Merge branch 'perf/urgent' into perf/core, to pick up fixes and refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index 1d27f0a..639e748 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -202,8 +202,8 @@
 
 $(MEDIA_OBJ_DIR)/v4l2.xml: $(OBJIMGFILES)
 	@$($(quiet)gen_xml)
-	@(ln -sf $(MEDIA_SRC_DIR)/v4l/*xml $(MEDIA_OBJ_DIR)/)
-	@(ln -sf $(MEDIA_SRC_DIR)/dvb/*xml $(MEDIA_OBJ_DIR)/)
+	@(ln -sf `cd $(MEDIA_SRC_DIR) && /bin/pwd`/v4l/*xml $(MEDIA_OBJ_DIR)/)
+	@(ln -sf `cd $(MEDIA_SRC_DIR) && /bin/pwd`/dvb/*xml $(MEDIA_OBJ_DIR)/)
 
 $(MEDIA_OBJ_DIR)/videodev2.h.xml: $(srctree)/include/uapi/linux/videodev2.h $(MEDIA_OBJ_DIR)/v4l2.xml
 	@$($(quiet)gen_xml)
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index a5160d8..b9ec668 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -20,12 +20,15 @@
 	"allwinner,sun5i-a13-ahb-gates-clk" - for the AHB gates on A13
 	"allwinner,sun5i-a10s-ahb-gates-clk" - for the AHB gates on A10s
 	"allwinner,sun7i-a20-ahb-gates-clk" - for the AHB gates on A20
+	"allwinner,sun6i-a31-ar100-clk" - for the AR100 on A31
 	"allwinner,sun6i-a31-ahb1-mux-clk" - for the AHB1 multiplexer on A31
 	"allwinner,sun6i-a31-ahb1-gates-clk" - for the AHB1 gates on A31
 	"allwinner,sun4i-a10-apb0-clk" - for the APB0 clock
+	"allwinner,sun6i-a31-apb0-clk" - for the APB0 clock on A31
 	"allwinner,sun4i-a10-apb0-gates-clk" - for the APB0 gates on A10
 	"allwinner,sun5i-a13-apb0-gates-clk" - for the APB0 gates on A13
 	"allwinner,sun5i-a10s-apb0-gates-clk" - for the APB0 gates on A10s
+	"allwinner,sun6i-a31-apb0-gates-clk" - for the APB0 gates on A31
 	"allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20
 	"allwinner,sun4i-a10-apb1-clk" - for the APB1 clock
 	"allwinner,sun4i-a10-apb1-mux-clk" - for the APB1 clock muxing
@@ -41,6 +44,7 @@
 	"allwinner,sun7i-a20-gmac-clk" - for the GMAC clock module on A20/A31
 	"allwinner,sun4i-a10-usb-clk" - for usb gates + resets on A10 / A20
 	"allwinner,sun5i-a13-usb-clk" - for usb gates + resets on A13
+	"allwinner,sun6i-a31-usb-clk" - for usb gates + resets on A31
 
 Required properties for all clocks:
 - reg : shall be the control register address for the clock.
diff --git a/Documentation/devicetree/bindings/clock/ti/apll.txt b/Documentation/devicetree/bindings/clock/ti/apll.txt
index 7faf5a6..ade4dd4 100644
--- a/Documentation/devicetree/bindings/clock/ti/apll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/apll.txt
@@ -14,18 +14,32 @@
 [2] Documentation/devicetree/bindings/clock/ti/dpll.txt
 
 Required properties:
-- compatible : shall be "ti,dra7-apll-clock"
+- compatible : shall be "ti,dra7-apll-clock" or "ti,omap2-apll-clock"
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : link phandles of parent clocks (clk-ref and clk-bypass)
 - reg : address and length of the register set for controlling the APLL.
   It contains the information of registers in the following order:
-	"control" - contains the control register base address
-	"idlest" - contains the idlest register base address
+	"control" - contains the control register offset
+	"idlest" - contains the idlest register offset
+	"autoidle" - contains the autoidle register offset (OMAP2 only)
+- ti,clock-frequency : static clock frequency for the clock (OMAP2 only)
+- ti,idlest-shift : bit-shift for the idlest field (OMAP2 only)
+- ti,bit-shift : bit-shift for enable and autoidle fields (OMAP2 only)
 
 Examples:
-	apll_pcie_ck: apll_pcie_ck@4a008200 {
+	apll_pcie_ck: apll_pcie_ck {
 		#clock-cells = <0>;
 		clocks = <&apll_pcie_in_clk_mux>, <&dpll_pcie_ref_ck>;
-		reg = <0x4a00821c 0x4>, <0x4a008220 0x4>;
+		reg = <0x021c>, <0x0220>;
 		compatible = "ti,dra7-apll-clock";
 	};
+
+	apll96_ck: apll96_ck {
+		#clock-cells = <0>;
+		compatible = "ti,omap2-apll-clock";
+		clocks = <&sys_ck>;
+		ti,bit-shift = <2>;
+		ti,idlest-shift = <8>;
+		ti,clock-frequency = <96000000>;
+		reg = <0x0500>, <0x0530>, <0x0520>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/ti/dpll.txt b/Documentation/devicetree/bindings/clock/ti/dpll.txt
index 30bfdb7..df57009 100644
--- a/Documentation/devicetree/bindings/clock/ti/dpll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/dpll.txt
@@ -24,12 +24,14 @@
 		"ti,omap4-dpll-core-clock",
 		"ti,omap4-dpll-m4xen-clock",
 		"ti,omap4-dpll-j-type-clock",
+		"ti,omap5-mpu-dpll-clock",
 		"ti,am3-dpll-no-gate-clock",
 		"ti,am3-dpll-j-type-clock",
 		"ti,am3-dpll-no-gate-j-type-clock",
 		"ti,am3-dpll-clock",
 		"ti,am3-dpll-core-clock",
 		"ti,am3-dpll-x2-clock",
+		"ti,omap2-dpll-core-clock",
 
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : link phandles of parent clocks, first entry lists reference clock
@@ -41,6 +43,7 @@
 	"mult-div1" - contains the multiplier / divider register base address
 	"autoidle" - contains the autoidle register base address (optional)
   ti,am3-* dpll types do not have autoidle register
+  ti,omap2-* dpll type does not support idlest / autoidle registers
 
 Optional properties:
 - DPLL mode setting - defining any one or more of the following overrides
@@ -73,3 +76,10 @@
 		clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
 		reg = <0x90>, <0x5c>, <0x68>;
 	};
+
+	dpll_ck: dpll_ck {
+		#clock-cells = <0>;
+		compatible = "ti,omap2-dpll-core-clock";
+		clocks = <&sys_ck>, <&sys_ck>;
+		reg = <0x0500>, <0x0540>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
new file mode 100644
index 0000000..585e8c1
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
@@ -0,0 +1,96 @@
+Device Tree Clock bindings for ATL (Audio Tracking Logic) of DRA7 SoC.
+
+The ATL IP is used to generate clock to be used to synchronize baseband and
+audio codec. A single ATL IP provides four ATL clock instances sharing the same
+functional clock but can be configured to provide different clocks.
+ATL can maintain a clock averages to some desired frequency based on the bws/aws
+signals - can compensate the drift between the two ws signal.
+
+In order to provide the support for ATL and it's output clocks (which can be used
+internally within the SoC or external components) two sets of bindings is needed:
+
+Clock tree binding:
+This binding uses the common clock binding[1].
+To be able to integrate the ATL clocks with DT clock tree.
+Provides ccf level representation of the ATL clocks to be used by drivers.
+Since the clock instances are part of a single IP this binding is used as a node
+for the DT clock tree, the IP driver is needed to handle the actual configuration
+of the IP.
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible : shall be "ti,dra7-atl-clock"
+- #clock-cells : from common clock binding; shall be set to 0.
+- clocks : link phandles to functional clock of ATL
+
+Binding for the IP driver:
+This binding is used to configure the IP driver which is going to handle the
+configuration of the IP for the ATL clock instances.
+
+Required properties:
+- compatible : shall be "ti,dra7-atl"
+- reg : base address for the ATL IP
+- ti,provided-clocks : List of phandles to the clocks associated with the ATL
+- clocks : link phandles to functional clock of ATL
+- clock-names : Shall be set to "fck"
+- ti,hwmods : Shall be set to "atl"
+
+Optional properties:
+Configuration of ATL instances:
+- atl{0/1/2/3} {
+	- bws : Baseband word select signal selection
+	- aws : Audio word select signal selection
+};
+
+For valid word select signals, see the dt-bindings/clk/ti-dra7-atl.h include
+file.
+
+Examples:
+/* clock bindings for atl provided clocks */
+atl_clkin0_ck: atl_clkin0_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+atl_clkin1_ck: atl_clkin1_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+atl_clkin2_ck: atl_clkin2_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+atl_clkin3_ck: atl_clkin3_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+/* binding for the IP */
+atl: atl@4843c000 {
+	compatible = "ti,dra7-atl";
+	reg = <0x4843c000 0x3ff>;
+	ti,hwmods = "atl";
+	ti,provided-clocks = <&atl_clkin0_ck>, <&atl_clkin1_ck>,
+				<&atl_clkin2_ck>, <&atl_clkin3_ck>;
+	clocks = <&atl_gfclk_mux>;
+	clock-names = "fck";
+	status = "disabled";
+};
+
+#include <dt-bindings/clk/ti-dra7-atl.h>
+
+&atl {
+	status = "okay";
+
+	atl2 {
+		bws = <DRA7_ATL_WS_MCASP2_FSX>;
+		aws = <DRA7_ATL_WS_MCASP3_FSX>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/ti/gate.txt b/Documentation/devicetree/bindings/clock/ti/gate.txt
index 125281a..03f8fde 100644
--- a/Documentation/devicetree/bindings/clock/ti/gate.txt
+++ b/Documentation/devicetree/bindings/clock/ti/gate.txt
@@ -25,6 +25,11 @@
 			  to map clockdomains properly
   "ti,hsdiv-gate-clock" - gate clock with OMAP36xx specific hardware handling,
 			  required for a hardware errata
+  "ti,composite-gate-clock" - composite gate clock, to be part of composite
+			      clock
+  "ti,composite-no-wait-gate-clock" - composite gate clock that does not wait
+				      for clock to be active before returning
+				      from clk_enable()
 - #clock-cells : from common clock binding; shall be set to 0
 - clocks : link to phandle of parent clock
 - reg : offset for register controlling adjustable gate, not needed for
@@ -41,7 +46,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
 		clocks = <&core_96m_fck>;
-		reg = <0x48004a00 0x4>;
+		reg = <0x0a00>;
 		ti,bit-shift = <25>;
 	};
 
@@ -57,7 +62,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,dss-gate-clock";
 		clocks = <&dpll4_m4x2_ck>;
-		reg = <0x48004e00 0x4>;
+		reg = <0x0e00>;
 		ti,bit-shift = <0>;
 	};
 
@@ -65,7 +70,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,am35xx-gate-clock";
 		clocks = <&ipss_ick>;
-		reg = <0x4800259c 0x4>;
+		reg = <0x059c>;
 		ti,bit-shift = <1>;
 	};
 
@@ -80,6 +85,22 @@
 		compatible = "ti,hsdiv-gate-clock";
 		clocks = <&dpll4_m2x2_mul_ck>;
 		ti,bit-shift = <0x1b>;
-		reg = <0x48004d00 0x4>;
+		reg = <0x0d00>;
 		ti,set-bit-to-disable;
 	};
+
+	vlynq_gate_fck: vlynq_gate_fck {
+		#clock-cells = <0>;
+		compatible = "ti,composite-gate-clock";
+		clocks = <&core_ck>;
+		ti,bit-shift = <3>;
+		reg = <0x0200>;
+	};
+
+	sys_clkout2_src_gate: sys_clkout2_src_gate {
+		#clock-cells = <0>;
+		compatible = "ti,composite-no-wait-gate-clock";
+		clocks = <&core_ck>;
+		ti,bit-shift = <15>;
+		reg = <0x0070>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/ti/interface.txt b/Documentation/devicetree/bindings/clock/ti/interface.txt
index 064e8ca..3111a40 100644
--- a/Documentation/devicetree/bindings/clock/ti/interface.txt
+++ b/Documentation/devicetree/bindings/clock/ti/interface.txt
@@ -21,6 +21,8 @@
   "ti,omap3-dss-interface-clock" - interface clock with DSS specific HW handling
   "ti,omap3-ssi-interface-clock" - interface clock with SSI specific HW handling
   "ti,am35xx-interface-clock" - interface clock with AM35xx specific HW handling
+  "ti,omap2430-interface-clock" - interface clock with OMAP2430 specific HW
+				  handling
 - #clock-cells : from common clock binding; shall be set to 0
 - clocks : link to phandle of parent clock
 - reg : base address for the control register
diff --git a/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt
new file mode 100644
index 0000000..dde6c22
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt
@@ -0,0 +1,42 @@
+* Rockchip RK3xxx I2C controller
+
+This driver interfaces with the native I2C controller present in Rockchip
+RK3xxx SoCs.
+
+Required properties :
+
+ - reg : Offset and length of the register set for the device
+ - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c" or
+		"rockchip,rk3288-i2c".
+ - interrupts : interrupt number
+ - clocks : parent clock
+
+Required on RK3066, RK3188 :
+
+ - rockchip,grf : the phandle of the syscon node for the general register
+		  file (GRF)
+ - on those SoCs an alias with the correct I2C bus ID (bit offset in the GRF)
+   is also required.
+
+Optional properties :
+
+ - clock-frequency : SCL frequency to use (in Hz). If omitted, 100kHz is used.
+
+Example:
+
+aliases {
+	i2c0 = &i2c0;
+}
+
+i2c0: i2c@2002d000 {
+	compatible = "rockchip,rk3188-i2c";
+	reg = <0x2002d000 0x1000>;
+	interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	rockchip,grf = <&grf>;
+
+	clock-names = "i2c";
+	clocks = <&cru PCLK_I2C0>;
+};
diff --git a/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt b/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt
new file mode 100644
index 0000000..6b76548
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt
@@ -0,0 +1,41 @@
+
+* Allwinner P2WI (Push/Pull 2 Wire Interface) controller
+
+Required properties :
+
+ - reg             : Offset and length of the register set for the device.
+ - compatible      : Should one of the following:
+                     - "allwinner,sun6i-a31-p2wi"
+ - interrupts      : The interrupt line connected to the P2WI peripheral.
+ - clocks          : The gate clk connected to the P2WI peripheral.
+ - resets          : The reset line connected to the P2WI peripheral.
+
+Optional properties :
+
+ - clock-frequency : Desired P2WI bus clock frequency in Hz. If not set the
+default frequency is 100kHz
+
+A P2WI may contain one child node encoding a P2WI slave device.
+
+Slave device properties:
+  Required properties:
+   - reg           : the I2C slave address used during the initialization
+                     process to switch from I2C to P2WI mode
+
+Example:
+
+	p2wi@01f03400 {
+		compatible = "allwinner,sun6i-a31-p2wi";
+		reg = <0x01f03400 0x400>;
+		interrupts = <0 39 4>;
+		clocks = <&apb0_gates 3>;
+		clock-frequency = <6000000>;
+		resets = <&apb0_rst 3>;
+
+		axp221: pmic@68 {
+			compatible = "x-powers,axp221";
+			reg = <0x68>;
+
+			/* ... */
+		};
+	};
diff --git a/Documentation/hwmon/shtc1 b/Documentation/hwmon/shtc1
new file mode 100644
index 0000000..6b1e054
--- /dev/null
+++ b/Documentation/hwmon/shtc1
@@ -0,0 +1,43 @@
+Kernel driver shtc1
+===================
+
+Supported chips:
+  * Sensirion SHTC1
+    Prefix: 'shtc1'
+    Addresses scanned: none
+    Datasheet: http://www.sensirion.com/file/datasheet_shtc1
+
+  * Sensirion SHTW1
+    Prefix: 'shtw1'
+    Addresses scanned: none
+    Datasheet: Not publicly available
+
+Author:
+  Johannes Winkelmann <johannes.winkelmann@sensirion.com>
+
+Description
+-----------
+
+This driver implements support for the Sensirion SHTC1 chip, a humidity and
+temperature sensor. Temperature is measured in degrees celsius, relative
+humidity is expressed as a percentage. Driver can be used as well for SHTW1
+chip, which has the same electrical interface.
+
+The device communicates with the I2C protocol. All sensors are set to I2C
+address 0x70. See Documentation/i2c/instantiating-devices for methods to
+instantiate the device.
+
+There are two options configurable by means of shtc1_platform_data:
+1. blocking (pull the I2C clock line down while performing the measurement) or
+   non-blocking mode. Blocking mode will guarantee the fastest result but
+   the I2C bus will be busy during that time. By default, non-blocking mode
+   is used. Make sure clock-stretching works properly on your device if you
+   want to use blocking mode.
+2. high or low accuracy. High accuracy is used by default and using it is
+   strongly recommended.
+
+sysfs-Interface
+---------------
+
+temp1_input - temperature input
+humidity1_input - humidity input
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index d567a7c..c600e2f 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -1171,7 +1171,7 @@
 	      obvious reason.
 
     dtc
-	Create flattend device tree blob object suitable for linking
+	Create flattened device tree blob object suitable for linking
 	into vmlinux. Device tree blobs linked into vmlinux are placed
 	in an init section in the image. Platform code *must* copy the
 	blob to non-init memory prior to calling unflatten_device_tree().
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 6eaa9cd..8849049 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1474,6 +1474,13 @@
 	js=		[HW,JOY] Analog joystick
 			See Documentation/input/joystick.txt.
 
+	kaslr/nokaslr	[X86]
+			Enable/disable kernel and module base offset ASLR
+			(Address Space Layout Randomization) if built into
+			the kernel. When CONFIG_HIBERNATION is selected,
+			kASLR is disabled by default. When kASLR is enabled,
+			hibernation will be disabled.
+
 	keepinitrd	[HW,ARM]
 
 	kernelcore=nn[KMG]	[KNL,X86,IA-64,PPC] This parameter
@@ -2110,10 +2117,6 @@
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
-	nokaslr		[X86]
-			Disable kernel and module base offset ASLR (Address
-			Space Layout Randomization) if built into the kernel.
-
 	noautogroup	Disable scheduler automatic task group creation.
 
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
@@ -2184,6 +2187,8 @@
 			in certain environments such as networked servers or
 			real-time systems.
 
+	nohibernate	[HIBERNATION] Disable hibernation and resume.
+
 	nohz=		[KNL] Boottime enable/disable dynamic ticks
 			Valid arguments: on, off
 			Default: on
@@ -2980,6 +2985,7 @@
 		noresume	Don't check if there's a hibernation image
 				present during boot.
 		nocompress	Don't compress/decompress hibernation images.
+		no		Disable hibernation and resume.
 
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
diff --git a/Documentation/thermal/nouveau_thermal b/Documentation/thermal/nouveau_thermal
index efceb78..60bc293 100644
--- a/Documentation/thermal/nouveau_thermal
+++ b/Documentation/thermal/nouveau_thermal
@@ -4,7 +4,7 @@
 Supported chips:
 * NV43+
 
-Authors: Martin Peres (mupuf) <martin.peres@labri.fr>
+Authors: Martin Peres (mupuf) <martin.peres@free.fr>
 
 Description
 ---------
@@ -68,8 +68,9 @@
 
 NOTE: Be sure to use the manual mode if you want to drive the fan speed manually
 
-NOTE2: Not all fan management modes may be supported on all chipsets. We are
-working on it.
+NOTE2: When operating in manual mode outside the vbios-defined
+[PWM_min, PWM_max] range, the reported fan speed (RPM) may not be accurate
+depending on your hardware.
 
 Bug reports
 ---------
diff --git a/Documentation/vDSO/parse_vdso.c b/Documentation/vDSO/parse_vdso.c
index 8587020..1dbb4b8 100644
--- a/Documentation/vDSO/parse_vdso.c
+++ b/Documentation/vDSO/parse_vdso.c
@@ -1,6 +1,6 @@
 /*
  * parse_vdso.c: Linux reference vDSO parser
- * Written by Andrew Lutomirski, 2011.
+ * Written by Andrew Lutomirski, 2011-2014.
  *
  * This code is meant to be linked in to various programs that run on Linux.
  * As such, it is available with as few restrictions as possible.  This file
@@ -11,13 +11,14 @@
  * it starts a program.  It works equally well in statically and dynamically
  * linked binaries.
  *
- * This code is tested on x86_64.  In principle it should work on any 64-bit
+ * This code is tested on x86.  In principle it should work on any
  * architecture that has a vDSO.
  */
 
 #include <stdbool.h>
 #include <stdint.h>
 #include <string.h>
+#include <limits.h>
 #include <elf.h>
 
 /*
@@ -45,11 +46,18 @@
 
 
 /* And here's the code. */
-
-#ifndef __x86_64__
-# error Not yet ported to non-x86_64 architectures
+#ifndef ELF_BITS
+# if ULONG_MAX > 0xffffffffUL
+#  define ELF_BITS 64
+# else
+#  define ELF_BITS 32
+# endif
 #endif
 
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
 static struct vdso_info
 {
 	bool valid;
@@ -59,14 +67,14 @@
 	uintptr_t load_offset;  /* load_addr - recorded vaddr */
 
 	/* Symbol table */
-	Elf64_Sym *symtab;
+	ELF(Sym) *symtab;
 	const char *symstrings;
-	Elf64_Word *bucket, *chain;
-	Elf64_Word nbucket, nchain;
+	ELF(Word) *bucket, *chain;
+	ELF(Word) nbucket, nchain;
 
 	/* Version table */
-	Elf64_Versym *versym;
-	Elf64_Verdef *verdef;
+	ELF(Versym) *versym;
+	ELF(Verdef) *verdef;
 } vdso_info;
 
 /* Straight from the ELF specification. */
@@ -92,9 +100,14 @@
 
 	vdso_info.load_addr = base;
 
-	Elf64_Ehdr *hdr = (Elf64_Ehdr*)base;
-	Elf64_Phdr *pt = (Elf64_Phdr*)(vdso_info.load_addr + hdr->e_phoff);
-	Elf64_Dyn *dyn = 0;
+	ELF(Ehdr) *hdr = (ELF(Ehdr)*)base;
+	if (hdr->e_ident[EI_CLASS] !=
+	    (ELF_BITS == 32 ? ELFCLASS32 : ELFCLASS64)) {
+		return;  /* Wrong ELF class -- check ELF_BITS */
+	}
+
+	ELF(Phdr) *pt = (ELF(Phdr)*)(vdso_info.load_addr + hdr->e_phoff);
+	ELF(Dyn) *dyn = 0;
 
 	/*
 	 * We need two things from the segment table: the load offset
@@ -108,7 +121,7 @@
 				+ (uintptr_t)pt[i].p_offset
 				- (uintptr_t)pt[i].p_vaddr;
 		} else if (pt[i].p_type == PT_DYNAMIC) {
-			dyn = (Elf64_Dyn*)(base + pt[i].p_offset);
+			dyn = (ELF(Dyn)*)(base + pt[i].p_offset);
 		}
 	}
 
@@ -118,7 +131,7 @@
 	/*
 	 * Fish out the useful bits of the dynamic table.
 	 */
-	Elf64_Word *hash = 0;
+	ELF(Word) *hash = 0;
 	vdso_info.symstrings = 0;
 	vdso_info.symtab = 0;
 	vdso_info.versym = 0;
@@ -131,22 +144,22 @@
 				 + vdso_info.load_offset);
 			break;
 		case DT_SYMTAB:
-			vdso_info.symtab = (Elf64_Sym *)
+			vdso_info.symtab = (ELF(Sym) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
 		case DT_HASH:
-			hash = (Elf64_Word *)
+			hash = (ELF(Word) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
 		case DT_VERSYM:
-			vdso_info.versym = (Elf64_Versym *)
+			vdso_info.versym = (ELF(Versym) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
 		case DT_VERDEF:
-			vdso_info.verdef = (Elf64_Verdef *)
+			vdso_info.verdef = (ELF(Verdef) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
@@ -168,8 +181,8 @@
 	vdso_info.valid = true;
 }
 
-static bool vdso_match_version(Elf64_Versym ver,
-			       const char *name, Elf64_Word hash)
+static bool vdso_match_version(ELF(Versym) ver,
+			       const char *name, ELF(Word) hash)
 {
 	/*
 	 * This is a helper function to check if the version indexed by
@@ -188,7 +201,7 @@
 
 	/* First step: find the version definition */
 	ver &= 0x7fff;  /* Apparently bit 15 means "hidden" */
-	Elf64_Verdef *def = vdso_info.verdef;
+	ELF(Verdef) *def = vdso_info.verdef;
 	while(true) {
 		if ((def->vd_flags & VER_FLG_BASE) == 0
 		    && (def->vd_ndx & 0x7fff) == ver)
@@ -197,11 +210,11 @@
 		if (def->vd_next == 0)
 			return false;  /* No definition. */
 
-		def = (Elf64_Verdef *)((char *)def + def->vd_next);
+		def = (ELF(Verdef) *)((char *)def + def->vd_next);
 	}
 
 	/* Now figure out whether it matches. */
-	Elf64_Verdaux *aux = (Elf64_Verdaux*)((char *)def + def->vd_aux);
+	ELF(Verdaux) *aux = (ELF(Verdaux)*)((char *)def + def->vd_aux);
 	return def->vd_hash == hash
 		&& !strcmp(name, vdso_info.symstrings + aux->vda_name);
 }
@@ -213,10 +226,10 @@
 		return 0;
 
 	ver_hash = elf_hash(version);
-	Elf64_Word chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];
+	ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];
 
 	for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) {
-		Elf64_Sym *sym = &vdso_info.symtab[chain];
+		ELF(Sym) *sym = &vdso_info.symtab[chain];
 
 		/* Check for a defined global or weak function w/ right name. */
 		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
@@ -243,7 +256,7 @@
 
 void vdso_init_from_auxv(void *auxv)
 {
-	Elf64_auxv_t *elf_auxv = auxv;
+	ELF(auxv_t) *elf_auxv = auxv;
 	for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++)
 	{
 		if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) {
diff --git a/Documentation/vDSO/vdso_standalone_test_x86.c b/Documentation/vDSO/vdso_standalone_test_x86.c
new file mode 100644
index 0000000..d462402
--- /dev/null
+++ b/Documentation/vDSO/vdso_standalone_test_x86.c
@@ -0,0 +1,128 @@
+/*
+ * vdso_test.c: Sample code to test parse_vdso.c on x86
+ * Copyright (c) 2011-2014 Andy Lutomirski
+ * Subject to the GNU General Public License, version 2
+ *
+ * You can amuse yourself by compiling with:
+ * gcc -std=gnu99 -nostdlib
+ *     -Os -fno-asynchronous-unwind-tables -flto -lgcc_s
+ *      vdso_standalone_test_x86.c parse_vdso.c
+ * to generate a small binary.  On x86_64, you can omit -lgcc_s
+ * if you want the binary to be completely standalone.
+ */
+
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <stdint.h>
+
+extern void *vdso_sym(const char *version, const char *name);
+extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+extern void vdso_init_from_auxv(void *auxv);
+
+/* We need a libc functions... */
+int strcmp(const char *a, const char *b)
+{
+	/* This implementation is buggy: it never returns -1. */
+	while (*a || *b) {
+		if (*a != *b)
+			return 1;
+		if (*a == 0 || *b == 0)
+			return 1;
+		a++;
+		b++;
+	}
+
+	return 0;
+}
+
+/* ...and two syscalls.  This is x86-specific. */
+static inline long x86_syscall3(long nr, long a0, long a1, long a2)
+{
+	long ret;
+#ifdef __x86_64__
+	asm volatile ("syscall" : "=a" (ret) : "a" (nr),
+		      "D" (a0), "S" (a1), "d" (a2) :
+		      "cc", "memory", "rcx",
+		      "r8", "r9", "r10", "r11" );
+#else
+	asm volatile ("int $0x80" : "=a" (ret) : "a" (nr),
+		      "b" (a0), "c" (a1), "d" (a2) :
+		      "cc", "memory" );
+#endif
+	return ret;
+}
+
+static inline long linux_write(int fd, const void *data, size_t len)
+{
+	return x86_syscall3(__NR_write, fd, (long)data, (long)len);
+}
+
+static inline void linux_exit(int code)
+{
+	x86_syscall3(__NR_exit, code, 0, 0);
+}
+
+void to_base10(char *lastdig, uint64_t n)
+{
+	while (n) {
+		*lastdig = (n % 10) + '0';
+		n /= 10;
+		lastdig--;
+	}
+}
+
+__attribute__((externally_visible)) void c_main(void **stack)
+{
+	/* Parse the stack */
+	long argc = (long)*stack;
+	stack += argc + 2;
+
+	/* Now we're pointing at the environment.  Skip it. */
+	while(*stack)
+		stack++;
+	stack++;
+
+	/* Now we're pointing at auxv.  Initialize the vDSO parser. */
+	vdso_init_from_auxv((void *)stack);
+
+	/* Find gettimeofday. */
+	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
+	gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+
+	if (!gtod)
+		linux_exit(1);
+
+	struct timeval tv;
+	long ret = gtod(&tv, 0);
+
+	if (ret == 0) {
+		char buf[] = "The time is                     .000000\n";
+		to_base10(buf + 31, tv.tv_sec);
+		to_base10(buf + 38, tv.tv_usec);
+		linux_write(1, buf, sizeof(buf) - 1);
+	} else {
+		linux_exit(ret);
+	}
+
+	linux_exit(0);
+}
+
+/*
+ * This is the real entry point.  It passes the initial stack into
+ * the C entry point.
+ */
+asm (
+	".text\n"
+	".global _start\n"
+	".type _start,@function\n"
+	"_start:\n\t"
+#ifdef __x86_64__
+	"mov %rsp,%rdi\n\t"
+	"jmp c_main"
+#else
+	"push %esp\n\t"
+	"call c_main\n\t"
+	"int $3"
+#endif
+	);
diff --git a/Documentation/vDSO/vdso_test.c b/Documentation/vDSO/vdso_test.c
index fff6334..8daeb7d7 100644
--- a/Documentation/vDSO/vdso_test.c
+++ b/Documentation/vDSO/vdso_test.c
@@ -1,111 +1,52 @@
 /*
- * vdso_test.c: Sample code to test parse_vdso.c on x86_64
- * Copyright (c) 2011 Andy Lutomirski
+ * vdso_test.c: Sample code to test parse_vdso.c
+ * Copyright (c) 2014 Andy Lutomirski
  * Subject to the GNU General Public License, version 2
  *
- * You can amuse yourself by compiling with:
- * gcc -std=gnu99 -nostdlib
- *     -Os -fno-asynchronous-unwind-tables -flto
- *      vdso_test.c parse_vdso.c -o vdso_test
- * to generate a small binary with no dependencies at all.
+ * Compile with:
+ * gcc -std=gnu99 vdso_test.c parse_vdso.c
+ *
+ * Tested on x86, 32-bit and 64-bit.  It may work on other architectures, too.
  */
 
-#include <sys/syscall.h>
-#include <sys/time.h>
-#include <unistd.h>
 #include <stdint.h>
+#include <elf.h>
+#include <stdio.h>
+#include <sys/auxv.h>
+#include <sys/time.h>
 
 extern void *vdso_sym(const char *version, const char *name);
 extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
 extern void vdso_init_from_auxv(void *auxv);
 
-/* We need a libc functions... */
-int strcmp(const char *a, const char *b)
+int main(int argc, char **argv)
 {
-	/* This implementation is buggy: it never returns -1. */
-	while (*a || *b) {
-		if (*a != *b)
-			return 1;
-		if (*a == 0 || *b == 0)
-			return 1;
-		a++;
-		b++;
+	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+	if (!sysinfo_ehdr) {
+		printf("AT_SYSINFO_EHDR is not present!\n");
+		return 0;
 	}
 
-	return 0;
-}
-
-/* ...and two syscalls.  This is x86_64-specific. */
-static inline long linux_write(int fd, const void *data, size_t len)
-{
-
-	long ret;
-	asm volatile ("syscall" : "=a" (ret) : "a" (__NR_write),
-		      "D" (fd), "S" (data), "d" (len) :
-		      "cc", "memory", "rcx",
-		      "r8", "r9", "r10", "r11" );
-	return ret;
-}
-
-static inline void linux_exit(int code)
-{
-	asm volatile ("syscall" : : "a" (__NR_exit), "D" (code));
-}
-
-void to_base10(char *lastdig, uint64_t n)
-{
-	while (n) {
-		*lastdig = (n % 10) + '0';
-		n /= 10;
-		lastdig--;
-	}
-}
-
-__attribute__((externally_visible)) void c_main(void **stack)
-{
-	/* Parse the stack */
-	long argc = (long)*stack;
-	stack += argc + 2;
-
-	/* Now we're pointing at the environment.  Skip it. */
-	while(*stack)
-		stack++;
-	stack++;
-
-	/* Now we're pointing at auxv.  Initialize the vDSO parser. */
-	vdso_init_from_auxv((void *)stack);
+	vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
 
 	/* Find gettimeofday. */
 	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
 	gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
 
-	if (!gtod)
-		linux_exit(1);
+	if (!gtod) {
+		printf("Could not find __vdso_gettimeofday\n");
+		return 1;
+	}
 
 	struct timeval tv;
 	long ret = gtod(&tv, 0);
 
 	if (ret == 0) {
-		char buf[] = "The time is                     .000000\n";
-		to_base10(buf + 31, tv.tv_sec);
-		to_base10(buf + 38, tv.tv_usec);
-		linux_write(1, buf, sizeof(buf) - 1);
+		printf("The time is %lld.%06lld\n",
+		       (long long)tv.tv_sec, (long long)tv.tv_usec);
 	} else {
-		linux_exit(ret);
+		printf("__vdso_gettimeofday failed\n");
 	}
 
-	linux_exit(0);
+	return 0;
 }
-
-/*
- * This is the real entry point.  It passes the initial stack into
- * the C entry point.
- */
-asm (
-	".text\n"
-	".global _start\n"
-        ".type _start,@function\n"
-        "_start:\n\t"
-        "mov %rsp,%rdi\n\t"
-        "jmp c_main"
-	);
diff --git a/MAINTAINERS b/MAINTAINERS
index 055f952..3f2e171 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2594,7 +2594,7 @@
 F:	drivers/infiniband/hw/cxgb3/
 
 CXGB4 ETHERNET DRIVER (CXGB4)
-M:	Dimitris Michailidis <dm@chelsio.com>
+M:	Hariprasad S <hariprasad@chelsio.com>
 L:	netdev@vger.kernel.org
 W:	http://www.chelsio.com
 S:	Supported
@@ -6960,7 +6960,7 @@
 M:	Guan Xuetao <gxt@mprc.pku.edu.cn>
 W:	http://mprc.pku.edu.cn/~guanxuetao/linux
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/epip/linux-2.6-unicore32.git
+T:	git git://github.com/gxt/linux.git
 F:	drivers/input/serio/i8042-unicore32io.h
 F:	drivers/i2c/busses/i2c-puv3.c
 F:	drivers/video/fb-puv3.c
@@ -7948,6 +7948,7 @@
 
 SECURITY SUBSYSTEM
 M:	James Morris <james.l.morris@oracle.com>
+M:	Serge E. Hallyn <serge@hallyn.com>
 L:	linux-security-module@vger.kernel.org (suggested Cc:)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git
 W:	http://kernsec.org/
@@ -9276,7 +9277,7 @@
 M:	Guan Xuetao <gxt@mprc.pku.edu.cn>
 W:	http://mprc.pku.edu.cn/~guanxuetao/linux
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/epip/linux-2.6-unicore32.git
+T:	git git://github.com/gxt/linux.git
 F:	arch/unicore32/
 
 UNIFDEF
@@ -9743,6 +9744,14 @@
 S:	Supported
 F:	arch/x86/kernel/cpu/vmware.c
 
+VMWARE BALLOON DRIVER
+M:	Xavier Deguillard <xdeguillard@vmware.com>
+M:	Philip Moltmann <moltmann@vmware.com>
+M:	"VMware, Inc." <pv-drivers@vmware.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/misc/vmw_balloon.c
+
 VMWARE VMXNET3 ETHERNET DRIVER
 M:	Shreyas Bhatewara <sbhatewara@vmware.com>
 M:	"VMware, Inc." <pv-drivers@vmware.com>
diff --git a/Makefile b/Makefile
index 7680d7c..b11e2d5 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
-PATCHLEVEL = 15
+PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc2
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 87b63fd..245058b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -175,13 +175,6 @@
 config ARCH_HAS_ILOG2_U64
 	bool
 
-config ARCH_HAS_CPUFREQ
-	bool
-	help
-	  Internal node to signify that the ARCH has CPUFREQ support
-	  and that the relevant menu configurations are displayed for
-	  it.
-
 config ARCH_HAS_BANDGAP
 	bool
 
@@ -318,7 +311,6 @@
 
 config ARCH_INTEGRATOR
 	bool "ARM Ltd. Integrator family"
-	select ARCH_HAS_CPUFREQ
 	select ARM_AMBA
 	select ARM_PATCH_PHYS_VIRT
 	select AUTO_ZRELADDR
@@ -538,7 +530,6 @@
 
 config ARCH_KIRKWOOD
 	bool "Marvell Kirkwood"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
@@ -637,7 +628,6 @@
 config ARCH_PXA
 	bool "PXA2xx/PXA3xx-based"
 	depends on MMU
-	select ARCH_HAS_CPUFREQ
 	select ARCH_MTD_XIP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_CPU_SUSPEND if PM
@@ -707,7 +697,6 @@
 
 config ARCH_SA1100
 	bool "SA1100-based"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_MTD_XIP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SPARSEMEM_ENABLE
@@ -725,7 +714,6 @@
 
 config ARCH_S3C24XX
 	bool "Samsung S3C24XX SoCs"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ATAGS
 	select CLKDEV_LOOKUP
@@ -746,7 +734,6 @@
 
 config ARCH_S3C64XX
 	bool "Samsung S3C64XX"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_VIC
@@ -809,7 +796,6 @@
 
 config ARCH_S5PV210
 	bool "Samsung S5PV210/S5PC110"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_SPARSEMEM_ENABLE
 	select ATAGS
@@ -845,7 +831,6 @@
 config ARCH_OMAP1
 	bool "TI OMAP1"
 	depends on MMU
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
@@ -1009,8 +994,6 @@
 
 source "arch/arm/mach-sa1100/Kconfig"
 
-source "arch/arm/plat-samsung/Kconfig"
-
 source "arch/arm/mach-socfpga/Kconfig"
 
 source "arch/arm/mach-spear/Kconfig"
@@ -1028,6 +1011,7 @@
 source "arch/arm/mach-s5pv210/Kconfig"
 
 source "arch/arm/mach-exynos/Kconfig"
+source "arch/arm/plat-samsung/Kconfig"
 
 source "arch/arm/mach-shmobile/Kconfig"
 
@@ -2109,9 +2093,7 @@
 
 menu "CPU Power Management"
 
-if ARCH_HAS_CPUFREQ
 source "drivers/cpufreq/Kconfig"
-endif
 
 source "drivers/cpuidle/Kconfig"
 
diff --git a/arch/arm/boot/dts/armada-375-db.dts b/arch/arm/boot/dts/armada-375-db.dts
index 772fec2..1e2919d 100644
--- a/arch/arm/boot/dts/armada-375-db.dts
+++ b/arch/arm/boot/dts/armada-375-db.dts
@@ -91,6 +91,8 @@
 				marvell,nand-keep-config;
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
 
 				partition@0 {
 					label = "U-Boot";
diff --git a/arch/arm/boot/dts/armada-385-db.dts b/arch/arm/boot/dts/armada-385-db.dts
index ff9637d..5bae473 100644
--- a/arch/arm/boot/dts/armada-385-db.dts
+++ b/arch/arm/boot/dts/armada-385-db.dts
@@ -98,6 +98,8 @@
 				marvell,nand-keep-config;
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
 
 				partition@0 {
 					label = "U-Boot";
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index e5c6a04..4e5a59e 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -25,7 +25,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0 0x00000000 0 0xC0000000>; /* 3 GB */
+		reg = <0 0x00000000 0 0x40000000>; /* 1 GB soldered on */
 	};
 
 	soc {
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index c767687..b03cfe4 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -26,7 +26,7 @@
 		clock-frequency = <0>;
 	};
 
-	atlclkin3_ck: atlclkin3_ck {
+	atl_clkin3_ck: atl_clkin3_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
 		clock-frequency = <0>;
@@ -277,7 +277,7 @@
 
 	dpll_mpu_ck: dpll_mpu_ck {
 		#clock-cells = <0>;
-		compatible = "ti,omap4-dpll-clock";
+		compatible = "ti,omap5-mpu-dpll-clock";
 		clocks = <&sys_clkin1>, <&mpu_dpll_hs_clk_div>;
 		reg = <0x0160>, <0x0164>, <0x016c>, <0x0168>;
 	};
@@ -730,7 +730,7 @@
 	mcasp1_ahclkr_mux: mcasp1_ahclkr_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <28>;
 		reg = <0x0550>;
 	};
@@ -738,7 +738,7 @@
 	mcasp1_ahclkx_mux: mcasp1_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x0550>;
 	};
@@ -1639,7 +1639,7 @@
 	mcasp2_ahclkr_mux: mcasp2_ahclkr_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <28>;
 		reg = <0x1860>;
 	};
@@ -1647,7 +1647,7 @@
 	mcasp2_ahclkx_mux: mcasp2_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1860>;
 	};
@@ -1663,7 +1663,7 @@
 	mcasp3_ahclkx_mux: mcasp3_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1868>;
 	};
@@ -1679,7 +1679,7 @@
 	mcasp4_ahclkx_mux: mcasp4_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1898>;
 	};
@@ -1695,7 +1695,7 @@
 	mcasp5_ahclkx_mux: mcasp5_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1878>;
 	};
@@ -1711,7 +1711,7 @@
 	mcasp6_ahclkx_mux: mcasp6_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1904>;
 	};
@@ -1727,7 +1727,7 @@
 	mcasp7_ahclkx_mux: mcasp7_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1908>;
 	};
@@ -1743,7 +1743,7 @@
 	mcasp8_ahclk_mux: mcasp8_ahclk_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <22>;
 		reg = <0x1890>;
 	};
diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi
index aeb142c..e67a23b 100644
--- a/arch/arm/boot/dts/omap54xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi
@@ -335,7 +335,7 @@
 
 	dpll_mpu_ck: dpll_mpu_ck {
 		#clock-cells = <0>;
-		compatible = "ti,omap4-dpll-clock";
+		compatible = "ti,omap5-mpu-dpll-clock";
 		clocks = <&sys_clkin>, <&mpu_dpll_hs_clk_div>;
 		reg = <0x0160>, <0x0164>, <0x016c>, <0x0168>;
 	};
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index e2d6204..17d9462 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -300,6 +300,7 @@
 CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_ARMMMCI=y
 CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_OF_ARASAN=y
 CONFIG_MMC_SDHCI_ESDHC_IMX=y
 CONFIG_MMC_SDHCI_DOVE=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 59066cf..536a137 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -32,6 +32,7 @@
 CONFIG_SOC_AM33XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_SOC_DRA7XX=y
+CONFIG_CACHE_L2X0=y
 CONFIG_ARM_THUMBEE=y
 CONFIG_ARM_ERRATA_411920=y
 CONFIG_SMP=y
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index eb577f4..39eb16b 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -52,7 +52,7 @@
 
 #endif
 
-#define ftrace_return_addr(n) return_address(n)
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 9bc6db1..41c8391 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -1,10 +1,9 @@
-config ARCH_BCM
+menuconfig ARCH_BCM
 	bool "Broadcom SoC Support" if ARCH_MULTI_V6_V7
 	help
 	  This enables support for Broadcom ARM based SoC chips
 
-menu "Broadcom SoC Selection"
-	depends on ARCH_BCM
+if ARCH_BCM
 
 config ARCH_BCM_MOBILE
 	bool "Broadcom Mobile SoC Support" if ARCH_MULTI_V7
@@ -88,4 +87,4 @@
 	  different SoC or with the older BCM47XX and BCM53XX based
 	  network SoC using a MIPS CPU, they are supported by arch/mips/bcm47xx
 
-endmenu
+endif
diff --git a/arch/arm/mach-berlin/Kconfig b/arch/arm/mach-berlin/Kconfig
index 101e0f3..2631cfc 100644
--- a/arch/arm/mach-berlin/Kconfig
+++ b/arch/arm/mach-berlin/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_BERLIN
+menuconfig ARCH_BERLIN
 	bool "Marvell Berlin SoCs" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
@@ -9,8 +9,6 @@
 
 if ARCH_BERLIN
 
-menu "Marvell Berlin SoC variants"
-
 config MACH_BERLIN_BG2
 	bool "Marvell Armada 1500 (BG2)"
 	select CACHE_L2X0
@@ -30,6 +28,4 @@
 	select HAVE_ARM_TWD if SMP
 	select PINCTRL_BERLIN_BG2Q
 
-endmenu
-
 endif
diff --git a/arch/arm/mach-cns3xxx/Kconfig b/arch/arm/mach-cns3xxx/Kconfig
index 66838f4..3c22a19 100644
--- a/arch/arm/mach-cns3xxx/Kconfig
+++ b/arch/arm/mach-cns3xxx/Kconfig
@@ -1,12 +1,11 @@
-config ARCH_CNS3XXX
+menuconfig ARCH_CNS3XXX
 	bool "Cavium Networks CNS3XXX family" if ARCH_MULTI_V6
 	select ARM_GIC
 	select PCI_DOMAINS if PCI
 	help
 	  Support for Cavium Networks CNS3XXX platform.
 
-menu "CNS3XXX platform type"
-	depends on ARCH_CNS3XXX
+if ARCH_CNS3XXX
 
 config MACH_CNS3420VB
 	bool "Support for CNS3420 Validation Board"
@@ -17,4 +16,4 @@
 	  This is a platform with an on-board ARM11 MPCore and has support
 	  for USB, USB-OTG, MMC/SD/SDIO, SATA, PCI-E, etc.
 
-endmenu
+endif
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index db18ef8..584e8d4 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -39,7 +39,6 @@
 config ARCH_DAVINCI_DA850
 	bool "DA850/OMAP-L138/AM18x based system"
 	select ARCH_DAVINCI_DA8XX
-	select ARCH_HAS_CPUFREQ
 	select CP_INTC
 
 config ARCH_DAVINCI_DA8XX
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index d58995c9..8f9b66c 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -7,10 +7,9 @@
 
 # Configuration options for the EXYNOS4
 
-config ARCH_EXYNOS
+menuconfig ARCH_EXYNOS
 	bool "Samsung EXYNOS" if ARCH_MULTI_V7
 	select ARCH_HAS_BANDGAP
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
@@ -30,8 +29,6 @@
 
 if ARCH_EXYNOS
 
-menu "SAMSUNG EXYNOS SoCs Support"
-
 config ARCH_EXYNOS3
 	bool "SAMSUNG EXYNOS3"
 	select ARM_CPU_SUSPEND if PM
@@ -118,8 +115,6 @@
 	default y
 	depends on SOC_EXYNOS5420
 
-endmenu
-
 config EXYNOS5420_MCPM
 	bool "Exynos5420 Multi-Cluster PM support"
 	depends on MCPM && SOC_EXYNOS5420
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 16617bd..1ee9176 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -118,6 +118,7 @@
 extern void __iomem *sysram_base_addr;
 void exynos_init_io(void);
 void exynos_restart(enum reboot_mode mode, const char *cmd);
+void exynos_sysram_init(void);
 void exynos_cpuidle_init(void);
 void exynos_cpufreq_init(void);
 void exynos_init_late(void);
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 90aab4d..f38cf7c1 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -184,6 +184,28 @@
 	platform_device_register_simple("exynos-cpufreq", -1, NULL, 0);
 }
 
+void __iomem *sysram_base_addr;
+void __iomem *sysram_ns_base_addr;
+
+void __init exynos_sysram_init(void)
+{
+	struct device_node *node;
+
+	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram") {
+		if (!of_device_is_available(node))
+			continue;
+		sysram_base_addr = of_iomap(node, 0);
+		break;
+	}
+
+	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram-ns") {
+		if (!of_device_is_available(node))
+			continue;
+		sysram_ns_base_addr = of_iomap(node, 0);
+		break;
+	}
+}
+
 void __init exynos_init_late(void)
 {
 	if (of_machine_is_compatible("samsung,exynos5440"))
@@ -198,7 +220,7 @@
 					int depth, void *data)
 {
 	struct map_desc iodesc;
-	__be32 *reg;
+	const __be32 *reg;
 	int len;
 
 	if (!of_flat_dt_is_compatible(node, "samsung,exynos4210-chipid") &&
@@ -271,6 +293,13 @@
 		}
 	}
 
+	/*
+	 * This is called from smp_prepare_cpus if we've built for SMP, but
+	 * we still need to set it up for PM and firmware ops if not.
+	 */
+	if (!IS_ENABLED(SMP))
+		exynos_sysram_init();
+
 	exynos_cpuidle_init();
 	exynos_cpufreq_init();
 
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index ec02422..1c8d31e 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -32,28 +32,6 @@
 
 extern void exynos4_secondary_startup(void);
 
-void __iomem *sysram_base_addr;
-void __iomem *sysram_ns_base_addr;
-
-static void __init exynos_smp_prepare_sysram(void)
-{
-	struct device_node *node;
-
-	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram") {
-		if (!of_device_is_available(node))
-			continue;
-		sysram_base_addr = of_iomap(node, 0);
-		break;
-	}
-
-	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram-ns") {
-		if (!of_device_is_available(node))
-			continue;
-		sysram_ns_base_addr = of_iomap(node, 0);
-		break;
-	}
-}
-
 static inline void __iomem *cpu_boot_reg_base(void)
 {
 	if (soc_is_exynos4210() && samsung_rev() == EXYNOS4210_REV_1_1)
@@ -234,11 +212,11 @@
 {
 	int i;
 
+	exynos_sysram_init();
+
 	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
 		scu_enable(scu_base_addr());
 
-	exynos_smp_prepare_sysram();
-
 	/*
 	 * Write the address of secondary startup into the
 	 * system-wide flags register. The boot monitor waits
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index 830b76e..a5960e2 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -1,7 +1,6 @@
 config ARCH_HIGHBANK
 	bool "Calxeda ECX-1000/2000 (Highbank/Midway)" if ARCH_MULTI_V7
 	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_HAS_OPP
 	select ARCH_SUPPORTS_BIG_ENDIAN
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 8d42eab..28fa2fa 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -1,6 +1,5 @@
-config ARCH_MXC
+menuconfig ARCH_MXC
 	bool "Freescale i.MX family" if ARCH_MULTI_V4_V5 || ARCH_MULTI_V6_V7
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_CPU_SUSPEND if PM
@@ -13,8 +12,7 @@
 	help
 	  Support for Freescale MXC/iMX-based family of processors
 
-menu "Freescale i.MX support"
-	depends on ARCH_MXC
+if ARCH_MXC
 
 config MXC_TZIC
 	bool
@@ -99,7 +97,6 @@
 
 config SOC_IMX27
 	bool
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select CPU_ARM926T
 	select IMX_HAVE_IOMUX_V1
@@ -124,7 +121,6 @@
 
 config SOC_IMX5
 	bool
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_MXC_IOMUX_V3
 	select MXC_TZIC
@@ -786,4 +782,4 @@
 
 source "arch/arm/mach-imx/devices/Kconfig"
 
-endmenu
+endif
diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig
index ba43321..64f8e25 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -28,7 +28,7 @@
 	bool
 
 config INTEGRATOR_IMPD1
-	tristate "Include support for Integrator/IM-PD1"
+	bool "Include support for Integrator/IM-PD1"
 	depends on ARCH_INTEGRATOR_AP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index 0e870ea..3ce8807 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -308,7 +308,12 @@
  */
 #define IMPD1_VALID_IRQS 0x00000bffU
 
-static int __init impd1_probe(struct lm_device *dev)
+/*
+ * As this module is bool, it is OK to have this as __init_refok() - no
+ * probe calls will be done after the initial system bootup, as devices
+ * are discovered as part of the machine startup.
+ */
+static int __init_refok impd1_probe(struct lm_device *dev)
 {
 	struct impd1_module *impd1;
 	int irq_base;
@@ -397,6 +402,11 @@
 static struct lm_driver impd1_driver = {
 	.drv = {
 		.name	= "impd1",
+		/*
+		 * As we're dropping the probe() function, suppress driver
+		 * binding from sysfs.
+		 */
+		.suppress_bind_attrs = true,
 	},
 	.probe		= impd1_probe,
 	.remove		= impd1_remove,
diff --git a/arch/arm/mach-keystone/Kconfig b/arch/arm/mach-keystone/Kconfig
index f50bc93..98a156a 100644
--- a/arch/arm/mach-keystone/Kconfig
+++ b/arch/arm/mach-keystone/Kconfig
@@ -1,6 +1,7 @@
 config ARCH_KEYSTONE
 	bool "Texas Instruments Keystone Devices"
 	depends on ARCH_MULTI_V7
+	depends on ARM_PATCH_PHYS_VIRT
 	select ARM_GIC
 	select HAVE_ARM_ARCH_TIMER
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index 82a4ba8..f49328c 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_MOXART
+menuconfig ARCH_MOXART
 	bool "MOXA ART SoC" if ARCH_MULTI_V4
 	select CPU_FA526
 	select ARM_DMA_MEM_BUFFERABLE
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 6090b9e..4a7c250 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_MVEBU
+menuconfig ARCH_MVEBU
 	bool "Marvell Engineering Business Unit (MVEBU) SoCs" if (ARCH_MULTI_V7 || ARCH_MULTI_V5)
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CLKSRC_MMIO
@@ -13,8 +13,6 @@
 
 if ARCH_MVEBU
 
-menu "Marvell EBU SoC variants"
-
 config MACH_MVEBU_V7
 	bool
 	select ARMADA_370_XP_TIMER
@@ -84,7 +82,6 @@
 
 config MACH_KIRKWOOD
 	bool "Marvell Kirkwood boards" if ARCH_MULTI_V5
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select KIRKWOOD_CLK
@@ -97,6 +94,4 @@
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Kirkwood device tree.
 
-endmenu
-
 endif
diff --git a/arch/arm/mach-nomadik/Kconfig b/arch/arm/mach-nomadik/Kconfig
index 486d301..3c61096 100644
--- a/arch/arm/mach-nomadik/Kconfig
+++ b/arch/arm/mach-nomadik/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_NOMADIK
+menuconfig ARCH_NOMADIK
 	bool "ST-Ericsson Nomadik"
 	depends on ARCH_MULTI_V5
 	select ARCH_REQUIRE_GPIOLIB
@@ -15,7 +15,6 @@
 	  Support for the Nomadik platform by ST-Ericsson
 
 if ARCH_NOMADIK
-menu "Nomadik boards"
 
 config MACH_NOMADIK_8815NHK
 	bool "ST 8815 Nomadik Hardware Kit (evaluation board)"
@@ -24,7 +23,6 @@
 	select I2C_ALGOBIT
 	select I2C_NOMADIK
 
-endmenu
 endif
 
 config NOMADIK_8815
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 0ba4826..06250534 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -1,3 +1,6 @@
+menu "TI OMAP/AM/DM/DRA Family"
+	depends on ARCH_MULTI_V6 || ARCH_MULTI_V7
+
 config ARCH_OMAP
 	bool
 
@@ -28,7 +31,6 @@
 	select ARM_CPU_SUSPEND if PM
 	select ARM_ERRATA_720789
 	select ARM_GIC
-	select CACHE_L2X0
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select OMAP_INTERCONNECT
@@ -80,7 +82,6 @@
 config ARCH_OMAP2PLUS
 	bool
 	select ARCH_HAS_BANDGAP
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
@@ -343,3 +344,5 @@
 endmenu
 
 endif
+
+endmenu
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index b935ed2..85e0b0c0 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -208,3 +208,56 @@
 		clk_put(c);
 	}
 }
+
+#ifdef CONFIG_OF
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+
+static const struct clk_ops virt_prcm_set_ops = {
+	.recalc_rate	= &omap2_table_mpu_recalc,
+	.set_rate	= &omap2_select_table_rate,
+	.round_rate	= &omap2_round_to_table_rate,
+};
+
+/**
+ * omap2xxx_clkt_vps_init - initialize virt_prcm_set clock
+ *
+ * Does a manual init for the virtual prcm DVFS clock for OMAP2. This
+ * function is called only from omap2 DT clock init, as the virtual
+ * node is not modelled in the DT clock data.
+ */
+void omap2xxx_clkt_vps_init(void)
+{
+	struct clk_init_data init = { NULL };
+	struct clk_hw_omap *hw = NULL;
+	struct clk *clk;
+	const char *parent_name = "mpu_ck";
+	struct clk_lookup *lookup = NULL;
+
+	omap2xxx_clkt_vps_late_init();
+	omap2xxx_clkt_vps_check_bootloader_rates();
+
+	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
+	lookup = kzalloc(sizeof(*lookup), GFP_KERNEL);
+	if (!hw || !lookup)
+		goto cleanup;
+	init.name = "virt_prcm_set";
+	init.ops = &virt_prcm_set_ops;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	hw->hw.init = &init;
+
+	clk = clk_register(NULL, &hw->hw);
+
+	lookup->dev_id = NULL;
+	lookup->con_id = "cpufreq_ck";
+	lookup->clk = clk;
+
+	clkdev_add(lookup);
+	return;
+cleanup:
+	kfree(hw);
+	kfree(lookup);
+}
+#endif
diff --git a/arch/arm/mach-omap2/clock.h b/arch/arm/mach-omap2/clock.h
index bda767a..12f54d4 100644
--- a/arch/arm/mach-omap2/clock.h
+++ b/arch/arm/mach-omap2/clock.h
@@ -178,17 +178,6 @@
 	const struct clksel_rate *rates;
 };
 
-struct clk_hw_omap_ops {
-	void			(*find_idlest)(struct clk_hw_omap *oclk,
-					void __iomem **idlest_reg,
-					u8 *idlest_bit, u8 *idlest_val);
-	void			(*find_companion)(struct clk_hw_omap *oclk,
-					void __iomem **other_reg,
-					u8 *other_bit);
-	void			(*allow_idle)(struct clk_hw_omap *oclk);
-	void			(*deny_idle)(struct clk_hw_omap *oclk);
-};
-
 unsigned long omap_fixed_divisor_recalc(struct clk_hw *hw,
 					unsigned long parent_rate);
 
@@ -279,8 +268,6 @@
 extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait;
 extern const struct clk_hw_omap_ops clkhwops_apll54;
 extern const struct clk_hw_omap_ops clkhwops_apll96;
-extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll;
-extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait;
 
 /* clksel_rate blocks shared between OMAP44xx and AM33xx */
 extern const struct clksel_rate div_1_0_rates[];
diff --git a/arch/arm/mach-omap2/clock2xxx.h b/arch/arm/mach-omap2/clock2xxx.h
index 539dc08..45f41a4 100644
--- a/arch/arm/mach-omap2/clock2xxx.h
+++ b/arch/arm/mach-omap2/clock2xxx.h
@@ -21,10 +21,6 @@
 				      unsigned long parent_rate);
 unsigned long omap2_osc_clk_recalc(struct clk_hw *clk,
 				   unsigned long parent_rate);
-unsigned long omap2_dpllcore_recalc(struct clk_hw *hw,
-				    unsigned long parent_rate);
-int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate,
-			     unsigned long parent_rate);
 void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw);
 unsigned long omap2_clk_apll54_recalc(struct clk_hw *hw,
 				      unsigned long parent_rate);
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index ff02973..a373d50 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -91,7 +91,14 @@
 extern void omap3_secure_sync32k_timer_init(void);
 extern void omap3_gptimer_timer_init(void);
 extern void omap4_local_timer_init(void);
+#ifdef CONFIG_CACHE_L2X0
 int omap_l2_cache_init(void);
+#else
+static inline int omap_l2_cache_init(void)
+{
+	return 0;
+}
+#endif
 extern void omap5_realtime_timer_init(void);
 
 void omap2420_init_early(void);
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index fcd8036..6d7ba37 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -319,6 +319,15 @@
 
 	/* Set DPLL multiplier, divider */
 	v = omap2_clk_readl(clk, dd->mult_div1_reg);
+
+	/* Handle Duty Cycle Correction */
+	if (dd->dcc_mask) {
+		if (dd->last_rounded_rate >= dd->dcc_rate)
+			v |= dd->dcc_mask; /* Enable DCC */
+		else
+			v &= ~dd->dcc_mask; /* Disable DCC */
+	}
+
 	v &= ~(dd->mult_mask | dd->div1_mask);
 	v |= dd->last_rounded_m << __ffs(dd->mult_mask);
 	v |= (dd->last_rounded_n - 1) << __ffs(dd->div1_mask);
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index e4e505f..042f693 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_SIRF
+menuconfig ARCH_SIRF
 	bool "CSR SiRF" if ARCH_MULTI_V7
 	select ARCH_HAS_RESET_CONTROLLER
 	select ARCH_REQUIRE_GPIOLIB
@@ -11,7 +11,7 @@
 
 if ARCH_SIRF
 
-menu "CSR SiRF atlas6/primaII/Marco/Polo Specific Features"
+comment "CSR SiRF atlas6/primaII/Marco/Polo Specific Features"
 
 config ARCH_ATLAS6
 	bool "CSR SiRFSoC ATLAS6 ARM Cortex A9 Platform"
@@ -37,8 +37,6 @@
 	help
           Support for CSR SiRFSoC ARM Cortex A9 Platform
 
-endmenu
-
 config SIRF_IRQ
 	bool
 
diff --git a/arch/arm/mach-qcom/Kconfig b/arch/arm/mach-qcom/Kconfig
index fd2b99d..ee5697b 100644
--- a/arch/arm/mach-qcom/Kconfig
+++ b/arch/arm/mach-qcom/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_QCOM
+menuconfig ARCH_QCOM
 	bool "Qualcomm Support" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
@@ -11,8 +11,6 @@
 
 if ARCH_QCOM
 
-menu "Qualcomm SoC Selection"
-
 config ARCH_MSM8X60
 	bool "Enable support for MSM8X60"
 	select CLKSRC_QCOM
@@ -25,8 +23,6 @@
 	bool "Enable support for MSM8974"
 	select HAVE_ARM_ARCH_TIMER
 
-endmenu
-
 config QCOM_SCM
 	bool
 
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index 04284de..ad5316a 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -117,7 +117,7 @@
 	  Compile in platform device definition for Samsung TouchScreen.
 
 config S3C24XX_DMA
-	bool "S3C2410 DMA support"
+	bool "S3C2410 DMA support (deprecated)"
 	select S3C_DMA
 	help
 	  S3C2410 DMA support. This is needed for drivers like sound which
diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig
index 3136d86..26ca242 100644
--- a/arch/arm/mach-s3c64xx/Kconfig
+++ b/arch/arm/mach-s3c64xx/Kconfig
@@ -18,9 +18,9 @@
 	  Enable S3C6410 CPU support
 
 config S3C64XX_PL080
-	bool "S3C64XX DMA using generic PL08x driver"
+	def_bool DMADEVICES
+	select ARM_AMBA
 	select AMBA_PL08X
-	select SAMSUNG_DMADEV
 
 config S3C64XX_SETUP_SDHCI
 	bool
diff --git a/arch/arm/mach-s5p64x0/Kconfig b/arch/arm/mach-s5p64x0/Kconfig
index bb2111b..26003e2 100644
--- a/arch/arm/mach-s5p64x0/Kconfig
+++ b/arch/arm/mach-s5p64x0/Kconfig
@@ -9,16 +9,18 @@
 
 config CPU_S5P6440
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_SLEEP if PM
-	select SAMSUNG_DMADEV
 	select SAMSUNG_WAKEMASK if PM
 	help
 	  Enable S5P6440 CPU support
 
 config CPU_S5P6450
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_SLEEP if PM
-	select SAMSUNG_DMADEV
 	select SAMSUNG_WAKEMASK if PM
 	help
 	  Enable S5P6450 CPU support
diff --git a/arch/arm/mach-s5pc100/Kconfig b/arch/arm/mach-s5pc100/Kconfig
index 15170be..c5e3a96 100644
--- a/arch/arm/mach-s5pc100/Kconfig
+++ b/arch/arm/mach-s5pc100/Kconfig
@@ -9,8 +9,9 @@
 
 config CPU_S5PC100
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_EXT_INT
-	select SAMSUNG_DMADEV
 	help
 	  Enable S5PC100 CPU support
 
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index 8c3abe5..f60f286 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -11,10 +11,11 @@
 
 config CPU_S5PV210
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_EXT_INT
 	select S5P_PM if PM
 	select S5P_SLEEP if PM
-	select SAMSUNG_DMADEV
 	help
 	  Enable S5PV210 CPU support
 
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index dbd954e..7980730 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -1,7 +1,7 @@
 config ARCH_SHMOBILE
 	bool
 
-config ARCH_SHMOBILE_MULTI
+menuconfig ARCH_SHMOBILE_MULTI
 	bool "Renesas ARM SoCs" if ARCH_MULTI_V7
 	depends on MMU
 	select ARCH_SHMOBILE
@@ -15,7 +15,7 @@
 
 if ARCH_SHMOBILE_MULTI
 
-comment "Renesas ARM SoCs System Type"
+#comment "Renesas ARM SoCs System Type"
 
 config ARCH_EMEV2
 	bool "Emma Mobile EV2"
@@ -85,7 +85,6 @@
 	select CPU_V7
 	select SH_CLK_CPG
 	select RENESAS_IRQC
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select SYS_SUPPORTS_SH_CMT
 	select SYS_SUPPORTS_SH_TMU
@@ -264,7 +263,6 @@
 config MACH_KZM9G
 	bool "KZM-A9-GT board"
 	depends on ARCH_SH73A0
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_REQUIRE_GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
diff --git a/arch/arm/mach-spear/Kconfig b/arch/arm/mach-spear/Kconfig
index 0786249..90df202 100644
--- a/arch/arm/mach-spear/Kconfig
+++ b/arch/arm/mach-spear/Kconfig
@@ -14,7 +14,6 @@
 config ARCH_SPEAR13XX
 	bool "ST SPEAr13xx"
 	depends on ARCH_MULTI_V7 || PLAT_SPEAR_SINGLE
-	select ARCH_HAS_CPUFREQ
 	select ARM_GIC
 	select GPIO_SPEAR_SPICS
 	select HAVE_ARM_SCU if SMP
diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig
index abf9ee9..7e33e9d 100644
--- a/arch/arm/mach-sti/Kconfig
+++ b/arch/arm/mach-sti/Kconfig
@@ -1,5 +1,5 @@
 menuconfig ARCH_STI
-	bool "STMicroelectronics Consumer Electronics SOCs with Device Trees" if ARCH_MULTI_V7
+	bool "STMicroelectronics Consumer Electronics SOCs" if ARCH_MULTI_V7
 	select ARM_GIC
 	select ARM_GLOBAL_TIMER
 	select PINCTRL
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index e16999e..0953996 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -1,6 +1,5 @@
-config ARCH_TEGRA
+menuconfig ARCH_TEGRA
 	bool "NVIDIA Tegra" if ARCH_MULTI_V7
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_TRUSTED_FOUNDATIONS
 	select ARM_GIC
@@ -16,8 +15,7 @@
 	help
 	  This enables support for NVIDIA Tegra based systems.
 
-menu "NVIDIA Tegra options"
-	depends on ARCH_TEGRA
+if ARCH_TEGRA
 
 config ARCH_TEGRA_2x_SOC
 	bool "Enable support for Tegra20 family"
@@ -69,4 +67,4 @@
 	  which controls AHB bus master arbitration and some
 	  performance parameters(priority, prefech size).
 
-endmenu
+endif
diff --git a/arch/arm/mach-u300/Kconfig b/arch/arm/mach-u300/Kconfig
index e3a96d7..bc51a71 100644
--- a/arch/arm/mach-u300/Kconfig
+++ b/arch/arm/mach-u300/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_U300
+menuconfig ARCH_U300
 	bool "ST-Ericsson U300 Series" if ARCH_MULTI_V5
 	depends on MMU
 	select ARCH_REQUIRE_GPIOLIB
@@ -16,8 +16,6 @@
 
 if ARCH_U300
 
-menu "ST-Ericsson AB U300/U335 Platform"
-
 config MACH_U300
 	depends on ARCH_U300
 	bool "U300"
@@ -43,6 +41,4 @@
 		you don't need it. Selecting this will activate the
 		SPI framework and ARM PL022 support.
 
-endmenu
-
 endif
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index b41a42d..5be7c45 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -1,9 +1,8 @@
-config ARCH_U8500
+menuconfig ARCH_U8500
 	bool "ST-Ericsson U8500 Series" if ARCH_MULTI_V7
 	depends on MMU
 	select AB8500_CORE
 	select ABX500_CORE
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_ERRATA_754322
@@ -34,8 +33,6 @@
 	select REGULATOR
 	select REGULATOR_DB8500_PRCMU
 
-menu "Ux500 target platform (boards)"
-
 config MACH_MOP500
 	bool "U8500 Development platform, MOP500 versions"
 	select I2C
@@ -68,8 +65,6 @@
 	  a working kernel. If everything else is disabled, this
 	  automatically enables MACH_MOP500.
 
-endmenu
-
 config UX500_DEBUG_UART
 	int "Ux500 UART to use for low-level debug"
 	default 2
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 90249cf..99c1f15 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_VEXPRESS
+menuconfig ARCH_VEXPRESS
 	bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_BIG_ENDIAN
@@ -37,8 +37,7 @@
 	  platforms. The traditional (ATAGs) boot method is not usable on
 	  these boards with this option.
 
-menu "Versatile Express platform type"
-	depends on ARCH_VEXPRESS
+if ARCH_VEXPRESS
 
 config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 	bool "Enable A5 and A9 only errata work-arounds"
@@ -65,7 +64,6 @@
 
 config ARCH_VEXPRESS_SPC
 	bool "Versatile Express Serial Power Controller (SPC)"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select PM_OPP
 	help
@@ -83,4 +81,4 @@
 	  Support for CPU and cluster power management on Versatile Express
 	  with a TC2 (A15x2 A7x3) big.LITTLE core tile.
 
-endmenu
+endif
diff --git a/arch/arm/mach-vt8500/Kconfig b/arch/arm/mach-vt8500/Kconfig
index 08f56a4..aaaa24f 100644
--- a/arch/arm/mach-vt8500/Kconfig
+++ b/arch/arm/mach-vt8500/Kconfig
@@ -1,6 +1,5 @@
 config ARCH_VT8500
 	bool
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
 	select VT8500_TIMER
diff --git a/arch/arm/mach-zynq/Kconfig b/arch/arm/mach-zynq/Kconfig
index 573e0db..0c164f8 100644
--- a/arch/arm/mach-zynq/Kconfig
+++ b/arch/arm/mach-zynq/Kconfig
@@ -1,6 +1,5 @@
 config ARCH_ZYNQ
 	bool "Xilinx Zynq ARM Cortex A9 Platform" if ARCH_MULTI_V7
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 243dfcb..301b892 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -35,27 +35,15 @@
 	  Base platform power management code for samsung code
 
 if PLAT_SAMSUNG
+menu "Samsung Common options"
 
 # boot configurations
 
 comment "Boot options"
 
-config S3C_BOOT_ERROR_RESET
-	bool "S3C Reboot on decompression error"
-	help
-	  Say y here to use the watchdog to reset the system if the
-	  kernel decompressor detects an error during decompression.
-
-config S3C_BOOT_UART_FORCE_FIFO
-       bool "Force UART FIFO on during boot process"
-       default y
-       help
-         Say Y here to force the UART FIFOs on during the kernel
-	 uncompressor
-
-
 config S3C_LOWLEVEL_UART_PORT
 	int "S3C UART to use for low-level messages"
+	depends on ARCH_S3C64XX
 	default 0
 	help
 	  Choice of which UART port to use for the low-level messages,
@@ -407,17 +395,16 @@
 	  Include legacy GPIO power management code for platforms not using
 	  pinctrl-samsung driver.
 
-endif
-
 config SAMSUNG_DMADEV
-	bool
-	select ARM_AMBA
+	bool "Use legacy Samsung DMA abstraction"
+	depends on CPU_S5PV210 || CPU_S5PC100 || ARCH_S5P64X0 || ARCH_S3C64XX
 	select DMADEVICES
-	select PL330_DMA if (ARCH_EXYNOS5 || ARCH_EXYNOS4 || CPU_S5PV210 || CPU_S5PC100 || \
-					CPU_S5P6450 || CPU_S5P6440)
+	default y
 	help
 	  Use DMA device engine for PL330 DMAC.
 
+endif
+
 config S5P_DEV_MFC
 	bool
 	help
@@ -503,4 +490,5 @@
 	default "2" if DEBUG_S3C_UART2
 	default "3" if DEBUG_S3C_UART3
 
+endmenu
 endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7295419..a474de34 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,8 +1,9 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_HAS_OPP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
index 1247ca1..6541962 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -24,3 +24,7 @@
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
 };
+
+&serial0 {
+	status = "ok";
+};
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index c5f0a47..40aa96c 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -273,8 +273,9 @@
 		};
 
 		serial0: serial@1c020000 {
+			status = "disabled";
 			device_type = "serial";
-			compatible = "ns16550";
+			compatible = "ns16550a";
 			reg = <0 0x1c020000 0x0 0x1000>;
 			reg-shift = <2>;
 			clock-frequency = <10000000>; /* Updated by bootloader */
@@ -282,6 +283,39 @@
 			interrupts = <0x0 0x4c 0x4>;
 		};
 
+		serial1: serial@1c021000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c021000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4d 0x4>;
+		};
+
+		serial2: serial@1c022000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c022000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4e 0x4>;
+		};
+
+		serial3: serial@1c023000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c023000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4f 0x4>;
+		};
+
 		phy1: phy@1f21a000 {
 			compatible = "apm,xgene-phy";
 			reg = <0x0 0x1f21a000 0x0 0x100>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 157e1d8..3421f31 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -6,9 +6,18 @@
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
 # CONFIG_UTS_NS is not set
 # CONFIG_IPC_NS is not set
 # CONFIG_PID_NS is not set
@@ -27,6 +36,7 @@
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
+CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
@@ -45,6 +55,7 @@
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DMA_CMA=y
+CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
@@ -53,6 +64,7 @@
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
+CONFIG_TUN=y
 CONFIG_SMC91X=y
 CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
@@ -85,6 +97,8 @@
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
+CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=y
 CONFIG_VFAT_FS=y
@@ -104,6 +118,7 @@
 CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_FTRACE is not set
+CONFIG_SECURITY=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
 CONFIG_CRYPTO_SHA1_ARM64_CE=y
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index b9e6eaf41..dc45701 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -3,14 +3,6 @@
  *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
- * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S
- *
- * Copyright (c) 2009 Intel Corp.
- *   Author: Huang Ying <ying.huang@intel.com>
- *           Vinodh Gopal
- *           Erdinc Ozturk
- *           Deniz Karakoyunlu
- *
  * 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.
@@ -19,13 +11,15 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-	DATA	.req	v0
-	SHASH	.req	v1
-	IN1	.req	v2
+	SHASH	.req	v0
+	SHASH2	.req	v1
 	T1	.req	v2
 	T2	.req	v3
-	T3	.req	v4
-	VZR	.req	v5
+	MASK	.req	v4
+	XL	.req	v5
+	XM	.req	v6
+	XH	.req	v7
+	IN1	.req	v7
 
 	.text
 	.arch		armv8-a+crypto
@@ -35,61 +29,51 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{DATA.16b}, [x1]
 	ld1		{SHASH.16b}, [x3]
-	eor		VZR.16b, VZR.16b, VZR.16b
+	ld1		{XL.16b}, [x1]
+	movi		MASK.16b, #0xe1
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	shl		MASK.2d, MASK.2d, #57
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	/* do the head block first, if supplied */
 	cbz		x4, 0f
-	ld1		{IN1.2d}, [x4]
+	ld1		{T1.2d}, [x4]
 	b		1f
 
-0:	ld1		{IN1.2d}, [x2], #16
+0:	ld1		{T1.2d}, [x2], #16
 	sub		w0, w0, #1
-1:	ext		IN1.16b, IN1.16b, IN1.16b, #8
-CPU_LE(	rev64		IN1.16b, IN1.16b	)
-	eor		DATA.16b, DATA.16b, IN1.16b
 
-	/* multiply DATA by SHASH in GF(2^128) */
-	ext		T2.16b, DATA.16b, DATA.16b, #8
-	ext		T3.16b, SHASH.16b, SHASH.16b, #8
-	eor		T2.16b, T2.16b, DATA.16b
-	eor		T3.16b, T3.16b, SHASH.16b
+1:	/* multiply XL by SHASH in GF(2^128) */
+CPU_LE(	rev64		T1.16b, T1.16b	)
 
-	pmull2		T1.1q, SHASH.2d, DATA.2d	// a1 * b1
-	pmull		DATA.1q, SHASH.1d, DATA.1d	// a0 * b0
-	pmull		T2.1q, T2.1d, T3.1d		// (a1 + a0)(b1 + b0)
-	eor		T2.16b, T2.16b, T1.16b		// (a0 * b1) + (a1 * b0)
-	eor		T2.16b, T2.16b, DATA.16b
-
-	ext		T3.16b, VZR.16b, T2.16b, #8
-	ext		T2.16b, T2.16b, VZR.16b, #8
-	eor		DATA.16b, DATA.16b, T3.16b
-	eor		T1.16b, T1.16b, T2.16b	// <T1:DATA> is result of
-						// carry-less multiplication
-
-	/* first phase of the reduction */
-	shl		T3.2d, DATA.2d, #1
-	eor		T3.16b, T3.16b, DATA.16b
-	shl		T3.2d, T3.2d, #5
-	eor		T3.16b, T3.16b, DATA.16b
-	shl		T3.2d, T3.2d, #57
-	ext		T2.16b, VZR.16b, T3.16b, #8
-	ext		T3.16b, T3.16b, VZR.16b, #8
-	eor		DATA.16b, DATA.16b, T2.16b
-	eor		T1.16b, T1.16b, T3.16b
-
-	/* second phase of the reduction */
-	ushr		T2.2d, DATA.2d, #5
-	eor		T2.16b, T2.16b, DATA.16b
-	ushr		T2.2d, T2.2d, #1
-	eor		T2.16b, T2.16b, DATA.16b
-	ushr		T2.2d, T2.2d, #1
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
 	eor		T1.16b, T1.16b, T2.16b
-	eor		DATA.16b, DATA.16b, T1.16b
+	eor		XL.16b, XL.16b, IN1.16b
+
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
 
 	cbnz		w0, 0b
 
-	st1		{DATA.16b}, [x1]
+	st1		{XL.16b}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index b92baf3..833ec1e 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -67,11 +67,12 @@
 		blocks = len / GHASH_BLOCK_SIZE;
 		len %= GHASH_BLOCK_SIZE;
 
-		kernel_neon_begin_partial(6);
+		kernel_neon_begin_partial(8);
 		pmull_ghash_update(blocks, ctx->digest, src, key,
 				   partial ? ctx->buf : NULL);
 		kernel_neon_end();
 		src += blocks * GHASH_BLOCK_SIZE;
+		partial = 0;
 	}
 	if (len)
 		memcpy(ctx->buf + partial, src, len);
@@ -88,7 +89,7 @@
 
 		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
 
-		kernel_neon_begin_partial(6);
+		kernel_neon_begin_partial(8);
 		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
 		kernel_neon_end();
 	}
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 42c7eec..0b3fcf8 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -30,7 +30,6 @@
 generic-y += mutex.h
 generic-y += pci.h
 generic-y += poll.h
-generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 3a4572e..dc82e52a 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -26,8 +26,6 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops coherent_swiotlb_dma_ops;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 598cc38..5797020 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -246,7 +246,7 @@
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
diff --git a/arch/arm64/include/uapi/asm/posix_types.h b/arch/arm64/include/uapi/asm/posix_types.h
new file mode 100644
index 0000000..7985ff6
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/posix_types.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_POSIX_TYPES_H
+#define __ASM_POSIX_TYPES_H
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+
+#include <asm-generic/posix_types.h>
+
+#endif /*  __ASM_POSIX_TYPES_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index b72cf40..ee469be 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -58,7 +58,7 @@
 
 struct esr_context {
 	struct _aarch64_ctx head;
-	u64 esr;
+	__u64 esr;
 };
 
 #endif /* _UAPI__ASM_SIGCONTEXT_H */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index b051871..aa5f9fc 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -205,7 +205,7 @@
  *
  * Run ftrace_return_to_handler() before going back to parent.
  * @fp is checked against the value passed by ftrace_graph_caller()
- * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
  */
 ENTRY(return_to_handler)
 	str	x0, [sp, #-16]!
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index bf017f4..9ce04ba 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -279,7 +279,6 @@
 	 */
 	mrs	x0, far_el1
 	enable_dbg
-	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
 el1_undef:
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 3e926b9..9fde010 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -655,11 +655,16 @@
 			reg = task_pt_regs(target)->regs[idx];
 		}
 
-		ret = copy_to_user(ubuf, &reg, sizeof(reg));
-		if (ret)
-			break;
+		if (kbuf) {
+			memcpy(kbuf, &reg, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_to_user(ubuf, &reg, sizeof(reg));
+			if (ret)
+				break;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 	}
 
 	return ret;
@@ -689,11 +694,16 @@
 		unsigned int idx = start + i;
 		compat_ulong_t reg;
 
-		ret = copy_from_user(&reg, ubuf, sizeof(reg));
-		if (ret)
-			return ret;
+		if (kbuf) {
+			memcpy(&reg, kbuf, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_from_user(&reg, ubuf, sizeof(reg));
+			if (ret)
+				return ret;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 
 		switch (idx) {
 		case 15:
@@ -827,6 +837,7 @@
 				    compat_ulong_t val)
 {
 	int ret;
+	mm_segment_t old_fs = get_fs();
 
 	if (off & 3 || off >= COMPAT_USER_SZ)
 		return -EIO;
@@ -834,10 +845,13 @@
 	if (off >= sizeof(compat_elf_gregset_t))
 		return 0;
 
+	set_fs(KERNEL_DS);
 	ret = copy_regset_from_user(tsk, &user_aarch32_view,
 				    REGSET_COMPAT_GPR, off,
 				    sizeof(compat_ulong_t),
 				    &val);
+	set_fs(old_fs);
+
 	return ret;
 }
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 091d428..f43db8a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -71,7 +71,7 @@
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
 		unsigned long max_dma_phys =
-			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+			(unsigned long)(dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1);
 		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
 		zone_size[ZONE_DMA] = max_dma - min;
 	}
@@ -126,6 +126,8 @@
 
 void __init arm64_memblock_init(void)
 {
+	phys_addr_t dma_phys_limit = 0;
+
 	/* Register the kernel text, kernel data and initrd with memblock */
 	memblock_reserve(__pa(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -141,7 +143,11 @@
 	memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
 
 	early_init_fdt_scan_reserved_mem();
-	dma_contiguous_reserve(0);
+
+	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		dma_phys_limit = dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1;
+	dma_contiguous_reserve(dma_phys_limit);
 
 	memblock_allow_resize();
 	memblock_dump_all();
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 1a871b7..344387a 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -242,7 +242,7 @@
 	struct pci_dev	*sac_only_dev;
 };
 
-static struct ioc *ioc_list;
+static struct ioc *ioc_list, *ioc_found;
 static int reserve_sba_gart = 1;
 
 static SBA_INLINE void sba_mark_invalid(struct ioc *, dma_addr_t, size_t);
@@ -1809,20 +1809,13 @@
 	{ SX2000_IOC_ID, "sx2000", NULL },
 };
 
-static struct ioc *
-ioc_init(unsigned long hpa, void *handle)
+static void ioc_init(unsigned long hpa, struct ioc *ioc)
 {
-	struct ioc *ioc;
 	struct ioc_iommu *info;
 
-	ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
-	if (!ioc)
-		return NULL;
-
 	ioc->next = ioc_list;
 	ioc_list = ioc;
 
-	ioc->handle = handle;
 	ioc->ioc_hpa = ioremap(hpa, 0x1000);
 
 	ioc->func_id = READ_REG(ioc->ioc_hpa + IOC_FUNC_ID);
@@ -1863,8 +1856,6 @@
 		"%s %d.%d HPA 0x%lx IOVA space %dMb at 0x%lx\n",
 		ioc->name, (ioc->rev >> 4) & 0xF, ioc->rev & 0xF,
 		hpa, ioc->iov_size >> 20, ioc->ibase);
-
-	return ioc;
 }
 
 
@@ -2031,22 +2022,21 @@
 #endif
 }
 
-static int
-acpi_sba_ioc_add(struct acpi_device *device,
-		 const struct acpi_device_id *not_used)
+static void acpi_sba_ioc_add(struct ioc *ioc)
 {
-	struct ioc *ioc;
+	acpi_handle handle = ioc->handle;
 	acpi_status status;
 	u64 hpa, length;
 	struct acpi_device_info *adi;
 
-	status = hp_acpi_csr_space(device->handle, &hpa, &length);
+	ioc_found = ioc->next;
+	status = hp_acpi_csr_space(handle, &hpa, &length);
 	if (ACPI_FAILURE(status))
-		return 1;
+		goto err;
 
-	status = acpi_get_object_info(device->handle, &adi);
+	status = acpi_get_object_info(handle, &adi);
 	if (ACPI_FAILURE(status))
-		return 1;
+		goto err;
 
 	/*
 	 * For HWP0001, only SBA appears in ACPI namespace.  It encloses the PCI
@@ -2067,13 +2057,13 @@
 	if (!iovp_shift)
 		iovp_shift = 12;
 
-	ioc = ioc_init(hpa, device->handle);
-	if (!ioc)
-		return 1;
-
+	ioc_init(hpa, ioc);
 	/* setup NUMA node association */
-	sba_map_ioc_to_node(ioc, device->handle);
-	return 0;
+	sba_map_ioc_to_node(ioc, handle);
+	return;
+
+ err:
+	kfree(ioc);
 }
 
 static const struct acpi_device_id hp_ioc_iommu_device_ids[] = {
@@ -2081,9 +2071,26 @@
 	{"HWP0004", 0},
 	{"", 0},
 };
+
+static int acpi_sba_ioc_attach(struct acpi_device *device,
+			       const struct acpi_device_id *not_used)
+{
+	struct ioc *ioc;
+
+	ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
+	if (!ioc)
+		return -ENOMEM;
+
+	ioc->next = ioc_found;
+	ioc_found = ioc;
+	ioc->handle = device->handle;
+	return 1;
+}
+
+
 static struct acpi_scan_handler acpi_sba_ioc_handler = {
 	.ids	= hp_ioc_iommu_device_ids,
-	.attach	= acpi_sba_ioc_add,
+	.attach	= acpi_sba_ioc_attach,
 };
 
 static int __init acpi_sba_ioc_init_acpi(void)
@@ -2118,9 +2125,12 @@
 #endif
 
 	/*
-	 * ioc_list should be populated by the acpi_sba_ioc_handler's .attach()
+	 * ioc_found should be populated by the acpi_sba_ioc_handler's .attach()
 	 * routine, but that only happens if acpi_scan_init() has already run.
 	 */
+	while (ioc_found)
+		acpi_sba_ioc_add(ioc_found);
+
 	if (!ioc_list) {
 #ifdef CONFIG_IA64_GENERIC
 		/*
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 8df022c..fd09a10 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -45,7 +45,8 @@
 CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
@@ -240,7 +241,6 @@
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
 CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -456,6 +456,7 @@
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
+CONFIG_DIAG288_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index c81a74e..b061180 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -45,7 +45,8 @@
 CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
@@ -238,7 +239,6 @@
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
 CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -453,6 +453,7 @@
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
+CONFIG_DIAG288_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index b5ba8fe..d279baa 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -43,7 +43,8 @@
 CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
@@ -236,7 +237,6 @@
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
 CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -451,6 +451,7 @@
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
+CONFIG_DIAG288_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index cef073c..948e0e0 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -8,7 +8,8 @@
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 # CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 # CONFIG_HOTPLUG_CPU is not set
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 4557cb7..2e56498 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -135,8 +135,8 @@
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_PI_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_PROVE_RCU=y
@@ -199,4 +199,10 @@
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRC7=m
+# CONFIG_XZ_DEC_X86 is not set
+# CONFIG_XZ_DEC_POWERPC is not set
+# CONFIG_XZ_DEC_IA64 is not set
+# CONFIG_XZ_DEC_ARM is not set
+# CONFIG_XZ_DEC_ARMTHUMB is not set
+# CONFIG_XZ_DEC_SPARC is not set
 CONFIG_CMM=m
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index c28f32a..3815bfe 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -33,10 +33,9 @@
 
 static inline void set_user_asce(struct mm_struct *mm)
 {
-	pgd_t *pgd = mm->pgd;
-
-	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
-	set_fs(current->thread.mm_segment);
+	S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
+	if (current->thread.mm_segment.ar4)
+		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	set_cpu_flag(CIF_ASCE);
 }
 
@@ -70,12 +69,11 @@
 	/* Clear old ASCE by loading the kernel ASCE. */
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
-	/* Delay loading of the new ASCE to control registers CR1 & CR7 */
-	set_cpu_flag(CIF_ASCE);
 	atomic_inc(&next->context.attach_count);
 	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
@@ -84,17 +82,18 @@
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 
-	if (!mm)
-		return;
-	preempt_disable();
-	while (atomic_read(&mm->context.attach_count) >> 16)
-		cpu_relax();
+	load_kernel_asce();
+	if (mm) {
+		preempt_disable();
+		while (atomic_read(&mm->context.attach_count) >> 16)
+			cpu_relax();
 
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-	set_user_asce(mm);
-	if (mm->context.flush_mm)
-		__tlb_flush_mm(mm);
-	preempt_enable();
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		if (mm->context.flush_mm)
+			__tlb_flush_mm(mm);
+		preempt_enable();
+	}
+	set_fs(current->thread.mm_segment);
 }
 
 #define enter_lazy_tlb(mm,tsk)	do { } while (0)
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 29c81f8..df38c70 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -134,8 +134,4 @@
 	prev = __switch_to(prev,next);					\
 } while (0)
 
-#define finish_arch_switch(prev) do {					     \
-	set_fs(current->thread.mm_segment);				     \
-} while (0)
-
 #endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h
index 200e063..3e077b2 100644
--- a/arch/s390/include/uapi/asm/ucontext.h
+++ b/arch/s390/include/uapi/asm/ucontext.h
@@ -16,7 +16,9 @@
 	struct ucontext  *uc_link;
 	stack_t		  uc_stack;
 	_sigregs	  uc_mcontext;
-	unsigned long	  uc_sigmask[2];
+	sigset_t	  uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char	  __unused[128 - sizeof(sigset_t)];
 	unsigned long	  uc_gprs_high[16];
 };
 
@@ -27,7 +29,9 @@
 	struct ucontext  *uc_link;
 	stack_t		  uc_stack;
 	_sigregs          uc_mcontext;
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
+	sigset_t	  uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char	  __unused[128 - sizeof(sigset_t)];
 };
 
 #endif /* !_ASM_S390_UCONTEXT_H */
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 39ddfdb..70d4b7c 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -69,7 +69,9 @@
 	__u32			uc_link;	/* pointer */	
 	compat_stack_t		uc_stack;
 	_sigregs32		uc_mcontext;
-	compat_sigset_t		uc_sigmask;	/* mask last for extensibility */
+	compat_sigset_t		uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char		__unused[128 - sizeof(compat_sigset_t)];
 };
 
 struct stat64_emu31;
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 503e6d9..df922f5 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -124,7 +124,7 @@
 				      u64 *output, unsigned int len,
 				      u64 *iv);
 
-struct aes_ops aes128_ops = {
+static struct aes_ops aes128_ops = {
 	.encrypt		= aes_sparc64_encrypt_128,
 	.decrypt		= aes_sparc64_decrypt_128,
 	.load_encrypt_keys	= aes_sparc64_load_encrypt_keys_128,
@@ -136,7 +136,7 @@
 	.ctr_crypt		= aes_sparc64_ctr_crypt_128,
 };
 
-struct aes_ops aes192_ops = {
+static struct aes_ops aes192_ops = {
 	.encrypt		= aes_sparc64_encrypt_192,
 	.decrypt		= aes_sparc64_decrypt_192,
 	.load_encrypt_keys	= aes_sparc64_load_encrypt_keys_192,
@@ -148,7 +148,7 @@
 	.ctr_crypt		= aes_sparc64_ctr_crypt_192,
 };
 
-struct aes_ops aes256_ops = {
+static struct aes_ops aes256_ops = {
 	.encrypt		= aes_sparc64_encrypt_256,
 	.decrypt		= aes_sparc64_decrypt_256,
 	.load_encrypt_keys	= aes_sparc64_load_encrypt_keys_256,
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index f08fe51..7aed2be 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,11 +20,11 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-extern int __atomic_add_return(int, atomic_t *);
-extern int atomic_cmpxchg(atomic_t *, int, int);
+int __atomic_add_return(int, atomic_t *);
+int atomic_cmpxchg(atomic_t *, int, int);
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-extern int __atomic_add_unless(atomic_t *, int, int);
-extern void atomic_set(atomic_t *, int);
+int __atomic_add_unless(atomic_t *, int, int);
+void atomic_set(atomic_t *, int);
 
 #define atomic_read(v)          (*(volatile int *)&(v)->counter)
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 8b2f1bd..bb894c8 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -20,15 +20,15 @@
 #define atomic_set(v, i)	(((v)->counter) = i)
 #define atomic64_set(v, i)	(((v)->counter) = i)
 
-extern void atomic_add(int, atomic_t *);
-extern void atomic64_add(long, atomic64_t *);
-extern void atomic_sub(int, atomic_t *);
-extern void atomic64_sub(long, atomic64_t *);
+void atomic_add(int, atomic_t *);
+void atomic64_add(long, atomic64_t *);
+void atomic_sub(int, atomic_t *);
+void atomic64_sub(long, atomic64_t *);
 
-extern int atomic_add_ret(int, atomic_t *);
-extern long atomic64_add_ret(long, atomic64_t *);
-extern int atomic_sub_ret(int, atomic_t *);
-extern long atomic64_sub_ret(long, atomic64_t *);
+int atomic_add_ret(int, atomic_t *);
+long atomic64_add_ret(long, atomic64_t *);
+int atomic_sub_ret(int, atomic_t *);
+long atomic64_sub_ret(long, atomic64_t *);
 
 #define atomic_dec_return(v) atomic_sub_ret(1, v)
 #define atomic64_dec_return(v) atomic64_sub_ret(1, v)
@@ -107,6 +107,6 @@
 
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
-extern long atomic64_dec_if_positive(atomic64_t *v);
+long atomic64_dec_if_positive(atomic64_t *v);
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/sparc/include/asm/auxio.h b/arch/sparc/include/asm/auxio.h
index 13dc67f..3e09a07 100644
--- a/arch/sparc/include/asm/auxio.h
+++ b/arch/sparc/include/asm/auxio.h
@@ -1,5 +1,12 @@
 #ifndef ___ASM_SPARC_AUXIO_H
 #define ___ASM_SPARC_AUXIO_H
+
+#ifndef __ASSEMBLY__
+
+extern void __iomem *auxio_register;
+
+#endif /* ifndef __ASSEMBLY__ */
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/auxio_64.h>
 #else
diff --git a/arch/sparc/include/asm/auxio_32.h b/arch/sparc/include/asm/auxio_32.h
index 3a31977..5d685df 100644
--- a/arch/sparc/include/asm/auxio_32.h
+++ b/arch/sparc/include/asm/auxio_32.h
@@ -34,8 +34,8 @@
  * NOTE: these routines are implementation dependent--
  * understand the hardware you are querying!
  */
-extern void set_auxio(unsigned char bits_on, unsigned char bits_off);
-extern unsigned char get_auxio(void); /* .../asm/floppy.h */
+void set_auxio(unsigned char bits_on, unsigned char bits_off);
+unsigned char get_auxio(void); /* .../asm/floppy.h */
 
 /*
  * The following routines are provided for driver-compatibility
@@ -78,7 +78,7 @@
 
 
 /* AUXIO2 (Power Off Control) */
-extern __volatile__ unsigned char * auxio_power_register;
+extern volatile u8 __iomem *auxio_power_register;
 
 #define	AUXIO_POWER_DETECT_FAILURE	32
 #define	AUXIO_POWER_CLEAR_FAILURE	2
diff --git a/arch/sparc/include/asm/auxio_64.h b/arch/sparc/include/asm/auxio_64.h
index f61cd1e..6079e59 100644
--- a/arch/sparc/include/asm/auxio_64.h
+++ b/arch/sparc/include/asm/auxio_64.h
@@ -75,8 +75,6 @@
 
 #ifndef __ASSEMBLY__
 
-extern void __iomem *auxio_register;
-
 #define AUXIO_LTE_ON	1
 #define AUXIO_LTE_OFF	0
 
@@ -84,7 +82,7 @@
  *
  * on - AUXIO_LTE_ON or AUXIO_LTE_OFF
  */
-extern void auxio_set_lte(int on);
+void auxio_set_lte(int on);
 
 #define AUXIO_LED_ON	1
 #define AUXIO_LED_OFF	0
@@ -93,7 +91,7 @@
  *
  * on - AUXIO_LED_ON or AUXIO_LED_OFF
  */
-extern void auxio_set_led(int on);
+void auxio_set_led(int on);
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/sparc/include/asm/bitext.h b/arch/sparc/include/asm/bitext.h
index 297b2f2..9c988bf 100644
--- a/arch/sparc/include/asm/bitext.h
+++ b/arch/sparc/include/asm/bitext.h
@@ -20,8 +20,8 @@
 	int num_colors;
 };
 
-extern int bit_map_string_get(struct bit_map *t, int len, int align);
-extern void bit_map_clear(struct bit_map *t, int offset, int len);
-extern void bit_map_init(struct bit_map *t, unsigned long *map, int size);
+int bit_map_string_get(struct bit_map *t, int len, int align);
+void bit_map_clear(struct bit_map *t, int offset, int len);
+void bit_map_init(struct bit_map *t, unsigned long *map, int size);
 
 #endif /* defined(_SPARC_BITEXT_H) */
diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h
index 88c9a96..600ed1d 100644
--- a/arch/sparc/include/asm/bitops_32.h
+++ b/arch/sparc/include/asm/bitops_32.h
@@ -18,9 +18,9 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
-extern unsigned long ___set_bit(unsigned long *addr, unsigned long mask);
-extern unsigned long ___clear_bit(unsigned long *addr, unsigned long mask);
-extern unsigned long ___change_bit(unsigned long *addr, unsigned long mask);
+unsigned long ___set_bit(unsigned long *addr, unsigned long mask);
+unsigned long ___clear_bit(unsigned long *addr, unsigned long mask);
+unsigned long ___change_bit(unsigned long *addr, unsigned long mask);
 
 /*
  * Set bit 'nr' in 32-bit quantity at address 'addr' where bit '0'
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index f1a051c..2d52240 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -15,12 +15,12 @@
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 
-extern int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
-extern int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
-extern int test_and_change_bit(unsigned long nr, volatile unsigned long *addr);
-extern void set_bit(unsigned long nr, volatile unsigned long *addr);
-extern void clear_bit(unsigned long nr, volatile unsigned long *addr);
-extern void change_bit(unsigned long nr, volatile unsigned long *addr);
+int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
+int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
+int test_and_change_bit(unsigned long nr, volatile unsigned long *addr);
+void set_bit(unsigned long nr, volatile unsigned long *addr);
+void clear_bit(unsigned long nr, volatile unsigned long *addr);
+void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #include <asm-generic/bitops/non-atomic.h>
 
@@ -30,8 +30,8 @@
 
 #ifdef __KERNEL__
 
-extern int ffs(int x);
-extern unsigned long __ffs(unsigned long);
+int ffs(int x);
+unsigned long __ffs(unsigned long);
 
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/sched.h>
@@ -41,10 +41,10 @@
  * of bits set) of a N-bit word
  */
 
-extern unsigned long __arch_hweight64(__u64 w);
-extern unsigned int __arch_hweight32(unsigned int w);
-extern unsigned int __arch_hweight16(unsigned int w);
-extern unsigned int __arch_hweight8(unsigned int w);
+unsigned long __arch_hweight64(__u64 w);
+unsigned int __arch_hweight32(unsigned int w);
+unsigned int __arch_hweight16(unsigned int w);
+unsigned int __arch_hweight8(unsigned int w);
 
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
diff --git a/arch/sparc/include/asm/btext.h b/arch/sparc/include/asm/btext.h
index 9b2bc6b..75a32b1 100644
--- a/arch/sparc/include/asm/btext.h
+++ b/arch/sparc/include/asm/btext.h
@@ -1,6 +1,6 @@
 #ifndef _SPARC_BTEXT_H
 #define _SPARC_BTEXT_H
 
-extern int btext_find_display(void);
+int btext_find_display(void);
 
 #endif /* _SPARC_BTEXT_H */
diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h
index 6bd9f43..eaa8f8d 100644
--- a/arch/sparc/include/asm/bug.h
+++ b/arch/sparc/include/asm/bug.h
@@ -5,7 +5,7 @@
 #include <linux/compiler.h>
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-extern void do_BUG(const char *file, int line);
+void do_BUG(const char *file, int line);
 #define BUG() do {					\
 	do_BUG(__FILE__, __LINE__);			\
 	__builtin_trap();				\
@@ -20,6 +20,6 @@
 #include <asm-generic/bug.h>
 
 struct pt_regs;
-extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));
+void __noreturn die_if_kernel(char *str, struct pt_regs *regs);
 
 #endif
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index bb014c2..1216400 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -36,7 +36,7 @@
 #define flush_page_for_dma(addr) \
 	sparc32_cachetlb_ops->page_for_dma(addr)
 
-extern void sparc_flush_page_to_ram(struct page *page);
+void sparc_flush_page_to_ram(struct page *page);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 #define flush_dcache_page(page)			sparc_flush_page_to_ram(page)
@@ -51,8 +51,8 @@
  * way the windows are all clean for the next process and the stack
  * frames are up to date.
  */
-extern void flush_user_windows(void);
-extern void kill_user_windows(void);
-extern void flushw_all(void);
+void flush_user_windows(void);
+void kill_user_windows(void);
+void flushw_all(void);
 
 #endif /* _SPARC_CACHEFLUSH_H */
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 301736d..3896537 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -10,7 +10,7 @@
 /* Cache flush operations. */
 #define flushw_all()	__asm__ __volatile__("flushw")
 
-extern void __flushw_user(void);
+void __flushw_user(void);
 #define flushw_user() __flushw_user()
 
 #define flush_user_windows flushw_user
@@ -30,29 +30,29 @@
  * use block commit stores (which invalidate icache lines) during
  * module load, so we need this.
  */
-extern void flush_icache_range(unsigned long start, unsigned long end);
-extern void __flush_icache_page(unsigned long);
+void flush_icache_range(unsigned long start, unsigned long end);
+void __flush_icache_page(unsigned long);
 
-extern void __flush_dcache_page(void *addr, int flush_icache);
-extern void flush_dcache_page_impl(struct page *page);
+void __flush_dcache_page(void *addr, int flush_icache);
+void flush_dcache_page_impl(struct page *page);
 #ifdef CONFIG_SMP
-extern void smp_flush_dcache_page_impl(struct page *page, int cpu);
-extern void flush_dcache_page_all(struct mm_struct *mm, struct page *page);
+void smp_flush_dcache_page_impl(struct page *page, int cpu);
+void flush_dcache_page_all(struct mm_struct *mm, struct page *page);
 #else
 #define smp_flush_dcache_page_impl(page,cpu) flush_dcache_page_impl(page)
 #define flush_dcache_page_all(mm,page) flush_dcache_page_impl(page)
 #endif
 
-extern void __flush_dcache_range(unsigned long start, unsigned long end);
+void __flush_dcache_range(unsigned long start, unsigned long end);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
 
 #define flush_icache_page(vma, pg)	do { } while(0)
 #define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
 
-extern void flush_ptrace_access(struct vm_area_struct *, struct page *,
-				unsigned long uaddr, void *kaddr,
-				unsigned long len, int write);
+void flush_ptrace_access(struct vm_area_struct *, struct page *,
+			 unsigned long uaddr, void *kaddr,
+			 unsigned long len, int write);
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
 	do {								\
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index 04471dc..426b238 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -29,7 +29,7 @@
  *
  * it's best to have buff aligned on a 32-bit boundary
  */
-extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+__wsum csum_partial(const void *buff, int len, __wsum sum);
 
 /* the same as csum_partial, but copies from fs:src while it
  * checksums
@@ -38,7 +38,7 @@
  * better 64-bit) boundary
  */
 
-extern unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *);
+unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *);
 
 static inline __wsum
 csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 2ff81ae..b8779a6 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -29,7 +29,7 @@
  *
  * it's best to have buff aligned on a 32-bit boundary
  */
-extern __wsum csum_partial(const void * buff, int len, __wsum sum);
+__wsum csum_partial(const void * buff, int len, __wsum sum);
 
 /* the same as csum_partial, but copies from user space while it
  * checksums
@@ -37,12 +37,12 @@
  * here even more important to align src and dst on a 32-bit (or even
  * better 64-bit) boundary
  */
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					      int len, __wsum sum);
+__wsum csum_partial_copy_nocheck(const void *src, void *dst,
+				 int len, __wsum sum);
 
-extern long __csum_partial_copy_from_user(const void __user *src,
-					  void *dst, int len,
-					  __wsum sum);
+long __csum_partial_copy_from_user(const void __user *src,
+				   void *dst, int len,
+				   __wsum sum);
 
 static inline __wsum
 csum_partial_copy_from_user(const void __user *src,
@@ -59,9 +59,9 @@
  *	Copy and checksum to user
  */
 #define HAVE_CSUM_COPY_USER
-extern long __csum_partial_copy_to_user(const void *src,
-					void __user *dst, int len,
-					  __wsum sum);
+long __csum_partial_copy_to_user(const void *src,
+				 void __user *dst, int len,
+				 __wsum sum);
 
 static inline __wsum
 csum_and_copy_to_user(const void *src,
@@ -77,7 +77,7 @@
 /* ihl is always 5 or greater, almost always is 5, and iph is word aligned
  * the majority of the time.
  */
-extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 
 /* Fold a partial checksum without adding pseudo headers. */
 static inline __sum16 csum_fold(__wsum sum)
@@ -96,9 +96,9 @@
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned int len,
-					       unsigned short proto,
-					       __wsum sum)
+					unsigned int len,
+					unsigned short proto,
+					__wsum sum)
 {
 	__asm__ __volatile__(
 "	addcc		%1, %0, %0\n"
@@ -116,9 +116,9 @@
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 1fae1a0..32c29a1 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -20,7 +20,7 @@
 	return val;
 }
 
-extern void __xchg_called_with_bad_pointer(void);
+void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
@@ -45,9 +45,9 @@
 #define __HAVE_ARCH_CMPXCHG	1
 
 /* bug catcher for when unsupported size is used - won't link */
-extern void __cmpxchg_called_with_bad_pointer(void);
+void __cmpxchg_called_with_bad_pointer(void);
 /* we only need to support cmpxchg of a u32 on sparc */
-extern unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
+unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 4adefe8..0e1ed6c 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -42,7 +42,7 @@
 
 #define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
-extern void __xchg_called_with_bad_pointer(void);
+void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 				       int size)
@@ -91,7 +91,7 @@
 
 /* This function doesn't exist, so you'll get a linker error
    if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
+void __cmpxchg_called_with_bad_pointer(void);
 
 static inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
diff --git a/arch/sparc/include/asm/cpudata.h b/arch/sparc/include/asm/cpudata.h
index b5976de..128b56b 100644
--- a/arch/sparc/include/asm/cpudata.h
+++ b/arch/sparc/include/asm/cpudata.h
@@ -1,5 +1,15 @@
 #ifndef ___ASM_SPARC_CPUDATA_H
 #define ___ASM_SPARC_CPUDATA_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/threads.h>
+#include <linux/percpu.h>
+
+extern const struct seq_operations cpuinfo_op;
+
+#endif /* !(__ASSEMBLY__) */
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/cpudata_64.h>
 #else
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 050ef35..0e59407 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -8,9 +8,6 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/percpu.h>
-#include <linux/threads.h>
-
 typedef struct {
 	/* Dcache line 1 */
 	unsigned int	__softirq_pending; /* must be 1st, see rtrap.S */
@@ -35,8 +32,6 @@
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
 #define local_cpu_data()	__get_cpu_var(__cpu_data)
 
-extern const struct seq_operations cpuinfo_op;
-
 #endif /* !(__ASSEMBLY__) */
 
 #include <asm/trap_block.h>
diff --git a/arch/sparc/include/asm/delay_32.h b/arch/sparc/include/asm/delay_32.h
index bc9aba2..3fb8ca1 100644
--- a/arch/sparc/include/asm/delay_32.h
+++ b/arch/sparc/include/asm/delay_32.h
@@ -20,8 +20,8 @@
 }
 
 /* This is too messy with inline asm on the Sparc. */
-extern void __udelay(unsigned long usecs, unsigned long lpj);
-extern void __ndelay(unsigned long nsecs, unsigned long lpj);
+void __udelay(unsigned long usecs, unsigned long lpj);
+void __ndelay(unsigned long nsecs, unsigned long lpj);
 
 #ifdef CONFIG_SMP
 #define __udelay_val	cpu_data(smp_processor_id()).udelay_val
diff --git a/arch/sparc/include/asm/delay_64.h b/arch/sparc/include/asm/delay_64.h
index a77aa62..0ba5424 100644
--- a/arch/sparc/include/asm/delay_64.h
+++ b/arch/sparc/include/asm/delay_64.h
@@ -8,8 +8,8 @@
 
 #ifndef __ASSEMBLY__
 
-extern void __delay(unsigned long loops);
-extern void udelay(unsigned long usecs);
+void __delay(unsigned long loops);
+void udelay(unsigned long usecs);
 #define mdelay(n)	udelay((n) * 1000)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/sparc/include/asm/device.h b/arch/sparc/include/asm/device.h
index daa6a8a..bb3f0b0 100644
--- a/arch/sparc/include/asm/device.h
+++ b/arch/sparc/include/asm/device.h
@@ -19,7 +19,7 @@
 	int			numa_node;
 };
 
-extern void of_propagate_archdata(struct platform_device *bus);
+void of_propagate_archdata(struct platform_device *bus);
 
 struct pdev_archdata {
 	struct resource		resource[PROMREG_MAX];
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 05fe53f..1ee0271 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -7,7 +7,7 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 
-extern int dma_supported(struct device *dev, u64 mask);
+int dma_supported(struct device *dev, u64 mask);
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
diff --git a/arch/sparc/include/asm/ebus_dma.h b/arch/sparc/include/asm/ebus_dma.h
index f07a5b5..fcfb494 100644
--- a/arch/sparc/include/asm/ebus_dma.h
+++ b/arch/sparc/include/asm/ebus_dma.h
@@ -22,14 +22,14 @@
 	unsigned char	name[64];
 };
 
-extern int ebus_dma_register(struct ebus_dma_info *p);
-extern int ebus_dma_irq_enable(struct ebus_dma_info *p, int on);
-extern void ebus_dma_unregister(struct ebus_dma_info *p);
-extern int ebus_dma_request(struct ebus_dma_info *p, dma_addr_t bus_addr,
+int ebus_dma_register(struct ebus_dma_info *p);
+int ebus_dma_irq_enable(struct ebus_dma_info *p, int on);
+void ebus_dma_unregister(struct ebus_dma_info *p);
+int ebus_dma_request(struct ebus_dma_info *p, dma_addr_t bus_addr,
 			    size_t len);
-extern void ebus_dma_prepare(struct ebus_dma_info *p, int write);
-extern unsigned int ebus_dma_residue(struct ebus_dma_info *p);
-extern unsigned int ebus_dma_addr(struct ebus_dma_info *p);
-extern void ebus_dma_enable(struct ebus_dma_info *p, int on);
+void ebus_dma_prepare(struct ebus_dma_info *p, int write);
+unsigned int ebus_dma_residue(struct ebus_dma_info *p);
+unsigned int ebus_dma_addr(struct ebus_dma_info *p);
+void ebus_dma_enable(struct ebus_dma_info *p, int on);
 
 #endif /* __ASM_SPARC_EBUS_DMA_H */
diff --git a/arch/sparc/include/asm/floppy_32.h b/arch/sparc/include/asm/floppy_32.h
index fb3f169..071b83e 100644
--- a/arch/sparc/include/asm/floppy_32.h
+++ b/arch/sparc/include/asm/floppy_32.h
@@ -9,11 +9,12 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/idprom.h>
 #include <asm/oplib.h>
 #include <asm/auxio.h>
+#include <asm/setup.h>
+#include <asm/page.h>
 #include <asm/irq.h>
 
 /* We don't need no stinkin' I/O port allocation crap. */
@@ -49,7 +50,6 @@
 
 /* You'll only ever find one controller on a SparcStation anyways. */
 static struct sun_flpy_controller *sun_fdc = NULL;
-extern volatile unsigned char *fdc_status;
 
 struct sun_floppy_ops {
 	unsigned char (*fd_inb)(int port);
@@ -212,13 +212,6 @@
  * underruns.  If non-zero, doing_pdma encodes the direction of
  * the transfer for debugging.  1=read 2=write
  */
-extern char *pdma_vaddr;
-extern unsigned long pdma_size;
-extern volatile int doing_pdma;
-
-/* This is software state */
-extern char *pdma_base;
-extern unsigned long pdma_areasize;
 
 /* Common routines to all controller types on the Sparc. */
 static inline void virtual_dma_init(void)
@@ -263,8 +256,7 @@
 	pdma_areasize = pdma_size;
 }
 
-extern int sparc_floppy_request_irq(unsigned int irq,
-                                    irq_handler_t irq_handler);
+int sparc_floppy_request_irq(unsigned int irq, irq_handler_t irq_handler);
 
 static int sun_fd_request_irq(void)
 {
diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h
index 7c90c50..6257564 100644
--- a/arch/sparc/include/asm/floppy_64.h
+++ b/arch/sparc/include/asm/floppy_64.h
@@ -296,7 +296,7 @@
 static struct sun_pci_dma_op sun_pci_dma_current = { -1U, 0, 0, NULL};
 static struct sun_pci_dma_op sun_pci_dma_pending = { -1U, 0, 0, NULL};
 
-extern irqreturn_t floppy_interrupt(int irq, void *dev_id);
+irqreturn_t floppy_interrupt(int irq, void *dev_id);
 
 static unsigned char sun_pci_fd_inb(unsigned long port)
 {
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index b0f18e9..9ec94ad 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -6,7 +6,7 @@
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
-extern void _mcount(void);
+void _mcount(void);
 #endif
 
 #endif
@@ -22,4 +22,8 @@
 };
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 
+unsigned long prepare_ftrace_return(unsigned long parent,
+				    unsigned long self_addr,
+				    unsigned long frame_pointer);
+
 #endif /* _ASM_SPARC64_FTRACE */
diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h
index 4f9e15c..92ded29 100644
--- a/arch/sparc/include/asm/highmem.h
+++ b/arch/sparc/include/asm/highmem.h
@@ -31,7 +31,7 @@
 extern pgprot_t kmap_prot;
 extern pte_t *pkmap_page_table;
 
-extern void kmap_init(void) __init;
+void kmap_init(void) __init;
 
 /*
  * Right now we initialize only a single pte table. It can be extended
@@ -49,8 +49,8 @@
 
 #define PKMAP_END (PKMAP_ADDR(LAST_PKMAP))
 
-extern void *kmap_high(struct page *page);
-extern void kunmap_high(struct page *page);
+void *kmap_high(struct page *page);
+void kunmap_high(struct page *page);
 
 static inline void *kmap(struct page *page)
 {
@@ -68,8 +68,8 @@
 	kunmap_high(page);
 }
 
-extern void *kmap_atomic(struct page *page);
-extern void __kunmap_atomic(void *kvaddr);
+void *kmap_atomic(struct page *page);
+void __kunmap_atomic(void *kvaddr);
 
 #define flush_cache_kmaps()	flush_cache_all()
 
diff --git a/arch/sparc/include/asm/hvtramp.h b/arch/sparc/include/asm/hvtramp.h
index b2b9b94..04b56f8 100644
--- a/arch/sparc/include/asm/hvtramp.h
+++ b/arch/sparc/include/asm/hvtramp.h
@@ -19,7 +19,7 @@
 	struct hvtramp_mapping	maps[1];
 };
 
-extern void hv_cpu_startup(unsigned long hvdescr_pa);
+void hv_cpu_startup(unsigned long hvdescr_pa);
 
 #endif
 
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index ca121f0..94b39ca 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -98,7 +98,7 @@
 #define HV_FAST_MACH_EXIT		0x00
 
 #ifndef __ASSEMBLY__
-extern void sun4v_mach_exit(unsigned long exit_code);
+void sun4v_mach_exit(unsigned long exit_code);
 #endif
 
 /* Domain services.  */
@@ -127,9 +127,9 @@
 #define HV_FAST_MACH_DESC		0x01
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mach_desc(unsigned long buffer_pa,
-				     unsigned long buf_len,
-				     unsigned long *real_buf_len);
+unsigned long sun4v_mach_desc(unsigned long buffer_pa,
+			      unsigned long buf_len,
+			      unsigned long *real_buf_len);
 #endif
 
 /* mach_sir()
@@ -148,7 +148,7 @@
 #define HV_FAST_MACH_SIR		0x02
 
 #ifndef __ASSEMBLY__
-extern void sun4v_mach_sir(void);
+void sun4v_mach_sir(void);
 #endif
 
 /* mach_set_watchdog()
@@ -204,8 +204,8 @@
 #define HV_FAST_MACH_SET_WATCHDOG	0x05
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mach_set_watchdog(unsigned long timeout,
-					     unsigned long *orig_timeout);
+unsigned long sun4v_mach_set_watchdog(unsigned long timeout,
+				      unsigned long *orig_timeout);
 #endif
 
 /* CPU services.
@@ -250,10 +250,10 @@
 #define HV_FAST_CPU_START		0x10
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_start(unsigned long cpuid,
-				     unsigned long pc,
-				     unsigned long rtba,
-				     unsigned long arg0);
+unsigned long sun4v_cpu_start(unsigned long cpuid,
+			      unsigned long pc,
+			      unsigned long rtba,
+			      unsigned long arg0);
 #endif
 
 /* cpu_stop()
@@ -278,7 +278,7 @@
 #define HV_FAST_CPU_STOP		0x11
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_stop(unsigned long cpuid);
+unsigned long sun4v_cpu_stop(unsigned long cpuid);
 #endif
 
 /* cpu_yield()
@@ -295,7 +295,7 @@
 #define HV_FAST_CPU_YIELD		0x12
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_yield(void);
+unsigned long sun4v_cpu_yield(void);
 #endif
 
 /* cpu_qconf()
@@ -341,9 +341,9 @@
 #define  HV_CPU_QUEUE_NONRES_ERROR	 0x3f
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_qconf(unsigned long type,
-				     unsigned long queue_paddr,
-				     unsigned long num_queue_entries);
+unsigned long sun4v_cpu_qconf(unsigned long type,
+			      unsigned long queue_paddr,
+			      unsigned long num_queue_entries);
 #endif
 
 /* cpu_qinfo()
@@ -394,7 +394,9 @@
 #define HV_FAST_CPU_MONDO_SEND		0x42
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_mondo_send(unsigned long cpu_count, unsigned long cpu_list_pa, unsigned long mondo_block_pa);
+unsigned long sun4v_cpu_mondo_send(unsigned long cpu_count,
+				   unsigned long cpu_list_pa,
+				   unsigned long mondo_block_pa);
 #endif
 
 /* cpu_myid()
@@ -425,7 +427,7 @@
 #define  HV_CPU_STATE_ERROR		 0x03
 
 #ifndef __ASSEMBLY__
-extern long sun4v_cpu_state(unsigned long cpuid);
+long sun4v_cpu_state(unsigned long cpuid);
 #endif
 
 /* cpu_set_rtba()
@@ -625,8 +627,8 @@
 #define HV_FAST_MMU_TSB_CTX0		0x20
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mmu_tsb_ctx0(unsigned long num_descriptions,
-					unsigned long tsb_desc_ra);
+unsigned long sun4v_mmu_tsb_ctx0(unsigned long num_descriptions,
+				 unsigned long tsb_desc_ra);
 #endif
 
 /* mmu_tsb_ctxnon0()
@@ -710,7 +712,7 @@
 #define HV_FAST_MMU_DEMAP_ALL		0x24
 
 #ifndef __ASSEMBLY__
-extern void sun4v_mmu_demap_all(void);
+void sun4v_mmu_demap_all(void);
 #endif
 
 /* mmu_map_perm_addr()
@@ -740,10 +742,10 @@
 #define HV_FAST_MMU_MAP_PERM_ADDR	0x25
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mmu_map_perm_addr(unsigned long vaddr,
-					     unsigned long set_to_zero,
-					     unsigned long tte,
-					     unsigned long flags);
+unsigned long sun4v_mmu_map_perm_addr(unsigned long vaddr,
+				      unsigned long set_to_zero,
+				      unsigned long tte,
+				      unsigned long flags);
 #endif
 
 /* mmu_fault_area_conf()
@@ -945,7 +947,7 @@
 #define HV_FAST_TOD_GET			0x50
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_tod_get(unsigned long *time);
+unsigned long sun4v_tod_get(unsigned long *time);
 #endif
 
 /* tod_set()
@@ -962,7 +964,7 @@
 #define HV_FAST_TOD_SET			0x51
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_tod_set(unsigned long time);
+unsigned long sun4v_tod_set(unsigned long time);
 #endif
 
 /* Console services */
@@ -1038,14 +1040,14 @@
 #define HV_FAST_CONS_WRITE		0x63
 
 #ifndef __ASSEMBLY__
-extern long sun4v_con_getchar(long *status);
-extern long sun4v_con_putchar(long c);
-extern long sun4v_con_read(unsigned long buffer,
-			   unsigned long size,
-			   unsigned long *bytes_read);
-extern unsigned long sun4v_con_write(unsigned long buffer,
-				     unsigned long size,
-				     unsigned long *bytes_written);
+long sun4v_con_getchar(long *status);
+long sun4v_con_putchar(long c);
+long sun4v_con_read(unsigned long buffer,
+		    unsigned long size,
+		    unsigned long *bytes_read);
+unsigned long sun4v_con_write(unsigned long buffer,
+			      unsigned long size,
+			      unsigned long *bytes_written);
 #endif
 
 /* mach_set_soft_state()
@@ -1080,8 +1082,8 @@
 #define  HV_SOFT_STATE_TRANSITION	 0x02
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mach_set_soft_state(unsigned long soft_state,
-					       unsigned long msg_string_ra);
+unsigned long sun4v_mach_set_soft_state(unsigned long soft_state,
+				        unsigned long msg_string_ra);
 #endif
 
 /* mach_get_soft_state()
@@ -1159,20 +1161,20 @@
 #define HV_FAST_SVC_CLRSTATUS		0x84
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_svc_send(unsigned long svc_id,
-				    unsigned long buffer,
-				    unsigned long buffer_size,
-				    unsigned long *sent_bytes);
-extern unsigned long sun4v_svc_recv(unsigned long svc_id,
-				    unsigned long buffer,
-				    unsigned long buffer_size,
-				    unsigned long *recv_bytes);
-extern unsigned long sun4v_svc_getstatus(unsigned long svc_id,
-					 unsigned long *status_bits);
-extern unsigned long sun4v_svc_setstatus(unsigned long svc_id,
-					 unsigned long status_bits);
-extern unsigned long sun4v_svc_clrstatus(unsigned long svc_id,
-					 unsigned long status_bits);
+unsigned long sun4v_svc_send(unsigned long svc_id,
+			     unsigned long buffer,
+			     unsigned long buffer_size,
+			     unsigned long *sent_bytes);
+unsigned long sun4v_svc_recv(unsigned long svc_id,
+			     unsigned long buffer,
+			     unsigned long buffer_size,
+			     unsigned long *recv_bytes);
+unsigned long sun4v_svc_getstatus(unsigned long svc_id,
+				  unsigned long *status_bits);
+unsigned long sun4v_svc_setstatus(unsigned long svc_id,
+				  unsigned long status_bits);
+unsigned long sun4v_svc_clrstatus(unsigned long svc_id,
+				  unsigned long status_bits);
 #endif
 
 /* Trap trace services.
@@ -1458,8 +1460,8 @@
 #define HV_FAST_INTR_DEVINO2SYSINO	0xa0
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_devino_to_sysino(unsigned long devhandle,
-					    unsigned long devino);
+unsigned long sun4v_devino_to_sysino(unsigned long devhandle,
+				     unsigned long devino);
 #endif
 
 /* intr_getenabled()
@@ -1476,7 +1478,7 @@
 #define HV_FAST_INTR_GETENABLED		0xa1
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_getenabled(unsigned long sysino);
+unsigned long sun4v_intr_getenabled(unsigned long sysino);
 #endif
 
 /* intr_setenabled()
@@ -1492,7 +1494,8 @@
 #define HV_FAST_INTR_SETENABLED		0xa2
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_setenabled(unsigned long sysino, unsigned long intr_enabled);
+unsigned long sun4v_intr_setenabled(unsigned long sysino,
+				    unsigned long intr_enabled);
 #endif
 
 /* intr_getstate()
@@ -1508,7 +1511,7 @@
 #define HV_FAST_INTR_GETSTATE		0xa3
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_getstate(unsigned long sysino);
+unsigned long sun4v_intr_getstate(unsigned long sysino);
 #endif
 
 /* intr_setstate()
@@ -1528,7 +1531,7 @@
 #define HV_FAST_INTR_SETSTATE		0xa4
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_setstate(unsigned long sysino, unsigned long intr_state);
+unsigned long sun4v_intr_setstate(unsigned long sysino, unsigned long intr_state);
 #endif
 
 /* intr_gettarget()
@@ -1546,7 +1549,7 @@
 #define HV_FAST_INTR_GETTARGET		0xa5
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_gettarget(unsigned long sysino);
+unsigned long sun4v_intr_gettarget(unsigned long sysino);
 #endif
 
 /* intr_settarget()
@@ -1563,7 +1566,7 @@
 #define HV_FAST_INTR_SETTARGET		0xa6
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_settarget(unsigned long sysino, unsigned long cpuid);
+unsigned long sun4v_intr_settarget(unsigned long sysino, unsigned long cpuid);
 #endif
 
 /* vintr_get_cookie()
@@ -1647,30 +1650,30 @@
 #define HV_FAST_VINTR_SET_TARGET	0xae
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_vintr_get_cookie(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long *cookie);
-extern unsigned long sun4v_vintr_set_cookie(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long cookie);
-extern unsigned long sun4v_vintr_get_valid(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long *valid);
-extern unsigned long sun4v_vintr_set_valid(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long valid);
-extern unsigned long sun4v_vintr_get_state(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long *state);
-extern unsigned long sun4v_vintr_set_state(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long state);
-extern unsigned long sun4v_vintr_get_target(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long *cpuid);
-extern unsigned long sun4v_vintr_set_target(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long cpuid);
+unsigned long sun4v_vintr_get_cookie(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long *cookie);
+unsigned long sun4v_vintr_set_cookie(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long cookie);
+unsigned long sun4v_vintr_get_valid(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long *valid);
+unsigned long sun4v_vintr_set_valid(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long valid);
+unsigned long sun4v_vintr_get_state(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long *state);
+unsigned long sun4v_vintr_set_state(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long state);
+unsigned long sun4v_vintr_get_target(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long *cpuid);
+unsigned long sun4v_vintr_set_target(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long cpuid);
 #endif
 
 /* PCI IO services.
@@ -2627,50 +2630,50 @@
 #define HV_FAST_LDC_REVOKE		0xef
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_ldc_tx_qconf(unsigned long channel,
-					unsigned long ra,
-					unsigned long num_entries);
-extern unsigned long sun4v_ldc_tx_qinfo(unsigned long channel,
-					unsigned long *ra,
-					unsigned long *num_entries);
-extern unsigned long sun4v_ldc_tx_get_state(unsigned long channel,
-					    unsigned long *head_off,
-					    unsigned long *tail_off,
-					    unsigned long *chan_state);
-extern unsigned long sun4v_ldc_tx_set_qtail(unsigned long channel,
-					    unsigned long tail_off);
-extern unsigned long sun4v_ldc_rx_qconf(unsigned long channel,
-					unsigned long ra,
-					unsigned long num_entries);
-extern unsigned long sun4v_ldc_rx_qinfo(unsigned long channel,
-					unsigned long *ra,
-					unsigned long *num_entries);
-extern unsigned long sun4v_ldc_rx_get_state(unsigned long channel,
-					    unsigned long *head_off,
-					    unsigned long *tail_off,
-					    unsigned long *chan_state);
-extern unsigned long sun4v_ldc_rx_set_qhead(unsigned long channel,
-					    unsigned long head_off);
-extern unsigned long sun4v_ldc_set_map_table(unsigned long channel,
-					     unsigned long ra,
-					     unsigned long num_entries);
-extern unsigned long sun4v_ldc_get_map_table(unsigned long channel,
-					     unsigned long *ra,
-					     unsigned long *num_entries);
-extern unsigned long sun4v_ldc_copy(unsigned long channel,
-				    unsigned long dir_code,
-				    unsigned long tgt_raddr,
-				    unsigned long lcl_raddr,
-				    unsigned long len,
-				    unsigned long *actual_len);
-extern unsigned long sun4v_ldc_mapin(unsigned long channel,
-				     unsigned long cookie,
-				     unsigned long *ra,
-				     unsigned long *perm);
-extern unsigned long sun4v_ldc_unmap(unsigned long ra);
-extern unsigned long sun4v_ldc_revoke(unsigned long channel,
-				      unsigned long cookie,
-				      unsigned long mte_cookie);
+unsigned long sun4v_ldc_tx_qconf(unsigned long channel,
+				 unsigned long ra,
+				 unsigned long num_entries);
+unsigned long sun4v_ldc_tx_qinfo(unsigned long channel,
+				 unsigned long *ra,
+				 unsigned long *num_entries);
+unsigned long sun4v_ldc_tx_get_state(unsigned long channel,
+				     unsigned long *head_off,
+				     unsigned long *tail_off,
+				     unsigned long *chan_state);
+unsigned long sun4v_ldc_tx_set_qtail(unsigned long channel,
+				     unsigned long tail_off);
+unsigned long sun4v_ldc_rx_qconf(unsigned long channel,
+				 unsigned long ra,
+				 unsigned long num_entries);
+unsigned long sun4v_ldc_rx_qinfo(unsigned long channel,
+				 unsigned long *ra,
+				 unsigned long *num_entries);
+unsigned long sun4v_ldc_rx_get_state(unsigned long channel,
+				     unsigned long *head_off,
+				     unsigned long *tail_off,
+				     unsigned long *chan_state);
+unsigned long sun4v_ldc_rx_set_qhead(unsigned long channel,
+				     unsigned long head_off);
+unsigned long sun4v_ldc_set_map_table(unsigned long channel,
+				      unsigned long ra,
+				      unsigned long num_entries);
+unsigned long sun4v_ldc_get_map_table(unsigned long channel,
+				      unsigned long *ra,
+				      unsigned long *num_entries);
+unsigned long sun4v_ldc_copy(unsigned long channel,
+			     unsigned long dir_code,
+			     unsigned long tgt_raddr,
+			     unsigned long lcl_raddr,
+			     unsigned long len,
+			     unsigned long *actual_len);
+unsigned long sun4v_ldc_mapin(unsigned long channel,
+			      unsigned long cookie,
+			      unsigned long *ra,
+			      unsigned long *perm);
+unsigned long sun4v_ldc_unmap(unsigned long ra);
+unsigned long sun4v_ldc_revoke(unsigned long channel,
+			       unsigned long cookie,
+			       unsigned long mte_cookie);
 #endif
 
 /* Performance counter services.  */
@@ -2727,14 +2730,14 @@
 #define HV_FAST_N2_SET_PERFREG		0x105
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_niagara_getperf(unsigned long reg,
-					   unsigned long *val);
-extern unsigned long sun4v_niagara_setperf(unsigned long reg,
-					   unsigned long val);
-extern unsigned long sun4v_niagara2_getperf(unsigned long reg,
-					    unsigned long *val);
-extern unsigned long sun4v_niagara2_setperf(unsigned long reg,
-					    unsigned long val);
+unsigned long sun4v_niagara_getperf(unsigned long reg,
+				    unsigned long *val);
+unsigned long sun4v_niagara_setperf(unsigned long reg,
+				    unsigned long val);
+unsigned long sun4v_niagara2_getperf(unsigned long reg,
+				     unsigned long *val);
+unsigned long sun4v_niagara2_setperf(unsigned long reg,
+				     unsigned long val);
 #endif
 
 /* MMU statistics services.
@@ -2829,8 +2832,8 @@
 #define HV_FAST_MMUSTAT_INFO		0x103
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mmustat_conf(unsigned long ra, unsigned long *orig_ra);
-extern unsigned long sun4v_mmustat_info(unsigned long *ra);
+unsigned long sun4v_mmustat_conf(unsigned long ra, unsigned long *orig_ra);
+unsigned long sun4v_mmustat_info(unsigned long *ra);
 #endif
 
 /* NCS crypto services  */
@@ -2919,9 +2922,9 @@
 #define HV_FAST_NCS_REQUEST		0x110
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_ncs_request(unsigned long request,
-				       unsigned long arg_ra,
-				       unsigned long arg_size);
+unsigned long sun4v_ncs_request(unsigned long request,
+			        unsigned long arg_ra,
+			        unsigned long arg_size);
 #endif
 
 #define HV_FAST_FIRE_GET_PERFREG	0x120
@@ -2930,18 +2933,18 @@
 #define HV_FAST_REBOOT_DATA_SET		0x172
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_reboot_data_set(unsigned long ra,
-					   unsigned long len);
+unsigned long sun4v_reboot_data_set(unsigned long ra,
+				    unsigned long len);
 #endif
 
 #define HV_FAST_VT_GET_PERFREG		0x184
 #define HV_FAST_VT_SET_PERFREG		0x185
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_vt_get_perfreg(unsigned long reg_num,
-					  unsigned long *reg_val);
-extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
-					  unsigned long reg_val);
+unsigned long sun4v_vt_get_perfreg(unsigned long reg_num,
+				   unsigned long *reg_val);
+unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
+				   unsigned long reg_val);
 #endif
 
 /* Function numbers for HV_CORE_TRAP.  */
@@ -2978,21 +2981,21 @@
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_get_version(unsigned long group,
-				       unsigned long *major,
-				       unsigned long *minor);
-extern unsigned long sun4v_set_version(unsigned long group,
-				       unsigned long major,
-				       unsigned long minor,
-				       unsigned long *actual_minor);
+unsigned long sun4v_get_version(unsigned long group,
+			        unsigned long *major,
+			        unsigned long *minor);
+unsigned long sun4v_set_version(unsigned long group,
+			        unsigned long major,
+			        unsigned long minor,
+			        unsigned long *actual_minor);
 
-extern int sun4v_hvapi_register(unsigned long group, unsigned long major,
-				unsigned long *minor);
-extern void sun4v_hvapi_unregister(unsigned long group);
-extern int sun4v_hvapi_get(unsigned long group,
-			   unsigned long *major,
-			   unsigned long *minor);
-extern void sun4v_hvapi_init(void);
+int sun4v_hvapi_register(unsigned long group, unsigned long major,
+			 unsigned long *minor);
+void sun4v_hvapi_unregister(unsigned long group);
+int sun4v_hvapi_get(unsigned long group,
+		    unsigned long *major,
+		    unsigned long *minor);
+void sun4v_hvapi_init(void);
 #endif
 
 #endif /* !(_SPARC64_HYPERVISOR_H) */
diff --git a/arch/sparc/include/asm/idprom.h b/arch/sparc/include/asm/idprom.h
index 6976aa2..3793f7f 100644
--- a/arch/sparc/include/asm/idprom.h
+++ b/arch/sparc/include/asm/idprom.h
@@ -20,6 +20,6 @@
 };
 
 extern struct idprom *idprom;
-extern void idprom_init(void);
+void idprom_init(void);
 
 #endif /* !(_SPARC_IDPROM_H) */
diff --git a/arch/sparc/include/asm/io-unit.h b/arch/sparc/include/asm/io-unit.h
index 01ab2f6..04a9701 100644
--- a/arch/sparc/include/asm/io-unit.h
+++ b/arch/sparc/include/asm/io-unit.h
@@ -43,7 +43,7 @@
 struct iounit_struct {
 	unsigned long		bmap[(IOUNIT_DMA_SIZE >> (PAGE_SHIFT + 3)) / sizeof(unsigned long)];
 	spinlock_t		lock;
-	iopte_t			*page_table;
+	iopte_t __iomem		*page_table;
 	unsigned long		rotor[3];
 	unsigned long		limit[4];
 };
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index c1acbd8..9f53290 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -2,200 +2,22 @@
 #define __SPARC_IO_H
 
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/ioport.h>  /* struct resource */
 
-#include <asm/page.h>      /* IO address mapping routines need this */
-#include <asm-generic/pci_iomap.h>
-
-#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
-
-static inline u32 flip_dword (u32 l)
-{
-	return ((l&0xff)<<24) | (((l>>8)&0xff)<<16) | (((l>>16)&0xff)<<8)| ((l>>24)&0xff);
-}
-
-static inline u16 flip_word (u16 w)
-{
-	return ((w&0xff) << 8) | ((w>>8)&0xff);
-}
-
-#define mmiowb()
-
-/*
- * Memory mapped I/O to PCI
- */
-
-static inline u8 __raw_readb(const volatile void __iomem *addr)
-{
-	return *(__force volatile u8 *)addr;
-}
-
-static inline u16 __raw_readw(const volatile void __iomem *addr)
-{
-	return *(__force volatile u16 *)addr;
-}
-
-static inline u32 __raw_readl(const volatile void __iomem *addr)
-{
-	return *(__force volatile u32 *)addr;
-}
-
-static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
-{
-	*(__force volatile u8 *)addr = b;
-}
-
-static inline void __raw_writew(u16 w, volatile void __iomem *addr)
-{
-	*(__force volatile u16 *)addr = w;
-}
-
-static inline void __raw_writel(u32 l, volatile void __iomem *addr)
-{
-	*(__force volatile u32 *)addr = l;
-}
-
-static inline u8 __readb(const volatile void __iomem *addr)
-{
-	return *(__force volatile u8 *)addr;
-}
-
-static inline u16 __readw(const volatile void __iomem *addr)
-{
-	return flip_word(*(__force volatile u16 *)addr);
-}
-
-static inline u32 __readl(const volatile void __iomem *addr)
-{
-	return flip_dword(*(__force volatile u32 *)addr);
-}
-
-static inline void __writeb(u8 b, volatile void __iomem *addr)
-{
-	*(__force volatile u8 *)addr = b;
-}
-
-static inline void __writew(u16 w, volatile void __iomem *addr)
-{
-	*(__force volatile u16 *)addr = flip_word(w);
-}
-
-static inline void __writel(u32 l, volatile void __iomem *addr)
-{
-	*(__force volatile u32 *)addr = flip_dword(l);
-}
-
-#define readb(__addr)		__readb(__addr)
-#define readw(__addr)		__readw(__addr)
-#define readl(__addr)		__readl(__addr)
 #define readb_relaxed(__addr)	readb(__addr)
 #define readw_relaxed(__addr)	readw(__addr)
 #define readl_relaxed(__addr)	readl(__addr)
 
-#define writeb(__b, __addr)	__writeb((__b),(__addr))
-#define writew(__w, __addr)	__writew((__w),(__addr))
-#define writel(__l, __addr)	__writel((__l),(__addr))
-
-/*
- * I/O space operations
- *
- * Arrangement on a Sun is somewhat complicated.
- *
- * First of all, we want to use standard Linux drivers
- * for keyboard, PC serial, etc. These drivers think
- * they access I/O space and use inb/outb.
- * On the other hand, EBus bridge accepts PCI *memory*
- * cycles and converts them into ISA *I/O* cycles.
- * Ergo, we want inb & outb to generate PCI memory cycles.
- *
- * If we want to issue PCI *I/O* cycles, we do this
- * with a low 64K fixed window in PCIC. This window gets
- * mapped somewhere into virtual kernel space and we
- * can use inb/outb again.
- */
-#define inb_local(__addr)	__readb((void __iomem *)(unsigned long)(__addr))
-#define inb(__addr)		__readb((void __iomem *)(unsigned long)(__addr))
-#define inw(__addr)		__readw((void __iomem *)(unsigned long)(__addr))
-#define inl(__addr)		__readl((void __iomem *)(unsigned long)(__addr))
-
-#define outb_local(__b, __addr)	__writeb(__b, (void __iomem *)(unsigned long)(__addr))
-#define outb(__b, __addr)	__writeb(__b, (void __iomem *)(unsigned long)(__addr))
-#define outw(__w, __addr)	__writew(__w, (void __iomem *)(unsigned long)(__addr))
-#define outl(__l, __addr)	__writel(__l, (void __iomem *)(unsigned long)(__addr))
-
-#define inb_p(__addr)		inb(__addr)
-#define outb_p(__b, __addr)	outb(__b, __addr)
-#define inw_p(__addr)		inw(__addr)
-#define outw_p(__w, __addr)	outw(__w, __addr)
-#define inl_p(__addr)		inl(__addr)
-#define outl_p(__l, __addr)	outl(__l, __addr)
-
-void outsb(unsigned long addr, const void *src, unsigned long cnt);
-void outsw(unsigned long addr, const void *src, unsigned long cnt);
-void outsl(unsigned long addr, const void *src, unsigned long cnt);
-void insb(unsigned long addr, void *dst, unsigned long count);
-void insw(unsigned long addr, void *dst, unsigned long count);
-void insl(unsigned long addr, void *dst, unsigned long count);
-
 #define IO_SPACE_LIMIT 0xffffffff
 
-/*
- * SBus accessors.
- *
- * SBus has only one, memory mapped, I/O space.
- * We do not need to flip bytes for SBus of course.
- */
-static inline u8 _sbus_readb(const volatile void __iomem *addr)
-{
-	return *(__force volatile u8 *)addr;
-}
+#define memset_io(d,c,sz)     _memset_io(d,c,sz)
+#define memcpy_fromio(d,s,sz) _memcpy_fromio(d,s,sz)
+#define memcpy_toio(d,s,sz)   _memcpy_toio(d,s,sz)
 
-static inline u16 _sbus_readw(const volatile void __iomem *addr)
-{
-	return *(__force volatile u16 *)addr;
-}
+#include <asm-generic/io.h>
 
-static inline u32 _sbus_readl(const volatile void __iomem *addr)
-{
-	return *(__force volatile u32 *)addr;
-}
-
-static inline void _sbus_writeb(u8 b, volatile void __iomem *addr)
-{
-	*(__force volatile u8 *)addr = b;
-}
-
-static inline void _sbus_writew(u16 w, volatile void __iomem *addr)
-{
-	*(__force volatile u16 *)addr = w;
-}
-
-static inline void _sbus_writel(u32 l, volatile void __iomem *addr)
-{
-	*(__force volatile u32 *)addr = l;
-}
-
-/*
- * The only reason for #define's is to hide casts to unsigned long.
- */
-#define sbus_readb(__addr)		_sbus_readb(__addr)
-#define sbus_readw(__addr)		_sbus_readw(__addr)
-#define sbus_readl(__addr)		_sbus_readl(__addr)
-#define sbus_writeb(__b, __addr)	_sbus_writeb(__b, __addr)
-#define sbus_writew(__w, __addr)	_sbus_writew(__w, __addr)
-#define sbus_writel(__l, __addr)	_sbus_writel(__l, __addr)
-
-static inline void sbus_memset_io(volatile void __iomem *__dst, int c, __kernel_size_t n)
-{
-	while(n--) {
-		sbus_writeb(c, __dst);
-		__dst++;
-	}
-}
-
-static inline void
-_memset_io(volatile void __iomem *dst, int c, __kernel_size_t n)
+static inline void _memset_io(volatile void __iomem *dst,
+                              int c, __kernel_size_t n)
 {
 	volatile void __iomem *d = dst;
 
@@ -205,25 +27,8 @@
 	}
 }
 
-#define memset_io(d,c,sz)	_memset_io(d,c,sz)
-
-static inline void
-_sbus_memcpy_fromio(void *dst, const volatile void __iomem *src,
-		    __kernel_size_t n)
-{
-	char *d = dst;
-
-	while (n--) {
-		char tmp = sbus_readb(src);
-		*d++ = tmp;
-		src++;
-	}
-}
-
-#define sbus_memcpy_fromio(d, s, sz)	_sbus_memcpy_fromio(d, s, sz)
-
-static inline void
-_memcpy_fromio(void *dst, const volatile void __iomem *src, __kernel_size_t n)
+static inline void _memcpy_fromio(void *dst, const volatile void __iomem *src,
+                                  __kernel_size_t n)
 {
 	char *d = dst;
 
@@ -234,26 +39,8 @@
 	}
 }
 
-#define memcpy_fromio(d,s,sz)	_memcpy_fromio(d,s,sz)
-
-static inline void
-_sbus_memcpy_toio(volatile void __iomem *dst, const void *src,
-		  __kernel_size_t n)
-{
-	const char *s = src;
-	volatile void __iomem *d = dst;
-
-	while (n--) {
-		char tmp = *s++;
-		sbus_writeb(tmp, d);
-		d++;
-	}
-}
-
-#define sbus_memcpy_toio(d, s, sz)	_sbus_memcpy_toio(d, s, sz)
-
-static inline void
-_memcpy_toio(volatile void __iomem *dst, const void *src, __kernel_size_t n)
+static inline void _memcpy_toio(volatile void __iomem *dst, const void *src,
+                                __kernel_size_t n)
 {
 	const char *s = src;
 	volatile void __iomem *d = dst;
@@ -265,7 +52,77 @@
 	}
 }
 
-#define memcpy_toio(d,s,sz)	_memcpy_toio(d,s,sz)
+/*
+ * SBus accessors.
+ *
+ * SBus has only one, memory mapped, I/O space.
+ * We do not need to flip bytes for SBus of course.
+ */
+static inline u8 sbus_readb(const volatile void __iomem *addr)
+{
+	return *(__force volatile u8 *)addr;
+}
+
+static inline u16 sbus_readw(const volatile void __iomem *addr)
+{
+	return *(__force volatile u16 *)addr;
+}
+
+static inline u32 sbus_readl(const volatile void __iomem *addr)
+{
+	return *(__force volatile u32 *)addr;
+}
+
+static inline void sbus_writeb(u8 b, volatile void __iomem *addr)
+{
+	*(__force volatile u8 *)addr = b;
+}
+
+static inline void sbus_writew(u16 w, volatile void __iomem *addr)
+{
+	*(__force volatile u16 *)addr = w;
+}
+
+static inline void sbus_writel(u32 l, volatile void __iomem *addr)
+{
+	*(__force volatile u32 *)addr = l;
+}
+
+static inline void sbus_memset_io(volatile void __iomem *__dst, int c,
+                                  __kernel_size_t n)
+{
+	while(n--) {
+		sbus_writeb(c, __dst);
+		__dst++;
+	}
+}
+
+static inline void sbus_memcpy_fromio(void *dst,
+                                      const volatile void __iomem *src,
+                                      __kernel_size_t n)
+{
+	char *d = dst;
+
+	while (n--) {
+		char tmp = sbus_readb(src);
+		*d++ = tmp;
+		src++;
+	}
+}
+
+static inline void sbus_memcpy_toio(volatile void __iomem *dst,
+                                    const void *src,
+                                    __kernel_size_t n)
+{
+	const char *s = src;
+	volatile void __iomem *d = dst;
+
+	while (n--) {
+		char tmp = *s++;
+		sbus_writeb(tmp, d);
+		d++;
+	}
+}
 
 #ifdef __KERNEL__
 
@@ -273,58 +130,20 @@
  * Bus number may be embedded in the higher bits of the physical address.
  * This is why we have no bus number argument to ioremap().
  */
-extern void __iomem *ioremap(unsigned long offset, unsigned long size);
+void __iomem *ioremap(unsigned long offset, unsigned long size);
 #define ioremap_nocache(X,Y)	ioremap((X),(Y))
 #define ioremap_wc(X,Y)		ioremap((X),(Y))
-extern void iounmap(volatile void __iomem *addr);
-
-#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)
-
-static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
-{
-	insb((unsigned long __force)port, buf, count);
-}
-static inline void ioread16_rep(void __iomem *port, void *buf, unsigned long count)
-{
-	insw((unsigned long __force)port, buf, count);
-}
-
-static inline void ioread32_rep(void __iomem *port, void *buf, unsigned long count)
-{
-	insl((unsigned long __force)port, buf, count);
-}
-
-static inline void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count)
-{
-	outsb((unsigned long __force)port, buf, count);
-}
-
-static inline void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count)
-{
-	outsw((unsigned long __force)port, buf, count);
-}
-
-static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count)
-{
-	outsl((unsigned long __force)port, buf, count);
-}
+void iounmap(volatile void __iomem *addr);
 
 /* Create a virtual mapping cookie for an IO port range */
-extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
-extern void ioport_unmap(void __iomem *);
+void __iomem *ioport_map(unsigned long port, unsigned int nr);
+void ioport_unmap(void __iomem *);
 
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 struct pci_dev;
-extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
+void pci_iounmap(struct pci_dev *dev, void __iomem *);
+
+
 
 /*
  * At the moment, we do not use CMOS_READ anywhere outside of rtc.c,
@@ -343,21 +162,11 @@
 	return 0; /* actually, sparc_cpu_model==sun4d */
 }
 struct device;
-extern void sbus_set_sbus64(struct device *, int);
+void sbus_set_sbus64(struct device *, int);
 
 #endif
 
 #define __ARCH_HAS_NO_PAGE_ZERO_MAPPED		1
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
 
 #endif /* !(__SPARC_IO_H) */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 09b0b88..05381c3 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -15,7 +15,6 @@
 
 /* BIO layer definitions. */
 extern unsigned long kern_base, kern_size;
-#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
 
 static inline u8 _inb(unsigned long addr)
 {
@@ -91,12 +90,12 @@
 #define inl_p(__addr)		inl(__addr)
 #define outl_p(__l, __addr)	outl(__l, __addr)
 
-extern void outsb(unsigned long, const void *, unsigned long);
-extern void outsw(unsigned long, const void *, unsigned long);
-extern void outsl(unsigned long, const void *, unsigned long);
-extern void insb(unsigned long, void *, unsigned long);
-extern void insw(unsigned long, void *, unsigned long);
-extern void insl(unsigned long, void *, unsigned long);
+void outsb(unsigned long, const void *, unsigned long);
+void outsw(unsigned long, const void *, unsigned long);
+void outsl(unsigned long, const void *, unsigned long);
+void insb(unsigned long, void *, unsigned long);
+void insw(unsigned long, void *, unsigned long);
+void insl(unsigned long, void *, unsigned long);
 
 static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
 {
@@ -509,12 +508,12 @@
 #define iowrite32be(val,X)		__raw_writel(val,X)
 
 /* Create a virtual mapping cookie for an IO port range */
-extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
-extern void ioport_unmap(void __iomem *);
+void __iomem *ioport_map(unsigned long port, unsigned int nr);
+void ioport_unmap(void __iomem *);
 
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 struct pci_dev;
-extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
+void pci_iounmap(struct pci_dev *dev, void __iomem *);
 
 static inline int sbus_can_dma_64bit(void)
 {
@@ -525,7 +524,7 @@
 	return 1;
 }
 struct device;
-extern void sbus_set_sbus64(struct device *, int);
+void sbus_set_sbus64(struct device *, int);
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/sparc/include/asm/iommu_32.h b/arch/sparc/include/asm/iommu_32.h
index 70c589c..f6c066b 100644
--- a/arch/sparc/include/asm/iommu_32.h
+++ b/arch/sparc/include/asm/iommu_32.h
@@ -99,7 +99,7 @@
 #define IOPTE_WAZ           0x00000001 /* Write as zeros */
 
 struct iommu_struct {
-	struct iommu_regs *regs;
+	struct iommu_regs __iomem *regs;
 	iopte_t *page_table;
 	/* For convenience */
 	unsigned long start; /* First managed virtual address */
@@ -108,14 +108,14 @@
 	struct bit_map usemap;
 };
 
-static inline void iommu_invalidate(struct iommu_regs *regs)
+static inline void iommu_invalidate(struct iommu_regs __iomem *regs)
 {
-	regs->tlbflush = 0;
+	sbus_writel(0, &regs->tlbflush);
 }
 
-static inline void iommu_invalidate_page(struct iommu_regs *regs, unsigned long ba)
+static inline void iommu_invalidate_page(struct iommu_regs __iomem *regs, unsigned long ba)
 {
-	regs->pageflush = (ba & PAGE_MASK);
+	sbus_writel(ba & PAGE_MASK, &regs->pageflush);
 }
 
 #endif /* !(_SPARC_IOMMU_H) */
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h
index caf798b..2b9321a 100644
--- a/arch/sparc/include/asm/iommu_64.h
+++ b/arch/sparc/include/asm/iommu_64.h
@@ -58,8 +58,8 @@
 	volatile unsigned long	__flushflag_buf[(64+(64-1)) / sizeof(long)];
 };
 
-extern int iommu_table_init(struct iommu *iommu, int tsbsize,
-			    u32 dma_offset, u32 dma_addr_mask,
-			    int numa_node);
+int iommu_table_init(struct iommu *iommu, int tsbsize,
+		     u32 dma_offset, u32 dma_addr_mask,
+		     int numa_node);
 
 #endif /* !(_SPARC64_IOMMU_H) */
diff --git a/arch/sparc/include/asm/irq_32.h b/arch/sparc/include/asm/irq_32.h
index 2ae3aca..eecd3d8 100644
--- a/arch/sparc/include/asm/irq_32.h
+++ b/arch/sparc/include/asm/irq_32.h
@@ -16,7 +16,8 @@
 
 #define irq_canonicalize(irq)	(irq)
 
-extern void __init init_IRQ(void);
+void __init init_IRQ(void);
+void __init sun4d_init_sbi_irq(void);
 
 #define NO_IRQ		0xffffffff
 
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index abf6afe..375cffc 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -39,32 +39,32 @@
  */
 #define NR_IRQS    255
 
-extern void irq_install_pre_handler(int irq,
-				    void (*func)(unsigned int, void *, void *),
-				    void *arg1, void *arg2);
+void irq_install_pre_handler(int irq,
+			     void (*func)(unsigned int, void *, void *),
+			     void *arg1, void *arg2);
 #define irq_canonicalize(irq)	(irq)
-extern unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap);
-extern unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino);
-extern unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino);
-extern unsigned int sun4v_build_msi(u32 devhandle, unsigned int *irq_p,
-				    unsigned int msi_devino_start,
-				    unsigned int msi_devino_end);
-extern void sun4v_destroy_msi(unsigned int irq);
-extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
-				    unsigned int msi_devino_start,
-				    unsigned int msi_devino_end,
-				    unsigned long imap_base,
-				    unsigned long iclr_base);
-extern void sun4u_destroy_msi(unsigned int irq);
+unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap);
+unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino);
+unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino);
+unsigned int sun4v_build_msi(u32 devhandle, unsigned int *irq_p,
+			     unsigned int msi_devino_start,
+			     unsigned int msi_devino_end);
+void sun4v_destroy_msi(unsigned int irq);
+unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
+			     unsigned int msi_devino_start,
+			     unsigned int msi_devino_end,
+			     unsigned long imap_base,
+			     unsigned long iclr_base);
+void sun4u_destroy_msi(unsigned int irq);
 
-extern unsigned char irq_alloc(unsigned int dev_handle,
-				    unsigned int dev_ino);
+unsigned char irq_alloc(unsigned int dev_handle,
+			unsigned int dev_ino);
 #ifdef CONFIG_PCI_MSI
-extern void irq_free(unsigned int irq);
+void irq_free(unsigned int irq);
 #endif
 
-extern void __init init_IRQ(void);
-extern void fixup_irqs(void);
+void __init init_IRQ(void);
+void fixup_irqs(void);
 
 static inline void set_softint(unsigned long bits)
 {
diff --git a/arch/sparc/include/asm/irqflags_32.h b/arch/sparc/include/asm/irqflags_32.h
index e414c06..71cc284 100644
--- a/arch/sparc/include/asm/irqflags_32.h
+++ b/arch/sparc/include/asm/irqflags_32.h
@@ -15,9 +15,9 @@
 #include <linux/types.h>
 #include <asm/psr.h>
 
-extern void arch_local_irq_restore(unsigned long);
-extern unsigned long arch_local_irq_save(void);
-extern void arch_local_irq_enable(void);
+void arch_local_irq_restore(unsigned long);
+unsigned long arch_local_irq_save(void);
+void arch_local_irq_enable(void);
 
 static inline notrace unsigned long arch_local_save_flags(void)
 {
diff --git a/arch/sparc/include/asm/kdebug_64.h b/arch/sparc/include/asm/kdebug_64.h
index feb3578..04465de 100644
--- a/arch/sparc/include/asm/kdebug_64.h
+++ b/arch/sparc/include/asm/kdebug_64.h
@@ -3,7 +3,7 @@
 
 struct pt_regs;
 
-extern void bad_trap(struct pt_regs *, long);
+void bad_trap(struct pt_regs *, long);
 
 /* Grossly misnamed. */
 enum die_val {
diff --git a/arch/sparc/include/asm/kgdb.h b/arch/sparc/include/asm/kgdb.h
index b6ef301..47366af 100644
--- a/arch/sparc/include/asm/kgdb.h
+++ b/arch/sparc/include/asm/kgdb.h
@@ -28,9 +28,12 @@
 #define NUMREGBYTES		((GDB_CSR + 1) * 4)
 #else
 #define NUMREGBYTES		((GDB_Y + 1) * 8)
+
+struct pt_regs;
+asmlinkage void kgdb_trap(unsigned long trap_level, struct pt_regs *regs);
 #endif
 
-extern void arch_kgdb_breakpoint(void);
+void arch_kgdb_breakpoint(void);
 
 #define BREAK_INSTR_SIZE	4
 #define CACHE_FLUSH_IS_SAFE	1
diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 5879d71..a145d79 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -43,7 +43,9 @@
 	struct prev_kprobe prev_kprobe;
 };
 
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
-extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+asmlinkage void __kprobes kprobe_trap(unsigned long trap_level,
+				      struct pt_regs *regs);
 #endif /* _SPARC64_KPROBES_H */
diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h
index bdb524a..c8c67f6 100644
--- a/arch/sparc/include/asm/ldc.h
+++ b/arch/sparc/include/asm/ldc.h
@@ -4,9 +4,9 @@
 #include <asm/hypervisor.h>
 
 extern int ldom_domaining_enabled;
-extern void ldom_set_var(const char *var, const char *value);
-extern void ldom_reboot(const char *boot_command);
-extern void ldom_power_off(void);
+void ldom_set_var(const char *var, const char *value);
+void ldom_reboot(const char *boot_command);
+void ldom_power_off(void);
 
 /* The event handler will be evoked when link state changes
  * or data becomes available on the receive side.
@@ -51,30 +51,30 @@
 struct ldc_channel;
 
 /* Allocate state for a channel.  */
-extern struct ldc_channel *ldc_alloc(unsigned long id,
-				     const struct ldc_channel_config *cfgp,
-				     void *event_arg);
+struct ldc_channel *ldc_alloc(unsigned long id,
+			      const struct ldc_channel_config *cfgp,
+			      void *event_arg);
 
 /* Shut down and free state for a channel.  */
-extern void ldc_free(struct ldc_channel *lp);
+void ldc_free(struct ldc_channel *lp);
 
 /* Register TX and RX queues of the link with the hypervisor.  */
-extern int ldc_bind(struct ldc_channel *lp, const char *name);
+int ldc_bind(struct ldc_channel *lp, const char *name);
 
 /* For non-RAW protocols we need to complete a handshake before
  * communication can proceed.  ldc_connect() does that, if the
  * handshake completes successfully, an LDC_EVENT_UP event will
  * be sent up to the driver.
  */
-extern int ldc_connect(struct ldc_channel *lp);
-extern int ldc_disconnect(struct ldc_channel *lp);
+int ldc_connect(struct ldc_channel *lp);
+int ldc_disconnect(struct ldc_channel *lp);
 
-extern int ldc_state(struct ldc_channel *lp);
+int ldc_state(struct ldc_channel *lp);
 
 /* Read and write operations.  Only valid when the link is up.  */
-extern int ldc_write(struct ldc_channel *lp, const void *buf,
-		     unsigned int size);
-extern int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size);
+int ldc_write(struct ldc_channel *lp, const void *buf,
+	      unsigned int size);
+int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size);
 
 #define LDC_MAP_SHADOW	0x01
 #define LDC_MAP_DIRECT	0x02
@@ -92,22 +92,22 @@
 };
 
 struct scatterlist;
-extern int ldc_map_sg(struct ldc_channel *lp,
-		      struct scatterlist *sg, int num_sg,
-		      struct ldc_trans_cookie *cookies, int ncookies,
-		      unsigned int map_perm);
+int ldc_map_sg(struct ldc_channel *lp,
+	       struct scatterlist *sg, int num_sg,
+	       struct ldc_trans_cookie *cookies, int ncookies,
+	       unsigned int map_perm);
 
-extern int ldc_map_single(struct ldc_channel *lp,
-			  void *buf, unsigned int len,
-			  struct ldc_trans_cookie *cookies, int ncookies,
-			  unsigned int map_perm);
+int ldc_map_single(struct ldc_channel *lp,
+		   void *buf, unsigned int len,
+		   struct ldc_trans_cookie *cookies, int ncookies,
+		   unsigned int map_perm);
 
-extern void ldc_unmap(struct ldc_channel *lp, struct ldc_trans_cookie *cookies,
-		      int ncookies);
+void ldc_unmap(struct ldc_channel *lp, struct ldc_trans_cookie *cookies,
+	       int ncookies);
 
-extern int ldc_copy(struct ldc_channel *lp, int copy_dir,
-		    void *buf, unsigned int len, unsigned long offset,
-		    struct ldc_trans_cookie *cookies, int ncookies);
+int ldc_copy(struct ldc_channel *lp, int copy_dir,
+	     void *buf, unsigned int len, unsigned long offset,
+	     struct ldc_trans_cookie *cookies, int ncookies);
 
 static inline int ldc_get_dring_entry(struct ldc_channel *lp,
 				      void *buf, unsigned int len,
@@ -127,12 +127,12 @@
 	return ldc_copy(lp, LDC_COPY_OUT, buf, len, offset, cookies, ncookies);
 }
 
-extern void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
-				 struct ldc_trans_cookie *cookies,
-				 int *ncookies, unsigned int map_perm);
+void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
+			  struct ldc_trans_cookie *cookies,
+			  int *ncookies, unsigned int map_perm);
 
-extern void ldc_free_exp_dring(struct ldc_channel *lp, void *buf,
-			       unsigned int len,
-			       struct ldc_trans_cookie *cookies, int ncookies);
+void ldc_free_exp_dring(struct ldc_channel *lp, void *buf,
+		        unsigned int len,
+		        struct ldc_trans_cookie *cookies, int ncookies);
 
 #endif /* _SPARC64_LDC_H */
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
index c2f6ff6..204771c 100644
--- a/arch/sparc/include/asm/leon.h
+++ b/arch/sparc/include/asm/leon.h
@@ -82,8 +82,8 @@
 #define LEON_BYPASS_LOAD_PA(x)      leon_load_reg((unsigned long)(x))
 #define LEON_BYPASS_STORE_PA(x, v)  leon_store_reg((unsigned long)(x), (unsigned long)(v))
 
-extern void leon_switch_mm(void);
-extern void leon_init_IRQ(void);
+void leon_switch_mm(void);
+void leon_init_IRQ(void);
 
 static inline unsigned long sparc_leon3_get_dcachecfg(void)
 {
@@ -196,14 +196,14 @@
 #ifndef __ASSEMBLY__
 struct vm_area_struct;
 
-extern unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr);
-extern void leon_flush_icache_all(void);
-extern void leon_flush_dcache_all(void);
-extern void leon_flush_cache_all(void);
-extern void leon_flush_tlb_all(void);
+unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr);
+void leon_flush_icache_all(void);
+void leon_flush_dcache_all(void);
+void leon_flush_cache_all(void);
+void leon_flush_tlb_all(void);
 extern int leon_flush_during_switch;
-extern int leon_flush_needed(void);
-extern void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page);
+int leon_flush_needed(void);
+void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page);
 
 /* struct that hold LEON3 cache configuration registers */
 struct leon3_cacheregs {
@@ -217,29 +217,29 @@
 
 struct device_node;
 struct task_struct;
-extern unsigned int leon_build_device_irq(unsigned int real_irq,
-					   irq_flow_handler_t flow_handler,
-					   const char *name, int do_ack);
-extern void leon_update_virq_handling(unsigned int virq,
-			      irq_flow_handler_t flow_handler,
-			      const char *name, int do_ack);
-extern void leon_init_timers(void);
-extern void leon_trans_init(struct device_node *dp);
-extern void leon_node_init(struct device_node *dp, struct device_node ***nextp);
-extern void init_leon(void);
-extern void poke_leonsparc(void);
-extern void leon3_getCacheRegs(struct leon3_cacheregs *regs);
+unsigned int leon_build_device_irq(unsigned int real_irq,
+				   irq_flow_handler_t flow_handler,
+				   const char *name, int do_ack);
+void leon_update_virq_handling(unsigned int virq,
+			       irq_flow_handler_t flow_handler,
+			       const char *name, int do_ack);
+void leon_init_timers(void);
+void leon_trans_init(struct device_node *dp);
+void leon_node_init(struct device_node *dp, struct device_node ***nextp);
+void init_leon(void);
+void poke_leonsparc(void);
+void leon3_getCacheRegs(struct leon3_cacheregs *regs);
 extern int leon3_ticker_irq;
 
 #ifdef CONFIG_SMP
-extern int leon_smp_nrcpus(void);
-extern void leon_clear_profile_irq(int cpu);
-extern void leon_smp_done(void);
-extern void leon_boot_cpus(void);
-extern int leon_boot_one_cpu(int i, struct task_struct *);
+int leon_smp_nrcpus(void);
+void leon_clear_profile_irq(int cpu);
+void leon_smp_done(void);
+void leon_boot_cpus(void);
+int leon_boot_one_cpu(int i, struct task_struct *);
 void leon_init_smp(void);
 void leon_enable_irq_cpu(unsigned int irq_nr, unsigned int cpu);
-extern irqreturn_t leon_percpu_timer_interrupt(int irq, void *unused);
+irqreturn_t leon_percpu_timer_interrupt(int irq, void *unused);
 
 extern unsigned int smpleon_ipi[];
 extern unsigned int linux_trap_ipi15_leon[];
diff --git a/arch/sparc/include/asm/leon_pci.h b/arch/sparc/include/asm/leon_pci.h
index bfd3ab3..049d067 100644
--- a/arch/sparc/include/asm/leon_pci.h
+++ b/arch/sparc/include/asm/leon_pci.h
@@ -16,7 +16,7 @@
 	int (*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
 };
 
-extern void leon_pci_init(struct platform_device *ofdev,
-				struct leon_pci_info *info);
+void leon_pci_init(struct platform_device *ofdev,
+		   struct leon_pci_info *info);
 
 #endif /* _ASM_LEON_PCI_H_ */
diff --git a/arch/sparc/include/asm/mc146818rtc.h b/arch/sparc/include/asm/mc146818rtc.h
index 67ed9e3..d8e72f3 100644
--- a/arch/sparc/include/asm/mc146818rtc.h
+++ b/arch/sparc/include/asm/mc146818rtc.h
@@ -1,5 +1,10 @@
 #ifndef ___ASM_SPARC_MC146818RTC_H
 #define ___ASM_SPARC_MC146818RTC_H
+
+#include <linux/spinlock.h>
+
+extern spinlock_t rtc_lock;
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/mc146818rtc_64.h>
 #else
diff --git a/arch/sparc/include/asm/mdesc.h b/arch/sparc/include/asm/mdesc.h
index 139097f..aebeb88 100644
--- a/arch/sparc/include/asm/mdesc.h
+++ b/arch/sparc/include/asm/mdesc.h
@@ -12,13 +12,13 @@
  * the first argument to all of the operational calls that work
  * on mdescs.
  */
-extern struct mdesc_handle *mdesc_grab(void);
-extern void mdesc_release(struct mdesc_handle *);
+struct mdesc_handle *mdesc_grab(void);
+void mdesc_release(struct mdesc_handle *);
 
 #define MDESC_NODE_NULL		(~(u64)0)
 
-extern u64 mdesc_node_by_name(struct mdesc_handle *handle,
-			      u64 from_node, const char *name);
+u64 mdesc_node_by_name(struct mdesc_handle *handle,
+		       u64 from_node, const char *name);
 #define mdesc_for_each_node_by_name(__hdl, __node, __name) \
 	for (__node = mdesc_node_by_name(__hdl, MDESC_NODE_NULL, __name); \
 	     (__node) != MDESC_NODE_NULL; \
@@ -34,9 +34,9 @@
  *
  * These same rules apply to mdesc_node_name().
  */
-extern const void *mdesc_get_property(struct mdesc_handle *handle,
-				      u64 node, const char *name, int *lenp);
-extern const char *mdesc_node_name(struct mdesc_handle *hp, u64 node);
+const void *mdesc_get_property(struct mdesc_handle *handle,
+			       u64 node, const char *name, int *lenp);
+const char *mdesc_node_name(struct mdesc_handle *hp, u64 node);
 
 /* MD arc iteration, the standard sequence is:
  *
@@ -50,16 +50,16 @@
 #define MDESC_ARC_TYPE_FWD	"fwd"
 #define MDESC_ARC_TYPE_BACK	"back"
 
-extern u64 mdesc_next_arc(struct mdesc_handle *handle, u64 from,
-			  const char *arc_type);
+u64 mdesc_next_arc(struct mdesc_handle *handle, u64 from,
+		   const char *arc_type);
 #define mdesc_for_each_arc(__arc, __hdl, __node, __type) \
 	for (__arc = mdesc_next_arc(__hdl, __node, __type); \
 	     (__arc) != MDESC_NODE_NULL; \
 	     __arc = mdesc_next_arc(__hdl, __arc, __type))
 
-extern u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc);
+u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc);
 
-extern void mdesc_update(void);
+void mdesc_update(void);
 
 struct mdesc_notifier_client {
 	void (*add)(struct mdesc_handle *handle, u64 node);
@@ -69,12 +69,12 @@
 	struct mdesc_notifier_client	*next;
 };
 
-extern void mdesc_register_notifier(struct mdesc_notifier_client *client);
+void mdesc_register_notifier(struct mdesc_notifier_client *client);
 
-extern void mdesc_fill_in_cpu_data(cpumask_t *mask);
-extern void mdesc_populate_present_mask(cpumask_t *mask);
-extern void mdesc_get_page_sizes(cpumask_t *mask, unsigned long *pgsz_mask);
+void mdesc_fill_in_cpu_data(cpumask_t *mask);
+void mdesc_populate_present_mask(cpumask_t *mask);
+void mdesc_get_page_sizes(cpumask_t *mask, unsigned long *pgsz_mask);
 
-extern void sun4v_mdesc_init(void);
+void sun4v_mdesc_init(void);
 
 #endif
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index f668797..70067ce 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -67,9 +67,9 @@
 	unsigned long pte;
 } __attribute__((aligned(TSB_ENTRY_ALIGNMENT)));
 
-extern void __tsb_insert(unsigned long ent, unsigned long tag, unsigned long pte);
-extern void tsb_flush(unsigned long ent, unsigned long tag);
-extern void tsb_init(struct tsb *tsb, unsigned long size);
+void __tsb_insert(unsigned long ent, unsigned long tag, unsigned long pte);
+void tsb_flush(unsigned long ent, unsigned long tag);
+void tsb_init(struct tsb *tsb, unsigned long size);
 
 struct tsb_config {
 	struct tsb		*tsb;
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 3d528f0..b84be67 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -17,20 +17,20 @@
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
-extern void get_new_mmu_context(struct mm_struct *mm);
+void get_new_mmu_context(struct mm_struct *mm);
 #ifdef CONFIG_SMP
-extern void smp_new_mmu_context_version(void);
+void smp_new_mmu_context_version(void);
 #else
 #define smp_new_mmu_context_version() do { } while (0)
 #endif
 
-extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-extern void destroy_context(struct mm_struct *mm);
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
 
-extern void __tsb_context_switch(unsigned long pgd_pa,
-				 struct tsb_config *tsb_base,
-				 struct tsb_config *tsb_huge,
-				 unsigned long tsb_descr_pa);
+void __tsb_context_switch(unsigned long pgd_pa,
+			  struct tsb_config *tsb_base,
+			  struct tsb_config *tsb_huge,
+			  unsigned long tsb_descr_pa);
 
 static inline void tsb_context_switch(struct mm_struct *mm)
 {
@@ -46,9 +46,11 @@
 			     , __pa(&mm->context.tsb_descr[0]));
 }
 
-extern void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long mm_rss);
+void tsb_grow(struct mm_struct *mm,
+	      unsigned long tsb_index,
+	      unsigned long mm_rss);
 #ifdef CONFIG_SMP
-extern void smp_tsb_sync(struct mm_struct *mm);
+void smp_tsb_sync(struct mm_struct *mm);
 #else
 #define smp_tsb_sync(__mm) do { } while (0)
 #endif
@@ -66,7 +68,7 @@
 	: "r" (CTX_HWBITS((__mm)->context)), \
 	  "r" (SECONDARY_CONTEXT), "i" (ASI_DMMU), "i" (ASI_MMU))
 
-extern void __flush_tlb_mm(unsigned long, unsigned long);
+void __flush_tlb_mm(unsigned long, unsigned long);
 
 /* Switch the current MM context. */
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
index 72e6500..26ad2b2 100644
--- a/arch/sparc/include/asm/nmi.h
+++ b/arch/sparc/include/asm/nmi.h
@@ -1,13 +1,13 @@
 #ifndef __NMI_H
 #define __NMI_H
 
-extern int __init nmi_init(void);
-extern void perfctr_irq(int irq, struct pt_regs *regs);
-extern void nmi_adjust_hz(unsigned int new_hz);
+int __init nmi_init(void);
+void perfctr_irq(int irq, struct pt_regs *regs);
+void nmi_adjust_hz(unsigned int new_hz);
 
 extern atomic_t nmi_active;
 
-extern void start_nmi_watchdog(void *unused);
-extern void stop_nmi_watchdog(void *unused);
+void start_nmi_watchdog(void *unused);
+void stop_nmi_watchdog(void *unused);
 
 #endif /* __NMI_H */
diff --git a/arch/sparc/include/asm/oplib_32.h b/arch/sparc/include/asm/oplib_32.h
index c72f3045..56a09b9 100644
--- a/arch/sparc/include/asm/oplib_32.h
+++ b/arch/sparc/include/asm/oplib_32.h
@@ -43,28 +43,28 @@
 /* You must call prom_init() before using any of the library services,
  * preferably as early as possible.  Pass it the romvec pointer.
  */
-extern void prom_init(struct linux_romvec *rom_ptr);
+void prom_init(struct linux_romvec *rom_ptr);
 
 /* Boot argument acquisition, returns the boot command line string. */
-extern char *prom_getbootargs(void);
+char *prom_getbootargs(void);
 
 /* Miscellaneous routines, don't really fit in any category per se. */
 
 /* Reboot the machine with the command line passed. */
-extern void prom_reboot(char *boot_command);
+void prom_reboot(char *boot_command);
 
 /* Evaluate the forth string passed. */
-extern void prom_feval(char *forth_string);
+void prom_feval(char *forth_string);
 
 /* Enter the prom, with possibility of continuation with the 'go'
  * command in newer proms.
  */
-extern void prom_cmdline(void);
+void prom_cmdline(void);
 
 /* Enter the prom, with no chance of continuation for the stand-alone
  * which calls this.
  */
-extern void __noreturn prom_halt(void);
+void __noreturn prom_halt(void);
 
 /* Set the PROM 'sync' callback function to the passed function pointer.
  * When the user gives the 'sync' command at the prom prompt while the
@@ -73,37 +73,37 @@
  * XXX The arguments are different on V0 vs. V2->higher proms, grrr! XXX
  */
 typedef void (*sync_func_t)(void);
-extern void prom_setsync(sync_func_t func_ptr);
+void prom_setsync(sync_func_t func_ptr);
 
 /* Acquire the IDPROM of the root node in the prom device tree.  This
  * gets passed a buffer where you would like it stuffed.  The return value
  * is the format type of this idprom or 0xff on error.
  */
-extern unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
+unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
 
 /* Get the prom major version. */
-extern int prom_version(void);
+int prom_version(void);
 
 /* Get the prom plugin revision. */
-extern int prom_getrev(void);
+int prom_getrev(void);
 
 /* Get the prom firmware revision. */
-extern int prom_getprev(void);
+int prom_getprev(void);
 
 /* Write a buffer of characters to the console. */
-extern void prom_console_write_buf(const char *buf, int len);
+void prom_console_write_buf(const char *buf, int len);
 
 /* Prom's internal routines, don't use in kernel/boot code. */
-extern __printf(1, 2) void prom_printf(const char *fmt, ...);
-extern void prom_write(const char *buf, unsigned int len);
+__printf(1, 2) void prom_printf(const char *fmt, ...);
+void prom_write(const char *buf, unsigned int len);
 
 /* Multiprocessor operations... */
 
 /* Start the CPU with the given device tree node, context table, and context
  * at the passed program counter.
  */
-extern int prom_startcpu(int cpunode, struct linux_prom_registers *context_table,
-			 int context, char *program_counter);
+int prom_startcpu(int cpunode, struct linux_prom_registers *context_table,
+		  int context, char *program_counter);
 
 /* Initialize the memory lists based upon the prom version. */
 void prom_meminit(void);
@@ -111,65 +111,65 @@
 /* PROM device tree traversal functions... */
 
 /* Get the child node of the given node, or zero if no child exists. */
-extern phandle prom_getchild(phandle parent_node);
+phandle prom_getchild(phandle parent_node);
 
 /* Get the next sibling node of the given node, or zero if no further
  * siblings exist.
  */
-extern phandle prom_getsibling(phandle node);
+phandle prom_getsibling(phandle node);
 
 /* Get the length, at the passed node, of the given property type.
  * Returns -1 on error (ie. no such property at this node).
  */
-extern int prom_getproplen(phandle thisnode, const char *property);
+int prom_getproplen(phandle thisnode, const char *property);
 
 /* Fetch the requested property using the given buffer.  Returns
  * the number of bytes the prom put into your buffer or -1 on error.
  */
-extern int __must_check prom_getproperty(phandle thisnode, const char *property,
-					 char *prop_buffer, int propbuf_size);
+int __must_check prom_getproperty(phandle thisnode, const char *property,
+				  char *prop_buffer, int propbuf_size);
 
 /* Acquire an integer property. */
-extern int prom_getint(phandle node, char *property);
+int prom_getint(phandle node, char *property);
 
 /* Acquire an integer property, with a default value. */
-extern int prom_getintdefault(phandle node, char *property, int defval);
+int prom_getintdefault(phandle node, char *property, int defval);
 
 /* Acquire a boolean property, 0=FALSE 1=TRUE. */
-extern int prom_getbool(phandle node, char *prop);
+int prom_getbool(phandle node, char *prop);
 
 /* Acquire a string property, null string on error. */
-extern void prom_getstring(phandle node, char *prop, char *buf, int bufsize);
+void prom_getstring(phandle node, char *prop, char *buf, int bufsize);
 
 /* Search all siblings starting at the passed node for "name" matching
  * the given string.  Returns the node on success, zero on failure.
  */
-extern phandle prom_searchsiblings(phandle node_start, char *name);
+phandle prom_searchsiblings(phandle node_start, char *name);
 
 /* Returns the next property after the passed property for the given
  * node.  Returns null string on failure.
  */
-extern char *prom_nextprop(phandle node, char *prev_property, char *buffer);
+char *prom_nextprop(phandle node, char *prev_property, char *buffer);
 
 /* Returns phandle of the path specified */
-extern phandle prom_finddevice(char *name);
+phandle prom_finddevice(char *name);
 
 /* Set the indicated property at the given node with the passed value.
  * Returns the number of bytes of your value that the prom took.
  */
-extern int prom_setprop(phandle node, const char *prop_name, char *prop_value,
-			int value_size);
+int prom_setprop(phandle node, const char *prop_name, char *prop_value,
+		 int value_size);
 
-extern phandle prom_inst2pkg(int);
+phandle prom_inst2pkg(int);
 
 /* Dorking with Bus ranges... */
 
 /* Apply promlib probes OBIO ranges to registers. */
-extern void prom_apply_obio_ranges(struct linux_prom_registers *obioregs, int nregs);
+void prom_apply_obio_ranges(struct linux_prom_registers *obioregs, int nregs);
 
 /* Apply ranges of any prom node (and optionally parent node as well) to registers. */
-extern void prom_apply_generic_ranges(phandle node, phandle parent,
-				      struct linux_prom_registers *sbusregs, int nregs);
+void prom_apply_generic_ranges(phandle node, phandle parent,
+			       struct linux_prom_registers *sbusregs, int nregs);
 
 void prom_ranges_init(void);
 
diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h
index a12dbe3..f346824 100644
--- a/arch/sparc/include/asm/oplib_64.h
+++ b/arch/sparc/include/asm/oplib_64.h
@@ -62,100 +62,100 @@
 /* You must call prom_init() before using any of the library services,
  * preferably as early as possible.  Pass it the romvec pointer.
  */
-extern void prom_init(void *cif_handler, void *cif_stack);
+void prom_init(void *cif_handler, void *cif_stack);
 
 /* Boot argument acquisition, returns the boot command line string. */
-extern char *prom_getbootargs(void);
+char *prom_getbootargs(void);
 
 /* Miscellaneous routines, don't really fit in any category per se. */
 
 /* Reboot the machine with the command line passed. */
-extern void prom_reboot(const char *boot_command);
+void prom_reboot(const char *boot_command);
 
 /* Evaluate the forth string passed. */
-extern void prom_feval(const char *forth_string);
+void prom_feval(const char *forth_string);
 
 /* Enter the prom, with possibility of continuation with the 'go'
  * command in newer proms.
  */
-extern void prom_cmdline(void);
+void prom_cmdline(void);
 
 /* Enter the prom, with no chance of continuation for the stand-alone
  * which calls this.
  */
-extern void prom_halt(void) __attribute__ ((noreturn));
+void prom_halt(void) __attribute__ ((noreturn));
 
 /* Halt and power-off the machine. */
-extern void prom_halt_power_off(void) __attribute__ ((noreturn));
+void prom_halt_power_off(void) __attribute__ ((noreturn));
 
 /* Acquire the IDPROM of the root node in the prom device tree.  This
  * gets passed a buffer where you would like it stuffed.  The return value
  * is the format type of this idprom or 0xff on error.
  */
-extern unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
+unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
 
 /* Write a buffer of characters to the console. */
-extern void prom_console_write_buf(const char *buf, int len);
+void prom_console_write_buf(const char *buf, int len);
 
 /* Prom's internal routines, don't use in kernel/boot code. */
-extern __printf(1, 2) void prom_printf(const char *fmt, ...);
-extern void prom_write(const char *buf, unsigned int len);
+__printf(1, 2) void prom_printf(const char *fmt, ...);
+void prom_write(const char *buf, unsigned int len);
 
 /* Multiprocessor operations... */
 #ifdef CONFIG_SMP
 /* Start the CPU with the given device tree node at the passed program
  * counter with the given arg passed in via register %o0.
  */
-extern void prom_startcpu(int cpunode, unsigned long pc, unsigned long arg);
+void prom_startcpu(int cpunode, unsigned long pc, unsigned long arg);
 
 /* Start the CPU with the given cpu ID at the passed program
  * counter with the given arg passed in via register %o0.
  */
-extern void prom_startcpu_cpuid(int cpuid, unsigned long pc, unsigned long arg);
+void prom_startcpu_cpuid(int cpuid, unsigned long pc, unsigned long arg);
 
 /* Stop the CPU with the given cpu ID.  */
-extern void prom_stopcpu_cpuid(int cpuid);
+void prom_stopcpu_cpuid(int cpuid);
 
 /* Stop the current CPU. */
-extern void prom_stopself(void);
+void prom_stopself(void);
 
 /* Idle the current CPU. */
-extern void prom_idleself(void);
+void prom_idleself(void);
 
 /* Resume the CPU with the passed device tree node. */
-extern void prom_resumecpu(int cpunode);
+void prom_resumecpu(int cpunode);
 #endif
 
 /* Power management interfaces. */
 
 /* Put the current CPU to sleep. */
-extern void prom_sleepself(void);
+void prom_sleepself(void);
 
 /* Put the entire system to sleep. */
-extern int prom_sleepsystem(void);
+int prom_sleepsystem(void);
 
 /* Initiate a wakeup event. */
-extern int prom_wakeupsystem(void);
+int prom_wakeupsystem(void);
 
 /* MMU and memory related OBP interfaces. */
 
 /* Get unique string identifying SIMM at given physical address. */
-extern int prom_getunumber(int syndrome_code,
-			   unsigned long phys_addr,
-			   char *buf, int buflen);
+int prom_getunumber(int syndrome_code,
+		    unsigned long phys_addr,
+		    char *buf, int buflen);
 
 /* Retain physical memory to the caller across soft resets. */
-extern int prom_retain(const char *name, unsigned long size,
-		       unsigned long align, unsigned long *paddr);
+int prom_retain(const char *name, unsigned long size,
+		unsigned long align, unsigned long *paddr);
 
 /* Load explicit I/D TLB entries into the calling processor. */
-extern long prom_itlb_load(unsigned long index,
-			   unsigned long tte_data,
-			   unsigned long vaddr);
+long prom_itlb_load(unsigned long index,
+		    unsigned long tte_data,
+		    unsigned long vaddr);
 
-extern long prom_dtlb_load(unsigned long index,
-			   unsigned long tte_data,
-			   unsigned long vaddr);
+long prom_dtlb_load(unsigned long index,
+		    unsigned long tte_data,
+		    unsigned long vaddr);
 
 /* Map/Unmap client program address ranges.  First the format of
  * the mapping mode argument.
@@ -170,81 +170,81 @@
 #define PROM_MAP_IE	0x0100 /* Invert-Endianness */
 #define PROM_MAP_DEFAULT (PROM_MAP_WRITE | PROM_MAP_READ | PROM_MAP_EXEC | PROM_MAP_CACHED)
 
-extern int prom_map(int mode, unsigned long size,
-		    unsigned long vaddr, unsigned long paddr);
-extern void prom_unmap(unsigned long size, unsigned long vaddr);
+int prom_map(int mode, unsigned long size,
+	     unsigned long vaddr, unsigned long paddr);
+void prom_unmap(unsigned long size, unsigned long vaddr);
 
 
 /* PROM device tree traversal functions... */
 
 /* Get the child node of the given node, or zero if no child exists. */
-extern phandle prom_getchild(phandle parent_node);
+phandle prom_getchild(phandle parent_node);
 
 /* Get the next sibling node of the given node, or zero if no further
  * siblings exist.
  */
-extern phandle prom_getsibling(phandle node);
+phandle prom_getsibling(phandle node);
 
 /* Get the length, at the passed node, of the given property type.
  * Returns -1 on error (ie. no such property at this node).
  */
-extern int prom_getproplen(phandle thisnode, const char *property);
+int prom_getproplen(phandle thisnode, const char *property);
 
 /* Fetch the requested property using the given buffer.  Returns
  * the number of bytes the prom put into your buffer or -1 on error.
  */
-extern int prom_getproperty(phandle thisnode, const char *property,
-			    char *prop_buffer, int propbuf_size);
+int prom_getproperty(phandle thisnode, const char *property,
+		     char *prop_buffer, int propbuf_size);
 
 /* Acquire an integer property. */
-extern int prom_getint(phandle node, const char *property);
+int prom_getint(phandle node, const char *property);
 
 /* Acquire an integer property, with a default value. */
-extern int prom_getintdefault(phandle node, const char *property, int defval);
+int prom_getintdefault(phandle node, const char *property, int defval);
 
 /* Acquire a boolean property, 0=FALSE 1=TRUE. */
-extern int prom_getbool(phandle node, const char *prop);
+int prom_getbool(phandle node, const char *prop);
 
 /* Acquire a string property, null string on error. */
-extern void prom_getstring(phandle node, const char *prop, char *buf,
-			   int bufsize);
+void prom_getstring(phandle node, const char *prop, char *buf,
+		    int bufsize);
 
 /* Does the passed node have the given "name"? YES=1 NO=0 */
-extern int prom_nodematch(phandle thisnode, const char *name);
+int prom_nodematch(phandle thisnode, const char *name);
 
 /* Search all siblings starting at the passed node for "name" matching
  * the given string.  Returns the node on success, zero on failure.
  */
-extern phandle prom_searchsiblings(phandle node_start, const char *name);
+phandle prom_searchsiblings(phandle node_start, const char *name);
 
 /* Return the first property type, as a string, for the given node.
  * Returns a null string on error. Buffer should be at least 32B long.
  */
-extern char *prom_firstprop(phandle node, char *buffer);
+char *prom_firstprop(phandle node, char *buffer);
 
 /* Returns the next property after the passed property for the given
  * node.  Returns null string on failure. Buffer should be at least 32B long.
  */
-extern char *prom_nextprop(phandle node, const char *prev_property, char *buf);
+char *prom_nextprop(phandle node, const char *prev_property, char *buf);
 
 /* Returns 1 if the specified node has given property. */
-extern int prom_node_has_property(phandle node, const char *property);
+int prom_node_has_property(phandle node, const char *property);
 
 /* Returns phandle of the path specified */
-extern phandle prom_finddevice(const char *name);
+phandle prom_finddevice(const char *name);
 
 /* Set the indicated property at the given node with the passed value.
  * Returns the number of bytes of your value that the prom took.
  */
-extern int prom_setprop(phandle node, const char *prop_name, char *prop_value,
-			int value_size);
+int prom_setprop(phandle node, const char *prop_name, char *prop_value,
+		 int value_size);
 
-extern phandle prom_inst2pkg(int);
-extern void prom_sun4v_guest_soft_state(void);
+phandle prom_inst2pkg(int);
+void prom_sun4v_guest_soft_state(void);
 
-extern int prom_ihandle2path(int handle, char *buffer, int bufsize);
+int prom_ihandle2path(int handle, char *buffer, int bufsize);
 
 /* Client interface level routines. */
-extern void p1275_cmd_direct(unsigned long *);
+void p1275_cmd_direct(unsigned long *);
 
 #endif /* !(__SPARC64_OPLIB_H) */
diff --git a/arch/sparc/include/asm/page.h b/arch/sparc/include/asm/page.h
index f21de03..1be2fde 100644
--- a/arch/sparc/include/asm/page.h
+++ b/arch/sparc/include/asm/page.h
@@ -1,5 +1,8 @@
 #ifndef ___ASM_SPARC_PAGE_H
 #define ___ASM_SPARC_PAGE_H
+
+#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/page_64.h>
 #else
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index aac53fc..bf10998 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -31,17 +31,17 @@
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
 struct pt_regs;
-extern void hugetlb_setup(struct pt_regs *regs);
+void hugetlb_setup(struct pt_regs *regs);
 #endif
 
 #define WANT_PAGE_VIRTUAL
 
-extern void _clear_page(void *page);
+void _clear_page(void *page);
 #define clear_page(X)	_clear_page((void *)(X))
 struct page;
-extern void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
 #define copy_page(X,Y)	memcpy((void *)(X), (void *)(Y), PAGE_SIZE)
-extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
+void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
 
 /* Unlike sparc32, sparc64's parameter passing API is more
  * sane in that structures which as small enough are passed
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index c6c7396..bd00a62 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -52,7 +52,7 @@
 
 /* Return the index of the PCI controller for device PDEV. */
 
-extern int pci_domain_nr(struct pci_bus *bus);
+int pci_domain_nr(struct pci_bus *bus);
 static inline int pci_proc_domain(struct pci_bus *bus)
 {
 	return 1;
@@ -64,9 +64,9 @@
 #define HAVE_ARCH_PCI_GET_UNMAPPED_AREA
 #define get_pci_unmapped_area get_fb_unmapped_area
 
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			       enum pci_mmap_state mmap_state,
-			       int write_combine);
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state,
+			int write_combine);
 
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
@@ -74,9 +74,9 @@
 }
 
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
-extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
-				 const struct resource *rsrc,
-				 resource_size_t *start, resource_size_t *end);
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc,
+			  resource_size_t *start, resource_size_t *end);
 #endif /* __KERNEL__ */
 
 #endif /* __SPARC64_PCI_H */
diff --git a/arch/sparc/include/asm/pcic.h b/arch/sparc/include/asm/pcic.h
index 6676cbc..f417067 100644
--- a/arch/sparc/include/asm/pcic.h
+++ b/arch/sparc/include/asm/pcic.h
@@ -30,10 +30,10 @@
 };
 
 #ifdef CONFIG_PCIC_PCI
-extern int pcic_present(void);
-extern int pcic_probe(void);
-extern void pci_time_init(void);
-extern void sun4m_pci_init_IRQ(void);
+int pcic_present(void);
+int pcic_probe(void);
+void pci_time_init(void);
+void sun4m_pci_init_IRQ(void);
 #else
 static inline int pcic_present(void) { return 0; }
 static inline int pcic_probe(void) { return 0; }
diff --git a/arch/sparc/include/asm/pcr.h b/arch/sparc/include/asm/pcr.h
index 942bb17..cdf800c 100644
--- a/arch/sparc/include/asm/pcr.h
+++ b/arch/sparc/include/asm/pcr.h
@@ -12,8 +12,8 @@
 };
 extern const struct pcr_ops *pcr_ops;
 
-extern void deferred_pcr_work_irq(int irq, struct pt_regs *regs);
-extern void schedule_deferred_pcr_work(void);
+void deferred_pcr_work_irq(int irq, struct pt_regs *regs);
+void schedule_deferred_pcr_work(void);
 
 #define PCR_PIC_PRIV		0x00000001 /* PIC access is privileged */
 #define PCR_STRACE		0x00000002 /* Trace supervisor events  */
@@ -45,6 +45,6 @@
 #define PCR_N4_PICNHT		0x00020000 /* PIC non-hypervisor trap  */
 #define PCR_N4_NTC		0x00040000 /* Next-To-Commit wrap      */
 
-extern int pcr_arch_init(void);
+int pcr_arch_init(void);
 
 #endif /* __PCR_H */
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index 9b1c36d..a3890da 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -14,6 +14,8 @@
 void *srmmu_get_nocache(int size, int align);
 void srmmu_free_nocache(void *addr, int size);
 
+extern struct resource sparc_iomap;
+
 #define check_pgt_cache()	do { } while (0)
 
 pgd_t *get_pgd_fast(void);
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index bcfe063..39a7ac4 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -38,12 +38,12 @@
 	kmem_cache_free(pgtable_cache, pmd);
 }
 
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-				   unsigned long address);
-extern pgtable_t pte_alloc_one(struct mm_struct *mm,
-			       unsigned long address);
-extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, pgtable_t ptepage);
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+			    unsigned long address);
+pgtable_t pte_alloc_one(struct mm_struct *mm,
+			unsigned long address);
+void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
+void pte_free(struct mm_struct *mm, pgtable_t ptepage);
 
 #define pmd_populate_kernel(MM, PMD, PTE)	pmd_set(MM, PMD, PTE)
 #define pmd_populate(MM, PMD, PTE)		pmd_set(MM, PMD, PTE)
@@ -51,12 +51,12 @@
 
 #define check_pgt_cache()	do { } while (0)
 
-extern void pgtable_free(void *table, bool is_page);
+void pgtable_free(void *table, bool is_page);
 
 #ifdef CONFIG_SMP
 
 struct mmu_gather;
-extern void tlb_remove_table(struct mmu_gather *, void *);
+void tlb_remove_table(struct mmu_gather *, void *);
 
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page)
 {
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 502f632..b9b91ae 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -25,8 +25,9 @@
 struct vm_area_struct;
 struct page;
 
-extern void load_mmu(void);
-extern unsigned long calc_highpages(void);
+void load_mmu(void);
+unsigned long calc_highpages(void);
+unsigned long __init bootmem_init(unsigned long *pages_avail);
 
 #define pte_ERROR(e)   __builtin_trap()
 #define pmd_ERROR(e)   __builtin_trap()
@@ -56,7 +57,7 @@
  * srmmu.c will assign the real one (which is dynamically sized) */
 #define swapper_pg_dir NULL
 
-extern void paging_init(void);
+void paging_init(void);
 
 extern unsigned long ptr_in_current_pgd;
 
@@ -428,8 +429,8 @@
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffUL)
 
-extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
-			   unsigned long, pgprot_t);
+int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+		    unsigned long, pgprot_t);
 
 static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 				     unsigned long from, unsigned long pfn,
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 1a49ffd..3770bf5 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -210,9 +210,9 @@
 
 #ifndef __ASSEMBLY__
 
-extern pte_t mk_pte_io(unsigned long, pgprot_t, int, unsigned long);
+pte_t mk_pte_io(unsigned long, pgprot_t, int, unsigned long);
 
-extern unsigned long pte_sz_bits(unsigned long size);
+unsigned long pte_sz_bits(unsigned long size);
 
 extern pgprot_t PAGE_KERNEL;
 extern pgprot_t PAGE_KERNEL_LOCKED;
@@ -780,8 +780,8 @@
 					 !__kern_addr_valid(pud_val(pud)))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-		       pmd_t *pmdp, pmd_t pmd);
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd);
 #else
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t pmd)
@@ -840,8 +840,8 @@
 #define pte_unmap(pte)			do { } while (0)
 
 /* Actual page table PTE updates.  */
-extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
-			  pte_t *ptep, pte_t orig, int fullmm);
+void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+		   pte_t *ptep, pte_t orig, int fullmm);
 
 #define __HAVE_ARCH_PMDP_GET_AND_CLEAR
 static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
@@ -900,28 +900,28 @@
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD];
 
-extern void paging_init(void);
-extern unsigned long find_ecache_flush_span(unsigned long size);
+void paging_init(void);
+unsigned long find_ecache_flush_span(unsigned long size);
 
 struct seq_file;
-extern void mmu_info(struct seq_file *);
+void mmu_info(struct seq_file *);
 
 struct vm_area_struct;
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
+void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
-				 pmd_t *pmd);
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+			  pmd_t *pmd);
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
 extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				       pgtable_t pgtable);
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
 /* Encode and de-code a swap entry */
@@ -937,12 +937,12 @@
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
 /* File offset in PTE support. */
-extern unsigned long pte_file(pte_t);
+unsigned long pte_file(pte_t);
 #define pte_to_pgoff(pte)	(pte_val(pte) >> PAGE_SHIFT)
-extern pte_t pgoff_to_pte(unsigned long);
+pte_t pgoff_to_pte(unsigned long);
 #define PTE_FILE_MAX_BITS	(64UL - PAGE_SHIFT - 1UL)
 
-extern int page_in_phys_avail(unsigned long paddr);
+int page_in_phys_avail(unsigned long paddr);
 
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
@@ -952,8 +952,8 @@
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffffffffffUL)
 
-extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
-			   unsigned long, pgprot_t);
+int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+		    unsigned long, pgprot_t);
 
 static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 				     unsigned long from, unsigned long pfn,
@@ -981,20 +981,20 @@
 /* We provide a special get_unmapped_area for framebuffer mmaps to try and use
  * the largest alignment possible such that larget PTEs can be used.
  */
-extern unsigned long get_fb_unmapped_area(struct file *filp, unsigned long,
-					  unsigned long, unsigned long,
-					  unsigned long);
+unsigned long get_fb_unmapped_area(struct file *filp, unsigned long,
+				   unsigned long, unsigned long,
+				   unsigned long);
 #define HAVE_ARCH_FB_UNMAPPED_AREA
 
-extern void pgtable_cache_init(void);
-extern void sun4v_register_fault_status(void);
-extern void sun4v_ktsb_register(void);
-extern void __init cheetah_ecache_flush_init(void);
-extern void sun4v_patch_tlb_handlers(void);
+void pgtable_cache_init(void);
+void sun4v_register_fault_status(void);
+void sun4v_ktsb_register(void);
+void __init cheetah_ecache_flush_init(void);
+void sun4v_patch_tlb_handlers(void);
 
 extern unsigned long cmdline_memory_size;
 
-extern asmlinkage void do_sparc64_fault(struct pt_regs *regs);
+asmlinkage void do_sparc64_fault(struct pt_regs *regs);
 
 #endif /* !(__ASSEMBLY__) */
 
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 2c7baa4..a564817 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -74,7 +74,7 @@
 }
 
 /* Return saved PC of a blocked thread. */
-extern unsigned long thread_saved_pc(struct task_struct *t);
+unsigned long thread_saved_pc(struct task_struct *t);
 
 /* Do necessary setup to start up a newly executed thread. */
 static inline void start_thread(struct pt_regs * regs, unsigned long pc,
@@ -107,7 +107,7 @@
 /* Free all resources held by a thread. */
 #define release_thread(tsk)		do { } while(0)
 
-extern unsigned long get_wchan(struct task_struct *);
+unsigned long get_wchan(struct task_struct *);
 
 #define task_pt_regs(tsk) ((tsk)->thread.kregs)
 #define KSTK_EIP(tsk)  ((tsk)->thread.kregs->pc)
@@ -116,6 +116,7 @@
 #ifdef __KERNEL__
 
 extern struct task_struct *last_task_used_math;
+int do_mathemu(struct pt_regs *regs, struct task_struct *fpt);
 
 #define cpu_relax()	barrier()
 extern void (*sparc_idle)(void);
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 4c3f7f0..7028fe1 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -95,7 +95,7 @@
 
 /* Return saved PC of a blocked thread. */
 struct task_struct;
-extern unsigned long thread_saved_pc(struct task_struct *);
+unsigned long thread_saved_pc(struct task_struct *);
 
 /* On Uniprocessor, even in RMO processes see TSO semantics */
 #ifdef CONFIG_SMP
@@ -194,7 +194,7 @@
 /* Free all resources held by a thread. */
 #define release_thread(tsk)		do { } while (0)
 
-extern unsigned long get_wchan(struct task_struct *task);
+unsigned long get_wchan(struct task_struct *task);
 
 #define task_pt_regs(tsk) (task_thread_info(tsk)->kregs)
 #define KSTK_EIP(tsk)  (task_pt_regs(tsk)->tpc)
@@ -253,6 +253,8 @@
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
 
+int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap);
+
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__ASM_SPARC64_PROCESSOR_H) */
diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index 11ebd65..d955c8d 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -36,28 +36,28 @@
 	void		*data;
 };
 
-extern struct device_node *of_find_node_by_cpuid(int cpuid);
-extern int of_set_property(struct device_node *node, const char *name, void *val, int len);
+struct device_node *of_find_node_by_cpuid(int cpuid);
+int of_set_property(struct device_node *node, const char *name, void *val, int len);
 extern struct mutex of_set_property_mutex;
-extern int of_getintprop_default(struct device_node *np,
-				 const char *name,
+int of_getintprop_default(struct device_node *np,
+			  const char *name,
 				 int def);
-extern int of_find_in_proplist(const char *list, const char *match, int len);
+int of_find_in_proplist(const char *list, const char *match, int len);
 
-extern void prom_build_devicetree(void);
-extern void of_populate_present_mask(void);
-extern void of_fill_in_cpu_data(void);
+void prom_build_devicetree(void);
+void of_populate_present_mask(void);
+void of_fill_in_cpu_data(void);
 
 struct resource;
-extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name);
-extern void of_iounmap(struct resource *res, void __iomem *base, unsigned long size);
+void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name);
+void of_iounmap(struct resource *res, void __iomem *base, unsigned long size);
 
 extern struct device_node *of_console_device;
 extern char *of_console_path;
 extern char *of_console_options;
 
-extern void irq_trans_init(struct device_node *dp);
-extern char *build_path_component(struct device_node *dp);
+void irq_trans_init(struct device_node *dp);
+char *build_path_component(struct device_node *dp);
 
 #endif /* __KERNEL__ */
 #endif /* _SPARC_PROM_H */
diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h
index bdfafd7..bac6a94 100644
--- a/arch/sparc/include/asm/ptrace.h
+++ b/arch/sparc/include/asm/ptrace.h
@@ -73,7 +73,7 @@
 	return regs->u_regs[UREG_I0];
 }
 #ifdef CONFIG_SMP
-extern unsigned long profile_pc(struct pt_regs *);
+unsigned long profile_pc(struct pt_regs *);
 #else
 #define profile_pc(regs) instruction_pointer(regs)
 #endif
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 5e35e05..f5fffd8 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -4,8 +4,9 @@
 #ifndef _SPARC_SETUP_H
 #define _SPARC_SETUP_H
 
-#include <uapi/asm/setup.h>
+#include <linux/interrupt.h>
 
+#include <uapi/asm/setup.h>
 
 extern char reboot_command[];
 
@@ -22,9 +23,43 @@
 {
 	return serial_console ? 0 : 1;
 }
+
+/* from irq_32.c */
+extern volatile unsigned char *fdc_status;
+extern char *pdma_vaddr;
+extern unsigned long pdma_size;
+extern volatile int doing_pdma;
+
+/* This is software state */
+extern char *pdma_base;
+extern unsigned long pdma_areasize;
+
+int sparc_floppy_request_irq(unsigned int irq, irq_handler_t irq_handler);
+
+/* setup_32.c */
+extern unsigned long cmdline_memory_size;
+
+/* devices.c */
+void __init device_scan(void);
+
+/* unaligned_32.c */
+unsigned long safe_compute_effective_address(struct pt_regs *, unsigned int);
+
 #endif
 
-extern void sun_do_break(void);
+#ifdef CONFIG_SPARC64
+/* unaligned_64.c */
+int handle_ldf_stq(u32 insn, struct pt_regs *regs);
+void handle_ld_nf(u32 insn, struct pt_regs *regs);
+
+/* init_64.c */
+extern atomic_t dcpage_flushes;
+extern atomic_t dcpage_flushes_xcall;
+
+extern int sysctl_tsb_ratio;
+#endif
+
+void sun_do_break(void);
 extern int stop_a_enabled;
 extern int scons_pwroff;
 
diff --git a/arch/sparc/include/asm/sfp-machine_32.h b/arch/sparc/include/asm/sfp-machine_32.h
index 01d9c3b..838c9d58 100644
--- a/arch/sparc/include/asm/sfp-machine_32.h
+++ b/arch/sparc/include/asm/sfp-machine_32.h
@@ -79,9 +79,9 @@
   __asm__ ("addcc %r7,%8,%2\n\t"					\
 	   "addxcc %r5,%6,%1\n\t"					\
 	   "addx %r3,%4,%0\n"						\
-	   : "=r" ((USItype)(r2)),					\
-	     "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=r" (r2),							\
+	     "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x2)),					\
 	     "rI" ((USItype)(y2)),					\
 	     "%rJ" ((USItype)(x1)),					\
@@ -94,9 +94,9 @@
   __asm__ ("subcc %r7,%8,%2\n\t"					\
 	    "subxcc %r5,%6,%1\n\t"					\
 	    "subx %r3,%4,%0\n"						\
-	   : "=r" ((USItype)(r2)),					\
-	     "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=r" (r2),							\
+	     "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x2)),					\
 	     "rI" ((USItype)(y2)),					\
 	     "%rJ" ((USItype)(x1)),					\
@@ -115,8 +115,8 @@
 	    "addxcc %r6,%7,%0\n\t"					\
 	    "addxcc %r4,%5,%%g2\n\t"					\
 	    "addx %r2,%3,%%g1\n\t"					\
-	   : "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x3)),					\
 	     "rI" ((USItype)(y3)),					\
 	     "%rJ" ((USItype)(x2)),					\
@@ -140,8 +140,8 @@
 	    "subxcc %r6,%7,%0\n\t"					\
 	    "subxcc %r4,%5,%%g2\n\t"					\
 	    "subx %r2,%3,%%g1\n\t"					\
-	   : "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x3)),					\
 	     "rI" ((USItype)(y3)),					\
 	     "%rJ" ((USItype)(x2)),					\
@@ -164,10 +164,10 @@
 	   "addxcc %2,%%g0,%2\n\t"					\
 	   "addxcc %1,%%g0,%1\n\t"					\
 	   "addx %0,%%g0,%0\n\t"					\
-	   : "=&r" ((USItype)(x3)),					\
-	     "=&r" ((USItype)(x2)),					\
-	     "=&r" ((USItype)(x1)),					\
-	     "=&r" ((USItype)(x0))					\
+	   : "=&r" (x3),						\
+	     "=&r" (x2),						\
+	     "=&r" (x1),						\
+	     "=&r" (x0)							\
 	   : "rI" ((USItype)(i)),					\
 	     "0" ((USItype)(x3)),					\
 	     "1" ((USItype)(x2)),					\
diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h
index 3c8917f..7c24e08a 100644
--- a/arch/sparc/include/asm/smp_32.h
+++ b/arch/sparc/include/asm/smp_32.h
@@ -93,15 +93,15 @@
 				    arg1, arg2, arg3, arg4);
 }
 
-extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+void arch_send_call_function_single_ipi(int cpu);
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 static inline int cpu_logical_map(int cpu)
 {
 	return cpu;
 }
 
-extern int hard_smp_processor_id(void);
+int hard_smp_processor_id(void);
 
 #define raw_smp_processor_id()		(current_thread_info()->cpu)
 
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index 0571039..26d9e77 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -33,29 +33,35 @@
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern cpumask_t cpu_core_map[NR_CPUS];
 
-extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+void arch_send_call_function_single_ipi(int cpu);
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 /*
  *	General functions that each host system must provide.
  */
 
-extern int hard_smp_processor_id(void);
+int hard_smp_processor_id(void);
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
-extern void smp_fill_in_sib_core_maps(void);
-extern void cpu_play_dead(void);
+void smp_fill_in_sib_core_maps(void);
+void cpu_play_dead(void);
 
-extern void smp_fetch_global_regs(void);
-extern void smp_fetch_global_pmu(void);
+void smp_fetch_global_regs(void);
+void smp_fetch_global_pmu(void);
 
 struct seq_file;
 void smp_bogo(struct seq_file *);
 void smp_info(struct seq_file *);
 
+void smp_callin(void);
+void cpu_panic(void);
+void smp_synchronize_tick_client(void);
+void smp_capture(void);
+void smp_release(void);
+
 #ifdef CONFIG_HOTPLUG_CPU
-extern int __cpu_disable(void);
-extern void __cpu_die(unsigned int cpu);
+int __cpu_disable(void);
+void __cpu_die(unsigned int cpu);
 #endif
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 6b67e50..3fc58691 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -62,7 +62,7 @@
 extern int sun4v_chip_type;
 
 extern int cheetah_pcache_forced_on;
-extern void cheetah_enable_pcache(void);
+void cheetah_enable_pcache(void);
 
 #define sparc64_highest_locked_tlbent()	\
 	(tlb_type == spitfire ? \
diff --git a/arch/sparc/include/asm/stacktrace.h b/arch/sparc/include/asm/stacktrace.h
index 6cee39a..c30d066 100644
--- a/arch/sparc/include/asm/stacktrace.h
+++ b/arch/sparc/include/asm/stacktrace.h
@@ -1,6 +1,6 @@
 #ifndef _SPARC64_STACKTRACE_H
 #define _SPARC64_STACKTRACE_H
 
-extern void stack_trace_flush(void);
+void stack_trace_flush(void);
 
 #endif /* _SPARC64_STACKTRACE_H */
diff --git a/arch/sparc/include/asm/starfire.h b/arch/sparc/include/asm/starfire.h
index d56ce60a..c100dc2 100644
--- a/arch/sparc/include/asm/starfire.h
+++ b/arch/sparc/include/asm/starfire.h
@@ -11,10 +11,10 @@
 
 extern int this_is_starfire;
 
-extern void check_if_starfire(void);
-extern int starfire_hard_smp_processor_id(void);
-extern void starfire_hookup(int);
-extern unsigned int starfire_translate(unsigned long imap, unsigned int upaid);
+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);
 
 #endif
 #endif
diff --git a/arch/sparc/include/asm/string_32.h b/arch/sparc/include/asm/string_32.h
index 12f6785..69974e9 100644
--- a/arch/sparc/include/asm/string_32.h
+++ b/arch/sparc/include/asm/string_32.h
@@ -15,7 +15,7 @@
 
 #ifdef __KERNEL__
 
-extern void __memmove(void *,const void *,__kernel_size_t);
+void __memmove(void *,const void *,__kernel_size_t);
 
 #ifndef EXPORT_SYMTAB_STROPS
 
@@ -40,8 +40,8 @@
 #undef memscan
 #define memscan(__arg0, __char, __arg2)						\
 ({										\
-	extern void *__memscan_zero(void *, size_t);				\
-	extern void *__memscan_generic(void *, int, size_t);			\
+	void *__memscan_zero(void *, size_t);					\
+	void *__memscan_generic(void *, int, size_t);				\
 	void *__retval, *__addr = (__arg0);					\
 	size_t __size = (__arg2);						\
 										\
@@ -54,14 +54,14 @@
 })
 
 #define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *,const void *,__kernel_size_t);
+int memcmp(const void *,const void *,__kernel_size_t);
 
 /* Now the str*() stuff... */
 #define __HAVE_ARCH_STRLEN
-extern __kernel_size_t strlen(const char *);
+__kernel_size_t strlen(const char *);
 
 #define __HAVE_ARCH_STRNCMP
-extern int strncmp(const char *, const char *, __kernel_size_t);
+int strncmp(const char *, const char *, __kernel_size_t);
 
 #endif /* !EXPORT_SYMTAB_STROPS */
 
diff --git a/arch/sparc/include/asm/string_64.h b/arch/sparc/include/asm/string_64.h
index 9623bc2..5936b8f 100644
--- a/arch/sparc/include/asm/string_64.h
+++ b/arch/sparc/include/asm/string_64.h
@@ -19,7 +19,7 @@
 
 /* First the mem*() things. */
 #define __HAVE_ARCH_MEMMOVE
-extern void *memmove(void *, const void *, __kernel_size_t);
+void *memmove(void *, const void *, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMCPY
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
@@ -32,8 +32,8 @@
 #undef memscan
 #define memscan(__arg0, __char, __arg2)					\
 ({									\
-	extern void *__memscan_zero(void *, size_t);			\
-	extern void *__memscan_generic(void *, int, size_t);		\
+	void *__memscan_zero(void *, size_t);				\
+	void *__memscan_generic(void *, int, size_t);			\
 	void *__retval, *__addr = (__arg0);				\
 	size_t __size = (__arg2);					\
 									\
@@ -46,14 +46,14 @@
 })
 
 #define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *,const void *,__kernel_size_t);
+int memcmp(const void *,const void *,__kernel_size_t);
 
 /* Now the str*() stuff... */
 #define __HAVE_ARCH_STRLEN
-extern __kernel_size_t strlen(const char *);
+__kernel_size_t strlen(const char *);
 
 #define __HAVE_ARCH_STRNCMP
-extern int strncmp(const char *, const char *, __kernel_size_t);
+int strncmp(const char *, const char *, __kernel_size_t);
 
 #endif /* !EXPORT_SYMTAB_STROPS */
 
diff --git a/arch/sparc/include/asm/switch_to_32.h b/arch/sparc/include/asm/switch_to_32.h
index e32e82b..16f1037 100644
--- a/arch/sparc/include/asm/switch_to_32.h
+++ b/arch/sparc/include/asm/switch_to_32.h
@@ -99,8 +99,8 @@
 	  "o0", "o1", "o2", "o3",                   "o7");	\
 	} while(0)
 
-extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
-		   void *fpqueue, unsigned long *fpqdepth);
-extern void synchronize_user_stack(void);
+void fpsave(unsigned long *fpregs, unsigned long *fsr,
+	    void *fpqueue, unsigned long *fpqdepth);
+void synchronize_user_stack(void);
 
 #endif /* __SPARC_SWITCH_TO_H */
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
index 8d28480..10e7633 100644
--- a/arch/sparc/include/asm/switch_to_64.h
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -65,7 +65,7 @@
 	  "o0", "o1", "o2", "o3", "o4", "o5",       "o7");		\
 } while(0)
 
-extern void synchronize_user_stack(void);
-extern void fault_in_user_windows(void);
+void synchronize_user_stack(void);
+void fault_in_user_windows(void);
 
 #endif /* __SPARC64_SWITCH_TO_64_H */
diff --git a/arch/sparc/include/asm/syscalls.h b/arch/sparc/include/asm/syscalls.h
index bf8972a..b0a0db8 100644
--- a/arch/sparc/include/asm/syscalls.h
+++ b/arch/sparc/include/asm/syscalls.h
@@ -3,9 +3,9 @@
 
 struct pt_regs;
 
-extern asmlinkage long sparc_do_fork(unsigned long clone_flags,
-				     unsigned long stack_start,
-				     struct pt_regs *regs,
-				     unsigned long stack_size);
+asmlinkage long sparc_do_fork(unsigned long clone_flags,
+			      unsigned long stack_start,
+			      struct pt_regs *regs,
+			      unsigned long stack_size);
 
 #endif /* _SPARC64_SYSCALLS_H */
diff --git a/arch/sparc/include/asm/timer_32.h b/arch/sparc/include/asm/timer_32.h
index 72f40a5..f8e708a 100644
--- a/arch/sparc/include/asm/timer_32.h
+++ b/arch/sparc/include/asm/timer_32.h
@@ -32,13 +32,13 @@
 	return (value + 1) << TIMER_VALUE_SHIFT;
 }
 
-extern __volatile__ unsigned int *master_l10_counter;
+extern volatile u32 __iomem *master_l10_counter;
 
-extern irqreturn_t notrace timer_interrupt(int dummy, void *dev_id);
+irqreturn_t notrace timer_interrupt(int dummy, void *dev_id);
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU(struct clock_event_device, sparc32_clockevent);
-extern void register_percpu_ce(int cpu);
+void register_percpu_ce(int cpu);
 #endif
 
 #endif /* !(_SPARC_TIMER_H) */
diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h
index 01197d8..fce4150 100644
--- a/arch/sparc/include/asm/timer_64.h
+++ b/arch/sparc/include/asm/timer_64.h
@@ -23,8 +23,8 @@
 
 extern struct sparc64_tick_ops *tick_ops;
 
-extern unsigned long sparc64_get_clock_tick(unsigned int cpu);
-extern void setup_sparc64_timer(void);
-extern void __init time_init(void);
+unsigned long sparc64_get_clock_tick(unsigned int cpu);
+void setup_sparc64_timer(void);
+void __init time_init(void);
 
 #endif /* _SPARC64_TIMER_H */
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 190e189..4cb392f 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -8,19 +8,19 @@
 #include <asm/mmu_context.h>
 
 #ifdef CONFIG_SMP
-extern void smp_flush_tlb_pending(struct mm_struct *,
+void smp_flush_tlb_pending(struct mm_struct *,
 				  unsigned long, unsigned long *);
 #endif
 
 #ifdef CONFIG_SMP
-extern void smp_flush_tlb_mm(struct mm_struct *mm);
+void smp_flush_tlb_mm(struct mm_struct *mm);
 #define do_flush_tlb_mm(mm) smp_flush_tlb_mm(mm)
 #else
 #define do_flush_tlb_mm(mm) __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT)
 #endif
 
-extern void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
-extern void flush_tlb_pending(void);
+void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
+void flush_tlb_pending(void);
 
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 3c3c89f..816d820 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -14,9 +14,9 @@
 	unsigned long vaddrs[TLB_BATCH_NR];
 };
 
-extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
-extern void flush_tsb_user(struct tlb_batch *tb);
-extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_kernel_range(unsigned long start, unsigned long end);
+void flush_tsb_user(struct tlb_batch *tb);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
@@ -36,15 +36,15 @@
 
 #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
-extern void flush_tlb_pending(void);
-extern void arch_enter_lazy_mmu_mode(void);
-extern void arch_leave_lazy_mmu_mode(void);
+void flush_tlb_pending(void);
+void arch_enter_lazy_mmu_mode(void);
+void arch_leave_lazy_mmu_mode(void);
 #define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
-extern void __flush_tlb_all(void);
-extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
-extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void __flush_tlb_all(void);
+void __flush_tlb_page(unsigned long context, unsigned long vaddr);
+void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
 
@@ -60,8 +60,8 @@
 
 #else /* CONFIG_SMP */
 
-extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
-extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
+void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {	flush_tsb_kernel_range(start,end); \
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index a2d10fc..ed8f071 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -18,7 +18,7 @@
 
 struct pci_bus;
 #ifdef CONFIG_PCI
-extern int pcibus_to_node(struct pci_bus *pbus);
+int pcibus_to_node(struct pci_bus *pbus);
 #else
 static inline int pcibus_to_node(struct pci_bus *pbus)
 {
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 7e26b2d..6fd4436 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -51,11 +51,11 @@
 	unsigned long		__per_cpu_base;
 } __attribute__((aligned(64)));
 extern struct trap_per_cpu trap_block[NR_CPUS];
-extern void init_cur_cpu_trap(struct thread_info *);
-extern void setup_tba(void);
+void init_cur_cpu_trap(struct thread_info *);
+void setup_tba(void);
 extern int ncpus_probed;
 
-extern unsigned long real_hard_smp_processor_id(void);
+unsigned long real_hard_smp_processor_id(void);
 
 struct cpuid_patch_entry {
 	unsigned int	addr;
diff --git a/arch/sparc/include/asm/uaccess.h b/arch/sparc/include/asm/uaccess.h
index 0167d26..bd56c28 100644
--- a/arch/sparc/include/asm/uaccess.h
+++ b/arch/sparc/include/asm/uaccess.h
@@ -9,6 +9,6 @@
 #define user_addr_max() \
 	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
 
-extern long strncpy_from_user(char *dest, const char __user *src, long count);
+long strncpy_from_user(char *dest, const char __user *src, long count);
 
 #endif
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 53a28dd..9634d08 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -78,9 +78,9 @@
 };
 
 /* Returns 0 if exception not found and fixup otherwise.  */
-extern unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
+unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
 
-extern void __ret_efault(void);
+void __ret_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
@@ -152,7 +152,7 @@
        : "=&r" (ret) : "r" (x), "m" (*__m(addr)),			\
 	 "i" (-EFAULT))
 
-extern int __put_user_bad(void);
+int __put_user_bad(void);
 
 #define __get_user_check(x,addr,size,type) ({ \
 register int __gu_ret; \
@@ -244,9 +244,9 @@
 	".previous\n\t"							\
        : "=&r" (x) : "m" (*__m(addr)), "i" (retval))
 
-extern int __get_user_bad(void);
+int __get_user_bad(void);
 
-extern unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
+unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
 
 static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
 {
@@ -306,8 +306,8 @@
 		return n;
 }
 
-extern __must_check long strlen_user(const char __user *str);
-extern __must_check long strnlen_user(const char __user *str, long n);
+__must_check long strlen_user(const char __user *str);
+__must_check long strnlen_user(const char __user *str, long n);
 
 #endif  /* __ASSEMBLY__ */
 
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index ad7e178..c990a5e 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -76,8 +76,8 @@
         unsigned int insn, fixup;
 };
 
-extern void __ret_efault(void);
-extern void __retl_efault(void);
+void __ret_efault(void);
+void __retl_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
@@ -134,7 +134,7 @@
        : "=r" (ret) : "r" (x), "r" (__m(addr)),				\
 	 "i" (-EFAULT))
 
-extern int __put_user_bad(void);
+int __put_user_bad(void);
 
 #define __get_user_nocheck(data,addr,size,type) ({ \
 register int __gu_ret; \
@@ -204,13 +204,13 @@
 	".previous\n\t"							\
        : "=r" (x) : "r" (__m(addr)), "i" (retval))
 
-extern int __get_user_bad(void);
+int __get_user_bad(void);
 
-extern unsigned long __must_check ___copy_from_user(void *to,
-						    const void __user *from,
-						    unsigned long size);
-extern unsigned long copy_from_user_fixup(void *to, const void __user *from,
-					  unsigned long size);
+unsigned long __must_check ___copy_from_user(void *to,
+					     const void __user *from,
+					     unsigned long size);
+unsigned long copy_from_user_fixup(void *to, const void __user *from,
+				   unsigned long size);
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long size)
 {
@@ -223,11 +223,11 @@
 }
 #define __copy_from_user copy_from_user
 
-extern unsigned long __must_check ___copy_to_user(void __user *to,
-						  const void *from,
-						  unsigned long size);
-extern unsigned long copy_to_user_fixup(void __user *to, const void *from,
-					unsigned long size);
+unsigned long __must_check ___copy_to_user(void __user *to,
+					   const void *from,
+					   unsigned long size);
+unsigned long copy_to_user_fixup(void __user *to, const void *from,
+				 unsigned long size);
 static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long size)
 {
@@ -239,11 +239,11 @@
 }
 #define __copy_to_user copy_to_user
 
-extern unsigned long __must_check ___copy_in_user(void __user *to,
-						  const void __user *from,
-						  unsigned long size);
-extern unsigned long copy_in_user_fixup(void __user *to, void __user *from,
-					unsigned long size);
+unsigned long __must_check ___copy_in_user(void __user *to,
+					   const void __user *from,
+					   unsigned long size);
+unsigned long copy_in_user_fixup(void __user *to, void __user *from,
+				 unsigned long size);
 static inline unsigned long __must_check
 copy_in_user(void __user *to, void __user *from, unsigned long size)
 {
@@ -255,20 +255,20 @@
 }
 #define __copy_in_user copy_in_user
 
-extern unsigned long __must_check __clear_user(void __user *, unsigned long);
+unsigned long __must_check __clear_user(void __user *, unsigned long);
 
 #define clear_user __clear_user
 
-extern __must_check long strlen_user(const char __user *str);
-extern __must_check long strnlen_user(const char __user *str, long n);
+__must_check long strlen_user(const char __user *str);
+__must_check long strnlen_user(const char __user *str, long n);
 
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
 struct pt_regs;
-extern unsigned long compute_effective_address(struct pt_regs *,
-					       unsigned int insn,
-					       unsigned int rd);
+unsigned long compute_effective_address(struct pt_regs *,
+					unsigned int insn,
+					unsigned int rd);
 
 #endif  /* __ASSEMBLY__ */
 
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 432afa8..e0f6c39 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -372,14 +372,14 @@
 		       vio->vdev->channel_id, ## a); \
 } while (0)
 
-extern int __vio_register_driver(struct vio_driver *drv, struct module *owner,
+int __vio_register_driver(struct vio_driver *drv, struct module *owner,
 				 const char *mod_name);
 /*
  * vio_register_driver must be a macro so that KBUILD_MODNAME can be expanded
  */
 #define vio_register_driver(driver)		\
 	__vio_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
-extern void vio_unregister_driver(struct vio_driver *drv);
+void vio_unregister_driver(struct vio_driver *drv);
 
 static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
 {
@@ -391,21 +391,21 @@
 	return container_of(dev, struct vio_dev, dev);
 }
 
-extern int vio_ldc_send(struct vio_driver_state *vio, void *data, int len);
-extern void vio_link_state_change(struct vio_driver_state *vio, int event);
-extern void vio_conn_reset(struct vio_driver_state *vio);
-extern int vio_control_pkt_engine(struct vio_driver_state *vio, void *pkt);
-extern int vio_validate_sid(struct vio_driver_state *vio,
-			    struct vio_msg_tag *tp);
-extern u32 vio_send_sid(struct vio_driver_state *vio);
-extern int vio_ldc_alloc(struct vio_driver_state *vio,
-			 struct ldc_channel_config *base_cfg, void *event_arg);
-extern void vio_ldc_free(struct vio_driver_state *vio);
-extern int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
-			   u8 dev_class, struct vio_version *ver_table,
-			   int ver_table_size, struct vio_driver_ops *ops,
-			   char *name);
+int vio_ldc_send(struct vio_driver_state *vio, void *data, int len);
+void vio_link_state_change(struct vio_driver_state *vio, int event);
+void vio_conn_reset(struct vio_driver_state *vio);
+int vio_control_pkt_engine(struct vio_driver_state *vio, void *pkt);
+int vio_validate_sid(struct vio_driver_state *vio,
+		     struct vio_msg_tag *tp);
+u32 vio_send_sid(struct vio_driver_state *vio);
+int vio_ldc_alloc(struct vio_driver_state *vio,
+		  struct ldc_channel_config *base_cfg, void *event_arg);
+void vio_ldc_free(struct vio_driver_state *vio);
+int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
+		    u8 dev_class, struct vio_version *ver_table,
+		    int ver_table_size, struct vio_driver_ops *ops,
+		    char *name);
 
-extern void vio_port_up(struct vio_driver_state *vio);
+void vio_port_up(struct vio_driver_state *vio);
 
 #endif /* _SPARC64_VIO_H */
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 39ca301..b266737 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -57,7 +57,8 @@
 "		" : : "i" (FPRS_FEF|FPRS_DU) :
 		"o5", "g1", "g2", "g3", "g7", "cc");
 }
-extern int vis_emul(struct pt_regs *, unsigned int);
+
+int vis_emul(struct pt_regs *, unsigned int);
 #endif
 
 #endif /* _SPARC64_ASI_H */
diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h
index ee8edc6..50c8828 100644
--- a/arch/sparc/include/asm/xor_64.h
+++ b/arch/sparc/include/asm/xor_64.h
@@ -20,13 +20,13 @@
 
 #include <asm/spitfire.h>
 
-extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
-		      unsigned long *);
-extern void xor_vis_4(unsigned long, unsigned long *, unsigned long *,
-		      unsigned long *, unsigned long *);
-extern void xor_vis_5(unsigned long, unsigned long *, unsigned long *,
-		      unsigned long *, unsigned long *, unsigned long *);
+void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
+void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
+	       unsigned long *);
+void xor_vis_4(unsigned long, unsigned long *, unsigned long *,
+	       unsigned long *, unsigned long *);
+void xor_vis_5(unsigned long, unsigned long *, unsigned long *,
+	       unsigned long *, unsigned long *, unsigned long *);
 
 /* XXX Ugh, write cheetah versions... -DaveM */
 
@@ -38,13 +38,13 @@
         .do_5	= xor_vis_5,
 };
 
-extern void xor_niagara_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_niagara_3(unsigned long, unsigned long *, unsigned long *,
-			  unsigned long *);
-extern void xor_niagara_4(unsigned long, unsigned long *, unsigned long *,
-			  unsigned long *, unsigned long *);
-extern void xor_niagara_5(unsigned long, unsigned long *, unsigned long *,
-			  unsigned long *, unsigned long *, unsigned long *);
+void xor_niagara_2(unsigned long, unsigned long *, unsigned long *);
+void xor_niagara_3(unsigned long, unsigned long *, unsigned long *,
+		   unsigned long *);
+void xor_niagara_4(unsigned long, unsigned long *, unsigned long *,
+		   unsigned long *, unsigned long *);
+void xor_niagara_5(unsigned long, unsigned long *, unsigned long *,
+		   unsigned long *, unsigned long *, unsigned long *);
 
 static struct xor_block_template xor_block_niagara = {
         .name	= "Niagara",
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index d15cc17..7cf9c6e 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -42,7 +42,6 @@
 obj-$(CONFIG_SPARC32)   += windows.o
 obj-y                   += cpu.o
 obj-$(CONFIG_SPARC32)   += devices.o
-obj-$(CONFIG_SPARC32)   += tadpole.o
 obj-y                   += ptrace_$(BITS).o
 obj-y                   += unaligned_$(BITS).o
 obj-y                   += una_asm_$(BITS).o
diff --git a/arch/sparc/kernel/audit.c b/arch/sparc/kernel/audit.c
index 8fff0ac..24361b4 100644
--- a/arch/sparc/kernel/audit.c
+++ b/arch/sparc/kernel/audit.c
@@ -3,6 +3,8 @@
 #include <linux/audit.h>
 #include <asm/unistd.h>
 
+#include "kernel.h"
+
 static unsigned dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
 ~0U
@@ -40,7 +42,6 @@
 int audit_classify_syscall(int abi, unsigned syscall)
 {
 #ifdef CONFIG_COMPAT
-	extern int sparc32_classify_syscall(unsigned);
 	if (abi == AUDIT_ARCH_SPARC)
 		return sparc32_classify_syscall(syscall);
 #endif
@@ -61,11 +62,6 @@
 static int __init audit_classes_init(void)
 {
 #ifdef CONFIG_COMPAT
-	extern __u32 sparc32_dir_class[];
-	extern __u32 sparc32_write_class[];
-	extern __u32 sparc32_read_class[];
-	extern __u32 sparc32_chattr_class[];
-	extern __u32 sparc32_signal_class[];
 	audit_register_class(AUDIT_CLASS_WRITE_32, sparc32_write_class);
 	audit_register_class(AUDIT_CLASS_READ_32, sparc32_read_class);
 	audit_register_class(AUDIT_CLASS_DIR_WRITE_32, sparc32_dir_class);
diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c
index e20cc55..ae88c22 100644
--- a/arch/sparc/kernel/auxio_32.c
+++ b/arch/sparc/kernel/auxio_32.c
@@ -9,12 +9,15 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/export.h>
+
 #include <asm/oplib.h>
 #include <asm/io.h>
 #include <asm/auxio.h>
 #include <asm/string.h>		/* memset(), Linux has no bzero() */
 #include <asm/cpu_type.h>
 
+#include "kernel.h"
+
 /* Probe and map in the Auxiliary I/O register */
 
 /* auxio_register is not static because it is referenced 
@@ -103,7 +106,7 @@
 
 /* sun4m power control register (AUXIO2) */
 
-volatile unsigned char * auxio_power_register = NULL;
+volatile u8 __iomem *auxio_power_register = NULL;
 
 void __init auxio_power_probe(void)
 {
@@ -127,8 +130,8 @@
 	r.flags = regs.which_io & 0xF;
 	r.start = regs.phys_addr;
 	r.end = regs.phys_addr + regs.reg_size - 1;
-	auxio_power_register = (unsigned char *) of_ioremap(&r, 0,
-	    regs.reg_size, "auxpower");
+	auxio_power_register =
+		(u8 __iomem *)of_ioremap(&r, 0, regs.reg_size, "auxpower");
 
 	/* Display a quick message on the console. */
 	if (auxio_power_register)
diff --git a/arch/sparc/kernel/btext.c b/arch/sparc/kernel/btext.c
index 57073e5..987f7ec 100644
--- a/arch/sparc/kernel/btext.c
+++ b/arch/sparc/kernel/btext.c
@@ -137,7 +137,7 @@
 }
 #endif /* ndef NO_SCROLL */
 
-void btext_drawchar(char c)
+static void btext_drawchar(char c)
 {
 	int cline = 0;
 #ifdef NO_SCROLL
diff --git a/arch/sparc/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c
index d865575..7062263 100644
--- a/arch/sparc/kernel/compat_audit.c
+++ b/arch/sparc/kernel/compat_audit.c
@@ -1,5 +1,6 @@
 #define __32bit_syscall_numbers__
 #include <asm/unistd.h>
+#include "kernel.h"
 
 unsigned sparc32_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 5c51258..82a3a71 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -22,6 +22,7 @@
 #include <asm/cpudata.h>
 
 #include "kernel.h"
+#include "entry.h"
 
 DEFINE_PER_CPU(cpuinfo_sparc, __cpu_data) = { 0 };
 EXPORT_PER_CPU_SYMBOL(__cpu_data);
diff --git a/arch/sparc/kernel/cpumap.h b/arch/sparc/kernel/cpumap.h
index e639880..9dac398 100644
--- a/arch/sparc/kernel/cpumap.h
+++ b/arch/sparc/kernel/cpumap.h
@@ -2,8 +2,8 @@
 #define _CPUMAP_H
 
 #ifdef CONFIG_SMP
-extern void cpu_map_rebuild(void);
-extern int  map_to_cpu(unsigned int index);
+void cpu_map_rebuild(void);
+int map_to_cpu(unsigned int index);
 #define cpu_map_init() cpu_map_rebuild()
 #else
 #define cpu_map_init() do {} while (0)
diff --git a/arch/sparc/kernel/devices.c b/arch/sparc/kernel/devices.c
index 3d465e8..8d5d09f 100644
--- a/arch/sparc/kernel/devices.c
+++ b/arch/sparc/kernel/devices.c
@@ -19,8 +19,9 @@
 #include <asm/smp.h>
 #include <asm/cpudata.h>
 #include <asm/cpu_type.h>
+#include <asm/setup.h>
 
-extern void clock_stop_probe(void); /* tadpole.c */
+#include "kernel.h"
 
 static char *cpu_mid_prop(void)
 {
@@ -131,11 +132,6 @@
 	}
 #endif /* !CONFIG_SMP */
 
-	{
-		extern void auxio_probe(void);
-		extern void auxio_power_probe(void);
-		auxio_probe();
-		auxio_power_probe();
-	}
-	clock_stop_probe();
+	auxio_probe();
+	auxio_power_probe();
 }
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 140966f..ebaba61 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -6,40 +6,39 @@
 #include <linux/init.h>
 
 /* irq */
-extern void handler_irq(int irq, struct pt_regs *regs);
+void handler_irq(int irq, struct pt_regs *regs);
 
 #ifdef CONFIG_SPARC32
 /* traps */
-extern void do_hw_interrupt(struct pt_regs *regs, unsigned long type);
-extern void do_illegal_instruction(struct pt_regs *regs, unsigned long pc,
-                                   unsigned long npc, unsigned long psr);
+void do_hw_interrupt(struct pt_regs *regs, unsigned long type);
+void do_illegal_instruction(struct pt_regs *regs, unsigned long pc,
+                            unsigned long npc, unsigned long psr);
 
-extern void do_priv_instruction(struct pt_regs *regs, unsigned long pc,
-                                unsigned long npc, unsigned long psr);
-extern void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc,
-                                   unsigned long npc,
-                                   unsigned long psr);
-extern void do_fpd_trap(struct pt_regs *regs, unsigned long pc,
+void do_priv_instruction(struct pt_regs *regs, unsigned long pc,
+                         unsigned long npc, unsigned long psr);
+void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc,
+                            unsigned long npc, unsigned long psr);
+void do_fpd_trap(struct pt_regs *regs, unsigned long pc,
+                 unsigned long npc, unsigned long psr);
+void do_fpe_trap(struct pt_regs *regs, unsigned long pc,
+                 unsigned long npc, unsigned long psr);
+void handle_tag_overflow(struct pt_regs *regs, unsigned long pc,
+                         unsigned long npc, unsigned long psr);
+void handle_watchpoint(struct pt_regs *regs, unsigned long pc,
+                       unsigned long npc, unsigned long psr);
+void handle_reg_access(struct pt_regs *regs, unsigned long pc,
+                       unsigned long npc, unsigned long psr);
+void handle_cp_disabled(struct pt_regs *regs, unsigned long pc,
                         unsigned long npc, unsigned long psr);
-extern void do_fpe_trap(struct pt_regs *regs, unsigned long pc,
-                        unsigned long npc, unsigned long psr);
-extern void handle_tag_overflow(struct pt_regs *regs, unsigned long pc,
-                                unsigned long npc, unsigned long psr);
-extern void handle_watchpoint(struct pt_regs *regs, unsigned long pc,
-                              unsigned long npc, unsigned long psr);
-extern void handle_reg_access(struct pt_regs *regs, unsigned long pc,
-                              unsigned long npc, unsigned long psr);
-extern void handle_cp_disabled(struct pt_regs *regs, unsigned long pc,
-                               unsigned long npc, unsigned long psr);
-extern void handle_cp_exception(struct pt_regs *regs, unsigned long pc,
-                                unsigned long npc, unsigned long psr);
+void handle_cp_exception(struct pt_regs *regs, unsigned long pc,
+                         unsigned long npc, unsigned long psr);
 
 
 
 /* entry.S */
-extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
-                   void *fpqueue, unsigned long *fpqdepth);
-extern void fpload(unsigned long *fpregs, unsigned long *fsr);
+void fpsave(unsigned long *fpregs, unsigned long *fsr,
+            void *fpqueue, unsigned long *fpqdepth);
+void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
 
@@ -66,123 +65,123 @@
 extern struct pause_patch_entry __pause_3insn_patch,
 	__pause_3insn_patch_end;
 
-extern void __init per_cpu_patch(void);
-extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
-				    struct sun4v_1insn_patch_entry *);
-extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
-				    struct sun4v_2insn_patch_entry *);
-extern void __init sun4v_patch(void);
-extern void __init boot_cpu_id_too_large(int cpu);
+void __init per_cpu_patch(void);
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+			     struct sun4v_1insn_patch_entry *);
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+			     struct sun4v_2insn_patch_entry *);
+void __init sun4v_patch(void);
+void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
-extern asmlinkage void sparc_breakpoint(struct pt_regs *regs);
-extern void timer_interrupt(int irq, struct pt_regs *regs);
+asmlinkage void sparc_breakpoint(struct pt_regs *regs);
+void timer_interrupt(int irq, struct pt_regs *regs);
 
-extern void do_notify_resume(struct pt_regs *regs,
-			     unsigned long orig_i0,
-			     unsigned long thread_info_flags);
+void do_notify_resume(struct pt_regs *regs,
+		      unsigned long orig_i0,
+		      unsigned long thread_info_flags);
 
-extern asmlinkage int syscall_trace_enter(struct pt_regs *regs);
-extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
+asmlinkage int syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void syscall_trace_leave(struct pt_regs *regs);
 
-extern void bad_trap_tl1(struct pt_regs *regs, long lvl);
+void bad_trap_tl1(struct pt_regs *regs, long lvl);
 
-extern void do_fpieee(struct pt_regs *regs);
-extern void do_fpother(struct pt_regs *regs);
-extern void do_tof(struct pt_regs *regs);
-extern void do_div0(struct pt_regs *regs);
-extern void do_illegal_instruction(struct pt_regs *regs);
-extern void mem_address_unaligned(struct pt_regs *regs,
-				  unsigned long sfar,
-				  unsigned long sfsr);
-extern void sun4v_do_mna(struct pt_regs *regs,
-			 unsigned long addr,
-			 unsigned long type_ctx);
-extern void do_privop(struct pt_regs *regs);
-extern void do_privact(struct pt_regs *regs);
-extern void do_cee(struct pt_regs *regs);
-extern void do_cee_tl1(struct pt_regs *regs);
-extern void do_dae_tl1(struct pt_regs *regs);
-extern void do_iae_tl1(struct pt_regs *regs);
-extern void do_div0_tl1(struct pt_regs *regs);
-extern void do_fpdis_tl1(struct pt_regs *regs);
-extern void do_fpieee_tl1(struct pt_regs *regs);
-extern void do_fpother_tl1(struct pt_regs *regs);
-extern void do_ill_tl1(struct pt_regs *regs);
-extern void do_irq_tl1(struct pt_regs *regs);
-extern void do_lddfmna_tl1(struct pt_regs *regs);
-extern void do_stdfmna_tl1(struct pt_regs *regs);
-extern void do_paw(struct pt_regs *regs);
-extern void do_paw_tl1(struct pt_regs *regs);
-extern void do_vaw(struct pt_regs *regs);
-extern void do_vaw_tl1(struct pt_regs *regs);
-extern void do_tof_tl1(struct pt_regs *regs);
-extern void do_getpsr(struct pt_regs *regs);
+void do_fpieee(struct pt_regs *regs);
+void do_fpother(struct pt_regs *regs);
+void do_tof(struct pt_regs *regs);
+void do_div0(struct pt_regs *regs);
+void do_illegal_instruction(struct pt_regs *regs);
+void mem_address_unaligned(struct pt_regs *regs,
+			   unsigned long sfar,
+			   unsigned long sfsr);
+void sun4v_do_mna(struct pt_regs *regs,
+		  unsigned long addr,
+		  unsigned long type_ctx);
+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);
+void do_irq_tl1(struct pt_regs *regs);
+void do_lddfmna_tl1(struct pt_regs *regs);
+void do_stdfmna_tl1(struct pt_regs *regs);
+void do_paw(struct pt_regs *regs);
+void do_paw_tl1(struct pt_regs *regs);
+void do_vaw(struct pt_regs *regs);
+void do_vaw_tl1(struct pt_regs *regs);
+void do_tof_tl1(struct pt_regs *regs);
+void do_getpsr(struct pt_regs *regs);
 
-extern void spitfire_insn_access_exception(struct pt_regs *regs,
-					   unsigned long sfsr,
-					   unsigned long sfar);
-extern void spitfire_insn_access_exception_tl1(struct pt_regs *regs,
-					       unsigned long sfsr,
-					       unsigned long sfar);
-extern void spitfire_data_access_exception(struct pt_regs *regs,
-					   unsigned long sfsr,
-					   unsigned long sfar);
-extern void spitfire_data_access_exception_tl1(struct pt_regs *regs,
-					       unsigned long sfsr,
-					       unsigned long sfar);
-extern void spitfire_access_error(struct pt_regs *regs,
-				  unsigned long status_encoded,
-				  unsigned long afar);
+void spitfire_insn_access_exception(struct pt_regs *regs,
+				    unsigned long sfsr,
+				    unsigned long sfar);
+void spitfire_insn_access_exception_tl1(struct pt_regs *regs,
+				        unsigned long sfsr,
+				        unsigned long sfar);
+void spitfire_data_access_exception(struct pt_regs *regs,
+				    unsigned long sfsr,
+				    unsigned long sfar);
+void spitfire_data_access_exception_tl1(struct pt_regs *regs,
+				        unsigned long sfsr,
+				        unsigned long sfar);
+void spitfire_access_error(struct pt_regs *regs,
+			   unsigned long status_encoded,
+			   unsigned long afar);
 
-extern void cheetah_fecc_handler(struct pt_regs *regs,
-				 unsigned long afsr,
-				 unsigned long afar);
-extern void cheetah_cee_handler(struct pt_regs *regs,
-				unsigned long afsr,
-				unsigned long afar);
-extern void cheetah_deferred_handler(struct pt_regs *regs,
-				     unsigned long afsr,
-				     unsigned long afar);
-extern void cheetah_plus_parity_error(int type, struct pt_regs *regs);
+void cheetah_fecc_handler(struct pt_regs *regs,
+			  unsigned long afsr,
+			  unsigned long afar);
+void cheetah_cee_handler(struct pt_regs *regs,
+			 unsigned long afsr,
+			 unsigned long afar);
+void cheetah_deferred_handler(struct pt_regs *regs,
+			      unsigned long afsr,
+			      unsigned long afar);
+void cheetah_plus_parity_error(int type, struct pt_regs *regs);
 
-extern void sun4v_insn_access_exception(struct pt_regs *regs,
-					unsigned long addr,
-					unsigned long type_ctx);
-extern void sun4v_insn_access_exception_tl1(struct pt_regs *regs,
-					    unsigned long addr,
-					    unsigned long type_ctx);
-extern void sun4v_data_access_exception(struct pt_regs *regs,
-					unsigned long addr,
-					unsigned long type_ctx);
-extern void sun4v_data_access_exception_tl1(struct pt_regs *regs,
-					    unsigned long addr,
-					    unsigned long type_ctx);
-extern void sun4v_resum_error(struct pt_regs *regs,
-			      unsigned long offset);
-extern void sun4v_resum_overflow(struct pt_regs *regs);
-extern void sun4v_nonresum_error(struct pt_regs *regs,
-				 unsigned long offset);
-extern void sun4v_nonresum_overflow(struct pt_regs *regs);
+void sun4v_insn_access_exception(struct pt_regs *regs,
+				 unsigned long addr,
+				 unsigned long type_ctx);
+void sun4v_insn_access_exception_tl1(struct pt_regs *regs,
+				     unsigned long addr,
+				     unsigned long type_ctx);
+void sun4v_data_access_exception(struct pt_regs *regs,
+				 unsigned long addr,
+				 unsigned long type_ctx);
+void sun4v_data_access_exception_tl1(struct pt_regs *regs,
+				     unsigned long addr,
+				     unsigned long type_ctx);
+void sun4v_resum_error(struct pt_regs *regs,
+		       unsigned long offset);
+void sun4v_resum_overflow(struct pt_regs *regs);
+void sun4v_nonresum_error(struct pt_regs *regs,
+			  unsigned long offset);
+void sun4v_nonresum_overflow(struct pt_regs *regs);
 
 extern unsigned long sun4v_err_itlb_vaddr;
 extern unsigned long sun4v_err_itlb_ctx;
 extern unsigned long sun4v_err_itlb_pte;
 extern unsigned long sun4v_err_itlb_error;
 
-extern void sun4v_itlb_error_report(struct pt_regs *regs, int tl);
+void sun4v_itlb_error_report(struct pt_regs *regs, int tl);
 
 extern unsigned long sun4v_err_dtlb_vaddr;
 extern unsigned long sun4v_err_dtlb_ctx;
 extern unsigned long sun4v_err_dtlb_pte;
 extern unsigned long sun4v_err_dtlb_error;
 
-extern void sun4v_dtlb_error_report(struct pt_regs *regs, int tl);
-extern void hypervisor_tlbop_error(unsigned long err,
-				   unsigned long op);
-extern void hypervisor_tlbop_error_xcall(unsigned long err,
-					 unsigned long op);
+void sun4v_dtlb_error_report(struct pt_regs *regs, int tl);
+void hypervisor_tlbop_error(unsigned long err,
+			    unsigned long op);
+void hypervisor_tlbop_error_xcall(unsigned long err,
+				  unsigned long op);
 
 /* WARNING: The error trap handlers in assembly know the precise
  *	    layout of the following structure.
@@ -248,8 +247,8 @@
 extern struct ino_bucket *ivector_table;
 extern unsigned long ivector_table_pa;
 
-extern void init_irqwork_curcpu(void);
-extern void sun4v_register_mondo_queues(int this_cpu);
+void init_irqwork_curcpu(void);
+void sun4v_register_mondo_queues(int this_cpu);
 
 #endif /* CONFIG_SPARC32 */
 #endif /* _ENTRY_H */
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 76663b0..bfa4d0c 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -21,6 +21,7 @@
 #include <asm/iommu.h>
 
 #include "iommu_common.h"
+#include "kernel.h"
 
 #define STC_CTXMATCH_ADDR(STC, CTX)	\
 	((STC)->strbuf_ctxmatch_base + ((CTX) << 3))
@@ -840,8 +841,6 @@
 struct dma_map_ops *dma_ops = &sun4u_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-extern int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
-
 int dma_supported(struct device *dev, u64 device_mask)
 {
 	struct iommu *iommu = dev->archdata.iommu;
diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h
index 591f587..1ec0de4 100644
--- a/arch/sparc/kernel/iommu_common.h
+++ b/arch/sparc/kernel/iommu_common.h
@@ -48,12 +48,12 @@
 	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 }
 
-extern unsigned long iommu_range_alloc(struct device *dev,
-				       struct iommu *iommu,
-				       unsigned long npages,
-				       unsigned long *handle);
-extern void iommu_range_free(struct iommu *iommu,
-			     dma_addr_t dma_addr,
-			     unsigned long npages);
+unsigned long iommu_range_alloc(struct device *dev,
+				struct iommu *iommu,
+				unsigned long npages,
+				unsigned long *handle);
+void iommu_range_free(struct iommu *iommu,
+		      dma_addr_t dma_addr,
+		      unsigned long npages);
 
 #endif /* _IOMMU_COMMON_H */
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index e7e215d..7f08ec8 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -186,7 +186,7 @@
 
 	if (name == NULL) name = "???";
 
-	if ((xres = xres_alloc()) != 0) {
+	if ((xres = xres_alloc()) != NULL) {
 		tack = xres->xname;
 		res = &xres->xres;
 	} else {
@@ -400,7 +400,7 @@
 	BUG();
 }
 
-struct dma_map_ops sbus_dma_ops = {
+static struct dma_map_ops sbus_dma_ops = {
 	.alloc			= sbus_alloc_coherent,
 	.free			= sbus_free_coherent,
 	.map_page		= sbus_map_page,
@@ -681,7 +681,7 @@
 	const char *nm;
 
 	for (r = root->child; r != NULL; r = r->sibling) {
-		if ((nm = r->name) == 0) nm = "???";
+		if ((nm = r->name) == NULL) nm = "???";
 		seq_printf(m, "%016llx-%016llx: %s\n",
 				(unsigned long long)r->start,
 				(unsigned long long)r->end, nm);
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
index b66b6aa..70a0b8d 100644
--- a/arch/sparc/kernel/irq.h
+++ b/arch/sparc/kernel/irq.h
@@ -82,11 +82,20 @@
 
 unsigned long leon_get_irqmask(unsigned int irq);
 
+/* irq_32.c */
+void sparc_floppy_irq(int irq, void *dev_id, struct pt_regs *regs);
+
+/* sun4m_irq.c */
+void sun4m_nmi(struct pt_regs *regs);
+
+/* sun4d_irq.c */
+void sun4d_handler_irq(unsigned int pil, struct pt_regs *regs);
+
 #ifdef CONFIG_SMP
 
 /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */
 #define SUN4D_IPI_IRQ 13
 
-extern void sun4d_ipi_interrupt(void);
+void sun4d_ipi_interrupt(void);
 
 #endif
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index c145f6f..a979e99 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -17,6 +17,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpudata.h>
+#include <asm/setup.h>
 #include <asm/pcic.h>
 #include <asm/leon.h>
 
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index a702d9a..e7f652b 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -2,6 +2,7 @@
 #define __SPARC_KERNEL_H
 
 #include <linux/interrupt.h>
+#include <linux/ftrace.h>
 
 #include <asm/traps.h>
 #include <asm/head.h>
@@ -15,62 +16,111 @@
 #ifdef CONFIG_SPARC64
 /* setup_64.c */
 struct seq_file;
-extern void cpucap_info(struct seq_file *);
+void cpucap_info(struct seq_file *);
 
-static inline unsigned long kimage_addr_to_ra(const char *p)
+static inline unsigned long kimage_addr_to_ra(const void *p)
 {
 	unsigned long val = (unsigned long) p;
 
 	return kern_base + (val - KERNBASE);
 }
+
+/* sys_sparc_64.c */
+asmlinkage long sys_kern_features(void);
+
+/* unaligned_64.c */
+asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn);
+int handle_popc(u32 insn, struct pt_regs *regs);
+void handle_lddfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr);
+void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr);
+
+/* smp_64.c */
+void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
+void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
+void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
+void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
+void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
+
+/* kgdb_64.c */
+void __irq_entry smp_kgdb_capture_client(int irq, struct pt_regs *regs);
+
+/* pci.c */
+int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
+
+/* signal32.c */
+void do_sigreturn32(struct pt_regs *regs);
+asmlinkage void do_rt_sigreturn32(struct pt_regs *regs);
+void do_signal32(struct pt_regs * regs);
+asmlinkage int do_sys32_sigstack(u32 u_ssptr, u32 u_ossptr, unsigned long sp);
+
+/* compat_audit.c */
+extern unsigned sparc32_dir_class[];
+extern unsigned sparc32_chattr_class[];
+extern unsigned sparc32_write_class[];
+extern unsigned sparc32_read_class[];
+extern unsigned sparc32_signal_class[];
+int sparc32_classify_syscall(unsigned syscall);
 #endif
 
 #ifdef CONFIG_SPARC32
 /* setup_32.c */
+struct linux_romvec;
 void sparc32_start_kernel(struct linux_romvec *rp);
 
 /* cpu.c */
-extern void cpu_probe(void);
+void cpu_probe(void);
 
 /* traps_32.c */
-extern void handle_hw_divzero(struct pt_regs *regs, unsigned long pc,
-                              unsigned long npc, unsigned long psr);
+void handle_hw_divzero(struct pt_regs *regs, unsigned long pc,
+                       unsigned long npc, unsigned long psr);
 /* irq_32.c */
 extern struct irqaction static_irqaction[];
 extern int static_irq_count;
 extern spinlock_t irq_action_lock;
 
-extern void unexpected_irq(int irq, void *dev_id, struct pt_regs * regs);
-extern void init_IRQ(void);
+void unexpected_irq(int irq, void *dev_id, struct pt_regs * regs);
+void init_IRQ(void);
 
 /* sun4m_irq.c */
-extern void sun4m_init_IRQ(void);
-extern void sun4m_unmask_profile_irq(void);
-extern void sun4m_clear_profile_irq(int cpu);
+void sun4m_init_IRQ(void);
+void sun4m_unmask_profile_irq(void);
+void sun4m_clear_profile_irq(int cpu);
 
 /* sun4m_smp.c */
 void sun4m_cpu_pre_starting(void *arg);
 void sun4m_cpu_pre_online(void *arg);
+void __init smp4m_boot_cpus(void);
+int smp4m_boot_one_cpu(int i, struct task_struct *idle);
+void __init smp4m_smp_done(void);
+void smp4m_cross_call_irq(void);
+void smp4m_percpu_timer_interrupt(struct pt_regs *regs);
 
 /* sun4d_irq.c */
 extern spinlock_t sun4d_imsk_lock;
 
-extern void sun4d_init_IRQ(void);
-extern int sun4d_request_irq(unsigned int irq,
-                             irq_handler_t handler,
-                             unsigned long irqflags,
-                             const char *devname, void *dev_id);
-extern int show_sun4d_interrupts(struct seq_file *, void *);
-extern void sun4d_distribute_irqs(void);
-extern void sun4d_free_irq(unsigned int irq, void *dev_id);
+void sun4d_init_IRQ(void);
+int sun4d_request_irq(unsigned int irq,
+                      irq_handler_t handler,
+                      unsigned long irqflags,
+                      const char *devname, void *dev_id);
+int show_sun4d_interrupts(struct seq_file *, void *);
+void sun4d_distribute_irqs(void);
+void sun4d_free_irq(unsigned int irq, void *dev_id);
 
 /* sun4d_smp.c */
 void sun4d_cpu_pre_starting(void *arg);
 void sun4d_cpu_pre_online(void *arg);
+void __init smp4d_boot_cpus(void);
+int smp4d_boot_one_cpu(int i, struct task_struct *idle);
+void __init smp4d_smp_done(void);
+void smp4d_cross_call_irq(void);
+void smp4d_percpu_timer_interrupt(struct pt_regs *regs);
 
 /* leon_smp.c */
 void leon_cpu_pre_starting(void *arg);
 void leon_cpu_pre_online(void *arg);
+void leonsmp_ipi_interrupt(void);
+void leon_cross_call_irq(void);
 
 /* head_32.S */
 extern unsigned int t_nmi[];
@@ -89,12 +139,48 @@
 extern unsigned int smp4d_ticker[];
 extern unsigned int patchme_maybe_smp_msg[];
 
-extern void floppy_hardint(void);
+void floppy_hardint(void);
 
 /* trampoline_32.S */
 extern unsigned long sun4m_cpu_startup;
 extern unsigned long sun4d_cpu_startup;
 
+/* process_32.c */
+asmlinkage int sparc_do_fork(unsigned long clone_flags,
+                             unsigned long stack_start,
+                             struct pt_regs *regs,
+                             unsigned long stack_size);
+
+/* signal_32.c */
+asmlinkage void do_sigreturn(struct pt_regs *regs);
+asmlinkage void do_rt_sigreturn(struct pt_regs *regs);
+void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
+                      unsigned long thread_info_flags);
+asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,
+                               struct sigstack __user *ossptr,
+                               unsigned long sp);
+
+/* ptrace_32.c */
+asmlinkage int syscall_trace(struct pt_regs *regs, int syscall_exit_p);
+
+/* unaligned_32.c */
+asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn);
+asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn);
+
+/* windows.c */
+void try_to_clear_window_buffer(struct pt_regs *regs, int who);
+
+/* auxio_32.c */
+void __init auxio_probe(void);
+void __init auxio_power_probe(void);
+
+/* pcic.c */
+extern void __iomem *pcic_regs;
+void pcic_nmi(unsigned int pend, struct pt_regs *regs);
+
+/* time_32.c */
+void __init time_init(void);
+
 #else /* CONFIG_SPARC32 */
 #endif /* CONFIG_SPARC32 */
 #endif /* !(__SPARC_KERNEL_H) */
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index b45fe3f..cbf21d0 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -13,6 +13,8 @@
 #include <asm/ptrace.h>
 #include <asm/irq.h>
 
+#include "kernel.h"
+
 void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
 	struct reg_window *win;
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 1b09735..98d7128 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -512,7 +512,8 @@
 /*
  * Called when the probe at kretprobe trampoline is hit
  */
-int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+static int __kprobes trampoline_probe_handler(struct kprobe *p,
+					      struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
@@ -576,7 +577,7 @@
 	return 1;
 }
 
-void kretprobe_trampoline_holder(void)
+static void __used kretprobe_trampoline_holder(void)
 {
 	asm volatile(".global kretprobe_trampoline\n"
 		     "kretprobe_trampoline:\n"
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index b7c6897..683c4af 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -32,12 +32,12 @@
 
 int leondebug_irq_disable;
 int leon_debug_irqout;
-static int dummy_master_l10_counter;
+static volatile u32 dummy_master_l10_counter;
 unsigned long amba_system_id;
 static DEFINE_SPINLOCK(leon_irq_lock);
 
+static unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
 unsigned long leon3_gptimer_irq; /* interrupt controller irq number */
-unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
 unsigned int sparc_leon_eirq;
 #define LEON_IMASK(cpu) (&leon3_irqctrl_regs->mask[cpu])
 #define LEON_IACK (&leon3_irqctrl_regs->iclear)
@@ -65,7 +65,7 @@
 }
 
 /* The extended IRQ controller has been found, this function registers it */
-void leon_eirq_setup(unsigned int eirq)
+static void leon_eirq_setup(unsigned int eirq)
 {
 	unsigned long mask, oldmask;
 	unsigned int veirq;
@@ -270,7 +270,7 @@
 #ifdef CONFIG_SMP
 
 /* smp clockevent irq */
-irqreturn_t leon_percpu_timer_ce_interrupt(int irq, void *unused)
+static irqreturn_t leon_percpu_timer_ce_interrupt(int irq, void *unused)
 {
 	struct clock_event_device *ce;
 	int cpu = smp_processor_id();
@@ -313,7 +313,7 @@
 
 	leondebug_irq_disable = 0;
 	leon_debug_irqout = 0;
-	master_l10_counter = (unsigned int *)&dummy_master_l10_counter;
+	master_l10_counter = (u32 __iomem *)&dummy_master_l10_counter;
 	dummy_master_l10_counter = 0;
 
 	rootnp = of_find_node_by_path("/ambapp0");
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index e16c415..899b720 100644
--- a/arch/sparc/kernel/leon_pci.c
+++ b/arch/sparc/kernel/leon_pci.c
@@ -98,82 +98,3 @@
 {
 	return res->start;
 }
-
-/* in/out routines taken from pcic.c
- *
- * This probably belongs here rather than ioport.c because
- * we do not want this crud linked into SBus kernels.
- * Also, think for a moment about likes of floppy.c that
- * include architecture specific parts. They may want to redefine ins/outs.
- *
- * We do not use horrible macros here because we want to
- * advance pointer by sizeof(size).
- */
-void outsb(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		outb(*(const char *)src, addr);
-		src += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(outsb);
-
-void outsw(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		outw(*(const short *)src, addr);
-		src += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(outsw);
-
-void outsl(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		outl(*(const long *)src, addr);
-		src += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(outsl);
-
-void insb(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		*(unsigned char *)dst = inb(addr);
-		dst += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(insb);
-
-void insw(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		*(unsigned short *)dst = inw(addr);
-		dst += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(insw);
-
-void insl(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		/*
-		 * XXX I am sure we are in for an unaligned trap here.
-		 */
-		*(unsigned long *)dst = inl(addr);
-		dst += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(insl);
diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c
index 6df26e3..c8bf26e 100644
--- a/arch/sparc/kernel/leon_pci_grpci1.c
+++ b/arch/sparc/kernel/leon_pci_grpci1.c
@@ -80,7 +80,7 @@
 
 struct grpci1_priv {
 	struct leon_pci_info	info; /* must be on top of this structure */
-	struct grpci1_regs	*regs;		/* GRPCI register map */
+	struct grpci1_regs __iomem *regs;		/* GRPCI register map */
 	struct device		*dev;
 	int			pci_err_mask;	/* STATUS register error mask */
 	int			irq;		/* LEON irqctrl GRPCI IRQ */
@@ -101,7 +101,7 @@
 static int grpci1_cfg_w32(struct grpci1_priv *priv, unsigned int bus,
 				unsigned int devfn, int where, u32 val);
 
-int grpci1_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int grpci1_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct grpci1_priv *priv = dev->bus->sysdata;
 	int irq_group;
@@ -144,7 +144,7 @@
 		grpci1_cfg_w32(priv, TGT, 0, PCI_COMMAND, tmp);
 	} else {
 		/* Bus always little endian (unaffected by byte-swapping) */
-		*val = flip_dword(tmp);
+		*val = swab32(tmp);
 	}
 
 	return 0;
@@ -197,7 +197,7 @@
 
 	pci_conf = (unsigned int *) (priv->pci_conf |
 						(devfn << 8) | (where & 0xfc));
-	LEON3_BYPASS_STORE_PA(pci_conf, flip_dword(val));
+	LEON3_BYPASS_STORE_PA(pci_conf, swab32(val));
 
 	return 0;
 }
@@ -417,10 +417,10 @@
  *  BAR1: peripheral DMA to host's memory (size at least 256MByte)
  *  BAR2..BAR5: not implemented in hardware
  */
-void grpci1_hw_init(struct grpci1_priv *priv)
+static void grpci1_hw_init(struct grpci1_priv *priv)
 {
 	u32 ahbadr, bar_sz, data, pciadr;
-	struct grpci1_regs *regs = priv->regs;
+	struct grpci1_regs __iomem *regs = priv->regs;
 
 	/* set 1:1 mapping between AHB -> PCI memory space */
 	REGSTORE(regs->cfg_stat, priv->pci_area & 0xf0000000);
@@ -509,7 +509,7 @@
 
 static int grpci1_of_probe(struct platform_device *ofdev)
 {
-	struct grpci1_regs *regs;
+	struct grpci1_regs __iomem *regs;
 	struct grpci1_priv *priv;
 	int err, len;
 	const int *tmp;
@@ -690,7 +690,7 @@
 err2:
 	release_resource(&priv->info.mem_space);
 err1:
-	iounmap((void *)priv->pci_io_va);
+	iounmap((void __iomem *)priv->pci_io_va);
 	grpci1priv = NULL;
 	return err;
 }
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 24d6a44..e433a4d 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -191,7 +191,7 @@
 
 struct grpci2_priv {
 	struct leon_pci_info	info; /* must be on top of this structure */
-	struct grpci2_regs	*regs;
+	struct grpci2_regs __iomem *regs;
 	char			irq;
 	char			irq_mode; /* IRQ Mode from CAPSTS REG */
 	char			bt_enabled;
@@ -215,10 +215,10 @@
 	struct grpci2_barcfg	tgtbars[6];
 };
 
-DEFINE_SPINLOCK(grpci2_dev_lock);
-struct grpci2_priv *grpci2priv;
+static DEFINE_SPINLOCK(grpci2_dev_lock);
+static struct grpci2_priv *grpci2priv;
 
-int grpci2_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int grpci2_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct grpci2_priv *priv = dev->bus->sysdata;
 	int irq_group;
@@ -270,7 +270,7 @@
 		*val = 0xffffffff;
 	} else {
 		/* Bus always little endian (unaffected by byte-swapping) */
-		*val = flip_dword(tmp);
+		*val = swab32(tmp);
 	}
 
 	return 0;
@@ -328,7 +328,7 @@
 
 	pci_conf = (unsigned int *) (priv->pci_conf |
 						(devfn << 8) | (where & 0xfc));
-	LEON3_BYPASS_STORE_PA(pci_conf, flip_dword(val));
+	LEON3_BYPASS_STORE_PA(pci_conf, swab32(val));
 
 	/* Wait until GRPCI2 signals that CFG access is done, it should be
 	 * done instantaneously unless a DMA operation is ongoing...
@@ -561,10 +561,10 @@
 	return virq;
 }
 
-void grpci2_hw_init(struct grpci2_priv *priv)
+static void grpci2_hw_init(struct grpci2_priv *priv)
 {
 	u32 ahbadr, pciadr, bar_sz, capptr, io_map, data;
-	struct grpci2_regs *regs = priv->regs;
+	struct grpci2_regs __iomem *regs = priv->regs;
 	int i;
 	struct grpci2_barcfg *barcfg = priv->tgtbars;
 
@@ -655,7 +655,7 @@
 static irqreturn_t grpci2_err_interrupt(int irq, void *arg)
 {
 	struct grpci2_priv *priv = arg;
-	struct grpci2_regs *regs = priv->regs;
+	struct grpci2_regs __iomem *regs = priv->regs;
 	unsigned int status;
 
 	status = REGLOAD(regs->sts_cap);
@@ -682,7 +682,7 @@
 
 static int grpci2_of_probe(struct platform_device *ofdev)
 {
-	struct grpci2_regs *regs;
+	struct grpci2_regs __iomem *regs;
 	struct grpci2_priv *priv;
 	int err, i, len;
 	const int *tmp;
@@ -878,7 +878,7 @@
 	release_resource(&priv->info.mem_space);
 err3:
 	err = -ENOMEM;
-	iounmap((void *)priv->pci_io_va);
+	iounmap((void __iomem *)priv->pci_io_va);
 err2:
 	kfree(priv);
 err1:
diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c
index b0b3967..ddcf950 100644
--- a/arch/sparc/kernel/leon_pmc.c
+++ b/arch/sparc/kernel/leon_pmc.c
@@ -12,14 +12,14 @@
 #include <asm/processor.h>
 
 /* List of Systems that need fixup instructions around power-down instruction */
-unsigned int pmc_leon_fixup_ids[] = {
+static unsigned int pmc_leon_fixup_ids[] = {
 	AEROFLEX_UT699,
 	GAISLER_GR712RC,
 	LEON4_NEXTREME1,
 	0
 };
 
-int pmc_leon_need_fixup(void)
+static int pmc_leon_need_fixup(void)
 {
 	unsigned int systemid = amba_system_id >> 16;
 	unsigned int *id;
@@ -38,7 +38,7 @@
  * CPU idle callback function for systems that need some extra handling
  * See .../arch/sparc/kernel/process.c
  */
-void pmc_leon_idle_fixup(void)
+static void pmc_leon_idle_fixup(void)
 {
 	/* Prepare an address to a non-cachable region. APB is always
 	 * none-cachable. One instruction is executed after the Sleep
@@ -62,7 +62,7 @@
  * CPU idle callback function
  * See .../arch/sparc/kernel/process.c
  */
-void pmc_leon_idle(void)
+static void pmc_leon_idle(void)
 {
 	/* Interrupts need to be enabled to not hang the CPU */
 	local_irq_enable();
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 6edf955..018ef11 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -130,7 +130,7 @@
 	local_ops->tlb_all();
 }
 
-void leon_smp_setbroadcast(unsigned int mask)
+static void leon_smp_setbroadcast(unsigned int mask)
 {
 	int broadcast =
 	    ((LEON3_BYPASS_LOAD_PA(&(leon3_irqctrl_regs->mpstatus)) >>
@@ -148,13 +148,6 @@
 	LEON_BYPASS_STORE_PA(&(leon3_irqctrl_regs->mpbroadcast), mask);
 }
 
-unsigned int leon_smp_getbroadcast(void)
-{
-	unsigned int mask;
-	mask = LEON_BYPASS_LOAD_PA(&(leon3_irqctrl_regs->mpbroadcast));
-	return mask;
-}
-
 int leon_smp_nrcpus(void)
 {
 	int nrcpu =
@@ -266,10 +259,6 @@
 
 }
 
-void leon_irq_rotate(int cpu)
-{
-}
-
 struct leon_ipi_work {
 	int single;
 	int msk;
diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c
index 3241f56..de0ee39 100644
--- a/arch/sparc/kernel/of_device_common.c
+++ b/arch/sparc/kernel/of_device_common.c
@@ -5,8 +5,10 @@
 #include <linux/mod_devicetable.h>
 #include <linux/errno.h>
 #include <linux/irq.h>
-#include <linux/of_device.h>
 #include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
 
 #include "of_device_common.h"
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 857ad77..539babf 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -28,6 +28,7 @@
 #include <asm/apb.h>
 
 #include "pci_impl.h"
+#include "kernel.h"
 
 /* List of all PCI controllers found in the system. */
 struct pci_pbm_info *pci_pbm_root = NULL;
diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h
index 5f68853..75803c7 100644
--- a/arch/sparc/kernel/pci_impl.h
+++ b/arch/sparc/kernel/pci_impl.h
@@ -48,8 +48,8 @@
 			      unsigned long devino);
 };
 
-extern void sparc64_pbm_msi_init(struct pci_pbm_info *pbm,
-				 const struct sparc64_msiq_ops *ops);
+void sparc64_pbm_msi_init(struct pci_pbm_info *pbm,
+			  const struct sparc64_msiq_ops *ops);
 
 struct sparc64_msiq_cookie {
 	struct pci_pbm_info *pbm;
@@ -158,23 +158,23 @@
 extern int pci_num_pbms;
 
 /* PCI bus scanning and fixup support. */
-extern void pci_get_pbm_props(struct pci_pbm_info *pbm);
-extern struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm,
-					struct device *parent);
-extern void pci_determine_mem_io_space(struct pci_pbm_info *pbm);
+void pci_get_pbm_props(struct pci_pbm_info *pbm);
+struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm,
+				 struct device *parent);
+void pci_determine_mem_io_space(struct pci_pbm_info *pbm);
 
 /* Error reporting support. */
-extern void pci_scan_for_target_abort(struct pci_pbm_info *, struct pci_bus *);
-extern void pci_scan_for_master_abort(struct pci_pbm_info *, struct pci_bus *);
-extern void pci_scan_for_parity_error(struct pci_pbm_info *, struct pci_bus *);
+void pci_scan_for_target_abort(struct pci_pbm_info *, struct pci_bus *);
+void pci_scan_for_master_abort(struct pci_pbm_info *, struct pci_bus *);
+void pci_scan_for_parity_error(struct pci_pbm_info *, struct pci_bus *);
 
 /* Configuration space access. */
-extern void pci_config_read8(u8 *addr, u8 *ret);
-extern void pci_config_read16(u16 *addr, u16 *ret);
-extern void pci_config_read32(u32 *addr, u32 *ret);
-extern void pci_config_write8(u8 *addr, u8 val);
-extern void pci_config_write16(u16 *addr, u16 val);
-extern void pci_config_write32(u32 *addr, u32 val);
+void pci_config_read8(u8 *addr, u8 *ret);
+void pci_config_read16(u16 *addr, u16 *ret);
+void pci_config_read32(u32 *addr, u32 *ret);
+void pci_config_write8(u8 *addr, u8 val);
+void pci_config_write16(u16 *addr, u16 val);
+void pci_config_write32(u32 *addr, u32 val);
 
 extern struct pci_ops sun4u_pci_ops;
 extern struct pci_ops sun4v_pci_ops;
diff --git a/arch/sparc/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h
index 8e9fc3a..5642212 100644
--- a/arch/sparc/kernel/pci_sun4v.h
+++ b/arch/sparc/kernel/pci_sun4v.h
@@ -6,87 +6,87 @@
 #ifndef _PCI_SUN4V_H
 #define _PCI_SUN4V_H
 
-extern long pci_sun4v_iommu_map(unsigned long devhandle,
-				unsigned long tsbid,
-				unsigned long num_ttes,
-				unsigned long io_attributes,
-				unsigned long io_page_list_pa);
-extern unsigned long pci_sun4v_iommu_demap(unsigned long devhandle,
-					   unsigned long tsbid,
-					   unsigned long num_ttes);
-extern unsigned long pci_sun4v_iommu_getmap(unsigned long devhandle,
-					    unsigned long tsbid,
-					    unsigned long *io_attributes,
-					    unsigned long *real_address);
-extern unsigned long pci_sun4v_config_get(unsigned long devhandle,
-					  unsigned long pci_device,
-					  unsigned long config_offset,
-					  unsigned long size);
-extern int pci_sun4v_config_put(unsigned long devhandle,
-				unsigned long pci_device,
-				unsigned long config_offset,
-				unsigned long size,
-				unsigned long data);
+long pci_sun4v_iommu_map(unsigned long devhandle,
+			 unsigned long tsbid,
+			 unsigned long num_ttes,
+			 unsigned long io_attributes,
+			 unsigned long io_page_list_pa);
+unsigned long pci_sun4v_iommu_demap(unsigned long devhandle,
+				    unsigned long tsbid,
+				    unsigned long num_ttes);
+unsigned long pci_sun4v_iommu_getmap(unsigned long devhandle,
+				     unsigned long tsbid,
+				     unsigned long *io_attributes,
+				     unsigned long *real_address);
+unsigned long pci_sun4v_config_get(unsigned long devhandle,
+				   unsigned long pci_device,
+				   unsigned long config_offset,
+				   unsigned long size);
+int pci_sun4v_config_put(unsigned long devhandle,
+			 unsigned long pci_device,
+			 unsigned long config_offset,
+			 unsigned long size,
+			 unsigned long data);
 
-extern unsigned long pci_sun4v_msiq_conf(unsigned long devhandle,
+unsigned long pci_sun4v_msiq_conf(unsigned long devhandle,
 					 unsigned long msiqid,
 					 unsigned long msiq_paddr,
 					 unsigned long num_entries);
-extern unsigned long pci_sun4v_msiq_info(unsigned long devhandle,
-					 unsigned long msiqid,
-					 unsigned long *msiq_paddr,
-					 unsigned long *num_entries);
-extern unsigned long pci_sun4v_msiq_getvalid(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *valid);
-extern unsigned long pci_sun4v_msiq_setvalid(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long valid);
-extern unsigned long pci_sun4v_msiq_getstate(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *state);
-extern unsigned long pci_sun4v_msiq_setstate(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long state);
-extern unsigned long pci_sun4v_msiq_gethead(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *head);
-extern unsigned long pci_sun4v_msiq_sethead(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long head);
-extern unsigned long pci_sun4v_msiq_gettail(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *head);
-extern unsigned long pci_sun4v_msi_getvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long *valid);
-extern unsigned long pci_sun4v_msi_setvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long valid);
-extern unsigned long pci_sun4v_msi_getmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long *msiq);
-extern unsigned long pci_sun4v_msi_setmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long msiq,
-					   unsigned long msitype);
-extern unsigned long pci_sun4v_msi_getstate(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long *state);
-extern unsigned long pci_sun4v_msi_setstate(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long state);
-extern unsigned long pci_sun4v_msg_getmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long *msiq);
-extern unsigned long pci_sun4v_msg_setmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long msiq);
-extern unsigned long pci_sun4v_msg_getvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long *valid);
-extern unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long valid);
+unsigned long pci_sun4v_msiq_info(unsigned long devhandle,
+				  unsigned long msiqid,
+				  unsigned long *msiq_paddr,
+				  unsigned long *num_entries);
+unsigned long pci_sun4v_msiq_getvalid(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long *valid);
+unsigned long pci_sun4v_msiq_setvalid(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long valid);
+unsigned long pci_sun4v_msiq_getstate(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long *state);
+unsigned long pci_sun4v_msiq_setstate(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long state);
+unsigned long pci_sun4v_msiq_gethead(unsigned long devhandle,
+				     unsigned long msiqid,
+				     unsigned long *head);
+unsigned long pci_sun4v_msiq_sethead(unsigned long devhandle,
+				     unsigned long msiqid,
+				     unsigned long head);
+unsigned long pci_sun4v_msiq_gettail(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long *head);
+unsigned long pci_sun4v_msi_getvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long *valid);
+unsigned long pci_sun4v_msi_setvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long valid);
+unsigned long pci_sun4v_msi_getmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long *msiq);
+unsigned long pci_sun4v_msi_setmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long msiq,
+				    unsigned long msitype);
+unsigned long pci_sun4v_msi_getstate(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long *state);
+unsigned long pci_sun4v_msi_setstate(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long state);
+unsigned long pci_sun4v_msg_getmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long *msiq);
+unsigned long pci_sun4v_msg_setmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long msiq);
+unsigned long pci_sun4v_msg_getvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long *valid);
+unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long valid);
 
 #endif /* !(_PCI_SUN4V_H) */
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 09f4fdd..6cc78c2 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -36,6 +36,7 @@
 #include <asm/uaccess.h>
 #include <asm/irq_regs.h>
 
+#include "kernel.h"
 #include "irq.h"
 
 /*
@@ -162,8 +163,8 @@
 static struct linux_pcic pcic0;
 
 void __iomem *pcic_regs;
-volatile int pcic_speculative;
-volatile int pcic_trapped;
+static volatile int pcic_speculative;
+static volatile int pcic_trapped;
 
 /* forward */
 unsigned int pcic_build_device_irq(struct platform_device *op,
@@ -329,7 +330,7 @@
 
 	pcic->pcic_res_cfg_addr.name = "pcic_cfg_addr";
 	if ((pcic->pcic_config_space_addr =
-	    ioremap(regs[2].phys_addr, regs[2].reg_size * 2)) == 0) {
+	    ioremap(regs[2].phys_addr, regs[2].reg_size * 2)) == NULL) {
 		prom_printf("PCIC: Error, cannot map "
 			    "PCI Configuration Space Address.\n");
 		prom_halt();
@@ -341,7 +342,7 @@
 	 */
 	pcic->pcic_res_cfg_data.name = "pcic_cfg_data";
 	if ((pcic->pcic_config_space_data =
-	    ioremap(regs[3].phys_addr, regs[3].reg_size * 2)) == 0) {
+	    ioremap(regs[3].phys_addr, regs[3].reg_size * 2)) == NULL) {
 		prom_printf("PCIC: Error, cannot map "
 			    "PCI Configuration Space Data.\n");
 		prom_halt();
@@ -353,7 +354,6 @@
 	strcpy(pbm->prom_name, namebuf);
 
 	{
-		extern volatile int t_nmi[4];
 		extern int pcic_nmi_trap_patch[4];
 
 		t_nmi[0] = pcic_nmi_trap_patch[0];
@@ -536,7 +536,7 @@
 		prom_getstring(node, "name", namebuf, sizeof(namebuf));
 	}
 
-	if ((p = pcic->pcic_imap) == 0) {
+	if ((p = pcic->pcic_imap) == NULL) {
 		dev->irq = 0;
 		return;
 	}
@@ -670,30 +670,6 @@
 	}
 }
 
-/*
- * pcic_pin_to_irq() is exported to bus probing code
- */
-unsigned int
-pcic_pin_to_irq(unsigned int pin, const char *name)
-{
-	struct linux_pcic *pcic = &pcic0;
-	unsigned int irq;
-	unsigned int ivec;
-
-	if (pin < 4) {
-		ivec = readw(pcic->pcic_regs+PCI_INT_SELECT_LO);
-		irq = ivec >> (pin << 2) & 0xF;
-	} else if (pin < 8) {
-		ivec = readw(pcic->pcic_regs+PCI_INT_SELECT_HI);
-		irq = ivec >> ((pin-4) << 2) & 0xF;
-	} else {					/* Corrupted map */
-		printk("PCIC: BAD PIN %d FOR %s\n", pin, name);
-		for (;;) {}	/* XXX Cannot panic properly in case of PROLL */
-	}
-/* P3 */ /* printk("PCIC: dev %s pin %d ivec 0x%x irq %x\n", name, pin, ivec, irq); */
-	return irq;
-}
-
 /* Makes compiler happy */
 static volatile int pcic_timer_dummy;
 
@@ -783,7 +759,7 @@
 void pcic_nmi(unsigned int pend, struct pt_regs *regs)
 {
 
-	pend = flip_dword(pend);
+	pend = swab32(pend);
 
 	if (!pcic_speculative || (pend & PCI_SYS_INT_PENDING_PIO) == 0) {
 		/*
@@ -875,82 +851,4 @@
 	sparc_config.load_profile_irq = pcic_load_profile_irq;
 }
 
-/*
- * This probably belongs here rather than ioport.c because
- * we do not want this crud linked into SBus kernels.
- * Also, think for a moment about likes of floppy.c that
- * include architecture specific parts. They may want to redefine ins/outs.
- *
- * We do not use horrible macros here because we want to
- * advance pointer by sizeof(size).
- */
-void outsb(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		outb(*(const char *)src, addr);
-		src += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(outsb);
-
-void outsw(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		outw(*(const short *)src, addr);
-		src += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(outsw);
-
-void outsl(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		outl(*(const long *)src, addr);
-		src += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(outsl);
-
-void insb(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		*(unsigned char *)dst = inb(addr);
-		dst += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(insb);
-
-void insw(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		*(unsigned short *)dst = inw(addr);
-		dst += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(insw);
-
-void insl(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		/*
-		 * XXX I am sure we are in for an unaligned trap here.
-		 */
-		*(unsigned long *)dst = inl(addr);
-		dst += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(insl);
-
 subsys_initcall(pcic_init);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b5c38fa..8efd337 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -110,7 +110,7 @@
 
 	unsigned int		group_flag;
 };
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
 
 /* An event map describes the characteristics of a performance
  * counter event.  In particular it gives the encoding as well as
@@ -1153,7 +1153,7 @@
 		cpuc->pcr[i] = pcr_ops->read_pcr(i);
 }
 
-void perf_event_grab_pmc(void)
+static void perf_event_grab_pmc(void)
 {
 	if (atomic_inc_not_zero(&active_events))
 		return;
@@ -1169,7 +1169,7 @@
 	mutex_unlock(&pmc_grab_mutex);
 }
 
-void perf_event_release_pmc(void)
+static void perf_event_release_pmc(void)
 {
 	if (atomic_dec_and_mutex_lock(&active_events, &pmc_grab_mutex)) {
 		if (atomic_read(&nmi_active) == 0)
@@ -1669,7 +1669,7 @@
 	return false;
 }
 
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
 {
 	pr_info("Performance events: ");
 
@@ -1742,10 +1742,11 @@
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
 	do {
-		struct sparc_stackf *usf, sf;
+		struct sparc_stackf __user *usf;
+		struct sparc_stackf sf;
 		unsigned long pc;
 
-		usf = (struct sparc_stackf *) ufp;
+		usf = (struct sparc_stackf __user *)ufp;
 		if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 			break;
 
@@ -1765,17 +1766,19 @@
 		unsigned long pc;
 
 		if (thread32_stack_is_64bit(ufp)) {
-			struct sparc_stackf *usf, sf;
+			struct sparc_stackf __user *usf;
+			struct sparc_stackf sf;
 
 			ufp += STACK_BIAS;
-			usf = (struct sparc_stackf *) ufp;
+			usf = (struct sparc_stackf __user *)ufp;
 			if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 				break;
 			pc = sf.callers_pc & 0xffffffff;
 			ufp = ((unsigned long) sf.fp) & 0xffffffff;
 		} else {
-			struct sparc_stackf32 *usf, sf;
-			usf = (struct sparc_stackf32 *) ufp;
+			struct sparc_stackf32 __user *usf;
+			struct sparc_stackf32 sf;
+			usf = (struct sparc_stackf32 __user *)ufp;
 			if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 				break;
 			pc = sf.callers_pc;
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 510baec..50e7b62 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -10,6 +10,7 @@
 
 #include <stdarg.h>
 
+#include <linux/elfcore.h>
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -23,6 +24,7 @@
 #include <linux/delay.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 
 #include <asm/auxio.h>
 #include <asm/oplib.h>
@@ -38,6 +40,8 @@
 #include <asm/unistd.h>
 #include <asm/setup.h>
 
+#include "kernel.h"
+
 /* 
  * Power management idle function 
  * Set in pm platform drivers (apc.c and pmc.c)
@@ -102,8 +106,12 @@
 void machine_power_off(void)
 {
 	if (auxio_power_register &&
-	    (strcmp(of_console_device->type, "serial") || scons_pwroff))
-		*auxio_power_register |= AUXIO_POWER_OFF;
+	    (strcmp(of_console_device->type, "serial") || scons_pwroff)) {
+		u8 power_register = sbus_readb(auxio_power_register);
+		power_register |= AUXIO_POWER_OFF;
+		sbus_writeb(power_register, auxio_power_register);
+	}
+
 	machine_halt();
 }
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d7b4967..b2988f2 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -88,7 +88,7 @@
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead()
+void arch_cpu_idle_dead(void)
 {
 	sched_preempt_enable_no_resched();
 	cpu_play_dead();
diff --git a/arch/sparc/kernel/prom.h b/arch/sparc/kernel/prom.h
index cf5fe1c..890281b 100644
--- a/arch/sparc/kernel/prom.h
+++ b/arch/sparc/kernel/prom.h
@@ -4,7 +4,7 @@
 #include <linux/spinlock.h>
 #include <asm/prom.h>
 
-extern void of_console_init(void);
+void of_console_init(void);
 
 extern unsigned int prom_early_allocated;
 
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index 9a690d3..20cc5d8 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -15,11 +15,12 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/mm.h>
 #include <linux/memblock.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/cpu.h>
+#include <linux/mm.h>
 #include <linux/of.h>
 
 #include <asm/prom.h>
diff --git a/arch/sparc/kernel/psycho_common.h b/arch/sparc/kernel/psycho_common.h
index 590b4ed..05a6e30 100644
--- a/arch/sparc/kernel/psycho_common.h
+++ b/arch/sparc/kernel/psycho_common.h
@@ -30,19 +30,19 @@
 	UE_ERR, CE_ERR, PCI_ERR
 };
 
-extern void psycho_check_iommu_error(struct pci_pbm_info *pbm,
-				     unsigned long afsr,
-				     unsigned long afar,
-				     enum psycho_error_type type);
+void psycho_check_iommu_error(struct pci_pbm_info *pbm,
+			      unsigned long afsr,
+			      unsigned long afar,
+			      enum psycho_error_type type);
 
-extern irqreturn_t psycho_pcierr_intr(int irq, void *dev_id);
+irqreturn_t psycho_pcierr_intr(int irq, void *dev_id);
 
-extern int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize,
-			     u32 dvma_offset, u32 dma_mask,
-			     unsigned long write_complete_offset);
+int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize,
+		      u32 dvma_offset, u32 dma_mask,
+		      unsigned long write_complete_offset);
 
-extern void psycho_pbm_init_common(struct pci_pbm_info *pbm,
-				   struct platform_device *op,
-				   const char *chip_name, int chip_type);
+void psycho_pbm_init_common(struct pci_pbm_info *pbm,
+			    struct platform_device *op,
+			    const char *chip_name, int chip_type);
 
 #endif /* _PSYCHO_COMMON_H */
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 896ba7c..a331fdc 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -26,6 +26,8 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 
+#include "kernel.h"
+
 /* #define ALLOW_INIT_TRACING */
 
 /*
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 1434526..baef495 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -267,7 +267,7 @@
 }
 
 struct tt_entry *sparc_ttable;
-struct pt_regs fake_swapper_regs;
+static struct pt_regs fake_swapper_regs;
 
 /* Called from head_32.S - before we have setup anything
  * in the kernel. Be very careful with what you do here.
@@ -365,7 +365,7 @@
 
 	prom_setsync(prom_sync_me);
 
-	if((boot_flags&BOOTME_DEBUG) && (linux_dbvec!=0) && 
+	if((boot_flags & BOOTME_DEBUG) && (linux_dbvec != NULL) &&
 	   ((*(short *)linux_dbvec) != -1)) {
 		printk("Booted under KADB. Syncing trap table.\n");
 		(*(linux_dbvec->teach_debugger))();
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index ee789d2..62deba7 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -31,6 +31,7 @@
 #include <asm/switch_to.h>
 
 #include "sigutil.h"
+#include "kernel.h"
 
 /* This magic should be in g_upper[0] for all upper parts
  * to be valid.
@@ -145,7 +146,7 @@
 	unsigned int psr;
 	unsigned pc, npc;
 	sigset_t set;
-	unsigned seta[_COMPAT_NSIG_WORDS];
+	compat_sigset_t seta;
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
@@ -209,17 +210,13 @@
 		if (restore_rwin_state(compat_ptr(rwin_save)))
 			goto segv;
 	}
-	err |= __get_user(seta[0], &sf->info.si_mask);
-	err |= copy_from_user(seta+1, &sf->extramask,
+	err |= __get_user(seta.sig[0], &sf->info.si_mask);
+	err |= copy_from_user(&seta.sig[1], &sf->extramask,
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
 	if (err)
 	    	goto segv;
-	switch (_NSIG_WORDS) {
-		case 4: set.sig[3] = seta[6] + (((long)seta[7]) << 32);
-		case 3: set.sig[2] = seta[4] + (((long)seta[5]) << 32);
-		case 2: set.sig[1] = seta[2] + (((long)seta[3]) << 32);
-		case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32);
-	}
+
+	set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32);
 	set_current_blocked(&set);
 	return;
 
@@ -303,12 +300,7 @@
 			goto segv;
 	}
 
-	switch (_NSIG_WORDS) {
-		case 4: set.sig[3] = seta.sig[6] + (((long)seta.sig[7]) << 32);
-		case 3: set.sig[2] = seta.sig[4] + (((long)seta.sig[5]) << 32);
-		case 2: set.sig[1] = seta.sig[2] + (((long)seta.sig[3]) << 32);
-		case 1: set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32);
-	}
+	set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32);
 	set_current_blocked(&set);
 	return;
 segv:
@@ -417,7 +409,7 @@
 	void __user *tail;
 	int sigframe_size;
 	u32 psr;
-	unsigned int seta[_COMPAT_NSIG_WORDS];
+	compat_sigset_t seta;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
@@ -481,18 +473,14 @@
 		err |= __put_user(0, &sf->rwin_save);
 	}
 
-	switch (_NSIG_WORDS) {
-	case 4: seta[7] = (oldset->sig[3] >> 32);
-	        seta[6] = oldset->sig[3];
-	case 3: seta[5] = (oldset->sig[2] >> 32);
-	        seta[4] = oldset->sig[2];
-	case 2: seta[3] = (oldset->sig[1] >> 32);
-	        seta[2] = oldset->sig[1];
-	case 1: seta[1] = (oldset->sig[0] >> 32);
-	        seta[0] = oldset->sig[0];
-	}
-	err |= __put_user(seta[0], &sf->info.si_mask);
-	err |= __copy_to_user(sf->extramask, seta + 1,
+	/* If these change we need to know - assignments to seta relies on these sizes */
+	BUILD_BUG_ON(_NSIG_WORDS != 1);
+	BUILD_BUG_ON(_COMPAT_NSIG_WORDS != 2);
+	seta.sig[1] = (oldset->sig[0] >> 32);
+	seta.sig[0] = oldset->sig[0];
+
+	err |= __put_user(seta.sig[0], &sf->info.si_mask);
+	err |= __copy_to_user(sf->extramask, &seta.sig[1],
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
 
 	if (!wsaved) {
@@ -622,16 +610,8 @@
 	/* Setup sigaltstack */
 	err |= __compat_save_altstack(&sf->stack, regs->u_regs[UREG_FP]);
 
-	switch (_NSIG_WORDS) {
-	case 4: seta.sig[7] = (oldset->sig[3] >> 32);
-		seta.sig[6] = oldset->sig[3];
-	case 3: seta.sig[5] = (oldset->sig[2] >> 32);
-		seta.sig[4] = oldset->sig[2];
-	case 2: seta.sig[3] = (oldset->sig[1] >> 32);
-		seta.sig[2] = oldset->sig[1];
-	case 1: seta.sig[1] = (oldset->sig[0] >> 32);
-		seta.sig[0] = oldset->sig[0];
-	}
+	seta.sig[1] = (oldset->sig[0] >> 32);
+	seta.sig[0] = oldset->sig[0];
 	err |= __copy_to_user(&sf->mask, &seta, sizeof(compat_sigset_t));
 
 	if (!wsaved) {
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 7d5d8e1..9ee72fc 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -28,6 +28,7 @@
 #include <asm/switch_to.h>
 
 #include "sigutil.h"
+#include "kernel.h"
 
 extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 		   void *fpqueue, unsigned long *fpqdepth);
@@ -341,7 +342,7 @@
 	err |= __put_user(0, &sf->extra_size);
 
 	if (psr & PSR_EF) {
-		__siginfo_fpu_t *fp = tail;
+		__siginfo_fpu_t __user *fp = tail;
 		tail += sizeof(*fp);
 		err |= save_fpu_state(regs, fp);
 		err |= __put_user(fp, &sf->fpu_save);
@@ -349,7 +350,7 @@
 		err |= __put_user(0, &sf->fpu_save);
 	}
 	if (wsaved) {
-		__siginfo_rwin_t *rwp = tail;
+		__siginfo_rwin_t __user *rwp = tail;
 		tail += sizeof(*rwp);
 		err |= save_rwin_state(wsaved, rwp);
 		err |= __put_user(rwp, &sf->rwin_save);
@@ -517,9 +518,9 @@
 	}
 }
 
-asmlinkage int
-do_sys_sigstack(struct sigstack __user *ssptr, struct sigstack __user *ossptr,
-		unsigned long sp)
+asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,
+                               struct sigstack __user *ossptr,
+                               unsigned long sp)
 {
 	int ret = -EFAULT;
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index cd91d01..1a69998 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -35,9 +35,10 @@
 #include <asm/switch_to.h>
 #include <asm/cacheflush.h>
 
-#include "entry.h"
-#include "systbls.h"
 #include "sigutil.h"
+#include "systbls.h"
+#include "kernel.h"
+#include "entry.h"
 
 /* {set, get}context() needed for 64-bit SparcLinux userland. */
 asmlinkage void sparc64_set_context(struct pt_regs *regs)
@@ -492,7 +493,6 @@
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT)) {
-		extern void do_signal32(struct pt_regs *);
 		do_signal32(regs);
 		return;
 	}
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index a102bfb..7958242 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -20,6 +20,7 @@
 #include <linux/seq_file.h>
 #include <linux/cache.h>
 #include <linux/delay.h>
+#include <linux/profile.h>
 #include <linux/cpu.h>
 
 #include <asm/ptrace.h>
@@ -75,8 +76,6 @@
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	extern void smp4m_smp_done(void);
-	extern void smp4d_smp_done(void);
 	unsigned long bogosum = 0;
 	int cpu, num = 0;
 
@@ -183,8 +182,6 @@
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	extern void __init smp4m_boot_cpus(void);
-	extern void __init smp4d_boot_cpus(void);
 	int i, cpuid, extra;
 
 	printk("Entering SMP Mode...\n");
@@ -261,8 +258,6 @@
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
-	extern int smp4m_boot_one_cpu(int, struct task_struct *);
-	extern int smp4d_boot_one_cpu(int, struct task_struct *);
 	int ret=0;
 
 	switch(sparc_cpu_model) {
@@ -297,7 +292,7 @@
 	return ret;
 }
 
-void arch_cpu_pre_starting(void *arg)
+static void arch_cpu_pre_starting(void *arg)
 {
 	local_ops->cache_all();
 	local_ops->tlb_all();
@@ -317,7 +312,7 @@
 	}
 }
 
-void arch_cpu_pre_online(void *arg)
+static void arch_cpu_pre_online(void *arg)
 {
 	unsigned int cpuid = hard_smp_processor_id();
 
@@ -344,7 +339,7 @@
 	}
 }
 
-void sparc_start_secondary(void *arg)
+static void sparc_start_secondary(void *arg)
 {
 	unsigned int cpu;
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 745a363..41aa247 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -25,6 +25,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>
+#include <linux/kgdb.h>
 
 #include <asm/head.h>
 #include <asm/ptrace.h>
@@ -35,6 +36,7 @@
 #include <asm/hvtramp.h>
 #include <asm/io.h>
 #include <asm/timer.h>
+#include <asm/setup.h>
 
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
@@ -52,6 +54,7 @@
 #include <asm/pcr.h>
 
 #include "cpumap.h"
+#include "kernel.h"
 
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
@@ -272,14 +275,6 @@
 }
 
 #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
-/* XXX Put this in some common place. XXX */
-static unsigned long kimage_addr_to_ra(void *p)
-{
-	unsigned long val = (unsigned long) p;
-
-	return kern_base + (val - KERNBASE);
-}
-
 static void ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread_reg,
 				void **descrp)
 {
@@ -867,11 +862,6 @@
 #endif
 extern unsigned long xcall_flush_dcache_page_spitfire;
 
-#ifdef CONFIG_DEBUG_DCFLUSH
-extern atomic_t dcpage_flushes;
-extern atomic_t dcpage_flushes_xcall;
-#endif
-
 static inline void __local_flush_dcache_page(struct page *page)
 {
 #ifdef DCACHE_ALIASING_POSSIBLE
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index f8933be..a1bb267 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -143,7 +143,7 @@
 	}
 }
 
-void sun4d_handler_irq(int pil, struct pt_regs *regs)
+void sun4d_handler_irq(unsigned int pil, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
 	/* SBUS IRQ level (1 - 7) */
@@ -236,7 +236,7 @@
 	irq_unlink(data->irq);
 }
 
-struct irq_chip sun4d_irq = {
+static struct irq_chip sun4d_irq = {
 	.name		= "sun4d",
 	.irq_startup	= sun4d_startup_irq,
 	.irq_shutdown	= sun4d_shutdown_irq,
@@ -285,9 +285,9 @@
 	}
 }
 
-unsigned int _sun4d_build_device_irq(unsigned int real_irq,
-                                     unsigned int pil,
-                                     unsigned int board)
+static unsigned int _sun4d_build_device_irq(unsigned int real_irq,
+                                            unsigned int pil,
+                                            unsigned int board)
 {
 	struct sun4d_handler_data *handler_data;
 	unsigned int irq;
@@ -320,8 +320,8 @@
 
 
 
-unsigned int sun4d_build_device_irq(struct platform_device *op,
-                                    unsigned int real_irq)
+static unsigned int sun4d_build_device_irq(struct platform_device *op,
+                                           unsigned int real_irq)
 {
 	struct device_node *dp = op->dev.of_node;
 	struct device_node *board_parent, *bus = dp->parent;
@@ -383,7 +383,8 @@
 	return irq;
 }
 
-unsigned int sun4d_build_timer_irq(unsigned int board, unsigned int real_irq)
+static unsigned int sun4d_build_timer_irq(unsigned int board,
+                                          unsigned int real_irq)
 {
 	return _sun4d_build_device_irq(real_irq, real_irq, board);
 }
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 7136885..022c30c 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -49,6 +49,8 @@
 #include <asm/mmu_context.h>
 #include <asm/compat_signal.h>
 
+#include "systbls.h"
+
 asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low)
 {
 	if ((int)high < 0)
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index 3a8d184..646988d 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -24,6 +24,8 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
+#include "systbls.h"
+
 /* #define DEBUG_UNIMP_SYSCALL */
 
 /* XXX Make this per-binary type, this way we can detect the type of
@@ -68,7 +70,7 @@
  * sys_pipe() is the normal C calling standard for creating
  * a pipe. It's not the way unix traditionally does this, though.
  */
-asmlinkage int sparc_pipe(struct pt_regs *regs)
+asmlinkage long sparc_pipe(struct pt_regs *regs)
 {
 	int fd[2];
 	int error;
@@ -93,7 +95,7 @@
 
 /* Linux version of mmap */
 
-asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len,
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
 	unsigned long pgoff)
 {
@@ -103,7 +105,7 @@
 			      pgoff >> (PAGE_SHIFT - 12));
 }
 
-asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len,
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
 	unsigned long off)
 {
@@ -197,7 +199,7 @@
 	return ret;
 }
 
-asmlinkage int sys_getdomainname(char __user *name, int len)
+asmlinkage long sys_getdomainname(char __user *name, int len)
 {
  	int nlen, err;
  	
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index beb0b5a..c85403d 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -31,6 +31,7 @@
 #include <asm/unistd.h>
 
 #include "entry.h"
+#include "kernel.h"
 #include "systbls.h"
 
 /* #define DEBUG_UNIMP_SYSCALL */
diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h
index 26e6dd7..2dab823 100644
--- a/arch/sparc/kernel/systbls.h
+++ b/arch/sparc/kernel/systbls.h
@@ -1,41 +1,103 @@
 #ifndef _SYSTBLS_H
 #define _SYSTBLS_H
 
-#include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/signal.h>
+#include <linux/kernel.h>
+#include <linux/compat.h>
+#include <linux/types.h>
+
 #include <asm/utrap.h>
 
-extern asmlinkage unsigned long sys_getpagesize(void);
-extern asmlinkage long sparc_pipe(struct pt_regs *regs);
-extern asmlinkage long sys_sparc_ipc(unsigned int call, int first,
-			       unsigned long second,
-			       unsigned long third,
-			       void __user *ptr, long fifth);
-extern asmlinkage long sparc64_personality(unsigned long personality);
-extern asmlinkage long sys64_munmap(unsigned long addr, size_t len);
-extern asmlinkage unsigned long sys64_mremap(unsigned long addr,
-					     unsigned long old_len,
-					     unsigned long new_len,
-					     unsigned long flags,
-					     unsigned long new_addr);
-extern asmlinkage unsigned long c_sys_nis_syscall(struct pt_regs *regs);
-extern asmlinkage long sys_getdomainname(char __user *name, int len);
-extern asmlinkage long sys_utrap_install(utrap_entry_t type,
-					 utrap_handler_t new_p,
-					 utrap_handler_t new_d,
-					 utrap_handler_t __user *old_p,
-					 utrap_handler_t __user *old_d);
-extern asmlinkage long sparc_memory_ordering(unsigned long model,
-					     struct pt_regs *regs);
-extern asmlinkage long sys_rt_sigaction(int sig,
-					const struct sigaction __user *act,
-					struct sigaction __user *oact,
-					void __user *restorer,
-					size_t sigsetsize);
+asmlinkage unsigned long sys_getpagesize(void);
+asmlinkage long sparc_pipe(struct pt_regs *regs);
+asmlinkage unsigned long c_sys_nis_syscall(struct pt_regs *regs);
+asmlinkage long sys_getdomainname(char __user *name, int len);
+void do_rt_sigreturn(struct pt_regs *regs);
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
+			 unsigned long prot, unsigned long flags,
+			 unsigned long fd, unsigned long off);
+asmlinkage void sparc_breakpoint(struct pt_regs *regs);
 
-extern asmlinkage void sparc64_set_context(struct pt_regs *regs);
-extern asmlinkage void sparc64_get_context(struct pt_regs *regs);
-extern void do_rt_sigreturn(struct pt_regs *regs);
+#ifdef CONFIG_SPARC32
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+			  unsigned long prot, unsigned long flags,
+			  unsigned long fd, unsigned long pgoff);
+long sparc_remap_file_pages(unsigned long start, unsigned long size,
+			    unsigned long prot, unsigned long pgoff,
+			    unsigned long flags);
 
+#endif /* CONFIG_SPARC32 */
+
+#ifdef CONFIG_SPARC64
+asmlinkage long sys_sparc_ipc(unsigned int call, int first,
+			      unsigned long second,
+			      unsigned long third,
+			      void __user *ptr, long fifth);
+asmlinkage long sparc64_personality(unsigned long personality);
+asmlinkage long sys64_munmap(unsigned long addr, size_t len);
+asmlinkage unsigned long sys64_mremap(unsigned long addr,
+				      unsigned long old_len,
+				      unsigned long new_len,
+				      unsigned long flags,
+				      unsigned long new_addr);
+asmlinkage long sys_utrap_install(utrap_entry_t type,
+				  utrap_handler_t new_p,
+				  utrap_handler_t new_d,
+				  utrap_handler_t __user *old_p,
+				  utrap_handler_t __user *old_d);
+asmlinkage long sparc_memory_ordering(unsigned long model,
+				      struct pt_regs *regs);
+asmlinkage void sparc64_set_context(struct pt_regs *regs);
+asmlinkage void sparc64_get_context(struct pt_regs *regs);
+asmlinkage long sys32_truncate64(const char __user * path,
+				 unsigned long high,
+				 unsigned long low);
+asmlinkage long sys32_ftruncate64(unsigned int fd,
+				  unsigned long high,
+				  unsigned long low);
+struct compat_stat64;
+asmlinkage long compat_sys_stat64(const char __user * filename,
+				  struct compat_stat64 __user *statbuf);
+asmlinkage long compat_sys_lstat64(const char __user * filename,
+				   struct compat_stat64 __user *statbuf);
+asmlinkage long compat_sys_fstat64(unsigned int fd,
+				   struct compat_stat64 __user * statbuf);
+asmlinkage long compat_sys_fstatat64(unsigned int dfd,
+				     const char __user *filename,
+				     struct compat_stat64 __user * statbuf, int flag);
+asmlinkage compat_ssize_t sys32_pread64(unsigned int fd,
+					char __user *ubuf,
+					compat_size_t count,
+					unsigned long poshi,
+					unsigned long poslo);
+asmlinkage compat_ssize_t sys32_pwrite64(unsigned int fd,
+					 char __user *ubuf,
+					 compat_size_t count,
+					 unsigned long poshi,
+					 unsigned long poslo);
+asmlinkage long compat_sys_readahead(int fd,
+				     unsigned long offhi,
+				     unsigned long offlo,
+				     compat_size_t count);
+long compat_sys_fadvise64(int fd,
+			  unsigned long offhi,
+			  unsigned long offlo,
+			  compat_size_t len, int advice);
+long compat_sys_fadvise64_64(int fd,
+			     unsigned long offhi, unsigned long offlo,
+			     unsigned long lenhi, unsigned long lenlo,
+			     int advice);
+long sys32_sync_file_range(unsigned int fd,
+			   unsigned long off_high, unsigned long off_low,
+			   unsigned long nb_high, unsigned long nb_low,
+			   unsigned int flags);
+asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo,
+				     u32 lenhi, u32 lenlo);
+asmlinkage long compat_sys_fstat64(unsigned int fd,
+				   struct compat_stat64 __user * statbuf);
+asmlinkage long compat_sys_fstatat64(unsigned int dfd,
+				     const char __user *filename,
+				     struct compat_stat64 __user * statbuf,
+				     int flag);
+#endif /* CONFIG_SPARC64 */
 #endif /* _SYSTBLS_H */
diff --git a/arch/sparc/kernel/tadpole.c b/arch/sparc/kernel/tadpole.c
deleted file mode 100644
index 9aba8bd..0000000
--- a/arch/sparc/kernel/tadpole.c
+++ /dev/null
@@ -1,126 +0,0 @@
-/* tadpole.c: Probing for the tadpole clock stopping h/w at boot time.
- *
- * Copyright (C) 1996 David Redman (djhr@tadpole.co.uk)
- */
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-
-#include <asm/asi.h>
-#include <asm/oplib.h>
-#include <asm/io.h>
-
-#define MACIO_SCSI_CSR_ADDR	0x78400000
-#define MACIO_EN_DMA		0x00000200
-#define CLOCK_INIT_DONE		1
-
-static int clk_state;
-static volatile unsigned char *clk_ctrl;
-void (*cpu_pwr_save)(void);
-
-static inline unsigned int ldphys(unsigned int addr)
-{
-	unsigned long data;
-    
-	__asm__ __volatile__("\n\tlda [%1] %2, %0\n\t" : 
-			     "=r" (data) :
-			     "r" (addr), "i" (ASI_M_BYPASS));
-	return data;
-}
-
-static void clk_init(void)
-{
-	__asm__ __volatile__("mov 0x6c, %%g1\n\t"
-			     "mov 0x4c, %%g2\n\t"
-			     "mov 0xdf, %%g3\n\t"
-			     "stb %%g1, [%0+3]\n\t"
-			     "stb %%g2, [%0+3]\n\t"
-			     "stb %%g3, [%0+3]\n\t" : :
-			     "r" (clk_ctrl) :
-			     "g1", "g2", "g3");
-}
-
-static void clk_slow(void)
-{
-	__asm__ __volatile__("mov 0xcc, %%g2\n\t"
-			     "mov 0x4c, %%g3\n\t"
-			     "mov 0xcf, %%g4\n\t"
-			     "mov 0xdf, %%g5\n\t"
-			     "stb %%g2, [%0+3]\n\t"
-			     "stb %%g3, [%0+3]\n\t"
-			     "stb %%g4, [%0+3]\n\t"
-			     "stb %%g5, [%0+3]\n\t" : :
-			     "r" (clk_ctrl) :
-			     "g2", "g3", "g4", "g5");
-}
-
-/*
- * Tadpole is guaranteed to be UP, using local_irq_save.
- */
-static void tsu_clockstop(void)
-{
-	unsigned int mcsr;
-	unsigned long flags;
-
-	if (!clk_ctrl)
-		return;
-	if (!(clk_state & CLOCK_INIT_DONE)) {
-		local_irq_save(flags);
-		clk_init();
-		clk_state |= CLOCK_INIT_DONE;       /* all done */
-		local_irq_restore(flags);
-		return;
-	}
-	if (!(clk_ctrl[2] & 1))
-		return;               /* no speed up yet */
-
-	local_irq_save(flags);
-
-	/* if SCSI DMA in progress, don't slow clock */
-	mcsr = ldphys(MACIO_SCSI_CSR_ADDR);
-	if ((mcsr&MACIO_EN_DMA) != 0) {
-		local_irq_restore(flags);
-		return;
-	}
-	/* TODO... the minimum clock setting ought to increase the
-	 * memory refresh interval..
-	 */
-	clk_slow();
-	local_irq_restore(flags);
-}
-
-static void swift_clockstop(void)
-{
-	if (!clk_ctrl)
-		return;
-	clk_ctrl[0] = 0;
-}
-
-void __init clock_stop_probe(void)
-{
-	phandle node, clk_nd;
-	char name[20];
-    
-	prom_getstring(prom_root_node, "name", name, sizeof(name));
-	if (strncmp(name, "Tadpole", 7))
-		return;
-	node = prom_getchild(prom_root_node);
-	node = prom_searchsiblings(node, "obio");
-	node = prom_getchild(node);
-	clk_nd = prom_searchsiblings(node, "clk-ctrl");
-	if (!clk_nd)
-		return;
-	printk("Clock Stopping h/w detected... ");
-	clk_ctrl = (char *) prom_getint(clk_nd, "address");
-	clk_state = 0;
-	if (name[10] == '\0') {
-		cpu_pwr_save = tsu_clockstop;
-		printk("enabled (S3)\n");
-	} else if ((name[10] == 'X') || (name[10] == 'G')) {
-		cpu_pwr_save = swift_clockstop;
-		printk("enabled (%s)\n",name+7);
-	} else
-		printk("disabled %s\n",name+7);
-}
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index c4c27b0..5923d1e 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -36,6 +36,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 
+#include <asm/mc146818rtc.h>
 #include <asm/oplib.h>
 #include <asm/timex.h>
 #include <asm/timer.h>
@@ -47,6 +48,7 @@
 #include <asm/irq_regs.h>
 #include <asm/setup.h>
 
+#include "kernel.h"
 #include "irq.h"
 
 static __cacheline_aligned_in_smp DEFINE_SEQLOCK(timer_cs_lock);
@@ -83,7 +85,7 @@
 
 EXPORT_SYMBOL(profile_pc);
 
-__volatile__ unsigned int *master_l10_counter;
+volatile u32 __iomem *master_l10_counter;
 
 int update_persistent_clock(struct timespec now)
 {
@@ -143,9 +145,9 @@
 
 static unsigned int sbus_cycles_offset(void)
 {
-	unsigned int val, offset;
+	u32 val, offset;
 
-	val = *master_l10_counter;
+	val = sbus_readl(master_l10_counter);
 	offset = (val >> TIMER_VALUE_SHIFT) & TIMER_VALUE_MASK;
 
 	/* Limit hit? */
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 6629829..6fd386c 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -44,7 +44,7 @@
 #define __SAVE __asm__ __volatile__("save %sp, -0x40, %sp\n\t")
 #define __RESTORE __asm__ __volatile__("restore %g0, %g0, %g0\n\t")
 
-void die_if_kernel(char *str, struct pt_regs *regs)
+void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
 {
 	static int die_counter;
 	int count = 0;
@@ -219,8 +219,6 @@
 static unsigned long fake_queue[32] __attribute__ ((aligned (8)));
 static unsigned long fake_depth;
 
-extern int do_mathemu(struct pt_regs *, struct task_struct *);
-
 void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 		 unsigned long psr)
 {
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4ced92f..fb6640e 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -43,8 +43,10 @@
 #include <asm/prom.h>
 #include <asm/memctrl.h>
 #include <asm/cacheflush.h>
+#include <asm/setup.h>
 
 #include "entry.h"
+#include "kernel.h"
 #include "kstack.h"
 
 /* When an irrecoverable trap occurs at tl > 0, the trap entry
@@ -2209,8 +2211,6 @@
 	exception_exit(prev_state);
 }
 
-extern int do_mathemu(struct pt_regs *, struct fpustate *, bool);
-
 void do_fpother(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -2383,7 +2383,7 @@
 	return (struct reg_window *) (fp + STACK_BIAS);
 }
 
-void die_if_kernel(char *str, struct pt_regs *regs)
+void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
 {
 	static int die_counter;
 	int count = 0;
@@ -2433,9 +2433,6 @@
 #define VIS_OPCODE_MASK	((0x3 << 30) | (0x3f << 19))
 #define VIS_OPCODE_VAL	((0x2 << 30) | (0x36 << 19))
 
-extern int handle_popc(u32 insn, struct pt_regs *regs);
-extern int handle_ldf_stq(u32 insn, struct pt_regs *regs);
-
 void do_illegal_instruction(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -2486,8 +2483,6 @@
 	exception_exit(prev_state);
 }
 
-extern void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn);
-
 void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr)
 {
 	enum ctx_state prev_state = exception_enter();
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index c0ec897..c5c61b3 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -16,6 +16,10 @@
 #include <linux/smp.h>
 #include <linux/perf_event.h>
 
+#include <asm/setup.h>
+
+#include "kernel.h"
+
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
 	store,   /* st, std, sth, stsh */
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 35ab8b6..62098a8 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -24,8 +24,10 @@
 #include <linux/context_tracking.h>
 #include <asm/fpumacro.h>
 #include <asm/cacheflush.h>
+#include <asm/setup.h>
 
 #include "entry.h"
+#include "kernel.h"
 
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index 3107381..87bab0a 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -10,8 +10,11 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 
+#include <asm/cacheflush.h>
 #include <asm/uaccess.h>
 
+#include "kernel.h"
+
 /* Do save's until all user register windows are out of the cpu. */
 void flush_user_windows(void)
 {
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index dbe119b..3269b02 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -41,7 +41,7 @@
 lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
 lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
-obj-y                 += iomap.o
+obj-$(CONFIG_SPARC64) += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o
 obj-y                 += ksyms.o
 obj-$(CONFIG_SPARC64) += PeeCeeI.o
diff --git a/arch/sparc/math-emu/sfp-util_32.h b/arch/sparc/math-emu/sfp-util_32.h
index d1b2aff3..bb587d5 100644
--- a/arch/sparc/math-emu/sfp-util_32.h
+++ b/arch/sparc/math-emu/sfp-util_32.h
@@ -4,20 +4,20 @@
 #include <asm/byteorder.h>
 
 #define add_ssaaaa(sh, sl, ah, al, bh, bl) 				\
-  __asm__ ("addcc %r4,%5,%1\n\t"						\
+  __asm__ ("addcc %r4,%5,%1\n\t"					\
 	   "addx %r2,%3,%0\n"						\
-	   : "=r" ((USItype)(sh)),					\
-	     "=&r" ((USItype)(sl))					\
+	   : "=r" (sh),							\
+	     "=&r" (sl)							\
 	   : "%rJ" ((USItype)(ah)),					\
 	     "rI" ((USItype)(bh)),					\
 	     "%rJ" ((USItype)(al)),					\
 	     "rI" ((USItype)(bl))					\
 	   : "cc")
 #define sub_ddmmss(sh, sl, ah, al, bh, bl) 				\
-  __asm__ ("subcc %r4,%5,%1\n\t"						\
+  __asm__ ("subcc %r4,%5,%1\n\t"					\
 	   "subx %r2,%3,%0\n"						\
-	   : "=r" ((USItype)(sh)),					\
-	     "=&r" ((USItype)(sl))					\
+	   : "=r" (sh),							\
+	     "=&r" (sl)							\
 	   : "rJ" ((USItype)(ah)),					\
 	     "rI" ((USItype)(bh)),					\
 	     "rJ" ((USItype)(al)),					\
@@ -65,8 +65,8 @@
 	"mulscc	%%g1,0,%%g1\n\t" 					\
 	"add	%%g1,%%g2,%0\n\t" 					\
 	"rd	%%y,%1\n"						\
-	   : "=r" ((USItype)(w1)),					\
-	     "=r" ((USItype)(w0))					\
+	   : "=r" (w1),							\
+	     "=r" (w0)							\
 	   : "%rI" ((USItype)(u)),					\
 	     "r" ((USItype)(v))						\
 	   : "%g1", "%g2", "cc")
@@ -98,8 +98,8 @@
 	   "sub	%1,%2,%1\n\t"						\
 	   "3:	xnor	%0,0,%0\n\t"					\
 	   "! End of inline udiv_qrnnd\n"				\
-	   : "=&r" ((USItype)(q)),					\
-	     "=&r" ((USItype)(r))					\
+	   : "=&r" (q),							\
+	     "=&r" (r)							\
 	   : "r" ((USItype)(d)),					\
 	     "1" ((USItype)(n1)),					\
 	     "0" ((USItype)(n0)) : "%g1", "cc")
diff --git a/arch/sparc/math-emu/sfp-util_64.h b/arch/sparc/math-emu/sfp-util_64.h
index 425d3cf..51320a8 100644
--- a/arch/sparc/math-emu/sfp-util_64.h
+++ b/arch/sparc/math-emu/sfp-util_64.h
@@ -17,8 +17,8 @@
   	   "bcs,a,pn %%xcc, 1f\n\t"		\
   	   "add %0, 1, %0\n"			\
   	   "1:"					\
-	   : "=r" ((UDItype)(sh)),		\
-	     "=&r" ((UDItype)(sl))		\
+	   : "=r" (sh),				\
+	     "=&r" (sl)				\
 	   : "r" ((UDItype)(ah)),		\
 	     "r" ((UDItype)(bh)),		\
 	     "r" ((UDItype)(al)),		\
@@ -31,8 +31,8 @@
   	   "bcs,a,pn %%xcc, 1f\n\t"		\
   	   "sub %0, 1, %0\n"			\
   	   "1:"					\
-	   : "=r" ((UDItype)(sh)),		\
-	     "=&r" ((UDItype)(sl))		\
+	   : "=r" (sh),				\
+	     "=&r" (sl)				\
 	   : "r" ((UDItype)(ah)),		\
 	     "r" ((UDItype)(bh)),		\
 	     "r" ((UDItype)(al)),		\
@@ -64,8 +64,8 @@
 		   "sllx %3,32,%3\n\t"			\
 		   "add %1,%3,%1\n\t"			\
 		   "add %5,%2,%0"			\
-	   : "=r" ((UDItype)(wh)),			\
-	     "=&r" ((UDItype)(wl)),			\
+	   : "=r" (wh),					\
+	     "=&r" (wl),				\
 	     "=&r" (tmp1), "=&r" (tmp2), "=&r" (tmp3), "=&r" (tmp4) \
 	   : "r" ((UDItype)(u)),			\
 	     "r" ((UDItype)(v))				\
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 59dbd46..908e8c1 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -26,14 +26,14 @@
 #include <asm/pgtable.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
+#include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
 
-int show_unhandled_signals = 1;
+#include "mm_32.h"
 
-static void unhandled_fault(unsigned long, struct task_struct *,
-		struct pt_regs *) __attribute__ ((noreturn));
+int show_unhandled_signals = 1;
 
 static void __noreturn unhandled_fault(unsigned long address,
 				       struct task_struct *tsk,
@@ -141,9 +141,6 @@
 	force_sig_info (sig, &info, current);
 }
 
-extern unsigned long safe_compute_effective_address(struct pt_regs *,
-						    unsigned int);
-
 static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault)
 {
 	unsigned int insn;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 4ced3fc..587cd05 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -32,6 +32,7 @@
 #include <asm/lsu.h>
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
+#include <asm/setup.h>
 
 int show_unhandled_signals = 1;
 
@@ -196,9 +197,6 @@
 	force_sig_info(sig, &info, current);
 }
 
-extern int handle_ldf_stq(u32, struct pt_regs *);
-extern int handle_ld_nf(u32, struct pt_regs *);
-
 static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
 {
 	if (!insn) {
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index db69870..eb82871 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -31,10 +31,13 @@
 #include <asm/pgtable.h>
 #include <asm/vaddrs.h>
 #include <asm/pgalloc.h>	/* bug in asm-generic/tlb.h: check_pgt_cache */
+#include <asm/setup.h>
 #include <asm/tlb.h>
 #include <asm/prom.h>
 #include <asm/leon.h>
 
+#include "mm_32.h"
+
 unsigned long *sparc_valid_addr_bitmap;
 EXPORT_SYMBOL(sparc_valid_addr_bitmap);
 
@@ -63,7 +66,6 @@
 }
 
 
-extern unsigned long cmdline_memory_size;
 unsigned long last_valid_pfn;
 
 unsigned long calc_highpages(void)
@@ -246,9 +248,6 @@
  * init routine based upon the Sun model type on the Sparc.
  *
  */
-extern void srmmu_paging_init(void);
-extern void device_scan(void);
-
 void __init paging_init(void)
 {
 	srmmu_paging_init();
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index ed3c969..16b58ff 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -47,6 +47,7 @@
 #include <asm/prom.h>
 #include <asm/mdesc.h>
 #include <asm/cpudata.h>
+#include <asm/setup.h>
 #include <asm/irq.h>
 
 #include "init_64.h"
@@ -794,11 +795,11 @@
 static struct node_mem_mask node_masks[MAX_NUMNODES];
 static int num_node_masks;
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-
 struct mdesc_mblock {
 	u64	base;
 	u64	size;
@@ -887,17 +888,21 @@
 
 static void init_node_masks_nonnuma(void)
 {
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	int i;
+#endif
 
 	numadbg("Initializing tables for non-numa.\n");
 
 	node_masks[0].mask = node_masks[0].val = 0;
 	num_node_masks = 1;
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	for (i = 0; i < NR_CPUS; i++)
 		numa_cpu_lookup_table[i] = 0;
 
 	cpumask_setall(&numa_cpumask_lookup_table[0]);
+#endif
 }
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 5d3782de..0668b36 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -21,7 +21,7 @@
 extern unsigned long sparc64_kern_pri_context;
 extern unsigned long sparc64_kern_pri_nuc_bits;
 extern unsigned long sparc64_kern_sec_context;
-extern void mmu_info(struct seq_file *m);
+void mmu_info(struct seq_file *m);
 
 struct linux_prom_translation {
 	unsigned long virt;
@@ -36,7 +36,7 @@
 /* Exported for SMP bootup purposes. */
 extern unsigned long kern_locked_tte_data;
 
-extern void prom_world(int enter);
+void prom_world(int enter);
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #define VMEMMAP_CHUNK_SHIFT	22
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index eb99862..f311bf2 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -25,6 +25,8 @@
 #include <asm/dma.h>
 #include <asm/oplib.h>
 
+#include "mm_32.h"
+
 /* #define IOUNIT_DEBUG */
 #ifdef IOUNIT_DEBUG
 #define IOD(x) printk(x)
@@ -38,7 +40,8 @@
 static void __init iounit_iommu_init(struct platform_device *op)
 {
 	struct iounit_struct *iounit;
-	iopte_t *xpt, *xptend;
+	iopte_t __iomem *xpt;
+	iopte_t __iomem *xptend;
 
 	iounit = kzalloc(sizeof(struct iounit_struct), GFP_ATOMIC);
 	if (!iounit) {
@@ -62,10 +65,10 @@
 	op->dev.archdata.iommu = iounit;
 	iounit->page_table = xpt;
 	spin_lock_init(&iounit->lock);
-	
-	for (xptend = iounit->page_table + (16 * PAGE_SIZE) / sizeof(iopte_t);
-	     xpt < xptend;)
-	     	iopte_val(*xpt++) = 0;
+
+	xptend = iounit->page_table + (16 * PAGE_SIZE) / sizeof(iopte_t);
+	for (; xpt < xptend; xpt++)
+		sbus_writel(0, xpt);
 }
 
 static int __init iounit_init(void)
@@ -130,7 +133,7 @@
 	vaddr = IOUNIT_DMA_BASE + (scan << PAGE_SHIFT) + (vaddr & ~PAGE_MASK);
 	for (k = 0; k < npages; k++, iopte = __iopte(iopte_val(iopte) + 0x100), scan++) {
 		set_bit(scan, iounit->bmap);
-		iounit->page_table[scan] = iopte;
+		sbus_writel(iopte, &iounit->page_table[scan]);
 	}
 	IOD(("%08lx\n", vaddr));
 	return vaddr;
@@ -202,7 +205,7 @@
 	struct iounit_struct *iounit = dev->archdata.iommu;
 	unsigned long page, end;
 	pgprot_t dvma_prot;
-	iopte_t *iopte;
+	iopte_t __iomem *iopte;
 
 	*pba = addr;
 
@@ -224,8 +227,8 @@
 			
 			i = ((addr - IOUNIT_DMA_BASE) >> PAGE_SHIFT);
 
-			iopte = (iopte_t *)(iounit->page_table + i);
-			*iopte = MKIOPTE(__pa(page));
+			iopte = iounit->page_table + i;
+			sbus_writel(MKIOPTE(__pa(page)), iopte);
 		}
 		addr += PAGE_SIZE;
 		va += PAGE_SIZE;
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 28f96f2..491511d 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -27,6 +27,8 @@
 #include <asm/iommu.h>
 #include <asm/dma.h>
 
+#include "mm_32.h"
+
 /*
  * This can be sized dynamically, but we will do this
  * only when we have a guidance about actual I/O pressures.
@@ -37,9 +39,6 @@
 #define IOMMU_NPTES	(IOMMU_WINSIZE/PAGE_SIZE)	/* 64K PTEs, 256KB */
 #define IOMMU_ORDER	6				/* 4096 * (1<<6) */
 
-/* srmmu.c */
-extern int viking_mxcc_present;
-extern int flush_page_for_dma_global;
 static int viking_flush;
 /* viking.S */
 extern void viking_flush_page(unsigned long page);
@@ -59,6 +58,8 @@
 	struct iommu_struct *iommu;
 	unsigned int impl, vers;
 	unsigned long *bitmap;
+	unsigned long control;
+	unsigned long base;
 	unsigned long tmp;
 
 	iommu = kmalloc(sizeof(struct iommu_struct), GFP_KERNEL);
@@ -73,12 +74,14 @@
 		prom_printf("Cannot map IOMMU registers\n");
 		prom_halt();
 	}
-	impl = (iommu->regs->control & IOMMU_CTRL_IMPL) >> 28;
-	vers = (iommu->regs->control & IOMMU_CTRL_VERS) >> 24;
-	tmp = iommu->regs->control;
-	tmp &= ~(IOMMU_CTRL_RNGE);
-	tmp |= (IOMMU_RNGE_256MB | IOMMU_CTRL_ENAB);
-	iommu->regs->control = tmp;
+
+	control = sbus_readl(&iommu->regs->control);
+	impl = (control & IOMMU_CTRL_IMPL) >> 28;
+	vers = (control & IOMMU_CTRL_VERS) >> 24;
+	control &= ~(IOMMU_CTRL_RNGE);
+	control |= (IOMMU_RNGE_256MB | IOMMU_CTRL_ENAB);
+	sbus_writel(control, &iommu->regs->control);
+
 	iommu_invalidate(iommu->regs);
 	iommu->start = IOMMU_START;
 	iommu->end = 0xffffffff;
@@ -100,7 +103,9 @@
 	memset(iommu->page_table, 0, IOMMU_NPTES*sizeof(iopte_t));
 	flush_cache_all();
 	flush_tlb_all();
-	iommu->regs->base = __pa((unsigned long) iommu->page_table) >> 4;
+
+	base = __pa((unsigned long)iommu->page_table) >> 4;
+	sbus_writel(base, &iommu->regs->base);
 	iommu_invalidate(iommu->regs);
 
 	bitmap = kmalloc(IOMMU_NPTES>>3, GFP_KERNEL);
diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c
index 5bed085..3b17b6f 100644
--- a/arch/sparc/mm/leon_mm.c
+++ b/arch/sparc/mm/leon_mm.c
@@ -15,10 +15,10 @@
 #include <asm/leon.h>
 #include <asm/tlbflush.h>
 
-#include "srmmu.h"
+#include "mm_32.h"
 
 int leon_flush_during_switch = 1;
-int srmmu_swprobe_trace;
+static int srmmu_swprobe_trace;
 
 static inline unsigned long leon_get_ctable_ptr(void)
 {
diff --git a/arch/sparc/mm/mm_32.h b/arch/sparc/mm/mm_32.h
new file mode 100644
index 0000000..a6c27ca
--- /dev/null
+++ b/arch/sparc/mm/mm_32.h
@@ -0,0 +1,24 @@
+/* fault_32.c - visible as they are called from assembler */
+asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
+                            unsigned long address);
+asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
+                               unsigned long address);
+
+void window_overflow_fault(void);
+void window_underflow_fault(unsigned long sp);
+void window_ret_fault(struct pt_regs *regs);
+
+/* srmmu.c */
+extern char *srmmu_name;
+extern int viking_mxcc_present;
+extern int flush_page_for_dma_global;
+
+extern void (*poke_srmmu)(void);
+
+void __init srmmu_paging_init(void);
+
+/* iommu.c */
+void ld_mmu_iommu(void);
+
+/* io-unit.c */
+void ld_mmu_iounit(void);
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index cfbe53c..be65f03 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -49,7 +49,7 @@
 #include <asm/mxcc.h>
 #include <asm/ross.h>
 
-#include "srmmu.h"
+#include "mm_32.h"
 
 enum mbus_module srmmu_modtype;
 static unsigned int hwbug_bitmask;
@@ -100,7 +100,6 @@
 #define SRMMU_NOCACHE_ALIGN_MAX (sizeof(ctxd_t)*SRMMU_MAX_CONTEXTS)
 
 void *srmmu_nocache_pool;
-void *srmmu_nocache_bitmap;
 static struct bit_map srmmu_nocache_map;
 
 static inline int srmmu_pmd_none(pmd_t pmd)
@@ -173,7 +172,7 @@
 		printk(KERN_ERR "srmmu: out of nocache %d: %d/%d\n",
 		       size, (int) srmmu_nocache_size,
 		       srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
-		return 0;
+		return NULL;
 	}
 
 	addr = SRMMU_NOCACHE_VADDR + (offset << SRMMU_NOCACHE_BITMAP_SHIFT);
@@ -269,6 +268,7 @@
 
 static void __init srmmu_nocache_init(void)
 {
+	void *srmmu_nocache_bitmap;
 	unsigned int bitmap_bits;
 	pgd_t *pgd;
 	pmd_t *pmd;
@@ -728,7 +728,7 @@
 				     "=r" (retval) :
 				     "r" (vaddr | 0x400), "i" (ASI_M_FLUSH_PROBE));
 	} else {
-		retval = leon_swprobe(vaddr, 0);
+		retval = leon_swprobe(vaddr, NULL);
 	}
 	return retval;
 }
@@ -865,8 +865,6 @@
 
 void (*poke_srmmu)(void) = NULL;
 
-extern unsigned long bootmem_init(unsigned long *pages_avail);
-
 void __init srmmu_paging_init(void)
 {
 	int i;
@@ -1771,9 +1769,6 @@
 /* Load up routines and constants for sun4m and sun4d mmu */
 void __init load_mmu(void)
 {
-	extern void ld_mmu_iommu(void);
-	extern void ld_mmu_iounit(void);
-
 	/* Functions */
 	get_srmmu_type();
 
diff --git a/arch/sparc/mm/srmmu.h b/arch/sparc/mm/srmmu.h
deleted file mode 100644
index 5703274..0000000
--- a/arch/sparc/mm/srmmu.h
+++ /dev/null
@@ -1,4 +0,0 @@
-/* srmmu.c */
-extern char *srmmu_name;
-
-extern void (*poke_srmmu)(void);
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index fe19b81..a065766 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -9,6 +9,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
+#include <asm/setup.h>
 #include <asm/tsb.h>
 #include <asm/tlb.h>
 #include <asm/oplib.h>
diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c
index f178b9d..53a696d 100644
--- a/arch/sparc/prom/misc_64.c
+++ b/arch/sparc/prom/misc_64.c
@@ -81,11 +81,6 @@
 }
 EXPORT_SYMBOL(prom_feval);
 
-#ifdef CONFIG_SMP
-extern void smp_capture(void);
-extern void smp_release(void);
-#endif
-
 /* Drop into the prom, with the chance to continue with the 'go'
  * prom command.
  */
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index aafad6f..928237a 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -51,9 +51,6 @@
 config ARCH_HAS_ILOG2_U64
 	bool
 
-config ARCH_HAS_CPUFREQ
-	bool
-
 config GENERIC_HWEIGHT
 	def_bool y
 
@@ -87,7 +84,6 @@
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
 	select ARCH_REQUIRE_GPIOLIB
-	select ARCH_HAS_CPUFREQ
 
 # CONFIGs for ARCH_PUV3
 
@@ -198,9 +194,7 @@
 
 source "kernel/power/Kconfig"
 
-if ARCH_HAS_CPUFREQ
 source "drivers/cpufreq/Kconfig"
-endif
 
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y if !ARCH_FPGA
diff --git a/arch/unicore32/include/asm/io.h b/arch/unicore32/include/asm/io.h
index 39decb6..cb1d8fd 100644
--- a/arch/unicore32/include/asm/io.h
+++ b/arch/unicore32/include/asm/io.h
@@ -39,10 +39,37 @@
 #define ioremap_nocache(cookie, size)	__uc32_ioremap(cookie, size)
 #define iounmap(cookie)			__uc32_iounmap(cookie)
 
+#define readb_relaxed readb
+#define readw_relaxed readw
+#define readl_relaxed readl
+
 #define HAVE_ARCH_PIO_SIZE
 #define PIO_OFFSET		(unsigned int)(PCI_IOBASE)
 #define PIO_MASK		(unsigned int)(IO_SPACE_LIMIT)
 #define PIO_RESERVED		(PIO_OFFSET + PIO_MASK + 1)
 
+#ifdef CONFIG_STRICT_DEVMEM
+
+#include <linux/ioport.h>
+#include <linux/mm.h>
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain
+ * address is valid. The argument is a physical page number.
+ * We mimic x86 here by disallowing access to system RAM as well as
+ * device-exclusive MMIO regions. This effectively disable read()/write()
+ * on /dev/mem.
+ */
+static inline int devmem_is_allowed(unsigned long pfn)
+{
+	if (iomem_is_exclusive(pfn << PAGE_SHIFT))
+		return 0;
+	if (!page_is_ram(pfn))
+		return 1;
+	return 0;
+}
+
+#endif /* CONFIG_STRICT_DEVMEM */
+
 #endif	/* __KERNEL__ */
 #endif	/* __UNICORE_IO_H__ */
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
index 233c258..ed6f7d0 100644
--- a/arch/unicore32/include/asm/pgtable.h
+++ b/arch/unicore32/include/asm/pgtable.h
@@ -87,16 +87,16 @@
 
 #define PAGE_NONE		pgprot_user
 #define PAGE_SHARED		__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_WRITE)
+								| PTE_WRITE))
 #define PAGE_SHARED_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
 								| PTE_WRITE \
-								| PTE_EXEC)
+								| PTE_EXEC))
 #define PAGE_COPY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
 #define PAGE_COPY_EXEC		__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_EXEC)
-#define PAGE_READONLY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
+								| PTE_EXEC))
+#define PAGE_READONLY		__pgprot(pgprot_val(pgprot_user | PTE_READ))
 #define PAGE_READONLY_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_EXEC)
+								| PTE_EXEC))
 #define PAGE_KERNEL		pgprot_kernel
 #define PAGE_KERNEL_EXEC	__pgprot(pgprot_val(pgprot_kernel | PTE_EXEC))
 
diff --git a/arch/unicore32/include/asm/ptrace.h b/arch/unicore32/include/asm/ptrace.h
index 9df53d9..02bf5a4 100644
--- a/arch/unicore32/include/asm/ptrace.h
+++ b/arch/unicore32/include/asm/ptrace.h
@@ -55,6 +55,7 @@
 
 #define instruction_pointer(regs)	((regs)->UCreg_pc)
 #define user_stack_pointer(regs)	((regs)->UCreg_sp)
+#define profile_pc(regs)		instruction_pointer(regs)
 
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/unicore32/kernel/clock.c b/arch/unicore32/kernel/clock.c
index 18d4563..b1ca775 100644
--- a/arch/unicore32/kernel/clock.c
+++ b/arch/unicore32/kernel/clock.c
@@ -179,7 +179,7 @@
 	}
 #ifdef CONFIG_CPU_FREQ
 	if (clk == &clk_mclk_clk) {
-		u32 pll_rate, divstatus = PM_DIVSTATUS;
+		u32 pll_rate, divstatus = readl(PM_DIVSTATUS);
 		int ret, i;
 
 		/* lookup mclk_clk_table */
@@ -201,10 +201,10 @@
 				/ (((divstatus & 0x0000f000) >> 12) + 1);
 
 		/* set pll sys cfg reg. */
-		PM_PLLSYSCFG = pll_rate;
+		writel(pll_rate, PM_PLLSYSCFG);
 
-		PM_PMCR = PM_PMCR_CFBSYS;
-		while ((PM_PLLDFCDONE & PM_PLLDFCDONE_SYSDFC)
+		writel(PM_PMCR_CFBSYS, PM_PMCR);
+		while ((readl(PM_PLLDFCDONE) & PM_PLLDFCDONE_SYSDFC)
 				!= PM_PLLDFCDONE_SYSDFC)
 			udelay(100);
 			/* about 1ms */
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index d285d71..0323528 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -23,41 +23,15 @@
 
 #include "ksyms.h"
 
+EXPORT_SYMBOL(find_first_bit);
+EXPORT_SYMBOL(find_first_zero_bit);
 EXPORT_SYMBOL(find_next_zero_bit);
 EXPORT_SYMBOL(find_next_bit);
 
-EXPORT_SYMBOL(__backtrace);
-
 	/* platform dependent support */
 EXPORT_SYMBOL(__udelay);
 EXPORT_SYMBOL(__const_udelay);
 
-	/* networking */
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_from_user);
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-EXPORT_SYMBOL(__csum_ipv6_magic);
-
-	/* io */
-#ifndef __raw_readsb
-EXPORT_SYMBOL(__raw_readsb);
-#endif
-#ifndef __raw_readsw
-EXPORT_SYMBOL(__raw_readsw);
-#endif
-#ifndef __raw_readsl
-EXPORT_SYMBOL(__raw_readsl);
-#endif
-#ifndef __raw_writesb
-EXPORT_SYMBOL(__raw_writesb);
-#endif
-#ifndef __raw_writesw
-EXPORT_SYMBOL(__raw_writesw);
-#endif
-#ifndef __raw_writesl
-EXPORT_SYMBOL(__raw_writesl);
-#endif
-
 	/* string / mem functions */
 EXPORT_SYMBOL(strchr);
 EXPORT_SYMBOL(strrchr);
@@ -76,23 +50,12 @@
 EXPORT_SYMBOL(__copy_to_user);
 EXPORT_SYMBOL(__clear_user);
 
-EXPORT_SYMBOL(__get_user_1);
-EXPORT_SYMBOL(__get_user_2);
-EXPORT_SYMBOL(__get_user_4);
-
-EXPORT_SYMBOL(__put_user_1);
-EXPORT_SYMBOL(__put_user_2);
-EXPORT_SYMBOL(__put_user_4);
-EXPORT_SYMBOL(__put_user_8);
-
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
 EXPORT_SYMBOL(__divsi3);
 EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__muldi3);
 EXPORT_SYMBOL(__ucmpdi2);
 EXPORT_SYMBOL(__udivsi3);
 EXPORT_SYMBOL(__umodsi3);
-EXPORT_SYMBOL(__bswapsi2);
 
diff --git a/arch/unicore32/kernel/ksyms.h b/arch/unicore32/kernel/ksyms.h
index 185cdc7..31472ad 100644
--- a/arch/unicore32/kernel/ksyms.h
+++ b/arch/unicore32/kernel/ksyms.h
@@ -8,8 +8,6 @@
 extern void __divsi3(void);
 extern void __lshrdi3(void);
 extern void __modsi3(void);
-extern void __muldi3(void);
 extern void __ucmpdi2(void);
 extern void __udivsi3(void);
 extern void __umodsi3(void);
-extern void __bswapsi2(void);
diff --git a/arch/unicore32/kernel/module.c b/arch/unicore32/kernel/module.c
index 16bd149..dc41f6d 100644
--- a/arch/unicore32/kernel/module.c
+++ b/arch/unicore32/kernel/module.c
@@ -24,14 +24,9 @@
 
 void *module_alloc(unsigned long size)
 {
-	struct vm_struct *area;
-
-	size = PAGE_ALIGN(size);
-	area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END);
-	if (!area)
-		return NULL;
-
-	return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL_EXEC);
+	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+				GFP_KERNEL, PAGE_KERNEL_EXEC, NUMA_NO_NODE,
+				__builtin_return_address(0));
 }
 
 int
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 778ebba..b008e99 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -60,6 +60,7 @@
  * Function pointers to optional machine specific functions
  */
 void (*pm_power_off)(void) = NULL;
+EXPORT_SYMBOL(pm_power_off);
 
 void machine_power_off(void)
 {
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
index 87adbf5..3fa317f 100644
--- a/arch/unicore32/kernel/setup.c
+++ b/arch/unicore32/kernel/setup.c
@@ -53,6 +53,10 @@
 
 static struct stack stacks[NR_CPUS];
 
+#ifdef CONFIG_VGA_CONSOLE
+struct screen_info screen_info;
+#endif
+
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
 
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index de7dc5f..24e8360 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/unaligned.h>
 
diff --git a/arch/unicore32/mm/proc-syms.c b/arch/unicore32/mm/proc-syms.c
index f30071e..21c00fc 100644
--- a/arch/unicore32/mm/proc-syms.c
+++ b/arch/unicore32/mm/proc-syms.c
@@ -19,5 +19,7 @@
 EXPORT_SYMBOL(cpu_dcache_clean_area);
 EXPORT_SYMBOL(cpu_set_pte);
 
+EXPORT_SYMBOL(__cpuc_coherent_kern_range);
+
 EXPORT_SYMBOL(__cpuc_dma_flush_range);
 EXPORT_SYMBOL(__cpuc_dma_clean_range);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fcefdda..a8f749e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1672,7 +1672,6 @@
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image"
 	depends on RELOCATABLE
-	depends on !HIBERNATION
 	default n
 	---help---
 	   Randomizes the physical and virtual address at which the
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 4dbf967..fc6091a 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -289,10 +289,17 @@
 	unsigned long choice = (unsigned long)output;
 	unsigned long random;
 
-	if (cmdline_find_option_bool("nokaslr")) {
-		debug_putstr("KASLR disabled...\n");
+#ifdef CONFIG_HIBERNATION
+	if (!cmdline_find_option_bool("kaslr")) {
+		debug_putstr("KASLR disabled by default...\n");
 		goto out;
 	}
+#else
+	if (cmdline_find_option_bool("nokaslr")) {
+		debug_putstr("KASLR disabled by cmdline...\n");
+		goto out;
+	}
+#endif
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 9769df0..3c0809a 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -9,18 +9,9 @@
 VDSO32-$(CONFIG_X86_32)		:= y
 VDSO32-$(CONFIG_COMPAT)		:= y
 
-vdso-install-$(VDSO64-y)	+= vdso.so
-vdso-install-$(VDSOX32-y)	+= vdsox32.so
-vdso-install-$(VDSO32-y)	+= $(vdso32-images)
-
-
 # files to link into the vdso
-vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
-
-vobjs-$(VDSOX32-y) += $(vobjx32s-compat)
-
-# Filter out x32 objects.
-vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y))
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vdso-fakesections.o
+vobjs-nox32 := vdso-fakesections.o
 
 # files to link into kernel
 obj-y				+= vma.o
@@ -34,7 +25,7 @@
 
 obj-$(VDSO32-y)			+= vdso32-setup.o
 
-vobjs := $(foreach F,$(vobj64s),$(obj)/$F)
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
@@ -104,7 +95,13 @@
 			   -Wl,-z,max-page-size=4096 \
 			   -Wl,-z,common-page-size=4096
 
-vobjx32s-y := $(vobj64s:.o=-x32.o)
+# 64-bit objects to re-brand as x32
+vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
+
+# x32-rebranded versions
+vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o)
+
+# same thing, but in the output directory
 vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
 
 # Convert 64bit object file to x32 for x32 vDSO.
@@ -176,15 +173,20 @@
 GCOV_PROFILE := n
 
 #
-# Install the unstripped copy of vdso*.so listed in $(vdso-install-y).
+# Install the unstripped copies of vdso*.so.
 #
-quiet_cmd_vdso_install = INSTALL $@
-      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
-$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE
+quiet_cmd_vdso_install = INSTALL $(@:install_%=%)
+      cmd_vdso_install = cp $< $(MODLIB)/vdso/$(@:install_%=%)
+
+vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%)
+
+$(MODLIB)/vdso: FORCE
 	@mkdir -p $(MODLIB)/vdso
+
+$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
 	$(call cmd,vdso_install)
 
-PHONY += vdso_install $(vdso-install-y)
-vdso_install: $(vdso-install-y)
+PHONY += vdso_install $(vdso_img_insttargets)
+vdso_install: $(vdso_img_insttargets) FORCE
 
 clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80*
diff --git a/arch/x86/vdso/vdso-fakesections.c b/arch/x86/vdso/vdso-fakesections.c
new file mode 100644
index 0000000..cb8a8d7
--- /dev/null
+++ b/arch/x86/vdso/vdso-fakesections.c
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2014 Andy Lutomirski
+ * Subject to the GNU Public License, v.2
+ *
+ * Hack to keep broken Go programs working.
+ *
+ * The Go runtime had a couple of bugs: it would read the section table to try
+ * to figure out how many dynamic symbols there were (it shouldn't have looked
+ * at the section table at all) and, if there were no SHT_SYNDYM section table
+ * entry, it would use an uninitialized value for the number of symbols.  As a
+ * workaround, we supply a minimal section table.  vdso2c will adjust the
+ * in-memory image so that "vdso_fake_sections" becomes the section table.
+ *
+ * The bug was introduced by:
+ * https://code.google.com/p/go/source/detail?r=56ea40aac72b (2012-08-31)
+ * and is being addressed in the Go runtime in this issue:
+ * https://code.google.com/p/go/issues/detail?id=8197
+ */
+
+#ifndef __x86_64__
+#error This hack is specific to the 64-bit vDSO
+#endif
+
+#include <linux/elf.h>
+
+extern const __visible struct elf64_shdr vdso_fake_sections[];
+const __visible struct elf64_shdr vdso_fake_sections[] = {
+	{
+		.sh_type = SHT_DYNSYM,
+		.sh_entsize = sizeof(Elf64_Sym),
+	}
+};
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c
index 450ac6e..7a6bf50 100644
--- a/arch/x86/vdso/vdso2c.c
+++ b/arch/x86/vdso/vdso2c.c
@@ -54,7 +54,7 @@
 }
 
 /*
- * Evil macros to do a little-endian read.
+ * Evil macros for little-endian reads and writes
  */
 #define GLE(x, bits, ifnot)						\
 	__builtin_choose_expr(						\
@@ -62,11 +62,24 @@
 		(__typeof__(*(x)))get_unaligned_le##bits(x), ifnot)
 
 extern void bad_get_le(void);
-#define LAST_LE(x)							\
+#define LAST_GLE(x)							\
 	__builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le())
 
 #define GET_LE(x)							\
-	GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_LE(x))))
+	GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x))))
+
+#define PLE(x, val, bits, ifnot)					\
+	__builtin_choose_expr(						\
+		(sizeof(*(x)) == bits/8),				\
+		put_unaligned_le##bits((val), (x)), ifnot)
+
+extern void bad_put_le(void);
+#define LAST_PLE(x, val)						\
+	__builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le())
+
+#define PUT_LE(x, val)					\
+	PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val))))
+
 
 #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
 
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h
index 8a07463..c6eefaf 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/vdso/vdso2c.h
@@ -18,6 +18,8 @@
 	const char *secstrings;
 	uint64_t syms[NSYMS] = {};
 
+	uint64_t fake_sections_value = 0, fake_sections_size = 0;
+
 	Elf_Phdr *pt = (Elf_Phdr *)(addr + GET_LE(&hdr->e_phoff));
 
 	/* Walk the segment table. */
@@ -84,6 +86,7 @@
 			GET_LE(&symtab_hdr->sh_entsize) * i;
 		const char *name = addr + GET_LE(&strtab_hdr->sh_offset) +
 			GET_LE(&sym->st_name);
+
 		for (k = 0; k < NSYMS; k++) {
 			if (!strcmp(name, required_syms[k])) {
 				if (syms[k]) {
@@ -93,6 +96,13 @@
 				syms[k] = GET_LE(&sym->st_value);
 			}
 		}
+
+		if (!strcmp(name, "vdso_fake_sections")) {
+			if (fake_sections_value)
+				fail("duplicate vdso_fake_sections\n");
+			fake_sections_value = GET_LE(&sym->st_value);
+			fake_sections_size = GET_LE(&sym->st_size);
+		}
 	}
 
 	/* Validate mapping addresses. */
@@ -112,11 +122,14 @@
 	if (syms[sym_end_mapping] % 4096)
 		fail("end_mapping must be a multiple of 4096\n");
 
-	/* Remove sections. */
-	hdr->e_shoff = 0;
-	hdr->e_shentsize = 0;
-	hdr->e_shnum = 0;
-	hdr->e_shstrndx = htole16(SHN_UNDEF);
+	/* Remove sections or use fakes */
+	if (fake_sections_size % sizeof(Elf_Shdr))
+		fail("vdso_fake_sections size is not a multiple of %ld\n",
+		     (long)sizeof(Elf_Shdr));
+	PUT_LE(&hdr->e_shoff, fake_sections_value);
+	PUT_LE(&hdr->e_shentsize, fake_sections_value ? sizeof(Elf_Shdr) : 0);
+	PUT_LE(&hdr->e_shnum, fake_sections_size / sizeof(Elf_Shdr));
+	PUT_LE(&hdr->e_shstrndx, SHN_UNDEF);
 
 	if (!name) {
 		fwrite(addr, load_size, 1, outfile);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f17b292..ffb101e 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1537,7 +1537,10 @@
 	if (!xen_pvh_domain())
 		pv_cpu_ops = xen_cpu_ops;
 
-	x86_init.resources.memory_setup = xen_memory_setup;
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
+	else
+		x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 821a11a..2e555163 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -27,7 +27,6 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
-#include "mmu.h"
 #include "xen-ops.h"
 #include "vdso.h"
 
@@ -82,9 +81,6 @@
 
 	memblock_reserve(start, size);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
 	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
@@ -107,7 +103,6 @@
 		.domid        = DOMID_SELF
 	};
 	unsigned long len = 0;
-	int xlated_phys = xen_feature(XENFEAT_auto_translated_physmap);
 	unsigned long pfn;
 	int ret;
 
@@ -121,7 +116,7 @@
 				continue;
 			frame = mfn;
 		} else {
-			if (!xlated_phys && mfn != INVALID_P2M_ENTRY)
+			if (mfn != INVALID_P2M_ENTRY)
 				continue;
 			frame = pfn;
 		}
@@ -159,13 +154,6 @@
 static unsigned long __init xen_release_chunk(unsigned long start,
 					      unsigned long end)
 {
-	/*
-	 * Xen already ballooned out the E820 non RAM regions for us
-	 * and set them up properly in EPT.
-	 */
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return end - start;
-
 	return xen_do_chunk(start, end, true);
 }
 
@@ -234,13 +222,7 @@
 	 * (except for the ISA region which must be 1:1 mapped) to
 	 * release the refcounts (in Xen) on the original frames.
 	 */
-
-	/*
-	 * PVH E820 matches the hypervisor's P2M which means we need to
-	 * account for the proper values of *release and *identity.
-	 */
-	for (pfn = start_pfn; !xen_feature(XENFEAT_auto_translated_physmap) &&
-	     pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
 		pte_t pte = __pte_ma(0);
 
 		if (pfn < PFN_UP(ISA_END_ADDRESS))
@@ -518,6 +500,35 @@
 }
 
 /*
+ * Machine specific memory setup for auto-translated guests.
+ */
+char * __init xen_auto_xlated_memory_setup(void)
+{
+	static struct e820entry map[E820MAX] __initdata;
+
+	struct xen_memory_map memmap;
+	int i;
+	int rc;
+
+	memmap.nr_entries = E820MAX;
+	set_xen_guest_handle(memmap.buffer, map);
+
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc < 0)
+		panic("No memory map (%d)\n", rc);
+
+	sanitize_e820_map(map, ARRAY_SIZE(map), &memmap.nr_entries);
+
+	for (i = 0; i < memmap.nr_entries; i++)
+		e820_add_region(map[i].addr, map[i].size, map[i].type);
+
+	memblock_reserve(__pa(xen_start_info->mfn_list),
+			 xen_start_info->pt_base - xen_start_info->mfn_list);
+
+	return "Xen";
+}
+
+/*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
  * can have un-truncated segments, so wrapping around is allowed.
@@ -590,13 +601,7 @@
 	}
 #endif /* CONFIG_X86_64 */
 }
-void xen_enable_nmi(void)
-{
-#ifdef CONFIG_X86_64
-	if (register_callback(CALLBACKTYPE_nmi, (char *)nmi))
-		BUG();
-#endif
-}
+
 void __init xen_pvmmu_arch_setup(void)
 {
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -611,7 +616,6 @@
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-	xen_enable_nmi();
 }
 
 /* This function is not called for HVM domains */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c834d4b..97d8765 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -36,6 +36,7 @@
 void xen_set_pat(u64);
 
 char * __init xen_memory_setup(void);
+char * xen_auto_xlated_memory_setup(void);
 void __init xen_arch_setup(void);
 void xen_enable_sysenter(void);
 void xen_enable_syscall(void);
diff --git a/block/blk-core.c b/block/blk-core.c
index 9aca8c7..6f8dba1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -43,6 +43,7 @@
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 
 DEFINE_IDA(blk_queue_ida);
@@ -3311,8 +3312,7 @@
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
-					    WQ_MEM_RECLAIM | WQ_HIGHPRI |
-					    WQ_POWER_EFFICIENT, 0);
+					    WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 8ffee4b..3cb5e9e 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -422,44 +422,6 @@
 }
 
 /**
- * blk_abort_flushes - @q is being aborted, abort flush requests
- * @q: request_queue being aborted
- *
- * To be called from elv_abort_queue().  @q is being aborted.  Prepare all
- * FLUSH/FUA requests for abortion.
- *
- * CONTEXT:
- * spin_lock_irq(q->queue_lock)
- */
-void blk_abort_flushes(struct request_queue *q)
-{
-	struct request *rq, *n;
-	int i;
-
-	/*
-	 * Requests in flight for data are already owned by the dispatch
-	 * queue or the device driver.  Just restore for normal completion.
-	 */
-	list_for_each_entry_safe(rq, n, &q->flush_data_in_flight, flush.list) {
-		list_del_init(&rq->flush.list);
-		blk_flush_restore_request(rq);
-	}
-
-	/*
-	 * We need to give away requests on flush queues.  Restore for
-	 * normal completion and put them on the dispatch queue.
-	 */
-	for (i = 0; i < ARRAY_SIZE(q->flush_queue); i++) {
-		list_for_each_entry_safe(rq, n, &q->flush_queue[i],
-					 flush.list) {
-			list_del_init(&rq->flush.list);
-			blk_flush_restore_request(rq);
-			list_add_tail(&rq->queuelist, &q->queue_head);
-		}
-	}
-}
-
-/**
  * blkdev_issue_flush - queue a flush
  * @bdev:	blockdev to issue flush for
  * @gfp_mask:	memory allocation flags (for bio_alloc)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 1aab39f..c1b9242 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -43,9 +43,16 @@
 	return bt_has_free_tags(&tags->bitmap_tags);
 }
 
-static inline void bt_index_inc(unsigned int *index)
+static inline int bt_index_inc(int index)
 {
-	*index = (*index + 1) & (BT_WAIT_QUEUES - 1);
+	return (index + 1) & (BT_WAIT_QUEUES - 1);
+}
+
+static inline void bt_index_atomic_inc(atomic_t *index)
+{
+	int old = atomic_read(index);
+	int new = bt_index_inc(old);
+	atomic_cmpxchg(index, old, new);
 }
 
 /*
@@ -69,14 +76,14 @@
 	int i, wake_index;
 
 	bt = &tags->bitmap_tags;
-	wake_index = bt->wake_index;
+	wake_index = atomic_read(&bt->wake_index);
 	for (i = 0; i < BT_WAIT_QUEUES; i++) {
 		struct bt_wait_state *bs = &bt->bs[wake_index];
 
 		if (waitqueue_active(&bs->wait))
 			wake_up(&bs->wait);
 
-		bt_index_inc(&wake_index);
+		wake_index = bt_index_inc(wake_index);
 	}
 }
 
@@ -212,12 +219,14 @@
 					 struct blk_mq_hw_ctx *hctx)
 {
 	struct bt_wait_state *bs;
+	int wait_index;
 
 	if (!hctx)
 		return &bt->bs[0];
 
-	bs = &bt->bs[hctx->wait_index];
-	bt_index_inc(&hctx->wait_index);
+	wait_index = atomic_read(&hctx->wait_index);
+	bs = &bt->bs[wait_index];
+	bt_index_atomic_inc(&hctx->wait_index);
 	return bs;
 }
 
@@ -239,18 +248,12 @@
 
 	bs = bt_wait_ptr(bt, hctx);
 	do {
-		bool was_empty;
-
-		was_empty = list_empty(&wait.task_list);
 		prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
 
 		tag = __bt_get(hctx, bt, last_tag);
 		if (tag != -1)
 			break;
 
-		if (was_empty)
-			atomic_set(&bs->wait_cnt, bt->wake_cnt);
-
 		blk_mq_put_ctx(data->ctx);
 
 		io_schedule();
@@ -313,18 +316,19 @@
 {
 	int i, wake_index;
 
-	wake_index = bt->wake_index;
+	wake_index = atomic_read(&bt->wake_index);
 	for (i = 0; i < BT_WAIT_QUEUES; i++) {
 		struct bt_wait_state *bs = &bt->bs[wake_index];
 
 		if (waitqueue_active(&bs->wait)) {
-			if (wake_index != bt->wake_index)
-				bt->wake_index = wake_index;
+			int o = atomic_read(&bt->wake_index);
+			if (wake_index != o)
+				atomic_cmpxchg(&bt->wake_index, o, wake_index);
 
 			return bs;
 		}
 
-		bt_index_inc(&wake_index);
+		wake_index = bt_index_inc(wake_index);
 	}
 
 	return NULL;
@@ -334,6 +338,7 @@
 {
 	const int index = TAG_TO_INDEX(bt, tag);
 	struct bt_wait_state *bs;
+	int wait_cnt;
 
 	/*
 	 * The unlock memory barrier need to order access to req in free
@@ -342,10 +347,19 @@
 	clear_bit_unlock(TAG_TO_BIT(bt, tag), &bt->map[index].word);
 
 	bs = bt_wake_ptr(bt);
-	if (bs && atomic_dec_and_test(&bs->wait_cnt)) {
-		atomic_set(&bs->wait_cnt, bt->wake_cnt);
-		bt_index_inc(&bt->wake_index);
+	if (!bs)
+		return;
+
+	wait_cnt = atomic_dec_return(&bs->wait_cnt);
+	if (wait_cnt == 0) {
+wake:
+		atomic_add(bt->wake_cnt, &bs->wait_cnt);
+		bt_index_atomic_inc(&bt->wake_index);
 		wake_up(&bs->wait);
+	} else if (wait_cnt < 0) {
+		wait_cnt = atomic_inc_return(&bs->wait_cnt);
+		if (!wait_cnt)
+			goto wake;
 	}
 }
 
@@ -499,10 +513,13 @@
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < BT_WAIT_QUEUES; i++)
-		init_waitqueue_head(&bt->bs[i].wait);
-
 	bt_update_count(bt, depth);
+
+	for (i = 0; i < BT_WAIT_QUEUES; i++) {
+		init_waitqueue_head(&bt->bs[i].wait);
+		atomic_set(&bt->bs[i].wait_cnt, bt->wake_cnt);
+	}
+
 	return 0;
 }
 
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 98696a6..6206ed1 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -24,7 +24,7 @@
 	unsigned int map_nr;
 	struct blk_align_bitmap *map;
 
-	unsigned int wake_index;
+	atomic_t wake_index;
 	struct bt_wait_state *bs;
 };
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e11f5f8..0ef2dc7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -109,7 +109,7 @@
 	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
 }
 
-static void __blk_mq_drain_queue(struct request_queue *q)
+void blk_mq_drain_queue(struct request_queue *q)
 {
 	while (true) {
 		s64 count;
@@ -120,7 +120,7 @@
 
 		if (count == 0)
 			break;
-		blk_mq_run_queues(q, false);
+		blk_mq_start_hw_queues(q);
 		msleep(10);
 	}
 }
@@ -139,12 +139,7 @@
 	spin_unlock_irq(q->queue_lock);
 
 	if (drain)
-		__blk_mq_drain_queue(q);
-}
-
-void blk_mq_drain_queue(struct request_queue *q)
-{
-	__blk_mq_drain_queue(q);
+		blk_mq_drain_queue(q);
 }
 
 static void blk_mq_unfreeze_queue(struct request_queue *q)
diff --git a/block/blk.h b/block/blk.h
index 45385e9..6748c4f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -84,7 +84,6 @@
 #define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
 
 void blk_insert_flush(struct request *rq);
-void blk_abort_flushes(struct request_queue *q);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
diff --git a/block/elevator.c b/block/elevator.c
index f35eddd..34bded1 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -729,26 +729,6 @@
 	return ELV_MQUEUE_MAY;
 }
 
-void elv_abort_queue(struct request_queue *q)
-{
-	struct request *rq;
-
-	blk_abort_flushes(q);
-
-	while (!list_empty(&q->queue_head)) {
-		rq = list_entry_rq(q->queue_head.next);
-		rq->cmd_flags |= REQ_QUIET;
-		trace_block_rq_abort(q, rq);
-		/*
-		 * Mark this request as started so we don't trigger
-		 * any debug logic in the end I/O path.
-		 */
-		blk_start_request(rq);
-		__blk_end_request_all(rq, -EIO);
-	}
-}
-EXPORT_SYMBOL(elv_abort_queue);
-
 void elv_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 63407d2..9cb65b0 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -34,6 +34,9 @@
 
 /* Offsets relative to LPSS_PRIVATE_OFFSET */
 #define LPSS_CLK_DIVIDER_DEF_MASK	(BIT(1) | BIT(16))
+#define LPSS_RESETS			0x04
+#define LPSS_RESETS_RESET_FUNC		BIT(0)
+#define LPSS_RESETS_RESET_APB		BIT(1)
 #define LPSS_GENERAL			0x08
 #define LPSS_GENERAL_LTR_MODE_SW	BIT(2)
 #define LPSS_GENERAL_UART_RTS_OVRD	BIT(3)
@@ -99,6 +102,17 @@
 	writel(reg | LPSS_GENERAL_UART_RTS_OVRD, pdata->mmio_base + offset);
 }
 
+static void lpss_i2c_setup(struct lpss_private_data *pdata)
+{
+	unsigned int offset;
+	u32 val;
+
+	offset = pdata->dev_desc->prv_offset + LPSS_RESETS;
+	val = readl(pdata->mmio_base + offset);
+	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
+	writel(val, pdata->mmio_base + offset);
+}
+
 static struct lpss_device_desc lpt_dev_desc = {
 	.clk_required = true,
 	.prv_offset = 0x800,
@@ -171,6 +185,7 @@
 	.prv_offset = 0x800,
 	.save_ctx = true,
 	.shared_clock = &i2c_clock,
+	.setup = lpss_i2c_setup,
 };
 
 #else
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index e48fc98..0d7116f 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -32,6 +32,7 @@
 #include <linux/jiffies.h>
 #include <linux/async.h>
 #include <linux/dmi.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <asm/unaligned.h>
@@ -70,6 +71,7 @@
 MODULE_LICENSE("GPL");
 
 static int battery_bix_broken_package;
+static int battery_notification_delay_ms;
 static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -930,7 +932,10 @@
 		goto end;
 	}
 	alarm_string[count] = '\0';
-	battery->alarm = simple_strtol(alarm_string, NULL, 0);
+	if (kstrtoint(alarm_string, 0, &battery->alarm)) {
+		result = -EINVAL;
+		goto end;
+	}
 	result = acpi_battery_set_alarm(battery);
       end:
 	if (!result)
@@ -1062,6 +1067,14 @@
 	if (!battery)
 		return;
 	old = battery->bat.dev;
+	/*
+	* On Acer Aspire V5-573G notifications are sometimes triggered too
+	* early. For example, when AC is unplugged and notification is
+	* triggered, battery state is still reported as "Full", and changes to
+	* "Discharging" only after short delay, without any notification.
+	*/
+	if (battery_notification_delay_ms > 0)
+		msleep(battery_notification_delay_ms);
 	if (event == ACPI_BATTERY_NOTIFY_INFO)
 		acpi_battery_refresh(battery);
 	acpi_battery_update(battery, false);
@@ -1106,14 +1119,35 @@
 	return 0;
 }
 
+static int battery_bix_broken_package_quirk(const struct dmi_system_id *d)
+{
+	battery_bix_broken_package = 1;
+	return 0;
+}
+
+static int battery_notification_delay_quirk(const struct dmi_system_id *d)
+{
+	battery_notification_delay_ms = 1000;
+	return 0;
+}
+
 static struct dmi_system_id bat_dmi_table[] = {
 	{
+		.callback = battery_bix_broken_package_quirk,
 		.ident = "NEC LZ750/LS",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
 		},
 	},
+	{
+		.callback = battery_notification_delay_quirk,
+		.ident = "Acer Aspire V5-573G",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-573G"),
+		},
+	},
 	{},
 };
 
@@ -1227,8 +1261,7 @@
 	if (acpi_disabled)
 		return;
 
-	if (dmi_check_system(bat_dmi_table))
-		battery_bix_broken_package = 1;
+	dmi_check_system(bat_dmi_table);
 	
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_battery_dir = acpi_lock_battery_dir();
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 3f2bdc8..bad25b0 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -235,7 +235,8 @@
 static unsigned long acpi_rsdp;
 static int __init setup_acpi_rsdp(char *arg)
 {
-	acpi_rsdp = simple_strtoul(arg, NULL, 16);
+	if (kstrtoul(arg, 16, &acpi_rsdp))
+		return -EINVAL;
 	return 0;
 }
 early_param("acpi_rsdp", setup_acpi_rsdp);
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 05550ba..6d5a6cd 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -360,7 +360,8 @@
 	if (!str)
 		return -EINVAL;
 
-	acpi_apic_instance = simple_strtoul(str, NULL, 0);
+	if (kstrtoint(str, 0, &acpi_apic_instance))
+		return -EINVAL;
 
 	pr_notice("Shall use APIC/MADT table %d\n", acpi_apic_instance);
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 77087a2..a3b042c 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -79,7 +79,7 @@
 
 static int queue_mode = NULL_Q_MQ;
 module_param(queue_mode, int, S_IRUGO);
-MODULE_PARM_DESC(use_mq, "Use blk-mq interface (0=bio,1=rq,2=multiqueue)");
+MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
 
 static int gb = 250;
 module_param(gb, int, S_IRUGO);
@@ -227,7 +227,10 @@
 
 static void null_softirq_done_fn(struct request *rq)
 {
-	end_cmd(blk_mq_rq_to_pdu(rq));
+	if (queue_mode == NULL_Q_MQ)
+		end_cmd(blk_mq_rq_to_pdu(rq));
+	else
+		end_cmd(rq->special);
 }
 
 static inline void null_handle_cmd(struct nullb_cmd *cmd)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index a842c71..02351e2 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #include <linux/nvme.h>
@@ -46,16 +42,26 @@
 #include <scsi/sg.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
-#define NVME_Q_DEPTH 1024
+#include <trace/events/block.h>
+
+#define NVME_Q_DEPTH		1024
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
-#define ADMIN_TIMEOUT	(60 * HZ)
-#define IOD_TIMEOUT	(4 * NVME_IO_TIMEOUT)
+#define ADMIN_TIMEOUT		(admin_timeout * HZ)
+#define IOD_TIMEOUT		(retry_time * HZ)
 
-unsigned char io_timeout = 30;
-module_param(io_timeout, byte, 0644);
+static unsigned char admin_timeout = 60;
+module_param(admin_timeout, byte, 0644);
+MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands");
+
+unsigned char nvme_io_timeout = 30;
+module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
 MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
 
+static unsigned char retry_time = 30;
+module_param(retry_time, byte, 0644);
+MODULE_PARM_DESC(retry_time, "time in seconds to retry failed I/O");
+
 static int nvme_major;
 module_param(nvme_major, int, 0);
 
@@ -67,6 +73,7 @@
 static struct task_struct *nvme_thread;
 static struct workqueue_struct *nvme_workq;
 static wait_queue_head_t nvme_kthread_wait;
+static struct notifier_block nvme_nb;
 
 static void nvme_reset_failed_dev(struct work_struct *ws);
 
@@ -199,16 +206,13 @@
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
 #define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
 #define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
-#define CMD_CTX_FLUSH		(0x318 + CMD_CTX_BASE)
-#define CMD_CTX_ABORT		(0x31C + CMD_CTX_BASE)
+#define CMD_CTX_ABORT		(0x318 + CMD_CTX_BASE)
 
 static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	if (ctx == CMD_CTX_CANCELLED)
 		return;
-	if (ctx == CMD_CTX_FLUSH)
-		return;
 	if (ctx == CMD_CTX_ABORT) {
 		++nvmeq->dev->abort_limit;
 		return;
@@ -247,8 +251,9 @@
 	void *ctx;
 	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
 
-	if (cmdid >= nvmeq->q_depth) {
-		*fn = special_completion;
+	if (cmdid >= nvmeq->q_depth || !info[cmdid].fn) {
+		if (fn)
+			*fn = special_completion;
 		return CMD_CTX_INVALID;
 	}
 	if (fn)
@@ -281,9 +286,17 @@
 
 static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
 {
+	struct nvme_queue *nvmeq;
 	unsigned queue_id = get_cpu_var(*dev->io_queue);
+
 	rcu_read_lock();
-	return rcu_dereference(dev->queues[queue_id]);
+	nvmeq = rcu_dereference(dev->queues[queue_id]);
+	if (nvmeq)
+		return nvmeq;
+
+	rcu_read_unlock();
+	put_cpu_var(*dev->io_queue);
+	return NULL;
 }
 
 static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
@@ -295,8 +308,15 @@
 static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
 							__acquires(RCU)
 {
+	struct nvme_queue *nvmeq;
+
 	rcu_read_lock();
-	return rcu_dereference(dev->queues[q_idx]);
+	nvmeq = rcu_dereference(dev->queues[q_idx]);
+	if (nvmeq)
+		return nvmeq;
+
+	rcu_read_unlock();
+	return NULL;
 }
 
 static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
@@ -387,25 +407,30 @@
 static void nvme_start_io_acct(struct bio *bio)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	const int rw = bio_data_dir(bio);
-	int cpu = part_stat_lock();
-	part_round_stats(cpu, &disk->part0);
-	part_stat_inc(cpu, &disk->part0, ios[rw]);
-	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
-	part_inc_in_flight(&disk->part0, rw);
-	part_stat_unlock();
+	if (blk_queue_io_stat(disk->queue)) {
+		const int rw = bio_data_dir(bio);
+		int cpu = part_stat_lock();
+		part_round_stats(cpu, &disk->part0);
+		part_stat_inc(cpu, &disk->part0, ios[rw]);
+		part_stat_add(cpu, &disk->part0, sectors[rw],
+							bio_sectors(bio));
+		part_inc_in_flight(&disk->part0, rw);
+		part_stat_unlock();
+	}
 }
 
 static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	const int rw = bio_data_dir(bio);
-	unsigned long duration = jiffies - start_time;
-	int cpu = part_stat_lock();
-	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
-	part_round_stats(cpu, &disk->part0);
-	part_dec_in_flight(&disk->part0, rw);
-	part_stat_unlock();
+	if (blk_queue_io_stat(disk->queue)) {
+		const int rw = bio_data_dir(bio);
+		unsigned long duration = jiffies - start_time;
+		int cpu = part_stat_lock();
+		part_stat_add(cpu, &disk->part0, ticks[rw], duration);
+		part_round_stats(cpu, &disk->part0);
+		part_dec_in_flight(&disk->part0, rw);
+		part_stat_unlock();
+	}
 }
 
 static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
@@ -414,6 +439,7 @@
 	struct nvme_iod *iod = ctx;
 	struct bio *bio = iod->private;
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
+	int error = 0;
 
 	if (unlikely(status)) {
 		if (!(status & NVME_SC_DNR ||
@@ -426,6 +452,7 @@
 			wake_up(&nvmeq->sq_full);
 			return;
 		}
+		error = -EIO;
 	}
 	if (iod->nents) {
 		dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
@@ -433,10 +460,9 @@
 		nvme_end_io_acct(bio, iod->start_time);
 	}
 	nvme_free_iod(nvmeq->dev, iod);
-	if (status)
-		bio_endio(bio, -EIO);
-	else
-		bio_endio(bio, 0);
+
+	trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, error);
+	bio_endio(bio, error);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
@@ -525,6 +551,8 @@
 	if (!split)
 		return -ENOMEM;
 
+	trace_block_split(bdev_get_queue(bio->bi_bdev), bio,
+					split->bi_iter.bi_sector);
 	bio_chain(split, bio);
 
 	if (!waitqueue_active(&nvmeq->sq_full))
@@ -627,16 +655,6 @@
 	return 0;
 }
 
-int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns)
-{
-	int cmdid = alloc_cmdid(nvmeq, (void *)CMD_CTX_FLUSH,
-					special_completion, NVME_IO_TIMEOUT);
-	if (unlikely(cmdid < 0))
-		return cmdid;
-
-	return nvme_submit_flush(nvmeq, ns, cmdid);
-}
-
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 {
 	struct bio *bio = iod->private;
@@ -652,7 +670,7 @@
 
 	if (bio->bi_rw & REQ_DISCARD)
 		return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
-	if ((bio->bi_rw & REQ_FLUSH) && !iod->nents)
+	if (bio->bi_rw & REQ_FLUSH)
 		return nvme_submit_flush(nvmeq, ns, cmdid);
 
 	control = 0;
@@ -686,6 +704,26 @@
 	return 0;
 }
 
+static int nvme_split_flush_data(struct nvme_queue *nvmeq, struct bio *bio)
+{
+	struct bio *split = bio_clone(bio, GFP_ATOMIC);
+	if (!split)
+		return -ENOMEM;
+
+	split->bi_iter.bi_size = 0;
+	split->bi_phys_segments = 0;
+	bio->bi_rw &= ~REQ_FLUSH;
+	bio_chain(split, bio);
+
+	if (!waitqueue_active(&nvmeq->sq_full))
+		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
+	bio_list_add(&nvmeq->sq_cong, split);
+	bio_list_add(&nvmeq->sq_cong, bio);
+	wake_up_process(nvme_thread);
+
+	return 0;
+}
+
 /*
  * Called with local interrupts disabled and the q_lock held.  May not sleep.
  */
@@ -696,11 +734,8 @@
 	int psegs = bio_phys_segments(ns->queue, bio);
 	int result;
 
-	if ((bio->bi_rw & REQ_FLUSH) && psegs) {
-		result = nvme_submit_flush_data(nvmeq, ns);
-		if (result)
-			return result;
-	}
+	if ((bio->bi_rw & REQ_FLUSH) && psegs)
+		return nvme_split_flush_data(nvmeq, bio);
 
 	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
 	if (!iod)
@@ -795,7 +830,6 @@
 	int result = -EBUSY;
 
 	if (!nvmeq) {
-		put_nvmeq(NULL);
 		bio_endio(bio, -EIO);
 		return;
 	}
@@ -870,10 +904,8 @@
 	struct nvme_queue *nvmeq;
 
 	nvmeq = lock_nvmeq(dev, q_idx);
-	if (!nvmeq) {
-		unlock_nvmeq(nvmeq);
+	if (!nvmeq)
 		return -ENODEV;
-	}
 
 	cmdinfo.task = current;
 	cmdinfo.status = -EINTR;
@@ -898,9 +930,10 @@
 
 	if (cmdinfo.status == -EINTR) {
 		nvmeq = lock_nvmeq(dev, q_idx);
-		if (nvmeq)
+		if (nvmeq) {
 			nvme_abort_command(nvmeq, cmdid);
-		unlock_nvmeq(nvmeq);
+			unlock_nvmeq(nvmeq);
+		}
 		return -EINTR;
 	}
 
@@ -1358,7 +1391,8 @@
 			return -EINTR;
 		if (time_after(jiffies, timeout)) {
 			dev_err(&dev->pci_dev->dev,
-				"Device not ready; aborting initialisation\n");
+				"Device not ready; aborting %s\n", enabled ?
+						"initialisation" : "reset");
 			return -ENODEV;
 		}
 	}
@@ -1481,7 +1515,11 @@
 		goto put_pages;
 	}
 
+	err = -ENOMEM;
 	iod = nvme_alloc_iod(count, length, GFP_KERNEL);
+	if (!iod)
+		goto put_pages;
+
 	sg = iod->sg;
 	sg_init_table(sg, count);
 	for (i = 0; i < count; i++) {
@@ -1494,7 +1532,6 @@
 	sg_mark_end(&sg[i - 1]);
 	iod->nents = count;
 
-	err = -ENOMEM;
 	nents = dma_map_sg(&dev->pci_dev->dev, sg, count,
 				write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	if (!nents)
@@ -1894,6 +1931,8 @@
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	if (dev->max_hw_sectors)
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
+	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
+		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
 
 	disk->major = nvme_major;
 	disk->first_minor = 0;
@@ -2062,8 +2101,13 @@
 
 	status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0,
 								&result);
-	if (status)
-		return status < 0 ? -EIO : -EBUSY;
+	if (status < 0)
+		return status;
+	if (status > 0) {
+		dev_err(&dev->pci_dev->dev, "Could not set queue count (%d)\n",
+									status);
+		return -EBUSY;
+	}
 	return min(result & 0xffff, result >> 16) + 1;
 }
 
@@ -2072,14 +2116,25 @@
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
 }
 
+static void nvme_cpu_workfn(struct work_struct *work)
+{
+	struct nvme_dev *dev = container_of(work, struct nvme_dev, cpu_work);
+	if (dev->initialized)
+		nvme_assign_io_queues(dev);
+}
+
 static int nvme_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *hcpu)
 {
-	struct nvme_dev *dev = container_of(self, struct nvme_dev, nb);
+	struct nvme_dev *dev;
+
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DEAD:
-		nvme_assign_io_queues(dev);
+		spin_lock(&dev_list_lock);
+		list_for_each_entry(dev, &dev_list, node)
+			schedule_work(&dev->cpu_work);
+		spin_unlock(&dev_list_lock);
 		break;
 	}
 	return NOTIFY_OK;
@@ -2148,11 +2203,6 @@
 	nvme_free_queues(dev, nr_io_queues + 1);
 	nvme_assign_io_queues(dev);
 
-	dev->nb.notifier_call = &nvme_cpu_notify;
-	result = register_hotcpu_notifier(&dev->nb);
-	if (result)
-		goto free_queues;
-
 	return 0;
 
  free_queues:
@@ -2184,6 +2234,7 @@
 
 	res = nvme_identify(dev, 0, 1, dma_addr);
 	if (res) {
+		dev_err(&pdev->dev, "Identify Controller failed (%d)\n", res);
 		res = -EIO;
 		goto out;
 	}
@@ -2192,6 +2243,7 @@
 	nn = le32_to_cpup(&ctrl->nn);
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
+	dev->vwc = ctrl->vwc;
 	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
 	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
 	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
@@ -2450,8 +2502,6 @@
 	int i;
 
 	dev->initialized = 0;
-	unregister_hotcpu_notifier(&dev->nb);
-
 	nvme_dev_list_remove(dev);
 
 	if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
@@ -2722,6 +2772,7 @@
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->reset_workfn = nvme_reset_failed_dev;
 	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
+	INIT_WORK(&dev->cpu_work, nvme_cpu_workfn);
 	dev->pci_dev = pdev;
 	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
@@ -2801,6 +2852,7 @@
 
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->reset_work);
+	flush_work(&dev->cpu_work);
 	misc_deregister(&dev->miscdev);
 	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
@@ -2889,11 +2941,18 @@
 	else if (result > 0)
 		nvme_major = result;
 
-	result = pci_register_driver(&nvme_driver);
+	nvme_nb.notifier_call = &nvme_cpu_notify;
+	result = register_hotcpu_notifier(&nvme_nb);
 	if (result)
 		goto unregister_blkdev;
+
+	result = pci_register_driver(&nvme_driver);
+	if (result)
+		goto unregister_hotcpu;
 	return 0;
 
+ unregister_hotcpu:
+	unregister_hotcpu_notifier(&nvme_nb);
  unregister_blkdev:
 	unregister_blkdev(nvme_major, "nvme");
  kill_workq:
@@ -2904,9 +2963,11 @@
 static void __exit nvme_exit(void)
 {
 	pci_unregister_driver(&nvme_driver);
+	unregister_hotcpu_notifier(&nvme_nb);
 	unregister_blkdev(nvme_major, "nvme");
 	destroy_workqueue(nvme_workq);
 	BUG_ON(nvme_thread && !IS_ERR(nvme_thread));
+	_nvme_check_size();
 }
 
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 2c3f5be..a4cd6d6 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -1,6 +1,6 @@
 /*
  * NVM Express device driver
- * Copyright (c) 2011, Intel Corporation.
+ * Copyright (c) 2011-2014, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 /*
@@ -243,8 +239,6 @@
 #define READ_CAP_16_RESP_SIZE				32
 
 /* NVMe Namespace and Command Defines */
-#define NVME_GET_SMART_LOG_PAGE				0x02
-#define NVME_GET_FEAT_TEMP_THRESH			0x04
 #define BYTES_TO_DWORDS					4
 #define NVME_MAX_FIRMWARE_SLOT				7
 
@@ -686,6 +680,7 @@
 	u8 resp_data_format = 0x02;
 	u8 protect;
 	u8 cmdque = 0x01 << 1;
+	u8 fw_offset = sizeof(dev->firmware_rev);
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
 				&dma_addr, GFP_KERNEL);
@@ -721,7 +716,11 @@
 	inq_response[7] = cmdque;	/* wbus16=0 | sync=0 | vs=0 */
 	strncpy(&inq_response[8], "NVMe    ", 8);
 	strncpy(&inq_response[16], dev->model, 16);
-	strncpy(&inq_response[32], dev->firmware_rev, 4);
+
+	while (dev->firmware_rev[fw_offset - 1] == ' ' && fw_offset > 4)
+		fw_offset--;
+	fw_offset -= 4;
+	strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4);
 
 	xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
 	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
@@ -1018,8 +1017,8 @@
 	c.common.opcode = nvme_admin_get_log_page;
 	c.common.nsid = cpu_to_le32(0xFFFFFFFF);
 	c.common.prp1 = cpu_to_le64(dma_addr);
-	c.common.cdw10[0] = cpu_to_le32(((sizeof(struct nvme_smart_log) /
-			BYTES_TO_DWORDS) << 16) | NVME_GET_SMART_LOG_PAGE);
+	c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) /
+			BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART);
 	res = nvme_submit_admin_cmd(dev, &c, NULL);
 	if (res != NVME_SC_SUCCESS) {
 		temp_c = LOG_TEMP_UNKNOWN;
@@ -1086,8 +1085,8 @@
 	c.common.opcode = nvme_admin_get_log_page;
 	c.common.nsid = cpu_to_le32(0xFFFFFFFF);
 	c.common.prp1 = cpu_to_le64(dma_addr);
-	c.common.cdw10[0] = cpu_to_le32(((sizeof(struct nvme_smart_log) /
-			BYTES_TO_DWORDS) << 16) | NVME_GET_SMART_LOG_PAGE);
+	c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) /
+			BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART);
 	res = nvme_submit_admin_cmd(dev, &c, NULL);
 	if (res != NVME_SC_SUCCESS) {
 		temp_c_cur = LOG_TEMP_UNKNOWN;
@@ -1477,7 +1476,7 @@
 		goto out_dma;
 	}
 	id_ctrl = mem;
-	lowest_pow_st = id_ctrl->npss - 1;
+	lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
 
 	switch (pc) {
 	case NVME_POWER_STATE_START_VALID:
@@ -1494,20 +1493,19 @@
 		break;
 	case NVME_POWER_STATE_IDLE:
 		/* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */
-		/* min of desired state and (lps-1) because lps is STOP */
 		if (pcmod == 0x0)
-			ps_desired = min(POWER_STATE_1, (lowest_pow_st - 1));
+			ps_desired = POWER_STATE_1;
 		else if (pcmod == 0x1)
-			ps_desired = min(POWER_STATE_2, (lowest_pow_st - 1));
+			ps_desired = POWER_STATE_2;
 		else if (pcmod == 0x2)
-			ps_desired = min(POWER_STATE_3, (lowest_pow_st - 1));
+			ps_desired = POWER_STATE_3;
 		break;
 	case NVME_POWER_STATE_STANDBY:
 		/* Action unspecified if POWER CONDITION MODIFIER != [0,1] */
 		if (pcmod == 0x0)
-			ps_desired = max(0, (lowest_pow_st - 2));
+			ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2));
 		else if (pcmod == 0x1)
-			ps_desired = max(0, (lowest_pow_st - 1));
+			ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1));
 		break;
 	case NVME_POWER_STATE_LU_CONTROL:
 	default:
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4c95b50..bbeb404 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -541,7 +541,6 @@
 		return -ENOENT;
 
 	(void) get_device(&rbd_dev->dev);
-	set_device_ro(bdev, rbd_dev->mapping.read_only);
 
 	return 0;
 }
@@ -559,10 +558,76 @@
 	put_device(&rbd_dev->dev);
 }
 
+static int rbd_ioctl_set_ro(struct rbd_device *rbd_dev, unsigned long arg)
+{
+	int ret = 0;
+	int val;
+	bool ro;
+	bool ro_changed = false;
+
+	/* get_user() may sleep, so call it before taking rbd_dev->lock */
+	if (get_user(val, (int __user *)(arg)))
+		return -EFAULT;
+
+	ro = val ? true : false;
+	/* Snapshot doesn't allow to write*/
+	if (rbd_dev->spec->snap_id != CEPH_NOSNAP && !ro)
+		return -EROFS;
+
+	spin_lock_irq(&rbd_dev->lock);
+	/* prevent others open this device */
+	if (rbd_dev->open_count > 1) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (rbd_dev->mapping.read_only != ro) {
+		rbd_dev->mapping.read_only = ro;
+		ro_changed = true;
+	}
+
+out:
+	spin_unlock_irq(&rbd_dev->lock);
+	/* set_disk_ro() may sleep, so call it after releasing rbd_dev->lock */
+	if (ret == 0 && ro_changed)
+		set_disk_ro(rbd_dev->disk, ro ? 1 : 0);
+
+	return ret;
+}
+
+static int rbd_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned int cmd, unsigned long arg)
+{
+	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
+	int ret = 0;
+
+	switch (cmd) {
+	case BLKROSET:
+		ret = rbd_ioctl_set_ro(rbd_dev, arg);
+		break;
+	default:
+		ret = -ENOTTY;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static int rbd_compat_ioctl(struct block_device *bdev, fmode_t mode,
+				unsigned int cmd, unsigned long arg)
+{
+	return rbd_ioctl(bdev, mode, cmd, arg);
+}
+#endif /* CONFIG_COMPAT */
+
 static const struct block_device_operations rbd_bd_ops = {
 	.owner			= THIS_MODULE,
 	.open			= rbd_open,
 	.release		= rbd_release,
+	.ioctl			= rbd_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= rbd_compat_ioctl,
+#endif
 };
 
 /*
@@ -1382,6 +1447,13 @@
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
+static void rbd_img_request_get(struct rbd_img_request *img_request)
+{
+	dout("%s: img %p (was %d)\n", __func__, img_request,
+	     atomic_read(&img_request->kref.refcount));
+	kref_get(&img_request->kref);
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request);
 static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
@@ -2142,6 +2214,7 @@
 	img_request->next_completion = which;
 out:
 	spin_unlock_irq(&img_request->completion_lock);
+	rbd_img_request_put(img_request);
 
 	if (!more)
 		rbd_img_request_complete(img_request);
@@ -2242,6 +2315,7 @@
 			goto out_unwind;
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
+		rbd_img_request_get(img_request);
 
 		if (write_request) {
 			osd_req_op_alloc_hint_init(osd_req, which,
@@ -2872,56 +2946,55 @@
 }
 
 /*
- * Request sync osd watch/unwatch.  The value of "start" determines
- * whether a watch request is being initiated or torn down.
+ * Initiate a watch request, synchronously.
  */
-static int __rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start)
+static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
 	struct rbd_obj_request *obj_request;
 	int ret;
 
-	rbd_assert(start ^ !!rbd_dev->watch_event);
-	rbd_assert(start ^ !!rbd_dev->watch_request);
+	rbd_assert(!rbd_dev->watch_event);
+	rbd_assert(!rbd_dev->watch_request);
 
-	if (start) {
-		ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev,
-						&rbd_dev->watch_event);
-		if (ret < 0)
-			return ret;
-		rbd_assert(rbd_dev->watch_event != NULL);
-	}
+	ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev,
+				     &rbd_dev->watch_event);
+	if (ret < 0)
+		return ret;
 
-	ret = -ENOMEM;
+	rbd_assert(rbd_dev->watch_event);
+
 	obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0,
-							OBJ_REQUEST_NODATA);
-	if (!obj_request)
+					     OBJ_REQUEST_NODATA);
+	if (!obj_request) {
+		ret = -ENOMEM;
 		goto out_cancel;
+	}
 
 	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
 						  obj_request);
-	if (!obj_request->osd_req)
-		goto out_cancel;
+	if (!obj_request->osd_req) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
 
-	if (start)
-		ceph_osdc_set_request_linger(osdc, obj_request->osd_req);
-	else
-		ceph_osdc_unregister_linger_request(osdc,
-					rbd_dev->watch_request->osd_req);
+	ceph_osdc_set_request_linger(osdc, obj_request->osd_req);
 
 	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
-				rbd_dev->watch_event->cookie, 0, start ? 1 : 0);
+			      rbd_dev->watch_event->cookie, 0, 1);
 	rbd_osd_req_format_write(obj_request);
 
 	ret = rbd_obj_request_submit(osdc, obj_request);
 	if (ret)
-		goto out_cancel;
+		goto out_linger;
+
 	ret = rbd_obj_request_wait(obj_request);
 	if (ret)
-		goto out_cancel;
+		goto out_linger;
+
 	ret = obj_request->result;
 	if (ret)
-		goto out_cancel;
+		goto out_linger;
 
 	/*
 	 * A watch request is set to linger, so the underlying osd
@@ -2931,36 +3004,84 @@
 	 * it.  We'll drop that reference (below) after we've
 	 * unregistered it.
 	 */
-	if (start) {
-		rbd_dev->watch_request = obj_request;
+	rbd_dev->watch_request = obj_request;
 
-		return 0;
-	}
+	return 0;
 
-	/* We have successfully torn down the watch request */
-
-	rbd_obj_request_put(rbd_dev->watch_request);
-	rbd_dev->watch_request = NULL;
+out_linger:
+	ceph_osdc_unregister_linger_request(osdc, obj_request->osd_req);
+out_put:
+	rbd_obj_request_put(obj_request);
 out_cancel:
-	/* Cancel the event if we're tearing down, or on error */
 	ceph_osdc_cancel_event(rbd_dev->watch_event);
 	rbd_dev->watch_event = NULL;
-	if (obj_request)
-		rbd_obj_request_put(obj_request);
 
 	return ret;
 }
 
-static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev)
+/*
+ * Tear down a watch request, synchronously.
+ */
+static int __rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
 {
-	return __rbd_dev_header_watch_sync(rbd_dev, true);
+	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+	struct rbd_obj_request *obj_request;
+	int ret;
+
+	rbd_assert(rbd_dev->watch_event);
+	rbd_assert(rbd_dev->watch_request);
+
+	obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0,
+					     OBJ_REQUEST_NODATA);
+	if (!obj_request) {
+		ret = -ENOMEM;
+		goto out_cancel;
+	}
+
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
+						  obj_request);
+	if (!obj_request->osd_req) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
+
+	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
+			      rbd_dev->watch_event->cookie, 0, 0);
+	rbd_osd_req_format_write(obj_request);
+
+	ret = rbd_obj_request_submit(osdc, obj_request);
+	if (ret)
+		goto out_put;
+
+	ret = rbd_obj_request_wait(obj_request);
+	if (ret)
+		goto out_put;
+
+	ret = obj_request->result;
+	if (ret)
+		goto out_put;
+
+	/* We have successfully torn down the watch request */
+
+	ceph_osdc_unregister_linger_request(osdc,
+					    rbd_dev->watch_request->osd_req);
+	rbd_obj_request_put(rbd_dev->watch_request);
+	rbd_dev->watch_request = NULL;
+
+out_put:
+	rbd_obj_request_put(obj_request);
+out_cancel:
+	ceph_osdc_cancel_event(rbd_dev->watch_event);
+	rbd_dev->watch_event = NULL;
+
+	return ret;
 }
 
 static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
 {
 	int ret;
 
-	ret = __rbd_dev_header_watch_sync(rbd_dev, false);
+	ret = __rbd_dev_header_unwatch_sync(rbd_dev);
 	if (ret) {
 		rbd_warn(rbd_dev, "unable to tear down watch request: %d\n",
 			 ret);
@@ -3058,7 +3179,6 @@
 		__releases(q->queue_lock) __acquires(q->queue_lock)
 {
 	struct rbd_device *rbd_dev = q->queuedata;
-	bool read_only = rbd_dev->mapping.read_only;
 	struct request *rq;
 	int result;
 
@@ -3094,7 +3214,7 @@
 
 		if (write_request) {
 			result = -EROFS;
-			if (read_only)
+			if (rbd_dev->mapping.read_only)
 				goto end_request;
 			rbd_assert(rbd_dev->spec->snap_id == CEPH_NOSNAP);
 		}
@@ -4683,6 +4803,38 @@
 }
 
 /*
+ * Return pool id (>= 0) or a negative error code.
+ */
+static int rbd_add_get_pool_id(struct rbd_client *rbdc, const char *pool_name)
+{
+	u64 newest_epoch;
+	unsigned long timeout = rbdc->client->options->mount_timeout * HZ;
+	int tries = 0;
+	int ret;
+
+again:
+	ret = ceph_pg_poolid_by_name(rbdc->client->osdc.osdmap, pool_name);
+	if (ret == -ENOENT && tries++ < 1) {
+		ret = ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
+					       &newest_epoch);
+		if (ret < 0)
+			return ret;
+
+		if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
+			ceph_monc_request_next_osdmap(&rbdc->client->monc);
+			(void) ceph_monc_wait_osdmap(&rbdc->client->monc,
+						     newest_epoch, timeout);
+			goto again;
+		} else {
+			/* the osdmap we have is new enough */
+			return -ENOENT;
+		}
+	}
+
+	return ret;
+}
+
+/*
  * An rbd format 2 image has a unique identifier, distinct from the
  * name given to it by the user.  Internally, that identifier is
  * what's used to specify the names of objects related to the image.
@@ -4752,7 +4904,7 @@
 
 		image_id = ceph_extract_encoded_string(&p, p + ret,
 						NULL, GFP_NOIO);
-		ret = IS_ERR(image_id) ? PTR_ERR(image_id) : 0;
+		ret = PTR_ERR_OR_ZERO(image_id);
 		if (!ret)
 			rbd_dev->image_format = 2;
 	} else {
@@ -4907,6 +5059,7 @@
 	if (ret)
 		goto err_out_disk;
 	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
+	set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
 
 	ret = rbd_bus_add_dev(rbd_dev);
 	if (ret)
@@ -5053,7 +5206,6 @@
 	struct rbd_options *rbd_opts = NULL;
 	struct rbd_spec *spec = NULL;
 	struct rbd_client *rbdc;
-	struct ceph_osd_client *osdc;
 	bool read_only;
 	int rc = -ENOMEM;
 
@@ -5075,8 +5227,7 @@
 	}
 
 	/* pick the pool */
-	osdc = &rbdc->client->osdc;
-	rc = ceph_pg_poolid_by_name(osdc->osdmap, spec->pool_name);
+	rc = rbd_add_get_pool_id(rbdc, spec->pool_name);
 	if (rc < 0)
 		goto err_out_client;
 	spec->pool_id = (u64)rc;
@@ -5387,6 +5538,7 @@
 
 static void __exit rbd_exit(void)
 {
+	ida_destroy(&rbd_dev_id_ida);
 	rbd_sysfs_cleanup();
 	if (single_major)
 		unregister_blkdev(rbd_major, RBD_DRV_NAME);
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index a118ec1..1f37d98 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -45,7 +45,7 @@
 
 config ARM_CCI
 	bool "ARM CCI driver support"
-	depends on ARM
+	depends on ARM && OF && CPU_V7
 	help
 	  Driver supporting the CCI cache coherent interconnect for ARM
 	  platforms.
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4ad71ef..0a7ac0a 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -980,7 +980,6 @@
 static size_t account(struct entropy_store *r, size_t nbytes, int min,
 		      int reserved)
 {
-	int have_bytes;
 	int entropy_count, orig;
 	size_t ibytes;
 
@@ -989,17 +988,19 @@
 	/* Can we pull enough? */
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
-	have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
 	ibytes = nbytes;
 	/* If limited, never pull more than available */
-	if (r->limit)
-		ibytes = min_t(size_t, ibytes, have_bytes - reserved);
+	if (r->limit) {
+		int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
+
+		if ((have_bytes -= reserved) < 0)
+			have_bytes = 0;
+		ibytes = min_t(size_t, ibytes, have_bytes);
+	}
 	if (ibytes < min)
 		ibytes = 0;
-	if (have_bytes >= ibytes + reserved)
-		entropy_count -= ibytes << (ENTROPY_SHIFT + 3);
-	else
-		entropy_count = reserved << (ENTROPY_SHIFT + 3);
+	if ((entropy_count -= ibytes << (ENTROPY_SHIFT + 3)) < 0)
+		entropy_count = 0;
 
 	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
 		goto retry;
diff --git a/drivers/clk/sunxi/Makefile b/drivers/clk/sunxi/Makefile
index b5bac91..762fd64 100644
--- a/drivers/clk/sunxi/Makefile
+++ b/drivers/clk/sunxi/Makefile
@@ -3,3 +3,7 @@
 #
 
 obj-y += clk-sunxi.o clk-factors.o
+obj-y += clk-a10-hosc.o
+obj-y += clk-a20-gmac.o
+
+obj-$(CONFIG_MFD_SUN6I_PRCM) += clk-sun6i-ar100.o clk-sun6i-apb0.o clk-sun6i-apb0-gates.o
diff --git a/drivers/clk/sunxi/clk-a10-hosc.c b/drivers/clk/sunxi/clk-a10-hosc.c
new file mode 100644
index 0000000..0481d5d
--- /dev/null
+++ b/drivers/clk/sunxi/clk-a10-hosc.c
@@ -0,0 +1,73 @@
+/*
+ * Copyright 2013 Emilio López
+ *
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#define SUNXI_OSC24M_GATE	0
+
+static DEFINE_SPINLOCK(hosc_lock);
+
+static void __init sun4i_osc_clk_setup(struct device_node *node)
+{
+	struct clk *clk;
+	struct clk_fixed_rate *fixed;
+	struct clk_gate *gate;
+	const char *clk_name = node->name;
+	u32 rate;
+
+	if (of_property_read_u32(node, "clock-frequency", &rate))
+		return;
+
+	/* allocate fixed-rate and gate clock structs */
+	fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL);
+	if (!fixed)
+		return;
+	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+	if (!gate)
+		goto err_free_fixed;
+
+	of_property_read_string(node, "clock-output-names", &clk_name);
+
+	/* set up gate and fixed rate properties */
+	gate->reg = of_iomap(node, 0);
+	gate->bit_idx = SUNXI_OSC24M_GATE;
+	gate->lock = &hosc_lock;
+	fixed->fixed_rate = rate;
+
+	clk = clk_register_composite(NULL, clk_name,
+			NULL, 0,
+			NULL, NULL,
+			&fixed->hw, &clk_fixed_rate_ops,
+			&gate->hw, &clk_gate_ops,
+			CLK_IS_ROOT);
+
+	if (IS_ERR(clk))
+		goto err_free_gate;
+
+	of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	clk_register_clkdev(clk, clk_name, NULL);
+
+	return;
+
+err_free_gate:
+	kfree(gate);
+err_free_fixed:
+	kfree(fixed);
+}
+CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-a10-osc-clk", sun4i_osc_clk_setup);
diff --git a/drivers/clk/sunxi/clk-a20-gmac.c b/drivers/clk/sunxi/clk-a20-gmac.c
new file mode 100644
index 0000000..633ddc4
--- /dev/null
+++ b/drivers/clk/sunxi/clk-a20-gmac.c
@@ -0,0 +1,119 @@
+/*
+ * Copyright 2013 Emilio López
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * Copyright 2013 Chen-Yu Tsai
+ * Chen-Yu Tsai <wens@csie.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+static DEFINE_SPINLOCK(gmac_lock);
+
+/**
+ * sun7i_a20_gmac_clk_setup - Setup function for A20/A31 GMAC clock module
+ *
+ * This clock looks something like this
+ *                               ________________________
+ *  MII TX clock from PHY >-----|___________    _________|----> to GMAC core
+ *  GMAC Int. RGMII TX clk >----|___________\__/__gate---|----> to PHY
+ *  Ext. 125MHz RGMII TX clk >--|__divider__/            |
+ *                              |________________________|
+ *
+ * The external 125 MHz reference is optional, i.e. GMAC can use its
+ * internal TX clock just fine. The A31 GMAC clock module does not have
+ * the divider controls for the external reference.
+ *
+ * To keep it simple, let the GMAC use either the MII TX clock for MII mode,
+ * and its internal TX clock for GMII and RGMII modes. The GMAC driver should
+ * select the appropriate source and gate/ungate the output to the PHY.
+ *
+ * Only the GMAC should use this clock. Altering the clock so that it doesn't
+ * match the GMAC's operation parameters will result in the GMAC not being
+ * able to send traffic out. The GMAC driver should set the clock rate and
+ * enable/disable this clock to configure the required state. The clock
+ * driver then responds by auto-reparenting the clock.
+ */
+
+#define SUN7I_A20_GMAC_GPIT	2
+#define SUN7I_A20_GMAC_MASK	0x3
+#define SUN7I_A20_GMAC_PARENTS	2
+
+static void __init sun7i_a20_gmac_clk_setup(struct device_node *node)
+{
+	struct clk *clk;
+	struct clk_mux *mux;
+	struct clk_gate *gate;
+	const char *clk_name = node->name;
+	const char *parents[SUN7I_A20_GMAC_PARENTS];
+	void *reg;
+
+	if (of_property_read_string(node, "clock-output-names", &clk_name))
+		return;
+
+	/* allocate mux and gate clock structs */
+	mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
+	if (!mux)
+		return;
+
+	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+	if (!gate)
+		goto free_mux;
+
+	/* gmac clock requires exactly 2 parents */
+	parents[0] = of_clk_get_parent_name(node, 0);
+	parents[1] = of_clk_get_parent_name(node, 1);
+	if (!parents[0] || !parents[1])
+		goto free_gate;
+
+	reg = of_iomap(node, 0);
+	if (!reg)
+		goto free_gate;
+
+	/* set up gate and fixed rate properties */
+	gate->reg = reg;
+	gate->bit_idx = SUN7I_A20_GMAC_GPIT;
+	gate->lock = &gmac_lock;
+	mux->reg = reg;
+	mux->mask = SUN7I_A20_GMAC_MASK;
+	mux->flags = CLK_MUX_INDEX_BIT;
+	mux->lock = &gmac_lock;
+
+	clk = clk_register_composite(NULL, clk_name,
+			parents, SUN7I_A20_GMAC_PARENTS,
+			&mux->hw, &clk_mux_ops,
+			NULL, NULL,
+			&gate->hw, &clk_gate_ops,
+			0);
+
+	if (IS_ERR(clk))
+		goto iounmap_reg;
+
+	of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	clk_register_clkdev(clk, clk_name, NULL);
+
+	return;
+
+iounmap_reg:
+	iounmap(reg);
+free_gate:
+	kfree(gate);
+free_mux:
+	kfree(mux);
+}
+CLK_OF_DECLARE(sun7i_a20_gmac, "allwinner,sun7i-a20-gmac-clk",
+		sun7i_a20_gmac_clk_setup);
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
new file mode 100644
index 0000000..44cd27c
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * Allwinner A31 APB0 clock gates driver
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#define SUN6I_APB0_GATES_MAX_SIZE	32
+
+static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct clk_onecell_data *clk_data;
+	const char *clk_parent;
+	const char *clk_name;
+	struct resource *r;
+	void __iomem *reg;
+	int gate_id;
+	int ngates;
+	int i;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg = devm_ioremap_resource(&pdev->dev, r);
+	if (!reg)
+		return PTR_ERR(reg);
+
+	clk_parent = of_clk_get_parent_name(np, 0);
+	if (!clk_parent)
+		return -EINVAL;
+
+	ngates = of_property_count_strings(np, "clock-output-names");
+	if (ngates < 0)
+		return ngates;
+
+	if (!ngates || ngates > SUN6I_APB0_GATES_MAX_SIZE)
+		return -EINVAL;
+
+	clk_data = devm_kzalloc(&pdev->dev, sizeof(struct clk_onecell_data),
+				GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	clk_data->clks = devm_kzalloc(&pdev->dev,
+				      SUN6I_APB0_GATES_MAX_SIZE *
+				      sizeof(struct clk *),
+				      GFP_KERNEL);
+	if (!clk_data->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < ngates; i++) {
+		of_property_read_string_index(np, "clock-output-names",
+					      i, &clk_name);
+
+		gate_id = i;
+		of_property_read_u32_index(np, "clock-indices", i, &gate_id);
+
+		WARN_ON(gate_id >= SUN6I_APB0_GATES_MAX_SIZE);
+		if (gate_id >= SUN6I_APB0_GATES_MAX_SIZE)
+			continue;
+
+		clk_data->clks[gate_id] = clk_register_gate(&pdev->dev,
+							    clk_name,
+							    clk_parent, 0,
+							    reg, gate_id,
+							    0, NULL);
+		WARN_ON(IS_ERR(clk_data->clks[gate_id]));
+	}
+
+	clk_data->clk_num = ngates;
+
+	return of_clk_add_provider(np, of_clk_src_onecell_get, clk_data);
+}
+
+const struct of_device_id sun6i_a31_apb0_gates_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun6i-a31-apb0-gates-clk" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver sun6i_a31_apb0_gates_clk_driver = {
+	.driver = {
+		.name = "sun6i-a31-apb0-gates-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun6i_a31_apb0_gates_clk_dt_ids,
+	},
+	.probe = sun6i_a31_apb0_gates_clk_probe,
+};
+module_platform_driver(sun6i_a31_apb0_gates_clk_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 APB0 gate clocks driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0.c b/drivers/clk/sunxi/clk-sun6i-apb0.c
new file mode 100644
index 0000000..11f17c3
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun6i-apb0.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * Allwinner A31 APB0 clock driver
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+/*
+ * The APB0 clk has a configurable divisor.
+ *
+ * We must use a clk_div_table and not a regular power of 2
+ * divisor here, because the first 2 values divide the clock
+ * by 2.
+ */
+static const struct clk_div_table sun6i_a31_apb0_divs[] = {
+	{ .val = 0, .div = 2, },
+	{ .val = 1, .div = 2, },
+	{ .val = 2, .div = 4, },
+	{ .val = 3, .div = 8, },
+	{ /* sentinel */ },
+};
+
+static int sun6i_a31_apb0_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const char *clk_name = np->name;
+	const char *clk_parent;
+	struct resource *r;
+	void __iomem *reg;
+	struct clk *clk;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	clk_parent = of_clk_get_parent_name(np, 0);
+	if (!clk_parent)
+		return -EINVAL;
+
+	of_property_read_string(np, "clock-output-names", &clk_name);
+
+	clk = clk_register_divider_table(&pdev->dev, clk_name, clk_parent,
+					 0, reg, 0, 2, 0, sun6i_a31_apb0_divs,
+					 NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return of_clk_add_provider(np, of_clk_src_simple_get, clk);
+}
+
+const struct of_device_id sun6i_a31_apb0_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun6i-a31-apb0-clk" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver sun6i_a31_apb0_clk_driver = {
+	.driver = {
+		.name = "sun6i-a31-apb0-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun6i_a31_apb0_clk_dt_ids,
+	},
+	.probe = sun6i_a31_apb0_clk_probe,
+};
+module_platform_driver(sun6i_a31_apb0_clk_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 APB0 clock Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c
new file mode 100644
index 0000000..f73cc05
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun6i-ar100.c
@@ -0,0 +1,233 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * Allwinner A31 AR100 clock driver
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#define SUN6I_AR100_MAX_PARENTS		4
+#define SUN6I_AR100_SHIFT_MASK		0x3
+#define SUN6I_AR100_SHIFT_MAX		SUN6I_AR100_SHIFT_MASK
+#define SUN6I_AR100_SHIFT_SHIFT		4
+#define SUN6I_AR100_DIV_MASK		0x1f
+#define SUN6I_AR100_DIV_MAX		(SUN6I_AR100_DIV_MASK + 1)
+#define SUN6I_AR100_DIV_SHIFT		8
+#define SUN6I_AR100_MUX_MASK		0x3
+#define SUN6I_AR100_MUX_SHIFT		16
+
+struct ar100_clk {
+	struct clk_hw hw;
+	void __iomem *reg;
+};
+
+static inline struct ar100_clk *to_ar100_clk(struct clk_hw *hw)
+{
+	return container_of(hw, struct ar100_clk, hw);
+}
+
+static unsigned long ar100_recalc_rate(struct clk_hw *hw,
+				       unsigned long parent_rate)
+{
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	u32 val = readl(clk->reg);
+	int shift = (val >> SUN6I_AR100_SHIFT_SHIFT) & SUN6I_AR100_SHIFT_MASK;
+	int div = (val >> SUN6I_AR100_DIV_SHIFT) & SUN6I_AR100_DIV_MASK;
+
+	return (parent_rate >> shift) / (div + 1);
+}
+
+static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate,
+				 unsigned long *best_parent_rate,
+				 struct clk **best_parent_clk)
+{
+	int nparents = __clk_get_num_parents(hw->clk);
+	long best_rate = -EINVAL;
+	int i;
+
+	*best_parent_clk = NULL;
+
+	for (i = 0; i < nparents; i++) {
+		unsigned long parent_rate;
+		unsigned long tmp_rate;
+		struct clk *parent;
+		unsigned long div;
+		int shift;
+
+		parent = clk_get_parent_by_index(hw->clk, i);
+		parent_rate = __clk_get_rate(parent);
+		div = DIV_ROUND_UP(parent_rate, rate);
+
+		/*
+		 * The AR100 clk contains 2 divisors:
+		 * - one power of 2 divisor
+		 * - one regular divisor
+		 *
+		 * First check if we can safely shift (or divide by a power
+		 * of 2) without losing precision on the requested rate.
+		 */
+		shift = ffs(div) - 1;
+		if (shift > SUN6I_AR100_SHIFT_MAX)
+			shift = SUN6I_AR100_SHIFT_MAX;
+
+		div >>= shift;
+
+		/*
+		 * Then if the divisor is still bigger than what the HW
+		 * actually supports, use a bigger shift (or power of 2
+		 * divider) value and accept to lose some precision.
+		 */
+		while (div > SUN6I_AR100_DIV_MAX) {
+			shift++;
+			div >>= 1;
+			if (shift > SUN6I_AR100_SHIFT_MAX)
+				break;
+		}
+
+		/*
+		 * If the shift value (or power of 2 divider) is bigger
+		 * than what the HW actually support, skip this parent.
+		 */
+		if (shift > SUN6I_AR100_SHIFT_MAX)
+			continue;
+
+		tmp_rate = (parent_rate >> shift) / div;
+		if (!*best_parent_clk || tmp_rate > best_rate) {
+			*best_parent_clk = parent;
+			*best_parent_rate = parent_rate;
+			best_rate = tmp_rate;
+		}
+	}
+
+	return best_rate;
+}
+
+static int ar100_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	u32 val = readl(clk->reg);
+
+	if (index >= SUN6I_AR100_MAX_PARENTS)
+		return -EINVAL;
+
+	val &= ~(SUN6I_AR100_MUX_MASK << SUN6I_AR100_MUX_SHIFT);
+	val |= (index << SUN6I_AR100_MUX_SHIFT);
+	writel(val, clk->reg);
+
+	return 0;
+}
+
+static u8 ar100_get_parent(struct clk_hw *hw)
+{
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	return (readl(clk->reg) >> SUN6I_AR100_MUX_SHIFT) &
+	       SUN6I_AR100_MUX_MASK;
+}
+
+static int ar100_set_rate(struct clk_hw *hw, unsigned long rate,
+			  unsigned long parent_rate)
+{
+	unsigned long div = parent_rate / rate;
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	u32 val = readl(clk->reg);
+	int shift;
+
+	if (parent_rate % rate)
+		return -EINVAL;
+
+	shift = ffs(div) - 1;
+	if (shift > SUN6I_AR100_SHIFT_MAX)
+		shift = SUN6I_AR100_SHIFT_MAX;
+
+	div >>= shift;
+
+	if (div > SUN6I_AR100_DIV_MAX)
+		return -EINVAL;
+
+	val &= ~((SUN6I_AR100_SHIFT_MASK << SUN6I_AR100_SHIFT_SHIFT) |
+		 (SUN6I_AR100_DIV_MASK << SUN6I_AR100_DIV_SHIFT));
+	val |= (shift << SUN6I_AR100_SHIFT_SHIFT) |
+	       (div << SUN6I_AR100_DIV_SHIFT);
+	writel(val, clk->reg);
+
+	return 0;
+}
+
+struct clk_ops ar100_ops = {
+	.recalc_rate = ar100_recalc_rate,
+	.determine_rate = ar100_determine_rate,
+	.set_parent = ar100_set_parent,
+	.get_parent = ar100_get_parent,
+	.set_rate = ar100_set_rate,
+};
+
+static int sun6i_a31_ar100_clk_probe(struct platform_device *pdev)
+{
+	const char *parents[SUN6I_AR100_MAX_PARENTS];
+	struct device_node *np = pdev->dev.of_node;
+	const char *clk_name = np->name;
+	struct clk_init_data init;
+	struct ar100_clk *ar100;
+	struct resource *r;
+	struct clk *clk;
+	int nparents;
+	int i;
+
+	ar100 = devm_kzalloc(&pdev->dev, sizeof(*ar100), GFP_KERNEL);
+	if (!ar100)
+		return -ENOMEM;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ar100->reg = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(ar100->reg))
+		return PTR_ERR(ar100->reg);
+
+	nparents = of_clk_get_parent_count(np);
+	if (nparents > SUN6I_AR100_MAX_PARENTS)
+		nparents = SUN6I_AR100_MAX_PARENTS;
+
+	for (i = 0; i < nparents; i++)
+		parents[i] = of_clk_get_parent_name(np, i);
+
+	of_property_read_string(np, "clock-output-names", &clk_name);
+
+	init.name = clk_name;
+	init.ops = &ar100_ops;
+	init.parent_names = parents;
+	init.num_parents = nparents;
+	init.flags = 0;
+
+	ar100->hw.init = &init;
+
+	clk = clk_register(&pdev->dev, &ar100->hw);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return of_clk_add_provider(np, of_clk_src_simple_get, clk);
+}
+
+const struct of_device_id sun6i_a31_ar100_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun6i-a31-ar100-clk" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver sun6i_a31_ar100_clk_driver = {
+	.driver = {
+		.name = "sun6i-a31-ar100-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun6i_a31_ar100_clk_dt_ids,
+	},
+	.probe = sun6i_a31_ar100_clk_probe,
+};
+module_platform_driver(sun6i_a31_ar100_clk_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 AR100 clock Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 4264834..fb2ce84 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -28,63 +28,6 @@
 #define SUNXI_MAX_PARENTS	5
 
 /**
- * sun4i_osc_clk_setup() - Setup function for gatable oscillator
- */
-
-#define SUNXI_OSC24M_GATE	0
-
-static void __init sun4i_osc_clk_setup(struct device_node *node)
-{
-	struct clk *clk;
-	struct clk_fixed_rate *fixed;
-	struct clk_gate *gate;
-	const char *clk_name = node->name;
-	u32 rate;
-
-	if (of_property_read_u32(node, "clock-frequency", &rate))
-		return;
-
-	/* allocate fixed-rate and gate clock structs */
-	fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL);
-	if (!fixed)
-		return;
-	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
-	if (!gate)
-		goto err_free_fixed;
-
-	of_property_read_string(node, "clock-output-names", &clk_name);
-
-	/* set up gate and fixed rate properties */
-	gate->reg = of_iomap(node, 0);
-	gate->bit_idx = SUNXI_OSC24M_GATE;
-	gate->lock = &clk_lock;
-	fixed->fixed_rate = rate;
-
-	clk = clk_register_composite(NULL, clk_name,
-			NULL, 0,
-			NULL, NULL,
-			&fixed->hw, &clk_fixed_rate_ops,
-			&gate->hw, &clk_gate_ops,
-			CLK_IS_ROOT);
-
-	if (IS_ERR(clk))
-		goto err_free_gate;
-
-	of_clk_add_provider(node, of_clk_src_simple_get, clk);
-	clk_register_clkdev(clk, clk_name, NULL);
-
-	return;
-
-err_free_gate:
-	kfree(gate);
-err_free_fixed:
-	kfree(fixed);
-}
-CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-a10-osc-clk", sun4i_osc_clk_setup);
-
-
-
-/**
  * sun4i_get_pll1_factors() - calculates n, k, m, p factors for PLL1
  * PLL1 rate is calculated as follows
  * rate = (parent_rate * n * (k + 1) >> p) / (m + 1);
@@ -408,104 +351,6 @@
 	*p = calcp;
 }
 
-
-
-/**
- * sun7i_a20_gmac_clk_setup - Setup function for A20/A31 GMAC clock module
- *
- * This clock looks something like this
- *                               ________________________
- *  MII TX clock from PHY >-----|___________    _________|----> to GMAC core
- *  GMAC Int. RGMII TX clk >----|___________\__/__gate---|----> to PHY
- *  Ext. 125MHz RGMII TX clk >--|__divider__/            |
- *                              |________________________|
- *
- * The external 125 MHz reference is optional, i.e. GMAC can use its
- * internal TX clock just fine. The A31 GMAC clock module does not have
- * the divider controls for the external reference.
- *
- * To keep it simple, let the GMAC use either the MII TX clock for MII mode,
- * and its internal TX clock for GMII and RGMII modes. The GMAC driver should
- * select the appropriate source and gate/ungate the output to the PHY.
- *
- * Only the GMAC should use this clock. Altering the clock so that it doesn't
- * match the GMAC's operation parameters will result in the GMAC not being
- * able to send traffic out. The GMAC driver should set the clock rate and
- * enable/disable this clock to configure the required state. The clock
- * driver then responds by auto-reparenting the clock.
- */
-
-#define SUN7I_A20_GMAC_GPIT	2
-#define SUN7I_A20_GMAC_MASK	0x3
-#define SUN7I_A20_GMAC_PARENTS	2
-
-static void __init sun7i_a20_gmac_clk_setup(struct device_node *node)
-{
-	struct clk *clk;
-	struct clk_mux *mux;
-	struct clk_gate *gate;
-	const char *clk_name = node->name;
-	const char *parents[SUN7I_A20_GMAC_PARENTS];
-	void *reg;
-
-	if (of_property_read_string(node, "clock-output-names", &clk_name))
-		return;
-
-	/* allocate mux and gate clock structs */
-	mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
-	if (!mux)
-		return;
-
-	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
-	if (!gate)
-		goto free_mux;
-
-	/* gmac clock requires exactly 2 parents */
-	parents[0] = of_clk_get_parent_name(node, 0);
-	parents[1] = of_clk_get_parent_name(node, 1);
-	if (!parents[0] || !parents[1])
-		goto free_gate;
-
-	reg = of_iomap(node, 0);
-	if (!reg)
-		goto free_gate;
-
-	/* set up gate and fixed rate properties */
-	gate->reg = reg;
-	gate->bit_idx = SUN7I_A20_GMAC_GPIT;
-	gate->lock = &clk_lock;
-	mux->reg = reg;
-	mux->mask = SUN7I_A20_GMAC_MASK;
-	mux->flags = CLK_MUX_INDEX_BIT;
-	mux->lock = &clk_lock;
-
-	clk = clk_register_composite(NULL, clk_name,
-			parents, SUN7I_A20_GMAC_PARENTS,
-			&mux->hw, &clk_mux_ops,
-			NULL, NULL,
-			&gate->hw, &clk_gate_ops,
-			0);
-
-	if (IS_ERR(clk))
-		goto iounmap_reg;
-
-	of_clk_add_provider(node, of_clk_src_simple_get, clk);
-	clk_register_clkdev(clk, clk_name, NULL);
-
-	return;
-
-iounmap_reg:
-	iounmap(reg);
-free_gate:
-	kfree(gate);
-free_mux:
-	kfree(mux);
-}
-CLK_OF_DECLARE(sun7i_a20_gmac, "allwinner,sun7i-a20-gmac-clk",
-		sun7i_a20_gmac_clk_setup);
-
-
-
 /**
  * clk_sunxi_mmc_phase_control() - configures MMC clock phase control
  */
@@ -1009,6 +854,11 @@
 	.reset_mask = 0x03,
 };
 
+static const struct gates_data sun6i_a31_usb_gates_data __initconst = {
+	.mask = { BIT(18) | BIT(17) | BIT(16) | BIT(10) | BIT(9) | BIT(8) },
+	.reset_mask = BIT(2) | BIT(1) | BIT(0),
+};
+
 static void __init sunxi_gates_clk_setup(struct device_node *node,
 					 struct gates_data *data)
 {
@@ -1304,6 +1154,7 @@
 	{.compatible = "allwinner,sun6i-a31-apb2-gates-clk", .data = &sun6i_a31_apb2_gates_data,},
 	{.compatible = "allwinner,sun4i-a10-usb-clk", .data = &sun4i_a10_usb_gates_data,},
 	{.compatible = "allwinner,sun5i-a13-usb-clk", .data = &sun5i_a13_usb_gates_data,},
+	{.compatible = "allwinner,sun6i-a31-usb-clk", .data = &sun6i_a31_usb_gates_data,},
 	{}
 };
 
@@ -1321,33 +1172,10 @@
 	}
 }
 
-/**
- * System clock protection
- *
- * By enabling these critical clocks, we prevent their accidental gating
- * by the framework
- */
-static void __init sunxi_clock_protect(void)
+static void __init sunxi_init_clocks(const char *clocks[], int nclocks)
 {
-	struct clk *clk;
+	unsigned int i;
 
-	/* memory bus clock - sun5i+ */
-	clk = clk_get(NULL, "mbus");
-	if (!IS_ERR(clk)) {
-		clk_prepare_enable(clk);
-		clk_put(clk);
-	}
-
-	/* DDR clock - sun4i+ */
-	clk = clk_get(NULL, "pll5_ddr");
-	if (!IS_ERR(clk)) {
-		clk_prepare_enable(clk);
-		clk_put(clk);
-	}
-}
-
-static void __init sunxi_init_clocks(struct device_node *np)
-{
 	/* Register factor clocks */
 	of_sunxi_table_clock_setup(clk_factors_match, sunxi_factors_clk_setup);
 
@@ -1363,11 +1191,48 @@
 	/* Register gate clocks */
 	of_sunxi_table_clock_setup(clk_gates_match, sunxi_gates_clk_setup);
 
-	/* Enable core system clocks */
-	sunxi_clock_protect();
+	/* Protect the clocks that needs to stay on */
+	for (i = 0; i < nclocks; i++) {
+		struct clk *clk = clk_get(NULL, clocks[i]);
+
+		if (!IS_ERR(clk))
+			clk_prepare_enable(clk);
+	}
 }
-CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sunxi_init_clocks);
-CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sunxi_init_clocks);
-CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sunxi_init_clocks);
-CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sunxi_init_clocks);
-CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sunxi_init_clocks);
+
+static const char *sun4i_a10_critical_clocks[] __initdata = {
+	"pll5_ddr",
+};
+
+static void __init sun4i_a10_init_clocks(struct device_node *node)
+{
+	sunxi_init_clocks(sun4i_a10_critical_clocks,
+			  ARRAY_SIZE(sun4i_a10_critical_clocks));
+}
+CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sun4i_a10_init_clocks);
+
+static const char *sun5i_critical_clocks[] __initdata = {
+	"mbus",
+	"pll5_ddr",
+};
+
+static void __init sun5i_init_clocks(struct device_node *node)
+{
+	sunxi_init_clocks(sun5i_critical_clocks,
+			  ARRAY_SIZE(sun5i_critical_clocks));
+}
+CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sun5i_init_clocks);
+CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sun5i_init_clocks);
+CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sun5i_init_clocks);
+
+static const char *sun6i_critical_clocks[] __initdata = {
+	"cpu",
+	"ahb1_sdram",
+};
+
+static void __init sun6i_init_clocks(struct device_node *node)
+{
+	sunxi_init_clocks(sun6i_critical_clocks,
+			  ARRAY_SIZE(sun6i_critical_clocks));
+}
+CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sun6i_init_clocks);
diff --git a/drivers/clk/ti/Makefile b/drivers/clk/ti/Makefile
index 4319d40..ed4d0aa 100644
--- a/drivers/clk/ti/Makefile
+++ b/drivers/clk/ti/Makefile
@@ -3,9 +3,11 @@
 clk-common				= dpll.o composite.o divider.o gate.o \
 					  fixed-factor.o mux.o apll.o
 obj-$(CONFIG_SOC_AM33XX)		+= $(clk-common) clk-33xx.o
+obj-$(CONFIG_ARCH_OMAP2)		+= $(clk-common) interface.o clk-2xxx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= $(clk-common) interface.o clk-3xxx.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(clk-common) clk-44xx.o
 obj-$(CONFIG_SOC_OMAP5)			+= $(clk-common) clk-54xx.o
-obj-$(CONFIG_SOC_DRA7XX)		+= $(clk-common) clk-7xx.o
+obj-$(CONFIG_SOC_DRA7XX)		+= $(clk-common) clk-7xx.o \
+					   clk-dra7-atl.o
 obj-$(CONFIG_SOC_AM43XX)		+= $(clk-common) clk-43xx.o
 endif
diff --git a/drivers/clk/ti/apll.c b/drivers/clk/ti/apll.c
index b986f61..5428c9c 100644
--- a/drivers/clk/ti/apll.c
+++ b/drivers/clk/ti/apll.c
@@ -221,3 +221,184 @@
 	kfree(init);
 }
 CLK_OF_DECLARE(dra7_apll_clock, "ti,dra7-apll-clock", of_dra7_apll_setup);
+
+#define OMAP2_EN_APLL_LOCKED	0x3
+#define OMAP2_EN_APLL_STOPPED	0x0
+
+static int omap2_apll_is_enabled(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+	v &= ad->enable_mask;
+
+	v >>= __ffs(ad->enable_mask);
+
+	return v == OMAP2_EN_APLL_LOCKED ? 1 : 0;
+}
+
+static unsigned long omap2_apll_recalc(struct clk_hw *hw,
+				       unsigned long parent_rate)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+
+	if (omap2_apll_is_enabled(hw))
+		return clk->fixed_rate;
+
+	return 0;
+}
+
+static int omap2_apll_enable(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+	int i = 0;
+
+	v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+	v &= ~ad->enable_mask;
+	v |= OMAP2_EN_APLL_LOCKED << __ffs(ad->enable_mask);
+	ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+
+	while (1) {
+		v = ti_clk_ll_ops->clk_readl(ad->idlest_reg);
+		if (v & ad->idlest_mask)
+			break;
+		if (i > MAX_APLL_WAIT_TRIES)
+			break;
+		i++;
+		udelay(1);
+	}
+
+	if (i == MAX_APLL_WAIT_TRIES) {
+		pr_warn("%s failed to transition to locked\n",
+			__clk_get_name(clk->hw.clk));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void omap2_apll_disable(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+	v &= ~ad->enable_mask;
+	v |= OMAP2_EN_APLL_STOPPED << __ffs(ad->enable_mask);
+	ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+}
+
+static struct clk_ops omap2_apll_ops = {
+	.enable		= &omap2_apll_enable,
+	.disable	= &omap2_apll_disable,
+	.is_enabled	= &omap2_apll_is_enabled,
+	.recalc_rate	= &omap2_apll_recalc,
+};
+
+static void omap2_apll_set_autoidle(struct clk_hw_omap *clk, u32 val)
+{
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(ad->autoidle_reg);
+	v &= ~ad->autoidle_mask;
+	v |= val << __ffs(ad->autoidle_mask);
+	ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+}
+
+#define OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP	0x3
+#define OMAP2_APLL_AUTOIDLE_DISABLE		0x0
+
+static void omap2_apll_allow_idle(struct clk_hw_omap *clk)
+{
+	omap2_apll_set_autoidle(clk, OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP);
+}
+
+static void omap2_apll_deny_idle(struct clk_hw_omap *clk)
+{
+	omap2_apll_set_autoidle(clk, OMAP2_APLL_AUTOIDLE_DISABLE);
+}
+
+static struct clk_hw_omap_ops omap2_apll_hwops = {
+	.allow_idle	= &omap2_apll_allow_idle,
+	.deny_idle	= &omap2_apll_deny_idle,
+};
+
+static void __init of_omap2_apll_setup(struct device_node *node)
+{
+	struct dpll_data *ad = NULL;
+	struct clk_hw_omap *clk_hw = NULL;
+	struct clk_init_data *init = NULL;
+	struct clk *clk;
+	const char *parent_name;
+	u32 val;
+
+	ad = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
+	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
+	init = kzalloc(sizeof(*init), GFP_KERNEL);
+
+	if (!ad || !clk_hw || !init)
+		goto cleanup;
+
+	clk_hw->dpll_data = ad;
+	clk_hw->hw.init = init;
+	init->ops = &omap2_apll_ops;
+	init->name = node->name;
+	clk_hw->ops = &omap2_apll_hwops;
+
+	init->num_parents = of_clk_get_parent_count(node);
+	if (init->num_parents != 1) {
+		pr_err("%s must have one parent\n", node->name);
+		goto cleanup;
+	}
+
+	parent_name = of_clk_get_parent_name(node, 0);
+	init->parent_names = &parent_name;
+
+	if (of_property_read_u32(node, "ti,clock-frequency", &val)) {
+		pr_err("%s missing clock-frequency\n", node->name);
+		goto cleanup;
+	}
+	clk_hw->fixed_rate = val;
+
+	if (of_property_read_u32(node, "ti,bit-shift", &val)) {
+		pr_err("%s missing bit-shift\n", node->name);
+		goto cleanup;
+	}
+
+	clk_hw->enable_bit = val;
+	ad->enable_mask = 0x3 << val;
+	ad->autoidle_mask = 0x3 << val;
+
+	if (of_property_read_u32(node, "ti,idlest-shift", &val)) {
+		pr_err("%s missing idlest-shift\n", node->name);
+		goto cleanup;
+	}
+
+	ad->idlest_mask = 1 << val;
+
+	ad->control_reg = ti_clk_get_reg_addr(node, 0);
+	ad->autoidle_reg = ti_clk_get_reg_addr(node, 1);
+	ad->idlest_reg = ti_clk_get_reg_addr(node, 2);
+
+	if (!ad->control_reg || !ad->autoidle_reg || !ad->idlest_reg)
+		goto cleanup;
+
+	clk = clk_register(NULL, &clk_hw->hw);
+	if (!IS_ERR(clk)) {
+		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		kfree(init);
+		return;
+	}
+cleanup:
+	kfree(ad);
+	kfree(clk_hw);
+	kfree(init);
+}
+CLK_OF_DECLARE(omap2_apll_clock, "ti,omap2-apll-clock",
+	       of_omap2_apll_setup);
diff --git a/drivers/clk/ti/clk-2xxx.c b/drivers/clk/ti/clk-2xxx.c
new file mode 100644
index 0000000..c808ab3
--- /dev/null
+++ b/drivers/clk/ti/clk-2xxx.c
@@ -0,0 +1,256 @@
+/*
+ * OMAP2 Clock init
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc
+ *     Tero Kristo (t-kristo@ti.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/clk-provider.h>
+#include <linux/clk/ti.h>
+
+static struct ti_dt_clk omap2xxx_clks[] = {
+	DT_CLK(NULL, "func_32k_ck", "func_32k_ck"),
+	DT_CLK(NULL, "secure_32k_ck", "secure_32k_ck"),
+	DT_CLK(NULL, "virt_12m_ck", "virt_12m_ck"),
+	DT_CLK(NULL, "virt_13m_ck", "virt_13m_ck"),
+	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
+	DT_CLK(NULL, "virt_26m_ck", "virt_26m_ck"),
+	DT_CLK(NULL, "aplls_clkin_ck", "aplls_clkin_ck"),
+	DT_CLK(NULL, "aplls_clkin_x2_ck", "aplls_clkin_x2_ck"),
+	DT_CLK(NULL, "osc_ck", "osc_ck"),
+	DT_CLK(NULL, "sys_ck", "sys_ck"),
+	DT_CLK(NULL, "alt_ck", "alt_ck"),
+	DT_CLK(NULL, "mcbsp_clks", "mcbsp_clks"),
+	DT_CLK(NULL, "dpll_ck", "dpll_ck"),
+	DT_CLK(NULL, "apll96_ck", "apll96_ck"),
+	DT_CLK(NULL, "apll54_ck", "apll54_ck"),
+	DT_CLK(NULL, "func_54m_ck", "func_54m_ck"),
+	DT_CLK(NULL, "core_ck", "core_ck"),
+	DT_CLK(NULL, "func_96m_ck", "func_96m_ck"),
+	DT_CLK(NULL, "func_48m_ck", "func_48m_ck"),
+	DT_CLK(NULL, "func_12m_ck", "func_12m_ck"),
+	DT_CLK(NULL, "sys_clkout_src", "sys_clkout_src"),
+	DT_CLK(NULL, "sys_clkout", "sys_clkout"),
+	DT_CLK(NULL, "emul_ck", "emul_ck"),
+	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
+	DT_CLK(NULL, "dsp_fck", "dsp_fck"),
+	DT_CLK(NULL, "gfx_3d_fck", "gfx_3d_fck"),
+	DT_CLK(NULL, "gfx_2d_fck", "gfx_2d_fck"),
+	DT_CLK(NULL, "gfx_ick", "gfx_ick"),
+	DT_CLK("omapdss_dss", "ick", "dss_ick"),
+	DT_CLK(NULL, "dss_ick", "dss_ick"),
+	DT_CLK(NULL, "dss1_fck", "dss1_fck"),
+	DT_CLK(NULL, "dss2_fck", "dss2_fck"),
+	DT_CLK(NULL, "dss_54m_fck", "dss_54m_fck"),
+	DT_CLK(NULL, "core_l3_ck", "core_l3_ck"),
+	DT_CLK(NULL, "ssi_fck", "ssi_ssr_sst_fck"),
+	DT_CLK(NULL, "usb_l4_ick", "usb_l4_ick"),
+	DT_CLK(NULL, "l4_ck", "l4_ck"),
+	DT_CLK(NULL, "ssi_l4_ick", "ssi_l4_ick"),
+	DT_CLK(NULL, "gpt1_ick", "gpt1_ick"),
+	DT_CLK(NULL, "gpt1_fck", "gpt1_fck"),
+	DT_CLK(NULL, "gpt2_ick", "gpt2_ick"),
+	DT_CLK(NULL, "gpt2_fck", "gpt2_fck"),
+	DT_CLK(NULL, "gpt3_ick", "gpt3_ick"),
+	DT_CLK(NULL, "gpt3_fck", "gpt3_fck"),
+	DT_CLK(NULL, "gpt4_ick", "gpt4_ick"),
+	DT_CLK(NULL, "gpt4_fck", "gpt4_fck"),
+	DT_CLK(NULL, "gpt5_ick", "gpt5_ick"),
+	DT_CLK(NULL, "gpt5_fck", "gpt5_fck"),
+	DT_CLK(NULL, "gpt6_ick", "gpt6_ick"),
+	DT_CLK(NULL, "gpt6_fck", "gpt6_fck"),
+	DT_CLK(NULL, "gpt7_ick", "gpt7_ick"),
+	DT_CLK(NULL, "gpt7_fck", "gpt7_fck"),
+	DT_CLK(NULL, "gpt8_ick", "gpt8_ick"),
+	DT_CLK(NULL, "gpt8_fck", "gpt8_fck"),
+	DT_CLK(NULL, "gpt9_ick", "gpt9_ick"),
+	DT_CLK(NULL, "gpt9_fck", "gpt9_fck"),
+	DT_CLK(NULL, "gpt10_ick", "gpt10_ick"),
+	DT_CLK(NULL, "gpt10_fck", "gpt10_fck"),
+	DT_CLK(NULL, "gpt11_ick", "gpt11_ick"),
+	DT_CLK(NULL, "gpt11_fck", "gpt11_fck"),
+	DT_CLK(NULL, "gpt12_ick", "gpt12_ick"),
+	DT_CLK(NULL, "gpt12_fck", "gpt12_fck"),
+	DT_CLK("omap-mcbsp.1", "ick", "mcbsp1_ick"),
+	DT_CLK(NULL, "mcbsp1_ick", "mcbsp1_ick"),
+	DT_CLK(NULL, "mcbsp1_fck", "mcbsp1_fck"),
+	DT_CLK("omap-mcbsp.2", "ick", "mcbsp2_ick"),
+	DT_CLK(NULL, "mcbsp2_ick", "mcbsp2_ick"),
+	DT_CLK(NULL, "mcbsp2_fck", "mcbsp2_fck"),
+	DT_CLK("omap2_mcspi.1", "ick", "mcspi1_ick"),
+	DT_CLK(NULL, "mcspi1_ick", "mcspi1_ick"),
+	DT_CLK(NULL, "mcspi1_fck", "mcspi1_fck"),
+	DT_CLK("omap2_mcspi.2", "ick", "mcspi2_ick"),
+	DT_CLK(NULL, "mcspi2_ick", "mcspi2_ick"),
+	DT_CLK(NULL, "mcspi2_fck", "mcspi2_fck"),
+	DT_CLK(NULL, "uart1_ick", "uart1_ick"),
+	DT_CLK(NULL, "uart1_fck", "uart1_fck"),
+	DT_CLK(NULL, "uart2_ick", "uart2_ick"),
+	DT_CLK(NULL, "uart2_fck", "uart2_fck"),
+	DT_CLK(NULL, "uart3_ick", "uart3_ick"),
+	DT_CLK(NULL, "uart3_fck", "uart3_fck"),
+	DT_CLK(NULL, "gpios_ick", "gpios_ick"),
+	DT_CLK(NULL, "gpios_fck", "gpios_fck"),
+	DT_CLK("omap_wdt", "ick", "mpu_wdt_ick"),
+	DT_CLK(NULL, "mpu_wdt_ick", "mpu_wdt_ick"),
+	DT_CLK(NULL, "mpu_wdt_fck", "mpu_wdt_fck"),
+	DT_CLK(NULL, "sync_32k_ick", "sync_32k_ick"),
+	DT_CLK(NULL, "wdt1_ick", "wdt1_ick"),
+	DT_CLK(NULL, "omapctrl_ick", "omapctrl_ick"),
+	DT_CLK("omap24xxcam", "fck", "cam_fck"),
+	DT_CLK(NULL, "cam_fck", "cam_fck"),
+	DT_CLK("omap24xxcam", "ick", "cam_ick"),
+	DT_CLK(NULL, "cam_ick", "cam_ick"),
+	DT_CLK(NULL, "mailboxes_ick", "mailboxes_ick"),
+	DT_CLK(NULL, "wdt4_ick", "wdt4_ick"),
+	DT_CLK(NULL, "wdt4_fck", "wdt4_fck"),
+	DT_CLK(NULL, "mspro_ick", "mspro_ick"),
+	DT_CLK(NULL, "mspro_fck", "mspro_fck"),
+	DT_CLK(NULL, "fac_ick", "fac_ick"),
+	DT_CLK(NULL, "fac_fck", "fac_fck"),
+	DT_CLK("omap_hdq.0", "ick", "hdq_ick"),
+	DT_CLK(NULL, "hdq_ick", "hdq_ick"),
+	DT_CLK("omap_hdq.0", "fck", "hdq_fck"),
+	DT_CLK(NULL, "hdq_fck", "hdq_fck"),
+	DT_CLK("omap_i2c.1", "ick", "i2c1_ick"),
+	DT_CLK(NULL, "i2c1_ick", "i2c1_ick"),
+	DT_CLK("omap_i2c.2", "ick", "i2c2_ick"),
+	DT_CLK(NULL, "i2c2_ick", "i2c2_ick"),
+	DT_CLK(NULL, "gpmc_fck", "gpmc_fck"),
+	DT_CLK(NULL, "sdma_fck", "sdma_fck"),
+	DT_CLK(NULL, "sdma_ick", "sdma_ick"),
+	DT_CLK(NULL, "sdrc_ick", "sdrc_ick"),
+	DT_CLK(NULL, "des_ick", "des_ick"),
+	DT_CLK("omap-sham", "ick", "sha_ick"),
+	DT_CLK(NULL, "sha_ick", "sha_ick"),
+	DT_CLK("omap_rng", "ick", "rng_ick"),
+	DT_CLK(NULL, "rng_ick", "rng_ick"),
+	DT_CLK("omap-aes", "ick", "aes_ick"),
+	DT_CLK(NULL, "aes_ick", "aes_ick"),
+	DT_CLK(NULL, "pka_ick", "pka_ick"),
+	DT_CLK(NULL, "usb_fck", "usb_fck"),
+	DT_CLK(NULL, "timer_32k_ck", "func_32k_ck"),
+	DT_CLK(NULL, "timer_sys_ck", "sys_ck"),
+	DT_CLK(NULL, "timer_ext_ck", "alt_ck"),
+	{ .node_name = NULL },
+};
+
+static struct ti_dt_clk omap2420_clks[] = {
+	DT_CLK(NULL, "sys_clkout2_src", "sys_clkout2_src"),
+	DT_CLK(NULL, "sys_clkout2", "sys_clkout2"),
+	DT_CLK(NULL, "dsp_ick", "dsp_ick"),
+	DT_CLK(NULL, "iva1_ifck", "iva1_ifck"),
+	DT_CLK(NULL, "iva1_mpu_int_ifck", "iva1_mpu_int_ifck"),
+	DT_CLK(NULL, "wdt3_ick", "wdt3_ick"),
+	DT_CLK(NULL, "wdt3_fck", "wdt3_fck"),
+	DT_CLK("mmci-omap.0", "ick", "mmc_ick"),
+	DT_CLK(NULL, "mmc_ick", "mmc_ick"),
+	DT_CLK("mmci-omap.0", "fck", "mmc_fck"),
+	DT_CLK(NULL, "mmc_fck", "mmc_fck"),
+	DT_CLK(NULL, "eac_ick", "eac_ick"),
+	DT_CLK(NULL, "eac_fck", "eac_fck"),
+	DT_CLK(NULL, "i2c1_fck", "i2c1_fck"),
+	DT_CLK(NULL, "i2c2_fck", "i2c2_fck"),
+	DT_CLK(NULL, "vlynq_ick", "vlynq_ick"),
+	DT_CLK(NULL, "vlynq_fck", "vlynq_fck"),
+	DT_CLK("musb-hdrc", "fck", "osc_ck"),
+	{ .node_name = NULL },
+};
+
+static struct ti_dt_clk omap2430_clks[] = {
+	DT_CLK("twl", "fck", "osc_ck"),
+	DT_CLK(NULL, "iva2_1_ick", "iva2_1_ick"),
+	DT_CLK(NULL, "mdm_ick", "mdm_ick"),
+	DT_CLK(NULL, "mdm_osc_ck", "mdm_osc_ck"),
+	DT_CLK("omap-mcbsp.3", "ick", "mcbsp3_ick"),
+	DT_CLK(NULL, "mcbsp3_ick", "mcbsp3_ick"),
+	DT_CLK(NULL, "mcbsp3_fck", "mcbsp3_fck"),
+	DT_CLK("omap-mcbsp.4", "ick", "mcbsp4_ick"),
+	DT_CLK(NULL, "mcbsp4_ick", "mcbsp4_ick"),
+	DT_CLK(NULL, "mcbsp4_fck", "mcbsp4_fck"),
+	DT_CLK("omap-mcbsp.5", "ick", "mcbsp5_ick"),
+	DT_CLK(NULL, "mcbsp5_ick", "mcbsp5_ick"),
+	DT_CLK(NULL, "mcbsp5_fck", "mcbsp5_fck"),
+	DT_CLK("omap2_mcspi.3", "ick", "mcspi3_ick"),
+	DT_CLK(NULL, "mcspi3_ick", "mcspi3_ick"),
+	DT_CLK(NULL, "mcspi3_fck", "mcspi3_fck"),
+	DT_CLK(NULL, "icr_ick", "icr_ick"),
+	DT_CLK(NULL, "i2chs1_fck", "i2chs1_fck"),
+	DT_CLK(NULL, "i2chs2_fck", "i2chs2_fck"),
+	DT_CLK("musb-omap2430", "ick", "usbhs_ick"),
+	DT_CLK(NULL, "usbhs_ick", "usbhs_ick"),
+	DT_CLK("omap_hsmmc.0", "ick", "mmchs1_ick"),
+	DT_CLK(NULL, "mmchs1_ick", "mmchs1_ick"),
+	DT_CLK(NULL, "mmchs1_fck", "mmchs1_fck"),
+	DT_CLK("omap_hsmmc.1", "ick", "mmchs2_ick"),
+	DT_CLK(NULL, "mmchs2_ick", "mmchs2_ick"),
+	DT_CLK(NULL, "mmchs2_fck", "mmchs2_fck"),
+	DT_CLK(NULL, "gpio5_ick", "gpio5_ick"),
+	DT_CLK(NULL, "gpio5_fck", "gpio5_fck"),
+	DT_CLK(NULL, "mdm_intc_ick", "mdm_intc_ick"),
+	DT_CLK("omap_hsmmc.0", "mmchsdb_fck", "mmchsdb1_fck"),
+	DT_CLK(NULL, "mmchsdb1_fck", "mmchsdb1_fck"),
+	DT_CLK("omap_hsmmc.1", "mmchsdb_fck", "mmchsdb2_fck"),
+	DT_CLK(NULL, "mmchsdb2_fck", "mmchsdb2_fck"),
+	{ .node_name = NULL },
+};
+
+static const char *enable_init_clks[] = {
+	"apll96_ck",
+	"apll54_ck",
+	"sync_32k_ick",
+	"omapctrl_ick",
+	"gpmc_fck",
+	"sdrc_ick",
+};
+
+enum {
+	OMAP2_SOC_OMAP2420,
+	OMAP2_SOC_OMAP2430,
+};
+
+static int __init omap2xxx_dt_clk_init(int soc_type)
+{
+	ti_dt_clocks_register(omap2xxx_clks);
+
+	if (soc_type == OMAP2_SOC_OMAP2420)
+		ti_dt_clocks_register(omap2420_clks);
+	else
+		ti_dt_clocks_register(omap2430_clks);
+
+	omap2xxx_clkt_vps_init();
+
+	omap2_clk_disable_autoidle_all();
+
+	omap2_clk_enable_init_clocks(enable_init_clks,
+				     ARRAY_SIZE(enable_init_clks));
+
+	pr_info("Clocking rate (Crystal/DPLL/MPU): %ld.%01ld/%ld/%ld MHz\n",
+		(clk_get_rate(clk_get_sys(NULL, "sys_ck")) / 1000000),
+		(clk_get_rate(clk_get_sys(NULL, "sys_ck")) / 100000) % 10,
+		(clk_get_rate(clk_get_sys(NULL, "dpll_ck")) / 1000000),
+		(clk_get_rate(clk_get_sys(NULL, "mpu_ck")) / 1000000));
+
+	return 0;
+}
+
+int __init omap2420_dt_clk_init(void)
+{
+	return omap2xxx_dt_clk_init(OMAP2_SOC_OMAP2420);
+}
+
+int __init omap2430_dt_clk_init(void)
+{
+	return omap2xxx_dt_clk_init(OMAP2_SOC_OMAP2430);
+}
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 08f3d1b..5e18399 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -240,6 +240,12 @@
 	if (rc)
 		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
+	abe_dpll = clk_get_sys(NULL, "dpll_abe_m2x2_ck");
+	if (!rc)
+		rc = clk_set_rate(abe_dpll, OMAP5_DPLL_ABE_DEFFREQ * 2);
+	if (rc)
+		pr_err("%s: failed to configure ABE m2x2 DPLL!\n", __func__);
+
 	usb_dpll = clk_get_sys(NULL, "dpll_usb_ck");
 	rc = clk_set_rate(usb_dpll, OMAP5_DPLL_USB_DEFFREQ);
 	if (rc)
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index f7e4073..e158133 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -24,7 +24,7 @@
 	DT_CLK(NULL, "atl_clkin0_ck", "atl_clkin0_ck"),
 	DT_CLK(NULL, "atl_clkin1_ck", "atl_clkin1_ck"),
 	DT_CLK(NULL, "atl_clkin2_ck", "atl_clkin2_ck"),
-	DT_CLK(NULL, "atlclkin3_ck", "atlclkin3_ck"),
+	DT_CLK(NULL, "atl_clkin3_ck", "atl_clkin3_ck"),
 	DT_CLK(NULL, "hdmi_clkin_ck", "hdmi_clkin_ck"),
 	DT_CLK(NULL, "mlb_clkin_ck", "mlb_clkin_ck"),
 	DT_CLK(NULL, "mlbp_clkin_ck", "mlbp_clkin_ck"),
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
new file mode 100644
index 0000000..4a65b41
--- /dev/null
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -0,0 +1,312 @@
+/*
+ * DRA7 ATL (Audio Tracking Logic) clock driver
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc.
+ *
+ * Peter Ujfalusi <peter.ujfalusi@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/clk-provider.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#define DRA7_ATL_INSTANCES	4
+
+#define DRA7_ATL_PPMR_REG(id)		(0x200 + (id * 0x80))
+#define DRA7_ATL_BBSR_REG(id)		(0x204 + (id * 0x80))
+#define DRA7_ATL_ATLCR_REG(id)		(0x208 + (id * 0x80))
+#define DRA7_ATL_SWEN_REG(id)		(0x210 + (id * 0x80))
+#define DRA7_ATL_BWSMUX_REG(id)		(0x214 + (id * 0x80))
+#define DRA7_ATL_AWSMUX_REG(id)		(0x218 + (id * 0x80))
+#define DRA7_ATL_PCLKMUX_REG(id)	(0x21c + (id * 0x80))
+
+#define DRA7_ATL_SWEN			BIT(0)
+#define DRA7_ATL_DIVIDER_MASK		(0x1f)
+#define DRA7_ATL_PCLKMUX		BIT(0)
+struct dra7_atl_clock_info;
+
+struct dra7_atl_desc {
+	struct clk *clk;
+	struct clk_hw hw;
+	struct dra7_atl_clock_info *cinfo;
+	int id;
+
+	bool probed;		/* the driver for the IP has been loaded */
+	bool valid;		/* configured */
+	bool enabled;
+	u32 bws;		/* Baseband Word Select Mux */
+	u32 aws;		/* Audio Word Select Mux */
+	u32 divider;		/* Cached divider value */
+};
+
+struct dra7_atl_clock_info {
+	struct device *dev;
+	void __iomem *iobase;
+
+	struct dra7_atl_desc *cdesc;
+};
+
+#define to_atl_desc(_hw)	container_of(_hw, struct dra7_atl_desc, hw)
+
+static inline void atl_write(struct dra7_atl_clock_info *cinfo, u32 reg,
+			     u32 val)
+{
+	__raw_writel(val, cinfo->iobase + reg);
+}
+
+static inline int atl_read(struct dra7_atl_clock_info *cinfo, u32 reg)
+{
+	return __raw_readl(cinfo->iobase + reg);
+}
+
+static int atl_clk_enable(struct clk_hw *hw)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	if (!cdesc->probed)
+		goto out;
+
+	if (unlikely(!cdesc->valid))
+		dev_warn(cdesc->cinfo->dev, "atl%d has not been configured\n",
+			 cdesc->id);
+	pm_runtime_get_sync(cdesc->cinfo->dev);
+
+	atl_write(cdesc->cinfo, DRA7_ATL_ATLCR_REG(cdesc->id),
+		  cdesc->divider - 1);
+	atl_write(cdesc->cinfo, DRA7_ATL_SWEN_REG(cdesc->id), DRA7_ATL_SWEN);
+
+out:
+	cdesc->enabled = true;
+
+	return 0;
+}
+
+static void atl_clk_disable(struct clk_hw *hw)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	if (!cdesc->probed)
+		goto out;
+
+	atl_write(cdesc->cinfo, DRA7_ATL_SWEN_REG(cdesc->id), 0);
+	pm_runtime_put_sync(cdesc->cinfo->dev);
+
+out:
+	cdesc->enabled = false;
+}
+
+static int atl_clk_is_enabled(struct clk_hw *hw)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	return cdesc->enabled;
+}
+
+static unsigned long atl_clk_recalc_rate(struct clk_hw *hw,
+					 unsigned long parent_rate)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	return parent_rate / cdesc->divider;
+}
+
+static long atl_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long *parent_rate)
+{
+	unsigned divider;
+
+	divider = (*parent_rate + rate / 2) / rate;
+	if (divider > DRA7_ATL_DIVIDER_MASK + 1)
+		divider = DRA7_ATL_DIVIDER_MASK + 1;
+
+	return *parent_rate / divider;
+}
+
+static int atl_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+			    unsigned long parent_rate)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+	u32 divider;
+
+	divider = ((parent_rate + rate / 2) / rate) - 1;
+	if (divider > DRA7_ATL_DIVIDER_MASK)
+		divider = DRA7_ATL_DIVIDER_MASK;
+
+	cdesc->divider = divider + 1;
+
+	return 0;
+}
+
+const struct clk_ops atl_clk_ops = {
+	.enable		= atl_clk_enable,
+	.disable	= atl_clk_disable,
+	.is_enabled	= atl_clk_is_enabled,
+	.recalc_rate	= atl_clk_recalc_rate,
+	.round_rate	= atl_clk_round_rate,
+	.set_rate	= atl_clk_set_rate,
+};
+
+static void __init of_dra7_atl_clock_setup(struct device_node *node)
+{
+	struct dra7_atl_desc *clk_hw = NULL;
+	struct clk_init_data init = { 0 };
+	const char **parent_names = NULL;
+	struct clk *clk;
+
+	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
+	if (!clk_hw) {
+		pr_err("%s: could not allocate dra7_atl_desc\n", __func__);
+		return;
+	}
+
+	clk_hw->hw.init = &init;
+	clk_hw->divider = 1;
+	init.name = node->name;
+	init.ops = &atl_clk_ops;
+	init.flags = CLK_IGNORE_UNUSED;
+	init.num_parents = of_clk_get_parent_count(node);
+
+	if (init.num_parents != 1) {
+		pr_err("%s: atl clock %s must have 1 parent\n", __func__,
+		       node->name);
+		goto cleanup;
+	}
+
+	parent_names = kzalloc(sizeof(char *), GFP_KERNEL);
+
+	if (!parent_names)
+		goto cleanup;
+
+	parent_names[0] = of_clk_get_parent_name(node, 0);
+
+	init.parent_names = parent_names;
+
+	clk = clk_register(NULL, &clk_hw->hw);
+
+	if (!IS_ERR(clk)) {
+		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		return;
+	}
+cleanup:
+	kfree(parent_names);
+	kfree(clk_hw);
+}
+CLK_OF_DECLARE(dra7_atl_clock, "ti,dra7-atl-clock", of_dra7_atl_clock_setup);
+
+static int of_dra7_atl_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct dra7_atl_clock_info *cinfo;
+	int i;
+	int ret = 0;
+
+	if (!node)
+		return -ENODEV;
+
+	cinfo = devm_kzalloc(&pdev->dev, sizeof(*cinfo), GFP_KERNEL);
+	if (!cinfo)
+		return -ENOMEM;
+
+	cinfo->iobase = of_iomap(node, 0);
+	cinfo->dev = &pdev->dev;
+	pm_runtime_enable(cinfo->dev);
+
+	pm_runtime_get_sync(cinfo->dev);
+	atl_write(cinfo, DRA7_ATL_PCLKMUX_REG(0), DRA7_ATL_PCLKMUX);
+
+	for (i = 0; i < DRA7_ATL_INSTANCES; i++) {
+		struct device_node *cfg_node;
+		char prop[5];
+		struct dra7_atl_desc *cdesc;
+		struct of_phandle_args clkspec;
+		struct clk *clk;
+		int rc;
+
+		rc = of_parse_phandle_with_args(node, "ti,provided-clocks",
+						NULL, i, &clkspec);
+
+		if (rc) {
+			pr_err("%s: failed to lookup atl clock %d\n", __func__,
+			       i);
+			return -EINVAL;
+		}
+
+		clk = of_clk_get_from_provider(&clkspec);
+
+		cdesc = to_atl_desc(__clk_get_hw(clk));
+		cdesc->cinfo = cinfo;
+		cdesc->id = i;
+
+		/* Get configuration for the ATL instances */
+		snprintf(prop, sizeof(prop), "atl%u", i);
+		cfg_node = of_find_node_by_name(node, prop);
+		if (cfg_node) {
+			ret = of_property_read_u32(cfg_node, "bws",
+						   &cdesc->bws);
+			ret |= of_property_read_u32(cfg_node, "aws",
+						    &cdesc->aws);
+			if (!ret) {
+				cdesc->valid = true;
+				atl_write(cinfo, DRA7_ATL_BWSMUX_REG(i),
+					  cdesc->bws);
+				atl_write(cinfo, DRA7_ATL_AWSMUX_REG(i),
+					  cdesc->aws);
+			}
+		}
+
+		cdesc->probed = true;
+		/*
+		 * Enable the clock if it has been asked prior to loading the
+		 * hw driver
+		 */
+		if (cdesc->enabled)
+			atl_clk_enable(__clk_get_hw(clk));
+	}
+	pm_runtime_put_sync(cinfo->dev);
+
+	return ret;
+}
+
+static int of_dra7_atl_clk_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static struct of_device_id of_dra7_atl_clk_match_tbl[] = {
+	{ .compatible = "ti,dra7-atl", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_dra7_atl_clk_match_tbl);
+
+static struct platform_driver dra7_atl_clk_driver = {
+	.driver = {
+		.name = "dra7-atl",
+		.owner = THIS_MODULE,
+		.of_match_table = of_dra7_atl_clk_match_tbl,
+	},
+	.probe = of_dra7_atl_clk_probe,
+	.remove = of_dra7_atl_clk_remove,
+};
+
+module_platform_driver(dra7_atl_clk_driver);
+
+MODULE_DESCRIPTION("Clock driver for DRA7 Audio Tracking Logic");
+MODULE_ALIAS("platform:dra7-atl-clock");
+MODULE_AUTHOR("Peter Ujfalusi <peter.ujfalusi@ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c
index 7e498a4..abd956d 100644
--- a/drivers/clk/ti/dpll.c
+++ b/drivers/clk/ti/dpll.c
@@ -25,8 +25,6 @@
 #undef pr_fmt
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
-#define DPLL_HAS_AUTOIDLE	0x1
-
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
 	defined(CONFIG_SOC_DRA7XX)
 static const struct clk_ops dpll_m4xen_ck_ops = {
@@ -37,21 +35,18 @@
 	.set_rate	= &omap3_noncore_dpll_set_rate,
 	.get_parent	= &omap2_init_dpll_parent,
 };
+#else
+static const struct clk_ops dpll_m4xen_ck_ops = {};
 #endif
 
+#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_ARCH_OMAP4) || \
+	defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX) || \
+	defined(CONFIG_SOC_AM33XX) || defined(CONFIG_SOC_AM43XX)
 static const struct clk_ops dpll_core_ck_ops = {
 	.recalc_rate	= &omap3_dpll_recalc,
 	.get_parent	= &omap2_init_dpll_parent,
 };
 
-#ifdef CONFIG_ARCH_OMAP3
-static const struct clk_ops omap3_dpll_core_ck_ops = {
-	.get_parent	= &omap2_init_dpll_parent,
-	.recalc_rate	= &omap3_dpll_recalc,
-	.round_rate	= &omap2_dpll_round_rate,
-};
-#endif
-
 static const struct clk_ops dpll_ck_ops = {
 	.enable		= &omap3_noncore_dpll_enable,
 	.disable	= &omap3_noncore_dpll_disable,
@@ -67,6 +62,33 @@
 	.round_rate	= &omap2_dpll_round_rate,
 	.set_rate	= &omap3_noncore_dpll_set_rate,
 };
+#else
+static const struct clk_ops dpll_core_ck_ops = {};
+static const struct clk_ops dpll_ck_ops = {};
+static const struct clk_ops dpll_no_gate_ck_ops = {};
+const struct clk_hw_omap_ops clkhwops_omap3_dpll = {};
+#endif
+
+#ifdef CONFIG_ARCH_OMAP2
+static const struct clk_ops omap2_dpll_core_ck_ops = {
+	.get_parent	= &omap2_init_dpll_parent,
+	.recalc_rate	= &omap2_dpllcore_recalc,
+	.round_rate	= &omap2_dpll_round_rate,
+	.set_rate	= &omap2_reprogram_dpllcore,
+};
+#else
+static const struct clk_ops omap2_dpll_core_ck_ops = {};
+#endif
+
+#ifdef CONFIG_ARCH_OMAP3
+static const struct clk_ops omap3_dpll_core_ck_ops = {
+	.get_parent	= &omap2_init_dpll_parent,
+	.recalc_rate	= &omap3_dpll_recalc,
+	.round_rate	= &omap2_dpll_round_rate,
+};
+#else
+static const struct clk_ops omap3_dpll_core_ck_ops = {};
+#endif
 
 #ifdef CONFIG_ARCH_OMAP3
 static const struct clk_ops omap3_dpll_ck_ops = {
@@ -193,14 +215,12 @@
  * @node: device node containing the DPLL info
  * @ops: ops for the DPLL
  * @ddt: DPLL data template to use
- * @init_flags: flags for controlling init types
  *
  * Initializes a DPLL clock from device tree data.
  */
 static void __init of_ti_dpll_setup(struct device_node *node,
 				    const struct clk_ops *ops,
-				    const struct dpll_data *ddt,
-				    u8 init_flags)
+				    const struct dpll_data *ddt)
 {
 	struct clk_hw_omap *clk_hw = NULL;
 	struct clk_init_data *init = NULL;
@@ -241,13 +261,30 @@
 	init->parent_names = parent_names;
 
 	dd->control_reg = ti_clk_get_reg_addr(node, 0);
-	dd->idlest_reg = ti_clk_get_reg_addr(node, 1);
-	dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2);
 
-	if (!dd->control_reg || !dd->idlest_reg || !dd->mult_div1_reg)
+	/*
+	 * Special case for OMAP2 DPLL, register order is different due to
+	 * missing idlest_reg, also clkhwops is different. Detected from
+	 * missing idlest_mask.
+	 */
+	if (!dd->idlest_mask) {
+		dd->mult_div1_reg = ti_clk_get_reg_addr(node, 1);
+#ifdef CONFIG_ARCH_OMAP2
+		clk_hw->ops = &clkhwops_omap2xxx_dpll;
+		omap2xxx_clkt_dpllcore_init(&clk_hw->hw);
+#endif
+	} else {
+		dd->idlest_reg = ti_clk_get_reg_addr(node, 1);
+		if (!dd->idlest_reg)
+			goto cleanup;
+
+		dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2);
+	}
+
+	if (!dd->control_reg || !dd->mult_div1_reg)
 		goto cleanup;
 
-	if (init_flags & DPLL_HAS_AUTOIDLE) {
+	if (dd->autoidle_mask) {
 		dd->autoidle_reg = ti_clk_get_reg_addr(node, 3);
 		if (!dd->autoidle_reg)
 			goto cleanup;
@@ -310,7 +347,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_dpll_clock, "ti,omap3-dpll-clock",
 	       of_ti_omap3_dpll_setup);
@@ -329,7 +366,7 @@
 		.freqsel_mask = 0xf0,
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_core_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_core_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_core_dpll_clock, "ti,omap3-dpll-core-clock",
 	       of_ti_omap3_core_dpll_setup);
@@ -349,7 +386,7 @@
 		.modes = (1 << DPLL_LOW_POWER_STOP) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_per_dpll_clock, "ti,omap3-dpll-per-clock",
 	       of_ti_omap3_per_dpll_setup);
@@ -371,7 +408,7 @@
 		.modes = (1 << DPLL_LOW_POWER_STOP) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_per_jtype_dpll_clock, "ti,omap3-dpll-per-j-type-clock",
 	       of_ti_omap3_per_jtype_dpll_setup);
@@ -391,11 +428,32 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_dpll_clock, "ti,omap4-dpll-clock",
 	       of_ti_omap4_dpll_setup);
 
+static void __init of_ti_omap5_mpu_dpll_setup(struct device_node *node)
+{
+	const struct dpll_data dd = {
+		.idlest_mask = 0x1,
+		.enable_mask = 0x7,
+		.autoidle_mask = 0x7,
+		.mult_mask = 0x7ff << 8,
+		.div1_mask = 0x7f,
+		.max_multiplier = 2047,
+		.max_divider = 128,
+		.dcc_mask = BIT(22),
+		.dcc_rate = 1400000000, /* DCC beyond 1.4GHz */
+		.min_divider = 1,
+		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
+	};
+
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
+}
+CLK_OF_DECLARE(of_ti_omap5_mpu_dpll_clock, "ti,omap5-mpu-dpll-clock",
+	       of_ti_omap5_mpu_dpll_setup);
+
 static void __init of_ti_omap4_core_dpll_setup(struct device_node *node)
 {
 	const struct dpll_data dd = {
@@ -410,7 +468,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_core_dpll_clock, "ti,omap4-dpll-core-clock",
 	       of_ti_omap4_core_dpll_setup);
@@ -433,7 +491,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_m4xen_dpll_clock, "ti,omap4-dpll-m4xen-clock",
 	       of_ti_omap4_m4xen_dpll_setup);
@@ -454,7 +512,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_jtype_dpll_clock, "ti,omap4-dpll-j-type-clock",
 	       of_ti_omap4_jtype_dpll_setup);
@@ -465,7 +523,6 @@
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -474,7 +531,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_no_gate_dpll_clock, "ti,am3-dpll-no-gate-clock",
 	       of_ti_am3_no_gate_dpll_setup);
@@ -484,7 +541,6 @@
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 4095,
@@ -494,7 +550,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_jtype_dpll_clock, "ti,am3-dpll-j-type-clock",
 	       of_ti_am3_jtype_dpll_setup);
@@ -504,7 +560,6 @@
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -514,7 +569,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_no_gate_jtype_dpll_clock,
 	       "ti,am3-dpll-no-gate-j-type-clock",
@@ -525,7 +580,6 @@
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -534,7 +588,7 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_dpll_clock, "ti,am3-dpll-clock", of_ti_am3_dpll_setup);
 
@@ -543,7 +597,6 @@
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -552,7 +605,22 @@
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_core_dpll_clock, "ti,am3-dpll-core-clock",
 	       of_ti_am3_core_dpll_setup);
+
+static void __init of_ti_omap2_core_dpll_setup(struct device_node *node)
+{
+	const struct dpll_data dd = {
+		.enable_mask = 0x3,
+		.mult_mask = 0x3ff << 12,
+		.div1_mask = 0xf << 8,
+		.max_divider = 16,
+		.min_divider = 1,
+	};
+
+	of_ti_dpll_setup(node, &omap2_dpll_core_ck_ops, &dd);
+}
+CLK_OF_DECLARE(ti_omap2_core_dpll_clock, "ti,omap2-dpll-core-clock",
+	       of_ti_omap2_core_dpll_setup);
diff --git a/drivers/clk/ti/gate.c b/drivers/clk/ti/gate.c
index 5873481..b326d27 100644
--- a/drivers/clk/ti/gate.c
+++ b/drivers/clk/ti/gate.c
@@ -185,7 +185,7 @@
 CLK_OF_DECLARE(ti_composite_no_wait_gate_clk, "ti,composite-no-wait-gate-clock",
 	       of_ti_composite_no_wait_gate_clk_setup);
 
-#ifdef CONFIG_ARCH_OMAP3
+#if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3)
 static void __init of_ti_composite_interface_clk_setup(struct device_node *node)
 {
 	_of_ti_composite_gate_clk_setup(node, &clkhwops_iclk_wait);
diff --git a/drivers/clk/ti/interface.c b/drivers/clk/ti/interface.c
index 320a2b1..9c3e8c4 100644
--- a/drivers/clk/ti/interface.c
+++ b/drivers/clk/ti/interface.c
@@ -94,6 +94,7 @@
 CLK_OF_DECLARE(ti_no_wait_interface_clk, "ti,omap3-no-wait-interface-clock",
 	       of_ti_no_wait_interface_clk_setup);
 
+#ifdef CONFIG_ARCH_OMAP3
 static void __init of_ti_hsotgusb_interface_clk_setup(struct device_node *node)
 {
 	_of_ti_interface_clk_setup(node,
@@ -123,3 +124,13 @@
 }
 CLK_OF_DECLARE(ti_am35xx_interface_clk, "ti,am35xx-interface-clock",
 	       of_ti_am35xx_interface_clk_setup);
+#endif
+
+#ifdef CONFIG_SOC_OMAP2430
+static void __init of_ti_omap2430_interface_clk_setup(struct device_node *node)
+{
+	_of_ti_interface_clk_setup(node, &clkhwops_omap2430_i2chs_wait);
+}
+CLK_OF_DECLARE(ti_omap2430_interface_clk, "ti,omap2430-interface-clock",
+	       of_ti_omap2430_interface_clk_setup);
+#endif
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index e473d65..ffe350f 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -186,6 +186,8 @@
 config GENERIC_CPUFREQ_CPU0
 	tristate "Generic CPU0 cpufreq driver"
 	depends on HAVE_CLK && OF
+	# if CPU_THERMAL is on and THERMAL=m, CPU0 cannot be =y:
+	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds a generic cpufreq driver for CPU0 frequency management.
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index aed2b0c..62259d2 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2242,10 +2242,8 @@
 	struct cpufreq_policy new_policy;
 	int ret;
 
-	if (!policy) {
-		ret = -ENODEV;
-		goto no_policy;
-	}
+	if (!policy)
+		return -ENODEV;
 
 	down_write(&policy->rwsem);
 
@@ -2264,7 +2262,7 @@
 		new_policy.cur = cpufreq_driver->get(cpu);
 		if (WARN_ON(!new_policy.cur)) {
 			ret = -EIO;
-			goto no_policy;
+			goto unlock;
 		}
 
 		if (!policy->cur) {
@@ -2279,10 +2277,10 @@
 
 	ret = cpufreq_set_policy(policy, &new_policy);
 
+unlock:
 	up_write(&policy->rwsem);
 
 	cpufreq_cpu_put(policy);
-no_policy:
 	return ret;
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4e7f492..924bb2d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -196,10 +196,7 @@
 	pid->last_err = fp_error;
 
 	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
-	if (result >= 0)
-		result = result + (1 << (FRAC_BITS-1));
-	else
-		result = result - (1 << (FRAC_BITS-1));
+	result = result + (1 << (FRAC_BITS-1));
 	return (signed int)fp_toint(result);
 }
 
diff --git a/drivers/cpuidle/cpuidle-armada-370-xp.c b/drivers/cpuidle/cpuidle-armada-370-xp.c
index 28587d0..a5fba02 100644
--- a/drivers/cpuidle/cpuidle-armada-370-xp.c
+++ b/drivers/cpuidle/cpuidle-armada-370-xp.c
@@ -55,7 +55,7 @@
 		.power_usage		= 50,
 		.target_residency	= 100,
 		.flags			= CPUIDLE_FLAG_TIME_VALID,
-		.name			= "MV CPU IDLE",
+		.name			= "Idle",
 		.desc			= "CPU power down",
 	},
 	.states[2]		= {
@@ -65,7 +65,7 @@
 		.target_residency	= 1000,
 		.flags			= CPUIDLE_FLAG_TIME_VALID |
 						ARMADA_370_XP_FLAG_DEEP_IDLE,
-		.name			= "MV CPU DEEP IDLE",
+		.name			= "Deep idle",
 		.desc			= "CPU and L2 Fabric power down",
 	},
 	.state_count = ARMADA_370_XP_MAX_STATES,
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d9c9cb4..2ebc907 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2614,7 +2614,7 @@
 
 		desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx,
 						&of_flags);
-		if (!IS_ERR(desc))
+		if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER))
 			break;
 	}
 
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 7c2497d..0dc57d5 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -64,6 +64,7 @@
 void drm_modeset_acquire_init(struct drm_modeset_acquire_ctx *ctx,
 		uint32_t flags)
 {
+	memset(ctx, 0, sizeof(*ctx));
 	ww_acquire_init(&ctx->ww_ctx, &crtc_ww_class);
 	INIT_LIST_HEAD(&ctx->locked);
 }
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 4c22a5b..6c65639 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -36,6 +36,8 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include <linux/pci.h>
+#include <linux/console.h>
+#include <linux/vt.h>
 #include <linux/vgaarb.h>
 #include <linux/acpi.h>
 #include <linux/pnp.h>
@@ -1386,7 +1388,6 @@
 	i915_gem_context_fini(dev);
 	mutex_unlock(&dev->struct_mutex);
 	WARN_ON(dev_priv->mm.aliasing_ppgtt);
-	drm_mm_takedown(&dev_priv->gtt.base.mm);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
@@ -1450,6 +1451,38 @@
 }
 #endif
 
+#if !defined(CONFIG_VGA_CONSOLE)
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	return 0;
+}
+#elif !defined(CONFIG_DUMMY_CONSOLE)
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	return -ENODEV;
+}
+#else
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	DRM_INFO("Replacing VGA console driver\n");
+
+	console_lock();
+	ret = do_take_over_console(&dummy_con, 0, MAX_NR_CONSOLES - 1, 1);
+	if (ret == 0) {
+		ret = do_unregister_con_driver(&vga_con);
+
+		/* Ignore "already unregistered". */
+		if (ret == -ENODEV)
+			ret = 0;
+	}
+	console_unlock();
+
+	return ret;
+}
+#endif
+
 static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 {
 	const struct intel_device_info *info = &dev_priv->info;
@@ -1623,8 +1656,15 @@
 	if (ret)
 		goto out_regs;
 
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		ret = i915_kick_out_vgacon(dev_priv);
+		if (ret) {
+			DRM_ERROR("failed to remove conflicting VGA console\n");
+			goto out_gtt;
+		}
+
 		i915_kick_out_firmware_fb(dev_priv);
+	}
 
 	pci_set_master(dev->pdev);
 
@@ -1756,8 +1796,6 @@
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
 	io_mapping_free(dev_priv->gtt.mappable);
 out_gtt:
-	list_del(&dev_priv->gtt.base.global_link);
-	drm_mm_takedown(&dev_priv->gtt.base.mm);
 	dev_priv->gtt.base.cleanup(&dev_priv->gtt.base);
 out_regs:
 	intel_uncore_fini(dev);
@@ -1846,7 +1884,6 @@
 			i915_free_hws(dev);
 	}
 
-	list_del(&dev_priv->gtt.base.global_link);
 	WARN_ON(!list_empty(&dev_priv->vm_list));
 
 	drm_vblank_cleanup(dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index eec820a..8b3cde7 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1992,7 +1992,10 @@
 
 	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
 
-	drm_mm_takedown(&vm->mm);
+	if (drm_mm_initialized(&vm->mm)) {
+		drm_mm_takedown(&vm->mm);
+		list_del(&vm->global_link);
+	}
 	iounmap(gtt->gsm);
 	teardown_scratch_page(vm->dev);
 }
@@ -2025,6 +2028,10 @@
 
 static void i915_gmch_remove(struct i915_address_space *vm)
 {
+	if (drm_mm_initialized(&vm->mm)) {
+		drm_mm_takedown(&vm->mm);
+		list_del(&vm->global_link);
+	}
 	intel_gmch_remove();
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 87ec60e..66cf417 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -888,6 +888,8 @@
 	for (i = 0; i < I915_NUM_RINGS; i++) {
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
 
+		error->ring[i].pid = -1;
+
 		if (ring->dev == NULL)
 			continue;
 
@@ -895,7 +897,6 @@
 
 		i915_record_ring_state(dev, ring, &error->ring[i]);
 
-		error->ring[i].pid = -1;
 		request = i915_gem_find_active_request(ring);
 		if (request) {
 			/* We need to copy these to an anonymous buffer
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6f8017a..267f069 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2847,10 +2847,14 @@
 	struct intel_engine_cs *signaller;
 	u32 seqno, ctl;
 
-	ring->hangcheck.deadlock = true;
+	ring->hangcheck.deadlock++;
 
 	signaller = semaphore_waits_for(ring, &seqno);
-	if (signaller == NULL || signaller->hangcheck.deadlock)
+	if (signaller == NULL)
+		return -1;
+
+	/* Prevent pathological recursion due to driver bugs */
+	if (signaller->hangcheck.deadlock >= I915_NUM_RINGS)
 		return -1;
 
 	/* cursory check for an unkickable deadlock */
@@ -2858,7 +2862,13 @@
 	if (ctl & RING_WAIT_SEMAPHORE && semaphore_passed(signaller) < 0)
 		return -1;
 
-	return i915_seqno_passed(signaller->get_seqno(signaller, false), seqno);
+	if (i915_seqno_passed(signaller->get_seqno(signaller, false), seqno))
+		return 1;
+
+	if (signaller->hangcheck.deadlock)
+		return -1;
+
+	return 0;
 }
 
 static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
@@ -2867,7 +2877,7 @@
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
-		ring->hangcheck.deadlock = false;
+		ring->hangcheck.deadlock = 0;
 }
 
 static enum intel_ring_hangcheck_action
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 5e6c888..38a9857 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -798,9 +798,6 @@
 	ctl = freq << 16;
 	I915_WRITE(BLC_PWM_CTL, ctl);
 
-	/* XXX: combine this into above write? */
-	intel_panel_actually_set_backlight(connector, panel->backlight.level);
-
 	ctl2 = BLM_PIPE(pipe);
 	if (panel->backlight.combination_mode)
 		ctl2 |= BLM_COMBINATION_MODE;
@@ -809,6 +806,8 @@
 	I915_WRITE(BLC_PWM_CTL2, ctl2);
 	POSTING_READ(BLC_PWM_CTL2);
 	I915_WRITE(BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE);
+
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
 }
 
 static void vlv_enable_backlight(struct intel_connector *connector)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d1e53ab..54242e4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -511,8 +511,7 @@
 	obj = intel_fb->obj;
 	adjusted_mode = &intel_crtc->config.adjusted_mode;
 
-	if (i915.enable_fbc < 0 &&
-	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
+	if (i915.enable_fbc < 0) {
 		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
 			DRM_DEBUG_KMS("disabled per chip default\n");
 		goto out_disable;
@@ -3506,15 +3505,11 @@
 
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
 
-	/* WaDisablePwrmtrEvent:chv (pre-production hw) */
-	I915_WRITE(0xA80C, I915_READ(0xA80C) & 0x00ffffff);
-	I915_WRITE(0xA810, I915_READ(0xA810) & 0xffffff00);
-
 	/* 5: Enable RPS */
 	I915_WRITE(GEN6_RP_CONTROL,
 		   GEN6_RP_MEDIA_TURBO |
 		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX | /* WaSetMaskForGfxBusyness:chv (pre-production hw ?) */
+		   GEN6_RP_MEDIA_IS_GFX |
 		   GEN6_RP_ENABLE |
 		   GEN6_RP_UP_BUSY_AVG |
 		   GEN6_RP_DOWN_IDLE_AVG);
@@ -6024,30 +6019,32 @@
 static struct i915_power_domains *hsw_pwr;
 
 /* Display audio driver power well request */
-void i915_request_power_well(void)
+int i915_request_power_well(void)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (WARN_ON(!hsw_pwr))
-		return;
+	if (!hsw_pwr)
+		return -ENODEV;
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
 	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(i915_request_power_well);
 
 /* Display audio driver power well release */
-void i915_release_power_well(void)
+int i915_release_power_well(void)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (WARN_ON(!hsw_pwr))
-		return;
+	if (!hsw_pwr)
+		return -ENODEV;
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
 	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(i915_release_power_well);
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 910c83c..e72017b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -55,7 +55,7 @@
 	u32 seqno;
 	int score;
 	enum intel_ring_hangcheck_action action;
-	bool deadlock;
+	int deadlock;
 };
 
 struct intel_ringbuffer {
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 6a4d5bc..20375cc 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1385,7 +1385,9 @@
 			 >> SDVO_PORT_MULTIPLY_SHIFT) + 1;
 	}
 
-	dotclock = pipe_config->port_clock / pipe_config->pixel_multiplier;
+	dotclock = pipe_config->port_clock;
+	if (pipe_config->pixel_multiplier)
+		dotclock /= pipe_config->pixel_multiplier;
 
 	if (HAS_PCH_SPLIT(dev))
 		ironlake_check_encoder_dotclock(pipe_config, dotclock);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 79cba59..4f6fef7 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -320,7 +320,8 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
 
-	del_timer_sync(&dev_priv->uncore.force_wake_timer);
+	if (del_timer_sync(&dev_priv->uncore.force_wake_timer))
+		gen6_force_wake_timer((unsigned long)dev_priv);
 
 	/* Hold uncore.lock across reset to prevent any register access
 	 * with forcewake not set correctly
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index 2b6156d..8b307e1 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -140,6 +140,7 @@
 nouveau-y += core/subdev/i2c/nv50.o
 nouveau-y += core/subdev/i2c/nv94.o
 nouveau-y += core/subdev/i2c/nvd0.o
+nouveau-y += core/subdev/i2c/gf117.o
 nouveau-y += core/subdev/i2c/nve0.o
 nouveau-y += core/subdev/ibus/nvc0.o
 nouveau-y += core/subdev/ibus/nve0.o
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
index f199957..8d55ed6 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
@@ -314,7 +314,7 @@
 		device->cname = "GF117";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nvd0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  gf117_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/base.c b/drivers/gpu/drm/nouveau/core/engine/disp/base.c
index c41f656..9c38c5e 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/base.c
@@ -99,8 +99,10 @@
 
 	nouveau_event_destroy(&disp->vblank);
 
-	list_for_each_entry_safe(outp, outt, &disp->outp, head) {
-		nouveau_object_ref(NULL, (struct nouveau_object **)&outp);
+	if (disp->outp.next) {
+		list_for_each_entry_safe(outp, outt, &disp->outp, head) {
+			nouveau_object_ref(NULL, (struct nouveau_object **)&outp);
+		}
 	}
 
 	nouveau_engine_destroy(&disp->base);
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dport.c b/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
index 39562d4..5a5b59b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
@@ -241,7 +241,9 @@
 		dp_set_training_pattern(dp, 2);
 
 	do {
-		if (dp_link_train_update(dp, dp->pc2, 400))
+		if ((tries &&
+		    dp_link_train_commit(dp, dp->pc2)) ||
+		    dp_link_train_update(dp, dp->pc2, 400))
 			break;
 
 		eq_done = !!(dp->stat[2] & DPCD_LS04_INTERLANE_ALIGN_DONE);
@@ -253,9 +255,6 @@
 			    !(lane & DPCD_LS02_LANE0_SYMBOL_LOCKED))
 				eq_done = false;
 		}
-
-		if (dp_link_train_commit(dp, dp->pc2))
-			break;
 	} while (!eq_done && cr_done && ++tries <= 5);
 
 	return eq_done ? 0 : -1;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 1e85f36..26e962b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -1270,7 +1270,7 @@
 	i--;
 
 	outp = exec_lookup(priv, head, i, ctrl, &data, &ver, &hdr, &cnt, &len, &info1);
-	if (!data)
+	if (!outp)
 		return NULL;
 
 	if (outp->info.location == 0) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc
index 2f7345f..7445f12 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc
@@ -54,7 +54,7 @@
 #ifdef INCLUDE_CODE
 // reports an exception to the host
 //
-// In: $r15 error code (see nvc0.fuc)
+// In: $r15 error code (see os.h)
 //
 error:
 	push $r14
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc
index c8ddb8d..b4ad18b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc
@@ -49,7 +49,7 @@
 #ifdef INCLUDE_CODE
 // reports an exception to the host
 //
-// In: $r15 error code (see nvc0.fuc)
+// In: $r15 error code (see os.h)
 //
 error:
 	nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(5), 0, $r15)
@@ -343,13 +343,25 @@
 	ih_no_ctxsw:
 	and $r11 $r10 NV_PGRAPH_FECS_INTR_FWMTHD
 	bra e #ih_no_fwmthd
-		// none we handle, ack, and fall-through to unhandled
+		// none we handle; report to host and ack
+		nv_rd32($r15, NV_PGRAPH_TRAPPED_DATA_LO)
+		nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(4), 0, $r15)
+		nv_rd32($r15, NV_PGRAPH_TRAPPED_ADDR)
+		nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(3), 0, $r15)
+		extr $r14 $r15 16:18
+		shl b32 $r14 $r14 2
+		imm32($r15, NV_PGRAPH_FE_OBJECT_TABLE(0))
+		add b32 $r14 $r15
+		call(nv_rd32)
+		nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(2), 0, $r15)
+		mov $r15 E_BAD_FWMTHD
+		call(error)
 		mov $r11 0x100
 		nv_wr32(0x400144, $r11)
 
 	// anything we didn't handle, bring it to the host's attention
 	ih_no_fwmthd:
-	mov $r11 0x104 // FIFO | CHSW
+	mov $r11 0x504 // FIFO | CHSW | FWMTHD
 	not b32 $r11
 	and $r11 $r10 $r11
 	bra e #ih_no_other
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h
index 214dd16..5f953c5 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h
@@ -478,10 +478,10 @@
 	0x01040080,
 	0xbd0001f6,
 	0x01004104,
-	0x627e020f,
-	0x717e0006,
+	0xa87e020f,
+	0xb77e0006,
 	0x100f0006,
-	0x0006b37e,
+	0x0006f97e,
 	0x98000e98,
 	0x207e010f,
 	0x14950001,
@@ -523,8 +523,8 @@
 	0x800040b7,
 	0xf40132b6,
 	0x000fb41b,
-	0x0006b37e,
-	0x627e000f,
+	0x0006f97e,
+	0xa87e000f,
 	0x00800006,
 	0x01f60201,
 	0xbd04bd00,
@@ -554,7 +554,7 @@
 	0x0009f602,
 	0x32f404bd,
 	0x0231f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -563,7 +563,7 @@
 	0x37008006,
 	0x0009f602,
 	0x31f404bd,
-	0x08367e01,
+	0x087c7e01,
 	0xf094bd00,
 	0x00800699,
 	0x09f60217,
@@ -572,7 +572,7 @@
 	0x20f92f0e,
 	0x32f412b2,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x008020fc,
 	0x02f602c0,
 	0xf404bd00,
@@ -580,7 +580,7 @@
 	0x23c8130e,
 	0x0d0bf41f,
 	0xf40131f4,
-	0x367e0232,
+	0x7c7e0232,
 /* 0x054e: chsw_done */
 	0x01020008,
 	0x02c30080,
@@ -593,7 +593,7 @@
 	0xb0ff2a0e,
 	0x1bf401e4,
 	0x7ef2b20c,
-	0xf40007d6,
+	0xf400081c,
 /* 0x057a: main_not_ctx_chan */
 	0xe4b0400e,
 	0x2c1bf402,
@@ -602,7 +602,7 @@
 	0x0009f602,
 	0x32f404bd,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -642,238 +642,238 @@
 /* 0x061a: ih_no_ctxsw */
 	0xabe40000,
 	0x0bf40400,
-	0x01004b10,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x062e: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd01,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x0642: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0x0032f480,
-/* 0x0662: ctx_4170s */
-	0xf5f001f8,
-	0x8effb210,
-	0x7e404170,
-	0xf800008f,
-/* 0x0671: ctx_4170w */
-	0x41708e00,
+	0x07088e56,
 	0x00657e40,
-	0xf0ffb200,
-	0x1bf410f4,
-/* 0x0683: ctx_redswitch */
-	0x4e00f8f3,
-	0xe5f00200,
-	0x20e5f040,
-	0x8010e5f0,
-	0xf6018500,
-	0x04bd000e,
-/* 0x069a: ctx_redswitch_delay */
-	0xf2b6080f,
-	0xfd1bf401,
-	0x0400e5f1,
-	0x0100e5f1,
-	0x01850080,
-	0xbd000ef6,
-/* 0x06b3: ctx_86c */
-	0x8000f804,
-	0xf6022300,
+	0x80ffb200,
+	0xf6020400,
 	0x04bd000f,
-	0x148effb2,
-	0x8f7e408a,
-	0xffb20000,
-	0x41a88c8e,
-	0x00008f7e,
-/* 0x06d2: ctx_mem */
-	0x008000f8,
-	0x0ff60284,
-/* 0x06db: ctx_mem_wait */
-	0x8f04bd00,
-	0xcf028400,
-	0xfffd00ff,
-	0xf61bf405,
-/* 0x06ea: ctx_load */
-	0x94bd00f8,
-	0x800599f0,
-	0xf6023700,
-	0x04bd0009,
-	0xb87e0c0a,
-	0xf4bd0000,
-	0x02890080,
+	0x4007048e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60203,
+	0xc704bd00,
+	0xee9450fe,
+	0x07008f02,
+	0x00efbb40,
+	0x0000657e,
+	0x02020080,
 	0xbd000ff6,
-	0xc1008004,
-	0x0002f602,
-	0x008004bd,
-	0x02f60283,
-	0x0f04bd00,
-	0x06d27e07,
-	0xc0008000,
-	0x0002f602,
-	0x0bfe04bd,
-	0x1f2af000,
-	0xb60424b6,
-	0x94bd0220,
-	0x800899f0,
-	0xf6023700,
-	0x04bd0009,
-	0x02810080,
-	0xbd0002f6,
-	0x0000d204,
-	0x25f08000,
-	0x88008002,
-	0x0002f602,
-	0x100104bd,
-	0xf0020042,
-	0x12fa0223,
-	0xbd03f805,
-	0x0899f094,
-	0x02170080,
-	0xbd0009f6,
-	0x81019804,
-	0x981814b6,
-	0x25b68002,
-	0x0512fd08,
-	0xbd1601b5,
-	0x0999f094,
-	0x02370080,
-	0xbd0009f6,
-	0x81008004,
-	0x0001f602,
-	0x010204bd,
-	0x02880080,
-	0xbd0002f6,
-	0x01004104,
-	0xfa0613f0,
-	0x03f80501,
+	0x7e030f04,
+	0x4b0002f8,
+	0xbfb20100,
+	0x4001448e,
+	0x00008f7e,
+/* 0x0674: ih_no_fwmthd */
+	0xbd05044b,
+	0xb4abffb0,
+	0x800c0bf4,
+	0xf6030700,
+	0x04bd000b,
+/* 0x0688: ih_no_other */
+	0xf6010040,
+	0x04bd000a,
+	0xe0fcf0fc,
+	0xb0fcd0fc,
+	0x90fca0fc,
+	0x88fe80fc,
+	0xf480fc00,
+	0x01f80032,
+/* 0x06a8: ctx_4170s */
+	0xb210f5f0,
+	0x41708eff,
+	0x008f7e40,
+/* 0x06b7: ctx_4170w */
+	0x8e00f800,
+	0x7e404170,
+	0xb2000065,
+	0x10f4f0ff,
+	0xf8f31bf4,
+/* 0x06c9: ctx_redswitch */
+	0x02004e00,
+	0xf040e5f0,
+	0xe5f020e5,
+	0x85008010,
+	0x000ef601,
+	0x080f04bd,
+/* 0x06e0: ctx_redswitch_delay */
+	0xf401f2b6,
+	0xe5f1fd1b,
+	0xe5f10400,
+	0x00800100,
+	0x0ef60185,
+	0xf804bd00,
+/* 0x06f9: ctx_86c */
+	0x23008000,
+	0x000ff602,
+	0xffb204bd,
+	0x408a148e,
+	0x00008f7e,
+	0x8c8effb2,
+	0x8f7e41a8,
+	0x00f80000,
+/* 0x0718: ctx_mem */
+	0x02840080,
+	0xbd000ff6,
+/* 0x0721: ctx_mem_wait */
+	0x84008f04,
+	0x00ffcf02,
+	0xf405fffd,
+	0x00f8f61b,
+/* 0x0730: ctx_load */
 	0x99f094bd,
-	0x17008009,
+	0x37008005,
 	0x0009f602,
-	0x94bd04bd,
-	0x800599f0,
+	0x0c0a04bd,
+	0x0000b87e,
+	0x0080f4bd,
+	0x0ff60289,
+	0x8004bd00,
+	0xf602c100,
+	0x04bd0002,
+	0x02830080,
+	0xbd0002f6,
+	0x7e070f04,
+	0x80000718,
+	0xf602c000,
+	0x04bd0002,
+	0xf0000bfe,
+	0x24b61f2a,
+	0x0220b604,
+	0x99f094bd,
+	0x37008008,
+	0x0009f602,
+	0x008004bd,
+	0x02f60281,
+	0xd204bd00,
+	0x80000000,
+	0x800225f0,
+	0xf6028800,
+	0x04bd0002,
+	0x00421001,
+	0x0223f002,
+	0xf80512fa,
+	0xf094bd03,
+	0x00800899,
+	0x09f60217,
+	0x9804bd00,
+	0x14b68101,
+	0x80029818,
+	0xfd0825b6,
+	0x01b50512,
+	0xf094bd16,
+	0x00800999,
+	0x09f60237,
+	0x8004bd00,
+	0xf6028100,
+	0x04bd0001,
+	0x00800102,
+	0x02f60288,
+	0x4104bd00,
+	0x13f00100,
+	0x0501fa06,
+	0x94bd03f8,
+	0x800999f0,
 	0xf6021700,
 	0x04bd0009,
-/* 0x07d6: ctx_chan */
-	0xea7e00f8,
-	0x0c0a0006,
-	0x0000b87e,
-	0xd27e050f,
-	0x00f80006,
-/* 0x07e8: ctx_mmio_exec */
-	0x80410398,
+	0x99f094bd,
+	0x17008005,
+	0x0009f602,
+	0x00f804bd,
+/* 0x081c: ctx_chan */
+	0x0007307e,
+	0xb87e0c0a,
+	0x050f0000,
+	0x0007187e,
+/* 0x082e: ctx_mmio_exec */
+	0x039800f8,
+	0x81008041,
+	0x0003f602,
+	0x34bd04bd,
+/* 0x083c: ctx_mmio_loop */
+	0xf4ff34c4,
+	0x00450e1b,
+	0x0653f002,
+	0xf80535fa,
+/* 0x084d: ctx_mmio_pull */
+	0x804e9803,
+	0x7e814f98,
+	0xb600008f,
+	0x12b60830,
+	0xdf1bf401,
+/* 0x0860: ctx_mmio_done */
+	0x80160398,
 	0xf6028100,
 	0x04bd0003,
-/* 0x07f6: ctx_mmio_loop */
-	0x34c434bd,
-	0x0e1bf4ff,
-	0xf0020045,
-	0x35fa0653,
-/* 0x0807: ctx_mmio_pull */
-	0x9803f805,
-	0x4f98804e,
-	0x008f7e81,
-	0x0830b600,
-	0xf40112b6,
-/* 0x081a: ctx_mmio_done */
-	0x0398df1b,
-	0x81008016,
-	0x0003f602,
-	0x00b504bd,
-	0x01004140,
-	0xfa0613f0,
-	0x03f80601,
-/* 0x0836: ctx_xfer */
-	0x040e00f8,
-	0x03020080,
-	0xbd000ef6,
-/* 0x0841: ctx_xfer_idle */
-	0x00008e04,
-	0x00eecf03,
-	0x2000e4f1,
-	0xf4f51bf4,
-	0x02f40611,
-/* 0x0855: ctx_xfer_pre */
-	0x7e100f0c,
-	0xf40006b3,
-/* 0x085e: ctx_xfer_pre_load */
-	0x020f1b11,
-	0x0006627e,
-	0x0006717e,
-	0x0006837e,
-	0x627ef4bd,
-	0xea7e0006,
-/* 0x0876: ctx_xfer_exec */
-	0x01980006,
-	0x8024bd16,
-	0xf6010500,
-	0x04bd0002,
-	0x008e1fb2,
-	0x8f7e41a5,
-	0xfcf00000,
-	0x022cf001,
-	0xfd0124b6,
-	0xffb205f2,
-	0x41a5048e,
-	0x00008f7e,
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
-	0x0002f602,
-	0xacf004bd,
-	0x06a5f001,
-	0x0c98000b,
-	0x010d9800,
-	0x3d7e000e,
-	0x080a0001,
-	0x0000ec7e,
-	0x00020a7e,
-	0x0a1201f4,
-	0x00b87e0c,
-	0x7e050f00,
-	0xf40006d2,
-/* 0x08f2: ctx_xfer_post */
-	0x020f2d02,
-	0x0006627e,
-	0xb37ef4bd,
-	0x277e0006,
-	0x717e0002,
+	0x414000b5,
+	0x13f00100,
+	0x0601fa06,
+	0x00f803f8,
+/* 0x087c: ctx_xfer */
+	0x0080040e,
+	0x0ef60302,
+/* 0x0887: ctx_xfer_idle */
+	0x8e04bd00,
+	0xcf030000,
+	0xe4f100ee,
+	0x1bf42000,
+	0x0611f4f5,
+/* 0x089b: ctx_xfer_pre */
+	0x0f0c02f4,
+	0x06f97e10,
+	0x1b11f400,
+/* 0x08a4: ctx_xfer_pre_load */
+	0xa87e020f,
+	0xb77e0006,
+	0xc97e0006,
 	0xf4bd0006,
-	0x0006627e,
-	0x981011f4,
-	0x11fd4001,
-	0x070bf405,
-	0x0007e87e,
-/* 0x091c: ctx_xfer_no_post_mmio */
-/* 0x091c: ctx_xfer_done */
-	0x000000f8,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
+	0x0006a87e,
+	0x0007307e,
+/* 0x08bc: ctx_xfer_exec */
+	0xbd160198,
+	0x05008024,
+	0x0002f601,
+	0x1fb204bd,
+	0x41a5008e,
+	0x00008f7e,
+	0xf001fcf0,
+	0x24b6022c,
+	0x05f2fd01,
+	0x048effb2,
+	0x8f7e41a5,
+	0x167e0000,
+	0x24bd0002,
+	0x0247fc80,
+	0xbd0002f6,
+	0x012cf004,
+	0x800320b6,
+	0xf6024afc,
+	0x04bd0002,
+	0xf001acf0,
+	0x000b06a5,
+	0x98000c98,
+	0x000e010d,
+	0x00013d7e,
+	0xec7e080a,
+	0x0a7e0000,
+	0x01f40002,
+	0x7e0c0a12,
+	0x0f0000b8,
+	0x07187e05,
+	0x2d02f400,
+/* 0x0938: ctx_xfer_post */
+	0xa87e020f,
+	0xf4bd0006,
+	0x0006f97e,
+	0x0002277e,
+	0x0006b77e,
+	0xa87ef4bd,
+	0x11f40006,
+	0x40019810,
+	0xf40511fd,
+	0x2e7e070b,
+/* 0x0962: ctx_xfer_no_post_mmio */
+/* 0x0962: ctx_xfer_done */
+	0x00f80008,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h
index 64dfd75..e49b5a8 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h
@@ -478,10 +478,10 @@
 	0x01040080,
 	0xbd0001f6,
 	0x01004104,
-	0x627e020f,
-	0x717e0006,
+	0xa87e020f,
+	0xb77e0006,
 	0x100f0006,
-	0x0006b37e,
+	0x0006f97e,
 	0x98000e98,
 	0x207e010f,
 	0x14950001,
@@ -523,8 +523,8 @@
 	0x800040b7,
 	0xf40132b6,
 	0x000fb41b,
-	0x0006b37e,
-	0x627e000f,
+	0x0006f97e,
+	0xa87e000f,
 	0x00800006,
 	0x01f60201,
 	0xbd04bd00,
@@ -554,7 +554,7 @@
 	0x0009f602,
 	0x32f404bd,
 	0x0231f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -563,7 +563,7 @@
 	0x37008006,
 	0x0009f602,
 	0x31f404bd,
-	0x08367e01,
+	0x087c7e01,
 	0xf094bd00,
 	0x00800699,
 	0x09f60217,
@@ -572,7 +572,7 @@
 	0x20f92f0e,
 	0x32f412b2,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x008020fc,
 	0x02f602c0,
 	0xf404bd00,
@@ -580,7 +580,7 @@
 	0x23c8130e,
 	0x0d0bf41f,
 	0xf40131f4,
-	0x367e0232,
+	0x7c7e0232,
 /* 0x054e: chsw_done */
 	0x01020008,
 	0x02c30080,
@@ -593,7 +593,7 @@
 	0xb0ff2a0e,
 	0x1bf401e4,
 	0x7ef2b20c,
-	0xf40007d6,
+	0xf400081c,
 /* 0x057a: main_not_ctx_chan */
 	0xe4b0400e,
 	0x2c1bf402,
@@ -602,7 +602,7 @@
 	0x0009f602,
 	0x32f404bd,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -642,238 +642,238 @@
 /* 0x061a: ih_no_ctxsw */
 	0xabe40000,
 	0x0bf40400,
-	0x01004b10,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x062e: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd01,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x0642: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0x0032f480,
-/* 0x0662: ctx_4170s */
-	0xf5f001f8,
-	0x8effb210,
-	0x7e404170,
-	0xf800008f,
-/* 0x0671: ctx_4170w */
-	0x41708e00,
+	0x07088e56,
 	0x00657e40,
-	0xf0ffb200,
-	0x1bf410f4,
-/* 0x0683: ctx_redswitch */
-	0x4e00f8f3,
-	0xe5f00200,
-	0x20e5f040,
-	0x8010e5f0,
-	0xf6018500,
-	0x04bd000e,
-/* 0x069a: ctx_redswitch_delay */
-	0xf2b6080f,
-	0xfd1bf401,
-	0x0400e5f1,
-	0x0100e5f1,
-	0x01850080,
-	0xbd000ef6,
-/* 0x06b3: ctx_86c */
-	0x8000f804,
-	0xf6022300,
+	0x80ffb200,
+	0xf6020400,
 	0x04bd000f,
-	0x148effb2,
-	0x8f7e408a,
-	0xffb20000,
-	0x41a88c8e,
-	0x00008f7e,
-/* 0x06d2: ctx_mem */
-	0x008000f8,
-	0x0ff60284,
-/* 0x06db: ctx_mem_wait */
-	0x8f04bd00,
-	0xcf028400,
-	0xfffd00ff,
-	0xf61bf405,
-/* 0x06ea: ctx_load */
-	0x94bd00f8,
-	0x800599f0,
-	0xf6023700,
-	0x04bd0009,
-	0xb87e0c0a,
-	0xf4bd0000,
-	0x02890080,
+	0x4007048e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60203,
+	0xc704bd00,
+	0xee9450fe,
+	0x07008f02,
+	0x00efbb40,
+	0x0000657e,
+	0x02020080,
 	0xbd000ff6,
-	0xc1008004,
-	0x0002f602,
-	0x008004bd,
-	0x02f60283,
-	0x0f04bd00,
-	0x06d27e07,
-	0xc0008000,
-	0x0002f602,
-	0x0bfe04bd,
-	0x1f2af000,
-	0xb60424b6,
-	0x94bd0220,
-	0x800899f0,
-	0xf6023700,
-	0x04bd0009,
-	0x02810080,
-	0xbd0002f6,
-	0x0000d204,
-	0x25f08000,
-	0x88008002,
-	0x0002f602,
-	0x100104bd,
-	0xf0020042,
-	0x12fa0223,
-	0xbd03f805,
-	0x0899f094,
-	0x02170080,
-	0xbd0009f6,
-	0x81019804,
-	0x981814b6,
-	0x25b68002,
-	0x0512fd08,
-	0xbd1601b5,
-	0x0999f094,
-	0x02370080,
-	0xbd0009f6,
-	0x81008004,
-	0x0001f602,
-	0x010204bd,
-	0x02880080,
-	0xbd0002f6,
-	0x01004104,
-	0xfa0613f0,
-	0x03f80501,
+	0x7e030f04,
+	0x4b0002f8,
+	0xbfb20100,
+	0x4001448e,
+	0x00008f7e,
+/* 0x0674: ih_no_fwmthd */
+	0xbd05044b,
+	0xb4abffb0,
+	0x800c0bf4,
+	0xf6030700,
+	0x04bd000b,
+/* 0x0688: ih_no_other */
+	0xf6010040,
+	0x04bd000a,
+	0xe0fcf0fc,
+	0xb0fcd0fc,
+	0x90fca0fc,
+	0x88fe80fc,
+	0xf480fc00,
+	0x01f80032,
+/* 0x06a8: ctx_4170s */
+	0xb210f5f0,
+	0x41708eff,
+	0x008f7e40,
+/* 0x06b7: ctx_4170w */
+	0x8e00f800,
+	0x7e404170,
+	0xb2000065,
+	0x10f4f0ff,
+	0xf8f31bf4,
+/* 0x06c9: ctx_redswitch */
+	0x02004e00,
+	0xf040e5f0,
+	0xe5f020e5,
+	0x85008010,
+	0x000ef601,
+	0x080f04bd,
+/* 0x06e0: ctx_redswitch_delay */
+	0xf401f2b6,
+	0xe5f1fd1b,
+	0xe5f10400,
+	0x00800100,
+	0x0ef60185,
+	0xf804bd00,
+/* 0x06f9: ctx_86c */
+	0x23008000,
+	0x000ff602,
+	0xffb204bd,
+	0x408a148e,
+	0x00008f7e,
+	0x8c8effb2,
+	0x8f7e41a8,
+	0x00f80000,
+/* 0x0718: ctx_mem */
+	0x02840080,
+	0xbd000ff6,
+/* 0x0721: ctx_mem_wait */
+	0x84008f04,
+	0x00ffcf02,
+	0xf405fffd,
+	0x00f8f61b,
+/* 0x0730: ctx_load */
 	0x99f094bd,
-	0x17008009,
+	0x37008005,
 	0x0009f602,
-	0x94bd04bd,
-	0x800599f0,
+	0x0c0a04bd,
+	0x0000b87e,
+	0x0080f4bd,
+	0x0ff60289,
+	0x8004bd00,
+	0xf602c100,
+	0x04bd0002,
+	0x02830080,
+	0xbd0002f6,
+	0x7e070f04,
+	0x80000718,
+	0xf602c000,
+	0x04bd0002,
+	0xf0000bfe,
+	0x24b61f2a,
+	0x0220b604,
+	0x99f094bd,
+	0x37008008,
+	0x0009f602,
+	0x008004bd,
+	0x02f60281,
+	0xd204bd00,
+	0x80000000,
+	0x800225f0,
+	0xf6028800,
+	0x04bd0002,
+	0x00421001,
+	0x0223f002,
+	0xf80512fa,
+	0xf094bd03,
+	0x00800899,
+	0x09f60217,
+	0x9804bd00,
+	0x14b68101,
+	0x80029818,
+	0xfd0825b6,
+	0x01b50512,
+	0xf094bd16,
+	0x00800999,
+	0x09f60237,
+	0x8004bd00,
+	0xf6028100,
+	0x04bd0001,
+	0x00800102,
+	0x02f60288,
+	0x4104bd00,
+	0x13f00100,
+	0x0501fa06,
+	0x94bd03f8,
+	0x800999f0,
 	0xf6021700,
 	0x04bd0009,
-/* 0x07d6: ctx_chan */
-	0xea7e00f8,
-	0x0c0a0006,
-	0x0000b87e,
-	0xd27e050f,
-	0x00f80006,
-/* 0x07e8: ctx_mmio_exec */
-	0x80410398,
+	0x99f094bd,
+	0x17008005,
+	0x0009f602,
+	0x00f804bd,
+/* 0x081c: ctx_chan */
+	0x0007307e,
+	0xb87e0c0a,
+	0x050f0000,
+	0x0007187e,
+/* 0x082e: ctx_mmio_exec */
+	0x039800f8,
+	0x81008041,
+	0x0003f602,
+	0x34bd04bd,
+/* 0x083c: ctx_mmio_loop */
+	0xf4ff34c4,
+	0x00450e1b,
+	0x0653f002,
+	0xf80535fa,
+/* 0x084d: ctx_mmio_pull */
+	0x804e9803,
+	0x7e814f98,
+	0xb600008f,
+	0x12b60830,
+	0xdf1bf401,
+/* 0x0860: ctx_mmio_done */
+	0x80160398,
 	0xf6028100,
 	0x04bd0003,
-/* 0x07f6: ctx_mmio_loop */
-	0x34c434bd,
-	0x0e1bf4ff,
-	0xf0020045,
-	0x35fa0653,
-/* 0x0807: ctx_mmio_pull */
-	0x9803f805,
-	0x4f98804e,
-	0x008f7e81,
-	0x0830b600,
-	0xf40112b6,
-/* 0x081a: ctx_mmio_done */
-	0x0398df1b,
-	0x81008016,
-	0x0003f602,
-	0x00b504bd,
-	0x01004140,
-	0xfa0613f0,
-	0x03f80601,
-/* 0x0836: ctx_xfer */
-	0x040e00f8,
-	0x03020080,
-	0xbd000ef6,
-/* 0x0841: ctx_xfer_idle */
-	0x00008e04,
-	0x00eecf03,
-	0x2000e4f1,
-	0xf4f51bf4,
-	0x02f40611,
-/* 0x0855: ctx_xfer_pre */
-	0x7e100f0c,
-	0xf40006b3,
-/* 0x085e: ctx_xfer_pre_load */
-	0x020f1b11,
-	0x0006627e,
-	0x0006717e,
-	0x0006837e,
-	0x627ef4bd,
-	0xea7e0006,
-/* 0x0876: ctx_xfer_exec */
-	0x01980006,
-	0x8024bd16,
-	0xf6010500,
-	0x04bd0002,
-	0x008e1fb2,
-	0x8f7e41a5,
-	0xfcf00000,
-	0x022cf001,
-	0xfd0124b6,
-	0xffb205f2,
-	0x41a5048e,
-	0x00008f7e,
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
-	0x0002f602,
-	0xacf004bd,
-	0x06a5f001,
-	0x0c98000b,
-	0x010d9800,
-	0x3d7e000e,
-	0x080a0001,
-	0x0000ec7e,
-	0x00020a7e,
-	0x0a1201f4,
-	0x00b87e0c,
-	0x7e050f00,
-	0xf40006d2,
-/* 0x08f2: ctx_xfer_post */
-	0x020f2d02,
-	0x0006627e,
-	0xb37ef4bd,
-	0x277e0006,
-	0x717e0002,
+	0x414000b5,
+	0x13f00100,
+	0x0601fa06,
+	0x00f803f8,
+/* 0x087c: ctx_xfer */
+	0x0080040e,
+	0x0ef60302,
+/* 0x0887: ctx_xfer_idle */
+	0x8e04bd00,
+	0xcf030000,
+	0xe4f100ee,
+	0x1bf42000,
+	0x0611f4f5,
+/* 0x089b: ctx_xfer_pre */
+	0x0f0c02f4,
+	0x06f97e10,
+	0x1b11f400,
+/* 0x08a4: ctx_xfer_pre_load */
+	0xa87e020f,
+	0xb77e0006,
+	0xc97e0006,
 	0xf4bd0006,
-	0x0006627e,
-	0x981011f4,
-	0x11fd4001,
-	0x070bf405,
-	0x0007e87e,
-/* 0x091c: ctx_xfer_no_post_mmio */
-/* 0x091c: ctx_xfer_done */
-	0x000000f8,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
+	0x0006a87e,
+	0x0007307e,
+/* 0x08bc: ctx_xfer_exec */
+	0xbd160198,
+	0x05008024,
+	0x0002f601,
+	0x1fb204bd,
+	0x41a5008e,
+	0x00008f7e,
+	0xf001fcf0,
+	0x24b6022c,
+	0x05f2fd01,
+	0x048effb2,
+	0x8f7e41a5,
+	0x167e0000,
+	0x24bd0002,
+	0x0247fc80,
+	0xbd0002f6,
+	0x012cf004,
+	0x800320b6,
+	0xf6024afc,
+	0x04bd0002,
+	0xf001acf0,
+	0x000b06a5,
+	0x98000c98,
+	0x000e010d,
+	0x00013d7e,
+	0xec7e080a,
+	0x0a7e0000,
+	0x01f40002,
+	0x7e0c0a12,
+	0x0f0000b8,
+	0x07187e05,
+	0x2d02f400,
+/* 0x0938: ctx_xfer_post */
+	0xa87e020f,
+	0xf4bd0006,
+	0x0006f97e,
+	0x0002277e,
+	0x0006b77e,
+	0xa87ef4bd,
+	0x11f40006,
+	0x40019810,
+	0xf40511fd,
+	0x2e7e070b,
+/* 0x0962: ctx_xfer_no_post_mmio */
+/* 0x0962: ctx_xfer_done */
+	0x00f80008,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h
index f8f7b27..92dfe6a 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h
@@ -528,10 +528,10 @@
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0xb521f502,
-	0xc721f507,
-	0x10f7f007,
-	0x081421f5,
+	0x0d21f502,
+	0x1f21f508,
+	0x10f7f008,
+	0x086c21f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x081421f5,
+	0x086c21f5,
 	0xf500f7f0,
-	0xf107b521,
+	0xf1080d21,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@
 	0x0203f00f,
 	0xbd0009d0,
 	0x0131f404,
-	0x09e821f5,
+	0x0a4021f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09e821,
+	0xfc0a4021,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09e821f5,
+	0x0a4021f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x7821f502,
+	0xd021f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,36 +753,36 @@
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4160s */
+/* 0x07d7: ctx_4160s */
 	0xf001f800,
 	0xffb901f7,
 	0x60e7f102,
 	0x40e3f041,
-/* 0x078f: ctx_4160s_wait */
+/* 0x07e7: ctx_4160s_wait */
 	0xf19d21f4,
 	0xf04160e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf404ffc8,
 	0x00f8f00b,
-/* 0x07a4: ctx_4160c */
+/* 0x07fc: ctx_4160c */
 	0xffb9f4bd,
 	0x60e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x07b5: ctx_4170s */
+/* 0x080d: ctx_4170s */
 	0x10f5f000,
 	0xf102ffb9,
 	0xf04170e7,
 	0x21f440e3,
-/* 0x07c7: ctx_4170w */
+/* 0x081f: ctx_4170w */
 	0xf100f89d,
 	0xf04170e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf410f4f0,
 	0x00f8f01b,
-/* 0x07dc: ctx_redswitch */
+/* 0x0834: ctx_redswitch */
 	0x0200e7f1,
 	0xf040e5f0,
 	0xe5f020e5,
@@ -768,7 +790,7 @@
 	0x0103f085,
 	0xbd000ed0,
 	0x08f7f004,
-/* 0x07f8: ctx_redswitch_delay */
+/* 0x0850: ctx_redswitch_delay */
 	0xf401f2b6,
 	0xe5f1fd1b,
 	0xe5f10400,
@@ -776,7 +798,7 @@
 	0x03f08500,
 	0x000ed001,
 	0x00f804bd,
-/* 0x0814: ctx_86c */
+/* 0x086c: ctx_86c */
 	0x1b0007f1,
 	0xd00203f0,
 	0x04bd000f,
@@ -787,16 +809,16 @@
 	0xa86ce7f1,
 	0xf441e3f0,
 	0x00f89d21,
-/* 0x083c: ctx_mem */
+/* 0x0894: ctx_mem */
 	0x840007f1,
 	0xd00203f0,
 	0x04bd000f,
-/* 0x0848: ctx_mem_wait */
+/* 0x08a0: ctx_mem_wait */
 	0x8400f7f1,
 	0xcf02f3f0,
 	0xfffd00ff,
 	0xf31bf405,
-/* 0x085a: ctx_load */
+/* 0x08b2: ctx_load */
 	0x94bd00f8,
 	0xf10599f0,
 	0xf00f0007,
@@ -814,7 +836,7 @@
 	0x02d00203,
 	0xf004bd00,
 	0x21f507f7,
-	0x07f1083c,
+	0x07f10894,
 	0x03f0c000,
 	0x0002d002,
 	0x0bfe04bd,
@@ -869,31 +891,31 @@
 	0x03f01700,
 	0x0009d002,
 	0x00f804bd,
-/* 0x0978: ctx_chan */
-	0x077f21f5,
-	0x085a21f5,
+/* 0x09d0: ctx_chan */
+	0x07d721f5,
+	0x08b221f5,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
-	0xa421f508,
-/* 0x0993: ctx_mmio_exec */
+	0x9421f505,
+	0xfc21f508,
+/* 0x09eb: ctx_mmio_exec */
 	0x9800f807,
 	0x07f14103,
 	0x03f08100,
 	0x0003d002,
 	0x34bd04bd,
-/* 0x09a4: ctx_mmio_loop */
+/* 0x09fc: ctx_mmio_loop */
 	0xf4ff34c4,
 	0x57f10f1b,
 	0x53f00200,
 	0x0535fa06,
-/* 0x09b6: ctx_mmio_pull */
+/* 0x0a0e: ctx_mmio_pull */
 	0x4e9803f8,
 	0x814f9880,
 	0xb69d21f4,
 	0x12b60830,
 	0xdf1bf401,
-/* 0x09c8: ctx_mmio_done */
+/* 0x0a20: ctx_mmio_done */
 	0xf1160398,
 	0xf0810007,
 	0x03d00203,
@@ -902,30 +924,30 @@
 	0x13f00100,
 	0x0601fa06,
 	0x00f803f8,
-/* 0x09e8: ctx_xfer */
+/* 0x0a40: ctx_xfer */
 	0xf104e7f0,
 	0xf0020007,
 	0x0ed00303,
-/* 0x09f7: ctx_xfer_idle */
+/* 0x0a4f: ctx_xfer_idle */
 	0xf104bd00,
 	0xf00000e7,
 	0xeecf03e3,
 	0x00e4f100,
 	0xf21bf420,
 	0xf40611f4,
-/* 0x0a0e: ctx_xfer_pre */
+/* 0x0a66: ctx_xfer_pre */
 	0xf7f01102,
-	0x1421f510,
-	0x7f21f508,
+	0x6c21f510,
+	0xd721f508,
 	0x1c11f407,
-/* 0x0a1c: ctx_xfer_pre_load */
+/* 0x0a74: ctx_xfer_pre_load */
 	0xf502f7f0,
-	0xf507b521,
-	0xf507c721,
-	0xbd07dc21,
-	0xb521f5f4,
-	0x5a21f507,
-/* 0x0a35: ctx_xfer_exec */
+	0xf5080d21,
+	0xf5081f21,
+	0xbd083421,
+	0x0d21f5f4,
+	0xb221f508,
+/* 0x0a8d: ctx_xfer_exec */
 	0x16019808,
 	0x07f124bd,
 	0x03f00500,
@@ -960,23 +982,65 @@
 	0x1301f402,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
+	0x9421f505,
 	0x3202f408,
-/* 0x0ac4: ctx_xfer_post */
+/* 0x0b1c: ctx_xfer_post */
 	0xf502f7f0,
-	0xbd07b521,
-	0x1421f5f4,
+	0xbd080d21,
+	0x6c21f5f4,
 	0x7f21f508,
-	0xc721f502,
-	0xf5f4bd07,
-	0xf407b521,
+	0x1f21f502,
+	0xf5f4bd08,
+	0xf4080d21,
 	0x01981011,
 	0x0511fd40,
 	0xf5070bf4,
-/* 0x0aef: ctx_xfer_no_post_mmio */
-	0xf5099321,
-/* 0x0af3: ctx_xfer_done */
-	0xf807a421,
+/* 0x0b47: ctx_xfer_no_post_mmio */
+	0xf509eb21,
+/* 0x0b4b: ctx_xfer_done */
+	0xf807fc21,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h
index 624215a..62b0c76 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h
@@ -528,10 +528,10 @@
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0xb521f502,
-	0xc721f507,
-	0x10f7f007,
-	0x081421f5,
+	0x0d21f502,
+	0x1f21f508,
+	0x10f7f008,
+	0x086c21f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x081421f5,
+	0x086c21f5,
 	0xf500f7f0,
-	0xf107b521,
+	0xf1080d21,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@
 	0x0203f00f,
 	0xbd0009d0,
 	0x0131f404,
-	0x09e821f5,
+	0x0a4021f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09e821,
+	0xfc0a4021,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09e821f5,
+	0x0a4021f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x7821f502,
+	0xd021f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,36 +753,36 @@
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4160s */
+/* 0x07d7: ctx_4160s */
 	0xf001f800,
 	0xffb901f7,
 	0x60e7f102,
 	0x40e3f041,
-/* 0x078f: ctx_4160s_wait */
+/* 0x07e7: ctx_4160s_wait */
 	0xf19d21f4,
 	0xf04160e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf404ffc8,
 	0x00f8f00b,
-/* 0x07a4: ctx_4160c */
+/* 0x07fc: ctx_4160c */
 	0xffb9f4bd,
 	0x60e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x07b5: ctx_4170s */
+/* 0x080d: ctx_4170s */
 	0x10f5f000,
 	0xf102ffb9,
 	0xf04170e7,
 	0x21f440e3,
-/* 0x07c7: ctx_4170w */
+/* 0x081f: ctx_4170w */
 	0xf100f89d,
 	0xf04170e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf410f4f0,
 	0x00f8f01b,
-/* 0x07dc: ctx_redswitch */
+/* 0x0834: ctx_redswitch */
 	0x0200e7f1,
 	0xf040e5f0,
 	0xe5f020e5,
@@ -768,7 +790,7 @@
 	0x0103f085,
 	0xbd000ed0,
 	0x08f7f004,
-/* 0x07f8: ctx_redswitch_delay */
+/* 0x0850: ctx_redswitch_delay */
 	0xf401f2b6,
 	0xe5f1fd1b,
 	0xe5f10400,
@@ -776,7 +798,7 @@
 	0x03f08500,
 	0x000ed001,
 	0x00f804bd,
-/* 0x0814: ctx_86c */
+/* 0x086c: ctx_86c */
 	0x1b0007f1,
 	0xd00203f0,
 	0x04bd000f,
@@ -787,16 +809,16 @@
 	0xa86ce7f1,
 	0xf441e3f0,
 	0x00f89d21,
-/* 0x083c: ctx_mem */
+/* 0x0894: ctx_mem */
 	0x840007f1,
 	0xd00203f0,
 	0x04bd000f,
-/* 0x0848: ctx_mem_wait */
+/* 0x08a0: ctx_mem_wait */
 	0x8400f7f1,
 	0xcf02f3f0,
 	0xfffd00ff,
 	0xf31bf405,
-/* 0x085a: ctx_load */
+/* 0x08b2: ctx_load */
 	0x94bd00f8,
 	0xf10599f0,
 	0xf00f0007,
@@ -814,7 +836,7 @@
 	0x02d00203,
 	0xf004bd00,
 	0x21f507f7,
-	0x07f1083c,
+	0x07f10894,
 	0x03f0c000,
 	0x0002d002,
 	0x0bfe04bd,
@@ -869,31 +891,31 @@
 	0x03f01700,
 	0x0009d002,
 	0x00f804bd,
-/* 0x0978: ctx_chan */
-	0x077f21f5,
-	0x085a21f5,
+/* 0x09d0: ctx_chan */
+	0x07d721f5,
+	0x08b221f5,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
-	0xa421f508,
-/* 0x0993: ctx_mmio_exec */
+	0x9421f505,
+	0xfc21f508,
+/* 0x09eb: ctx_mmio_exec */
 	0x9800f807,
 	0x07f14103,
 	0x03f08100,
 	0x0003d002,
 	0x34bd04bd,
-/* 0x09a4: ctx_mmio_loop */
+/* 0x09fc: ctx_mmio_loop */
 	0xf4ff34c4,
 	0x57f10f1b,
 	0x53f00200,
 	0x0535fa06,
-/* 0x09b6: ctx_mmio_pull */
+/* 0x0a0e: ctx_mmio_pull */
 	0x4e9803f8,
 	0x814f9880,
 	0xb69d21f4,
 	0x12b60830,
 	0xdf1bf401,
-/* 0x09c8: ctx_mmio_done */
+/* 0x0a20: ctx_mmio_done */
 	0xf1160398,
 	0xf0810007,
 	0x03d00203,
@@ -902,30 +924,30 @@
 	0x13f00100,
 	0x0601fa06,
 	0x00f803f8,
-/* 0x09e8: ctx_xfer */
+/* 0x0a40: ctx_xfer */
 	0xf104e7f0,
 	0xf0020007,
 	0x0ed00303,
-/* 0x09f7: ctx_xfer_idle */
+/* 0x0a4f: ctx_xfer_idle */
 	0xf104bd00,
 	0xf00000e7,
 	0xeecf03e3,
 	0x00e4f100,
 	0xf21bf420,
 	0xf40611f4,
-/* 0x0a0e: ctx_xfer_pre */
+/* 0x0a66: ctx_xfer_pre */
 	0xf7f01102,
-	0x1421f510,
-	0x7f21f508,
+	0x6c21f510,
+	0xd721f508,
 	0x1c11f407,
-/* 0x0a1c: ctx_xfer_pre_load */
+/* 0x0a74: ctx_xfer_pre_load */
 	0xf502f7f0,
-	0xf507b521,
-	0xf507c721,
-	0xbd07dc21,
-	0xb521f5f4,
-	0x5a21f507,
-/* 0x0a35: ctx_xfer_exec */
+	0xf5080d21,
+	0xf5081f21,
+	0xbd083421,
+	0x0d21f5f4,
+	0xb221f508,
+/* 0x0a8d: ctx_xfer_exec */
 	0x16019808,
 	0x07f124bd,
 	0x03f00500,
@@ -960,23 +982,65 @@
 	0x1301f402,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
+	0x9421f505,
 	0x3202f408,
-/* 0x0ac4: ctx_xfer_post */
+/* 0x0b1c: ctx_xfer_post */
 	0xf502f7f0,
-	0xbd07b521,
-	0x1421f5f4,
+	0xbd080d21,
+	0x6c21f5f4,
 	0x7f21f508,
-	0xc721f502,
-	0xf5f4bd07,
-	0xf407b521,
+	0x1f21f502,
+	0xf5f4bd08,
+	0xf4080d21,
 	0x01981011,
 	0x0511fd40,
 	0xf5070bf4,
-/* 0x0aef: ctx_xfer_no_post_mmio */
-	0xf5099321,
-/* 0x0af3: ctx_xfer_done */
-	0xf807a421,
+/* 0x0b47: ctx_xfer_no_post_mmio */
+	0xf509eb21,
+/* 0x0b4b: ctx_xfer_done */
+	0xf807fc21,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h
index 6547b3d..51c3797 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h
@@ -528,10 +528,10 @@
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0x7f21f502,
-	0x9121f507,
+	0xd721f502,
+	0xe921f507,
 	0x10f7f007,
-	0x07de21f5,
+	0x083621f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x07de21f5,
+	0x083621f5,
 	0xf500f7f0,
-	0xf1077f21,
+	0xf107d721,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@
 	0x0203f00f,
 	0xbd0009d0,
 	0x0131f404,
-	0x09aa21f5,
+	0x0a0221f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09aa21,
+	0xfc0a0221,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09aa21f5,
+	0x0a0221f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x4221f502,
+	0x9a21f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,19 +753,19 @@
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4170s */
+/* 0x07d7: ctx_4170s */
 	0xf001f800,
 	0xffb910f5,
 	0x70e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x0791: ctx_4170w */
+/* 0x07e9: ctx_4170w */
 	0x70e7f100,
 	0x40e3f041,
 	0xb96821f4,
 	0xf4f002ff,
 	0xf01bf410,
-/* 0x07a6: ctx_redswitch */
+/* 0x07fe: ctx_redswitch */
 	0xe7f100f8,
 	0xe5f00200,
 	0x20e5f040,
@@ -751,7 +773,7 @@
 	0xf0850007,
 	0x0ed00103,
 	0xf004bd00,
-/* 0x07c2: ctx_redswitch_delay */
+/* 0x081a: ctx_redswitch_delay */
 	0xf2b608f7,
 	0xfd1bf401,
 	0x0400e5f1,
@@ -759,7 +781,7 @@
 	0x850007f1,
 	0xd00103f0,
 	0x04bd000e,
-/* 0x07de: ctx_86c */
+/* 0x0836: ctx_86c */
 	0x07f100f8,
 	0x03f01b00,
 	0x000fd002,
@@ -770,17 +792,17 @@
 	0xe7f102ff,
 	0xe3f0a86c,
 	0x9d21f441,
-/* 0x0806: ctx_mem */
+/* 0x085e: ctx_mem */
 	0x07f100f8,
 	0x03f08400,
 	0x000fd002,
-/* 0x0812: ctx_mem_wait */
+/* 0x086a: ctx_mem_wait */
 	0xf7f104bd,
 	0xf3f08400,
 	0x00ffcf02,
 	0xf405fffd,
 	0x00f8f31b,
-/* 0x0824: ctx_load */
+/* 0x087c: ctx_load */
 	0x99f094bd,
 	0x0007f105,
 	0x0203f00f,
@@ -797,7 +819,7 @@
 	0x0203f083,
 	0xbd0002d0,
 	0x07f7f004,
-	0x080621f5,
+	0x085e21f5,
 	0xc00007f1,
 	0xd00203f0,
 	0x04bd0002,
@@ -852,29 +874,29 @@
 	0x170007f1,
 	0xd00203f0,
 	0x04bd0009,
-/* 0x0942: ctx_chan */
+/* 0x099a: ctx_chan */
 	0x21f500f8,
-	0xa7f00824,
+	0xa7f0087c,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf8080621,
-/* 0x0955: ctx_mmio_exec */
+	0xf8085e21,
+/* 0x09ad: ctx_mmio_exec */
 	0x41039800,
 	0x810007f1,
 	0xd00203f0,
 	0x04bd0003,
-/* 0x0966: ctx_mmio_loop */
+/* 0x09be: ctx_mmio_loop */
 	0x34c434bd,
 	0x0f1bf4ff,
 	0x020057f1,
 	0xfa0653f0,
 	0x03f80535,
-/* 0x0978: ctx_mmio_pull */
+/* 0x09d0: ctx_mmio_pull */
 	0x98804e98,
 	0x21f4814f,
 	0x0830b69d,
 	0xf40112b6,
-/* 0x098a: ctx_mmio_done */
+/* 0x09e2: ctx_mmio_done */
 	0x0398df1b,
 	0x0007f116,
 	0x0203f081,
@@ -883,30 +905,30 @@
 	0x010017f1,
 	0xfa0613f0,
 	0x03f80601,
-/* 0x09aa: ctx_xfer */
+/* 0x0a02: ctx_xfer */
 	0xe7f000f8,
 	0x0007f104,
 	0x0303f002,
 	0xbd000ed0,
-/* 0x09b9: ctx_xfer_idle */
+/* 0x0a11: ctx_xfer_idle */
 	0x00e7f104,
 	0x03e3f000,
 	0xf100eecf,
 	0xf42000e4,
 	0x11f4f21b,
 	0x0d02f406,
-/* 0x09d0: ctx_xfer_pre */
+/* 0x0a28: ctx_xfer_pre */
 	0xf510f7f0,
-	0xf407de21,
-/* 0x09da: ctx_xfer_pre_load */
+	0xf4083621,
+/* 0x0a32: ctx_xfer_pre_load */
 	0xf7f01c11,
-	0x7f21f502,
-	0x9121f507,
-	0xa621f507,
+	0xd721f502,
+	0xe921f507,
+	0xfe21f507,
 	0xf5f4bd07,
-	0xf5077f21,
-/* 0x09f3: ctx_xfer_exec */
-	0x98082421,
+	0xf507d721,
+/* 0x0a4b: ctx_xfer_exec */
+	0x98087c21,
 	0x24bd1601,
 	0x050007f1,
 	0xd00103f0,
@@ -941,21 +963,21 @@
 	0xa7f01301,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf4080621,
-/* 0x0a82: ctx_xfer_post */
+	0xf4085e21,
+/* 0x0ada: ctx_xfer_post */
 	0xf7f02e02,
-	0x7f21f502,
+	0xd721f502,
 	0xf5f4bd07,
-	0xf507de21,
+	0xf5083621,
 	0xf5027f21,
-	0xbd079121,
-	0x7f21f5f4,
+	0xbd07e921,
+	0xd721f5f4,
 	0x1011f407,
 	0xfd400198,
 	0x0bf40511,
-	0x5521f507,
-/* 0x0aad: ctx_xfer_no_post_mmio */
-/* 0x0aad: ctx_xfer_done */
+	0xad21f507,
+/* 0x0b05: ctx_xfer_no_post_mmio */
+/* 0x0b05: ctx_xfer_done */
 	0x0000f809,
 	0x00000000,
 	0x00000000,
@@ -977,4 +999,46 @@
 	0x00000000,
 	0x00000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h
index a5aee5a..a0af4b7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h
@@ -528,10 +528,10 @@
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0x7f21f502,
-	0x9121f507,
+	0xd721f502,
+	0xe921f507,
 	0x10f7f007,
-	0x07de21f5,
+	0x083621f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x07de21f5,
+	0x083621f5,
 	0xf500f7f0,
-	0xf1077f21,
+	0xf107d721,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@
 	0x0203f037,
 	0xbd0009d0,
 	0x0131f404,
-	0x09aa21f5,
+	0x0a0221f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09aa21,
+	0xfc0a0221,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09aa21f5,
+	0x0a0221f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x4221f502,
+	0x9a21f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,19 +753,19 @@
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4170s */
+/* 0x07d7: ctx_4170s */
 	0xf001f800,
 	0xffb910f5,
 	0x70e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x0791: ctx_4170w */
+/* 0x07e9: ctx_4170w */
 	0x70e7f100,
 	0x40e3f041,
 	0xb96821f4,
 	0xf4f002ff,
 	0xf01bf410,
-/* 0x07a6: ctx_redswitch */
+/* 0x07fe: ctx_redswitch */
 	0xe7f100f8,
 	0xe5f00200,
 	0x20e5f040,
@@ -751,7 +773,7 @@
 	0xf0850007,
 	0x0ed00103,
 	0xf004bd00,
-/* 0x07c2: ctx_redswitch_delay */
+/* 0x081a: ctx_redswitch_delay */
 	0xf2b608f7,
 	0xfd1bf401,
 	0x0400e5f1,
@@ -759,7 +781,7 @@
 	0x850007f1,
 	0xd00103f0,
 	0x04bd000e,
-/* 0x07de: ctx_86c */
+/* 0x0836: ctx_86c */
 	0x07f100f8,
 	0x03f02300,
 	0x000fd002,
@@ -770,17 +792,17 @@
 	0xe7f102ff,
 	0xe3f0a88c,
 	0x9d21f441,
-/* 0x0806: ctx_mem */
+/* 0x085e: ctx_mem */
 	0x07f100f8,
 	0x03f08400,
 	0x000fd002,
-/* 0x0812: ctx_mem_wait */
+/* 0x086a: ctx_mem_wait */
 	0xf7f104bd,
 	0xf3f08400,
 	0x00ffcf02,
 	0xf405fffd,
 	0x00f8f31b,
-/* 0x0824: ctx_load */
+/* 0x087c: ctx_load */
 	0x99f094bd,
 	0x0007f105,
 	0x0203f037,
@@ -797,7 +819,7 @@
 	0x0203f083,
 	0xbd0002d0,
 	0x07f7f004,
-	0x080621f5,
+	0x085e21f5,
 	0xc00007f1,
 	0xd00203f0,
 	0x04bd0002,
@@ -852,29 +874,29 @@
 	0x170007f1,
 	0xd00203f0,
 	0x04bd0009,
-/* 0x0942: ctx_chan */
+/* 0x099a: ctx_chan */
 	0x21f500f8,
-	0xa7f00824,
+	0xa7f0087c,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf8080621,
-/* 0x0955: ctx_mmio_exec */
+	0xf8085e21,
+/* 0x09ad: ctx_mmio_exec */
 	0x41039800,
 	0x810007f1,
 	0xd00203f0,
 	0x04bd0003,
-/* 0x0966: ctx_mmio_loop */
+/* 0x09be: ctx_mmio_loop */
 	0x34c434bd,
 	0x0f1bf4ff,
 	0x020057f1,
 	0xfa0653f0,
 	0x03f80535,
-/* 0x0978: ctx_mmio_pull */
+/* 0x09d0: ctx_mmio_pull */
 	0x98804e98,
 	0x21f4814f,
 	0x0830b69d,
 	0xf40112b6,
-/* 0x098a: ctx_mmio_done */
+/* 0x09e2: ctx_mmio_done */
 	0x0398df1b,
 	0x0007f116,
 	0x0203f081,
@@ -883,30 +905,30 @@
 	0x010017f1,
 	0xfa0613f0,
 	0x03f80601,
-/* 0x09aa: ctx_xfer */
+/* 0x0a02: ctx_xfer */
 	0xe7f000f8,
 	0x0007f104,
 	0x0303f002,
 	0xbd000ed0,
-/* 0x09b9: ctx_xfer_idle */
+/* 0x0a11: ctx_xfer_idle */
 	0x00e7f104,
 	0x03e3f000,
 	0xf100eecf,
 	0xf42000e4,
 	0x11f4f21b,
 	0x0d02f406,
-/* 0x09d0: ctx_xfer_pre */
+/* 0x0a28: ctx_xfer_pre */
 	0xf510f7f0,
-	0xf407de21,
-/* 0x09da: ctx_xfer_pre_load */
+	0xf4083621,
+/* 0x0a32: ctx_xfer_pre_load */
 	0xf7f01c11,
-	0x7f21f502,
-	0x9121f507,
-	0xa621f507,
+	0xd721f502,
+	0xe921f507,
+	0xfe21f507,
 	0xf5f4bd07,
-	0xf5077f21,
-/* 0x09f3: ctx_xfer_exec */
-	0x98082421,
+	0xf507d721,
+/* 0x0a4b: ctx_xfer_exec */
+	0x98087c21,
 	0x24bd1601,
 	0x050007f1,
 	0xd00103f0,
@@ -941,21 +963,21 @@
 	0xa7f01301,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf4080621,
-/* 0x0a82: ctx_xfer_post */
+	0xf4085e21,
+/* 0x0ada: ctx_xfer_post */
 	0xf7f02e02,
-	0x7f21f502,
+	0xd721f502,
 	0xf5f4bd07,
-	0xf507de21,
+	0xf5083621,
 	0xf5027f21,
-	0xbd079121,
-	0x7f21f5f4,
+	0xbd07e921,
+	0xd721f5f4,
 	0x1011f407,
 	0xfd400198,
 	0x0bf40511,
-	0x5521f507,
-/* 0x0aad: ctx_xfer_no_post_mmio */
-/* 0x0aad: ctx_xfer_done */
+	0xad21f507,
+/* 0x0b05: ctx_xfer_no_post_mmio */
+/* 0x0b05: ctx_xfer_done */
 	0x0000f809,
 	0x00000000,
 	0x00000000,
@@ -977,4 +999,46 @@
 	0x00000000,
 	0x00000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc
index a47d49d..2a0b0f8 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc
@@ -30,6 +30,12 @@
 #define GK110 0xf0
 #define GK208 0x108
 
+#define NV_PGRAPH_TRAPPED_ADDR                                         0x400704
+#define NV_PGRAPH_TRAPPED_DATA_LO                                      0x400708
+#define NV_PGRAPH_TRAPPED_DATA_HI                                      0x40070c
+
+#define NV_PGRAPH_FE_OBJECT_TABLE(n)                        ((n) * 4 + 0x400700)
+
 #define NV_PGRAPH_FECS_INTR_ACK                                        0x409004
 #define NV_PGRAPH_FECS_INTR                                            0x409008
 #define NV_PGRAPH_FECS_INTR_FWMTHD                                   0x00000400
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h
index fd1d380..1718ae4 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h
@@ -3,5 +3,6 @@
 
 #define E_BAD_COMMAND  0x00000001
 #define E_CMD_OVERFLOW 0x00000002
+#define E_BAD_FWMTHD   0x00000003
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
index 1a2d564..20665c2 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
@@ -976,7 +976,6 @@
 		break;
 	case 0xa0:
 	default:
-		nv_wr32(priv, 0x402cc0, 0x00000000);
 		if (nv_device(priv)->chipset == 0xa0 ||
 		    nv_device(priv)->chipset == 0xaa ||
 		    nv_device(priv)->chipset == 0xac) {
@@ -991,10 +990,10 @@
 
 	/* zero out zcull regions */
 	for (i = 0; i < 8; i++) {
-		nv_wr32(priv, 0x402c20 + (i * 8), 0x00000000);
-		nv_wr32(priv, 0x402c24 + (i * 8), 0x00000000);
-		nv_wr32(priv, 0x402c28 + (i * 8), 0x00000000);
-		nv_wr32(priv, 0x402c2c + (i * 8), 0x00000000);
+		nv_wr32(priv, 0x402c20 + (i * 0x10), 0x00000000);
+		nv_wr32(priv, 0x402c24 + (i * 0x10), 0x00000000);
+		nv_wr32(priv, 0x402c28 + (i * 0x10), 0x00000000);
+		nv_wr32(priv, 0x402c2c + (i * 0x10), 0x00000000);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
index bf7bdb1..aa08389 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
@@ -789,17 +789,40 @@
 static void
 nvc0_graph_ctxctl_isr(struct nvc0_graph_priv *priv)
 {
-	u32 ustat = nv_rd32(priv, 0x409c18);
+	u32 stat = nv_rd32(priv, 0x409c18);
 
-	if (ustat & 0x00000001)
-		nv_error(priv, "CTXCTL ucode error\n");
-	if (ustat & 0x00080000)
-		nv_error(priv, "CTXCTL watchdog timeout\n");
-	if (ustat & ~0x00080001)
-		nv_error(priv, "CTXCTL 0x%08x\n", ustat);
+	if (stat & 0x00000001) {
+		u32 code = nv_rd32(priv, 0x409814);
+		if (code == E_BAD_FWMTHD) {
+			u32 class = nv_rd32(priv, 0x409808);
+			u32  addr = nv_rd32(priv, 0x40980c);
+			u32  subc = (addr & 0x00070000) >> 16;
+			u32  mthd = (addr & 0x00003ffc);
+			u32  data = nv_rd32(priv, 0x409810);
 
-	nvc0_graph_ctxctl_debug(priv);
-	nv_wr32(priv, 0x409c20, ustat);
+			nv_error(priv, "FECS MTHD subc %d class 0x%04x "
+				       "mthd 0x%04x data 0x%08x\n",
+				 subc, class, mthd, data);
+
+			nv_wr32(priv, 0x409c20, 0x00000001);
+			stat &= ~0x00000001;
+		} else {
+			nv_error(priv, "FECS ucode error %d\n", code);
+		}
+	}
+
+	if (stat & 0x00080000) {
+		nv_error(priv, "FECS watchdog timeout\n");
+		nvc0_graph_ctxctl_debug(priv);
+		nv_wr32(priv, 0x409c20, 0x00080000);
+		stat &= ~0x00080000;
+	}
+
+	if (stat) {
+		nv_error(priv, "FECS 0x%08x\n", stat);
+		nvc0_graph_ctxctl_debug(priv);
+		nv_wr32(priv, 0x409c20, stat);
+	}
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h
index 75203a9..ffc2891 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h
@@ -38,6 +38,8 @@
 #include <engine/fifo.h>
 #include <engine/graph.h>
 
+#include "fuc/os.h"
+
 #define GPC_MAX 32
 #define TPC_MAX (GPC_MAX * 8)
 
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
index db1b39d0..825f7bb 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
@@ -84,6 +84,7 @@
 extern struct nouveau_oclass *nv50_i2c_oclass;
 extern struct nouveau_oclass *nv94_i2c_oclass;
 extern struct nouveau_oclass *nvd0_i2c_oclass;
+extern struct nouveau_oclass *gf117_i2c_oclass;
 extern struct nouveau_oclass *nve0_i2c_oclass;
 
 static inline int
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c
index 4ac1aa3..0e62a32 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c
@@ -307,7 +307,6 @@
 		info->dsrc = src0;
 		if (div0) {
 			info->ddiv |= 0x80000000;
-			info->ddiv |= div0 << 8;
 			info->ddiv |= div0;
 		}
 		if (div1D) {
@@ -352,7 +351,7 @@
 {
 	struct nve0_clock_info *info = &priv->eng[clk];
 	if (!info->ssel) {
-		nv_mask(priv, 0x1371d0 + (clk * 0x04), 0x80003f3f, info->ddiv);
+		nv_mask(priv, 0x1371d0 + (clk * 0x04), 0x8000003f, info->ddiv);
 		nv_wr32(priv, 0x137160 + (clk * 0x04), info->dsrc);
 	}
 }
@@ -389,7 +388,10 @@
 nve0_clock_prog_3(struct nve0_clock_priv *priv, int clk)
 {
 	struct nve0_clock_info *info = &priv->eng[clk];
-	nv_mask(priv, 0x137250 + (clk * 0x04), 0x00003f3f, info->mdiv);
+	if (info->ssel)
+		nv_mask(priv, 0x137250 + (clk * 0x04), 0x00003f00, info->mdiv);
+	else
+		nv_mask(priv, 0x137250 + (clk * 0x04), 0x0000003f, info->mdiv);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
index 84c7efb..1ad3ea5 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
@@ -262,8 +262,8 @@
 	struct nve0_ram *ram = (void *)pfb->ram;
 	struct nve0_ramfuc *fuc = &ram->fuc;
 	struct nouveau_ram_data *next = ram->base.next;
-	int vc = !(next->bios.ramcfg_11_02_08);
-	int mv = !(next->bios.ramcfg_11_02_04);
+	int vc = !next->bios.ramcfg_11_02_08;
+	int mv = !next->bios.ramcfg_11_02_04;
 	u32 mask, data;
 
 	ram_mask(fuc, 0x10f808, 0x40000000, 0x40000000);
@@ -370,8 +370,8 @@
 		}
 	}
 
-	if ( (next->bios.ramcfg_11_02_40) ||
-	     (next->bios.ramcfg_11_07_10)) {
+	if (next->bios.ramcfg_11_02_40 ||
+	    next->bios.ramcfg_11_07_10) {
 		ram_mask(fuc, 0x132040, 0x00010000, 0x00010000);
 		ram_nsec(fuc, 20000);
 	}
@@ -417,7 +417,7 @@
 		ram_mask(fuc, 0x10f694, 0xff00ff00, data);
 	}
 
-	if (ram->mode == 2 && (next->bios.ramcfg_11_08_10))
+	if (ram->mode == 2 && next->bios.ramcfg_11_08_10)
 		data = 0x00000080;
 	else
 		data = 0x00000000;
@@ -425,13 +425,13 @@
 
 	mask = 0x00070000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_02_80))
+	if (!next->bios.ramcfg_11_02_80)
 		data |= 0x03000000;
-	if (!(next->bios.ramcfg_11_02_40))
+	if (!next->bios.ramcfg_11_02_40)
 		data |= 0x00002000;
-	if (!(next->bios.ramcfg_11_07_10))
+	if (!next->bios.ramcfg_11_07_10)
 		data |= 0x00004000;
-	if (!(next->bios.ramcfg_11_07_08))
+	if (!next->bios.ramcfg_11_07_08)
 		data |= 0x00000003;
 	else
 		data |= 0x74000000;
@@ -486,7 +486,7 @@
 
 	data = mask = 0x00000000;
 	if (NOTE00(ramcfg_02_03 != 0)) {
-		data |= (next->bios.ramcfg_11_02_03) << 8;
+		data |= next->bios.ramcfg_11_02_03 << 8;
 		mask |= 0x00000300;
 	}
 	if (NOTE00(ramcfg_01_10)) {
@@ -498,7 +498,7 @@
 
 	data = mask = 0x00000000;
 	if (NOTE00(timing_30_07 != 0)) {
-		data |= (next->bios.timing_20_30_07) << 28;
+		data |= next->bios.timing_20_30_07 << 28;
 		mask |= 0x70000000;
 	}
 	if (NOTE00(ramcfg_01_01)) {
@@ -510,7 +510,7 @@
 
 	data = mask = 0x00000000;
 	if (NOTE00(timing_30_07 != 0)) {
-		data |= (next->bios.timing_20_30_07) << 28;
+		data |= next->bios.timing_20_30_07 << 28;
 		mask |= 0x70000000;
 	}
 	if (NOTE00(ramcfg_01_02)) {
@@ -522,16 +522,16 @@
 
 	mask = 0x33f00000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_01_04))
+	if (!next->bios.ramcfg_11_01_04)
 		data |= 0x20200000;
-	if (!(next->bios.ramcfg_11_07_80))
+	if (!next->bios.ramcfg_11_07_80)
 		data |= 0x12800000;
 	/*XXX: see note above about there probably being some condition
 	 *     for the 10f824 stuff that uses ramcfg 3...
 	 */
-	if ( (next->bios.ramcfg_11_03_f0)) {
+	if (next->bios.ramcfg_11_03_f0) {
 		if (next->bios.rammap_11_08_0c) {
-			if (!(next->bios.ramcfg_11_07_80))
+			if (!next->bios.ramcfg_11_07_80)
 				mask |= 0x00000020;
 			else
 				data |= 0x00000020;
@@ -563,7 +563,7 @@
 		ram_wait(fuc, 0x100710, 0x80000000, 0x80000000, 200000);
 	}
 
-	data = (next->bios.timing_20_30_07) << 8;
+	data = next->bios.timing_20_30_07 << 8;
 	if (next->bios.ramcfg_11_01_01)
 		data |= 0x80000000;
 	ram_mask(fuc, 0x100778, 0x00000700, data);
@@ -588,7 +588,7 @@
 	ram_wr32(fuc, 0x10f310, 0x00000001); /* REFRESH */
 	ram_wr32(fuc, 0x10f210, 0x80000000); /* REFRESH_AUTO = 1 */
 
-	if ((next->bios.ramcfg_11_08_10) && (ram->mode == 2) /*XXX*/) {
+	if (next->bios.ramcfg_11_08_10 && (ram->mode == 2) /*XXX*/) {
 		u32 temp = ram_mask(fuc, 0x10f294, 0xff000000, 0x24000000);
 		nve0_ram_train(fuc, 0xbc0e0000, 0xa4010000); /*XXX*/
 		ram_nsec(fuc, 1000);
@@ -621,8 +621,8 @@
 	data  = ram_rd32(fuc, 0x10f978);
 	data &= ~0x00046144;
 	data |=  0x0000000b;
-	if (!(next->bios.ramcfg_11_07_08)) {
-		if (!(next->bios.ramcfg_11_07_04))
+	if (!next->bios.ramcfg_11_07_08) {
+		if (!next->bios.ramcfg_11_07_04)
 			data |= 0x0000200c;
 		else
 			data |= 0x00000000;
@@ -636,11 +636,11 @@
 		ram_wr32(fuc, 0x10f830, data);
 	}
 
-	if (!(next->bios.ramcfg_11_07_08)) {
+	if (!next->bios.ramcfg_11_07_08) {
 		data = 0x88020000;
-		if ( (next->bios.ramcfg_11_07_04))
+		if ( next->bios.ramcfg_11_07_04)
 			data |= 0x10000000;
-		if (!(next->bios.rammap_11_08_10))
+		if (!next->bios.rammap_11_08_10)
 			data |= 0x00080000;
 	} else {
 		data = 0xa40e0000;
@@ -689,8 +689,8 @@
 	const u32 runk0 = ram->fN1 << 16;
 	const u32 runk1 = ram->fN1;
 	struct nouveau_ram_data *next = ram->base.next;
-	int vc = !(next->bios.ramcfg_11_02_08);
-	int mv = !(next->bios.ramcfg_11_02_04);
+	int vc = !next->bios.ramcfg_11_02_08;
+	int mv = !next->bios.ramcfg_11_02_04;
 	u32 mask, data;
 
 	ram_mask(fuc, 0x10f808, 0x40000000, 0x40000000);
@@ -705,7 +705,7 @@
 	}
 
 	ram_mask(fuc, 0x10f200, 0x00000800, 0x00000000);
-	if ((next->bios.ramcfg_11_03_f0))
+	if (next->bios.ramcfg_11_03_f0)
 		ram_mask(fuc, 0x10f808, 0x04000000, 0x04000000);
 
 	ram_wr32(fuc, 0x10f314, 0x00000001); /* PRECHARGE */
@@ -761,7 +761,7 @@
 
 	ram_mask(fuc, 0x1373f4, 0x00000000, 0x00010010);
 	data  = ram_rd32(fuc, 0x1373ec) & ~0x00030000;
-	data |= (next->bios.ramcfg_11_03_30) << 12;
+	data |= next->bios.ramcfg_11_03_30 << 16;
 	ram_wr32(fuc, 0x1373ec, data);
 	ram_mask(fuc, 0x1373f4, 0x00000003, 0x00000000);
 	ram_mask(fuc, 0x1373f4, 0x00000010, 0x00000000);
@@ -793,8 +793,8 @@
 		}
 	}
 
-	if ( (next->bios.ramcfg_11_02_40) ||
-	     (next->bios.ramcfg_11_07_10)) {
+	if (next->bios.ramcfg_11_02_40 ||
+	    next->bios.ramcfg_11_07_10) {
 		ram_mask(fuc, 0x132040, 0x00010000, 0x00010000);
 		ram_nsec(fuc, 20000);
 	}
@@ -810,13 +810,13 @@
 
 	mask = 0x00010000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_02_80))
+	if (!next->bios.ramcfg_11_02_80)
 		data |= 0x03000000;
-	if (!(next->bios.ramcfg_11_02_40))
+	if (!next->bios.ramcfg_11_02_40)
 		data |= 0x00002000;
-	if (!(next->bios.ramcfg_11_07_10))
+	if (!next->bios.ramcfg_11_07_10)
 		data |= 0x00004000;
-	if (!(next->bios.ramcfg_11_07_08))
+	if (!next->bios.ramcfg_11_07_08)
 		data |= 0x00000003;
 	else
 		data |= 0x14000000;
@@ -844,16 +844,16 @@
 
 	mask = 0x33f00000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_01_04))
+	if (!next->bios.ramcfg_11_01_04)
 		data |= 0x20200000;
-	if (!(next->bios.ramcfg_11_07_80))
+	if (!next->bios.ramcfg_11_07_80)
 		data |= 0x12800000;
 	/*XXX: see note above about there probably being some condition
 	 *     for the 10f824 stuff that uses ramcfg 3...
 	 */
-	if ( (next->bios.ramcfg_11_03_f0)) {
+	if (next->bios.ramcfg_11_03_f0) {
 		if (next->bios.rammap_11_08_0c) {
-			if (!(next->bios.ramcfg_11_07_80))
+			if (!next->bios.ramcfg_11_07_80)
 				mask |= 0x00000020;
 			else
 				data |= 0x00000020;
@@ -876,7 +876,7 @@
 		data = next->bios.timing_20_2c_1fc0;
 	ram_mask(fuc, 0x10f24c, 0x7f000000, data << 24);
 
-	ram_mask(fuc, 0x10f224, 0x001f0000, next->bios.timing_20_30_f8);
+	ram_mask(fuc, 0x10f224, 0x001f0000, next->bios.timing_20_30_f8 << 16);
 
 	ram_wr32(fuc, 0x10f090, 0x4000007f);
 	ram_nsec(fuc, 1000);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/gf117.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/gf117.c
new file mode 100644
index 0000000..fa891c3
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/gf117.c
@@ -0,0 +1,39 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "nv50.h"
+
+struct nouveau_oclass *
+gf117_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0xd7),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
+		.dtor = _nouveau_i2c_dtor,
+		.init = _nouveau_i2c_init,
+		.fini = _nouveau_i2c_fini,
+	},
+	.sclass = nvd0_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+	.pad_s = &nv04_i2c_pad_oclass,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c b/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c
index 7120124..ebef970 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c
@@ -95,6 +95,23 @@
 }
 
 static int
+nve0_ibus_init(struct nouveau_object *object)
+{
+	struct nve0_ibus_priv *priv = (void *)object;
+	int ret = nouveau_ibus_init(&priv->base);
+	if (ret == 0) {
+		nv_mask(priv, 0x122318, 0x0003ffff, 0x00001000);
+		nv_mask(priv, 0x12231c, 0x0003ffff, 0x00000200);
+		nv_mask(priv, 0x122310, 0x0003ffff, 0x00000800);
+		nv_mask(priv, 0x122348, 0x0003ffff, 0x00000100);
+		nv_mask(priv, 0x1223b0, 0x0003ffff, 0x00000fff);
+		nv_mask(priv, 0x122348, 0x0003ffff, 0x00000200);
+		nv_mask(priv, 0x122358, 0x0003ffff, 0x00002880);
+	}
+	return ret;
+}
+
+static int
 nve0_ibus_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	       struct nouveau_oclass *oclass, void *data, u32 size,
 	       struct nouveau_object **pobject)
@@ -117,7 +134,7 @@
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nve0_ibus_ctor,
 		.dtor = _nouveau_ibus_dtor,
-		.init = _nouveau_ibus_init,
+		.init = nve0_ibus_init,
 		.fini = _nouveau_ibus_fini,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc
index 2284ecb..c2bb616a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc
@@ -83,7 +83,7 @@
 		// increment GET
 		add b32 $r1 0x1
 		and $r14 $r1 #fifo_qmaskf
-		nv_iowr(NV_PPWR_FIFO_GET(0), $r1)
+		nv_iowr(NV_PPWR_FIFO_GET(0), $r14)
 		bra #host_send
 	host_send_done:
 	ret
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
index 4bd43a9..39a5dc1 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
@@ -1018,7 +1018,7 @@
 	0xb600023f,
 	0x1ec40110,
 	0x04b0400f,
-	0xbd0001f6,
+	0xbd000ef6,
 	0xc70ef404,
 /* 0x0328: host_send_done */
 /* 0x032a: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
index 5a73fa6..254205c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
@@ -1124,7 +1124,7 @@
 	0x0f1ec401,
 	0x04b007f1,
 	0xd00604b6,
-	0x04bd0001,
+	0x04bd000e,
 /* 0x03cb: host_send_done */
 	0xf8ba0ef4,
 /* 0x03cd: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
index 4dba00d..7ac8740 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
@@ -1124,7 +1124,7 @@
 	0x0f1ec401,
 	0x04b007f1,
 	0xd00604b6,
-	0x04bd0001,
+	0x04bd000e,
 /* 0x03cb: host_send_done */
 	0xf8ba0ef4,
 /* 0x03cd: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
index 5e24c6b..cd9ff1a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
@@ -1033,7 +1033,7 @@
 	0xb6026b21,
 	0x1ec40110,
 	0xb007f10f,
-	0x0001d004,
+	0x000ed004,
 	0x0ef404bd,
 /* 0x0365: host_send_done */
 /* 0x0367: host_recv */
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 26b5647..47ad742 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -736,6 +736,9 @@
 		  fb->bits_per_pixel, fb->pitches[0], crtc->x, crtc->y,
 		  new_bo->bo.offset };
 
+	/* Keep vblanks on during flip, for the target crtc of this flip */
+	drm_vblank_get(dev, nouveau_crtc(crtc)->index);
+
 	/* Emit a page flip */
 	if (nv_device(drm->device)->card_type >= NV_50) {
 		ret = nv50_display_flip_next(crtc, fb, chan, swap_interval);
@@ -779,6 +782,7 @@
 	return 0;
 
 fail_unreserve:
+	drm_vblank_put(dev, nouveau_crtc(crtc)->index);
 	ttm_bo_unreserve(&old_bo->bo);
 fail_unpin:
 	mutex_unlock(&chan->cli->mutex);
@@ -817,6 +821,9 @@
 		drm_send_vblank_event(dev, crtcid, s->event);
 	}
 
+	/* Give up ownership of vblank for page-flipped crtc */
+	drm_vblank_put(dev, s->crtc);
+
 	list_del(&s->head);
 	if (ps)
 		*ps = *s;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 26c12a3..a03c734 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1052,7 +1052,7 @@
 	int encoder_mode = atombios_get_encoder_mode(radeon_crtc->encoder);
 
 	/* pass the actual clock to atombios_crtc_program_pll for DCE5,6 for HDMI */
-	if (ASIC_IS_DCE5(rdev) && !ASIC_IS_DCE8(rdev) &&
+	if (ASIC_IS_DCE5(rdev) &&
 	    (encoder_mode == ATOM_ENCODER_MODE_HDMI) &&
 	    (radeon_crtc->bpc > 8))
 		clock = radeon_crtc->adjusted_clock;
@@ -1136,6 +1136,7 @@
 	u32 fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_NONE);
 	u32 tmp, viewport_w, viewport_h;
 	int r;
+	bool bypass_lut = false;
 
 	/* no fb bound */
 	if (!atomic && !crtc->primary->fb) {
@@ -1174,33 +1175,73 @@
 	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(rbo);
 
-	switch (target_fb->bits_per_pixel) {
-	case 8:
+	switch (target_fb->pixel_format) {
+	case DRM_FORMAT_C8:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_8BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_INDEXED));
 		break;
-	case 15:
+	case DRM_FORMAT_XRGB4444:
+	case DRM_FORMAT_ARGB4444:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB4444));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
+#endif
+		break;
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_ARGB1555:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB1555));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
+#endif
 		break;
-	case 16:
+	case DRM_FORMAT_BGRX5551:
+	case DRM_FORMAT_BGRA5551:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_BGRA5551));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
+#endif
+		break;
+	case DRM_FORMAT_RGB565:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB565));
 #ifdef __BIG_ENDIAN
 		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
 #endif
 		break;
-	case 24:
-	case 32:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_32BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB8888));
 #ifdef __BIG_ENDIAN
 		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN32);
 #endif
 		break;
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_32BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB2101010));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN32);
+#endif
+		/* Greater 8 bpc fb needs to bypass hw-lut to retain precision */
+		bypass_lut = true;
+		break;
+	case DRM_FORMAT_BGRX1010102:
+	case DRM_FORMAT_BGRA1010102:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_32BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_BGRA1010102));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN32);
+#endif
+		/* Greater 8 bpc fb needs to bypass hw-lut to retain precision */
+		bypass_lut = true;
+		break;
 	default:
-		DRM_ERROR("Unsupported screen depth %d\n",
-			  target_fb->bits_per_pixel);
+		DRM_ERROR("Unsupported screen format %s\n",
+			  drm_get_format_name(target_fb->pixel_format));
 		return -EINVAL;
 	}
 
@@ -1329,6 +1370,18 @@
 	WREG32(EVERGREEN_GRPH_CONTROL + radeon_crtc->crtc_offset, fb_format);
 	WREG32(EVERGREEN_GRPH_SWAP_CONTROL + radeon_crtc->crtc_offset, fb_swap);
 
+	/*
+	 * The LUT only has 256 slots for indexing by a 8 bpc fb. Bypass the LUT
+	 * for > 8 bpc scanout to avoid truncation of fb indices to 8 msb's, to
+	 * retain the full precision throughout the pipeline.
+	 */
+	WREG32_P(EVERGREEN_GRPH_LUT_10BIT_BYPASS_CONTROL + radeon_crtc->crtc_offset,
+		 (bypass_lut ? EVERGREEN_LUT_10BIT_BYPASS_EN : 0),
+		 ~EVERGREEN_LUT_10BIT_BYPASS_EN);
+
+	if (bypass_lut)
+		DRM_DEBUG_KMS("Bypassing hardware LUT due to 10 bit fb scanout.\n");
+
 	WREG32(EVERGREEN_GRPH_SURFACE_OFFSET_X + radeon_crtc->crtc_offset, 0);
 	WREG32(EVERGREEN_GRPH_SURFACE_OFFSET_Y + radeon_crtc->crtc_offset, 0);
 	WREG32(EVERGREEN_GRPH_X_START + radeon_crtc->crtc_offset, 0);
@@ -1396,6 +1449,7 @@
 	u32 fb_swap = R600_D1GRPH_SWAP_ENDIAN_NONE;
 	u32 tmp, viewport_w, viewport_h;
 	int r;
+	bool bypass_lut = false;
 
 	/* no fb bound */
 	if (!atomic && !crtc->primary->fb) {
@@ -1433,18 +1487,30 @@
 	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(rbo);
 
-	switch (target_fb->bits_per_pixel) {
-	case 8:
+	switch (target_fb->pixel_format) {
+	case DRM_FORMAT_C8:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_8BPP |
 		    AVIVO_D1GRPH_CONTROL_8BPP_INDEXED;
 		break;
-	case 15:
+	case DRM_FORMAT_XRGB4444:
+	case DRM_FORMAT_ARGB4444:
+		fb_format =
+		    AVIVO_D1GRPH_CONTROL_DEPTH_16BPP |
+		    AVIVO_D1GRPH_CONTROL_16BPP_ARGB4444;
+#ifdef __BIG_ENDIAN
+		fb_swap = R600_D1GRPH_SWAP_ENDIAN_16BIT;
+#endif
+		break;
+	case DRM_FORMAT_XRGB1555:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_16BPP |
 		    AVIVO_D1GRPH_CONTROL_16BPP_ARGB1555;
+#ifdef __BIG_ENDIAN
+		fb_swap = R600_D1GRPH_SWAP_ENDIAN_16BIT;
+#endif
 		break;
-	case 16:
+	case DRM_FORMAT_RGB565:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_16BPP |
 		    AVIVO_D1GRPH_CONTROL_16BPP_RGB565;
@@ -1452,8 +1518,8 @@
 		fb_swap = R600_D1GRPH_SWAP_ENDIAN_16BIT;
 #endif
 		break;
-	case 24:
-	case 32:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_32BPP |
 		    AVIVO_D1GRPH_CONTROL_32BPP_ARGB8888;
@@ -1461,9 +1527,20 @@
 		fb_swap = R600_D1GRPH_SWAP_ENDIAN_32BIT;
 #endif
 		break;
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
+		fb_format =
+		    AVIVO_D1GRPH_CONTROL_DEPTH_32BPP |
+		    AVIVO_D1GRPH_CONTROL_32BPP_ARGB2101010;
+#ifdef __BIG_ENDIAN
+		fb_swap = R600_D1GRPH_SWAP_ENDIAN_32BIT;
+#endif
+		/* Greater 8 bpc fb needs to bypass hw-lut to retain precision */
+		bypass_lut = true;
+		break;
 	default:
-		DRM_ERROR("Unsupported screen depth %d\n",
-			  target_fb->bits_per_pixel);
+		DRM_ERROR("Unsupported screen format %s\n",
+			  drm_get_format_name(target_fb->pixel_format));
 		return -EINVAL;
 	}
 
@@ -1502,6 +1579,13 @@
 	if (rdev->family >= CHIP_R600)
 		WREG32(R600_D1GRPH_SWAP_CONTROL + radeon_crtc->crtc_offset, fb_swap);
 
+	/* LUT only has 256 slots for 8 bpc fb. Bypass for > 8 bpc scanout for precision */
+	WREG32_P(AVIVO_D1GRPH_LUT_SEL + radeon_crtc->crtc_offset,
+		 (bypass_lut ? AVIVO_LUT_10BIT_BYPASS_EN : 0), ~AVIVO_LUT_10BIT_BYPASS_EN);
+
+	if (bypass_lut)
+		DRM_DEBUG_KMS("Bypassing hardware LUT due to 10 bit fb scanout.\n");
+
 	WREG32(AVIVO_D1GRPH_SURFACE_OFFSET_X + radeon_crtc->crtc_offset, 0);
 	WREG32(AVIVO_D1GRPH_SURFACE_OFFSET_Y + radeon_crtc->crtc_offset, 0);
 	WREG32(AVIVO_D1GRPH_X_START + radeon_crtc->crtc_offset, 0);
diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h
index a0f63ff..333d143 100644
--- a/drivers/gpu/drm/radeon/evergreen_reg.h
+++ b/drivers/gpu/drm/radeon/evergreen_reg.h
@@ -116,6 +116,8 @@
 #       define EVERGREEN_GRPH_ARRAY_LINEAR_ALIGNED      1
 #       define EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1      2
 #       define EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1      4
+#define EVERGREEN_GRPH_LUT_10BIT_BYPASS_CONTROL         0x6808
+#       define EVERGREEN_LUT_10BIT_BYPASS_EN            (1 << 8)
 #define EVERGREEN_GRPH_SWAP_CONTROL                     0x680c
 #       define EVERGREEN_GRPH_ENDIAN_SWAP(x)            (((x) & 0x3) << 0)
 #       define EVERGREEN_GRPH_ENDIAN_NONE               0
diff --git a/drivers/gpu/drm/radeon/r500_reg.h b/drivers/gpu/drm/radeon/r500_reg.h
index 1dd0d32..136b7bc 100644
--- a/drivers/gpu/drm/radeon/r500_reg.h
+++ b/drivers/gpu/drm/radeon/r500_reg.h
@@ -402,6 +402,7 @@
  * block and vice versa.  This applies to GRPH, CUR, etc.
  */
 #define AVIVO_D1GRPH_LUT_SEL                                    0x6108
+#       define AVIVO_LUT_10BIT_BYPASS_EN                        (1 << 8)
 #define AVIVO_D1GRPH_PRIMARY_SURFACE_ADDRESS                    0x6110
 #define R700_D1GRPH_PRIMARY_SURFACE_ADDRESS_HIGH                0x6914
 #define R700_D2GRPH_PRIMARY_SURFACE_ADDRESS_HIGH                0x6114
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 933c5c3..1b9177e 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1288,17 +1288,15 @@
 		    (radeon_connector->connector_object_id == CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D) ||
 		    (radeon_connector->connector_object_id == CONNECTOR_OBJECT_ID_HDMI_TYPE_B))
 			return MODE_OK;
-		else if (radeon_connector->connector_object_id == CONNECTOR_OBJECT_ID_HDMI_TYPE_A) {
-			if (ASIC_IS_DCE6(rdev)) {
-				/* HDMI 1.3+ supports max clock of 340 Mhz */
-				if (mode->clock > 340000)
-					return MODE_CLOCK_HIGH;
-				else
-					return MODE_OK;
-			} else
+		else if (ASIC_IS_DCE6(rdev) && drm_detect_hdmi_monitor(radeon_connector->edid)) {
+			/* HDMI 1.3+ supports max clock of 340 Mhz */
+			if (mode->clock > 340000)
 				return MODE_CLOCK_HIGH;
-		} else
+			else
+				return MODE_OK;
+		} else {
 			return MODE_CLOCK_HIGH;
+		}
 	}
 
 	/* check against the max pixel clock */
@@ -1549,6 +1547,8 @@
 static int radeon_dp_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
+	struct drm_device *dev = connector->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
 
@@ -1579,14 +1579,23 @@
 					return MODE_PANEL;
 			}
 		}
-		return MODE_OK;
 	} else {
 		if ((radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
-		    (radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP))
+		    (radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
 			return radeon_dp_mode_valid_helper(connector, mode);
-		else
-			return MODE_OK;
+		} else {
+			if (ASIC_IS_DCE6(rdev) && drm_detect_hdmi_monitor(radeon_connector->edid)) {
+				/* HDMI 1.3+ supports max clock of 340 Mhz */
+				if (mode->clock > 340000)
+					return MODE_CLOCK_HIGH;
+			} else {
+				if (mode->clock > 165000)
+					return MODE_CLOCK_HIGH;
+			}
+		}
 	}
+
+	return MODE_OK;
 }
 
 static const struct drm_connector_helper_funcs radeon_dp_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 5ed6170..8fc362a 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -66,7 +66,8 @@
 			     (radeon_crtc->lut_b[i] << 0));
 	}
 
-	WREG32(AVIVO_D1GRPH_LUT_SEL + radeon_crtc->crtc_offset, radeon_crtc->crtc_id);
+	/* Only change bit 0 of LUT_SEL, other bits are set elsewhere */
+	WREG32_P(AVIVO_D1GRPH_LUT_SEL + radeon_crtc->crtc_offset, radeon_crtc->crtc_id, ~1);
 }
 
 static void dce4_crtc_load_lut(struct drm_crtc *crtc)
@@ -357,8 +358,9 @@
 
 	spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
 
+	drm_vblank_put(rdev->ddev, radeon_crtc->crtc_id);
 	radeon_fence_unref(&work->fence);
-	radeon_irq_kms_pflip_irq_get(rdev, work->crtc_id);
+	radeon_irq_kms_pflip_irq_put(rdev, work->crtc_id);
 	queue_work(radeon_crtc->flip_queue, &work->unpin_work);
 }
 
@@ -459,6 +461,12 @@
 		base &= ~7;
 	}
 
+	r = drm_vblank_get(crtc->dev, radeon_crtc->crtc_id);
+	if (r) {
+		DRM_ERROR("failed to get vblank before flip\n");
+		goto pflip_cleanup;
+	}
+
 	/* We borrow the event spin lock for protecting flip_work */
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
@@ -473,6 +481,16 @@
 
 	return;
 
+pflip_cleanup:
+	if (unlikely(radeon_bo_reserve(work->new_rbo, false) != 0)) {
+		DRM_ERROR("failed to reserve new rbo in error path\n");
+		goto cleanup;
+	}
+	if (unlikely(radeon_bo_unpin(work->new_rbo) != 0)) {
+		DRM_ERROR("failed to unpin new rbo in error path\n");
+	}
+	radeon_bo_unreserve(work->new_rbo);
+
 cleanup:
 	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
 	radeon_fence_unref(&work->fence);
diff --git a/drivers/hsi/clients/Kconfig b/drivers/hsi/clients/Kconfig
index 71b9f9a..bc60dec 100644
--- a/drivers/hsi/clients/Kconfig
+++ b/drivers/hsi/clients/Kconfig
@@ -15,7 +15,7 @@
 
 config SSI_PROTOCOL
 	tristate "SSI protocol"
-	depends on HSI && PHONET && (OMAP_SSI=y || OMAP_SSI=m)
+	depends on HSI && PHONET && OMAP_SSI
 	help
 	If you say Y here, you will enable the SSI protocol aka McSAAB.
 
diff --git a/drivers/hsi/controllers/omap_ssi_port.c b/drivers/hsi/controllers/omap_ssi_port.c
index b8693f0..29aea0b 100644
--- a/drivers/hsi/controllers/omap_ssi_port.c
+++ b/drivers/hsi/controllers/omap_ssi_port.c
@@ -1116,8 +1116,7 @@
 
 	dev_dbg(&pd->dev, "init ssi port...\n");
 
-	err = ref_module(THIS_MODULE, ssi->owner);
-	if (err) {
+	if (!try_module_get(ssi->owner)) {
 		dev_err(&pd->dev, "could not increment parent module refcount (err=%d)\n",
 			err);
 		return -ENODEV;
@@ -1254,6 +1253,7 @@
 
 	omap_ssi->port[omap_port->port_id] = NULL;
 	platform_set_drvdata(pd, NULL);
+	module_put(ssi->owner);
 	pm_runtime_disable(&pd->dev);
 
 	return 0;
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 0034316..08531a1 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1124,6 +1124,16 @@
 	  This driver can also be built as a module.  If so, the module
 	  will be called sht21.
 
+config SENSORS_SHTC1
+	tristate "Sensiron humidity and temperature sensors. SHTC1 and compat."
+	depends on I2C
+	help
+	  If you say yes here you get support for the Sensiron SHTC1 and SHTW1
+	  humidity and temperature sensors.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called shtc1.
+
 config SENSORS_S3C
 	tristate "Samsung built-in ADC"
 	depends on S3C_ADC
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 11798ad..3dc0f02 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -126,6 +126,7 @@
 obj-$(CONFIG_SENSORS_SCH5636)	+= sch5636.o
 obj-$(CONFIG_SENSORS_SHT15)	+= sht15.o
 obj-$(CONFIG_SENSORS_SHT21)	+= sht21.o
+obj-$(CONFIG_SENSORS_SHTC1)	+= shtc1.o
 obj-$(CONFIG_SENSORS_SIS5595)	+= sis5595.o
 obj-$(CONFIG_SENSORS_SMM665)	+= smm665.o
 obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o
diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index 6edce42..2ae8a30 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -45,30 +45,6 @@
 
 static const unsigned short normal_i2c[] = { 0x37, 0x4e, I2C_CLIENT_END };
 
-static int atxp1_probe(struct i2c_client *client,
-		       const struct i2c_device_id *id);
-static int atxp1_remove(struct i2c_client *client);
-static struct atxp1_data *atxp1_update_device(struct device *dev);
-static int atxp1_detect(struct i2c_client *client, struct i2c_board_info *info);
-
-static const struct i2c_device_id atxp1_id[] = {
-	{ "atxp1", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, atxp1_id);
-
-static struct i2c_driver atxp1_driver = {
-	.class		= I2C_CLASS_HWMON,
-	.driver = {
-		.name	= "atxp1",
-	},
-	.probe		= atxp1_probe,
-	.remove		= atxp1_remove,
-	.id_table	= atxp1_id,
-	.detect		= atxp1_detect,
-	.address_list	= normal_i2c,
-};
-
 struct atxp1_data {
 	struct device *hwmon_dev;
 	struct mutex update_lock;
@@ -386,4 +362,22 @@
 	return 0;
 };
 
+static const struct i2c_device_id atxp1_id[] = {
+	{ "atxp1", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, atxp1_id);
+
+static struct i2c_driver atxp1_driver = {
+	.class		= I2C_CLASS_HWMON,
+	.driver = {
+		.name	= "atxp1",
+	},
+	.probe		= atxp1_probe,
+	.remove		= atxp1_remove,
+	.id_table	= atxp1_id,
+	.detect		= atxp1_detect,
+	.address_list	= normal_i2c,
+};
+
 module_i2c_driver(atxp1_driver);
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 93d26e8..bfd3f3e 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -148,7 +148,8 @@
 
 	switch (reg) {
 	case INA2XX_SHUNT_VOLTAGE:
-		val = DIV_ROUND_CLOSEST(data->regs[reg],
+		/* signed register */
+		val = DIV_ROUND_CLOSEST((s16)data->regs[reg],
 					data->config->shunt_div);
 		break;
 	case INA2XX_BUS_VOLTAGE:
@@ -160,8 +161,8 @@
 		val = data->regs[reg] * data->config->power_lsb;
 		break;
 	case INA2XX_CURRENT:
-		/* LSB=1mA (selected). Is in mA */
-		val = data->regs[reg];
+		/* signed register, LSB=1mA (selected), in mA */
+		val = (s16)data->regs[reg];
 		break;
 	default:
 		/* programmer goofed */
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index bed4af35..b0129a5 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -5,7 +5,7 @@
  * Copyright (c) 2002, 2003  Philip Pokorny <ppokorny@penguincomputing.com>
  * Copyright (c) 2003        Margit Schubert-While <margitsw@t-online.de>
  * Copyright (c) 2004        Justin Thiessen <jthiessen@penguincomputing.com>
- * Copyright (C) 2007--2009  Jean Delvare <jdelvare@suse.de>
+ * Copyright (C) 2007--2014  Jean Delvare <jdelvare@suse.de>
  *
  * Chip details at	      <http://www.national.com/ds/LM/LM85.pdf>
  *
@@ -39,7 +39,7 @@
 static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, I2C_CLIENT_END };
 
 enum chips {
-	any_chip, lm85b, lm85c,
+	lm85,
 	adm1027, adt7463, adt7468,
 	emc6d100, emc6d102, emc6d103, emc6d103s
 };
@@ -75,9 +75,6 @@
 #define LM85_COMPANY_NATIONAL		0x01
 #define LM85_COMPANY_ANALOG_DEV		0x41
 #define LM85_COMPANY_SMSC		0x5c
-#define LM85_VERSTEP_VMASK              0xf0
-#define LM85_VERSTEP_GENERIC		0x60
-#define LM85_VERSTEP_GENERIC2		0x70
 #define LM85_VERSTEP_LM85C		0x60
 #define LM85_VERSTEP_LM85B		0x62
 #define LM85_VERSTEP_LM96000_1		0x68
@@ -351,9 +348,9 @@
 	{ "adm1027", adm1027 },
 	{ "adt7463", adt7463 },
 	{ "adt7468", adt7468 },
-	{ "lm85", any_chip },
-	{ "lm85b", lm85b },
-	{ "lm85c", lm85c },
+	{ "lm85", lm85 },
+	{ "lm85b", lm85 },
+	{ "lm85c", lm85 },
 	{ "emc6d100", emc6d100 },
 	{ "emc6d101", emc6d100 },
 	{ "emc6d102", emc6d102 },
@@ -1281,7 +1278,7 @@
 {
 	struct i2c_adapter *adapter = client->adapter;
 	int address = client->addr;
-	const char *type_name;
+	const char *type_name = NULL;
 	int company, verstep;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
@@ -1297,16 +1294,6 @@
 		"Detecting device at 0x%02x with COMPANY: 0x%02x and VERSTEP: 0x%02x\n",
 		address, company, verstep);
 
-	/* All supported chips have the version in common */
-	if ((verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC &&
-	    (verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC2) {
-		dev_dbg(&adapter->dev,
-			"Autodetection failed: unsupported version\n");
-		return -ENODEV;
-	}
-	type_name = "lm85";
-
-	/* Now, refine the detection */
 	if (company == LM85_COMPANY_NATIONAL) {
 		switch (verstep) {
 		case LM85_VERSTEP_LM85C:
@@ -1323,6 +1310,7 @@
 					"Found Winbond WPCD377I, ignoring\n");
 				return -ENODEV;
 			}
+			type_name = "lm85";
 			break;
 		}
 	} else if (company == LM85_COMPANY_ANALOG_DEV) {
@@ -1357,12 +1345,11 @@
 			type_name = "emc6d103s";
 			break;
 		}
-	} else {
-		dev_dbg(&adapter->dev,
-			"Autodetection failed: unknown vendor\n");
-		return -ENODEV;
 	}
 
+	if (!type_name)
+		return -ENODEV;
+
 	strlcpy(info->type, type_name, I2C_NAME_SIZE);
 
 	return 0;
diff --git a/drivers/hwmon/ltc4151.c b/drivers/hwmon/ltc4151.c
index af81be1..c86a184 100644
--- a/drivers/hwmon/ltc4151.c
+++ b/drivers/hwmon/ltc4151.c
@@ -47,7 +47,7 @@
 #define LTC4151_ADIN_L	0x05
 
 struct ltc4151_data {
-	struct device *hwmon_dev;
+	struct i2c_client *client;
 
 	struct mutex update_lock;
 	bool valid;
@@ -59,8 +59,8 @@
 
 static struct ltc4151_data *ltc4151_update_device(struct device *dev)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ltc4151_data *data = i2c_get_clientdata(client);
+	struct ltc4151_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
 	struct ltc4151_data *ret = data;
 
 	mutex_lock(&data->update_lock);
@@ -159,7 +159,7 @@
  * Finally, construct an array of pointers to members of the above objects,
  * as required for sysfs_create_group()
  */
-static struct attribute *ltc4151_attributes[] = {
+static struct attribute *ltc4151_attrs[] = {
 	&sensor_dev_attr_in1_input.dev_attr.attr,
 	&sensor_dev_attr_in2_input.dev_attr.attr,
 
@@ -167,54 +167,30 @@
 
 	NULL,
 };
-
-static const struct attribute_group ltc4151_group = {
-	.attrs = ltc4151_attributes,
-};
+ATTRIBUTE_GROUPS(ltc4151);
 
 static int ltc4151_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
 	struct i2c_adapter *adapter = client->adapter;
+	struct device *dev = &client->dev;
 	struct ltc4151_data *data;
-	int ret;
+	struct device *hwmon_dev;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
 		return -ENODEV;
 
-	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	i2c_set_clientdata(client, data);
+	data->client = client;
 	mutex_init(&data->update_lock);
 
-	/* Register sysfs hooks */
-	ret = sysfs_create_group(&client->dev.kobj, &ltc4151_group);
-	if (ret)
-		return ret;
-
-	data->hwmon_dev = hwmon_device_register(&client->dev);
-	if (IS_ERR(data->hwmon_dev)) {
-		ret = PTR_ERR(data->hwmon_dev);
-		goto out_hwmon_device_register;
-	}
-
-	return 0;
-
-out_hwmon_device_register:
-	sysfs_remove_group(&client->dev.kobj, &ltc4151_group);
-	return ret;
-}
-
-static int ltc4151_remove(struct i2c_client *client)
-{
-	struct ltc4151_data *data = i2c_get_clientdata(client);
-
-	hwmon_device_unregister(data->hwmon_dev);
-	sysfs_remove_group(&client->dev.kobj, &ltc4151_group);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
+							   data,
+							   ltc4151_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct i2c_device_id ltc4151_id[] = {
@@ -229,7 +205,6 @@
 		.name	= "ltc4151",
 	},
 	.probe		= ltc4151_probe,
-	.remove		= ltc4151_remove,
 	.id_table	= ltc4151_id,
 };
 
diff --git a/drivers/hwmon/shtc1.c b/drivers/hwmon/shtc1.c
new file mode 100644
index 0000000..decd7df
--- /dev/null
+++ b/drivers/hwmon/shtc1.c
@@ -0,0 +1,251 @@
+/* Sensirion SHTC1 humidity and temperature sensor driver
+ *
+ * Copyright (C) 2014 Sensirion AG, Switzerland
+ * Author: Johannes Winkelmann <johannes.winkelmann@sensirion.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/platform_data/shtc1.h>
+
+/* commands (high precision mode) */
+static const unsigned char shtc1_cmd_measure_blocking_hpm[]    = { 0x7C, 0xA2 };
+static const unsigned char shtc1_cmd_measure_nonblocking_hpm[] = { 0x78, 0x66 };
+
+/* commands (low precision mode) */
+static const unsigned char shtc1_cmd_measure_blocking_lpm[]    = { 0x64, 0x58 };
+static const unsigned char shtc1_cmd_measure_nonblocking_lpm[] = { 0x60, 0x9c };
+
+/* command for reading the ID register */
+static const unsigned char shtc1_cmd_read_id_reg[]	       = { 0xef, 0xc8 };
+
+/* constants for reading the ID register */
+#define SHTC1_ID	  0x07
+#define SHTC1_ID_REG_MASK 0x1f
+
+/* delays for non-blocking i2c commands, both in us */
+#define SHTC1_NONBLOCKING_WAIT_TIME_HPM  14400
+#define SHTC1_NONBLOCKING_WAIT_TIME_LPM   1000
+
+#define SHTC1_CMD_LENGTH      2
+#define SHTC1_RESPONSE_LENGTH 6
+
+struct shtc1_data {
+	struct i2c_client *client;
+	struct mutex update_lock;
+	bool valid;
+	unsigned long last_updated; /* in jiffies */
+
+	const unsigned char *command;
+	unsigned int nonblocking_wait_time; /* in us */
+
+	struct shtc1_platform_data setup;
+
+	int temperature; /* 1000 * temperature in dgr C */
+	int humidity; /* 1000 * relative humidity in %RH */
+};
+
+static int shtc1_update_values(struct i2c_client *client,
+			       struct shtc1_data *data,
+			       char *buf, int bufsize)
+{
+	int ret = i2c_master_send(client, data->command, SHTC1_CMD_LENGTH);
+	if (ret != SHTC1_CMD_LENGTH) {
+		dev_err(&client->dev, "failed to send command: %d\n", ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	/*
+	 * In blocking mode (clock stretching mode) the I2C bus
+	 * is blocked for other traffic, thus the call to i2c_master_recv()
+	 * will wait until the data is ready. For non blocking mode, we
+	 * have to wait ourselves.
+	 */
+	if (!data->setup.blocking_io)
+		usleep_range(data->nonblocking_wait_time,
+			     data->nonblocking_wait_time + 1000);
+
+	ret = i2c_master_recv(client, buf, bufsize);
+	if (ret != bufsize) {
+		dev_err(&client->dev, "failed to read values: %d\n", ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	return 0;
+}
+
+/* sysfs attributes */
+static struct shtc1_data *shtc1_update_client(struct device *dev)
+{
+	struct shtc1_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	unsigned char buf[SHTC1_RESPONSE_LENGTH];
+	int val;
+	int ret = 0;
+
+	mutex_lock(&data->update_lock);
+
+	if (time_after(jiffies, data->last_updated + HZ / 10) || !data->valid) {
+		ret = shtc1_update_values(client, data, buf, sizeof(buf));
+		if (ret)
+			goto out;
+
+		/*
+		 * From datasheet:
+		 * T = -45 + 175 * ST / 2^16
+		 * RH = 100 * SRH / 2^16
+		 *
+		 * Adapted for integer fixed point (3 digit) arithmetic.
+		 */
+		val = be16_to_cpup((__be16 *)buf);
+		data->temperature = ((21875 * val) >> 13) - 45000;
+		val = be16_to_cpup((__be16 *)(buf + 3));
+		data->humidity = ((12500 * val) >> 13);
+
+		data->last_updated = jiffies;
+		data->valid = true;
+	}
+
+out:
+	mutex_unlock(&data->update_lock);
+
+	return ret == 0 ? data : ERR_PTR(ret);
+}
+
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct shtc1_data *data = shtc1_update_client(dev);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	return sprintf(buf, "%d\n", data->temperature);
+}
+
+static ssize_t humidity1_input_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct shtc1_data *data = shtc1_update_client(dev);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	return sprintf(buf, "%d\n", data->humidity);
+}
+
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RO(humidity1_input);
+
+static struct attribute *shtc1_attrs[] = {
+	&dev_attr_temp1_input.attr,
+	&dev_attr_humidity1_input.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(shtc1);
+
+static void shtc1_select_command(struct shtc1_data *data)
+{
+	if (data->setup.high_precision) {
+		data->command = data->setup.blocking_io ?
+				shtc1_cmd_measure_blocking_hpm :
+				shtc1_cmd_measure_nonblocking_hpm;
+		data->nonblocking_wait_time = SHTC1_NONBLOCKING_WAIT_TIME_HPM;
+
+	} else {
+		data->command = data->setup.blocking_io ?
+				shtc1_cmd_measure_blocking_lpm :
+				shtc1_cmd_measure_nonblocking_lpm;
+		data->nonblocking_wait_time = SHTC1_NONBLOCKING_WAIT_TIME_LPM;
+	}
+}
+
+static int shtc1_probe(struct i2c_client *client,
+		       const struct i2c_device_id *id)
+{
+	int ret;
+	char id_reg[2];
+	struct shtc1_data *data;
+	struct device *hwmon_dev;
+	struct i2c_adapter *adap = client->adapter;
+	struct device *dev = &client->dev;
+
+	if (!i2c_check_functionality(adap, I2C_FUNC_I2C)) {
+		dev_err(dev, "plain i2c transactions not supported\n");
+		return -ENODEV;
+	}
+
+	ret = i2c_master_send(client, shtc1_cmd_read_id_reg, SHTC1_CMD_LENGTH);
+	if (ret != SHTC1_CMD_LENGTH) {
+		dev_err(dev, "could not send read_id_reg command: %d\n", ret);
+		return ret < 0 ? ret : -ENODEV;
+	}
+	ret = i2c_master_recv(client, id_reg, sizeof(id_reg));
+	if (ret != sizeof(id_reg)) {
+		dev_err(dev, "could not read ID register: %d\n", ret);
+		return -ENODEV;
+	}
+	if ((id_reg[1] & SHTC1_ID_REG_MASK) != SHTC1_ID) {
+		dev_err(dev, "ID register doesn't match\n");
+		return -ENODEV;
+	}
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->setup.blocking_io = false;
+	data->setup.high_precision = true;
+	data->client = client;
+
+	if (client->dev.platform_data)
+		data->setup = *(struct shtc1_platform_data *)dev->platform_data;
+	shtc1_select_command(data);
+	mutex_init(&data->update_lock);
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev,
+							   client->name,
+							   data,
+							   shtc1_groups);
+	if (IS_ERR(hwmon_dev))
+		dev_dbg(dev, "unable to register hwmon device\n");
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+/* device ID table */
+static const struct i2c_device_id shtc1_id[] = {
+	{ "shtc1", 0 },
+	{ "shtw1", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, shtc1_id);
+
+static struct i2c_driver shtc1_i2c_driver = {
+	.driver.name  = "shtc1",
+	.probe        = shtc1_probe,
+	.id_table     = shtc1_id,
+};
+
+module_i2c_driver(shtc1_i2c_driver);
+
+MODULE_AUTHOR("Johannes Winkelmann <johannes.winkelmann@sensirion.com>");
+MODULE_DESCRIPTION("Sensirion SHTC1 humidity and temperature sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/vexpress.c b/drivers/hwmon/vexpress.c
index 611f34c..c536190 100644
--- a/drivers/hwmon/vexpress.c
+++ b/drivers/hwmon/vexpress.c
@@ -27,17 +27,8 @@
 struct vexpress_hwmon_data {
 	struct device *hwmon_dev;
 	struct regmap *reg;
-	const char *name;
 };
 
-static ssize_t vexpress_hwmon_name_show(struct device *dev,
-		struct device_attribute *dev_attr, char *buffer)
-{
-	struct vexpress_hwmon_data *data = dev_get_drvdata(dev);
-
-	return sprintf(buffer, "%s\n", data->name);
-}
-
 static ssize_t vexpress_hwmon_label_show(struct device *dev,
 		struct device_attribute *dev_attr, char *buffer)
 {
@@ -95,16 +86,6 @@
 	return attr->mode;
 }
 
-static DEVICE_ATTR(name, S_IRUGO, vexpress_hwmon_name_show, NULL);
-
-#define VEXPRESS_HWMON_ATTRS(_name, _label_attr, _input_attr)	\
-struct attribute *vexpress_hwmon_attrs_##_name[] = {		\
-	&dev_attr_name.attr,					\
-	&dev_attr_##_label_attr.attr,				\
-	&sensor_dev_attr_##_input_attr.dev_attr.attr,		\
-	NULL							\
-}
-
 struct vexpress_hwmon_type {
 	const char *name;
 	const struct attribute_group **attr_groups;
@@ -114,7 +95,11 @@
 static DEVICE_ATTR(in1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(in1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1000);
-static VEXPRESS_HWMON_ATTRS(volt, in1_label, in1_input);
+static struct attribute *vexpress_hwmon_attrs_volt[] = {
+	&dev_attr_in1_label.attr,
+	&sensor_dev_attr_in1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_volt = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_volt,
@@ -131,7 +116,11 @@
 static DEVICE_ATTR(curr1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1000);
-static VEXPRESS_HWMON_ATTRS(amp, curr1_label, curr1_input);
+static struct attribute *vexpress_hwmon_attrs_amp[] = {
+	&dev_attr_curr1_label.attr,
+	&sensor_dev_attr_curr1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_amp = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_amp,
@@ -147,7 +136,11 @@
 static DEVICE_ATTR(temp1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1000);
-static VEXPRESS_HWMON_ATTRS(temp, temp1_label, temp1_input);
+static struct attribute *vexpress_hwmon_attrs_temp[] = {
+	&dev_attr_temp1_label.attr,
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_temp = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_temp,
@@ -163,7 +156,11 @@
 static DEVICE_ATTR(power1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(power1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1);
-static VEXPRESS_HWMON_ATTRS(power, power1_label, power1_input);
+static struct attribute *vexpress_hwmon_attrs_power[] = {
+	&dev_attr_power1_label.attr,
+	&sensor_dev_attr_power1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_power = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_power,
@@ -179,7 +176,11 @@
 static DEVICE_ATTR(energy1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(energy1_input, S_IRUGO, vexpress_hwmon_u64_show,
 		NULL, 1);
-static VEXPRESS_HWMON_ATTRS(energy, energy1_label, energy1_input);
+static struct attribute *vexpress_hwmon_attrs_energy[] = {
+	&dev_attr_energy1_label.attr,
+	&sensor_dev_attr_energy1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_energy = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_energy,
@@ -218,7 +219,6 @@
 
 static int vexpress_hwmon_probe(struct platform_device *pdev)
 {
-	int err;
 	const struct of_device_id *match;
 	struct vexpress_hwmon_data *data;
 	const struct vexpress_hwmon_type *type;
@@ -232,45 +232,19 @@
 	if (!match)
 		return -ENODEV;
 	type = match->data;
-	data->name = type->name;
 
 	data->reg = devm_regmap_init_vexpress_config(&pdev->dev);
 	if (IS_ERR(data->reg))
 		return PTR_ERR(data->reg);
 
-	err = sysfs_create_groups(&pdev->dev.kobj, type->attr_groups);
-	if (err)
-		goto error;
+	data->hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev,
+			type->name, data, type->attr_groups);
 
-	data->hwmon_dev = hwmon_device_register(&pdev->dev);
-	if (IS_ERR(data->hwmon_dev)) {
-		err = PTR_ERR(data->hwmon_dev);
-		goto error;
-	}
-
-	return 0;
-
-error:
-	sysfs_remove_group(&pdev->dev.kobj, match->data);
-	return err;
-}
-
-static int vexpress_hwmon_remove(struct platform_device *pdev)
-{
-	struct vexpress_hwmon_data *data = platform_get_drvdata(pdev);
-	const struct of_device_id *match;
-
-	hwmon_device_unregister(data->hwmon_dev);
-
-	match = of_match_device(vexpress_hwmon_of_match, &pdev->dev);
-	sysfs_remove_group(&pdev->dev.kobj, match->data);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(data->hwmon_dev);
 }
 
 static struct platform_driver vexpress_hwmon_driver = {
 	.probe = vexpress_hwmon_probe,
-	.remove = vexpress_hwmon_remove,
 	.driver	= {
 		.name = DRVNAME,
 		.owner = THIS_MODULE,
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 620d100..9f7d585 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -676,6 +676,16 @@
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-riic.
 
+config I2C_RK3X
+	tristate "Rockchip RK3xxx I2C adapter"
+	depends on OF
+	help
+	  Say Y here to include support for the I2C adapter in Rockchip RK3xxx
+	  SoCs.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called i2c-rk3x.
+
 config HAVE_S3C2410_I2C
 	bool
 	help
@@ -764,6 +774,19 @@
 	  This driver can also be built as a module. If so, the module
 	  will be called i2c-stu300.
 
+config I2C_SUN6I_P2WI
+	tristate "Allwinner sun6i internal P2WI controller"
+	depends on RESET_CONTROLLER
+	depends on MACH_SUN6I || COMPILE_TEST
+	help
+	  If you say yes to this option, support will be included for the
+	  P2WI (Push/Pull 2 Wire Interface) controller embedded in some sunxi
+	  SOCs.
+	  The P2WI looks like an SMBus controller (which supports only byte
+	  accesses), except that it only supports one slave device.
+	  This interface is used to connect to specific PMIC devices (like the
+	  AXP221).
+
 config I2C_TEGRA
 	tristate "NVIDIA Tegra internal I2C controller"
 	depends on ARCH_TEGRA
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 298692c..dd9a7f8 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -66,6 +66,7 @@
 obj-$(CONFIG_I2C_PXA_PCI)	+= i2c-pxa-pci.o
 obj-$(CONFIG_I2C_QUP)		+= i2c-qup.o
 obj-$(CONFIG_I2C_RIIC)		+= i2c-riic.o
+obj-$(CONFIG_I2C_RK3X)		+= i2c-rk3x.o
 obj-$(CONFIG_I2C_S3C2410)	+= i2c-s3c2410.o
 obj-$(CONFIG_I2C_S6000)		+= i2c-s6000.o
 obj-$(CONFIG_I2C_SH7760)	+= i2c-sh7760.o
@@ -74,6 +75,7 @@
 obj-$(CONFIG_I2C_SIRF)		+= i2c-sirf.o
 obj-$(CONFIG_I2C_ST)		+= i2c-st.o
 obj-$(CONFIG_I2C_STU300)	+= i2c-stu300.o
+obj-$(CONFIG_I2C_SUN6I_P2WI)	+= i2c-sun6i-p2wi.o
 obj-$(CONFIG_I2C_TEGRA)		+= i2c-tegra.o
 obj-$(CONFIG_I2C_VERSATILE)	+= i2c-versatile.o
 obj-$(CONFIG_I2C_WMT)		+= i2c-wmt.o
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
new file mode 100644
index 0000000..a979150
--- /dev/null
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -0,0 +1,763 @@
+/*
+ * Driver for I2C adapter in Rockchip RK3xxx SoC
+ *
+ * Max Schwarz <max.schwarz@online.de>
+ * based on the patches by Rockchip Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/wait.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+
+
+/* Register Map */
+#define REG_CON        0x00 /* control register */
+#define REG_CLKDIV     0x04 /* clock divisor register */
+#define REG_MRXADDR    0x08 /* slave address for REGISTER_TX */
+#define REG_MRXRADDR   0x0c /* slave register address for REGISTER_TX */
+#define REG_MTXCNT     0x10 /* number of bytes to be transmitted */
+#define REG_MRXCNT     0x14 /* number of bytes to be received */
+#define REG_IEN        0x18 /* interrupt enable */
+#define REG_IPD        0x1c /* interrupt pending */
+#define REG_FCNT       0x20 /* finished count */
+
+/* Data buffer offsets */
+#define TXBUFFER_BASE 0x100
+#define RXBUFFER_BASE 0x200
+
+/* REG_CON bits */
+#define REG_CON_EN        BIT(0)
+enum {
+	REG_CON_MOD_TX = 0,      /* transmit data */
+	REG_CON_MOD_REGISTER_TX, /* select register and restart */
+	REG_CON_MOD_RX,          /* receive data */
+	REG_CON_MOD_REGISTER_RX, /* broken: transmits read addr AND writes
+				  * register addr */
+};
+#define REG_CON_MOD(mod)  ((mod) << 1)
+#define REG_CON_MOD_MASK  (BIT(1) | BIT(2))
+#define REG_CON_START     BIT(3)
+#define REG_CON_STOP      BIT(4)
+#define REG_CON_LASTACK   BIT(5) /* 1: send NACK after last received byte */
+#define REG_CON_ACTACK    BIT(6) /* 1: stop if NACK is received */
+
+/* REG_MRXADDR bits */
+#define REG_MRXADDR_VALID(x) BIT(24 + (x)) /* [x*8+7:x*8] of MRX[R]ADDR valid */
+
+/* REG_IEN/REG_IPD bits */
+#define REG_INT_BTF       BIT(0) /* a byte was transmitted */
+#define REG_INT_BRF       BIT(1) /* a byte was received */
+#define REG_INT_MBTF      BIT(2) /* master data transmit finished */
+#define REG_INT_MBRF      BIT(3) /* master data receive finished */
+#define REG_INT_START     BIT(4) /* START condition generated */
+#define REG_INT_STOP      BIT(5) /* STOP condition generated */
+#define REG_INT_NAKRCV    BIT(6) /* NACK received */
+#define REG_INT_ALL       0x7f
+
+/* Constants */
+#define WAIT_TIMEOUT      200 /* ms */
+#define DEFAULT_SCL_RATE  (100 * 1000) /* Hz */
+
+enum rk3x_i2c_state {
+	STATE_IDLE,
+	STATE_START,
+	STATE_READ,
+	STATE_WRITE,
+	STATE_STOP
+};
+
+/**
+ * @grf_offset: offset inside the grf regmap for setting the i2c type
+ */
+struct rk3x_i2c_soc_data {
+	int grf_offset;
+};
+
+struct rk3x_i2c {
+	struct i2c_adapter adap;
+	struct device *dev;
+	struct rk3x_i2c_soc_data *soc_data;
+
+	/* Hardware resources */
+	void __iomem *regs;
+	struct clk *clk;
+
+	/* Settings */
+	unsigned int scl_frequency;
+
+	/* Synchronization & notification */
+	spinlock_t lock;
+	wait_queue_head_t wait;
+	bool busy;
+
+	/* Current message */
+	struct i2c_msg *msg;
+	u8 addr;
+	unsigned int mode;
+	bool is_last_msg;
+
+	/* I2C state machine */
+	enum rk3x_i2c_state state;
+	unsigned int processed; /* sent/received bytes */
+	int error;
+};
+
+static inline void i2c_writel(struct rk3x_i2c *i2c, u32 value,
+			      unsigned int offset)
+{
+	writel(value, i2c->regs + offset);
+}
+
+static inline u32 i2c_readl(struct rk3x_i2c *i2c, unsigned int offset)
+{
+	return readl(i2c->regs + offset);
+}
+
+/* Reset all interrupt pending bits */
+static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c)
+{
+	i2c_writel(i2c, REG_INT_ALL, REG_IPD);
+}
+
+/**
+ * Generate a START condition, which triggers a REG_INT_START interrupt.
+ */
+static void rk3x_i2c_start(struct rk3x_i2c *i2c)
+{
+	u32 val;
+
+	rk3x_i2c_clean_ipd(i2c);
+	i2c_writel(i2c, REG_INT_START, REG_IEN);
+
+	/* enable adapter with correct mode, send START condition */
+	val = REG_CON_EN | REG_CON_MOD(i2c->mode) | REG_CON_START;
+
+	/* if we want to react to NACK, set ACTACK bit */
+	if (!(i2c->msg->flags & I2C_M_IGNORE_NAK))
+		val |= REG_CON_ACTACK;
+
+	i2c_writel(i2c, val, REG_CON);
+}
+
+/**
+ * Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
+ *
+ * @error: Error code to return in rk3x_i2c_xfer
+ */
+static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error)
+{
+	unsigned int ctrl;
+
+	i2c->processed = 0;
+	i2c->msg = NULL;
+	i2c->error = error;
+
+	if (i2c->is_last_msg) {
+		/* Enable stop interrupt */
+		i2c_writel(i2c, REG_INT_STOP, REG_IEN);
+
+		i2c->state = STATE_STOP;
+
+		ctrl = i2c_readl(i2c, REG_CON);
+		ctrl |= REG_CON_STOP;
+		i2c_writel(i2c, ctrl, REG_CON);
+	} else {
+		/* Signal rk3x_i2c_xfer to start the next message. */
+		i2c->busy = false;
+		i2c->state = STATE_IDLE;
+
+		/*
+		 * The HW is actually not capable of REPEATED START. But we can
+		 * get the intended effect by resetting its internal state
+		 * and issuing an ordinary START.
+		 */
+		i2c_writel(i2c, 0, REG_CON);
+
+		/* signal that we are finished with the current msg */
+		wake_up(&i2c->wait);
+	}
+}
+
+/**
+ * Setup a read according to i2c->msg
+ */
+static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c)
+{
+	unsigned int len = i2c->msg->len - i2c->processed;
+	u32 con;
+
+	con = i2c_readl(i2c, REG_CON);
+
+	/*
+	 * The hw can read up to 32 bytes at a time. If we need more than one
+	 * chunk, send an ACK after the last byte of the current chunk.
+	 */
+	if (unlikely(len > 32)) {
+		len = 32;
+		con &= ~REG_CON_LASTACK;
+	} else {
+		con |= REG_CON_LASTACK;
+	}
+
+	/* make sure we are in plain RX mode if we read a second chunk */
+	if (i2c->processed != 0) {
+		con &= ~REG_CON_MOD_MASK;
+		con |= REG_CON_MOD(REG_CON_MOD_RX);
+	}
+
+	i2c_writel(i2c, con, REG_CON);
+	i2c_writel(i2c, len, REG_MRXCNT);
+}
+
+/**
+ * Fill the transmit buffer with data from i2c->msg
+ */
+static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c)
+{
+	unsigned int i, j;
+	u32 cnt = 0;
+	u32 val;
+	u8 byte;
+
+	for (i = 0; i < 8; ++i) {
+		val = 0;
+		for (j = 0; j < 4; ++j) {
+			if (i2c->processed == i2c->msg->len)
+				break;
+
+			if (i2c->processed == 0 && cnt == 0)
+				byte = (i2c->addr & 0x7f) << 1;
+			else
+				byte = i2c->msg->buf[i2c->processed++];
+
+			val |= byte << (j * 8);
+			cnt++;
+		}
+
+		i2c_writel(i2c, val, TXBUFFER_BASE + 4 * i);
+
+		if (i2c->processed == i2c->msg->len)
+			break;
+	}
+
+	i2c_writel(i2c, cnt, REG_MTXCNT);
+}
+
+
+/* IRQ handlers for individual states */
+
+static void rk3x_i2c_handle_start(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	if (!(ipd & REG_INT_START)) {
+		rk3x_i2c_stop(i2c, -EIO);
+		dev_warn(i2c->dev, "unexpected irq in START: 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		return;
+	}
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_START, REG_IPD);
+
+	/* disable start bit */
+	i2c_writel(i2c, i2c_readl(i2c, REG_CON) & ~REG_CON_START, REG_CON);
+
+	/* enable appropriate interrupts and transition */
+	if (i2c->mode == REG_CON_MOD_TX) {
+		i2c_writel(i2c, REG_INT_MBTF | REG_INT_NAKRCV, REG_IEN);
+		i2c->state = STATE_WRITE;
+		rk3x_i2c_fill_transmit_buf(i2c);
+	} else {
+		/* in any other case, we are going to be reading. */
+		i2c_writel(i2c, REG_INT_MBRF | REG_INT_NAKRCV, REG_IEN);
+		i2c->state = STATE_READ;
+		rk3x_i2c_prepare_read(i2c);
+	}
+}
+
+static void rk3x_i2c_handle_write(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	if (!(ipd & REG_INT_MBTF)) {
+		rk3x_i2c_stop(i2c, -EIO);
+		dev_err(i2c->dev, "unexpected irq in WRITE: 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		return;
+	}
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_MBTF, REG_IPD);
+
+	/* are we finished? */
+	if (i2c->processed == i2c->msg->len)
+		rk3x_i2c_stop(i2c, i2c->error);
+	else
+		rk3x_i2c_fill_transmit_buf(i2c);
+}
+
+static void rk3x_i2c_handle_read(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	unsigned int i;
+	unsigned int len = i2c->msg->len - i2c->processed;
+	u32 uninitialized_var(val);
+	u8 byte;
+
+	/* we only care for MBRF here. */
+	if (!(ipd & REG_INT_MBRF))
+		return;
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_MBRF, REG_IPD);
+
+	/* read the data from receive buffer */
+	for (i = 0; i < len; ++i) {
+		if (i % 4 == 0)
+			val = i2c_readl(i2c, RXBUFFER_BASE + (i / 4) * 4);
+
+		byte = (val >> ((i % 4) * 8)) & 0xff;
+		i2c->msg->buf[i2c->processed++] = byte;
+	}
+
+	/* are we finished? */
+	if (i2c->processed == i2c->msg->len)
+		rk3x_i2c_stop(i2c, i2c->error);
+	else
+		rk3x_i2c_prepare_read(i2c);
+}
+
+static void rk3x_i2c_handle_stop(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	unsigned int con;
+
+	if (!(ipd & REG_INT_STOP)) {
+		rk3x_i2c_stop(i2c, -EIO);
+		dev_err(i2c->dev, "unexpected irq in STOP: 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		return;
+	}
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_STOP, REG_IPD);
+
+	/* disable STOP bit */
+	con = i2c_readl(i2c, REG_CON);
+	con &= ~REG_CON_STOP;
+	i2c_writel(i2c, con, REG_CON);
+
+	i2c->busy = false;
+	i2c->state = STATE_IDLE;
+
+	/* signal rk3x_i2c_xfer that we are finished */
+	wake_up(&i2c->wait);
+}
+
+static irqreturn_t rk3x_i2c_irq(int irqno, void *dev_id)
+{
+	struct rk3x_i2c *i2c = dev_id;
+	unsigned int ipd;
+
+	spin_lock(&i2c->lock);
+
+	ipd = i2c_readl(i2c, REG_IPD);
+	if (i2c->state == STATE_IDLE) {
+		dev_warn(i2c->dev, "irq in STATE_IDLE, ipd = 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		goto out;
+	}
+
+	dev_dbg(i2c->dev, "IRQ: state %d, ipd: %x\n", i2c->state, ipd);
+
+	/* Clean interrupt bits we don't care about */
+	ipd &= ~(REG_INT_BRF | REG_INT_BTF);
+
+	if (ipd & REG_INT_NAKRCV) {
+		/*
+		 * We got a NACK in the last operation. Depending on whether
+		 * IGNORE_NAK is set, we have to stop the operation and report
+		 * an error.
+		 */
+		i2c_writel(i2c, REG_INT_NAKRCV, REG_IPD);
+
+		ipd &= ~REG_INT_NAKRCV;
+
+		if (!(i2c->msg->flags & I2C_M_IGNORE_NAK))
+			rk3x_i2c_stop(i2c, -ENXIO);
+	}
+
+	/* is there anything left to handle? */
+	if (unlikely(ipd == 0))
+		goto out;
+
+	switch (i2c->state) {
+	case STATE_START:
+		rk3x_i2c_handle_start(i2c, ipd);
+		break;
+	case STATE_WRITE:
+		rk3x_i2c_handle_write(i2c, ipd);
+		break;
+	case STATE_READ:
+		rk3x_i2c_handle_read(i2c, ipd);
+		break;
+	case STATE_STOP:
+		rk3x_i2c_handle_stop(i2c, ipd);
+		break;
+	case STATE_IDLE:
+		break;
+	}
+
+out:
+	spin_unlock(&i2c->lock);
+	return IRQ_HANDLED;
+}
+
+static void rk3x_i2c_set_scl_rate(struct rk3x_i2c *i2c, unsigned long scl_rate)
+{
+	unsigned long i2c_rate = clk_get_rate(i2c->clk);
+	unsigned int div;
+
+	/* SCL rate = (clk rate) / (8 * DIV) */
+	div = DIV_ROUND_UP(i2c_rate, scl_rate * 8);
+
+	/* The lower and upper half of the CLKDIV reg describe the length of
+	 * SCL low & high periods. */
+	div = DIV_ROUND_UP(div, 2);
+
+	i2c_writel(i2c, (div << 16) | (div & 0xffff), REG_CLKDIV);
+}
+
+/**
+ * Setup I2C registers for an I2C operation specified by msgs, num.
+ *
+ * Must be called with i2c->lock held.
+ *
+ * @msgs: I2C msgs to process
+ * @num: Number of msgs
+ *
+ * returns: Number of I2C msgs processed or negative in case of error
+ */
+static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num)
+{
+	u32 addr = (msgs[0].addr & 0x7f) << 1;
+	int ret = 0;
+
+	/*
+	 * The I2C adapter can issue a small (len < 4) write packet before
+	 * reading. This speeds up SMBus-style register reads.
+	 * The MRXADDR/MRXRADDR hold the slave address and the slave register
+	 * address in this case.
+	 */
+
+	if (num >= 2 && msgs[0].len < 4 &&
+	    !(msgs[0].flags & I2C_M_RD) && (msgs[1].flags & I2C_M_RD)) {
+		u32 reg_addr = 0;
+		int i;
+
+		dev_dbg(i2c->dev, "Combined write/read from addr 0x%x\n",
+			addr >> 1);
+
+		/* Fill MRXRADDR with the register address(es) */
+		for (i = 0; i < msgs[0].len; ++i) {
+			reg_addr |= msgs[0].buf[i] << (i * 8);
+			reg_addr |= REG_MRXADDR_VALID(i);
+		}
+
+		/* msgs[0] is handled by hw. */
+		i2c->msg = &msgs[1];
+
+		i2c->mode = REG_CON_MOD_REGISTER_TX;
+
+		i2c_writel(i2c, addr | REG_MRXADDR_VALID(0), REG_MRXADDR);
+		i2c_writel(i2c, reg_addr, REG_MRXRADDR);
+
+		ret = 2;
+	} else {
+		/*
+		 * We'll have to do it the boring way and process the msgs
+		 * one-by-one.
+		 */
+
+		if (msgs[0].flags & I2C_M_RD) {
+			addr |= 1; /* set read bit */
+
+			/*
+			 * We have to transmit the slave addr first. Use
+			 * MOD_REGISTER_TX for that purpose.
+			 */
+			i2c->mode = REG_CON_MOD_REGISTER_TX;
+			i2c_writel(i2c, addr | REG_MRXADDR_VALID(0),
+				   REG_MRXADDR);
+			i2c_writel(i2c, 0, REG_MRXRADDR);
+		} else {
+			i2c->mode = REG_CON_MOD_TX;
+		}
+
+		i2c->msg = &msgs[0];
+
+		ret = 1;
+	}
+
+	i2c->addr = msgs[0].addr;
+	i2c->busy = true;
+	i2c->state = STATE_START;
+	i2c->processed = 0;
+	i2c->error = 0;
+
+	rk3x_i2c_clean_ipd(i2c);
+
+	return ret;
+}
+
+static int rk3x_i2c_xfer(struct i2c_adapter *adap,
+			 struct i2c_msg *msgs, int num)
+{
+	struct rk3x_i2c *i2c = (struct rk3x_i2c *)adap->algo_data;
+	unsigned long timeout, flags;
+	int ret = 0;
+	int i;
+
+	spin_lock_irqsave(&i2c->lock, flags);
+
+	clk_enable(i2c->clk);
+
+	/* The clock rate might have changed, so setup the divider again */
+	rk3x_i2c_set_scl_rate(i2c, i2c->scl_frequency);
+
+	i2c->is_last_msg = false;
+
+	/*
+	 * Process msgs. We can handle more than one message at once (see
+	 * rk3x_i2c_setup()).
+	 */
+	for (i = 0; i < num; i += ret) {
+		ret = rk3x_i2c_setup(i2c, msgs + i, num - i);
+
+		if (ret < 0) {
+			dev_err(i2c->dev, "rk3x_i2c_setup() failed\n");
+			break;
+		}
+
+		if (i + ret >= num)
+			i2c->is_last_msg = true;
+
+		spin_unlock_irqrestore(&i2c->lock, flags);
+
+		rk3x_i2c_start(i2c);
+
+		timeout = wait_event_timeout(i2c->wait, !i2c->busy,
+					     msecs_to_jiffies(WAIT_TIMEOUT));
+
+		spin_lock_irqsave(&i2c->lock, flags);
+
+		if (timeout == 0) {
+			dev_err(i2c->dev, "timeout, ipd: 0x%02x, state: %d\n",
+				i2c_readl(i2c, REG_IPD), i2c->state);
+
+			/* Force a STOP condition without interrupt */
+			i2c_writel(i2c, 0, REG_IEN);
+			i2c_writel(i2c, REG_CON_EN | REG_CON_STOP, REG_CON);
+
+			i2c->state = STATE_IDLE;
+
+			ret = -ETIMEDOUT;
+			break;
+		}
+
+		if (i2c->error) {
+			ret = i2c->error;
+			break;
+		}
+	}
+
+	clk_disable(i2c->clk);
+	spin_unlock_irqrestore(&i2c->lock, flags);
+
+	return ret;
+}
+
+static u32 rk3x_i2c_func(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING;
+}
+
+static const struct i2c_algorithm rk3x_i2c_algorithm = {
+	.master_xfer		= rk3x_i2c_xfer,
+	.functionality		= rk3x_i2c_func,
+};
+
+static struct rk3x_i2c_soc_data soc_data[3] = {
+	{ .grf_offset = 0x154 }, /* rk3066 */
+	{ .grf_offset = 0x0a4 }, /* rk3188 */
+	{ .grf_offset = -1 },    /* no I2C switching needed */
+};
+
+static const struct of_device_id rk3x_i2c_match[] = {
+	{ .compatible = "rockchip,rk3066-i2c", .data = (void *)&soc_data[0] },
+	{ .compatible = "rockchip,rk3188-i2c", .data = (void *)&soc_data[1] },
+	{ .compatible = "rockchip,rk3288-i2c", .data = (void *)&soc_data[2] },
+	{},
+};
+
+static int rk3x_i2c_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct rk3x_i2c *i2c;
+	struct resource *mem;
+	int ret = 0;
+	int bus_nr;
+	u32 value;
+	int irq;
+
+	i2c = devm_kzalloc(&pdev->dev, sizeof(struct rk3x_i2c), GFP_KERNEL);
+	if (!i2c)
+		return -ENOMEM;
+
+	match = of_match_node(rk3x_i2c_match, np);
+	i2c->soc_data = (struct rk3x_i2c_soc_data *)match->data;
+
+	if (of_property_read_u32(pdev->dev.of_node, "clock-frequency",
+				 &i2c->scl_frequency)) {
+		dev_info(&pdev->dev, "using default SCL frequency: %d\n",
+			 DEFAULT_SCL_RATE);
+		i2c->scl_frequency = DEFAULT_SCL_RATE;
+	}
+
+	if (i2c->scl_frequency == 0 || i2c->scl_frequency > 400 * 1000) {
+		dev_warn(&pdev->dev, "invalid SCL frequency specified.\n");
+		dev_warn(&pdev->dev, "using default SCL frequency: %d\n",
+			 DEFAULT_SCL_RATE);
+		i2c->scl_frequency = DEFAULT_SCL_RATE;
+	}
+
+	strlcpy(i2c->adap.name, "rk3x-i2c", sizeof(i2c->adap.name));
+	i2c->adap.owner = THIS_MODULE;
+	i2c->adap.algo = &rk3x_i2c_algorithm;
+	i2c->adap.retries = 3;
+	i2c->adap.dev.of_node = np;
+	i2c->adap.algo_data = i2c;
+	i2c->adap.dev.parent = &pdev->dev;
+
+	i2c->dev = &pdev->dev;
+
+	spin_lock_init(&i2c->lock);
+	init_waitqueue_head(&i2c->wait);
+
+	i2c->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(i2c->clk)) {
+		dev_err(&pdev->dev, "cannot get clock\n");
+		return PTR_ERR(i2c->clk);
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	i2c->regs = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(i2c->regs))
+		return PTR_ERR(i2c->regs);
+
+	/* Try to set the I2C adapter number from dt */
+	bus_nr = of_alias_get_id(np, "i2c");
+
+	/*
+	 * Switch to new interface if the SoC also offers the old one.
+	 * The control bit is located in the GRF register space.
+	 */
+	if (i2c->soc_data->grf_offset >= 0) {
+		struct regmap *grf;
+
+		grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
+		if (IS_ERR(grf)) {
+			dev_err(&pdev->dev,
+				"rk3x-i2c needs 'rockchip,grf' property\n");
+			return PTR_ERR(grf);
+		}
+
+		if (bus_nr < 0) {
+			dev_err(&pdev->dev, "rk3x-i2c needs i2cX alias");
+			return -EINVAL;
+		}
+
+		/* 27+i: write mask, 11+i: value */
+		value = BIT(27 + bus_nr) | BIT(11 + bus_nr);
+
+		ret = regmap_write(grf, i2c->soc_data->grf_offset, value);
+		if (ret != 0) {
+			dev_err(i2c->dev, "Could not write to GRF: %d\n", ret);
+			return ret;
+		}
+	}
+
+	/* IRQ setup */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "cannot find rk3x IRQ\n");
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, rk3x_i2c_irq,
+			       0, dev_name(&pdev->dev), i2c);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "cannot request IRQ\n");
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, i2c);
+
+	ret = clk_prepare(i2c->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not prepare clock\n");
+		return ret;
+	}
+
+	ret = i2c_add_adapter(&i2c->adap);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not register adapter\n");
+		goto err_clk;
+	}
+
+	dev_info(&pdev->dev, "Initialized RK3xxx I2C bus at %p\n", i2c->regs);
+
+	return 0;
+
+err_clk:
+	clk_unprepare(i2c->clk);
+	return ret;
+}
+
+static int rk3x_i2c_remove(struct platform_device *pdev)
+{
+	struct rk3x_i2c *i2c = platform_get_drvdata(pdev);
+
+	i2c_del_adapter(&i2c->adap);
+	clk_unprepare(i2c->clk);
+
+	return 0;
+}
+
+static struct platform_driver rk3x_i2c_driver = {
+	.probe   = rk3x_i2c_probe,
+	.remove  = rk3x_i2c_remove,
+	.driver  = {
+		.owner = THIS_MODULE,
+		.name  = "rk3x-i2c",
+		.of_match_table = rk3x_i2c_match,
+	},
+};
+
+module_platform_driver(rk3x_i2c_driver);
+
+MODULE_DESCRIPTION("Rockchip RK3xxx I2C Bus driver");
+MODULE_AUTHOR("Max Schwarz <max.schwarz@online.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/i2c/busses/i2c-sun6i-p2wi.c b/drivers/i2c/busses/i2c-sun6i-p2wi.c
new file mode 100644
index 0000000..09de4fd
--- /dev/null
+++ b/drivers/i2c/busses/i2c-sun6i-p2wi.c
@@ -0,0 +1,345 @@
+/*
+ * P2WI (Push-Pull Two Wire Interface) bus driver.
+ *
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ * The P2WI controller looks like an SMBus controller which only supports byte
+ * data transfers. But, it differs from standard SMBus protocol on several
+ * aspects:
+ * - it supports only one slave device, and thus drop the address field
+ * - it adds a parity bit every 8bits of data
+ * - only one read access is required to read a byte (instead of a write
+ *   followed by a read access in standard SMBus protocol)
+ * - there's no Ack bit after each byte transfer
+ *
+ * This means this bus cannot be used to interface with standard SMBus
+ * devices (the only known device to support this interface is the AXP221
+ * PMIC).
+ *
+ */
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+
+/* P2WI registers */
+#define P2WI_CTRL		0x0
+#define P2WI_CCR		0x4
+#define P2WI_INTE		0x8
+#define P2WI_INTS		0xc
+#define P2WI_DADDR0		0x10
+#define P2WI_DADDR1		0x14
+#define P2WI_DLEN		0x18
+#define P2WI_DATA0		0x1c
+#define P2WI_DATA1		0x20
+#define P2WI_LCR		0x24
+#define P2WI_PMCR		0x28
+
+/* CTRL fields */
+#define P2WI_CTRL_START_TRANS		BIT(7)
+#define P2WI_CTRL_ABORT_TRANS		BIT(6)
+#define P2WI_CTRL_GLOBAL_INT_ENB	BIT(1)
+#define P2WI_CTRL_SOFT_RST		BIT(0)
+
+/* CLK CTRL fields */
+#define P2WI_CCR_SDA_OUT_DELAY(v)	(((v) & 0x7) << 8)
+#define P2WI_CCR_MAX_CLK_DIV		0xff
+#define P2WI_CCR_CLK_DIV(v)		((v) & P2WI_CCR_MAX_CLK_DIV)
+
+/* STATUS fields */
+#define P2WI_INTS_TRANS_ERR_ID(v)	(((v) >> 8) & 0xff)
+#define P2WI_INTS_LOAD_BSY		BIT(2)
+#define P2WI_INTS_TRANS_ERR		BIT(1)
+#define P2WI_INTS_TRANS_OVER		BIT(0)
+
+/* DATA LENGTH fields*/
+#define P2WI_DLEN_READ			BIT(4)
+#define P2WI_DLEN_DATA_LENGTH(v)	((v - 1) & 0x7)
+
+/* LINE CTRL fields*/
+#define P2WI_LCR_SCL_STATE		BIT(5)
+#define P2WI_LCR_SDA_STATE		BIT(4)
+#define P2WI_LCR_SCL_CTL		BIT(3)
+#define P2WI_LCR_SCL_CTL_EN		BIT(2)
+#define P2WI_LCR_SDA_CTL		BIT(1)
+#define P2WI_LCR_SDA_CTL_EN		BIT(0)
+
+/* PMU MODE CTRL fields */
+#define P2WI_PMCR_PMU_INIT_SEND		BIT(31)
+#define P2WI_PMCR_PMU_INIT_DATA(v)	(((v) & 0xff) << 16)
+#define P2WI_PMCR_PMU_MODE_REG(v)	(((v) & 0xff) << 8)
+#define P2WI_PMCR_PMU_DEV_ADDR(v)	((v) & 0xff)
+
+#define P2WI_MAX_FREQ			6000000
+
+struct p2wi {
+	struct i2c_adapter adapter;
+	struct completion complete;
+	unsigned int status;
+	void __iomem *regs;
+	struct clk *clk;
+	struct reset_control *rstc;
+	int slave_addr;
+};
+
+static irqreturn_t p2wi_interrupt(int irq, void *dev_id)
+{
+	struct p2wi *p2wi = dev_id;
+	unsigned long status;
+
+	status = readl(p2wi->regs + P2WI_INTS);
+	p2wi->status = status;
+
+	/* Clear interrupts */
+	status &= (P2WI_INTS_LOAD_BSY | P2WI_INTS_TRANS_ERR |
+		   P2WI_INTS_TRANS_OVER);
+	writel(status, p2wi->regs + P2WI_INTS);
+
+	complete(&p2wi->complete);
+
+	return IRQ_HANDLED;
+}
+
+static u32 p2wi_functionality(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_SMBUS_BYTE_DATA;
+}
+
+static int p2wi_smbus_xfer(struct i2c_adapter *adap, u16 addr,
+			   unsigned short flags, char read_write,
+			   u8 command, int size, union i2c_smbus_data *data)
+{
+	struct p2wi *p2wi = i2c_get_adapdata(adap);
+	unsigned long dlen = P2WI_DLEN_DATA_LENGTH(1);
+
+	if (p2wi->slave_addr >= 0 && addr != p2wi->slave_addr) {
+		dev_err(&adap->dev, "invalid P2WI address\n");
+		return -EINVAL;
+	}
+
+	if (!data)
+		return -EINVAL;
+
+	writel(command, p2wi->regs + P2WI_DADDR0);
+
+	if (read_write == I2C_SMBUS_READ)
+		dlen |= P2WI_DLEN_READ;
+	else
+		writel(data->byte, p2wi->regs + P2WI_DATA0);
+
+	writel(dlen, p2wi->regs + P2WI_DLEN);
+
+	if (readl(p2wi->regs + P2WI_CTRL) & P2WI_CTRL_START_TRANS) {
+		dev_err(&adap->dev, "P2WI bus busy\n");
+		return -EBUSY;
+	}
+
+	reinit_completion(&p2wi->complete);
+
+	writel(P2WI_INTS_LOAD_BSY | P2WI_INTS_TRANS_ERR | P2WI_INTS_TRANS_OVER,
+	       p2wi->regs + P2WI_INTE);
+
+	writel(P2WI_CTRL_START_TRANS | P2WI_CTRL_GLOBAL_INT_ENB,
+	       p2wi->regs + P2WI_CTRL);
+
+	wait_for_completion(&p2wi->complete);
+
+	if (p2wi->status & P2WI_INTS_LOAD_BSY) {
+		dev_err(&adap->dev, "P2WI bus busy\n");
+		return -EBUSY;
+	}
+
+	if (p2wi->status & P2WI_INTS_TRANS_ERR) {
+		dev_err(&adap->dev, "P2WI bus xfer error\n");
+		return -ENXIO;
+	}
+
+	if (read_write == I2C_SMBUS_READ)
+		data->byte = readl(p2wi->regs + P2WI_DATA0);
+
+	return 0;
+}
+
+static const struct i2c_algorithm p2wi_algo = {
+	.smbus_xfer = p2wi_smbus_xfer,
+	.functionality = p2wi_functionality,
+};
+
+static const struct of_device_id p2wi_of_match_table[] = {
+	{ .compatible = "allwinner,sun6i-a31-p2wi" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, p2wi_of_match_table);
+
+static int p2wi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device_node *childnp;
+	unsigned long parent_clk_freq;
+	u32 clk_freq = 100000;
+	struct resource *r;
+	struct p2wi *p2wi;
+	u32 slave_addr;
+	int clk_div;
+	int irq;
+	int ret;
+
+	of_property_read_u32(np, "clock-frequency", &clk_freq);
+	if (clk_freq > P2WI_MAX_FREQ) {
+		dev_err(dev,
+			"required clock-frequency (%u Hz) is too high (max = 6MHz)",
+			clk_freq);
+		return -EINVAL;
+	}
+
+	if (of_get_child_count(np) > 1) {
+		dev_err(dev, "P2WI only supports one slave device\n");
+		return -EINVAL;
+	}
+
+	p2wi = devm_kzalloc(dev, sizeof(struct p2wi), GFP_KERNEL);
+	if (!p2wi)
+		return -ENOMEM;
+
+	p2wi->slave_addr = -1;
+
+	/*
+	 * Authorize a p2wi node without any children to be able to use an
+	 * i2c-dev from userpace.
+	 * In this case the slave_addr is set to -1 and won't be checked when
+	 * launching a P2WI transfer.
+	 */
+	childnp = of_get_next_available_child(np, NULL);
+	if (childnp) {
+		ret = of_property_read_u32(childnp, "reg", &slave_addr);
+		if (ret) {
+			dev_err(dev, "invalid slave address on node %s\n",
+				childnp->full_name);
+			return -EINVAL;
+		}
+
+		p2wi->slave_addr = slave_addr;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	p2wi->regs = devm_ioremap_resource(dev, r);
+	if (IS_ERR(p2wi->regs))
+		return PTR_ERR(p2wi->regs);
+
+	strlcpy(p2wi->adapter.name, pdev->name, sizeof(p2wi->adapter.name));
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "failed to retrieve irq: %d\n", irq);
+		return irq;
+	}
+
+	p2wi->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(p2wi->clk)) {
+		ret = PTR_ERR(p2wi->clk);
+		dev_err(dev, "failed to retrieve clk: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(p2wi->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clk: %d\n", ret);
+		return ret;
+	}
+
+	parent_clk_freq = clk_get_rate(p2wi->clk);
+
+	p2wi->rstc = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(p2wi->rstc)) {
+		ret = PTR_ERR(p2wi->rstc);
+		dev_err(dev, "failed to retrieve reset controller: %d\n", ret);
+		goto err_clk_disable;
+	}
+
+	ret = reset_control_deassert(p2wi->rstc);
+	if (ret) {
+		dev_err(dev, "failed to deassert reset line: %d\n", ret);
+		goto err_clk_disable;
+	}
+
+	init_completion(&p2wi->complete);
+	p2wi->adapter.dev.parent = dev;
+	p2wi->adapter.algo = &p2wi_algo;
+	p2wi->adapter.owner = THIS_MODULE;
+	p2wi->adapter.dev.of_node = pdev->dev.of_node;
+	platform_set_drvdata(pdev, p2wi);
+	i2c_set_adapdata(&p2wi->adapter, p2wi);
+
+	ret = devm_request_irq(dev, irq, p2wi_interrupt, 0, pdev->name, p2wi);
+	if (ret) {
+		dev_err(dev, "can't register interrupt handler irq%d: %d\n",
+			irq, ret);
+		goto err_reset_assert;
+	}
+
+	writel(P2WI_CTRL_SOFT_RST, p2wi->regs + P2WI_CTRL);
+
+	clk_div = parent_clk_freq / clk_freq;
+	if (!clk_div) {
+		dev_warn(dev,
+			 "clock-frequency is too high, setting it to %lu Hz\n",
+			 parent_clk_freq);
+		clk_div = 1;
+	} else if (clk_div > P2WI_CCR_MAX_CLK_DIV) {
+		dev_warn(dev,
+			 "clock-frequency is too low, setting it to %lu Hz\n",
+			 parent_clk_freq / P2WI_CCR_MAX_CLK_DIV);
+		clk_div = P2WI_CCR_MAX_CLK_DIV;
+	}
+
+	writel(P2WI_CCR_SDA_OUT_DELAY(1) | P2WI_CCR_CLK_DIV(clk_div),
+	       p2wi->regs + P2WI_CCR);
+
+	ret = i2c_add_adapter(&p2wi->adapter);
+	if (!ret)
+		return 0;
+
+err_reset_assert:
+	reset_control_assert(p2wi->rstc);
+
+err_clk_disable:
+	clk_disable_unprepare(p2wi->clk);
+
+	return ret;
+}
+
+static int p2wi_remove(struct platform_device *dev)
+{
+	struct p2wi *p2wi = platform_get_drvdata(dev);
+
+	reset_control_assert(p2wi->rstc);
+	clk_disable_unprepare(p2wi->clk);
+	i2c_del_adapter(&p2wi->adapter);
+
+	return 0;
+}
+
+static struct platform_driver p2wi_driver = {
+	.probe	= p2wi_probe,
+	.remove	= p2wi_remove,
+	.driver	= {
+		.owner = THIS_MODULE,
+		.name = "i2c-sunxi-p2wi",
+		.of_match_table = p2wi_of_match_table,
+	},
+};
+module_platform_driver(p2wi_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner P2WI driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 3b5bacd..2b6a9ce9 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -510,12 +510,11 @@
 	return idev->num_channels;
 }
 
-static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
+static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 					     struct at91_adc_trigger *triggers,
 					     const char *trigger_name)
 {
 	struct at91_adc_state *st = iio_priv(idev);
-	u8 value = 0;
 	int i;
 
 	for (i = 0; i < st->trigger_number; i++) {
@@ -528,15 +527,16 @@
 			return -ENOMEM;
 
 		if (strcmp(trigger_name, name) == 0) {
-			value = triggers[i].value;
 			kfree(name);
-			break;
+			if (triggers[i].value == 0)
+				return -EINVAL;
+			return triggers[i].value;
 		}
 
 		kfree(name);
 	}
 
-	return value;
+	return -EINVAL;
 }
 
 static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
@@ -546,14 +546,14 @@
 	struct iio_buffer *buffer = idev->buffer;
 	struct at91_adc_reg_desc *reg = st->registers;
 	u32 status = at91_adc_readl(st, reg->trigger_register);
-	u8 value;
+	int value;
 	u8 bit;
 
 	value = at91_adc_get_trigger_value_by_name(idev,
 						   st->trigger_list,
 						   idev->trig->name);
-	if (value == 0)
-		return -EINVAL;
+	if (value < 0)
+		return value;
 
 	if (state) {
 		st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL);
diff --git a/drivers/iio/adc/men_z188_adc.c b/drivers/iio/adc/men_z188_adc.c
index 6989c16..b58d630 100644
--- a/drivers/iio/adc/men_z188_adc.c
+++ b/drivers/iio/adc/men_z188_adc.c
@@ -121,8 +121,8 @@
 	indio_dev->num_channels = ARRAY_SIZE(z188_adc_iio_channels);
 
 	mem = mcb_request_mem(dev, "z188-adc");
-	if (!mem)
-		return -ENOMEM;
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
 
 	adc->base = ioremap(mem->start, resource_size(mem));
 	if (adc->base == NULL)
diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c
index 7de1c4c..eb86786 100644
--- a/drivers/iio/adc/twl4030-madc.c
+++ b/drivers/iio/adc/twl4030-madc.c
@@ -645,6 +645,7 @@
 	req.channels = (1 << channel_no);
 	req.method = TWL4030_MADC_SW2;
 	req.active = 0;
+	req.raw = 0;
 	req.func_cb = NULL;
 	ret = twl4030_madc_conversion(&req);
 	if (ret < 0)
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 73282ce..a3109a6 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -75,6 +75,9 @@
 					(s32)report_val);
 	}
 
+	sensor_hub_get_feature(st->hsdev, st->power_state.report_id,
+					st->power_state.index,
+					&state_val);
 	return 0;
 }
 EXPORT_SYMBOL(hid_sensor_power_state);
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 09ea5c4..ea08313 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -373,8 +373,6 @@
 {
 	struct ak8975_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	u16 meas_reg;
-	s16 raw;
 	int ret;
 
 	mutex_lock(&data->lock);
@@ -422,16 +420,11 @@
 		dev_err(&client->dev, "Read axis data fails\n");
 		goto exit;
 	}
-	meas_reg = ret;
 
 	mutex_unlock(&data->lock);
 
-	/* Endian conversion of the measured values. */
-	raw = (s16) (le16_to_cpu(meas_reg));
-
 	/* Clamp to valid range. */
-	raw = clamp_t(s16, raw, -4096, 4095);
-	*val = raw;
+	*val = clamp_t(s16, ret, -4096, 4095);
 	return IIO_VAL_INT;
 
 exit:
diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c
index ba6d0c5..01b2e0b 100644
--- a/drivers/iio/pressure/mpl3115.c
+++ b/drivers/iio/pressure/mpl3115.c
@@ -98,7 +98,7 @@
 			mutex_unlock(&data->lock);
 			if (ret < 0)
 				return ret;
-			*val = sign_extend32(be32_to_cpu(tmp) >> 12, 23);
+			*val = be32_to_cpu(tmp) >> 12;
 			return IIO_VAL_INT;
 		case IIO_TEMP: /* in 0.0625 celsius / LSB */
 			mutex_lock(&data->lock);
@@ -112,7 +112,7 @@
 			mutex_unlock(&data->lock);
 			if (ret < 0)
 				return ret;
-			*val = sign_extend32(be32_to_cpu(tmp) >> 20, 15);
+			*val = sign_extend32(be32_to_cpu(tmp) >> 20, 11);
 			return IIO_VAL_INT;
 		default:
 			return -EINVAL;
@@ -185,7 +185,7 @@
 			BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index = 0,
 		.scan_type = {
-			.sign = 's',
+			.sign = 'u',
 			.realbits = 20,
 			.storagebits = 32,
 			.shift = 12,
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 20f1655..8108c69 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -93,7 +93,9 @@
 
 config VIDEO_OMAP3
 	tristate "OMAP 3 Camera support"
-	depends on OMAP_IOVMM && VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && ARCH_OMAP3
+	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && ARCH_OMAP3
+	select ARM_DMA_USE_IOMMU
+	select OMAP_IOMMU
 	---help---
 	  Driver for an OMAP 3 camera controller.
 
diff --git a/drivers/media/platform/omap3isp/Makefile b/drivers/media/platform/omap3isp/Makefile
index e8847e7..254975a 100644
--- a/drivers/media/platform/omap3isp/Makefile
+++ b/drivers/media/platform/omap3isp/Makefile
@@ -3,7 +3,7 @@
 ccflags-$(CONFIG_VIDEO_OMAP3_DEBUG) += -DDEBUG
 
 omap3-isp-objs += \
-	isp.o ispqueue.o ispvideo.o \
+	isp.o ispvideo.o \
 	ispcsiphy.o ispccp2.o ispcsi2.o \
 	ispccdc.o isppreview.o ispresizer.o \
 	ispstat.o isph3a_aewb.o isph3a_af.o isphist.o
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 06a0df4..2c7aa67 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -69,6 +69,8 @@
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
 
+#include <asm/dma-iommu.h>
+
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
 
@@ -1397,14 +1399,14 @@
 	if (isp_pipeline_is_last(me)) {
 		struct isp_video *video = pipe->output;
 		unsigned long flags;
-		spin_lock_irqsave(&video->queue->irqlock, flags);
+		spin_lock_irqsave(&video->irqlock, flags);
 		if (video->dmaqueue_flags & ISP_VIDEO_DMAQUEUE_UNDERRUN) {
-			spin_unlock_irqrestore(&video->queue->irqlock, flags);
+			spin_unlock_irqrestore(&video->irqlock, flags);
 			atomic_set(stopping, 0);
 			smp_mb();
 			return 0;
 		}
-		spin_unlock_irqrestore(&video->queue->irqlock, flags);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 		if (!wait_event_timeout(*wait, !atomic_read(stopping),
 					msecs_to_jiffies(1000))) {
 			atomic_set(stopping, 0);
@@ -1625,7 +1627,7 @@
  * Decrement the reference count on the ISP. If the last reference is released,
  * power-down all submodules, disable clocks and free temporary buffers.
  */
-void omap3isp_put(struct isp_device *isp)
+static void __omap3isp_put(struct isp_device *isp, bool save_ctx)
 {
 	if (isp == NULL)
 		return;
@@ -1634,7 +1636,7 @@
 	BUG_ON(isp->ref_count == 0);
 	if (--isp->ref_count == 0) {
 		isp_disable_interrupts(isp);
-		if (isp->domain) {
+		if (save_ctx) {
 			isp_save_ctx(isp);
 			isp->has_context = 1;
 		}
@@ -1648,6 +1650,11 @@
 	mutex_unlock(&isp->isp_mutex);
 }
 
+void omap3isp_put(struct isp_device *isp)
+{
+	__omap3isp_put(isp, true);
+}
+
 /* --------------------------------------------------------------------------
  * Platform device driver
  */
@@ -2120,6 +2127,61 @@
 	return ret;
 }
 
+static void isp_detach_iommu(struct isp_device *isp)
+{
+	arm_iommu_release_mapping(isp->mapping);
+	isp->mapping = NULL;
+	iommu_group_remove_device(isp->dev);
+}
+
+static int isp_attach_iommu(struct isp_device *isp)
+{
+	struct dma_iommu_mapping *mapping;
+	struct iommu_group *group;
+	int ret;
+
+	/* Create a device group and add the device to it. */
+	group = iommu_group_alloc();
+	if (IS_ERR(group)) {
+		dev_err(isp->dev, "failed to allocate IOMMU group\n");
+		return PTR_ERR(group);
+	}
+
+	ret = iommu_group_add_device(group, isp->dev);
+	iommu_group_put(group);
+
+	if (ret < 0) {
+		dev_err(isp->dev, "failed to add device to IPMMU group\n");
+		return ret;
+	}
+
+	/*
+	 * Create the ARM mapping, used by the ARM DMA mapping core to allocate
+	 * VAs. This will allocate a corresponding IOMMU domain.
+	 */
+	mapping = arm_iommu_create_mapping(&platform_bus_type, SZ_1G, SZ_2G);
+	if (IS_ERR(mapping)) {
+		dev_err(isp->dev, "failed to create ARM IOMMU mapping\n");
+		ret = PTR_ERR(mapping);
+		goto error;
+	}
+
+	isp->mapping = mapping;
+
+	/* Attach the ARM VA mapping to the device. */
+	ret = arm_iommu_attach_device(isp->dev, mapping);
+	if (ret < 0) {
+		dev_err(isp->dev, "failed to attach device to VA mapping\n");
+		goto error;
+	}
+
+	return 0;
+
+error:
+	isp_detach_iommu(isp);
+	return ret;
+}
+
 /*
  * isp_remove - Remove ISP platform device
  * @pdev: Pointer to ISP platform device
@@ -2135,10 +2197,8 @@
 	isp_xclk_cleanup(isp);
 
 	__omap3isp_get(isp, false);
-	iommu_detach_device(isp->domain, &pdev->dev);
-	iommu_domain_free(isp->domain);
-	isp->domain = NULL;
-	omap3isp_put(isp);
+	isp_detach_iommu(isp);
+	__omap3isp_put(isp, false);
 
 	return 0;
 }
@@ -2265,39 +2325,32 @@
 		}
 	}
 
-	isp->domain = iommu_domain_alloc(pdev->dev.bus);
-	if (!isp->domain) {
-		dev_err(isp->dev, "can't alloc iommu domain\n");
-		ret = -ENOMEM;
+	/* IOMMU */
+	ret = isp_attach_iommu(isp);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "unable to attach to IOMMU\n");
 		goto error_isp;
 	}
 
-	ret = iommu_attach_device(isp->domain, &pdev->dev);
-	if (ret) {
-		dev_err(&pdev->dev, "can't attach iommu device: %d\n", ret);
-		ret = -EPROBE_DEFER;
-		goto free_domain;
-	}
-
 	/* Interrupt */
 	isp->irq_num = platform_get_irq(pdev, 0);
 	if (isp->irq_num <= 0) {
 		dev_err(isp->dev, "No IRQ resource\n");
 		ret = -ENODEV;
-		goto detach_dev;
+		goto error_iommu;
 	}
 
 	if (devm_request_irq(isp->dev, isp->irq_num, isp_isr, IRQF_SHARED,
 			     "OMAP3 ISP", isp)) {
 		dev_err(isp->dev, "Unable to request IRQ\n");
 		ret = -EINVAL;
-		goto detach_dev;
+		goto error_iommu;
 	}
 
 	/* Entities */
 	ret = isp_initialize_modules(isp);
 	if (ret < 0)
-		goto detach_dev;
+		goto error_iommu;
 
 	ret = isp_register_entities(isp);
 	if (ret < 0)
@@ -2310,14 +2363,11 @@
 
 error_modules:
 	isp_cleanup_modules(isp);
-detach_dev:
-	iommu_detach_device(isp->domain, &pdev->dev);
-free_domain:
-	iommu_domain_free(isp->domain);
-	isp->domain = NULL;
+error_iommu:
+	isp_detach_iommu(isp);
 error_isp:
 	isp_xclk_cleanup(isp);
-	omap3isp_put(isp);
+	__omap3isp_put(isp, false);
 error:
 	mutex_destroy(&isp->isp_mutex);
 
diff --git a/drivers/media/platform/omap3isp/isp.h b/drivers/media/platform/omap3isp/isp.h
index 6d5e697..2c314ee 100644
--- a/drivers/media/platform/omap3isp/isp.h
+++ b/drivers/media/platform/omap3isp/isp.h
@@ -45,8 +45,6 @@
 #include "ispcsi2.h"
 #include "ispccp2.h"
 
-#define IOMMU_FLAG (IOVMF_ENDIAN_LITTLE | IOVMF_ELSZ_8)
-
 #define ISP_TOK_TERM		0xFFFFFFFF	/*
 						 * terminating token for ISP
 						 * modules reg list
@@ -152,6 +150,7 @@
  *             regions.
  * @mmio_base_phys: Array with physical L4 bus addresses for ISP register
  *                  regions.
+ * @mapping: IOMMU mapping
  * @stat_lock: Spinlock for handling statistics
  * @isp_mutex: Mutex for serializing requests to ISP.
  * @stop_failure: Indicates that an entity failed to stop.
@@ -171,7 +170,6 @@
  * @isp_res: Pointer to current settings for ISP Resizer.
  * @isp_prev: Pointer to current settings for ISP Preview.
  * @isp_ccdc: Pointer to current settings for ISP CCDC.
- * @iommu: Pointer to requested IOMMU instance for ISP.
  * @platform_cb: ISP driver callback function pointers for platform code
  *
  * This structure is used to store the OMAP ISP Information.
@@ -189,6 +187,8 @@
 	void __iomem *mmio_base[OMAP3_ISP_IOMEM_LAST];
 	unsigned long mmio_base_phys[OMAP3_ISP_IOMEM_LAST];
 
+	struct dma_iommu_mapping *mapping;
+
 	/* ISP Obj */
 	spinlock_t stat_lock;	/* common lock for statistic drivers */
 	struct mutex isp_mutex;	/* For handling ref_count field */
@@ -219,8 +219,6 @@
 
 	unsigned int sbl_resources;
 	unsigned int subclk_resources;
-
-	struct iommu_domain *domain;
 };
 
 #define v4l2_dev_to_isp_device(dev) \
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index 4d920c8..9f727d2 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -30,7 +30,6 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
-#include <linux/omap-iommu.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <media/v4l2-event.h>
@@ -206,7 +205,8 @@
  * ccdc_lsc_program_table - Program Lens Shading Compensation table address.
  * @ccdc: Pointer to ISP CCDC device.
  */
-static void ccdc_lsc_program_table(struct isp_ccdc_device *ccdc, u32 addr)
+static void ccdc_lsc_program_table(struct isp_ccdc_device *ccdc,
+				   dma_addr_t addr)
 {
 	isp_reg_writel(to_isp_device(ccdc), addr,
 		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_LSC_TABLE_BASE);
@@ -333,7 +333,7 @@
 		return -EBUSY;
 
 	ccdc_lsc_setup_regs(ccdc, &req->config);
-	ccdc_lsc_program_table(ccdc, req->table);
+	ccdc_lsc_program_table(ccdc, req->table.dma);
 	return 0;
 }
 
@@ -368,11 +368,12 @@
 	if (req == NULL)
 		return;
 
-	if (req->iovm)
-		dma_unmap_sg(isp->dev, req->iovm->sgt->sgl,
-			     req->iovm->sgt->nents, DMA_TO_DEVICE);
-	if (req->table)
-		omap_iommu_vfree(isp->domain, isp->dev, req->table);
+	if (req->table.addr) {
+		sg_free_table(&req->table.sgt);
+		dma_free_coherent(isp->dev, req->config.size, req->table.addr,
+				  req->table.dma);
+	}
+
 	kfree(req);
 }
 
@@ -416,7 +417,6 @@
 	struct isp_device *isp = to_isp_device(ccdc);
 	struct ispccdc_lsc_config_req *req;
 	unsigned long flags;
-	void *table;
 	u16 update;
 	int ret;
 
@@ -444,38 +444,31 @@
 
 		req->enable = 1;
 
-		req->table = omap_iommu_vmalloc(isp->domain, isp->dev, 0,
-					req->config.size, IOMMU_FLAG);
-		if (IS_ERR_VALUE(req->table)) {
-			req->table = 0;
+		req->table.addr = dma_alloc_coherent(isp->dev, req->config.size,
+						     &req->table.dma,
+						     GFP_KERNEL);
+		if (req->table.addr == NULL) {
 			ret = -ENOMEM;
 			goto done;
 		}
 
-		req->iovm = omap_find_iovm_area(isp->dev, req->table);
-		if (req->iovm == NULL) {
-			ret = -ENOMEM;
+		ret = dma_get_sgtable(isp->dev, &req->table.sgt,
+				      req->table.addr, req->table.dma,
+				      req->config.size);
+		if (ret < 0)
 			goto done;
-		}
 
-		if (!dma_map_sg(isp->dev, req->iovm->sgt->sgl,
-				req->iovm->sgt->nents, DMA_TO_DEVICE)) {
-			ret = -ENOMEM;
-			req->iovm = NULL;
-			goto done;
-		}
+		dma_sync_sg_for_cpu(isp->dev, req->table.sgt.sgl,
+				    req->table.sgt.nents, DMA_TO_DEVICE);
 
-		dma_sync_sg_for_cpu(isp->dev, req->iovm->sgt->sgl,
-				    req->iovm->sgt->nents, DMA_TO_DEVICE);
-
-		table = omap_da_to_va(isp->dev, req->table);
-		if (copy_from_user(table, config->lsc, req->config.size)) {
+		if (copy_from_user(req->table.addr, config->lsc,
+				   req->config.size)) {
 			ret = -EFAULT;
 			goto done;
 		}
 
-		dma_sync_sg_for_device(isp->dev, req->iovm->sgt->sgl,
-				       req->iovm->sgt->nents, DMA_TO_DEVICE);
+		dma_sync_sg_for_device(isp->dev, req->table.sgt.sgl,
+				       req->table.sgt.nents, DMA_TO_DEVICE);
 	}
 
 	spin_lock_irqsave(&ccdc->lsc.req_lock, flags);
@@ -584,7 +577,7 @@
 	if (!ccdc->fpc_en)
 		return;
 
-	isp_reg_writel(isp, ccdc->fpc.fpcaddr, OMAP3_ISP_IOMEM_CCDC,
+	isp_reg_writel(isp, ccdc->fpc.dma, OMAP3_ISP_IOMEM_CCDC,
 		       ISPCCDC_FPC_ADDR);
 	/* The FPNUM field must be set before enabling FPC. */
 	isp_reg_writel(isp, (ccdc->fpc.fpnum << ISPCCDC_FPC_FPNUM_SHIFT),
@@ -724,8 +717,9 @@
 	ccdc->shadow_update = 0;
 
 	if (OMAP3ISP_CCDC_FPC & ccdc_struct->update) {
-		u32 table_old = 0;
-		u32 table_new;
+		struct omap3isp_ccdc_fpc fpc;
+		struct ispccdc_fpc fpc_old = { .addr = NULL, };
+		struct ispccdc_fpc fpc_new;
 		u32 size;
 
 		if (ccdc->state != ISP_PIPELINE_STREAM_STOPPED)
@@ -734,35 +728,39 @@
 		ccdc->fpc_en = !!(OMAP3ISP_CCDC_FPC & ccdc_struct->flag);
 
 		if (ccdc->fpc_en) {
-			if (copy_from_user(&ccdc->fpc, ccdc_struct->fpc,
-					   sizeof(ccdc->fpc)))
+			if (copy_from_user(&fpc, ccdc_struct->fpc, sizeof(fpc)))
 				return -EFAULT;
 
+			size = fpc.fpnum * 4;
+
 			/*
-			 * table_new must be 64-bytes aligned, but it's
-			 * already done by omap_iommu_vmalloc().
+			 * The table address must be 64-bytes aligned, which is
+			 * guaranteed by dma_alloc_coherent().
 			 */
-			size = ccdc->fpc.fpnum * 4;
-			table_new = omap_iommu_vmalloc(isp->domain, isp->dev,
-							0, size, IOMMU_FLAG);
-			if (IS_ERR_VALUE(table_new))
+			fpc_new.fpnum = fpc.fpnum;
+			fpc_new.addr = dma_alloc_coherent(isp->dev, size,
+							  &fpc_new.dma,
+							  GFP_KERNEL);
+			if (fpc_new.addr == NULL)
 				return -ENOMEM;
 
-			if (copy_from_user(omap_da_to_va(isp->dev, table_new),
-					   (__force void __user *)
-					   ccdc->fpc.fpcaddr, size)) {
-				omap_iommu_vfree(isp->domain, isp->dev,
-								table_new);
+			if (copy_from_user(fpc_new.addr,
+					   (__force void __user *)fpc.fpcaddr,
+					   size)) {
+				dma_free_coherent(isp->dev, size, fpc_new.addr,
+						  fpc_new.dma);
 				return -EFAULT;
 			}
 
-			table_old = ccdc->fpc.fpcaddr;
-			ccdc->fpc.fpcaddr = table_new;
+			fpc_old = ccdc->fpc;
+			ccdc->fpc = fpc_new;
 		}
 
 		ccdc_configure_fpc(ccdc);
-		if (table_old != 0)
-			omap_iommu_vfree(isp->domain, isp->dev, table_old);
+
+		if (fpc_old.addr != NULL)
+			dma_free_coherent(isp->dev, fpc_old.fpnum * 4,
+					  fpc_old.addr, fpc_old.dma);
 	}
 
 	return ccdc_lsc_config(ccdc, ccdc_struct);
@@ -1523,7 +1521,7 @@
 
 	buffer = omap3isp_video_buffer_next(&ccdc->video_out);
 	if (buffer != NULL) {
-		ccdc_set_outaddr(ccdc, buffer->isp_addr);
+		ccdc_set_outaddr(ccdc, buffer->dma);
 		restart = 1;
 	}
 
@@ -1662,7 +1660,7 @@
 	if (!(ccdc->output & CCDC_OUTPUT_MEMORY))
 		return -ENODEV;
 
-	ccdc_set_outaddr(ccdc, buffer->isp_addr);
+	ccdc_set_outaddr(ccdc, buffer->dma);
 
 	/* We now have a buffer queued on the output, restart the pipeline
 	 * on the next CCDC interrupt if running in continuous mode (or when
@@ -2580,8 +2578,9 @@
 	cancel_work_sync(&ccdc->lsc.table_work);
 	ccdc_lsc_free_queue(ccdc, &ccdc->lsc.free_queue);
 
-	if (ccdc->fpc.fpcaddr != 0)
-		omap_iommu_vfree(isp->domain, isp->dev, ccdc->fpc.fpcaddr);
+	if (ccdc->fpc.addr != NULL)
+		dma_free_coherent(isp->dev, ccdc->fpc.fpnum * 4, ccdc->fpc.addr,
+				  ccdc->fpc.dma);
 
 	mutex_destroy(&ccdc->ioctl_lock);
 }
diff --git a/drivers/media/platform/omap3isp/ispccdc.h b/drivers/media/platform/omap3isp/ispccdc.h
index 9d24e41..f650616 100644
--- a/drivers/media/platform/omap3isp/ispccdc.h
+++ b/drivers/media/platform/omap3isp/ispccdc.h
@@ -46,6 +46,12 @@
 
 #define	OMAP3ISP_CCDC_NEVENTS	16
 
+struct ispccdc_fpc {
+	void *addr;
+	dma_addr_t dma;
+	unsigned int fpnum;
+};
+
 enum ispccdc_lsc_state {
 	LSC_STATE_STOPPED = 0,
 	LSC_STATE_STOPPING = 1,
@@ -57,8 +63,12 @@
 	struct list_head list;
 	struct omap3isp_ccdc_lsc_config config;
 	unsigned char enable;
-	u32 table;
-	struct iovm_struct *iovm;
+
+	struct {
+		void *addr;
+		dma_addr_t dma;
+		struct sg_table sgt;
+	} table;
 };
 
 /*
@@ -136,7 +146,7 @@
 		     fpc_en:1;
 	struct omap3isp_ccdc_blcomp blcomp;
 	struct omap3isp_ccdc_bclamp clamp;
-	struct omap3isp_ccdc_fpc fpc;
+	struct ispccdc_fpc fpc;
 	struct ispccdc_lsc lsc;
 	unsigned int update;
 	unsigned int shadow_update;
diff --git a/drivers/media/platform/omap3isp/ispccp2.c b/drivers/media/platform/omap3isp/ispccp2.c
index b30b67d..f3801db 100644
--- a/drivers/media/platform/omap3isp/ispccp2.c
+++ b/drivers/media/platform/omap3isp/ispccp2.c
@@ -549,7 +549,7 @@
 
 	buffer = omap3isp_video_buffer_next(&ccp2->video_in);
 	if (buffer != NULL)
-		ccp2_set_inaddr(ccp2, buffer->isp_addr);
+		ccp2_set_inaddr(ccp2, buffer->dma);
 
 	pipe->state |= ISP_PIPELINE_IDLE_INPUT;
 
@@ -940,7 +940,7 @@
 {
 	struct isp_ccp2_device *ccp2 = &video->isp->isp_ccp2;
 
-	ccp2_set_inaddr(ccp2, buffer->isp_addr);
+	ccp2_set_inaddr(ccp2, buffer->dma);
 	return 0;
 }
 
diff --git a/drivers/media/platform/omap3isp/ispcsi2.c b/drivers/media/platform/omap3isp/ispcsi2.c
index 62056082..5a2e47e 100644
--- a/drivers/media/platform/omap3isp/ispcsi2.c
+++ b/drivers/media/platform/omap3isp/ispcsi2.c
@@ -695,7 +695,7 @@
 	if (buffer == NULL)
 		return;
 
-	csi2_set_outaddr(csi2, buffer->isp_addr);
+	csi2_set_outaddr(csi2, buffer->dma);
 	csi2_ctx_enable(isp, csi2, 0, 1);
 }
 
@@ -812,7 +812,7 @@
 	struct isp_device *isp = video->isp;
 	struct isp_csi2_device *csi2 = &isp->isp_csi2a;
 
-	csi2_set_outaddr(csi2, buffer->isp_addr);
+	csi2_set_outaddr(csi2, buffer->dma);
 
 	/*
 	 * If streaming was enabled before there was a buffer queued
diff --git a/drivers/media/platform/omap3isp/isph3a_aewb.c b/drivers/media/platform/omap3isp/isph3a_aewb.c
index 75fd82b..d6811ce 100644
--- a/drivers/media/platform/omap3isp/isph3a_aewb.c
+++ b/drivers/media/platform/omap3isp/isph3a_aewb.c
@@ -47,7 +47,7 @@
 	if (aewb->state == ISPSTAT_DISABLED)
 		return;
 
-	isp_reg_writel(aewb->isp, aewb->active_buf->iommu_addr,
+	isp_reg_writel(aewb->isp, aewb->active_buf->dma_addr,
 		       OMAP3_ISP_IOMEM_H3A, ISPH3A_AEWBUFST);
 
 	if (!aewb->update)
diff --git a/drivers/media/platform/omap3isp/isph3a_af.c b/drivers/media/platform/omap3isp/isph3a_af.c
index a0bf5af..6fc960c 100644
--- a/drivers/media/platform/omap3isp/isph3a_af.c
+++ b/drivers/media/platform/omap3isp/isph3a_af.c
@@ -51,7 +51,7 @@
 	if (af->state == ISPSTAT_DISABLED)
 		return;
 
-	isp_reg_writel(af->isp, af->active_buf->iommu_addr, OMAP3_ISP_IOMEM_H3A,
+	isp_reg_writel(af->isp, af->active_buf->dma_addr, OMAP3_ISP_IOMEM_H3A,
 		       ISPH3A_AFBUFST);
 
 	if (!af->update)
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 395b2b0..720809b 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -1499,14 +1499,14 @@
 	if (prev->input == PREVIEW_INPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&prev->video_in);
 		if (buffer != NULL)
-			preview_set_inaddr(prev, buffer->isp_addr);
+			preview_set_inaddr(prev, buffer->dma);
 		pipe->state |= ISP_PIPELINE_IDLE_INPUT;
 	}
 
 	if (prev->output & PREVIEW_OUTPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&prev->video_out);
 		if (buffer != NULL) {
-			preview_set_outaddr(prev, buffer->isp_addr);
+			preview_set_outaddr(prev, buffer->dma);
 			restart = 1;
 		}
 		pipe->state |= ISP_PIPELINE_IDLE_OUTPUT;
@@ -1577,10 +1577,10 @@
 	struct isp_prev_device *prev = &video->isp->isp_prev;
 
 	if (video->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
-		preview_set_inaddr(prev, buffer->isp_addr);
+		preview_set_inaddr(prev, buffer->dma);
 
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		preview_set_outaddr(prev, buffer->isp_addr);
+		preview_set_outaddr(prev, buffer->dma);
 
 	return 0;
 }
diff --git a/drivers/media/platform/omap3isp/ispqueue.c b/drivers/media/platform/omap3isp/ispqueue.c
deleted file mode 100644
index a5e6585..0000000
--- a/drivers/media/platform/omap3isp/ispqueue.c
+++ /dev/null
@@ -1,1161 +0,0 @@
-/*
- * ispqueue.c
- *
- * TI OMAP3 ISP - Video buffers queue handling
- *
- * Copyright (C) 2010 Nokia Corporation
- *
- * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *	     Sakari Ailus <sakari.ailus@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- */
-
-#include <asm/cacheflush.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/poll.h>
-#include <linux/scatterlist.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-
-#include "ispqueue.h"
-
-/* -----------------------------------------------------------------------------
- * Video buffers management
- */
-
-/*
- * isp_video_buffer_cache_sync - Keep the buffers coherent between CPU and ISP
- *
- * The typical operation required here is Cache Invalidation across
- * the (user space) buffer address range. And this _must_ be done
- * at QBUF stage (and *only* at QBUF).
- *
- * We try to use optimal cache invalidation function:
- * - dmac_map_area:
- *    - used when the number of pages are _low_.
- *    - it becomes quite slow as the number of pages increase.
- *       - for 648x492 viewfinder (150 pages) it takes 1.3 ms.
- *       - for 5 Mpix buffer (2491 pages) it takes between 25-50 ms.
- *
- * - flush_cache_all:
- *    - used when the number of pages are _high_.
- *    - time taken in the range of 500-900 us.
- *    - has a higher penalty but, as whole dcache + icache is invalidated
- */
-/*
- * FIXME: dmac_inv_range crashes randomly on the user space buffer
- *        address. Fall back to flush_cache_all for now.
- */
-#define ISP_CACHE_FLUSH_PAGES_MAX       0
-
-static void isp_video_buffer_cache_sync(struct isp_video_buffer *buf)
-{
-	if (buf->skip_cache)
-		return;
-
-	if (buf->vbuf.m.userptr == 0 || buf->npages == 0 ||
-	    buf->npages > ISP_CACHE_FLUSH_PAGES_MAX)
-		flush_cache_all();
-	else {
-		dmac_map_area((void *)buf->vbuf.m.userptr, buf->vbuf.length,
-			      DMA_FROM_DEVICE);
-		outer_inv_range(buf->vbuf.m.userptr,
-				buf->vbuf.m.userptr + buf->vbuf.length);
-	}
-}
-
-/*
- * isp_video_buffer_lock_vma - Prevent VMAs from being unmapped
- *
- * Lock the VMAs underlying the given buffer into memory. This avoids the
- * userspace buffer mapping from being swapped out, making VIPT cache handling
- * easier.
- *
- * Note that the pages will not be freed as the buffers have been locked to
- * memory using by a call to get_user_pages(), but the userspace mapping could
- * still disappear if the VMAs are not locked. This is caused by the memory
- * management code trying to be as lock-less as possible, which results in the
- * userspace mapping manager not finding out that the pages are locked under
- * some conditions.
- */
-static int isp_video_buffer_lock_vma(struct isp_video_buffer *buf, int lock)
-{
-	struct vm_area_struct *vma;
-	unsigned long start;
-	unsigned long end;
-	int ret = 0;
-
-	if (buf->vbuf.memory == V4L2_MEMORY_MMAP)
-		return 0;
-
-	/* We can be called from workqueue context if the current task dies to
-	 * unlock the VMAs. In that case there's no current memory management
-	 * context so unlocking can't be performed, but the VMAs have been or
-	 * are getting destroyed anyway so it doesn't really matter.
-	 */
-	if (!current || !current->mm)
-		return lock ? -EINVAL : 0;
-
-	start = buf->vbuf.m.userptr;
-	end = buf->vbuf.m.userptr + buf->vbuf.length - 1;
-
-	down_write(&current->mm->mmap_sem);
-	spin_lock(&current->mm->page_table_lock);
-
-	do {
-		vma = find_vma(current->mm, start);
-		if (vma == NULL) {
-			ret = -EFAULT;
-			goto out;
-		}
-
-		if (lock)
-			vma->vm_flags |= VM_LOCKED;
-		else
-			vma->vm_flags &= ~VM_LOCKED;
-
-		start = vma->vm_end + 1;
-	} while (vma->vm_end < end);
-
-	if (lock)
-		buf->vm_flags |= VM_LOCKED;
-	else
-		buf->vm_flags &= ~VM_LOCKED;
-
-out:
-	spin_unlock(&current->mm->page_table_lock);
-	up_write(&current->mm->mmap_sem);
-	return ret;
-}
-
-/*
- * isp_video_buffer_sglist_kernel - Build a scatter list for a vmalloc'ed buffer
- *
- * Iterate over the vmalloc'ed area and create a scatter list entry for every
- * page.
- */
-static int isp_video_buffer_sglist_kernel(struct isp_video_buffer *buf)
-{
-	struct scatterlist *sglist;
-	unsigned int npages;
-	unsigned int i;
-	void *addr;
-
-	addr = buf->vaddr;
-	npages = PAGE_ALIGN(buf->vbuf.length) >> PAGE_SHIFT;
-
-	sglist = vmalloc(npages * sizeof(*sglist));
-	if (sglist == NULL)
-		return -ENOMEM;
-
-	sg_init_table(sglist, npages);
-
-	for (i = 0; i < npages; ++i, addr += PAGE_SIZE) {
-		struct page *page = vmalloc_to_page(addr);
-
-		if (page == NULL || PageHighMem(page)) {
-			vfree(sglist);
-			return -EINVAL;
-		}
-
-		sg_set_page(&sglist[i], page, PAGE_SIZE, 0);
-	}
-
-	buf->sglen = npages;
-	buf->sglist = sglist;
-
-	return 0;
-}
-
-/*
- * isp_video_buffer_sglist_user - Build a scatter list for a userspace buffer
- *
- * Walk the buffer pages list and create a 1:1 mapping to a scatter list.
- */
-static int isp_video_buffer_sglist_user(struct isp_video_buffer *buf)
-{
-	struct scatterlist *sglist;
-	unsigned int offset = buf->offset;
-	unsigned int i;
-
-	sglist = vmalloc(buf->npages * sizeof(*sglist));
-	if (sglist == NULL)
-		return -ENOMEM;
-
-	sg_init_table(sglist, buf->npages);
-
-	for (i = 0; i < buf->npages; ++i) {
-		if (PageHighMem(buf->pages[i])) {
-			vfree(sglist);
-			return -EINVAL;
-		}
-
-		sg_set_page(&sglist[i], buf->pages[i], PAGE_SIZE - offset,
-			    offset);
-		offset = 0;
-	}
-
-	buf->sglen = buf->npages;
-	buf->sglist = sglist;
-
-	return 0;
-}
-
-/*
- * isp_video_buffer_sglist_pfnmap - Build a scatter list for a VM_PFNMAP buffer
- *
- * Create a scatter list of physically contiguous pages starting at the buffer
- * memory physical address.
- */
-static int isp_video_buffer_sglist_pfnmap(struct isp_video_buffer *buf)
-{
-	struct scatterlist *sglist;
-	unsigned int offset = buf->offset;
-	unsigned long pfn = buf->paddr >> PAGE_SHIFT;
-	unsigned int i;
-
-	sglist = vmalloc(buf->npages * sizeof(*sglist));
-	if (sglist == NULL)
-		return -ENOMEM;
-
-	sg_init_table(sglist, buf->npages);
-
-	for (i = 0; i < buf->npages; ++i, ++pfn) {
-		sg_set_page(&sglist[i], pfn_to_page(pfn), PAGE_SIZE - offset,
-			    offset);
-		/* PFNMAP buffers will not get DMA-mapped, set the DMA address
-		 * manually.
-		 */
-		sg_dma_address(&sglist[i]) = (pfn << PAGE_SHIFT) + offset;
-		offset = 0;
-	}
-
-	buf->sglen = buf->npages;
-	buf->sglist = sglist;
-
-	return 0;
-}
-
-/*
- * isp_video_buffer_cleanup - Release pages for a userspace VMA.
- *
- * Release pages locked by a call isp_video_buffer_prepare_user and free the
- * pages table.
- */
-static void isp_video_buffer_cleanup(struct isp_video_buffer *buf)
-{
-	enum dma_data_direction direction;
-	unsigned int i;
-
-	if (buf->queue->ops->buffer_cleanup)
-		buf->queue->ops->buffer_cleanup(buf);
-
-	if (!(buf->vm_flags & VM_PFNMAP)) {
-		direction = buf->vbuf.type == V4L2_BUF_TYPE_VIDEO_CAPTURE
-			  ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-		dma_unmap_sg(buf->queue->dev, buf->sglist, buf->sglen,
-			     direction);
-	}
-
-	vfree(buf->sglist);
-	buf->sglist = NULL;
-	buf->sglen = 0;
-
-	if (buf->pages != NULL) {
-		isp_video_buffer_lock_vma(buf, 0);
-
-		for (i = 0; i < buf->npages; ++i)
-			page_cache_release(buf->pages[i]);
-
-		vfree(buf->pages);
-		buf->pages = NULL;
-	}
-
-	buf->npages = 0;
-	buf->skip_cache = false;
-}
-
-/*
- * isp_video_buffer_prepare_user - Pin userspace VMA pages to memory.
- *
- * This function creates a list of pages for a userspace VMA. The number of
- * pages is first computed based on the buffer size, and pages are then
- * retrieved by a call to get_user_pages.
- *
- * Pages are pinned to memory by get_user_pages, making them available for DMA
- * transfers. However, due to memory management optimization, it seems the
- * get_user_pages doesn't guarantee that the pinned pages will not be written
- * to swap and removed from the userspace mapping(s). When this happens, a page
- * fault can be generated when accessing those unmapped pages.
- *
- * If the fault is triggered by a page table walk caused by VIPT cache
- * management operations, the page fault handler might oops if the MM semaphore
- * is held, as it can't handle kernel page faults in that case. To fix that, a
- * fixup entry needs to be added to the cache management code, or the userspace
- * VMA must be locked to avoid removing pages from the userspace mapping in the
- * first place.
- *
- * If the number of pages retrieved is smaller than the number required by the
- * buffer size, the function returns -EFAULT.
- */
-static int isp_video_buffer_prepare_user(struct isp_video_buffer *buf)
-{
-	unsigned long data;
-	unsigned int first;
-	unsigned int last;
-	int ret;
-
-	data = buf->vbuf.m.userptr;
-	first = (data & PAGE_MASK) >> PAGE_SHIFT;
-	last = ((data + buf->vbuf.length - 1) & PAGE_MASK) >> PAGE_SHIFT;
-
-	buf->offset = data & ~PAGE_MASK;
-	buf->npages = last - first + 1;
-	buf->pages = vmalloc(buf->npages * sizeof(buf->pages[0]));
-	if (buf->pages == NULL)
-		return -ENOMEM;
-
-	down_read(&current->mm->mmap_sem);
-	ret = get_user_pages(current, current->mm, data & PAGE_MASK,
-			     buf->npages,
-			     buf->vbuf.type == V4L2_BUF_TYPE_VIDEO_CAPTURE, 0,
-			     buf->pages, NULL);
-	up_read(&current->mm->mmap_sem);
-
-	if (ret != buf->npages) {
-		buf->npages = ret < 0 ? 0 : ret;
-		isp_video_buffer_cleanup(buf);
-		return -EFAULT;
-	}
-
-	ret = isp_video_buffer_lock_vma(buf, 1);
-	if (ret < 0)
-		isp_video_buffer_cleanup(buf);
-
-	return ret;
-}
-
-/*
- * isp_video_buffer_prepare_pfnmap - Validate a VM_PFNMAP userspace buffer
- *
- * Userspace VM_PFNMAP buffers are supported only if they are contiguous in
- * memory and if they span a single VMA.
- *
- * Return 0 if the buffer is valid, or -EFAULT otherwise.
- */
-static int isp_video_buffer_prepare_pfnmap(struct isp_video_buffer *buf)
-{
-	struct vm_area_struct *vma;
-	unsigned long prev_pfn;
-	unsigned long this_pfn;
-	unsigned long start;
-	unsigned long end;
-	dma_addr_t pa = 0;
-	int ret = -EFAULT;
-
-	start = buf->vbuf.m.userptr;
-	end = buf->vbuf.m.userptr + buf->vbuf.length - 1;
-
-	buf->offset = start & ~PAGE_MASK;
-	buf->npages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
-	buf->pages = NULL;
-
-	down_read(&current->mm->mmap_sem);
-	vma = find_vma(current->mm, start);
-	if (vma == NULL || vma->vm_end < end)
-		goto done;
-
-	for (prev_pfn = 0; start <= end; start += PAGE_SIZE) {
-		ret = follow_pfn(vma, start, &this_pfn);
-		if (ret)
-			goto done;
-
-		if (prev_pfn == 0)
-			pa = this_pfn << PAGE_SHIFT;
-		else if (this_pfn != prev_pfn + 1) {
-			ret = -EFAULT;
-			goto done;
-		}
-
-		prev_pfn = this_pfn;
-	}
-
-	buf->paddr = pa + buf->offset;
-	ret = 0;
-
-done:
-	up_read(&current->mm->mmap_sem);
-	return ret;
-}
-
-/*
- * isp_video_buffer_prepare_vm_flags - Get VMA flags for a userspace address
- *
- * This function locates the VMAs for the buffer's userspace address and checks
- * that their flags match. The only flag that we need to care for at the moment
- * is VM_PFNMAP.
- *
- * The buffer vm_flags field is set to the first VMA flags.
- *
- * Return -EFAULT if no VMA can be found for part of the buffer, or if the VMAs
- * have incompatible flags.
- */
-static int isp_video_buffer_prepare_vm_flags(struct isp_video_buffer *buf)
-{
-	struct vm_area_struct *vma;
-	pgprot_t uninitialized_var(vm_page_prot);
-	unsigned long start;
-	unsigned long end;
-	int ret = -EFAULT;
-
-	start = buf->vbuf.m.userptr;
-	end = buf->vbuf.m.userptr + buf->vbuf.length - 1;
-
-	down_read(&current->mm->mmap_sem);
-
-	do {
-		vma = find_vma(current->mm, start);
-		if (vma == NULL)
-			goto done;
-
-		if (start == buf->vbuf.m.userptr) {
-			buf->vm_flags = vma->vm_flags;
-			vm_page_prot = vma->vm_page_prot;
-		}
-
-		if ((buf->vm_flags ^ vma->vm_flags) & VM_PFNMAP)
-			goto done;
-
-		if (vm_page_prot != vma->vm_page_prot)
-			goto done;
-
-		start = vma->vm_end + 1;
-	} while (vma->vm_end < end);
-
-	/* Skip cache management to enhance performances for non-cached or
-	 * write-combining buffers.
-	 */
-	if (vm_page_prot == pgprot_noncached(vm_page_prot) ||
-	    vm_page_prot == pgprot_writecombine(vm_page_prot))
-		buf->skip_cache = true;
-
-	ret = 0;
-
-done:
-	up_read(&current->mm->mmap_sem);
-	return ret;
-}
-
-/*
- * isp_video_buffer_prepare - Make a buffer ready for operation
- *
- * Preparing a buffer involves:
- *
- * - validating VMAs (userspace buffers only)
- * - locking pages and VMAs into memory (userspace buffers only)
- * - building page and scatter-gather lists
- * - mapping buffers for DMA operation
- * - performing driver-specific preparation
- *
- * The function must be called in userspace context with a valid mm context
- * (this excludes cleanup paths such as sys_close when the userspace process
- * segfaults).
- */
-static int isp_video_buffer_prepare(struct isp_video_buffer *buf)
-{
-	enum dma_data_direction direction;
-	int ret;
-
-	switch (buf->vbuf.memory) {
-	case V4L2_MEMORY_MMAP:
-		ret = isp_video_buffer_sglist_kernel(buf);
-		break;
-
-	case V4L2_MEMORY_USERPTR:
-		ret = isp_video_buffer_prepare_vm_flags(buf);
-		if (ret < 0)
-			return ret;
-
-		if (buf->vm_flags & VM_PFNMAP) {
-			ret = isp_video_buffer_prepare_pfnmap(buf);
-			if (ret < 0)
-				return ret;
-
-			ret = isp_video_buffer_sglist_pfnmap(buf);
-		} else {
-			ret = isp_video_buffer_prepare_user(buf);
-			if (ret < 0)
-				return ret;
-
-			ret = isp_video_buffer_sglist_user(buf);
-		}
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	if (ret < 0)
-		goto done;
-
-	if (!(buf->vm_flags & VM_PFNMAP)) {
-		direction = buf->vbuf.type == V4L2_BUF_TYPE_VIDEO_CAPTURE
-			  ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-		ret = dma_map_sg(buf->queue->dev, buf->sglist, buf->sglen,
-				 direction);
-		if (ret != buf->sglen) {
-			ret = -EFAULT;
-			goto done;
-		}
-	}
-
-	if (buf->queue->ops->buffer_prepare)
-		ret = buf->queue->ops->buffer_prepare(buf);
-
-done:
-	if (ret < 0) {
-		isp_video_buffer_cleanup(buf);
-		return ret;
-	}
-
-	return ret;
-}
-
-/*
- * isp_video_queue_query - Query the status of a given buffer
- *
- * Locking: must be called with the queue lock held.
- */
-static void isp_video_buffer_query(struct isp_video_buffer *buf,
-				   struct v4l2_buffer *vbuf)
-{
-	memcpy(vbuf, &buf->vbuf, sizeof(*vbuf));
-
-	if (buf->vma_use_count)
-		vbuf->flags |= V4L2_BUF_FLAG_MAPPED;
-
-	switch (buf->state) {
-	case ISP_BUF_STATE_ERROR:
-		vbuf->flags |= V4L2_BUF_FLAG_ERROR;
-		/* Fallthrough */
-	case ISP_BUF_STATE_DONE:
-		vbuf->flags |= V4L2_BUF_FLAG_DONE;
-		break;
-	case ISP_BUF_STATE_QUEUED:
-	case ISP_BUF_STATE_ACTIVE:
-		vbuf->flags |= V4L2_BUF_FLAG_QUEUED;
-		break;
-	case ISP_BUF_STATE_IDLE:
-	default:
-		break;
-	}
-}
-
-/*
- * isp_video_buffer_wait - Wait for a buffer to be ready
- *
- * In non-blocking mode, return immediately with 0 if the buffer is ready or
- * -EAGAIN if the buffer is in the QUEUED or ACTIVE state.
- *
- * In blocking mode, wait (interruptibly but with no timeout) on the buffer wait
- * queue using the same condition.
- */
-static int isp_video_buffer_wait(struct isp_video_buffer *buf, int nonblocking)
-{
-	if (nonblocking) {
-		return (buf->state != ISP_BUF_STATE_QUEUED &&
-			buf->state != ISP_BUF_STATE_ACTIVE)
-			? 0 : -EAGAIN;
-	}
-
-	return wait_event_interruptible(buf->wait,
-		buf->state != ISP_BUF_STATE_QUEUED &&
-		buf->state != ISP_BUF_STATE_ACTIVE);
-}
-
-/* -----------------------------------------------------------------------------
- * Queue management
- */
-
-/*
- * isp_video_queue_free - Free video buffers memory
- *
- * Buffers can only be freed if the queue isn't streaming and if no buffer is
- * mapped to userspace. Return -EBUSY if those conditions aren't satisfied.
- *
- * This function must be called with the queue lock held.
- */
-static int isp_video_queue_free(struct isp_video_queue *queue)
-{
-	unsigned int i;
-
-	if (queue->streaming)
-		return -EBUSY;
-
-	for (i = 0; i < queue->count; ++i) {
-		if (queue->buffers[i]->vma_use_count != 0)
-			return -EBUSY;
-	}
-
-	for (i = 0; i < queue->count; ++i) {
-		struct isp_video_buffer *buf = queue->buffers[i];
-
-		isp_video_buffer_cleanup(buf);
-
-		vfree(buf->vaddr);
-		buf->vaddr = NULL;
-
-		kfree(buf);
-		queue->buffers[i] = NULL;
-	}
-
-	INIT_LIST_HEAD(&queue->queue);
-	queue->count = 0;
-	return 0;
-}
-
-/*
- * isp_video_queue_alloc - Allocate video buffers memory
- *
- * This function must be called with the queue lock held.
- */
-static int isp_video_queue_alloc(struct isp_video_queue *queue,
-				 unsigned int nbuffers,
-				 unsigned int size, enum v4l2_memory memory)
-{
-	struct isp_video_buffer *buf;
-	unsigned int i;
-	void *mem;
-	int ret;
-
-	/* Start by freeing the buffers. */
-	ret = isp_video_queue_free(queue);
-	if (ret < 0)
-		return ret;
-
-	/* Bail out if no buffers should be allocated. */
-	if (nbuffers == 0)
-		return 0;
-
-	/* Initialize the allocated buffers. */
-	for (i = 0; i < nbuffers; ++i) {
-		buf = kzalloc(queue->bufsize, GFP_KERNEL);
-		if (buf == NULL)
-			break;
-
-		if (memory == V4L2_MEMORY_MMAP) {
-			/* Allocate video buffers memory for mmap mode. Align
-			 * the size to the page size.
-			 */
-			mem = vmalloc_32_user(PAGE_ALIGN(size));
-			if (mem == NULL) {
-				kfree(buf);
-				break;
-			}
-
-			buf->vbuf.m.offset = i * PAGE_ALIGN(size);
-			buf->vaddr = mem;
-		}
-
-		buf->vbuf.index = i;
-		buf->vbuf.length = size;
-		buf->vbuf.type = queue->type;
-		buf->vbuf.flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		buf->vbuf.field = V4L2_FIELD_NONE;
-		buf->vbuf.memory = memory;
-
-		buf->queue = queue;
-		init_waitqueue_head(&buf->wait);
-
-		queue->buffers[i] = buf;
-	}
-
-	if (i == 0)
-		return -ENOMEM;
-
-	queue->count = i;
-	return nbuffers;
-}
-
-/**
- * omap3isp_video_queue_cleanup - Clean up the video buffers queue
- * @queue: Video buffers queue
- *
- * Free all allocated resources and clean up the video buffers queue. The queue
- * must not be busy (no ongoing video stream) and buffers must have been
- * unmapped.
- *
- * Return 0 on success or -EBUSY if the queue is busy or buffers haven't been
- * unmapped.
- */
-int omap3isp_video_queue_cleanup(struct isp_video_queue *queue)
-{
-	return isp_video_queue_free(queue);
-}
-
-/**
- * omap3isp_video_queue_init - Initialize the video buffers queue
- * @queue: Video buffers queue
- * @type: V4L2 buffer type (capture or output)
- * @ops: Driver-specific queue operations
- * @dev: Device used for DMA operations
- * @bufsize: Size of the driver-specific buffer structure
- *
- * Initialize the video buffers queue with the supplied parameters.
- *
- * The queue type must be one of V4L2_BUF_TYPE_VIDEO_CAPTURE or
- * V4L2_BUF_TYPE_VIDEO_OUTPUT. Other buffer types are not supported yet.
- *
- * Buffer objects will be allocated using the given buffer size to allow room
- * for driver-specific fields. Driver-specific buffer structures must start
- * with a struct isp_video_buffer field. Drivers with no driver-specific buffer
- * structure must pass the size of the isp_video_buffer structure in the bufsize
- * parameter.
- *
- * Return 0 on success.
- */
-int omap3isp_video_queue_init(struct isp_video_queue *queue,
-			      enum v4l2_buf_type type,
-			      const struct isp_video_queue_operations *ops,
-			      struct device *dev, unsigned int bufsize)
-{
-	INIT_LIST_HEAD(&queue->queue);
-	mutex_init(&queue->lock);
-	spin_lock_init(&queue->irqlock);
-
-	queue->type = type;
-	queue->ops = ops;
-	queue->dev = dev;
-	queue->bufsize = bufsize;
-
-	return 0;
-}
-
-/* -----------------------------------------------------------------------------
- * V4L2 operations
- */
-
-/**
- * omap3isp_video_queue_reqbufs - Allocate video buffers memory
- *
- * This function is intended to be used as a VIDIOC_REQBUFS ioctl handler. It
- * allocated video buffer objects and, for MMAP buffers, buffer memory.
- *
- * If the number of buffers is 0, all buffers are freed and the function returns
- * without performing any allocation.
- *
- * If the number of buffers is not 0, currently allocated buffers (if any) are
- * freed and the requested number of buffers are allocated. Depending on
- * driver-specific requirements and on memory availability, a number of buffer
- * smaller or bigger than requested can be allocated. This isn't considered as
- * an error.
- *
- * Return 0 on success or one of the following error codes:
- *
- * -EINVAL if the buffer type or index are invalid
- * -EBUSY if the queue is busy (streaming or buffers mapped)
- * -ENOMEM if the buffers can't be allocated due to an out-of-memory condition
- */
-int omap3isp_video_queue_reqbufs(struct isp_video_queue *queue,
-				 struct v4l2_requestbuffers *rb)
-{
-	unsigned int nbuffers = rb->count;
-	unsigned int size;
-	int ret;
-
-	if (rb->type != queue->type)
-		return -EINVAL;
-
-	queue->ops->queue_prepare(queue, &nbuffers, &size);
-	if (size == 0)
-		return -EINVAL;
-
-	nbuffers = min_t(unsigned int, nbuffers, ISP_VIDEO_MAX_BUFFERS);
-
-	mutex_lock(&queue->lock);
-
-	ret = isp_video_queue_alloc(queue, nbuffers, size, rb->memory);
-	if (ret < 0)
-		goto done;
-
-	rb->count = ret;
-	ret = 0;
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_querybuf - Query the status of a buffer in a queue
- *
- * This function is intended to be used as a VIDIOC_QUERYBUF ioctl handler. It
- * returns the status of a given video buffer.
- *
- * Return 0 on success or -EINVAL if the buffer type or index are invalid.
- */
-int omap3isp_video_queue_querybuf(struct isp_video_queue *queue,
-				  struct v4l2_buffer *vbuf)
-{
-	struct isp_video_buffer *buf;
-	int ret = 0;
-
-	if (vbuf->type != queue->type)
-		return -EINVAL;
-
-	mutex_lock(&queue->lock);
-
-	if (vbuf->index >= queue->count) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	buf = queue->buffers[vbuf->index];
-	isp_video_buffer_query(buf, vbuf);
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_qbuf - Queue a buffer
- *
- * This function is intended to be used as a VIDIOC_QBUF ioctl handler.
- *
- * The v4l2_buffer structure passed from userspace is first sanity tested. If
- * sane, the buffer is then processed and added to the main queue and, if the
- * queue is streaming, to the IRQ queue.
- *
- * Before being enqueued, USERPTR buffers are checked for address changes. If
- * the buffer has a different userspace address, the old memory area is unlocked
- * and the new memory area is locked.
- */
-int omap3isp_video_queue_qbuf(struct isp_video_queue *queue,
-			      struct v4l2_buffer *vbuf)
-{
-	struct isp_video_buffer *buf;
-	unsigned long flags;
-	int ret = -EINVAL;
-
-	if (vbuf->type != queue->type)
-		goto done;
-
-	mutex_lock(&queue->lock);
-
-	if (vbuf->index >= queue->count)
-		goto done;
-
-	buf = queue->buffers[vbuf->index];
-
-	if (vbuf->memory != buf->vbuf.memory)
-		goto done;
-
-	if (buf->state != ISP_BUF_STATE_IDLE)
-		goto done;
-
-	if (vbuf->memory == V4L2_MEMORY_USERPTR &&
-	    vbuf->length < buf->vbuf.length)
-		goto done;
-
-	if (vbuf->memory == V4L2_MEMORY_USERPTR &&
-	    vbuf->m.userptr != buf->vbuf.m.userptr) {
-		isp_video_buffer_cleanup(buf);
-		buf->vbuf.m.userptr = vbuf->m.userptr;
-		buf->prepared = 0;
-	}
-
-	if (!buf->prepared) {
-		ret = isp_video_buffer_prepare(buf);
-		if (ret < 0)
-			goto done;
-		buf->prepared = 1;
-	}
-
-	isp_video_buffer_cache_sync(buf);
-
-	buf->state = ISP_BUF_STATE_QUEUED;
-	list_add_tail(&buf->stream, &queue->queue);
-
-	if (queue->streaming) {
-		spin_lock_irqsave(&queue->irqlock, flags);
-		queue->ops->buffer_queue(buf);
-		spin_unlock_irqrestore(&queue->irqlock, flags);
-	}
-
-	ret = 0;
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_dqbuf - Dequeue a buffer
- *
- * This function is intended to be used as a VIDIOC_DQBUF ioctl handler.
- *
- * Wait until a buffer is ready to be dequeued, remove it from the queue and
- * copy its information to the v4l2_buffer structure.
- *
- * If the nonblocking argument is not zero and no buffer is ready, return
- * -EAGAIN immediately instead of waiting.
- *
- * If no buffer has been enqueued, or if the requested buffer type doesn't match
- * the queue type, return -EINVAL.
- */
-int omap3isp_video_queue_dqbuf(struct isp_video_queue *queue,
-			       struct v4l2_buffer *vbuf, int nonblocking)
-{
-	struct isp_video_buffer *buf;
-	int ret;
-
-	if (vbuf->type != queue->type)
-		return -EINVAL;
-
-	mutex_lock(&queue->lock);
-
-	if (list_empty(&queue->queue)) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	buf = list_first_entry(&queue->queue, struct isp_video_buffer, stream);
-	ret = isp_video_buffer_wait(buf, nonblocking);
-	if (ret < 0)
-		goto done;
-
-	list_del(&buf->stream);
-
-	isp_video_buffer_query(buf, vbuf);
-	buf->state = ISP_BUF_STATE_IDLE;
-	vbuf->flags &= ~V4L2_BUF_FLAG_QUEUED;
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_streamon - Start streaming
- *
- * This function is intended to be used as a VIDIOC_STREAMON ioctl handler. It
- * starts streaming on the queue and calls the buffer_queue operation for all
- * queued buffers.
- *
- * Return 0 on success.
- */
-int omap3isp_video_queue_streamon(struct isp_video_queue *queue)
-{
-	struct isp_video_buffer *buf;
-	unsigned long flags;
-
-	mutex_lock(&queue->lock);
-
-	if (queue->streaming)
-		goto done;
-
-	queue->streaming = 1;
-
-	spin_lock_irqsave(&queue->irqlock, flags);
-	list_for_each_entry(buf, &queue->queue, stream)
-		queue->ops->buffer_queue(buf);
-	spin_unlock_irqrestore(&queue->irqlock, flags);
-
-done:
-	mutex_unlock(&queue->lock);
-	return 0;
-}
-
-/**
- * omap3isp_video_queue_streamoff - Stop streaming
- *
- * This function is intended to be used as a VIDIOC_STREAMOFF ioctl handler. It
- * stops streaming on the queue and wakes up all the buffers.
- *
- * Drivers must stop the hardware and synchronize with interrupt handlers and/or
- * delayed works before calling this function to make sure no buffer will be
- * touched by the driver and/or hardware.
- */
-void omap3isp_video_queue_streamoff(struct isp_video_queue *queue)
-{
-	struct isp_video_buffer *buf;
-	unsigned long flags;
-	unsigned int i;
-
-	mutex_lock(&queue->lock);
-
-	if (!queue->streaming)
-		goto done;
-
-	queue->streaming = 0;
-
-	spin_lock_irqsave(&queue->irqlock, flags);
-	for (i = 0; i < queue->count; ++i) {
-		buf = queue->buffers[i];
-
-		if (buf->state == ISP_BUF_STATE_ACTIVE)
-			wake_up(&buf->wait);
-
-		buf->state = ISP_BUF_STATE_IDLE;
-	}
-	spin_unlock_irqrestore(&queue->irqlock, flags);
-
-	INIT_LIST_HEAD(&queue->queue);
-
-done:
-	mutex_unlock(&queue->lock);
-}
-
-/**
- * omap3isp_video_queue_discard_done - Discard all buffers marked as DONE
- *
- * This function is intended to be used with suspend/resume operations. It
- * discards all 'done' buffers as they would be too old to be requested after
- * resume.
- *
- * Drivers must stop the hardware and synchronize with interrupt handlers and/or
- * delayed works before calling this function to make sure no buffer will be
- * touched by the driver and/or hardware.
- */
-void omap3isp_video_queue_discard_done(struct isp_video_queue *queue)
-{
-	struct isp_video_buffer *buf;
-	unsigned int i;
-
-	mutex_lock(&queue->lock);
-
-	if (!queue->streaming)
-		goto done;
-
-	for (i = 0; i < queue->count; ++i) {
-		buf = queue->buffers[i];
-
-		if (buf->state == ISP_BUF_STATE_DONE)
-			buf->state = ISP_BUF_STATE_ERROR;
-	}
-
-done:
-	mutex_unlock(&queue->lock);
-}
-
-static void isp_video_queue_vm_open(struct vm_area_struct *vma)
-{
-	struct isp_video_buffer *buf = vma->vm_private_data;
-
-	buf->vma_use_count++;
-}
-
-static void isp_video_queue_vm_close(struct vm_area_struct *vma)
-{
-	struct isp_video_buffer *buf = vma->vm_private_data;
-
-	buf->vma_use_count--;
-}
-
-static const struct vm_operations_struct isp_video_queue_vm_ops = {
-	.open = isp_video_queue_vm_open,
-	.close = isp_video_queue_vm_close,
-};
-
-/**
- * omap3isp_video_queue_mmap - Map buffers to userspace
- *
- * This function is intended to be used as an mmap() file operation handler. It
- * maps a buffer to userspace based on the VMA offset.
- *
- * Only buffers of memory type MMAP are supported.
- */
-int omap3isp_video_queue_mmap(struct isp_video_queue *queue,
-			 struct vm_area_struct *vma)
-{
-	struct isp_video_buffer *uninitialized_var(buf);
-	unsigned long size;
-	unsigned int i;
-	int ret = 0;
-
-	mutex_lock(&queue->lock);
-
-	for (i = 0; i < queue->count; ++i) {
-		buf = queue->buffers[i];
-		if ((buf->vbuf.m.offset >> PAGE_SHIFT) == vma->vm_pgoff)
-			break;
-	}
-
-	if (i == queue->count) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	size = vma->vm_end - vma->vm_start;
-
-	if (buf->vbuf.memory != V4L2_MEMORY_MMAP ||
-	    size != PAGE_ALIGN(buf->vbuf.length)) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	ret = remap_vmalloc_range(vma, buf->vaddr, 0);
-	if (ret < 0)
-		goto done;
-
-	vma->vm_ops = &isp_video_queue_vm_ops;
-	vma->vm_private_data = buf;
-	isp_video_queue_vm_open(vma);
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_poll - Poll video queue state
- *
- * This function is intended to be used as a poll() file operation handler. It
- * polls the state of the video buffer at the front of the queue and returns an
- * events mask.
- *
- * If no buffer is present at the front of the queue, POLLERR is returned.
- */
-unsigned int omap3isp_video_queue_poll(struct isp_video_queue *queue,
-				       struct file *file, poll_table *wait)
-{
-	struct isp_video_buffer *buf;
-	unsigned int mask = 0;
-
-	mutex_lock(&queue->lock);
-	if (list_empty(&queue->queue)) {
-		mask |= POLLERR;
-		goto done;
-	}
-	buf = list_first_entry(&queue->queue, struct isp_video_buffer, stream);
-
-	poll_wait(file, &buf->wait, wait);
-	if (buf->state == ISP_BUF_STATE_DONE ||
-	    buf->state == ISP_BUF_STATE_ERROR) {
-		if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-			mask |= POLLIN | POLLRDNORM;
-		else
-			mask |= POLLOUT | POLLWRNORM;
-	}
-
-done:
-	mutex_unlock(&queue->lock);
-	return mask;
-}
diff --git a/drivers/media/platform/omap3isp/ispqueue.h b/drivers/media/platform/omap3isp/ispqueue.h
deleted file mode 100644
index 3e048ad..0000000
--- a/drivers/media/platform/omap3isp/ispqueue.h
+++ /dev/null
@@ -1,188 +0,0 @@
-/*
- * ispqueue.h
- *
- * TI OMAP3 ISP - Video buffers queue handling
- *
- * Copyright (C) 2010 Nokia Corporation
- *
- * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *	     Sakari Ailus <sakari.ailus@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- */
-
-#ifndef OMAP3_ISP_QUEUE_H
-#define OMAP3_ISP_QUEUE_H
-
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/mm_types.h>
-#include <linux/mutex.h>
-#include <linux/videodev2.h>
-#include <linux/wait.h>
-
-struct isp_video_queue;
-struct page;
-struct scatterlist;
-
-#define ISP_VIDEO_MAX_BUFFERS		16
-
-/**
- * enum isp_video_buffer_state - ISP video buffer state
- * @ISP_BUF_STATE_IDLE:	The buffer is under userspace control (dequeued
- *	or not queued yet).
- * @ISP_BUF_STATE_QUEUED: The buffer has been queued but isn't used by the
- *	device yet.
- * @ISP_BUF_STATE_ACTIVE: The buffer is in use for an active video transfer.
- * @ISP_BUF_STATE_ERROR: The device is done with the buffer and an error
- *	occurred. For capture device the buffer likely contains corrupted data or
- *	no data at all.
- * @ISP_BUF_STATE_DONE: The device is done with the buffer and no error occurred.
- *	For capture devices the buffer contains valid data.
- */
-enum isp_video_buffer_state {
-	ISP_BUF_STATE_IDLE,
-	ISP_BUF_STATE_QUEUED,
-	ISP_BUF_STATE_ACTIVE,
-	ISP_BUF_STATE_ERROR,
-	ISP_BUF_STATE_DONE,
-};
-
-/**
- * struct isp_video_buffer - ISP video buffer
- * @vma_use_count: Number of times the buffer is mmap'ed to userspace
- * @stream: List head for insertion into main queue
- * @queue: ISP buffers queue this buffer belongs to
- * @prepared: Whether the buffer has been prepared
- * @skip_cache: Whether to skip cache management operations for this buffer
- * @vaddr: Memory virtual address (for kernel buffers)
- * @vm_flags: Buffer VMA flags (for userspace buffers)
- * @offset: Offset inside the first page (for userspace buffers)
- * @npages: Number of pages (for userspace buffers)
- * @pages: Pages table (for userspace non-VM_PFNMAP buffers)
- * @paddr: Memory physical address (for userspace VM_PFNMAP buffers)
- * @sglen: Number of elements in the scatter list (for non-VM_PFNMAP buffers)
- * @sglist: Scatter list (for non-VM_PFNMAP buffers)
- * @vbuf: V4L2 buffer
- * @irqlist: List head for insertion into IRQ queue
- * @state: Current buffer state
- * @wait: Wait queue to signal buffer completion
- */
-struct isp_video_buffer {
-	unsigned long vma_use_count;
-	struct list_head stream;
-	struct isp_video_queue *queue;
-	unsigned int prepared:1;
-	bool skip_cache;
-
-	/* For kernel buffers. */
-	void *vaddr;
-
-	/* For userspace buffers. */
-	vm_flags_t vm_flags;
-	unsigned long offset;
-	unsigned int npages;
-	struct page **pages;
-	dma_addr_t paddr;
-
-	/* For all buffers except VM_PFNMAP. */
-	unsigned int sglen;
-	struct scatterlist *sglist;
-
-	/* Touched by the interrupt handler. */
-	struct v4l2_buffer vbuf;
-	struct list_head irqlist;
-	enum isp_video_buffer_state state;
-	wait_queue_head_t wait;
-};
-
-#define to_isp_video_buffer(vb)	container_of(vb, struct isp_video_buffer, vb)
-
-/**
- * struct isp_video_queue_operations - Driver-specific operations
- * @queue_prepare: Called before allocating buffers. Drivers should clamp the
- *	number of buffers according to their requirements, and must return the
- *	buffer size in bytes.
- * @buffer_prepare: Called the first time a buffer is queued, or after changing
- *	the userspace memory address for a USERPTR buffer, with the queue lock
- *	held. Drivers should perform device-specific buffer preparation (such as
- *	mapping the buffer memory in an IOMMU). This operation is optional.
- * @buffer_queue: Called when a buffer is being added to the queue with the
- *	queue irqlock spinlock held.
- * @buffer_cleanup: Called before freeing buffers, or before changing the
- *	userspace memory address for a USERPTR buffer, with the queue lock held.
- *	Drivers must perform cleanup operations required to undo the
- *	buffer_prepare call. This operation is optional.
- */
-struct isp_video_queue_operations {
-	void (*queue_prepare)(struct isp_video_queue *queue,
-			      unsigned int *nbuffers, unsigned int *size);
-	int  (*buffer_prepare)(struct isp_video_buffer *buf);
-	void (*buffer_queue)(struct isp_video_buffer *buf);
-	void (*buffer_cleanup)(struct isp_video_buffer *buf);
-};
-
-/**
- * struct isp_video_queue - ISP video buffers queue
- * @type: Type of video buffers handled by this queue
- * @ops: Queue operations
- * @dev: Device used for DMA operations
- * @bufsize: Size of a driver-specific buffer object
- * @count: Number of currently allocated buffers
- * @buffers: ISP video buffers
- * @lock: Mutex to protect access to the buffers, main queue and state
- * @irqlock: Spinlock to protect access to the IRQ queue
- * @streaming: Queue state, indicates whether the queue is streaming
- * @queue: List of all queued buffers
- */
-struct isp_video_queue {
-	enum v4l2_buf_type type;
-	const struct isp_video_queue_operations *ops;
-	struct device *dev;
-	unsigned int bufsize;
-
-	unsigned int count;
-	struct isp_video_buffer *buffers[ISP_VIDEO_MAX_BUFFERS];
-	struct mutex lock;
-	spinlock_t irqlock;
-
-	unsigned int streaming:1;
-
-	struct list_head queue;
-};
-
-int omap3isp_video_queue_cleanup(struct isp_video_queue *queue);
-int omap3isp_video_queue_init(struct isp_video_queue *queue,
-			      enum v4l2_buf_type type,
-			      const struct isp_video_queue_operations *ops,
-			      struct device *dev, unsigned int bufsize);
-
-int omap3isp_video_queue_reqbufs(struct isp_video_queue *queue,
-				 struct v4l2_requestbuffers *rb);
-int omap3isp_video_queue_querybuf(struct isp_video_queue *queue,
-				  struct v4l2_buffer *vbuf);
-int omap3isp_video_queue_qbuf(struct isp_video_queue *queue,
-			      struct v4l2_buffer *vbuf);
-int omap3isp_video_queue_dqbuf(struct isp_video_queue *queue,
-			       struct v4l2_buffer *vbuf, int nonblocking);
-int omap3isp_video_queue_streamon(struct isp_video_queue *queue);
-void omap3isp_video_queue_streamoff(struct isp_video_queue *queue);
-void omap3isp_video_queue_discard_done(struct isp_video_queue *queue);
-int omap3isp_video_queue_mmap(struct isp_video_queue *queue,
-			      struct vm_area_struct *vma);
-unsigned int omap3isp_video_queue_poll(struct isp_video_queue *queue,
-				       struct file *file, poll_table *wait);
-
-#endif /* OMAP3_ISP_QUEUE_H */
diff --git a/drivers/media/platform/omap3isp/ispresizer.c b/drivers/media/platform/omap3isp/ispresizer.c
index 86369df..6f077c2 100644
--- a/drivers/media/platform/omap3isp/ispresizer.c
+++ b/drivers/media/platform/omap3isp/ispresizer.c
@@ -1040,7 +1040,7 @@
 	 */
 	buffer = omap3isp_video_buffer_next(&res->video_out);
 	if (buffer != NULL) {
-		resizer_set_outaddr(res, buffer->isp_addr);
+		resizer_set_outaddr(res, buffer->dma);
 		restart = 1;
 	}
 
@@ -1049,7 +1049,7 @@
 	if (res->input == RESIZER_INPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&res->video_in);
 		if (buffer != NULL)
-			resizer_set_inaddr(res, buffer->isp_addr);
+			resizer_set_inaddr(res, buffer->dma);
 		pipe->state |= ISP_PIPELINE_IDLE_INPUT;
 	}
 
@@ -1101,7 +1101,7 @@
 	struct isp_res_device *res = &video->isp->isp_res;
 
 	if (video->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
-		resizer_set_inaddr(res, buffer->isp_addr);
+		resizer_set_inaddr(res, buffer->dma);
 
 	/*
 	 * We now have a buffer queued on the output. Despite what the
@@ -1116,7 +1116,7 @@
 	 * continuous mode or when starting the stream.
 	 */
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		resizer_set_outaddr(res, buffer->isp_addr);
+		resizer_set_outaddr(res, buffer->dma);
 
 	return 0;
 }
diff --git a/drivers/media/platform/omap3isp/ispstat.c b/drivers/media/platform/omap3isp/ispstat.c
index 5707f85..e6cbc1e 100644
--- a/drivers/media/platform/omap3isp/ispstat.c
+++ b/drivers/media/platform/omap3isp/ispstat.c
@@ -26,13 +26,12 @@
  */
 
 #include <linux/dma-mapping.h>
-#include <linux/omap-iommu.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
 #include "isp.h"
 
-#define IS_COHERENT_BUF(stat)	((stat)->dma_ch >= 0)
+#define ISP_STAT_USES_DMAENGINE(stat)	((stat)->dma_ch >= 0)
 
 /*
  * MAGIC_SIZE must always be the greatest common divisor of
@@ -77,21 +76,10 @@
 					dma_addr_t, unsigned long, size_t,
 					enum dma_data_direction))
 {
-	struct device *dev = stat->isp->dev;
-	struct page *pg;
-	dma_addr_t dma_addr;
-	u32 offset;
-
-	/* Initial magic words */
-	pg = vmalloc_to_page(buf->virt_addr);
-	dma_addr = pfn_to_dma(dev, page_to_pfn(pg));
-	dma_sync(dev, dma_addr, 0, MAGIC_SIZE, dir);
-
-	/* Final magic words */
-	pg = vmalloc_to_page(buf->virt_addr + buf_size);
-	dma_addr = pfn_to_dma(dev, page_to_pfn(pg));
-	offset = ((u32)buf->virt_addr + buf_size) & ~PAGE_MASK;
-	dma_sync(dev, dma_addr, offset, MAGIC_SIZE, dir);
+	/* Sync the initial and final magic words. */
+	dma_sync(stat->isp->dev, buf->dma_addr, 0, MAGIC_SIZE, dir);
+	dma_sync(stat->isp->dev, buf->dma_addr + (buf_size & PAGE_MASK),
+		 buf_size & ~PAGE_MASK, MAGIC_SIZE, dir);
 }
 
 static void isp_stat_buf_sync_magic_for_device(struct ispstat *stat,
@@ -99,7 +87,7 @@
 					       u32 buf_size,
 					       enum dma_data_direction dir)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
 	__isp_stat_buf_sync_magic(stat, buf, buf_size, dir,
@@ -111,7 +99,7 @@
 					    u32 buf_size,
 					    enum dma_data_direction dir)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
 	__isp_stat_buf_sync_magic(stat, buf, buf_size, dir,
@@ -180,21 +168,21 @@
 static void isp_stat_buf_sync_for_device(struct ispstat *stat,
 					 struct ispstat_buffer *buf)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
-	dma_sync_sg_for_device(stat->isp->dev, buf->iovm->sgt->sgl,
-			       buf->iovm->sgt->nents, DMA_FROM_DEVICE);
+	dma_sync_sg_for_device(stat->isp->dev, buf->sgt.sgl,
+			       buf->sgt.nents, DMA_FROM_DEVICE);
 }
 
 static void isp_stat_buf_sync_for_cpu(struct ispstat *stat,
 				      struct ispstat_buffer *buf)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
-	dma_sync_sg_for_cpu(stat->isp->dev, buf->iovm->sgt->sgl,
-			    buf->iovm->sgt->nents, DMA_FROM_DEVICE);
+	dma_sync_sg_for_cpu(stat->isp->dev, buf->sgt.sgl,
+			    buf->sgt.nents, DMA_FROM_DEVICE);
 }
 
 static void isp_stat_buf_clear(struct ispstat *stat)
@@ -354,29 +342,21 @@
 
 static void isp_stat_bufs_free(struct ispstat *stat)
 {
-	struct isp_device *isp = stat->isp;
-	int i;
+	struct device *dev = ISP_STAT_USES_DMAENGINE(stat)
+			   ? NULL : stat->isp->dev;
+	unsigned int i;
 
 	for (i = 0; i < STAT_MAX_BUFS; i++) {
 		struct ispstat_buffer *buf = &stat->buf[i];
 
-		if (!IS_COHERENT_BUF(stat)) {
-			if (IS_ERR_OR_NULL((void *)buf->iommu_addr))
-				continue;
-			if (buf->iovm)
-				dma_unmap_sg(isp->dev, buf->iovm->sgt->sgl,
-					     buf->iovm->sgt->nents,
-					     DMA_FROM_DEVICE);
-			omap_iommu_vfree(isp->domain, isp->dev,
-							buf->iommu_addr);
-		} else {
-			if (!buf->virt_addr)
-				continue;
-			dma_free_coherent(stat->isp->dev, stat->buf_alloc_size,
-					  buf->virt_addr, buf->dma_addr);
-		}
-		buf->iommu_addr = 0;
-		buf->iovm = NULL;
+		if (!buf->virt_addr)
+			continue;
+
+		sg_free_table(&buf->sgt);
+
+		dma_free_coherent(dev, stat->buf_alloc_size, buf->virt_addr,
+				  buf->dma_addr);
+
 		buf->dma_addr = 0;
 		buf->virt_addr = NULL;
 		buf->empty = 1;
@@ -389,83 +369,51 @@
 	stat->active_buf = NULL;
 }
 
-static int isp_stat_bufs_alloc_iommu(struct ispstat *stat, unsigned int size)
+static int isp_stat_bufs_alloc_one(struct device *dev,
+				   struct ispstat_buffer *buf,
+				   unsigned int size)
 {
-	struct isp_device *isp = stat->isp;
-	int i;
+	int ret;
 
-	stat->buf_alloc_size = size;
+	buf->virt_addr = dma_alloc_coherent(dev, size, &buf->dma_addr,
+					    GFP_KERNEL | GFP_DMA);
+	if (!buf->virt_addr)
+		return -ENOMEM;
 
-	for (i = 0; i < STAT_MAX_BUFS; i++) {
-		struct ispstat_buffer *buf = &stat->buf[i];
-		struct iovm_struct *iovm;
-
-		WARN_ON(buf->dma_addr);
-		buf->iommu_addr = omap_iommu_vmalloc(isp->domain, isp->dev, 0,
-							size, IOMMU_FLAG);
-		if (IS_ERR((void *)buf->iommu_addr)) {
-			dev_err(stat->isp->dev,
-				 "%s: Can't acquire memory for "
-				 "buffer %d\n", stat->subdev.name, i);
-			isp_stat_bufs_free(stat);
-			return -ENOMEM;
-		}
-
-		iovm = omap_find_iovm_area(isp->dev, buf->iommu_addr);
-		if (!iovm ||
-		    !dma_map_sg(isp->dev, iovm->sgt->sgl, iovm->sgt->nents,
-				DMA_FROM_DEVICE)) {
-			isp_stat_bufs_free(stat);
-			return -ENOMEM;
-		}
-		buf->iovm = iovm;
-
-		buf->virt_addr = omap_da_to_va(stat->isp->dev,
-					  (u32)buf->iommu_addr);
-		buf->empty = 1;
-		dev_dbg(stat->isp->dev, "%s: buffer[%d] allocated."
-			"iommu_addr=0x%08lx virt_addr=0x%08lx",
-			stat->subdev.name, i, buf->iommu_addr,
-			(unsigned long)buf->virt_addr);
+	ret = dma_get_sgtable(dev, &buf->sgt, buf->virt_addr, buf->dma_addr,
+			      size);
+	if (ret < 0) {
+		dma_free_coherent(dev, size, buf->virt_addr, buf->dma_addr);
+		buf->virt_addr = NULL;
+		buf->dma_addr = 0;
+		return ret;
 	}
 
 	return 0;
 }
 
-static int isp_stat_bufs_alloc_dma(struct ispstat *stat, unsigned int size)
-{
-	int i;
-
-	stat->buf_alloc_size = size;
-
-	for (i = 0; i < STAT_MAX_BUFS; i++) {
-		struct ispstat_buffer *buf = &stat->buf[i];
-
-		WARN_ON(buf->iommu_addr);
-		buf->virt_addr = dma_alloc_coherent(stat->isp->dev, size,
-					&buf->dma_addr, GFP_KERNEL | GFP_DMA);
-
-		if (!buf->virt_addr || !buf->dma_addr) {
-			dev_info(stat->isp->dev,
-				 "%s: Can't acquire memory for "
-				 "DMA buffer %d\n", stat->subdev.name, i);
-			isp_stat_bufs_free(stat);
-			return -ENOMEM;
-		}
-		buf->empty = 1;
-
-		dev_dbg(stat->isp->dev, "%s: buffer[%d] allocated."
-			"dma_addr=0x%08lx virt_addr=0x%08lx\n",
-			stat->subdev.name, i, (unsigned long)buf->dma_addr,
-			(unsigned long)buf->virt_addr);
-	}
-
-	return 0;
-}
-
+/*
+ * The device passed to the DMA API depends on whether the statistics block uses
+ * ISP DMA, external DMA or PIO to transfer data.
+ *
+ * The first case (for the AEWB and AF engines) passes the ISP device, resulting
+ * in the DMA buffers being mapped through the ISP IOMMU.
+ *
+ * The second case (for the histogram engine) should pass the DMA engine device.
+ * As that device isn't accessible through the OMAP DMA engine API the driver
+ * passes NULL instead, resulting in the buffers being mapped directly as
+ * physical pages.
+ *
+ * The third case (for the histogram engine) doesn't require any mapping. The
+ * buffers could be allocated with kmalloc/vmalloc, but we still use
+ * dma_alloc_coherent() for consistency purpose.
+ */
 static int isp_stat_bufs_alloc(struct ispstat *stat, u32 size)
 {
+	struct device *dev = ISP_STAT_USES_DMAENGINE(stat)
+			   ? NULL : stat->isp->dev;
 	unsigned long flags;
+	unsigned int i;
 
 	spin_lock_irqsave(&stat->isp->stat_lock, flags);
 
@@ -489,10 +437,31 @@
 
 	isp_stat_bufs_free(stat);
 
-	if (IS_COHERENT_BUF(stat))
-		return isp_stat_bufs_alloc_dma(stat, size);
-	else
-		return isp_stat_bufs_alloc_iommu(stat, size);
+	stat->buf_alloc_size = size;
+
+	for (i = 0; i < STAT_MAX_BUFS; i++) {
+		struct ispstat_buffer *buf = &stat->buf[i];
+		int ret;
+
+		ret = isp_stat_bufs_alloc_one(dev, buf, size);
+		if (ret < 0) {
+			dev_err(stat->isp->dev,
+				"%s: Failed to allocate DMA buffer %u\n",
+				stat->subdev.name, i);
+			isp_stat_bufs_free(stat);
+			return ret;
+		}
+
+		buf->empty = 1;
+
+		dev_dbg(stat->isp->dev,
+			"%s: buffer[%u] allocated. dma=0x%08lx virt=0x%08lx",
+			stat->subdev.name, i,
+			(unsigned long)buf->dma_addr,
+			(unsigned long)buf->virt_addr);
+	}
+
+	return 0;
 }
 
 static void isp_stat_queue_event(struct ispstat *stat, int err)
diff --git a/drivers/media/platform/omap3isp/ispstat.h b/drivers/media/platform/omap3isp/ispstat.h
index 9a047c9..58d6ac7 100644
--- a/drivers/media/platform/omap3isp/ispstat.h
+++ b/drivers/media/platform/omap3isp/ispstat.h
@@ -46,8 +46,7 @@
 struct ispstat;
 
 struct ispstat_buffer {
-	unsigned long iommu_addr;
-	struct iovm_struct *iovm;
+	struct sg_table sgt;
 	void *virt_addr;
 	dma_addr_t dma_addr;
 	struct timespec ts;
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index 85b4036..e36bac2 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -27,7 +27,6 @@
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/omap-iommu.h>
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
@@ -35,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
+#include <media/videobuf2-dma-contig.h>
 
 #include "ispvideo.h"
 #include "isp.h"
@@ -326,90 +326,36 @@
 }
 
 /* -----------------------------------------------------------------------------
- * IOMMU management
- */
-
-#define IOMMU_FLAG	(IOVMF_ENDIAN_LITTLE | IOVMF_ELSZ_8)
-
-/*
- * ispmmu_vmap - Wrapper for Virtual memory mapping of a scatter gather list
- * @isp: Device pointer specific to the OMAP3 ISP.
- * @sglist: Pointer to source Scatter gather list to allocate.
- * @sglen: Number of elements of the scatter-gatter list.
- *
- * Returns a resulting mapped device address by the ISP MMU, or -ENOMEM if
- * we ran out of memory.
- */
-static dma_addr_t
-ispmmu_vmap(struct isp_device *isp, const struct scatterlist *sglist, int sglen)
-{
-	struct sg_table *sgt;
-	u32 da;
-
-	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
-	if (sgt == NULL)
-		return -ENOMEM;
-
-	sgt->sgl = (struct scatterlist *)sglist;
-	sgt->nents = sglen;
-	sgt->orig_nents = sglen;
-
-	da = omap_iommu_vmap(isp->domain, isp->dev, 0, sgt, IOMMU_FLAG);
-	if (IS_ERR_VALUE(da))
-		kfree(sgt);
-
-	return da;
-}
-
-/*
- * ispmmu_vunmap - Unmap a device address from the ISP MMU
- * @isp: Device pointer specific to the OMAP3 ISP.
- * @da: Device address generated from a ispmmu_vmap call.
- */
-static void ispmmu_vunmap(struct isp_device *isp, dma_addr_t da)
-{
-	struct sg_table *sgt;
-
-	sgt = omap_iommu_vunmap(isp->domain, isp->dev, (u32)da);
-	kfree(sgt);
-}
-
-/* -----------------------------------------------------------------------------
  * Video queue operations
  */
 
-static void isp_video_queue_prepare(struct isp_video_queue *queue,
-				    unsigned int *nbuffers, unsigned int *size)
+static int isp_video_queue_setup(struct vb2_queue *queue,
+				 const struct v4l2_format *fmt,
+				 unsigned int *count, unsigned int *num_planes,
+				 unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct isp_video_fh *vfh =
-		container_of(queue, struct isp_video_fh, queue);
+	struct isp_video_fh *vfh = vb2_get_drv_priv(queue);
 	struct isp_video *video = vfh->video;
 
-	*size = vfh->format.fmt.pix.sizeimage;
-	if (*size == 0)
-		return;
+	*num_planes = 1;
 
-	*nbuffers = min(*nbuffers, video->capture_mem / PAGE_ALIGN(*size));
+	sizes[0] = vfh->format.fmt.pix.sizeimage;
+	if (sizes[0] == 0)
+		return -EINVAL;
+
+	alloc_ctxs[0] = video->alloc_ctx;
+
+	*count = min(*count, video->capture_mem / PAGE_ALIGN(sizes[0]));
+
+	return 0;
 }
 
-static void isp_video_buffer_cleanup(struct isp_video_buffer *buf)
+static int isp_video_buffer_prepare(struct vb2_buffer *buf)
 {
-	struct isp_video_fh *vfh = isp_video_queue_to_isp_video_fh(buf->queue);
+	struct isp_video_fh *vfh = vb2_get_drv_priv(buf->vb2_queue);
 	struct isp_buffer *buffer = to_isp_buffer(buf);
 	struct isp_video *video = vfh->video;
-
-	if (buffer->isp_addr) {
-		ispmmu_vunmap(video->isp, buffer->isp_addr);
-		buffer->isp_addr = 0;
-	}
-}
-
-static int isp_video_buffer_prepare(struct isp_video_buffer *buf)
-{
-	struct isp_video_fh *vfh = isp_video_queue_to_isp_video_fh(buf->queue);
-	struct isp_buffer *buffer = to_isp_buffer(buf);
-	struct isp_video *video = vfh->video;
-	unsigned long addr;
+	dma_addr_t addr;
 
 	/* Refuse to prepare the buffer is the video node has registered an
 	 * error. We don't need to take any lock here as the operation is
@@ -420,19 +366,16 @@
 	if (unlikely(video->error))
 		return -EIO;
 
-	addr = ispmmu_vmap(video->isp, buf->sglist, buf->sglen);
-	if (IS_ERR_VALUE(addr))
-		return -EIO;
-
+	addr = vb2_dma_contig_plane_dma_addr(buf, 0);
 	if (!IS_ALIGNED(addr, 32)) {
-		dev_dbg(video->isp->dev, "Buffer address must be "
-			"aligned to 32 bytes boundary.\n");
-		ispmmu_vunmap(video->isp, buffer->isp_addr);
+		dev_dbg(video->isp->dev,
+			"Buffer address must be aligned to 32 bytes boundary.\n");
 		return -EINVAL;
 	}
 
-	buf->vbuf.bytesused = vfh->format.fmt.pix.sizeimage;
-	buffer->isp_addr = addr;
+	vb2_set_plane_payload(&buffer->vb, 0, vfh->format.fmt.pix.sizeimage);
+	buffer->dma = addr;
+
 	return 0;
 }
 
@@ -445,9 +388,9 @@
  * If the pipeline is busy, it will be restarted in the output module interrupt
  * handler.
  */
-static void isp_video_buffer_queue(struct isp_video_buffer *buf)
+static void isp_video_buffer_queue(struct vb2_buffer *buf)
 {
-	struct isp_video_fh *vfh = isp_video_queue_to_isp_video_fh(buf->queue);
+	struct isp_video_fh *vfh = vb2_get_drv_priv(buf->vb2_queue);
 	struct isp_buffer *buffer = to_isp_buffer(buf);
 	struct isp_video *video = vfh->video;
 	struct isp_pipeline *pipe = to_isp_pipeline(&video->video.entity);
@@ -456,14 +399,18 @@
 	unsigned int empty;
 	unsigned int start;
 
+	spin_lock_irqsave(&video->irqlock, flags);
+
 	if (unlikely(video->error)) {
-		buf->state = ISP_BUF_STATE_ERROR;
-		wake_up(&buf->wait);
+		vb2_buffer_done(&buffer->vb, VB2_BUF_STATE_ERROR);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 		return;
 	}
 
 	empty = list_empty(&video->dmaqueue);
-	list_add_tail(&buffer->buffer.irqlist, &video->dmaqueue);
+	list_add_tail(&buffer->irqlist, &video->dmaqueue);
+
+	spin_unlock_irqrestore(&video->irqlock, flags);
 
 	if (empty) {
 		if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
@@ -487,23 +434,22 @@
 	}
 }
 
-static const struct isp_video_queue_operations isp_video_queue_ops = {
-	.queue_prepare = &isp_video_queue_prepare,
-	.buffer_prepare = &isp_video_buffer_prepare,
-	.buffer_queue = &isp_video_buffer_queue,
-	.buffer_cleanup = &isp_video_buffer_cleanup,
+static const struct vb2_ops isp_video_queue_ops = {
+	.queue_setup = isp_video_queue_setup,
+	.buf_prepare = isp_video_buffer_prepare,
+	.buf_queue = isp_video_buffer_queue,
 };
 
 /*
  * omap3isp_video_buffer_next - Complete the current buffer and return the next
  * @video: ISP video object
  *
- * Remove the current video buffer from the DMA queue and fill its timestamp,
- * field count and state fields before waking up its completion handler.
+ * Remove the current video buffer from the DMA queue and fill its timestamp and
+ * field count before handing it back to videobuf2.
  *
- * For capture video nodes the buffer state is set to ISP_BUF_STATE_DONE if no
- * error has been flagged in the pipeline, or to ISP_BUF_STATE_ERROR otherwise.
- * For video output nodes the buffer state is always set to ISP_BUF_STATE_DONE.
+ * For capture video nodes the buffer state is set to VB2_BUF_STATE_DONE if no
+ * error has been flagged in the pipeline, or to VB2_BUF_STATE_ERROR otherwise.
+ * For video output nodes the buffer state is always set to VB2_BUF_STATE_DONE.
  *
  * The DMA queue is expected to contain at least one buffer.
  *
@@ -513,26 +459,25 @@
 struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 {
 	struct isp_pipeline *pipe = to_isp_pipeline(&video->video.entity);
-	struct isp_video_queue *queue = video->queue;
 	enum isp_pipeline_state state;
-	struct isp_video_buffer *buf;
+	struct isp_buffer *buf;
 	unsigned long flags;
 	struct timespec ts;
 
-	spin_lock_irqsave(&queue->irqlock, flags);
+	spin_lock_irqsave(&video->irqlock, flags);
 	if (WARN_ON(list_empty(&video->dmaqueue))) {
-		spin_unlock_irqrestore(&queue->irqlock, flags);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 		return NULL;
 	}
 
-	buf = list_first_entry(&video->dmaqueue, struct isp_video_buffer,
+	buf = list_first_entry(&video->dmaqueue, struct isp_buffer,
 			       irqlist);
 	list_del(&buf->irqlist);
-	spin_unlock_irqrestore(&queue->irqlock, flags);
+	spin_unlock_irqrestore(&video->irqlock, flags);
 
 	ktime_get_ts(&ts);
-	buf->vbuf.timestamp.tv_sec = ts.tv_sec;
-	buf->vbuf.timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+	buf->vb.v4l2_buf.timestamp.tv_sec = ts.tv_sec;
+	buf->vb.v4l2_buf.timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
 
 	/* Do frame number propagation only if this is the output video node.
 	 * Frame number either comes from the CSI receivers or it gets
@@ -541,22 +486,27 @@
 	 * first, so the input number might lag behind by 1 in some cases.
 	 */
 	if (video == pipe->output && !pipe->do_propagation)
-		buf->vbuf.sequence = atomic_inc_return(&pipe->frame_number);
+		buf->vb.v4l2_buf.sequence =
+			atomic_inc_return(&pipe->frame_number);
 	else
-		buf->vbuf.sequence = atomic_read(&pipe->frame_number);
+		buf->vb.v4l2_buf.sequence = atomic_read(&pipe->frame_number);
 
 	/* Report pipeline errors to userspace on the capture device side. */
-	if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
-		buf->state = ISP_BUF_STATE_ERROR;
+	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
+		state = VB2_BUF_STATE_ERROR;
 		pipe->error = false;
 	} else {
-		buf->state = ISP_BUF_STATE_DONE;
+		state = VB2_BUF_STATE_DONE;
 	}
 
-	wake_up(&buf->wait);
+	vb2_buffer_done(&buf->vb, state);
+
+	spin_lock_irqsave(&video->irqlock, flags);
 
 	if (list_empty(&video->dmaqueue)) {
-		if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		spin_unlock_irqrestore(&video->irqlock, flags);
+
+		if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
 			state = ISP_PIPELINE_QUEUE_OUTPUT
 			      | ISP_PIPELINE_STREAM;
 		else
@@ -571,16 +521,19 @@
 		return NULL;
 	}
 
-	if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->input != NULL) {
-		spin_lock_irqsave(&pipe->lock, flags);
+	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->input != NULL) {
+		spin_lock(&pipe->lock);
 		pipe->state &= ~ISP_PIPELINE_STREAM;
-		spin_unlock_irqrestore(&pipe->lock, flags);
+		spin_unlock(&pipe->lock);
 	}
 
-	buf = list_first_entry(&video->dmaqueue, struct isp_video_buffer,
+	buf = list_first_entry(&video->dmaqueue, struct isp_buffer,
 			       irqlist);
-	buf->state = ISP_BUF_STATE_ACTIVE;
-	return to_isp_buffer(buf);
+	buf->vb.state = VB2_BUF_STATE_ACTIVE;
+
+	spin_unlock_irqrestore(&video->irqlock, flags);
+
+	return buf;
 }
 
 /*
@@ -592,25 +545,22 @@
  */
 void omap3isp_video_cancel_stream(struct isp_video *video)
 {
-	struct isp_video_queue *queue = video->queue;
 	unsigned long flags;
 
-	spin_lock_irqsave(&queue->irqlock, flags);
+	spin_lock_irqsave(&video->irqlock, flags);
 
 	while (!list_empty(&video->dmaqueue)) {
-		struct isp_video_buffer *buf;
+		struct isp_buffer *buf;
 
 		buf = list_first_entry(&video->dmaqueue,
-				       struct isp_video_buffer, irqlist);
+				       struct isp_buffer, irqlist);
 		list_del(&buf->irqlist);
-
-		buf->state = ISP_BUF_STATE_ERROR;
-		wake_up(&buf->wait);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
 
 	video->error = true;
 
-	spin_unlock_irqrestore(&queue->irqlock, flags);
+	spin_unlock_irqrestore(&video->irqlock, flags);
 }
 
 /*
@@ -627,12 +577,15 @@
 {
 	struct isp_buffer *buf = NULL;
 
-	if (continuous && video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		omap3isp_video_queue_discard_done(video->queue);
+	if (continuous && video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) {
+		mutex_lock(&video->queue_lock);
+		vb2_discard_done(video->queue);
+		mutex_unlock(&video->queue_lock);
+	}
 
 	if (!list_empty(&video->dmaqueue)) {
 		buf = list_first_entry(&video->dmaqueue,
-				       struct isp_buffer, buffer.irqlist);
+				       struct isp_buffer, irqlist);
 		video->ops->queue(video, buf);
 		video->dmaqueue_flags |= ISP_VIDEO_DMAQUEUE_QUEUED;
 	} else {
@@ -840,33 +793,56 @@
 isp_video_reqbufs(struct file *file, void *fh, struct v4l2_requestbuffers *rb)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_reqbufs(&vfh->queue, rb);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_reqbufs(&vfh->queue, rb);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int
 isp_video_querybuf(struct file *file, void *fh, struct v4l2_buffer *b)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_querybuf(&vfh->queue, b);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_querybuf(&vfh->queue, b);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int
 isp_video_qbuf(struct file *file, void *fh, struct v4l2_buffer *b)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_qbuf(&vfh->queue, b);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_qbuf(&vfh->queue, b);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int
 isp_video_dqbuf(struct file *file, void *fh, struct v4l2_buffer *b)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_dqbuf(&vfh->queue, b,
-					  file->f_flags & O_NONBLOCK);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_dqbuf(&vfh->queue, b, file->f_flags & O_NONBLOCK);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int isp_video_check_external_subdevs(struct isp_video *video,
@@ -1006,11 +982,6 @@
 
 	mutex_lock(&video->stream_lock);
 
-	if (video->streaming) {
-		mutex_unlock(&video->stream_lock);
-		return -EBUSY;
-	}
-
 	/* Start streaming on the pipeline. No link touching an entity in the
 	 * pipeline can be activated or deactivated once streaming is started.
 	 */
@@ -1069,7 +1040,9 @@
 	INIT_LIST_HEAD(&video->dmaqueue);
 	atomic_set(&pipe->frame_number, -1);
 
-	ret = omap3isp_video_queue_streamon(&vfh->queue);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_streamon(&vfh->queue, type);
+	mutex_unlock(&video->queue_lock);
 	if (ret < 0)
 		goto err_check_format;
 
@@ -1082,19 +1055,19 @@
 					      ISP_PIPELINE_STREAM_CONTINUOUS);
 		if (ret < 0)
 			goto err_set_stream;
-		spin_lock_irqsave(&video->queue->irqlock, flags);
+		spin_lock_irqsave(&video->irqlock, flags);
 		if (list_empty(&video->dmaqueue))
 			video->dmaqueue_flags |= ISP_VIDEO_DMAQUEUE_UNDERRUN;
-		spin_unlock_irqrestore(&video->queue->irqlock, flags);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 	}
 
-	video->streaming = 1;
-
 	mutex_unlock(&video->stream_lock);
 	return 0;
 
 err_set_stream:
-	omap3isp_video_queue_streamoff(&vfh->queue);
+	mutex_lock(&video->queue_lock);
+	vb2_streamoff(&vfh->queue, type);
+	mutex_unlock(&video->queue_lock);
 err_check_format:
 	media_entity_pipeline_stop(&video->video.entity);
 err_pipeline_start:
@@ -1130,9 +1103,9 @@
 	mutex_lock(&video->stream_lock);
 
 	/* Make sure we're not streaming yet. */
-	mutex_lock(&vfh->queue.lock);
-	streaming = vfh->queue.streaming;
-	mutex_unlock(&vfh->queue.lock);
+	mutex_lock(&video->queue_lock);
+	streaming = vb2_is_streaming(&vfh->queue);
+	mutex_unlock(&video->queue_lock);
 
 	if (!streaming)
 		goto done;
@@ -1151,9 +1124,12 @@
 
 	/* Stop the stream. */
 	omap3isp_pipeline_set_stream(pipe, ISP_PIPELINE_STREAM_STOPPED);
-	omap3isp_video_queue_streamoff(&vfh->queue);
+	omap3isp_video_cancel_stream(video);
+
+	mutex_lock(&video->queue_lock);
+	vb2_streamoff(&vfh->queue, type);
+	mutex_unlock(&video->queue_lock);
 	video->queue = NULL;
-	video->streaming = 0;
 	video->error = false;
 
 	if (video->isp->pdata->set_constraints)
@@ -1223,6 +1199,7 @@
 {
 	struct isp_video *video = video_drvdata(file);
 	struct isp_video_fh *handle;
+	struct vb2_queue *queue;
 	int ret = 0;
 
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
@@ -1244,9 +1221,20 @@
 		goto done;
 	}
 
-	omap3isp_video_queue_init(&handle->queue, video->type,
-				  &isp_video_queue_ops, video->isp->dev,
-				  sizeof(struct isp_buffer));
+	queue = &handle->queue;
+	queue->type = video->type;
+	queue->io_modes = VB2_MMAP | VB2_USERPTR;
+	queue->drv_priv = handle;
+	queue->ops = &isp_video_queue_ops;
+	queue->mem_ops = &vb2_dma_contig_memops;
+	queue->buf_struct_size = sizeof(struct isp_buffer);
+	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+
+	ret = vb2_queue_init(&handle->queue);
+	if (ret < 0) {
+		omap3isp_put(video->isp);
+		goto done;
+	}
 
 	memset(&handle->format, 0, sizeof(handle->format));
 	handle->format.type = video->type;
@@ -1273,9 +1261,9 @@
 	/* Disable streaming and free the buffers queue resources. */
 	isp_video_streamoff(file, vfh, video->type);
 
-	mutex_lock(&handle->queue.lock);
-	omap3isp_video_queue_cleanup(&handle->queue);
-	mutex_unlock(&handle->queue.lock);
+	mutex_lock(&video->queue_lock);
+	vb2_queue_release(&handle->queue);
+	mutex_unlock(&video->queue_lock);
 
 	omap3isp_pipeline_pm_use(&video->video.entity, 0);
 
@@ -1292,16 +1280,27 @@
 static unsigned int isp_video_poll(struct file *file, poll_table *wait)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(file->private_data);
-	struct isp_video_queue *queue = &vfh->queue;
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_poll(queue, file, wait);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_poll(&vfh->queue, file, wait);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int isp_video_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(file->private_data);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_mmap(&vfh->queue, vma);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_mmap(&vfh->queue, vma);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static struct v4l2_file_operations isp_video_fops = {
@@ -1342,15 +1341,23 @@
 		return -EINVAL;
 	}
 
+	video->alloc_ctx = vb2_dma_contig_init_ctx(video->isp->dev);
+	if (IS_ERR(video->alloc_ctx))
+		return PTR_ERR(video->alloc_ctx);
+
 	ret = media_entity_init(&video->video.entity, 1, &video->pad, 0);
-	if (ret < 0)
+	if (ret < 0) {
+		vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 		return ret;
+	}
 
 	mutex_init(&video->mutex);
 	atomic_set(&video->active, 0);
 
 	spin_lock_init(&video->pipe.lock);
 	mutex_init(&video->stream_lock);
+	mutex_init(&video->queue_lock);
+	spin_lock_init(&video->irqlock);
 
 	/* Initialize the video device. */
 	if (video->ops == NULL)
@@ -1371,7 +1378,9 @@
 
 void omap3isp_video_cleanup(struct isp_video *video)
 {
+	vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	media_entity_cleanup(&video->video.entity);
+	mutex_destroy(&video->queue_lock);
 	mutex_destroy(&video->stream_lock);
 	mutex_destroy(&video->mutex);
 }
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index 4e19407..7d2e821 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -30,8 +30,7 @@
 #include <media/media-entity.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-fh.h>
-
-#include "ispqueue.h"
+#include <media/videobuf2-core.h>
 
 #define ISP_VIDEO_DRIVER_NAME		"ispvideo"
 #define ISP_VIDEO_DRIVER_VERSION	"0.0.2"
@@ -124,17 +123,19 @@
 			       ISP_PIPELINE_IDLE_OUTPUT);
 }
 
-/*
- * struct isp_buffer - ISP buffer
- * @buffer: ISP video buffer
- * @isp_addr: MMU mapped address (a.k.a. device address) of the buffer.
+/**
+ * struct isp_buffer - ISP video buffer
+ * @vb: videobuf2 buffer
+ * @irqlist: List head for insertion into IRQ queue
+ * @dma: DMA address
  */
 struct isp_buffer {
-	struct isp_video_buffer buffer;
-	dma_addr_t isp_addr;
+	struct vb2_buffer vb;
+	struct list_head irqlist;
+	dma_addr_t dma;
 };
 
-#define to_isp_buffer(buf)	container_of(buf, struct isp_buffer, buffer)
+#define to_isp_buffer(buf)	container_of(buf, struct isp_buffer, vb)
 
 enum isp_video_dmaqueue_flags {
 	/* Set if DMA queue becomes empty when ISP_PIPELINE_STREAM_CONTINUOUS */
@@ -172,16 +173,16 @@
 	unsigned int bpl_value;		/* bytes per line value */
 	unsigned int bpl_padding;	/* padding at end of line */
 
-	/* Entity video node streaming */
-	unsigned int streaming:1;
-
 	/* Pipeline state */
 	struct isp_pipeline pipe;
 	struct mutex stream_lock;	/* pipeline and stream states */
 	bool error;
 
 	/* Video buffers queue */
-	struct isp_video_queue *queue;
+	void *alloc_ctx;
+	struct vb2_queue *queue;
+	struct mutex queue_lock;	/* protects the queue */
+	spinlock_t irqlock;		/* protects dmaqueue */
 	struct list_head dmaqueue;
 	enum isp_video_dmaqueue_flags dmaqueue_flags;
 
@@ -193,7 +194,7 @@
 struct isp_video_fh {
 	struct v4l2_fh vfh;
 	struct isp_video *video;
-	struct isp_video_queue queue;
+	struct vb2_queue queue;
 	struct v4l2_format format;
 	struct v4l2_fract timeperframe;
 };
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 349e659..7c4489c 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -1200,6 +1200,30 @@
 EXPORT_SYMBOL_GPL(vb2_buffer_done);
 
 /**
+ * vb2_discard_done() - discard all buffers marked as DONE
+ * @q:		videobuf2 queue
+ *
+ * This function is intended to be used with suspend/resume operations. It
+ * discards all 'done' buffers as they would be too old to be requested after
+ * resume.
+ *
+ * Drivers must stop the hardware and synchronize with interrupt handlers and/or
+ * delayed works before calling this function to make sure no buffer will be
+ * touched by the driver and/or hardware.
+ */
+void vb2_discard_done(struct vb2_queue *q)
+{
+	struct vb2_buffer *vb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->done_lock, flags);
+	list_for_each_entry(vb, &q->done_list, done_entry)
+		vb->state = VB2_BUF_STATE_ERROR;
+	spin_unlock_irqrestore(&q->done_lock, flags);
+}
+EXPORT_SYMBOL_GPL(vb2_discard_done);
+
+/**
  * __fill_vb2_buffer() - fill a vb2_buffer with information provided in a
  * v4l2_buffer by the userspace. The caller has already verified that struct
  * v4l2_buffer has a valid number of planes.
diff --git a/drivers/misc/vexpress-syscfg.c b/drivers/misc/vexpress-syscfg.c
index 73068e5..3250fc1 100644
--- a/drivers/misc/vexpress-syscfg.c
+++ b/drivers/misc/vexpress-syscfg.c
@@ -199,7 +199,7 @@
 	func = kzalloc(sizeof(*func) + sizeof(*func->template) * num,
 			GFP_KERNEL);
 	if (!func)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	func->syscfg = syscfg;
 	func->num_templates = num;
@@ -231,10 +231,14 @@
 	func->regmap = regmap_init(dev, NULL, func,
 			&vexpress_syscfg_regmap_config);
 
-	if (IS_ERR(func->regmap))
+	if (IS_ERR(func->regmap)) {
+		void *err = func->regmap;
+
 		kfree(func);
-	else
-		list_add(&func->list, &syscfg->funcs);
+		return err;
+	}
+
+	list_add(&func->list, &syscfg->funcs);
 
 	return func->regmap;
 }
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index 2421835..1916174 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -17,7 +17,8 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  *
- * Maintained by: Dmitry Torokhov <dtor@vmware.com>
+ * Maintained by:	Xavier Deguillard <xdeguillard@vmware.com>
+ *			Philip Moltmann <moltmann@vmware.com>
  */
 
 /*
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1610d51..ade33ef 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1156,15 +1156,7 @@
 	if (!vs)
 		goto drop;
 
-	/* If the NIC driver gave us an encapsulated packet
-	 * with the encapsulation mark, the device checksummed it
-	 * for us. Otherwise force the upper layers to verify it.
-	 */
-	if ((skb->ip_summed != CHECKSUM_UNNECESSARY && skb->ip_summed != CHECKSUM_PARTIAL) ||
-	    !skb->encapsulation)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	skb->encapsulation = 0;
+	skb_pop_rcv_encapsulation(skb);
 
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
@@ -1201,6 +1193,7 @@
 	skb_reset_mac_header(skb);
 	skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
 	skb->protocol = eth_type_trans(skb, vxlan->dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	/* Ignore packet loops (and multicast echo) */
 	if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
@@ -2247,9 +2240,9 @@
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
 	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
 	else
-		dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;
@@ -2646,8 +2639,7 @@
 		if (!tb[IFLA_MTU])
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
-		/* update header length based on lower device */
-		dev->hard_header_len = lowerdev->hard_header_len +
+		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 	} else if (use_ipv6)
 		vxlan->flags |= VXLAN_F_IPV6;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 8368d96..b986480 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -227,7 +227,8 @@
 	np->kobj.kset = of_kset;
 	if (!np->parent) {
 		/* Nodes without parents are new top level trees */
-		rc = kobject_add(&np->kobj, NULL, safe_name(&of_kset->kobj, "base"));
+		rc = kobject_add(&np->kobj, NULL, "%s",
+				 safe_name(&of_kset->kobj, "base"));
 	} else {
 		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
 		if (!name || !name[0])
@@ -1960,9 +1961,9 @@
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np->sibling = np->parent->child;
-	np->allnext = of_allnodes;
+	np->allnext = np->parent->allnext;
+	np->parent->allnext = np;
 	np->parent->child = np;
-	of_allnodes = np;
 	of_node_clear_flag(np, OF_DETACHED);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 6c48d73..500436f 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -166,10 +166,6 @@
 	int ret;
 	struct device *dev = &pdev->dev;
 
-#if defined(CONFIG_MICROBLAZE)
-	pdev->archdata.dma_mask = 0xffffffffUL;
-#endif
-
 	/*
 	 * Set default dma-mask to 32 bit. Drivers are expected to setup
 	 * the correct supported dma_mask.
diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c
index 8558521..ad9e0c9 100644
--- a/drivers/regulator/as3722-regulator.c
+++ b/drivers/regulator/as3722-regulator.c
@@ -433,6 +433,7 @@
 };
 
 static const struct regulator_linear_range as3722_ldo_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x00, 0x00, 0),
 	REGULATOR_LINEAR_RANGE(825000, 0x01, 0x24, 25000),
 	REGULATOR_LINEAR_RANGE(1725000, 0x40, 0x7F, 25000),
 };
@@ -609,6 +610,7 @@
 }
 
 static const struct regulator_linear_range as3722_sd2345_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x00, 0x00, 0),
 	REGULATOR_LINEAR_RANGE(612500, 0x01, 0x40, 12500),
 	REGULATOR_LINEAR_RANGE(1425000, 0x41, 0x70, 25000),
 	REGULATOR_LINEAR_RANGE(2650000, 0x71, 0x7F, 50000),
diff --git a/drivers/regulator/ltc3589.c b/drivers/regulator/ltc3589.c
index 110a99e..c810518 100644
--- a/drivers/regulator/ltc3589.c
+++ b/drivers/regulator/ltc3589.c
@@ -255,7 +255,7 @@
 	struct device_node *node;
 	int i, ret;
 
-	node = of_find_node_by_name(dev->of_node, "regulators");
+	node = of_get_child_by_name(dev->of_node, "regulators");
 	if (!node) {
 		dev_err(dev, "regulators node not found\n");
 		return -EINVAL;
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 864ed02..b982f0f 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -37,12 +37,14 @@
 };
 
 static const struct regulator_linear_range smps_low_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(500000, 0x1, 0x6, 0),
 	REGULATOR_LINEAR_RANGE(510000, 0x7, 0x79, 10000),
 	REGULATOR_LINEAR_RANGE(1650000, 0x7A, 0x7f, 0),
 };
 
 static const struct regulator_linear_range smps_high_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(1000000, 0x1, 0x6, 0),
 	REGULATOR_LINEAR_RANGE(1020000, 0x7, 0x79, 20000),
 	REGULATOR_LINEAR_RANGE(3300000, 0x7A, 0x7f, 0),
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index ce1743d..5e343ba 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -44,7 +44,7 @@
 config DA8XX_REMOTEPROC
 	tristate "DA8xx/OMAP-L13x remoteproc support"
 	depends on ARCH_DAVINCI_DA8XX
-	select CMA
+	select CMA if MMU
 	select REMOTEPROC
 	select RPMSG
 	help
diff --git a/drivers/rtc/rtc-puv3.c b/drivers/rtc/rtc-puv3.c
index 1ecfe3b..1cff2a2 100644
--- a/drivers/rtc/rtc-puv3.c
+++ b/drivers/rtc/rtc-puv3.c
@@ -71,7 +71,7 @@
 {
 	unsigned int tmp;
 
-	dev_debug(dev, "%s: pie=%d\n", __func__, enabled);
+	dev_dbg(dev, "%s: pie=%d\n", __func__, enabled);
 
 	spin_lock_irq(&puv3_rtc_pie_lock);
 	tmp = readl(RTC_RTSR) & ~RTC_RTSR_HZE;
@@ -140,7 +140,7 @@
 	rtc_tm_to_time(tm, &rtcalarm_count);
 	writel(rtcalarm_count, RTC_RTAR);
 
-	puv3_rtc_setaie(&dev->dev, alrm->enabled);
+	puv3_rtc_setaie(dev, alrm->enabled);
 
 	if (alrm->enabled)
 		enable_irq_wake(puv3_rtc_alarmno);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index ee0e85a..0f47175 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -593,7 +593,7 @@
 	dev_info->start = dcssblk_find_lowest_addr(dev_info);
 	dev_info->end = dcssblk_find_highest_addr(dev_info);
 
-	dev_set_name(&dev_info->dev, dev_info->segment_name);
+	dev_set_name(&dev_info->dev, "%s", dev_info->segment_name);
 	dev_info->dev.release = dcssblk_release_segment;
 	dev_info->dev.groups = dcssblk_dev_attr_groups;
 	INIT_LIST_HEAD(&dev_info->lh);
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 629fcc2..78b6ace 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -19,7 +19,6 @@
 obj-$(CONFIG_SCLP_CPI) += sclp_cpi.o
 obj-$(CONFIG_SCLP_ASYNC) += sclp_async.o
 
-obj-$(CONFIG_ZVM_WATCHDOG) += vmwatchdog.o
 obj-$(CONFIG_VMLOGRDR) += vmlogrdr.o
 obj-$(CONFIG_VMCP) += vmcp.o
 
diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c
index cd9c919..b9a9f72 100644
--- a/drivers/s390/char/sclp_vt220.c
+++ b/drivers/s390/char/sclp_vt220.c
@@ -838,8 +838,6 @@
 {
 	int rc;
 
-	if (!CONSOLE_IS_SCLP)
-		return 0;
 	rc = __sclp_vt220_init(sclp_console_pages);
 	if (rc)
 		return rc;
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index cf31d33..a8848db 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -761,7 +761,7 @@
 
 	dev = kzalloc(sizeof(struct device), GFP_KERNEL);
 	if (dev) {
-		dev_set_name(dev, priv->internal_name);
+		dev_set_name(dev, "%s", priv->internal_name);
 		dev->bus = &iucv_bus;
 		dev->parent = iucv_root;
 		dev->driver = &vmlogrdr_driver;
diff --git a/drivers/s390/char/vmwatchdog.c b/drivers/s390/char/vmwatchdog.c
deleted file mode 100644
index d5eac98..0000000
--- a/drivers/s390/char/vmwatchdog.c
+++ /dev/null
@@ -1,338 +0,0 @@
-/*
- * Watchdog implementation based on z/VM Watchdog Timer API
- *
- * Copyright IBM Corp. 2004, 2009
- *
- * The user space watchdog daemon can use this driver as
- * /dev/vmwatchdog to have z/VM execute the specified CP
- * command when the timeout expires. The default command is
- * "IPL", which which cause an immediate reboot.
- */
-#define KMSG_COMPONENT "vmwatchdog"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/miscdevice.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/slab.h>
-#include <linux/suspend.h>
-#include <linux/watchdog.h>
-
-#include <asm/ebcdic.h>
-#include <asm/io.h>
-#include <asm/uaccess.h>
-
-#define MAX_CMDLEN 240
-#define MIN_INTERVAL 15
-static char vmwdt_cmd[MAX_CMDLEN] = "IPL";
-static bool vmwdt_conceal;
-
-static bool vmwdt_nowayout = WATCHDOG_NOWAYOUT;
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
-MODULE_DESCRIPTION("z/VM Watchdog Timer");
-module_param_string(cmd, vmwdt_cmd, MAX_CMDLEN, 0644);
-MODULE_PARM_DESC(cmd, "CP command that is run when the watchdog triggers");
-module_param_named(conceal, vmwdt_conceal, bool, 0644);
-MODULE_PARM_DESC(conceal, "Enable the CONCEAL CP option while the watchdog "
-		" is active");
-module_param_named(nowayout, vmwdt_nowayout, bool, 0);
-MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started"
-		" (default=CONFIG_WATCHDOG_NOWAYOUT)");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
-
-static unsigned int vmwdt_interval = 60;
-static unsigned long vmwdt_is_open;
-static int vmwdt_expect_close;
-
-static DEFINE_MUTEX(vmwdt_mutex);
-
-#define VMWDT_OPEN	0	/* devnode is open or suspend in progress */
-#define VMWDT_RUNNING	1	/* The watchdog is armed */
-
-enum vmwdt_func {
-	/* function codes */
-	wdt_init   = 0,
-	wdt_change = 1,
-	wdt_cancel = 2,
-	/* flags */
-	wdt_conceal = 0x80000000,
-};
-
-static int __diag288(enum vmwdt_func func, unsigned int timeout,
-			    char *cmd, size_t len)
-{
-	register unsigned long __func asm("2") = func;
-	register unsigned long __timeout asm("3") = timeout;
-	register unsigned long __cmdp asm("4") = virt_to_phys(cmd);
-	register unsigned long __cmdl asm("5") = len;
-	int err;
-
-	err = -EINVAL;
-	asm volatile(
-		"	diag	%1,%3,0x288\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (err) : "d"(__func), "d"(__timeout),
-		  "d"(__cmdp), "d"(__cmdl) : "1", "cc");
-	return err;
-}
-
-static int vmwdt_keepalive(void)
-{
-	/* we allocate new memory every time to avoid having
-	 * to track the state. static allocation is not an
-	 * option since that might not be contiguous in real
-	 * storage in case of a modular build */
-	static char *ebc_cmd;
-	size_t len;
-	int ret;
-	unsigned int func;
-
-	ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
-	if (!ebc_cmd)
-		return -ENOMEM;
-
-	len = strlcpy(ebc_cmd, vmwdt_cmd, MAX_CMDLEN);
-	ASCEBC(ebc_cmd, MAX_CMDLEN);
-	EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
-
-	func = vmwdt_conceal ? (wdt_init | wdt_conceal) : wdt_init;
-	set_bit(VMWDT_RUNNING, &vmwdt_is_open);
-	ret = __diag288(func, vmwdt_interval, ebc_cmd, len);
-	WARN_ON(ret != 0);
-	kfree(ebc_cmd);
-	return ret;
-}
-
-static int vmwdt_disable(void)
-{
-	char cmd[] = {'\0'};
-	int ret = __diag288(wdt_cancel, 0, cmd, 0);
-	WARN_ON(ret != 0);
-	clear_bit(VMWDT_RUNNING, &vmwdt_is_open);
-	return ret;
-}
-
-static int __init vmwdt_probe(void)
-{
-	/* there is no real way to see if the watchdog is supported,
-	 * so we try initializing it with a NOP command ("BEGIN")
-	 * that won't cause any harm even if the following disable
-	 * fails for some reason */
-	char ebc_begin[] = {
-		194, 197, 199, 201, 213
-	};
-	if (__diag288(wdt_init, 15, ebc_begin, sizeof(ebc_begin)) != 0)
-		return -EINVAL;
-	return vmwdt_disable();
-}
-
-static int vmwdt_open(struct inode *i, struct file *f)
-{
-	int ret;
-	if (test_and_set_bit(VMWDT_OPEN, &vmwdt_is_open))
-		return -EBUSY;
-	ret = vmwdt_keepalive();
-	if (ret)
-		clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-	return ret ? ret : nonseekable_open(i, f);
-}
-
-static int vmwdt_close(struct inode *i, struct file *f)
-{
-	if (vmwdt_expect_close == 42)
-		vmwdt_disable();
-	vmwdt_expect_close = 0;
-	clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-	return 0;
-}
-
-static struct watchdog_info vmwdt_info = {
-	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
-	.firmware_version = 0,
-	.identity = "z/VM Watchdog Timer",
-};
-
-static int __vmwdt_ioctl(unsigned int cmd, unsigned long arg)
-{
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user((void __user *)arg, &vmwdt_info,
-					sizeof(vmwdt_info)))
-			return -EFAULT;
-		return 0;
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, (int __user *)arg);
-	case WDIOC_GETTEMP:
-		return -EINVAL;
-	case WDIOC_SETOPTIONS:
-		{
-			int options, ret;
-			if (get_user(options, (int __user *)arg))
-				return -EFAULT;
-			ret = -EINVAL;
-			if (options & WDIOS_DISABLECARD) {
-				ret = vmwdt_disable();
-				if (ret)
-					return ret;
-			}
-			if (options & WDIOS_ENABLECARD) {
-				ret = vmwdt_keepalive();
-			}
-			return ret;
-		}
-	case WDIOC_GETTIMEOUT:
-		return put_user(vmwdt_interval, (int __user *)arg);
-	case WDIOC_SETTIMEOUT:
-		{
-			int interval;
-			if (get_user(interval, (int __user *)arg))
-				return -EFAULT;
-			if (interval < MIN_INTERVAL)
-				return -EINVAL;
-			vmwdt_interval = interval;
-		}
-		return vmwdt_keepalive();
-	case WDIOC_KEEPALIVE:
-		return vmwdt_keepalive();
-	}
-	return -EINVAL;
-}
-
-static long vmwdt_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
-	int rc;
-
-	mutex_lock(&vmwdt_mutex);
-	rc = __vmwdt_ioctl(cmd, arg);
-	mutex_unlock(&vmwdt_mutex);
-	return (long) rc;
-}
-
-static ssize_t vmwdt_write(struct file *f, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	if(count) {
-		if (!vmwdt_nowayout) {
-			size_t i;
-
-			/* note: just in case someone wrote the magic character
-			 * five months ago... */
-			vmwdt_expect_close = 0;
-
-			for (i = 0; i != count; i++) {
-				char c;
-				if (get_user(c, buf+i))
-					return -EFAULT;
-				if (c == 'V')
-					vmwdt_expect_close = 42;
-			}
-		}
-		/* someone wrote to us, we should restart timer */
-		vmwdt_keepalive();
-	}
-	return count;
-}
-
-static int vmwdt_resume(void)
-{
-	clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-	return NOTIFY_DONE;
-}
-
-/*
- * It makes no sense to go into suspend while the watchdog is running.
- * Depending on the memory size, the watchdog might trigger, while we
- * are still saving the memory.
- * We reuse the open flag to ensure that suspend and watchdog open are
- * exclusive operations
- */
-static int vmwdt_suspend(void)
-{
-	if (test_and_set_bit(VMWDT_OPEN, &vmwdt_is_open)) {
-		pr_err("The system cannot be suspended while the watchdog"
-			" is in use\n");
-		return notifier_from_errno(-EBUSY);
-	}
-	if (test_bit(VMWDT_RUNNING, &vmwdt_is_open)) {
-		clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-		pr_err("The system cannot be suspended while the watchdog"
-			" is running\n");
-		return notifier_from_errno(-EBUSY);
-	}
-	return NOTIFY_DONE;
-}
-
-/*
- * This function is called for suspend and resume.
- */
-static int vmwdt_power_event(struct notifier_block *this, unsigned long event,
-			     void *ptr)
-{
-	switch (event) {
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
-		return vmwdt_resume();
-	case PM_HIBERNATION_PREPARE:
-	case PM_SUSPEND_PREPARE:
-		return vmwdt_suspend();
-	default:
-		return NOTIFY_DONE;
-	}
-}
-
-static struct notifier_block vmwdt_power_notifier = {
-	.notifier_call = vmwdt_power_event,
-};
-
-static const struct file_operations vmwdt_fops = {
-	.open    = &vmwdt_open,
-	.release = &vmwdt_close,
-	.unlocked_ioctl = &vmwdt_ioctl,
-	.write   = &vmwdt_write,
-	.owner   = THIS_MODULE,
-	.llseek  = noop_llseek,
-};
-
-static struct miscdevice vmwdt_dev = {
-	.minor      = WATCHDOG_MINOR,
-	.name       = "watchdog",
-	.fops       = &vmwdt_fops,
-};
-
-static int __init vmwdt_init(void)
-{
-	int ret;
-
-	ret = vmwdt_probe();
-	if (ret)
-		return ret;
-	ret = register_pm_notifier(&vmwdt_power_notifier);
-	if (ret)
-		return ret;
-	/*
-	 * misc_register() has to be the last action in module_init(), because
-	 * file operations will be available right after this.
-	 */
-	ret = misc_register(&vmwdt_dev);
-	if (ret) {
-		unregister_pm_notifier(&vmwdt_power_notifier);
-		return ret;
-	}
-	return 0;
-}
-module_init(vmwdt_init);
-
-static void __exit vmwdt_exit(void)
-{
-	unregister_pm_notifier(&vmwdt_power_notifier);
-	misc_deregister(&vmwdt_dev);
-}
-module_exit(vmwdt_exit);
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index 445564c..00bfbee 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -196,11 +196,11 @@
  */
 unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num)
 {
-	unsigned long bit, i;
+	unsigned long bit, i, flags;
 
 	if (!iv->avail || num == 0)
 		return -1UL;
-	spin_lock(&iv->lock);
+	spin_lock_irqsave(&iv->lock, flags);
 	bit = find_first_bit_inv(iv->avail, iv->bits);
 	while (bit + num <= iv->bits) {
 		for (i = 1; i < num; i++)
@@ -218,9 +218,8 @@
 	}
 	if (bit + num > iv->bits)
 		bit = -1UL;
-	spin_unlock(&iv->lock);
+	spin_unlock_irqrestore(&iv->lock, flags);
 	return bit;
-
 }
 EXPORT_SYMBOL(airq_iv_alloc);
 
@@ -232,11 +231,11 @@
  */
 void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num)
 {
-	unsigned long i;
+	unsigned long i, flags;
 
 	if (!iv->avail || num == 0)
 		return;
-	spin_lock(&iv->lock);
+	spin_lock_irqsave(&iv->lock, flags);
 	for (i = 0; i < num; i++) {
 		/* Clear (possibly left over) interrupt bit */
 		clear_bit_inv(bit + i, iv->vector);
@@ -248,7 +247,7 @@
 		while (iv->end > 0 && !test_bit_inv(iv->end - 1, iv->avail))
 			iv->end--;
 	}
-	spin_unlock(&iv->lock);
+	spin_unlock_irqrestore(&iv->lock, flags);
 }
 EXPORT_SYMBOL(airq_iv_free);
 
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index dfd7bc6..e443b0d 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -184,7 +184,7 @@
 				      const char *buf, size_t count)
 {
 	struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
-	int rc;
+	int rc = 0;
 
 	/* Prevent concurrent online/offline processing and ungrouping. */
 	if (atomic_cmpxchg(&gdev->onoff, 0, 1) != 0)
@@ -196,11 +196,12 @@
 
 	if (device_remove_file_self(dev, attr))
 		ccwgroup_ungroup(gdev);
+	else
+		rc = -ENODEV;
 out:
 	if (rc) {
-		if (rc != -EAGAIN)
-			/* Release onoff "lock" when ungrouping failed. */
-			atomic_set(&gdev->onoff, 0);
+		/* Release onoff "lock" when ungrouping failed. */
+		atomic_set(&gdev->onoff, 0);
 		return rc;
 	}
 	return count;
@@ -227,6 +228,7 @@
 		container_of(work, struct ccwgroup_device, ungroup_work);
 
 	ccwgroup_ungroup(gdev);
+	put_device(&gdev->dev);
 }
 
 static void ccwgroup_release(struct device *dev)
@@ -412,8 +414,10 @@
 {
 	struct ccwgroup_device *gdev = to_ccwgroupdev(data);
 
-	if (action == BUS_NOTIFY_UNBIND_DRIVER)
+	if (action == BUS_NOTIFY_UNBIND_DRIVER) {
+		get_device(&gdev->dev);
 		schedule_work(&gdev->ungroup_work);
+	}
 
 	return NOTIFY_OK;
 }
@@ -582,11 +586,7 @@
 					 __ccwgroup_match_all))) {
 		struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
 
-		mutex_lock(&gdev->reg_mutex);
-		__ccwgroup_remove_symlinks(gdev);
-		device_unregister(dev);
-		__ccwgroup_remove_cdev_refs(gdev);
-		mutex_unlock(&gdev->reg_mutex);
+		ccwgroup_ungroup(gdev);
 		put_device(dev);
 	}
 	driver_unregister(&cdriver->driver);
@@ -633,13 +633,7 @@
 	get_device(&gdev->dev);
 	spin_unlock_irq(cdev->ccwlock);
 	/* Unregister group device. */
-	mutex_lock(&gdev->reg_mutex);
-	if (device_is_registered(&gdev->dev)) {
-		__ccwgroup_remove_symlinks(gdev);
-		device_unregister(&gdev->dev);
-		__ccwgroup_remove_cdev_refs(gdev);
-	}
-	mutex_unlock(&gdev->reg_mutex);
+	ccwgroup_ungroup(gdev);
 	/* Release ccwgroup device reference for local processing. */
 	put_device(&gdev->dev);
 }
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 77f9c92d..2905d8b 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -602,6 +602,7 @@
 
 #ifdef CONFIG_CCW_CONSOLE
 static struct subchannel *console_sch;
+static struct lock_class_key console_sch_key;
 
 /*
  * Use cio_tsch to update the subchannel status and call the interrupt handler
@@ -686,6 +687,7 @@
 	if (IS_ERR(sch))
 		return sch;
 
+	lockdep_set_class(sch->lock, &console_sch_key);
 	isc_register(CONSOLE_ISC);
 	sch->config.isc = CONSOLE_ISC;
 	sch->config.intparm = (u32)(addr_t)sch;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index d8d9b5b..dfef5e6 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -678,18 +678,11 @@
 	NULL,
 };
 
-/* this is a simple abstraction for device_register that sets the
- * correct bus type and adds the bus specific files */
-static int ccw_device_register(struct ccw_device *cdev)
+static int ccw_device_add(struct ccw_device *cdev)
 {
 	struct device *dev = &cdev->dev;
-	int ret;
 
 	dev->bus = &ccw_bus_type;
-	ret = dev_set_name(&cdev->dev, "0.%x.%04x", cdev->private->dev_id.ssid,
-			   cdev->private->dev_id.devno);
-	if (ret)
-		return ret;
 	return device_add(dev);
 }
 
@@ -764,22 +757,46 @@
 static int io_subchannel_initialize_dev(struct subchannel *sch,
 					struct ccw_device *cdev)
 {
-	cdev->private->cdev = cdev;
-	cdev->private->int_class = IRQIO_CIO;
-	atomic_set(&cdev->private->onoff, 0);
+	struct ccw_device_private *priv = cdev->private;
+	int ret;
+
+	priv->cdev = cdev;
+	priv->int_class = IRQIO_CIO;
+	priv->state = DEV_STATE_NOT_OPER;
+	priv->dev_id.devno = sch->schib.pmcw.dev;
+	priv->dev_id.ssid = sch->schid.ssid;
+	priv->schid = sch->schid;
+
+	INIT_WORK(&priv->todo_work, ccw_device_todo);
+	INIT_LIST_HEAD(&priv->cmb_list);
+	init_waitqueue_head(&priv->wait_q);
+	init_timer(&priv->timer);
+
+	atomic_set(&priv->onoff, 0);
+	cdev->ccwlock = sch->lock;
 	cdev->dev.parent = &sch->dev;
 	cdev->dev.release = ccw_device_release;
-	INIT_WORK(&cdev->private->todo_work, ccw_device_todo);
 	cdev->dev.groups = ccwdev_attr_groups;
 	/* Do first half of device_register. */
 	device_initialize(&cdev->dev);
+	ret = dev_set_name(&cdev->dev, "0.%x.%04x", cdev->private->dev_id.ssid,
+			   cdev->private->dev_id.devno);
+	if (ret)
+		goto out_put;
 	if (!get_device(&sch->dev)) {
-		/* Release reference from device_initialize(). */
-		put_device(&cdev->dev);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_put;
 	}
-	cdev->private->flags.initialized = 1;
+	priv->flags.initialized = 1;
+	spin_lock_irq(sch->lock);
+	sch_set_cdev(sch, cdev);
+	spin_unlock_irq(sch->lock);
 	return 0;
+
+out_put:
+	/* Release reference from device_initialize(). */
+	put_device(&cdev->dev);
+	return ret;
 }
 
 static struct ccw_device * io_subchannel_create_ccwdev(struct subchannel *sch)
@@ -858,7 +875,7 @@
 	dev_set_uevent_suppress(&sch->dev, 0);
 	kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
 	/* make it known to the system */
-	ret = ccw_device_register(cdev);
+	ret = ccw_device_add(cdev);
 	if (ret) {
 		CIO_MSG_EVENT(0, "Could not register ccw dev 0.%x.%04x: %d\n",
 			      cdev->private->dev_id.ssid,
@@ -923,26 +940,11 @@
 
 static void io_subchannel_recog(struct ccw_device *cdev, struct subchannel *sch)
 {
-	struct ccw_device_private *priv;
-
-	cdev->ccwlock = sch->lock;
-
-	/* Init private data. */
-	priv = cdev->private;
-	priv->dev_id.devno = sch->schib.pmcw.dev;
-	priv->dev_id.ssid = sch->schid.ssid;
-	priv->schid = sch->schid;
-	priv->state = DEV_STATE_NOT_OPER;
-	INIT_LIST_HEAD(&priv->cmb_list);
-	init_waitqueue_head(&priv->wait_q);
-	init_timer(&priv->timer);
-
 	/* Increase counter of devices currently in recognition. */
 	atomic_inc(&ccw_device_init_count);
 
 	/* Start async. device sensing. */
 	spin_lock_irq(sch->lock);
-	sch_set_cdev(sch, cdev);
 	ccw_device_recognition(cdev);
 	spin_unlock_irq(sch->lock);
 }
@@ -1083,7 +1085,7 @@
 		dev_set_uevent_suppress(&sch->dev, 0);
 		kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
 		cdev = sch_get_cdev(sch);
-		rc = ccw_device_register(cdev);
+		rc = ccw_device_add(cdev);
 		if (rc) {
 			/* Release online reference. */
 			put_device(&cdev->dev);
@@ -1597,7 +1599,6 @@
 	if (rc)
 		return rc;
 	sch->driver = &io_subchannel_driver;
-	sch_set_cdev(sch, cdev);
 	io_subchannel_recog(cdev, sch);
 	/* Now wait for the async. recognition to come to an end. */
 	spin_lock_irq(cdev->ccwlock);
@@ -1639,6 +1640,7 @@
 		put_device(&sch->dev);
 		return ERR_PTR(-ENOMEM);
 	}
+	set_io_private(sch, io_priv);
 	cdev = io_subchannel_create_ccwdev(sch);
 	if (IS_ERR(cdev)) {
 		put_device(&sch->dev);
@@ -1646,7 +1648,6 @@
 		return cdev;
 	}
 	cdev->drv = drv;
-	set_io_private(sch, io_priv);
 	ccw_device_set_int_class(cdev);
 	return cdev;
 }
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index 4221b02..f1f3baa 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -7,6 +7,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/export.h>
+#include <linux/slab.h>
 #include <asm/debug.h>
 #include "qdio_debug.h"
 #include "qdio.h"
@@ -16,11 +17,51 @@
 
 static struct dentry *debugfs_root;
 #define QDIO_DEBUGFS_NAME_LEN	10
+#define QDIO_DBF_NAME_LEN	20
 
-void qdio_allocate_dbf(struct qdio_initialize *init_data,
+struct qdio_dbf_entry {
+	char dbf_name[QDIO_DBF_NAME_LEN];
+	debug_info_t *dbf_info;
+	struct list_head dbf_list;
+};
+
+static LIST_HEAD(qdio_dbf_list);
+static DEFINE_MUTEX(qdio_dbf_list_mutex);
+
+static debug_info_t *qdio_get_dbf_entry(char *name)
+{
+	struct qdio_dbf_entry *entry;
+	debug_info_t *rc = NULL;
+
+	mutex_lock(&qdio_dbf_list_mutex);
+	list_for_each_entry(entry, &qdio_dbf_list, dbf_list) {
+		if (strcmp(entry->dbf_name, name) == 0) {
+			rc = entry->dbf_info;
+			break;
+		}
+	}
+	mutex_unlock(&qdio_dbf_list_mutex);
+	return rc;
+}
+
+static void qdio_clear_dbf_list(void)
+{
+	struct qdio_dbf_entry *entry, *tmp;
+
+	mutex_lock(&qdio_dbf_list_mutex);
+	list_for_each_entry_safe(entry, tmp, &qdio_dbf_list, dbf_list) {
+		list_del(&entry->dbf_list);
+		debug_unregister(entry->dbf_info);
+		kfree(entry);
+	}
+	mutex_unlock(&qdio_dbf_list_mutex);
+}
+
+int qdio_allocate_dbf(struct qdio_initialize *init_data,
 		       struct qdio_irq *irq_ptr)
 {
-	char text[20];
+	char text[QDIO_DBF_NAME_LEN];
+	struct qdio_dbf_entry *new_entry;
 
 	DBF_EVENT("qfmt:%1d", init_data->q_format);
 	DBF_HEX(init_data->adapter_name, 8);
@@ -38,11 +79,34 @@
 	DBF_EVENT("irq:%8lx", (unsigned long)irq_ptr);
 
 	/* allocate trace view for the interface */
-	snprintf(text, 20, "qdio_%s", dev_name(&init_data->cdev->dev));
-	irq_ptr->debug_area = debug_register(text, 2, 1, 16);
-	debug_register_view(irq_ptr->debug_area, &debug_hex_ascii_view);
-	debug_set_level(irq_ptr->debug_area, DBF_WARN);
-	DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf created");
+	snprintf(text, QDIO_DBF_NAME_LEN, "qdio_%s",
+					dev_name(&init_data->cdev->dev));
+	irq_ptr->debug_area = qdio_get_dbf_entry(text);
+	if (irq_ptr->debug_area)
+		DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf reused");
+	else {
+		irq_ptr->debug_area = debug_register(text, 2, 1, 16);
+		if (!irq_ptr->debug_area)
+			return -ENOMEM;
+		if (debug_register_view(irq_ptr->debug_area,
+						&debug_hex_ascii_view)) {
+			debug_unregister(irq_ptr->debug_area);
+			return -ENOMEM;
+		}
+		debug_set_level(irq_ptr->debug_area, DBF_WARN);
+		DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf created");
+		new_entry = kzalloc(sizeof(struct qdio_dbf_entry), GFP_KERNEL);
+		if (!new_entry) {
+			debug_unregister(irq_ptr->debug_area);
+			return -ENOMEM;
+		}
+		strlcpy(new_entry->dbf_name, text, QDIO_DBF_NAME_LEN);
+		new_entry->dbf_info = irq_ptr->debug_area;
+		mutex_lock(&qdio_dbf_list_mutex);
+		list_add(&new_entry->dbf_list, &qdio_dbf_list);
+		mutex_unlock(&qdio_dbf_list_mutex);
+	}
+	return 0;
 }
 
 static int qstat_show(struct seq_file *m, void *v)
@@ -300,6 +364,7 @@
 
 void qdio_debug_exit(void)
 {
+	qdio_clear_dbf_list();
 	debugfs_remove(debugfs_root);
 	if (qdio_dbf_setup)
 		debug_unregister(qdio_dbf_setup);
diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h
index dfac9bf..f33ce85 100644
--- a/drivers/s390/cio/qdio_debug.h
+++ b/drivers/s390/cio/qdio_debug.h
@@ -75,7 +75,7 @@
 	}
 }
 
-void qdio_allocate_dbf(struct qdio_initialize *init_data,
+int qdio_allocate_dbf(struct qdio_initialize *init_data,
 		       struct qdio_irq *irq_ptr);
 void qdio_setup_debug_entries(struct qdio_irq *irq_ptr,
 			      struct ccw_device *cdev);
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 77466c4..848e3b6 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -409,17 +409,16 @@
 		set_buf_state(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT);
 }
 
-static inline void account_sbals(struct qdio_q *q, int count)
+static inline void account_sbals(struct qdio_q *q, unsigned int count)
 {
-	int pos = 0;
+	int pos;
 
 	q->q_stats.nr_sbal_total += count;
 	if (count == QDIO_MAX_BUFFERS_MASK) {
 		q->q_stats.nr_sbals[7]++;
 		return;
 	}
-	while (count >>= 1)
-		pos++;
+	pos = ilog2(count);
 	q->q_stats.nr_sbals[pos]++;
 }
 
@@ -1234,12 +1233,10 @@
 		return -ENODEV;
 
 	DBF_EVENT("qfree:%4x", cdev->private->schid.sch_no);
+	DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf abandoned");
 	mutex_lock(&irq_ptr->setup_mutex);
 
-	if (irq_ptr->debug_area != NULL) {
-		debug_unregister(irq_ptr->debug_area);
-		irq_ptr->debug_area = NULL;
-	}
+	irq_ptr->debug_area = NULL;
 	cdev->private->qdio_data = NULL;
 	mutex_unlock(&irq_ptr->setup_mutex);
 
@@ -1276,7 +1273,8 @@
 		goto out_err;
 
 	mutex_init(&irq_ptr->setup_mutex);
-	qdio_allocate_dbf(init_data, irq_ptr);
+	if (qdio_allocate_dbf(init_data, irq_ptr))
+		goto out_rel;
 
 	/*
 	 * Allocate a page for the chsc calls in qdio_establish.
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 8eec165..69ef4f8 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -77,12 +77,12 @@
  * Module parameter
  */
 int ap_domain_index = -1;	/* Adjunct Processor Domain Index */
-module_param_named(domain, ap_domain_index, int, 0000);
+module_param_named(domain, ap_domain_index, int, S_IRUSR|S_IRGRP);
 MODULE_PARM_DESC(domain, "domain index for ap devices");
 EXPORT_SYMBOL(ap_domain_index);
 
 static int ap_thread_flag = 0;
-module_param_named(poll_thread, ap_thread_flag, int, 0000);
+module_param_named(poll_thread, ap_thread_flag, int, S_IRUSR|S_IRGRP);
 MODULE_PARM_DESC(poll_thread, "Turn on/off poll thread, default is 0 (off).");
 
 static struct device *ap_root_device = NULL;
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 5222ebe..0e18c5d 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -356,7 +356,7 @@
 
 	zops = __ops_lookup(name, variant);
 	if (!zops) {
-		request_module(name);
+		request_module("%s", name);
 		zops = __ops_lookup(name, variant);
 	}
 	if ((!zops) || (!try_module_get(zops->owner)))
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 5858600..31184b3 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -48,6 +48,7 @@
 #include <linux/bitmap.h>
 #include <linux/atomic.h>
 #include <linux/jiffies.h>
+#include <linux/percpu.h>
 #include <asm/div64.h>
 #include "hpsa_cmd.h"
 #include "hpsa.h"
@@ -193,7 +194,8 @@
 static irqreturn_t do_hpsa_intr_intx(int irq, void *dev_id);
 static irqreturn_t do_hpsa_intr_msi(int irq, void *dev_id);
 static int hpsa_ioctl(struct scsi_device *dev, int cmd, void *arg);
-static void start_io(struct ctlr_info *h);
+static void lock_and_start_io(struct ctlr_info *h);
+static void start_io(struct ctlr_info *h, unsigned long *flags);
 
 #ifdef CONFIG_COMPAT
 static int hpsa_compat_ioctl(struct scsi_device *dev, int cmd, void *arg);
@@ -695,7 +697,7 @@
 static inline u32 next_command(struct ctlr_info *h, u8 q)
 {
 	u32 a;
-	struct reply_pool *rq = &h->reply_queue[q];
+	struct reply_queue_buffer *rq = &h->reply_queue[q];
 	unsigned long flags;
 
 	if (h->transMethod & CFGTBL_Trans_io_accel1)
@@ -844,8 +846,8 @@
 	spin_lock_irqsave(&h->lock, flags);
 	addQ(&h->reqQ, c);
 	h->Qdepth++;
+	start_io(h, &flags);
 	spin_unlock_irqrestore(&h->lock, flags);
-	start_io(h);
 }
 
 static inline void removeQ(struct CommandList *c)
@@ -1554,9 +1556,13 @@
 			dev_warn(&h->pdev->dev,
 				"%s: task complete with check condition.\n",
 				"HP SSD Smart Path");
+			cmd->result |= SAM_STAT_CHECK_CONDITION;
 			if (c2->error_data.data_present !=
-					IOACCEL2_SENSE_DATA_PRESENT)
+					IOACCEL2_SENSE_DATA_PRESENT) {
+				memset(cmd->sense_buffer, 0,
+					SCSI_SENSE_BUFFERSIZE);
 				break;
+			}
 			/* copy the sense data */
 			data_len = c2->error_data.sense_data_len;
 			if (data_len > SCSI_SENSE_BUFFERSIZE)
@@ -1566,7 +1572,6 @@
 					sizeof(c2->error_data.sense_data_buff);
 			memcpy(cmd->sense_buffer,
 				c2->error_data.sense_data_buff, data_len);
-			cmd->result |= SAM_STAT_CHECK_CONDITION;
 			retry = 1;
 			break;
 		case IOACCEL2_STATUS_SR_TASK_COMP_BUSY:
@@ -1651,16 +1656,6 @@
 	if (is_logical_dev_addr_mode(dev->scsi3addr) &&
 		c2->error_data.serv_response ==
 			IOACCEL2_SERV_RESPONSE_FAILURE) {
-		if (c2->error_data.status ==
-			IOACCEL2_STATUS_SR_IOACCEL_DISABLED)
-			dev_warn(&h->pdev->dev,
-				"%s: Path is unavailable, retrying on standard path.\n",
-				"HP SSD Smart Path");
-		else
-			dev_warn(&h->pdev->dev,
-				"%s: Error 0x%02x, retrying on standard path.\n",
-				"HP SSD Smart Path", c2->error_data.status);
-
 		dev->offload_enabled = 0;
 		h->drv_req_rescan = 1;	/* schedule controller for a rescan */
 		cmd->result = DID_SOFT_ERROR << 16;
@@ -1991,20 +1986,26 @@
 	wait_for_completion(&wait);
 }
 
+static u32 lockup_detected(struct ctlr_info *h)
+{
+	int cpu;
+	u32 rc, *lockup_detected;
+
+	cpu = get_cpu();
+	lockup_detected = per_cpu_ptr(h->lockup_detected, cpu);
+	rc = *lockup_detected;
+	put_cpu();
+	return rc;
+}
+
 static void hpsa_scsi_do_simple_cmd_core_if_no_lockup(struct ctlr_info *h,
 	struct CommandList *c)
 {
-	unsigned long flags;
-
 	/* If controller lockup detected, fake a hardware error. */
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h)))
 		c->err_info->CommandStatus = CMD_HARDWARE_ERR;
-	} else {
-		spin_unlock_irqrestore(&h->lock, flags);
+	else
 		hpsa_scsi_do_simple_cmd_core(h, c);
-	}
 }
 
 #define MAX_DRIVER_CMD_RETRIES 25
@@ -2429,7 +2430,7 @@
 		buflen = 16;
 	buf = kzalloc(64, GFP_KERNEL);
 	if (!buf)
-		return -1;
+		return -ENOMEM;
 	rc = hpsa_scsi_do_inquiry(h, scsi3addr, VPD_PAGE | 0x83, buf, 64);
 	if (rc == 0)
 		memcpy(device_id, &buf[8], buflen);
@@ -2515,27 +2516,21 @@
 		return HPSA_VPD_LV_STATUS_UNSUPPORTED;
 
 	/* Does controller have VPD for logical volume status? */
-	if (!hpsa_vpd_page_supported(h, scsi3addr, HPSA_VPD_LV_STATUS)) {
-		dev_warn(&h->pdev->dev, "Logical volume status VPD page is unsupported.\n");
+	if (!hpsa_vpd_page_supported(h, scsi3addr, HPSA_VPD_LV_STATUS))
 		goto exit_failed;
-	}
 
 	/* Get the size of the VPD return buffer */
 	rc = hpsa_scsi_do_inquiry(h, scsi3addr, VPD_PAGE | HPSA_VPD_LV_STATUS,
 					buf, HPSA_VPD_HEADER_SZ);
-	if (rc != 0) {
-		dev_warn(&h->pdev->dev, "Logical volume status VPD inquiry failed.\n");
+	if (rc != 0)
 		goto exit_failed;
-	}
 	size = buf[3];
 
 	/* Now get the whole VPD buffer */
 	rc = hpsa_scsi_do_inquiry(h, scsi3addr, VPD_PAGE | HPSA_VPD_LV_STATUS,
 					buf, size + HPSA_VPD_HEADER_SZ);
-	if (rc != 0) {
-		dev_warn(&h->pdev->dev, "Logical volume status VPD inquiry failed.\n");
+	if (rc != 0)
 		goto exit_failed;
-	}
 	status = buf[4]; /* status byte */
 
 	kfree(buf);
@@ -2548,11 +2543,11 @@
 /* Determine offline status of a volume.
  * Return either:
  *  0 (not offline)
- * -1 (offline for unknown reasons)
+ *  0xff (offline for unknown reasons)
  *  # (integer code indicating one of several NOT READY states
  *     describing why a volume is to be kept offline)
  */
-static unsigned char hpsa_volume_offline(struct ctlr_info *h,
+static int hpsa_volume_offline(struct ctlr_info *h,
 					unsigned char scsi3addr[])
 {
 	struct CommandList *c;
@@ -2651,11 +2646,15 @@
 
 	if (this_device->devtype == TYPE_DISK &&
 		is_logical_dev_addr_mode(scsi3addr)) {
+		int volume_offline;
+
 		hpsa_get_raid_level(h, scsi3addr, &this_device->raid_level);
 		if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC)
 			hpsa_get_ioaccel_status(h, scsi3addr, this_device);
-		this_device->volume_offline =
-			hpsa_volume_offline(h, scsi3addr);
+		volume_offline = hpsa_volume_offline(h, scsi3addr);
+		if (volume_offline < 0 || volume_offline > 0xff)
+			volume_offline = HPSA_VPD_LV_STATUS_UNSUPPORTED;
+		this_device->volume_offline = volume_offline & 0xff;
 	} else {
 		this_device->raid_level = RAID_UNKNOWN;
 		this_device->offload_config = 0;
@@ -2861,26 +2860,20 @@
 	nphysicals = be32_to_cpu(*((__be32 *)physicals->LUNListLength)) /
 							responsesize;
 
-
 	/* find ioaccel2 handle in list of physicals: */
 	for (i = 0; i < nphysicals; i++) {
+		struct ext_report_lun_entry *entry = &physicals->LUN[i];
+
 		/* handle is in bytes 28-31 of each lun */
-		if (memcmp(&((struct ReportExtendedLUNdata *)
-				physicals)->LUN[i][20], &find, 4) != 0) {
+		if (entry->ioaccel_handle != find)
 			continue; /* didn't match */
-		}
 		found = 1;
-		memcpy(scsi3addr, &((struct ReportExtendedLUNdata *)
-					physicals)->LUN[i][0], 8);
+		memcpy(scsi3addr, entry->lunid, 8);
 		if (h->raid_offload_debug > 0)
 			dev_info(&h->pdev->dev,
-				"%s: Searched h=0x%08x, Found h=0x%08x, scsiaddr 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
+				"%s: Searched h=0x%08x, Found h=0x%08x, scsiaddr 0x%8phN\n",
 				__func__, find,
-				((struct ReportExtendedLUNdata *)
-					physicals)->LUN[i][20],
-				scsi3addr[0], scsi3addr[1], scsi3addr[2],
-				scsi3addr[3], scsi3addr[4], scsi3addr[5],
-				scsi3addr[6], scsi3addr[7]);
+				entry->ioaccel_handle, scsi3addr);
 		break; /* found it */
 	}
 
@@ -2965,7 +2958,8 @@
 		return RAID_CTLR_LUNID;
 
 	if (i < logicals_start)
-		return &physdev_list->LUN[i - (raid_ctlr_position == 0)][0];
+		return &physdev_list->LUN[i -
+				(raid_ctlr_position == 0)].lunid[0];
 
 	if (i < last_device)
 		return &logdev_list->LUN[i - nphysicals -
@@ -3074,7 +3068,7 @@
 		ndev_allocated++;
 	}
 
-	if (unlikely(is_scsi_rev_5(h)))
+	if (is_scsi_rev_5(h))
 		raid_ctlr_position = 0;
 	else
 		raid_ctlr_position = nphysicals + nlogicals;
@@ -3971,7 +3965,6 @@
 	struct hpsa_scsi_dev_t *dev;
 	unsigned char scsi3addr[8];
 	struct CommandList *c;
-	unsigned long flags;
 	int rc = 0;
 
 	/* Get the ptr to our adapter structure out of cmd->host. */
@@ -3984,14 +3977,11 @@
 	}
 	memcpy(scsi3addr, dev->scsi3addr, sizeof(scsi3addr));
 
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h))) {
 		cmd->result = DID_ERROR << 16;
 		done(cmd);
 		return 0;
 	}
-	spin_unlock_irqrestore(&h->lock, flags);
 	c = cmd_alloc(h);
 	if (c == NULL) {			/* trouble... */
 		dev_err(&h->pdev->dev, "cmd_alloc returned NULL!\n");
@@ -4103,16 +4093,13 @@
 	 * we can prevent new rescan threads from piling up on a
 	 * locked up controller.
 	 */
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h))) {
 		spin_lock_irqsave(&h->scan_lock, flags);
 		h->scan_finished = 1;
 		wake_up_all(&h->scan_wait_queue);
 		spin_unlock_irqrestore(&h->scan_lock, flags);
 		return 1;
 	}
-	spin_unlock_irqrestore(&h->lock, flags);
 	return 0;
 }
 
@@ -4963,7 +4950,7 @@
 		buff = kmalloc(iocommand.buf_size, GFP_KERNEL);
 		if (buff == NULL)
 			return -EFAULT;
-		if (iocommand.Request.Type.Direction == XFER_WRITE) {
+		if (iocommand.Request.Type.Direction & XFER_WRITE) {
 			/* Copy the data into the buffer we created */
 			if (copy_from_user(buff, iocommand.buf,
 				iocommand.buf_size)) {
@@ -5026,7 +5013,7 @@
 		rc = -EFAULT;
 		goto out;
 	}
-	if (iocommand.Request.Type.Direction == XFER_READ &&
+	if ((iocommand.Request.Type.Direction & XFER_READ) &&
 		iocommand.buf_size > 0) {
 		/* Copy the data out of the buffer we created */
 		if (copy_to_user(iocommand.buf, buff, iocommand.buf_size)) {
@@ -5103,7 +5090,7 @@
 			status = -ENOMEM;
 			goto cleanup1;
 		}
-		if (ioc->Request.Type.Direction == XFER_WRITE) {
+		if (ioc->Request.Type.Direction & XFER_WRITE) {
 			if (copy_from_user(buff[sg_used], data_ptr, sz)) {
 				status = -ENOMEM;
 				goto cleanup1;
@@ -5155,7 +5142,7 @@
 		status = -EFAULT;
 		goto cleanup0;
 	}
-	if (ioc->Request.Type.Direction == XFER_READ && ioc->buf_size > 0) {
+	if ((ioc->Request.Type.Direction & XFER_READ) && ioc->buf_size > 0) {
 		/* Copy the data out of the buffer we created */
 		BYTE __user *ptr = ioc->buf;
 		for (i = 0; i < sg_used; i++) {
@@ -5459,13 +5446,12 @@
 
 /* Takes cmds off the submission queue and sends them to the hardware,
  * then puts them on the queue of cmds waiting for completion.
+ * Assumes h->lock is held
  */
-static void start_io(struct ctlr_info *h)
+static void start_io(struct ctlr_info *h, unsigned long *flags)
 {
 	struct CommandList *c;
-	unsigned long flags;
 
-	spin_lock_irqsave(&h->lock, flags);
 	while (!list_empty(&h->reqQ)) {
 		c = list_entry(h->reqQ.next, struct CommandList, list);
 		/* can't do anything if fifo is full */
@@ -5488,14 +5474,20 @@
 		 * condition.
 		 */
 		h->commands_outstanding++;
-		if (h->commands_outstanding > h->max_outstanding)
-			h->max_outstanding = h->commands_outstanding;
 
 		/* Tell the controller execute command */
-		spin_unlock_irqrestore(&h->lock, flags);
+		spin_unlock_irqrestore(&h->lock, *flags);
 		h->access.submit_command(h, c);
-		spin_lock_irqsave(&h->lock, flags);
+		spin_lock_irqsave(&h->lock, *flags);
 	}
+}
+
+static void lock_and_start_io(struct ctlr_info *h)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&h->lock, flags);
+	start_io(h, &flags);
 	spin_unlock_irqrestore(&h->lock, flags);
 }
 
@@ -5563,7 +5555,7 @@
 	else if (c->cmd_type == CMD_IOCTL_PEND)
 		complete(c->waiting);
 	if (unlikely(io_may_be_stalled))
-		start_io(h);
+		lock_and_start_io(h);
 }
 
 static inline u32 hpsa_tag_contains_index(u32 tag)
@@ -5840,12 +5832,12 @@
 		dev_info(&pdev->dev, "using doorbell to reset controller\n");
 		writel(use_doorbell, vaddr + SA5_DOORBELL);
 
-		/* PMC hardware guys tell us we need a 5 second delay after
+		/* PMC hardware guys tell us we need a 10 second delay after
 		 * doorbell reset and before any attempt to talk to the board
 		 * at all to ensure that this actually works and doesn't fall
 		 * over in some weird corner cases.
 		 */
-		msleep(5000);
+		msleep(10000);
 	} else { /* Try to do it the PCI power state way */
 
 		/* Quoting from the Open CISS Specification: "The Power
@@ -6166,6 +6158,8 @@
 	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSIX)) {
 		dev_info(&h->pdev->dev, "MSIX\n");
 		h->msix_vector = MAX_REPLY_QUEUES;
+		if (h->msix_vector > num_online_cpus())
+			h->msix_vector = num_online_cpus();
 		err = pci_enable_msix(h->pdev, hpsa_msix_entries,
 				      h->msix_vector);
 		if (err > 0) {
@@ -6615,6 +6609,17 @@
 			h->ioaccel_cmd_pool, h->ioaccel_cmd_pool_dhandle);
 }
 
+static void hpsa_irq_affinity_hints(struct ctlr_info *h)
+{
+	int i, cpu, rc;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < h->msix_vector; i++) {
+		rc = irq_set_affinity_hint(h->intr[i], get_cpu_mask(cpu));
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+}
+
 static int hpsa_request_irq(struct ctlr_info *h,
 	irqreturn_t (*msixhandler)(int, void *),
 	irqreturn_t (*intxhandler)(int, void *))
@@ -6634,6 +6639,7 @@
 			rc = request_irq(h->intr[i], msixhandler,
 					0, h->devname,
 					&h->q[i]);
+		hpsa_irq_affinity_hints(h);
 	} else {
 		/* Use single reply pool */
 		if (h->msix_vector > 0 || h->msi_vector) {
@@ -6685,12 +6691,15 @@
 	if (!h->msix_vector || h->intr_mode != PERF_MODE_INT) {
 		/* Single reply queue, only one irq to free */
 		i = h->intr_mode;
+		irq_set_affinity_hint(h->intr[i], NULL);
 		free_irq(h->intr[i], &h->q[i]);
 		return;
 	}
 
-	for (i = 0; i < h->msix_vector; i++)
+	for (i = 0; i < h->msix_vector; i++) {
+		irq_set_affinity_hint(h->intr[i], NULL);
 		free_irq(h->intr[i], &h->q[i]);
+	}
 }
 
 static void hpsa_free_irqs_and_disable_msix(struct ctlr_info *h)
@@ -6707,6 +6716,20 @@
 #endif /* CONFIG_PCI_MSI */
 }
 
+static void hpsa_free_reply_queues(struct ctlr_info *h)
+{
+	int i;
+
+	for (i = 0; i < h->nreply_queues; i++) {
+		if (!h->reply_queue[i].head)
+			continue;
+		pci_free_consistent(h->pdev, h->reply_queue_size,
+			h->reply_queue[i].head, h->reply_queue[i].busaddr);
+		h->reply_queue[i].head = NULL;
+		h->reply_queue[i].busaddr = 0;
+	}
+}
+
 static void hpsa_undo_allocations_after_kdump_soft_reset(struct ctlr_info *h)
 {
 	hpsa_free_irqs_and_disable_msix(h);
@@ -6714,8 +6737,7 @@
 	hpsa_free_cmd_pool(h);
 	kfree(h->ioaccel1_blockFetchTable);
 	kfree(h->blockFetchTable);
-	pci_free_consistent(h->pdev, h->reply_pool_size,
-		h->reply_pool, h->reply_pool_dhandle);
+	hpsa_free_reply_queues(h);
 	if (h->vaddr)
 		iounmap(h->vaddr);
 	if (h->transtable)
@@ -6740,16 +6762,38 @@
 	}
 }
 
+static void set_lockup_detected_for_all_cpus(struct ctlr_info *h, u32 value)
+{
+	int i, cpu;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < num_online_cpus(); i++) {
+		u32 *lockup_detected;
+		lockup_detected = per_cpu_ptr(h->lockup_detected, cpu);
+		*lockup_detected = value;
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+	wmb(); /* be sure the per-cpu variables are out to memory */
+}
+
 static void controller_lockup_detected(struct ctlr_info *h)
 {
 	unsigned long flags;
+	u32 lockup_detected;
 
 	h->access.set_intr_mask(h, HPSA_INTR_OFF);
 	spin_lock_irqsave(&h->lock, flags);
-	h->lockup_detected = readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
+	lockup_detected = readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
+	if (!lockup_detected) {
+		/* no heartbeat, but controller gave us a zero. */
+		dev_warn(&h->pdev->dev,
+			"lockup detected but scratchpad register is zero\n");
+		lockup_detected = 0xffffffff;
+	}
+	set_lockup_detected_for_all_cpus(h, lockup_detected);
 	spin_unlock_irqrestore(&h->lock, flags);
 	dev_warn(&h->pdev->dev, "Controller lockup detected: 0x%08x\n",
-			h->lockup_detected);
+			lockup_detected);
 	pci_disable_device(h->pdev);
 	spin_lock_irqsave(&h->lock, flags);
 	fail_all_cmds_on_list(h, &h->cmpQ);
@@ -6884,7 +6928,7 @@
 	struct ctlr_info *h = container_of(to_delayed_work(work),
 					struct ctlr_info, monitor_ctlr_work);
 	detect_controller_lockup(h);
-	if (h->lockup_detected)
+	if (lockup_detected(h))
 		return;
 
 	if (hpsa_ctlr_needs_rescan(h) || hpsa_offline_devices_ready(h)) {
@@ -6934,7 +6978,6 @@
 	 * the 5 lower bits of the address are used by the hardware. and by
 	 * the driver.  See comments in hpsa.h for more info.
 	 */
-#define COMMANDLIST_ALIGNMENT 128
 	BUILD_BUG_ON(sizeof(struct CommandList) % COMMANDLIST_ALIGNMENT);
 	h = kzalloc(sizeof(*h), GFP_KERNEL);
 	if (!h)
@@ -6949,6 +6992,13 @@
 	spin_lock_init(&h->offline_device_lock);
 	spin_lock_init(&h->scan_lock);
 	spin_lock_init(&h->passthru_count_lock);
+
+	/* Allocate and clear per-cpu variable lockup_detected */
+	h->lockup_detected = alloc_percpu(u32);
+	if (!h->lockup_detected)
+		goto clean1;
+	set_lockup_detected_for_all_cpus(h, 0);
+
 	rc = hpsa_pci_init(h);
 	if (rc != 0)
 		goto clean1;
@@ -7072,6 +7122,8 @@
 	free_irqs(h);
 clean2:
 clean1:
+	if (h->lockup_detected)
+		free_percpu(h->lockup_detected);
 	kfree(h);
 	return rc;
 }
@@ -7080,16 +7132,10 @@
 {
 	char *flush_buf;
 	struct CommandList *c;
-	unsigned long flags;
 
 	/* Don't bother trying to flush the cache if locked up */
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h)))
 		return;
-	}
-	spin_unlock_irqrestore(&h->lock, flags);
-
 	flush_buf = kzalloc(4, GFP_KERNEL);
 	if (!flush_buf)
 		return;
@@ -7165,8 +7211,7 @@
 	pci_free_consistent(h->pdev,
 		h->nr_cmds * sizeof(struct ErrorInfo),
 		h->errinfo_pool, h->errinfo_pool_dhandle);
-	pci_free_consistent(h->pdev, h->reply_pool_size,
-		h->reply_pool, h->reply_pool_dhandle);
+	hpsa_free_reply_queues(h);
 	kfree(h->cmd_pool_bits);
 	kfree(h->blockFetchTable);
 	kfree(h->ioaccel1_blockFetchTable);
@@ -7174,6 +7219,7 @@
 	kfree(h->hba_inquiry_data);
 	pci_disable_device(pdev);
 	pci_release_regions(pdev);
+	free_percpu(h->lockup_detected);
 	kfree(h);
 }
 
@@ -7278,8 +7324,16 @@
 	 * 10 = 6 s/g entry or 24k
 	 */
 
+	/* If the controller supports either ioaccel method then
+	 * we can also use the RAID stack submit path that does not
+	 * perform the superfluous readl() after each command submission.
+	 */
+	if (trans_support & (CFGTBL_Trans_io_accel1 | CFGTBL_Trans_io_accel2))
+		access = SA5_performant_access_no_read;
+
 	/* Controller spec: zero out this buffer. */
-	memset(h->reply_pool, 0, h->reply_pool_size);
+	for (i = 0; i < h->nreply_queues; i++)
+		memset(h->reply_queue[i].head, 0, h->reply_queue_size);
 
 	bft[7] = SG_ENTRIES_IN_CMD + 4;
 	calc_bucket_map(bft, ARRAY_SIZE(bft),
@@ -7295,8 +7349,7 @@
 
 	for (i = 0; i < h->nreply_queues; i++) {
 		writel(0, &h->transtable->RepQAddr[i].upper);
-		writel(h->reply_pool_dhandle +
-			(h->max_commands * sizeof(u64) * i),
+		writel(h->reply_queue[i].busaddr,
 			&h->transtable->RepQAddr[i].lower);
 	}
 
@@ -7344,8 +7397,10 @@
 				h->ioaccel1_blockFetchTable);
 
 		/* initialize all reply queue entries to unused */
-		memset(h->reply_pool, (u8) IOACCEL_MODE1_REPLY_UNUSED,
-				h->reply_pool_size);
+		for (i = 0; i < h->nreply_queues; i++)
+			memset(h->reply_queue[i].head,
+				(u8) IOACCEL_MODE1_REPLY_UNUSED,
+				h->reply_queue_size);
 
 		/* set all the constant fields in the accelerator command
 		 * frames once at init time to save CPU cycles later.
@@ -7407,7 +7462,6 @@
 	 * because the 7 lower bits of the address are used by the
 	 * hardware.
 	 */
-#define IOACCEL1_COMMANDLIST_ALIGNMENT 128
 	BUILD_BUG_ON(sizeof(struct io_accel1_cmd) %
 			IOACCEL1_COMMANDLIST_ALIGNMENT);
 	h->ioaccel_cmd_pool =
@@ -7445,7 +7499,6 @@
 	if (h->ioaccel_maxsg > IOACCEL2_MAXSGENTRIES)
 		h->ioaccel_maxsg = IOACCEL2_MAXSGENTRIES;
 
-#define IOACCEL2_COMMANDLIST_ALIGNMENT 128
 	BUILD_BUG_ON(sizeof(struct io_accel2_cmd) %
 			IOACCEL2_COMMANDLIST_ALIGNMENT);
 	h->ioaccel2_cmd_pool =
@@ -7503,16 +7556,17 @@
 		}
 	}
 
-	/* TODO, check that this next line h->nreply_queues is correct */
 	h->nreply_queues = h->msix_vector > 0 ? h->msix_vector : 1;
 	hpsa_get_max_perf_mode_cmds(h);
 	/* Performant mode ring buffer and supporting data structures */
-	h->reply_pool_size = h->max_commands * sizeof(u64) * h->nreply_queues;
-	h->reply_pool = pci_alloc_consistent(h->pdev, h->reply_pool_size,
-				&(h->reply_pool_dhandle));
+	h->reply_queue_size = h->max_commands * sizeof(u64);
 
 	for (i = 0; i < h->nreply_queues; i++) {
-		h->reply_queue[i].head = &h->reply_pool[h->max_commands * i];
+		h->reply_queue[i].head = pci_alloc_consistent(h->pdev,
+						h->reply_queue_size,
+						&(h->reply_queue[i].busaddr));
+		if (!h->reply_queue[i].head)
+			goto clean_up;
 		h->reply_queue[i].size = h->max_commands;
 		h->reply_queue[i].wraparound = 1;  /* spec: init to 1 */
 		h->reply_queue[i].current_entry = 0;
@@ -7521,18 +7575,14 @@
 	/* Need a block fetch table for performant mode */
 	h->blockFetchTable = kmalloc(((SG_ENTRIES_IN_CMD + 1) *
 				sizeof(u32)), GFP_KERNEL);
-
-	if ((h->reply_pool == NULL)
-		|| (h->blockFetchTable == NULL))
+	if (!h->blockFetchTable)
 		goto clean_up;
 
 	hpsa_enter_performant_mode(h, trans_support);
 	return;
 
 clean_up:
-	if (h->reply_pool)
-		pci_free_consistent(h->pdev, h->reply_pool_size,
-			h->reply_pool, h->reply_pool_dhandle);
+	hpsa_free_reply_queues(h);
 	kfree(h->blockFetchTable);
 }
 
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 1e3cf33..24472ce 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -57,11 +57,12 @@
 
 };
 
-struct reply_pool {
+struct reply_queue_buffer {
 	u64 *head;
 	size_t size;
 	u8 wraparound;
 	u32 current_entry;
+	dma_addr_t busaddr;
 };
 
 #pragma pack(1)
@@ -116,11 +117,8 @@
 	int 	nr_cmds; /* Number of commands allowed on this controller */
 	struct CfgTable __iomem *cfgtable;
 	int	interrupts_enabled;
-	int	major;
 	int 	max_commands;
 	int	commands_outstanding;
-	int 	max_outstanding; /* Debug */
-	int	usage_count;  /* number of opens all all minor devices */
 #	define PERF_MODE_INT	0
 #	define DOORBELL_INT	1
 #	define SIMPLE_MODE_INT	2
@@ -177,11 +175,9 @@
 	/*
 	 * Performant mode completion buffers
 	 */
-	u64 *reply_pool;
-	size_t reply_pool_size;
-	struct reply_pool reply_queue[MAX_REPLY_QUEUES];
+	size_t reply_queue_size;
+	struct reply_queue_buffer reply_queue[MAX_REPLY_QUEUES];
 	u8 nreply_queues;
-	dma_addr_t reply_pool_dhandle;
 	u32 *blockFetchTable;
 	u32 *ioaccel1_blockFetchTable;
 	u32 *ioaccel2_blockFetchTable;
@@ -196,7 +192,7 @@
 	u64 last_heartbeat_timestamp;
 	u32 heartbeat_sample_interval;
 	atomic_t firmware_flash_in_progress;
-	u32 lockup_detected;
+	u32 *lockup_detected;
 	struct delayed_work monitor_ctlr_work;
 	int remove_in_progress;
 	u32 fifo_recently_full;
@@ -233,11 +229,9 @@
 #define CTLR_STATE_CHANGE_EVENT_AIO_CONFIG_CHANGE	(1 << 31)
 
 #define RESCAN_REQUIRED_EVENT_BITS \
-		(CTLR_STATE_CHANGE_EVENT | \
-		CTLR_ENCLOSURE_HOT_PLUG_EVENT | \
+		(CTLR_ENCLOSURE_HOT_PLUG_EVENT | \
 		CTLR_STATE_CHANGE_EVENT_PHYSICAL_DRV | \
 		CTLR_STATE_CHANGE_EVENT_LOGICAL_DRV | \
-		CTLR_STATE_CHANGE_EVENT_REDUNDANT_CNTRL | \
 		CTLR_STATE_CHANGE_EVENT_AIO_ENABLED_DISABLED | \
 		CTLR_STATE_CHANGE_EVENT_AIO_CONFIG_CHANGE)
 	spinlock_t offline_device_lock;
@@ -346,22 +340,23 @@
 static void SA5_submit_command(struct ctlr_info *h,
 	struct CommandList *c)
 {
-	dev_dbg(&h->pdev->dev, "Sending %x, tag = %x\n", c->busaddr,
-		c->Header.Tag.lower);
 	writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
 	(void) readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
 }
 
+static void SA5_submit_command_no_read(struct ctlr_info *h,
+	struct CommandList *c)
+{
+	writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
+}
+
 static void SA5_submit_command_ioaccel2(struct ctlr_info *h,
 	struct CommandList *c)
 {
-	dev_dbg(&h->pdev->dev, "Sending %x, tag = %x\n", c->busaddr,
-		c->Header.Tag.lower);
 	if (c->cmd_type == CMD_IOACCEL2)
 		writel(c->busaddr, h->vaddr + IOACCEL2_INBOUND_POSTQ_32);
 	else
 		writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
-	(void) readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
 }
 
 /*
@@ -399,7 +394,7 @@
 
 static unsigned long SA5_performant_completed(struct ctlr_info *h, u8 q)
 {
-	struct reply_pool *rq = &h->reply_queue[q];
+	struct reply_queue_buffer *rq = &h->reply_queue[q];
 	unsigned long flags, register_value = FIFO_EMPTY;
 
 	/* msi auto clears the interrupt pending bit. */
@@ -478,7 +473,6 @@
 {
 	unsigned long register_value  =
 		readl(h->vaddr + SA5_INTR_STATUS);
-	dev_dbg(&h->pdev->dev, "intr_pending %lx\n", register_value);
 	return register_value & SA5_INTR_PENDING;
 }
 
@@ -515,7 +509,7 @@
 static unsigned long SA5_ioaccel_mode1_completed(struct ctlr_info *h, u8 q)
 {
 	u64 register_value;
-	struct reply_pool *rq = &h->reply_queue[q];
+	struct reply_queue_buffer *rq = &h->reply_queue[q];
 	unsigned long flags;
 
 	BUG_ON(q >= h->nreply_queues);
@@ -573,6 +567,14 @@
 	SA5_performant_completed,
 };
 
+static struct access_method SA5_performant_access_no_read = {
+	SA5_submit_command_no_read,
+	SA5_performant_intr_mask,
+	SA5_fifo_full,
+	SA5_performant_intr_pending,
+	SA5_performant_completed,
+};
+
 struct board_type {
 	u32	board_id;
 	char	*product_name;
diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index b5cc705..b5125dc 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -151,7 +151,7 @@
 #define HPSA_VPD_HEADER_SZ              4
 
 /* Logical volume states */
-#define HPSA_VPD_LV_STATUS_UNSUPPORTED			-1
+#define HPSA_VPD_LV_STATUS_UNSUPPORTED			0xff
 #define HPSA_LV_OK                                      0x0
 #define HPSA_LV_UNDERGOING_ERASE			0x0F
 #define HPSA_LV_UNDERGOING_RPI				0x12
@@ -238,11 +238,21 @@
 	u8 LUN[HPSA_MAX_LUN][8];
 };
 
+struct ext_report_lun_entry {
+	u8 lunid[8];
+	u8 wwid[8];
+	u8 device_type;
+	u8 device_flags;
+	u8 lun_count; /* multi-lun device, how many luns */
+	u8 redundant_paths;
+	u32 ioaccel_handle; /* ioaccel1 only uses lower 16 bits */
+};
+
 struct ReportExtendedLUNdata {
 	u8 LUNListLength[4];
 	u8 extended_response_flag;
 	u8 reserved[3];
-	u8 LUN[HPSA_MAX_LUN][24];
+	struct ext_report_lun_entry LUN[HPSA_MAX_LUN];
 };
 
 struct SenseSubsystem_info {
@@ -375,6 +385,7 @@
  *        or a bus address.
  */
 
+#define COMMANDLIST_ALIGNMENT 128
 struct CommandList {
 	struct CommandListHeader Header;
 	struct RequestBlock      Request;
@@ -389,21 +400,7 @@
 	struct list_head list;
 	struct completion *waiting;
 	void   *scsi_cmd;
-
-/* on 64 bit architectures, to get this to be 32-byte-aligned
- * it so happens we need PAD_64 bytes of padding, on 32 bit systems,
- * we need PAD_32 bytes of padding (see below).   This does that.
- * If it happens that 64 bit and 32 bit systems need different
- * padding, PAD_32 and PAD_64 can be set independently, and.
- * the code below will do the right thing.
- */
-#define IS_32_BIT ((8 - sizeof(long))/4)
-#define IS_64_BIT (!IS_32_BIT)
-#define PAD_32 (40)
-#define PAD_64 (12)
-#define COMMANDLIST_PAD (IS_32_BIT * PAD_32 + IS_64_BIT * PAD_64)
-	u8 pad[COMMANDLIST_PAD];
-};
+} __aligned(COMMANDLIST_ALIGNMENT);
 
 /* Max S/G elements in I/O accelerator command */
 #define IOACCEL1_MAXSGENTRIES           24
@@ -413,6 +410,7 @@
  * Structure for I/O accelerator (mode 1) commands.
  * Note that this structure must be 128-byte aligned in size.
  */
+#define IOACCEL1_COMMANDLIST_ALIGNMENT 128
 struct io_accel1_cmd {
 	u16 dev_handle;			/* 0x00 - 0x01 */
 	u8  reserved1;			/* 0x02 */
@@ -440,12 +438,7 @@
 	struct vals32 host_addr;	/* 0x70 - 0x77 */
 	u8  CISS_LUN[8];		/* 0x78 - 0x7F */
 	struct SGDescriptor SG[IOACCEL1_MAXSGENTRIES];
-#define IOACCEL1_PAD_64 0
-#define IOACCEL1_PAD_32 0
-#define IOACCEL1_PAD (IS_32_BIT * IOACCEL1_PAD_32 + \
-			IS_64_BIT * IOACCEL1_PAD_64)
-	u8 pad[IOACCEL1_PAD];
-};
+} __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT);
 
 #define IOACCEL1_FUNCTION_SCSIIO        0x00
 #define IOACCEL1_SGLOFFSET              32
@@ -510,14 +503,11 @@
 	u8 sense_data_buff[32];		/* sense/response data buffer */
 };
 
-#define IOACCEL2_64_PAD 76
-#define IOACCEL2_32_PAD 76
-#define IOACCEL2_PAD (IS_32_BIT * IOACCEL2_32_PAD + \
-			IS_64_BIT * IOACCEL2_64_PAD)
 /*
  * Structure for I/O accelerator (mode 2 or m2) commands.
  * Note that this structure must be 128-byte aligned in size.
  */
+#define IOACCEL2_COMMANDLIST_ALIGNMENT 128
 struct io_accel2_cmd {
 	u8  IU_type;			/* IU Type */
 	u8  direction;			/* direction, memtype, and encryption */
@@ -544,8 +534,7 @@
 	u32 tweak_upper;		/* Encryption tweak, upper 4 bytes */
 	struct ioaccel2_sg_element sg[IOACCEL2_MAXSGENTRIES];
 	struct io_accel2_scsi_response error_data;
-	u8 pad[IOACCEL2_PAD];
-};
+} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
 
 /*
  * defines for Mode 2 command struct
@@ -636,7 +625,7 @@
 	u32            RepQCount;
 	u32            RepQCtrAddrLow32;
 	u32            RepQCtrAddrHigh32;
-#define MAX_REPLY_QUEUES 8
+#define MAX_REPLY_QUEUES 64
 	struct vals32  RepQAddr[MAX_REPLY_QUEUES];
 };
 
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 94a3caf..434e903 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -640,6 +640,7 @@
 #define HBA_DEVLOSS_TMO         0x2000 /* HBA in devloss timeout */
 #define HBA_RRQ_ACTIVE		0x4000 /* process the rrq active list */
 #define HBA_FCP_IOQ_FLUSH	0x8000 /* FCP I/O queues being flushed */
+#define HBA_FW_DUMP_OP		0x10000 /* Skips fn reset before FW dump */
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
 
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 8d5b6ce..1d7a5c3 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -919,10 +919,15 @@
 		phba->cfg_sriov_nr_virtfn = 0;
 	}
 
+	if (opcode == LPFC_FW_DUMP)
+		phba->hba_flag |= HBA_FW_DUMP_OP;
+
 	status = lpfc_do_offline(phba, LPFC_EVT_OFFLINE);
 
-	if (status != 0)
+	if (status != 0) {
+		phba->hba_flag &= ~HBA_FW_DUMP_OP;
 		return status;
+	}
 
 	/* wait for the device to be quiesced before firmware reset */
 	msleep(100);
@@ -2364,7 +2369,7 @@
 	uint8_t wwpn[WWN_SZ];
 	int rc;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	/* count may include a LF at end of string */
@@ -2432,7 +2437,7 @@
 	uint8_t wwpn[WWN_SZ];
 	int rc;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	/* count may include a LF at end of string */
@@ -2499,7 +2504,7 @@
 	struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
 	int val = 0;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (!isdigit(buf[0]))
@@ -2565,7 +2570,7 @@
 
 	int rc = 0;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (oas_state) {
@@ -2670,7 +2675,7 @@
 	uint64_t oas_lun;
 	int len = 0;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (wwn_to_u64(phba->cfg_oas_vpt_wwpn) == 0)
@@ -2716,7 +2721,7 @@
 	uint64_t scsi_lun;
 	ssize_t rc;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (wwn_to_u64(phba->cfg_oas_vpt_wwpn) == 0)
@@ -4655,7 +4660,7 @@
 #       0x0 - 0x7f  = CS_CTL field in FC header (high 7 bits)
 # Value range is [0x0,0x7f]. Default value is 0
 */
-LPFC_ATTR_R(XLanePriority, 0, 0x0, 0x7f, "CS_CTL for Express Lane Feature.");
+LPFC_ATTR_RW(XLanePriority, 0, 0x0, 0x7f, "CS_CTL for Express Lane Feature.");
 
 /*
 # lpfc_enable_bg: Enable BlockGuard (Emulex's Implementation of T10-DIF)
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index ca2f4ea..5b5c825 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2009-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index a94d4c9..928ef60 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2010-2012 Emulex.  All rights reserved.                *
+ * Copyright (C) 2010-2014 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index adda0bf..db5604f 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -289,6 +289,7 @@
 void lpfc_sli_pcimem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_bemem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_abort_iocb_ring(struct lpfc_hba *, struct lpfc_sli_ring *);
+void lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba);
 void lpfc_sli_hba_iocb_abort(struct lpfc_hba *);
 void lpfc_sli_flush_fcp_rings(struct lpfc_hba *);
 int lpfc_sli_ringpostbuf_put(struct lpfc_hba *, struct lpfc_sli_ring *,
@@ -310,6 +311,9 @@
 int lpfc_sli_sum_iocb(struct lpfc_vport *, uint16_t, uint64_t, lpfc_ctx_cmd);
 int lpfc_sli_abort_iocb(struct lpfc_vport *, struct lpfc_sli_ring *, uint16_t,
 			uint64_t, lpfc_ctx_cmd);
+int
+lpfc_sli_abort_taskmgmt(struct lpfc_vport *, struct lpfc_sli_ring *,
+			uint16_t, uint64_t, lpfc_ctx_cmd);
 
 void lpfc_mbox_timeout(unsigned long);
 void lpfc_mbox_timeout_handler(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 828c08e..b0aedce 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2007-2012 Emulex.  All rights reserved.           *
+ * Copyright (C) 2007-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -2314,7 +2314,7 @@
 			goto too_big;
 	}
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		/* OAS CQ */
 		qp = phba->sli4_hba.oas_cq;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 624fe0b..7a5d81a 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 294c072..2a17e31 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -5634,6 +5634,9 @@
 		ndlp->active_rrqs_xri_bitmap =
 				mempool_alloc(vport->phba->active_rrq_pool,
 					      GFP_KERNEL);
+		if (ndlp->active_rrqs_xri_bitmap)
+			memset(ndlp->active_rrqs_xri_bitmap, 0,
+			       ndlp->phba->cfg_rrq_xri_bitmap_sz);
 	}
 
 
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 3d9438c..2362592 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index fd79f7d..f432ec1 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2013 Emulex.  All rights reserved.                *
+ * Copyright (C) 2009-2014 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 635eeb3..06f9a5b 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -820,7 +820,139 @@
 }
 
 /**
+ * lpfc_sli4_free_sp_events - Cleanup sp_queue_events to free
+ * rspiocb which got deferred
+ *
+ * @phba: pointer to lpfc HBA data structure.
+ *
+ * This routine will cleanup completed slow path events after HBA is reset
+ * when bringing down the SLI Layer.
+ *
+ *
+ * Return codes
+ *   void.
+ **/
+static void
+lpfc_sli4_free_sp_events(struct lpfc_hba *phba)
+{
+	struct lpfc_iocbq *rspiocbq;
+	struct hbq_dmabuf *dmabuf;
+	struct lpfc_cq_event *cq_event;
+
+	spin_lock_irq(&phba->hbalock);
+	phba->hba_flag &= ~HBA_SP_QUEUE_EVT;
+	spin_unlock_irq(&phba->hbalock);
+
+	while (!list_empty(&phba->sli4_hba.sp_queue_event)) {
+		/* Get the response iocb from the head of work queue */
+		spin_lock_irq(&phba->hbalock);
+		list_remove_head(&phba->sli4_hba.sp_queue_event,
+				 cq_event, struct lpfc_cq_event, list);
+		spin_unlock_irq(&phba->hbalock);
+
+		switch (bf_get(lpfc_wcqe_c_code, &cq_event->cqe.wcqe_cmpl)) {
+		case CQE_CODE_COMPL_WQE:
+			rspiocbq = container_of(cq_event, struct lpfc_iocbq,
+						 cq_event);
+			lpfc_sli_release_iocbq(phba, rspiocbq);
+			break;
+		case CQE_CODE_RECEIVE:
+		case CQE_CODE_RECEIVE_V1:
+			dmabuf = container_of(cq_event, struct hbq_dmabuf,
+					      cq_event);
+			lpfc_in_buf_free(phba, &dmabuf->dbuf);
+		}
+	}
+}
+
+/**
+ * lpfc_hba_free_post_buf - Perform lpfc uninitialization after HBA reset
+ * @phba: pointer to lpfc HBA data structure.
+ *
+ * This routine will cleanup posted ELS buffers after the HBA is reset
+ * when bringing down the SLI Layer.
+ *
+ *
+ * Return codes
+ *   void.
+ **/
+static void
+lpfc_hba_free_post_buf(struct lpfc_hba *phba)
+{
+	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_sli_ring *pring;
+	struct lpfc_dmabuf *mp, *next_mp;
+	LIST_HEAD(buflist);
+	int count;
+
+	if (phba->sli3_options & LPFC_SLI3_HBQ_ENABLED)
+		lpfc_sli_hbqbuf_free_all(phba);
+	else {
+		/* Cleanup preposted buffers on the ELS ring */
+		pring = &psli->ring[LPFC_ELS_RING];
+		spin_lock_irq(&phba->hbalock);
+		list_splice_init(&pring->postbufq, &buflist);
+		spin_unlock_irq(&phba->hbalock);
+
+		count = 0;
+		list_for_each_entry_safe(mp, next_mp, &buflist, list) {
+			list_del(&mp->list);
+			count++;
+			lpfc_mbuf_free(phba, mp->virt, mp->phys);
+			kfree(mp);
+		}
+
+		spin_lock_irq(&phba->hbalock);
+		pring->postbufq_cnt -= count;
+		spin_unlock_irq(&phba->hbalock);
+	}
+}
+
+/**
+ * lpfc_hba_clean_txcmplq - Perform lpfc uninitialization after HBA reset
+ * @phba: pointer to lpfc HBA data structure.
+ *
+ * This routine will cleanup the txcmplq after the HBA is reset when bringing
+ * down the SLI Layer.
+ *
+ * Return codes
+ *   void
+ **/
+static void
+lpfc_hba_clean_txcmplq(struct lpfc_hba *phba)
+{
+	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_sli_ring *pring;
+	LIST_HEAD(completions);
+	int i;
+
+	for (i = 0; i < psli->num_rings; i++) {
+		pring = &psli->ring[i];
+		if (phba->sli_rev >= LPFC_SLI_REV4)
+			spin_lock_irq(&pring->ring_lock);
+		else
+			spin_lock_irq(&phba->hbalock);
+		/* At this point in time the HBA is either reset or DOA. Either
+		 * way, nothing should be on txcmplq as it will NEVER complete.
+		 */
+		list_splice_init(&pring->txcmplq, &completions);
+		pring->txcmplq_cnt = 0;
+
+		if (phba->sli_rev >= LPFC_SLI_REV4)
+			spin_unlock_irq(&pring->ring_lock);
+		else
+			spin_unlock_irq(&phba->hbalock);
+
+		/* Cancel all the IOCBs from the completions list */
+		lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_ABORTED);
+		lpfc_sli_abort_iocb_ring(phba, pring);
+	}
+}
+
+/**
  * lpfc_hba_down_post_s3 - Perform lpfc uninitialization after HBA reset
+	int i;
  * @phba: pointer to lpfc HBA data structure.
  *
  * This routine will do uninitialization after the HBA is reset when bring
@@ -833,44 +965,8 @@
 static int
 lpfc_hba_down_post_s3(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring;
-	struct lpfc_dmabuf *mp, *next_mp;
-	LIST_HEAD(completions);
-	int i;
-
-	if (phba->sli3_options & LPFC_SLI3_HBQ_ENABLED)
-		lpfc_sli_hbqbuf_free_all(phba);
-	else {
-		/* Cleanup preposted buffers on the ELS ring */
-		pring = &psli->ring[LPFC_ELS_RING];
-		list_for_each_entry_safe(mp, next_mp, &pring->postbufq, list) {
-			list_del(&mp->list);
-			pring->postbufq_cnt--;
-			lpfc_mbuf_free(phba, mp->virt, mp->phys);
-			kfree(mp);
-		}
-	}
-
-	spin_lock_irq(&phba->hbalock);
-	for (i = 0; i < psli->num_rings; i++) {
-		pring = &psli->ring[i];
-
-		/* At this point in time the HBA is either reset or DOA. Either
-		 * way, nothing should be on txcmplq as it will NEVER complete.
-		 */
-		list_splice_init(&pring->txcmplq, &completions);
-		spin_unlock_irq(&phba->hbalock);
-
-		/* Cancel all the IOCBs from the completions list */
-		lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
-				      IOERR_SLI_ABORTED);
-
-		lpfc_sli_abort_iocb_ring(phba, pring);
-		spin_lock_irq(&phba->hbalock);
-	}
-	spin_unlock_irq(&phba->hbalock);
-
+	lpfc_hba_free_post_buf(phba);
+	lpfc_hba_clean_txcmplq(phba);
 	return 0;
 }
 
@@ -890,13 +986,12 @@
 {
 	struct lpfc_scsi_buf *psb, *psb_next;
 	LIST_HEAD(aborts);
-	int ret;
 	unsigned long iflag = 0;
 	struct lpfc_sglq *sglq_entry = NULL;
 
-	ret = lpfc_hba_down_post_s3(phba);
-	if (ret)
-		return ret;
+	lpfc_hba_free_post_buf(phba);
+	lpfc_hba_clean_txcmplq(phba);
+
 	/* At this point in time the HBA is either reset or DOA. Either
 	 * way, nothing should be on lpfc_abts_els_sgl_list, it needs to be
 	 * on the lpfc_sgl_list so that it can either be freed if the
@@ -932,6 +1027,8 @@
 	spin_lock_irqsave(&phba->scsi_buf_list_put_lock, iflag);
 	list_splice(&aborts, &phba->lpfc_scsi_buf_list_put);
 	spin_unlock_irqrestore(&phba->scsi_buf_list_put_lock, iflag);
+
+	lpfc_sli4_free_sp_events(phba);
 	return 0;
 }
 
@@ -1250,7 +1347,6 @@
 lpfc_handle_deferred_eratt(struct lpfc_hba *phba)
 {
 	uint32_t old_host_status = phba->work_hs;
-	struct lpfc_sli_ring  *pring;
 	struct lpfc_sli *psli = &phba->sli;
 
 	/* If the pci channel is offline, ignore possible errors,
@@ -1279,8 +1375,7 @@
 	 * dropped by the firmware. Error iocb (I/O) on txcmplq and let the
 	 * SCSI layer retry it after re-establishing link.
 	 */
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 
 	/*
 	 * There was a firmware error. Take the hba offline and then
@@ -1348,7 +1443,6 @@
 {
 	struct lpfc_vport *vport = phba->pport;
 	struct lpfc_sli   *psli = &phba->sli;
-	struct lpfc_sli_ring  *pring;
 	uint32_t event_data;
 	unsigned long temperature;
 	struct temp_event temp_event_data;
@@ -1400,8 +1494,7 @@
 		* Error iocb (I/O) on txcmplq and let the SCSI layer
 		* retry it after re-establishing link.
 		*/
-		pring = &psli->ring[psli->fcp_ring];
-		lpfc_sli_abort_iocb_ring(phba, pring);
+		lpfc_sli_abort_fcp_rings(phba);
 
 		/*
 		 * There was a firmware error.  Take the hba offline and then
@@ -1940,78 +2033,81 @@
 
 	switch (dev_id) {
 	case PCI_DEVICE_ID_FIREFLY:
-		m = (typeof(m)){"LP6000", "PCI", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP6000", "PCI",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_SUPERFLY:
 		if (vp->rev.biuRev >= 1 && vp->rev.biuRev <= 3)
-			m = (typeof(m)){"LP7000", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP7000", "PCI", ""};
 		else
-			m = (typeof(m)){"LP7000E", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP7000E", "PCI", ""};
+		m.function = "Obsolete, Unsupported Fibre Channel Adapter";
 		break;
 	case PCI_DEVICE_ID_DRAGONFLY:
 		m = (typeof(m)){"LP8000", "PCI",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_CENTAUR:
 		if (FC_JEDEC_ID(vp->rev.biuRev) == CENTAUR_2G_JEDEC_ID)
-			m = (typeof(m)){"LP9002", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP9002", "PCI", ""};
 		else
-			m = (typeof(m)){"LP9000", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP9000", "PCI", ""};
+		m.function = "Obsolete, Unsupported Fibre Channel Adapter";
 		break;
 	case PCI_DEVICE_ID_RFLY:
 		m = (typeof(m)){"LP952", "PCI",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PEGASUS:
 		m = (typeof(m)){"LP9802", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_THOR:
 		m = (typeof(m)){"LP10000", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_VIPER:
 		m = (typeof(m)){"LPX1000",  "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PFLY:
 		m = (typeof(m)){"LP982", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_TFLY:
 		m = (typeof(m)){"LP1050", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HELIOS:
 		m = (typeof(m)){"LP11000", "PCI-X2",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HELIOS_SCSP:
 		m = (typeof(m)){"LP11000-SP", "PCI-X2",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HELIOS_DCSP:
 		m = (typeof(m)){"LP11002-SP",  "PCI-X2",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_NEPTUNE:
-		m = (typeof(m)){"LPe1000", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe1000", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_NEPTUNE_SCSP:
-		m = (typeof(m)){"LPe1000-SP", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe1000-SP", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_NEPTUNE_DCSP:
-		m = (typeof(m)){"LPe1002-SP", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe1002-SP", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_BMID:
 		m = (typeof(m)){"LP1150", "PCI-X2", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_BSMB:
-		m = (typeof(m)){"LP111", "PCI-X2", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP111", "PCI-X2",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_ZEPHYR:
 		m = (typeof(m)){"LPe11000", "PCIe", "Fibre Channel Adapter"};
@@ -2030,16 +2126,20 @@
 		m = (typeof(m)){"LPe111", "PCIe", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LP101:
-		m = (typeof(m)){"LP101", "PCI-X", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP101", "PCI-X",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LP10000S:
-		m = (typeof(m)){"LP10000-S", "PCI", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP10000-S", "PCI",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LP11000S:
-		m = (typeof(m)){"LP11000-S", "PCI-X2", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP11000-S", "PCI-X2",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LPE11000S:
-		m = (typeof(m)){"LPe11000-S", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe11000-S", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_SAT:
 		m = (typeof(m)){"LPe12000", "PCIe", "Fibre Channel Adapter"};
@@ -2060,20 +2160,21 @@
 		m = (typeof(m)){"LPe12000-S", "PCIe", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HORNET:
-		m = (typeof(m)){"LP21000", "PCIe", "FCoE Adapter"};
+		m = (typeof(m)){"LP21000", "PCIe",
+				"Obsolete, Unsupported FCoE Adapter"};
 		GE = 1;
 		break;
 	case PCI_DEVICE_ID_PROTEUS_VF:
 		m = (typeof(m)){"LPev12000", "PCIe IOV",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PROTEUS_PF:
 		m = (typeof(m)){"LPev12000", "PCIe IOV",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PROTEUS_S:
 		m = (typeof(m)){"LPemv12002-S", "PCIe IOV",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_TIGERSHARK:
 		oneConnect = 1;
@@ -2089,17 +2190,24 @@
 		break;
 	case PCI_DEVICE_ID_BALIUS:
 		m = (typeof(m)){"LPVe12002", "PCIe Shared I/O",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LANCER_FC:
-	case PCI_DEVICE_ID_LANCER_FC_VF:
 		m = (typeof(m)){"LPe16000", "PCIe", "Fibre Channel Adapter"};
 		break;
+	case PCI_DEVICE_ID_LANCER_FC_VF:
+		m = (typeof(m)){"LPe16000", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
+		break;
 	case PCI_DEVICE_ID_LANCER_FCOE:
-	case PCI_DEVICE_ID_LANCER_FCOE_VF:
 		oneConnect = 1;
 		m = (typeof(m)){"OCe15100", "PCIe", "FCoE"};
 		break;
+	case PCI_DEVICE_ID_LANCER_FCOE_VF:
+		oneConnect = 1;
+		m = (typeof(m)){"OCe15100", "PCIe",
+				"Obsolete, Unsupported FCoE"};
+		break;
 	case PCI_DEVICE_ID_SKYHAWK:
 	case PCI_DEVICE_ID_SKYHAWK_VF:
 		oneConnect = 1;
@@ -4614,7 +4722,10 @@
 		phba->link_state = LPFC_HBA_ERROR;
 		return;
 	}
-	lpfc_offline_prep(phba, LPFC_MBX_WAIT);
+	if (phba->sli.sli_flag & LPFC_SLI_ACTIVE)
+		lpfc_offline_prep(phba, LPFC_MBX_WAIT);
+	else
+		lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT);
 	lpfc_offline(phba);
 	lpfc_sli_brdrestart(phba);
 	lpfc_online(phba);
@@ -9663,9 +9774,6 @@
 static void
 lpfc_sli_prep_dev_for_recover(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring  *pring;
-
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			"2723 PCI channel I/O abort preparing for recovery\n");
 
@@ -9673,8 +9781,7 @@
 	 * There may be errored I/Os through HBA, abort all I/Os on txcmplq
 	 * and let the SCSI mid-layer to retry them to recover.
 	 */
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 }
 
 /**
@@ -10417,17 +10524,13 @@
 static void
 lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring  *pring;
-
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			"2828 PCI channel I/O abort preparing for recovery\n");
 	/*
 	 * There may be errored I/Os through HBA, abort all I/Os on txcmplq
 	 * and let the SCSI mid-layer to retry them to recover.
 	 */
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 }
 
 /**
@@ -10898,7 +11001,7 @@
 	if (phba->sli4_hba.pc_sli4_params.oas_supported) {
 		phba->cfg_fof = 1;
 	} else {
-		phba->cfg_EnableXLane = 0;
+		phba->cfg_fof = 0;
 		if (phba->device_data_mem_pool)
 			mempool_destroy(phba->device_data_mem_pool);
 		phba->device_data_mem_pool = NULL;
@@ -10928,7 +11031,7 @@
 	if (rc)
 		return -ENOMEM;
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		rc = lpfc_cq_create(phba, phba->sli4_hba.oas_cq,
 				    phba->sli4_hba.fof_eq, LPFC_WCQ, LPFC_FCP);
@@ -10947,8 +11050,7 @@
 	return 0;
 
 out_oas_wq:
-	if (phba->cfg_EnableXLane)
-		lpfc_cq_destroy(phba, phba->sli4_hba.oas_cq);
+	lpfc_cq_destroy(phba, phba->sli4_hba.oas_cq);
 out_oas_cq:
 	lpfc_eq_destroy(phba, phba->sli4_hba.fof_eq);
 	return rc;
@@ -10982,7 +11084,7 @@
 
 	phba->sli4_hba.fof_eq = qdesc;
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		/* Create OAS CQ */
 		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.cq_esize,
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index ed419aa..3fa6533 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 462453e..2df11da 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -73,7 +73,7 @@
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *)sdev->host->hostdata;
 
-	if (vport->phba->cfg_EnableXLane)
+	if (vport->phba->cfg_fof)
 		return ((struct lpfc_device_data *)sdev->hostdata)->rport_data;
 	else
 		return (struct lpfc_rport_data *)sdev->hostdata;
@@ -3462,7 +3462,7 @@
 	 * If the OAS driver feature is enabled and the lun is enabled for
 	 * OAS, set the oas iocb related flags.
 	 */
-	if ((phba->cfg_EnableXLane) && ((struct lpfc_device_data *)
+	if ((phba->cfg_fof) && ((struct lpfc_device_data *)
 		scsi_cmnd->device->hostdata)->oas_enabled)
 		lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_IO_OAS;
 	return 0;
@@ -4314,6 +4314,7 @@
 		fcp_cmnd->fcpCntl1 = SIMPLE_Q;
 
 	sli4 = (phba->sli_rev == LPFC_SLI_REV4);
+	piocbq->iocb.un.fcpi.fcpi_XRdy = 0;
 
 	/*
 	 * There are three possibilities here - use scatter-gather segment, use
@@ -4782,7 +4783,9 @@
 	struct lpfc_scsi_buf *lpfc_cmd;
 	IOCB_t *cmd, *icmd;
 	int ret = SUCCESS, status = 0;
-	unsigned long flags;
+	struct lpfc_sli_ring *pring_s4;
+	int ring_number, ret_val;
+	unsigned long flags, iflags;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
 
 	status = fc_block_scsi_eh(cmnd);
@@ -4833,6 +4836,14 @@
 
 	BUG_ON(iocb->context1 != lpfc_cmd);
 
+	/* abort issued in recovery is still in progress */
+	if (iocb->iocb_flag & LPFC_DRIVER_ABORTED) {
+		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
+			 "3389 SCSI Layer I/O Abort Request is pending\n");
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		goto wait_for_cmpl;
+	}
+
 	abtsiocb = __lpfc_sli_get_iocbq(phba);
 	if (abtsiocb == NULL) {
 		ret = FAILED;
@@ -4871,11 +4882,23 @@
 
 	abtsiocb->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
 	abtsiocb->vport = vport;
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		ring_number = MAX_SLI3_CONFIGURED_RINGS + iocb->fcp_wqidx;
+		pring_s4 = &phba->sli.ring[ring_number];
+		/* Note: both hbalock and ring_lock must be set here */
+		spin_lock_irqsave(&pring_s4->ring_lock, iflags);
+		ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
+						abtsiocb, 0);
+		spin_unlock_irqrestore(&pring_s4->ring_lock, iflags);
+	} else {
+		ret_val = __lpfc_sli_issue_iocb(phba, LPFC_FCP_RING,
+						abtsiocb, 0);
+	}
 	/* no longer need the lock after this point */
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
-	if (lpfc_sli_issue_iocb(phba, LPFC_FCP_RING, abtsiocb, 0) ==
-	    IOCB_ERROR) {
+
+	if (ret_val == IOCB_ERROR) {
 		lpfc_sli_release_iocbq(phba, abtsiocb);
 		ret = FAILED;
 		goto out;
@@ -4885,12 +4908,16 @@
 		lpfc_sli_handle_fast_ring_event(phba,
 			&phba->sli.ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
+wait_for_cmpl:
 	lpfc_cmd->waitq = &waitq;
 	/* Wait for abort to complete */
 	wait_event_timeout(waitq,
 			  (lpfc_cmd->pCmd != cmnd),
 			   msecs_to_jiffies(2*vport->cfg_devloss_tmo*1000));
+
+	spin_lock_irqsave(shost->host_lock, flags);
 	lpfc_cmd->waitq = NULL;
+	spin_unlock_irqrestore(shost->host_lock, flags);
 
 	if (lpfc_cmd->pCmd == cmnd) {
 		ret = FAILED;
@@ -5172,8 +5199,9 @@
 
 	cnt = lpfc_sli_sum_iocb(vport, tgt_id, lun_id, context);
 	if (cnt)
-		lpfc_sli_abort_iocb(vport, &phba->sli.ring[phba->sli.fcp_ring],
-				    tgt_id, lun_id, context);
+		lpfc_sli_abort_taskmgmt(vport,
+					&phba->sli.ring[phba->sli.fcp_ring],
+					tgt_id, lun_id, context);
 	later = msecs_to_jiffies(2 * vport->cfg_devloss_tmo * 1000) + jiffies;
 	while (time_after(later, jiffies) && cnt) {
 		schedule_timeout_uninterruptible(msecs_to_jiffies(20));
@@ -5491,7 +5519,7 @@
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		/*
 		 * Check to see if the device data structure for the lun
@@ -5616,7 +5644,7 @@
 	struct lpfc_device_data *device_data = sdev->hostdata;
 
 	atomic_dec(&phba->sdev_cnt);
-	if ((phba->cfg_EnableXLane) && (device_data)) {
+	if ((phba->cfg_fof) && (device_data)) {
 		spin_lock_irqsave(&phba->devicelock, flags);
 		device_data->available = false;
 		if (!device_data->oas_enabled)
@@ -5655,7 +5683,7 @@
 	int memory_flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn  ||
-	    !(phba->cfg_EnableXLane))
+	    !(phba->cfg_fof))
 		return NULL;
 
 	/* Attempt to create the device data to contain lun info */
@@ -5693,7 +5721,7 @@
 {
 
 	if (unlikely(!phba) || !lun_info  ||
-	    !(phba->cfg_EnableXLane))
+	    !(phba->cfg_fof))
 		return;
 
 	if (!list_empty(&lun_info->listentry))
@@ -5727,7 +5755,7 @@
 	struct lpfc_device_data *lun_info;
 
 	if (unlikely(!phba) || !list || !vport_wwpn || !target_wwpn ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return NULL;
 
 	/* Check to see if the lun is already enabled for OAS. */
@@ -5789,7 +5817,7 @@
 	    !starting_lun || !found_vport_wwpn ||
 	    !found_target_wwpn || !found_lun || !found_lun_status ||
 	    (*starting_lun == NO_MORE_OAS_LUN) ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return false;
 
 	lun = *starting_lun;
@@ -5873,7 +5901,7 @@
 	unsigned long flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return false;
 
 	spin_lock_irqsave(&phba->devicelock, flags);
@@ -5930,7 +5958,7 @@
 	unsigned long flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return false;
 
 	spin_lock_irqsave(&phba->devicelock, flags);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index 0120bfc..0389ac1 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 393662c..32ada05 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -3532,14 +3532,27 @@
 	/* Error everything on txq and txcmplq
 	 * First do the txq.
 	 */
-	spin_lock_irq(&phba->hbalock);
-	list_splice_init(&pring->txq, &completions);
+	if (phba->sli_rev >= LPFC_SLI_REV4) {
+		spin_lock_irq(&pring->ring_lock);
+		list_splice_init(&pring->txq, &completions);
+		pring->txq_cnt = 0;
+		spin_unlock_irq(&pring->ring_lock);
 
-	/* Next issue ABTS for everything on the txcmplq */
-	list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
-		lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+		spin_lock_irq(&phba->hbalock);
+		/* Next issue ABTS for everything on the txcmplq */
+		list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
+			lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+		spin_unlock_irq(&phba->hbalock);
+	} else {
+		spin_lock_irq(&phba->hbalock);
+		list_splice_init(&pring->txq, &completions);
+		pring->txq_cnt = 0;
 
-	spin_unlock_irq(&phba->hbalock);
+		/* Next issue ABTS for everything on the txcmplq */
+		list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
+			lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+		spin_unlock_irq(&phba->hbalock);
+	}
 
 	/* Cancel all the IOCBs from the completions list */
 	lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
@@ -3547,6 +3560,36 @@
 }
 
 /**
+ * lpfc_sli_abort_fcp_rings - Abort all iocbs in all FCP rings
+ * @phba: Pointer to HBA context object.
+ * @pring: Pointer to driver SLI ring object.
+ *
+ * This function aborts all iocbs in FCP rings and frees all the iocb
+ * objects in txq. This function issues an abort iocb for all the iocb commands
+ * in txcmplq. The iocbs in the txcmplq is not guaranteed to complete before
+ * the return of this function. The caller is not required to hold any locks.
+ **/
+void
+lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba)
+{
+	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_sli_ring  *pring;
+	uint32_t i;
+
+	/* Look on all the FCP Rings for the iotag */
+	if (phba->sli_rev >= LPFC_SLI_REV4) {
+		for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
+			pring = &psli->ring[i + MAX_SLI3_CONFIGURED_RINGS];
+			lpfc_sli_abort_iocb_ring(phba, pring);
+		}
+	} else {
+		pring = &psli->ring[psli->fcp_ring];
+		lpfc_sli_abort_iocb_ring(phba, pring);
+	}
+}
+
+
+/**
  * lpfc_sli_flush_fcp_rings - flush all iocbs in the fcp ring
  * @phba: Pointer to HBA context object.
  *
@@ -3563,28 +3606,55 @@
 	LIST_HEAD(txcmplq);
 	struct lpfc_sli *psli = &phba->sli;
 	struct lpfc_sli_ring  *pring;
-
-	/* Currently, only one fcp ring */
-	pring = &psli->ring[psli->fcp_ring];
+	uint32_t i;
 
 	spin_lock_irq(&phba->hbalock);
-	/* Retrieve everything on txq */
-	list_splice_init(&pring->txq, &txq);
-
-	/* Retrieve everything on the txcmplq */
-	list_splice_init(&pring->txcmplq, &txcmplq);
-
 	/* Indicate the I/O queues are flushed */
 	phba->hba_flag |= HBA_FCP_IOQ_FLUSH;
 	spin_unlock_irq(&phba->hbalock);
 
-	/* Flush the txq */
-	lpfc_sli_cancel_iocbs(phba, &txq, IOSTAT_LOCAL_REJECT,
-			      IOERR_SLI_DOWN);
+	/* Look on all the FCP Rings for the iotag */
+	if (phba->sli_rev >= LPFC_SLI_REV4) {
+		for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
+			pring = &psli->ring[i + MAX_SLI3_CONFIGURED_RINGS];
 
-	/* Flush the txcmpq */
-	lpfc_sli_cancel_iocbs(phba, &txcmplq, IOSTAT_LOCAL_REJECT,
-			      IOERR_SLI_DOWN);
+			spin_lock_irq(&pring->ring_lock);
+			/* Retrieve everything on txq */
+			list_splice_init(&pring->txq, &txq);
+			/* Retrieve everything on the txcmplq */
+			list_splice_init(&pring->txcmplq, &txcmplq);
+			pring->txq_cnt = 0;
+			pring->txcmplq_cnt = 0;
+			spin_unlock_irq(&pring->ring_lock);
+
+			/* Flush the txq */
+			lpfc_sli_cancel_iocbs(phba, &txq,
+					      IOSTAT_LOCAL_REJECT,
+					      IOERR_SLI_DOWN);
+			/* Flush the txcmpq */
+			lpfc_sli_cancel_iocbs(phba, &txcmplq,
+					      IOSTAT_LOCAL_REJECT,
+					      IOERR_SLI_DOWN);
+		}
+	} else {
+		pring = &psli->ring[psli->fcp_ring];
+
+		spin_lock_irq(&phba->hbalock);
+		/* Retrieve everything on txq */
+		list_splice_init(&pring->txq, &txq);
+		/* Retrieve everything on the txcmplq */
+		list_splice_init(&pring->txcmplq, &txcmplq);
+		pring->txq_cnt = 0;
+		pring->txcmplq_cnt = 0;
+		spin_unlock_irq(&phba->hbalock);
+
+		/* Flush the txq */
+		lpfc_sli_cancel_iocbs(phba, &txq, IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_DOWN);
+		/* Flush the txcmpq */
+		lpfc_sli_cancel_iocbs(phba, &txcmplq, IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_DOWN);
+	}
 }
 
 /**
@@ -3987,12 +4057,13 @@
 {
 	struct lpfc_sli *psli = &phba->sli;
 	uint16_t cfg_value;
-	int rc;
+	int rc = 0;
 
 	/* Reset HBA */
 	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-			"0295 Reset HBA Data: x%x x%x\n",
-			phba->pport->port_state, psli->sli_flag);
+			"0295 Reset HBA Data: x%x x%x x%x\n",
+			phba->pport->port_state, psli->sli_flag,
+			phba->hba_flag);
 
 	/* perform board reset */
 	phba->fc_eventTag = 0;
@@ -4005,6 +4076,12 @@
 	phba->fcf.fcf_flag = 0;
 	spin_unlock_irq(&phba->hbalock);
 
+	/* SLI4 INTF 2: if FW dump is being taken skip INIT_PORT */
+	if (phba->hba_flag & HBA_FW_DUMP_OP) {
+		phba->hba_flag &= ~HBA_FW_DUMP_OP;
+		return rc;
+	}
+
 	/* Now physically reset the device */
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 			"0389 Performing PCI function reset!\n");
@@ -5002,7 +5079,7 @@
 		} while (++fcp_eqidx < phba->cfg_fcp_io_channel);
 	}
 
-	if (phba->cfg_EnableXLane)
+	if (phba->cfg_fof)
 		lpfc_sli4_cq_release(phba->sli4_hba.oas_cq, LPFC_QUEUE_REARM);
 
 	if (phba->sli4_hba.hba_eq) {
@@ -6722,7 +6799,6 @@
 	LPFC_MBOXQ_t *pmbox = phba->sli.mbox_active;
 	MAILBOX_t *mb = &pmbox->u.mb;
 	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring;
 
 	/* If the mailbox completed, process the completion and return */
 	if (lpfc_sli4_process_missed_mbox_completions(phba))
@@ -6764,8 +6840,7 @@
 	psli->sli_flag &= ~LPFC_SLI_ACTIVE;
 	spin_unlock_irq(&phba->hbalock);
 
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
 			"0345 Resetting board due to mailbox timeout\n");
@@ -8133,6 +8208,7 @@
 	abort_tag = (uint32_t) iocbq->iotag;
 	xritag = iocbq->sli4_xritag;
 	wqe->generic.wqe_com.word7 = 0; /* The ct field has moved so reset */
+	wqe->generic.wqe_com.word10 = 0;
 	/* words0-2 bpl convert bde */
 	if (iocbq->iocb.un.genreq64.bdl.bdeFlags == BUFF_TYPE_BLP_64) {
 		numBdes = iocbq->iocb.un.genreq64.bdl.bdeSize /
@@ -8639,8 +8715,7 @@
 
 	if ((piocb->iocb_flag & LPFC_IO_FCP) ||
 	    (piocb->iocb_flag & LPFC_USE_FCPWQIDX)) {
-		if (!phba->cfg_EnableXLane || (!(piocb->iocb_flag &
-			LPFC_IO_OAS))) {
+		if (!phba->cfg_fof || (!(piocb->iocb_flag & LPFC_IO_OAS))) {
 			wq = phba->sli4_hba.fcp_wq[piocb->fcp_wqidx];
 		} else {
 			wq = phba->sli4_hba.oas_wq;
@@ -8735,7 +8810,7 @@
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		if (piocb->iocb_flag &  LPFC_IO_FCP) {
-			if (!phba->cfg_EnableXLane || (!(piocb->iocb_flag &
+			if (!phba->cfg_fof || (!(piocb->iocb_flag &
 				LPFC_IO_OAS))) {
 				if (unlikely(!phba->sli4_hba.fcp_wq))
 					return IOCB_ERROR;
@@ -9170,6 +9245,7 @@
 		pring->sli.sli3.next_cmdidx  = 0;
 		pring->sli.sli3.local_getidx = 0;
 		pring->sli.sli3.cmdidx = 0;
+		pring->flag = 0;
 		INIT_LIST_HEAD(&pring->txq);
 		INIT_LIST_HEAD(&pring->txcmplq);
 		INIT_LIST_HEAD(&pring->iocb_continueq);
@@ -9805,43 +9881,6 @@
 }
 
 /**
- * lpfc_sli_iocb_ring_abort - Unconditionally abort all iocbs on an iocb ring
- * @phba: Pointer to HBA context object.
- * @pring: Pointer to driver SLI ring object.
- *
- * This function aborts all iocbs in the given ring and frees all the iocb
- * objects in txq. This function issues abort iocbs unconditionally for all
- * the iocb commands in txcmplq. The iocbs in the txcmplq is not guaranteed
- * to complete before the return of this function. The caller is not required
- * to hold any locks.
- **/
-static void
-lpfc_sli_iocb_ring_abort(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
-{
-	LIST_HEAD(completions);
-	struct lpfc_iocbq *iocb, *next_iocb;
-
-	if (pring->ringno == LPFC_ELS_RING)
-		lpfc_fabric_abort_hba(phba);
-
-	spin_lock_irq(&phba->hbalock);
-
-	/* Take off all the iocbs on txq for cancelling */
-	list_splice_init(&pring->txq, &completions);
-	pring->txq_cnt = 0;
-
-	/* Next issue ABTS for everything on the txcmplq */
-	list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
-		lpfc_sli_abort_iotag_issue(phba, pring, iocb);
-
-	spin_unlock_irq(&phba->hbalock);
-
-	/* Cancel all the IOCBs from the completions list */
-	lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
-			      IOERR_SLI_ABORTED);
-}
-
-/**
  * lpfc_sli_hba_iocb_abort - Abort all iocbs to an hba.
  * @phba: pointer to lpfc HBA data structure.
  *
@@ -9856,7 +9895,7 @@
 
 	for (i = 0; i < psli->num_rings; i++) {
 		pring = &psli->ring[i];
-		lpfc_sli_iocb_ring_abort(phba, pring);
+		lpfc_sli_abort_iocb_ring(phba, pring);
 	}
 }
 
@@ -10081,6 +10120,124 @@
 }
 
 /**
+ * lpfc_sli_abort_taskmgmt - issue abort for all commands on a host/target/LUN
+ * @vport: Pointer to virtual port.
+ * @pring: Pointer to driver SLI ring object.
+ * @tgt_id: SCSI ID of the target.
+ * @lun_id: LUN ID of the scsi device.
+ * @taskmgmt_cmd: LPFC_CTX_LUN/LPFC_CTX_TGT/LPFC_CTX_HOST.
+ *
+ * This function sends an abort command for every SCSI command
+ * associated with the given virtual port pending on the ring
+ * filtered by lpfc_sli_validate_fcp_iocb function.
+ * When taskmgmt_cmd == LPFC_CTX_LUN, the function sends abort only to the
+ * FCP iocbs associated with lun specified by tgt_id and lun_id
+ * parameters
+ * When taskmgmt_cmd == LPFC_CTX_TGT, the function sends abort only to the
+ * FCP iocbs associated with SCSI target specified by tgt_id parameter.
+ * When taskmgmt_cmd == LPFC_CTX_HOST, the function sends abort to all
+ * FCP iocbs associated with virtual port.
+ * This function returns number of iocbs it aborted .
+ * This function is called with no locks held right after a taskmgmt
+ * command is sent.
+ **/
+int
+lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
+			uint16_t tgt_id, uint64_t lun_id, lpfc_ctx_cmd cmd)
+{
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_iocbq *abtsiocbq;
+	struct lpfc_iocbq *iocbq;
+	IOCB_t *icmd;
+	int sum, i, ret_val;
+	unsigned long iflags;
+	struct lpfc_sli_ring *pring_s4;
+	uint32_t ring_number;
+
+	spin_lock_irq(&phba->hbalock);
+
+	/* all I/Os are in process of being flushed */
+	if (phba->hba_flag & HBA_FCP_IOQ_FLUSH) {
+		spin_unlock_irq(&phba->hbalock);
+		return 0;
+	}
+	sum = 0;
+
+	for (i = 1; i <= phba->sli.last_iotag; i++) {
+		iocbq = phba->sli.iocbq_lookup[i];
+
+		if (lpfc_sli_validate_fcp_iocb(iocbq, vport, tgt_id, lun_id,
+					       cmd) != 0)
+			continue;
+
+		/*
+		 * If the iocbq is already being aborted, don't take a second
+		 * action, but do count it.
+		 */
+		if (iocbq->iocb_flag & LPFC_DRIVER_ABORTED)
+			continue;
+
+		/* issue ABTS for this IOCB based on iotag */
+		abtsiocbq = __lpfc_sli_get_iocbq(phba);
+		if (abtsiocbq == NULL)
+			continue;
+
+		icmd = &iocbq->iocb;
+		abtsiocbq->iocb.un.acxri.abortType = ABORT_TYPE_ABTS;
+		abtsiocbq->iocb.un.acxri.abortContextTag = icmd->ulpContext;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			abtsiocbq->iocb.un.acxri.abortIoTag =
+							 iocbq->sli4_xritag;
+		else
+			abtsiocbq->iocb.un.acxri.abortIoTag = icmd->ulpIoTag;
+		abtsiocbq->iocb.ulpLe = 1;
+		abtsiocbq->iocb.ulpClass = icmd->ulpClass;
+		abtsiocbq->vport = vport;
+
+		/* ABTS WQE must go to the same WQ as the WQE to be aborted */
+		abtsiocbq->fcp_wqidx = iocbq->fcp_wqidx;
+		if (iocbq->iocb_flag & LPFC_IO_FCP)
+			abtsiocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
+
+		if (lpfc_is_link_up(phba))
+			abtsiocbq->iocb.ulpCommand = CMD_ABORT_XRI_CN;
+		else
+			abtsiocbq->iocb.ulpCommand = CMD_CLOSE_XRI_CN;
+
+		/* Setup callback routine and issue the command. */
+		abtsiocbq->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
+
+		/*
+		 * Indicate the IO is being aborted by the driver and set
+		 * the caller's flag into the aborted IO.
+		 */
+		iocbq->iocb_flag |= LPFC_DRIVER_ABORTED;
+
+		if (phba->sli_rev == LPFC_SLI_REV4) {
+			ring_number = MAX_SLI3_CONFIGURED_RINGS +
+					 iocbq->fcp_wqidx;
+			pring_s4 = &phba->sli.ring[ring_number];
+			/* Note: both hbalock and ring_lock must be set here */
+			spin_lock_irqsave(&pring_s4->ring_lock, iflags);
+			ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
+							abtsiocbq, 0);
+			spin_unlock_irqrestore(&pring_s4->ring_lock, iflags);
+		} else {
+			ret_val = __lpfc_sli_issue_iocb(phba, pring->ringno,
+							abtsiocbq, 0);
+		}
+
+
+		if (ret_val == IOCB_ERROR)
+			__lpfc_sli_release_iocbq(phba, abtsiocbq);
+		else
+			sum++;
+	}
+	spin_unlock_irq(&phba->hbalock);
+	return sum;
+}
+
+/**
  * lpfc_sli_wake_iocb_wait - lpfc_sli_issue_iocb_wait's completion handler
  * @phba: Pointer to HBA context object.
  * @cmdiocbq: Pointer to command iocb.
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 6f04080..edb4883 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 9b8cda8..7f50aa0 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2009-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index e32cbec..41675c1 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "8.3.45"
+#define LPFC_DRIVER_VERSION "10.2.8001.0."
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
@@ -30,4 +30,4 @@
 
 #define LPFC_MODULE_DESC "Emulex LightPulse Fibre Channel SCSI driver " \
 		LPFC_DRIVER_VERSION
-#define LPFC_COPYRIGHT "Copyright(c) 2004-2013 Emulex.  All rights reserved."
+#define LPFC_COPYRIGHT "Copyright(c) 2004-2014 Emulex.  All rights reserved."
diff --git a/drivers/scsi/mvsas/mv_94xx.c b/drivers/scsi/mvsas/mv_94xx.c
index 1e4479f..9270d15 100644
--- a/drivers/scsi/mvsas/mv_94xx.c
+++ b/drivers/scsi/mvsas/mv_94xx.c
@@ -564,7 +564,7 @@
 	u32 tmp;
 
 	tmp = mr32(MVS_GBL_CTL);
-	tmp |= (IRQ_SAS_A | IRQ_SAS_B);
+	tmp |= (MVS_IRQ_SAS_A | MVS_IRQ_SAS_B);
 	mw32(MVS_GBL_INT_STAT, tmp);
 	writel(tmp, regs + 0x0C);
 	writel(tmp, regs + 0x10);
@@ -580,7 +580,7 @@
 
 	tmp = mr32(MVS_GBL_CTL);
 
-	tmp &= ~(IRQ_SAS_A | IRQ_SAS_B);
+	tmp &= ~(MVS_IRQ_SAS_A | MVS_IRQ_SAS_B);
 	mw32(MVS_GBL_INT_STAT, tmp);
 	writel(tmp, regs + 0x0C);
 	writel(tmp, regs + 0x10);
@@ -596,7 +596,7 @@
 	if (!(mvi->flags & MVF_FLAG_SOC)) {
 		stat = mr32(MVS_GBL_INT_STAT);
 
-		if (!(stat & (IRQ_SAS_A | IRQ_SAS_B)))
+		if (!(stat & (MVS_IRQ_SAS_A | MVS_IRQ_SAS_B)))
 			return 0;
 	}
 	return stat;
@@ -606,8 +606,8 @@
 {
 	void __iomem *regs = mvi->regs;
 
-	if (((stat & IRQ_SAS_A) && mvi->id == 0) ||
-			((stat & IRQ_SAS_B) && mvi->id == 1)) {
+	if (((stat & MVS_IRQ_SAS_A) && mvi->id == 0) ||
+			((stat & MVS_IRQ_SAS_B) && mvi->id == 1)) {
 		mw32_f(MVS_INT_STAT, CINT_DONE);
 
 		spin_lock(&mvi->lock);
diff --git a/drivers/scsi/mvsas/mv_94xx.h b/drivers/scsi/mvsas/mv_94xx.h
index 487aa6f..14e1974 100644
--- a/drivers/scsi/mvsas/mv_94xx.h
+++ b/drivers/scsi/mvsas/mv_94xx.h
@@ -150,35 +150,35 @@
 
 enum pci_interrupt_cause {
 	/*  MAIN_IRQ_CAUSE (R10200) Bits*/
-	IRQ_COM_IN_I2O_IOP0            = (1 << 0),
-	IRQ_COM_IN_I2O_IOP1            = (1 << 1),
-	IRQ_COM_IN_I2O_IOP2            = (1 << 2),
-	IRQ_COM_IN_I2O_IOP3            = (1 << 3),
-	IRQ_COM_OUT_I2O_HOS0           = (1 << 4),
-	IRQ_COM_OUT_I2O_HOS1           = (1 << 5),
-	IRQ_COM_OUT_I2O_HOS2           = (1 << 6),
-	IRQ_COM_OUT_I2O_HOS3           = (1 << 7),
-	IRQ_PCIF_TO_CPU_DRBL0          = (1 << 8),
-	IRQ_PCIF_TO_CPU_DRBL1          = (1 << 9),
-	IRQ_PCIF_TO_CPU_DRBL2          = (1 << 10),
-	IRQ_PCIF_TO_CPU_DRBL3          = (1 << 11),
-	IRQ_PCIF_DRBL0                 = (1 << 12),
-	IRQ_PCIF_DRBL1                 = (1 << 13),
-	IRQ_PCIF_DRBL2                 = (1 << 14),
-	IRQ_PCIF_DRBL3                 = (1 << 15),
-	IRQ_XOR_A                      = (1 << 16),
-	IRQ_XOR_B                      = (1 << 17),
-	IRQ_SAS_A                      = (1 << 18),
-	IRQ_SAS_B                      = (1 << 19),
-	IRQ_CPU_CNTRL                  = (1 << 20),
-	IRQ_GPIO                       = (1 << 21),
-	IRQ_UART                       = (1 << 22),
-	IRQ_SPI                        = (1 << 23),
-	IRQ_I2C                        = (1 << 24),
-	IRQ_SGPIO                      = (1 << 25),
-	IRQ_COM_ERR                    = (1 << 29),
-	IRQ_I2O_ERR                    = (1 << 30),
-	IRQ_PCIE_ERR                   = (1 << 31),
+	MVS_IRQ_COM_IN_I2O_IOP0        = (1 << 0),
+	MVS_IRQ_COM_IN_I2O_IOP1        = (1 << 1),
+	MVS_IRQ_COM_IN_I2O_IOP2        = (1 << 2),
+	MVS_IRQ_COM_IN_I2O_IOP3        = (1 << 3),
+	MVS_IRQ_COM_OUT_I2O_HOS0       = (1 << 4),
+	MVS_IRQ_COM_OUT_I2O_HOS1       = (1 << 5),
+	MVS_IRQ_COM_OUT_I2O_HOS2       = (1 << 6),
+	MVS_IRQ_COM_OUT_I2O_HOS3       = (1 << 7),
+	MVS_IRQ_PCIF_TO_CPU_DRBL0      = (1 << 8),
+	MVS_IRQ_PCIF_TO_CPU_DRBL1      = (1 << 9),
+	MVS_IRQ_PCIF_TO_CPU_DRBL2      = (1 << 10),
+	MVS_IRQ_PCIF_TO_CPU_DRBL3      = (1 << 11),
+	MVS_IRQ_PCIF_DRBL0             = (1 << 12),
+	MVS_IRQ_PCIF_DRBL1             = (1 << 13),
+	MVS_IRQ_PCIF_DRBL2             = (1 << 14),
+	MVS_IRQ_PCIF_DRBL3             = (1 << 15),
+	MVS_IRQ_XOR_A                  = (1 << 16),
+	MVS_IRQ_XOR_B                  = (1 << 17),
+	MVS_IRQ_SAS_A                  = (1 << 18),
+	MVS_IRQ_SAS_B                  = (1 << 19),
+	MVS_IRQ_CPU_CNTRL              = (1 << 20),
+	MVS_IRQ_GPIO                   = (1 << 21),
+	MVS_IRQ_UART                   = (1 << 22),
+	MVS_IRQ_SPI                    = (1 << 23),
+	MVS_IRQ_I2C                    = (1 << 24),
+	MVS_IRQ_SGPIO                  = (1 << 25),
+	MVS_IRQ_COM_ERR                = (1 << 29),
+	MVS_IRQ_I2O_ERR                = (1 << 30),
+	MVS_IRQ_PCIE_ERR               = (1 << 31),
 };
 
 union reg_phy_cfg {
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 1fa0104..de5d0ae 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1648,16 +1648,16 @@
  */
 struct crc_context {
 	uint32_t handle;		/* System handle. */
-	uint32_t ref_tag;
-	uint16_t app_tag;
+	__le32 ref_tag;
+	__le16 app_tag;
 	uint8_t ref_tag_mask[4];	/* Validation/Replacement Mask*/
 	uint8_t app_tag_mask[2];	/* Validation/Replacement Mask*/
-	uint16_t guard_seed;		/* Initial Guard Seed */
-	uint16_t prot_opts;		/* Requested Data Protection Mode */
-	uint16_t blk_size;		/* Data size in bytes */
+	__le16 guard_seed;		/* Initial Guard Seed */
+	__le16 prot_opts;		/* Requested Data Protection Mode */
+	__le16 blk_size;		/* Data size in bytes */
 	uint16_t runt_blk_guard;	/* Guard value for runt block (tape
 					 * only) */
-	uint32_t byte_count;		/* Total byte count/ total data
+	__le32 byte_count;		/* Total byte count/ total data
 					 * transfer count */
 	union {
 		struct {
@@ -1671,10 +1671,10 @@
 			uint32_t	reserved_6;
 		} nobundling;
 		struct {
-			uint32_t	dif_byte_count;	/* Total DIF byte
+			__le32	dif_byte_count;	/* Total DIF byte
 							 * count */
 			uint16_t	reserved_1;
-			uint16_t	dseg_count;	/* Data segment count */
+			__le16	dseg_count;	/* Data segment count */
 			uint32_t	reserved_2;
 			uint32_t	data_address[2];
 			uint32_t	data_length;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 8d85ed8..4b188b0 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1996,7 +1996,7 @@
 	 * have been immplemented by TCM, before AppTag is avail.
 	 * Look for modesense_handlers[]
 	 */
-	ctx->app_tag = __constant_cpu_to_le16(0);
+	ctx->app_tag = 0;
 	ctx->app_tag_mask[0] = 0x0;
 	ctx->app_tag_mask[1] = 0x0;
 
@@ -2078,6 +2078,7 @@
 	struct se_cmd		*se_cmd = &cmd->se_cmd;
 	uint32_t h;
 	struct atio_from_isp *atio = &prm->cmd->atio;
+	uint16_t t16;
 
 	sgc = 0;
 	ha = vha->hw;
@@ -2174,8 +2175,13 @@
 	pkt->initiator_id[1] = atio->u.isp24.fcp_hdr.s_id[1];
 	pkt->initiator_id[2] = atio->u.isp24.fcp_hdr.s_id[0];
 	pkt->exchange_addr   = atio->u.isp24.exchange_addr;
-	pkt->ox_id  = swab16(atio->u.isp24.fcp_hdr.ox_id);
-	pkt->flags |= (atio->u.isp24.attr << 9);
+
+	/* silence compile warning */
+	t16 = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+	pkt->ox_id  = cpu_to_le16(t16);
+
+	t16 = (atio->u.isp24.attr << 9);
+	pkt->flags |= cpu_to_le16(t16);
 	pkt->relative_offset = cpu_to_le32(prm->cmd->offset);
 
 	/* Set transfer direction */
@@ -2250,8 +2256,7 @@
 
 	if (bundling && prm->prot_seg_cnt) {
 		/* Walks dif segments */
-		pkt->add_flags |=
-			__constant_cpu_to_le16(CTIO_CRC2_AF_DIF_DSD_ENA);
+		pkt->add_flags |= CTIO_CRC2_AF_DIF_DSD_ENA;
 
 		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.bundling.dif_address;
 		if (qla24xx_walk_and_build_prot_sglist(ha, NULL, cur_dsd,
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 5c9f185..e0a58fd 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -316,7 +316,7 @@
 	uint8_t  seq_id;
 	uint8_t  df_ctl;
 	uint16_t seq_cnt;
-	uint16_t ox_id;
+	__be16   ox_id;
 	uint16_t rx_id;
 	uint32_t parameter;
 } __packed;
@@ -441,7 +441,7 @@
 	union {
 		struct {
 			uint16_t reserved1;
-			uint16_t flags;
+			__le16 flags;
 			uint32_t residual;
 			uint16_t ox_id;
 			uint16_t scsi_status;
@@ -527,7 +527,7 @@
 
 	uint32_t handle;		/* System handle. */
 	uint16_t nport_handle;		/* N_PORT handle. */
-	uint16_t timeout;		/* Command timeout. */
+	__le16 timeout;		/* Command timeout. */
 
 	uint16_t dseg_count;		/* Data segment count. */
 	uint8_t  vp_index;
@@ -538,15 +538,15 @@
 	uint8_t  reserved1;
 	uint32_t exchange_addr;		/* rcv exchange address */
 	uint16_t reserved2;
-	uint16_t flags;			/* refer to CTIO7 flags values */
+	__le16 flags;			/* refer to CTIO7 flags values */
 	uint32_t residual;
-	uint16_t ox_id;
+	__le16 ox_id;
 	uint16_t scsi_status;
-	uint32_t relative_offset;
+	__le32 relative_offset;
 	uint32_t reserved5;
-	uint32_t transfer_length;		/* total fc transfer length */
+	__le32 transfer_length;		/* total fc transfer length */
 	uint32_t reserved6;
-	uint32_t crc_context_address[2];/* Data segment address. */
+	__le32 crc_context_address[2];/* Data segment address. */
 	uint16_t crc_context_len;	/* Data segment length. */
 	uint16_t reserved_1;		/* MUST be set to 0. */
 } __packed;
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index f6759dc..c41ff14 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -368,7 +368,7 @@
 	 * otherwise we use the default. Also we use the default FIFO
 	 * thresholds for now.
 	 */
-	*burst_code = chip_info ? chip_info->dma_burst_size : 16;
+	*burst_code = chip_info ? chip_info->dma_burst_size : 1;
 	*threshold = SSCR1_RxTresh(RX_THRESH_DFLT)
 		   | SSCR1_TxTresh(TX_THRESH_DFLT);
 
diff --git a/drivers/staging/android/timed_output.c b/drivers/staging/android/timed_output.c
index 2c61783..c341ac1 100644
--- a/drivers/staging/android/timed_output.c
+++ b/drivers/staging/android/timed_output.c
@@ -97,7 +97,6 @@
 {
 	tdev->enable(tdev, 0);
 	device_destroy(timed_output_class, MKDEV(0, tdev->index));
-	dev_set_drvdata(tdev->dev, NULL);
 }
 EXPORT_SYMBOL_GPL(timed_output_dev_unregister);
 
diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig
index 5d56428..a2f6957 100644
--- a/drivers/staging/comedi/Kconfig
+++ b/drivers/staging/comedi/Kconfig
@@ -651,6 +651,7 @@
 
 config COMEDI_ADDI_APCI_1564
 	tristate "ADDI-DATA APCI_1564 support"
+	select COMEDI_ADDI_WATCHDOG
 	---help---
 	  Enable support for ADDI-DATA APCI_1564 cards
 
diff --git a/drivers/staging/iio/Kconfig b/drivers/staging/iio/Kconfig
index b36feb0..fa38be0 100644
--- a/drivers/staging/iio/Kconfig
+++ b/drivers/staging/iio/Kconfig
@@ -36,10 +36,11 @@
          Add some dummy events to the simple dummy driver.
 
 config IIO_SIMPLE_DUMMY_BUFFER
-       boolean "Buffered capture support"
-       select IIO_KFIFO_BUF
-       help
-         Add buffered data capture to the simple dummy driver.
+	boolean "Buffered capture support"
+	select IIO_BUFFER
+	select IIO_KFIFO_BUF
+	help
+	  Add buffered data capture to the simple dummy driver.
 
 endif # IIO_SIMPLE_DUMMY
 
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index dae8d1a..52d7517 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -846,6 +846,14 @@
 			LRADC_CTRL1);
 	mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0);
 
+	/* Enable / disable the divider per requirement */
+	if (test_bit(chan, &lradc->is_divided))
+		mxs_lradc_reg_set(lradc, 1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
+			LRADC_CTRL2);
+	else
+		mxs_lradc_reg_clear(lradc,
+			1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, LRADC_CTRL2);
+
 	/* Clean the slot's previous content, then set new one. */
 	mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(0),
 			LRADC_CTRL4);
@@ -961,15 +969,11 @@
 		if (val == scale_avail[MXS_LRADC_DIV_DISABLED].integer &&
 		    val2 == scale_avail[MXS_LRADC_DIV_DISABLED].nano) {
 			/* divider by two disabled */
-			writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
-			       lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_CLR);
 			clear_bit(chan->channel, &lradc->is_divided);
 			ret = 0;
 		} else if (val == scale_avail[MXS_LRADC_DIV_ENABLED].integer &&
 			   val2 == scale_avail[MXS_LRADC_DIV_ENABLED].nano) {
 			/* divider by two enabled */
-			writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
-			       lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_SET);
 			set_bit(chan->channel, &lradc->is_divided);
 			ret = 0;
 		}
diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c
index 9e0f2a9..ab338e3 100644
--- a/drivers/staging/iio/light/tsl2x7x_core.c
+++ b/drivers/staging/iio/light/tsl2x7x_core.c
@@ -667,9 +667,13 @@
 	chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] =
 			chip->tsl2x7x_settings.prox_pulse_count;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] =
-	chip->tsl2x7x_settings.prox_thres_low;
+			(chip->tsl2x7x_settings.prox_thres_low) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] =
-			chip->tsl2x7x_settings.prox_thres_high;
+			(chip->tsl2x7x_settings.prox_thres_high) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF;
 
 	/* and make sure we're not already on */
 	if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) {
diff --git a/drivers/staging/imx-drm/parallel-display.c b/drivers/staging/imx-drm/parallel-display.c
index b567832..4ca61af 100644
--- a/drivers/staging/imx-drm/parallel-display.c
+++ b/drivers/staging/imx-drm/parallel-display.c
@@ -173,6 +173,13 @@
 	if (ret)
 		return ret;
 
+	/* set the connector's dpms to OFF so that
+	 * drm_helper_connector_dpms() won't return
+	 * immediately since the current state is ON
+	 * at this point.
+	 */
+	imxpd->connector.dpms = DRM_MODE_DPMS_OFF;
+
 	drm_encoder_helper_add(&imxpd->encoder, &imx_pd_encoder_helper_funcs);
 	drm_encoder_init(drm, &imxpd->encoder, &imx_pd_encoder_funcs,
 			 DRM_MODE_ENCODER_NONE);
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index ded31ea..cbf455d 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -396,7 +396,7 @@
 	}
 }
 
-static struct vb2_ops iss_video_vb2ops = {
+static const struct vb2_ops iss_video_vb2ops = {
 	.queue_setup	= iss_video_queue_setup,
 	.buf_prepare	= iss_video_buf_prepare,
 	.buf_queue	= iss_video_buf_queue,
diff --git a/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c b/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c
index 0acacab..46f5abc 100644
--- a/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c
+++ b/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c
@@ -298,7 +298,7 @@
 	RT_TRACE(_module_hal_init_c_, _drv_info_, ("+%s\n", __func__));
 
 	if (IS_8723A_A_CUT(pHalData->VersionID)) {
-		fw_name = "rtlwifi/rtl8723aufw.bin";
+		fw_name = "rtlwifi/rtl8723aufw_A.bin";
 		RT_TRACE(_module_hal_init_c_, _drv_info_,
 			 ("rtl8723a_FirmwareDownload: R8723FwImageArray_UMC "
 			  "for RTL8723A A CUT\n"));
diff --git a/drivers/staging/rtl8723au/os_dep/os_intfs.c b/drivers/staging/rtl8723au/os_dep/os_intfs.c
index 4e32003..1fb3438 100644
--- a/drivers/staging/rtl8723au/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723au/os_dep/os_intfs.c
@@ -29,7 +29,9 @@
 MODULE_AUTHOR("Larry Finger <Larry.Finger@lwfinger.net>");
 MODULE_AUTHOR("Jes Sorensen <Jes.Sorensen@redhat.com>");
 MODULE_VERSION(DRIVERVERSION);
-MODULE_FIRMWARE("rtlwifi/rtl8821aefw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723aufw_A.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723aufw_B.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723aufw_B_NoBT.bin");
 
 /* module param defaults */
 static int rtw_chip_version = 0x00;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index f95569d..f44f1ba 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1214,15 +1214,16 @@
 {
 	struct n_tty_data *ldata = tty->disc_data;
 
-	if (I_IGNPAR(tty))
-		return;
-	if (I_PARMRK(tty)) {
-		put_tty_queue('\377', ldata);
-		put_tty_queue('\0', ldata);
-		put_tty_queue(c, ldata);
-	} else	if (I_INPCK(tty))
-		put_tty_queue('\0', ldata);
-	else
+	if (I_INPCK(tty)) {
+		if (I_IGNPAR(tty))
+			return;
+		if (I_PARMRK(tty)) {
+			put_tty_queue('\377', ldata);
+			put_tty_queue('\0', ldata);
+			put_tty_queue(c, ldata);
+		} else
+			put_tty_queue('\0', ldata);
+	} else
 		put_tty_queue(c, ldata);
 	if (waitqueue_active(&tty->read_wait))
 		wake_up_interruptible(&tty->read_wait);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 27f7ad6..7a91c6d 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2357,7 +2357,7 @@
 	port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index cfef801..4858b8a 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -144,8 +144,11 @@
 	if (!(device->port.membase || device->port.iobase))
 		return 0;
 
-	if (!device->baud)
+	if (!device->baud) {
 		device->baud = probe_baud(&device->port);
+		snprintf(device->options, sizeof(device->options), "%u",
+			 device->baud);
+	}
 
 	init_port(device);
 
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 501667e3..3233766 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -185,6 +185,12 @@
 	uart_update_timeout(port, termios->c_cflag, baud);
 	altera_uart_writel(port, baudclk, ALTERA_UART_DIVISOR_REG);
 	spin_unlock_irqrestore(&port->lock, flags);
+
+	/*
+	 * FIXME: port->read_status_mask and port->ignore_status_mask
+	 * need to be initialized based on termios settings for
+	 * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT
+	 */
 }
 
 static void altera_uart_rx_chars(struct altera_uart *pp)
diff --git a/drivers/tty/serial/amba-pl010.c b/drivers/tty/serial/amba-pl010.c
index 01c9e72..971af1e 100644
--- a/drivers/tty/serial/amba-pl010.c
+++ b/drivers/tty/serial/amba-pl010.c
@@ -420,7 +420,7 @@
 	uap->port.read_status_mask = UART01x_RSR_OE;
 	if (termios->c_iflag & INPCK)
 		uap->port.read_status_mask |= UART01x_RSR_FE | UART01x_RSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uap->port.read_status_mask |= UART01x_RSR_BE;
 
 	/*
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 908a6e3..0e26dcb 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1744,7 +1744,7 @@
 	port->read_status_mask = UART011_DR_OE | 255;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART011_DR_FE | UART011_DR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART011_DR_BE;
 
 	/*
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 3fceae0..c4f7503 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1932,7 +1932,7 @@
 	port->read_status_mask = ATMEL_US_OVRE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (ATMEL_US_FRAME | ATMEL_US_PARE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= ATMEL_US_RXBRK;
 
 	if (atmel_use_pdc_rx(port))
diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index a47421e..2315190 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -567,7 +567,7 @@
 		port->read_status_mask |= UART_FIFO_FRAMEERR_MASK;
 		port->read_status_mask |= UART_FIFO_PARERR_MASK;
 	}
-	if (new->c_iflag & (BRKINT))
+	if (new->c_iflag & (IGNBRK | BRKINT))
 		port->read_status_mask |= UART_FIFO_BRKDET_MASK;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/bfin_uart.c b/drivers/tty/serial/bfin_uart.c
index 869ceba..ac86a20 100644
--- a/drivers/tty/serial/bfin_uart.c
+++ b/drivers/tty/serial/bfin_uart.c
@@ -833,7 +833,7 @@
 	port->read_status_mask = OE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (FE | PE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= BI;
 
 	/*
diff --git a/drivers/tty/serial/dz.c b/drivers/tty/serial/dz.c
index 2f2b2e5..cdbbc78 100644
--- a/drivers/tty/serial/dz.c
+++ b/drivers/tty/serial/dz.c
@@ -625,7 +625,7 @@
 	dport->port.read_status_mask = DZ_OERR;
 	if (termios->c_iflag & INPCK)
 		dport->port.read_status_mask |= DZ_FERR | DZ_PERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		dport->port.read_status_mask |= DZ_BREAK;
 
 	/* characters to ignore */
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
index 5131b5e..a514ee6 100644
--- a/drivers/tty/serial/earlycon.c
+++ b/drivers/tty/serial/earlycon.c
@@ -25,7 +25,7 @@
 #include <asm/serial.h>
 
 static struct console early_con = {
-	.name =		"earlycon",
+	.name =		"uart", /* 8250 console switch requires this name */
 	.flags =	CON_PRINTBUFFER | CON_BOOT,
 	.index =	-1,
 };
diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c
index b373f64..3b0ee9a 100644
--- a/drivers/tty/serial/efm32-uart.c
+++ b/drivers/tty/serial/efm32-uart.c
@@ -407,7 +407,7 @@
 	if (new->c_iflag & INPCK)
 		port->read_status_mask |=
 			UARTn_RXDATAX_FERR | UARTn_RXDATAX_PERR;
-	if (new->c_iflag & (BRKINT | PARMRK))
+	if (new->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SW_UARTn_RXDATAX_BERR;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index c5eb897..49385c8 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -902,7 +902,7 @@
 	sport->port.read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
 		sport->port.read_status_mask |=	(UARTSR1_FE | UARTSR1_PE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		sport->port.read_status_mask |= UARTSR1_FE;
 
 	/* characters to ignore */
diff --git a/drivers/tty/serial/ip22zilog.c b/drivers/tty/serial/ip22zilog.c
index 1d94205..1efd4c3 100644
--- a/drivers/tty/serial/ip22zilog.c
+++ b/drivers/tty/serial/ip22zilog.c
@@ -850,7 +850,7 @@
 	up->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= BRK_ABRT;
 
 	up->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/m32r_sio.c b/drivers/tty/serial/m32r_sio.c
index 9cd9b4e..68f2c53 100644
--- a/drivers/tty/serial/m32r_sio.c
+++ b/drivers/tty/serial/m32r_sio.c
@@ -737,7 +737,7 @@
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 2a99d0c..ba285cd 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -835,7 +835,7 @@
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= MAX310X_LSR_RXPAR_BIT |
 					  MAX310X_LSR_FRERR_BIT;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= MAX310X_LSR_RXBRK_BIT;
 
 	/* Set status ignore mask */
diff --git a/drivers/tty/serial/mcf.c b/drivers/tty/serial/mcf.c
index 0edfaf8..a6f0857 100644
--- a/drivers/tty/serial/mcf.c
+++ b/drivers/tty/serial/mcf.c
@@ -248,6 +248,12 @@
 		mr1 |= MCFUART_MR1_PARITYNONE;
 	}
 
+	/*
+	 * FIXME: port->read_status_mask and port->ignore_status_mask
+	 * need to be initialized based on termios settings for
+	 * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT
+	 */
+
 	if (termios->c_cflag & CSTOPB)
 		mr2 |= MCFUART_MR2_STOP2;
 	else
diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c
index 52c930f..445799d 100644
--- a/drivers/tty/serial/mfd.c
+++ b/drivers/tty/serial/mfd.c
@@ -977,7 +977,7 @@
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/* Characters to ignore */
diff --git a/drivers/tty/serial/mpsc.c b/drivers/tty/serial/mpsc.c
index e30a3ca..759c6a6 100644
--- a/drivers/tty/serial/mpsc.c
+++ b/drivers/tty/serial/mpsc.c
@@ -1458,7 +1458,7 @@
 		pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_PE
 			| SDMA_DESC_CMDSTAT_FR;
 
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_BR;
 
 	/* Characters/events to ignore */
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 778e376..c41aca4 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -582,7 +582,7 @@
 	port->read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_SR_PAR_FRAME_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_SR_RX_BREAK;
 
 	uart_update_timeout(port, termios->c_cflag, baud);
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 4b5b3c2..86de447 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -604,7 +604,7 @@
 
 	if (termios->c_iflag & INPCK)
 		u->read_status_mask |= AUART_STAT_PERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		u->read_status_mask |= AUART_STAT_BERR;
 
 	/*
diff --git a/drivers/tty/serial/netx-serial.c b/drivers/tty/serial/netx-serial.c
index 0a4dd70..7a67456 100644
--- a/drivers/tty/serial/netx-serial.c
+++ b/drivers/tty/serial/netx-serial.c
@@ -419,7 +419,7 @@
 	}
 
 	port->read_status_mask = 0;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SR_BE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= SR_PE | SR_FE;
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index e9d420f..8193635 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -1092,7 +1092,7 @@
 	uap->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		uap->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		uap->port.read_status_mask |= BRK_ABRT;
 
 	uap->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/pnx8xxx_uart.c b/drivers/tty/serial/pnx8xxx_uart.c
index de6c05c..2ba24a4 100644
--- a/drivers/tty/serial/pnx8xxx_uart.c
+++ b/drivers/tty/serial/pnx8xxx_uart.c
@@ -477,7 +477,7 @@
 		sport->port.read_status_mask |=
 			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) |
 			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		sport->port.read_status_mask |=
 			ISTAT_TO_SM(PNX8XXX_UART_INT_BREAK);
 
diff --git a/drivers/tty/serial/pxa.c b/drivers/tty/serial/pxa.c
index 9e7ee39..c638c53 100644
--- a/drivers/tty/serial/pxa.c
+++ b/drivers/tty/serial/pxa.c
@@ -492,7 +492,7 @@
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 3293377..c1d3ebd 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -66,7 +66,7 @@
 	char buff[256];
 
 	va_start(va, fmt);
-	vscnprintf(buff, sizeof(buf), fmt, va);
+	vscnprintf(buff, sizeof(buff), fmt, va);
 	va_end(va);
 
 	printascii(buff);
diff --git a/drivers/tty/serial/sb1250-duart.c b/drivers/tty/serial/sb1250-duart.c
index a7cdec2..771f361 100644
--- a/drivers/tty/serial/sb1250-duart.c
+++ b/drivers/tty/serial/sb1250-duart.c
@@ -596,7 +596,7 @@
 	if (termios->c_iflag & INPCK)
 		uport->read_status_mask |= M_DUART_FRM_ERR |
 					   M_DUART_PARITY_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uport->read_status_mask |= M_DUART_RCVD_BRK;
 
 	uport->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index 5443b46..e84b6a3 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -665,7 +665,7 @@
 	port->read_status_mask = SR_OVR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= SR_PE | SR_FE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SR_BRK;
 
 	/* Set status ignore mask */
diff --git a/drivers/tty/serial/serial_ks8695.c b/drivers/tty/serial/serial_ks8695.c
index e1caa99..5c79bda 100644
--- a/drivers/tty/serial/serial_ks8695.c
+++ b/drivers/tty/serial/serial_ks8695.c
@@ -437,7 +437,7 @@
 	port->read_status_mask = URLS_URROE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (URLS_URFE | URLS_URPE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= URLS_URBI;
 
 	/*
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index 60f49b9..ea85460 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -697,7 +697,7 @@
 		TXX9_SIDISR_TDIS | TXX9_SIDISR_RDIS;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= TXX9_SIDISR_UFER | TXX9_SIDISR_UPER;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= TXX9_SIDISR_UBRK;
 
 	/*
diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c
index 1f2be48..9b4d71c 100644
--- a/drivers/tty/serial/sirfsoc_uart.c
+++ b/drivers/tty/serial/sirfsoc_uart.c
@@ -896,7 +896,7 @@
 		if (termios->c_iflag & INPCK)
 			port->read_status_mask |= uint_en->sirfsoc_frm_err_en;
 	}
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 			port->read_status_mask |= uint_en->sirfsoc_rxd_brk_en;
 	if (sirfport->uart_reg->uart_type == SIRF_REAL_UART) {
 		if (termios->c_iflag & IGNPAR)
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index c7f61ac..f48b1cc 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -547,7 +547,7 @@
 	ascport->port.read_status_mask = ASC_RXBUF_DUMMY_OE;
 	if (termios->c_iflag & INPCK)
 		ascport->port.read_status_mask |= ASC_RXBUF_FE | ASC_RXBUF_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		ascport->port.read_status_mask |= ASC_RXBUF_DUMMY_BE;
 
 	/*
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 5faa8e9..80a58ec 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -719,7 +719,7 @@
 	if (iflag & INPCK)
 		up->port.read_status_mask |= (SAB82532_ISR0_PERR |
 					      SAB82532_ISR0_FERR);
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= (SAB82532_ISR1_BRK << 8);
 
 	/*
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index 9a0f24f..5326ae1 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -834,7 +834,7 @@
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index a2c40ed..a85db8b 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -915,7 +915,7 @@
 	up->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= BRK_ABRT;
 
 	up->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index d569ca5..1c52074 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -936,7 +936,7 @@
 	port->read_status_mask = BD_SC_EMPTY | BD_SC_OV;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= BD_SC_FR | BD_SC_PR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= BD_SC_BR;
 
 	/*
diff --git a/drivers/tty/serial/vr41xx_siu.c b/drivers/tty/serial/vr41xx_siu.c
index a63c14b..db0c8a4 100644
--- a/drivers/tty/serial/vr41xx_siu.c
+++ b/drivers/tty/serial/vr41xx_siu.c
@@ -559,7 +559,7 @@
 	port->read_status_mask = UART_LSR_THRE | UART_LSR_OE | UART_LSR_DR;
 	if (c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (c_iflag & (BRKINT | PARMRK))
+	if (c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_LSR_BI;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/zs.c b/drivers/tty/serial/zs.c
index 6a16987..2b65bb7 100644
--- a/drivers/tty/serial/zs.c
+++ b/drivers/tty/serial/zs.c
@@ -923,7 +923,7 @@
 	uport->read_status_mask = Rx_OVR;
 	if (termios->c_iflag & INPCK)
 		uport->read_status_mask |= FRM_ERR | PAR_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uport->read_status_mask |= Rx_BRK;
 
 	uport->ignore_status_mask = 0;
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 5e0f6ff..b33b00b 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3226,8 +3226,7 @@
 	for (i = 0; i < MAX_NR_CON_DRIVER; i++) {
 		con_back = &registered_con_driver[i];
 
-		if (con_back->con &&
-		    !(con_back->flag & CON_DRIVER_FLAG_MODULE)) {
+		if (con_back->con && con_back->con != csw) {
 			defcsw = con_back->con;
 			retval = 0;
 			break;
@@ -3332,6 +3331,7 @@
 {
 	const struct consw *csw = NULL;
 	int i, more = 1, first = -1, last = -1, deflt = 0;
+	int ret;
 
  	if (!con->con || !(con->flag & CON_DRIVER_FLAG_MODULE) ||
 	    con_is_graphics(con->con, con->first, con->last))
@@ -3357,8 +3357,10 @@
 
 		if (first != -1) {
 			console_lock();
-			do_unbind_con_driver(csw, first, last, deflt);
+			ret = do_unbind_con_driver(csw, first, last, deflt);
 			console_unlock();
+			if (ret != 0)
+				return ret;
 		}
 
 		first = -1;
@@ -3645,17 +3647,20 @@
  */
 int do_unregister_con_driver(const struct consw *csw)
 {
-	int i, retval = -ENODEV;
+	int i;
 
 	/* cannot unregister a bound driver */
 	if (con_is_bound(csw))
-		goto err;
+		return -EBUSY;
+
+	if (csw == conswitchp)
+		return -EINVAL;
 
 	for (i = 0; i < MAX_NR_CON_DRIVER; i++) {
 		struct con_driver *con_driver = &registered_con_driver[i];
 
 		if (con_driver->con == csw &&
-		    con_driver->flag & CON_DRIVER_FLAG_MODULE) {
+		    con_driver->flag & CON_DRIVER_FLAG_INIT) {
 			vtconsole_deinit_device(con_driver);
 			device_destroy(vtconsole_class,
 				       MKDEV(0, con_driver->node));
@@ -3666,12 +3671,11 @@
 			con_driver->flag = 0;
 			con_driver->first = 0;
 			con_driver->last = 0;
-			retval = 0;
-			break;
+			return 0;
 		}
 	}
-err:
-	return retval;
+
+	return -ENODEV;
 }
 EXPORT_SYMBOL_GPL(do_unregister_con_driver);
 
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index e371f5a..a673e5b 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -655,7 +655,7 @@
 
 	if (mem->addr & ~PAGE_MASK)
 		return -ENODEV;
-	if (vma->vm_end - vma->vm_start > PAGE_ALIGN(mem->size))
+	if (vma->vm_end - vma->vm_start > mem->size)
 		return -EINVAL;
 
 	vma->vm_ops = &uio_physical_vm_ops;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 879b66e..21b99b4 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1526,18 +1526,6 @@
 		dev_dbg(hub_dev, "%umA bus power budget for each child\n",
 				hub->mA_per_port);
 
-	/* Update the HCD's internal representation of this hub before khubd
-	 * starts getting port status changes for devices under the hub.
-	 */
-	if (hcd->driver->update_hub_device) {
-		ret = hcd->driver->update_hub_device(hcd, hdev,
-				&hub->tt, GFP_KERNEL);
-		if (ret < 0) {
-			message = "can't update HCD hub info";
-			goto fail;
-		}
-	}
-
 	ret = hub_hub_status(hub, &hubstatus, &hubchange);
 	if (ret < 0) {
 		message = "can't get hub status";
@@ -1589,10 +1577,28 @@
 		}
 	}
 	hdev->maxchild = i;
+	for (i = 0; i < hdev->maxchild; i++) {
+		struct usb_port *port_dev = hub->ports[i];
+
+		pm_runtime_put(&port_dev->dev);
+	}
+
 	mutex_unlock(&usb_port_peer_mutex);
 	if (ret < 0)
 		goto fail;
 
+	/* Update the HCD's internal representation of this hub before khubd
+	 * starts getting port status changes for devices under the hub.
+	 */
+	if (hcd->driver->update_hub_device) {
+		ret = hcd->driver->update_hub_device(hcd, hdev,
+				&hub->tt, GFP_KERNEL);
+		if (ret < 0) {
+			message = "can't update HCD hub info";
+			goto fail;
+		}
+	}
+
 	usb_hub_adjust_deviceremovable(hdev, hub->descriptor);
 
 	hub_activate(hub, HUB_INIT);
@@ -3458,7 +3464,8 @@
 		struct usb_device *udev = port_dev->child;
 
 		if (udev && udev->can_submit) {
-			dev_warn(&port_dev->dev, "not suspended yet\n");
+			dev_warn(&port_dev->dev, "device %s not suspended yet\n",
+					dev_name(&udev->dev));
 			if (PMSG_IS_AUTO(msg))
 				return -EBUSY;
 		}
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index 0a7cdc0..326308e 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -84,6 +84,7 @@
  * @dev: generic device interface
  * @port_owner: port's owner
  * @peer: related usb2 and usb3 ports (share the same connector)
+ * @req: default pm qos request for hubs without port power control
  * @connect_type: port's connect type
  * @location: opaque representation of platform connector location
  * @status_lock: synchronize port_event() vs usb_port_{suspend|resume}
@@ -95,6 +96,7 @@
 	struct device dev;
 	struct usb_dev_state *port_owner;
 	struct usb_port *peer;
+	struct dev_pm_qos_request *req;
 	enum usb_port_connect_type connect_type;
 	usb_port_location_t location;
 	struct mutex status_lock;
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 62036fa..fe1b6d0 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -21,6 +21,8 @@
 
 #include "hub.h"
 
+static int usb_port_block_power_off;
+
 static const struct attribute_group *port_dev_group[];
 
 static ssize_t connect_type_show(struct device *dev,
@@ -66,6 +68,7 @@
 {
 	struct usb_port *port_dev = to_usb_port(dev);
 
+	kfree(port_dev->req);
 	kfree(port_dev);
 }
 
@@ -142,6 +145,9 @@
 			== PM_QOS_FLAGS_ALL)
 		return -EAGAIN;
 
+	if (usb_port_block_power_off)
+		return -EBUSY;
+
 	usb_autopm_get_interface(intf);
 	retval = usb_hub_set_port_power(hdev, hub, port1, false);
 	usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_CONNECTION);
@@ -190,11 +196,19 @@
 	if (left->peer || right->peer) {
 		struct usb_port *lpeer = left->peer;
 		struct usb_port *rpeer = right->peer;
+		char *method;
 
-		WARN(1, "failed to peer %s and %s (%s -> %p) (%s -> %p)\n",
-			dev_name(&left->dev), dev_name(&right->dev),
-			dev_name(&left->dev), lpeer,
-			dev_name(&right->dev), rpeer);
+		if (left->location && left->location == right->location)
+			method = "location";
+		else
+			method = "default";
+
+		pr_warn("usb: failed to peer %s and %s by %s (%s:%s) (%s:%s)\n",
+			dev_name(&left->dev), dev_name(&right->dev), method,
+			dev_name(&left->dev),
+			lpeer ? dev_name(&lpeer->dev) : "none",
+			dev_name(&right->dev),
+			rpeer ? dev_name(&rpeer->dev) : "none");
 		return -EBUSY;
 	}
 
@@ -251,6 +265,7 @@
 		dev_warn(&left->dev, "failed to peer to %s (%d)\n",
 				dev_name(&right->dev), rc);
 		pr_warn_once("usb: port power management may be unreliable\n");
+		usb_port_block_power_off = 1;
 	}
 }
 
@@ -386,9 +401,13 @@
 	int retval;
 
 	port_dev = kzalloc(sizeof(*port_dev), GFP_KERNEL);
-	if (!port_dev) {
-		retval = -ENOMEM;
-		goto exit;
+	if (!port_dev)
+		return -ENOMEM;
+
+	port_dev->req = kzalloc(sizeof(*(port_dev->req)), GFP_KERNEL);
+	if (!port_dev->req) {
+		kfree(port_dev);
+		return -ENOMEM;
 	}
 
 	hub->ports[port1 - 1] = port_dev;
@@ -404,31 +423,53 @@
 			port1);
 	mutex_init(&port_dev->status_lock);
 	retval = device_register(&port_dev->dev);
-	if (retval)
-		goto error_register;
+	if (retval) {
+		put_device(&port_dev->dev);
+		return retval;
+	}
+
+	/* Set default policy of port-poweroff disabled. */
+	retval = dev_pm_qos_add_request(&port_dev->dev, port_dev->req,
+			DEV_PM_QOS_FLAGS, PM_QOS_FLAG_NO_POWER_OFF);
+	if (retval < 0) {
+		device_unregister(&port_dev->dev);
+		return retval;
+	}
 
 	find_and_link_peer(hub, port1);
 
+	/*
+	 * Enable runtime pm and hold a refernce that hub_configure()
+	 * will drop once the PM_QOS_NO_POWER_OFF flag state has been set
+	 * and the hub has been fully registered (hdev->maxchild set).
+	 */
 	pm_runtime_set_active(&port_dev->dev);
+	pm_runtime_get_noresume(&port_dev->dev);
+	pm_runtime_enable(&port_dev->dev);
+	device_enable_async_suspend(&port_dev->dev);
 
 	/*
-	 * Do not enable port runtime pm if the hub does not support
-	 * power switching.  Also, userspace must have final say of
-	 * whether a port is permitted to power-off.  Do not enable
-	 * runtime pm if we fail to expose pm_qos_no_power_off.
+	 * Keep hidden the ability to enable port-poweroff if the hub
+	 * does not support power switching.
 	 */
-	if (hub_is_port_power_switchable(hub)
-			&& dev_pm_qos_expose_flags(&port_dev->dev,
-			PM_QOS_FLAG_NO_POWER_OFF) == 0)
-		pm_runtime_enable(&port_dev->dev);
+	if (!hub_is_port_power_switchable(hub))
+		return 0;
 
-	device_enable_async_suspend(&port_dev->dev);
+	/* Attempt to let userspace take over the policy. */
+	retval = dev_pm_qos_expose_flags(&port_dev->dev,
+			PM_QOS_FLAG_NO_POWER_OFF);
+	if (retval < 0) {
+		dev_warn(&port_dev->dev, "failed to expose pm_qos_no_poweroff\n");
+		return 0;
+	}
+
+	/* Userspace owns the policy, drop the kernel 'no_poweroff' request. */
+	retval = dev_pm_qos_remove_request(port_dev->req);
+	if (retval >= 0) {
+		kfree(port_dev->req);
+		port_dev->req = NULL;
+	}
 	return 0;
-
-error_register:
-	put_device(&port_dev->dev);
-exit:
-	return retval;
 }
 
 void usb_hub_remove_port_device(struct usb_hub *hub, int port1)
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 4a6d3dd..2f3aceb 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -656,6 +656,14 @@
 			DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"),
 		},
 	},
+	{
+		/* HASEE E200 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"),
+			DMI_MATCH(DMI_BOARD_NAME, "E210"),
+			DMI_MATCH(DMI_BIOS_VERSION, "6.00"),
+		},
+	},
 	{ }
 };
 
@@ -665,9 +673,14 @@
 {
 	int try_handoff = 1, tried_handoff = 0;
 
-	/* The Pegatron Lucid tablet sporadically waits for 98 seconds trying
-	 * the handoff on its unused controller.  Skip it. */
-	if (pdev->vendor == 0x8086 && pdev->device == 0x283a) {
+	/*
+	 * The Pegatron Lucid tablet sporadically waits for 98 seconds trying
+	 * the handoff on its unused controller.  Skip it.
+	 *
+	 * The HASEE E200 hangs when the semaphore is set (bugzilla #77021).
+	 */
+	if (pdev->vendor == 0x8086 && (pdev->device == 0x283a ||
+			pdev->device == 0x27cc)) {
 		if (dmi_check_system(ehci_dmi_nohandoff_table))
 			try_handoff = 0;
 	}
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 6231ce6..2b998c6 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -287,7 +287,7 @@
 		if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue) {
 			struct xhci_command *command;
 			command = xhci_alloc_command(xhci, false, false,
-						     GFP_NOIO);
+						     GFP_NOWAIT);
 			if (!command) {
 				spin_unlock_irqrestore(&xhci->lock, flags);
 				xhci_free_command(xhci, cmd);
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 51a6da2..829f446 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -7,7 +7,7 @@
 #include <linux/moduleparam.h>
 #include <linux/scatterlist.h>
 #include <linux/mutex.h>
-
+#include <linux/timer.h>
 #include <linux/usb.h>
 
 #define SIMPLE_IO_TIMEOUT	10000	/* in milliseconds */
@@ -484,6 +484,14 @@
 	return sg;
 }
 
+static void sg_timeout(unsigned long _req)
+{
+	struct usb_sg_request	*req = (struct usb_sg_request *) _req;
+
+	req->status = -ETIMEDOUT;
+	usb_sg_cancel(req);
+}
+
 static int perform_sglist(
 	struct usbtest_dev	*tdev,
 	unsigned		iterations,
@@ -495,6 +503,9 @@
 {
 	struct usb_device	*udev = testdev_to_usbdev(tdev);
 	int			retval = 0;
+	struct timer_list	sg_timer;
+
+	setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req);
 
 	while (retval == 0 && iterations-- > 0) {
 		retval = usb_sg_init(req, udev, pipe,
@@ -505,7 +516,10 @@
 
 		if (retval)
 			break;
+		mod_timer(&sg_timer, jiffies +
+				msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
 		usb_sg_wait(req);
+		del_timer_sync(&sg_timer);
 		retval = req->status;
 
 		/* FIXME check resulting data pattern */
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index b63860f..40bec8d 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -77,3 +77,4 @@
     .con_set_palette =	DUMMY,
     .con_scrolldelta =	DUMMY,
 };
+EXPORT_SYMBOL_GPL(dummy_con);
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index f267284..6e6aa70 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -1441,5 +1441,6 @@
 	.con_build_attr = vgacon_build_attr,
 	.con_invert_region = vgacon_invert_region,
 };
+EXPORT_SYMBOL(vga_con);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c
index 7d44d66..43a0a52 100644
--- a/drivers/video/fbdev/offb.c
+++ b/drivers/video/fbdev/offb.c
@@ -91,15 +91,6 @@
 #define AVIVO_DC_LUTB_WHITE_OFFSET_GREEN        0x6cd4
 #define AVIVO_DC_LUTB_WHITE_OFFSET_RED          0x6cd8
 
-#define FB_RIGHT_POS(p, bpp)         (fb_be_math(p) ? 0 : (32 - (bpp)))
-
-static inline u32 offb_cmap_byteswap(struct fb_info *info, u32 value)
-{
-	u32 bpp = info->var.bits_per_pixel;
-
-	return cpu_to_be32(value) >> FB_RIGHT_POS(info, bpp);
-}
-
     /*
      *  Set a single color register. The values supplied are already
      *  rounded down to the hardware's capabilities (according to the
@@ -129,7 +120,7 @@
 			mask <<= info->var.transp.offset;
 			value |= mask;
 		}
-		pal[regno] = offb_cmap_byteswap(info, value);
+		pal[regno] = value;
 		return 0;
 	}
 
diff --git a/drivers/w1/masters/mxc_w1.c b/drivers/w1/masters/mxc_w1.c
index 67b067a..a5df5e8 100644
--- a/drivers/w1/masters/mxc_w1.c
+++ b/drivers/w1/masters/mxc_w1.c
@@ -66,7 +66,7 @@
 
 		udelay(100);
 	}
-	return !!(reg_val & MXC_W1_CONTROL_PST);
+	return !(reg_val & MXC_W1_CONTROL_PST);
 }
 
 /*
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index c845527..76dd541 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1280,14 +1280,17 @@
 
 # S390 Architecture
 
-config ZVM_WATCHDOG
-	tristate "z/VM Watchdog Timer"
+config DIAG288_WATCHDOG
+	tristate "System z diag288 Watchdog"
 	depends on S390
+	select WATCHDOG_CORE
 	help
 	  IBM s/390 and zSeries machines running under z/VM 5.1 or later
 	  provide a virtual watchdog timer to their guest that cause a
 	  user define Control Program command to be executed after a
 	  timeout.
+	  LPAR provides a very similar interface. This driver handles
+	  both.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called vmwatchdog.
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 7b8a91e..468c320 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -153,6 +153,7 @@
 obj-$(CONFIG_WATCHDOG_RTAS) += wdrtas.o
 
 # S390 Architecture
+obj-$(CONFIG_DIAG288_WATCHDOG) += diag288_wdt.o
 
 # SUPERH (sh + sh64) Architecture
 obj-$(CONFIG_SH_WDT) += shwdt.o
diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c
new file mode 100644
index 0000000..429494b
--- /dev/null
+++ b/drivers/watchdog/diag288_wdt.c
@@ -0,0 +1,316 @@
+/*
+ * Watchdog driver for z/VM and LPAR using the diag 288 interface.
+ *
+ * Under z/VM, expiration of the watchdog will send a "system restart" command
+ * to CP.
+ *
+ * The command can be altered using the module parameter "cmd". This is
+ * not recommended because it's only supported on z/VM but not whith LPAR.
+ *
+ * On LPAR, the watchdog will always trigger a system restart. the module
+ * paramter cmd is meaningless here.
+ *
+ *
+ * Copyright IBM Corp. 2004, 2013
+ * Author(s): Arnd Bergmann (arndb@de.ibm.com)
+ *	      Philipp Hachtmann (phacht@de.ibm.com)
+ *
+ */
+
+#define KMSG_COMPONENT "diag288_wdt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/miscdevice.h>
+#include <linux/watchdog.h>
+#include <linux/suspend.h>
+#include <asm/ebcdic.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
+
+#define MAX_CMDLEN 240
+#define DEFAULT_CMD "SYSTEM RESTART"
+
+#define MIN_INTERVAL 15     /* Minimal time supported by diag88 */
+#define MAX_INTERVAL 3600   /* One hour should be enough - pure estimation */
+
+#define WDT_DEFAULT_TIMEOUT 30
+
+/* Function codes - init, change, cancel */
+#define WDT_FUNC_INIT 0
+#define WDT_FUNC_CHANGE 1
+#define WDT_FUNC_CANCEL 2
+#define WDT_FUNC_CONCEAL 0x80000000
+
+/* Action codes for LPAR watchdog */
+#define LPARWDT_RESTART 0
+
+static char wdt_cmd[MAX_CMDLEN] = DEFAULT_CMD;
+static bool conceal_on;
+static bool nowayout_info = WATCHDOG_NOWAYOUT;
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
+MODULE_AUTHOR("Philipp Hachtmann <phacht@de.ibm.com>");
+
+MODULE_DESCRIPTION("System z diag288  Watchdog Timer");
+
+module_param_string(cmd, wdt_cmd, MAX_CMDLEN, 0644);
+MODULE_PARM_DESC(cmd, "CP command that is run when the watchdog triggers (z/VM only)");
+
+module_param_named(conceal, conceal_on, bool, 0644);
+MODULE_PARM_DESC(conceal, "Enable the CONCEAL CP option while the watchdog is active (z/VM only)");
+
+module_param_named(nowayout, nowayout_info, bool, 0444);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default = CONFIG_WATCHDOG_NOWAYOUT)");
+
+MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
+MODULE_ALIAS("vmwatchdog");
+
+static int __diag288(unsigned int func, unsigned int timeout,
+		     unsigned long action, unsigned int len)
+{
+	register unsigned long __func asm("2") = func;
+	register unsigned long __timeout asm("3") = timeout;
+	register unsigned long __action asm("4") = action;
+	register unsigned long __len asm("5") = len;
+	int err;
+
+	err = -EINVAL;
+	asm volatile(
+		"	diag	%1, %3, 0x288\n"
+		"0:	la	%0, 0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (err) : "d"(__func), "d"(__timeout),
+		  "d"(__action), "d"(__len) : "1", "cc");
+	return err;
+}
+
+static int __diag288_vm(unsigned int  func, unsigned int timeout,
+			char *cmd, size_t len)
+{
+	return __diag288(func, timeout, virt_to_phys(cmd), len);
+}
+
+static int __diag288_lpar(unsigned int func, unsigned int timeout,
+			  unsigned long action)
+{
+	return __diag288(func, timeout, action, 0);
+}
+
+static int wdt_start(struct watchdog_device *dev)
+{
+	char *ebc_cmd;
+	size_t len;
+	int ret;
+	unsigned int func;
+
+	ret = -ENODEV;
+
+	if (MACHINE_IS_VM) {
+		ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
+		if (!ebc_cmd)
+			return -ENOMEM;
+		len = strlcpy(ebc_cmd, wdt_cmd, MAX_CMDLEN);
+		ASCEBC(ebc_cmd, MAX_CMDLEN);
+		EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
+
+		func = conceal_on ? (WDT_FUNC_INIT | WDT_FUNC_CONCEAL)
+			: WDT_FUNC_INIT;
+		ret = __diag288_vm(func, dev->timeout, ebc_cmd, len);
+		WARN_ON(ret != 0);
+		kfree(ebc_cmd);
+	}
+
+	if (MACHINE_IS_LPAR) {
+		ret = __diag288_lpar(WDT_FUNC_INIT,
+				     dev->timeout, LPARWDT_RESTART);
+	}
+
+	if (ret) {
+		pr_err("The watchdog cannot be activated\n");
+		return ret;
+	}
+	pr_info("The watchdog was activated\n");
+	return 0;
+}
+
+static int wdt_stop(struct watchdog_device *dev)
+{
+	int ret;
+
+	ret = __diag288(WDT_FUNC_CANCEL, 0, 0, 0);
+	pr_info("The watchdog was deactivated\n");
+	return ret;
+}
+
+static int wdt_ping(struct watchdog_device *dev)
+{
+	char *ebc_cmd;
+	size_t len;
+	int ret;
+	unsigned int func;
+
+	ret = -ENODEV;
+
+	if (MACHINE_IS_VM) {
+		ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
+		if (!ebc_cmd)
+			return -ENOMEM;
+		len = strlcpy(ebc_cmd, wdt_cmd, MAX_CMDLEN);
+		ASCEBC(ebc_cmd, MAX_CMDLEN);
+		EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
+
+		/*
+		 * It seems to be ok to z/VM to use the init function to
+		 * retrigger the watchdog. On LPAR WDT_FUNC_CHANGE must
+		 * be used when the watchdog is running.
+		 */
+		func = conceal_on ? (WDT_FUNC_INIT | WDT_FUNC_CONCEAL)
+			: WDT_FUNC_INIT;
+
+		ret = __diag288_vm(func, dev->timeout, ebc_cmd, len);
+		WARN_ON(ret != 0);
+		kfree(ebc_cmd);
+	}
+
+	if (MACHINE_IS_LPAR)
+		ret = __diag288_lpar(WDT_FUNC_CHANGE, dev->timeout, 0);
+
+	if (ret)
+		pr_err("The watchdog timer cannot be started or reset\n");
+	return ret;
+}
+
+static int wdt_set_timeout(struct watchdog_device * dev, unsigned int new_to)
+{
+	dev->timeout = new_to;
+	return wdt_ping(dev);
+}
+
+static struct watchdog_ops wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = wdt_start,
+	.stop = wdt_stop,
+	.ping = wdt_ping,
+	.set_timeout = wdt_set_timeout,
+};
+
+static struct watchdog_info wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE,
+	.firmware_version = 0,
+	.identity = "z Watchdog",
+};
+
+static struct watchdog_device wdt_dev = {
+	.parent = NULL,
+	.info = &wdt_info,
+	.ops = &wdt_ops,
+	.bootstatus = 0,
+	.timeout = WDT_DEFAULT_TIMEOUT,
+	.min_timeout = MIN_INTERVAL,
+	.max_timeout = MAX_INTERVAL,
+};
+
+/*
+ * It makes no sense to go into suspend while the watchdog is running.
+ * Depending on the memory size, the watchdog might trigger, while we
+ * are still saving the memory.
+ * We reuse the open flag to ensure that suspend and watchdog open are
+ * exclusive operations
+ */
+static int wdt_suspend(void)
+{
+	if (test_and_set_bit(WDOG_DEV_OPEN, &wdt_dev.status)) {
+		pr_err("Linux cannot be suspended while the watchdog is in use\n");
+		return notifier_from_errno(-EBUSY);
+	}
+	if (test_bit(WDOG_ACTIVE, &wdt_dev.status)) {
+		clear_bit(WDOG_DEV_OPEN, &wdt_dev.status);
+		pr_err("Linux cannot be suspended while the watchdog is in use\n");
+		return notifier_from_errno(-EBUSY);
+	}
+	return NOTIFY_DONE;
+}
+
+static int wdt_resume(void)
+{
+	clear_bit(WDOG_DEV_OPEN, &wdt_dev.status);
+	return NOTIFY_DONE;
+}
+
+static int wdt_power_event(struct notifier_block *this, unsigned long event,
+			   void *ptr)
+{
+	switch (event) {
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		return wdt_resume();
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		return wdt_suspend();
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block wdt_power_notifier = {
+	.notifier_call = wdt_power_event,
+};
+
+static int __init diag288_init(void)
+{
+	int ret;
+	char ebc_begin[] = {
+		194, 197, 199, 201, 213
+	};
+
+	watchdog_set_nowayout(&wdt_dev, nowayout_info);
+
+	if (MACHINE_IS_VM) {
+		pr_info("The watchdog device driver detected a z/VM environment\n");
+		if (__diag288_vm(WDT_FUNC_INIT, 15,
+				 ebc_begin, sizeof(ebc_begin)) != 0) {
+			pr_err("The watchdog cannot be initialized\n");
+			return -EINVAL;
+		}
+	} else if (MACHINE_IS_LPAR) {
+		pr_info("The watchdog device driver detected an LPAR environment\n");
+		if (__diag288_lpar(WDT_FUNC_INIT, 30, LPARWDT_RESTART)) {
+			pr_err("The watchdog cannot be initialized\n");
+			return -EINVAL;
+		}
+	} else {
+		pr_err("Linux runs in an environment that does not support the diag288 watchdog\n");
+		return -ENODEV;
+	}
+
+	if (__diag288_lpar(WDT_FUNC_CANCEL, 0, 0)) {
+		pr_err("The watchdog cannot be deactivated\n");
+		return -EINVAL;
+	}
+
+	ret = register_pm_notifier(&wdt_power_notifier);
+	if (ret)
+		return ret;
+
+	ret = watchdog_register_device(&wdt_dev);
+	if (ret)
+		unregister_pm_notifier(&wdt_power_notifier);
+
+	return ret;
+}
+
+static void __exit diag288_exit(void)
+{
+	watchdog_unregister_device(&wdt_dev);
+	unregister_pm_notifier(&wdt_power_notifier);
+}
+
+module_init(diag288_init);
+module_exit(diag288_exit);
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 6d325bd..5d4de88 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -1168,7 +1168,8 @@
 
 int gnttab_suspend(void)
 {
-	gnttab_interface->unmap_frames();
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		gnttab_interface->unmap_frames();
 	return 0;
 }
 
diff --git a/fs/aio.c b/fs/aio.c
index 56b2860..4f078c0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -477,7 +477,7 @@
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
-static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb)
+static int kiocb_cancel(struct kiocb *kiocb)
 {
 	kiocb_cancel_fn *old, *cancel;
 
@@ -538,7 +538,7 @@
 				       struct kiocb, ki_list);
 
 		list_del_init(&req->ki_list);
-		kiocb_cancel(ctx, req);
+		kiocb_cancel(req);
 	}
 
 	spin_unlock_irq(&ctx->ctx_lock);
@@ -727,42 +727,42 @@
  *	when the processes owning a context have all exited to encourage
  *	the rapid destruction of the kioctx.
  */
-static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
+static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 		struct completion *requests_done)
 {
-	if (!atomic_xchg(&ctx->dead, 1)) {
-		struct kioctx_table *table;
+	struct kioctx_table *table;
 
-		spin_lock(&mm->ioctx_lock);
-		rcu_read_lock();
-		table = rcu_dereference(mm->ioctx_table);
+	if (atomic_xchg(&ctx->dead, 1))
+		return -EINVAL;
 
-		WARN_ON(ctx != table->table[ctx->id]);
-		table->table[ctx->id] = NULL;
-		rcu_read_unlock();
-		spin_unlock(&mm->ioctx_lock);
 
-		/* percpu_ref_kill() will do the necessary call_rcu() */
-		wake_up_all(&ctx->wait);
+	spin_lock(&mm->ioctx_lock);
+	rcu_read_lock();
+	table = rcu_dereference(mm->ioctx_table);
 
-		/*
-		 * It'd be more correct to do this in free_ioctx(), after all
-		 * the outstanding kiocbs have finished - but by then io_destroy
-		 * has already returned, so io_setup() could potentially return
-		 * -EAGAIN with no ioctxs actually in use (as far as userspace
-		 *  could tell).
-		 */
-		aio_nr_sub(ctx->max_reqs);
+	WARN_ON(ctx != table->table[ctx->id]);
+	table->table[ctx->id] = NULL;
+	rcu_read_unlock();
+	spin_unlock(&mm->ioctx_lock);
 
-		if (ctx->mmap_size)
-			vm_munmap(ctx->mmap_base, ctx->mmap_size);
+	/* percpu_ref_kill() will do the necessary call_rcu() */
+	wake_up_all(&ctx->wait);
 
-		ctx->requests_done = requests_done;
-		percpu_ref_kill(&ctx->users);
-	} else {
-		if (requests_done)
-			complete(requests_done);
-	}
+	/*
+	 * It'd be more correct to do this in free_ioctx(), after all
+	 * the outstanding kiocbs have finished - but by then io_destroy
+	 * has already returned, so io_setup() could potentially return
+	 * -EAGAIN with no ioctxs actually in use (as far as userspace
+	 *  could tell).
+	 */
+	aio_nr_sub(ctx->max_reqs);
+
+	if (ctx->mmap_size)
+		vm_munmap(ctx->mmap_base, ctx->mmap_size);
+
+	ctx->requests_done = requests_done;
+	percpu_ref_kill(&ctx->users);
+	return 0;
 }
 
 /* wait_on_sync_kiocb:
@@ -1219,21 +1219,23 @@
 	if (likely(NULL != ioctx)) {
 		struct completion requests_done =
 			COMPLETION_INITIALIZER_ONSTACK(requests_done);
+		int ret;
 
 		/* Pass requests_done to kill_ioctx() where it can be set
 		 * in a thread-safe way. If we try to set it here then we have
 		 * a race condition if two io_destroy() called simultaneously.
 		 */
-		kill_ioctx(current->mm, ioctx, &requests_done);
+		ret = kill_ioctx(current->mm, ioctx, &requests_done);
 		percpu_ref_put(&ioctx->users);
 
 		/* Wait until all IO for the context are done. Otherwise kernel
 		 * keep using user-space buffers even if user thinks the context
 		 * is destroyed.
 		 */
-		wait_for_completion(&requests_done);
+		if (!ret)
+			wait_for_completion(&requests_done);
 
-		return 0;
+		return ret;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
 	return -EINVAL;
@@ -1595,7 +1597,7 @@
 
 	kiocb = lookup_kiocb(ctx, iocb, key);
 	if (kiocb)
-		ret = kiocb_cancel(ctx, kiocb);
+		ret = kiocb_cancel(kiocb);
 	else
 		ret = -EINVAL;
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b7e2c1c..be91397 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1259,11 +1259,19 @@
 	spinlock_t lock;
 	u64 pinned;
 	u64 reserved;
+	u64 delalloc_bytes;
 	u64 bytes_super;
 	u64 flags;
 	u64 sectorsize;
 	u64 cache_generation;
 
+	/*
+	 * It is just used for the delayed data space allocation because
+	 * only the data space allocation and the relative metadata update
+	 * can be done cross the transaction.
+	 */
+	struct rw_semaphore data_rwsem;
+
 	/* for raid56, this is a full stripe, without parity */
 	unsigned long full_stripe_len;
 
@@ -3316,7 +3324,7 @@
 				   struct btrfs_key *ins);
 int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
 			 u64 min_alloc_size, u64 empty_size, u64 hint_byte,
-			 struct btrfs_key *ins, int is_data);
+			 struct btrfs_key *ins, int is_data, int delalloc);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		  struct extent_buffer *buf, int full_backref, int no_quota);
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@@ -3330,7 +3338,8 @@
 		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
 		      u64 owner, u64 offset, int no_quota);
 
-int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len,
+			       int delalloc);
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
 				       u64 start, u64 len);
 void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index fafb3e5..99c2539 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -105,7 +105,8 @@
 static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
 			    int dump_block_groups);
 static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				       u64 num_bytes, int reserve);
+				       u64 num_bytes, int reserve,
+				       int delalloc);
 static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
 			       u64 num_bytes);
 int btrfs_pin_extent(struct btrfs_root *root,
@@ -3260,7 +3261,8 @@
 
 	spin_lock(&block_group->lock);
 	if (block_group->cached != BTRFS_CACHE_FINISHED ||
-	    !btrfs_test_opt(root, SPACE_CACHE)) {
+	    !btrfs_test_opt(root, SPACE_CACHE) ||
+	    block_group->delalloc_bytes) {
 		/*
 		 * don't bother trying to write stuff out _if_
 		 * a) we're not cached,
@@ -5613,6 +5615,7 @@
  * @cache:	The cache we are manipulating
  * @num_bytes:	The number of bytes in question
  * @reserve:	One of the reservation enums
+ * @delalloc:   The blocks are allocated for the delalloc write
  *
  * This is called by the allocator when it reserves space, or by somebody who is
  * freeing space that was never actually used on disk.  For example if you
@@ -5631,7 +5634,7 @@
  * succeeds.
  */
 static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				       u64 num_bytes, int reserve)
+				       u64 num_bytes, int reserve, int delalloc)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
 	int ret = 0;
@@ -5650,12 +5653,18 @@
 						num_bytes, 0);
 				space_info->bytes_may_use -= num_bytes;
 			}
+
+			if (delalloc)
+				cache->delalloc_bytes += num_bytes;
 		}
 	} else {
 		if (cache->ro)
 			space_info->bytes_readonly += num_bytes;
 		cache->reserved -= num_bytes;
 		space_info->bytes_reserved -= num_bytes;
+
+		if (delalloc)
+			cache->delalloc_bytes -= num_bytes;
 	}
 	spin_unlock(&cache->lock);
 	spin_unlock(&space_info->lock);
@@ -6206,7 +6215,7 @@
 		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
-		btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE);
+		btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
 		trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
 		pin = 0;
 	}
@@ -6365,6 +6374,70 @@
 	LOOP_NO_EMPTY_SIZE = 3,
 };
 
+static inline void
+btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
+		       int delalloc)
+{
+	if (delalloc)
+		down_read(&cache->data_rwsem);
+}
+
+static inline void
+btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
+		       int delalloc)
+{
+	btrfs_get_block_group(cache);
+	if (delalloc)
+		down_read(&cache->data_rwsem);
+}
+
+static struct btrfs_block_group_cache *
+btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
+		   struct btrfs_free_cluster *cluster,
+		   int delalloc)
+{
+	struct btrfs_block_group_cache *used_bg;
+	bool locked = false;
+again:
+	spin_lock(&cluster->refill_lock);
+	if (locked) {
+		if (used_bg == cluster->block_group)
+			return used_bg;
+
+		up_read(&used_bg->data_rwsem);
+		btrfs_put_block_group(used_bg);
+	}
+
+	used_bg = cluster->block_group;
+	if (!used_bg)
+		return NULL;
+
+	if (used_bg == block_group)
+		return used_bg;
+
+	btrfs_get_block_group(used_bg);
+
+	if (!delalloc)
+		return used_bg;
+
+	if (down_read_trylock(&used_bg->data_rwsem))
+		return used_bg;
+
+	spin_unlock(&cluster->refill_lock);
+	down_read(&used_bg->data_rwsem);
+	locked = true;
+	goto again;
+}
+
+static inline void
+btrfs_release_block_group(struct btrfs_block_group_cache *cache,
+			 int delalloc)
+{
+	if (delalloc)
+		up_read(&cache->data_rwsem);
+	btrfs_put_block_group(cache);
+}
+
 /*
  * walks the btree of allocated extents and find a hole of a given size.
  * The key ins is changed to record the hole:
@@ -6379,7 +6452,7 @@
 static noinline int find_free_extent(struct btrfs_root *orig_root,
 				     u64 num_bytes, u64 empty_size,
 				     u64 hint_byte, struct btrfs_key *ins,
-				     u64 flags)
+				     u64 flags, int delalloc)
 {
 	int ret = 0;
 	struct btrfs_root *root = orig_root->fs_info->extent_root;
@@ -6467,6 +6540,7 @@
 				up_read(&space_info->groups_sem);
 			} else {
 				index = get_block_group_index(block_group);
+				btrfs_lock_block_group(block_group, delalloc);
 				goto have_block_group;
 			}
 		} else if (block_group) {
@@ -6481,7 +6555,7 @@
 		u64 offset;
 		int cached;
 
-		btrfs_get_block_group(block_group);
+		btrfs_grab_block_group(block_group, delalloc);
 		search_start = block_group->key.objectid;
 
 		/*
@@ -6529,16 +6603,16 @@
 			 * the refill lock keeps out other
 			 * people trying to start a new cluster
 			 */
-			spin_lock(&last_ptr->refill_lock);
-			used_block_group = last_ptr->block_group;
-			if (used_block_group != block_group &&
-			    (!used_block_group ||
-			     used_block_group->ro ||
-			     !block_group_bits(used_block_group, flags)))
+			used_block_group = btrfs_lock_cluster(block_group,
+							      last_ptr,
+							      delalloc);
+			if (!used_block_group)
 				goto refill_cluster;
 
-			if (used_block_group != block_group)
-				btrfs_get_block_group(used_block_group);
+			if (used_block_group != block_group &&
+			    (used_block_group->ro ||
+			     !block_group_bits(used_block_group, flags)))
+				goto release_cluster;
 
 			offset = btrfs_alloc_from_cluster(used_block_group,
 						last_ptr,
@@ -6552,16 +6626,15 @@
 						used_block_group,
 						search_start, num_bytes);
 				if (used_block_group != block_group) {
-					btrfs_put_block_group(block_group);
+					btrfs_release_block_group(block_group,
+								  delalloc);
 					block_group = used_block_group;
 				}
 				goto checks;
 			}
 
 			WARN_ON(last_ptr->block_group != used_block_group);
-			if (used_block_group != block_group)
-				btrfs_put_block_group(used_block_group);
-refill_cluster:
+release_cluster:
 			/* If we are on LOOP_NO_EMPTY_SIZE, we can't
 			 * set up a new clusters, so lets just skip it
 			 * and let the allocator find whatever block
@@ -6578,8 +6651,10 @@
 			 * succeeding in the unclustered
 			 * allocation.  */
 			if (loop >= LOOP_NO_EMPTY_SIZE &&
-			    last_ptr->block_group != block_group) {
+			    used_block_group != block_group) {
 				spin_unlock(&last_ptr->refill_lock);
+				btrfs_release_block_group(used_block_group,
+							  delalloc);
 				goto unclustered_alloc;
 			}
 
@@ -6589,6 +6664,10 @@
 			 */
 			btrfs_return_cluster_to_free_space(NULL, last_ptr);
 
+			if (used_block_group != block_group)
+				btrfs_release_block_group(used_block_group,
+							  delalloc);
+refill_cluster:
 			if (loop >= LOOP_NO_EMPTY_SIZE) {
 				spin_unlock(&last_ptr->refill_lock);
 				goto unclustered_alloc;
@@ -6696,7 +6775,7 @@
 		BUG_ON(offset > search_start);
 
 		ret = btrfs_update_reserved_bytes(block_group, num_bytes,
-						  alloc_type);
+						  alloc_type, delalloc);
 		if (ret == -EAGAIN) {
 			btrfs_add_free_space(block_group, offset, num_bytes);
 			goto loop;
@@ -6708,13 +6787,13 @@
 
 		trace_btrfs_reserve_extent(orig_root, block_group,
 					   search_start, num_bytes);
-		btrfs_put_block_group(block_group);
+		btrfs_release_block_group(block_group, delalloc);
 		break;
 loop:
 		failed_cluster_refill = false;
 		failed_alloc = false;
 		BUG_ON(index != get_block_group_index(block_group));
-		btrfs_put_block_group(block_group);
+		btrfs_release_block_group(block_group, delalloc);
 	}
 	up_read(&space_info->groups_sem);
 
@@ -6827,7 +6906,7 @@
 int btrfs_reserve_extent(struct btrfs_root *root,
 			 u64 num_bytes, u64 min_alloc_size,
 			 u64 empty_size, u64 hint_byte,
-			 struct btrfs_key *ins, int is_data)
+			 struct btrfs_key *ins, int is_data, int delalloc)
 {
 	bool final_tried = false;
 	u64 flags;
@@ -6837,7 +6916,7 @@
 again:
 	WARN_ON(num_bytes < root->sectorsize);
 	ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
-			       flags);
+			       flags, delalloc);
 
 	if (ret == -ENOSPC) {
 		if (!final_tried && ins->offset) {
@@ -6862,7 +6941,8 @@
 }
 
 static int __btrfs_free_reserved_extent(struct btrfs_root *root,
-					u64 start, u64 len, int pin)
+					u64 start, u64 len,
+					int pin, int delalloc)
 {
 	struct btrfs_block_group_cache *cache;
 	int ret = 0;
@@ -6881,7 +6961,7 @@
 		pin_down_extent(root, cache, start, len, 1);
 	else {
 		btrfs_add_free_space(cache, start, len);
-		btrfs_update_reserved_bytes(cache, len, RESERVE_FREE);
+		btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
 	}
 	btrfs_put_block_group(cache);
 
@@ -6891,15 +6971,15 @@
 }
 
 int btrfs_free_reserved_extent(struct btrfs_root *root,
-					u64 start, u64 len)
+			       u64 start, u64 len, int delalloc)
 {
-	return __btrfs_free_reserved_extent(root, start, len, 0);
+	return __btrfs_free_reserved_extent(root, start, len, 0, delalloc);
 }
 
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
 				       u64 start, u64 len)
 {
-	return __btrfs_free_reserved_extent(root, start, len, 1);
+	return __btrfs_free_reserved_extent(root, start, len, 1, 0);
 }
 
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
@@ -7114,7 +7194,7 @@
 		return -EINVAL;
 
 	ret = btrfs_update_reserved_bytes(block_group, ins->offset,
-					  RESERVE_ALLOC_NO_ACCOUNT);
+					  RESERVE_ALLOC_NO_ACCOUNT, 0);
 	BUG_ON(ret); /* logic error */
 	ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
 					 0, owner, offset, ins, 1);
@@ -7256,7 +7336,7 @@
 		return ERR_CAST(block_rsv);
 
 	ret = btrfs_reserve_extent(root, blocksize, blocksize,
-				   empty_size, hint, &ins, 0);
+				   empty_size, hint, &ins, 0, 0);
 	if (ret) {
 		unuse_block_rsv(root->fs_info, block_rsv, blocksize);
 		return ERR_PTR(ret);
@@ -8659,6 +8739,7 @@
 					       start);
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
+	init_rwsem(&cache->data_rwsem);
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
 	INIT_LIST_HEAD(&cache->new_bg_list);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f25a909..a389820 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2354,7 +2354,7 @@
 {
 	int uptodate = (err == 0);
 	struct extent_io_tree *tree;
-	int ret;
+	int ret = 0;
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
@@ -5068,6 +5068,43 @@
 	}
 }
 
+int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
+			unsigned long start,
+			unsigned long len)
+{
+	size_t cur;
+	size_t offset;
+	struct page *page;
+	char *kaddr;
+	char __user *dst = (char __user *)dstv;
+	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	int ret = 0;
+
+	WARN_ON(start > eb->len);
+	WARN_ON(start + len > eb->start + eb->len);
+
+	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+
+	while (len > 0) {
+		page = extent_buffer_page(eb, i);
+
+		cur = min(len, (PAGE_CACHE_SIZE - offset));
+		kaddr = page_address(page);
+		if (copy_to_user(dst, kaddr + offset, cur)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		dst += cur;
+		len -= cur;
+		offset = 0;
+		i++;
+	}
+
+	return ret;
+}
+
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 			       unsigned long min_len, char **map,
 			       unsigned long *map_start,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 8b63f2d..ccc264e 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -158,7 +158,6 @@
 	 * to unlock
 	 */
 	wait_queue_head_t read_lock_wq;
-	wait_queue_head_t lock_wq;
 	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
@@ -304,6 +303,9 @@
 void read_extent_buffer(struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
+int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst,
+			       unsigned long start,
+			       unsigned long len);
 void write_extent_buffer(struct extent_buffer *eb, const void *src,
 			 unsigned long start, unsigned long len);
 void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 1874aee..225302b 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -75,6 +75,8 @@
 	if (atomic_dec_and_test(&em->refs)) {
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
+		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
+			kfree(em->bdev);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index e7fd8a5..b2991fd 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -15,6 +15,7 @@
 #define EXTENT_FLAG_PREALLOC 3 /* pre-allocated extent */
 #define EXTENT_FLAG_LOGGING 4 /* Logging this extent */
 #define EXTENT_FLAG_FILLING 5 /* Filling in a preallocated extent */
+#define EXTENT_FLAG_FS_MAPPING 6 /* filesystem extent mapping type */
 
 struct extent_map {
 	struct rb_node rb_node;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 372b05f..2b0a627 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -274,18 +274,32 @@
 };
 
 static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode,
-		       struct btrfs_root *root)
+		       struct btrfs_root *root, int write)
 {
+	int num_pages;
+	int check_crcs = 0;
+
+	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+		    PAGE_CACHE_SHIFT;
+
+	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
+		check_crcs = 1;
+
+	/* Make sure we can fit our crcs into the first page */
+	if (write && check_crcs &&
+	    (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
+		return -ENOSPC;
+
 	memset(io_ctl, 0, sizeof(struct io_ctl));
-	io_ctl->num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-		PAGE_CACHE_SHIFT;
-	io_ctl->pages = kzalloc(sizeof(struct page *) * io_ctl->num_pages,
-				GFP_NOFS);
+
+	io_ctl->pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS);
 	if (!io_ctl->pages)
 		return -ENOMEM;
+
+	io_ctl->num_pages = num_pages;
 	io_ctl->root = root;
-	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
-		io_ctl->check_crcs = 1;
+	io_ctl->check_crcs = check_crcs;
+
 	return 0;
 }
 
@@ -666,6 +680,13 @@
 	generation = btrfs_free_space_generation(leaf, header);
 	btrfs_release_path(path);
 
+	if (!BTRFS_I(inode)->generation) {
+		btrfs_info(root->fs_info,
+			   "The free space cache file (%llu) is invalid. skip it\n",
+			   offset);
+		return 0;
+	}
+
 	if (BTRFS_I(inode)->generation != generation) {
 		btrfs_err(root->fs_info,
 			"free space inode generation (%llu) "
@@ -677,7 +698,7 @@
 	if (!num_entries)
 		return 0;
 
-	ret = io_ctl_init(&io_ctl, inode, root);
+	ret = io_ctl_init(&io_ctl, inode, root, 0);
 	if (ret)
 		return ret;
 
@@ -957,19 +978,18 @@
 }
 
 static noinline_for_stack int
-add_ioctl_entries(struct btrfs_root *root,
-		  struct inode *inode,
-		  struct btrfs_block_group_cache *block_group,
-		  struct io_ctl *io_ctl,
-		  struct extent_state **cached_state,
-		  struct list_head *bitmap_list,
-		  int *entries)
+write_pinned_extent_entries(struct btrfs_root *root,
+			    struct btrfs_block_group_cache *block_group,
+			    struct io_ctl *io_ctl,
+			    int *entries)
 {
 	u64 start, extent_start, extent_end, len;
-	struct list_head *pos, *n;
 	struct extent_io_tree *unpin = NULL;
 	int ret;
 
+	if (!block_group)
+		return 0;
+
 	/*
 	 * We want to add any pinned extents to our free space cache
 	 * so we don't leak the space
@@ -979,23 +999,19 @@
 	 */
 	unpin = root->fs_info->pinned_extents;
 
-	if (block_group)
-		start = block_group->key.objectid;
+	start = block_group->key.objectid;
 
-	while (block_group && (start < block_group->key.objectid +
-			       block_group->key.offset)) {
+	while (start < block_group->key.objectid + block_group->key.offset) {
 		ret = find_first_extent_bit(unpin, start,
 					    &extent_start, &extent_end,
 					    EXTENT_DIRTY, NULL);
-		if (ret) {
-			ret = 0;
-			break;
-		}
+		if (ret)
+			return 0;
 
 		/* This pinned extent is out of our range */
 		if (extent_start >= block_group->key.objectid +
 		    block_group->key.offset)
-			break;
+			return 0;
 
 		extent_start = max(extent_start, start);
 		extent_end = min(block_group->key.objectid +
@@ -1005,11 +1021,20 @@
 		*entries += 1;
 		ret = io_ctl_add_entry(io_ctl, extent_start, len, NULL);
 		if (ret)
-			goto out_nospc;
+			return -ENOSPC;
 
 		start = extent_end;
 	}
 
+	return 0;
+}
+
+static noinline_for_stack int
+write_bitmap_entries(struct io_ctl *io_ctl, struct list_head *bitmap_list)
+{
+	struct list_head *pos, *n;
+	int ret;
+
 	/* Write out the bitmaps */
 	list_for_each_safe(pos, n, bitmap_list) {
 		struct btrfs_free_space *entry =
@@ -1017,36 +1042,24 @@
 
 		ret = io_ctl_add_bitmap(io_ctl, entry->bitmap);
 		if (ret)
-			goto out_nospc;
+			return -ENOSPC;
 		list_del_init(&entry->list);
 	}
 
-	/* Zero out the rest of the pages just to make sure */
-	io_ctl_zero_remaining_pages(io_ctl);
+	return 0;
+}
 
-	ret = btrfs_dirty_pages(root, inode, io_ctl->pages, io_ctl->num_pages,
-				0, i_size_read(inode), cached_state);
-	io_ctl_drop_pages(io_ctl);
-	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
-			     i_size_read(inode) - 1, cached_state, GFP_NOFS);
-
-	if (ret)
-		goto fail;
+static int flush_dirty_cache(struct inode *inode)
+{
+	int ret;
 
 	ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
-	if (ret) {
+	if (ret)
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
 				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
 				 GFP_NOFS);
-		goto fail;
-	}
-	return 0;
 
-fail:
-	return -1;
-
-out_nospc:
-	return -ENOSPC;
+	return ret;
 }
 
 static void noinline_for_stack
@@ -1056,6 +1069,7 @@
 			   struct list_head *bitmap_list)
 {
 	struct list_head *pos, *n;
+
 	list_for_each_safe(pos, n, bitmap_list) {
 		struct btrfs_free_space *entry =
 			list_entry(pos, struct btrfs_free_space, list);
@@ -1088,64 +1102,104 @@
 {
 	struct extent_state *cached_state = NULL;
 	struct io_ctl io_ctl;
-	struct list_head bitmap_list;
+	LIST_HEAD(bitmap_list);
 	int entries = 0;
 	int bitmaps = 0;
 	int ret;
-	int err = -1;
-
-	INIT_LIST_HEAD(&bitmap_list);
 
 	if (!i_size_read(inode))
 		return -1;
 
-	ret = io_ctl_init(&io_ctl, inode, root);
+	ret = io_ctl_init(&io_ctl, inode, root, 1);
 	if (ret)
 		return -1;
 
+	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) {
+		down_write(&block_group->data_rwsem);
+		spin_lock(&block_group->lock);
+		if (block_group->delalloc_bytes) {
+			block_group->disk_cache_state = BTRFS_DC_WRITTEN;
+			spin_unlock(&block_group->lock);
+			up_write(&block_group->data_rwsem);
+			BTRFS_I(inode)->generation = 0;
+			ret = 0;
+			goto out;
+		}
+		spin_unlock(&block_group->lock);
+	}
+
 	/* Lock all pages first so we can lock the extent safely. */
 	io_ctl_prepare_pages(&io_ctl, inode, 0);
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
 			 0, &cached_state);
 
-
-	/* Make sure we can fit our crcs into the first page */
-	if (io_ctl.check_crcs &&
-	    (io_ctl.num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
-		goto out_nospc;
-
 	io_ctl_set_generation(&io_ctl, trans->transid);
 
+	/* Write out the extent entries in the free space cache */
 	ret = write_cache_extent_entries(&io_ctl, ctl,
 					 block_group, &entries, &bitmaps,
 					 &bitmap_list);
 	if (ret)
 		goto out_nospc;
 
-	ret = add_ioctl_entries(root, inode, block_group, &io_ctl,
-				&cached_state, &bitmap_list, &entries);
-
-	if (ret == -ENOSPC)
+	/*
+	 * Some spaces that are freed in the current transaction are pinned,
+	 * they will be added into free space cache after the transaction is
+	 * committed, we shouldn't lose them.
+	 */
+	ret = write_pinned_extent_entries(root, block_group, &io_ctl, &entries);
+	if (ret)
 		goto out_nospc;
-	else if (ret)
+
+	/* At last, we write out all the bitmaps. */
+	ret = write_bitmap_entries(&io_ctl, &bitmap_list);
+	if (ret)
+		goto out_nospc;
+
+	/* Zero out the rest of the pages just to make sure */
+	io_ctl_zero_remaining_pages(&io_ctl);
+
+	/* Everything is written out, now we dirty the pages in the file. */
+	ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages,
+				0, i_size_read(inode), &cached_state);
+	if (ret)
+		goto out_nospc;
+
+	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+		up_write(&block_group->data_rwsem);
+	/*
+	 * Release the pages and unlock the extent, we will flush
+	 * them out later
+	 */
+	io_ctl_drop_pages(&io_ctl);
+
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
+
+	/* Flush the dirty pages in the cache file. */
+	ret = flush_dirty_cache(inode);
+	if (ret)
 		goto out;
 
-	err = update_cache_item(trans, root, inode, path, offset,
+	/* Update the cache item to tell everyone this cache file is valid. */
+	ret = update_cache_item(trans, root, inode, path, offset,
 				entries, bitmaps);
-
 out:
 	io_ctl_free(&io_ctl);
-	if (err) {
+	if (ret) {
 		invalidate_inode_pages2(inode->i_mapping);
 		BTRFS_I(inode)->generation = 0;
 	}
 	btrfs_update_inode(trans, root, inode);
-	return err;
+	return ret;
 
 out_nospc:
-
 	cleanup_write_cache_enospc(inode, &io_ctl, &cached_state, &bitmap_list);
+
+	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+		up_write(&block_group->data_rwsem);
+
 	goto out;
 }
 
@@ -1165,6 +1219,12 @@
 		spin_unlock(&block_group->lock);
 		return 0;
 	}
+
+	if (block_group->delalloc_bytes) {
+		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
+		spin_unlock(&block_group->lock);
+		return 0;
+	}
 	spin_unlock(&block_group->lock);
 
 	inode = lookup_free_space_inode(root, block_group, path);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8925f66..3668048 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -693,7 +693,7 @@
 		ret = btrfs_reserve_extent(root,
 					   async_extent->compressed_size,
 					   async_extent->compressed_size,
-					   0, alloc_hint, &ins, 1);
+					   0, alloc_hint, &ins, 1, 1);
 		if (ret) {
 			int i;
 
@@ -794,7 +794,7 @@
 out:
 	return ret;
 out_free_reserve:
-	btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 out_free:
 	extent_clear_unlock_delalloc(inode, async_extent->start,
 				     async_extent->start +
@@ -917,7 +917,7 @@
 		cur_alloc_size = disk_num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size,
 					   root->sectorsize, 0, alloc_hint,
-					   &ins, 1);
+					   &ins, 1, 1);
 		if (ret < 0)
 			goto out_unlock;
 
@@ -995,7 +995,7 @@
 	return ret;
 
 out_reserve:
-	btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 out_unlock:
 	extent_clear_unlock_delalloc(inode, start, end, locked_page,
 				     EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
@@ -2599,6 +2599,21 @@
 	return NULL;
 }
 
+static void btrfs_release_delalloc_bytes(struct btrfs_root *root,
+					 u64 start, u64 len)
+{
+	struct btrfs_block_group_cache *cache;
+
+	cache = btrfs_lookup_block_group(root->fs_info, start);
+	ASSERT(cache);
+
+	spin_lock(&cache->lock);
+	cache->delalloc_bytes -= len;
+	spin_unlock(&cache->lock);
+
+	btrfs_put_block_group(cache);
+}
+
 /* as ordered data IO finishes, this gets called so we can finish
  * an ordered extent if the range of bytes in the file it covers are
  * fully written.
@@ -2698,6 +2713,10 @@
 						logical_len, logical_len,
 						compress_type, 0, 0,
 						BTRFS_FILE_EXTENT_REG);
+		if (!ret)
+			btrfs_release_delalloc_bytes(root,
+						     ordered_extent->start,
+						     ordered_extent->disk_len);
 	}
 	unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
 			   ordered_extent->file_offset, ordered_extent->len,
@@ -2750,7 +2769,7 @@
 		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
 		    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
 			btrfs_free_reserved_extent(root, ordered_extent->start,
-						   ordered_extent->disk_len);
+						   ordered_extent->disk_len, 1);
 	}
 
 
@@ -6535,21 +6554,21 @@
 
 	alloc_hint = get_extent_allocation_hint(inode, start, len);
 	ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
-				   alloc_hint, &ins, 1);
+				   alloc_hint, &ins, 1, 1);
 	if (ret)
 		return ERR_PTR(ret);
 
 	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
 			      ins.offset, ins.offset, ins.offset, 0);
 	if (IS_ERR(em)) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 		return em;
 	}
 
 	ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
 					   ins.offset, ins.offset, 0);
 	if (ret) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 		free_extent_map(em);
 		return ERR_PTR(ret);
 	}
@@ -7437,7 +7456,7 @@
 		if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
 		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
 			btrfs_free_reserved_extent(root, ordered->start,
-						   ordered->disk_len);
+						   ordered->disk_len, 1);
 		btrfs_put_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 	}
@@ -8808,7 +8827,7 @@
 		cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
 		cur_bytes = max(cur_bytes, min_size);
 		ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
-					   *alloc_hint, &ins, 1);
+					   *alloc_hint, &ins, 1, 0);
 		if (ret) {
 			if (own_trans)
 				btrfs_end_transaction(trans, root);
@@ -8822,7 +8841,7 @@
 						  BTRFS_FILE_EXTENT_PREALLOC);
 		if (ret) {
 			btrfs_free_reserved_extent(root, ins.objectid,
-						   ins.offset);
+						   ins.offset, 0);
 			btrfs_abort_transaction(trans, root, ret);
 			if (own_trans)
 				btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 82c18ba..0d321c2 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1957,7 +1957,8 @@
 			       struct btrfs_path *path,
 			       struct btrfs_key *key,
 			       struct btrfs_ioctl_search_key *sk,
-			       char *buf,
+			       size_t *buf_size,
+			       char __user *ubuf,
 			       unsigned long *sk_offset,
 			       int *num_found)
 {
@@ -1989,13 +1990,25 @@
 		if (!key_in_sk(key, sk))
 			continue;
 
-		if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
-			item_len = 0;
+		if (sizeof(sh) + item_len > *buf_size) {
+			if (*num_found) {
+				ret = 1;
+				goto out;
+			}
 
-		if (sizeof(sh) + item_len + *sk_offset >
-		    BTRFS_SEARCH_ARGS_BUFSIZE) {
+			/*
+			 * return one empty item back for v1, which does not
+			 * handle -EOVERFLOW
+			 */
+
+			*buf_size = sizeof(sh) + item_len;
+			item_len = 0;
+			ret = -EOVERFLOW;
+		}
+
+		if (sizeof(sh) + item_len + *sk_offset > *buf_size) {
 			ret = 1;
-			goto overflow;
+			goto out;
 		}
 
 		sh.objectid = key->objectid;
@@ -2005,20 +2018,33 @@
 		sh.transid = found_transid;
 
 		/* copy search result header */
-		memcpy(buf + *sk_offset, &sh, sizeof(sh));
+		if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
+			ret = -EFAULT;
+			goto out;
+		}
+
 		*sk_offset += sizeof(sh);
 
 		if (item_len) {
-			char *p = buf + *sk_offset;
+			char __user *up = ubuf + *sk_offset;
 			/* copy the item */
-			read_extent_buffer(leaf, p,
-					   item_off, item_len);
+			if (read_extent_buffer_to_user(leaf, up,
+						       item_off, item_len)) {
+				ret = -EFAULT;
+				goto out;
+			}
+
 			*sk_offset += item_len;
 		}
 		(*num_found)++;
 
-		if (*num_found >= sk->nr_items)
-			break;
+		if (ret) /* -EOVERFLOW from above */
+			goto out;
+
+		if (*num_found >= sk->nr_items) {
+			ret = 1;
+			goto out;
+		}
 	}
 advance_key:
 	ret = 0;
@@ -2033,22 +2059,37 @@
 		key->objectid++;
 	} else
 		ret = 1;
-overflow:
+out:
+	/*
+	 *  0: all items from this leaf copied, continue with next
+	 *  1: * more items can be copied, but unused buffer is too small
+	 *     * all items were found
+	 *     Either way, it will stops the loop which iterates to the next
+	 *     leaf
+	 *  -EOVERFLOW: item was to large for buffer
+	 *  -EFAULT: could not copy extent buffer back to userspace
+	 */
 	return ret;
 }
 
 static noinline int search_ioctl(struct inode *inode,
-				 struct btrfs_ioctl_search_args *args)
+				 struct btrfs_ioctl_search_key *sk,
+				 size_t *buf_size,
+				 char __user *ubuf)
 {
 	struct btrfs_root *root;
 	struct btrfs_key key;
 	struct btrfs_path *path;
-	struct btrfs_ioctl_search_key *sk = &args->key;
 	struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info;
 	int ret;
 	int num_found = 0;
 	unsigned long sk_offset = 0;
 
+	if (*buf_size < sizeof(struct btrfs_ioctl_search_header)) {
+		*buf_size = sizeof(struct btrfs_ioctl_search_header);
+		return -EOVERFLOW;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -2082,14 +2123,15 @@
 				ret = 0;
 			goto err;
 		}
-		ret = copy_to_sk(root, path, &key, sk, args->buf,
+		ret = copy_to_sk(root, path, &key, sk, buf_size, ubuf,
 				 &sk_offset, &num_found);
 		btrfs_release_path(path);
-		if (ret || num_found >= sk->nr_items)
+		if (ret)
 			break;
 
 	}
-	ret = 0;
+	if (ret > 0)
+		ret = 0;
 err:
 	sk->nr_items = num_found;
 	btrfs_free_path(path);
@@ -2099,22 +2141,73 @@
 static noinline int btrfs_ioctl_tree_search(struct file *file,
 					   void __user *argp)
 {
-	 struct btrfs_ioctl_search_args *args;
-	 struct inode *inode;
-	 int ret;
+	struct btrfs_ioctl_search_args __user *uargs;
+	struct btrfs_ioctl_search_key sk;
+	struct inode *inode;
+	int ret;
+	size_t buf_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	args = memdup_user(argp, sizeof(*args));
-	if (IS_ERR(args))
-		return PTR_ERR(args);
+	uargs = (struct btrfs_ioctl_search_args __user *)argp;
+
+	if (copy_from_user(&sk, &uargs->key, sizeof(sk)))
+		return -EFAULT;
+
+	buf_size = sizeof(uargs->buf);
 
 	inode = file_inode(file);
-	ret = search_ioctl(inode, args);
-	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+	ret = search_ioctl(inode, &sk, &buf_size, uargs->buf);
+
+	/*
+	 * In the origin implementation an overflow is handled by returning a
+	 * search header with a len of zero, so reset ret.
+	 */
+	if (ret == -EOVERFLOW)
+		ret = 0;
+
+	if (ret == 0 && copy_to_user(&uargs->key, &sk, sizeof(sk)))
 		ret = -EFAULT;
-	kfree(args);
+	return ret;
+}
+
+static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
+					       void __user *argp)
+{
+	struct btrfs_ioctl_search_args_v2 __user *uarg;
+	struct btrfs_ioctl_search_args_v2 args;
+	struct inode *inode;
+	int ret;
+	size_t buf_size;
+	const size_t buf_limit = 16 * 1024 * 1024;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* copy search header and buffer size */
+	uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp;
+	if (copy_from_user(&args, uarg, sizeof(args)))
+		return -EFAULT;
+
+	buf_size = args.buf_size;
+
+	if (buf_size < sizeof(struct btrfs_ioctl_search_header))
+		return -EOVERFLOW;
+
+	/* limit result size to 16MB */
+	if (buf_size > buf_limit)
+		buf_size = buf_limit;
+
+	inode = file_inode(file);
+	ret = search_ioctl(inode, &args.key, &buf_size,
+			   (char *)(&uarg->buf[0]));
+	if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key)))
+		ret = -EFAULT;
+	else if (ret == -EOVERFLOW &&
+		copy_to_user(&uarg->buf_size, &buf_size, sizeof(buf_size)))
+		ret = -EFAULT;
+
 	return ret;
 }
 
@@ -5198,6 +5291,8 @@
 		return btrfs_ioctl_trans_end(file);
 	case BTRFS_IOC_TREE_SEARCH:
 		return btrfs_ioctl_tree_search(file, argp);
+	case BTRFS_IOC_TREE_SEARCH_V2:
+		return btrfs_ioctl_tree_search_v2(file, argp);
 	case BTRFS_IOC_INO_LOOKUP:
 		return btrfs_ioctl_ino_lookup(file, argp);
 	case BTRFS_IOC_INO_PATHS:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 01277b8..5665d21 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -33,14 +33,14 @@
  */
 void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
-	}
+	/*
+	 * no lock is required.  The lock owner may change if
+	 * we have a read lock, but it won't change to or away
+	 * from us.  If we have the write lock, we are the owner
+	 * and it'll never change.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner)
+		return;
 	if (rw == BTRFS_WRITE_LOCK) {
 		if (atomic_read(&eb->blocking_writers) == 0) {
 			WARN_ON(atomic_read(&eb->spinning_writers) != 1);
@@ -65,14 +65,15 @@
  */
 void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
-	}
+	/*
+	 * no lock is required.  The lock owner may change if
+	 * we have a read lock, but it won't change to or away
+	 * from us.  If we have the write lock, we are the owner
+	 * and it'll never change.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner)
+		return;
+
 	if (rw == BTRFS_WRITE_LOCK_BLOCKING) {
 		BUG_ON(atomic_read(&eb->blocking_writers) != 1);
 		write_lock(&eb->lock);
@@ -99,6 +100,9 @@
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
 again:
+	BUG_ON(!atomic_read(&eb->blocking_writers) &&
+	       current->pid == eb->lock_owner);
+
 	read_lock(&eb->lock);
 	if (atomic_read(&eb->blocking_writers) &&
 	    current->pid == eb->lock_owner) {
@@ -132,7 +136,9 @@
 	if (atomic_read(&eb->blocking_writers))
 		return 0;
 
-	read_lock(&eb->lock);
+	if (!read_trylock(&eb->lock))
+		return 0;
+
 	if (atomic_read(&eb->blocking_writers)) {
 		read_unlock(&eb->lock);
 		return 0;
@@ -151,7 +157,10 @@
 	if (atomic_read(&eb->blocking_writers) ||
 	    atomic_read(&eb->blocking_readers))
 		return 0;
-	write_lock(&eb->lock);
+
+	if (!write_trylock(&eb->lock))
+		return 0;
+
 	if (atomic_read(&eb->blocking_writers) ||
 	    atomic_read(&eb->blocking_readers)) {
 		write_unlock(&eb->lock);
@@ -168,14 +177,15 @@
  */
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			eb->lock_nested = 0;
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
+	/*
+	 * if we're nested, we have the write lock.  No new locking
+	 * is needed as long as we are the lock owner.
+	 * The write unlock will do a barrier for us, and the lock_nested
+	 * field only matters to the lock owner.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner) {
+		eb->lock_nested = 0;
+		return;
 	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
@@ -189,14 +199,15 @@
  */
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			eb->lock_nested = 0;
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
+	/*
+	 * if we're nested, we have the write lock.  No new locking
+	 * is needed as long as we are the lock owner.
+	 * The write unlock will do a barrier for us, and the lock_nested
+	 * field only matters to the lock owner.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner) {
+		eb->lock_nested = 0;
+		return;
 	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->blocking_readers) == 0);
@@ -244,6 +255,7 @@
 	BUG_ON(blockers > 1);
 
 	btrfs_assert_tree_locked(eb);
+	eb->lock_owner = 0;
 	atomic_dec(&eb->write_locks);
 
 	if (blockers) {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index cf5aead..98cb6b2 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1798,8 +1798,10 @@
 		return -ENOMEM;
 
 	tmp = ulist_alloc(GFP_NOFS);
-	if (!tmp)
+	if (!tmp) {
+		ulist_free(qgroups);
 		return -ENOMEM;
+	}
 
 	btrfs_get_tree_mod_seq(fs_info, &elem);
 	ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, elem.seq,
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 30947f9..09230cf 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -428,8 +428,13 @@
 			continue;
 		}
 		if (!dev->bdev) {
-			/* cannot read ahead on missing device */
-			continue;
+			/*
+			 * cannot read ahead on missing device, but for RAID5/6,
+			 * REQ_GET_READ_MIRRORS return 1. So don't skip missing
+			 * device for such case.
+			 */
+			if (nzones > 1)
+				continue;
 		}
 		if (dev_replace_is_ongoing &&
 		    dev == fs_info->dev_replace.tgtdev) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index ac80188..b6d198f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2725,11 +2725,8 @@
 		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
 		length = btrfs_dev_extent_length(l, dev_extent);
 
-		if (found_key.offset + length <= start) {
-			key.offset = found_key.offset + length;
-			btrfs_release_path(path);
-			continue;
-		}
+		if (found_key.offset + length <= start)
+			goto skip;
 
 		chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent);
 		chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent);
@@ -2740,10 +2737,12 @@
 		 * the chunk from going away while we scrub it
 		 */
 		cache = btrfs_lookup_block_group(fs_info, chunk_offset);
-		if (!cache) {
-			ret = -ENOENT;
-			break;
-		}
+
+		/* some chunks are removed but not committed to disk yet,
+		 * continue scrubbing */
+		if (!cache)
+			goto skip;
+
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
@@ -2802,7 +2801,7 @@
 
 		dev_replace->cursor_left = dev_replace->cursor_right;
 		dev_replace->item_needs_writeback = 1;
-
+skip:
 		key.offset = found_key.offset + length;
 		btrfs_release_path(path);
 	}
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index a5dcacb..9626252 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -135,7 +135,7 @@
 	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
 		struct extent_buffer *eb;
 
-		eb = radix_tree_deref_slot(slot);
+		eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock);
 		if (!eb)
 			continue;
 		/* Shouldn't happen but that kind of thinking creates CVE's */
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index fa691b7..ec3dcb2 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -415,6 +415,8 @@
 		ret = -ENOMEM;
 		goto out;
 	}
+	btrfs_set_header_level(root->node, 0);
+	btrfs_set_header_nritems(root->node, 0);
 	root->alloc_bytenr += 8192;
 
 	tmp_root = btrfs_alloc_dummy_root();
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9630f10..511839c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1284,11 +1284,13 @@
 		goto fail;
 	}
 
-	pending->error = btrfs_qgroup_inherit(trans, fs_info,
-					      root->root_key.objectid,
-					      objectid, pending->inherit);
-	if (pending->error)
-		goto no_free_objectid;
+	ret = btrfs_qgroup_inherit(trans, fs_info,
+				   root->root_key.objectid,
+				   objectid, pending->inherit);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto fail;
+	}
 
 	/* see comments in should_cow_block() */
 	set_bit(BTRFS_ROOT_FORCE_COW, &root->state);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ffeed6d..c83b242 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2543,9 +2543,6 @@
 	remove_extent_mapping(em_tree, em);
 	write_unlock(&em_tree->lock);
 
-	kfree(map);
-	em->bdev = NULL;
-
 	/* once for the tree */
 	free_extent_map(em);
 	/* once for us */
@@ -4301,9 +4298,11 @@
 
 	em = alloc_extent_map();
 	if (!em) {
+		kfree(map);
 		ret = -ENOMEM;
 		goto error;
 	}
+	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
 	em->bdev = (struct block_device *)map;
 	em->start = start;
 	em->len = num_bytes;
@@ -4346,7 +4345,6 @@
 	/* One for the tree reference */
 	free_extent_map(em);
 error:
-	kfree(map);
 	kfree(devices_info);
 	return ret;
 }
@@ -4558,7 +4556,6 @@
 		write_unlock(&tree->map_tree.lock);
 		if (!em)
 			break;
-		kfree(em->bdev);
 		/* once for us */
 		free_extent_map(em);
 		/* once for the tree */
@@ -5362,6 +5359,15 @@
 	return 0;
 }
 
+static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err)
+{
+	if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED))
+		bio_endio_nodec(bio, err);
+	else
+		bio_endio(bio, err);
+	kfree(bbio);
+}
+
 static void btrfs_end_bio(struct bio *bio, int err)
 {
 	struct btrfs_bio *bbio = bio->bi_private;
@@ -5402,12 +5408,6 @@
 			bio = bbio->orig_bio;
 		}
 
- 		/*
-		 * We have original bio now. So increment bi_remaining to
-		 * account for it in endio
-		 */
-		atomic_inc(&bio->bi_remaining);
-
 		bio->bi_private = bbio->private;
 		bio->bi_end_io = bbio->end_io;
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
@@ -5424,9 +5424,8 @@
 			set_bit(BIO_UPTODATE, &bio->bi_flags);
 			err = 0;
 		}
-		kfree(bbio);
 
-		bio_endio(bio, err);
+		btrfs_end_bbio(bbio, bio, err);
 	} else if (!is_orig_bio) {
 		bio_put(bio);
 	}
@@ -5589,12 +5588,15 @@
 {
 	atomic_inc(&bbio->error);
 	if (atomic_dec_and_test(&bbio->stripes_pending)) {
+		/* Shoud be the original bio. */
+		WARN_ON(bio != bbio->orig_bio);
+
 		bio->bi_private = bbio->private;
 		bio->bi_end_io = bbio->end_io;
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
 		bio->bi_iter.bi_sector = logical >> 9;
-		kfree(bbio);
-		bio_endio(bio, -EIO);
+
+		btrfs_end_bbio(bbio, bio, -EIO);
 	}
 }
 
@@ -5681,6 +5683,7 @@
 			BUG_ON(!bio); /* -ENOMEM */
 		} else {
 			bio = first_bio;
+			bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED;
 		}
 
 		submit_stripe_bio(root, bbio, bio,
@@ -5822,6 +5825,7 @@
 		return -ENOMEM;
 	}
 
+	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
 	em->bdev = (struct block_device *)map;
 	em->start = logical;
 	em->len = length;
@@ -5846,7 +5850,6 @@
 		map->stripes[i].dev = btrfs_find_device(root->fs_info, devid,
 							uuid, NULL);
 		if (!map->stripes[i].dev && !btrfs_test_opt(root, DEGRADED)) {
-			kfree(map);
 			free_extent_map(em);
 			return -EIO;
 		}
@@ -5854,7 +5857,6 @@
 			map->stripes[i].dev =
 				add_missing_dev(root, devid, uuid);
 			if (!map->stripes[i].dev) {
-				kfree(map);
 				free_extent_map(em);
 				return -EIO;
 			}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1a15bbe..2aaa00c 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -190,11 +190,14 @@
 struct btrfs_bio;
 typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
 
+#define BTRFS_BIO_ORIG_BIO_SUBMITTED	0x1
+
 struct btrfs_bio {
 	atomic_t stripes_pending;
 	struct btrfs_fs_info *fs_info;
 	bio_end_io_t *end_io;
 	struct bio *orig_bio;
+	unsigned long flags;
 	void *private;
 	atomic_t error;
 	int max_errors;
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 21887d6..469f2e8 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -104,12 +104,6 @@
 	umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
 	struct dentry *dentry;
 
-	if (acl) {
-		ret = posix_acl_valid(acl);
-		if (ret < 0)
-			goto out;
-	}
-
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4f3f690..90b3954 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -211,18 +211,15 @@
 		SetPageError(page);
 		ceph_fscache_readpage_cancel(inode, page);
 		goto out;
-	} else {
-		if (err < PAGE_CACHE_SIZE) {
-		/* zero fill remainder of page */
-			zero_user_segment(page, err, PAGE_CACHE_SIZE);
-		} else {
-			flush_dcache_page(page);
-		}
 	}
-	SetPageUptodate(page);
+	if (err < PAGE_CACHE_SIZE)
+		/* zero fill remainder of page */
+		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+	else
+		flush_dcache_page(page);
 
-	if (err >= 0)
-		ceph_readpage_to_fscache(inode, page);
+	SetPageUptodate(page);
+	ceph_readpage_to_fscache(inode, page);
 
 out:
 	return err < 0 ? err : 0;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c561b62..1fde164 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -221,8 +221,8 @@
 	return 0;
 }
 
-static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc,
-				struct ceph_cap_reservation *ctx)
+struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+			      struct ceph_cap_reservation *ctx)
 {
 	struct ceph_cap *cap = NULL;
 
@@ -508,15 +508,14 @@
  * it is < 0.  (This is so we can atomically add the cap and add an
  * open file reference to it.)
  */
-int ceph_add_cap(struct inode *inode,
-		 struct ceph_mds_session *session, u64 cap_id,
-		 int fmode, unsigned issued, unsigned wanted,
-		 unsigned seq, unsigned mseq, u64 realmino, int flags,
-		 struct ceph_cap_reservation *caps_reservation)
+void ceph_add_cap(struct inode *inode,
+		  struct ceph_mds_session *session, u64 cap_id,
+		  int fmode, unsigned issued, unsigned wanted,
+		  unsigned seq, unsigned mseq, u64 realmino, int flags,
+		  struct ceph_cap **new_cap)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_cap *new_cap = NULL;
 	struct ceph_cap *cap;
 	int mds = session->s_mds;
 	int actual_wanted;
@@ -531,20 +530,10 @@
 	if (fmode >= 0)
 		wanted |= ceph_caps_for_mode(fmode);
 
-retry:
-	spin_lock(&ci->i_ceph_lock);
 	cap = __get_cap_for_mds(ci, mds);
 	if (!cap) {
-		if (new_cap) {
-			cap = new_cap;
-			new_cap = NULL;
-		} else {
-			spin_unlock(&ci->i_ceph_lock);
-			new_cap = get_cap(mdsc, caps_reservation);
-			if (new_cap == NULL)
-				return -ENOMEM;
-			goto retry;
-		}
+		cap = *new_cap;
+		*new_cap = NULL;
 
 		cap->issued = 0;
 		cap->implemented = 0;
@@ -562,9 +551,6 @@
 		session->s_nr_caps++;
 		spin_unlock(&session->s_cap_lock);
 	} else {
-		if (new_cap)
-			ceph_put_cap(mdsc, new_cap);
-
 		/*
 		 * auth mds of the inode changed. we received the cap export
 		 * message, but still haven't received the cap import message.
@@ -626,7 +612,6 @@
 			ci->i_auth_cap = cap;
 			cap->mds_wanted = wanted;
 		}
-		ci->i_cap_exporting_issued = 0;
 	} else {
 		WARN_ON(ci->i_auth_cap == cap);
 	}
@@ -648,9 +633,6 @@
 
 	if (fmode >= 0)
 		__ceph_get_fmode(ci, fmode);
-	spin_unlock(&ci->i_ceph_lock);
-	wake_up_all(&ci->i_cap_wq);
-	return 0;
 }
 
 /*
@@ -685,7 +667,7 @@
  */
 int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
 {
-	int have = ci->i_snap_caps | ci->i_cap_exporting_issued;
+	int have = ci->i_snap_caps;
 	struct ceph_cap *cap;
 	struct rb_node *p;
 
@@ -900,7 +882,7 @@
  */
 static int __ceph_is_any_caps(struct ceph_inode_info *ci)
 {
-	return !RB_EMPTY_ROOT(&ci->i_caps) || ci->i_cap_exporting_issued;
+	return !RB_EMPTY_ROOT(&ci->i_caps);
 }
 
 int ceph_is_any_caps(struct inode *inode)
@@ -2397,32 +2379,30 @@
  * actually be a revocation if it specifies a smaller cap set.)
  *
  * caller holds s_mutex and i_ceph_lock, we drop both.
- *
- * return value:
- *  0 - ok
- *  1 - check_caps on auth cap only (writeback)
- *  2 - check_caps (ack revoke)
  */
-static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
+static void handle_cap_grant(struct ceph_mds_client *mdsc,
+			     struct inode *inode, struct ceph_mds_caps *grant,
+			     void *snaptrace, int snaptrace_len,
+			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
-			     struct ceph_cap *cap,
-			     struct ceph_buffer *xattr_buf)
-		__releases(ci->i_ceph_lock)
+			     struct ceph_cap *cap, int issued)
+	__releases(ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int mds = session->s_mds;
 	int seq = le32_to_cpu(grant->seq);
 	int newcaps = le32_to_cpu(grant->caps);
-	int issued, implemented, used, wanted, dirty;
+	int used, wanted, dirty;
 	u64 size = le64_to_cpu(grant->size);
 	u64 max_size = le64_to_cpu(grant->max_size);
 	struct timespec mtime, atime, ctime;
 	int check_caps = 0;
-	int wake = 0;
-	int writeback = 0;
-	int queue_invalidate = 0;
-	int deleted_inode = 0;
-	int queue_revalidate = 0;
+	bool wake = 0;
+	bool writeback = 0;
+	bool queue_trunc = 0;
+	bool queue_invalidate = 0;
+	bool queue_revalidate = 0;
+	bool deleted_inode = 0;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2466,16 +2446,13 @@
 	}
 
 	/* side effects now are allowed */
-
-	issued = __ceph_caps_issued(ci, &implemented);
-	issued |= implemented | __ceph_caps_dirty(ci);
-
 	cap->cap_gen = session->s_cap_gen;
 	cap->seq = seq;
 
 	__check_cap_issue(ci, cap, newcaps);
 
-	if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = le32_to_cpu(grant->mode);
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
@@ -2484,7 +2461,8 @@
 		     from_kgid(&init_user_ns, inode->i_gid));
 	}
 
-	if ((issued & CEPH_CAP_LINK_EXCL) == 0) {
+	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+	    (issued & CEPH_CAP_LINK_EXCL) == 0) {
 		set_nlink(inode, le32_to_cpu(grant->nlink));
 		if (inode->i_nlink == 0 &&
 		    (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
@@ -2511,30 +2489,35 @@
 	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
 		queue_revalidate = 1;
 
-	/* size/ctime/mtime/atime? */
-	ceph_fill_file_size(inode, issued,
-			    le32_to_cpu(grant->truncate_seq),
-			    le64_to_cpu(grant->truncate_size), size);
-	ceph_decode_timespec(&mtime, &grant->mtime);
-	ceph_decode_timespec(&atime, &grant->atime);
-	ceph_decode_timespec(&ctime, &grant->ctime);
-	ceph_fill_file_time(inode, issued,
-			    le32_to_cpu(grant->time_warp_seq), &ctime, &mtime,
-			    &atime);
+	if (newcaps & CEPH_CAP_ANY_RD) {
+		/* ctime/mtime/atime? */
+		ceph_decode_timespec(&mtime, &grant->mtime);
+		ceph_decode_timespec(&atime, &grant->atime);
+		ceph_decode_timespec(&ctime, &grant->ctime);
+		ceph_fill_file_time(inode, issued,
+				    le32_to_cpu(grant->time_warp_seq),
+				    &ctime, &mtime, &atime);
+	}
 
-
-	/* file layout may have changed */
-	ci->i_layout = grant->layout;
-
-	/* max size increase? */
-	if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
-		dout("max_size %lld -> %llu\n", ci->i_max_size, max_size);
-		ci->i_max_size = max_size;
-		if (max_size >= ci->i_wanted_max_size) {
-			ci->i_wanted_max_size = 0;  /* reset */
-			ci->i_requested_max_size = 0;
+	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
+		/* file layout may have changed */
+		ci->i_layout = grant->layout;
+		/* size/truncate_seq? */
+		queue_trunc = ceph_fill_file_size(inode, issued,
+					le32_to_cpu(grant->truncate_seq),
+					le64_to_cpu(grant->truncate_size),
+					size);
+		/* max size increase? */
+		if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
+			dout("max_size %lld -> %llu\n",
+			     ci->i_max_size, max_size);
+			ci->i_max_size = max_size;
+			if (max_size >= ci->i_wanted_max_size) {
+				ci->i_wanted_max_size = 0;  /* reset */
+				ci->i_requested_max_size = 0;
+			}
+			wake = 1;
 		}
-		wake = 1;
 	}
 
 	/* check cap bits */
@@ -2595,6 +2578,23 @@
 
 	spin_unlock(&ci->i_ceph_lock);
 
+	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+		down_write(&mdsc->snap_rwsem);
+		ceph_update_snap_trace(mdsc, snaptrace,
+				       snaptrace + snaptrace_len, false);
+		downgrade_write(&mdsc->snap_rwsem);
+		kick_flushing_inode_caps(mdsc, session, inode);
+		up_read(&mdsc->snap_rwsem);
+		if (newcaps & ~issued)
+			wake = 1;
+	}
+
+	if (queue_trunc) {
+		ceph_queue_vmtruncate(inode);
+		ceph_queue_revalidate(inode);
+	} else if (queue_revalidate)
+		ceph_queue_revalidate(inode);
+
 	if (writeback)
 		/*
 		 * queue inode for writeback: we can't actually call
@@ -2606,8 +2606,6 @@
 		ceph_queue_invalidate(inode);
 	if (deleted_inode)
 		invalidate_aliases(inode);
-	if (queue_revalidate)
-		ceph_queue_revalidate(inode);
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 
@@ -2784,7 +2782,7 @@
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_session *tsession = NULL;
-	struct ceph_cap *cap, *tcap;
+	struct ceph_cap *cap, *tcap, *new_cap = NULL;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 t_cap_id;
 	unsigned mseq = le32_to_cpu(ex->migrate_seq);
@@ -2807,7 +2805,7 @@
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	cap = __get_cap_for_mds(ci, mds);
-	if (!cap)
+	if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
 		goto out_unlock;
 
 	if (target < 0) {
@@ -2846,15 +2844,14 @@
 		}
 		__ceph_remove_cap(cap, false);
 		goto out_unlock;
-	}
-
-	if (tsession) {
-		int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
-		spin_unlock(&ci->i_ceph_lock);
+	} else if (tsession) {
 		/* add placeholder for the export tagert */
+		int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
 		ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
-			     t_seq - 1, t_mseq, (u64)-1, flag, NULL);
-		goto retry;
+			     t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
+
+		__ceph_remove_cap(cap, false);
+		goto out_unlock;
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
@@ -2873,6 +2870,7 @@
 					  SINGLE_DEPTH_NESTING);
 		}
 		ceph_add_cap_releases(mdsc, tsession);
+		new_cap = ceph_get_cap(mdsc, NULL);
 	} else {
 		WARN_ON(1);
 		tsession = NULL;
@@ -2887,24 +2885,27 @@
 		mutex_unlock(&tsession->s_mutex);
 		ceph_put_mds_session(tsession);
 	}
+	if (new_cap)
+		ceph_put_cap(mdsc, new_cap);
 }
 
 /*
- * Handle cap IMPORT.  If there are temp bits from an older EXPORT,
- * clean them up.
+ * Handle cap IMPORT.
  *
- * caller holds s_mutex.
+ * caller holds s_mutex. acquires i_ceph_lock
  */
 static void handle_cap_import(struct ceph_mds_client *mdsc,
 			      struct inode *inode, struct ceph_mds_caps *im,
 			      struct ceph_mds_cap_peer *ph,
 			      struct ceph_mds_session *session,
-			      void *snaptrace, int snaptrace_len)
+			      struct ceph_cap **target_cap, int *old_issued)
+	__acquires(ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_cap *cap;
+	struct ceph_cap *cap, *ocap, *new_cap = NULL;
 	int mds = session->s_mds;
-	unsigned issued = le32_to_cpu(im->caps);
+	int issued;
+	unsigned caps = le32_to_cpu(im->caps);
 	unsigned wanted = le32_to_cpu(im->wanted);
 	unsigned seq = le32_to_cpu(im->seq);
 	unsigned mseq = le32_to_cpu(im->migrate_seq);
@@ -2924,40 +2925,52 @@
 	dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
 	     inode, ci, mds, mseq, peer);
 
+retry:
 	spin_lock(&ci->i_ceph_lock);
-	cap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
-	if (cap && cap->cap_id == p_cap_id) {
+	cap = __get_cap_for_mds(ci, mds);
+	if (!cap) {
+		if (!new_cap) {
+			spin_unlock(&ci->i_ceph_lock);
+			new_cap = ceph_get_cap(mdsc, NULL);
+			goto retry;
+		}
+		cap = new_cap;
+	} else {
+		if (new_cap) {
+			ceph_put_cap(mdsc, new_cap);
+			new_cap = NULL;
+		}
+	}
+
+	__ceph_caps_issued(ci, &issued);
+	issued |= __ceph_caps_dirty(ci);
+
+	ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+		     realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
+
+	ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
+	if (ocap && ocap->cap_id == p_cap_id) {
 		dout(" remove export cap %p mds%d flags %d\n",
-		     cap, peer, ph->flags);
+		     ocap, peer, ph->flags);
 		if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
-		    (cap->seq != le32_to_cpu(ph->seq) ||
-		     cap->mseq != le32_to_cpu(ph->mseq))) {
+		    (ocap->seq != le32_to_cpu(ph->seq) ||
+		     ocap->mseq != le32_to_cpu(ph->mseq))) {
 			pr_err("handle_cap_import: mismatched seq/mseq: "
 			       "ino (%llx.%llx) mds%d seq %d mseq %d "
 			       "importer mds%d has peer seq %d mseq %d\n",
-			       ceph_vinop(inode), peer, cap->seq,
-			       cap->mseq, mds, le32_to_cpu(ph->seq),
+			       ceph_vinop(inode), peer, ocap->seq,
+			       ocap->mseq, mds, le32_to_cpu(ph->seq),
 			       le32_to_cpu(ph->mseq));
 		}
-		ci->i_cap_exporting_issued = cap->issued;
-		__ceph_remove_cap(cap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
+		__ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
 	}
 
 	/* make sure we re-request max_size, if necessary */
 	ci->i_wanted_max_size = 0;
 	ci->i_requested_max_size = 0;
-	spin_unlock(&ci->i_ceph_lock);
 
-	down_write(&mdsc->snap_rwsem);
-	ceph_update_snap_trace(mdsc, snaptrace, snaptrace+snaptrace_len,
-			       false);
-	downgrade_write(&mdsc->snap_rwsem);
-	ceph_add_cap(inode, session, cap_id, -1,
-		     issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
-		     NULL /* no caps context */);
-	kick_flushing_inode_caps(mdsc, session, inode);
-	up_read(&mdsc->snap_rwsem);
-
+	*old_issued = issued;
+	*target_cap = cap;
 }
 
 /*
@@ -2977,7 +2990,7 @@
 	struct ceph_mds_caps *h;
 	struct ceph_mds_cap_peer *peer = NULL;
 	int mds = session->s_mds;
-	int op;
+	int op, issued;
 	u32 seq, mseq;
 	struct ceph_vino vino;
 	u64 cap_id;
@@ -3069,7 +3082,10 @@
 
 	case CEPH_CAP_OP_IMPORT:
 		handle_cap_import(mdsc, inode, h, peer, session,
-				  snaptrace, snaptrace_len);
+				  &cap, &issued);
+		handle_cap_grant(mdsc, inode, h,  snaptrace, snaptrace_len,
+				 msg->middle, session, cap, issued);
+		goto done_unlocked;
 	}
 
 	/* the rest require a cap */
@@ -3086,8 +3102,10 @@
 	switch (op) {
 	case CEPH_CAP_OP_REVOKE:
 	case CEPH_CAP_OP_GRANT:
-	case CEPH_CAP_OP_IMPORT:
-		handle_cap_grant(inode, h, session, cap, msg->middle);
+		__ceph_caps_issued(ci, &issued);
+		issued |= __ceph_caps_dirty(ci);
+		handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle,
+				 session, cap, issued);
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 00d6af6..8d7d782 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -169,7 +169,7 @@
 	return dentry;
 }
 
-struct dentry *ceph_get_parent(struct dentry *child)
+static struct dentry *ceph_get_parent(struct dentry *child)
 {
 	/* don't re-export snaps */
 	if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e4fff9f..04c89c2 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -10,6 +10,7 @@
 #include <linux/writeback.h>
 #include <linux/vmalloc.h>
 #include <linux/posix_acl.h>
+#include <linux/random.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -179,9 +180,8 @@
  * specified, copy the frag delegation info to the caller if
  * it is present.
  */
-u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
-		     struct ceph_inode_frag *pfrag,
-		     int *found)
+static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+			      struct ceph_inode_frag *pfrag, int *found)
 {
 	u32 t = ceph_frag_make(0, 0);
 	struct ceph_inode_frag *frag;
@@ -191,7 +191,6 @@
 	if (found)
 		*found = 0;
 
-	mutex_lock(&ci->i_fragtree_mutex);
 	while (1) {
 		WARN_ON(!ceph_frag_contains_value(t, v));
 		frag = __ceph_find_frag(ci, t);
@@ -220,10 +219,19 @@
 	}
 	dout("choose_frag(%x) = %x\n", v, t);
 
-	mutex_unlock(&ci->i_fragtree_mutex);
 	return t;
 }
 
+u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+		     struct ceph_inode_frag *pfrag, int *found)
+{
+	u32 ret;
+	mutex_lock(&ci->i_fragtree_mutex);
+	ret = __ceph_choose_frag(ci, v, pfrag, found);
+	mutex_unlock(&ci->i_fragtree_mutex);
+	return ret;
+}
+
 /*
  * Process dirfrag (delegation) info from the mds.  Include leaf
  * fragment in tree ONLY if ndist > 0.  Otherwise, only
@@ -237,11 +245,17 @@
 	u32 id = le32_to_cpu(dirinfo->frag);
 	int mds = le32_to_cpu(dirinfo->auth);
 	int ndist = le32_to_cpu(dirinfo->ndist);
+	int diri_auth = -1;
 	int i;
 	int err = 0;
 
+	spin_lock(&ci->i_ceph_lock);
+	if (ci->i_auth_cap)
+		diri_auth = ci->i_auth_cap->mds;
+	spin_unlock(&ci->i_ceph_lock);
+
 	mutex_lock(&ci->i_fragtree_mutex);
-	if (ndist == 0) {
+	if (ndist == 0 && mds == diri_auth) {
 		/* no delegation info needed. */
 		frag = __ceph_find_frag(ci, id);
 		if (!frag)
@@ -286,6 +300,75 @@
 	return err;
 }
 
+static int ceph_fill_fragtree(struct inode *inode,
+			      struct ceph_frag_tree_head *fragtree,
+			      struct ceph_mds_reply_dirfrag *dirinfo)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_inode_frag *frag;
+	struct rb_node *rb_node;
+	int i;
+	u32 id, nsplits;
+	bool update = false;
+
+	mutex_lock(&ci->i_fragtree_mutex);
+	nsplits = le32_to_cpu(fragtree->nsplits);
+	if (nsplits) {
+		i = prandom_u32() % nsplits;
+		id = le32_to_cpu(fragtree->splits[i].frag);
+		if (!__ceph_find_frag(ci, id))
+			update = true;
+	} else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) {
+		rb_node = rb_first(&ci->i_fragtree);
+		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+		if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node))
+			update = true;
+	}
+	if (!update && dirinfo) {
+		id = le32_to_cpu(dirinfo->frag);
+		if (id != __ceph_choose_frag(ci, id, NULL, NULL))
+			update = true;
+	}
+	if (!update)
+		goto out_unlock;
+
+	dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
+	rb_node = rb_first(&ci->i_fragtree);
+	for (i = 0; i < nsplits; i++) {
+		id = le32_to_cpu(fragtree->splits[i].frag);
+		frag = NULL;
+		while (rb_node) {
+			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+			if (ceph_frag_compare(frag->frag, id) >= 0) {
+				if (frag->frag != id)
+					frag = NULL;
+				else
+					rb_node = rb_next(rb_node);
+				break;
+			}
+			rb_node = rb_next(rb_node);
+			rb_erase(&frag->node, &ci->i_fragtree);
+			kfree(frag);
+			frag = NULL;
+		}
+		if (!frag) {
+			frag = __get_or_create_frag(ci, id);
+			if (IS_ERR(frag))
+				continue;
+		}
+		frag->split_by = le32_to_cpu(fragtree->splits[i].by);
+		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+	}
+	while (rb_node) {
+		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+		rb_node = rb_next(rb_node);
+		rb_erase(&frag->node, &ci->i_fragtree);
+		kfree(frag);
+	}
+out_unlock:
+	mutex_unlock(&ci->i_fragtree_mutex);
+	return 0;
+}
 
 /*
  * initialize a newly allocated inode.
@@ -341,7 +424,6 @@
 	INIT_LIST_HEAD(&ci->i_cap_snaps);
 	ci->i_head_snapc = NULL;
 	ci->i_snap_caps = 0;
-	ci->i_cap_exporting_issued = 0;
 
 	for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
 		ci->i_nr_by_mode[i] = 0;
@@ -407,7 +489,7 @@
 
 	/*
 	 * we may still have a snap_realm reference if there are stray
-	 * caps in i_cap_exporting_issued or i_snap_caps.
+	 * caps in i_snap_caps.
 	 */
 	if (ci->i_snap_realm) {
 		struct ceph_mds_client *mdsc =
@@ -582,22 +664,26 @@
 		      unsigned long ttl_from, int cap_fmode,
 		      struct ceph_cap_reservation *caps_reservation)
 {
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_reply_inode *info = iinfo->in;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int i;
-	int issued = 0, implemented;
+	int issued = 0, implemented, new_issued;
 	struct timespec mtime, atime, ctime;
-	u32 nsplits;
-	struct ceph_inode_frag *frag;
-	struct rb_node *rb_node;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_cap *new_cap = NULL;
 	int err = 0;
-	int queue_trunc = 0;
+	bool wake = false;
+	bool queue_trunc = false;
+	bool new_version = false;
 
 	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
 	     ci->i_version);
 
+	/* prealloc new cap struct */
+	if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
+		new_cap = ceph_get_cap(mdsc, caps_reservation);
+
 	/*
 	 * prealloc xattr data, if it looks like we'll need it.  only
 	 * if len > 4 (meaning there are actually xattrs; the first 4
@@ -623,19 +709,23 @@
 	 *   3    2     skip
 	 *   3    3     update
 	 */
-	if (le64_to_cpu(info->version) > 0 &&
-	    (ci->i_version & ~1) >= le64_to_cpu(info->version))
-		goto no_change;
-	
+	if (ci->i_version == 0 ||
+	    ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+	     le64_to_cpu(info->version) > (ci->i_version & ~1)))
+		new_version = true;
+
 	issued = __ceph_caps_issued(ci, &implemented);
 	issued |= implemented | __ceph_caps_dirty(ci);
+	new_issued = ~issued & le32_to_cpu(info->cap.caps);
 
 	/* update inode */
 	ci->i_version = le64_to_cpu(info->version);
 	inode->i_version++;
 	inode->i_rdev = le32_to_cpu(info->rdev);
+	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
 
-	if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+	if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
+	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = le32_to_cpu(info->mode);
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
@@ -644,23 +734,35 @@
 		     from_kgid(&init_user_ns, inode->i_gid));
 	}
 
-	if ((issued & CEPH_CAP_LINK_EXCL) == 0)
+	if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
+	    (issued & CEPH_CAP_LINK_EXCL) == 0)
 		set_nlink(inode, le32_to_cpu(info->nlink));
 
-	/* be careful with mtime, atime, size */
-	ceph_decode_timespec(&atime, &info->atime);
-	ceph_decode_timespec(&mtime, &info->mtime);
-	ceph_decode_timespec(&ctime, &info->ctime);
-	queue_trunc = ceph_fill_file_size(inode, issued,
-					  le32_to_cpu(info->truncate_seq),
-					  le64_to_cpu(info->truncate_size),
-					  le64_to_cpu(info->size));
-	ceph_fill_file_time(inode, issued,
-			    le32_to_cpu(info->time_warp_seq),
-			    &ctime, &mtime, &atime);
+	if (new_version || (new_issued & CEPH_CAP_ANY_RD)) {
+		/* be careful with mtime, atime, size */
+		ceph_decode_timespec(&atime, &info->atime);
+		ceph_decode_timespec(&mtime, &info->mtime);
+		ceph_decode_timespec(&ctime, &info->ctime);
+		ceph_fill_file_time(inode, issued,
+				le32_to_cpu(info->time_warp_seq),
+				&ctime, &mtime, &atime);
+	}
 
-	ci->i_layout = info->layout;
-	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+	if (new_version ||
+	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+		ci->i_layout = info->layout;
+		queue_trunc = ceph_fill_file_size(inode, issued,
+					le32_to_cpu(info->truncate_seq),
+					le64_to_cpu(info->truncate_size),
+					le64_to_cpu(info->size));
+		/* only update max_size on auth cap */
+		if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+		    ci->i_max_size != le64_to_cpu(info->max_size)) {
+			dout("max_size %lld -> %llu\n", ci->i_max_size,
+					le64_to_cpu(info->max_size));
+			ci->i_max_size = le64_to_cpu(info->max_size);
+		}
+	}
 
 	/* xattrs */
 	/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
@@ -745,58 +847,6 @@
 		dout(" marking %p complete (empty)\n", inode);
 		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
 	}
-no_change:
-	/* only update max_size on auth cap */
-	if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
-	    ci->i_max_size != le64_to_cpu(info->max_size)) {
-		dout("max_size %lld -> %llu\n", ci->i_max_size,
-		     le64_to_cpu(info->max_size));
-		ci->i_max_size = le64_to_cpu(info->max_size);
-	}
-
-	spin_unlock(&ci->i_ceph_lock);
-
-	/* queue truncate if we saw i_size decrease */
-	if (queue_trunc)
-		ceph_queue_vmtruncate(inode);
-
-	/* populate frag tree */
-	/* FIXME: move me up, if/when version reflects fragtree changes */
-	nsplits = le32_to_cpu(info->fragtree.nsplits);
-	mutex_lock(&ci->i_fragtree_mutex);
-	rb_node = rb_first(&ci->i_fragtree);
-	for (i = 0; i < nsplits; i++) {
-		u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
-		frag = NULL;
-		while (rb_node) {
-			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
-			if (ceph_frag_compare(frag->frag, id) >= 0) {
-				if (frag->frag != id)
-					frag = NULL;
-				else
-					rb_node = rb_next(rb_node);
-				break;
-			}
-			rb_node = rb_next(rb_node);
-			rb_erase(&frag->node, &ci->i_fragtree);
-			kfree(frag);
-			frag = NULL;
-		}
-		if (!frag) {
-			frag = __get_or_create_frag(ci, id);
-			if (IS_ERR(frag))
-				continue;
-		}
-		frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
-		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
-	}
-	while (rb_node) {
-		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
-		rb_node = rb_next(rb_node);
-		rb_erase(&frag->node, &ci->i_fragtree);
-		kfree(frag);
-	}
-	mutex_unlock(&ci->i_fragtree_mutex);
 
 	/* were we issued a capability? */
 	if (info->cap.caps) {
@@ -809,30 +859,41 @@
 				     le32_to_cpu(info->cap.seq),
 				     le32_to_cpu(info->cap.mseq),
 				     le64_to_cpu(info->cap.realm),
-				     info->cap.flags,
-				     caps_reservation);
+				     info->cap.flags, &new_cap);
+			wake = true;
 		} else {
-			spin_lock(&ci->i_ceph_lock);
 			dout(" %p got snap_caps %s\n", inode,
 			     ceph_cap_string(le32_to_cpu(info->cap.caps)));
 			ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
 			if (cap_fmode >= 0)
 				__ceph_get_fmode(ci, cap_fmode);
-			spin_unlock(&ci->i_ceph_lock);
 		}
 	} else if (cap_fmode >= 0) {
 		pr_warn("mds issued no caps on %llx.%llx\n",
 			   ceph_vinop(inode));
 		__ceph_get_fmode(ci, cap_fmode);
 	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (wake)
+		wake_up_all(&ci->i_cap_wq);
+
+	/* queue truncate if we saw i_size decrease */
+	if (queue_trunc)
+		ceph_queue_vmtruncate(inode);
+
+	/* populate frag tree */
+	if (S_ISDIR(inode->i_mode))
+		ceph_fill_fragtree(inode, &info->fragtree, dirinfo);
 
 	/* update delegation info? */
 	if (dirinfo)
 		ceph_fill_dirfrag(inode, dirinfo);
 
 	err = 0;
-
 out:
+	if (new_cap)
+		ceph_put_cap(mdsc, new_cap);
 	if (xattr_blob)
 		ceph_buffer_put(xattr_blob);
 	return err;
@@ -1485,7 +1546,7 @@
 	orig_gen = ci->i_rdcache_gen;
 	spin_unlock(&ci->i_ceph_lock);
 
-	truncate_inode_pages(inode->i_mapping, 0);
+	truncate_pagecache(inode, 0);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (orig_gen == ci->i_rdcache_gen &&
@@ -1588,7 +1649,7 @@
 	     ci->i_truncate_pending, to);
 	spin_unlock(&ci->i_ceph_lock);
 
-	truncate_inode_pages(inode->i_mapping, to);
+	truncate_pagecache(inode, to);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (to == ci->i_truncate_size) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9a33b98..92a2548 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1558,6 +1558,8 @@
 	init_completion(&req->r_safe_completion);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 
+	req->r_stamp = CURRENT_TIME;
+
 	req->r_op = op;
 	req->r_direct_mode = mode;
 	return req;
@@ -1783,7 +1785,8 @@
 	}
 
 	len = sizeof(*head) +
-		pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64));
+		pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
+		sizeof(struct timespec);
 
 	/* calculate (max) length for cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
@@ -1800,6 +1803,7 @@
 		goto out_free2;
 	}
 
+	msg->hdr.version = 2;
 	msg->hdr.tid = cpu_to_le64(req->r_tid);
 
 	head = msg->front.iov_base;
@@ -1836,6 +1840,9 @@
 		      mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
 	head->num_releases = cpu_to_le16(releases);
 
+	/* time stamp */
+	ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+
 	BUG_ON(p > end);
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e90cfcc..e00737c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -194,6 +194,7 @@
 	int r_fmode;        /* file mode, if expecting cap */
 	kuid_t r_uid;
 	kgid_t r_gid;
+	struct timespec r_stamp;
 
 	/* for choosing which mds to send this request to */
 	int r_direct_mode;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index ead05cc..12b2074 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -292,7 +292,6 @@
 	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
 						    dirty|flushing caps */
 	unsigned i_snap_caps;           /* cap bits for snapped files */
-	unsigned i_cap_exporting_issued;
 
 	int i_nr_by_mode[CEPH_FILE_MODE_NUM];  /* open file counts */
 
@@ -775,11 +774,13 @@
 extern const char *ceph_cap_string(int c);
 extern void ceph_handle_caps(struct ceph_mds_session *session,
 			     struct ceph_msg *msg);
-extern int ceph_add_cap(struct inode *inode,
-			struct ceph_mds_session *session, u64 cap_id,
-			int fmode, unsigned issued, unsigned wanted,
-			unsigned cap, unsigned seq, u64 realmino, int flags,
-			struct ceph_cap_reservation *caps_reservation);
+extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+				     struct ceph_cap_reservation *ctx);
+extern void ceph_add_cap(struct inode *inode,
+			 struct ceph_mds_session *session, u64 cap_id,
+			 int fmode, unsigned issued, unsigned wanted,
+			 unsigned cap, unsigned seq, u64 realmino, int flags,
+			 struct ceph_cap **new_cap);
 extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
 extern void ceph_put_cap(struct ceph_mds_client *mdsc,
 			 struct ceph_cap *cap);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 1e5b453..d08e079 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -617,6 +617,11 @@
 	int nodeid = sn_send_failed->ssf_info.sinfo_ppid;
 
 	log_print("Retry sending %d bytes to node id %d", len, nodeid);
+	
+	if (!nodeid) {
+		log_print("Shouldn't resend data via listening connection.");
+		return;
+	}
 
 	con = nodeid2con(nodeid, 0);
 	if (!con) {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index b73e062..b10b48c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -910,7 +910,7 @@
 void eventpoll_release_file(struct file *file)
 {
 	struct eventpoll *ep;
-	struct epitem *epi;
+	struct epitem *epi, *next;
 
 	/*
 	 * We don't want to get "file->f_lock" because it is not
@@ -926,7 +926,7 @@
 	 * Besides, ep_remove() acquires the lock, so we can't hold it here.
 	 */
 	mutex_lock(&epmutex);
-	list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
+	list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
 		ep = epi->ep;
 		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
diff --git a/fs/locks.c b/fs/locks.c
index da57c9b..717fbc4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -431,7 +431,7 @@
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = (fl_owner_t)filp;
+	fl->fl_owner = (fl_owner_t)current->files;
 	fl->fl_pid = current->tgid;
 
 	fl->fl_file = filp;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c0d45ce..2204e1f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -41,6 +41,7 @@
 #include <linux/ratelimit.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/addr.h>
+#include <linux/hash.h>
 #include "xdr4.h"
 #include "xdr4cb.h"
 #include "vfs.h"
@@ -364,6 +365,79 @@
 	return openlockstateid(nfs4_alloc_stid(clp, stateid_slab));
 }
 
+/*
+ * When we recall a delegation, we should be careful not to hand it
+ * out again straight away.
+ * To ensure this we keep a pair of bloom filters ('new' and 'old')
+ * in which the filehandles of recalled delegations are "stored".
+ * If a filehandle appear in either filter, a delegation is blocked.
+ * When a delegation is recalled, the filehandle is stored in the "new"
+ * filter.
+ * Every 30 seconds we swap the filters and clear the "new" one,
+ * unless both are empty of course.
+ *
+ * Each filter is 256 bits.  We hash the filehandle to 32bit and use the
+ * low 3 bytes as hash-table indices.
+ *
+ * 'state_lock', which is always held when block_delegations() is called,
+ * is used to manage concurrent access.  Testing does not need the lock
+ * except when swapping the two filters.
+ */
+static struct bloom_pair {
+	int	entries, old_entries;
+	time_t	swap_time;
+	int	new; /* index into 'set' */
+	DECLARE_BITMAP(set[2], 256);
+} blocked_delegations;
+
+static int delegation_blocked(struct knfsd_fh *fh)
+{
+	u32 hash;
+	struct bloom_pair *bd = &blocked_delegations;
+
+	if (bd->entries == 0)
+		return 0;
+	if (seconds_since_boot() - bd->swap_time > 30) {
+		spin_lock(&state_lock);
+		if (seconds_since_boot() - bd->swap_time > 30) {
+			bd->entries -= bd->old_entries;
+			bd->old_entries = bd->entries;
+			memset(bd->set[bd->new], 0,
+			       sizeof(bd->set[0]));
+			bd->new = 1-bd->new;
+			bd->swap_time = seconds_since_boot();
+		}
+		spin_unlock(&state_lock);
+	}
+	hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0);
+	if (test_bit(hash&255, bd->set[0]) &&
+	    test_bit((hash>>8)&255, bd->set[0]) &&
+	    test_bit((hash>>16)&255, bd->set[0]))
+		return 1;
+
+	if (test_bit(hash&255, bd->set[1]) &&
+	    test_bit((hash>>8)&255, bd->set[1]) &&
+	    test_bit((hash>>16)&255, bd->set[1]))
+		return 1;
+
+	return 0;
+}
+
+static void block_delegations(struct knfsd_fh *fh)
+{
+	u32 hash;
+	struct bloom_pair *bd = &blocked_delegations;
+
+	hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0);
+
+	__set_bit(hash&255, bd->set[bd->new]);
+	__set_bit((hash>>8)&255, bd->set[bd->new]);
+	__set_bit((hash>>16)&255, bd->set[bd->new]);
+	if (bd->entries == 0)
+		bd->swap_time = seconds_since_boot();
+	bd->entries += 1;
+}
+
 static struct nfs4_delegation *
 alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh)
 {
@@ -372,6 +446,8 @@
 	dprintk("NFSD alloc_init_deleg\n");
 	if (num_delegations > max_delegations)
 		return NULL;
+	if (delegation_blocked(&current_fh->fh_handle))
+		return NULL;
 	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
 	if (dp == NULL)
 		return dp;
@@ -2770,6 +2846,8 @@
 	/* Only place dl_time is set; protected by i_lock: */
 	dp->dl_time = get_seconds();
 
+	block_delegations(&dp->dl_fh);
+
 	nfsd4_cb_recall(dp);
 }
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2d305a1..83baf2b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2687,6 +2687,7 @@
 		nfserr = nfserr_toosmall;
 		goto fail;
 	case nfserr_noent:
+		xdr_truncate_encode(xdr, start_offset);
 		goto skip_entry;
 	default:
 		/*
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 6eb1d3c..9b9b6f2 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -53,7 +53,7 @@
 	u8 bit_offset;
 	u8 access_size;
 	u64 address;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_processor_cx {
 	u8 valid;
@@ -83,7 +83,7 @@
 	u64 domain;
 	u64 coord_type;
 	u64 num_processors;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_pct_register {
 	u8 descriptor;
@@ -93,7 +93,7 @@
 	u8 bit_offset;
 	u8 reserved;
 	u64 address;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_processor_px {
 	u64 core_frequency;	/* megahertz */
@@ -124,7 +124,7 @@
 	u64 domain;
 	u64 coord_type;
 	u64 num_processors;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_ptc_register {
 	u8 descriptor;
@@ -134,7 +134,7 @@
 	u8 bit_offset;
 	u8 reserved;
 	u64 address;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_processor_tx_tss {
 	u64 freqpercentage;	/* */
diff --git a/include/drm/i915_powerwell.h b/include/drm/i915_powerwell.h
index cfdc884..2baba99 100644
--- a/include/drm/i915_powerwell.h
+++ b/include/drm/i915_powerwell.h
@@ -30,7 +30,7 @@
 #define _I915_POWERWELL_H_
 
 /* For use by hda_i915 driver */
-extern void i915_request_power_well(void);
-extern void i915_release_power_well(void);
+extern int i915_request_power_well(void);
+extern int i915_release_power_well(void);
 
 #endif				/* _I915_POWERWELL_H_ */
diff --git a/include/dt-bindings/clk/ti-dra7-atl.h b/include/dt-bindings/clk/ti-dra7-atl.h
new file mode 100644
index 0000000..42dd416
--- /dev/null
+++ b/include/dt-bindings/clk/ti-dra7-atl.h
@@ -0,0 +1,40 @@
+/*
+ * This header provides constants for DRA7 ATL (Audio Tracking Logic)
+ *
+ * The constants defined in this header are used in dts files
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc.
+ *
+ * Peter Ujfalusi <peter.ujfalusi@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_DRA7_ATL_H
+#define _DT_BINDINGS_CLK_DRA7_ATL_H
+
+#define DRA7_ATL_WS_MCASP1_FSR		0
+#define DRA7_ATL_WS_MCASP1_FSX		1
+#define DRA7_ATL_WS_MCASP2_FSR		2
+#define DRA7_ATL_WS_MCASP2_FSX		3
+#define DRA7_ATL_WS_MCASP3_FSX		4
+#define DRA7_ATL_WS_MCASP4_FSX		5
+#define DRA7_ATL_WS_MCASP5_FSX		6
+#define DRA7_ATL_WS_MCASP6_FSX		7
+#define DRA7_ATL_WS_MCASP7_FSX		8
+#define DRA7_ATL_WS_MCASP8_FSX		9
+#define DRA7_ATL_WS_MCASP8_AHCLKX	10
+#define DRA7_ATL_WS_XREF_CLK3		11
+#define DRA7_ATL_WS_XREF_CLK0		12
+#define DRA7_ATL_WS_XREF_CLK1		13
+#define DRA7_ATL_WS_XREF_CLK2		14
+#define DRA7_ATL_WS_OSC1_X1		15
+
+#endif
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a002cf1..eb726b9 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -42,7 +42,7 @@
 	unsigned int		nr_ctx;
 	struct blk_mq_ctx	**ctxs;
 
-	unsigned int		wait_index;
+	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 31e1105..713f8b6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -920,7 +920,7 @@
 					       sector_t offset)
 {
 	if (!q->limits.chunk_sectors)
-		return q->limits.max_hw_sectors;
+		return q->limits.max_sectors;
 
 	return q->limits.chunk_sectors -
 			(offset & (q->limits.chunk_sectors - 1));
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 5f6db18..3c97d5e 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -625,6 +625,8 @@
 			   CEPH_CAP_LINK_EXCL |		\
 			   CEPH_CAP_XATTR_EXCL |	\
 			   CEPH_CAP_FILE_EXCL)
+#define CEPH_CAP_ANY_FILE_RD (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE | \
+			      CEPH_CAP_FILE_SHARED)
 #define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |	\
 			      CEPH_CAP_FILE_EXCL)
 #define CEPH_CAP_ANY_WR   (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR)
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index a486f39..deb47e4 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -40,9 +40,9 @@
 };
 
 /*
- * ceph_mon_generic_request is being used for the statfs and poolop requests
- * which are bening done a bit differently because we need to get data back
- * to the caller
+ * ceph_mon_generic_request is being used for the statfs, poolop and
+ * mon_get_version requests which are being done a bit differently
+ * because we need to get data back to the caller
  */
 struct ceph_mon_generic_request {
 	struct kref kref;
@@ -104,10 +104,15 @@
 extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have);
 
 extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
+extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+				 unsigned long timeout);
 
 extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
 			       struct ceph_statfs *buf);
 
+extern int ceph_monc_do_get_version(struct ceph_mon_client *monc,
+				    const char *what, u64 *newest);
+
 extern int ceph_monc_open_session(struct ceph_mon_client *monc);
 
 extern int ceph_monc_validate_auth(struct ceph_mon_client *monc);
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 4a21a87..e8d8a35 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -41,6 +41,8 @@
  * @idlest_reg: register containing the DPLL idle status bitfield
  * @autoidle_mask: mask of the DPLL autoidle mode bitfield in @autoidle_reg
  * @freqsel_mask: mask of the DPLL jitter correction bitfield in @control_reg
+ * @dcc_mask: mask of the DPLL DCC correction bitfield @mult_div1_reg
+ * @dcc_rate: rate atleast which DCC @dcc_mask must be set
  * @idlest_mask: mask of the DPLL idle status bitfield in @idlest_reg
  * @lpmode_mask: mask of the DPLL low-power mode bitfield in @control_reg
  * @m4xen_mask: mask of the DPLL M4X multiplier bitfield in @control_reg
@@ -86,6 +88,8 @@
 	u32			idlest_mask;
 	u32			dco_mask;
 	u32			sddiv_mask;
+	u32			dcc_mask;
+	unsigned long		dcc_rate;
 	u32			lpmode_mask;
 	u32			m4xen_mask;
 	u8			auto_recal_bit;
@@ -94,7 +98,26 @@
 	u8			flags;
 };
 
-struct clk_hw_omap_ops;
+struct clk_hw_omap;
+
+/**
+ * struct clk_hw_omap_ops - OMAP clk ops
+ * @find_idlest: find idlest register information for a clock
+ * @find_companion: find companion clock register information for a clock,
+ *		    basically converts CM_ICLKEN* <-> CM_FCLKEN*
+ * @allow_idle: enables autoidle hardware functionality for a clock
+ * @deny_idle: prevent autoidle hardware functionality for a clock
+ */
+struct clk_hw_omap_ops {
+	void	(*find_idlest)(struct clk_hw_omap *oclk,
+			       void __iomem **idlest_reg,
+			       u8 *idlest_bit, u8 *idlest_val);
+	void	(*find_companion)(struct clk_hw_omap *oclk,
+				  void __iomem **other_reg,
+				  u8 *other_bit);
+	void	(*allow_idle)(struct clk_hw_omap *oclk);
+	void	(*deny_idle)(struct clk_hw_omap *oclk);
+};
 
 /**
  * struct clk_hw_omap - OMAP struct clk
@@ -259,6 +282,12 @@
 void omap2_dflt_clk_disable(struct clk_hw *hw);
 int omap2_dflt_clk_is_enabled(struct clk_hw *hw);
 void omap3_clk_lock_dpll5(void);
+unsigned long omap2_dpllcore_recalc(struct clk_hw *hw,
+				    unsigned long parent_rate);
+int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate,
+			     unsigned long parent_rate);
+void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw);
+void omap2xxx_clkt_vps_init(void);
 
 void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index);
 void ti_dt_clocks_register(struct ti_dt_clk *oclks);
@@ -278,6 +307,8 @@
 int dra7xx_dt_clk_init(void);
 int am33xx_dt_clk_init(void);
 int am43xx_dt_clk_init(void);
+int omap2420_dt_clk_init(void);
+int omap2430_dt_clk_init(void);
 
 #ifdef CONFIG_OF
 void of_ti_clk_allow_autoidle_all(void);
@@ -287,6 +318,8 @@
 static inline void of_ti_clk_deny_autoidle_all(void) { }
 #endif
 
+extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll;
+extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait;
 extern const struct clk_hw_omap_ops clkhwops_omap3_dpll;
 extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx;
 extern const struct clk_hw_omap_ops clkhwops_wait;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 4ff262e..e2a6bd7 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -133,7 +133,6 @@
 extern int elv_register_queue(struct request_queue *q);
 extern void elv_unregister_queue(struct request_queue *q);
 extern int elv_may_queue(struct request_queue *, int);
-extern void elv_abort_queue(struct request_queue *);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *q, struct request *rq,
 			   struct bio *bio, gfp_t gfp_mask);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 338e6f7..e11d60c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1921,6 +1921,12 @@
 
 static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
+	/*
+	 * Since this check is lockless, we must ensure that any refcounts
+	 * taken are done before checking inode->i_flock. Otherwise, we could
+	 * end up racing with tasks trying to set a new lease on this file.
+	 */
+	smp_mb();
 	if (inode->i_flock)
 		return __break_lease(inode, mode, FL_DELEG);
 	return 0;
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index e5a5894..d99800c 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -117,6 +117,7 @@
 #define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
+#define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index abe3de1..66f9a04 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3305,6 +3305,13 @@
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_IPIP    != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index a50173c..2bf4031 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1,6 +1,6 @@
 /*
  * Definitions for the NVM Express interface
- * Copyright (c) 2011-2013, Intel Corporation.
+ * Copyright (c) 2011-2014, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _LINUX_NVME_H
@@ -66,8 +62,8 @@
 
 #define NVME_VS(major, minor)	(major << 16 | minor)
 
-extern unsigned char io_timeout;
-#define NVME_IO_TIMEOUT	(io_timeout * HZ)
+extern unsigned char nvme_io_timeout;
+#define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
 
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
@@ -94,7 +90,7 @@
 	struct miscdevice miscdev;
 	work_func_t reset_workfn;
 	struct work_struct reset_work;
-	struct notifier_block nb;
+	struct work_struct cpu_work;
 	char name[12];
 	char serial[20];
 	char model[40];
@@ -103,6 +99,7 @@
 	u32 stripe_size;
 	u16 oncs;
 	u16 abort_limit;
+	u8 vwc;
 	u8 initialized;
 };
 
@@ -159,7 +156,6 @@
 void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
 			struct nvme_iod *iod);
 int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_command *, u32 *);
-int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns);
 int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *,
 							u32 *result);
 int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns,
diff --git a/include/linux/platform_data/shtc1.h b/include/linux/platform_data/shtc1.h
new file mode 100644
index 0000000..7b8c353
--- /dev/null
+++ b/include/linux/platform_data/shtc1.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2014 Sensirion AG, Switzerland
+ * Author: Johannes Winkelmann <johannes.winkelmann@sensirion.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ *
+ */
+
+#ifndef __SHTC1_H_
+#define __SHTC1_H_
+
+struct shtc1_platform_data {
+	bool blocking_io;
+	bool high_precision;
+};
+#endif /* __SHTC1_H_ */
diff --git a/include/linux/profile.h b/include/linux/profile.h
index aaad386..b537a25 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -44,6 +44,7 @@
 int profile_init(void);
 int profile_setup(char *str);
 void profile_tick(int type);
+int setup_profiling_timer(unsigned int multiplier);
 
 /*
  * Add multiple profiler hits to a given address:
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index a2d9d81..14ec18d 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -395,6 +395,11 @@
 {
 }
 
+static inline int regulator_can_change_voltage(struct regulator *regulator)
+{
+	return 0;
+}
+
 static inline int regulator_set_voltage(struct regulator *regulator,
 					int min_uV, int max_uV)
 {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5b5cd31..ec89301 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -338,17 +338,18 @@
 
 	SKB_GSO_GRE = 1 << 6,
 
-	SKB_GSO_IPIP = 1 << 7,
+	SKB_GSO_GRE_CSUM = 1 << 7,
 
-	SKB_GSO_SIT = 1 << 8,
+	SKB_GSO_IPIP = 1 << 8,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 9,
+	SKB_GSO_SIT = 1 << 9,
 
-	SKB_GSO_MPLS = 1 << 10,
+	SKB_GSO_UDP_TUNNEL = 1 << 10,
 
 	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
 
-	SKB_GSO_GRE_CSUM = 1 << 12,
+	SKB_GSO_MPLS = 1 << 12,
+
 };
 
 #if BITS_PER_LONG > 32
@@ -1853,6 +1854,18 @@
 	return pskb_may_pull(skb, skb_network_offset(skb) + len);
 }
 
+static inline void skb_pop_rcv_encapsulation(struct sk_buff *skb)
+{
+	/* Only continue with checksum unnecessary if device indicated
+	 * it is valid across encapsulation (skb->encapsulation was set).
+	 */
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY && !skb->encapsulation)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	skb->encapsulation = 0;
+	skb->csum_valid = 0;
+}
+
 /*
  * CPUs often take a performance hit when accessing unaligned memory
  * locations. The actual performance hit varies, it can be small if the
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index f76994b..519064e 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -327,6 +327,7 @@
 extern void hibernation_set_ops(const struct platform_hibernation_ops *ops);
 extern int hibernate(void);
 extern bool system_entering_hibernation(void);
+extern bool hibernation_available(void);
 asmlinkage int swsusp_save(void);
 extern struct pbe *restore_pblist;
 #else /* CONFIG_HIBERNATION */
@@ -339,6 +340,7 @@
 static inline void hibernation_set_ops(const struct platform_hibernation_ops *ops) {}
 static inline int hibernate(void) { return -ENOSYS; }
 static inline bool system_entering_hibernation(void) { return false; }
+static inline bool hibernation_available(void) { return false; }
 #endif /* CONFIG_HIBERNATION */
 
 /* Hibernation and suspend events */
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index bca25dc..8fab6fa 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -432,6 +432,7 @@
 void *vb2_plane_cookie(struct vb2_buffer *vb, unsigned int plane_no);
 
 void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state);
+void vb2_discard_done(struct vb2_queue *q);
 int vb2_wait_for_all_buffers(struct vb2_queue *q);
 
 int vb2_querybuf(struct vb2_queue *q, struct v4l2_buffer *b);
diff --git a/include/net/udp.h b/include/net/udp.h
index 2ecfc6e1..68a1fef 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -111,7 +111,9 @@
  */
 static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov);
+	return (UDP_SKB_CB(skb)->cscov == skb->len ?
+		__skb_checksum_complete(skb) :
+		__skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov));
 }
 
 static inline int udp_lib_checksum_complete(struct sk_buff *skb)
diff --git a/include/sound/core.h b/include/sound/core.h
index eedda2c..1df3f2f 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -116,6 +116,8 @@
 	int user_ctl_count;		/* count of all user controls */
 	struct list_head controls;	/* all controls for this card */
 	struct list_head ctl_files;	/* active control files */
+	struct mutex user_ctl_lock;	/* protects user controls against
+					   concurrent access */
 
 	struct snd_info_entry *proc_root;	/* root for soundcard specific files */
 	struct snd_info_entry *proc_id;	/* the card id */
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index b4d6697..d854fb3 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -932,7 +932,7 @@
 				   struct timespec *tv)
 {
 	if (runtime->tstamp_type == SNDRV_PCM_TSTAMP_TYPE_MONOTONIC)
-		do_posix_clock_monotonic_gettime(tv);
+		ktime_get_ts(tv);
 	else
 		getnstimeofday(tv);
 }
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 7554fd3..6f9c38c 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -306,6 +306,14 @@
 	char buf[BTRFS_SEARCH_ARGS_BUFSIZE];
 };
 
+struct btrfs_ioctl_search_args_v2 {
+	struct btrfs_ioctl_search_key key; /* in/out - search parameters */
+	__u64 buf_size;		   /* in - size of buffer
+					    * out - on EOVERFLOW: needed size
+					    *       to store item */
+	__u64 buf[0];                       /* out - found items */
+};
+
 struct btrfs_ioctl_clone_range_args {
   __s64 src_fd;
   __u64 src_offset, src_length;
@@ -558,6 +566,8 @@
 				struct btrfs_ioctl_defrag_range_args)
 #define BTRFS_IOC_TREE_SEARCH _IOWR(BTRFS_IOCTL_MAGIC, 17, \
 				   struct btrfs_ioctl_search_args)
+#define BTRFS_IOC_TREE_SEARCH_V2 _IOWR(BTRFS_IOCTL_MAGIC, 17, \
+					   struct btrfs_ioctl_search_args_v2)
 #define BTRFS_IOC_INO_LOOKUP _IOWR(BTRFS_IOCTL_MAGIC, 18, \
 				   struct btrfs_ioctl_ino_lookup_args)
 #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64)
diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index 096fe1c..29a7d86 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -1,6 +1,6 @@
 /*
  * Definitions for the NVM Express interface
- * Copyright (c) 2011-2013, Intel Corporation.
+ * Copyright (c) 2011-2014, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _UAPI_LINUX_NVME_H
@@ -31,7 +27,12 @@
 	__u8			read_lat;
 	__u8			write_tput;
 	__u8			write_lat;
-	__u8			rsvd16[16];
+	__le16			idle_power;
+	__u8			idle_scale;
+	__u8			rsvd19;
+	__le16			active_power;
+	__u8			active_work_scale;
+	__u8			rsvd23[9];
 };
 
 enum {
@@ -49,7 +50,9 @@
 	__u8			ieee[3];
 	__u8			mic;
 	__u8			mdts;
-	__u8			rsvd78[178];
+	__u16			cntlid;
+	__u32			ver;
+	__u8			rsvd84[172];
 	__le16			oacs;
 	__u8			acl;
 	__u8			aerl;
@@ -57,7 +60,11 @@
 	__u8			lpa;
 	__u8			elpe;
 	__u8			npss;
-	__u8			rsvd264[248];
+	__u8			avscc;
+	__u8			apsta;
+	__le16			wctemp;
+	__le16			cctemp;
+	__u8			rsvd270[242];
 	__u8			sqes;
 	__u8			cqes;
 	__u8			rsvd514[2];
@@ -68,7 +75,12 @@
 	__u8			vwc;
 	__le16			awun;
 	__le16			awupf;
-	__u8			rsvd530[1518];
+	__u8			nvscc;
+	__u8			rsvd531;
+	__le16			acwu;
+	__u8			rsvd534[2];
+	__le32			sgls;
+	__u8			rsvd540[1508];
 	struct nvme_id_power_state	psd[32];
 	__u8			vs[1024];
 };
@@ -77,6 +89,7 @@
 	NVME_CTRL_ONCS_COMPARE			= 1 << 0,
 	NVME_CTRL_ONCS_WRITE_UNCORRECTABLE	= 1 << 1,
 	NVME_CTRL_ONCS_DSM			= 1 << 2,
+	NVME_CTRL_VWC_PRESENT			= 1 << 0,
 };
 
 struct nvme_lbaf {
@@ -95,7 +108,15 @@
 	__u8			mc;
 	__u8			dpc;
 	__u8			dps;
-	__u8			rsvd30[98];
+	__u8			nmic;
+	__u8			rescap;
+	__u8			fpi;
+	__u8			rsvd33;
+	__le16			nawun;
+	__le16			nawupf;
+	__le16			nacwu;
+	__u8			rsvd40[80];
+	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
 	__u8			rsvd192[192];
 	__u8			vs[3712];
@@ -126,7 +147,10 @@
 	__u8			unsafe_shutdowns[16];
 	__u8			media_errors[16];
 	__u8			num_err_log_entries[16];
-	__u8			rsvd192[320];
+	__le32			warning_temp_time;
+	__le32			critical_comp_time;
+	__le16			temp_sensor[8];
+	__u8			rsvd216[296];
 };
 
 enum {
@@ -282,6 +306,10 @@
 	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
 	NVME_FEAT_ASYNC_EVENT	= 0x0b,
 	NVME_FEAT_SW_PROGRESS	= 0x0c,
+	NVME_LOG_ERROR		= 0x01,
+	NVME_LOG_SMART		= 0x02,
+	NVME_LOG_FW_SLOT	= 0x03,
+	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
 	NVME_FWACT_REPL_ACTV	= (1 << 3),
 	NVME_FWACT_ACTV		= (2 << 3),
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 5759810..21eed48 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -80,7 +80,7 @@
 struct snd_compr_avail {
 	__u64 avail;
 	struct snd_compr_tstamp tstamp;
-};
+} __attribute__((packed));
 
 enum snd_compr_direction {
 	SND_COMPRESS_PLAYBACK = 0,
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d5..ab29b6a 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -31,3 +31,8 @@
 {
 	return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index a620d4d..fc60594 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -83,6 +83,47 @@
 		owner = *p;
 	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+
+	clear_rt_mutex_waiters(lock);
+	raw_spin_unlock(&lock->wait_lock);
+	/*
+	 * If a new waiter comes in between the unlock and the cmpxchg
+	 * we have two situations:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 * cmpxchg(p, owner, 0) == owner
+	 *					mark_rt_mutex_waiters(lock);
+	 *					acquire(lock);
+	 * or:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					mark_rt_mutex_waiters(lock);
+	 *
+	 * cmpxchg(p, owner, 0) != owner
+	 *					enqueue_waiter();
+	 *					unlock(wait_lock);
+	 * lock(wait_lock);
+	 * wake waiter();
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					acquire(lock);
+	 */
+	return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)	(0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -90,6 +131,17 @@
 	lock->owner = (struct task_struct *)
 			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	lock->owner = NULL;
+	raw_spin_unlock(&lock->wait_lock);
+	return true;
+}
 #endif
 
 static inline int
@@ -260,27 +312,36 @@
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
  *
- * @task: the task owning the mutex (owner) for which a chain walk is probably
- *	  needed
+ * @task:	the task owning the mutex (owner) for which a chain walk is
+ *		probably needed
  * @deadlock_detect: do we have to carry out deadlock detection?
- * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck
- * 	       things for a task that has just got its priority adjusted, and
- *	       is waiting on a mutex)
+ * @orig_lock:	the mutex (can be NULL if we are walking the chain to recheck
+ *		things for a task that has just got its priority adjusted, and
+ *		is waiting on a mutex)
+ * @next_lock:	the mutex on which the owner of @orig_lock was blocked before
+ *		we dropped its pi_lock. Is never dereferenced, only used for
+ *		comparison to detect lock chain changes.
  * @orig_waiter: rt_mutex_waiter struct for the task that has just donated
- *		 its priority to the mutex owner (can be NULL in the case
- *		 depicted above or if the top waiter is gone away and we are
- *		 actually deboosting the owner)
- * @top_task: the current top waiter
+ *		its priority to the mutex owner (can be NULL in the case
+ *		depicted above or if the top waiter is gone away and we are
+ *		actually deboosting the owner)
+ * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      int deadlock_detect,
 				      struct rt_mutex *orig_lock,
+				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
@@ -314,7 +375,7 @@
 		}
 		put_task_struct(task);
 
-		return deadlock_detect ? -EDEADLK : 0;
+		return -EDEADLK;
 	}
  retry:
 	/*
@@ -339,6 +400,18 @@
 		goto out_unlock_pi;
 
 	/*
+	 * We dropped all locks after taking a refcount on @task, so
+	 * the task might have moved on in the lock chain or even left
+	 * the chain completely and blocks now on an unrelated lock or
+	 * on @orig_lock.
+	 *
+	 * We stored the lock on which @task was blocked in @next_lock,
+	 * so we can detect the chain change.
+	 */
+	if (next_lock != waiter->lock)
+		goto out_unlock_pi;
+
+	/*
 	 * Drop out, when the task has no waiters. Note,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
@@ -377,7 +450,7 @@
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
 		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
+		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
@@ -422,11 +495,26 @@
 		__rt_mutex_adjust_prio(task);
 	}
 
+	/*
+	 * Check whether the task which owns the current lock is pi
+	 * blocked itself. If yes we store a pointer to the lock for
+	 * the lock chain change detection above. After we dropped
+	 * task->pi_lock next_lock cannot be dereferenced anymore.
+	 */
+	next_lock = task_blocked_on_lock(task);
+
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 
+	/*
+	 * We reached the end of the lock chain. Stop right here. No
+	 * point to go back just to figure that out.
+	 */
+	if (!next_lock)
+		goto out_put_task;
+
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -536,8 +624,9 @@
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
+	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
+	unsigned long flags;
 
 	/*
 	 * Early deadlock detection. We really don't want the task to
@@ -548,7 +637,7 @@
 	 * which is wrong, as the other waiter is not in a deadlock
 	 * situation.
 	 */
-	if (detect_deadlock && owner == task)
+	if (owner == task)
 		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -569,20 +658,28 @@
 	if (!owner)
 		return 0;
 
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
 		chain_walk = 1;
+	}
 
-	if (!chain_walk)
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
+
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
 		return 0;
 
 	/*
@@ -594,8 +691,8 @@
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 task);
+	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -605,7 +702,8 @@
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
  *
  * Called with lock->wait_lock held.
  */
@@ -626,10 +724,23 @@
 	 */
 	rt_mutex_dequeue_pi(current, waiter);
 
-	rt_mutex_set_owner(lock, NULL);
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
+	/*
+	 * It's safe to dereference waiter as it cannot go away as
+	 * long as we hold lock->wait_lock. The waiter task needs to
+	 * acquire it in order to dequeue the waiter.
+	 */
 	wake_up_process(waiter->task);
 }
 
@@ -644,8 +755,8 @@
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
-	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	rt_mutex_dequeue(lock, waiter);
@@ -669,13 +780,13 @@
 		}
 		__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
+		/* Store the lock on which owner is blocked or NULL */
+		next_lock = task_blocked_on_lock(owner);
 
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
-	if (!chain_walk)
+	if (!next_lock)
 		return;
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -683,7 +794,7 @@
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -696,6 +807,7 @@
 void rt_mutex_adjust_pi(struct task_struct *task)
 {
 	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -706,12 +818,13 @@
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-
+	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
 }
 
 /**
@@ -763,6 +876,26 @@
 	return ret;
 }
 
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+				     struct rt_mutex_waiter *w)
+{
+	/*
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
 /*
  * Slow path lock function:
  */
@@ -802,8 +935,10 @@
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -859,12 +994,49 @@
 
 	rt_mutex_deadlock_account_unlock(current);
 
-	if (!rt_mutex_has_waiters(lock)) {
-		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
-		return;
+	/*
+	 * We must be careful here if the fast path is enabled. If we
+	 * have no waiters queued we cannot set owner to NULL here
+	 * because of:
+	 *
+	 * foo->lock->owner = NULL;
+	 *			rtmutex_lock(foo->lock);   <- fast path
+	 *			free = atomic_dec_and_test(foo->refcnt);
+	 *			rtmutex_unlock(foo->lock); <- fast path
+	 *			if (free)
+	 *				kfree(foo);
+	 * raw_spin_unlock(foo->lock->wait_lock);
+	 *
+	 * So for the fastpath enabled kernel:
+	 *
+	 * Nothing can set the waiters bit as long as we hold
+	 * lock->wait_lock. So we do the following sequence:
+	 *
+	 *	owner = rt_mutex_owner(lock);
+	 *	clear_rt_mutex_waiters(lock);
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
+	 *		return;
+	 *	goto retry;
+	 *
+	 * The fastpath disabled variant is simple as all access to
+	 * lock->owner is serialized by lock->wait_lock:
+	 *
+	 *	lock->owner = NULL;
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 */
+	while (!rt_mutex_has_waiters(lock)) {
+		/* Drops lock->wait_lock ! */
+		if (unlock_rt_mutex_safe(lock) == true)
+			return;
+		/* Relock the rtmutex and try again */
+		raw_spin_lock(&lock->wait_lock);
 	}
 
+	/*
+	 * The wakeup next waiter path does not suffer from the above
+	 * race. See the comments there.
+	 */
 	wakeup_next_waiter(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
@@ -1112,7 +1284,8 @@
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index a1a1dd0..f6a1f3c 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -24,3 +24,8 @@
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
 #define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	WARN(1, "rtmutex deadlock detected\n");
+}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 49e0a20..fcc2611 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -35,6 +35,7 @@
 
 static int nocompress;
 static int noresume;
+static int nohibernate;
 static int resume_wait;
 static unsigned int resume_delay;
 static char resume_file[256] = CONFIG_PM_STD_PARTITION;
@@ -62,6 +63,11 @@
 
 static const struct platform_hibernation_ops *hibernation_ops;
 
+bool hibernation_available(void)
+{
+	return (nohibernate == 0);
+}
+
 /**
  * hibernation_set_ops - Set the global hibernate operations.
  * @ops: Hibernation operations to use in subsequent hibernation transitions.
@@ -642,6 +648,11 @@
 {
 	int error;
 
+	if (!hibernation_available()) {
+		pr_debug("PM: Hibernation not available.\n");
+		return -EPERM;
+	}
+
 	lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
@@ -734,7 +745,7 @@
 	/*
 	 * If the user said "noresume".. bail out early.
 	 */
-	if (noresume)
+	if (noresume || !hibernation_available())
 		return 0;
 
 	/*
@@ -900,6 +911,9 @@
 	int i;
 	char *start = buf;
 
+	if (!hibernation_available())
+		return sprintf(buf, "[disabled]\n");
+
 	for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
 		if (!hibernation_modes[i])
 			continue;
@@ -934,6 +948,9 @@
 	char *p;
 	int mode = HIBERNATION_INVALID;
 
+	if (!hibernation_available())
+		return -EPERM;
+
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
@@ -1101,6 +1118,10 @@
 		noresume = 1;
 	else if (!strncmp(str, "nocompress", 10))
 		nocompress = 1;
+	else if (!strncmp(str, "no", 2)) {
+		noresume = 1;
+		nohibernate = 1;
+	}
 	return 1;
 }
 
@@ -1125,9 +1146,23 @@
 	return 1;
 }
 
+static int __init nohibernate_setup(char *str)
+{
+	noresume = 1;
+	nohibernate = 1;
+	return 1;
+}
+
+static int __init kaslr_nohibernate_setup(char *str)
+{
+	return nohibernate_setup(str);
+}
+
 __setup("noresume", noresume_setup);
 __setup("resume_offset=", resume_offset_setup);
 __setup("resume=", resume_setup);
 __setup("hibernate=", hibernate_setup);
 __setup("resumewait", resumewait_setup);
 __setup("resumedelay=", resumedelay_setup);
+__setup("nohibernate", nohibernate_setup);
+__setup("kaslr", kaslr_nohibernate_setup);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 573410d..8e90f33 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -300,13 +300,11 @@
 			s += sprintf(s,"%s ", pm_states[i].label);
 
 #endif
-#ifdef CONFIG_HIBERNATION
-	s += sprintf(s, "%s\n", "disk");
-#else
+	if (hibernation_available())
+		s += sprintf(s, "disk ");
 	if (s != buf)
 		/* convert the last space to a newline */
 		*(s-1) = '\n';
-#endif
 	return (s - buf);
 }
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 98d35758..526e891 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -49,6 +49,9 @@
 	struct snapshot_data *data;
 	int error;
 
+	if (!hibernation_available())
+		return -EPERM;
+
 	lock_system_sleep();
 
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ba9ed45..7de6555 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -152,10 +152,6 @@
 #ifdef CONFIG_SPARC
 #endif
 
-#ifdef CONFIG_SPARC64
-extern int sysctl_tsb_ratio;
-#endif
-
 #ifdef __hppa__
 extern int pwrsw_enabled;
 #endif
diff --git a/mm/page_io.c b/mm/page_io.c
index 243a9b7..955db8b 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -274,8 +274,8 @@
 			.count = PAGE_SIZE,
 			.iov_offset = 0,
 			.nr_segs = 1,
-			.bvec = &bv
 		};
+		from.bvec = &bv;	/* older gcc versions are broken */
 
 		init_sync_kiocb(&kiocb, swap_file);
 		kiocb.ki_pos = page_file_offset(page);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 67d7721..1675021 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -72,6 +72,8 @@
 	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
 	case CEPH_MSG_STATFS: return "statfs";
 	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
+	case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
 	case CEPH_MSG_MDS_MAP: return "mds_map";
 	case CEPH_MSG_CLIENT_SESSION: return "client_session";
 	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 10421a4..d1a62c6 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -126,9 +126,13 @@
 		req = rb_entry(rp, struct ceph_mon_generic_request, node);
 		op = le16_to_cpu(req->request->hdr.type);
 		if (op == CEPH_MSG_STATFS)
-			seq_printf(s, "%lld statfs\n", req->tid);
+			seq_printf(s, "%llu statfs\n", req->tid);
+		else if (op == CEPH_MSG_POOLOP)
+			seq_printf(s, "%llu poolop\n", req->tid);
+		else if (op == CEPH_MSG_MON_GET_VERSION)
+			seq_printf(s, "%llu mon_get_version", req->tid);
 		else
-			seq_printf(s, "%lld unknown\n", req->tid);
+			seq_printf(s, "%llu unknown\n", req->tid);
 	}
 
 	mutex_unlock(&monc->mutex);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 2ac9ef3..067d3af 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -296,6 +296,33 @@
 		__send_subscribe(monc);
 	mutex_unlock(&monc->mutex);
 }
+EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
+
+int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+			  unsigned long timeout)
+{
+	unsigned long started = jiffies;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	while (monc->have_osdmap < epoch) {
+		mutex_unlock(&monc->mutex);
+
+		if (timeout != 0 && time_after_eq(jiffies, started + timeout))
+			return -ETIMEDOUT;
+
+		ret = wait_event_interruptible_timeout(monc->client->auth_wq,
+					 monc->have_osdmap >= epoch, timeout);
+		if (ret < 0)
+			return ret;
+
+		mutex_lock(&monc->mutex);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_monc_wait_osdmap);
 
 /*
  *
@@ -477,14 +504,13 @@
 	return m;
 }
 
-static int do_generic_request(struct ceph_mon_client *monc,
-			      struct ceph_mon_generic_request *req)
+static int __do_generic_request(struct ceph_mon_client *monc, u64 tid,
+				struct ceph_mon_generic_request *req)
 {
 	int err;
 
 	/* register request */
-	mutex_lock(&monc->mutex);
-	req->tid = ++monc->last_tid;
+	req->tid = tid != 0 ? tid : ++monc->last_tid;
 	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
@@ -496,13 +522,24 @@
 	mutex_lock(&monc->mutex);
 	rb_erase(&req->node, &monc->generic_request_tree);
 	monc->num_generic_requests--;
-	mutex_unlock(&monc->mutex);
 
 	if (!err)
 		err = req->result;
 	return err;
 }
 
+static int do_generic_request(struct ceph_mon_client *monc,
+			      struct ceph_mon_generic_request *req)
+{
+	int err;
+
+	mutex_lock(&monc->mutex);
+	err = __do_generic_request(monc, 0, req);
+	mutex_unlock(&monc->mutex);
+
+	return err;
+}
+
 /*
  * statfs
  */
@@ -579,6 +616,96 @@
 }
 EXPORT_SYMBOL(ceph_monc_do_statfs);
 
+static void handle_get_version_reply(struct ceph_mon_client *monc,
+				     struct ceph_msg *msg)
+{
+	struct ceph_mon_generic_request *req;
+	u64 tid = le64_to_cpu(msg->hdr.tid);
+	void *p = msg->front.iov_base;
+	void *end = p + msg->front_alloc_len;
+	u64 handle;
+
+	dout("%s %p tid %llu\n", __func__, msg, tid);
+
+	ceph_decode_need(&p, end, 2*sizeof(u64), bad);
+	handle = ceph_decode_64(&p);
+	if (tid != 0 && tid != handle)
+		goto bad;
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, handle);
+	if (req) {
+		*(u64 *)req->buf = ceph_decode_64(&p);
+		req->result = 0;
+		get_generic_request(req);
+	}
+	mutex_unlock(&monc->mutex);
+	if (req) {
+		complete_all(&req->completion);
+		put_generic_request(req);
+	}
+
+	return;
+bad:
+	pr_err("corrupt mon_get_version reply\n");
+	ceph_msg_dump(msg);
+}
+
+/*
+ * Send MMonGetVersion and wait for the reply.
+ *
+ * @what: one of "mdsmap", "osdmap" or "monmap"
+ */
+int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
+			     u64 *newest)
+{
+	struct ceph_mon_generic_request *req;
+	void *p, *end;
+	u64 tid;
+	int err;
+
+	req = kzalloc(sizeof(*req), GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	kref_init(&req->kref);
+	req->buf = newest;
+	req->buf_len = sizeof(*newest);
+	init_completion(&req->completion);
+
+	req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
+				    sizeof(u64) + sizeof(u32) + strlen(what),
+				    GFP_NOFS, true);
+	if (!req->request) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 1024,
+				  GFP_NOFS, true);
+	if (!req->reply) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	p = req->request->front.iov_base;
+	end = p + req->request->front_alloc_len;
+
+	/* fill out request */
+	mutex_lock(&monc->mutex);
+	tid = ++monc->last_tid;
+	ceph_encode_64(&p, tid); /* handle */
+	ceph_encode_string(&p, end, what, strlen(what));
+
+	err = __do_generic_request(monc, tid, req);
+
+	mutex_unlock(&monc->mutex);
+out:
+	kref_put(&req->kref, release_generic_request);
+	return err;
+}
+EXPORT_SYMBOL(ceph_monc_do_get_version);
+
 /*
  * pool ops
  */
@@ -981,6 +1108,10 @@
 		handle_statfs_reply(monc, msg);
 		break;
 
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		handle_get_version_reply(monc, msg);
+		break;
+
 	case CEPH_MSG_POOLOP_REPLY:
 		handle_poolop_reply(monc, msg);
 		break;
@@ -1029,6 +1160,15 @@
 	case CEPH_MSG_AUTH_REPLY:
 		m = ceph_msg_get(monc->m_auth_reply);
 		break;
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		if (le64_to_cpu(hdr->tid) != 0)
+			return get_generic_reply(con, hdr, skip);
+
+		/*
+		 * Older OSDs don't set reply tid even if the orignal
+		 * request had a non-zero tid.  Workaround this weirdness
+		 * by falling through to the allocate case.
+		 */
 	case CEPH_MSG_MON_MAP:
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 6b1c04c..488dd1a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -739,22 +739,38 @@
 	__sum16 sum;
 
 	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
-	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !sum &&
-	    !skb->csum_complete_sw)
-		netdev_rx_csum_fault(skb->dev);
-
-	/* Save checksum complete for later use */
-	skb->csum = sum;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum_complete_sw = 1;
-
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+	skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
 
 __sum16 __skb_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, skb->len);
+	__wsum csum;
+	__sum16 sum;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+
+	/* skb->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(skb->csum, csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	/* Save full packet checksum */
+	skb->csum = csum;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb->csum_complete_sw = 1;
+	skb->csum_valid = !sum;
+
+	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bf92824..9cd5344 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -689,6 +689,9 @@
 	new->ooo_okay		= old->ooo_okay;
 	new->no_fcs		= old->no_fcs;
 	new->encapsulation	= old->encapsulation;
+	new->encap_hdr_csum	= old->encap_hdr_csum;
+	new->csum_valid		= old->csum_valid;
+	new->csum_complete_sw	= old->csum_complete_sw;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 185ed3e..d92f94b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1861,6 +1861,10 @@
 	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
 	rcu_read_lock();
 begin:
 	count = 0;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7e5eb75..dcb1959 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -34,6 +34,8 @@
  *    Sridhar Samudrala     <sri@us.ibm.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <linux/sysctl.h>
@@ -46,6 +48,11 @@
 static int sack_timer_max = 500;
 static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
 static int rwnd_scale_max = 16;
+static int rto_alpha_min = 0;
+static int rto_beta_min = 0;
+static int rto_alpha_max = 1000;
+static int rto_beta_max = 1000;
+
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
 	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
@@ -64,6 +71,9 @@
 static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos);
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos);
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp,
 			     loff_t *ppos);
@@ -126,15 +136,19 @@
 		.procname	= "rto_alpha_exp_divisor",
 		.data		= &init_net.sctp.rto_alpha,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_alpha_min,
+		.extra2		= &rto_alpha_max,
 	},
 	{
 		.procname	= "rto_beta_exp_divisor",
 		.data		= &init_net.sctp.rto_beta,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_beta_min,
+		.extra2		= &rto_beta_max,
 	},
 	{
 		.procname	= "max_burst",
@@ -403,6 +417,16 @@
 	return ret;
 }
 
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	pr_warn_once("Changing rto_alpha or rto_beta may lead to "
+		     "suboptimal rtt/srtt estimations!\n");
+
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp,
 			     loff_t *ppos)
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index b5f08f7..35d5a58 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -289,14 +289,16 @@
 
 fi
 
-# Build header package
-(cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl > "$objtree/debian/hdrsrcfiles")
-(cd $srctree; find arch/$SRCARCH/include include scripts -type f >> "$objtree/debian/hdrsrcfiles")
-(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f >> "$objtree/debian/hdrobjfiles")
+# Build kernel header package
+(cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles"
+(cd $srctree; find arch/$SRCARCH/include include scripts -type f) >> "$objtree/debian/hdrsrcfiles"
+(cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles"
+(cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles"
+(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f) >> "$objtree/debian/hdrobjfiles"
 destdir=$kernel_headers_dir/usr/src/linux-headers-$version
 mkdir -p "$destdir"
-(cd $srctree; tar -c -f - -T "$objtree/debian/hdrsrcfiles") | (cd $destdir; tar -xf -)
-(cd $objtree; tar -c -f - -T "$objtree/debian/hdrobjfiles") | (cd $destdir; tar -xf -)
+(cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -)
+(cd $objtree; tar -c -f - -T -) < "$objtree/debian/hdrobjfiles" | (cd $destdir; tar -xf -)
 (cd $objtree; cp $KCONFIG_CONFIG $destdir/.config) # copy .config manually to be where it's expected to be
 ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build"
 rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles"
diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index 995c1ea..e046bff 100644
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -125,12 +125,11 @@
 # Create the tarball
 #
 (
-	cd "${tmpdir}"
 	opts=
 	if tar --owner=root --group=root --help >/dev/null 2>&1; then
 		opts="--owner=root --group=root"
 	fi
-	tar cf - boot/* lib/* $opts | ${compress} > "${tarball}${file_ext}"
+	tar cf - -C "$tmpdir" boot/ lib/ $opts | ${compress} > "${tarball}${file_ext}"
 )
 
 echo "Tarball successfully created in ${tarball}${file_ext}"
diff --git a/security/integrity/evm/Kconfig b/security/integrity/evm/Kconfig
index d35b491..d606f3d 100644
--- a/security/integrity/evm/Kconfig
+++ b/security/integrity/evm/Kconfig
@@ -12,15 +12,41 @@
 
 	  If you are unsure how to answer this question, answer N.
 
-config EVM_HMAC_VERSION
-	int "EVM HMAC version"
-	depends on EVM
-	default 2
-	help
-	  This options adds EVM HMAC version support.
-	  1 - original version
-	  2 - add per filesystem unique identifier (UUID) (default)
+if EVM
 
-	  WARNING: changing the HMAC calculation method or adding 
+menu "EVM options"
+
+config EVM_ATTR_FSUUID
+	bool "FSUUID (version 2)"
+	default y
+	depends on EVM
+	help
+	  Include filesystem UUID for HMAC calculation.
+
+	  Default value is 'selected', which is former version 2.
+	  if 'not selected', it is former version 1
+
+	  WARNING: changing the HMAC calculation method or adding
 	  additional info to the calculation, requires existing EVM
-	  labeled file systems to be relabeled.  
+	  labeled file systems to be relabeled.
+
+config EVM_EXTRA_SMACK_XATTRS
+	bool "Additional SMACK xattrs"
+	depends on EVM && SECURITY_SMACK
+	default n
+	help
+	  Include additional SMACK xattrs for HMAC calculation.
+
+	  In addition to the original security xattrs (eg. security.selinux,
+	  security.SMACK64, security.capability, and security.ima) included
+	  in the HMAC calculation, enabling this option includes newly defined
+	  Smack xattrs: security.SMACK64EXEC, security.SMACK64TRANSMUTE and
+	  security.SMACK64MMAP.
+
+	  WARNING: changing the HMAC calculation method or adding
+	  additional info to the calculation, requires existing EVM
+	  labeled file systems to be relabeled.
+
+endmenu
+
+endif
diff --git a/security/integrity/evm/evm.h b/security/integrity/evm/evm.h
index 37c88dd..88bfe77 100644
--- a/security/integrity/evm/evm.h
+++ b/security/integrity/evm/evm.h
@@ -24,7 +24,10 @@
 extern int evm_initialized;
 extern char *evm_hmac;
 extern char *evm_hash;
-extern int evm_hmac_version;
+
+#define EVM_ATTR_FSUUID		0x0001
+
+extern int evm_hmac_attrs;
 
 extern struct crypto_shash *hmac_tfm;
 extern struct crypto_shash *hash_tfm;
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 6b540f1..5e9687f 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -112,7 +112,7 @@
 	hmac_misc.gid = from_kgid(&init_user_ns, inode->i_gid);
 	hmac_misc.mode = inode->i_mode;
 	crypto_shash_update(desc, (const u8 *)&hmac_misc, sizeof(hmac_misc));
-	if (evm_hmac_version > 1)
+	if (evm_hmac_attrs & EVM_ATTR_FSUUID)
 		crypto_shash_update(desc, inode->i_sb->s_uuid,
 				    sizeof(inode->i_sb->s_uuid));
 	crypto_shash_final(desc, digest);
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 6e0bd93..3bcb80d 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -32,7 +32,7 @@
 };
 char *evm_hmac = "hmac(sha1)";
 char *evm_hash = "sha1";
-int evm_hmac_version = CONFIG_EVM_HMAC_VERSION;
+int evm_hmac_attrs;
 
 char *evm_config_xattrnames[] = {
 #ifdef CONFIG_SECURITY_SELINUX
@@ -40,6 +40,11 @@
 #endif
 #ifdef CONFIG_SECURITY_SMACK
 	XATTR_NAME_SMACK,
+#ifdef CONFIG_EVM_EXTRA_SMACK_XATTRS
+	XATTR_NAME_SMACKEXEC,
+	XATTR_NAME_SMACKTRANSMUTE,
+	XATTR_NAME_SMACKMMAP,
+#endif
 #endif
 #ifdef CONFIG_IMA_APPRAISE
 	XATTR_NAME_IMA,
@@ -57,6 +62,14 @@
 }
 __setup("evm=", evm_set_fixmode);
 
+static void __init evm_init_config(void)
+{
+#ifdef CONFIG_EVM_ATTR_FSUUID
+	evm_hmac_attrs |= EVM_ATTR_FSUUID;
+#endif
+	pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs);
+}
+
 static int evm_find_protected_xattrs(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
@@ -287,12 +300,20 @@
  * @xattr_value: pointer to the new extended attribute value
  * @xattr_value_len: pointer to the new extended attribute value length
  *
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
  */
 int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0)
+	    && (xattr_data->type == EVM_XATTR_HMAC))
+		return -EPERM;
 	return evm_protect_xattr(dentry, xattr_name, xattr_value,
 				 xattr_value_len);
 }
@@ -432,6 +453,8 @@
 {
 	int error;
 
+	evm_init_config();
+
 	error = evm_init_secfs();
 	if (error < 0) {
 		pr_info("Error registering secfs\n");
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 291bf0f..d3113d4 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -341,7 +341,7 @@
 	return 0;
 }
 
-static void ima_reset_appraise_flags(struct inode *inode)
+static void ima_reset_appraise_flags(struct inode *inode, int digsig)
 {
 	struct integrity_iint_cache *iint;
 
@@ -353,18 +353,22 @@
 		return;
 
 	iint->flags &= ~IMA_DONE_MASK;
+	if (digsig)
+		iint->flags |= IMA_DIGSIG;
 	return;
 }
 
 int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xvalue = xattr_value;
 	int result;
 
 	result = ima_protect_xattr(dentry, xattr_name, xattr_value,
 				   xattr_value_len);
 	if (result == 1) {
-		ima_reset_appraise_flags(dentry->d_inode);
+		ima_reset_appraise_flags(dentry->d_inode,
+			 (xvalue->type == EVM_IMA_XATTR_DIGSIG) ? 1 : 0);
 		result = 0;
 	}
 	return result;
@@ -376,7 +380,7 @@
 
 	result = ima_protect_xattr(dentry, xattr_name, NULL, 0);
 	if (result == 1) {
-		ima_reset_appraise_flags(dentry->d_inode);
+		ima_reset_appraise_flags(dentry->d_inode, 0);
 		result = 0;
 	}
 	return result;
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 1bde8e6..ccd0ac8 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -27,6 +27,36 @@
 
 static struct crypto_shash *ima_shash_tfm;
 
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+			   char *addr, unsigned long count)
+{
+	mm_segment_t old_fs;
+	char __user *buf = addr;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!file->f_op->read && !file->f_op->aio_read)
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, &offset);
+	else
+		ret = do_sync_read(file, buf, count, &offset);
+	set_fs(old_fs);
+	return ret;
+}
+
 int ima_init_crypto(void)
 {
 	long rc;
@@ -104,7 +134,7 @@
 	while (offset < i_size) {
 		int rbuf_len;
 
-		rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE);
+		rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
 		if (rbuf_len < 0) {
 			rc = rbuf_len;
 			break;
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index dcc98cf..09baa33 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -81,7 +81,6 @@
 {
 	struct inode *inode = file_inode(file);
 	fmode_t mode = file->f_mode;
-	int must_measure;
 	bool send_tomtou = false, send_writers = false;
 	char *pathbuf = NULL;
 	const char *pathname;
@@ -92,18 +91,19 @@
 	mutex_lock(&inode->i_mutex);	/* file metadata: permissions, xattr */
 
 	if (mode & FMODE_WRITE) {
-		if (atomic_read(&inode->i_readcount) && IS_IMA(inode))
-			send_tomtou = true;
-		goto out;
+		if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) {
+			struct integrity_iint_cache *iint;
+			iint = integrity_iint_find(inode);
+			/* IMA_MEASURE is set from reader side */
+			if (iint && (iint->flags & IMA_MEASURE))
+				send_tomtou = true;
+		}
+	} else {
+		if ((atomic_read(&inode->i_writecount) > 0) &&
+		    ima_must_measure(inode, MAY_READ, FILE_CHECK))
+			send_writers = true;
 	}
 
-	must_measure = ima_must_measure(inode, MAY_READ, FILE_CHECK);
-	if (!must_measure)
-		goto out;
-
-	if (atomic_read(&inode->i_writecount) > 0)
-		send_writers = true;
-out:
 	mutex_unlock(&inode->i_mutex);
 
 	if (!send_tomtou && !send_writers)
diff --git a/sound/core/control.c b/sound/core/control.c
index f038f5a..f0b0e14 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -288,6 +288,10 @@
 {
 	struct snd_kcontrol *kctl;
 
+	/* Make sure that the ids assigned to the control do not wrap around */
+	if (card->last_numid >= UINT_MAX - count)
+		card->last_numid = 0;
+
 	list_for_each_entry(kctl, &card->controls, list) {
 		if (kctl->id.numid < card->last_numid + 1 + count &&
 		    kctl->id.numid + kctl->count > card->last_numid + 1) {
@@ -330,6 +334,7 @@
 {
 	struct snd_ctl_elem_id id;
 	unsigned int idx;
+	unsigned int count;
 	int err = -EINVAL;
 
 	if (! kcontrol)
@@ -337,6 +342,9 @@
 	if (snd_BUG_ON(!card || !kcontrol->info))
 		goto error;
 	id = kcontrol->id;
+	if (id.index > UINT_MAX - kcontrol->count)
+		goto error;
+
 	down_write(&card->controls_rwsem);
 	if (snd_ctl_find_id(card, &id)) {
 		up_write(&card->controls_rwsem);
@@ -358,8 +366,9 @@
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -388,6 +397,7 @@
 		    bool add_on_replace)
 {
 	struct snd_ctl_elem_id id;
+	unsigned int count;
 	unsigned int idx;
 	struct snd_kcontrol *old;
 	int ret;
@@ -423,8 +433,9 @@
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -897,9 +908,9 @@
 			result = kctl->put(kctl, control);
 		}
 		if (result > 0) {
+			struct snd_ctl_elem_id id = control->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
-				       &control->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
 			return 0;
 		}
 	}
@@ -991,6 +1002,7 @@
 
 struct user_element {
 	struct snd_ctl_elem_info info;
+	struct snd_card *card;
 	void *elem_data;		/* element data */
 	unsigned long elem_data_size;	/* size of element data in bytes */
 	void *tlv_data;			/* TLV data */
@@ -1034,7 +1046,9 @@
 {
 	struct user_element *ue = kcontrol->private_data;
 
+	mutex_lock(&ue->card->user_ctl_lock);
 	memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return 0;
 }
 
@@ -1043,10 +1057,12 @@
 {
 	int change;
 	struct user_element *ue = kcontrol->private_data;
-	
+
+	mutex_lock(&ue->card->user_ctl_lock);
 	change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0;
 	if (change)
 		memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return change;
 }
 
@@ -1066,19 +1082,32 @@
 		new_data = memdup_user(tlv, size);
 		if (IS_ERR(new_data))
 			return PTR_ERR(new_data);
+		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
 			change = memcmp(ue->tlv_data, new_data, size);
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;
+		mutex_unlock(&ue->card->user_ctl_lock);
 	} else {
-		if (! ue->tlv_data_size || ! ue->tlv_data)
-			return -ENXIO;
-		if (size < ue->tlv_data_size)
-			return -ENOSPC;
+		int ret = 0;
+
+		mutex_lock(&ue->card->user_ctl_lock);
+		if (!ue->tlv_data_size || !ue->tlv_data) {
+			ret = -ENXIO;
+			goto err_unlock;
+		}
+		if (size < ue->tlv_data_size) {
+			ret = -ENOSPC;
+			goto err_unlock;
+		}
 		if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size))
-			return -EFAULT;
+			ret = -EFAULT;
+err_unlock:
+		mutex_unlock(&ue->card->user_ctl_lock);
+		if (ret)
+			return ret;
 	}
 	return change;
 }
@@ -1136,8 +1165,6 @@
 	struct user_element *ue;
 	int idx, err;
 
-	if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS)
-		return -ENOMEM;
 	if (info->count < 1)
 		return -EINVAL;
 	access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
@@ -1146,21 +1173,16 @@
 				 SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE));
 	info->id.numid = 0;
 	memset(&kctl, 0, sizeof(kctl));
-	down_write(&card->controls_rwsem);
-	_kctl = snd_ctl_find_id(card, &info->id);
-	err = 0;
-	if (_kctl) {
-		if (replace)
-			err = snd_ctl_remove(card, _kctl);
-		else
-			err = -EBUSY;
-	} else {
-		if (replace)
-			err = -ENOENT;
+
+	if (replace) {
+		err = snd_ctl_remove_user_ctl(file, &info->id);
+		if (err)
+			return err;
 	}
-	up_write(&card->controls_rwsem);
-	if (err < 0)
-		return err;
+
+	if (card->user_ctl_count >= MAX_USER_CONTROLS)
+		return -ENOMEM;
+
 	memcpy(&kctl.id, &info->id, sizeof(info->id));
 	kctl.count = info->owner ? info->owner : 1;
 	access |= SNDRV_CTL_ELEM_ACCESS_USER;
@@ -1210,6 +1232,7 @@
 	ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL);
 	if (ue == NULL)
 		return -ENOMEM;
+	ue->card = card;
 	ue->info = *info;
 	ue->info.access = 0;
 	ue->elem_data = (char *)ue + sizeof(*ue);
@@ -1321,8 +1344,9 @@
 		}
 		err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv);
 		if (err > 0) {
+			struct snd_ctl_elem_id id = kctl->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id);
 			return 0;
 		}
 	} else {
diff --git a/sound/core/init.c b/sound/core/init.c
index 5ee8384..7bdfd19 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -232,6 +232,7 @@
 	INIT_LIST_HEAD(&card->devices);
 	init_rwsem(&card->controls_rwsem);
 	rwlock_init(&card->ctl_files_rwlock);
+	mutex_init(&card->user_ctl_lock);
 	INIT_LIST_HEAD(&card->controls);
 	INIT_LIST_HEAD(&card->ctl_files);
 	spin_lock_init(&card->files_lock);
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 9ca5e64..225c7315 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -660,7 +660,7 @@
 				  int atomic, int hop)
 {
 	struct snd_seq_subscribers *subs;
-	int err = 0, num_ev = 0;
+	int err, result = 0, num_ev = 0;
 	struct snd_seq_event event_saved;
 	struct snd_seq_client_port *src_port;
 	struct snd_seq_port_subs_info *grp;
@@ -685,8 +685,12 @@
 						  subs->info.flags & SNDRV_SEQ_PORT_SUBS_TIME_REAL);
 		err = snd_seq_deliver_single_event(client, event,
 						   0, atomic, hop);
-		if (err < 0)
-			break;
+		if (err < 0) {
+			/* save first error that occurs and continue */
+			if (!result)
+				result = err;
+			continue;
+		}
 		num_ev++;
 		/* restore original event record */
 		*event = event_saved;
@@ -697,7 +701,7 @@
 		up_read(&grp->list_mutex);
 	*event = event_saved; /* restore */
 	snd_seq_port_unlock(src_port);
-	return (err < 0) ? err : num_ev;
+	return (result < 0) ? result : num_ev;
 }
 
 
@@ -709,7 +713,7 @@
 				struct snd_seq_event *event,
 				int atomic, int hop)
 {
-	int num_ev = 0, err = 0;
+	int num_ev = 0, err, result = 0;
 	struct snd_seq_client *dest_client;
 	struct snd_seq_client_port *port;
 
@@ -724,14 +728,18 @@
 		err = snd_seq_deliver_single_event(NULL, event,
 						   SNDRV_SEQ_FILTER_BROADCAST,
 						   atomic, hop);
-		if (err < 0)
-			break;
+		if (err < 0) {
+			/* save first error that occurs and continue */
+			if (!result)
+				result = err;
+			continue;
+		}
 		num_ev++;
 	}
 	read_unlock(&dest_client->ports_lock);
 	snd_seq_client_unlock(dest_client);
 	event->dest.port = SNDRV_SEQ_ADDRESS_BROADCAST; /* restore */
-	return (err < 0) ? err : num_ev;
+	return (result < 0) ? result : num_ev;
 }
 
 /*
@@ -741,7 +749,7 @@
 static int broadcast_event(struct snd_seq_client *client,
 			   struct snd_seq_event *event, int atomic, int hop)
 {
-	int err = 0, num_ev = 0;
+	int err, result = 0, num_ev = 0;
 	int dest;
 	struct snd_seq_addr addr;
 
@@ -760,12 +768,16 @@
 			err = snd_seq_deliver_single_event(NULL, event,
 							   SNDRV_SEQ_FILTER_BROADCAST,
 							   atomic, hop);
-		if (err < 0)
-			break;
+		if (err < 0) {
+			/* save first error that occurs and continue */
+			if (!result)
+				result = err;
+			continue;
+		}
 		num_ev += err;
 	}
 	event->dest = addr; /* restore */
-	return (err < 0) ? err : num_ev;
+	return (result < 0) ? result : num_ev;
 }
 
 
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 5599899..53a403e 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -124,7 +124,7 @@
 	snd_use_lock_use(&f->use_lock);
 	err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL); /* always non-blocking */
 	if (err < 0) {
-		if (err == -ENOMEM)
+		if ((err == -ENOMEM) || (err == -EAGAIN))
 			atomic_inc(&f->overflow);
 		snd_use_lock_free(&f->use_lock);
 		return err;
diff --git a/sound/core/timer.c b/sound/core/timer.c
index cfd455a..777a45e 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -390,7 +390,7 @@
 	struct timespec tstamp;
 
 	if (timer_tstamp_monotonic)
-		do_posix_clock_monotonic_gettime(&tstamp);
+		ktime_get_ts(&tstamp);
 	else
 		getnstimeofday(&tstamp);
 	if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START ||
@@ -1203,7 +1203,7 @@
 	}
 	if (tu->last_resolution != resolution || ticks > 0) {
 		if (timer_tstamp_monotonic)
-			do_posix_clock_monotonic_gettime(&tstamp);
+			ktime_get_ts(&tstamp);
 		else
 			getnstimeofday(&tstamp);
 	}
diff --git a/sound/firewire/bebob/bebob.h b/sound/firewire/bebob/bebob.h
index d1c93a1..e13eef9 100644
--- a/sound/firewire/bebob/bebob.h
+++ b/sound/firewire/bebob/bebob.h
@@ -208,8 +208,6 @@
 int snd_bebob_stream_check_internal_clock(struct snd_bebob *bebob,
 					  bool *internal);
 int snd_bebob_stream_discover(struct snd_bebob *bebob);
-int snd_bebob_stream_map(struct snd_bebob *bebob,
-			 struct amdtp_stream *stream);
 int snd_bebob_stream_init_duplex(struct snd_bebob *bebob);
 int snd_bebob_stream_start_duplex(struct snd_bebob *bebob, unsigned int rate);
 void snd_bebob_stream_stop_duplex(struct snd_bebob *bebob);
diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c
index bc4f827..ef4d0c9 100644
--- a/sound/firewire/bebob/bebob_stream.c
+++ b/sound/firewire/bebob/bebob_stream.c
@@ -655,8 +655,6 @@
 	struct amdtp_stream *master, *slave;
 	atomic_t *master_substreams, *slave_substreams;
 
-	mutex_lock(&bebob->mutex);
-
 	if (bebob->master == &bebob->rx_stream) {
 		slave  = &bebob->tx_stream;
 		master = &bebob->rx_stream;
@@ -669,6 +667,8 @@
 		master_substreams = &bebob->capture_substreams;
 	}
 
+	mutex_lock(&bebob->mutex);
+
 	if (atomic_read(slave_substreams) == 0) {
 		amdtp_stream_pcm_abort(slave);
 		amdtp_stream_stop(slave);
diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c
index 996fdc4..3e2ed8e 100644
--- a/sound/firewire/fireworks/fireworks.c
+++ b/sound/firewire/fireworks/fireworks.c
@@ -346,7 +346,6 @@
 {
 	snd_efw_transaction_unregister();
 	driver_unregister(&efw_driver.driver);
-	mutex_destroy(&devices_mutex);
 }
 
 module_init(snd_efw_init);
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index d2b36be..4f0201a 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -162,7 +162,6 @@
 	SND_EFW_CH_TYPE_GUITAR			= 7,
 	SND_EFW_CH_TYPE_PIEZO_GUITAR		= 8,
 	SND_EFW_CH_TYPE_GUITAR_STRING		= 9,
-	SND_EFW_CH_TYPE_VIRTUAL			= 0x10000,
 	SND_EFW_CH_TYPE_DUMMY
 };
 struct snd_efw_phys_meters {
diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c
index 4f8216f..33df865 100644
--- a/sound/firewire/fireworks/fireworks_hwdep.c
+++ b/sound/firewire/fireworks/fireworks_hwdep.c
@@ -58,7 +58,7 @@
 			efw->pull_ptr += till_end;
 			if (efw->pull_ptr >= efw->resp_buf +
 					     snd_efw_resp_buf_size)
-				efw->pull_ptr = efw->resp_buf;
+				efw->pull_ptr -= snd_efw_resp_buf_size;
 
 			length -= till_end;
 			buf += till_end;
diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c
index 5415690..b985fc5 100644
--- a/sound/firewire/fireworks/fireworks_stream.c
+++ b/sound/firewire/fireworks/fireworks_stream.c
@@ -284,8 +284,6 @@
 	struct amdtp_stream *master, *slave;
 	atomic_t *master_substreams, *slave_substreams;
 
-	mutex_lock(&efw->mutex);
-
 	if (efw->master == &efw->rx_stream) {
 		slave  = &efw->tx_stream;
 		master = &efw->rx_stream;
@@ -298,6 +296,8 @@
 		master_substreams = &efw->capture_substreams;
 	}
 
+	mutex_lock(&efw->mutex);
+
 	if (atomic_read(slave_substreams) == 0) {
 		stop_stream(efw, slave);
 
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index aa56b8a..255dabc 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -8,19 +8,19 @@
 
 /*
  * Fireworks have its own transaction. The transaction can be delivered by AV/C
- * Vendor Specific command. But at least Windows driver and firmware version 5.5
- * or later don't use it.
+ * Vendor Specific command frame or usual asynchronous transaction. At least,
+ * Windows driver and firmware version 5.5 or later don't use AV/C command.
  *
  * Transaction substance:
- *  At first, 6 data exist. Following to the 6 data, parameters for each
- *  commands exists. All of parameters are 32 bit alighed to big endian.
+ *  At first, 6 data exist. Following to the data, parameters for each command
+ *  exist. All of the parameters are 32 bit alighed to big endian.
  *   data[0]:	Length of transaction substance
  *   data[1]:	Transaction version
  *   data[2]:	Sequence number. This is incremented by the device
- *   data[3]:	transaction category
- *   data[4]:	transaction command
- *   data[5]:	return value in response.
- *   data[6-]:	parameters
+ *   data[3]:	Transaction category
+ *   data[4]:	Transaction command
+ *   data[5]:	Return value in response.
+ *   data[6-]:	Parameters
  *
  * Transaction address:
  *  command:	0xecc000000000
@@ -148,7 +148,7 @@
 
 		efw->push_ptr += till_end;
 		if (efw->push_ptr >= efw->resp_buf + snd_efw_resp_buf_size)
-			efw->push_ptr = efw->resp_buf;
+			efw->push_ptr -= snd_efw_resp_buf_size;
 
 		length -= till_end;
 		data += till_end;
diff --git a/sound/pci/hda/hda_i915.c b/sound/pci/hda/hda_i915.c
index 9d07e4ed..e9e8a4a 100644
--- a/sound/pci/hda/hda_i915.c
+++ b/sound/pci/hda/hda_i915.c
@@ -22,20 +22,20 @@
 #include <drm/i915_powerwell.h>
 #include "hda_i915.h"
 
-static void (*get_power)(void);
-static void (*put_power)(void);
+static int (*get_power)(void);
+static int (*put_power)(void);
 
-void hda_display_power(bool enable)
+int hda_display_power(bool enable)
 {
 	if (!get_power || !put_power)
-		return;
+		return -ENODEV;
 
 	pr_debug("HDA display power %s \n",
 			enable ? "Enable" : "Disable");
 	if (enable)
-		get_power();
+		return get_power();
 	else
-		put_power();
+		return put_power();
 }
 
 int hda_i915_init(void)
diff --git a/sound/pci/hda/hda_i915.h b/sound/pci/hda/hda_i915.h
index 5a63da2..bfd835f 100644
--- a/sound/pci/hda/hda_i915.h
+++ b/sound/pci/hda/hda_i915.h
@@ -17,11 +17,11 @@
 #define __SOUND_HDA_I915_H
 
 #ifdef CONFIG_SND_HDA_I915
-void hda_display_power(bool enable);
+int hda_display_power(bool enable);
 int hda_i915_init(void);
 int hda_i915_exit(void);
 #else
-static inline void hda_display_power(bool enable) {}
+static inline int hda_display_power(bool enable) { return 0; }
 static inline int hda_i915_init(void)
 {
 	return -ENODEV;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index cd77b9b..23fd6b9 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -237,6 +237,12 @@
 	 AZX_DCAPS_COUNT_LPIB_DELAY | AZX_DCAPS_PM_RUNTIME | \
 	 AZX_DCAPS_I915_POWERWELL)
 
+/* Broadwell HDMI can't use position buffer reliably, force to use LPIB */
+#define AZX_DCAPS_INTEL_BROADWELL \
+	(AZX_DCAPS_SCH_SNOOP | AZX_DCAPS_ALIGN_BUFSIZE | \
+	 AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_PM_RUNTIME | \
+	 AZX_DCAPS_I915_POWERWELL)
+
 /* quirks for ATI SB / AMD Hudson */
 #define AZX_DCAPS_PRESET_ATI_SB \
 	(AZX_DCAPS_ATI_SNOOP | AZX_DCAPS_NO_TCSEL | \
@@ -1367,12 +1373,6 @@
 	/* initialize streams */
 	azx_init_stream(chip);
 
-	/* workaround for Broadwell HDMI: the first stream is broken,
-	 * so mask it by keeping it as if opened
-	 */
-	if (pci->vendor == 0x8086 && pci->device == 0x160c)
-		chip->azx_dev[0].opened = 1;
-
 	/* initialize chip */
 	azx_init_pci(chip);
 	azx_init_chip(chip, (probe_only[dev] & 2) == 0);
@@ -1656,8 +1656,13 @@
 				"Error request power-well from i915\n");
 			goto out_free;
 		}
+		err = hda_display_power(true);
+		if (err < 0) {
+			dev_err(chip->card->dev,
+				"Cannot turn on display power on i915\n");
+			goto out_free;
+		}
 #endif
-		hda_display_power(true);
 	}
 
 	err = azx_first_init(chip);
@@ -1769,7 +1774,7 @@
 	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL },
 	/* Broadwell */
 	{ PCI_DEVICE(0x8086, 0x160c),
-	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL },
+	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_BROADWELL },
 	/* 5 Series/3400 */
 	{ PCI_DEVICE(0x8086, 0x3b56),
 	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index be0a9ee..3e4417b 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1594,10 +1594,18 @@
 		 * Re-setup pin and infoframe. This is needed e.g. when
 		 * - sink is first plugged-in (infoframe is not set up if !monitor_present)
 		 * - transcoder can change during stream playback on Haswell
+		 *   and this can make HW reset converter selection on a pin.
 		 */
-		if (eld->eld_valid && !old_eld_valid && per_pin->setup)
+		if (eld->eld_valid && !old_eld_valid && per_pin->setup) {
+			if (is_haswell_plus(codec) || is_valleyview(codec)) {
+				intel_verify_pin_cvt_connect(codec, per_pin);
+				intel_not_share_assigned_cvt(codec, pin_nid,
+							per_pin->mux_idx);
+			}
+
 			hdmi_setup_audio_infoframe(codec, per_pin,
 						   per_pin->non_pcm);
+		}
 	}
 
 	if (eld_changed)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 12fb411..af76995 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -929,6 +929,7 @@
 };
 
 static struct alc_codec_rename_table rename_tbl[] = {
+	{ 0x10ec0221, 0xf00f, 0x1003, "ALC231" },
 	{ 0x10ec0269, 0xfff0, 0x3010, "ALC277" },
 	{ 0x10ec0269, 0xf0f0, 0x2010, "ALC259" },
 	{ 0x10ec0269, 0xf0f0, 0x3010, "ALC258" },
@@ -937,6 +938,7 @@
 	{ 0x10ec0269, 0xffff, 0x6023, "ALC281X" },
 	{ 0x10ec0269, 0x00f0, 0x0020, "ALC269VC" },
 	{ 0x10ec0269, 0x00f0, 0x0030, "ALC269VD" },
+	{ 0x10ec0662, 0xffff, 0x4020, "ALC656" },
 	{ 0x10ec0887, 0x00f0, 0x0030, "ALC887-VD" },
 	{ 0x10ec0888, 0x00f0, 0x0030, "ALC888-VD" },
 	{ 0x10ec0888, 0xf0f0, 0x3020, "ALC886" },
@@ -956,6 +958,19 @@
 	{ 0x10ec0293, 0x1028, 0, "ALC3235" },
 	{ 0x10ec0255, 0x1028, 0, "ALC3234" },
 	{ 0x10ec0668, 0x1028, 0, "ALC3661" },
+	{ 0x10ec0275, 0x1028, 0, "ALC3260" },
+	{ 0x10ec0899, 0x1028, 0, "ALC3861" },
+	{ 0x10ec0670, 0x1025, 0, "ALC669X" },
+	{ 0x10ec0676, 0x1025, 0, "ALC679X" },
+	{ 0x10ec0282, 0x1043, 0, "ALC3229" },
+	{ 0x10ec0233, 0x1043, 0, "ALC3236" },
+	{ 0x10ec0280, 0x103c, 0, "ALC3228" },
+	{ 0x10ec0282, 0x103c, 0, "ALC3227" },
+	{ 0x10ec0286, 0x103c, 0, "ALC3242" },
+	{ 0x10ec0290, 0x103c, 0, "ALC3241" },
+	{ 0x10ec0668, 0x103c, 0, "ALC3662" },
+	{ 0x10ec0283, 0x17aa, 0, "ALC3239" },
+	{ 0x10ec0292, 0x17aa, 0, "ALC3232" },
 	{ } /* terminator */
 };
 
@@ -1412,6 +1427,7 @@
 	SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS W5A", ALC880_FIXUP_ASUS_W5A),
 	SND_PCI_QUIRK(0x1043, 0x1964, "ASUS Z71V", ALC880_FIXUP_Z71V),
 	SND_PCI_QUIRK_VENDOR(0x1043, "ASUS", ALC880_FIXUP_GPIO1),
+	SND_PCI_QUIRK(0x147b, 0x1045, "ABit AA8XE", ALC880_FIXUP_6ST_AUTOMUTE),
 	SND_PCI_QUIRK(0x1558, 0x5401, "Clevo GPIO2", ALC880_FIXUP_GPIO2),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo", ALC880_FIXUP_EAPD_COEF),
 	SND_PCI_QUIRK(0x1584, 0x9050, "Uniwill", ALC880_FIXUP_UNIWILL_DIG),
@@ -4230,6 +4246,7 @@
 	ALC269_FIXUP_HEADSET_MIC,
 	ALC269_FIXUP_QUANTA_MUTE,
 	ALC269_FIXUP_LIFEBOOK,
+	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -4367,6 +4384,13 @@
 		.chained = true,
 		.chain_id = ALC269_FIXUP_QUANTA_MUTE
 	},
+	[ALC269_FIXUP_LIFEBOOK_EXTMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1903c }, /* headset mic, with jack detect */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4741,18 +4765,12 @@
 	SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
-	SND_PCI_QUIRK(0x1028, 0x062c, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x064d, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0668, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0669, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0674, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x067e, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x067f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0680, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0684, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
@@ -4764,14 +4782,24 @@
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2211, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2212, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -4811,6 +4839,10 @@
 	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2334, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4834,6 +4866,7 @@
 	SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
 	SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
@@ -4977,6 +5010,26 @@
 #endif
 		.pins = (const struct hda_pintbl[]) {
 			{0x12, 0x90a60160},
+			{0x14, 0x90170120},
+			{0x17, 0x90170140},
+			{0x18, 0x40000000},
+			{0x19, 0x411111f0},
+			{0x1a, 0x411111f0},
+			{0x1b, 0x411111f0},
+			{0x1d, 0x41163b05},
+			{0x1e, 0x411111f0},
+			{0x21, 0x0321102f},
+		},
+		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+	},
+	{
+		.codec = 0x10ec0255,
+		.subvendor = 0x1028,
+#ifdef CONFIG_SND_DEBUG_VERBOSE
+		.name = "Dell",
+#endif
+		.pins = (const struct hda_pintbl[]) {
+			{0x12, 0x90a60160},
 			{0x14, 0x90170130},
 			{0x17, 0x40000000},
 			{0x18, 0x411111f0},
@@ -5129,7 +5182,7 @@
 			{0x1d, 0x40700001},
 			{0x1e, 0x411111f0},
 		},
-		.value = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		.value = ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 	},
 	{}
 };
@@ -6014,6 +6067,27 @@
 		.name = "Dell",
 #endif
 		.pins = (const struct hda_pintbl[]) {
+			{0x12, 0x99a30140},
+			{0x14, 0x90170110},
+			{0x15, 0x0321101f},
+			{0x16, 0x03011020},
+			{0x18, 0x40000008},
+			{0x19, 0x411111f0},
+			{0x1a, 0x411111f0},
+			{0x1b, 0x411111f0},
+			{0x1d, 0x41000001},
+			{0x1e, 0x411111f0},
+			{0x1f, 0x411111f0},
+		},
+		.value = ALC668_FIXUP_AUTO_MUTE,
+	},
+	{
+		.codec = 0x10ec0668,
+		.subvendor = 0x1028,
+#ifdef CONFIG_SND_DEBUG_VERBOSE
+		.name = "Dell",
+#endif
+		.pins = (const struct hda_pintbl[]) {
 			{0x12, 0x99a30150},
 			{0x14, 0x90170110},
 			{0x15, 0x0321101f},
@@ -6190,6 +6264,7 @@
 	{ .id = 0x10ec0221, .name = "ALC221", .patch = patch_alc269 },
 	{ .id = 0x10ec0231, .name = "ALC231", .patch = patch_alc269 },
 	{ .id = 0x10ec0233, .name = "ALC233", .patch = patch_alc269 },
+	{ .id = 0x10ec0235, .name = "ALC233", .patch = patch_alc269 },
 	{ .id = 0x10ec0255, .name = "ALC255", .patch = patch_alc269 },
 	{ .id = 0x10ec0260, .name = "ALC260", .patch = patch_alc260 },
 	{ .id = 0x10ec0262, .name = "ALC262", .patch = patch_alc262 },
@@ -6223,10 +6298,12 @@
 	  .patch = patch_alc662 },
 	{ .id = 0x10ec0663, .name = "ALC663", .patch = patch_alc662 },
 	{ .id = 0x10ec0665, .name = "ALC665", .patch = patch_alc662 },
+	{ .id = 0x10ec0667, .name = "ALC667", .patch = patch_alc662 },
 	{ .id = 0x10ec0668, .name = "ALC668", .patch = patch_alc662 },
 	{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
 	{ .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 },
 	{ .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 },
+	{ .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 },
 	{ .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 },
 	{ .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 },
 	{ .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 },
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 68340d7..c91860e 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -2779,7 +2779,7 @@
 	unsigned long port;
 	unsigned long pos, pos1, t;
 	int civ, timeout = 1000, attempt = 1;
-	struct timespec start_time, stop_time;
+	ktime_t start_time, stop_time;
 
 	if (chip->ac97_bus->clock != 48000)
 		return; /* specified in module option */
@@ -2813,7 +2813,7 @@
 		iputbyte(chip, port + ICH_REG_OFF_CR, ICH_IOCE);
 		iputdword(chip, ICHREG(ALI_DMACR), 1 << ichdev->ali_slot);
 	}
-	do_posix_clock_monotonic_gettime(&start_time);
+	start_time = ktime_get();
 	spin_unlock_irq(&chip->reg_lock);
 	msleep(50);
 	spin_lock_irq(&chip->reg_lock);
@@ -2837,7 +2837,7 @@
 		pos += ichdev->position;
 	}
 	chip->in_measurement = 0;
-	do_posix_clock_monotonic_gettime(&stop_time);
+	stop_time = ktime_get();
 	/* stop */
 	if (chip->device_type == DEVICE_ALI) {
 		iputdword(chip, ICHREG(ALI_DMACR), 1 << (ichdev->ali_slot + 16));
@@ -2865,9 +2865,7 @@
 	}
 
 	pos /= 4;
-	t = stop_time.tv_sec - start_time.tv_sec;
-	t *= 1000000;
-	t += (stop_time.tv_nsec - start_time.tv_nsec) / 1000;
+	t = ktime_us_delta(stop_time, start_time);
 	dev_info(chip->card->dev,
 		 "%s: measured %lu usecs (%lu samples)\n", __func__, t, pos);
 	if (t == 0) {
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index cbfa1e1..0b9571c 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -225,11 +225,11 @@
 config SND_SOC_ADAU1701
 	tristate "Analog Devices ADAU1701 CODEC"
 	depends on I2C
-	select SND_SOC_SIGMADSP
+	select SND_SOC_SIGMADSP_I2C
 
 config SND_SOC_ADAU17X1
 	tristate
-	select SND_SOC_SIGMADSP
+	select SND_SOC_SIGMADSP_REGMAP
 
 config SND_SOC_ADAU1761
 	tristate
@@ -476,6 +476,14 @@
 	tristate
 	select CRC32
 
+config SND_SOC_SIGMADSP_I2C
+	tristate
+	select SND_SOC_SIGMADSP
+
+config SND_SOC_SIGMADSP_REGMAP
+	tristate
+	select SND_SOC_SIGMADSP
+
 config SND_SOC_SIRF_AUDIO_CODEC
 	tristate "SiRF SoC internal audio codec"
 	select REGMAP_MMIO
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index be3377b..1bd6e1c 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -77,6 +77,8 @@
 snd-soc-alc5623-objs := alc5623.o
 snd-soc-alc5632-objs := alc5632.o
 snd-soc-sigmadsp-objs := sigmadsp.o
+snd-soc-sigmadsp-i2c-objs := sigmadsp-i2c.o
+snd-soc-sigmadsp-regmap-objs := sigmadsp-regmap.o
 snd-soc-si476x-objs := si476x.o
 snd-soc-sirf-audio-codec-objs := sirf-audio-codec.o
 snd-soc-sn95031-objs := sn95031.o
@@ -240,6 +242,8 @@
 obj-$(CONFIG_SND_SOC_RT5677)	+= snd-soc-rt5677.o
 obj-$(CONFIG_SND_SOC_SGTL5000)  += snd-soc-sgtl5000.o
 obj-$(CONFIG_SND_SOC_SIGMADSP)	+= snd-soc-sigmadsp.o
+obj-$(CONFIG_SND_SOC_SIGMADSP_I2C)	+= snd-soc-sigmadsp-i2c.o
+obj-$(CONFIG_SND_SOC_SIGMADSP_REGMAP)	+= snd-soc-sigmadsp-regmap.o
 obj-$(CONFIG_SND_SOC_SI476X)	+= snd-soc-si476x.o
 obj-$(CONFIG_SND_SOC_SN95031)	+=snd-soc-sn95031.o
 obj-$(CONFIG_SND_SOC_SPDIF)	+= snd-soc-spdif-rx.o snd-soc-spdif-tx.o
diff --git a/sound/soc/codecs/sigmadsp-i2c.c b/sound/soc/codecs/sigmadsp-i2c.c
new file mode 100644
index 0000000..246081a
--- /dev/null
+++ b/sound/soc/codecs/sigmadsp-i2c.c
@@ -0,0 +1,35 @@
+/*
+ * Load Analog Devices SigmaStudio firmware files
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/i2c.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include "sigmadsp.h"
+
+static int sigma_action_write_i2c(void *control_data,
+	const struct sigma_action *sa, size_t len)
+{
+	return i2c_master_send(control_data, (const unsigned char *)&sa->addr,
+		len);
+}
+
+int process_sigma_firmware(struct i2c_client *client, const char *name)
+{
+	struct sigma_firmware ssfw;
+
+	ssfw.control_data = client;
+	ssfw.write = sigma_action_write_i2c;
+
+	return _process_sigma_firmware(&client->dev, &ssfw, name);
+}
+EXPORT_SYMBOL(process_sigma_firmware);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("SigmaDSP I2C firmware loader");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/sigmadsp-regmap.c b/sound/soc/codecs/sigmadsp-regmap.c
new file mode 100644
index 0000000..f78ed8d
--- /dev/null
+++ b/sound/soc/codecs/sigmadsp-regmap.c
@@ -0,0 +1,36 @@
+/*
+ * Load Analog Devices SigmaStudio firmware files
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/regmap.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include "sigmadsp.h"
+
+static int sigma_action_write_regmap(void *control_data,
+	const struct sigma_action *sa, size_t len)
+{
+	return regmap_raw_write(control_data, be16_to_cpu(sa->addr),
+		sa->payload, len - 2);
+}
+
+int process_sigma_firmware_regmap(struct device *dev, struct regmap *regmap,
+	const char *name)
+{
+	struct sigma_firmware ssfw;
+
+	ssfw.control_data = regmap;
+	ssfw.write = sigma_action_write_regmap;
+
+	return _process_sigma_firmware(dev, &ssfw, name);
+}
+EXPORT_SYMBOL(process_sigma_firmware_regmap);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("SigmaDSP regmap firmware loader");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c
index 4068f24..f2de7e0 100644
--- a/sound/soc/codecs/sigmadsp.c
+++ b/sound/soc/codecs/sigmadsp.c
@@ -34,23 +34,6 @@
 	SIGMA_ACTION_END,
 };
 
-struct sigma_action {
-	u8 instr;
-	u8 len_hi;
-	__le16 len;
-	__be16 addr;
-	unsigned char payload[];
-} __packed;
-
-struct sigma_firmware {
-	const struct firmware *fw;
-	size_t pos;
-
-	void *control_data;
-	int (*write)(void *control_data, const struct sigma_action *sa,
-			size_t len);
-};
-
 static inline u32 sigma_action_len(struct sigma_action *sa)
 {
 	return (sa->len_hi << 16) | le16_to_cpu(sa->len);
@@ -138,7 +121,7 @@
 	return 0;
 }
 
-static int _process_sigma_firmware(struct device *dev,
+int _process_sigma_firmware(struct device *dev,
 	struct sigma_firmware *ssfw, const char *name)
 {
 	int ret;
@@ -197,50 +180,6 @@
 
 	return ret;
 }
-
-#if IS_ENABLED(CONFIG_I2C)
-
-static int sigma_action_write_i2c(void *control_data,
-	const struct sigma_action *sa, size_t len)
-{
-	return i2c_master_send(control_data, (const unsigned char *)&sa->addr,
-		len);
-}
-
-int process_sigma_firmware(struct i2c_client *client, const char *name)
-{
-	struct sigma_firmware ssfw;
-
-	ssfw.control_data = client;
-	ssfw.write = sigma_action_write_i2c;
-
-	return _process_sigma_firmware(&client->dev, &ssfw, name);
-}
-EXPORT_SYMBOL(process_sigma_firmware);
-
-#endif
-
-#if IS_ENABLED(CONFIG_REGMAP)
-
-static int sigma_action_write_regmap(void *control_data,
-	const struct sigma_action *sa, size_t len)
-{
-	return regmap_raw_write(control_data, be16_to_cpu(sa->addr),
-		sa->payload, len - 2);
-}
-
-int process_sigma_firmware_regmap(struct device *dev, struct regmap *regmap,
-	const char *name)
-{
-	struct sigma_firmware ssfw;
-
-	ssfw.control_data = regmap;
-	ssfw.write = sigma_action_write_regmap;
-
-	return _process_sigma_firmware(dev, &ssfw, name);
-}
-EXPORT_SYMBOL(process_sigma_firmware_regmap);
-
-#endif
+EXPORT_SYMBOL_GPL(_process_sigma_firmware);
 
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/sigmadsp.h b/sound/soc/codecs/sigmadsp.h
index e439cbd..c47cd23 100644
--- a/sound/soc/codecs/sigmadsp.h
+++ b/sound/soc/codecs/sigmadsp.h
@@ -12,6 +12,26 @@
 #include <linux/device.h>
 #include <linux/regmap.h>
 
+struct sigma_action {
+	u8 instr;
+	u8 len_hi;
+	__le16 len;
+	__be16 addr;
+	unsigned char payload[];
+} __packed;
+
+struct sigma_firmware {
+	const struct firmware *fw;
+	size_t pos;
+
+	void *control_data;
+	int (*write)(void *control_data, const struct sigma_action *sa,
+			size_t len);
+};
+
+int _process_sigma_firmware(struct device *dev,
+	struct sigma_firmware *ssfw, const char *name);
+
 struct i2c_client;
 
 extern int process_sigma_firmware(struct i2c_client *client, const char *name);
diff --git a/sound/soc/fsl/fsl_dma.c b/sound/soc/fsl/fsl_dma.c
index 6bb0ea5..a609aaf 100644
--- a/sound/soc/fsl/fsl_dma.c
+++ b/sound/soc/fsl/fsl_dma.c
@@ -923,8 +923,8 @@
 	dma->dai.pcm_free = fsl_dma_free_dma_buffers;
 
 	/* Store the SSI-specific information that we need */
-	dma->ssi_stx_phys = res.start + offsetof(struct ccsr_ssi, stx0);
-	dma->ssi_srx_phys = res.start + offsetof(struct ccsr_ssi, srx0);
+	dma->ssi_stx_phys = res.start + CCSR_SSI_STX0;
+	dma->ssi_srx_phys = res.start + CCSR_SSI_SRX0;
 
 	iprop = of_get_property(ssi_np, "fsl,fifo-depth", NULL);
 	if (iprop)
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index b912d45..d7a6061 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -762,7 +762,7 @@
 	struct regmap *regmap = spdif_priv->regmap;
 	u32 val;
 
-	val = regmap_read(regmap, REG_SPDIF_SIS, &val);
+	regmap_read(regmap, REG_SPDIF_SIS, &val);
 	ucontrol->value.integer.value[0] = (val & INT_VAL_NOGOOD) != 0;
 	regmap_write(regmap, REG_SPDIF_SIC, INT_VAL_NOGOOD);
 
@@ -1076,7 +1076,7 @@
 				goto out;
 			} else if (arate / rate[index] == 1) {
 				/* A little bigger than expect */
-				sub = (arate - rate[index]) * 100000;
+				sub = (u64)(arate - rate[index]) * 100000;
 				do_div(sub, rate[index]);
 				if (sub >= savesub)
 					continue;
@@ -1086,7 +1086,7 @@
 				spdif_priv->txrate[index] = arate;
 			} else if (rate[index] / arate == 1) {
 				/* A little smaller than expect */
-				sub = (rate[index] - arate) * 100000;
+				sub = (u64)(rate[index] - arate) * 100000;
 				do_div(sub, rate[index]);
 				if (sub >= savesub)
 					continue;
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 6acb225..2434b6d 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -11,6 +11,7 @@
 config SND_MMP_SOC
 	bool "Soc Audio for Marvell MMP chips"
 	depends on ARCH_MMP
+	select MMP_SRAM
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 	select SND_ARM
 	help
@@ -40,7 +41,7 @@
 
 config SND_PXA2XX_SOC_CORGI
 	tristate "SoC Audio support for Sharp Zaurus SL-C7x0"
-	depends on SND_PXA2XX_SOC && PXA_SHARP_C7xx
+	depends on SND_PXA2XX_SOC && PXA_SHARP_C7xx && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8731
 	help
@@ -49,7 +50,7 @@
 
 config SND_PXA2XX_SOC_SPITZ
 	tristate "SoC Audio support for Sharp Zaurus SL-Cxx00"
-	depends on SND_PXA2XX_SOC && PXA_SHARP_Cxx00
+	depends on SND_PXA2XX_SOC && PXA_SHARP_Cxx00 && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8750
 	help
@@ -58,7 +59,7 @@
 
 config SND_PXA2XX_SOC_Z2
 	tristate "SoC Audio support for Zipit Z2"
-	depends on SND_PXA2XX_SOC && MACH_ZIPIT2
+	depends on SND_PXA2XX_SOC && MACH_ZIPIT2 && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8750
 	help
@@ -66,7 +67,7 @@
 
 config SND_PXA2XX_SOC_POODLE
 	tristate "SoC Audio support for Poodle"
-	depends on SND_PXA2XX_SOC && MACH_POODLE
+	depends on SND_PXA2XX_SOC && MACH_POODLE && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8731
 	help
@@ -181,7 +182,7 @@
 
 config SND_PXA2XX_SOC_MAGICIAN
 	tristate "SoC Audio support for HTC Magician"
-	depends on SND_PXA2XX_SOC && MACH_MAGICIAN
+	depends on SND_PXA2XX_SOC && MACH_MAGICIAN && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_PXA_SOC_SSP
 	select SND_SOC_UDA1380
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 9188015..4e86265 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -315,7 +315,7 @@
 		dst_mod = mod[index];
 	} else {
 		src_mod = mod[index];
-		dst_mod = mod[index + 1];
+		dst_mod = mod[index - 1];
 	}
 
 	index = 0;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index a74b9bf..cdc837e 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2755,7 +2755,7 @@
 	unsigned int mask = (1 << fls(max)) - 1;
 	unsigned int invert = mc->invert;
 	unsigned int val;
-	int connect, change;
+	int connect, change, reg_change = 0;
 	struct snd_soc_dapm_update update;
 	int ret = 0;
 
@@ -2773,20 +2773,23 @@
 	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 
 	change = dapm_kcontrol_set_value(kcontrol, val);
-	if (change) {
-		if (reg != SND_SOC_NOPM) {
-			mask = mask << shift;
-			val = val << shift;
 
-			if (snd_soc_test_bits(codec, reg, mask, val)) {
-				update.kcontrol = kcontrol;
-				update.reg = reg;
-				update.mask = mask;
-				update.val = val;
-				card->update = &update;
-			}
+	if (reg != SND_SOC_NOPM) {
+		mask = mask << shift;
+		val = val << shift;
 
+		reg_change = snd_soc_test_bits(codec, reg, mask, val);
+	}
+
+	if (change || reg_change) {
+		if (reg_change) {
+			update.kcontrol = kcontrol;
+			update.reg = reg;
+			update.mask = mask;
+			update.val = val;
+			card->update = &update;
 		}
+		change |= reg_change;
 
 		ret = soc_dapm_mixer_update_power(card, kcontrol, connect);
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 52c03fb..04a229a 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -17,6 +17,7 @@
 #include "../util.h"
 #include "../ui.h"
 #include "map.h"
+#include "annotate.h"
 
 struct hist_browser {
 	struct ui_browser   b;
@@ -1593,13 +1594,18 @@
 					 bi->to.sym->name) > 0)
 				annotate_t = nr_options++;
 		} else {
-
 			if (browser->selection != NULL &&
 			    browser->selection->sym != NULL &&
-			    !browser->selection->map->dso->annotate_warned &&
-				asprintf(&options[nr_options], "Annotate %s",
-					 browser->selection->sym->name) > 0)
-				annotate = nr_options++;
+			    !browser->selection->map->dso->annotate_warned) {
+				struct annotation *notes;
+
+				notes = symbol__annotation(browser->selection->sym);
+
+				if (notes->src &&
+				    asprintf(&options[nr_options], "Annotate %s",
+						 browser->selection->sym->name) > 0)
+					annotate = nr_options++;
+			}
 		}
 
 		if (thread != NULL &&
@@ -1656,6 +1662,7 @@
 
 		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
 			struct hist_entry *he;
+			struct annotation *notes;
 			int err;
 do_annotate:
 			if (!objdump_path && perf_session_env__lookup_objdump(env))
@@ -1679,6 +1686,10 @@
 				he->ms.map = he->branch_info->to.map;
 			}
 
+			notes = symbol__annotation(he->ms.sym);
+			if (!notes->src)
+				continue;
+
 			/*
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 0e5fea9..c73e1fc 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -496,18 +496,6 @@
 	u64 start;
 };
 
-static int symbol__in_kernel(void *arg, const char *name,
-			     char type __maybe_unused, u64 start)
-{
-	struct process_args *args = arg;
-
-	if (strchr(name, '['))
-		return 0;
-
-	args->start = start;
-	return 1;
-}
-
 static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
 					   size_t bufsz)
 {
@@ -517,27 +505,41 @@
 		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
 }
 
-/* Figure out the start address of kernel map from /proc/kallsyms */
-static u64 machine__get_kernel_start_addr(struct machine *machine)
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
+/* Figure out the start address of kernel map from /proc/kallsyms.
+ * Returns the name of the start symbol in *symbol_name. Pass in NULL as
+ * symbol_name if it's not that important.
+ */
+static u64 machine__get_kernel_start_addr(struct machine *machine,
+					  const char **symbol_name)
 {
 	char filename[PATH_MAX];
-	struct process_args args;
+	int i;
+	const char *name;
+	u64 addr = 0;
 
 	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return 0;
 
-	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
-		return 0;
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
 
-	return args.start;
+	if (symbol_name)
+		*symbol_name = name;
+
+	return addr;
 }
 
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine);
+	u64 start = machine__get_kernel_start_addr(machine, NULL);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
@@ -852,23 +854,11 @@
 	return 0;
 }
 
-const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
-
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
-	char filename[PATH_MAX];
 	const char *name;
-	u64 addr = 0;
-	int i;
-
-	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
-
-	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
-		addr = kallsyms__get_function_start(filename, name);
-		if (addr)
-			break;
-	}
+	u64 addr = machine__get_kernel_start_addr(machine, &name);
 	if (!addr)
 		return -1;