf(m, "total: %lu, used %lu free %lu\n", total, total_used, total_free);
+	seq_printf(m, "total: %llu, used %llu free %llu\n", total,
+		   total_used, total_free);
 	return 0;
 }
 EXPORT_SYMBOL(drm_mm_dump_table);
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index a5e7461..0a67803 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -50,7 +50,7 @@
 
 config DRM_EXYNOS_DP
 	bool "EXYNOS DRM DP driver support"
-	depends on (DRM_EXYNOS_FIMD || DRM_EXYNOS7DECON) && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS)
+	depends on (DRM_EXYNOS_FIMD || DRM_EXYNOS7_DECON) && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS)
 	default DRM_EXYNOS
 	select DRM_PANEL
 	help
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 63f02e2..9700461 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -888,8 +888,8 @@
 	of_node_put(i80_if_timings);
 
 	ctx->regs = of_iomap(dev->of_node, 0);
-	if (IS_ERR(ctx->regs)) {
-		ret = PTR_ERR(ctx->regs);
+	if (!ctx->regs) {
+		ret = -ENOMEM;
 		goto err_del_component;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
deleted file mode 100644
index ba9b3d5..0000000
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ /dev/null
@@ -1,245 +0,0 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Authors:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <drm/drmP.h>
-#include <drm/drm_crtc_helper.h>
-
-#include <drm/exynos_drm.h>
-#include "exynos_drm_drv.h"
-#include "exynos_drm_encoder.h"
-#include "exynos_drm_connector.h"
-
-#define to_exynos_connector(x)	container_of(x, struct exynos_drm_connector,\
-				drm_connector)
-
-struct exynos_drm_connector {
-	struct drm_connector		drm_connector;
-	uint32_t			encoder_id;
-	struct exynos_drm_display	*display;
-};
-
-static int exynos_drm_connector_get_modes(struct drm_connector *connector)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	struct edid *edid = NULL;
-	unsigned int count = 0;
-	int ret;
-
-	/*
-	 * if get_edid() exists then get_edid() callback of hdmi side
-	 * is called to get edid data through i2c interface else
-	 * get timing from the FIMD driver(display controller).
-	 *
-	 * P.S. in case of lcd panel, count is always 1 if success
-	 * because lcd panel has only one mode.
-	 */
-	if (display->ops->get_edid) {
-		edid = display->ops->get_edid(display, connector);
-		if (IS_ERR_OR_NULL(edid)) {
-			ret = PTR_ERR(edid);
-			edid = NULL;
-			DRM_ERROR("Panel operation get_edid failed %d\n", ret);
-			goto out;
-		}
-
-		count = drm_add_edid_modes(connector, edid);
-		if (!count) {
-			DRM_ERROR("Add edid modes failed %d\n", count);
-			goto out;
-		}
-
-		drm_mode_connector_update_edid_property(connector, edid);
-	} else {
-		struct exynos_drm_panel_info *panel;
-		struct drm_display_mode *mode = drm_mode_create(connector->dev);
-		if (!mode) {
-			DRM_ERROR("failed to create a new display mode.\n");
-			return 0;
-		}
-
-		if (display->ops->get_panel)
-			panel = display->ops->get_panel(display);
-		else {
-			drm_mode_destroy(connector->dev, mode);
-			return 0;
-		}
-
-		drm_display_mode_from_videomode(&panel->vm, mode);
-		mode->width_mm = panel->width_mm;
-		mode->height_mm = panel->height_mm;
-		connector->display_info.width_mm = mode->width_mm;
-		connector->display_info.height_mm = mode->height_mm;
-
-		mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-		drm_mode_set_name(mode);
-		drm_mode_probed_add(connector, mode);
-
-		count = 1;
-	}
-
-out:
-	kfree(edid);
-	return count;
-}
-
-static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	int ret = MODE_BAD;
-
-	DRM_DEBUG_KMS("%s\n", __FILE__);
-
-	if (display->ops->check_mode)
-		if (!display->ops->check_mode(display, mode))
-			ret = MODE_OK;
-
-	return ret;
-}
-
-static struct drm_encoder *exynos_drm_best_encoder(
-		struct drm_connector *connector)
-{
-	struct drm_device *dev = connector->dev;
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	return drm_encoder_find(dev, exynos_connector->encoder_id);
-}
-
-static struct drm_connector_helper_funcs exynos_connector_helper_funcs = {
-	.get_modes	= exynos_drm_connector_get_modes,
-	.mode_valid	= exynos_drm_connector_mode_valid,
-	.best_encoder	= exynos_drm_best_encoder,
-};
-
-static int exynos_drm_connector_fill_modes(struct drm_connector *connector,
-				unsigned int max_width, unsigned int max_height)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	unsigned int width, height;
-
-	width = max_width;
-	height = max_height;
-
-	/*
-	 * if specific driver want to find desired_mode using maxmum
-	 * resolution then get max width and height from that driver.
-	 */
-	if (display->ops->get_max_resol)
-		display->ops->get_max_resol(display, &width, &height);
-
-	return drm_helper_probe_single_connector_modes(connector, width,
-							height);
-}
-
-/* get detection status of display device. */
-static enum drm_connector_status
-exynos_drm_connector_detect(struct drm_connector *connector, bool force)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	enum drm_connector_status status = connector_status_disconnected;
-
-	if (display->ops->is_connected) {
-		if (display->ops->is_connected(display))
-			status = connector_status_connected;
-		else
-			status = connector_status_disconnected;
-	}
-
-	return status;
-}
-
-static void exynos_drm_connector_destroy(struct drm_connector *connector)
-{
-	struct exynos_drm_connector *exynos_connector =
-		to_exynos_connector(connector);
-
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(exynos_connector);
-}
-
-static struct drm_connector_funcs exynos_connector_funcs = {
-	.dpms		= drm_helper_connector_dpms,
-	.fill_modes	= exynos_drm_connector_fill_modes,
-	.detect		= exynos_drm_connector_detect,
-	.destroy	= exynos_drm_connector_destroy,
-};
-
-struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
-						   struct drm_encoder *encoder)
-{
-	struct exynos_drm_connector *exynos_connector;
-	struct exynos_drm_display *display = exynos_drm_get_display(encoder);
-	struct drm_connector *connector;
-	int type;
-	int err;
-
-	exynos_connector = kzalloc(sizeof(*exynos_connector), GFP_KERNEL);
-	if (!exynos_connector)
-		return NULL;
-
-	connector = &exynos_connector->drm_connector;
-
-	switch (display->type) {
-	case EXYNOS_DISPLAY_TYPE_HDMI:
-		type = DRM_MODE_CONNECTOR_HDMIA;
-		connector->interlace_allowed = true;
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
-		break;
-	case EXYNOS_DISPLAY_TYPE_VIDI:
-		type = DRM_MODE_CONNECTOR_VIRTUAL;
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
-		break;
-	default:
-		type = DRM_MODE_CONNECTOR_Unknown;
-		break;
-	}
-
-	drm_connector_init(dev, connector, &exynos_connector_funcs, type);
-	drm_connector_helper_add(connector, &exynos_connector_helper_funcs);
-
-	err = drm_connector_register(connector);
-	if (err)
-		goto err_connector;
-
-	exynos_connector->encoder_id = encoder->base.id;
-	exynos_connector->display = display;
-	connector->dpms = DRM_MODE_DPMS_OFF;
-	connector->encoder = encoder;
-
-	err = drm_mode_connector_attach_encoder(connector, encoder);
-	if (err) {
-		DRM_ERROR("failed to attach a connector to a encoder\n");
-		goto err_sysfs;
-	}
-
-	DRM_DEBUG_KMS("connector has been created\n");
-
-	return connector;
-
-err_sysfs:
-	drm_connector_unregister(connector);
-err_connector:
-	drm_connector_cleanup(connector);
-	kfree(exynos_connector);
-	return NULL;
-}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.h b/drivers/gpu/drm/exynos/exynos_drm_connector.h
deleted file mode 100644
index 4eb20d7..0000000
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Authors:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_DRM_CONNECTOR_H_
-#define _EXYNOS_DRM_CONNECTOR_H_
-
-struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
-						   struct drm_encoder *encoder);
-
-#endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 925fc69..c300e22 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -284,14 +284,9 @@
 	}
 }
 
-static int fimd_ctx_initialize(struct fimd_context *ctx,
+static int fimd_iommu_attach_devices(struct fimd_context *ctx,
 			struct drm_device *drm_dev)
 {
-	struct exynos_drm_private *priv;
-	priv = drm_dev->dev_private;
-
-	ctx->drm_dev = drm_dev;
-	ctx->pipe = priv->pipe++;
 
 	/* attach this sub driver to iommu mapping if supported. */
 	if (is_drm_iommu_supported(ctx->drm_dev)) {
@@ -313,7 +308,7 @@
 	return 0;
 }
 
-static void fimd_ctx_remove(struct fimd_context *ctx)
+static void fimd_iommu_detach_devices(struct fimd_context *ctx)
 {
 	/* detach this sub driver from iommu mapping if supported. */
 	if (is_drm_iommu_supported(ctx->drm_dev))
@@ -1056,25 +1051,23 @@
 {
 	struct fimd_context *ctx = dev_get_drvdata(dev);
 	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
 	int ret;
 
-	ret = fimd_ctx_initialize(ctx, drm_dev);
-	if (ret) {
-		DRM_ERROR("fimd_ctx_initialize failed.\n");
-		return ret;
-	}
+	ctx->drm_dev = drm_dev;
+	ctx->pipe = priv->pipe++;
 
 	ctx->crtc = exynos_drm_crtc_create(drm_dev, ctx->pipe,
 					   EXYNOS_DISPLAY_TYPE_LCD,
 					   &fimd_crtc_ops, ctx);
-	if (IS_ERR(ctx->crtc)) {
-		fimd_ctx_remove(ctx);
-		return PTR_ERR(ctx->crtc);
-	}
 
 	if (ctx->display)
 		exynos_drm_create_enc_conn(drm_dev, ctx->display);
 
+	ret = fimd_iommu_attach_devices(ctx, drm_dev);
+	if (ret)
+		return ret;
+
 	return 0;
 
 }
@@ -1086,10 +1079,10 @@
 
 	fimd_dpms(ctx->crtc, DRM_MODE_DPMS_OFF);
 
+	fimd_iommu_detach_devices(ctx);
+
 	if (ctx->display)
 		exynos_dpi_remove(ctx->display);
-
-	fimd_ctx_remove(ctx);
 }
 
 static const struct component_ops fimd_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index a561687..8ad5b72 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -175,7 +175,7 @@
 	struct exynos_drm_plane *exynos_plane = to_exynos_plane(plane);
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(plane->crtc);
 
-	if (exynos_crtc->ops->win_disable)
+	if (exynos_crtc && exynos_crtc->ops->win_disable)
 		exynos_crtc->ops->win_disable(exynos_crtc,
 					      exynos_plane->zpos);
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 96e811f..e8b18e5 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -152,12 +152,12 @@
 			seq_puts(m, " (pp");
 		else
 			seq_puts(m, " (g");
-		seq_printf(m, "gtt offset: %08lx, size: %08lx, type: %u)",
+		seq_printf(m, "gtt offset: %08llx, size: %08llx, type: %u)",
 			   vma->node.start, vma->node.size,
 			   vma->ggtt_view.type);
 	}
 	if (obj->stolen)
-		seq_printf(m, " (stolen: %08lx)", obj->stolen->start);
+		seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
 	if (obj->pin_mappable || obj->fault_mappable) {
 		char s[3], *t = s;
 		if (obj->pin_mappable)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 8039cec..cc6ea53 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -622,7 +622,7 @@
 	return 0;
 }
 
-static int i915_drm_suspend_late(struct drm_device *drm_dev)
+static int i915_drm_suspend_late(struct drm_device *drm_dev, bool hibernation)
 {
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	int ret;
@@ -636,7 +636,17 @@
 	}
 
 	pci_disable_device(drm_dev->pdev);
-	pci_set_power_state(drm_dev->pdev, PCI_D3hot);
+	/*
+	 * During hibernation on some GEN4 platforms the BIOS may try to access
+	 * the device even though it's already in D3 and hang the machine. So
+	 * leave the device in D0 on those platforms and hope the BIOS will
+	 * power down the device properly. Platforms where this was seen:
+	 * Lenovo Thinkpad X301, X61s
+	 */
+	if (!(hibernation &&
+	      drm_dev->pdev->subsystem_vendor == PCI_VENDOR_ID_LENOVO &&
+	      INTEL_INFO(dev_priv)->gen == 4))
+		pci_set_power_state(drm_dev->pdev, PCI_D3hot);
 
 	return 0;
 }
@@ -662,7 +672,7 @@
 	if (error)
 		return error;
 
-	return i915_drm_suspend_late(dev);
+	return i915_drm_suspend_late(dev, false);
 }
 
 static int i915_drm_resume(struct drm_device *dev)
@@ -950,7 +960,17 @@
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	return i915_drm_suspend_late(drm_dev);
+	return i915_drm_suspend_late(drm_dev, false);
+}
+
+static int i915_pm_poweroff_late(struct device *dev)
+{
+	struct drm_device *drm_dev = dev_to_i915(dev)->dev;
+
+	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+		return 0;
+
+	return i915_drm_suspend_late(drm_dev, true);
 }
 
 static int i915_pm_resume_early(struct device *dev)
@@ -1520,7 +1540,7 @@
 	.thaw_early = i915_pm_resume_early,
 	.thaw = i915_pm_resume,
 	.poweroff = i915_pm_suspend,
-	.poweroff_late = i915_pm_suspend_late,
+	.poweroff_late = i915_pm_poweroff_late,
 	.restore_early = i915_pm_resume_early,
 	.restore = i915_pm_resume,
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f2a825e..8727086 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2114,6 +2114,9 @@
  * number comparisons on buffer last_read|write_seqno. It also allows an
  * emission time to be associated with the request for tracking how far ahead
  * of the GPU the submission is.
+ *
+ * The requests are reference counted, so upon creation they should have an
+ * initial reference taken using kref_init
  */
 struct drm_i915_gem_request {
 	struct kref ref;
@@ -2137,7 +2140,16 @@
 	/** Position in the ringbuffer of the end of the whole request */
 	u32 tail;
 
-	/** Context related to this request */
+	/**
+	 * Context related to this request
+	 * Contexts are refcounted, so when this request is associated with a
+	 * context, we must increment the context's refcount, to guarantee that
+	 * it persists while any request is linked to it. Requests themselves
+	 * are also refcounted, so the request will only be freed when the last
+	 * reference to it is dismissed, and the code in
+	 * i915_gem_request_free() will then decrement the refcount on the
+	 * context.
+	 */
 	struct intel_context *ctx;
 
 	/** Batch buffer related to this request if any */
@@ -2374,6 +2386,7 @@
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
 				 ((INTEL_DEVID(dev) & 0xf) == 0x6 ||	\
+				 (INTEL_DEVID(dev) & 0xf) == 0xb ||	\
 				 (INTEL_DEVID(dev) & 0xf) == 0xe))
 #define IS_BDW_GT3(dev)		(IS_BROADWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0x00F0) == 0x0020)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c26d36c..27ea6bd 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2659,8 +2659,7 @@
 		if (submit_req->ctx != ring->default_context)
 			intel_lr_context_unpin(ring, submit_req->ctx);
 
-		i915_gem_context_unreference(submit_req->ctx);
-		kfree(submit_req);
+		i915_gem_request_unreference(submit_req);
 	}
 
 	/*
@@ -2738,24 +2737,11 @@
 
 	WARN_ON(i915_verify_lists(ring->dev));
 
-	/* Move any buffers on the active list that are no longer referenced
-	 * by the ringbuffer to the flushing/inactive lists as appropriate,
-	 * before we free the context associated with the requests.
+	/* Retire requests first as we use it above for the early return.
+	 * If we retire requests last, we may use a later seqno and so clear
+	 * the requests lists without clearing the active list, leading to
+	 * confusion.
 	 */
-	while (!list_empty(&ring->active_list)) {
-		struct drm_i915_gem_object *obj;
-
-		obj = list_first_entry(&ring->active_list,
-				      struct drm_i915_gem_object,
-				      ring_list);
-
-		if (!i915_gem_request_completed(obj->last_read_req, true))
-			break;
-
-		i915_gem_object_move_to_inactive(obj);
-	}
-
-
 	while (!list_empty(&ring->request_list)) {
 		struct drm_i915_gem_request *request;
 		struct intel_ringbuffer *ringbuf;
@@ -2790,6 +2776,23 @@
 		i915_gem_free_request(request);
 	}
 
+	/* Move any buffers on the active list that are no longer referenced
+	 * by the ringbuffer to the flushing/inactive lists as appropriate,
+	 * before we free the context associated with the requests.
+	 */
+	while (!list_empty(&ring->active_list)) {
+		struct drm_i915_gem_object *obj;
+
+		obj = list_first_entry(&ring->active_list,
+				      struct drm_i915_gem_object,
+				      ring_list);
+
+		if (!i915_gem_request_completed(obj->last_read_req, true))
+			break;
+
+		i915_gem_object_move_to_inactive(obj);
+	}
+
 	if (unlikely(ring->trace_irq_req &&
 		     i915_gem_request_completed(ring->trace_irq_req, true))) {
 		ring->irq_put(ring);
@@ -2937,9 +2940,9 @@
 	req = obj->last_read_req;
 
 	/* Do this after OLR check to make sure we make forward progress polling
-	 * on this IOCTL with a timeout <=0 (like busy ioctl)
+	 * on this IOCTL with a timeout == 0 (like busy ioctl)
 	 */
-	if (args->timeout_ns <= 0) {
+	if (args->timeout_ns == 0) {
 		ret = -ETIME;
 		goto out;
 	}
@@ -2949,7 +2952,8 @@
 	i915_gem_request_reference(req);
 	mutex_unlock(&dev->struct_mutex);
 
-	ret = __i915_wait_request(req, reset_counter, true, &args->timeout_ns,
+	ret = __i915_wait_request(req, reset_counter, true,
+				  args->timeout_ns > 0 ? &args->timeout_ns : NULL,
 				  file->driver_priv);
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_request_unreference(req);
@@ -4793,6 +4797,9 @@
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
 
+	/* Double layer security blanket, see i915_gem_init() */
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
 	if (dev_priv->ellc_size)
 		I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf));
 
@@ -4825,7 +4832,7 @@
 	for_each_ring(ring, dev_priv, i) {
 		ret = ring->init_hw(ring);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	for (i = 0; i < NUM_L3_SLICES(dev); i++)
@@ -4842,9 +4849,11 @@
 		DRM_ERROR("Context enable failed %d\n", ret);
 		i915_gem_cleanup_ringbuffer(dev);
 
-		return ret;
+		goto out;
 	}
 
+out:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	return ret;
 }
 
@@ -4878,6 +4887,14 @@
 		dev_priv->gt.stop_ring = intel_logical_ring_stop;
 	}
 
+	/* This is just a security blanket to placate dragons.
+	 * On some systems, we very sporadically observe that the first TLBs
+	 * used by the CS may be stale, despite us poking the TLB reset. If
+	 * we hold the forcewake during initialisation these problems
+	 * just magically go away.
+	 */
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
 	ret = i915_gem_init_userptr(dev);
 	if (ret)
 		goto out_unlock;
@@ -4904,6 +4921,7 @@
 	}
 
 out_unlock:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 746f77f..dccdc8a 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1145,7 +1145,7 @@
 
 	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
 
-	DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n",
+	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
 
@@ -1713,8 +1713,8 @@
 
 static void i915_gtt_color_adjust(struct drm_mm_node *node,
 				  unsigned long color,
-				  unsigned long *start,
-				  unsigned long *end)
+				  u64 *start,
+				  u64 *end)
 {
 	if (node->color != color)
 		*start += 4096;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index a204584..9c6f93e 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -485,10 +485,8 @@
 			stolen_offset, gtt_offset, size);
 
 	/* KISS and expect everything to be page-aligned */
-	BUG_ON(stolen_offset & 4095);
-	BUG_ON(size & 4095);
-
-	if (WARN_ON(size == 0))
+	if (WARN_ON(size == 0) || WARN_ON(size & 4095) ||
+	    WARN_ON(stolen_offset & 4095))
 		return NULL;
 
 	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 7a24bd1..6377b22 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -335,9 +335,10 @@
 		return -EINVAL;
 	}
 
+	mutex_lock(&dev->struct_mutex);
 	if (i915_gem_obj_is_pinned(obj) || obj->framebuffer_references) {
-		drm_gem_object_unreference_unlocked(&obj->base);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto err;
 	}
 
 	if (args->tiling_mode == I915_TILING_NONE) {
@@ -369,7 +370,6 @@
 		}
 	}
 
-	mutex_lock(&dev->struct_mutex);
 	if (args->tiling_mode != obj->tiling_mode ||
 	    args->stride != obj->stride) {
 		/* We need to rebind the object if its current allocation
@@ -424,6 +424,7 @@
 		obj->bit_17 = NULL;
 	}
 
+err:
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4145d95..ede5bbb 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1892,6 +1892,9 @@
 	u32 iir, gt_iir, pm_iir;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	while (true) {
 		/* Find, clear, then process each source of interrupt */
 
@@ -1936,6 +1939,9 @@
 	u32 master_ctl, iir;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	for (;;) {
 		master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL;
 		iir = I915_READ(VLV_IIR);
@@ -2208,6 +2214,9 @@
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	/* We get interrupts on unclaimed registers, so check for this before we
 	 * do any I915_{READ,WRITE}. */
 	intel_uncore_check_errors(dev);
@@ -2279,6 +2288,9 @@
 	enum pipe pipe;
 	u32 aux_mask = GEN8_AUX_CHANNEL_A;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	if (IS_GEN9(dev))
 		aux_mask |=  GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
 			GEN9_AUX_CHANNEL_D;
@@ -3771,6 +3783,9 @@
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ16(IIR);
 	if (iir == 0)
 		return IRQ_NONE;
@@ -3951,6 +3966,9 @@
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 	int pipe, ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ(IIR);
 	do {
 		bool irq_received = (iir & ~flip_mask) != 0;
@@ -4171,6 +4189,9 @@
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ(IIR);
 
 	for (;;) {
@@ -4520,6 +4541,7 @@
 {
 	dev_priv->dev->driver->irq_uninstall(dev_priv->dev);
 	dev_priv->pm.irqs_enabled = false;
+	synchronize_irq(dev_priv->dev->irq);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3d220a6..f75173c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -37,6 +37,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_crtc_helper.h>
@@ -2371,13 +2372,19 @@
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_gem_object *obj = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
-	u32 base = plane_config->base;
+	u32 base_aligned = round_down(plane_config->base, PAGE_SIZE);
+	u32 size_aligned = round_up(plane_config->base + plane_config->size,
+				    PAGE_SIZE);
+
+	size_aligned -= base_aligned;
 
 	if (plane_config->size == 0)
 		return false;
 
-	obj = i915_gem_object_create_stolen_for_preallocated(dev, base, base,
-							     plane_config->size);
+	obj = i915_gem_object_create_stolen_for_preallocated(dev,
+							     base_aligned,
+							     base_aligned,
+							     size_aligned);
 	if (!obj)
 		return false;
 
@@ -2410,6 +2417,14 @@
 	return false;
 }
 
+/* Update plane->state->fb to match plane->fb after driver-internal updates */
+static void
+update_state_fb(struct drm_plane *plane)
+{
+	if (plane->fb != plane->state->fb)
+		drm_atomic_set_fb_for_plane(plane->state, plane->fb);
+}
+
 static void
 intel_find_plane_obj(struct intel_crtc *intel_crtc,
 		     struct intel_initial_plane_config *plane_config)
@@ -2423,8 +2438,15 @@
 	if (!intel_crtc->base.primary->fb)
 		return;
 
-	if (intel_alloc_plane_obj(intel_crtc, plane_config))
+	if (intel_alloc_plane_obj(intel_crtc, plane_config)) {
+		struct drm_plane *primary = intel_crtc->base.primary;
+
+		primary->state->crtc = &intel_crtc->base;
+		primary->crtc = &intel_crtc->base;
+		update_state_fb(primary);
+
 		return;
+	}
 
 	kfree(intel_crtc->base.primary->fb);
 	intel_crtc->base.primary->fb = NULL;
@@ -2447,15 +2469,21 @@
 			continue;
 
 		if (i915_gem_obj_ggtt_offset(obj) == plane_config->base) {
+			struct drm_plane *primary = intel_crtc->base.primary;
+
 			if (obj->tiling_mode != I915_TILING_NONE)
 				dev_priv->preserve_bios_swizzle = true;
 
 			drm_framebuffer_reference(c->primary->fb);
-			intel_crtc->base.primary->fb = c->primary->fb;
+			primary->fb = c->primary->fb;
+			primary->state->crtc = &intel_crtc->base;
+			primary->crtc = &intel_crtc->base;
 			obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
 			break;
 		}
 	}
+
+	update_state_fb(intel_crtc->base.primary);
 }
 
 static void i9xx_update_primary_plane(struct drm_crtc *crtc,
@@ -2725,10 +2753,19 @@
 	case DRM_FORMAT_XRGB8888:
 		plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888;
 		break;
+	case DRM_FORMAT_ARGB8888:
+		plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888;
+		plane_ctl |= PLANE_CTL_ALPHA_SW_PREMULTIPLY;
+		break;
 	case DRM_FORMAT_XBGR8888:
 		plane_ctl |= PLANE_CTL_ORDER_RGBX;
 		plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888;
 		break;
+	case DRM_FORMAT_ABGR8888:
+		plane_ctl |= PLANE_CTL_ORDER_RGBX;
+		plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888;
+		plane_ctl |= PLANE_CTL_ALPHA_SW_PREMULTIPLY;
+		break;
 	case DRM_FORMAT_XRGB2101010:
 		plane_ctl |= PLANE_CTL_FORMAT_XRGB_2101010;
 		break;
@@ -6587,6 +6624,10 @@
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
+	val = I915_READ(DSPCNTR(plane));
+	if (!(val & DISPLAY_PLANE_ENABLE))
+		return;
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -6595,8 +6636,6 @@
 
 	fb = &intel_fb->base;
 
-	val = I915_READ(DSPCNTR(plane));
-
 	if (INTEL_INFO(dev)->gen >= 4)
 		if (val & DISPPLANE_TILED)
 			plane_config->tiling = I915_TILING_X;
@@ -6627,7 +6666,7 @@
 	aligned_height = intel_fb_align_height(dev, fb->height,
 					       plane_config->tiling);
 
-	plane_config->size = PAGE_ALIGN(fb->pitches[0] * aligned_height);
+	plane_config->size = fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe/plane %c/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe_name(pipe), plane, fb->width, fb->height,
@@ -7628,6 +7667,9 @@
 	fb = &intel_fb->base;
 
 	val = I915_READ(PLANE_CTL(pipe, 0));
+	if (!(val & PLANE_CTL_ENABLE))
+		goto error;
+
 	if (val & PLANE_CTL_TILED_MASK)
 		plane_config->tiling = I915_TILING_X;
 
@@ -7664,7 +7706,7 @@
 	aligned_height = intel_fb_align_height(dev, fb->height,
 					       plane_config->tiling);
 
-	plane_config->size = ALIGN(fb->pitches[0] * aligned_height, PAGE_SIZE);
+	plane_config->size = fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe %c with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe_name(pipe), fb->width, fb->height,
@@ -7715,6 +7757,10 @@
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
+	val = I915_READ(DSPCNTR(pipe));
+	if (!(val & DISPLAY_PLANE_ENABLE))
+		return;
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -7723,8 +7769,6 @@
 
 	fb = &intel_fb->base;
 
-	val = I915_READ(DSPCNTR(pipe));
-
 	if (INTEL_INFO(dev)->gen >= 4)
 		if (val & DISPPLANE_TILED)
 			plane_config->tiling = I915_TILING_X;
@@ -7755,7 +7799,7 @@
 	aligned_height = intel_fb_align_height(dev, fb->height,
 					       plane_config->tiling);
 
-	plane_config->size = PAGE_ALIGN(fb->pitches[0] * aligned_height);
+	plane_config->size = fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe %c with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe_name(pipe), fb->width, fb->height,
@@ -8698,6 +8742,7 @@
 			old->release_fb->funcs->destroy(old->release_fb);
 		goto fail;
 	}
+	crtc->primary->crtc = crtc;
 
 	/* let the connector get through one full cycle before testing */
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
@@ -9700,7 +9745,7 @@
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	WARN_ON(!in_irq());
+	WARN_ON(!in_interrupt());
 
 	if (crtc == NULL)
 		return;
@@ -9800,6 +9845,7 @@
 	drm_gem_object_reference(&obj->base);
 
 	crtc->primary->fb = fb;
+	update_state_fb(crtc->primary);
 
 	work->pending_flip_obj = obj;
 
@@ -9868,6 +9914,7 @@
 cleanup_pending:
 	atomic_dec(&intel_crtc->unpin_work_count);
 	crtc->primary->fb = old_fb;
+	update_state_fb(crtc->primary);
 	drm_gem_object_unreference(&work->old_fb_obj->base);
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
@@ -12182,9 +12229,6 @@
 		return -ENOMEM;
 	}
 
-	if (fb == crtc->cursor->fb)
-		return 0;
-
 	/* we only need to pin inside GTT if cursor is non-phy */
 	mutex_lock(&dev->struct_mutex);
 	if (!INTEL_INFO(dev)->cursor_needs_physical && obj->tiling_mode) {
@@ -13096,6 +13140,9 @@
 
 	/* HP Chromebook 14 (Celeron 2955U) */
 	{ 0x0a06, 0x103c, 0x21ed, quirk_backlight_present },
+
+	/* Dell Chromebook 11 */
+	{ 0x0a06, 0x1028, 0x0a35, quirk_backlight_present },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -13702,6 +13749,7 @@
 				  to_intel_crtc(c)->pipe);
 			drm_framebuffer_unreference(c->primary->fb);
 			c->primary->fb = NULL;
+			update_state_fb(c->primary);
 		}
 	}
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c
index 04e248d..54daa66 100644
--- a/drivers/gpu/drm/i915/intel_fifo_underrun.c
+++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c
@@ -282,16 +282,6 @@
 	return ret;
 }
 
-static bool
-__cpu_fifo_underrun_reporting_enabled(struct drm_i915_private *dev_priv,
-				      enum pipe pipe)
-{
-	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
-	return !intel_crtc->cpu_fifo_underrun_disabled;
-}
-
 /**
  * intel_set_pch_fifo_underrun_reporting - set PCH fifo underrun reporting state
  * @dev_priv: i915 device instance
@@ -352,9 +342,15 @@
 void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv,
 					 enum pipe pipe)
 {
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+
+	/* We may be called too early in init, thanks BIOS! */
+	if (crtc == NULL)
+		return;
+
 	/* GMCH can't disable fifo underruns, filter them. */
 	if (HAS_GMCH_DISPLAY(dev_priv->dev) &&
-	    !__cpu_fifo_underrun_reporting_enabled(dev_priv, pipe))
+	    to_intel_crtc(crtc)->cpu_fifo_underrun_disabled)
 		return;
 
 	if (intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false))
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0f358c5..e8d3da9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -503,18 +503,19 @@
 		 * If there isn't a request associated with this submission,
 		 * create one as a temporary holder.
 		 */
-		WARN(1, "execlist context submission without request");
 		request = kzalloc(sizeof(*request), GFP_KERNEL);
 		if (request == NULL)
 			return -ENOMEM;
 		request->ring = ring;
 		request->ctx = to;
+		kref_init(&request->ref);
+		request->uniq = dev_priv->request_uniq++;
+		i915_gem_context_reference(request->ctx);
 	} else {
+		i915_gem_request_reference(request);
 		WARN_ON(to != request->ctx);
 	}
 	request->tail = tail;
-	i915_gem_request_reference(request);
-	i915_gem_context_reference(request->ctx);
 
 	intel_runtime_pm_get(dev_priv);
 
@@ -731,7 +732,6 @@
 		if (ctx_obj && (ctx != ring->default_context))
 			intel_lr_context_unpin(ring, ctx);
 		intel_runtime_pm_put(dev_priv);
-		i915_gem_context_unreference(ctx);
 		list_del(&req->execlist_link);
 		i915_gem_request_unreference(req);
 	}
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index c47a3ba..4e8fb89 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1048,8 +1048,14 @@
 
 		/* We need to init first for ECOBUS access and then
 		 * determine later if we want to reinit, in case of MT access is
-		 * not working
+		 * not working. In this stage we don't know which flavour this
+		 * ivb is, so it is better to reset also the gen6 fw registers
+		 * before the ecobus check.
 		 */
+
+		__raw_i915_write32(dev_priv, FORCEWAKE, 0);
+		__raw_posting_read(dev_priv, ECOBUS);
+
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_MT, FORCEWAKE_MT_ACK);
 
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index 121d30c..87fe8ed 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -70,7 +70,9 @@
 		118800000, { 0x091c, 0x091c, 0x06dc },
 	}, {
 		216000000, { 0x06dc, 0x0b5c, 0x091c },
-	}
+	}, {
+		~0UL, { 0x0000, 0x0000, 0x0000 },
+	},
 };
 
 static const struct dw_hdmi_sym_term imx_sym_term[] = {
@@ -136,11 +138,34 @@
 	.destroy = drm_encoder_cleanup,
 };
 
+static enum drm_mode_status imx6q_hdmi_mode_valid(struct drm_connector *con,
+						  struct drm_display_mode *mode)
+{
+	if (mode->clock < 13500)
+		return MODE_CLOCK_LOW;
+	if (mode->clock > 266000)
+		return MODE_CLOCK_HIGH;
+
+	return MODE_OK;
+}
+
+static enum drm_mode_status imx6dl_hdmi_mode_valid(struct drm_connector *con,
+						   struct drm_display_mode *mode)
+{
+	if (mode->clock < 13500)
+		return MODE_CLOCK_LOW;
+	if (mode->clock > 270000)
+		return MODE_CLOCK_HIGH;
+
+	return MODE_OK;
+}
+
 static struct dw_hdmi_plat_data imx6q_hdmi_drv_data = {
-	.mpll_cfg = imx_mpll_cfg,
-	.cur_ctr  = imx_cur_ctr,
-	.sym_term = imx_sym_term,
-	.dev_type = IMX6Q_HDMI,
+	.mpll_cfg   = imx_mpll_cfg,
+	.cur_ctr    = imx_cur_ctr,
+	.sym_term   = imx_sym_term,
+	.dev_type   = IMX6Q_HDMI,
+	.mode_valid = imx6q_hdmi_mode_valid,
 };
 
 static struct dw_hdmi_plat_data imx6dl_hdmi_drv_data = {
@@ -148,6 +173,7 @@
 	.cur_ctr  = imx_cur_ctr,
 	.sym_term = imx_sym_term,
 	.dev_type = IMX6DL_HDMI,
+	.mode_valid = imx6dl_hdmi_mode_valid,
 };
 
 static const struct of_device_id dw_hdmi_imx_dt_ids[] = {
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 1b86aac..2d6dc94 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -163,22 +163,7 @@
 {
 	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
-	struct drm_display_mode *mode = &encoder->crtc->hwmode;
 	u32 pixel_fmt;
-	unsigned long serial_clk;
-	unsigned long di_clk = mode->clock * 1000;
-	int mux = imx_drm_encoder_get_mux_id(imx_ldb_ch->child, encoder);
-
-	if (ldb->ldb_ctrl & LDB_SPLIT_MODE_EN) {
-		/* dual channel LVDS mode */
-		serial_clk = 3500UL * mode->clock;
-		imx_ldb_set_clock(ldb, mux, 0, serial_clk, di_clk);
-		imx_ldb_set_clock(ldb, mux, 1, serial_clk, di_clk);
-	} else {
-		serial_clk = 7000UL * mode->clock;
-		imx_ldb_set_clock(ldb, mux, imx_ldb_ch->chno, serial_clk,
-				di_clk);
-	}
 
 	switch (imx_ldb_ch->chno) {
 	case 0:
@@ -247,6 +232,9 @@
 	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
 	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
+	unsigned long serial_clk;
+	unsigned long di_clk = mode->clock * 1000;
+	int mux = imx_drm_encoder_get_mux_id(imx_ldb_ch->child, encoder);
 
 	if (mode->clock > 170000) {
 		dev_warn(ldb->dev,
@@ -257,6 +245,16 @@
 			 "%s: mode exceeds 85 MHz pixel clock\n", __func__);
 	}
 
+	if (dual) {
+		serial_clk = 3500UL * mode->clock;
+		imx_ldb_set_clock(ldb, mux, 0, serial_clk, di_clk);
+		imx_ldb_set_clock(ldb, mux, 1, serial_clk, di_clk);
+	} else {
+		serial_clk = 7000UL * mode->clock;
+		imx_ldb_set_clock(ldb, mux, imx_ldb_ch->chno, serial_clk,
+				  di_clk);
+	}
+
 	/* FIXME - assumes straight connections DI0 --> CH0, DI1 --> CH1 */
 	if (imx_ldb_ch == &ldb->channel[0]) {
 		if (mode->flags & DRM_MODE_FLAG_NVSYNC)
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 5e83e00..900dda6 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -236,8 +236,11 @@
 	}
 
 	panel_node = of_parse_phandle(np, "fsl,panel", 0);
-	if (panel_node)
+	if (panel_node) {
 		imxpd->panel = of_drm_find_panel(panel_node);
+		if (!imxpd->panel)
+			return -EPROBE_DEFER;
+	}
 
 	imxpd->dev = dev;
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c
index 8edd531c..7369ee7 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c
@@ -32,7 +32,10 @@
 void mdp4_irq_preinstall(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
+	mdp4_enable(mdp4_kms);
 	mdp4_write(mdp4_kms, REG_MDP4_INTR_CLEAR, 0xffffffff);
+	mdp4_write(mdp4_kms, REG_MDP4_INTR_ENABLE, 0x00000000);
+	mdp4_disable(mdp4_kms);
 }
 
 int mdp4_irq_postinstall(struct msm_kms *kms)
@@ -53,7 +56,9 @@
 void mdp4_irq_uninstall(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
+	mdp4_enable(mdp4_kms);
 	mdp4_write(mdp4_kms, REG_MDP4_INTR_ENABLE, 0x00000000);
+	mdp4_disable(mdp4_kms);
 }
 
 irqreturn_t mdp4_irq(struct msm_kms *kms)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
index 09b4a25..c276624 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
@@ -8,17 +8,9 @@
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2014-12-05 15:34:49)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20908 bytes, from 2014-12-08 16:13:00)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2357 bytes, from 2014-12-08 16:13:00)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  27208 bytes, from 2015-01-13 23:56:11)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-10-31 16:48:57)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  26848 bytes, from 2015-01-13 23:55:57)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (   8253 bytes, from 2014-12-08 16:13:00)
+- /local/mnt2/workspace2/sviau/envytools/rnndb/mdp/mdp5.xml            (  27229 bytes, from 2015-02-10 17:00:41)
+- /local/mnt2/workspace2/sviau/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2014-06-02 18:31:15)
+- /local/mnt2/workspace2/sviau/envytools/rnndb/mdp/mdp_common.xml      (   2357 bytes, from 2015-01-23 16:20:19)
 
 Copyright (C) 2013-2015 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
@@ -910,6 +902,7 @@
 		case 2: return (mdp5_cfg->lm.base[2]);
 		case 3: return (mdp5_cfg->lm.base[3]);
 		case 4: return (mdp5_cfg->lm.base[4]);
+		case 5: return (mdp5_cfg->lm.base[5]);
 		default: return INVALID_IDX(idx);
 	}
 }
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 46fac54..2f2863c 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -62,8 +62,8 @@
 
 		/* current cursor being scanned out: */
 		struct drm_gem_object *scanout_bo;
-		uint32_t width;
-		uint32_t height;
+		uint32_t width, height;
+		uint32_t x, y;
 	} cursor;
 };
 #define to_mdp5_crtc(x) container_of(x, struct mdp5_crtc, base)
@@ -103,8 +103,8 @@
 	struct drm_plane *plane;
 	uint32_t flush_mask = 0;
 
-	/* we could have already released CTL in the disable path: */
-	if (!mdp5_crtc->ctl)
+	/* this should not happen: */
+	if (WARN_ON(!mdp5_crtc->ctl))
 		return;
 
 	drm_atomic_crtc_for_each_plane(plane, crtc) {
@@ -143,6 +143,11 @@
 	drm_atomic_crtc_for_each_plane(plane, crtc) {
 		mdp5_plane_complete_flip(plane);
 	}
+
+	if (mdp5_crtc->ctl && !crtc->state->enable) {
+		mdp5_ctl_release(mdp5_crtc->ctl);
+		mdp5_crtc->ctl = NULL;
+	}
 }
 
 static void unref_cursor_worker(struct drm_flip_work *work, void *val)
@@ -386,14 +391,17 @@
 	mdp5_crtc->event = crtc->state->event;
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
+	/*
+	 * If no CTL has been allocated in mdp5_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!mdp5_crtc->ctl))
+		return;
+
 	blend_setup(crtc);
 	crtc_flush_all(crtc);
 	request_pending(crtc, PENDING_FLIP);
-
-	if (mdp5_crtc->ctl && !crtc->state->enable) {
-		mdp5_ctl_release(mdp5_crtc->ctl);
-		mdp5_crtc->ctl = NULL;
-	}
 }
 
 static int mdp5_crtc_set_property(struct drm_crtc *crtc,
@@ -403,6 +411,32 @@
 	return -EINVAL;
 }
 
+static void get_roi(struct drm_crtc *crtc, uint32_t *roi_w, uint32_t *roi_h)
+{
+	struct mdp5_crtc *mdp5_crtc = to_mdp5_crtc(crtc);
+	uint32_t xres = crtc->mode.hdisplay;
+	uint32_t yres = crtc->mode.vdisplay;
+
+	/*
+	 * Cursor Region Of Interest (ROI) is a plane read from cursor
+	 * buffer to render. The ROI region is determined by the visibility of
+	 * the cursor point. In the default Cursor image the cursor point will
+	 * be at the top left of the cursor image, unless it is specified
+	 * otherwise using hotspot feature.
+	 *
+	 * If the cursor point reaches the right (xres - x < cursor.width) or
+	 * bottom (yres - y < cursor.height) boundary of the screen, then ROI
+	 * width and ROI height need to be evaluated to crop the cursor image
+	 * accordingly.
+	 * (xres-x) will be new cursor width when x > (xres - cursor.width)
+	 * (yres-y) will be new cursor height when y > (yres - cursor.height)
+	 */
+	*roi_w = min(mdp5_crtc->cursor.width, xres -
+			mdp5_crtc->cursor.x);
+	*roi_h = min(mdp5_crtc->cursor.height, yres -
+			mdp5_crtc->cursor.y);
+}
+
 static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 		struct drm_file *file, uint32_t handle,
 		uint32_t width, uint32_t height)
@@ -416,6 +450,7 @@
 	unsigned int depth;
 	enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL;
 	uint32_t flush_mask = mdp_ctl_flush_mask_cursor(0);
+	uint32_t roi_w, roi_h;
 	unsigned long flags;
 
 	if ((width > CURSOR_WIDTH) || (height > CURSOR_HEIGHT)) {
@@ -446,6 +481,12 @@
 	spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags);
 	old_bo = mdp5_crtc->cursor.scanout_bo;
 
+	mdp5_crtc->cursor.scanout_bo = cursor_bo;
+	mdp5_crtc->cursor.width = width;
+	mdp5_crtc->cursor.height = height;
+
+	get_roi(crtc, &roi_w, &roi_h);
+
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm),
 			MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888));
@@ -453,19 +494,14 @@
 			MDP5_LM_CURSOR_IMG_SIZE_SRC_H(height) |
 			MDP5_LM_CURSOR_IMG_SIZE_SRC_W(width));
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_SIZE(lm),
-			MDP5_LM_CURSOR_SIZE_ROI_H(height) |
-			MDP5_LM_CURSOR_SIZE_ROI_W(width));
+			MDP5_LM_CURSOR_SIZE_ROI_H(roi_h) |
+			MDP5_LM_CURSOR_SIZE_ROI_W(roi_w));
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BASE_ADDR(lm), cursor_addr);
 
-
 	blendcfg = MDP5_LM_CURSOR_BLEND_CONFIG_BLEND_EN;
-	blendcfg |= MDP5_LM_CURSOR_BLEND_CONFIG_BLEND_TRANSP_EN;
 	blendcfg |= MDP5_LM_CURSOR_BLEND_CONFIG_BLEND_ALPHA_SEL(cur_alpha);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BLEND_CONFIG(lm), blendcfg);
 
-	mdp5_crtc->cursor.scanout_bo = cursor_bo;
-	mdp5_crtc->cursor.width = width;
-	mdp5_crtc->cursor.height = height;
 	spin_unlock_irqrestore(&mdp5_crtc->cursor.lock, flags);
 
 	ret = mdp5_ctl_set_cursor(mdp5_crtc->ctl, true);
@@ -489,31 +525,18 @@
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	struct mdp5_crtc *mdp5_crtc = to_mdp5_crtc(crtc);
 	uint32_t flush_mask = mdp_ctl_flush_mask_cursor(0);
-	uint32_t xres = crtc->mode.hdisplay;
-	uint32_t yres = crtc->mode.vdisplay;
 	uint32_t roi_w;
 	uint32_t roi_h;
 	unsigned long flags;
 
-	x = (x > 0) ? x : 0;
-	y = (y > 0) ? y : 0;
+	/* In case the CRTC is disabled, just drop the cursor update */
+	if (unlikely(!crtc->state->enable))
+		return 0;
 
-	/*
-	 * Cursor Region Of Interest (ROI) is a plane read from cursor
-	 * buffer to render. The ROI region is determined by the visiblity of
-	 * the cursor point. In the default Cursor image the cursor point will
-	 * be at the top left of the cursor image, unless it is specified
-	 * otherwise using hotspot feature.
-	 *
-	 * If the cursor point reaches the right (xres - x < cursor.width) or
-	 * bottom (yres - y < cursor.height) boundary of the screen, then ROI
-	 * width and ROI height need to be evaluated to crop the cursor image
-	 * accordingly.
-	 * (xres-x) will be new cursor width when x > (xres - cursor.width)
-	 * (yres-y) will be new cursor height when y > (yres - cursor.height)
-	 */
-	roi_w = min(mdp5_crtc->cursor.width, xres - x);
-	roi_h = min(mdp5_crtc->cursor.height, yres - y);
+	mdp5_crtc->cursor.x = x = max(x, 0);
+	mdp5_crtc->cursor.y = y = max(y, 0);
+
+	get_roi(crtc, &roi_w, &roi_h);
 
 	spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_SIZE(mdp5_crtc->lm),
@@ -544,8 +567,8 @@
 static const struct drm_crtc_helper_funcs mdp5_crtc_helper_funcs = {
 	.mode_fixup = mdp5_crtc_mode_fixup,
 	.mode_set_nofb = mdp5_crtc_mode_set_nofb,
-	.prepare = mdp5_crtc_disable,
-	.commit = mdp5_crtc_enable,
+	.disable = mdp5_crtc_disable,
+	.enable = mdp5_crtc_enable,
 	.atomic_check = mdp5_crtc_atomic_check,
 	.atomic_begin = mdp5_crtc_atomic_begin,
 	.atomic_flush = mdp5_crtc_atomic_flush,
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c
index d6a14bb..af0e02f 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c
@@ -267,14 +267,14 @@
 	mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(intf), 1);
 	spin_unlock_irqrestore(&mdp5_encoder->intf_lock, flags);
 
-	mdp5_encoder->enabled = false;
+	mdp5_encoder->enabled = true;
 }
 
 static const struct drm_encoder_helper_funcs mdp5_encoder_helper_funcs = {
 	.mode_fixup = mdp5_encoder_mode_fixup,
 	.mode_set = mdp5_encoder_mode_set,
-	.prepare = mdp5_encoder_disable,
-	.commit = mdp5_encoder_enable,
+	.disable = mdp5_encoder_disable,
+	.enable = mdp5_encoder_enable,
 };
 
 /* initialize encoder */
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
index 70ac81e..a940710 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
@@ -34,7 +34,10 @@
 void mdp5_irq_preinstall(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+	mdp5_enable(mdp5_kms);
 	mdp5_write(mdp5_kms, REG_MDP5_INTR_CLEAR, 0xffffffff);
+	mdp5_write(mdp5_kms, REG_MDP5_INTR_EN, 0x00000000);
+	mdp5_disable(mdp5_kms);
 }
 
 int mdp5_irq_postinstall(struct msm_kms *kms)
@@ -57,7 +60,9 @@
 void mdp5_irq_uninstall(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+	mdp5_enable(mdp5_kms);
 	mdp5_write(mdp5_kms, REG_MDP5_INTR_EN, 0x00000000);
+	mdp5_disable(mdp5_kms);
 }
 
 static void mdp5_irq_mdp(struct mdp_kms *mdp_kms)
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 871aa21..18fd643 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -219,8 +219,10 @@
 	 * mark our set of crtc's as busy:
 	 */
 	ret = start_atomic(dev->dev_private, c->crtc_mask);
-	if (ret)
+	if (ret) {
+		kfree(c);
 		return ret;
+	}
 
 	/*
 	 * This is the point of no return - everything below never fails except
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 79924e4..6751553 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -418,7 +418,7 @@
 	nouveau_fbcon_zfill(dev, fbcon);
 
 	/* To allow resizeing without swapping buffers */
-	NV_INFO(drm, "allocated %dx%d fb: 0x%lx, bo %p\n",
+	NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n",
 		nouveau_fb->base.width, nouveau_fb->base.height,
 		nvbo->bo.offset, nvbo);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 29bd539..6efa8f3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -340,11 +340,13 @@
 
 		/* switch mmio to cpu's native endianness */
 #ifndef __BIG_ENDIAN
-		if (ioread32_native(map + 0x000004) != 0x00000000)
+		if (ioread32_native(map + 0x000004) != 0x00000000) {
 #else
-		if (ioread32_native(map + 0x000004) == 0x00000000)
+		if (ioread32_native(map + 0x000004) == 0x00000000) {
 #endif
 			iowrite32_native(0x01000001, map + 0x000004);
+			ioread32_native(map);
+		}
 
 		/* read boot0 and strapping information */
 		boot0 = ioread32_native(map + 0x000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c
index 539561e..108d048 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c
@@ -142,6 +142,49 @@
 		device->oclass[NVDEV_ENGINE_MSPPP  ] = &gf100_msppp_oclass;
 #endif
 		break;
+	case 0x126:
+		device->cname = "GM206";
+		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nvkm_bios_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  gk104_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  gm204_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gm107_fuse_oclass;
+#if 0
+		/* looks to be some non-trivial changes */
+		device->oclass[NVDEV_SUBDEV_CLK    ] = &gk104_clk_oclass;
+		/* priv ring says no to 0x10eb14 writes */
+		device->oclass[NVDEV_SUBDEV_THERM  ] = &gm107_therm_oclass;
+#endif
+		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
+		device->oclass[NVDEV_SUBDEV_DEVINIT] =  gm204_devinit_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  gk20a_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_BUS    ] =  gf100_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_TIMER  ] = &gk20a_timer_oclass;
+		device->oclass[NVDEV_SUBDEV_FB     ] =  gm107_fb_oclass;
+		device->oclass[NVDEV_SUBDEV_LTC    ] =  gm107_ltc_oclass;
+		device->oclass[NVDEV_SUBDEV_IBUS   ] = &gk104_ibus_oclass;
+		device->oclass[NVDEV_SUBDEV_INSTMEM] =  nv50_instmem_oclass;
+		device->oclass[NVDEV_SUBDEV_MMU    ] = &gf100_mmu_oclass;
+		device->oclass[NVDEV_SUBDEV_BAR    ] = &gf100_bar_oclass;
+		device->oclass[NVDEV_SUBDEV_PMU    ] =  gk208_pmu_oclass;
+#if 0
+		device->oclass[NVDEV_SUBDEV_VOLT   ] = &nv40_volt_oclass;
+#endif
+		device->oclass[NVDEV_ENGINE_DMAOBJ ] =  gf110_dmaeng_oclass;
+#if 0
+		device->oclass[NVDEV_ENGINE_FIFO   ] =  gk208_fifo_oclass;
+		device->oclass[NVDEV_ENGINE_SW     ] =  gf100_sw_oclass;
+		device->oclass[NVDEV_ENGINE_GR     ] =  gm107_gr_oclass;
+#endif
+		device->oclass[NVDEV_ENGINE_DISP   ] =  gm204_disp_oclass;
+#if 0
+		device->oclass[NVDEV_ENGINE_CE0    ] = &gm204_ce0_oclass;
+		device->oclass[NVDEV_ENGINE_CE1    ] = &gm204_ce1_oclass;
+		device->oclass[NVDEV_ENGINE_CE2    ] = &gm204_ce2_oclass;
+		device->oclass[NVDEV_ENGINE_MSVLD  ] = &gk104_msvld_oclass;
+		device->oclass[NVDEV_ENGINE_MSPDEC ] = &gk104_mspdec_oclass;
+		device->oclass[NVDEV_ENGINE_MSPPP  ] = &gf100_msppp_oclass;
+#endif
+		break;
 	default:
 		nv_fatal(device, "unknown Maxwell chipset\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
index b038b6e..043e429 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
@@ -502,72 +502,57 @@
 {
 	struct nvkm_device *device = nv_device(subdev);
 	struct nv04_fifo_priv *priv = (void *)subdev;
-	uint32_t status, reassign;
-	int cnt = 0;
+	u32 mask = nv_rd32(priv, NV03_PFIFO_INTR_EN_0);
+	u32 stat = nv_rd32(priv, NV03_PFIFO_INTR_0) & mask;
+	u32 reassign, chid, get, sem;
 
 	reassign = nv_rd32(priv, NV03_PFIFO_CACHES) & 1;
-	while ((status = nv_rd32(priv, NV03_PFIFO_INTR_0)) && (cnt++ < 100)) {
-		uint32_t chid, get;
+	nv_wr32(priv, NV03_PFIFO_CACHES, 0);
 
-		nv_wr32(priv, NV03_PFIFO_CACHES, 0);
+	chid = nv_rd32(priv, NV03_PFIFO_CACHE1_PUSH1) & priv->base.max;
+	get  = nv_rd32(priv, NV03_PFIFO_CACHE1_GET);
 
-		chid = nv_rd32(priv, NV03_PFIFO_CACHE1_PUSH1) & priv->base.max;
-		get  = nv_rd32(priv, NV03_PFIFO_CACHE1_GET);
-
-		if (status & NV_PFIFO_INTR_CACHE_ERROR) {
-			nv04_fifo_cache_error(device, priv, chid, get);
-			status &= ~NV_PFIFO_INTR_CACHE_ERROR;
-		}
-
-		if (status & NV_PFIFO_INTR_DMA_PUSHER) {
-			nv04_fifo_dma_pusher(device, priv, chid);
-			status &= ~NV_PFIFO_INTR_DMA_PUSHER;
-		}
-
-		if (status & NV_PFIFO_INTR_SEMAPHORE) {
-			uint32_t sem;
-
-			status &= ~NV_PFIFO_INTR_SEMAPHORE;
-			nv_wr32(priv, NV03_PFIFO_INTR_0,
-				NV_PFIFO_INTR_SEMAPHORE);
-
-			sem = nv_rd32(priv, NV10_PFIFO_CACHE1_SEMAPHORE);
-			nv_wr32(priv, NV10_PFIFO_CACHE1_SEMAPHORE, sem | 0x1);
-
-			nv_wr32(priv, NV03_PFIFO_CACHE1_GET, get + 4);
-			nv_wr32(priv, NV04_PFIFO_CACHE1_PULL0, 1);
-		}
-
-		if (device->card_type == NV_50) {
-			if (status & 0x00000010) {
-				status &= ~0x00000010;
-				nv_wr32(priv, 0x002100, 0x00000010);
-			}
-
-			if (status & 0x40000000) {
-				nv_wr32(priv, 0x002100, 0x40000000);
-				nvkm_fifo_uevent(&priv->base);
-				status &= ~0x40000000;
-			}
-		}
-
-		if (status) {
-			nv_warn(priv, "unknown intr 0x%08x, ch %d\n",
-				status, chid);
-			nv_wr32(priv, NV03_PFIFO_INTR_0, status);
-			status = 0;
-		}
-
-		nv_wr32(priv, NV03_PFIFO_CACHES, reassign);
+	if (stat & NV_PFIFO_INTR_CACHE_ERROR) {
+		nv04_fifo_cache_error(device, priv, chid, get);
+		stat &= ~NV_PFIFO_INTR_CACHE_ERROR;
 	}
 
-	if (status) {
-		nv_error(priv, "still angry after %d spins, halt\n", cnt);
-		nv_wr32(priv, 0x002140, 0);
-		nv_wr32(priv, 0x000140, 0);
+	if (stat & NV_PFIFO_INTR_DMA_PUSHER) {
+		nv04_fifo_dma_pusher(device, priv, chid);
+		stat &= ~NV_PFIFO_INTR_DMA_PUSHER;
 	}
 
-	nv_wr32(priv, 0x000100, 0x00000100);
+	if (stat & NV_PFIFO_INTR_SEMAPHORE) {
+		stat &= ~NV_PFIFO_INTR_SEMAPHORE;
+		nv_wr32(priv, NV03_PFIFO_INTR_0, NV_PFIFO_INTR_SEMAPHORE);
+
+		sem = nv_rd32(priv, NV10_PFIFO_CACHE1_SEMAPHORE);
+		nv_wr32(priv, NV10_PFIFO_CACHE1_SEMAPHORE, sem | 0x1);
+
+		nv_wr32(priv, NV03_PFIFO_CACHE1_GET, get + 4);
+		nv_wr32(priv, NV04_PFIFO_CACHE1_PULL0, 1);
+	}
+
+	if (device->card_type == NV_50) {
+		if (stat & 0x00000010) {
+			stat &= ~0x00000010;
+			nv_wr32(priv, 0x002100, 0x00000010);
+		}
+
+		if (stat & 0x40000000) {
+			nv_wr32(priv, 0x002100, 0x40000000);
+			nvkm_fifo_uevent(&priv->base);
+			stat &= ~0x40000000;
+		}
+	}
+
+	if (stat) {
+		nv_warn(priv, "unknown intr 0x%08x\n", stat);
+		nv_mask(priv, NV03_PFIFO_INTR_EN_0, stat, 0x00000000);
+		nv_wr32(priv, NV03_PFIFO_INTR_0, stat);
+	}
+
+	nv_wr32(priv, NV03_PFIFO_CACHES, reassign);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
index 2e7ec38..57e2c5b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
@@ -1032,9 +1032,9 @@
 	const int s = 8;
 	const int b = mmio_vram(info, impl->bundle_size, (1 << s), access);
 	mmio_refn(info, 0x408004, 0x00000000, s, b);
-	mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s));
 	mmio_refn(info, 0x418808, 0x00000000, s, b);
-	mmio_refn(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s));
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
index b52300d..5e9454b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
@@ -851,9 +851,9 @@
 	const int s = 8;
 	const int b = mmio_vram(info, impl->bundle_size, (1 << s), access);
 	mmio_refn(info, 0x408004, 0x00000000, s, b);
-	mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s));
 	mmio_refn(info, 0x418808, 0x00000000, s, b);
-	mmio_refn(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s));
 	mmio_wr32(info, 0x4064c8, (state_limit << 16) | token_limit);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
index 956f4dc..b2fae6e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
@@ -871,9 +871,9 @@
 	const int s = 8;
 	const int b = mmio_vram(info, impl->bundle_size, (1 << s), access);
 	mmio_refn(info, 0x408004, 0x00000000, s, b);
-	mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s));
 	mmio_refn(info, 0x418e24, 0x00000000, s, b);
-	mmio_refn(info, 0x418e28, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x418e28, 0x80000000 | (impl->bundle_size >> s));
 	mmio_wr32(info, 0x4064c8, (state_limit << 16) | token_limit);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c
index d1a89b2..c4e1f08 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c
@@ -74,7 +74,11 @@
 	u16 ent = dcb_i2c_entry(bios, idx, &ver, &len);
 	if (ent) {
 		if (ver >= 0x41) {
-			if (!(nv_ro32(bios, ent) & 0x80000000))
+			u32 ent_value = nv_ro32(bios, ent);
+			u8 i2c_port = (ent_value >> 27) & 0x1f;
+			u8 dpaux_port = (ent_value >> 22) & 0x1f;
+			/* value 0x1f means unused according to DCB 4.x spec */
+			if (i2c_port == 0x1f && dpaux_port == 0x1f)
 				info->type = DCB_I2C_UNUSED;
 			else
 				info->type = DCB_I2C_PMGR;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index ed644a4..86807ee 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1405,6 +1405,9 @@
 	       (x << 16) | y);
 	viewport_w = crtc->mode.hdisplay;
 	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
+	if ((rdev->family >= CHIP_BONAIRE) &&
+	    (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE))
+		viewport_h *= 2;
 	WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
 	       (viewport_w << 16) | viewport_h);
 
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 5bf825d..8d74de8 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -178,6 +178,13 @@
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_WRITE:
 	case DP_AUX_I2C_WRITE:
+		/* The atom implementation only supports writes with a max payload of
+		 * 12 bytes since it uses 4 bits for the total count (header + payload)
+		 * in the parameter space.  The atom interface supports 16 byte
+		 * payloads for reads. The hw itself supports up to 16 bytes of payload.
+		 */
+		if (WARN_ON_ONCE(msg->size > 12))
+			return -E2BIG;
 		/* tx_size needs to be 4 even for bare address packets since the atom
 		 * table needs the info in tx_buf[3].
 		 */
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 7c9df1e..c39c1d0 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -731,7 +731,9 @@
 		dig_connector = radeon_connector->con_priv;
 		if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 		    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
-			if (radeon_audio != 0 && ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev))
+			if (radeon_audio != 0 &&
+			    drm_detect_monitor_audio(radeon_connector_edid(connector)) &&
+			    ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev))
 				return ATOM_ENCODER_MODE_DP_AUDIO;
 			return ATOM_ENCODER_MODE_DP;
 		} else if (radeon_audio != 0) {
@@ -747,7 +749,9 @@
 		}
 		break;
 	case DRM_MODE_CONNECTOR_eDP:
-		if (radeon_audio != 0 && ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev))
+		if (radeon_audio != 0 &&
+		    drm_detect_monitor_audio(radeon_connector_edid(connector)) &&
+		    ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev))
 			return ATOM_ENCODER_MODE_DP_AUDIO;
 		return ATOM_ENCODER_MODE_DP;
 	case DRM_MODE_CONNECTOR_DVIA:
@@ -1622,7 +1626,6 @@
 	struct radeon_connector *radeon_connector = NULL;
 	struct radeon_connector_atom_dig *radeon_dig_connector = NULL;
 	bool travis_quirk = false;
-	int encoder_mode;
 
 	if (connector) {
 		radeon_connector = to_radeon_connector(connector);
@@ -1718,11 +1721,6 @@
 		}
 		break;
 	}
-
-	encoder_mode = atombios_get_encoder_mode(encoder);
-	if (radeon_audio != 0 &&
-		(encoder_mode == ATOM_ENCODER_MODE_HDMI || ENCODER_MODE_IS_DP(encoder_mode)))
-		radeon_audio_dpms(encoder, mode);
 }
 
 static void
@@ -1731,10 +1729,19 @@
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	int encoder_mode = atombios_get_encoder_mode(encoder);
 
 	DRM_DEBUG_KMS("encoder dpms %d to mode %d, devices %08x, active_devices %08x\n",
 		  radeon_encoder->encoder_id, mode, radeon_encoder->devices,
 		  radeon_encoder->active_device);
+
+	if (connector &&